Merge tag 'perf-tools-for-v5.17-2022-01-16' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux

Pull perf tool updates from Arnaldo Carvalho de Melo:
 "New features:

   - Add 'trace' subcommand for 'perf ftrace', setting the stage for
     more 'perf ftrace' subcommands. Not using a subcommand yields the
     previous behaviour of 'perf ftrace'.

   - Add 'latency' subcommand to 'perf ftrace', that can use the
     function graph tracer or a BPF optimized one, via the -b/--use-bpf
     option.

     E.g.:

	$ sudo perf ftrace latency -a -T mutex_lock sleep 1
	#   DURATION     |      COUNT | GRAPH                          |
	     0 - 1    us |       4596 | ########################       |
	     1 - 2    us |       1680 | #########                      |
	     2 - 4    us |       1106 | #####                          |
	     4 - 8    us |        546 | ##                             |
	     8 - 16   us |        562 | ###                            |
	    16 - 32   us |          1 |                                |
	    32 - 64   us |          0 |                                |
	    64 - 128  us |          0 |                                |
	   128 - 256  us |          0 |                                |
	   256 - 512  us |          0 |                                |
	   512 - 1024 us |          0 |                                |
	     1 - 2    ms |          0 |                                |
	     2 - 4    ms |          0 |                                |
	     4 - 8    ms |          0 |                                |
	     8 - 16   ms |          0 |                                |
	    16 - 32   ms |          0 |                                |
	    32 - 64   ms |          0 |                                |
	    64 - 128  ms |          0 |                                |
	   128 - 256  ms |          0 |                                |
	   256 - 512  ms |          0 |                                |
	   512 - 1024 ms |          0 |                                |
	     1 - ...   s |          0 |                                |

     The original implementation of this command was in the bcc tool.

   - Support --cputype option for hybrid events in 'perf stat'.

  Improvements:

   - Call chain improvements for ARM64.

   - No need to do any affinity setup when profiling pids.

   - Reduce multiplexing with duration_time in 'perf stat' metrics.

   - Improve error message for uncore events, stating that some event
     groups are can only be used in system wide (-a) mode.

   - perf stat metric group leader fixes/improvements, including arch
     specific changes to better support Intel topdown events.

   - Probe non-deprecated sysfs path first, i.e. try the path
     /sys/devices/system/cpu/cpuN/topology/thread_siblings first, then
     the old /sys/devices/system/cpu/cpuN/topology/core_cpus.

   - Disable debuginfod by default in 'perf record', to avoid stalls on
     distros such as Fedora 35.

   - Use unbuffered output in 'perf bench' when pipe/tee'ing to a file.

   - Enable ignore_missing_thread in 'perf trace'

  Fixes:

   - Avoid TUI crash when navigating in the annotation of recursive
     functions.

   - Fix hex dump character output in 'perf script'.

   - Fix JSON indentation to 4 spaces standard in the ARM vendor event
     files.

   - Fix use after free in metric__new().

   - Fix IS_ERR_OR_NULL() usage in the perf BPF loader.

   - Fix up cross-arch register support, i.e. when printing register
     names take into account the architecture where the perf.data file
     was collected.

   - Fix SMT fallback with large core counts.

   - Don't lower case MetricExpr when parsing JSON files so as not to
     lose info such as the ":G" event modifier in metrics.

  perf test:

   - Add basic stress test for sigtrap handling to 'perf test'.

   - Fix 'perf test' failures on s/390

   - Enable system wide for metricgroups test in 'perf test´.

   - Use 3 digits for test numbering now we can have more tests.

  Arch specific:

   - Add events for Arm Neoverse N2 in the ARM JSON vendor event files

   - Support PERF_MEM_LVLNUM encodings in powerpc, that came from a
     single patch series, where I incorrectly merged the kernel bits,
     that were then reverted after coordination with Michael Ellerman
     and Stephen Rothwell.

   - Add ARM SPE total latency as PERF_SAMPLE_WEIGHT.

   - Update AMD documentation, with info on raw event encoding.

   - Add support for global and local variants of the "p_stage_cyc" sort
     key, applicable to perf.data files collected on powerpc.

   - Remove duplicate and incorrect aux size checks in the ARM CoreSight
     ETM code.

  Refactorings:

   - Add a perf_cpu abstraction to disambiguate CPUs and CPU map
     indexes, fixing problems along the way.

   - Document CPU map methods.

  UAPI sync:

   - Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench
     mem memcpy'

   - Sync UAPI files with the kernel sources: drm, msr-index,
     cpufeatures.

  Build system

   - Enable warnings through HOSTCFLAGS.

   - Drop requirement for libstdc++.so for libopencsd check

  libperf:

   - Make libperf adopt perf_counts_values__scale() from tools/perf/util/.

   - Add a stat multiplexing test to libperf"

* tag 'perf-tools-for-v5.17-2022-01-16' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux: (115 commits)
  perf record: Disable debuginfod by default
  perf evlist: No need to do any affinity setup when profiling pids
  perf cpumap: Add is_dummy() method
  perf metric: Fix metric_leader
  perf cputopo: Fix CPU topology reading on s/390
  perf metricgroup: Fix use after free in metric__new()
  libperf tests: Update a use of the new cpumap API
  perf arm: Fix off-by-one directory path
  tools arch x86: Sync the msr-index.h copy with the kernel sources
  tools headers cpufeatures: Sync with the kernel sources
  tools headers UAPI: Update tools's copy of drm.h header
  tools arch: Update arch/x86/lib/mem{cpy,set}_64.S copies used in 'perf bench mem memcpy'
  perf pmu-events: Don't lower case MetricExpr
  perf expr: Add debug logging for literals
  perf tools: Probe non-deprecated sysfs path 1st
  perf tools: Fix SMT fallback with large core counts
  perf cpumap: Give CPUs their own type
  perf stat: Correct first_shadow_cpu to return index
  perf script: Fix flipped index and cpu
  perf c2c: Use more intention revealing iterator
  ...

153 files changed, 4685 insertions, 2175 deletions

diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index d5b5f2ab87a0..18de5f76f198 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -315,6 +315,7 @@
 #define X86_FEATURE_AMD_SSBD		(13*32+24) /* "" Speculative Store Bypass Disable */
 #define X86_FEATURE_VIRT_SSBD		(13*32+25) /* Virtualized Speculative Store Bypass Disable */
 #define X86_FEATURE_AMD_SSB_NO		(13*32+26) /* "" Speculative Store Bypass is fixed in hardware. */
+#define X86_FEATURE_CPPC		(13*32+27) /* Collaborative Processor Performance Control */
 
 /* Thermal and Power Management Leaf, CPUID level 0x00000006 (EAX), word 14 */
 #define X86_FEATURE_DTHERM		(14*32+ 0) /* Digital Thermal Sensor */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 01e2650b9585..3faf0f97edb1 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -486,6 +486,23 @@
 
 #define MSR_AMD64_VIRT_SPEC_CTRL	0xc001011f
 
+/* AMD Collaborative Processor Performance Control MSRs */
+#define MSR_AMD_CPPC_CAP1		0xc00102b0
+#define MSR_AMD_CPPC_ENABLE		0xc00102b1
+#define MSR_AMD_CPPC_CAP2		0xc00102b2
+#define MSR_AMD_CPPC_REQ		0xc00102b3
+#define MSR_AMD_CPPC_STATUS		0xc00102b4
+
+#define AMD_CPPC_LOWEST_PERF(x)		(((x) >> 0) & 0xff)
+#define AMD_CPPC_LOWNONLIN_PERF(x)	(((x) >> 8) & 0xff)
+#define AMD_CPPC_NOMINAL_PERF(x)	(((x) >> 16) & 0xff)
+#define AMD_CPPC_HIGHEST_PERF(x)	(((x) >> 24) & 0xff)
+
+#define AMD_CPPC_MAX_PERF(x)		(((x) & 0xff) << 0)
+#define AMD_CPPC_MIN_PERF(x)		(((x) & 0xff) << 8)
+#define AMD_CPPC_DES_PERF(x)		(((x) & 0xff) << 16)
+#define AMD_CPPC_ENERGY_PERF_PREF(x)	(((x) & 0xff) << 24)
+
 /* Fam 17h MSRs */
 #define MSR_F17H_IRPERF			0xc00000e9
 
diff --git a/tools/arch/x86/lib/memcpy_64.S b/tools/arch/x86/lib/memcpy_64.S
index 1cc9da6e29c7..59cf2343f3d9 100644
--- a/tools/arch/x86/lib/memcpy_64.S
+++ b/tools/arch/x86/lib/memcpy_64.S
@@ -39,7 +39,7 @@ SYM_FUNC_START_WEAK(memcpy)
 	rep movsq
 	movl %edx, %ecx
 	rep movsb
-	ret
+	RET
 SYM_FUNC_END(memcpy)
 SYM_FUNC_END_ALIAS(__memcpy)
 EXPORT_SYMBOL(memcpy)
@@ -53,7 +53,7 @@ SYM_FUNC_START_LOCAL(memcpy_erms)
 	movq %rdi, %rax
 	movq %rdx, %rcx
 	rep movsb
-	ret
+	RET
 SYM_FUNC_END(memcpy_erms)
 
 SYM_FUNC_START_LOCAL(memcpy_orig)
@@ -137,7 +137,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
 	movq %r9,	1*8(%rdi)
 	movq %r10,	-2*8(%rdi, %rdx)
 	movq %r11,	-1*8(%rdi, %rdx)
-	retq
+	RET
 	.p2align 4
 .Lless_16bytes:
 	cmpl $8,	%edx
@@ -149,7 +149,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
 	movq -1*8(%rsi, %rdx),	%r9
 	movq %r8,	0*8(%rdi)
 	movq %r9,	-1*8(%rdi, %rdx)
-	retq
+	RET
 	.p2align 4
 .Lless_8bytes:
 	cmpl $4,	%edx
@@ -162,7 +162,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
 	movl -4(%rsi, %rdx), %r8d
 	movl %ecx, (%rdi)
 	movl %r8d, -4(%rdi, %rdx)
-	retq
+	RET
 	.p2align 4
 .Lless_3bytes:
 	subl $1, %edx
@@ -180,7 +180,7 @@ SYM_FUNC_START_LOCAL(memcpy_orig)
 	movb %cl, (%rdi)
 
 .Lend:
-	retq
+	RET
 SYM_FUNC_END(memcpy_orig)
 
 .popsection
diff --git a/tools/arch/x86/lib/memset_64.S b/tools/arch/x86/lib/memset_64.S
index 9827ae267f96..d624f2bc42f1 100644
--- a/tools/arch/x86/lib/memset_64.S
+++ b/tools/arch/x86/lib/memset_64.S
@@ -40,7 +40,7 @@ SYM_FUNC_START(__memset)
 	movl %edx,%ecx
 	rep stosb
 	movq %r9,%rax
-	ret
+	RET
 SYM_FUNC_END(__memset)
 SYM_FUNC_END_ALIAS(memset)
 EXPORT_SYMBOL(memset)
@@ -63,7 +63,7 @@ SYM_FUNC_START_LOCAL(memset_erms)
 	movq %rdx,%rcx
 	rep stosb
 	movq %r9,%rax
-	ret
+	RET
 SYM_FUNC_END(memset_erms)
 
 SYM_FUNC_START_LOCAL(memset_orig)
@@ -125,7 +125,7 @@ SYM_FUNC_START_LOCAL(memset_orig)
 
 .Lende:
 	movq	%r10,%rax
-	ret
+	RET
 
 .Lbad_alignment:
 	cmpq $7,%rdx
diff --git a/tools/build/Build.include b/tools/build/Build.include
index 2cf3b1bde86e..c2a95ab47379 100644
--- a/tools/build/Build.include
+++ b/tools/build/Build.include
@@ -99,7 +99,7 @@ cxx_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(CXXFLAGS) -D"BUILD_STR(s)=\#s" $(CXX
 ###
 ## HOSTCC C flags
 
-host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(KBUILD_HOSTCFLAGS) -D"BUILD_STR(s)=\#s" $(HOSTCFLAGS_$(basetarget).o) $(HOSTCFLAGS_$(obj))
+host_c_flags = -Wp,-MD,$(depfile) -Wp,-MT,$@ $(HOSTCFLAGS) -D"BUILD_STR(s)=\#s" $(HOSTCFLAGS_$(basetarget).o) $(HOSTCFLAGS_$(obj))
 
 # output directory for tests below
 TMPOUT = .tmp_$$$$
diff --git a/tools/include/uapi/drm/drm.h b/tools/include/uapi/drm/drm.h
index 3b810b53ba8b..642808520d92 100644
--- a/tools/include/uapi/drm/drm.h
+++ b/tools/include/uapi/drm/drm.h
@@ -1096,6 +1096,24 @@ extern "C" {
 #define DRM_IOCTL_SYNCOBJ_TRANSFER	DRM_IOWR(0xCC, struct drm_syncobj_transfer)
 #define DRM_IOCTL_SYNCOBJ_TIMELINE_SIGNAL	DRM_IOWR(0xCD, struct drm_syncobj_timeline_array)
 
+/**
+ * DRM_IOCTL_MODE_GETFB2 - Get framebuffer metadata.
+ *
+ * This queries metadata about a framebuffer. User-space fills
+ * &drm_mode_fb_cmd2.fb_id as the input, and the kernels fills the rest of the
+ * struct as the output.
+ *
+ * If the client is DRM master or has &CAP_SYS_ADMIN, &drm_mode_fb_cmd2.handles
+ * will be filled with GEM buffer handles. Planes are valid until one has a
+ * zero handle -- this can be used to compute the number of planes.
+ *
+ * Otherwise, &drm_mode_fb_cmd2.handles will be zeroed and planes are valid
+ * until one has a zero &drm_mode_fb_cmd2.pitches.
+ *
+ * If the framebuffer has a format modifier, &DRM_MODE_FB_MODIFIERS will be set
+ * in &drm_mode_fb_cmd2.flags and &drm_mode_fb_cmd2.modifier will contain the
+ * modifier. Otherwise, user-space must ignore &drm_mode_fb_cmd2.modifier.
+ */
 #define DRM_IOCTL_MODE_GETFB2		DRM_IOWR(0xCE, struct drm_mode_fb_cmd2)
 
 /*
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index bd8860eeb291..4cd39aaccbe7 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -1332,7 +1332,10 @@ union perf_mem_data_src {
 
 /* hop level */
 #define PERF_MEM_HOPS_0		0x01 /* remote core, same node */
-/* 2-7 available */
+#define PERF_MEM_HOPS_1         0x02 /* remote node, same socket */
+#define PERF_MEM_HOPS_2         0x03 /* remote socket, same board */
+#define PERF_MEM_HOPS_3         0x04 /* remote board */
+/* 5-7 available */
 #define PERF_MEM_HOPS_SHIFT	43
 
 #define PERF_MEM_S(a, s) \
diff --git a/tools/lib/perf/Documentation/libperf.txt b/tools/lib/perf/Documentation/libperf.txt
index 63ae5e0195ce..32c5051c24eb 100644
--- a/tools/lib/perf/Documentation/libperf.txt
+++ b/tools/lib/perf/Documentation/libperf.txt
@@ -48,6 +48,7 @@ SYNOPSIS
   int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
   bool perf_cpu_map__empty(const struct perf_cpu_map *map);
   int perf_cpu_map__max(struct perf_cpu_map *map);
+  bool perf_cpu_map__has(const struct perf_cpu_map *map, int cpu);
 
   #define perf_cpu_map__for_each_cpu(cpu, idx, cpus)
 --
@@ -135,16 +136,16 @@ SYNOPSIS
   int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
                        struct perf_thread_map *threads);
   void perf_evsel__close(struct perf_evsel *evsel);
-  void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu);
+  void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx);
   int perf_evsel__mmap(struct perf_evsel *evsel, int pages);
   void perf_evsel__munmap(struct perf_evsel *evsel);
-  void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread);
-  int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+  void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread);
+  int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread,
                        struct perf_counts_values *count);
   int perf_evsel__enable(struct perf_evsel *evsel);
-  int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu);
+  int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx);
   int perf_evsel__disable(struct perf_evsel *evsel);
-  int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu);
+  int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx);
   struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel);
   struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel);
   struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel);
diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index adaad3dddf6e..ee66760f1e63 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -10,15 +10,24 @@
 #include <ctype.h>
 #include <limits.h>
 
-struct perf_cpu_map *perf_cpu_map__dummy_new(void)
+static struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus)
 {
-	struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(int));
+	struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus);
 
 	if (cpus != NULL) {
-		cpus->nr = 1;
-		cpus->map[0] = -1;
+		cpus->nr = nr_cpus;
 		refcount_set(&cpus->refcnt, 1);
+
 	}
+	return cpus;
+}
+
+struct perf_cpu_map *perf_cpu_map__dummy_new(void)
+{
+	struct perf_cpu_map *cpus = perf_cpu_map__alloc(1);
+
+	if (cpus)
+		cpus->map[0].cpu = -1;
 
 	return cpus;
 }
@@ -54,15 +63,12 @@ static struct perf_cpu_map *cpu_map__default_new(void)
 	if (nr_cpus < 0)
 		return NULL;
 
-	cpus = malloc(sizeof(*cpus) + nr_cpus * sizeof(int));
+	cpus = perf_cpu_map__alloc(nr_cpus);
 	if (cpus != NULL) {
 		int i;
 
 		for (i = 0; i < nr_cpus; ++i)
-			cpus->map[i] = i;
-
-		cpus->nr = nr_cpus;
-		refcount_set(&cpus->refcnt, 1);
+			cpus->map[i].cpu = i;
 	}
 
 	return cpus;
@@ -73,31 +79,32 @@ struct perf_cpu_map *perf_cpu_map__default_new(void)
 	return cpu_map__default_new();
 }
 
-static int cmp_int(const void *a, const void *b)
+
+static int cmp_cpu(const void *a, const void *b)
 {
-	return *(const int *)a - *(const int*)b;
+	const struct perf_cpu *cpu_a = a, *cpu_b = b;
+
+	return cpu_a->cpu - cpu_b->cpu;
 }
 
-static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, int *tmp_cpus)
+static struct perf_cpu_map *cpu_map__trim_new(int nr_cpus, const struct perf_cpu *tmp_cpus)
 {
-	size_t payload_size = nr_cpus * sizeof(int);
-	struct perf_cpu_map *cpus = malloc(sizeof(*cpus) + payload_size);
+	size_t payload_size = nr_cpus * sizeof(struct perf_cpu);
+	struct perf_cpu_map *cpus = perf_cpu_map__alloc(nr_cpus);
 	int i, j;
 
 	if (cpus != NULL) {
 		memcpy(cpus->map, tmp_cpus, payload_size);
-		qsort(cpus->map, nr_cpus, sizeof(int), cmp_int);
+		qsort(cpus->map, nr_cpus, sizeof(struct perf_cpu), cmp_cpu);
 		/* Remove dups */
 		j = 0;
 		for (i = 0; i < nr_cpus; i++) {
-			if (i == 0 || cpus->map[i] != cpus->map[i - 1])
-				cpus->map[j++] = cpus->map[i];
+			if (i == 0 || cpus->map[i].cpu != cpus->map[i - 1].cpu)
+				cpus->map[j++].cpu = cpus->map[i].cpu;
 		}
 		cpus->nr = j;
 		assert(j <= nr_cpus);
-		refcount_set(&cpus->refcnt, 1);
 	}
-
 	return cpus;
 }
 
@@ -105,7 +112,7 @@ struct perf_cpu_map *perf_cpu_map__read(FILE *file)
 {
 	struct perf_cpu_map *cpus = NULL;
 	int nr_cpus = 0;
-	int *tmp_cpus = NULL, *tmp;
+	struct perf_cpu *tmp_cpus = NULL, *tmp;
 	int max_entries = 0;
 	int n, cpu, prev;
 	char sep;
@@ -124,24 +131,24 @@ struct perf_cpu_map *perf_cpu_map__read(FILE *file)
 
 			if (new_max >= max_entries) {
 				max_entries = new_max + MAX_NR_CPUS / 2;
-				tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+				tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
 				if (tmp == NULL)
 					goto out_free_tmp;
 				tmp_cpus = tmp;
 			}
 
 			while (++prev < cpu)
-				tmp_cpus[nr_cpus++] = prev;
+				tmp_cpus[nr_cpus++].cpu = prev;
 		}
 		if (nr_cpus == max_entries) {
 			max_entries += MAX_NR_CPUS;
-			tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+			tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
 			if (tmp == NULL)
 				goto out_free_tmp;
 			tmp_cpus = tmp;
 		}
 
-		tmp_cpus[nr_cpus++] = cpu;
+		tmp_cpus[nr_cpus++].cpu = cpu;
 		if (n == 2 && sep == '-')
 			prev = cpu;
 		else
@@ -179,7 +186,7 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 	unsigned long start_cpu, end_cpu = 0;
 	char *p = NULL;
 	int i, nr_cpus = 0;
-	int *tmp_cpus = NULL, *tmp;
+	struct perf_cpu *tmp_cpus = NULL, *tmp;
 	int max_entries = 0;
 
 	if (!cpu_list)
@@ -220,17 +227,17 @@ struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list)
 		for (; start_cpu <= end_cpu; start_cpu++) {
 			/* check for duplicates */
 			for (i = 0; i < nr_cpus; i++)
-				if (tmp_cpus[i] == (int)start_cpu)
+				if (tmp_cpus[i].cpu == (int)start_cpu)
 					goto invalid;
 
 			if (nr_cpus == max_entries) {
 				max_entries += MAX_NR_CPUS;
-				tmp = realloc(tmp_cpus, max_entries * sizeof(int));
+				tmp = realloc(tmp_cpus, max_entries * sizeof(struct perf_cpu));
 				if (tmp == NULL)
 					goto invalid;
 				tmp_cpus = tmp;
 			}
-			tmp_cpus[nr_cpus++] = (int)start_cpu;
+			tmp_cpus[nr_cpus++].cpu = (int)start_cpu;
 		}
 		if (*p)
 			++p;
@@ -250,12 +257,16 @@ out:
 	return cpus;
 }
 
-int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx)
+struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx)
 {
+	struct perf_cpu result = {
+		.cpu = -1
+	};
+
 	if (cpus && idx < cpus->nr)
 		return cpus->map[idx];
 
-	return -1;
+	return result;
 }
 
 int perf_cpu_map__nr(const struct perf_cpu_map *cpus)
@@ -265,21 +276,26 @@ int perf_cpu_map__nr(const struct perf_cpu_map *cpus)
 
 bool perf_cpu_map__empty(const struct perf_cpu_map *map)
 {
-	return map ? map->map[0] == -1 : true;
+	return map ? map->map[0].cpu == -1 : true;
 }
 
-int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu)
+int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
 {
-	int low = 0, high = cpus->nr;
+	int low, high;
 
+	if (!cpus)
+		return -1;
+
+	low = 0;
+	high = cpus->nr;
 	while (low < high) {
-		int idx = (low + high) / 2,
-		    cpu_at_idx = cpus->map[idx];
+		int idx = (low + high) / 2;
+		struct perf_cpu cpu_at_idx = cpus->map[idx];
 
-		if (cpu_at_idx == cpu)
+		if (cpu_at_idx.cpu == cpu.cpu)
 			return idx;
 
-		if (cpu_at_idx > cpu)
+		if (cpu_at_idx.cpu > cpu.cpu)
 			high = idx;
 		else
 			low = idx + 1;
@@ -288,10 +304,19 @@ int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu)
 	return -1;
 }
 
-int perf_cpu_map__max(struct perf_cpu_map *map)
+bool perf_cpu_map__has(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
 {
+	return perf_cpu_map__idx(cpus, cpu) != -1;
+}
+
+struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map)
+{
+	struct perf_cpu result = {
+		.cpu = -1
+	};
+
 	// cpu_map__trim_new() qsort()s it, cpu_map__default_new() sorts it as well.
-	return map->nr > 0 ? map->map[map->nr - 1] : -1;
+	return map->nr > 0 ? map->map[map->nr - 1] : result;
 }
 
 /*
@@ -305,7 +330,7 @@ int perf_cpu_map__max(struct perf_cpu_map *map)
 struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
 					 struct perf_cpu_map *other)
 {
-	int *tmp_cpus;
+	struct perf_cpu *tmp_cpus;
 	int tmp_len;
 	int i, j, k;
 	struct perf_cpu_map *merged;
@@ -319,19 +344,19 @@ struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
 	if (!other)
 		return orig;
 	if (orig->nr == other->nr &&
-	    !memcmp(orig->map, other->map, orig->nr * sizeof(int)))
+	    !memcmp(orig->map, other->map, orig->nr * sizeof(struct perf_cpu)))
 		return orig;
 
 	tmp_len = orig->nr + other->nr;
-	tmp_cpus = malloc(tmp_len * sizeof(int));
+	tmp_cpus = malloc(tmp_len * sizeof(struct perf_cpu));
 	if (!tmp_cpus)
 		return NULL;
 
 	/* Standard merge algorithm from wikipedia */
 	i = j = k = 0;
 	while (i < orig->nr && j < other->nr) {
-		if (orig->map[i] <= other->map[j]) {
-			if (orig->map[i] == other->map[j])
+		if (orig->map[i].cpu <= other->map[j].cpu) {
+			if (orig->map[i].cpu == other->map[j].cpu)
 				j++;
 			tmp_cpus[k++] = orig->map[i++];
 		} else
diff --git a/tools/lib/perf/evlist.c b/tools/lib/perf/evlist.c
index e37dfad31383..9a770bfdc804 100644
--- a/tools/lib/perf/evlist.c
+++ b/tools/lib/perf/evlist.c
@@ -407,7 +407,7 @@ perf_evlist__mmap_cb_get(struct perf_evlist *evlist, bool overwrite, int idx)
 
 static int
 perf_evlist__mmap_cb_mmap(struct perf_mmap *map, struct perf_mmap_param *mp,
-			  int output, int cpu)
+			  int output, struct perf_cpu cpu)
 {
 	return perf_mmap__mmap(map, mp, output, cpu);
 }
@@ -426,7 +426,7 @@ 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 evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx);
+	struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->cpus, cpu_idx);
 	struct perf_evsel *evsel;
 	int revent;
 
@@ -643,14 +643,14 @@ perf_evlist__next_mmap(struct perf_evlist *evlist, struct perf_mmap *map,
 	return overwrite ? evlist->mmap_ovw_first : evlist->mmap_first;
 }
 
-void __perf_evlist__set_leader(struct list_head *list)
+void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader)
 {
-	struct perf_evsel *evsel, *leader;
+	struct perf_evsel *first, *last, *evsel;
 
-	leader = list_entry(list->next, struct perf_evsel, node);
-	evsel = list_entry(list->prev, struct perf_evsel, node);
+	first = list_first_entry(list, struct perf_evsel, node);
+	last = list_last_entry(list, struct perf_evsel, node);
 
-	leader->nr_members = evsel->idx - leader->idx + 1;
+	leader->nr_members = last->idx - first->idx + 1;
 
 	__perf_evlist__for_each_entry(list, evsel)
 		evsel->leader = leader;
@@ -659,7 +659,10 @@ void __perf_evlist__set_leader(struct list_head *list)
 void perf_evlist__set_leader(struct perf_evlist *evlist)
 {
 	if (evlist->nr_entries) {
+		struct perf_evsel *first = list_entry(evlist->entries.next,
+						struct perf_evsel, node);
+
 		evlist->nr_groups = evlist->nr_entries > 1 ? 1 : 0;
-		__perf_evlist__set_leader(&evlist->entries);
+		__perf_evlist__set_leader(&evlist->entries, first);
 	}
 }
diff --git a/tools/lib/perf/evsel.c b/tools/lib/perf/evsel.c
index 8441e3e1aaac..7ea86a44eae5 100644
--- a/tools/lib/perf/evsel.c
+++ b/tools/lib/perf/evsel.c
@@ -43,18 +43,22 @@ void perf_evsel__delete(struct perf_evsel *evsel)
 	free(evsel);
 }
 
-#define FD(e, x, y) ((int *) xyarray__entry(e->fd, x, y))
-#define MMAP(e, x, y) (e->mmap ? ((struct perf_mmap *) xyarray__entry(e->mmap, x, y)) : NULL)
+#define FD(_evsel, _cpu_map_idx, _thread)				\
+	((int *)xyarray__entry(_evsel->fd, _cpu_map_idx, _thread))
+#define MMAP(_evsel, _cpu_map_idx, _thread)				\
+	(_evsel->mmap ? ((struct perf_mmap *) xyarray__entry(_evsel->mmap, _cpu_map_idx, _thread)) \
+		      : NULL)
 
 int perf_evsel__alloc_fd(struct perf_evsel *evsel, int ncpus, int nthreads)
 {
 	evsel->fd = xyarray__new(ncpus, nthreads, sizeof(int));
 
 	if (evsel->fd) {
-		int cpu, thread;
-		for (cpu = 0; cpu < ncpus; cpu++) {
+		int idx, thread;
+
+		for (idx = 0; idx < ncpus; idx++) {
 			for (thread = 0; thread < nthreads; thread++) {
-				int *fd = FD(evsel, cpu, thread);
+				int *fd = FD(evsel, idx, thread);
 
 				if (fd)
 					*fd = -1;
@@ -74,13 +78,13 @@ static int perf_evsel__alloc_mmap(struct perf_evsel *evsel, int ncpus, int nthre
 
 static int
 sys_perf_event_open(struct perf_event_attr *attr,
-		    pid_t pid, int cpu, int group_fd,
+		    pid_t pid, struct perf_cpu cpu, int group_fd,
 		    unsigned long flags)
 {
-	return syscall(__NR_perf_event_open, attr, pid, cpu, group_fd, flags);
+	return syscall(__NR_perf_event_open, attr, pid, cpu.cpu, group_fd, flags);
 }
 
-static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *group_fd)
+static int get_group_fd(struct perf_evsel *evsel, int cpu_map_idx, int thread, int *group_fd)
 {
 	struct perf_evsel *leader = evsel->leader;
 	int *fd;
@@ -97,7 +101,7 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *grou
 	if (!leader->fd)
 		return -ENOTCONN;
 
-	fd = FD(leader, cpu, thread);
+	fd = FD(leader, cpu_map_idx, thread);
 	if (fd == NULL || *fd == -1)
 		return -EBADF;
 
@@ -109,7 +113,8 @@ static int get_group_fd(struct perf_evsel *evsel, int cpu, int thread, int *grou
 int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 		     struct perf_thread_map *threads)
 {
-	int cpu, thread, err = 0;
+	struct perf_cpu cpu;
+	int idx, thread, err = 0;
 
 	if (cpus == NULL) {
 		static struct perf_cpu_map *empty_cpu_map;
@@ -139,21 +144,21 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 	    perf_evsel__alloc_fd(evsel, cpus->nr, threads->nr) < 0)
 		return -ENOMEM;
 
-	for (cpu = 0; cpu < cpus->nr; cpu++) {
+	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
 		for (thread = 0; thread < threads->nr; thread++) {
 			int fd, group_fd, *evsel_fd;
 
-			evsel_fd = FD(evsel, cpu, thread);
+			evsel_fd = FD(evsel, idx, thread);
 			if (evsel_fd == NULL)
 				return -EINVAL;
 
-			err = get_group_fd(evsel, cpu, thread, &group_fd);
+			err = get_group_fd(evsel, idx, thread, &group_fd);
 			if (err < 0)
 				return err;
 
 			fd = sys_perf_event_open(&evsel->attr,
 						 threads->map[thread].pid,
-						 cpus->map[cpu], group_fd, 0);
+						 cpu, group_fd, 0);
 
 			if (fd < 0)
 				return -errno;
@@ -165,12 +170,12 @@ int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 	return err;
 }
 
-static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu)
+static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu_map_idx)
 {
 	int thread;
 
 	for (thread = 0; thread < xyarray__max_y(evsel->fd); ++thread) {
-		int *fd = FD(evsel, cpu, thread);
+		int *fd = FD(evsel, cpu_map_idx, thread);
 
 		if (fd && *fd >= 0) {
 			close(*fd);
@@ -181,10 +186,8 @@ static void perf_evsel__close_fd_cpu(struct perf_evsel *evsel, int cpu)
 
 void perf_evsel__close_fd(struct perf_evsel *evsel)
 {
-	int cpu;
-
-	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++)
-		perf_evsel__close_fd_cpu(evsel, cpu);
+	for (int idx = 0; idx < xyarray__max_x(evsel->fd); idx++)
+		perf_evsel__close_fd_cpu(evsel, idx);
 }
 
 void perf_evsel__free_fd(struct perf_evsel *evsel)
@@ -202,29 +205,29 @@ void perf_evsel__close(struct perf_evsel *evsel)
 	perf_evsel__free_fd(evsel);
 }
 
-void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu)
+void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx)
 {
 	if (evsel->fd == NULL)
 		return;
 
-	perf_evsel__close_fd_cpu(evsel, cpu);
+	perf_evsel__close_fd_cpu(evsel, cpu_map_idx);
 }
 
 void perf_evsel__munmap(struct perf_evsel *evsel)
 {
-	int cpu, thread;
+	int idx, thread;
 
 	if (evsel->fd == NULL || evsel->mmap == NULL)
 		return;
 
-	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
+	for (idx = 0; idx < xyarray__max_x(evsel->fd); idx++) {
 		for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
-			int *fd = FD(evsel, cpu, thread);
+			int *fd = FD(evsel, idx, thread);
 
 			if (fd == NULL || *fd < 0)
 				continue;
 
-			perf_mmap__munmap(MMAP(evsel, cpu, thread));
+			perf_mmap__munmap(MMAP(evsel, idx, thread));
 		}
 	}
 
@@ -234,7 +237,7 @@ void perf_evsel__munmap(struct perf_evsel *evsel)
 
 int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
 {
-	int ret, cpu, thread;
+	int ret, idx, thread;
 	struct perf_mmap_param mp = {
 		.prot = PROT_READ | PROT_WRITE,
 		.mask = (pages * page_size) - 1,
@@ -246,15 +249,16 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
 	if (perf_evsel__alloc_mmap(evsel, xyarray__max_x(evsel->fd), xyarray__max_y(evsel->fd)) < 0)
 		return -ENOMEM;
 
-	for (cpu = 0; cpu < xyarray__max_x(evsel->fd); cpu++) {
+	for (idx = 0; idx < xyarray__max_x(evsel->fd); idx++) {
 		for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
-			int *fd = FD(evsel, cpu, thread);
+			int *fd = FD(evsel, idx, thread);
 			struct perf_mmap *map;
+			struct perf_cpu cpu = perf_cpu_map__cpu(evsel->cpus, idx);
 
 			if (fd == NULL || *fd < 0)
 				continue;
 
-			map = MMAP(evsel, cpu, thread);
+			map = MMAP(evsel, idx, thread);
 			perf_mmap__init(map, NULL, false, NULL);
 
 			ret = perf_mmap__mmap(map, &mp, *fd, cpu);
@@ -268,14 +272,14 @@ int perf_evsel__mmap(struct perf_evsel *evsel, int pages)
 	return 0;
 }
 
-void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread)
+void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread)
 {
-	int *fd = FD(evsel, cpu, thread);
+	int *fd = FD(evsel, cpu_map_idx, thread);
 
-	if (fd == NULL || *fd < 0 || MMAP(evsel, cpu, thread) == NULL)
+	if (fd == NULL || *fd < 0 || MMAP(evsel, cpu_map_idx, thread) == NULL)
 		return NULL;
 
-	return MMAP(evsel, cpu, thread)->base;
+	return MMAP(evsel, cpu_map_idx, thread)->base;
 }
 
 int perf_evsel__read_size(struct perf_evsel *evsel)
@@ -303,19 +307,19 @@ int perf_evsel__read_size(struct perf_evsel *evsel)
 	return size;
 }
 
-int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread,
 		     struct perf_counts_values *count)
 {
 	size_t size = perf_evsel__read_size(evsel);
-	int *fd = FD(evsel, cpu, thread);
+	int *fd = FD(evsel, cpu_map_idx, thread);
 
 	memset(count, 0, sizeof(*count));
 
 	if (fd == NULL || *fd < 0)
 		return -EINVAL;
 
-	if (MMAP(evsel, cpu, thread) &&
-	    !perf_mmap__read_self(MMAP(evsel, cpu, thread), count))
+	if (MMAP(evsel, cpu_map_idx, thread) &&
+	    !perf_mmap__read_self(MMAP(evsel, cpu_map_idx, thread), count))
 		return 0;
 
 	if (readn(*fd, count->values, size) <= 0)
@@ -326,13 +330,13 @@ int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
 
 static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
 				 int ioc,  void *arg,
-				 int cpu)
+				 int cpu_map_idx)
 {
 	int thread;
 
 	for (thread = 0; thread < xyarray__max_y(evsel->fd); thread++) {
 		int err;
-		int *fd = FD(evsel, cpu, thread);
+		int *fd = FD(evsel, cpu_map_idx, thread);
 
 		if (fd == NULL || *fd < 0)
 			return -1;
@@ -346,9 +350,9 @@ static int perf_evsel__run_ioctl(struct perf_evsel *evsel,
 	return 0;
 }
 
-int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu)
+int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx)
 {
-	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu);
+	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_ENABLE, NULL, cpu_map_idx);
 }
 
 int perf_evsel__enable(struct perf_evsel *evsel)
@@ -361,9 +365,9 @@ int perf_evsel__enable(struct perf_evsel *evsel)
 	return err;
 }
 
-int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu)
+int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx)
 {
-	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu);
+	return perf_evsel__run_ioctl(evsel, PERF_EVENT_IOC_DISABLE, NULL, cpu_map_idx);
 }
 
 int perf_evsel__disable(struct perf_evsel *evsel)
@@ -431,3 +435,22 @@ void perf_evsel__free_id(struct perf_evsel *evsel)
 	zfree(&evsel->id);
 	evsel->ids = 0;
 }
+
+void perf_counts_values__scale(struct perf_counts_values *count,
+			       bool scale, __s8 *pscaled)
+{
+	s8 scaled = 0;
+
+	if (scale) {
+		if (count->run == 0) {
+			scaled = -1;
+			count->val = 0;
+		} else if (count->run < count->ena) {
+			scaled = 1;
+			count->val = (u64)((double)count->val * count->ena / count->run);
+		}
+	}
+
+	if (pscaled)
+		*pscaled = scaled;
+}
diff --git a/tools/lib/perf/include/internal/cpumap.h b/tools/lib/perf/include/internal/cpumap.h
index 840d4032587b..581f9ffb4237 100644
--- a/tools/lib/perf/include/internal/cpumap.h
+++ b/tools/lib/perf/include/internal/cpumap.h
@@ -4,16 +4,30 @@
 
 #include <linux/refcount.h>
 
+/** A wrapper around a CPU to avoid confusion with the perf_cpu_map's map's indices. */
+struct perf_cpu {
+	int cpu;
+};
+
+/**
+ * A sized, reference counted, sorted array of integers representing CPU
+ * numbers. This is commonly used to capture which CPUs a PMU is associated
+ * with. The indices into the cpumap are frequently used as they avoid having
+ * gaps if CPU numbers were used. For events associated with a pid, rather than
+ * a CPU, a single dummy map with an entry of -1 is used.
+ */
 struct perf_cpu_map {
 	refcount_t	refcnt;
+	/** Length of the map array. */
 	int		nr;
-	int		map[];
+	/** The CPU values. */
+	struct perf_cpu	map[];
 };
 
 #ifndef MAX_NR_CPUS
 #define MAX_NR_CPUS	2048
 #endif
 
-int perf_cpu_map__idx(struct perf_cpu_map *cpus, int cpu);
+int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu);
 
 #endif /* __LIBPERF_INTERNAL_CPUMAP_H */
diff --git a/tools/lib/perf/include/internal/evlist.h b/tools/lib/perf/include/internal/evlist.h
index f366dbad6a88..4cefade540bd 100644
--- a/tools/lib/perf/include/internal/evlist.h
+++ b/tools/lib/perf/include/internal/evlist.h
@@ -4,6 +4,7 @@
 
 #include <linux/list.h>
 #include <api/fd/array.h>
+#include <internal/cpumap.h>
 #include <internal/evsel.h>
 
 #define PERF_EVLIST__HLIST_BITS 8
@@ -36,7 +37,7 @@ typedef void
 typedef struct perf_mmap*
 (*perf_evlist_mmap__cb_get_t)(struct perf_evlist*, bool, int);
 typedef int
-(*perf_evlist_mmap__cb_mmap_t)(struct perf_mmap*, struct perf_mmap_param*, int, int);
+(*perf_evlist_mmap__cb_mmap_t)(struct perf_mmap*, struct perf_mmap_param*, int, struct perf_cpu);
 
 struct perf_evlist_mmap_ops {
 	perf_evlist_mmap__cb_idx_t	idx;
@@ -127,5 +128,5 @@ int perf_evlist__id_add_fd(struct perf_evlist *evlist,
 
 void perf_evlist__reset_id_hash(struct perf_evlist *evlist);
 
-void __perf_evlist__set_leader(struct list_head *list);
+void __perf_evlist__set_leader(struct list_head *list, struct perf_evsel *leader);
 #endif /* __LIBPERF_INTERNAL_EVLIST_H */
diff --git a/tools/lib/perf/include/internal/evsel.h b/tools/lib/perf/include/internal/evsel.h
index 1f3eacbad2e8..cfc9ebd7968e 100644
--- a/tools/lib/perf/include/internal/evsel.h
+++ b/tools/lib/perf/include/internal/evsel.h
@@ -6,8 +6,8 @@
 #include <linux/perf_event.h>
 #include <stdbool.h>
 #include <sys/types.h>
+#include <internal/cpumap.h>
 
-struct perf_cpu_map;
 struct perf_thread_map;
 struct xyarray;
 
@@ -27,7 +27,7 @@ struct perf_sample_id {
 	* queue number.
 	*/
 	int			 idx;
-	int			 cpu;
+	struct perf_cpu		 cpu;
 	pid_t			 tid;
 
 	/* Holds total ID period value for PERF_SAMPLE_READ processing. */
diff --git a/tools/lib/perf/include/internal/mmap.h b/tools/lib/perf/include/internal/mmap.h
index 5e3422f40ed5..5a062af8e9d8 100644
--- a/tools/lib/perf/include/internal/mmap.h
+++ b/tools/lib/perf/include/internal/mmap.h
@@ -6,6 +6,7 @@
 #include <linux/refcount.h>
 #include <linux/types.h>
 #include <stdbool.h>
+#include <internal/cpumap.h>
 
 /* perf sample has 16 bits size limit */
 #define PERF_SAMPLE_MAX_SIZE (1 << 16)
@@ -24,7 +25,7 @@ struct perf_mmap {
 	void			*base;
 	int			 mask;
 	int			 fd;
-	int			 cpu;
+	struct perf_cpu		 cpu;
 	refcount_t		 refcnt;
 	u64			 prev;
 	u64			 start;
@@ -46,7 +47,7 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map);
 void perf_mmap__init(struct perf_mmap *map, struct perf_mmap *prev,
 		     bool overwrite, libperf_unmap_cb_t unmap_cb);
 int perf_mmap__mmap(struct perf_mmap *map, struct perf_mmap_param *mp,
-		    int fd, int cpu);
+		    int fd, struct perf_cpu cpu);
 void perf_mmap__munmap(struct perf_mmap *map);
 void perf_mmap__get(struct perf_mmap *map);
 void perf_mmap__put(struct perf_mmap *map);
diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index 7c27766ea0bf..15b8faafd615 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -3,11 +3,10 @@
 #define __LIBPERF_CPUMAP_H
 
 #include <perf/core.h>
+#include <perf/cpumap.h>
 #include <stdio.h>
 #include <stdbool.h>
 
-struct perf_cpu_map;
-
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__dummy_new(void);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__default_new(void);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__new(const char *cpu_list);
@@ -16,10 +15,11 @@ LIBPERF_API struct perf_cpu_map *perf_cpu_map__get(struct perf_cpu_map *map);
 LIBPERF_API struct perf_cpu_map *perf_cpu_map__merge(struct perf_cpu_map *orig,
 						     struct perf_cpu_map *other);
 LIBPERF_API void perf_cpu_map__put(struct perf_cpu_map *map);
-LIBPERF_API int perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
+LIBPERF_API struct perf_cpu perf_cpu_map__cpu(const struct perf_cpu_map *cpus, int idx);
 LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
 LIBPERF_API bool perf_cpu_map__empty(const struct perf_cpu_map *map);
-LIBPERF_API int perf_cpu_map__max(struct perf_cpu_map *map);
+LIBPERF_API struct perf_cpu perf_cpu_map__max(struct perf_cpu_map *map);
+LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu);
 
 #define perf_cpu_map__for_each_cpu(cpu, idx, cpus)		\
 	for ((idx) = 0, (cpu) = perf_cpu_map__cpu(cpus, idx);	\
diff --git a/tools/lib/perf/include/perf/evsel.h b/tools/lib/perf/include/perf/evsel.h
index 60eae25076d3..2a9516b42d15 100644
--- a/tools/lib/perf/include/perf/evsel.h
+++ b/tools/lib/perf/include/perf/evsel.h
@@ -4,6 +4,8 @@
 
 #include <stdint.h>
 #include <perf/core.h>
+#include <stdbool.h>
+#include <linux/types.h>
 
 struct perf_evsel;
 struct perf_event_attr;
@@ -26,18 +28,20 @@ LIBPERF_API void perf_evsel__delete(struct perf_evsel *evsel);
 LIBPERF_API int perf_evsel__open(struct perf_evsel *evsel, struct perf_cpu_map *cpus,
 				 struct perf_thread_map *threads);
 LIBPERF_API void perf_evsel__close(struct perf_evsel *evsel);
-LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu);
+LIBPERF_API void perf_evsel__close_cpu(struct perf_evsel *evsel, int cpu_map_idx);
 LIBPERF_API int perf_evsel__mmap(struct perf_evsel *evsel, int pages);
 LIBPERF_API void perf_evsel__munmap(struct perf_evsel *evsel);
-LIBPERF_API void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu, int thread);
-LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu, int thread,
+LIBPERF_API void *perf_evsel__mmap_base(struct perf_evsel *evsel, int cpu_map_idx, int thread);
+LIBPERF_API int perf_evsel__read(struct perf_evsel *evsel, int cpu_map_idx, int thread,
 				 struct perf_counts_values *count);
 LIBPERF_API int perf_evsel__enable(struct perf_evsel *evsel);
-LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu);
+LIBPERF_API int perf_evsel__enable_cpu(struct perf_evsel *evsel, int cpu_map_idx);
 LIBPERF_API int perf_evsel__disable(struct perf_evsel *evsel);
-LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu);
+LIBPERF_API int perf_evsel__disable_cpu(struct perf_evsel *evsel, int cpu_map_idx);
 LIBPERF_API struct perf_cpu_map *perf_evsel__cpus(struct perf_evsel *evsel);
 LIBPERF_API struct perf_thread_map *perf_evsel__threads(struct perf_evsel *evsel);
 LIBPERF_API struct perf_event_attr *perf_evsel__attr(struct perf_evsel *evsel);
+LIBPERF_API void perf_counts_values__scale(struct perf_counts_values *count,
+					   bool scale, __s8 *pscaled);
 
 #endif /* __LIBPERF_EVSEL_H */
diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map
index 71468606e8a7..93696affda2e 100644
--- a/tools/lib/perf/libperf.map
+++ b/tools/lib/perf/libperf.map
@@ -10,6 +10,7 @@ LIBPERF_0.0.1 {
 		perf_cpu_map__cpu;
 		perf_cpu_map__empty;
 		perf_cpu_map__max;
+		perf_cpu_map__has;
 		perf_thread_map__new_dummy;
 		perf_thread_map__set_pid;
 		perf_thread_map__comm;
@@ -50,6 +51,7 @@ LIBPERF_0.0.1 {
 		perf_mmap__read_init;
 		perf_mmap__read_done;
 		perf_mmap__read_event;
+		perf_counts_values__scale;
 	local:
 		*;
 };
diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c
index c89dfa5f67b3..f7ee07cb5818 100644
--- a/tools/lib/perf/mmap.c
+++ b/tools/lib/perf/mmap.c
@@ -32,7 +32,7 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map)
 }
 
 int perf_mmap__mmap(struct perf_mmap *map, struct perf_mmap_param *mp,
-		    int fd, int cpu)
+		    int fd, struct perf_cpu cpu)
 {
 	map->prev = 0;
 	map->mask = mp->mask;
@@ -353,8 +353,6 @@ int perf_mmap__read_self(struct perf_mmap *map, struct perf_counts_values *count
 		count->ena += delta;
 		if (idx)
 			count->run += delta;
-
-		cnt = mul_u64_u64_div64(cnt, count->ena, count->run);
 	}
 
 	count->val = cnt;
diff --git a/tools/lib/perf/tests/test-evlist.c b/tools/lib/perf/tests/test-evlist.c
index ce91a582f0e4..b3479dfa9a1c 100644
--- a/tools/lib/perf/tests/test-evlist.c
+++ b/tools/lib/perf/tests/test-evlist.c
@@ -21,6 +21,9 @@
 #include "tests.h"
 #include <internal/evsel.h>
 
+#define EVENT_NUM 15
+#define WAIT_COUNT 100000000UL
+
 static int libperf_print(enum libperf_print_level level,
 			 const char *fmt, va_list ap)
 {
@@ -331,7 +334,8 @@ static int test_mmap_cpus(void)
 	};
 	cpu_set_t saved_mask;
 	char path[PATH_MAX];
-	int id, err, cpu, tmp;
+	int id, err, tmp;
+	struct perf_cpu cpu;
 	union perf_event *event;
 	int count = 0;
 
@@ -374,7 +378,7 @@ static int test_mmap_cpus(void)
 		cpu_set_t mask;
 
 		CPU_ZERO(&mask);
-		CPU_SET(cpu, &mask);
+		CPU_SET(cpu.cpu, &mask);
 
 		err = sched_setaffinity(0, sizeof(mask), &mask);
 		__T("sched_setaffinity failed", err == 0);
@@ -413,6 +417,159 @@ static int test_mmap_cpus(void)
 	return 0;
 }
 
+static double display_error(long long average,
+			    long long high,
+			    long long low,
+			    long long expected)
+{
+	double error;
+
+	error = (((double)average - expected) / expected) * 100.0;
+
+	__T_VERBOSE("   Expected: %lld\n", expected);
+	__T_VERBOSE("   High: %lld   Low:  %lld   Average:  %lld\n",
+		    high, low, average);
+
+	__T_VERBOSE("   Average Error = %.2f%%\n", error);
+
+	return error;
+}
+
+static int test_stat_multiplexing(void)
+{
+	struct perf_counts_values expected_counts = { .val = 0 };
+	struct perf_counts_values counts[EVENT_NUM] = {{ .val = 0 },};
+	struct perf_thread_map *threads;
+	struct perf_evlist *evlist;
+	struct perf_evsel *evsel;
+	struct perf_event_attr attr = {
+		.type	     = PERF_TYPE_HARDWARE,
+		.config	     = PERF_COUNT_HW_INSTRUCTIONS,
+		.read_format = PERF_FORMAT_TOTAL_TIME_ENABLED |
+			       PERF_FORMAT_TOTAL_TIME_RUNNING,
+		.disabled    = 1,
+	};
+	int err, i, nonzero = 0;
+	unsigned long count;
+	long long max = 0, min = 0, avg = 0;
+	double error = 0.0;
+	s8 scaled = 0;
+
+	/* read for non-multiplexing event count */
+	threads = perf_thread_map__new_dummy();
+	__T("failed to create threads", threads);
+
+	perf_thread_map__set_pid(threads, 0, 0);
+
+	evsel = perf_evsel__new(&attr);
+	__T("failed to create evsel", evsel);
+
+	err = perf_evsel__open(evsel, NULL, threads);
+	__T("failed to open evsel", err == 0);
+
+	err = perf_evsel__enable(evsel);
+	__T("failed to enable evsel", err == 0);
+
+	/* wait loop */
+	count = WAIT_COUNT;
+	while (count--)
+		;
+
+	perf_evsel__read(evsel, 0, 0, &expected_counts);
+	__T("failed to read value for evsel", expected_counts.val != 0);
+	__T("failed to read non-multiplexing event count",
+	    expected_counts.ena == expected_counts.run);
+
+	err = perf_evsel__disable(evsel);
+	__T("failed to enable evsel", err == 0);
+
+	perf_evsel__close(evsel);
+	perf_evsel__delete(evsel);
+
+	perf_thread_map__put(threads);
+
+	/* read for multiplexing event count */
+	threads = perf_thread_map__new_dummy();
+	__T("failed to create threads", threads);
+
+	perf_thread_map__set_pid(threads, 0, 0);
+
+	evlist = perf_evlist__new();
+	__T("failed to create evlist", evlist);
+
+	for (i = 0; i < EVENT_NUM; i++) {
+		evsel = perf_evsel__new(&attr);
+		__T("failed to create evsel", evsel);
+
+		perf_evlist__add(evlist, evsel);
+	}
+	perf_evlist__set_maps(evlist, NULL, threads);
+
+	err = perf_evlist__open(evlist);
+	__T("failed to open evsel", err == 0);
+
+	perf_evlist__enable(evlist);
+
+	/* wait loop */
+	count = WAIT_COUNT;
+	while (count--)
+		;
+
+	i = 0;
+	perf_evlist__for_each_evsel(evlist, evsel) {
+		perf_evsel__read(evsel, 0, 0, &counts[i]);
+		__T("failed to read value for evsel", counts[i].val != 0);
+		i++;
+	}
+
+	perf_evlist__disable(evlist);
+
+	min = counts[0].val;
+	for (i = 0; i < EVENT_NUM; i++) {
+		__T_VERBOSE("Event %2d -- Raw count = %lu, run = %lu, enable = %lu\n",
+			    i, counts[i].val, counts[i].run, counts[i].ena);
+
+		perf_counts_values__scale(&counts[i], true, &scaled);
+		if (scaled == 1) {
+			__T_VERBOSE("\t Scaled count = %lu (%.2lf%%, %lu/%lu)\n",
+				    counts[i].val,
+				    (double)counts[i].run / (double)counts[i].ena * 100.0,
+				    counts[i].run, counts[i].ena);
+		} else if (scaled == -1) {
+			__T_VERBOSE("\t Not Running\n");
+		} else {
+			__T_VERBOSE("\t Not Scaling\n");
+		}
+
+		if (counts[i].val > max)
+			max = counts[i].val;
+
+		if (counts[i].val < min)
+			min = counts[i].val;
+
+		avg += counts[i].val;
+
+		if (counts[i].val != 0)
+			nonzero++;
+	}
+
+	if (nonzero != 0)
+		avg = avg / nonzero;
+	else
+		avg = 0;
+
+	error = display_error(avg, max, min, expected_counts.val);
+
+	__T("Error out of range!", ((error <= 1.0) && (error >= -1.0)));
+
+	perf_evlist__close(evlist);
+	perf_evlist__delete(evlist);
+
+	perf_thread_map__put(threads);
+
+	return 0;
+}
+
 int test_evlist(int argc, char **argv)
 {
 	__T_START;
@@ -424,6 +581,7 @@ int test_evlist(int argc, char **argv)
 	test_stat_thread_enable();
 	test_mmap_thread();
 	test_mmap_cpus();
+	test_stat_multiplexing();
 
 	__T_END;
 	return tests_failed == 0 ? 0 : -1;
diff --git a/tools/perf/Documentation/perf-buildid-cache.txt b/tools/perf/Documentation/perf-buildid-cache.txt
index cd8ce6e8ec12..7e44b419d301 100644
--- a/tools/perf/Documentation/perf-buildid-cache.txt
+++ b/tools/perf/Documentation/perf-buildid-cache.txt
@@ -74,12 +74,15 @@ OPTIONS
 	used when creating a uprobe for a process that resides in a
 	different mount namespace from the perf(1) utility.
 
---debuginfod=URLs::
+--debuginfod[=URLs]::
 	Specify debuginfod URL to be used when retrieving perf.data binaries,
 	it follows the same syntax as the DEBUGINFOD_URLS variable, like:
 
 	  buildid-cache.debuginfod=http://192.168.122.174:8002
 
+	If the URLs is not specified, the value of DEBUGINFOD_URLS
+	system environment variable is used.
+
 SEE ALSO
 --------
 linkperf:perf-record[1], linkperf:perf-report[1], linkperf:perf-buildid-list[1]
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 3bb75c1f25e8..0420e71698ee 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -587,6 +587,15 @@ record.*::
 		Use 'n' control blocks in asynchronous (Posix AIO) trace writing
 		mode ('n' default: 1, max: 4).
 
+	record.debuginfod::
+		Specify debuginfod URL to be used when cacheing perf.data binaries,
+		it follows the same syntax as the DEBUGINFOD_URLS variable, like:
+
+		  http://192.168.122.174:8002
+
+		If the URLs is 'system', the value of DEBUGINFOD_URLS system environment
+		variable is used.
+
 diff.*::
 	diff.order::
 		This option sets the number of columns to sort the result.
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 4dc8d0af19df..57384a97c04f 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -81,7 +81,11 @@ On AMD systems it is implemented using IBS (up to precise-level 2).
 The precise modifier works with event types 0x76 (cpu-cycles, CPU
 clocks not halted) and 0xC1 (micro-ops retired). Both events map to
 IBS execution sampling (IBS op) with the IBS Op Counter Control bit
-(IbsOpCntCtl) set respectively (see AMD64 Architecture Programmer’s
+(IbsOpCntCtl) set respectively (see the
+Core Complex (CCX) -> Processor x86 Core -> Instruction Based Sampling (IBS)
+section of the [AMD Processor Programming Reference (PPR)] relevant to the
+family, model and stepping of the processor being used).
+
 Manual Volume 2: System Programming, 13.3 Instruction-Based
 Sampling). Examples to use IBS:
 
@@ -94,10 +98,12 @@ RAW HARDWARE EVENT DESCRIPTOR
 Even when an event is not available in a symbolic form within perf right now,
 it can be encoded in a per processor specific way.
 
-For instance For x86 CPUs NNN represents the raw register encoding with the
+For instance on x86 CPUs, N is a hexadecimal value that represents the raw register encoding with the
 layout of IA32_PERFEVTSELx MSRs (see [Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide] Figure 30-1 Layout
-of IA32_PERFEVTSELx MSRs) or AMD's PerfEvtSeln (see [AMD64 Architecture Programmer’s Manual Volume 2: System Programming], Page 344,
-Figure 13-7 Performance Event-Select Register (PerfEvtSeln)).
+of IA32_PERFEVTSELx MSRs) or AMD's PERF_CTL MSRs (see the
+Core Complex (CCX) -> Processor x86 Core -> MSR Registers section of the
+[AMD Processor Programming Reference (PPR)] relevant to the family, model
+and stepping of the processor being used).
 
 Note: Only the following bit fields can be set in x86 counter
 registers: event, umask, edge, inv, cmask. Esp. guest/host only and
@@ -126,6 +132,38 @@ It's also possible to use pmu syntax:
  perf record -e cpu/r1a8/ ...
  perf record -e cpu/r0x1a8/ ...
 
+Some processors, like those from AMD, support event codes and unit masks
+larger than a byte. In such cases, the bits corresponding to the event
+configuration parameters can be seen with:
+
+  cat /sys/bus/event_source/devices/<pmu>/format/<config>
+
+Example:
+
+If the AMD docs for an EPYC 7713 processor describe an event as:
+
+  Event  Umask  Event Mask
+  Num.   Value  Mnemonic                        Description
+
+  28FH     03H  op_cache_hit_miss.op_cache_hit  Counts Op Cache micro-tag
+                                                hit events.
+
+raw encoding of 0x0328F cannot be used since the upper nibble of the
+EventSelect bits have to be specified via bits 32-35 as can be seen with:
+
+  cat /sys/bus/event_source/devices/cpu/format/event
+
+raw encoding of 0x20000038F should be used instead:
+
+ perf stat -e r20000038f -a sleep 1
+ perf record -e r20000038f ...
+
+It's also possible to use pmu syntax:
+
+ perf record -e r20000038f -a sleep 1
+ perf record -e cpu/r20000038f/ ...
+ perf record -e cpu/r0x20000038f/ ...
+
 You should refer to the processor specific documentation for getting these
 details. Some of them are referenced in the SEE ALSO section below.
 
@@ -316,4 +354,4 @@ SEE ALSO
 linkperf:perf-stat[1], linkperf:perf-top[1],
 linkperf:perf-record[1],
 http://www.intel.com/sdm/[Intel® 64 and IA-32 Architectures Software Developer's Manual Volume 3B: System Programming Guide],
-http://support.amd.com/us/Processor_TechDocs/24593_APM_v2.pdf[AMD64 Architecture Programmer’s Manual Volume 2: System Programming]
+https://bugzilla.kernel.org/show_bug.cgi?id=206537[AMD Processor Programming Reference (PPR)]
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 3cf7bac67239..9ccc75935bc5 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -30,8 +30,10 @@ OPTIONS
 
         - a symbolic event name	(use 'perf list' to list all events)
 
-        - a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
-	  hexadecimal event descriptor.
+        - a raw PMU event in the form of rN where N is a hexadecimal value
+          that represents the raw register encoding with the layout of the
+          event control registers as described by entries in
+          /sys/bus/event_sources/devices/cpu/format/*.
 
         - a symbolic or raw PMU event followed by an optional colon
 	  and a list of event modifiers, e.g., cpu-cycles:p.  See the
@@ -713,6 +715,15 @@ measurements:
 
 include::intel-hybrid.txt[]
 
+--debuginfod[=URLs]::
+	Specify debuginfod URL to be used when cacheing perf.data binaries,
+	it follows the same syntax as the DEBUGINFOD_URLS variable, like:
+
+	  http://192.168.122.174:8002
+
+	If the URLs is not specified, the value of DEBUGINFOD_URLS
+	system environment variable is used.
+
 SEE ALSO
 --------
 linkperf:perf-stat[1], linkperf:perf-list[1], linkperf:perf-intel-pt[1]
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 7e6fb7cbc0f4..c06c341e72b9 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -36,8 +36,10 @@ report::
 
 	- a symbolic event name (use 'perf list' to list all events)
 
-	- a raw PMU event (eventsel+umask) in the form of rNNN where NNN is a
-	  hexadecimal event descriptor.
+	- a raw PMU event in the form of rN where N is a hexadecimal value
+	  that represents the raw register encoding with the layout of the
+	  event control registers as described by entries in
+	  /sys/bus/event_sources/devices/cpu/format/*.
 
         - a symbolic or raw PMU event followed by an optional colon
 	  and a list of event modifiers, e.g., cpu-cycles:p.  See the
@@ -493,6 +495,10 @@ This option can be enabled in perf config by setting the variable
 
 $ perf config stat.no-csv-summary=true
 
+--cputype::
+Only enable events on applying cpu with this type for hybrid platform
+(e.g. core or atom)"
+
 EXAMPLES
 --------
 
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 9898a32b8d9c..cac3dfbee7d8 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -38,9 +38,10 @@ Default is to monitor all CPUS.
 -e <event>::
 --event=<event>::
 	Select the PMU event. Selection can be a symbolic event name
-	(use 'perf list' to list all events) or a raw PMU
-	event (eventsel+umask) in the form of rNNN where NNN is a
-	hexadecimal event descriptor.
+	(use 'perf list' to list all events) or a raw PMU event in the form
+	of rN where N is a hexadecimal value that represents the raw register
+	encoding with the layout of the event control registers as described
+	by entries in /sys/bus/event_sources/devices/cpu/format/*.
 
 -E <entries>::
 --entries=<entries>::
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 3df74cf5651a..96ad944ca6a8 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -17,6 +17,7 @@ detected     = $(shell echo "$(1)=y"       >> $(OUTPUT).config-detected)
 detected_var = $(shell echo "$(1)=$($(1))" >> $(OUTPUT).config-detected)
 
 CFLAGS := $(EXTRA_CFLAGS) $(filter-out -Wnested-externs,$(EXTRA_WARNINGS))
+HOSTCFLAGS := $(filter-out -Wnested-externs,$(EXTRA_WARNINGS))
 
 include $(srctree)/tools/scripts/Makefile.arch
 
@@ -143,7 +144,10 @@ FEATURE_CHECK_LDFLAGS-libcrypto = -lcrypto
 ifdef CSINCLUDES
   LIBOPENCSD_CFLAGS := -I$(CSINCLUDES)
 endif
-OPENCSDLIBS := -lopencsd_c_api -lopencsd -lstdc++
+OPENCSDLIBS := -lopencsd_c_api
+ifeq ($(findstring -static,${LDFLAGS}),-static)
+  OPENCSDLIBS += -lopencsd -lstdc++
+endif
 ifdef CSLIBS
   LIBOPENCSD_LDFLAGS := -L$(CSLIBS)
 endif
@@ -211,6 +215,7 @@ endif
 ifneq ($(WERROR),0)
   CORE_CFLAGS += -Werror
   CXXFLAGS += -Werror
+  HOSTCFLAGS += -Werror
 endif
 
 ifndef DEBUG
@@ -290,6 +295,9 @@ CXXFLAGS += -ggdb3
 CXXFLAGS += -funwind-tables
 CXXFLAGS += -Wno-strict-aliasing
 
+HOSTCFLAGS += -Wall
+HOSTCFLAGS += -Wextra
+
 # Enforce a non-executable stack, as we may regress (again) in the future by
 # adding assembler files missing the .GNU-stack linker note.
 LDFLAGS += -Wl,-z,noexecstack
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 80522bcfafe0..ac861e42c8f7 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -226,7 +226,7 @@ else
 endif
 
 export srctree OUTPUT RM CC CXX LD AR CFLAGS CXXFLAGS V BISON FLEX AWK
-export HOSTCC HOSTLD HOSTAR
+export HOSTCC HOSTLD HOSTAR HOSTCFLAGS
 
 include $(srctree)/tools/build/Makefile.include
 
@@ -1041,7 +1041,7 @@ SKEL_OUT := $(abspath $(OUTPUT)util/bpf_skel)
 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
+SKELETONS += $(SKEL_OUT)/bperf_cgroup.skel.h $(SKEL_OUT)/func_latency.skel.h
 
 $(SKEL_TMP_OUT) $(LIBBPF_OUTPUT):
 	$(Q)$(MKDIR) -p $@
diff --git a/tools/perf/arch/arm/include/perf_regs.h b/tools/perf/arch/arm/include/perf_regs.h
index 4085419283d0..99a06550e25d 100644
--- a/tools/perf/arch/arm/include/perf_regs.h
+++ b/tools/perf/arch/arm/include/perf_regs.h
@@ -15,46 +15,4 @@ void perf_regs_load(u64 *regs);
 #define PERF_REG_IP	PERF_REG_ARM_PC
 #define PERF_REG_SP	PERF_REG_ARM_SP
 
-static inline const char *__perf_reg_name(int id)
-{
-	switch (id) {
-	case PERF_REG_ARM_R0:
-		return "r0";
-	case PERF_REG_ARM_R1:
-		return "r1";
-	case PERF_REG_ARM_R2:
-		return "r2";
-	case PERF_REG_ARM_R3:
-		return "r3";
-	case PERF_REG_ARM_R4:
-		return "r4";
-	case PERF_REG_ARM_R5:
-		return "r5";
-	case PERF_REG_ARM_R6:
-		return "r6";
-	case PERF_REG_ARM_R7:
-		return "r7";
-	case PERF_REG_ARM_R8:
-		return "r8";
-	case PERF_REG_ARM_R9:
-		return "r9";
-	case PERF_REG_ARM_R10:
-		return "r10";
-	case PERF_REG_ARM_FP:
-		return "fp";
-	case PERF_REG_ARM_IP:
-		return "ip";
-	case PERF_REG_ARM_SP:
-		return "sp";
-	case PERF_REG_ARM_LR:
-		return "lr";
-	case PERF_REG_ARM_PC:
-		return "pc";
-	default:
-		return NULL;
-	}
-
-	return NULL;
-}
-
 #endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 293a23bf8be3..2e8b2c4365a0 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -203,9 +203,11 @@ static int cs_etm_set_option(struct auxtrace_record *itr,
 	struct perf_cpu_map *online_cpus = perf_cpu_map__new(NULL);
 
 	/* Set option of each CPU we have */
-	for (i = 0; i < cpu__max_cpu(); i++) {
-		if (!cpu_map__has(event_cpus, i) ||
-		    !cpu_map__has(online_cpus, i))
+	for (i = 0; i < cpu__max_cpu().cpu; i++) {
+		struct perf_cpu cpu = { .cpu = i, };
+
+		if (!perf_cpu_map__has(event_cpus, cpu) ||
+		    !perf_cpu_map__has(online_cpus, cpu))
 			continue;
 
 		if (option & BIT(ETM_OPT_CTXTID)) {
@@ -407,25 +409,6 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 
 	}
 
-	/* Validate auxtrace_mmap_pages provided by user */
-	if (opts->auxtrace_mmap_pages) {
-		unsigned int max_page = (KiB(128) / page_size);
-		size_t sz = opts->auxtrace_mmap_pages * (size_t)page_size;
-
-		if (!privileged &&
-		    opts->auxtrace_mmap_pages > max_page) {
-			opts->auxtrace_mmap_pages = max_page;
-			pr_err("auxtrace too big, truncating to %d\n",
-			       max_page);
-		}
-
-		if (!is_power_of_2(sz)) {
-			pr_err("Invalid mmap size for %s: must be a power of 2\n",
-			       CORESIGHT_ETM_PMU_NAME);
-			return -EINVAL;
-		}
-	}
-
 	if (opts->auxtrace_snapshot_mode)
 		pr_debug2("%s snapshot size: %zu\n", CORESIGHT_ETM_PMU_NAME,
 			  opts->auxtrace_snapshot_size);
@@ -541,9 +524,11 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 
 	/* cpu map is not empty, we have specific CPUs to work with */
 	if (!perf_cpu_map__empty(event_cpus)) {
-		for (i = 0; i < cpu__max_cpu(); i++) {
-			if (!cpu_map__has(event_cpus, i) ||
-			    !cpu_map__has(online_cpus, i))
+		for (i = 0; i < cpu__max_cpu().cpu; i++) {
+			struct perf_cpu cpu = { .cpu = i, };
+
+			if (!perf_cpu_map__has(event_cpus, cpu) ||
+			    !perf_cpu_map__has(online_cpus, cpu))
 				continue;
 
 			if (cs_etm_is_ete(itr, i))
@@ -555,8 +540,10 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 		}
 	} else {
 		/* get configuration for all CPUs in the system */
-		for (i = 0; i < cpu__max_cpu(); i++) {
-			if (!cpu_map__has(online_cpus, i))
+		for (i = 0; i < cpu__max_cpu().cpu; i++) {
+			struct perf_cpu cpu = { .cpu = i, };
+
+			if (!perf_cpu_map__has(online_cpus, cpu))
 				continue;
 
 			if (cs_etm_is_ete(itr, i))
@@ -741,8 +728,10 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 	} else {
 		/* Make sure all specified CPUs are online */
 		for (i = 0; i < perf_cpu_map__nr(event_cpus); i++) {
-			if (cpu_map__has(event_cpus, i) &&
-			    !cpu_map__has(online_cpus, i))
+			struct perf_cpu cpu = { .cpu = i, };
+
+			if (perf_cpu_map__has(event_cpus, cpu) &&
+			    !perf_cpu_map__has(online_cpus, cpu))
 				return -EINVAL;
 		}
 
@@ -762,9 +751,12 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 
 	offset = CS_ETM_SNAPSHOT + 1;
 
-	for (i = 0; i < cpu__max_cpu() && offset < priv_size; i++)
-		if (cpu_map__has(cpu_map, i))
+	for (i = 0; i < cpu__max_cpu().cpu && offset < priv_size; i++) {
+		struct perf_cpu cpu = { .cpu = i, };
+
+		if (perf_cpu_map__has(cpu_map, cpu))
 			cs_etm_get_metadata(i, &offset, itr, info);
+	}
 
 	perf_cpu_map__put(online_cpus);
 
diff --git a/tools/perf/arch/arm64/include/perf_regs.h b/tools/perf/arch/arm64/include/perf_regs.h
index fa3e07459f76..35a3cc775b39 100644
--- a/tools/perf/arch/arm64/include/perf_regs.h
+++ b/tools/perf/arch/arm64/include/perf_regs.h
@@ -4,7 +4,9 @@
 
 #include <stdlib.h>
 #include <linux/types.h>
+#define perf_event_arm_regs perf_event_arm64_regs
 #include <asm/perf_regs.h>
+#undef perf_event_arm_regs
 
 void perf_regs_load(u64 *regs);
 
@@ -15,80 +17,4 @@ void perf_regs_load(u64 *regs);
 #define PERF_REG_IP	PERF_REG_ARM64_PC
 #define PERF_REG_SP	PERF_REG_ARM64_SP
 
-static inline const char *__perf_reg_name(int id)
-{
-	switch (id) {
-	case PERF_REG_ARM64_X0:
-		return "x0";
-	case PERF_REG_ARM64_X1:
-		return "x1";
-	case PERF_REG_ARM64_X2:
-		return "x2";
-	case PERF_REG_ARM64_X3:
-		return "x3";
-	case PERF_REG_ARM64_X4:
-		return "x4";
-	case PERF_REG_ARM64_X5:
-		return "x5";
-	case PERF_REG_ARM64_X6:
-		return "x6";
-	case PERF_REG_ARM64_X7:
-		return "x7";
-	case PERF_REG_ARM64_X8:
-		return "x8";
-	case PERF_REG_ARM64_X9:
-		return "x9";
-	case PERF_REG_ARM64_X10:
-		return "x10";
-	case PERF_REG_ARM64_X11:
-		return "x11";
-	case PERF_REG_ARM64_X12:
-		return "x12";
-	case PERF_REG_ARM64_X13:
-		return "x13";
-	case PERF_REG_ARM64_X14:
-		return "x14";
-	case PERF_REG_ARM64_X15:
-		return "x15";
-	case PERF_REG_ARM64_X16:
-		return "x16";
-	case PERF_REG_ARM64_X17:
-		return "x17";
-	case PERF_REG_ARM64_X18:
-		return "x18";
-	case PERF_REG_ARM64_X19:
-		return "x19";
-	case PERF_REG_ARM64_X20:
-		return "x20";
-	case PERF_REG_ARM64_X21:
-		return "x21";
-	case PERF_REG_ARM64_X22:
-		return "x22";
-	case PERF_REG_ARM64_X23:
-		return "x23";
-	case PERF_REG_ARM64_X24:
-		return "x24";
-	case PERF_REG_ARM64_X25:
-		return "x25";
-	case PERF_REG_ARM64_X26:
-		return "x26";
-	case PERF_REG_ARM64_X27:
-		return "x27";
-	case PERF_REG_ARM64_X28:
-		return "x28";
-	case PERF_REG_ARM64_X29:
-		return "x29";
-	case PERF_REG_ARM64_SP:
-		return "sp";
-	case PERF_REG_ARM64_LR:
-		return "lr";
-	case PERF_REG_ARM64_PC:
-		return "pc";
-	default:
-		return NULL;
-	}
-
-	return NULL;
-}
-
 #endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/arm64/util/machine.c b/tools/perf/arch/arm64/util/machine.c
index 7e7714290a87..d2ce31e28cd7 100644
--- a/tools/perf/arch/arm64/util/machine.c
+++ b/tools/perf/arch/arm64/util/machine.c
@@ -5,6 +5,8 @@
 #include <string.h>
 #include "debug.h"
 #include "symbol.h"
+#include "callchain.h"
+#include "record.h"
 
 /* On arm64, kernel text segment starts at high memory address,
  * for example 0xffff 0000 8xxx xxxx. Modules start at a low memory
@@ -26,3 +28,8 @@ void arch__symbols__fixup_end(struct symbol *p, struct symbol *c)
 		p->end = c->start;
 	pr_debug4("%s sym:%s end:%#" PRIx64 "\n", __func__, p->name, p->end);
 }
+
+void arch__add_leaf_frame_record_opts(struct record_opts *opts)
+{
+	opts->sample_user_regs |= sample_reg_masks[PERF_REG_ARM64_LR].mask;
+}
diff --git a/tools/perf/arch/arm64/util/pmu.c b/tools/perf/arch/arm64/util/pmu.c
index d3a18f9c85f6..79124bba713e 100644
--- a/tools/perf/arch/arm64/util/pmu.c
+++ b/tools/perf/arch/arm64/util/pmu.c
@@ -15,7 +15,7 @@ const struct pmu_events_map *pmu_events_map__find(void)
 		 * The cpumap should cover all CPUs. Otherwise, some CPUs may
 		 * not support some events or have different event IDs.
 		 */
-		if (pmu->cpus->nr != cpu__max_cpu())
+		if (pmu->cpus->nr != cpu__max_cpu().cpu)
 			return NULL;
 
 		return perf_pmu__find_map(pmu);
diff --git a/tools/perf/arch/csky/include/perf_regs.h b/tools/perf/arch/csky/include/perf_regs.h
index 25ac3bdcb9d1..1afcc0e916c2 100644
--- a/tools/perf/arch/csky/include/perf_regs.h
+++ b/tools/perf/arch/csky/include/perf_regs.h
@@ -15,86 +15,4 @@
 #define PERF_REG_IP	PERF_REG_CSKY_PC
 #define PERF_REG_SP	PERF_REG_CSKY_SP
 
-static inline const char *__perf_reg_name(int id)
-{
-	switch (id) {
-	case PERF_REG_CSKY_A0:
-		return "a0";
-	case PERF_REG_CSKY_A1:
-		return "a1";
-	case PERF_REG_CSKY_A2:
-		return "a2";
-	case PERF_REG_CSKY_A3:
-		return "a3";
-	case PERF_REG_CSKY_REGS0:
-		return "regs0";
-	case PERF_REG_CSKY_REGS1:
-		return "regs1";
-	case PERF_REG_CSKY_REGS2:
-		return "regs2";
-	case PERF_REG_CSKY_REGS3:
-		return "regs3";
-	case PERF_REG_CSKY_REGS4:
-		return "regs4";
-	case PERF_REG_CSKY_REGS5:
-		return "regs5";
-	case PERF_REG_CSKY_REGS6:
-		return "regs6";
-	case PERF_REG_CSKY_REGS7:
-		return "regs7";
-	case PERF_REG_CSKY_REGS8:
-		return "regs8";
-	case PERF_REG_CSKY_REGS9:
-		return "regs9";
-	case PERF_REG_CSKY_SP:
-		return "sp";
-	case PERF_REG_CSKY_LR:
-		return "lr";
-	case PERF_REG_CSKY_PC:
-		return "pc";
-#if defined(__CSKYABIV2__)
-	case PERF_REG_CSKY_EXREGS0:
-		return "exregs0";
-	case PERF_REG_CSKY_EXREGS1:
-		return "exregs1";
-	case PERF_REG_CSKY_EXREGS2:
-		return "exregs2";
-	case PERF_REG_CSKY_EXREGS3:
-		return "exregs3";
-	case PERF_REG_CSKY_EXREGS4:
-		return "exregs4";
-	case PERF_REG_CSKY_EXREGS5:
-		return "exregs5";
-	case PERF_REG_CSKY_EXREGS6:
-		return "exregs6";
-	case PERF_REG_CSKY_EXREGS7:
-		return "exregs7";
-	case PERF_REG_CSKY_EXREGS8:
-		return "exregs8";
-	case PERF_REG_CSKY_EXREGS9:
-		return "exregs9";
-	case PERF_REG_CSKY_EXREGS10:
-		return "exregs10";
-	case PERF_REG_CSKY_EXREGS11:
-		return "exregs11";
-	case PERF_REG_CSKY_EXREGS12:
-		return "exregs12";
-	case PERF_REG_CSKY_EXREGS13:
-		return "exregs13";
-	case PERF_REG_CSKY_EXREGS14:
-		return "exregs14";
-	case PERF_REG_CSKY_TLS:
-		return "tls";
-	case PERF_REG_CSKY_HI:
-		return "hi";
-	case PERF_REG_CSKY_LO:
-		return "lo";
-#endif
-	default:
-		return NULL;
-	}
-
-	return NULL;
-}
-
 #endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/mips/include/perf_regs.h b/tools/perf/arch/mips/include/perf_regs.h
index ee73b36a14d1..b8cd8bbb37ba 100644
--- a/tools/perf/arch/mips/include/perf_regs.h
+++ b/tools/perf/arch/mips/include/perf_regs.h
@@ -12,73 +12,4 @@
 
 #define PERF_REGS_MASK ((1ULL << PERF_REG_MIPS_MAX) - 1)
 
-static inline const char *__perf_reg_name(int id)
-{
-	switch (id) {
-	case PERF_REG_MIPS_PC:
-		return "PC";
-	case PERF_REG_MIPS_R1:
-		return "$1";
-	case PERF_REG_MIPS_R2:
-		return "$2";
-	case PERF_REG_MIPS_R3:
-		return "$3";
-	case PERF_REG_MIPS_R4:
-		return "$4";
-	case PERF_REG_MIPS_R5:
-		return "$5";
-	case PERF_REG_MIPS_R6:
-		return "$6";
-	case PERF_REG_MIPS_R7:
-		return "$7";
-	case PERF_REG_MIPS_R8:
-		return "$8";
-	case PERF_REG_MIPS_R9:
-		return "$9";
-	case PERF_REG_MIPS_R10:
-		return "$10";
-	case PERF_REG_MIPS_R11:
-		return "$11";
-	case PERF_REG_MIPS_R12:
-		return "$12";
-	case PERF_REG_MIPS_R13:
-		return "$13";
-	case PERF_REG_MIPS_R14:
-		return "$14";
-	case PERF_REG_MIPS_R15:
-		return "$15";
-	case PERF_REG_MIPS_R16:
-		return "$16";
-	case PERF_REG_MIPS_R17:
-		return "$17";
-	case PERF_REG_MIPS_R18:
-		return "$18";
-	case PERF_REG_MIPS_R19:
-		return "$19";
-	case PERF_REG_MIPS_R20:
-		return "$20";
-	case PERF_REG_MIPS_R21:
-		return "$21";
-	case PERF_REG_MIPS_R22:
-		return "$22";
-	case PERF_REG_MIPS_R23:
-		return "$23";
-	case PERF_REG_MIPS_R24:
-		return "$24";
-	case PERF_REG_MIPS_R25:
-		return "$25";
-	case PERF_REG_MIPS_R28:
-		return "$28";
-	case PERF_REG_MIPS_R29:
-		return "$29";
-	case PERF_REG_MIPS_R30:
-		return "$30";
-	case PERF_REG_MIPS_R31:
-		return "$31";
-	default:
-		break;
-	}
-	return NULL;
-}
-
 #endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/powerpc/include/perf_regs.h b/tools/perf/arch/powerpc/include/perf_regs.h
index 93339d17acc4..9bb17c3f370b 100644
--- a/tools/perf/arch/powerpc/include/perf_regs.h
+++ b/tools/perf/arch/powerpc/include/perf_regs.h
@@ -19,70 +19,4 @@ void perf_regs_load(u64 *regs);
 #define PERF_REG_IP     PERF_REG_POWERPC_NIP
 #define PERF_REG_SP     PERF_REG_POWERPC_R1
 
-static const char *reg_names[] = {
-	[PERF_REG_POWERPC_R0] = "r0",
-	[PERF_REG_POWERPC_R1] = "r1",
-	[PERF_REG_POWERPC_R2] = "r2",
-	[PERF_REG_POWERPC_R3] = "r3",
-	[PERF_REG_POWERPC_R4] = "r4",
-	[PERF_REG_POWERPC_R5] = "r5",
-	[PERF_REG_POWERPC_R6] = "r6",
-	[PERF_REG_POWERPC_R7] = "r7",
-	[PERF_REG_POWERPC_R8] = "r8",
-	[PERF_REG_POWERPC_R9] = "r9",
-	[PERF_REG_POWERPC_R10] = "r10",
-	[PERF_REG_POWERPC_R11] = "r11",
-	[PERF_REG_POWERPC_R12] = "r12",
-	[PERF_REG_POWERPC_R13] = "r13",
-	[PERF_REG_POWERPC_R14] = "r14",
-	[PERF_REG_POWERPC_R15] = "r15",
-	[PERF_REG_POWERPC_R16] = "r16",
-	[PERF_REG_POWERPC_R17] = "r17",
-	[PERF_REG_POWERPC_R18] = "r18",
-	[PERF_REG_POWERPC_R19] = "r19",
-	[PERF_REG_POWERPC_R20] = "r20",
-	[PERF_REG_POWERPC_R21] = "r21",
-	[PERF_REG_POWERPC_R22] = "r22",
-	[PERF_REG_POWERPC_R23] = "r23",
-	[PERF_REG_POWERPC_R24] = "r24",
-	[PERF_REG_POWERPC_R25] = "r25",
-	[PERF_REG_POWERPC_R26] = "r26",
-	[PERF_REG_POWERPC_R27] = "r27",
-	[PERF_REG_POWERPC_R28] = "r28",
-	[PERF_REG_POWERPC_R29] = "r29",
-	[PERF_REG_POWERPC_R30] = "r30",
-	[PERF_REG_POWERPC_R31] = "r31",
-	[PERF_REG_POWERPC_NIP] = "nip",
-	[PERF_REG_POWERPC_MSR] = "msr",
-	[PERF_REG_POWERPC_ORIG_R3] = "orig_r3",
-	[PERF_REG_POWERPC_CTR] = "ctr",
-	[PERF_REG_POWERPC_LINK] = "link",
-	[PERF_REG_POWERPC_XER] = "xer",
-	[PERF_REG_POWERPC_CCR] = "ccr",
-	[PERF_REG_POWERPC_SOFTE] = "softe",
-	[PERF_REG_POWERPC_TRAP] = "trap",
-	[PERF_REG_POWERPC_DAR] = "dar",
-	[PERF_REG_POWERPC_DSISR] = "dsisr",
-	[PERF_REG_POWERPC_SIER] = "sier",
-	[PERF_REG_POWERPC_MMCRA] = "mmcra",
-	[PERF_REG_POWERPC_MMCR0] = "mmcr0",
-	[PERF_REG_POWERPC_MMCR1] = "mmcr1",
-	[PERF_REG_POWERPC_MMCR2] = "mmcr2",
-	[PERF_REG_POWERPC_MMCR3] = "mmcr3",
-	[PERF_REG_POWERPC_SIER2] = "sier2",
-	[PERF_REG_POWERPC_SIER3] = "sier3",
-	[PERF_REG_POWERPC_PMC1] = "pmc1",
-	[PERF_REG_POWERPC_PMC2] = "pmc2",
-	[PERF_REG_POWERPC_PMC3] = "pmc3",
-	[PERF_REG_POWERPC_PMC4] = "pmc4",
-	[PERF_REG_POWERPC_PMC5] = "pmc5",
-	[PERF_REG_POWERPC_PMC6] = "pmc6",
-	[PERF_REG_POWERPC_SDAR] = "sdar",
-	[PERF_REG_POWERPC_SIAR] = "siar",
-};
-
-static inline const char *__perf_reg_name(int id)
-{
-	return reg_names[id];
-}
 #endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/powerpc/util/event.c b/tools/perf/arch/powerpc/util/event.c
index 3bf441257466..cf430a4c55b9 100644
--- a/tools/perf/arch/powerpc/util/event.c
+++ b/tools/perf/arch/powerpc/util/event.c
@@ -40,8 +40,12 @@ const char *arch_perf_header_entry(const char *se_header)
 {
 	if (!strcmp(se_header, "Local INSTR Latency"))
 		return "Finish Cyc";
-	else if (!strcmp(se_header, "Pipeline Stage Cycle"))
+	else if (!strcmp(se_header, "INSTR Latency"))
+		return "Global Finish_cyc";
+	else if (!strcmp(se_header, "Local Pipeline Stage Cycle"))
 		return "Dispatch Cyc";
+	else if (!strcmp(se_header, "Pipeline Stage Cycle"))
+		return "Global Dispatch_cyc";
 	return se_header;
 }
 
@@ -49,5 +53,7 @@ int arch_support_sort_key(const char *sort_key)
 {
 	if (!strcmp(sort_key, "p_stage_cyc"))
 		return 1;
+	if (!strcmp(sort_key, "local_p_stage_cyc"))
+		return 1;
 	return 0;
 }
diff --git a/tools/perf/arch/riscv/include/perf_regs.h b/tools/perf/arch/riscv/include/perf_regs.h
index 6b02a767c918..6944bf0de53e 100644
--- a/tools/perf/arch/riscv/include/perf_regs.h
+++ b/tools/perf/arch/riscv/include/perf_regs.h
@@ -19,78 +19,4 @@
 #define PERF_REG_IP	PERF_REG_RISCV_PC
 #define PERF_REG_SP	PERF_REG_RISCV_SP
 
-static inline const char *__perf_reg_name(int id)
-{
-	switch (id) {
-	case PERF_REG_RISCV_PC:
-		return "pc";
-	case PERF_REG_RISCV_RA:
-		return "ra";
-	case PERF_REG_RISCV_SP:
-		return "sp";
-	case PERF_REG_RISCV_GP:
-		return "gp";
-	case PERF_REG_RISCV_TP:
-		return "tp";
-	case PERF_REG_RISCV_T0:
-		return "t0";
-	case PERF_REG_RISCV_T1:
-		return "t1";
-	case PERF_REG_RISCV_T2:
-		return "t2";
-	case PERF_REG_RISCV_S0:
-		return "s0";
-	case PERF_REG_RISCV_S1:
-		return "s1";
-	case PERF_REG_RISCV_A0:
-		return "a0";
-	case PERF_REG_RISCV_A1:
-		return "a1";
-	case PERF_REG_RISCV_A2:
-		return "a2";
-	case PERF_REG_RISCV_A3:
-		return "a3";
-	case PERF_REG_RISCV_A4:
-		return "a4";
-	case PERF_REG_RISCV_A5:
-		return "a5";
-	case PERF_REG_RISCV_A6:
-		return "a6";
-	case PERF_REG_RISCV_A7:
-		return "a7";
-	case PERF_REG_RISCV_S2:
-		return "s2";
-	case PERF_REG_RISCV_S3:
-		return "s3";
-	case PERF_REG_RISCV_S4:
-		return "s4";
-	case PERF_REG_RISCV_S5:
-		return "s5";
-	case PERF_REG_RISCV_S6:
-		return "s6";
-	case PERF_REG_RISCV_S7:
-		return "s7";
-	case PERF_REG_RISCV_S8:
-		return "s8";
-	case PERF_REG_RISCV_S9:
-		return "s9";
-	case PERF_REG_RISCV_S10:
-		return "s10";
-	case PERF_REG_RISCV_S11:
-		return "s11";
-	case PERF_REG_RISCV_T3:
-		return "t3";
-	case PERF_REG_RISCV_T4:
-		return "t4";
-	case PERF_REG_RISCV_T5:
-		return "t5";
-	case PERF_REG_RISCV_T6:
-		return "t6";
-	default:
-		return NULL;
-	}
-
-	return NULL;
-}
-
 #endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/s390/include/perf_regs.h b/tools/perf/arch/s390/include/perf_regs.h
index ce3031526623..52fcc0891da6 100644
--- a/tools/perf/arch/s390/include/perf_regs.h
+++ b/tools/perf/arch/s390/include/perf_regs.h
@@ -14,82 +14,4 @@ void perf_regs_load(u64 *regs);
 #define PERF_REG_IP PERF_REG_S390_PC
 #define PERF_REG_SP PERF_REG_S390_R15
 
-static inline const char *__perf_reg_name(int id)
-{
-	switch (id) {
-	case PERF_REG_S390_R0:
-		return "R0";
-	case PERF_REG_S390_R1:
-		return "R1";
-	case PERF_REG_S390_R2:
-		return "R2";
-	case PERF_REG_S390_R3:
-		return "R3";
-	case PERF_REG_S390_R4:
-		return "R4";
-	case PERF_REG_S390_R5:
-		return "R5";
-	case PERF_REG_S390_R6:
-		return "R6";
-	case PERF_REG_S390_R7:
-		return "R7";
-	case PERF_REG_S390_R8:
-		return "R8";
-	case PERF_REG_S390_R9:
-		return "R9";
-	case PERF_REG_S390_R10:
-		return "R10";
-	case PERF_REG_S390_R11:
-		return "R11";
-	case PERF_REG_S390_R12:
-		return "R12";
-	case PERF_REG_S390_R13:
-		return "R13";
-	case PERF_REG_S390_R14:
-		return "R14";
-	case PERF_REG_S390_R15:
-		return "R15";
-	case PERF_REG_S390_FP0:
-		return "FP0";
-	case PERF_REG_S390_FP1:
-		return "FP1";
-	case PERF_REG_S390_FP2:
-		return "FP2";
-	case PERF_REG_S390_FP3:
-		return "FP3";
-	case PERF_REG_S390_FP4:
-		return "FP4";
-	case PERF_REG_S390_FP5:
-		return "FP5";
-	case PERF_REG_S390_FP6:
-		return "FP6";
-	case PERF_REG_S390_FP7:
-		return "FP7";
-	case PERF_REG_S390_FP8:
-		return "FP8";
-	case PERF_REG_S390_FP9:
-		return "FP9";
-	case PERF_REG_S390_FP10:
-		return "FP10";
-	case PERF_REG_S390_FP11:
-		return "FP11";
-	case PERF_REG_S390_FP12:
-		return "FP12";
-	case PERF_REG_S390_FP13:
-		return "FP13";
-	case PERF_REG_S390_FP14:
-		return "FP14";
-	case PERF_REG_S390_FP15:
-		return "FP15";
-	case PERF_REG_S390_MASK:
-		return "MASK";
-	case PERF_REG_S390_PC:
-		return "PC";
-	default:
-		return NULL;
-	}
-
-	return NULL;
-}
-
 #endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h
index cddc4cdc0d9b..16e23b722042 100644
--- a/tools/perf/arch/x86/include/perf_regs.h
+++ b/tools/perf/arch/x86/include/perf_regs.h
@@ -23,86 +23,4 @@ void perf_regs_load(u64 *regs);
 #define PERF_REG_IP PERF_REG_X86_IP
 #define PERF_REG_SP PERF_REG_X86_SP
 
-static inline const char *__perf_reg_name(int id)
-{
-	switch (id) {
-	case PERF_REG_X86_AX:
-		return "AX";
-	case PERF_REG_X86_BX:
-		return "BX";
-	case PERF_REG_X86_CX:
-		return "CX";
-	case PERF_REG_X86_DX:
-		return "DX";
-	case PERF_REG_X86_SI:
-		return "SI";
-	case PERF_REG_X86_DI:
-		return "DI";
-	case PERF_REG_X86_BP:
-		return "BP";
-	case PERF_REG_X86_SP:
-		return "SP";
-	case PERF_REG_X86_IP:
-		return "IP";
-	case PERF_REG_X86_FLAGS:
-		return "FLAGS";
-	case PERF_REG_X86_CS:
-		return "CS";
-	case PERF_REG_X86_SS:
-		return "SS";
-	case PERF_REG_X86_DS:
-		return "DS";
-	case PERF_REG_X86_ES:
-		return "ES";
-	case PERF_REG_X86_FS:
-		return "FS";
-	case PERF_REG_X86_GS:
-		return "GS";
-#ifdef HAVE_ARCH_X86_64_SUPPORT
-	case PERF_REG_X86_R8:
-		return "R8";
-	case PERF_REG_X86_R9:
-		return "R9";
-	case PERF_REG_X86_R10:
-		return "R10";
-	case PERF_REG_X86_R11:
-		return "R11";
-	case PERF_REG_X86_R12:
-		return "R12";
-	case PERF_REG_X86_R13:
-		return "R13";
-	case PERF_REG_X86_R14:
-		return "R14";
-	case PERF_REG_X86_R15:
-		return "R15";
-#endif /* HAVE_ARCH_X86_64_SUPPORT */
-
-#define XMM(x) \
-	case PERF_REG_X86_XMM ## x:	\
-	case PERF_REG_X86_XMM ## x + 1:	\
-		return "XMM" #x;
-	XMM(0)
-	XMM(1)
-	XMM(2)
-	XMM(3)
-	XMM(4)
-	XMM(5)
-	XMM(6)
-	XMM(7)
-	XMM(8)
-	XMM(9)
-	XMM(10)
-	XMM(11)
-	XMM(12)
-	XMM(13)
-	XMM(14)
-	XMM(15)
-#undef XMM
-	default:
-		return NULL;
-	}
-
-	return NULL;
-}
-
 #endif /* ARCH_PERF_REGS_H */
diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
index 0b0951030a2f..f924246eff78 100644
--- a/tools/perf/arch/x86/util/evlist.c
+++ b/tools/perf/arch/x86/util/evlist.c
@@ -17,3 +17,20 @@ int arch_evlist__add_default_attrs(struct evlist *evlist)
 	else
 		return parse_events(evlist, TOPDOWN_L1_EVENTS, NULL);
 }
+
+struct evsel *arch_evlist__leader(struct list_head *list)
+{
+	struct evsel *evsel, *first;
+
+	first = list_first_entry(list, struct evsel, core.node);
+
+	if (!pmu_have_event("cpu", "slots"))
+		return first;
+
+	__evlist__for_each_entry(list, evsel) {
+		if (evsel->pmu_name && !strcmp(evsel->pmu_name, "cpu") &&
+			evsel->name && strstr(evsel->name, "slots"))
+			return evsel;
+	}
+	return first;
+}
diff --git a/tools/perf/bench/epoll-ctl.c b/tools/perf/bench/epoll-ctl.c
index ddaca75c3bc0..1a17ec83d3c4 100644
--- a/tools/perf/bench/epoll-ctl.c
+++ b/tools/perf/bench/epoll-ctl.c
@@ -253,7 +253,7 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
 
 		if (!noaffinity) {
 			CPU_ZERO(&cpuset);
-			CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+			CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
 
 			ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
 			if (ret)
diff --git a/tools/perf/bench/epoll-wait.c b/tools/perf/bench/epoll-wait.c
index 79d13dbc0a47..0d1dd8879197 100644
--- a/tools/perf/bench/epoll-wait.c
+++ b/tools/perf/bench/epoll-wait.c
@@ -342,7 +342,7 @@ static int do_threads(struct worker *worker, struct perf_cpu_map *cpu)
 
 		if (!noaffinity) {
 			CPU_ZERO(&cpuset);
-			CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+			CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
 
 			ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
 			if (ret)
diff --git a/tools/perf/bench/futex-hash.c b/tools/perf/bench/futex-hash.c
index fcdea3e44937..9627b6ab8670 100644
--- a/tools/perf/bench/futex-hash.c
+++ b/tools/perf/bench/futex-hash.c
@@ -177,7 +177,7 @@ int bench_futex_hash(int argc, const char **argv)
 			goto errmem;
 
 		CPU_ZERO(&cpuset);
-		CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+		CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
 
 		ret = pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset);
 		if (ret)
diff --git a/tools/perf/bench/futex-lock-pi.c b/tools/perf/bench/futex-lock-pi.c
index 137890f78e17..a512a320df74 100644
--- a/tools/perf/bench/futex-lock-pi.c
+++ b/tools/perf/bench/futex-lock-pi.c
@@ -136,7 +136,7 @@ static void create_threads(struct worker *w, pthread_attr_t thread_attr,
 			worker[i].futex = &global_futex;
 
 		CPU_ZERO(&cpuset);
-		CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+		CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
 
 		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
diff --git a/tools/perf/bench/futex-requeue.c b/tools/perf/bench/futex-requeue.c
index f7a5ffebb940..aca47ce8b1e7 100644
--- a/tools/perf/bench/futex-requeue.c
+++ b/tools/perf/bench/futex-requeue.c
@@ -131,7 +131,7 @@ static void block_threads(pthread_t *w,
 	/* create and block all threads */
 	for (i = 0; i < params.nthreads; i++) {
 		CPU_ZERO(&cpuset);
-		CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+		CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
 
 		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
diff --git a/tools/perf/bench/futex-wake-parallel.c b/tools/perf/bench/futex-wake-parallel.c
index 0983f40b4b40..888ee6037945 100644
--- a/tools/perf/bench/futex-wake-parallel.c
+++ b/tools/perf/bench/futex-wake-parallel.c
@@ -152,7 +152,7 @@ static void block_threads(pthread_t *w, pthread_attr_t thread_attr,
 	/* create and block all threads */
 	for (i = 0; i < params.nthreads; i++) {
 		CPU_ZERO(&cpuset);
-		CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+		CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
 
 		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
diff --git a/tools/perf/bench/futex-wake.c b/tools/perf/bench/futex-wake.c
index 2226a475e782..aa82db51c0ab 100644
--- a/tools/perf/bench/futex-wake.c
+++ b/tools/perf/bench/futex-wake.c
@@ -105,7 +105,7 @@ static void block_threads(pthread_t *w,
 	/* create and block all threads */
 	for (i = 0; i < params.nthreads; i++) {
 		CPU_ZERO(&cpuset);
-		CPU_SET(cpu->map[i % cpu->nr], &cpuset);
+		CPU_SET(perf_cpu_map__cpu(cpu, i % perf_cpu_map__nr(cpu)).cpu, &cpuset);
 
 		if (pthread_attr_setaffinity_np(&thread_attr, sizeof(cpu_set_t), &cpuset))
 			err(EXIT_FAILURE, "pthread_attr_setaffinity_np");
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index d0895162c2ba..d291f3a8af5f 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -226,7 +226,6 @@ static void run_collection(struct collection *coll)
 		if (!bench->fn)
 			break;
 		printf("# Running %s/%s benchmark...\n", coll->name, bench->name);
-		fflush(stdout);
 
 		argv[1] = bench->name;
 		run_bench(coll->name, bench->name, bench->fn, 1, argv);
@@ -247,6 +246,9 @@ int cmd_bench(int argc, const char **argv)
 	struct collection *coll;
 	int ret = 0;
 
+	/* Unbuffered output */
+	setvbuf(stdout, NULL, _IONBF, 0);
+
 	if (argc < 2) {
 		/* No collection specified. */
 		print_usage();
@@ -300,7 +302,6 @@ int cmd_bench(int argc, const char **argv)
 
 			if (bench_format == BENCH_FORMAT_DEFAULT)
 				printf("# Running '%s/%s' benchmark:\n", coll->name, bench->name);
-			fflush(stdout);
 			ret = run_bench(coll->name, bench->name, bench->fn, argc-1, argv+1);
 			goto end;
 		}
diff --git a/tools/perf/builtin-buildid-cache.c b/tools/perf/builtin-buildid-cache.c
index 0db3cfc04c47..cd381693658b 100644
--- a/tools/perf/builtin-buildid-cache.c
+++ b/tools/perf/builtin-buildid-cache.c
@@ -351,10 +351,14 @@ static int build_id_cache__show_all(void)
 
 static int perf_buildid_cache_config(const char *var, const char *value, void *cb)
 {
-	const char **debuginfod = cb;
+	struct perf_debuginfod *di = cb;
 
-	if (!strcmp(var, "buildid-cache.debuginfod"))
-		*debuginfod = strdup(value);
+	if (!strcmp(var, "buildid-cache.debuginfod")) {
+		di->urls = strdup(value);
+		if (!di->urls)
+			return -ENOMEM;
+		di->set = true;
+	}
 
 	return 0;
 }
@@ -373,8 +377,8 @@ int cmd_buildid_cache(int argc, const char **argv)
 		   *purge_name_list_str = NULL,
 		   *missing_filename = NULL,
 		   *update_name_list_str = NULL,
-		   *kcore_filename = NULL,
-		   *debuginfod = NULL;
+		   *kcore_filename = NULL;
+	struct perf_debuginfod debuginfod = { };
 	char sbuf[STRERR_BUFSIZE];
 
 	struct perf_data data = {
@@ -399,8 +403,10 @@ int cmd_buildid_cache(int argc, const char **argv)
 	OPT_BOOLEAN('f', "force", &force, "don't complain, do it"),
 	OPT_STRING('u', "update", &update_name_list_str, "file list",
 		    "file(s) to update"),
-	OPT_STRING(0, "debuginfod", &debuginfod, "debuginfod url",
-		    "set debuginfod url"),
+	OPT_STRING_OPTARG_SET(0, "debuginfod", &debuginfod.urls,
+			&debuginfod.set, "debuginfod urls",
+			"Enable debuginfod data retrieval from DEBUGINFOD_URLS or specified urls",
+			"system"),
 	OPT_INCR('v', "verbose", &verbose, "be more verbose"),
 	OPT_INTEGER(0, "target-ns", &ns_id, "target pid for namespace context"),
 	OPT_END()
@@ -425,10 +431,7 @@ int cmd_buildid_cache(int argc, const char **argv)
 	if (argc || !(list_files || opts_flag))
 		usage_with_options(buildid_cache_usage, buildid_cache_options);
 
-	if (debuginfod) {
-		pr_debug("DEBUGINFOD_URLS=%s\n", debuginfod);
-		setenv("DEBUGINFOD_URLS", debuginfod, 1);
-	}
+	perf_debuginfod_setup(&debuginfod);
 
 	/* -l is exclusive. It can not be used with other options. */
 	if (list_files && opts_flag) {
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index b5c67ef73862..77dd4afacca4 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2015,7 +2015,8 @@ static int setup_nodes(struct perf_session *session)
 {
 	struct numa_node *n;
 	unsigned long **nodes;
-	int node, cpu;
+	int node, idx;
+	struct perf_cpu cpu;
 	int *cpu2node;
 
 	if (c2c.node_info > 2)
@@ -2038,8 +2039,8 @@ static int setup_nodes(struct perf_session *session)
 	if (!cpu2node)
 		return -ENOMEM;
 
-	for (cpu = 0; cpu < c2c.cpus_cnt; cpu++)
-		cpu2node[cpu] = -1;
+	for (idx = 0; idx < c2c.cpus_cnt; idx++)
+		cpu2node[idx] = -1;
 
 	c2c.cpu2node = cpu2node;
 
@@ -2057,13 +2058,13 @@ static int setup_nodes(struct perf_session *session)
 		if (perf_cpu_map__empty(map))
 			continue;
 
-		for (cpu = 0; cpu < map->nr; cpu++) {
-			set_bit(map->map[cpu], set);
+		perf_cpu_map__for_each_cpu(cpu, idx, map) {
+			set_bit(cpu.cpu, set);
 
-			if (WARN_ONCE(cpu2node[map->map[cpu]] != -1, "node/cpu topology bug"))
+			if (WARN_ONCE(cpu2node[cpu.cpu] != -1, "node/cpu topology bug"))
 				return -EINVAL;
 
-			cpu2node[map->map[cpu]] = node;
+			cpu2node[cpu.cpu] = node;
 		}
 	}
 
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 87cb11a7a3ee..71452599f87d 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -13,7 +13,9 @@
 #include <signal.h>
 #include <stdlib.h>
 #include <fcntl.h>
+#include <math.h>
 #include <poll.h>
+#include <ctype.h>
 #include <linux/capability.h>
 #include <linux/string.h>
 
@@ -28,36 +30,12 @@
 #include "strfilter.h"
 #include "util/cap.h"
 #include "util/config.h"
+#include "util/ftrace.h"
 #include "util/units.h"
 #include "util/parse-sublevel-options.h"
 
 #define DEFAULT_TRACER  "function_graph"
 
-struct perf_ftrace {
-	struct evlist		*evlist;
-	struct target		target;
-	const char		*tracer;
-	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 {
-	struct list_head	list;
-	char			name[];
-};
-
 static volatile int workload_exec_errno;
 static bool done;
 
@@ -303,7 +281,7 @@ static int set_tracing_cpumask(struct perf_cpu_map *cpumap)
 	int ret;
 	int last_cpu;
 
-	last_cpu = cpu_map__cpu(cpumap, cpumap->nr - 1);
+	last_cpu = perf_cpu_map__cpu(cpumap, cpumap->nr - 1).cpu;
 	mask_size = last_cpu / 4 + 2; /* one more byte for EOS */
 	mask_size += last_cpu / 32; /* ',' is needed for every 32th cpus */
 
@@ -565,7 +543,24 @@ static int set_tracing_options(struct perf_ftrace *ftrace)
 	return 0;
 }
 
-static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
+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);
+}
+
+static int __cmd_ftrace(struct perf_ftrace *ftrace)
 {
 	char *trace_file;
 	int trace_fd;
@@ -586,10 +581,7 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
 		return -1;
 	}
 
-	signal(SIGINT, sig_handler);
-	signal(SIGUSR1, sig_handler);
-	signal(SIGCHLD, sig_handler);
-	signal(SIGPIPE, sig_handler);
+	select_tracer(ftrace);
 
 	if (reset_tracing_files(ftrace) < 0) {
 		pr_err("failed to reset ftrace\n");
@@ -600,11 +592,6 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
 	if (write_tracing_file("trace", "0") < 0)
 		goto out;
 
-	if (argc && evlist__prepare_workload(ftrace->evlist, &ftrace->target, argv, false,
-					     ftrace__workload_exec_failed_signal) < 0) {
-		goto out;
-	}
-
 	if (set_tracing_options(ftrace) < 0)
 		goto out_reset;
 
@@ -693,6 +680,270 @@ out:
 	return (done && !workload_exec_errno) ? 0 : -1;
 }
 
+static void make_histogram(int buckets[], char *buf, size_t len, char *linebuf)
+{
+	char *p, *q;
+	char *unit;
+	double num;
+	int i;
+
+	/* ensure NUL termination */
+	buf[len] = '\0';
+
+	/* handle data line by line */
+	for (p = buf; (q = strchr(p, '\n')) != NULL; p = q + 1) {
+		*q = '\0';
+		/* move it to the line buffer */
+		strcat(linebuf, p);
+
+		/*
+		 * parse trace output to get function duration like in
+		 *
+		 * # tracer: function_graph
+		 * #
+		 * # CPU  DURATION                  FUNCTION CALLS
+		 * # |     |   |                     |   |   |   |
+		 *  1) + 10.291 us   |  do_filp_open();
+		 *  1)   4.889 us    |  do_filp_open();
+		 *  1)   6.086 us    |  do_filp_open();
+		 *
+		 */
+		if (linebuf[0] == '#')
+			goto next;
+
+		/* ignore CPU */
+		p = strchr(linebuf, ')');
+		if (p == NULL)
+			p = linebuf;
+
+		while (*p && !isdigit(*p) && (*p != '|'))
+			p++;
+
+		/* no duration */
+		if (*p == '\0' || *p == '|')
+			goto next;
+
+		num = strtod(p, &unit);
+		if (!unit || strncmp(unit, " us", 3))
+			goto next;
+
+		i = log2(num);
+		if (i < 0)
+			i = 0;
+		if (i >= NUM_BUCKET)
+			i = NUM_BUCKET - 1;
+
+		buckets[i]++;
+
+next:
+		/* empty the line buffer for the next output  */
+		linebuf[0] = '\0';
+	}
+
+	/* preserve any remaining output (before newline) */
+	strcat(linebuf, p);
+}
+
+static void display_histogram(int buckets[])
+{
+	int i;
+	int total = 0;
+	int bar_total = 46;  /* to fit in 80 column */
+	char bar[] = "###############################################";
+	int bar_len;
+
+	for (i = 0; i < NUM_BUCKET; i++)
+		total += buckets[i];
+
+	if (total == 0) {
+		printf("No data found\n");
+		return;
+	}
+
+	printf("# %14s | %10s | %-*s |\n",
+	       "  DURATION    ", "COUNT", bar_total, "GRAPH");
+
+	bar_len = buckets[0] * bar_total / total;
+	printf("  %4d - %-4d %s | %10d | %.*s%*s |\n",
+	       0, 1, "us", buckets[0], bar_len, bar, bar_total - bar_len, "");
+
+	for (i = 1; i < NUM_BUCKET - 1; i++) {
+		int start = (1 << (i - 1));
+		int stop = 1 << i;
+		const char *unit = "us";
+
+		if (start >= 1024) {
+			start >>= 10;
+			stop >>= 10;
+			unit = "ms";
+		}
+		bar_len = buckets[i] * bar_total / total;
+		printf("  %4d - %-4d %s | %10d | %.*s%*s |\n",
+		       start, stop, unit, buckets[i], bar_len, bar,
+		       bar_total - bar_len, "");
+	}
+
+	bar_len = buckets[NUM_BUCKET - 1] * bar_total / total;
+	printf("  %4d - %-4s %s | %10d | %.*s%*s |\n",
+	       1, "...", " s", buckets[NUM_BUCKET - 1], bar_len, bar,
+	       bar_total - bar_len, "");
+
+}
+
+static int prepare_func_latency(struct perf_ftrace *ftrace)
+{
+	char *trace_file;
+	int fd;
+
+	if (ftrace->target.use_bpf)
+		return perf_ftrace__latency_prepare_bpf(ftrace);
+
+	if (reset_tracing_files(ftrace) < 0) {
+		pr_err("failed to reset ftrace\n");
+		return -1;
+	}
+
+	/* reset ftrace buffer */
+	if (write_tracing_file("trace", "0") < 0)
+		return -1;
+
+	if (set_tracing_options(ftrace) < 0)
+		return -1;
+
+	/* force to use the function_graph tracer to track duration */
+	if (write_tracing_file("current_tracer", "function_graph") < 0) {
+		pr_err("failed to set current_tracer to function_graph\n");
+		return -1;
+	}
+
+	trace_file = get_tracing_file("trace_pipe");
+	if (!trace_file) {
+		pr_err("failed to open trace_pipe\n");
+		return -1;
+	}
+
+	fd = open(trace_file, O_RDONLY);
+	if (fd < 0)
+		pr_err("failed to open trace_pipe\n");
+
+	put_tracing_file(trace_file);
+	return fd;
+}
+
+static int start_func_latency(struct perf_ftrace *ftrace)
+{
+	if (ftrace->target.use_bpf)
+		return perf_ftrace__latency_start_bpf(ftrace);
+
+	if (write_tracing_file("tracing_on", "1") < 0) {
+		pr_err("can't enable tracing\n");
+		return -1;
+	}
+
+	return 0;
+}
+
+static int stop_func_latency(struct perf_ftrace *ftrace)
+{
+	if (ftrace->target.use_bpf)
+		return perf_ftrace__latency_stop_bpf(ftrace);
+
+	write_tracing_file("tracing_on", "0");
+	return 0;
+}
+
+static int read_func_latency(struct perf_ftrace *ftrace, int buckets[])
+{
+	if (ftrace->target.use_bpf)
+		return perf_ftrace__latency_read_bpf(ftrace, buckets);
+
+	return 0;
+}
+
+static int cleanup_func_latency(struct perf_ftrace *ftrace)
+{
+	if (ftrace->target.use_bpf)
+		return perf_ftrace__latency_cleanup_bpf(ftrace);
+
+	reset_tracing_files(ftrace);
+	return 0;
+}
+
+static int __cmd_latency(struct perf_ftrace *ftrace)
+{
+	int trace_fd;
+	char buf[4096];
+	char line[256];
+	struct pollfd pollfd = {
+		.events = POLLIN,
+	};
+	int buckets[NUM_BUCKET] = { };
+
+	if (!(perf_cap__capable(CAP_PERFMON) ||
+	      perf_cap__capable(CAP_SYS_ADMIN))) {
+		pr_err("ftrace only works for %s!\n",
+#ifdef HAVE_LIBCAP_SUPPORT
+		"users with the CAP_PERFMON or CAP_SYS_ADMIN capability"
+#else
+		"root"
+#endif
+		);
+		return -1;
+	}
+
+	trace_fd = prepare_func_latency(ftrace);
+	if (trace_fd < 0)
+		goto out;
+
+	fcntl(trace_fd, F_SETFL, O_NONBLOCK);
+	pollfd.fd = trace_fd;
+
+	if (start_func_latency(ftrace) < 0)
+		goto out;
+
+	evlist__start_workload(ftrace->evlist);
+
+	line[0] = '\0';
+	while (!done) {
+		if (poll(&pollfd, 1, -1) < 0)
+			break;
+
+		if (pollfd.revents & POLLIN) {
+			int n = read(trace_fd, buf, sizeof(buf) - 1);
+			if (n < 0)
+				break;
+
+			make_histogram(buckets, buf, n, line);
+		}
+	}
+
+	stop_func_latency(ftrace);
+
+	if (workload_exec_errno) {
+		const char *emsg = str_error_r(workload_exec_errno, buf, sizeof(buf));
+		pr_err("workload failed: %s\n", emsg);
+		goto out;
+	}
+
+	/* read remaining buffer contents */
+	while (!ftrace->target.use_bpf) {
+		int n = read(trace_fd, buf, sizeof(buf) - 1);
+		if (n <= 0)
+			break;
+		make_histogram(buckets, buf, n, line);
+	}
+
+	read_func_latency(ftrace, buckets);
+
+	display_histogram(buckets);
+
+out:
+	close(trace_fd);
+	cleanup_func_latency(ftrace);
+
+	return (done && !workload_exec_errno) ? 0 : -1;
+}
+
 static int perf_ftrace_config(const char *var, const char *value, void *cb)
 {
 	struct perf_ftrace *ftrace = cb;
@@ -855,22 +1106,11 @@ static int parse_graph_tracer_opts(const struct option *opt,
 	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);
-}
+enum perf_ftrace_subcommand {
+	PERF_FTRACE_NONE,
+	PERF_FTRACE_TRACE,
+	PERF_FTRACE_LATENCY,
+};
 
 int cmd_ftrace(int argc, const char **argv)
 {
@@ -879,17 +1119,7 @@ int cmd_ftrace(int argc, const char **argv)
 		.tracer = DEFAULT_TRACER,
 		.target = { .uid = UINT_MAX, },
 	};
-	const char * const ftrace_usage[] = {
-		"perf ftrace [<options>] [<command>]",
-		"perf ftrace [<options>] -- <command> [<options>]",
-		NULL
-	};
-	const struct option ftrace_options[] = {
-	OPT_STRING('t', "tracer", &ftrace.tracer, "tracer",
-		   "Tracer to use: function_graph(default) or function"),
-	OPT_CALLBACK_DEFAULT('F', "funcs", NULL, "[FILTER]",
-			     "Show available functions to filter",
-			     opt_list_avail_functions, "*"),
+	const struct option common_options[] = {
 	OPT_STRING('p', "pid", &ftrace.target.pid, "pid",
 		   "Trace on existing process id"),
 	/* TODO: Add short option -t after -t/--tracer can be removed. */
@@ -901,6 +1131,14 @@ int cmd_ftrace(int argc, const char **argv)
 		    "System-wide collection from all CPUs"),
 	OPT_STRING('C', "cpu", &ftrace.target.cpu_list, "cpu",
 		    "List of cpus to monitor"),
+	OPT_END()
+	};
+	const struct option ftrace_options[] = {
+	OPT_STRING('t', "tracer", &ftrace.tracer, "tracer",
+		   "Tracer to use: function_graph(default) or function"),
+	OPT_CALLBACK_DEFAULT('F', "funcs", NULL, "[FILTER]",
+			     "Show available functions to filter",
+			     opt_list_avail_functions, "*"),
 	OPT_CALLBACK('T', "trace-funcs", &ftrace.filters, "func",
 		     "Trace given functions using function tracer",
 		     parse_filter_func),
@@ -923,24 +1161,65 @@ int cmd_ftrace(int argc, const char **argv)
 		    "Trace children processes"),
 	OPT_UINTEGER('D', "delay", &ftrace.initial_delay,
 		     "Number of milliseconds to wait before starting tracing after program start"),
-	OPT_END()
+	OPT_PARENT(common_options),
+	};
+	const struct option latency_options[] = {
+	OPT_CALLBACK('T', "trace-funcs", &ftrace.filters, "func",
+		     "Show latency of given function", parse_filter_func),
+#ifdef HAVE_BPF_SKEL
+	OPT_BOOLEAN('b', "use-bpf", &ftrace.target.use_bpf,
+		    "Use BPF to measure function latency"),
+#endif
+	OPT_PARENT(common_options),
+	};
+	const struct option *options = ftrace_options;
+
+	const char * const ftrace_usage[] = {
+		"perf ftrace [<options>] [<command>]",
+		"perf ftrace [<options>] -- [<command>] [<options>]",
+		"perf ftrace {trace|latency} [<options>] [<command>]",
+		"perf ftrace {trace|latency} [<options>] -- [<command>] [<options>]",
+		NULL
 	};
+	enum perf_ftrace_subcommand subcmd = PERF_FTRACE_NONE;
 
 	INIT_LIST_HEAD(&ftrace.filters);
 	INIT_LIST_HEAD(&ftrace.notrace);
 	INIT_LIST_HEAD(&ftrace.graph_funcs);
 	INIT_LIST_HEAD(&ftrace.nograph_funcs);
 
+	signal(SIGINT, sig_handler);
+	signal(SIGUSR1, sig_handler);
+	signal(SIGCHLD, sig_handler);
+	signal(SIGPIPE, sig_handler);
+
 	ret = perf_config(perf_ftrace_config, &ftrace);
 	if (ret < 0)
 		return -1;
 
-	argc = parse_options(argc, argv, ftrace_options, ftrace_usage,
-			    PARSE_OPT_STOP_AT_NON_OPTION);
-	if (!argc && target__none(&ftrace.target))
-		ftrace.target.system_wide = true;
+	if (argc > 1) {
+		if (!strcmp(argv[1], "trace")) {
+			subcmd = PERF_FTRACE_TRACE;
+		} else if (!strcmp(argv[1], "latency")) {
+			subcmd = PERF_FTRACE_LATENCY;
+			options = latency_options;
+		}
+
+		if (subcmd != PERF_FTRACE_NONE) {
+			argc--;
+			argv++;
+		}
+	}
+	/* for backward compatibility */
+	if (subcmd == PERF_FTRACE_NONE)
+		subcmd = PERF_FTRACE_TRACE;
 
-	select_tracer(&ftrace);
+	argc = parse_options(argc, argv, options, ftrace_usage,
+			    PARSE_OPT_STOP_AT_NON_OPTION);
+	if (argc < 0) {
+		ret = -EINVAL;
+		goto out_delete_filters;
+	}
 
 	ret = target__validate(&ftrace.target);
 	if (ret) {
@@ -961,7 +1240,35 @@ int cmd_ftrace(int argc, const char **argv)
 	if (ret < 0)
 		goto out_delete_evlist;
 
-	ret = __cmd_ftrace(&ftrace, argc, argv);
+	if (argc) {
+		ret = evlist__prepare_workload(ftrace.evlist, &ftrace.target,
+					       argv, false,
+					       ftrace__workload_exec_failed_signal);
+		if (ret < 0)
+			goto out_delete_evlist;
+	}
+
+	switch (subcmd) {
+	case PERF_FTRACE_TRACE:
+		if (!argc && target__none(&ftrace.target))
+			ftrace.target.system_wide = true;
+		ret = __cmd_ftrace(&ftrace);
+		break;
+	case PERF_FTRACE_LATENCY:
+		if (list_empty(&ftrace.filters)) {
+			pr_err("Should provide a function to measure\n");
+			parse_options_usage(ftrace_usage, options, "T", 1);
+			ret = -EINVAL;
+			goto out_delete_evlist;
+		}
+		ret = __cmd_latency(&ftrace);
+		break;
+	case PERF_FTRACE_NONE:
+	default:
+		pr_err("Invalid subcommand\n");
+		ret = -EINVAL;
+		break;
+	}
 
 out_delete_evlist:
 	evlist__delete(ftrace.evlist);
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index da03a341c63c..99d7ff9a8eff 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -192,7 +192,7 @@ static int evsel__process_alloc_node_event(struct evsel *evsel, struct perf_samp
 	int ret = evsel__process_alloc_event(evsel, sample);
 
 	if (!ret) {
-		int node1 = cpu__get_node(sample->cpu),
+		int node1 = cpu__get_node((struct perf_cpu){.cpu = sample->cpu}),
 		    node2 = evsel__intval(evsel, sample, "node");
 
 		if (node1 != node2)
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index 0338b813585a..bb716c953d02 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -111,6 +111,7 @@ struct record {
 	unsigned long long	samples;
 	struct mmap_cpu_mask	affinity_mask;
 	unsigned long		output_max_size;	/* = 0: unlimited */
+	struct perf_debuginfod	debuginfod;
 };
 
 static volatile int done;
@@ -2177,6 +2178,12 @@ static int perf_record_config(const char *var, const char *value, void *cb)
 			rec->opts.nr_cblocks = nr_cblocks_default;
 	}
 #endif
+	if (!strcmp(var, "record.debuginfod")) {
+		rec->debuginfod.urls = strdup(value);
+		if (!rec->debuginfod.urls)
+			return -ENOMEM;
+		rec->debuginfod.set = true;
+	}
 
 	return 0;
 }
@@ -2267,6 +2274,10 @@ out_free:
 	return ret;
 }
 
+void __weak arch__add_leaf_frame_record_opts(struct record_opts *opts __maybe_unused)
+{
+}
+
 static int parse_control_option(const struct option *opt,
 				const char *str,
 				int unset __maybe_unused)
@@ -2663,6 +2674,10 @@ static struct option __record_options[] = {
 		      parse_control_option),
 	OPT_CALLBACK(0, "synth", &record.opts, "no|all|task|mmap|cgroup",
 		     "Fine-tune event synthesis: default=all", parse_record_synth_option),
+	OPT_STRING_OPTARG_SET(0, "debuginfod", &record.debuginfod.urls,
+			  &record.debuginfod.set, "debuginfod urls",
+			  "Enable debuginfod data retrieval from DEBUGINFOD_URLS or specified urls",
+			  "system"),
 	OPT_END()
 };
 
@@ -2716,6 +2731,8 @@ int cmd_record(int argc, const char **argv)
 	if (err)
 		return err;
 
+	perf_debuginfod_setup(&record.debuginfod);
+
 	/* Make system wide (-a) the default target. */
 	if (!argc && target__none(&rec->opts.target))
 		rec->opts.target.system_wide = true;
@@ -2792,7 +2809,7 @@ int cmd_record(int argc, const char **argv)
 	symbol__init(NULL);
 
 	if (rec->opts.affinity != PERF_AFFINITY_SYS) {
-		rec->affinity_mask.nbits = cpu__max_cpu();
+		rec->affinity_mask.nbits = cpu__max_cpu().cpu;
 		rec->affinity_mask.bits = bitmap_zalloc(rec->affinity_mask.nbits);
 		if (!rec->affinity_mask.bits) {
 			pr_err("Failed to allocate thread mask for %zd cpus\n", rec->affinity_mask.nbits);
@@ -2898,6 +2915,10 @@ int cmd_record(int argc, const char **argv)
 	}
 
 	rec->opts.target.hybrid = perf_pmu__has_hybrid();
+
+	if (callchain_param.enabled && callchain_param.record_mode == CALLCHAIN_FP)
+		arch__add_leaf_frame_record_opts(&rec->opts);
+
 	err = -ENOMEM;
 	if (evlist__create_maps(rec->evlist, &rec->opts.target) < 0)
 		usage_with_options(record_usage, record_options);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 8ae400429870..1dd92d8c9279 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -410,7 +410,7 @@ static int report__setup_sample_type(struct report *rep)
 		}
 	}
 
-	callchain_param_setup(sample_type);
+	callchain_param_setup(sample_type, perf_env__arch(&rep->session->header.env));
 
 	if (rep->stitch_lbr && (callchain_param.record_mode != CALLCHAIN_LBR)) {
 		ui__warning("Can't find LBR callchain. Switch off --stitch-lbr.\n"
@@ -1127,7 +1127,7 @@ static int process_attr(struct perf_tool *tool __maybe_unused,
 	 * on events sample_type.
 	 */
 	sample_type = evlist__combined_sample_type(*pevlist);
-	callchain_param_setup(sample_type);
+	callchain_param_setup(sample_type, perf_env__arch((*pevlist)->env));
 	return 0;
 }
 
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 4527f632ebe4..72d446de9c60 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -167,7 +167,7 @@ struct trace_sched_handler {
 
 struct perf_sched_map {
 	DECLARE_BITMAP(comp_cpus_mask, MAX_CPUS);
-	int			*comp_cpus;
+	struct perf_cpu		*comp_cpus;
 	bool			 comp;
 	struct perf_thread_map *color_pids;
 	const char		*color_pids_str;
@@ -191,7 +191,7 @@ struct perf_sched {
  * Track the current task - that way we can know whether there's any
  * weird events, such as a task being switched away that is not current.
  */
-	int		 max_cpu;
+	struct perf_cpu	 max_cpu;
 	u32		 curr_pid[MAX_CPUS];
 	struct thread	 *curr_thread[MAX_CPUS];
 	char		 next_shortname1;
@@ -1535,28 +1535,31 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
 	int new_shortname;
 	u64 timestamp0, timestamp = sample->time;
 	s64 delta;
-	int i, this_cpu = sample->cpu;
+	int i;
+	struct perf_cpu this_cpu = {
+		.cpu = sample->cpu,
+	};
 	int cpus_nr;
 	bool new_cpu = false;
 	const char *color = PERF_COLOR_NORMAL;
 	char stimestamp[32];
 
-	BUG_ON(this_cpu >= MAX_CPUS || this_cpu < 0);
+	BUG_ON(this_cpu.cpu >= MAX_CPUS || this_cpu.cpu < 0);
 
-	if (this_cpu > sched->max_cpu)
+	if (this_cpu.cpu > sched->max_cpu.cpu)
 		sched->max_cpu = this_cpu;
 
 	if (sched->map.comp) {
 		cpus_nr = bitmap_weight(sched->map.comp_cpus_mask, MAX_CPUS);
-		if (!test_and_set_bit(this_cpu, sched->map.comp_cpus_mask)) {
+		if (!test_and_set_bit(this_cpu.cpu, sched->map.comp_cpus_mask)) {
 			sched->map.comp_cpus[cpus_nr++] = this_cpu;
 			new_cpu = true;
 		}
 	} else
-		cpus_nr = sched->max_cpu;
+		cpus_nr = sched->max_cpu.cpu;
 
-	timestamp0 = sched->cpu_last_switched[this_cpu];
-	sched->cpu_last_switched[this_cpu] = timestamp;
+	timestamp0 = sched->cpu_last_switched[this_cpu.cpu];
+	sched->cpu_last_switched[this_cpu.cpu] = timestamp;
 	if (timestamp0)
 		delta = timestamp - timestamp0;
 	else
@@ -1577,7 +1580,7 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
 		return -1;
 	}
 
-	sched->curr_thread[this_cpu] = thread__get(sched_in);
+	sched->curr_thread[this_cpu.cpu] = thread__get(sched_in);
 
 	printf("  ");
 
@@ -1608,8 +1611,10 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
 	}
 
 	for (i = 0; i < cpus_nr; i++) {
-		int cpu = sched->map.comp ? sched->map.comp_cpus[i] : i;
-		struct thread *curr_thread = sched->curr_thread[cpu];
+		struct perf_cpu cpu = {
+			.cpu = sched->map.comp ? sched->map.comp_cpus[i].cpu : i,
+		};
+		struct thread *curr_thread = sched->curr_thread[cpu.cpu];
 		struct thread_runtime *curr_tr;
 		const char *pid_color = color;
 		const char *cpu_color = color;
@@ -1617,19 +1622,19 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
 		if (curr_thread && thread__has_color(curr_thread))
 			pid_color = COLOR_PIDS;
 
-		if (sched->map.cpus && !cpu_map__has(sched->map.cpus, cpu))
+		if (sched->map.cpus && !perf_cpu_map__has(sched->map.cpus, cpu))
 			continue;
 
-		if (sched->map.color_cpus && cpu_map__has(sched->map.color_cpus, cpu))
+		if (sched->map.color_cpus && perf_cpu_map__has(sched->map.color_cpus, cpu))
 			cpu_color = COLOR_CPUS;
 
-		if (cpu != this_cpu)
+		if (cpu.cpu != this_cpu.cpu)
 			color_fprintf(stdout, color, " ");
 		else
 			color_fprintf(stdout, cpu_color, "*");
 
-		if (sched->curr_thread[cpu]) {
-			curr_tr = thread__get_runtime(sched->curr_thread[cpu]);
+		if (sched->curr_thread[cpu.cpu]) {
+			curr_tr = thread__get_runtime(sched->curr_thread[cpu.cpu]);
 			if (curr_tr == NULL) {
 				thread__put(sched_in);
 				return -1;
@@ -1639,7 +1644,7 @@ static int map_switch_event(struct perf_sched *sched, struct evsel *evsel,
 			color_fprintf(stdout, color, "   ");
 	}
 
-	if (sched->map.cpus && !cpu_map__has(sched->map.cpus, this_cpu))
+	if (sched->map.cpus && !perf_cpu_map__has(sched->map.cpus, this_cpu))
 		goto out;
 
 	timestamp__scnprintf_usec(timestamp, stimestamp, sizeof(stimestamp));
@@ -1929,7 +1934,7 @@ static char *timehist_get_commstr(struct thread *thread)
 
 static void timehist_header(struct perf_sched *sched)
 {
-	u32 ncpus = sched->max_cpu + 1;
+	u32 ncpus = sched->max_cpu.cpu + 1;
 	u32 i, j;
 
 	printf("%15s %6s ", "time", "cpu");
@@ -2008,7 +2013,7 @@ static void timehist_print_sample(struct perf_sched *sched,
 	struct thread_runtime *tr = thread__priv(thread);
 	const char *next_comm = evsel__strval(evsel, sample, "next_comm");
 	const u32 next_pid = evsel__intval(evsel, sample, "next_pid");
-	u32 max_cpus = sched->max_cpu + 1;
+	u32 max_cpus = sched->max_cpu.cpu + 1;
 	char tstr[64];
 	char nstr[30];
 	u64 wait_time;
@@ -2389,7 +2394,7 @@ static void timehist_print_wakeup_event(struct perf_sched *sched,
 	timestamp__scnprintf_usec(sample->time, tstr, sizeof(tstr));
 	printf("%15s [%04d] ", tstr, sample->cpu);
 	if (sched->show_cpu_visual)
-		printf(" %*s ", sched->max_cpu + 1, "");
+		printf(" %*s ", sched->max_cpu.cpu + 1, "");
 
 	printf(" %-*s ", comm_width, timehist_get_commstr(thread));
 
@@ -2449,13 +2454,13 @@ static void timehist_print_migration_event(struct perf_sched *sched,
 {
 	struct thread *thread;
 	char tstr[64];
-	u32 max_cpus = sched->max_cpu + 1;
+	u32 max_cpus;
 	u32 ocpu, dcpu;
 
 	if (sched->summary_only)
 		return;
 
-	max_cpus = sched->max_cpu + 1;
+	max_cpus = sched->max_cpu.cpu + 1;
 	ocpu = evsel__intval(evsel, sample, "orig_cpu");
 	dcpu = evsel__intval(evsel, sample, "dest_cpu");
 
@@ -2918,7 +2923,7 @@ static void timehist_print_summary(struct perf_sched *sched,
 
 	printf("    Total scheduling time (msec): ");
 	print_sched_time(hist_time, 2);
-	printf(" (x %d)\n", sched->max_cpu);
+	printf(" (x %d)\n", sched->max_cpu.cpu);
 }
 
 typedef int (*sched_handler)(struct perf_tool *tool,
@@ -2935,9 +2940,11 @@ static int perf_timehist__process_sample(struct perf_tool *tool,
 {
 	struct perf_sched *sched = container_of(tool, struct perf_sched, tool);
 	int err = 0;
-	int this_cpu = sample->cpu;
+	struct perf_cpu this_cpu = {
+		.cpu = sample->cpu,
+	};
 
-	if (this_cpu > sched->max_cpu)
+	if (this_cpu.cpu > sched->max_cpu.cpu)
 		sched->max_cpu = this_cpu;
 
 	if (evsel->handler != NULL) {
@@ -3054,10 +3061,10 @@ static int perf_sched__timehist(struct perf_sched *sched)
 		goto out;
 
 	/* pre-allocate struct for per-CPU idle stats */
-	sched->max_cpu = session->header.env.nr_cpus_online;
-	if (sched->max_cpu == 0)
-		sched->max_cpu = 4;
-	if (init_idle_threads(sched->max_cpu))
+	sched->max_cpu.cpu = session->header.env.nr_cpus_online;
+	if (sched->max_cpu.cpu == 0)
+		sched->max_cpu.cpu = 4;
+	if (init_idle_threads(sched->max_cpu.cpu))
 		goto out;
 
 	/* summary_only implies summary option, but don't overwrite summary if set */
@@ -3209,10 +3216,10 @@ static int setup_map_cpus(struct perf_sched *sched)
 {
 	struct perf_cpu_map *map;
 
-	sched->max_cpu  = sysconf(_SC_NPROCESSORS_CONF);
+	sched->max_cpu.cpu  = sysconf(_SC_NPROCESSORS_CONF);
 
 	if (sched->map.comp) {
-		sched->map.comp_cpus = zalloc(sched->max_cpu * sizeof(int));
+		sched->map.comp_cpus = zalloc(sched->max_cpu.cpu * sizeof(int));
 		if (!sched->map.comp_cpus)
 			return -1;
 	}
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index c82b033e8942..ecd4f99a6c14 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -15,6 +15,7 @@
 #include "util/symbol.h"
 #include "util/thread.h"
 #include "util/trace-event.h"
+#include "util/env.h"
 #include "util/evlist.h"
 #include "util/evsel.h"
 #include "util/evsel_fprintf.h"
@@ -648,7 +649,7 @@ out:
 	return 0;
 }
 
-static int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask,
+static int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask, const char *arch,
 				     FILE *fp)
 {
 	unsigned i = 0, r;
@@ -661,7 +662,7 @@ static int perf_sample__fprintf_regs(struct regs_dump *regs, uint64_t mask,
 
 	for_each_set_bit(r, (unsigned long *) &mask, sizeof(mask) * 8) {
 		u64 val = regs->regs[i++];
-		printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r), val);
+		printed += fprintf(fp, "%5s:0x%"PRIx64" ", perf_reg_name(r, arch), val);
 	}
 
 	return printed;
@@ -718,17 +719,17 @@ tod_scnprintf(struct perf_script *script, char *buf, int buflen,
 }
 
 static int perf_sample__fprintf_iregs(struct perf_sample *sample,
-				      struct perf_event_attr *attr, FILE *fp)
+				      struct perf_event_attr *attr, const char *arch, FILE *fp)
 {
 	return perf_sample__fprintf_regs(&sample->intr_regs,
-					 attr->sample_regs_intr, fp);
+					 attr->sample_regs_intr, arch, fp);
 }
 
 static int perf_sample__fprintf_uregs(struct perf_sample *sample,
-				      struct perf_event_attr *attr, FILE *fp)
+				      struct perf_event_attr *attr, const char *arch, FILE *fp)
 {
 	return perf_sample__fprintf_regs(&sample->user_regs,
-					 attr->sample_regs_user, fp);
+					 attr->sample_regs_user, arch, fp);
 }
 
 static int perf_sample__fprintf_start(struct perf_script *script,
@@ -2000,6 +2001,7 @@ static void process_event(struct perf_script *script,
 	struct evsel_script *es = evsel->priv;
 	FILE *fp = es->fp;
 	char str[PAGE_SIZE_NAME_LEN];
+	const char *arch = perf_env__arch(machine->env);
 
 	if (output[type].fields == 0)
 		return;
@@ -2066,10 +2068,10 @@ static void process_event(struct perf_script *script,
 	}
 
 	if (PRINT_FIELD(IREGS))
-		perf_sample__fprintf_iregs(sample, attr, fp);
+		perf_sample__fprintf_iregs(sample, attr, arch, fp);
 
 	if (PRINT_FIELD(UREGS))
-		perf_sample__fprintf_uregs(sample, attr, fp);
+		perf_sample__fprintf_uregs(sample, attr, arch, fp);
 
 	if (PRINT_FIELD(BRSTACK))
 		perf_sample__fprintf_brstack(sample, thread, attr, fp);
@@ -2113,8 +2115,8 @@ static struct scripting_ops	*scripting_ops;
 static void __process_stat(struct evsel *counter, u64 tstamp)
 {
 	int nthreads = perf_thread_map__nr(counter->core.threads);
-	int ncpus = evsel__nr_cpus(counter);
-	int cpu, thread;
+	int idx, thread;
+	struct perf_cpu cpu;
 	static int header_printed;
 
 	if (counter->core.system_wide)
@@ -2127,13 +2129,13 @@ static void __process_stat(struct evsel *counter, u64 tstamp)
 	}
 
 	for (thread = 0; thread < nthreads; thread++) {
-		for (cpu = 0; cpu < ncpus; cpu++) {
+		perf_cpu_map__for_each_cpu(cpu, idx, evsel__cpus(counter)) {
 			struct perf_counts_values *counts;
 
-			counts = perf_counts(counter->counts, cpu, thread);
+			counts = perf_counts(counter->counts, idx, thread);
 
 			printf("%3d %8d %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %15" PRIu64 " %s\n",
-				counter->core.cpus->map[cpu],
+				cpu.cpu,
 				perf_thread_map__pid(counter->core.threads, thread),
 				counts->val,
 				counts->ena,
@@ -2316,7 +2318,7 @@ static int process_attr(struct perf_tool *tool, union perf_event *event,
 	 * on events sample_type.
 	 */
 	sample_type = evlist__combined_sample_type(evlist);
-	callchain_param_setup(sample_type);
+	callchain_param_setup(sample_type, perf_env__arch((*pevlist)->env));
 
 	/* Enable fields for callchain entries */
 	if (symbol_conf.use_callchain &&
@@ -3466,16 +3468,7 @@ static void script__setup_sample_type(struct perf_script *script)
 	struct perf_session *session = script->session;
 	u64 sample_type = evlist__combined_sample_type(session->evlist);
 
-	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) {
-		if ((sample_type & PERF_SAMPLE_REGS_USER) &&
-		    (sample_type & PERF_SAMPLE_STACK_USER)) {
-			callchain_param.record_mode = CALLCHAIN_DWARF;
-			dwarf_callchain_users = true;
-		} else if (sample_type & PERF_SAMPLE_BRANCH_STACK)
-			callchain_param.record_mode = CALLCHAIN_LBR;
-		else
-			callchain_param.record_mode = CALLCHAIN_FP;
-	}
+	callchain_param_setup(sample_type, perf_env__arch(session->machines.host.env));
 
 	if (script->stitch_lbr && (callchain_param.record_mode != CALLCHAIN_LBR)) {
 		pr_warning("Can't find LBR callchain. Switch off --stitch-lbr.\n"
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 7974933dbc77..973ade18b72a 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -234,7 +234,7 @@ static bool cpus_map_matched(struct evsel *a, struct evsel *b)
 		return false;
 
 	for (int i = 0; i < a->core.cpus->nr; i++) {
-		if (a->core.cpus->map[i] != b->core.cpus->map[i])
+		if (a->core.cpus->map[i].cpu != b->core.cpus->map[i].cpu)
 			return false;
 	}
 
@@ -327,34 +327,35 @@ static int write_stat_round_event(u64 tm, u64 type)
 
 #define SID(e, x, y) xyarray__entry(e->core.sample_id, x, y)
 
-static int evsel__write_stat_event(struct evsel *counter, u32 cpu, u32 thread,
+static int evsel__write_stat_event(struct evsel *counter, int cpu_map_idx, u32 thread,
 				   struct perf_counts_values *count)
 {
-	struct perf_sample_id *sid = SID(counter, cpu, thread);
+	struct perf_sample_id *sid = SID(counter, cpu_map_idx, thread);
+	struct perf_cpu cpu = perf_cpu_map__cpu(evsel__cpus(counter), cpu_map_idx);
 
 	return perf_event__synthesize_stat(NULL, cpu, thread, sid->id, count,
 					   process_synthesized_event, NULL);
 }
 
-static int read_single_counter(struct evsel *counter, int cpu,
+static int read_single_counter(struct evsel *counter, int cpu_map_idx,
 			       int thread, struct timespec *rs)
 {
 	if (counter->tool_event == PERF_TOOL_DURATION_TIME) {
 		u64 val = rs->tv_nsec + rs->tv_sec*1000000000ULL;
 		struct perf_counts_values *count =
-			perf_counts(counter->counts, cpu, thread);
+			perf_counts(counter->counts, cpu_map_idx, thread);
 		count->ena = count->run = val;
 		count->val = val;
 		return 0;
 	}
-	return evsel__read_counter(counter, cpu, thread);
+	return evsel__read_counter(counter, cpu_map_idx, thread);
 }
 
 /*
  * Read out the results of a single counter:
  * do not aggregate counts across CPUs in system-wide mode
  */
-static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
+static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu_map_idx)
 {
 	int nthreads = perf_thread_map__nr(evsel_list->core.threads);
 	int thread;
@@ -368,24 +369,24 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
 	for (thread = 0; thread < nthreads; thread++) {
 		struct perf_counts_values *count;
 
-		count = perf_counts(counter->counts, cpu, thread);
+		count = perf_counts(counter->counts, cpu_map_idx, thread);
 
 		/*
 		 * The leader's group read loads data into its group members
 		 * (via evsel__read_counter()) and sets their count->loaded.
 		 */
-		if (!perf_counts__is_loaded(counter->counts, cpu, thread) &&
-		    read_single_counter(counter, cpu, thread, rs)) {
+		if (!perf_counts__is_loaded(counter->counts, cpu_map_idx, thread) &&
+		    read_single_counter(counter, cpu_map_idx, thread, rs)) {
 			counter->counts->scaled = -1;
-			perf_counts(counter->counts, cpu, thread)->ena = 0;
-			perf_counts(counter->counts, cpu, thread)->run = 0;
+			perf_counts(counter->counts, cpu_map_idx, thread)->ena = 0;
+			perf_counts(counter->counts, cpu_map_idx, thread)->run = 0;
 			return -1;
 		}
 
-		perf_counts__set_loaded(counter->counts, cpu, thread, false);
+		perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, false);
 
 		if (STAT_RECORD) {
-			if (evsel__write_stat_event(counter, cpu, thread, count)) {
+			if (evsel__write_stat_event(counter, cpu_map_idx, thread, count)) {
 				pr_err("failed to write stat event\n");
 				return -1;
 			}
@@ -395,7 +396,8 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
 			fprintf(stat_config.output,
 				"%s: %d: %" PRIu64 " %" PRIu64 " %" PRIu64 "\n",
 					evsel__name(counter),
-					cpu,
+					perf_cpu_map__cpu(evsel__cpus(counter),
+							  cpu_map_idx).cpu,
 					count->val, count->ena, count->run);
 		}
 	}
@@ -405,36 +407,33 @@ static int read_counter_cpu(struct evsel *counter, struct timespec *rs, int cpu)
 
 static int read_affinity_counters(struct timespec *rs)
 {
-	struct evsel *counter;
-	struct affinity affinity;
-	int i, ncpus, cpu;
+	struct evlist_cpu_iterator evlist_cpu_itr;
+	struct affinity saved_affinity, *affinity;
 
 	if (all_counters_use_bpf)
 		return 0;
 
-	if (affinity__setup(&affinity) < 0)
+	if (!target__has_cpu(&target) || target__has_per_thread(&target))
+		affinity = NULL;
+	else if (affinity__setup(&saved_affinity) < 0)
 		return -1;
+	else
+		affinity = &saved_affinity;
 
-	ncpus = perf_cpu_map__nr(evsel_list->core.all_cpus);
-	if (!target__has_cpu(&target) || target__has_per_thread(&target))
-		ncpus = 1;
-	evlist__for_each_cpu(evsel_list, i, cpu) {
-		if (i >= ncpus)
-			break;
-		affinity__set(&affinity, cpu);
+	evlist__for_each_cpu(evlist_cpu_itr, evsel_list, affinity) {
+		struct evsel *counter = evlist_cpu_itr.evsel;
 
-		evlist__for_each_entry(evsel_list, counter) {
-			if (evsel__cpu_iter_skip(counter, cpu))
-				continue;
-			if (evsel__is_bpf(counter))
-				continue;
-			if (!counter->err) {
-				counter->err = read_counter_cpu(counter, rs,
-								counter->cpu_iter - 1);
-			}
+		if (evsel__is_bpf(counter))
+			continue;
+
+		if (!counter->err) {
+			counter->err = read_counter_cpu(counter, rs,
+							evlist_cpu_itr.cpu_map_idx);
 		}
 	}
-	affinity__cleanup(&affinity);
+	if (affinity)
+		affinity__cleanup(&saved_affinity);
+
 	return 0;
 }
 
@@ -788,8 +787,9 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 	int status = 0;
 	const bool forks = (argc > 0);
 	bool is_pipe = STAT_RECORD ? perf_stat.data.is_pipe : false;
+	struct evlist_cpu_iterator evlist_cpu_itr;
 	struct affinity affinity;
-	int i, cpu, err;
+	int err;
 	bool second_pass = false;
 
 	if (forks) {
@@ -813,102 +813,97 @@ static int __run_perf_stat(int argc, const char **argv, int run_idx)
 			all_counters_use_bpf = false;
 	}
 
-	evlist__for_each_cpu (evsel_list, i, cpu) {
+	evlist__for_each_cpu(evlist_cpu_itr, evsel_list, &affinity) {
+		counter = evlist_cpu_itr.evsel;
+
 		/*
 		 * bperf calls evsel__open_per_cpu() in bperf__load(), so
 		 * no need to call it again here.
 		 */
 		if (target.use_bpf)
 			break;
-		affinity__set(&affinity, cpu);
 
-		evlist__for_each_entry(evsel_list, counter) {
-			if (evsel__cpu_iter_skip(counter, cpu))
+		if (counter->reset_group || counter->errored)
+			continue;
+		if (evsel__is_bpf(counter))
+			continue;
+try_again:
+		if (create_perf_stat_counter(counter, &stat_config, &target,
+					     evlist_cpu_itr.cpu_map_idx) < 0) {
+
+			/*
+			 * Weak group failed. We cannot just undo this here
+			 * because earlier CPUs might be in group mode, and the kernel
+			 * doesn't support mixing group and non group reads. Defer
+			 * it to later.
+			 * Don't close here because we're in the wrong affinity.
+			 */
+			if ((errno == EINVAL || errno == EBADF) &&
+				evsel__leader(counter) != counter &&
+				counter->weak_group) {
+				evlist__reset_weak_group(evsel_list, counter, false);
+				assert(counter->reset_group);
+				second_pass = true;
 				continue;
-			if (counter->reset_group || counter->errored)
+			}
+
+			switch (stat_handle_error(counter)) {
+			case COUNTER_FATAL:
+				return -1;
+			case COUNTER_RETRY:
+				goto try_again;
+			case COUNTER_SKIP:
 				continue;
-			if (evsel__is_bpf(counter))
+			default:
+				break;
+			}
+
+		}
+		counter->supported = true;
+	}
+
+	if (second_pass) {
+		/*
+		 * Now redo all the weak group after closing them,
+		 * and also close errored counters.
+		 */
+
+		/* First close errored or weak retry */
+		evlist__for_each_cpu(evlist_cpu_itr, evsel_list, &affinity) {
+			counter = evlist_cpu_itr.evsel;
+
+			if (!counter->reset_group && !counter->errored)
 				continue;
-try_again:
+
+			perf_evsel__close_cpu(&counter->core, evlist_cpu_itr.cpu_map_idx);
+		}
+		/* Now reopen weak */
+		evlist__for_each_cpu(evlist_cpu_itr, evsel_list, &affinity) {
+			counter = evlist_cpu_itr.evsel;
+
+			if (!counter->reset_group && !counter->errored)
+				continue;
+			if (!counter->reset_group)
+				continue;
+try_again_reset:
+			pr_debug2("reopening weak %s\n", evsel__name(counter));
 			if (create_perf_stat_counter(counter, &stat_config, &target,
-						     counter->cpu_iter - 1) < 0) {
-
-				/*
-				 * Weak group failed. We cannot just undo this here
-				 * because earlier CPUs might be in group mode, and the kernel
-				 * doesn't support mixing group and non group reads. Defer
-				 * it to later.
-				 * Don't close here because we're in the wrong affinity.
-				 */
-				if ((errno == EINVAL || errno == EBADF) &&
-				    evsel__leader(counter) != counter &&
-				    counter->weak_group) {
-					evlist__reset_weak_group(evsel_list, counter, false);
-					assert(counter->reset_group);
-					second_pass = true;
-					continue;
-				}
+						     evlist_cpu_itr.cpu_map_idx) < 0) {
 
 				switch (stat_handle_error(counter)) {
 				case COUNTER_FATAL:
 					return -1;
 				case COUNTER_RETRY:
-					goto try_again;
+					goto try_again_reset;
 				case COUNTER_SKIP:
 					continue;
 				default:
 					break;
 				}
-
 			}
 			counter->supported = true;
 		}
 	}
-
-	if (second_pass) {
-		/*
-		 * Now redo all the weak group after closing them,
-		 * and also close errored counters.
-		 */
-
-		evlist__for_each_cpu(evsel_list, i, cpu) {
-			affinity__set(&affinity, cpu);
-			/* First close errored or weak retry */
-			evlist__for_each_entry(evsel_list, counter) {
-				if (!counter->reset_group && !counter->errored)
-					continue;
-				if (evsel__cpu_iter_skip_no_inc(counter, cpu))
-					continue;
-				perf_evsel__close_cpu(&counter->core, counter->cpu_iter);
-			}
-			/* Now reopen weak */
-			evlist__for_each_entry(evsel_list, counter) {
-				if (!counter->reset_group && !counter->errored)
-					continue;
-				if (evsel__cpu_iter_skip(counter, cpu))
-					continue;
-				if (!counter->reset_group)
-					continue;
-try_again_reset:
-				pr_debug2("reopening weak %s\n", evsel__name(counter));
-				if (create_perf_stat_counter(counter, &stat_config, &target,
-							     counter->cpu_iter - 1) < 0) {
-
-					switch (stat_handle_error(counter)) {
-					case COUNTER_FATAL:
-						return -1;
-					case COUNTER_RETRY:
-						goto try_again_reset;
-					case COUNTER_SKIP:
-						continue;
-					default:
-						break;
-					}
-				}
-				counter->supported = true;
-			}
-		}
-	}
 	affinity__cleanup(&affinity);
 
 	evlist__for_each_entry(evsel_list, counter) {
@@ -1168,6 +1163,26 @@ static int parse_stat_cgroups(const struct option *opt,
 	return parse_cgroups(opt, str, unset);
 }
 
+static int parse_hybrid_type(const struct option *opt,
+			     const char *str,
+			     int unset __maybe_unused)
+{
+	struct evlist *evlist = *(struct evlist **)opt->value;
+
+	if (!list_empty(&evlist->core.entries)) {
+		fprintf(stderr, "Must define cputype before events/metrics\n");
+		return -1;
+	}
+
+	evlist->hybrid_pmu_name = perf_pmu__hybrid_type_to_pmu(str);
+	if (!evlist->hybrid_pmu_name) {
+		fprintf(stderr, "--cputype %s is not supported!\n", str);
+		return -1;
+	}
+
+	return 0;
+}
+
 static struct option stat_options[] = {
 	OPT_BOOLEAN('T', "transaction", &transaction_run,
 		    "hardware transaction statistics"),
@@ -1282,6 +1297,10 @@ static struct option stat_options[] = {
 		       "don't print 'summary' for CSV summary output"),
 	OPT_BOOLEAN(0, "quiet", &stat_config.quiet,
 			"don't print output (useful with record)"),
+	OPT_CALLBACK(0, "cputype", &evsel_list, "hybrid cpu type",
+		     "Only enable events on applying cpu with this type "
+		     "for hybrid platform (e.g. core or atom)",
+		     parse_hybrid_type),
 #ifdef HAVE_LIBPFM
 	OPT_CALLBACK(0, "pfm-events", &evsel_list, "event",
 		"libpfm4 event selector. use 'perf list' to list available events",
@@ -1298,70 +1317,75 @@ static struct option stat_options[] = {
 	OPT_END()
 };
 
+static const char *const aggr_mode__string[] = {
+	[AGGR_CORE] = "core",
+	[AGGR_DIE] = "die",
+	[AGGR_GLOBAL] = "global",
+	[AGGR_NODE] = "node",
+	[AGGR_NONE] = "none",
+	[AGGR_SOCKET] = "socket",
+	[AGGR_THREAD] = "thread",
+	[AGGR_UNSET] = "unset",
+};
+
 static struct aggr_cpu_id perf_stat__get_socket(struct perf_stat_config *config __maybe_unused,
-				 struct perf_cpu_map *map, int cpu)
+						struct perf_cpu cpu)
 {
-	return cpu_map__get_socket(map, cpu, NULL);
+	return aggr_cpu_id__socket(cpu, /*data=*/NULL);
 }
 
 static struct aggr_cpu_id perf_stat__get_die(struct perf_stat_config *config __maybe_unused,
-			      struct perf_cpu_map *map, int cpu)
+					     struct perf_cpu cpu)
 {
-	return cpu_map__get_die(map, cpu, NULL);
+	return aggr_cpu_id__die(cpu, /*data=*/NULL);
 }
 
 static struct aggr_cpu_id perf_stat__get_core(struct perf_stat_config *config __maybe_unused,
-			       struct perf_cpu_map *map, int cpu)
+					      struct perf_cpu cpu)
 {
-	return cpu_map__get_core(map, cpu, NULL);
+	return aggr_cpu_id__core(cpu, /*data=*/NULL);
 }
 
 static struct aggr_cpu_id perf_stat__get_node(struct perf_stat_config *config __maybe_unused,
-			       struct perf_cpu_map *map, int cpu)
+					      struct perf_cpu cpu)
 {
-	return cpu_map__get_node(map, cpu, NULL);
+	return aggr_cpu_id__node(cpu, /*data=*/NULL);
 }
 
 static struct aggr_cpu_id perf_stat__get_aggr(struct perf_stat_config *config,
-			       aggr_get_id_t get_id, struct perf_cpu_map *map, int idx)
+					      aggr_get_id_t get_id, struct perf_cpu cpu)
 {
-	int cpu;
-	struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+	struct aggr_cpu_id id = aggr_cpu_id__empty();
 
-	if (idx >= map->nr)
-		return id;
+	if (aggr_cpu_id__is_empty(&config->cpus_aggr_map->map[cpu.cpu]))
+		config->cpus_aggr_map->map[cpu.cpu] = get_id(config, cpu);
 
-	cpu = map->map[idx];
-
-	if (cpu_map__aggr_cpu_id_is_empty(config->cpus_aggr_map->map[cpu]))
-		config->cpus_aggr_map->map[cpu] = get_id(config, map, idx);
-
-	id = config->cpus_aggr_map->map[cpu];
+	id = config->cpus_aggr_map->map[cpu.cpu];
 	return id;
 }
 
 static struct aggr_cpu_id perf_stat__get_socket_cached(struct perf_stat_config *config,
-					struct perf_cpu_map *map, int idx)
+						       struct perf_cpu cpu)
 {
-	return perf_stat__get_aggr(config, perf_stat__get_socket, map, idx);
+	return perf_stat__get_aggr(config, perf_stat__get_socket, cpu);
 }
 
 static struct aggr_cpu_id perf_stat__get_die_cached(struct perf_stat_config *config,
-					struct perf_cpu_map *map, int idx)
+						    struct perf_cpu cpu)
 {
-	return perf_stat__get_aggr(config, perf_stat__get_die, map, idx);
+	return perf_stat__get_aggr(config, perf_stat__get_die, cpu);
 }
 
 static struct aggr_cpu_id perf_stat__get_core_cached(struct perf_stat_config *config,
-				      struct perf_cpu_map *map, int idx)
+						     struct perf_cpu cpu)
 {
-	return perf_stat__get_aggr(config, perf_stat__get_core, map, idx);
+	return perf_stat__get_aggr(config, perf_stat__get_core, cpu);
 }
 
 static struct aggr_cpu_id perf_stat__get_node_cached(struct perf_stat_config *config,
-				      struct perf_cpu_map *map, int idx)
+						     struct perf_cpu cpu)
 {
-	return perf_stat__get_aggr(config, perf_stat__get_node, map, idx);
+	return perf_stat__get_aggr(config, perf_stat__get_node, cpu);
 }
 
 static bool term_percore_set(void)
@@ -1376,54 +1400,67 @@ static bool term_percore_set(void)
 	return false;
 }
 
-static int perf_stat_init_aggr_mode(void)
+static aggr_cpu_id_get_t aggr_mode__get_aggr(enum aggr_mode aggr_mode)
 {
-	int nr;
+	switch (aggr_mode) {
+	case AGGR_SOCKET:
+		return aggr_cpu_id__socket;
+	case AGGR_DIE:
+		return aggr_cpu_id__die;
+	case AGGR_CORE:
+		return aggr_cpu_id__core;
+	case AGGR_NODE:
+		return aggr_cpu_id__node;
+	case AGGR_NONE:
+		if (term_percore_set())
+			return aggr_cpu_id__core;
+
+		return NULL;
+	case AGGR_GLOBAL:
+	case AGGR_THREAD:
+	case AGGR_UNSET:
+	default:
+		return NULL;
+	}
+}
 
-	switch (stat_config.aggr_mode) {
+static aggr_get_id_t aggr_mode__get_id(enum aggr_mode aggr_mode)
+{
+	switch (aggr_mode) {
 	case AGGR_SOCKET:
-		if (cpu_map__build_socket_map(evsel_list->core.cpus, &stat_config.aggr_map)) {
-			perror("cannot build socket map");
-			return -1;
-		}
-		stat_config.aggr_get_id = perf_stat__get_socket_cached;
-		break;
+		return perf_stat__get_socket_cached;
 	case AGGR_DIE:
-		if (cpu_map__build_die_map(evsel_list->core.cpus, &stat_config.aggr_map)) {
-			perror("cannot build die map");
-			return -1;
-		}
-		stat_config.aggr_get_id = perf_stat__get_die_cached;
-		break;
+		return perf_stat__get_die_cached;
 	case AGGR_CORE:
-		if (cpu_map__build_core_map(evsel_list->core.cpus, &stat_config.aggr_map)) {
-			perror("cannot build core map");
-			return -1;
-		}
-		stat_config.aggr_get_id = perf_stat__get_core_cached;
-		break;
+		return perf_stat__get_core_cached;
 	case AGGR_NODE:
-		if (cpu_map__build_node_map(evsel_list->core.cpus, &stat_config.aggr_map)) {
-			perror("cannot build core map");
-			return -1;
-		}
-		stat_config.aggr_get_id = perf_stat__get_node_cached;
-		break;
+		return perf_stat__get_node_cached;
 	case AGGR_NONE:
 		if (term_percore_set()) {
-			if (cpu_map__build_core_map(evsel_list->core.cpus,
-						    &stat_config.aggr_map)) {
-				perror("cannot build core map");
-				return -1;
-			}
-			stat_config.aggr_get_id = perf_stat__get_core_cached;
+			return perf_stat__get_core_cached;
 		}
-		break;
+		return NULL;
 	case AGGR_GLOBAL:
 	case AGGR_THREAD:
 	case AGGR_UNSET:
 	default:
-		break;
+		return NULL;
+	}
+}
+
+static int perf_stat_init_aggr_mode(void)
+{
+	int nr;
+	aggr_cpu_id_get_t get_id = aggr_mode__get_aggr(stat_config.aggr_mode);
+
+	if (get_id) {
+		stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.cpus,
+							 get_id, /*data=*/NULL);
+		if (!stat_config.aggr_map) {
+			pr_err("cannot build %s map", aggr_mode__string[stat_config.aggr_mode]);
+			return -1;
+		}
+		stat_config.aggr_get_id = aggr_mode__get_id(stat_config.aggr_mode);
 	}
 
 	/*
@@ -1431,7 +1468,7 @@ static int perf_stat_init_aggr_mode(void)
 	 * taking the highest cpu number to be the size of
 	 * the aggregation translate cpumap.
 	 */
-	nr = perf_cpu_map__max(evsel_list->core.cpus);
+	nr = perf_cpu_map__max(evsel_list->core.cpus).cpu;
 	stat_config.cpus_aggr_map = cpu_aggr_map__empty_new(nr + 1);
 	return stat_config.cpus_aggr_map ? 0 : -ENOMEM;
 }
@@ -1459,169 +1496,139 @@ static void perf_stat__exit_aggr_mode(void)
 	stat_config.cpus_aggr_map = NULL;
 }
 
-static inline int perf_env__get_cpu(struct perf_env *env, struct perf_cpu_map *map, int idx)
-{
-	int cpu;
-
-	if (idx > map->nr)
-		return -1;
-
-	cpu = map->map[idx];
-
-	if (cpu >= env->nr_cpus_avail)
-		return -1;
-
-	return cpu;
-}
-
-static struct aggr_cpu_id perf_env__get_socket(struct perf_cpu_map *map, int idx, void *data)
+static struct aggr_cpu_id perf_env__get_socket_aggr_by_cpu(struct perf_cpu cpu, void *data)
 {
 	struct perf_env *env = data;
-	int cpu = perf_env__get_cpu(env, map, idx);
-	struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+	struct aggr_cpu_id id = aggr_cpu_id__empty();
 
-	if (cpu != -1)
-		id.socket = env->cpu[cpu].socket_id;
+	if (cpu.cpu != -1)
+		id.socket = env->cpu[cpu.cpu].socket_id;
 
 	return id;
 }
 
-static struct aggr_cpu_id perf_env__get_die(struct perf_cpu_map *map, int idx, void *data)
+static struct aggr_cpu_id perf_env__get_die_aggr_by_cpu(struct perf_cpu cpu, void *data)
 {
 	struct perf_env *env = data;
-	struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
-	int cpu = perf_env__get_cpu(env, map, idx);
+	struct aggr_cpu_id id = aggr_cpu_id__empty();
 
-	if (cpu != -1) {
+	if (cpu.cpu != -1) {
 		/*
 		 * die_id is relative to socket, so start
 		 * with the socket ID and then add die to
 		 * make a unique ID.
 		 */
-		id.socket = env->cpu[cpu].socket_id;
-		id.die = env->cpu[cpu].die_id;
+		id.socket = env->cpu[cpu.cpu].socket_id;
+		id.die = env->cpu[cpu.cpu].die_id;
 	}
 
 	return id;
 }
 
-static struct aggr_cpu_id perf_env__get_core(struct perf_cpu_map *map, int idx, void *data)
+static struct aggr_cpu_id perf_env__get_core_aggr_by_cpu(struct perf_cpu cpu, void *data)
 {
 	struct perf_env *env = data;
-	struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
-	int cpu = perf_env__get_cpu(env, map, idx);
+	struct aggr_cpu_id id = aggr_cpu_id__empty();
 
-	if (cpu != -1) {
+	if (cpu.cpu != -1) {
 		/*
 		 * core_id is relative to socket and die,
 		 * we need a global id. So we set
 		 * socket, die id and core id
 		 */
-		id.socket = env->cpu[cpu].socket_id;
-		id.die = env->cpu[cpu].die_id;
-		id.core = env->cpu[cpu].core_id;
+		id.socket = env->cpu[cpu.cpu].socket_id;
+		id.die = env->cpu[cpu.cpu].die_id;
+		id.core = env->cpu[cpu.cpu].core_id;
 	}
 
 	return id;
 }
 
-static struct aggr_cpu_id perf_env__get_node(struct perf_cpu_map *map, int idx, void *data)
+static struct aggr_cpu_id perf_env__get_node_aggr_by_cpu(struct perf_cpu cpu, void *data)
 {
-	int cpu = perf_env__get_cpu(data, map, idx);
-	struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+	struct aggr_cpu_id id = aggr_cpu_id__empty();
 
 	id.node = perf_env__numa_node(data, cpu);
 	return id;
 }
 
-static int perf_env__build_socket_map(struct perf_env *env, struct perf_cpu_map *cpus,
-				      struct cpu_aggr_map **sockp)
-{
-	return cpu_map__build_map(cpus, sockp, perf_env__get_socket, env);
-}
-
-static int perf_env__build_die_map(struct perf_env *env, struct perf_cpu_map *cpus,
-				   struct cpu_aggr_map **diep)
-{
-	return cpu_map__build_map(cpus, diep, perf_env__get_die, env);
-}
-
-static int perf_env__build_core_map(struct perf_env *env, struct perf_cpu_map *cpus,
-				    struct cpu_aggr_map **corep)
-{
-	return cpu_map__build_map(cpus, corep, perf_env__get_core, env);
-}
-
-static int perf_env__build_node_map(struct perf_env *env, struct perf_cpu_map *cpus,
-				    struct cpu_aggr_map **nodep)
-{
-	return cpu_map__build_map(cpus, nodep, perf_env__get_node, env);
-}
-
 static struct aggr_cpu_id perf_stat__get_socket_file(struct perf_stat_config *config __maybe_unused,
-				      struct perf_cpu_map *map, int idx)
+						     struct perf_cpu cpu)
 {
-	return perf_env__get_socket(map, idx, &perf_stat.session->header.env);
+	return perf_env__get_socket_aggr_by_cpu(cpu, &perf_stat.session->header.env);
 }
 static struct aggr_cpu_id perf_stat__get_die_file(struct perf_stat_config *config __maybe_unused,
-				   struct perf_cpu_map *map, int idx)
+						  struct perf_cpu cpu)
 {
-	return perf_env__get_die(map, idx, &perf_stat.session->header.env);
+	return perf_env__get_die_aggr_by_cpu(cpu, &perf_stat.session->header.env);
 }
 
 static struct aggr_cpu_id perf_stat__get_core_file(struct perf_stat_config *config __maybe_unused,
-				    struct perf_cpu_map *map, int idx)
+						   struct perf_cpu cpu)
 {
-	return perf_env__get_core(map, idx, &perf_stat.session->header.env);
+	return perf_env__get_core_aggr_by_cpu(cpu, &perf_stat.session->header.env);
 }
 
 static struct aggr_cpu_id perf_stat__get_node_file(struct perf_stat_config *config __maybe_unused,
-				    struct perf_cpu_map *map, int idx)
+						   struct perf_cpu cpu)
 {
-	return perf_env__get_node(map, idx, &perf_stat.session->header.env);
+	return perf_env__get_node_aggr_by_cpu(cpu, &perf_stat.session->header.env);
 }
 
-static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
+static aggr_cpu_id_get_t aggr_mode__get_aggr_file(enum aggr_mode aggr_mode)
 {
-	struct perf_env *env = &st->session->header.env;
+	switch (aggr_mode) {
+	case AGGR_SOCKET:
+		return perf_env__get_socket_aggr_by_cpu;
+	case AGGR_DIE:
+		return perf_env__get_die_aggr_by_cpu;
+	case AGGR_CORE:
+		return perf_env__get_core_aggr_by_cpu;
+	case AGGR_NODE:
+		return perf_env__get_node_aggr_by_cpu;
+	case AGGR_NONE:
+	case AGGR_GLOBAL:
+	case AGGR_THREAD:
+	case AGGR_UNSET:
+	default:
+		return NULL;
+	}
+}
 
-	switch (stat_config.aggr_mode) {
+static aggr_get_id_t aggr_mode__get_id_file(enum aggr_mode aggr_mode)
+{
+	switch (aggr_mode) {
 	case AGGR_SOCKET:
-		if (perf_env__build_socket_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) {
-			perror("cannot build socket map");
-			return -1;
-		}
-		stat_config.aggr_get_id = perf_stat__get_socket_file;
-		break;
+		return perf_stat__get_socket_file;
 	case AGGR_DIE:
-		if (perf_env__build_die_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) {
-			perror("cannot build die map");
-			return -1;
-		}
-		stat_config.aggr_get_id = perf_stat__get_die_file;
-		break;
+		return perf_stat__get_die_file;
 	case AGGR_CORE:
-		if (perf_env__build_core_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) {
-			perror("cannot build core map");
-			return -1;
-		}
-		stat_config.aggr_get_id = perf_stat__get_core_file;
-		break;
+		return perf_stat__get_core_file;
 	case AGGR_NODE:
-		if (perf_env__build_node_map(env, evsel_list->core.cpus, &stat_config.aggr_map)) {
-			perror("cannot build core map");
-			return -1;
-		}
-		stat_config.aggr_get_id = perf_stat__get_node_file;
-		break;
+		return perf_stat__get_node_file;
 	case AGGR_NONE:
 	case AGGR_GLOBAL:
 	case AGGR_THREAD:
 	case AGGR_UNSET:
 	default:
-		break;
+		return NULL;
 	}
+}
+
+static int perf_stat_init_aggr_mode_file(struct perf_stat *st)
+{
+	struct perf_env *env = &st->session->header.env;
+	aggr_cpu_id_get_t get_id = aggr_mode__get_aggr_file(stat_config.aggr_mode);
+
+	if (!get_id)
+		return 0;
 
+	stat_config.aggr_map = cpu_aggr_map__new(evsel_list->core.cpus, get_id, env);
+	if (!stat_config.aggr_map) {
+		pr_err("cannot build %s map", aggr_mode__string[stat_config.aggr_mode]);
+		return -1;
+	}
+	stat_config.aggr_get_id = aggr_mode__get_id_file(stat_config.aggr_mode);
 	return 0;
 }
 
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 273237a9c5e6..32844d8a0ea5 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -3964,6 +3964,9 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 		evlist__add(evlist, pgfault_min);
 	}
 
+	/* Enable ignoring missing threads when -u/-p option is defined. */
+	trace->opts.ignore_missing_thread = trace->opts.target.uid != UINT_MAX || trace->opts.target.pid;
+
 	if (trace->sched &&
 	    evlist__add_newtp(evlist, "sched", "sched_stat_runtime", trace__sched_stat_runtime))
 		goto out_error_sched_stat_runtime;
diff --git a/tools/perf/dlfilters/dlfilter-test-api-v0.c b/tools/perf/dlfilters/dlfilter-test-api-v0.c
index 7565a1852c74..b17eb52a0694 100644
--- a/tools/perf/dlfilters/dlfilter-test-api-v0.c
+++ b/tools/perf/dlfilters/dlfilter-test-api-v0.c
@@ -308,8 +308,6 @@ int filter_event_early(void *data, const struct perf_dlfilter_sample *sample, vo
 
 int filter_event(void *data, const struct perf_dlfilter_sample *sample, void *ctx)
 {
-	struct filter_data *d = data;
-
 	pr_debug("%s API\n", __func__);
 
 	return do_checks(data, sample, ctx, false);
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/branch.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/branch.json
new file mode 100644
index 000000000000..79f2016c53b0
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/branch.json
@@ -0,0 +1,8 @@
+[
+    {
+        "ArchStdEvent": "BR_MIS_PRED"
+    },
+    {
+        "ArchStdEvent": "BR_PRED"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/bus.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/bus.json
new file mode 100644
index 000000000000..579c1c993d17
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/bus.json
@@ -0,0 +1,20 @@
+[
+    {
+        "ArchStdEvent": "CPU_CYCLES"
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS"
+    },
+    {
+        "ArchStdEvent": "BUS_CYCLES"
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_RD"
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_WR"
+    },
+    {
+        "ArchStdEvent": "CNT_CYCLES"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/cache.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/cache.json
new file mode 100644
index 000000000000..0141f749bff3
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/cache.json
@@ -0,0 +1,155 @@
+[
+    {
+        "ArchStdEvent": "L1I_CACHE_REFILL"
+    },
+    {
+        "ArchStdEvent": "L1I_TLB_REFILL"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL"
+    },
+    {
+        "ArchStdEvent": "L1I_CACHE"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_ALLOCATE"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB"
+    },
+    {
+        "ArchStdEvent": "L1I_TLB"
+    },
+    {
+        "ArchStdEvent": "L3D_CACHE_ALLOCATE"
+    },
+    {
+        "ArchStdEvent": "L3D_CACHE_REFILL"
+    },
+    {
+        "ArchStdEvent": "L3D_CACHE"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB"
+    },
+    {
+        "ArchStdEvent": "DTLB_WALK"
+    },
+    {
+        "ArchStdEvent": "ITLB_WALK"
+    },
+    {
+        "ArchStdEvent": "LL_CACHE_RD"
+    },
+    {
+        "ArchStdEvent": "LL_CACHE_MISS_RD"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_LMISS_RD"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_RD"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WR"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_RD"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_WR"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_INNER"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_OUTER"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_VICTIM"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_CLEAN"
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_INVAL"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_RD"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_WR"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_RD"
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_WR"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_RD"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WR"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL_RD"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL_WR"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB_VICTIM"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB_CLEAN"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_INVAL"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL_RD"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_REFILL_WR"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_RD"
+    },
+    {
+        "ArchStdEvent": "L2D_TLB_WR"
+    },
+    {
+        "ArchStdEvent": "L3D_CACHE_RD"
+    },
+    {
+        "ArchStdEvent": "L1I_CACHE_LMISS"
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_LMISS_RD"
+    },
+    {
+        "ArchStdEvent": "L3D_CACHE_LMISS_RD"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/exception.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/exception.json
new file mode 100644
index 000000000000..344a2d552ad5
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/exception.json
@@ -0,0 +1,47 @@
+[
+    {
+        "ArchStdEvent": "EXC_TAKEN"
+    },
+    {
+        "ArchStdEvent": "MEMORY_ERROR"
+    },
+    {
+        "ArchStdEvent": "EXC_UNDEF"
+    },
+    {
+        "ArchStdEvent": "EXC_SVC"
+    },
+    {
+        "ArchStdEvent": "EXC_PABORT"
+    },
+    {
+        "ArchStdEvent": "EXC_DABORT"
+    },
+    {
+        "ArchStdEvent": "EXC_IRQ"
+    },
+    {
+        "ArchStdEvent": "EXC_FIQ"
+    },
+    {
+        "ArchStdEvent": "EXC_SMC"
+    },
+    {
+        "ArchStdEvent": "EXC_HVC"
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_PABORT"
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_DABORT"
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_OTHER"
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_IRQ"
+    },
+    {
+        "ArchStdEvent": "EXC_TRAP_FIQ"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/instruction.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/instruction.json
new file mode 100644
index 000000000000..e57cd55937c6
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/instruction.json
@@ -0,0 +1,143 @@
+[
+    {
+        "ArchStdEvent": "SW_INCR"
+    },
+    {
+        "ArchStdEvent": "INST_RETIRED"
+    },
+    {
+        "ArchStdEvent": "EXC_RETURN"
+    },
+    {
+        "ArchStdEvent": "CID_WRITE_RETIRED"
+    },
+    {
+        "ArchStdEvent": "INST_SPEC"
+    },
+    {
+        "ArchStdEvent": "TTBR_WRITE_RETIRED"
+    },
+    {
+        "ArchStdEvent": "BR_RETIRED"
+    },
+    {
+        "ArchStdEvent": "BR_MIS_PRED_RETIRED"
+    },
+    {
+        "ArchStdEvent": "OP_RETIRED"
+    },
+    {
+        "ArchStdEvent": "OP_SPEC"
+    },
+    {
+        "ArchStdEvent": "LDREX_SPEC"
+    },
+    {
+        "ArchStdEvent": "STREX_PASS_SPEC"
+    },
+    {
+        "ArchStdEvent": "STREX_FAIL_SPEC"
+    },
+    {
+        "ArchStdEvent": "STREX_SPEC"
+    },
+    {
+        "ArchStdEvent": "LD_SPEC"
+    },
+    {
+        "ArchStdEvent": "ST_SPEC"
+    },
+    {
+        "ArchStdEvent": "DP_SPEC"
+    },
+    {
+        "ArchStdEvent": "ASE_SPEC"
+    },
+    {
+        "ArchStdEvent": "VFP_SPEC"
+    },
+    {
+        "ArchStdEvent": "PC_WRITE_SPEC"
+    },
+    {
+        "ArchStdEvent": "CRYPTO_SPEC"
+    },
+    {
+        "ArchStdEvent": "BR_IMMED_SPEC"
+    },
+    {
+        "ArchStdEvent": "BR_RETURN_SPEC"
+    },
+    {
+        "ArchStdEvent": "BR_INDIRECT_SPEC"
+    },
+    {
+        "ArchStdEvent": "ISB_SPEC"
+    },
+    {
+        "ArchStdEvent": "DSB_SPEC"
+    },
+    {
+        "ArchStdEvent": "DMB_SPEC"
+    },
+    {
+        "ArchStdEvent": "RC_LD_SPEC"
+    },
+    {
+        "ArchStdEvent": "RC_ST_SPEC"
+    },
+    {
+        "ArchStdEvent": "ASE_INST_SPEC"
+    },
+    {
+        "ArchStdEvent": "SVE_INST_SPEC"
+    },
+    {
+        "ArchStdEvent": "FP_HP_SPEC"
+    },
+    {
+        "ArchStdEvent": "FP_SP_SPEC"
+    },
+    {
+        "ArchStdEvent": "FP_DP_SPEC"
+    },
+    {
+        "ArchStdEvent": "SVE_PRED_SPEC"
+    },
+    {
+        "ArchStdEvent": "SVE_PRED_EMPTY_SPEC"
+    },
+    {
+        "ArchStdEvent": "SVE_PRED_FULL_SPEC"
+    },
+    {
+        "ArchStdEvent": "SVE_PRED_PARTIAL_SPEC"
+    },
+    {
+        "ArchStdEvent": "SVE_PRED_NOT_FULL_SPEC"
+    },
+    {
+        "ArchStdEvent": "SVE_LDFF_SPEC"
+    },
+    {
+        "ArchStdEvent": "SVE_LDFF_FAULT_SPEC"
+    },
+    {
+        "ArchStdEvent": "FP_SCALE_OPS_SPEC"
+    },
+    {
+        "ArchStdEvent": "FP_FIXED_OPS_SPEC"
+    },
+    {
+        "ArchStdEvent": "ASE_SVE_INT8_SPEC"
+    },
+    {
+        "ArchStdEvent": "ASE_SVE_INT16_SPEC"
+    },
+    {
+        "ArchStdEvent": "ASE_SVE_INT32_SPEC"
+    },
+    {
+        "ArchStdEvent": "ASE_SVE_INT64_SPEC"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/memory.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/memory.json
new file mode 100644
index 000000000000..e522113aeb96
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/memory.json
@@ -0,0 +1,38 @@
+[
+    {
+        "ArchStdEvent": "MEM_ACCESS"
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_RD"
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_WR"
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LD_SPEC"
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_ST_SPEC"
+    },
+    {
+        "ArchStdEvent": "UNALIGNED_LDST_SPEC"
+    },
+    {
+        "ArchStdEvent": "LDST_ALIGN_LAT"
+    },
+    {
+        "ArchStdEvent": "LD_ALIGN_LAT"
+    },
+    {
+        "ArchStdEvent": "ST_ALIGN_LAT"
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_CHECKED"
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_CHECKED_RD"
+    },
+    {
+        "ArchStdEvent": "MEM_ACCESS_CHECKED_WR"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/other.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/other.json
new file mode 100644
index 000000000000..20d8365756c5
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/other.json
@@ -0,0 +1,5 @@
+[
+    {
+        "ArchStdEvent": "REMOTE_ACCESS"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/pipeline.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/pipeline.json
new file mode 100644
index 000000000000..f9fae15f7555
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/pipeline.json
@@ -0,0 +1,23 @@
+[
+    {
+        "ArchStdEvent": "STALL_FRONTEND"
+    },
+    {
+        "ArchStdEvent": "STALL_BACKEND"
+    },
+    {
+        "ArchStdEvent": "STALL"
+    },
+    {
+        "ArchStdEvent": "STALL_SLOT_BACKEND"
+    },
+    {
+        "ArchStdEvent": "STALL_SLOT_FRONTEND"
+    },
+    {
+        "ArchStdEvent": "STALL_SLOT"
+    },
+    {
+        "ArchStdEvent": "STALL_BACKEND_MEM"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/spe.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/spe.json
new file mode 100644
index 000000000000..20f2165c85fe
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/spe.json
@@ -0,0 +1,14 @@
+[
+    {
+        "ArchStdEvent": "SAMPLE_POP"
+    },
+    {
+        "ArchStdEvent": "SAMPLE_FEED"
+    },
+    {
+        "ArchStdEvent": "SAMPLE_FILTRATE"
+    },
+    {
+        "ArchStdEvent": "SAMPLE_COLLISION"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/trace.json b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/trace.json
new file mode 100644
index 000000000000..3116135c59e2
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/neoverse-n2/trace.json
@@ -0,0 +1,29 @@
+[
+    {
+        "ArchStdEvent": "TRB_WRAP"
+    },
+    {
+        "ArchStdEvent": "TRCEXTOUT0"
+    },
+    {
+        "ArchStdEvent": "TRCEXTOUT1"
+    },
+    {
+        "ArchStdEvent": "TRCEXTOUT2"
+    },
+    {
+        "ArchStdEvent": "TRCEXTOUT3"
+    },
+    {
+        "ArchStdEvent": "CTI_TRIGOUT4"
+    },
+    {
+        "ArchStdEvent": "CTI_TRIGOUT5"
+    },
+    {
+        "ArchStdEvent": "CTI_TRIGOUT6"
+    },
+    {
+        "ArchStdEvent": "CTI_TRIGOUT7"
+    }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/armv8-common-and-microarch.json b/tools/perf/pmu-events/arch/arm64/common-and-microarch.json
index 423767510aff..80d7a70829a0 100644
--- a/tools/perf/pmu-events/arch/arm64/armv8-common-and-microarch.json
+++ b/tools/perf/pmu-events/arch/arm64/common-and-microarch.json
@@ -300,6 +300,30 @@
         "BriefDescription": "No operation sent for execution on a slot"
     },
     {
+        "PublicDescription": "Sample Population",
+        "EventCode": "0x4000",
+        "EventName": "SAMPLE_POP",
+        "BriefDescription": "Sample Population"
+    },
+    {
+        "PublicDescription": "Sample Taken",
+        "EventCode": "0x4001",
+        "EventName": "SAMPLE_FEED",
+        "BriefDescription": "Sample Taken"
+    },
+    {
+        "PublicDescription": "Sample Taken and not removed by filtering",
+        "EventCode": "0x4002",
+        "EventName": "SAMPLE_FILTRATE",
+        "BriefDescription": "Sample Taken and not removed by filtering"
+    },
+    {
+        "PublicDescription": "Sample collided with previous sample",
+        "EventCode": "0x4003",
+        "EventName": "SAMPLE_COLLISION",
+        "BriefDescription": "Sample collided with previous sample"
+    },
+    {
         "PublicDescription": "Constant frequency cycles.  The counter increments at a constant frequency equal to the rate of increment of the system counter, CNTPCT_EL0.",
         "EventCode": "0x4004",
         "EventName": "CNT_CYCLES",
@@ -330,6 +354,96 @@
         "BriefDescription": "Level 3 data cache long-latency read miss"
     },
     {
+        "PublicDescription": "Trace buffer current write pointer wrapped",
+        "EventCode": "0x400C",
+        "EventName": "TRB_WRAP",
+        "BriefDescription": "Trace buffer current write pointer wrapped"
+    },
+    {
+        "PublicDescription": "PE Trace Unit external output 0",
+        "EventCode": "0x4010",
+        "EventName": "TRCEXTOUT0",
+        "BriefDescription": "PE Trace Unit external output 0"
+    },
+    {
+        "PublicDescription": "PE Trace Unit external output 1",
+        "EventCode": "0x4011",
+        "EventName": "TRCEXTOUT1",
+        "BriefDescription": "PE Trace Unit external output 1"
+    },
+    {
+        "PublicDescription": "PE Trace Unit external output 2",
+        "EventCode": "0x4012",
+        "EventName": "TRCEXTOUT2",
+        "BriefDescription": "PE Trace Unit external output 2"
+    },
+    {
+        "PublicDescription": "PE Trace Unit external output 3",
+        "EventCode": "0x4013",
+        "EventName": "TRCEXTOUT3",
+        "BriefDescription": "PE Trace Unit external output 3"
+    },
+    {
+        "PublicDescription": "Cross-trigger Interface output trigger 4",
+        "EventCode": "0x4018",
+        "EventName": "CTI_TRIGOUT4",
+        "BriefDescription": "Cross-trigger Interface output trigger 4"
+    },
+    {
+        "PublicDescription": "Cross-trigger Interface output trigger 5 ",
+        "EventCode": "0x4019",
+        "EventName": "CTI_TRIGOUT5",
+        "BriefDescription": "Cross-trigger Interface output trigger 5 "
+    },
+    {
+        "PublicDescription": "Cross-trigger Interface output trigger 6",
+        "EventCode": "0x401A",
+        "EventName": "CTI_TRIGOUT6",
+        "BriefDescription": "Cross-trigger Interface output trigger 6"
+    },
+    {
+        "PublicDescription": "Cross-trigger Interface output trigger 7",
+        "EventCode": "0x401B",
+        "EventName": "CTI_TRIGOUT7",
+        "BriefDescription": "Cross-trigger Interface output trigger 7"
+    },
+    {
+        "PublicDescription": "Access with additional latency from alignment",
+        "EventCode": "0x4020",
+        "EventName": "LDST_ALIGN_LAT",
+        "BriefDescription": "Access with additional latency from alignment"
+    },
+    {
+        "PublicDescription": "Load with additional latency from alignment",
+        "EventCode": "0x4021",
+        "EventName": "LD_ALIGN_LAT",
+        "BriefDescription": "Load with additional latency from alignment"
+    },
+    {
+        "PublicDescription": "Store with additional latency from alignment",
+        "EventCode": "0x4022",
+        "EventName": "ST_ALIGN_LAT",
+        "BriefDescription": "Store with additional latency from alignment"
+    },
+    {
+        "PublicDescription": "Checked data memory access",
+        "EventCode": "0x4024",
+        "EventName": "MEM_ACCESS_CHECKED",
+        "BriefDescription": "Checked data memory access"
+    },
+    {
+        "PublicDescription": "Checked data memory access, read",
+        "EventCode": "0x4025",
+        "EventName": "MEM_ACCESS_CHECKED_RD",
+        "BriefDescription": "Checked data memory access, read"
+    },
+    {
+        "PublicDescription": "Checked data memory access, write",
+        "EventCode": "0x4026",
+        "EventName": "MEM_ACCESS_CHECKED_WR",
+        "BriefDescription": "Checked data memory access, write"
+    },
+    {
         "PublicDescription": "SIMD Instruction architecturally executed.",
         "EventCode": "0x8000",
         "EventName": "SIMD_INST_RETIRED",
@@ -342,6 +456,18 @@
         "BriefDescription": "Instruction architecturally executed, SVE."
     },
     {
+        "PublicDescription": "ASE operations speculatively executed",
+        "EventCode": "0x8005",
+        "EventName": "ASE_INST_SPEC",
+        "BriefDescription": "ASE operations speculatively executed"
+    },
+    {
+        "PublicDescription": "SVE operations speculatively executed",
+        "EventCode": "0x8006",
+        "EventName": "SVE_INST_SPEC",
+        "BriefDescription": "SVE operations speculatively executed"
+    },
+    {
         "PublicDescription": "Microarchitectural operation, Operations speculatively executed.",
         "EventCode": "0x8008",
         "EventName": "UOP_SPEC",
@@ -360,6 +486,24 @@
         "BriefDescription": "Floating-point Operations speculatively executed."
     },
     {
+        "PublicDescription": "Floating-point half-precision operations speculatively executed",
+        "EventCode": "0x8014",
+        "EventName": "FP_HP_SPEC",
+        "BriefDescription": "Floating-point half-precision operations speculatively executed"
+    },
+    {
+        "PublicDescription": "Floating-point single-precision operations speculatively executed",
+        "EventCode": "0x8018",
+        "EventName": "FP_SP_SPEC",
+        "BriefDescription": "Floating-point single-precision operations speculatively executed"
+    },
+    {
+        "PublicDescription": "Floating-point double-precision operations speculatively executed",
+        "EventCode": "0x801C",
+        "EventName": "FP_DP_SPEC",
+        "BriefDescription": "Floating-point double-precision operations speculatively executed"
+    },
+    {
         "PublicDescription": "Floating-point FMA Operations speculatively executed.",
         "EventCode": "0x8028",
         "EventName": "FP_FMA_SPEC",
@@ -390,6 +534,30 @@
         "BriefDescription": "SVE predicated Operations speculatively executed."
     },
     {
+        "PublicDescription": "SVE predicated operations with no active predicates speculatively executed",
+        "EventCode": "0x8075",
+        "EventName": "SVE_PRED_EMPTY_SPEC",
+        "BriefDescription": "SVE predicated operations with no active predicates speculatively executed"
+    },
+    {
+        "PublicDescription": "SVE predicated operations speculatively executed with all active predicates",
+        "EventCode": "0x8076",
+        "EventName": "SVE_PRED_FULL_SPEC",
+        "BriefDescription": "SVE predicated operations speculatively executed with all active predicates"
+    },
+    {
+        "PublicDescription": "SVE predicated operations speculatively executed with partially active predicates",
+        "EventCode": "0x8077",
+        "EventName": "SVE_PRED_PARTIAL_SPEC",
+        "BriefDescription": "SVE predicated operations speculatively executed with partially active predicates"
+    },
+    {
+        "PublicDescription": "SVE predicated operations with empty or partially active predicates",
+        "EventCode": "0x8079",
+        "EventName": "SVE_PRED_NOT_FULL_SPEC",
+        "BriefDescription": "SVE predicated operations with empty or partially active predicates"
+    },
+    {
         "PublicDescription": "SVE MOVPRFX Operations speculatively executed.",
         "EventCode": "0x807C",
         "EventName": "SVE_MOVPRFX_SPEC",
@@ -498,6 +666,12 @@
         "BriefDescription": "SVE First-fault load Operations speculatively executed."
     },
     {
+        "PublicDescription": "SVE first-fault load operations speculatively executed which set FFR bit to 0",
+        "EventCode": "0x80BD",
+        "EventName": "SVE_LDFF_FAULT_SPEC",
+        "BriefDescription": "SVE first-fault load operations speculatively executed which set FFR bit to 0"
+    },
+    {
         "PublicDescription": "Scalable floating-point element Operations speculatively executed.",
         "EventCode": "0x80C0",
         "EventName": "FP_SCALE_OPS_SPEC",
@@ -544,5 +718,29 @@
         "EventCode": "0x80C7",
         "EventName": "FP_DP_FIXED_OPS_SPEC",
         "BriefDescription": "Non-scalable double-precision floating-point element Operations speculatively executed."
+    },
+    {
+        "PublicDescription": "Advanced SIMD and SVE 8-bit integer operations speculatively executed",
+        "EventCode": "0x80E3",
+        "EventName": "ASE_SVE_INT8_SPEC",
+        "BriefDescription": "Advanced SIMD and SVE 8-bit integer operations speculatively executed"
+    },
+    {
+        "PublicDescription": "Advanced SIMD and SVE 16-bit integer operations speculatively executed",
+        "EventCode": "0x80E7",
+        "EventName": "ASE_SVE_INT16_SPEC",
+        "BriefDescription": "Advanced SIMD and SVE 16-bit integer operations speculatively executed"
+    },
+    {
+        "PublicDescription": "Advanced SIMD and SVE 32-bit integer operations speculatively executed",
+        "EventCode": "0x80EB",
+        "EventName": "ASE_SVE_INT32_SPEC",
+        "BriefDescription": "Advanced SIMD and SVE 32-bit integer operations speculatively executed"
+    },
+    {
+        "PublicDescription": "Advanced SIMD and SVE 64-bit integer operations speculatively executed",
+        "EventCode": "0x80EF",
+        "EventName": "ASE_SVE_INT64_SPEC",
+        "BriefDescription": "Advanced SIMD and SVE 64-bit integer operations speculatively executed"
     }
 ]
diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv
index 31d8b57ca9bb..b899db48c12a 100644
--- a/tools/perf/pmu-events/arch/arm64/mapfile.csv
+++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv
@@ -19,6 +19,7 @@
 0x00000000410fd0b0,v1,arm/cortex-a76-n1,core
 0x00000000410fd0c0,v1,arm/cortex-a76-n1,core
 0x00000000410fd400,v1,arm/neoverse-v1,core
+0x00000000410fd490,v1,arm/neoverse-n2,core
 0x00000000420f5160,v1,cavium/thunderx2,core
 0x00000000430f0af0,v1,cavium/thunderx2,core
 0x00000000460f0010,v1,fujitsu/a64fx,core
diff --git a/tools/perf/pmu-events/arch/arm64/armv8-recommended.json b/tools/perf/pmu-events/arch/arm64/recommended.json
index d0a19866563d..210afa856091 100644
--- a/tools/perf/pmu-events/arch/arm64/armv8-recommended.json
+++ b/tools/perf/pmu-events/arch/arm64/recommended.json
@@ -148,305 +148,305 @@
         "EventCode": "0x60",
         "EventName": "BUS_ACCESS_RD",
         "BriefDescription": "Bus access read"
-   },
-   {
+    },
+    {
         "PublicDescription": "Bus access write",
         "EventCode": "0x61",
         "EventName": "BUS_ACCESS_WR",
         "BriefDescription": "Bus access write"
-   },
-   {
+    },
+    {
         "PublicDescription": "Bus access, Normal, Cacheable, Shareable",
         "EventCode": "0x62",
         "EventName": "BUS_ACCESS_SHARED",
         "BriefDescription": "Bus access, Normal, Cacheable, Shareable"
-   },
-   {
+    },
+    {
         "PublicDescription": "Bus access, not Normal, Cacheable, Shareable",
         "EventCode": "0x63",
         "EventName": "BUS_ACCESS_NOT_SHARED",
         "BriefDescription": "Bus access, not Normal, Cacheable, Shareable"
-   },
-   {
+    },
+    {
         "PublicDescription": "Bus access, Normal",
         "EventCode": "0x64",
         "EventName": "BUS_ACCESS_NORMAL",
         "BriefDescription": "Bus access, Normal"
-   },
-   {
+    },
+    {
         "PublicDescription": "Bus access, peripheral",
         "EventCode": "0x65",
         "EventName": "BUS_ACCESS_PERIPH",
         "BriefDescription": "Bus access, peripheral"
-   },
-   {
+    },
+    {
         "PublicDescription": "Data memory access, read",
         "EventCode": "0x66",
         "EventName": "MEM_ACCESS_RD",
         "BriefDescription": "Data memory access, read"
-   },
-   {
+    },
+    {
         "PublicDescription": "Data memory access, write",
         "EventCode": "0x67",
         "EventName": "MEM_ACCESS_WR",
         "BriefDescription": "Data memory access, write"
-   },
-   {
+    },
+    {
         "PublicDescription": "Unaligned access, read",
         "EventCode": "0x68",
         "EventName": "UNALIGNED_LD_SPEC",
         "BriefDescription": "Unaligned access, read"
-   },
-   {
+    },
+    {
         "PublicDescription": "Unaligned access, write",
         "EventCode": "0x69",
         "EventName": "UNALIGNED_ST_SPEC",
         "BriefDescription": "Unaligned access, write"
-   },
-   {
+    },
+    {
         "PublicDescription": "Unaligned access",
         "EventCode": "0x6a",
         "EventName": "UNALIGNED_LDST_SPEC",
         "BriefDescription": "Unaligned access"
-   },
-   {
+    },
+    {
         "PublicDescription": "Exclusive operation speculatively executed, LDREX or LDX",
         "EventCode": "0x6c",
         "EventName": "LDREX_SPEC",
         "BriefDescription": "Exclusive operation speculatively executed, LDREX or LDX"
-   },
-   {
+    },
+    {
         "PublicDescription": "Exclusive operation speculatively executed, STREX or STX pass",
         "EventCode": "0x6d",
         "EventName": "STREX_PASS_SPEC",
         "BriefDescription": "Exclusive operation speculatively executed, STREX or STX pass"
-   },
-   {
+    },
+    {
         "PublicDescription": "Exclusive operation speculatively executed, STREX or STX fail",
         "EventCode": "0x6e",
         "EventName": "STREX_FAIL_SPEC",
         "BriefDescription": "Exclusive operation speculatively executed, STREX or STX fail"
-   },
-   {
+    },
+    {
         "PublicDescription": "Exclusive operation speculatively executed, STREX or STX",
         "EventCode": "0x6f",
         "EventName": "STREX_SPEC",
         "BriefDescription": "Exclusive operation speculatively executed, STREX or STX"
-   },
-   {
+    },
+    {
         "PublicDescription": "Operation speculatively executed, load",
         "EventCode": "0x70",
         "EventName": "LD_SPEC",
         "BriefDescription": "Operation speculatively executed, load"
-   },
-   {
+    },
+    {
         "PublicDescription": "Operation speculatively executed, store",
         "EventCode": "0x71",
         "EventName": "ST_SPEC",
         "BriefDescription": "Operation speculatively executed, store"
-   },
-   {
+    },
+    {
         "PublicDescription": "Operation speculatively executed, load or store",
         "EventCode": "0x72",
         "EventName": "LDST_SPEC",
         "BriefDescription": "Operation speculatively executed, load or store"
-   },
-   {
+    },
+    {
         "PublicDescription": "Operation speculatively executed, integer data processing",
         "EventCode": "0x73",
         "EventName": "DP_SPEC",
         "BriefDescription": "Operation speculatively executed, integer data processing"
-   },
-   {
+    },
+    {
         "PublicDescription": "Operation speculatively executed, Advanced SIMD instruction",
         "EventCode": "0x74",
         "EventName": "ASE_SPEC",
         "BriefDescription": "Operation speculatively executed, Advanced SIMD instruction"
-   },
-   {
+    },
+    {
         "PublicDescription": "Operation speculatively executed, floating-point instruction",
         "EventCode": "0x75",
         "EventName": "VFP_SPEC",
         "BriefDescription": "Operation speculatively executed, floating-point instruction"
-   },
-   {
+    },
+    {
         "PublicDescription": "Operation speculatively executed, software change of the PC",
         "EventCode": "0x76",
         "EventName": "PC_WRITE_SPEC",
         "BriefDescription": "Operation speculatively executed, software change of the PC"
-   },
-   {
+    },
+    {
         "PublicDescription": "Operation speculatively executed, Cryptographic instruction",
         "EventCode": "0x77",
         "EventName": "CRYPTO_SPEC",
         "BriefDescription": "Operation speculatively executed, Cryptographic instruction"
-   },
-   {
+    },
+    {
         "PublicDescription": "Branch speculatively executed, immediate branch",
         "EventCode": "0x78",
         "EventName": "BR_IMMED_SPEC",
         "BriefDescription": "Branch speculatively executed, immediate branch"
-   },
-   {
+    },
+    {
         "PublicDescription": "Branch speculatively executed, procedure return",
         "EventCode": "0x79",
         "EventName": "BR_RETURN_SPEC",
         "BriefDescription": "Branch speculatively executed, procedure return"
-   },
-   {
+    },
+    {
         "PublicDescription": "Branch speculatively executed, indirect branch",
         "EventCode": "0x7a",
         "EventName": "BR_INDIRECT_SPEC",
         "BriefDescription": "Branch speculatively executed, indirect branch"
-   },
-   {
+    },
+    {
         "PublicDescription": "Barrier speculatively executed, ISB",
         "EventCode": "0x7c",
         "EventName": "ISB_SPEC",
         "BriefDescription": "Barrier speculatively executed, ISB"
-   },
-   {
+    },
+    {
         "PublicDescription": "Barrier speculatively executed, DSB",
         "EventCode": "0x7d",
         "EventName": "DSB_SPEC",
         "BriefDescription": "Barrier speculatively executed, DSB"
-   },
-   {
+    },
+    {
         "PublicDescription": "Barrier speculatively executed, DMB",
         "EventCode": "0x7e",
         "EventName": "DMB_SPEC",
         "BriefDescription": "Barrier speculatively executed, DMB"
-   },
-   {
+    },
+    {
         "PublicDescription": "Exception taken, Other synchronous",
         "EventCode": "0x81",
         "EventName": "EXC_UNDEF",
         "BriefDescription": "Exception taken, Other synchronous"
-   },
-   {
+    },
+    {
         "PublicDescription": "Exception taken, Supervisor Call",
         "EventCode": "0x82",
         "EventName": "EXC_SVC",
         "BriefDescription": "Exception taken, Supervisor Call"
-   },
-   {
+    },
+    {
         "PublicDescription": "Exception taken, Instruction Abort",
         "EventCode": "0x83",
         "EventName": "EXC_PABORT",
         "BriefDescription": "Exception taken, Instruction Abort"
-   },
-   {
+    },
+    {
         "PublicDescription": "Exception taken, Data Abort and SError",
         "EventCode": "0x84",
         "EventName": "EXC_DABORT",
         "BriefDescription": "Exception taken, Data Abort and SError"
-   },
-   {
+    },
+    {
         "PublicDescription": "Exception taken, IRQ",
         "EventCode": "0x86",
         "EventName": "EXC_IRQ",
         "BriefDescription": "Exception taken, IRQ"
-   },
-   {
+    },
+    {
         "PublicDescription": "Exception taken, FIQ",
         "EventCode": "0x87",
         "EventName": "EXC_FIQ",
         "BriefDescription": "Exception taken, FIQ"
-   },
-   {
+    },
+    {
         "PublicDescription": "Exception taken, Secure Monitor Call",
         "EventCode": "0x88",
         "EventName": "EXC_SMC",
         "BriefDescription": "Exception taken, Secure Monitor Call"
-   },
-   {
+    },
+    {
         "PublicDescription": "Exception taken, Hypervisor Call",
         "EventCode": "0x8a",
         "EventName": "EXC_HVC",
         "BriefDescription": "Exception taken, Hypervisor Call"
-   },
-   {
+    },
+    {
         "PublicDescription": "Exception taken, Instruction Abort not taken locally",
         "EventCode": "0x8b",
         "EventName": "EXC_TRAP_PABORT",
         "BriefDescription": "Exception taken, Instruction Abort not taken locally"
-   },
-   {
+    },
+    {
         "PublicDescription": "Exception taken, Data Abort or SError not taken locally",
         "EventCode": "0x8c",
         "EventName": "EXC_TRAP_DABORT",
         "BriefDescription": "Exception taken, Data Abort or SError not taken locally"
-   },
-   {
+    },
+    {
         "PublicDescription": "Exception taken, Other traps not taken locally",
         "EventCode": "0x8d",
         "EventName": "EXC_TRAP_OTHER",
         "BriefDescription": "Exception taken, Other traps not taken locally"
-   },
-   {
+    },
+    {
         "PublicDescription": "Exception taken, IRQ not taken locally",
         "EventCode": "0x8e",
         "EventName": "EXC_TRAP_IRQ",
         "BriefDescription": "Exception taken, IRQ not taken locally"
-   },
-   {
+    },
+    {
         "PublicDescription": "Exception taken, FIQ not taken locally",
         "EventCode": "0x8f",
         "EventName": "EXC_TRAP_FIQ",
         "BriefDescription": "Exception taken, FIQ not taken locally"
-   },
-   {
+    },
+    {
         "PublicDescription": "Release consistency operation speculatively executed, Load-Acquire",
         "EventCode": "0x90",
         "EventName": "RC_LD_SPEC",
         "BriefDescription": "Release consistency operation speculatively executed, Load-Acquire"
-   },
-   {
+    },
+    {
         "PublicDescription": "Release consistency operation speculatively executed, Store-Release",
         "EventCode": "0x91",
         "EventName": "RC_ST_SPEC",
         "BriefDescription": "Release consistency operation speculatively executed, Store-Release"
-   },
-   {
+    },
+    {
         "PublicDescription": "Attributable Level 3 data or unified cache access, read",
         "EventCode": "0xa0",
         "EventName": "L3D_CACHE_RD",
         "BriefDescription": "Attributable Level 3 data or unified cache access, read"
-   },
-   {
+    },
+    {
         "PublicDescription": "Attributable Level 3 data or unified cache access, write",
         "EventCode": "0xa1",
         "EventName": "L3D_CACHE_WR",
         "BriefDescription": "Attributable Level 3 data or unified cache access, write"
-   },
-   {
+    },
+    {
         "PublicDescription": "Attributable Level 3 data or unified cache refill, read",
         "EventCode": "0xa2",
         "EventName": "L3D_CACHE_REFILL_RD",
         "BriefDescription": "Attributable Level 3 data or unified cache refill, read"
-   },
-   {
+    },
+    {
         "PublicDescription": "Attributable Level 3 data or unified cache refill, write",
         "EventCode": "0xa3",
         "EventName": "L3D_CACHE_REFILL_WR",
         "BriefDescription": "Attributable Level 3 data or unified cache refill, write"
-   },
-   {
+    },
+    {
         "PublicDescription": "Attributable Level 3 data or unified cache Write-Back, victim",
         "EventCode": "0xa6",
         "EventName": "L3D_CACHE_WB_VICTIM",
         "BriefDescription": "Attributable Level 3 data or unified cache Write-Back, victim"
-   },
-   {
+    },
+    {
         "PublicDescription": "Attributable Level 3 data or unified cache Write-Back, cache clean",
         "EventCode": "0xa7",
         "EventName": "L3D_CACHE_WB_CLEAN",
         "BriefDescription": "Attributable Level 3 data or unified cache Write-Back, cache clean"
-   },
-   {
+    },
+    {
         "PublicDescription": "Attributable Level 3 data or unified cache access, invalidate",
         "EventCode": "0xa8",
         "EventName": "L3D_CACHE_INVAL",
         "BriefDescription": "Attributable Level 3 data or unified cache access, invalidate"
-   }
+    }
 ]
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index 2e7c4153875b..1a57c3f81dd4 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -672,8 +672,6 @@ static int json_events(const char *fn,
 				addfield(map, &je.metric_constraint, "", "", val);
 			} else if (json_streq(map, field, "MetricExpr")) {
 				addfield(map, &je.metric_expr, "", "", val);
-				for (s = je.metric_expr; *s; s++)
-					*s = tolower(*s);
 			} else if (json_streq(map, field, "ArchStdEvent")) {
 				addfield(map, &arch_std, "", "", val);
 				for (s = arch_std; *s; s++)
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 803ca426f8e6..af2b37ef7c70 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -65,6 +65,7 @@ perf-y += pe-file-parsing.o
 perf-y += expand-cgroup.o
 perf-y += perf-time-to-tsc.o
 perf-y += dlfilter-test.o
+perf-y += sigtrap.o
 
 $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
 	$(call rule_mkdir)
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 0f73e300f207..56fba08a3037 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -65,7 +65,7 @@ do {									\
 
 #define WRITE_ASS(field, fmt) __WRITE_ASS(field, fmt, attr->field)
 
-static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu,
+static int store_event(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu,
 		       int fd, int group_fd, unsigned long flags)
 {
 	FILE *file;
@@ -93,7 +93,7 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu,
 	/* syscall arguments */
 	__WRITE_ASS(fd,       "d", fd);
 	__WRITE_ASS(group_fd, "d", group_fd);
-	__WRITE_ASS(cpu,      "d", cpu);
+	__WRITE_ASS(cpu,      "d", cpu.cpu);
 	__WRITE_ASS(pid,      "d", pid);
 	__WRITE_ASS(flags,   "lu", flags);
 
@@ -144,7 +144,7 @@ static int store_event(struct perf_event_attr *attr, pid_t pid, int cpu,
 	return 0;
 }
 
-void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
+void test_attr__open(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu,
 		     int fd, int group_fd, unsigned long flags)
 {
 	int errno_saved = errno;
diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c
index 384856347236..0bf399c49849 100644
--- a/tools/perf/tests/bitmap.c
+++ b/tools/perf/tests/bitmap.c
@@ -18,7 +18,7 @@ static unsigned long *get_bitmap(const char *str, int nbits)
 
 	if (map && bm) {
 		for (i = 0; i < map->nr; i++)
-			set_bit(map->map[i], bm);
+			set_bit(map->map[i].cpu, bm);
 	}
 
 	if (map)
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index 8cb5a1c3489e..fac3717d9ba1 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -107,6 +107,7 @@ static struct test_suite *generic_tests[] = {
 	&suite__expand_cgroup_events,
 	&suite__perf_time_to_tsc,
 	&suite__dlfilter,
+	&suite__sigtrap,
 	NULL,
 };
 
@@ -420,7 +421,7 @@ static int run_shell_tests(int argc, const char *argv[], int i, int width,
 			continue;
 
 		st.file = ent->d_name;
-		pr_info("%2d: %-*s:", i, width, test_suite.desc);
+		pr_info("%3d: %-*s:", i, width, test_suite.desc);
 
 		if (intlist__find(skiplist, i)) {
 			color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n");
@@ -470,7 +471,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 				continue;
 		}
 
-		pr_info("%2d: %-*s:", i, width, test_description(t, -1));
+		pr_info("%3d: %-*s:", i, width, test_description(t, -1));
 
 		if (intlist__find(skiplist, i)) {
 			color_fprintf(stderr, PERF_COLOR_YELLOW, " Skip (user override)\n");
@@ -510,7 +511,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 							curr, argc, argv))
 					continue;
 
-				pr_info("%2d.%1d: %-*s:", i, subi + 1, subw,
+				pr_info("%3d.%1d: %-*s:", i, subi + 1, subw,
 					test_description(t, subi));
 				test_and_print(t, subi);
 			}
@@ -545,7 +546,7 @@ static int perf_test__list_shell(int argc, const char **argv, int i)
 		if (!perf_test__matches(t.desc, curr, argc, argv))
 			continue;
 
-		pr_info("%2d: %s\n", i, t.desc);
+		pr_info("%3d: %s\n", i, t.desc);
 
 	}
 
@@ -567,14 +568,14 @@ static int perf_test__list(int argc, const char **argv)
 		if (!perf_test__matches(test_description(t, -1), curr, argc, argv))
 			continue;
 
-		pr_info("%2d: %s\n", i, test_description(t, -1));
+		pr_info("%3d: %s\n", i, test_description(t, -1));
 
 		if (has_subtests(t)) {
 			int subn = num_subtests(t);
 			int subi;
 
 			for (subi = 0; subi < subn; subi++)
-				pr_info("%2d:%1d: %s\n", i, subi + 1,
+				pr_info("%3d:%1d: %s\n", i, subi + 1,
 					test_description(t, subi));
 		}
 	}
@@ -606,6 +607,9 @@ int cmd_test(int argc, const char **argv)
         if (ret < 0)
                 return ret;
 
+	/* Unbuffered output */
+	setvbuf(stdout, NULL, _IONBF, 0);
+
 	argc = parse_options_subcommand(argc, argv, test_options, test_subcommands, test_usage, 0);
 	if (argc >= 1 && !strcmp(argv[0], "list"))
 		return perf_test__list(argc - 1, argv + 1);
diff --git a/tools/perf/tests/cpumap.c b/tools/perf/tests/cpumap.c
index 89a155092f85..84e87e31f119 100644
--- a/tools/perf/tests/cpumap.c
+++ b/tools/perf/tests/cpumap.c
@@ -38,7 +38,7 @@ static int process_event_mask(struct perf_tool *tool __maybe_unused,
 	TEST_ASSERT_VAL("wrong nr",  map->nr == 20);
 
 	for (i = 0; i < 20; i++) {
-		TEST_ASSERT_VAL("wrong cpu", map->map[i] == i);
+		TEST_ASSERT_VAL("wrong cpu", map->map[i].cpu == i);
 	}
 
 	perf_cpu_map__put(map);
@@ -67,8 +67,8 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 
 	map = cpu_map__new_data(data);
 	TEST_ASSERT_VAL("wrong nr",  map->nr == 2);
-	TEST_ASSERT_VAL("wrong cpu", map->map[0] == 1);
-	TEST_ASSERT_VAL("wrong cpu", map->map[1] == 256);
+	TEST_ASSERT_VAL("wrong cpu", map->map[0].cpu == 1);
+	TEST_ASSERT_VAL("wrong cpu", map->map[1].cpu == 256);
 	TEST_ASSERT_VAL("wrong refcnt", refcount_read(&map->refcnt) == 1);
 	perf_cpu_map__put(map);
 	return 0;
diff --git a/tools/perf/tests/event_update.c b/tools/perf/tests/event_update.c
index d01532d40acb..16b6d6f47f38 100644
--- a/tools/perf/tests/event_update.c
+++ b/tools/perf/tests/event_update.c
@@ -76,9 +76,9 @@ static int process_event_cpus(struct perf_tool *tool __maybe_unused,
 	TEST_ASSERT_VAL("wrong id", ev->id == 123);
 	TEST_ASSERT_VAL("wrong type", ev->type == PERF_EVENT_UPDATE__CPUS);
 	TEST_ASSERT_VAL("wrong cpus", map->nr == 3);
-	TEST_ASSERT_VAL("wrong cpus", map->map[0] == 1);
-	TEST_ASSERT_VAL("wrong cpus", map->map[1] == 2);
-	TEST_ASSERT_VAL("wrong cpus", map->map[2] == 3);
+	TEST_ASSERT_VAL("wrong cpus", map->map[0].cpu == 1);
+	TEST_ASSERT_VAL("wrong cpus", map->map[1].cpu == 2);
+	TEST_ASSERT_VAL("wrong cpus", map->map[2].cpu == 3);
 	perf_cpu_map__put(map);
 	return 0;
 }
diff --git a/tools/perf/tests/mem2node.c b/tools/perf/tests/mem2node.c
index b17b86391383..f4a4aba33f76 100644
--- a/tools/perf/tests/mem2node.c
+++ b/tools/perf/tests/mem2node.c
@@ -31,7 +31,7 @@ static unsigned long *get_bitmap(const char *str, int nbits)
 
 	if (map && bm) {
 		for (i = 0; i < map->nr; i++) {
-			set_bit(map->map[i], bm);
+			set_bit(map->map[i].cpu, bm);
 		}
 	}
 
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index 90b2feda31ac..0ad62914b4d7 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -59,11 +59,11 @@ static int test__basic_mmap(struct test_suite *test __maybe_unused, int subtest
 	}
 
 	CPU_ZERO(&cpu_set);
-	CPU_SET(cpus->map[0], &cpu_set);
+	CPU_SET(cpus->map[0].cpu, &cpu_set);
 	sched_setaffinity(0, sizeof(cpu_set), &cpu_set);
 	if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
 		pr_debug("sched_setaffinity() failed on CPU %d: %s ",
-			 cpus->map[0], str_error_r(errno, sbuf, sizeof(sbuf)));
+			 cpus->map[0].cpu, str_error_r(errno, sbuf, sizeof(sbuf)));
 		goto out_free_cpus;
 	}
 
diff --git a/tools/perf/tests/openat-syscall-all-cpus.c b/tools/perf/tests/openat-syscall-all-cpus.c
index cd3dd463783f..1ab362323d25 100644
--- a/tools/perf/tests/openat-syscall-all-cpus.c
+++ b/tools/perf/tests/openat-syscall-all-cpus.c
@@ -22,7 +22,8 @@
 static int test__openat_syscall_event_on_all_cpus(struct test_suite *test __maybe_unused,
 						  int subtest __maybe_unused)
 {
-	int err = -1, fd, cpu;
+	int err = -1, fd, idx;
+	struct perf_cpu cpu;
 	struct perf_cpu_map *cpus;
 	struct evsel *evsel;
 	unsigned int nr_openat_calls = 111, i;
@@ -58,23 +59,23 @@ static int test__openat_syscall_event_on_all_cpus(struct test_suite *test __mayb
 		goto out_evsel_delete;
 	}
 
-	for (cpu = 0; cpu < cpus->nr; ++cpu) {
-		unsigned int ncalls = nr_openat_calls + cpu;
+	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+		unsigned int ncalls = nr_openat_calls + idx;
 		/*
 		 * XXX eventually lift this restriction in a way that
 		 * keeps perf building on older glibc installations
 		 * without CPU_ALLOC. 1024 cpus in 2010 still seems
 		 * a reasonable upper limit tho :-)
 		 */
-		if (cpus->map[cpu] >= CPU_SETSIZE) {
-			pr_debug("Ignoring CPU %d\n", cpus->map[cpu]);
+		if (cpu.cpu >= CPU_SETSIZE) {
+			pr_debug("Ignoring CPU %d\n", cpu.cpu);
 			continue;
 		}
 
-		CPU_SET(cpus->map[cpu], &cpu_set);
+		CPU_SET(cpu.cpu, &cpu_set);
 		if (sched_setaffinity(0, sizeof(cpu_set), &cpu_set) < 0) {
 			pr_debug("sched_setaffinity() failed on CPU %d: %s ",
-				 cpus->map[cpu],
+				 cpu.cpu,
 				 str_error_r(errno, sbuf, sizeof(sbuf)));
 			goto out_close_fd;
 		}
@@ -82,37 +83,29 @@ static int test__openat_syscall_event_on_all_cpus(struct test_suite *test __mayb
 			fd = openat(0, "/etc/passwd", O_RDONLY);
 			close(fd);
 		}
-		CPU_CLR(cpus->map[cpu], &cpu_set);
+		CPU_CLR(cpu.cpu, &cpu_set);
 	}
 
-	/*
-	 * Here we need to explicitly preallocate the counts, as if
-	 * we use the auto allocation it will allocate just for 1 cpu,
-	 * as we start by cpu 0.
-	 */
-	if (evsel__alloc_counts(evsel, cpus->nr, 1) < 0) {
-		pr_debug("evsel__alloc_counts(ncpus=%d)\n", cpus->nr);
-		goto out_close_fd;
-	}
+	evsel->core.cpus = perf_cpu_map__get(cpus);
 
 	err = 0;
 
-	for (cpu = 0; cpu < cpus->nr; ++cpu) {
+	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
 		unsigned int expected;
 
-		if (cpus->map[cpu] >= CPU_SETSIZE)
+		if (cpu.cpu >= CPU_SETSIZE)
 			continue;
 
-		if (evsel__read_on_cpu(evsel, cpu, 0) < 0) {
+		if (evsel__read_on_cpu(evsel, idx, 0) < 0) {
 			pr_debug("evsel__read_on_cpu\n");
 			err = -1;
 			break;
 		}
 
-		expected = nr_openat_calls + cpu;
-		if (perf_counts(evsel->counts, cpu, 0)->val != expected) {
+		expected = nr_openat_calls + idx;
+		if (perf_counts(evsel->counts, idx, 0)->val != expected) {
 			pr_debug("evsel__read_on_cpu: expected to intercept %d calls on cpu %d, got %" PRIu64 "\n",
-				 expected, cpus->map[cpu], perf_counts(evsel->counts, cpu, 0)->val);
+				 expected, cpu.cpu, perf_counts(evsel->counts, idx, 0)->val);
 			err = -1;
 		}
 	}
diff --git a/tools/perf/tests/shell/stat_all_metricgroups.sh b/tools/perf/tests/shell/stat_all_metricgroups.sh
index de24d374ce24..cb35e488809a 100755
--- a/tools/perf/tests/shell/stat_all_metricgroups.sh
+++ b/tools/perf/tests/shell/stat_all_metricgroups.sh
@@ -6,7 +6,7 @@ set -e
 
 for m in $(perf list --raw-dump metricgroups); do
   echo "Testing $m"
-  perf stat -M "$m" true
+  perf stat -M "$m" -a true
 done
 
 exit 0
diff --git a/tools/perf/tests/sigtrap.c b/tools/perf/tests/sigtrap.c
new file mode 100644
index 000000000000..1f147fe6595f
--- /dev/null
+++ b/tools/perf/tests/sigtrap.c
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Basic test for sigtrap support.
+ *
+ * Copyright (C) 2021, Google LLC.
+ */
+
+#include <errno.h>
+#include <stdint.h>
+#include <stdlib.h>
+#include <linux/hw_breakpoint.h>
+#include <linux/string.h>
+#include <pthread.h>
+#include <signal.h>
+#include <sys/ioctl.h>
+#include <sys/syscall.h>
+#include <unistd.h>
+
+#include "cloexec.h"
+#include "debug.h"
+#include "event.h"
+#include "tests.h"
+#include "../perf-sys.h"
+
+/*
+ * PowerPC and S390 do not support creation of instruction breakpoints using the
+ * perf_event interface.
+ *
+ * Just disable the test for these architectures until these issues are
+ * resolved.
+ */
+#if defined(__powerpc__) || defined(__s390x__)
+#define BP_ACCOUNT_IS_SUPPORTED 0
+#else
+#define BP_ACCOUNT_IS_SUPPORTED 1
+#endif
+
+#define NUM_THREADS 5
+
+static struct {
+	int tids_want_signal;		/* Which threads still want a signal. */
+	int signal_count;		/* Sanity check number of signals received. */
+	volatile int iterate_on;	/* Variable to set breakpoint on. */
+	siginfo_t first_siginfo;	/* First observed siginfo_t. */
+} ctx;
+
+#define TEST_SIG_DATA (~(unsigned long)(&ctx.iterate_on))
+
+static struct perf_event_attr make_event_attr(void)
+{
+	struct perf_event_attr attr = {
+		.type		= PERF_TYPE_BREAKPOINT,
+		.size		= sizeof(attr),
+		.sample_period	= 1,
+		.disabled	= 1,
+		.bp_addr	= (unsigned long)&ctx.iterate_on,
+		.bp_type	= HW_BREAKPOINT_RW,
+		.bp_len		= HW_BREAKPOINT_LEN_1,
+		.inherit	= 1, /* Children inherit events ... */
+		.inherit_thread = 1, /* ... but only cloned with CLONE_THREAD. */
+		.remove_on_exec = 1, /* Required by sigtrap. */
+		.sigtrap	= 1, /* Request synchronous SIGTRAP on event. */
+		.sig_data	= TEST_SIG_DATA,
+		.exclude_kernel = 1, /* To allow */
+		.exclude_hv     = 1, /* running as !root */
+	};
+	return attr;
+}
+
+static void
+sigtrap_handler(int signum __maybe_unused, siginfo_t *info, void *ucontext __maybe_unused)
+{
+	if (!__atomic_fetch_add(&ctx.signal_count, 1, __ATOMIC_RELAXED))
+		ctx.first_siginfo = *info;
+	__atomic_fetch_sub(&ctx.tids_want_signal, syscall(SYS_gettid), __ATOMIC_RELAXED);
+}
+
+static void *test_thread(void *arg)
+{
+	pthread_barrier_t *barrier = (pthread_barrier_t *)arg;
+	pid_t tid = syscall(SYS_gettid);
+	int i;
+
+	pthread_barrier_wait(barrier);
+
+	__atomic_fetch_add(&ctx.tids_want_signal, tid, __ATOMIC_RELAXED);
+	for (i = 0; i < ctx.iterate_on - 1; i++)
+		__atomic_fetch_add(&ctx.tids_want_signal, tid, __ATOMIC_RELAXED);
+
+	return NULL;
+}
+
+static int run_test_threads(pthread_t *threads, pthread_barrier_t *barrier)
+{
+	int i;
+
+	pthread_barrier_wait(barrier);
+	for (i = 0; i < NUM_THREADS; i++)
+		TEST_ASSERT_EQUAL("pthread_join() failed", pthread_join(threads[i], NULL), 0);
+
+	return TEST_OK;
+}
+
+static int run_stress_test(int fd, pthread_t *threads, pthread_barrier_t *barrier)
+{
+	int ret;
+
+	ctx.iterate_on = 3000;
+
+	TEST_ASSERT_EQUAL("misfired signal?", ctx.signal_count, 0);
+	TEST_ASSERT_EQUAL("enable failed", ioctl(fd, PERF_EVENT_IOC_ENABLE, 0), 0);
+	ret = run_test_threads(threads, barrier);
+	TEST_ASSERT_EQUAL("disable failed", ioctl(fd, PERF_EVENT_IOC_DISABLE, 0), 0);
+
+	TEST_ASSERT_EQUAL("unexpected sigtraps", ctx.signal_count, NUM_THREADS * ctx.iterate_on);
+	TEST_ASSERT_EQUAL("missing signals or incorrectly delivered", ctx.tids_want_signal, 0);
+	TEST_ASSERT_VAL("unexpected si_addr", ctx.first_siginfo.si_addr == &ctx.iterate_on);
+#if 0 /* FIXME: enable when libc's signal.h has si_perf_{type,data} */
+	TEST_ASSERT_EQUAL("unexpected si_perf_type", ctx.first_siginfo.si_perf_type,
+			  PERF_TYPE_BREAKPOINT);
+	TEST_ASSERT_EQUAL("unexpected si_perf_data", ctx.first_siginfo.si_perf_data,
+			  TEST_SIG_DATA);
+#endif
+
+	return ret;
+}
+
+static int test__sigtrap(struct test_suite *test __maybe_unused, int subtest __maybe_unused)
+{
+	struct perf_event_attr attr = make_event_attr();
+	struct sigaction action = {};
+	struct sigaction oldact;
+	pthread_t threads[NUM_THREADS];
+	pthread_barrier_t barrier;
+	char sbuf[STRERR_BUFSIZE];
+	int i, fd, ret = TEST_FAIL;
+
+	if (!BP_ACCOUNT_IS_SUPPORTED) {
+		pr_debug("Test not supported on this architecture");
+		return TEST_SKIP;
+	}
+
+	pthread_barrier_init(&barrier, NULL, NUM_THREADS + 1);
+
+	action.sa_flags = SA_SIGINFO | SA_NODEFER;
+	action.sa_sigaction = sigtrap_handler;
+	sigemptyset(&action.sa_mask);
+	if (sigaction(SIGTRAP, &action, &oldact)) {
+		pr_debug("FAILED sigaction(): %s\n", str_error_r(errno, sbuf, sizeof(sbuf)));
+		goto out;
+	}
+
+	fd = sys_perf_event_open(&attr, 0, -1, -1, perf_event_open_cloexec_flag());
+	if (fd < 0) {
+		pr_debug("FAILED sys_perf_event_open(): %s\n", str_error_r(errno, sbuf, sizeof(sbuf)));
+		goto out_restore_sigaction;
+	}
+
+	for (i = 0; i < NUM_THREADS; i++) {
+		if (pthread_create(&threads[i], NULL, test_thread, &barrier)) {
+			pr_debug("FAILED pthread_create(): %s\n", str_error_r(errno, sbuf, sizeof(sbuf)));
+			goto out_close_perf_event;
+		}
+	}
+
+	ret = run_stress_test(fd, threads, &barrier);
+
+out_close_perf_event:
+	close(fd);
+out_restore_sigaction:
+	sigaction(SIGTRAP, &oldact, NULL);
+out:
+	pthread_barrier_destroy(&barrier);
+	return ret;
+}
+
+DEFINE_SUITE("Sigtrap", sigtrap);
diff --git a/tools/perf/tests/stat.c b/tools/perf/tests/stat.c
index 2eb096b5e6da..500974040fe3 100644
--- a/tools/perf/tests/stat.c
+++ b/tools/perf/tests/stat.c
@@ -87,7 +87,8 @@ static int test__synthesize_stat(struct test_suite *test __maybe_unused, int sub
 	count.run = 300;
 
 	TEST_ASSERT_VAL("failed to synthesize stat_config",
-		!perf_event__synthesize_stat(NULL, 1, 2, 3, &count, process_stat_event, NULL));
+			!perf_event__synthesize_stat(NULL, (struct perf_cpu){.cpu = 1}, 2, 3,
+						     &count, process_stat_event, NULL));
 
 	return 0;
 }
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 8f65098110fc..5bbb8f6a48fc 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -146,6 +146,7 @@ DECLARE_SUITE(pe_file_parsing);
 DECLARE_SUITE(expand_cgroup_events);
 DECLARE_SUITE(perf_time_to_tsc);
 DECLARE_SUITE(dlfilter);
+DECLARE_SUITE(sigtrap);
 
 /*
  * PowerPC and S390 do not support creation of instruction breakpoints using the
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 869986139146..c4ef0c7002f1 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -112,62 +112,83 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
 	TEST_ASSERT_VAL("Session header CPU map not set", session->header.env.cpu);
 
 	for (i = 0; i < session->header.env.nr_cpus_avail; i++) {
-		if (!cpu_map__has(map, i))
+		struct perf_cpu cpu = { .cpu = i };
+
+		if (!perf_cpu_map__has(map, cpu))
 			continue;
 		pr_debug("CPU %d, core %d, socket %d\n", i,
 			 session->header.env.cpu[i].core_id,
 			 session->header.env.cpu[i].socket_id);
 	}
 
+	// Test that CPU ID contains socket, die, core and CPU
+	for (i = 0; i < map->nr; i++) {
+		id = aggr_cpu_id__cpu(perf_cpu_map__cpu(map, i), NULL);
+		TEST_ASSERT_VAL("Cpu map - CPU ID doesn't match", map->map[i].cpu == id.cpu.cpu);
+
+		TEST_ASSERT_VAL("Cpu map - Core ID doesn't match",
+			session->header.env.cpu[map->map[i].cpu].core_id == id.core);
+		TEST_ASSERT_VAL("Cpu map - Socket ID doesn't match",
+			session->header.env.cpu[map->map[i].cpu].socket_id == id.socket);
+
+		TEST_ASSERT_VAL("Cpu map - Die ID doesn't match",
+			session->header.env.cpu[map->map[i].cpu].die_id == id.die);
+		TEST_ASSERT_VAL("Cpu map - Node ID is set", id.node == -1);
+		TEST_ASSERT_VAL("Cpu map - Thread is set", id.thread == -1);
+	}
+
 	// Test that core ID contains socket, die and core
 	for (i = 0; i < map->nr; i++) {
-		id = cpu_map__get_core(map, i, NULL);
+		id = aggr_cpu_id__core(perf_cpu_map__cpu(map, i), NULL);
 		TEST_ASSERT_VAL("Core map - Core ID doesn't match",
-			session->header.env.cpu[map->map[i]].core_id == id.core);
+			session->header.env.cpu[map->map[i].cpu].core_id == id.core);
 
 		TEST_ASSERT_VAL("Core map - Socket ID doesn't match",
-			session->header.env.cpu[map->map[i]].socket_id == id.socket);
+			session->header.env.cpu[map->map[i].cpu].socket_id == id.socket);
 
 		TEST_ASSERT_VAL("Core map - Die ID doesn't match",
-			session->header.env.cpu[map->map[i]].die_id == id.die);
+			session->header.env.cpu[map->map[i].cpu].die_id == id.die);
 		TEST_ASSERT_VAL("Core map - Node ID is set", id.node == -1);
 		TEST_ASSERT_VAL("Core map - Thread is set", id.thread == -1);
 	}
 
 	// Test that die ID contains socket and die
 	for (i = 0; i < map->nr; i++) {
-		id = cpu_map__get_die(map, i, NULL);
+		id = aggr_cpu_id__die(perf_cpu_map__cpu(map, i), NULL);
 		TEST_ASSERT_VAL("Die map - Socket ID doesn't match",
-			session->header.env.cpu[map->map[i]].socket_id == id.socket);
+			session->header.env.cpu[map->map[i].cpu].socket_id == id.socket);
 
 		TEST_ASSERT_VAL("Die map - Die ID doesn't match",
-			session->header.env.cpu[map->map[i]].die_id == id.die);
+			session->header.env.cpu[map->map[i].cpu].die_id == id.die);
 
 		TEST_ASSERT_VAL("Die map - Node ID is set", id.node == -1);
 		TEST_ASSERT_VAL("Die map - Core is set", id.core == -1);
+		TEST_ASSERT_VAL("Die map - CPU is set", id.cpu.cpu == -1);
 		TEST_ASSERT_VAL("Die map - Thread is set", id.thread == -1);
 	}
 
 	// Test that socket ID contains only socket
 	for (i = 0; i < map->nr; i++) {
-		id = cpu_map__get_socket(map, i, NULL);
+		id = aggr_cpu_id__socket(perf_cpu_map__cpu(map, i), NULL);
 		TEST_ASSERT_VAL("Socket map - Socket ID doesn't match",
-			session->header.env.cpu[map->map[i]].socket_id == id.socket);
+			session->header.env.cpu[map->map[i].cpu].socket_id == id.socket);
 
 		TEST_ASSERT_VAL("Socket map - Node ID is set", id.node == -1);
 		TEST_ASSERT_VAL("Socket map - Die ID is set", id.die == -1);
 		TEST_ASSERT_VAL("Socket map - Core is set", id.core == -1);
+		TEST_ASSERT_VAL("Socket map - CPU is set", id.cpu.cpu == -1);
 		TEST_ASSERT_VAL("Socket map - Thread is set", id.thread == -1);
 	}
 
 	// Test that node ID contains only node
 	for (i = 0; i < map->nr; i++) {
-		id = cpu_map__get_node(map, i, NULL);
+		id = aggr_cpu_id__node(perf_cpu_map__cpu(map, i), NULL);
 		TEST_ASSERT_VAL("Node map - Node ID doesn't match",
 			cpu__get_node(map->map[i]) == id.node);
 		TEST_ASSERT_VAL("Node map - Socket is set", id.socket == -1);
 		TEST_ASSERT_VAL("Node map - Die ID is set", id.die == -1);
 		TEST_ASSERT_VAL("Node map - Core is set", id.core == -1);
+		TEST_ASSERT_VAL("Node map - CPU is set", id.cpu.cpu == -1);
 		TEST_ASSERT_VAL("Node map - Thread is set", id.thread == -1);
 	}
 	perf_session__delete(session);
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index e81c2493efdf..44ba900828f6 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -966,6 +966,7 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
 		.opts = opts,
 	};
 	int ret = -1, err;
+	int not_annotated = list_empty(&notes->src->source);
 
 	if (sym == NULL)
 		return -1;
@@ -973,13 +974,15 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
 	if (ms->map->dso->annotate_warned)
 		return -1;
 
-	err = symbol__annotate2(ms, evsel, opts, &browser.arch);
-	if (err) {
-		char msg[BUFSIZ];
-		ms->map->dso->annotate_warned = true;
-		symbol__strerror_disassemble(ms, err, msg, sizeof(msg));
-		ui__error("Couldn't annotate %s:\n%s", sym->name, msg);
-		goto out_free_offsets;
+	if (not_annotated) {
+		err = symbol__annotate2(ms, evsel, opts, &browser.arch);
+		if (err) {
+			char msg[BUFSIZ];
+			ms->map->dso->annotate_warned = true;
+			symbol__strerror_disassemble(ms, err, msg, sizeof(msg));
+			ui__error("Couldn't annotate %s:\n%s", sym->name, msg);
+			goto out_free_offsets;
+		}
 	}
 
 	ui_helpline__push("Press ESC to exit");
@@ -994,9 +997,11 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
 
 	ret = annotate_browser__run(&browser, evsel, hbt);
 
-	annotated_source__purge(notes->src);
+	if(not_annotated)
+		annotated_source__purge(notes->src);
 
 out_free_offsets:
-	zfree(&notes->offsets);
+	if(not_annotated)
+		zfree(&notes->offsets);
 	return ret;
 }
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 2e5bfbb69960..2a403cefcaf2 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -1,3 +1,4 @@
+perf-y += arm64-frame-pointer-unwind-support.o
 perf-y += annotate.o
 perf-y += block-info.o
 perf-y += block-range.o
@@ -144,6 +145,7 @@ perf-$(CONFIG_LIBBPF) += bpf-loader.o
 perf-$(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_BPF_PROLOGUE) += bpf-prologue.o
 perf-$(CONFIG_LIBELF) += symbol-elf.o
 perf-$(CONFIG_LIBELF) += probe-file.o
diff --git a/tools/perf/util/affinity.c b/tools/perf/util/affinity.c
index 7b12bd7a3080..f1e30d566db3 100644
--- a/tools/perf/util/affinity.c
+++ b/tools/perf/util/affinity.c
@@ -11,7 +11,7 @@
 
 static int get_cpu_set_size(void)
 {
-	int sz = cpu__max_cpu() + 8 - 1;
+	int sz = cpu__max_cpu().cpu + 8 - 1;
 	/*
 	 * sched_getaffinity doesn't like masks smaller than the kernel.
 	 * Hopefully that's big enough.
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
index 3fc528c9270c..5e390a1a79ab 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.c
@@ -179,6 +179,8 @@ static int arm_spe_read_record(struct arm_spe_decoder *decoder)
 				decoder->record.phys_addr = ip;
 			break;
 		case ARM_SPE_COUNTER:
+			if (idx == SPE_CNT_PKT_HDR_INDEX_TOTAL_LAT)
+				decoder->record.latency = payload;
 			break;
 		case ARM_SPE_CONTEXT:
 			decoder->record.context_id = payload;
diff --git a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
index 46a8556a9e95..69b31084d6be 100644
--- a/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
+++ b/tools/perf/util/arm-spe-decoder/arm-spe-decoder.h
@@ -33,6 +33,7 @@ struct arm_spe_record {
 	enum arm_spe_sample_type type;
 	int err;
 	u32 op;
+	u32 latency;
 	u64 from_ip;
 	u64 to_ip;
 	u64 timestamp;
diff --git a/tools/perf/util/arm-spe.c b/tools/perf/util/arm-spe.c
index fccac06b573a..d2b64e3f588b 100644
--- a/tools/perf/util/arm-spe.c
+++ b/tools/perf/util/arm-spe.c
@@ -58,6 +58,8 @@ struct arm_spe {
 	u8				sample_branch;
 	u8				sample_remote_access;
 	u8				sample_memory;
+	u8				sample_instructions;
+	u64				instructions_sample_period;
 
 	u64				l1d_miss_id;
 	u64				l1d_access_id;
@@ -68,6 +70,7 @@ struct arm_spe {
 	u64				branch_miss_id;
 	u64				remote_access_id;
 	u64				memory_id;
+	u64				instructions_id;
 
 	u64				kernel_start;
 
@@ -90,6 +93,7 @@ struct arm_spe_queue {
 	u64				time;
 	u64				timestamp;
 	struct thread			*thread;
+	u64				period_instructions;
 };
 
 static void arm_spe_dump(struct arm_spe *spe __maybe_unused,
@@ -202,6 +206,7 @@ static struct arm_spe_queue *arm_spe__alloc_queue(struct arm_spe *spe,
 	speq->pid = -1;
 	speq->tid = -1;
 	speq->cpu = -1;
+	speq->period_instructions = 0;
 
 	/* params set */
 	params.get_trace = arm_spe_get_trace;
@@ -330,6 +335,7 @@ static int arm_spe__synth_mem_sample(struct arm_spe_queue *speq,
 	sample.addr = record->virt_addr;
 	sample.phys_addr = record->phys_addr;
 	sample.data_src = data_src;
+	sample.weight = record->latency;
 
 	return arm_spe_deliver_synth_event(spe, speq, event, &sample);
 }
@@ -347,6 +353,36 @@ static int arm_spe__synth_branch_sample(struct arm_spe_queue *speq,
 	sample.id = spe_events_id;
 	sample.stream_id = spe_events_id;
 	sample.addr = record->to_ip;
+	sample.weight = record->latency;
+
+	return arm_spe_deliver_synth_event(spe, speq, event, &sample);
+}
+
+static int arm_spe__synth_instruction_sample(struct arm_spe_queue *speq,
+					     u64 spe_events_id, u64 data_src)
+{
+	struct arm_spe *spe = speq->spe;
+	struct arm_spe_record *record = &speq->decoder->record;
+	union perf_event *event = speq->event_buf;
+	struct perf_sample sample = { .ip = 0, };
+
+	/*
+	 * Handles perf instruction sampling period.
+	 */
+	speq->period_instructions++;
+	if (speq->period_instructions < spe->instructions_sample_period)
+		return 0;
+	speq->period_instructions = 0;
+
+	arm_spe_prep_sample(spe, speq, event, &sample);
+
+	sample.id = spe_events_id;
+	sample.stream_id = spe_events_id;
+	sample.addr = record->virt_addr;
+	sample.phys_addr = record->phys_addr;
+	sample.data_src = data_src;
+	sample.period = spe->instructions_sample_period;
+	sample.weight = record->latency;
 
 	return arm_spe_deliver_synth_event(spe, speq, event, &sample);
 }
@@ -480,6 +516,12 @@ static int arm_spe_sample(struct arm_spe_queue *speq)
 			return err;
 	}
 
+	if (spe->sample_instructions) {
+		err = arm_spe__synth_instruction_sample(speq, spe->instructions_id, data_src);
+		if (err)
+			return err;
+	}
+
 	return 0;
 }
 
@@ -993,7 +1035,8 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
 	attr.type = PERF_TYPE_HARDWARE;
 	attr.sample_type = evsel->core.attr.sample_type & PERF_SAMPLE_MASK;
 	attr.sample_type |= PERF_SAMPLE_IP | PERF_SAMPLE_TID |
-			    PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC;
+			    PERF_SAMPLE_PERIOD | PERF_SAMPLE_DATA_SRC |
+			    PERF_SAMPLE_WEIGHT;
 	if (spe->timeless_decoding)
 		attr.sample_type &= ~(u64)PERF_SAMPLE_TIME;
 	else
@@ -1107,7 +1150,29 @@ arm_spe_synth_events(struct arm_spe *spe, struct perf_session *session)
 			return err;
 		spe->memory_id = id;
 		arm_spe_set_event_name(evlist, id, "memory");
+		id += 1;
+	}
+
+	if (spe->synth_opts.instructions) {
+		if (spe->synth_opts.period_type != PERF_ITRACE_PERIOD_INSTRUCTIONS) {
+			pr_warning("Only instruction-based sampling period is currently supported by Arm SPE.\n");
+			goto synth_instructions_out;
+		}
+		if (spe->synth_opts.period > 1)
+			pr_warning("Arm SPE has a hardware-based sample period.\n"
+				   "Additional instruction events will be discarded by --itrace\n");
+
+		spe->sample_instructions = true;
+		attr.config = PERF_COUNT_HW_INSTRUCTIONS;
+		attr.sample_period = spe->synth_opts.period;
+		spe->instructions_sample_period = attr.sample_period;
+		err = arm_spe_synth_event(session, &attr, id);
+		if (err)
+			return err;
+		spe->instructions_id = id;
+		arm_spe_set_event_name(evlist, id, "instructions");
 	}
+synth_instructions_out:
 
 	return 0;
 }
diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.c b/tools/perf/util/arm64-frame-pointer-unwind-support.c
new file mode 100644
index 000000000000..2242a885fbd7
--- /dev/null
+++ b/tools/perf/util/arm64-frame-pointer-unwind-support.c
@@ -0,0 +1,63 @@
+// SPDX-License-Identifier: GPL-2.0
+#include "arm64-frame-pointer-unwind-support.h"
+#include "callchain.h"
+#include "event.h"
+#include "perf_regs.h" // SMPL_REG_MASK
+#include "unwind.h"
+
+#define perf_event_arm_regs perf_event_arm64_regs
+#include "../../arch/arm64/include/uapi/asm/perf_regs.h"
+#undef perf_event_arm_regs
+
+struct entries {
+	u64 stack[2];
+	size_t length;
+};
+
+static bool get_leaf_frame_caller_enabled(struct perf_sample *sample)
+{
+	return callchain_param.record_mode == CALLCHAIN_FP && sample->user_regs.regs
+		&& sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_LR);
+}
+
+static int add_entry(struct unwind_entry *entry, void *arg)
+{
+	struct entries *entries = arg;
+
+	entries->stack[entries->length++] = entry->ip;
+	return 0;
+}
+
+u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thread, int usr_idx)
+{
+	int ret;
+	struct entries entries = {};
+	struct regs_dump old_regs = sample->user_regs;
+
+	if (!get_leaf_frame_caller_enabled(sample))
+		return 0;
+
+	/*
+	 * If PC and SP are not recorded, get the value of PC from the stack
+	 * and set its mask. SP is not used when doing the unwinding but it
+	 * still needs to be set to prevent failures.
+	 */
+
+	if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_PC))) {
+		sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_PC);
+		sample->user_regs.cache_regs[PERF_REG_ARM64_PC] = sample->callchain->ips[usr_idx+1];
+	}
+
+	if (!(sample->user_regs.mask & SMPL_REG_MASK(PERF_REG_ARM64_SP))) {
+		sample->user_regs.cache_mask |= SMPL_REG_MASK(PERF_REG_ARM64_SP);
+		sample->user_regs.cache_regs[PERF_REG_ARM64_SP] = 0;
+	}
+
+	ret = unwind__get_entries(add_entry, &entries, thread, sample, 2);
+	sample->user_regs = old_regs;
+
+	if (ret || entries.length != 2)
+		return ret;
+
+	return callchain_param.order == ORDER_CALLER ? entries.stack[0] : entries.stack[1];
+}
diff --git a/tools/perf/util/arm64-frame-pointer-unwind-support.h b/tools/perf/util/arm64-frame-pointer-unwind-support.h
new file mode 100644
index 000000000000..32af9ce94398
--- /dev/null
+++ b/tools/perf/util/arm64-frame-pointer-unwind-support.h
@@ -0,0 +1,10 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H
+#define __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H
+
+#include "event.h"
+#include "thread.h"
+
+u64 get_leaf_frame_caller_aarch64(struct perf_sample *sample, struct thread *thread, int user_idx);
+
+#endif /* __PERF_ARM_FRAME_POINTER_UNWIND_SUPPORT_H */
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index c679394b898d..5632efc44738 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -123,7 +123,7 @@ int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
 	mm->prev = 0;
 	mm->idx = mp->idx;
 	mm->tid = mp->tid;
-	mm->cpu = mp->cpu;
+	mm->cpu = mp->cpu.cpu;
 
 	if (!mp->len) {
 		mm->base = NULL;
@@ -180,7 +180,7 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
 		else
 			mp->tid = -1;
 	} else {
-		mp->cpu = -1;
+		mp->cpu.cpu = -1;
 		mp->tid = perf_thread_map__pid(evlist->core.threads, idx);
 	}
 }
@@ -292,7 +292,7 @@ static int auxtrace_queues__queue_buffer(struct auxtrace_queues *queues,
 	if (!queue->set) {
 		queue->set = true;
 		queue->tid = buffer->tid;
-		queue->cpu = buffer->cpu;
+		queue->cpu = buffer->cpu.cpu;
 	}
 
 	buffer->buffer_nr = queues->next_buffer_nr++;
@@ -339,11 +339,11 @@ static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues,
 	return 0;
 }
 
-static bool filter_cpu(struct perf_session *session, int cpu)
+static bool filter_cpu(struct perf_session *session, struct perf_cpu cpu)
 {
 	unsigned long *cpu_bitmap = session->itrace_synth_opts->cpu_bitmap;
 
-	return cpu_bitmap && cpu != -1 && !test_bit(cpu, cpu_bitmap);
+	return cpu_bitmap && cpu.cpu != -1 && !test_bit(cpu.cpu, cpu_bitmap);
 }
 
 static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
@@ -399,7 +399,7 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues,
 	struct auxtrace_buffer buffer = {
 		.pid = -1,
 		.tid = event->auxtrace.tid,
-		.cpu = event->auxtrace.cpu,
+		.cpu = { event->auxtrace.cpu },
 		.data_offset = data_offset,
 		.offset = event->auxtrace.offset,
 		.reference = event->auxtrace.reference,
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index bbf0d78c6401..19910b9011f3 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -15,6 +15,7 @@
 #include <linux/list.h>
 #include <linux/perf_event.h>
 #include <linux/types.h>
+#include <internal/cpumap.h>
 #include <asm/bitsperlong.h>
 #include <asm/barrier.h>
 
@@ -240,7 +241,7 @@ struct auxtrace_buffer {
 	size_t			size;
 	pid_t			pid;
 	pid_t			tid;
-	int			cpu;
+	struct perf_cpu		cpu;
 	void			*data;
 	off_t			data_offset;
 	void			*mmap_addr;
@@ -350,7 +351,7 @@ struct auxtrace_mmap_params {
 	int		prot;
 	int		idx;
 	pid_t		tid;
-	int		cpu;
+	struct perf_cpu	cpu;
 };
 
 /**
diff --git a/tools/perf/util/bpf-loader.c b/tools/perf/util/bpf-loader.c
index 528aeb0ab79d..7ecfaac7536a 100644
--- a/tools/perf/util/bpf-loader.c
+++ b/tools/perf/util/bpf-loader.c
@@ -424,7 +424,7 @@ preproc_gen_prologue(struct bpf_program *prog, int n,
 	size_t prologue_cnt = 0;
 	int i, err;
 
-	if (IS_ERR(priv) || !priv || priv->is_tp)
+	if (IS_ERR_OR_NULL(priv) || priv->is_tp)
 		goto errout;
 
 	pev = &priv->pev;
@@ -573,7 +573,7 @@ static int hook_load_preprocessor(struct bpf_program *prog)
 	bool need_prologue = false;
 	int err, i;
 
-	if (IS_ERR(priv) || !priv) {
+	if (IS_ERR_OR_NULL(priv)) {
 		pr_debug("Internal error when hook preprocessor\n");
 		return -BPF_LOADER_ERRNO__INTERNAL;
 	}
@@ -645,8 +645,11 @@ int bpf__probe(struct bpf_object *obj)
 			goto out;
 
 		priv = bpf_program__priv(prog);
-		if (IS_ERR(priv) || !priv) {
-			err = PTR_ERR(priv);
+		if (IS_ERR_OR_NULL(priv)) {
+			if (!priv)
+				err = -BPF_LOADER_ERRNO__INTERNAL;
+			else
+				err = PTR_ERR(priv);
 			goto out;
 		}
 
@@ -696,7 +699,7 @@ int bpf__unprobe(struct bpf_object *obj)
 		struct bpf_prog_priv *priv = bpf_program__priv(prog);
 		int i;
 
-		if (IS_ERR(priv) || !priv || priv->is_tp)
+		if (IS_ERR_OR_NULL(priv) || priv->is_tp)
 			continue;
 
 		for (i = 0; i < priv->pev.ntevs; i++) {
@@ -754,7 +757,7 @@ int bpf__foreach_event(struct bpf_object *obj,
 		struct perf_probe_event *pev;
 		int i, fd;
 
-		if (IS_ERR(priv) || !priv) {
+		if (IS_ERR_OR_NULL(priv)) {
 			pr_debug("bpf: failed to get private field\n");
 			return -BPF_LOADER_ERRNO__INTERNAL;
 		}
diff --git a/tools/perf/util/bpf_counter.c b/tools/perf/util/bpf_counter.c
index 5a97fd7d0a71..3ce8d03cb7ec 100644
--- a/tools/perf/util/bpf_counter.c
+++ b/tools/perf/util/bpf_counter.c
@@ -265,7 +265,7 @@ static int bpf_program_profiler__read(struct evsel *evsel)
 	return 0;
 }
 
-static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu,
+static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu_map_idx,
 					    int fd)
 {
 	struct bpf_prog_profiler_bpf *skel;
@@ -277,7 +277,7 @@ static int bpf_program_profiler__install_pe(struct evsel *evsel, int cpu,
 		assert(skel != NULL);
 
 		ret = bpf_map_update_elem(bpf_map__fd(skel->maps.events),
-					  &cpu, &fd, BPF_ANY);
+					  &cpu_map_idx, &fd, BPF_ANY);
 		if (ret)
 			return ret;
 	}
@@ -554,7 +554,7 @@ static int bperf__load(struct evsel *evsel, struct target *target)
 		    filter_type == BPERF_FILTER_TGID)
 			key = evsel->core.threads->map[i].pid;
 		else if (filter_type == BPERF_FILTER_CPU)
-			key = evsel->core.cpus->map[i];
+			key = evsel->core.cpus->map[i].cpu;
 		else
 			break;
 
@@ -580,12 +580,12 @@ out:
 	return err;
 }
 
-static int bperf__install_pe(struct evsel *evsel, int cpu, int fd)
+static int bperf__install_pe(struct evsel *evsel, int cpu_map_idx, int fd)
 {
 	struct bperf_leader_bpf *skel = evsel->leader_skel;
 
 	return bpf_map_update_elem(bpf_map__fd(skel->maps.events),
-				   &cpu, &fd, BPF_ANY);
+				   &cpu_map_idx, &fd, BPF_ANY);
 }
 
 /*
@@ -598,7 +598,7 @@ static int bperf_sync_counters(struct evsel *evsel)
 
 	num_cpu = all_cpu_map->nr;
 	for (i = 0; i < num_cpu; i++) {
-		cpu = all_cpu_map->map[i];
+		cpu = all_cpu_map->map[i].cpu;
 		bperf_trigger_reading(evsel->bperf_leader_prog_fd, cpu);
 	}
 	return 0;
@@ -619,15 +619,17 @@ static int bperf__disable(struct evsel *evsel)
 static int bperf__read(struct evsel *evsel)
 {
 	struct bperf_follower_bpf *skel = evsel->follower_skel;
-	__u32 num_cpu_bpf = cpu__max_cpu();
+	__u32 num_cpu_bpf = cpu__max_cpu().cpu;
 	struct bpf_perf_event_value values[num_cpu_bpf];
 	int reading_map_fd, err = 0;
-	__u32 i, j, num_cpu;
+	__u32 i;
+	int j;
 
 	bperf_sync_counters(evsel);
 	reading_map_fd = bpf_map__fd(skel->maps.accum_readings);
 
 	for (i = 0; i < bpf_map__max_entries(skel->maps.accum_readings); i++) {
+		struct perf_cpu entry;
 		__u32 cpu;
 
 		err = bpf_map_lookup_elem(reading_map_fd, &i, values);
@@ -637,16 +639,15 @@ static int bperf__read(struct evsel *evsel)
 		case BPERF_FILTER_GLOBAL:
 			assert(i == 0);
 
-			num_cpu = all_cpu_map->nr;
-			for (j = 0; j < num_cpu; j++) {
-				cpu = all_cpu_map->map[j];
+			perf_cpu_map__for_each_cpu(entry, j, all_cpu_map) {
+				cpu = entry.cpu;
 				perf_counts(evsel->counts, cpu, 0)->val = values[cpu].counter;
 				perf_counts(evsel->counts, cpu, 0)->ena = values[cpu].enabled;
 				perf_counts(evsel->counts, cpu, 0)->run = values[cpu].running;
 			}
 			break;
 		case BPERF_FILTER_CPU:
-			cpu = evsel->core.cpus->map[i];
+			cpu = evsel->core.cpus->map[i].cpu;
 			perf_counts(evsel->counts, i, 0)->val = values[cpu].counter;
 			perf_counts(evsel->counts, i, 0)->ena = values[cpu].enabled;
 			perf_counts(evsel->counts, i, 0)->run = values[cpu].running;
@@ -771,11 +772,11 @@ static inline bool bpf_counter_skip(struct evsel *evsel)
 		evsel->follower_skel == NULL;
 }
 
-int bpf_counter__install_pe(struct evsel *evsel, int cpu, int fd)
+int bpf_counter__install_pe(struct evsel *evsel, int cpu_map_idx, int fd)
 {
 	if (bpf_counter_skip(evsel))
 		return 0;
-	return evsel->bpf_counter_ops->install_pe(evsel, cpu, fd);
+	return evsel->bpf_counter_ops->install_pe(evsel, cpu_map_idx, fd);
 }
 
 int bpf_counter__load(struct evsel *evsel, struct target *target)
diff --git a/tools/perf/util/bpf_counter.h b/tools/perf/util/bpf_counter.h
index 65ebaa6694fb..4dbf26408b69 100644
--- a/tools/perf/util/bpf_counter.h
+++ b/tools/perf/util/bpf_counter.h
@@ -16,7 +16,7 @@ typedef int (*bpf_counter_evsel_op)(struct evsel *evsel);
 typedef int (*bpf_counter_evsel_target_op)(struct evsel *evsel,
 					   struct target *target);
 typedef int (*bpf_counter_evsel_install_pe_op)(struct evsel *evsel,
-					       int cpu,
+					       int cpu_map_idx,
 					       int fd);
 
 struct bpf_counter_ops {
@@ -40,7 +40,7 @@ int bpf_counter__enable(struct evsel *evsel);
 int bpf_counter__disable(struct evsel *evsel);
 int bpf_counter__read(struct evsel *evsel);
 void bpf_counter__destroy(struct evsel *evsel);
-int bpf_counter__install_pe(struct evsel *evsel, int cpu, int fd);
+int bpf_counter__install_pe(struct evsel *evsel, int cpu_map_idx, int fd);
 
 #else /* HAVE_BPF_SKEL */
 
diff --git a/tools/perf/util/bpf_counter_cgroup.c b/tools/perf/util/bpf_counter_cgroup.c
index cbc6c2bca488..631e34a0b66f 100644
--- a/tools/perf/util/bpf_counter_cgroup.c
+++ b/tools/perf/util/bpf_counter_cgroup.c
@@ -48,7 +48,7 @@ static int bperf_load_program(struct evlist *evlist)
 	struct cgroup *cgrp, *leader_cgrp;
 	__u32 i, cpu;
 	__u32 nr_cpus = evlist->core.all_cpus->nr;
-	int total_cpus = cpu__max_cpu();
+	int total_cpus = cpu__max_cpu().cpu;
 	int map_size, map_fd;
 	int prog_fd, err;
 
@@ -125,7 +125,7 @@ static int bperf_load_program(struct evlist *evlist)
 			for (cpu = 0; cpu < nr_cpus; cpu++) {
 				int fd = FD(evsel, cpu);
 				__u32 idx = evsel->core.idx * total_cpus +
-					evlist->core.all_cpus->map[cpu];
+					evlist->core.all_cpus->map[cpu].cpu;
 
 				err = bpf_map_update_elem(map_fd, &idx, &fd,
 							  BPF_ANY);
@@ -212,7 +212,7 @@ static int bperf_cgrp__sync_counters(struct evlist *evlist)
 	int prog_fd = bpf_program__fd(skel->progs.trigger_read);
 
 	for (i = 0; i < nr_cpus; i++) {
-		cpu = evlist->core.all_cpus->map[i];
+		cpu = evlist->core.all_cpus->map[i].cpu;
 		bperf_trigger_reading(prog_fd, cpu);
 	}
 
@@ -245,7 +245,7 @@ static int bperf_cgrp__read(struct evsel *evsel)
 {
 	struct evlist *evlist = evsel->evlist;
 	int i, cpu, nr_cpus = evlist->core.all_cpus->nr;
-	int total_cpus = cpu__max_cpu();
+	int total_cpus = cpu__max_cpu().cpu;
 	struct perf_counts_values *counts;
 	struct bpf_perf_event_value *values;
 	int reading_map_fd, err = 0;
@@ -272,7 +272,7 @@ static int bperf_cgrp__read(struct evsel *evsel)
 		}
 
 		for (i = 0; i < nr_cpus; i++) {
-			cpu = evlist->core.all_cpus->map[i];
+			cpu = evlist->core.all_cpus->map[i].cpu;
 
 			counts = perf_counts(evsel->counts, i, 0);
 			counts->val = values[cpu].counter;
diff --git a/tools/perf/util/bpf_ftrace.c b/tools/perf/util/bpf_ftrace.c
new file mode 100644
index 000000000000..d756cc66eef3
--- /dev/null
+++ b/tools/perf/util/bpf_ftrace.c
@@ -0,0 +1,152 @@
+#include <stdio.h>
+#include <fcntl.h>
+#include <stdint.h>
+#include <stdlib.h>
+
+#include <linux/err.h>
+
+#include "util/ftrace.h"
+#include "util/cpumap.h"
+#include "util/thread_map.h"
+#include "util/debug.h"
+#include "util/evlist.h"
+#include "util/bpf_counter.h"
+
+#include "util/bpf_skel/func_latency.skel.h"
+
+static struct func_latency_bpf *skel;
+
+int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace)
+{
+	int fd, err;
+	int i, ncpus = 1, ntasks = 1;
+	struct filter_entry *func;
+
+	if (!list_is_singular(&ftrace->filters)) {
+		pr_err("ERROR: %s target function(s).\n",
+		       list_empty(&ftrace->filters) ? "No" : "Too many");
+		return -1;
+	}
+
+	func = list_first_entry(&ftrace->filters, struct filter_entry, list);
+
+	skel = func_latency_bpf__open();
+	if (!skel) {
+		pr_err("Failed to open func latency skeleton\n");
+		return -1;
+	}
+
+	/* don't need to set cpu filter for system-wide mode */
+	if (ftrace->target.cpu_list) {
+		ncpus = perf_cpu_map__nr(ftrace->evlist->core.cpus);
+		bpf_map__set_max_entries(skel->maps.cpu_filter, ncpus);
+	}
+
+	if (target__has_task(&ftrace->target) || target__none(&ftrace->target)) {
+		ntasks = perf_thread_map__nr(ftrace->evlist->core.threads);
+		bpf_map__set_max_entries(skel->maps.task_filter, ntasks);
+	}
+
+	set_max_rlimit();
+
+	err = func_latency_bpf__load(skel);
+	if (err) {
+		pr_err("Failed to load func latency skeleton\n");
+		goto out;
+	}
+
+	if (ftrace->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(ftrace->evlist->core.cpus, i).cpu;
+			bpf_map_update_elem(fd, &cpu, &val, BPF_ANY);
+		}
+	}
+
+	if (target__has_task(&ftrace->target) || target__none(&ftrace->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(ftrace->evlist->core.threads, i);
+			bpf_map_update_elem(fd, &pid, &val, BPF_ANY);
+		}
+	}
+
+	skel->links.func_begin = bpf_program__attach_kprobe(skel->progs.func_begin,
+							    false, func->name);
+	if (IS_ERR(skel->links.func_begin)) {
+		pr_err("Failed to attach fentry program\n");
+		err = PTR_ERR(skel->links.func_begin);
+		goto out;
+	}
+
+	skel->links.func_end = bpf_program__attach_kprobe(skel->progs.func_end,
+							  true, func->name);
+	if (IS_ERR(skel->links.func_end)) {
+		pr_err("Failed to attach fexit program\n");
+		err = PTR_ERR(skel->links.func_end);
+		goto out;
+	}
+
+	/* XXX: we don't actually use this fd - just for poll() */
+	return open("/dev/null", O_RDONLY);
+
+out:
+	return err;
+}
+
+int perf_ftrace__latency_start_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+	skel->bss->enabled = 1;
+	return 0;
+}
+
+int perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+	skel->bss->enabled = 0;
+	return 0;
+}
+
+int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused,
+				  int buckets[])
+{
+	int i, fd, err;
+	u32 idx;
+	u64 *hist;
+	int ncpus = cpu__max_cpu().cpu;
+
+	fd = bpf_map__fd(skel->maps.latency);
+
+	hist = calloc(ncpus, sizeof(*hist));
+	if (hist == NULL)
+		return -ENOMEM;
+
+	for (idx = 0; idx < NUM_BUCKET; idx++) {
+		err = bpf_map_lookup_elem(fd, &idx, hist);
+		if (err) {
+			buckets[idx] = 0;
+			continue;
+		}
+
+		for (i = 0; i < ncpus; i++)
+			buckets[idx] += hist[i];
+	}
+
+	free(hist);
+	return 0;
+}
+
+int perf_ftrace__latency_cleanup_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+	func_latency_bpf__destroy(skel);
+	return 0;
+}
diff --git a/tools/perf/util/bpf_skel/func_latency.bpf.c b/tools/perf/util/bpf_skel/func_latency.bpf.c
new file mode 100644
index 000000000000..ea94187fe443
--- /dev/null
+++ b/tools/perf/util/bpf_skel/func_latency.bpf.c
@@ -0,0 +1,114 @@
+// SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+// Copyright (c) 2021 Google
+#include "vmlinux.h"
+#include <bpf/bpf_helpers.h>
+#include <bpf/bpf_tracing.h>
+
+// This should be in sync with "util/ftrace.h"
+#define NUM_BUCKET  22
+
+struct {
+	__uint(type, BPF_MAP_TYPE_HASH);
+	__uint(key_size, sizeof(__u64));
+	__uint(value_size, sizeof(__u64));
+	__uint(max_entries, 10000);
+} functime 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_PERCPU_ARRAY);
+	__uint(key_size, sizeof(__u32));
+	__uint(value_size, sizeof(__u64));
+	__uint(max_entries, NUM_BUCKET);
+} latency SEC(".maps");
+
+
+int enabled = 0;
+int has_cpu = 0;
+int has_task = 0;
+
+SEC("kprobe/func")
+int BPF_PROG(func_begin)
+{
+	__u64 key, now;
+
+	if (!enabled)
+		return 0;
+
+	key = bpf_get_current_pid_tgid();
+
+	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) {
+		__u32 pid = key & 0xffffffff;
+		__u8 *ok;
+
+		ok = bpf_map_lookup_elem(&task_filter, &pid);
+		if (!ok)
+			return 0;
+	}
+
+	now = bpf_ktime_get_ns();
+
+	// overwrite timestamp for nested functions
+	bpf_map_update_elem(&functime, &key, &now, BPF_ANY);
+	return 0;
+}
+
+SEC("kretprobe/func")
+int BPF_PROG(func_end)
+{
+	__u64 tid;
+	__u64 *start;
+
+	if (!enabled)
+		return 0;
+
+	tid = bpf_get_current_pid_tgid();
+
+	start = bpf_map_lookup_elem(&functime, &tid);
+	if (start) {
+		__s64 delta = bpf_ktime_get_ns() - *start;
+		__u32 key;
+		__u64 *hist;
+
+		bpf_map_delete_elem(&functime, &tid);
+
+		if (delta < 0)
+			return 0;
+
+		// calculate index using delta in usec
+		for (key = 0; key < (NUM_BUCKET - 1); key++) {
+			if (delta < ((1000UL) << key))
+				break;
+		}
+
+		hist = bpf_map_lookup_elem(&latency, &key);
+		if (!hist)
+			return 0;
+
+		*hist += 1;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
index 8e2777133bd9..131207b91d15 100644
--- a/tools/perf/util/callchain.c
+++ b/tools/perf/util/callchain.c
@@ -1600,7 +1600,7 @@ void callchain_cursor_reset(struct callchain_cursor *cursor)
 		map__zput(node->ms.map);
 }
 
-void callchain_param_setup(u64 sample_type)
+void callchain_param_setup(u64 sample_type, const char *arch)
 {
 	if (symbol_conf.use_callchain || symbol_conf.cumulate_callchain) {
 		if ((sample_type & PERF_SAMPLE_REGS_USER) &&
@@ -1612,6 +1612,18 @@ void callchain_param_setup(u64 sample_type)
 		else
 			callchain_param.record_mode = CALLCHAIN_FP;
 	}
+
+	/*
+	 * It's necessary to use libunwind to reliably determine the caller of
+	 * a leaf function on aarch64, as otherwise we cannot know whether to
+	 * start from the LR or FP.
+	 *
+	 * Always starting from the LR can result in duplicate or entirely
+	 * erroneous entries. Always skipping the LR and starting from the FP
+	 * can result in missing entries.
+	 */
+	if (callchain_param.record_mode == CALLCHAIN_FP && !strcmp(arch, "arm64"))
+		dwarf_callchain_users = true;
 }
 
 static bool chain_match(struct callchain_list *base_chain,
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 5824134f983b..d95615daed73 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -280,6 +280,8 @@ static inline int arch_skip_callchain_idx(struct thread *thread __maybe_unused,
 }
 #endif
 
+void arch__add_leaf_frame_record_opts(struct record_opts *opts);
+
 char *callchain_list__sym_name(struct callchain_list *cl,
 			       char *bf, size_t bfsize, bool show_dso);
 char *callchain_node__scnprintf_value(struct callchain_node *node,
@@ -298,7 +300,7 @@ int callchain_branch_counts(struct callchain_root *root,
 			    u64 *branch_count, u64 *predicted_count,
 			    u64 *abort_count, u64 *cycles_count);
 
-void callchain_param_setup(u64 sample_type);
+void callchain_param_setup(u64 sample_type, const char *arch);
 
 bool callchain_cnode_matched(struct callchain_node *base_cnode,
 			     struct callchain_node *pair_cnode);
diff --git a/tools/perf/util/counts.c b/tools/perf/util/counts.c
index 582f3aeaf5e4..2b81707b9dba 100644
--- a/tools/perf/util/counts.c
+++ b/tools/perf/util/counts.c
@@ -4,6 +4,7 @@
 #include <string.h>
 #include "evsel.h"
 #include "counts.h"
+#include <perf/threadmap.h>
 #include <linux/zalloc.h>
 
 struct perf_counts *perf_counts__new(int ncpus, int nthreads)
@@ -55,9 +56,12 @@ void evsel__reset_counts(struct evsel *evsel)
 	perf_counts__reset(evsel->counts);
 }
 
-int evsel__alloc_counts(struct evsel *evsel, int ncpus, int nthreads)
+int evsel__alloc_counts(struct evsel *evsel)
 {
-	evsel->counts = perf_counts__new(ncpus, nthreads);
+	struct perf_cpu_map *cpus = evsel__cpus(evsel);
+	int nthreads = perf_thread_map__nr(evsel->core.threads);
+
+	evsel->counts = perf_counts__new(cpus ? cpus->nr : 1, nthreads);
 	return evsel->counts != NULL ? 0 : -ENOMEM;
 }
 
diff --git a/tools/perf/util/counts.h b/tools/perf/util/counts.h
index 7ff36bf6d644..5de275194f2b 100644
--- a/tools/perf/util/counts.h
+++ b/tools/perf/util/counts.h
@@ -18,21 +18,21 @@ struct perf_counts {
 
 
 static inline struct perf_counts_values*
-perf_counts(struct perf_counts *counts, int cpu, int thread)
+perf_counts(struct perf_counts *counts, int cpu_map_idx, int thread)
 {
-	return xyarray__entry(counts->values, cpu, thread);
+	return xyarray__entry(counts->values, cpu_map_idx, thread);
 }
 
 static inline bool
-perf_counts__is_loaded(struct perf_counts *counts, int cpu, int thread)
+perf_counts__is_loaded(struct perf_counts *counts, int cpu_map_idx, int thread)
 {
-	return *((bool *) xyarray__entry(counts->loaded, cpu, thread));
+	return *((bool *) xyarray__entry(counts->loaded, cpu_map_idx, thread));
 }
 
 static inline void
-perf_counts__set_loaded(struct perf_counts *counts, int cpu, int thread, bool loaded)
+perf_counts__set_loaded(struct perf_counts *counts, int cpu_map_idx, int thread, bool loaded)
 {
-	*((bool *) xyarray__entry(counts->loaded, cpu, thread)) = loaded;
+	*((bool *) xyarray__entry(counts->loaded, cpu_map_idx, thread)) = loaded;
 }
 
 struct perf_counts *perf_counts__new(int ncpus, int nthreads);
@@ -40,7 +40,7 @@ void perf_counts__delete(struct perf_counts *counts);
 void perf_counts__reset(struct perf_counts *counts);
 
 void evsel__reset_counts(struct evsel *evsel);
-int evsel__alloc_counts(struct evsel *evsel, int ncpus, int nthreads);
+int evsel__alloc_counts(struct evsel *evsel);
 void evsel__free_counts(struct evsel *evsel);
 
 #endif /* __PERF_COUNTS_H */
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 87d3eca9b872..12b2243222b0 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -13,9 +13,13 @@
 #include <linux/ctype.h>
 #include <linux/zalloc.h>
 
-static int max_cpu_num;
-static int max_present_cpu_num;
+static struct perf_cpu max_cpu_num;
+static struct perf_cpu max_present_cpu_num;
 static int max_node_num;
+/**
+ * The numa node X as read from /sys/devices/system/node/nodeX indexed by the
+ * CPU number.
+ */
 static int *cpunode_map;
 
 static struct perf_cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus)
@@ -33,9 +37,9 @@ static struct perf_cpu_map *cpu_map__from_entries(struct cpu_map_entries *cpus)
 			 * otherwise it would become 65535.
 			 */
 			if (cpus->cpu[i] == (u16) -1)
-				map->map[i] = -1;
+				map->map[i].cpu = -1;
 			else
-				map->map[i] = (int) cpus->cpu[i];
+				map->map[i].cpu = (int) cpus->cpu[i];
 		}
 	}
 
@@ -54,7 +58,7 @@ static struct perf_cpu_map *cpu_map__from_mask(struct perf_record_record_cpu_map
 		int cpu, i = 0;
 
 		for_each_set_bit(cpu, mask->mask, nbits)
-			map->map[i++] = cpu;
+			map->map[i++].cpu = cpu;
 	}
 	return map;
 
@@ -87,7 +91,7 @@ struct perf_cpu_map *perf_cpu_map__empty_new(int nr)
 
 		cpus->nr = nr;
 		for (i = 0; i < nr; i++)
-			cpus->map[i] = -1;
+			cpus->map[i].cpu = -1;
 
 		refcount_set(&cpus->refcnt, 1);
 	}
@@ -104,7 +108,7 @@ struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr)
 
 		cpus->nr = nr;
 		for (i = 0; i < nr; i++)
-			cpus->map[i] = cpu_map__empty_aggr_cpu_id();
+			cpus->map[i] = aggr_cpu_id__empty();
 
 		refcount_set(&cpus->refcnt, 1);
 	}
@@ -122,28 +126,21 @@ static int cpu__get_topology_int(int cpu, const char *name, int *value)
 	return sysfs__read_int(path, value);
 }
 
-int cpu_map__get_socket_id(int cpu)
+int cpu__get_socket_id(struct perf_cpu cpu)
 {
-	int value, ret = cpu__get_topology_int(cpu, "physical_package_id", &value);
+	int value, ret = cpu__get_topology_int(cpu.cpu, "physical_package_id", &value);
 	return ret ?: value;
 }
 
-struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx,
-					void *data __maybe_unused)
+struct aggr_cpu_id aggr_cpu_id__socket(struct perf_cpu cpu, void *data __maybe_unused)
 {
-	int cpu;
-	struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+	struct aggr_cpu_id id = aggr_cpu_id__empty();
 
-	if (idx > map->nr)
-		return id;
-
-	cpu = map->map[idx];
-
-	id.socket = cpu_map__get_socket_id(cpu);
+	id.socket = cpu__get_socket_id(cpu);
 	return id;
 }
 
-static int cmp_aggr_cpu_id(const void *a_pointer, const void *b_pointer)
+static int aggr_cpu_id__cmp(const void *a_pointer, const void *b_pointer)
 {
 	struct aggr_cpu_id *a = (struct aggr_cpu_id *)a_pointer;
 	struct aggr_cpu_id *b = (struct aggr_cpu_id *)b_pointer;
@@ -160,57 +157,64 @@ static int cmp_aggr_cpu_id(const void *a_pointer, const void *b_pointer)
 		return a->thread - b->thread;
 }
 
-int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res,
-		       struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data),
-		       void *data)
+struct cpu_aggr_map *cpu_aggr_map__new(const struct perf_cpu_map *cpus,
+				       aggr_cpu_id_get_t get_id,
+				       void *data)
 {
-	int nr = cpus->nr;
-	struct cpu_aggr_map *c = cpu_aggr_map__empty_new(nr);
-	int cpu, s2;
-	struct aggr_cpu_id s1;
+	int idx;
+	struct perf_cpu cpu;
+	struct cpu_aggr_map *c = cpu_aggr_map__empty_new(cpus->nr);
 
 	if (!c)
-		return -1;
+		return NULL;
 
 	/* Reset size as it may only be partially filled */
 	c->nr = 0;
 
-	for (cpu = 0; cpu < nr; cpu++) {
-		s1 = f(cpus, cpu, data);
-		for (s2 = 0; s2 < c->nr; s2++) {
-			if (cpu_map__compare_aggr_cpu_id(s1, c->map[s2]))
+	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+		bool duplicate = false;
+		struct aggr_cpu_id cpu_id = get_id(cpu, data);
+
+		for (int j = 0; j < c->nr; j++) {
+			if (aggr_cpu_id__equal(&cpu_id, &c->map[j])) {
+				duplicate = true;
 				break;
+			}
 		}
-		if (s2 == c->nr) {
-			c->map[c->nr] = s1;
+		if (!duplicate) {
+			c->map[c->nr] = cpu_id;
 			c->nr++;
 		}
 	}
+	/* Trim. */
+	if (c->nr != cpus->nr) {
+		struct cpu_aggr_map *trimmed_c =
+			realloc(c,
+				sizeof(struct cpu_aggr_map) + sizeof(struct aggr_cpu_id) * c->nr);
+
+		if (trimmed_c)
+			c = trimmed_c;
+	}
 	/* ensure we process id in increasing order */
-	qsort(c->map, c->nr, sizeof(struct aggr_cpu_id), cmp_aggr_cpu_id);
+	qsort(c->map, c->nr, sizeof(struct aggr_cpu_id), aggr_cpu_id__cmp);
+
+	return c;
 
-	*res = c;
-	return 0;
 }
 
-int cpu_map__get_die_id(int cpu)
+int cpu__get_die_id(struct perf_cpu cpu)
 {
-	int value, ret = cpu__get_topology_int(cpu, "die_id", &value);
+	int value, ret = cpu__get_topology_int(cpu.cpu, "die_id", &value);
 
 	return ret ?: value;
 }
 
-struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data)
+struct aggr_cpu_id aggr_cpu_id__die(struct perf_cpu cpu, void *data)
 {
-	int cpu, die;
-	struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+	struct aggr_cpu_id id;
+	int die;
 
-	if (idx > map->nr)
-		return id;
-
-	cpu = map->map[idx];
-
-	die = cpu_map__get_die_id(cpu);
+	die = cpu__get_die_id(cpu);
 	/* There is no die_id on legacy system. */
 	if (die == -1)
 		die = 0;
@@ -220,79 +224,59 @@ struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *dat
 	 * with the socket ID and then add die to
 	 * make a unique ID.
 	 */
-	id = cpu_map__get_socket(map, idx, data);
-	if (cpu_map__aggr_cpu_id_is_empty(id))
+	id = aggr_cpu_id__socket(cpu, data);
+	if (aggr_cpu_id__is_empty(&id))
 		return id;
 
 	id.die = die;
 	return id;
 }
 
-int cpu_map__get_core_id(int cpu)
+int cpu__get_core_id(struct perf_cpu cpu)
 {
-	int value, ret = cpu__get_topology_int(cpu, "core_id", &value);
+	int value, ret = cpu__get_topology_int(cpu.cpu, "core_id", &value);
 	return ret ?: value;
 }
 
-int cpu_map__get_node_id(int cpu)
-{
-	return cpu__get_node(cpu);
-}
-
-struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data)
+struct aggr_cpu_id aggr_cpu_id__core(struct perf_cpu cpu, void *data)
 {
-	int cpu;
-	struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
-
-	if (idx > map->nr)
-		return id;
+	struct aggr_cpu_id id;
+	int core = cpu__get_core_id(cpu);
 
-	cpu = map->map[idx];
-
-	cpu = cpu_map__get_core_id(cpu);
-
-	/* cpu_map__get_die returns a struct with socket and die set*/
-	id = cpu_map__get_die(map, idx, data);
-	if (cpu_map__aggr_cpu_id_is_empty(id))
+	/* aggr_cpu_id__die returns a struct with socket and die set. */
+	id = aggr_cpu_id__die(cpu, data);
+	if (aggr_cpu_id__is_empty(&id))
 		return id;
 
 	/*
 	 * core_id is relative to socket and die, we need a global id.
 	 * So we combine the result from cpu_map__get_die with the core id
 	 */
-	id.core = cpu;
+	id.core = core;
 	return id;
+
 }
 
-struct aggr_cpu_id cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data __maybe_unused)
+struct aggr_cpu_id aggr_cpu_id__cpu(struct perf_cpu cpu, void *data)
 {
-	struct aggr_cpu_id id = cpu_map__empty_aggr_cpu_id();
+	struct aggr_cpu_id id;
 
-	if (idx < 0 || idx >= map->nr)
+	/* aggr_cpu_id__core returns a struct with socket, die and core set. */
+	id = aggr_cpu_id__core(cpu, data);
+	if (aggr_cpu_id__is_empty(&id))
 		return id;
 
-	id.node = cpu_map__get_node_id(map->map[idx]);
+	id.cpu = cpu;
 	return id;
-}
 
-int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp)
-{
-	return cpu_map__build_map(cpus, sockp, cpu_map__get_socket, NULL);
 }
 
-int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep)
+struct aggr_cpu_id aggr_cpu_id__node(struct perf_cpu cpu, void *data __maybe_unused)
 {
-	return cpu_map__build_map(cpus, diep, cpu_map__get_die, NULL);
-}
-
-int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep)
-{
-	return cpu_map__build_map(cpus, corep, cpu_map__get_core, NULL);
-}
+	struct aggr_cpu_id id = aggr_cpu_id__empty();
 
-int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **numap)
-{
-	return cpu_map__build_map(cpus, numap, cpu_map__get_node, NULL);
+	id.node = cpu__get_node(cpu);
+	return id;
 }
 
 /* setup simple routines to easily access node numbers given a cpu number */
@@ -335,8 +319,8 @@ static void set_max_cpu_num(void)
 	int ret = -1;
 
 	/* set up default */
-	max_cpu_num = 4096;
-	max_present_cpu_num = 4096;
+	max_cpu_num.cpu = 4096;
+	max_present_cpu_num.cpu = 4096;
 
 	mnt = sysfs__mountpoint();
 	if (!mnt)
@@ -349,7 +333,7 @@ static void set_max_cpu_num(void)
 		goto out;
 	}
 
-	ret = get_max_num(path, &max_cpu_num);
+	ret = get_max_num(path, &max_cpu_num.cpu);
 	if (ret)
 		goto out;
 
@@ -360,11 +344,11 @@ static void set_max_cpu_num(void)
 		goto out;
 	}
 
-	ret = get_max_num(path, &max_present_cpu_num);
+	ret = get_max_num(path, &max_present_cpu_num.cpu);
 
 out:
 	if (ret)
-		pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num);
+		pr_err("Failed to read max cpus, using default of %d\n", max_cpu_num.cpu);
 }
 
 /* Determine highest possible node in the system for sparse allocation */
@@ -403,31 +387,31 @@ int cpu__max_node(void)
 	return max_node_num;
 }
 
-int cpu__max_cpu(void)
+struct perf_cpu cpu__max_cpu(void)
 {
-	if (unlikely(!max_cpu_num))
+	if (unlikely(!max_cpu_num.cpu))
 		set_max_cpu_num();
 
 	return max_cpu_num;
 }
 
-int cpu__max_present_cpu(void)
+struct perf_cpu cpu__max_present_cpu(void)
 {
-	if (unlikely(!max_present_cpu_num))
+	if (unlikely(!max_present_cpu_num.cpu))
 		set_max_cpu_num();
 
 	return max_present_cpu_num;
 }
 
 
-int cpu__get_node(int cpu)
+int cpu__get_node(struct perf_cpu cpu)
 {
 	if (unlikely(cpunode_map == NULL)) {
 		pr_debug("cpu_map not initialized\n");
 		return -1;
 	}
 
-	return cpunode_map[cpu];
+	return cpunode_map[cpu.cpu];
 }
 
 static int init_cpunode_map(void)
@@ -437,13 +421,13 @@ static int init_cpunode_map(void)
 	set_max_cpu_num();
 	set_max_node_num();
 
-	cpunode_map = calloc(max_cpu_num, sizeof(int));
+	cpunode_map = calloc(max_cpu_num.cpu, sizeof(int));
 	if (!cpunode_map) {
 		pr_err("%s: calloc failed\n", __func__);
 		return -1;
 	}
 
-	for (i = 0; i < max_cpu_num; i++)
+	for (i = 0; i < max_cpu_num.cpu; i++)
 		cpunode_map[i] = -1;
 
 	return 0;
@@ -502,47 +486,39 @@ int cpu__setup_cpunode_map(void)
 	return 0;
 }
 
-bool cpu_map__has(struct perf_cpu_map *cpus, int cpu)
-{
-	return perf_cpu_map__idx(cpus, cpu) != -1;
-}
-
-int cpu_map__cpu(struct perf_cpu_map *cpus, int idx)
-{
-	return cpus->map[idx];
-}
-
 size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size)
 {
-	int i, cpu, start = -1;
+	int i, start = -1;
 	bool first = true;
 	size_t ret = 0;
 
 #define COMMA first ? "" : ","
 
 	for (i = 0; i < map->nr + 1; i++) {
+		struct perf_cpu cpu = { .cpu = INT_MAX };
 		bool last = i == map->nr;
 
-		cpu = last ? INT_MAX : map->map[i];
+		if (!last)
+			cpu = map->map[i];
 
 		if (start == -1) {
 			start = i;
 			if (last) {
 				ret += snprintf(buf + ret, size - ret,
 						"%s%d", COMMA,
-						map->map[i]);
+						map->map[i].cpu);
 			}
-		} else if (((i - start) != (cpu - map->map[start])) || last) {
+		} else if (((i - start) != (cpu.cpu - map->map[start].cpu)) || last) {
 			int end = i - 1;
 
 			if (start == end) {
 				ret += snprintf(buf + ret, size - ret,
 						"%s%d", COMMA,
-						map->map[start]);
+						map->map[start].cpu);
 			} else {
 				ret += snprintf(buf + ret, size - ret,
 						"%s%d-%d", COMMA,
-						map->map[start], map->map[end]);
+						map->map[start].cpu, map->map[end].cpu);
 			}
 			first = false;
 			start = i;
@@ -569,23 +545,23 @@ size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size)
 	int i, cpu;
 	char *ptr = buf;
 	unsigned char *bitmap;
-	int last_cpu = cpu_map__cpu(map, map->nr - 1);
+	struct perf_cpu last_cpu = perf_cpu_map__cpu(map, map->nr - 1);
 
 	if (buf == NULL)
 		return 0;
 
-	bitmap = zalloc(last_cpu / 8 + 1);
+	bitmap = zalloc(last_cpu.cpu / 8 + 1);
 	if (bitmap == NULL) {
 		buf[0] = '\0';
 		return 0;
 	}
 
 	for (i = 0; i < map->nr; i++) {
-		cpu = cpu_map__cpu(map, i);
+		cpu = perf_cpu_map__cpu(map, i).cpu;
 		bitmap[cpu / 8] |= 1 << (cpu % 8);
 	}
 
-	for (cpu = last_cpu / 4 * 4; cpu >= 0; cpu -= 4) {
+	for (cpu = last_cpu.cpu / 4 * 4; cpu >= 0; cpu -= 4) {
 		unsigned char bits = bitmap[cpu / 8];
 
 		if (cpu % 8)
@@ -614,32 +590,35 @@ const struct perf_cpu_map *cpu_map__online(void) /* thread unsafe */
 	return online;
 }
 
-bool cpu_map__compare_aggr_cpu_id(struct aggr_cpu_id a, struct aggr_cpu_id b)
+bool aggr_cpu_id__equal(const struct aggr_cpu_id *a, const struct aggr_cpu_id *b)
 {
-	return a.thread == b.thread &&
-		a.node == b.node &&
-		a.socket == b.socket &&
-		a.die == b.die &&
-		a.core == b.core;
+	return a->thread == b->thread &&
+		a->node == b->node &&
+		a->socket == b->socket &&
+		a->die == b->die &&
+		a->core == b->core &&
+		a->cpu.cpu == b->cpu.cpu;
 }
 
-bool cpu_map__aggr_cpu_id_is_empty(struct aggr_cpu_id a)
+bool aggr_cpu_id__is_empty(const struct aggr_cpu_id *a)
 {
-	return a.thread == -1 &&
-		a.node == -1 &&
-		a.socket == -1 &&
-		a.die == -1 &&
-		a.core == -1;
+	return a->thread == -1 &&
+		a->node == -1 &&
+		a->socket == -1 &&
+		a->die == -1 &&
+		a->core == -1 &&
+		a->cpu.cpu == -1;
 }
 
-struct aggr_cpu_id cpu_map__empty_aggr_cpu_id(void)
+struct aggr_cpu_id aggr_cpu_id__empty(void)
 {
 	struct aggr_cpu_id ret = {
 		.thread = -1,
 		.node = -1,
 		.socket = -1,
 		.die = -1,
-		.core = -1
+		.core = -1,
+		.cpu = (struct perf_cpu){ .cpu = -1 },
 	};
 	return ret;
 }
diff --git a/tools/perf/util/cpumap.h b/tools/perf/util/cpumap.h
index a27eeaf086e8..0d3c2006a15d 100644
--- a/tools/perf/util/cpumap.h
+++ b/tools/perf/util/cpumap.h
@@ -2,71 +2,135 @@
 #ifndef __PERF_CPUMAP_H
 #define __PERF_CPUMAP_H
 
+#include <stdbool.h>
 #include <stdio.h>
 #include <stdbool.h>
 #include <internal/cpumap.h>
 #include <perf/cpumap.h>
 
+/** Identify where counts are aggregated, -1 implies not to aggregate. */
 struct aggr_cpu_id {
+	/** A value in the range 0 to number of threads. */
 	int thread;
+	/** The numa node X as read from /sys/devices/system/node/nodeX. */
 	int node;
+	/**
+	 * The socket number as read from
+	 * /sys/devices/system/cpu/cpuX/topology/physical_package_id.
+	 */
 	int socket;
+	/** The die id as read from /sys/devices/system/cpu/cpuX/topology/die_id. */
 	int die;
+	/** The core id as read from /sys/devices/system/cpu/cpuX/topology/core_id. */
 	int core;
+	/** CPU aggregation, note there is one CPU for each SMT thread. */
+	struct perf_cpu cpu;
 };
 
+/** A collection of aggr_cpu_id values, the "built" version is sorted and uniqued. */
 struct cpu_aggr_map {
 	refcount_t refcnt;
+	/** Number of valid entries. */
 	int nr;
+	/** The entries. */
 	struct aggr_cpu_id map[];
 };
 
 struct perf_record_cpu_map_data;
 
 struct perf_cpu_map *perf_cpu_map__empty_new(int nr);
-struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr);
 
 struct perf_cpu_map *cpu_map__new_data(struct perf_record_cpu_map_data *data);
 size_t cpu_map__snprint(struct perf_cpu_map *map, char *buf, size_t size);
 size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size);
 size_t cpu_map__fprintf(struct perf_cpu_map *map, FILE *fp);
-int cpu_map__get_socket_id(int cpu);
-struct aggr_cpu_id cpu_map__get_socket(struct perf_cpu_map *map, int idx, void *data);
-int cpu_map__get_die_id(int cpu);
-struct aggr_cpu_id cpu_map__get_die(struct perf_cpu_map *map, int idx, void *data);
-int cpu_map__get_core_id(int cpu);
-struct aggr_cpu_id cpu_map__get_core(struct perf_cpu_map *map, int idx, void *data);
-int cpu_map__get_node_id(int cpu);
-struct aggr_cpu_id  cpu_map__get_node(struct perf_cpu_map *map, int idx, void *data);
-int cpu_map__build_socket_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **sockp);
-int cpu_map__build_die_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **diep);
-int cpu_map__build_core_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **corep);
-int cpu_map__build_node_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **nodep);
 const struct perf_cpu_map *cpu_map__online(void); /* thread unsafe */
 
-static inline int cpu_map__socket(struct perf_cpu_map *sock, int s)
+int cpu__setup_cpunode_map(void);
+
+int cpu__max_node(void);
+struct perf_cpu cpu__max_cpu(void);
+struct perf_cpu cpu__max_present_cpu(void);
+
+/**
+ * cpu_map__is_dummy - Events associated with a pid, rather than a CPU, use a single dummy map with an entry of -1.
+ */
+static inline bool cpu_map__is_dummy(struct perf_cpu_map *cpus)
 {
-	if (!sock || s > sock->nr || s < 0)
-		return 0;
-	return sock->map[s];
+	return cpus->nr == 1 && cpus->map[0].cpu == -1;
 }
 
-int cpu__setup_cpunode_map(void);
+/**
+ * cpu__get_node - Returns the numa node X as read from
+ * /sys/devices/system/node/nodeX for the given CPU.
+ */
+int cpu__get_node(struct perf_cpu cpu);
+/**
+ * cpu__get_socket_id - Returns the socket number as read from
+ * /sys/devices/system/cpu/cpuX/topology/physical_package_id for the given CPU.
+ */
+int cpu__get_socket_id(struct perf_cpu cpu);
+/**
+ * cpu__get_die_id - Returns the die id as read from
+ * /sys/devices/system/cpu/cpuX/topology/die_id for the given CPU.
+ */
+int cpu__get_die_id(struct perf_cpu cpu);
+/**
+ * cpu__get_core_id - Returns the core id as read from
+ * /sys/devices/system/cpu/cpuX/topology/core_id for the given CPU.
+ */
+int cpu__get_core_id(struct perf_cpu cpu);
 
-int cpu__max_node(void);
-int cpu__max_cpu(void);
-int cpu__max_present_cpu(void);
-int cpu__get_node(int cpu);
+/**
+ * cpu_aggr_map__empty_new - Create a cpu_aggr_map of size nr with every entry
+ * being empty.
+ */
+struct cpu_aggr_map *cpu_aggr_map__empty_new(int nr);
+
+typedef struct aggr_cpu_id (*aggr_cpu_id_get_t)(struct perf_cpu cpu, void *data);
+
+/**
+ * cpu_aggr_map__new - Create a cpu_aggr_map with an aggr_cpu_id for each cpu in
+ * cpus. The aggr_cpu_id is created with 'get_id' that may have a data value
+ * passed to it. The cpu_aggr_map is sorted with duplicate values removed.
+ */
+struct cpu_aggr_map *cpu_aggr_map__new(const struct perf_cpu_map *cpus,
+				       aggr_cpu_id_get_t get_id,
+				       void *data);
 
-int cpu_map__build_map(struct perf_cpu_map *cpus, struct cpu_aggr_map **res,
-		       struct aggr_cpu_id (*f)(struct perf_cpu_map *map, int cpu, void *data),
-		       void *data);
+bool aggr_cpu_id__equal(const struct aggr_cpu_id *a, const struct aggr_cpu_id *b);
+bool aggr_cpu_id__is_empty(const struct aggr_cpu_id *a);
+struct aggr_cpu_id aggr_cpu_id__empty(void);
 
-int cpu_map__cpu(struct perf_cpu_map *cpus, int idx);
-bool cpu_map__has(struct perf_cpu_map *cpus, int cpu);
 
-bool cpu_map__compare_aggr_cpu_id(struct aggr_cpu_id a, struct aggr_cpu_id b);
-bool cpu_map__aggr_cpu_id_is_empty(struct aggr_cpu_id a);
-struct aggr_cpu_id cpu_map__empty_aggr_cpu_id(void);
+/**
+ * aggr_cpu_id__socket - Create an aggr_cpu_id with the socket populated with
+ * the socket for cpu. The function signature is compatible with
+ * aggr_cpu_id_get_t.
+ */
+struct aggr_cpu_id aggr_cpu_id__socket(struct perf_cpu cpu, void *data);
+/**
+ * aggr_cpu_id__die - Create an aggr_cpu_id with the die and socket populated
+ * with the die and socket for cpu. The function signature is compatible with
+ * aggr_cpu_id_get_t.
+ */
+struct aggr_cpu_id aggr_cpu_id__die(struct perf_cpu cpu, void *data);
+/**
+ * aggr_cpu_id__core - Create an aggr_cpu_id with the core, die and socket
+ * populated with the core, die and socket for cpu. The function signature is
+ * compatible with aggr_cpu_id_get_t.
+ */
+struct aggr_cpu_id aggr_cpu_id__core(struct perf_cpu cpu, void *data);
+/**
+ * aggr_cpu_id__core - Create an aggr_cpu_id with the cpu, core, die and socket
+ * populated with the cpu, core, die and socket for cpu. The function signature
+ * is compatible with aggr_cpu_id_get_t.
+ */
+struct aggr_cpu_id aggr_cpu_id__cpu(struct perf_cpu cpu, void *data);
+/**
+ * aggr_cpu_id__node - Create an aggr_cpu_id with the numa node populated for
+ * cpu. The function signature is compatible with aggr_cpu_id_get_t.
+ */
+struct aggr_cpu_id aggr_cpu_id__node(struct perf_cpu cpu, void *data);
 
 #endif /* __PERF_CPUMAP_H */
diff --git a/tools/perf/util/cputopo.c b/tools/perf/util/cputopo.c
index 51b429c86f98..e20b835a1194 100644
--- a/tools/perf/util/cputopo.c
+++ b/tools/perf/util/cputopo.c
@@ -165,7 +165,8 @@ static bool has_die_topology(void)
 	if (uname(&uts) < 0)
 		return false;
 
-	if (strncmp(uts.machine, "x86_64", 6))
+	if (strncmp(uts.machine, "x86_64", 6) &&
+	    strncmp(uts.machine, "s390x", 5))
 		return false;
 
 	scnprintf(filename, MAXPATHLEN, DIE_CPUS_FMT,
@@ -187,7 +188,7 @@ struct cpu_topology *cpu_topology__new(void)
 	struct perf_cpu_map *map;
 	bool has_die = has_die_topology();
 
-	ncpus = cpu__max_present_cpu();
+	ncpus = cpu__max_present_cpu().cpu;
 
 	/* build online CPU map */
 	map = perf_cpu_map__new(NULL);
@@ -218,7 +219,7 @@ struct cpu_topology *cpu_topology__new(void)
 	tp->core_cpus_list = addr;
 
 	for (i = 0; i < nr; i++) {
-		if (!cpu_map__has(map, i))
+		if (!perf_cpu_map__has(map, (struct perf_cpu){ .cpu = i }))
 			continue;
 
 		ret = build_cpu_topology(tp, i);
@@ -333,7 +334,7 @@ struct numa_topology *numa_topology__new(void)
 	tp->nr = nr;
 
 	for (i = 0; i < nr; i++) {
-		if (load_numa_node(&tp->nodes[i], node_map->map[i])) {
+		if (load_numa_node(&tp->nodes[i], node_map->map[i].cpu)) {
 			numa_topology__delete(tp);
 			tp = NULL;
 			break;
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index 2c06abf6dcd2..65e6c22f38e4 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -179,7 +179,7 @@ static int trace_event_printer(enum binary_printer_ops op,
 		break;
 	case BINARY_PRINT_CHAR_DATA:
 		printed += color_fprintf(fp, color, "%c",
-			      isprint(ch) ? ch : '.');
+			      isprint(ch) && isascii(ch) ? ch : '.');
 		break;
 	case BINARY_PRINT_CHAR_PAD:
 		printed += color_fprintf(fp, color, " ");
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index b9904896eb97..579e44c59914 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -285,13 +285,13 @@ out_enomem:
 
 int perf_env__read_cpu_topology_map(struct perf_env *env)
 {
-	int cpu, nr_cpus;
+	int idx, nr_cpus;
 
 	if (env->cpu != NULL)
 		return 0;
 
 	if (env->nr_cpus_avail == 0)
-		env->nr_cpus_avail = cpu__max_present_cpu();
+		env->nr_cpus_avail = cpu__max_present_cpu().cpu;
 
 	nr_cpus = env->nr_cpus_avail;
 	if (nr_cpus == -1)
@@ -301,10 +301,12 @@ int perf_env__read_cpu_topology_map(struct perf_env *env)
 	if (env->cpu == NULL)
 		return -ENOMEM;
 
-	for (cpu = 0; cpu < nr_cpus; ++cpu) {
-		env->cpu[cpu].core_id	= cpu_map__get_core_id(cpu);
-		env->cpu[cpu].socket_id	= cpu_map__get_socket_id(cpu);
-		env->cpu[cpu].die_id	= cpu_map__get_die_id(cpu);
+	for (idx = 0; idx < nr_cpus; ++idx) {
+		struct perf_cpu cpu = { .cpu = idx };
+
+		env->cpu[idx].core_id	= cpu__get_core_id(cpu);
+		env->cpu[idx].socket_id	= cpu__get_socket_id(cpu);
+		env->cpu[idx].die_id	= cpu__get_die_id(cpu);
 	}
 
 	env->nr_cpus_avail = nr_cpus;
@@ -381,7 +383,7 @@ static int perf_env__read_arch(struct perf_env *env)
 static int perf_env__read_nr_cpus_avail(struct perf_env *env)
 {
 	if (env->nr_cpus_avail == 0)
-		env->nr_cpus_avail = cpu__max_present_cpu();
+		env->nr_cpus_avail = cpu__max_present_cpu().cpu;
 
 	return env->nr_cpus_avail ? 0 : -ENOENT;
 }
@@ -487,7 +489,7 @@ const char *perf_env__pmu_mappings(struct perf_env *env)
 	return env->pmu_mappings;
 }
 
-int perf_env__numa_node(struct perf_env *env, int cpu)
+int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu)
 {
 	if (!env->nr_numa_map) {
 		struct numa_node *nn;
@@ -495,7 +497,7 @@ int perf_env__numa_node(struct perf_env *env, int cpu)
 
 		for (i = 0; i < env->nr_numa_nodes; i++) {
 			nn = &env->numa_nodes[i];
-			nr = max(nr, perf_cpu_map__max(nn->map));
+			nr = max(nr, perf_cpu_map__max(nn->map).cpu);
 		}
 
 		nr++;
@@ -514,13 +516,14 @@ int perf_env__numa_node(struct perf_env *env, int cpu)
 		env->nr_numa_map = nr;
 
 		for (i = 0; i < env->nr_numa_nodes; i++) {
-			int tmp, j;
+			struct perf_cpu tmp;
+			int j;
 
 			nn = &env->numa_nodes[i];
-			perf_cpu_map__for_each_cpu(j, tmp, nn->map)
-				env->numa_map[j] = i;
+			perf_cpu_map__for_each_cpu(tmp, j, nn->map)
+				env->numa_map[tmp.cpu] = i;
 		}
 	}
 
-	return cpu >= 0 && cpu < env->nr_numa_map ? env->numa_map[cpu] : -1;
+	return cpu.cpu >= 0 && cpu.cpu < env->nr_numa_map ? env->numa_map[cpu.cpu] : -1;
 }
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index 163e5ec503a2..a3541f98e1fc 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -4,6 +4,7 @@
 
 #include <linux/types.h>
 #include <linux/rbtree.h>
+#include "cpumap.h"
 #include "rwsem.h"
 
 struct perf_cpu_map;
@@ -170,5 +171,5 @@ struct bpf_prog_info_node *perf_env__find_bpf_prog_info(struct perf_env *env,
 bool perf_env__insert_btf(struct perf_env *env, struct btf_node *btf_node);
 struct btf_node *perf_env__find_btf(struct perf_env *env, __u32 btf_id);
 
-int perf_env__numa_node(struct perf_env *env, int cpu);
+int perf_env__numa_node(struct perf_env *env, struct perf_cpu cpu);
 #endif /* __PERF_ENV_H */
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index 5f92319ce258..6e88d404b5b3 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -342,36 +342,65 @@ static int evlist__nr_threads(struct evlist *evlist, struct evsel *evsel)
 		return perf_thread_map__nr(evlist->core.threads);
 }
 
-void evlist__cpu_iter_start(struct evlist *evlist)
-{
-	struct evsel *pos;
-
-	/*
-	 * Reset the per evsel cpu_iter. This is needed because
-	 * each evsel's cpumap may have a different index space,
-	 * and some operations need the index to modify
-	 * the FD xyarray (e.g. open, close)
-	 */
-	evlist__for_each_entry(evlist, pos)
-		pos->cpu_iter = 0;
-}
+struct evlist_cpu_iterator evlist__cpu_begin(struct evlist *evlist, struct affinity *affinity)
+{
+	struct evlist_cpu_iterator itr = {
+		.container = evlist,
+		.evsel = evlist__first(evlist),
+		.cpu_map_idx = 0,
+		.evlist_cpu_map_idx = 0,
+		.evlist_cpu_map_nr = perf_cpu_map__nr(evlist->core.all_cpus),
+		.cpu = (struct perf_cpu){ .cpu = -1},
+		.affinity = affinity,
+	};
 
-bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu)
-{
-	if (ev->cpu_iter >= ev->core.cpus->nr)
-		return true;
-	if (cpu >= 0 && ev->core.cpus->map[ev->cpu_iter] != cpu)
-		return true;
-	return false;
+	if (itr.affinity) {
+		itr.cpu = perf_cpu_map__cpu(evlist->core.all_cpus, 0);
+		affinity__set(itr.affinity, itr.cpu.cpu);
+		itr.cpu_map_idx = perf_cpu_map__idx(itr.evsel->core.cpus, itr.cpu);
+		/*
+		 * If this CPU isn't in the evsel's cpu map then advance through
+		 * the list.
+		 */
+		if (itr.cpu_map_idx == -1)
+			evlist_cpu_iterator__next(&itr);
+	}
+	return itr;
+}
+
+void evlist_cpu_iterator__next(struct evlist_cpu_iterator *evlist_cpu_itr)
+{
+	while (evlist_cpu_itr->evsel != evlist__last(evlist_cpu_itr->container)) {
+		evlist_cpu_itr->evsel = evsel__next(evlist_cpu_itr->evsel);
+		evlist_cpu_itr->cpu_map_idx =
+			perf_cpu_map__idx(evlist_cpu_itr->evsel->core.cpus,
+					  evlist_cpu_itr->cpu);
+		if (evlist_cpu_itr->cpu_map_idx != -1)
+			return;
+	}
+	evlist_cpu_itr->evlist_cpu_map_idx++;
+	if (evlist_cpu_itr->evlist_cpu_map_idx < evlist_cpu_itr->evlist_cpu_map_nr) {
+		evlist_cpu_itr->evsel = evlist__first(evlist_cpu_itr->container);
+		evlist_cpu_itr->cpu =
+			perf_cpu_map__cpu(evlist_cpu_itr->container->core.all_cpus,
+					  evlist_cpu_itr->evlist_cpu_map_idx);
+		if (evlist_cpu_itr->affinity)
+			affinity__set(evlist_cpu_itr->affinity, evlist_cpu_itr->cpu.cpu);
+		evlist_cpu_itr->cpu_map_idx =
+			perf_cpu_map__idx(evlist_cpu_itr->evsel->core.cpus,
+					  evlist_cpu_itr->cpu);
+		/*
+		 * If this CPU isn't in the evsel's cpu map then advance through
+		 * the list.
+		 */
+		if (evlist_cpu_itr->cpu_map_idx == -1)
+			evlist_cpu_iterator__next(evlist_cpu_itr);
+	}
 }
 
-bool evsel__cpu_iter_skip(struct evsel *ev, int cpu)
+bool evlist_cpu_iterator__end(const struct evlist_cpu_iterator *evlist_cpu_itr)
 {
-	if (!evsel__cpu_iter_skip_no_inc(ev, cpu)) {
-		ev->cpu_iter++;
-		return false;
-	}
-	return true;
+	return evlist_cpu_itr->evlist_cpu_map_idx >= evlist_cpu_itr->evlist_cpu_map_nr;
 }
 
 static int evsel__strcmp(struct evsel *pos, char *evsel_name)
@@ -400,31 +429,26 @@ static int evlist__is_enabled(struct evlist *evlist)
 static void __evlist__disable(struct evlist *evlist, char *evsel_name)
 {
 	struct evsel *pos;
+	struct evlist_cpu_iterator evlist_cpu_itr;
 	struct affinity affinity;
-	int cpu, i, imm = 0;
 	bool has_imm = false;
 
 	if (affinity__setup(&affinity) < 0)
 		return;
 
 	/* Disable 'immediate' events last */
-	for (imm = 0; imm <= 1; imm++) {
-		evlist__for_each_cpu(evlist, i, cpu) {
-			affinity__set(&affinity, cpu);
-
-			evlist__for_each_entry(evlist, pos) {
-				if (evsel__strcmp(pos, evsel_name))
-					continue;
-				if (evsel__cpu_iter_skip(pos, cpu))
-					continue;
-				if (pos->disabled || !evsel__is_group_leader(pos) || !pos->core.fd)
-					continue;
-				if (pos->immediate)
-					has_imm = true;
-				if (pos->immediate != imm)
-					continue;
-				evsel__disable_cpu(pos, pos->cpu_iter - 1);
-			}
+	for (int imm = 0; imm <= 1; imm++) {
+		evlist__for_each_cpu(evlist_cpu_itr, evlist, &affinity) {
+			pos = evlist_cpu_itr.evsel;
+			if (evsel__strcmp(pos, evsel_name))
+				continue;
+			if (pos->disabled || !evsel__is_group_leader(pos) || !pos->core.fd)
+				continue;
+			if (pos->immediate)
+				has_imm = true;
+			if (pos->immediate != imm)
+				continue;
+			evsel__disable_cpu(pos, evlist_cpu_itr.cpu_map_idx);
 		}
 		if (!has_imm)
 			break;
@@ -462,24 +486,19 @@ void evlist__disable_evsel(struct evlist *evlist, char *evsel_name)
 static void __evlist__enable(struct evlist *evlist, char *evsel_name)
 {
 	struct evsel *pos;
+	struct evlist_cpu_iterator evlist_cpu_itr;
 	struct affinity affinity;
-	int cpu, i;
 
 	if (affinity__setup(&affinity) < 0)
 		return;
 
-	evlist__for_each_cpu(evlist, i, cpu) {
-		affinity__set(&affinity, cpu);
-
-		evlist__for_each_entry(evlist, pos) {
-			if (evsel__strcmp(pos, evsel_name))
-				continue;
-			if (evsel__cpu_iter_skip(pos, cpu))
-				continue;
-			if (!evsel__is_group_leader(pos) || !pos->core.fd)
-				continue;
-			evsel__enable_cpu(pos, pos->cpu_iter - 1);
-		}
+	evlist__for_each_cpu(evlist_cpu_itr, evlist, &affinity) {
+		pos = evlist_cpu_itr.evsel;
+		if (evsel__strcmp(pos, evsel_name))
+			continue;
+		if (!evsel__is_group_leader(pos) || !pos->core.fd)
+			continue;
+		evsel__enable_cpu(pos, evlist_cpu_itr.cpu_map_idx);
 	}
 	affinity__cleanup(&affinity);
 	evlist__for_each_entry(evlist, pos) {
@@ -800,7 +819,7 @@ perf_evlist__mmap_cb_get(struct perf_evlist *_evlist, bool overwrite, int idx)
 
 static int
 perf_evlist__mmap_cb_mmap(struct perf_mmap *_map, struct perf_mmap_param *_mp,
-			  int output, int cpu)
+			  int output, struct perf_cpu cpu)
 {
 	struct mmap *map = container_of(_map, struct mmap, core);
 	struct mmap_params *mp = container_of(_mp, struct mmap_params, core);
@@ -1264,14 +1283,14 @@ void evlist__set_selected(struct evlist *evlist, struct evsel *evsel)
 void evlist__close(struct evlist *evlist)
 {
 	struct evsel *evsel;
+	struct evlist_cpu_iterator evlist_cpu_itr;
 	struct affinity affinity;
-	int cpu, i;
 
 	/*
 	 * With perf record core.cpus is usually NULL.
 	 * Use the old method to handle this for now.
 	 */
-	if (!evlist->core.cpus) {
+	if (!evlist->core.cpus || cpu_map__is_dummy(evlist->core.cpus)) {
 		evlist__for_each_entry_reverse(evlist, evsel)
 			evsel__close(evsel);
 		return;
@@ -1279,15 +1298,12 @@ void evlist__close(struct evlist *evlist)
 
 	if (affinity__setup(&affinity) < 0)
 		return;
-	evlist__for_each_cpu(evlist, i, cpu) {
-		affinity__set(&affinity, cpu);
 
-		evlist__for_each_entry_reverse(evlist, evsel) {
-			if (evsel__cpu_iter_skip(evsel, cpu))
-			    continue;
-			perf_evsel__close_cpu(&evsel->core, evsel->cpu_iter - 1);
-		}
+	evlist__for_each_cpu(evlist_cpu_itr, evlist, &affinity) {
+		perf_evsel__close_cpu(&evlist_cpu_itr.evsel->core,
+				      evlist_cpu_itr.cpu_map_idx);
 	}
+
 	affinity__cleanup(&affinity);
 	evlist__for_each_entry_reverse(evlist, evsel) {
 		perf_evsel__free_fd(&evsel->core);
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 97bfb8d0be4f..64cba56fbc74 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -64,6 +64,7 @@ struct evlist {
 	struct evsel *selected;
 	struct events_stats stats;
 	struct perf_env	*env;
+	const char *hybrid_pmu_name;
 	void (*trace_event_sample_raw)(struct evlist *evlist,
 				       union perf_event *event,
 				       struct perf_sample *sample);
@@ -110,6 +111,7 @@ int __evlist__add_default_attrs(struct evlist *evlist,
 	__evlist__add_default_attrs(evlist, array, ARRAY_SIZE(array))
 
 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);
 
@@ -325,17 +327,53 @@ void evlist__to_front(struct evlist *evlist, struct evsel *move_evsel);
 #define evlist__for_each_entry_safe(evlist, tmp, evsel) \
 	__evlist__for_each_entry_safe(&(evlist)->core.entries, tmp, evsel)
 
-#define evlist__for_each_cpu(evlist, index, cpu)	\
-	evlist__cpu_iter_start(evlist);			\
-	perf_cpu_map__for_each_cpu (cpu, index, (evlist)->core.all_cpus)
+/** Iterator state for evlist__for_each_cpu */
+struct evlist_cpu_iterator {
+	/** The list being iterated through. */
+	struct evlist *container;
+	/** The current evsel of the iterator. */
+	struct evsel *evsel;
+	/** The CPU map index corresponding to the evsel->core.cpus for the current CPU. */
+	int cpu_map_idx;
+	/**
+	 * The CPU map index corresponding to evlist->core.all_cpus for the
+	 * current CPU.  Distinct from cpu_map_idx as the evsel's cpu map may
+	 * contain fewer entries.
+	 */
+	int evlist_cpu_map_idx;
+	/** The number of CPU map entries in evlist->core.all_cpus. */
+	int evlist_cpu_map_nr;
+	/** The current CPU of the iterator. */
+	struct perf_cpu cpu;
+	/** If present, used to set the affinity when switching between CPUs. */
+	struct affinity *affinity;
+};
+
+/**
+ * evlist__for_each_cpu - without affinity, iterate over the evlist. With
+ *                        affinity, iterate over all CPUs and then the evlist
+ *                        for each evsel on that CPU. When switching between
+ *                        CPUs the affinity is set to the CPU to avoid IPIs
+ *                        during syscalls.
+ * @evlist_cpu_itr: the iterator instance.
+ * @evlist: evlist instance to iterate.
+ * @affinity: NULL or used to set the affinity to the current CPU.
+ */
+#define evlist__for_each_cpu(evlist_cpu_itr, evlist, affinity)		\
+	for ((evlist_cpu_itr) = evlist__cpu_begin(evlist, affinity);	\
+	     !evlist_cpu_iterator__end(&evlist_cpu_itr);		\
+	     evlist_cpu_iterator__next(&evlist_cpu_itr))
+
+/** Returns an iterator set to the first CPU/evsel of evlist. */
+struct evlist_cpu_iterator evlist__cpu_begin(struct evlist *evlist, struct affinity *affinity);
+/** Move to next element in iterator, updating CPU, evsel and the affinity. */
+void evlist_cpu_iterator__next(struct evlist_cpu_iterator *evlist_cpu_itr);
+/** Returns true when iterator is at the end of the CPUs and evlist. */
+bool evlist_cpu_iterator__end(const struct evlist_cpu_iterator *evlist_cpu_itr);
 
 struct evsel *evlist__get_tracking_event(struct evlist *evlist);
 void evlist__set_tracking_event(struct evlist *evlist, struct evsel *tracking_evsel);
 
-void evlist__cpu_iter_start(struct evlist *evlist);
-bool evsel__cpu_iter_skip(struct evsel *ev, int cpu);
-bool evsel__cpu_iter_skip_no_inc(struct evsel *ev, int cpu);
-
 struct evsel *evlist__find_evsel_by_str(struct evlist *evlist, const char *str);
 
 struct evsel *evlist__event2evsel(struct evlist *evlist, union perf_event *event);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index f29d37004f55..2f6b18af49e5 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -1372,9 +1372,9 @@ int evsel__append_addr_filter(struct evsel *evsel, const char *filter)
 }
 
 /* Caller has to clear disabled after going through all CPUs. */
-int evsel__enable_cpu(struct evsel *evsel, int cpu)
+int evsel__enable_cpu(struct evsel *evsel, int cpu_map_idx)
 {
-	return perf_evsel__enable_cpu(&evsel->core, cpu);
+	return perf_evsel__enable_cpu(&evsel->core, cpu_map_idx);
 }
 
 int evsel__enable(struct evsel *evsel)
@@ -1387,9 +1387,9 @@ int evsel__enable(struct evsel *evsel)
 }
 
 /* Caller has to set disabled after going through all CPUs. */
-int evsel__disable_cpu(struct evsel *evsel, int cpu)
+int evsel__disable_cpu(struct evsel *evsel, int cpu_map_idx)
 {
-	return perf_evsel__disable_cpu(&evsel->core, cpu);
+	return perf_evsel__disable_cpu(&evsel->core, cpu_map_idx);
 }
 
 int evsel__disable(struct evsel *evsel)
@@ -1455,7 +1455,7 @@ void evsel__delete(struct evsel *evsel)
 	free(evsel);
 }
 
-void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
+void evsel__compute_deltas(struct evsel *evsel, int cpu_map_idx, int thread,
 			   struct perf_counts_values *count)
 {
 	struct perf_counts_values tmp;
@@ -1463,12 +1463,12 @@ void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
 	if (!evsel->prev_raw_counts)
 		return;
 
-	if (cpu == -1) {
+	if (cpu_map_idx == -1) {
 		tmp = evsel->prev_raw_counts->aggr;
 		evsel->prev_raw_counts->aggr = *count;
 	} else {
-		tmp = *perf_counts(evsel->prev_raw_counts, cpu, thread);
-		*perf_counts(evsel->prev_raw_counts, cpu, thread) = *count;
+		tmp = *perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread);
+		*perf_counts(evsel->prev_raw_counts, cpu_map_idx, thread) = *count;
 	}
 
 	count->val = count->val - tmp.val;
@@ -1476,46 +1476,28 @@ void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
 	count->run = count->run - tmp.run;
 }
 
-void perf_counts_values__scale(struct perf_counts_values *count,
-			       bool scale, s8 *pscaled)
+static int evsel__read_one(struct evsel *evsel, int cpu_map_idx, int thread)
 {
-	s8 scaled = 0;
+	struct perf_counts_values *count = perf_counts(evsel->counts, cpu_map_idx, thread);
 
-	if (scale) {
-		if (count->run == 0) {
-			scaled = -1;
-			count->val = 0;
-		} else if (count->run < count->ena) {
-			scaled = 1;
-			count->val = (u64)((double) count->val * count->ena / count->run);
-		}
-	}
-
-	if (pscaled)
-		*pscaled = scaled;
-}
-
-static int evsel__read_one(struct evsel *evsel, int cpu, int thread)
-{
-	struct perf_counts_values *count = perf_counts(evsel->counts, cpu, thread);
-
-	return perf_evsel__read(&evsel->core, cpu, thread, count);
+	return perf_evsel__read(&evsel->core, cpu_map_idx, thread, count);
 }
 
-static void evsel__set_count(struct evsel *counter, int cpu, int thread, u64 val, u64 ena, u64 run)
+static void evsel__set_count(struct evsel *counter, int cpu_map_idx, int thread,
+			     u64 val, u64 ena, u64 run)
 {
 	struct perf_counts_values *count;
 
-	count = perf_counts(counter->counts, cpu, thread);
+	count = perf_counts(counter->counts, cpu_map_idx, thread);
 
 	count->val    = val;
 	count->ena    = ena;
 	count->run    = run;
 
-	perf_counts__set_loaded(counter->counts, cpu, thread, true);
+	perf_counts__set_loaded(counter->counts, cpu_map_idx, thread, true);
 }
 
-static int evsel__process_group_data(struct evsel *leader, int cpu, int thread, u64 *data)
+static int evsel__process_group_data(struct evsel *leader, int cpu_map_idx, int thread, u64 *data)
 {
 	u64 read_format = leader->core.attr.read_format;
 	struct sample_read_value *v;
@@ -1534,7 +1516,7 @@ static int evsel__process_group_data(struct evsel *leader, int cpu, int thread,
 
 	v = (struct sample_read_value *) data;
 
-	evsel__set_count(leader, cpu, thread, v[0].value, ena, run);
+	evsel__set_count(leader, cpu_map_idx, thread, v[0].value, ena, run);
 
 	for (i = 1; i < nr; i++) {
 		struct evsel *counter;
@@ -1543,13 +1525,13 @@ static int evsel__process_group_data(struct evsel *leader, int cpu, int thread,
 		if (!counter)
 			return -EINVAL;
 
-		evsel__set_count(counter, cpu, thread, v[i].value, ena, run);
+		evsel__set_count(counter, cpu_map_idx, thread, v[i].value, ena, run);
 	}
 
 	return 0;
 }
 
-static int evsel__read_group(struct evsel *leader, int cpu, int thread)
+static int evsel__read_group(struct evsel *leader, int cpu_map_idx, int thread)
 {
 	struct perf_stat_evsel *ps = leader->stats;
 	u64 read_format = leader->core.attr.read_format;
@@ -1570,67 +1552,67 @@ static int evsel__read_group(struct evsel *leader, int cpu, int thread)
 		ps->group_data = data;
 	}
 
-	if (FD(leader, cpu, thread) < 0)
+	if (FD(leader, cpu_map_idx, thread) < 0)
 		return -EINVAL;
 
-	if (readn(FD(leader, cpu, thread), data, size) <= 0)
+	if (readn(FD(leader, cpu_map_idx, thread), data, size) <= 0)
 		return -errno;
 
-	return evsel__process_group_data(leader, cpu, thread, data);
+	return evsel__process_group_data(leader, cpu_map_idx, thread, data);
 }
 
-int evsel__read_counter(struct evsel *evsel, int cpu, int thread)
+int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread)
 {
 	u64 read_format = evsel->core.attr.read_format;
 
 	if (read_format & PERF_FORMAT_GROUP)
-		return evsel__read_group(evsel, cpu, thread);
+		return evsel__read_group(evsel, cpu_map_idx, thread);
 
-	return evsel__read_one(evsel, cpu, thread);
+	return evsel__read_one(evsel, cpu_map_idx, thread);
 }
 
-int __evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread, bool scale)
+int __evsel__read_on_cpu(struct evsel *evsel, int cpu_map_idx, int thread, bool scale)
 {
 	struct perf_counts_values count;
 	size_t nv = scale ? 3 : 1;
 
-	if (FD(evsel, cpu, thread) < 0)
+	if (FD(evsel, cpu_map_idx, thread) < 0)
 		return -EINVAL;
 
-	if (evsel->counts == NULL && evsel__alloc_counts(evsel, cpu + 1, thread + 1) < 0)
+	if (evsel->counts == NULL && evsel__alloc_counts(evsel) < 0)
 		return -ENOMEM;
 
-	if (readn(FD(evsel, cpu, thread), &count, nv * sizeof(u64)) <= 0)
+	if (readn(FD(evsel, cpu_map_idx, thread), &count, nv * sizeof(u64)) <= 0)
 		return -errno;
 
-	evsel__compute_deltas(evsel, cpu, thread, &count);
+	evsel__compute_deltas(evsel, cpu_map_idx, thread, &count);
 	perf_counts_values__scale(&count, scale, NULL);
-	*perf_counts(evsel->counts, cpu, thread) = count;
+	*perf_counts(evsel->counts, cpu_map_idx, thread) = count;
 	return 0;
 }
 
 static int evsel__match_other_cpu(struct evsel *evsel, struct evsel *other,
-				  int cpu)
+				  int cpu_map_idx)
 {
-	int cpuid;
+	struct perf_cpu cpu;
 
-	cpuid = perf_cpu_map__cpu(evsel->core.cpus, cpu);
-	return perf_cpu_map__idx(other->core.cpus, cpuid);
+	cpu = perf_cpu_map__cpu(evsel->core.cpus, cpu_map_idx);
+	return perf_cpu_map__idx(other->core.cpus, cpu);
 }
 
-static int evsel__hybrid_group_cpu(struct evsel *evsel, int cpu)
+static int evsel__hybrid_group_cpu_map_idx(struct evsel *evsel, int cpu_map_idx)
 {
 	struct evsel *leader = evsel__leader(evsel);
 
 	if ((evsel__is_hybrid(evsel) && !evsel__is_hybrid(leader)) ||
 	    (!evsel__is_hybrid(evsel) && evsel__is_hybrid(leader))) {
-		return evsel__match_other_cpu(evsel, leader, cpu);
+		return evsel__match_other_cpu(evsel, leader, cpu_map_idx);
 	}
 
-	return cpu;
+	return cpu_map_idx;
 }
 
-static int get_group_fd(struct evsel *evsel, int cpu, int thread)
+static int get_group_fd(struct evsel *evsel, int cpu_map_idx, int thread)
 {
 	struct evsel *leader = evsel__leader(evsel);
 	int fd;
@@ -1644,11 +1626,11 @@ static int get_group_fd(struct evsel *evsel, int cpu, int thread)
 	 */
 	BUG_ON(!leader->core.fd);
 
-	cpu = evsel__hybrid_group_cpu(evsel, cpu);
-	if (cpu == -1)
+	cpu_map_idx = evsel__hybrid_group_cpu_map_idx(evsel, cpu_map_idx);
+	if (cpu_map_idx == -1)
 		return -1;
 
-	fd = FD(leader, cpu, thread);
+	fd = FD(leader, cpu_map_idx, thread);
 	BUG_ON(fd == -1);
 
 	return fd;
@@ -1662,16 +1644,16 @@ static void evsel__remove_fd(struct evsel *pos, int nr_cpus, int nr_threads, int
 }
 
 static int update_fds(struct evsel *evsel,
-		      int nr_cpus, int cpu_idx,
+		      int nr_cpus, int cpu_map_idx,
 		      int nr_threads, int thread_idx)
 {
 	struct evsel *pos;
 
-	if (cpu_idx >= nr_cpus || thread_idx >= nr_threads)
+	if (cpu_map_idx >= nr_cpus || thread_idx >= nr_threads)
 		return -EINVAL;
 
 	evlist__for_each_entry(evsel->evlist, pos) {
-		nr_cpus = pos != evsel ? nr_cpus : cpu_idx;
+		nr_cpus = pos != evsel ? nr_cpus : cpu_map_idx;
 
 		evsel__remove_fd(pos, nr_cpus, nr_threads, thread_idx);
 
@@ -1685,10 +1667,10 @@ static int update_fds(struct evsel *evsel,
 	return 0;
 }
 
-bool evsel__ignore_missing_thread(struct evsel *evsel,
-				  int nr_cpus, int cpu,
-				  struct perf_thread_map *threads,
-				  int thread, int err)
+static bool evsel__ignore_missing_thread(struct evsel *evsel,
+					 int nr_cpus, int cpu_map_idx,
+					 struct perf_thread_map *threads,
+					 int thread, int err)
 {
 	pid_t ignore_pid = perf_thread_map__pid(threads, thread);
 
@@ -1711,7 +1693,7 @@ bool evsel__ignore_missing_thread(struct evsel *evsel,
 	 * We should remove fd for missing_thread first
 	 * because thread_map__remove() will decrease threads->nr.
 	 */
-	if (update_fds(evsel, nr_cpus, cpu, threads->nr, thread))
+	if (update_fds(evsel, nr_cpus, cpu_map_idx, threads->nr, thread))
 		return false;
 
 	if (thread_map__remove(threads, thread))
@@ -1993,9 +1975,9 @@ bool evsel__increase_rlimit(enum rlimit_action *set_rlimit)
 
 static int evsel__open_cpu(struct evsel *evsel, struct perf_cpu_map *cpus,
 		struct perf_thread_map *threads,
-		int start_cpu, int end_cpu)
+		int start_cpu_map_idx, int end_cpu_map_idx)
 {
-	int cpu, thread, nthreads;
+	int idx, thread, nthreads;
 	int pid = -1, err, old_errno;
 	enum rlimit_action set_rlimit = NO_CHANGE;
 
@@ -2022,7 +2004,7 @@ fallback_missing_features:
 
 	display_attr(&evsel->core.attr);
 
-	for (cpu = start_cpu; cpu < end_cpu; cpu++) {
+	for (idx = start_cpu_map_idx; idx < end_cpu_map_idx; idx++) {
 
 		for (thread = 0; thread < nthreads; thread++) {
 			int fd, group_fd;
@@ -2033,17 +2015,17 @@ retry_open:
 			if (!evsel->cgrp && !evsel->core.system_wide)
 				pid = perf_thread_map__pid(threads, thread);
 
-			group_fd = get_group_fd(evsel, cpu, thread);
+			group_fd = get_group_fd(evsel, idx, thread);
 
 			test_attr__ready();
 
 			pr_debug2_peo("sys_perf_event_open: pid %d  cpu %d  group_fd %d  flags %#lx",
-				pid, cpus->map[cpu], group_fd, evsel->open_flags);
+				pid, cpus->map[idx].cpu, group_fd, evsel->open_flags);
 
-			fd = sys_perf_event_open(&evsel->core.attr, pid, cpus->map[cpu],
+			fd = sys_perf_event_open(&evsel->core.attr, pid, cpus->map[idx].cpu,
 						group_fd, evsel->open_flags);
 
-			FD(evsel, cpu, thread) = fd;
+			FD(evsel, idx, thread) = fd;
 
 			if (fd < 0) {
 				err = -errno;
@@ -2053,10 +2035,10 @@ retry_open:
 				goto try_fallback;
 			}
 
-			bpf_counter__install_pe(evsel, cpu, fd);
+			bpf_counter__install_pe(evsel, idx, fd);
 
 			if (unlikely(test_attr__enabled)) {
-				test_attr__open(&evsel->core.attr, pid, cpus->map[cpu],
+				test_attr__open(&evsel->core.attr, pid, cpus->map[idx],
 						fd, group_fd, evsel->open_flags);
 			}
 
@@ -2097,7 +2079,7 @@ try_fallback:
 	if (evsel__precise_ip_fallback(evsel))
 		goto retry_open;
 
-	if (evsel__ignore_missing_thread(evsel, cpus->nr, cpu, threads, thread, err)) {
+	if (evsel__ignore_missing_thread(evsel, cpus->nr, idx, threads, thread, err)) {
 		/* We just removed 1 thread, so lower the upper nthreads limit. */
 		nthreads--;
 
@@ -2112,7 +2094,7 @@ try_fallback:
 	if (err == -EMFILE && evsel__increase_rlimit(&set_rlimit))
 		goto retry_open;
 
-	if (err != -EINVAL || cpu > 0 || thread > 0)
+	if (err != -EINVAL || idx > 0 || thread > 0)
 		goto out_close;
 
 	if (evsel__detect_missing_features(evsel))
@@ -2124,12 +2106,12 @@ out_close:
 	old_errno = errno;
 	do {
 		while (--thread >= 0) {
-			if (FD(evsel, cpu, thread) >= 0)
-				close(FD(evsel, cpu, thread));
-			FD(evsel, cpu, thread) = -1;
+			if (FD(evsel, idx, thread) >= 0)
+				close(FD(evsel, idx, thread));
+			FD(evsel, idx, thread) = -1;
 		}
 		thread = nthreads;
-	} while (--cpu >= 0);
+	} while (--idx >= 0);
 	errno = old_errno;
 	return err;
 }
@@ -2146,13 +2128,13 @@ void evsel__close(struct evsel *evsel)
 	perf_evsel__free_id(&evsel->core);
 }
 
-int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu)
+int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu_map_idx)
 {
-	if (cpu == -1)
+	if (cpu_map_idx == -1)
 		return evsel__open_cpu(evsel, cpus, NULL, 0,
 					cpus ? cpus->nr : 1);
 
-	return evsel__open_cpu(evsel, cpus, NULL, cpu, cpu + 1);
+	return evsel__open_cpu(evsel, cpus, NULL, cpu_map_idx, cpu_map_idx + 1);
 }
 
 int evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads)
@@ -2952,6 +2934,10 @@ int evsel__open_strerror(struct evsel *evsel, struct target *target,
 			return scnprintf(msg, size, "wrong clockid (%d).", clockid);
 		if (perf_missing_features.aux_output)
 			return scnprintf(msg, size, "The 'aux_output' feature is not supported, update the kernel.");
+		if (!target__has_cpu(target))
+			return scnprintf(msg, size,
+	"Invalid event (%s) in per-thread mode, enable system wide with '-a'.",
+					evsel__name(evsel));
 		break;
 	case ENODATA:
 		return scnprintf(msg, size, "Cannot collect data source with the load latency event alone. "
@@ -2975,15 +2961,15 @@ struct perf_env *evsel__env(struct evsel *evsel)
 
 static int store_evsel_ids(struct evsel *evsel, struct evlist *evlist)
 {
-	int cpu, thread;
+	int cpu_map_idx, thread;
 
-	for (cpu = 0; cpu < xyarray__max_x(evsel->core.fd); cpu++) {
+	for (cpu_map_idx = 0; cpu_map_idx < xyarray__max_x(evsel->core.fd); cpu_map_idx++) {
 		for (thread = 0; thread < xyarray__max_y(evsel->core.fd);
 		     thread++) {
-			int fd = FD(evsel, cpu, thread);
+			int fd = FD(evsel, cpu_map_idx, thread);
 
 			if (perf_evlist__id_add_fd(&evlist->core, &evsel->core,
-						   cpu, thread, fd) < 0)
+						   cpu_map_idx, thread, fd) < 0)
 				return -1;
 		}
 	}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 29d49a8c1e92..5720ceebffac 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -121,7 +121,6 @@ struct evsel {
 	bool			errored;
 	struct hashmap		*per_pkg_mask;
 	int			err;
-	int			cpu_iter;
 	struct {
 		evsel__sb_cb_t	*cb;
 		void		*data;
@@ -195,9 +194,6 @@ static inline int evsel__nr_cpus(struct evsel *evsel)
 	return evsel__cpus(evsel)->nr;
 }
 
-void perf_counts_values__scale(struct perf_counts_values *count,
-			       bool scale, s8 *pscaled);
-
 void evsel__compute_deltas(struct evsel *evsel, int cpu, int thread,
 			   struct perf_counts_values *count);
 
@@ -288,12 +284,12 @@ void arch_evsel__fixup_new_cycles(struct perf_event_attr *attr);
 int evsel__set_filter(struct evsel *evsel, const char *filter);
 int evsel__append_tp_filter(struct evsel *evsel, const char *filter);
 int evsel__append_addr_filter(struct evsel *evsel, const char *filter);
-int evsel__enable_cpu(struct evsel *evsel, int cpu);
+int evsel__enable_cpu(struct evsel *evsel, int cpu_map_idx);
 int evsel__enable(struct evsel *evsel);
 int evsel__disable(struct evsel *evsel);
-int evsel__disable_cpu(struct evsel *evsel, int cpu);
+int evsel__disable_cpu(struct evsel *evsel, int cpu_map_idx);
 
-int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu);
+int evsel__open_per_cpu(struct evsel *evsel, struct perf_cpu_map *cpus, int cpu_map_idx);
 int evsel__open_per_thread(struct evsel *evsel, struct perf_thread_map *threads);
 int evsel__open(struct evsel *evsel, struct perf_cpu_map *cpus,
 		struct perf_thread_map *threads);
@@ -305,10 +301,6 @@ bool evsel__detect_missing_features(struct evsel *evsel);
 enum rlimit_action { NO_CHANGE, SET_TO_MAX, INCREASED_MAX };
 bool evsel__increase_rlimit(enum rlimit_action *set_rlimit);
 
-bool evsel__ignore_missing_thread(struct evsel *evsel,
-				  int nr_cpus, int cpu,
-				  struct perf_thread_map *threads,
-				  int thread, int err);
 bool evsel__precise_ip_fallback(struct evsel *evsel);
 
 struct perf_sample;
@@ -337,32 +329,32 @@ static inline bool evsel__match2(struct evsel *e1, struct evsel *e2)
 	       (e1->core.attr.config == e2->core.attr.config);
 }
 
-int evsel__read_counter(struct evsel *evsel, int cpu, int thread);
+int evsel__read_counter(struct evsel *evsel, int cpu_map_idx, int thread);
 
-int __evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread, bool scale);
+int __evsel__read_on_cpu(struct evsel *evsel, int cpu_map_idx, int thread, bool scale);
 
 /**
  * evsel__read_on_cpu - Read out the results on a CPU and thread
  *
  * @evsel - event selector to read value
- * @cpu - CPU of interest
+ * @cpu_map_idx - CPU of interest
  * @thread - thread of interest
  */
-static inline int evsel__read_on_cpu(struct evsel *evsel, int cpu, int thread)
+static inline int evsel__read_on_cpu(struct evsel *evsel, int cpu_map_idx, int thread)
 {
-	return __evsel__read_on_cpu(evsel, cpu, thread, false);
+	return __evsel__read_on_cpu(evsel, cpu_map_idx, thread, false);
 }
 
 /**
  * evsel__read_on_cpu_scaled - Read out the results on a CPU and thread, scaled
  *
  * @evsel - event selector to read value
- * @cpu - CPU of interest
+ * @cpu_map_idx - CPU of interest
  * @thread - thread of interest
  */
-static inline int evsel__read_on_cpu_scaled(struct evsel *evsel, int cpu, int thread)
+static inline int evsel__read_on_cpu_scaled(struct evsel *evsel, int cpu_map_idx, int thread)
 {
-	return __evsel__read_on_cpu(evsel, cpu, thread, true);
+	return __evsel__read_on_cpu(evsel, cpu_map_idx, thread, true);
 }
 
 int evsel__parse_sample(struct evsel *evsel, union perf_event *event,
diff --git a/tools/perf/util/expr.c b/tools/perf/util/expr.c
index 666b59baeb70..675f318ce7c1 100644
--- a/tools/perf/util/expr.c
+++ b/tools/perf/util/expr.c
@@ -405,12 +405,17 @@ double expr_id_data__source_count(const struct expr_id_data *data)
 double expr__get_literal(const char *literal)
 {
 	static struct cpu_topology *topology;
+	double result = NAN;
 
-	if (!strcmp("#smt_on", literal))
-		return smt_on() > 0 ? 1.0 : 0.0;
+	if (!strcasecmp("#smt_on", literal)) {
+		result = smt_on() > 0 ? 1.0 : 0.0;
+		goto out;
+	}
 
-	if (!strcmp("#num_cpus", literal))
-		return cpu__max_present_cpu();
+	if (!strcmp("#num_cpus", literal)) {
+		result = cpu__max_present_cpu().cpu;
+		goto out;
+	}
 
 	/*
 	 * Assume that topology strings are consistent, such as CPUs "0-1"
@@ -422,16 +427,24 @@ double expr__get_literal(const char *literal)
 		topology = cpu_topology__new();
 		if (!topology) {
 			pr_err("Error creating CPU topology");
-			return NAN;
+			goto out;
 		}
 	}
-	if (!strcmp("#num_packages", literal))
-		return topology->package_cpus_lists;
-	if (!strcmp("#num_dies", literal))
-		return topology->die_cpus_lists;
-	if (!strcmp("#num_cores", literal))
-		return topology->core_cpus_lists;
+	if (!strcmp("#num_packages", literal)) {
+		result = topology->package_cpus_lists;
+		goto out;
+	}
+	if (!strcmp("#num_dies", literal)) {
+		result = topology->die_cpus_lists;
+		goto out;
+	}
+	if (!strcmp("#num_cores", literal)) {
+		result = topology->core_cpus_lists;
+		goto out;
+	}
 
 	pr_err("Unrecognized literal '%s'", literal);
-	return NAN;
+out:
+	pr_debug2("literal: %s = %f\n", literal, result);
+	return result;
 }
diff --git a/tools/perf/util/ftrace.h b/tools/perf/util/ftrace.h
new file mode 100644
index 000000000000..887f68a185f7
--- /dev/null
+++ b/tools/perf/util/ftrace.h
@@ -0,0 +1,81 @@
+#ifndef __PERF_FTRACE_H__
+#define __PERF_FTRACE_H__
+
+#include <linux/list.h>
+
+#include "target.h"
+
+struct evlist;
+
+struct perf_ftrace {
+	struct evlist		*evlist;
+	struct target		target;
+	const char		*tracer;
+	struct list_head	filters;
+	struct list_head	notrace;
+	struct list_head	graph_funcs;
+	struct list_head	nograph_funcs;
+	unsigned long		percpu_buffer_size;
+	bool			inherit;
+	int			graph_depth;
+	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 {
+	struct list_head	list;
+	char			name[];
+};
+
+#define NUM_BUCKET  22  /* 20 + 2 (for outliers in both direction) */
+
+#ifdef HAVE_BPF_SKEL
+
+int perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace);
+int perf_ftrace__latency_start_bpf(struct perf_ftrace *ftrace);
+int perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace);
+int perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace,
+				  int buckets[]);
+int perf_ftrace__latency_cleanup_bpf(struct perf_ftrace *ftrace);
+
+#else  /* !HAVE_BPF_SKEL */
+
+static inline int
+perf_ftrace__latency_prepare_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+	return -1;
+}
+
+static inline int
+perf_ftrace__latency_start_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+	return -1;
+}
+
+static inline int
+perf_ftrace__latency_stop_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+	return -1;
+}
+
+static inline int
+perf_ftrace__latency_read_bpf(struct perf_ftrace *ftrace __maybe_unused,
+			      int buckets[] __maybe_unused)
+{
+	return -1;
+}
+
+static inline int
+perf_ftrace__latency_cleanup_bpf(struct perf_ftrace *ftrace __maybe_unused)
+{
+	return -1;
+}
+
+#endif  /* HAVE_BPF_SKEL */
+
+#endif  /* __PERF_FTRACE_H__ */
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index e3c1a532d059..6da12e522edc 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -472,7 +472,7 @@ static int write_nrcpus(struct feat_fd *ff,
 	u32 nrc, nra;
 	int ret;
 
-	nrc = cpu__max_present_cpu();
+	nrc = cpu__max_present_cpu().cpu;
 
 	nr = sysconf(_SC_NPROCESSORS_ONLN);
 	if (nr < 0)
@@ -1163,7 +1163,7 @@ static int build_caches(struct cpu_cache_level caches[], u32 *cntp)
 	u32 nr, cpu;
 	u16 level;
 
-	nr = cpu__max_cpu();
+	nr = cpu__max_cpu().cpu;
 
 	for (cpu = 0; cpu < nr; cpu++) {
 		for (level = 0; level < MAX_CACHE_LVL; level++) {
@@ -1195,7 +1195,7 @@ static int build_caches(struct cpu_cache_level caches[], u32 *cntp)
 static int write_cache(struct feat_fd *ff,
 		       struct evlist *evlist __maybe_unused)
 {
-	u32 max_caches = cpu__max_cpu() * MAX_CACHE_LVL;
+	u32 max_caches = cpu__max_cpu().cpu * MAX_CACHE_LVL;
 	struct cpu_cache_level caches[max_caches];
 	u32 cnt = 0, i, version = 1;
 	int ret;
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index b776465e04ef..0a8033b09e28 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -211,7 +211,9 @@ void hists__calc_col_len(struct hists *hists, struct hist_entry *h)
 	hists__new_col_len(hists, HISTC_MEM_BLOCKED, 10);
 	hists__new_col_len(hists, HISTC_LOCAL_INS_LAT, 13);
 	hists__new_col_len(hists, HISTC_GLOBAL_INS_LAT, 13);
-	hists__new_col_len(hists, HISTC_P_STAGE_CYC, 13);
+	hists__new_col_len(hists, HISTC_LOCAL_P_STAGE_CYC, 13);
+	hists__new_col_len(hists, HISTC_GLOBAL_P_STAGE_CYC, 13);
+
 	if (symbol_conf.nanosecs)
 		hists__new_col_len(hists, HISTC_TIME, 16);
 	else
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 621f35ae1efa..2a15e22fb89c 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -75,7 +75,8 @@ enum hist_column {
 	HISTC_MEM_BLOCKED,
 	HISTC_LOCAL_INS_LAT,
 	HISTC_GLOBAL_INS_LAT,
-	HISTC_P_STAGE_CYC,
+	HISTC_LOCAL_P_STAGE_CYC,
+	HISTC_GLOBAL_P_STAGE_CYC,
 	HISTC_NR_COLS, /* Last entry */
 };
 
diff --git a/tools/perf/util/libunwind/arm64.c b/tools/perf/util/libunwind/arm64.c
index c397be0c2e32..15f60fd09424 100644
--- a/tools/perf/util/libunwind/arm64.c
+++ b/tools/perf/util/libunwind/arm64.c
@@ -23,7 +23,9 @@
 
 #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>
+#undef perf_event_arm_regs
 #include "../../arch/arm64/util/unwind-libunwind.c"
 
 /* NO_LIBUNWIND_DEBUG_FRAME is a feature flag for local libunwind,
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index fb8496df8432..3901440aeff9 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -34,6 +34,7 @@
 #include "bpf-event.h"
 #include <internal/lib.h> // page_size
 #include "cgroup.h"
+#include "arm64-frame-pointer-unwind-support.h"
 
 #include <linux/ctype.h>
 #include <symbol/kallsyms.h>
@@ -2710,6 +2711,15 @@ static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread,
 	return err;
 }
 
+static u64 get_leaf_frame_caller(struct perf_sample *sample,
+		struct thread *thread, int usr_idx)
+{
+	if (machine__normalized_is(thread->maps->machine, "arm64"))
+		return get_leaf_frame_caller_aarch64(sample, thread, usr_idx);
+	else
+		return 0;
+}
+
 static int thread__resolve_callchain_sample(struct thread *thread,
 					    struct callchain_cursor *cursor,
 					    struct evsel *evsel,
@@ -2723,9 +2733,10 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	struct ip_callchain *chain = sample->callchain;
 	int chain_nr = 0;
 	u8 cpumode = PERF_RECORD_MISC_USER;
-	int i, j, err, nr_entries;
+	int i, j, err, nr_entries, usr_idx;
 	int skip_idx = -1;
 	int first_call = 0;
+	u64 leaf_frame_caller;
 
 	if (chain)
 		chain_nr = chain->nr;
@@ -2850,6 +2861,34 @@ check_calls:
 			continue;
 		}
 
+		/*
+		 * PERF_CONTEXT_USER allows us to locate where the user stack ends.
+		 * Depending on callchain_param.order and the position of PERF_CONTEXT_USER,
+		 * the index will be different in order to add the missing frame
+		 * at the right place.
+		 */
+
+		usr_idx = callchain_param.order == ORDER_CALLEE ? j-2 : j-1;
+
+		if (usr_idx >= 0 && chain->ips[usr_idx] == PERF_CONTEXT_USER) {
+
+			leaf_frame_caller = get_leaf_frame_caller(sample, thread, usr_idx);
+
+			/*
+			 * check if leaf_frame_Caller != ip to not add the same
+			 * value twice.
+			 */
+
+			if (leaf_frame_caller && leaf_frame_caller != ip) {
+
+				err = add_callchain_ip(thread, cursor, parent,
+					       root_al, &cpumode, leaf_frame_caller,
+					       false, NULL, NULL, 0);
+				if (err)
+					return (err < 0) ? err : 0;
+			}
+		}
+
 		err = add_callchain_ip(thread, cursor, parent,
 				       root_al, &cpumode, ip,
 				       false, NULL, NULL, 0);
@@ -3079,14 +3118,19 @@ int machine__set_current_tid(struct machine *machine, int cpu, pid_t pid,
 }
 
 /*
- * Compares the raw arch string. N.B. see instead perf_env__arch() if a
- * normalized arch is needed.
+ * Compares the raw arch string. N.B. see instead perf_env__arch() or
+ * machine__normalized_is() if a normalized arch is needed.
  */
 bool machine__is(struct machine *machine, const char *arch)
 {
 	return machine && !strcmp(perf_env__raw_arch(machine->env), arch);
 }
 
+bool machine__normalized_is(struct machine *machine, const char *arch)
+{
+	return machine && !strcmp(perf_env__arch(machine->env), arch);
+}
+
 int machine__nr_cpus_avail(struct machine *machine)
 {
 	return machine ? perf_env__nr_cpus_avail(machine->env) : 0;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index a143087eeb47..c5a45dc8df4c 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -208,6 +208,7 @@ static inline bool machine__is_host(struct machine *machine)
 }
 
 bool machine__is(struct machine *machine, const char *arch);
+bool machine__normalized_is(struct machine *machine, const char *arch);
 int machine__nr_cpus_avail(struct machine *machine);
 
 struct thread *__machine__findnew_thread(struct machine *machine, pid_t pid, pid_t tid);
diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
index 3167b4628b6d..ed0ab838bcc5 100644
--- a/tools/perf/util/mem-events.c
+++ b/tools/perf/util/mem-events.c
@@ -309,6 +309,9 @@ static const char * const mem_hops[] = {
 	 * to be set with mem_hops field.
 	 */
 	"core, same node",
+	"node, same socket",
+	"socket, same board",
+	"board",
 };
 
 int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
@@ -316,7 +319,7 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 	size_t i, l = 0;
 	u64 m =  PERF_MEM_LVL_NA;
 	u64 hit, miss;
-	int printed;
+	int printed = 0;
 
 	if (mem_info)
 		m  = mem_info->data_src.mem_lvl;
@@ -335,18 +338,22 @@ int perf_mem__lvl_scnprintf(char *out, size_t sz, struct mem_info *mem_info)
 		l += 7;
 	}
 
-	if (mem_info && mem_info->data_src.mem_hops)
+	/*
+	 * Incase mem_hops field is set, we can skip printing data source via
+	 * PERF_MEM_LVL namespace.
+	 */
+	if (mem_info && mem_info->data_src.mem_hops) {
 		l += scnprintf(out + l, sz - l, "%s ", mem_hops[mem_info->data_src.mem_hops]);
-
-	printed = 0;
-	for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
-		if (!(m & 0x1))
-			continue;
-		if (printed++) {
-			strcat(out, " or ");
-			l += 4;
+	} else {
+		for (i = 0; m && i < ARRAY_SIZE(mem_lvl); i++, m >>= 1) {
+			if (!(m & 0x1))
+				continue;
+			if (printed++) {
+				strcat(out, " or ");
+				l += 4;
+			}
+			l += scnprintf(out + l, sz - l, mem_lvl[i]);
 		}
-		l += scnprintf(out + l, sz - l, mem_lvl[i]);
 	}
 
 	if (mem_info && mem_info->data_src.mem_lvl_num) {
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index fffe02aae3ed..d8492e339521 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -209,8 +209,8 @@ static struct metric *metric__new(const struct pmu_event *pe,
 	m->metric_name = pe->metric_name;
 	m->modifier = modifier ? strdup(modifier) : NULL;
 	if (modifier && !m->modifier) {
-		free(m);
 		expr__ctx_free(m->pctx);
+		free(m);
 		return NULL;
 	}
 	m->metric_expr = pe->metric_expr;
@@ -314,7 +314,7 @@ static int setup_metric_events(struct hashmap *ids,
 		 */
 		metric_id = evsel__metric_id(ev);
 		evlist__for_each_entry_continue(metric_evlist, ev) {
-			if (!strcmp(evsel__metric_id(metric_events[i]), metric_id))
+			if (!strcmp(evsel__metric_id(ev), metric_id))
 				ev->metric_leader = metric_events[i];
 		}
 	}
@@ -1115,13 +1115,27 @@ out:
 	return ret;
 }
 
+/**
+ * metric_list_cmp - list_sort comparator that sorts metrics with more events to
+ *                   the front. duration_time is excluded from the count.
+ */
 static int metric_list_cmp(void *priv __maybe_unused, const struct list_head *l,
 			   const struct list_head *r)
 {
 	const struct metric *left = container_of(l, struct metric, nd);
 	const struct metric *right = container_of(r, struct metric, nd);
+	struct expr_id_data *data;
+	int left_count, right_count;
+
+	left_count = hashmap__size(left->pctx->ids);
+	if (!expr__get_id(left->pctx, "duration_time", &data))
+		left_count--;
+
+	right_count = hashmap__size(right->pctx->ids);
+	if (!expr__get_id(right->pctx, "duration_time", &data))
+		right_count--;
 
-	return hashmap__size(right->pctx->ids) - hashmap__size(left->pctx->ids);
+	return right_count - left_count;
 }
 
 /**
@@ -1299,14 +1313,16 @@ err_out:
 /**
  * parse_ids - Build the event string for the ids and parse them creating an
  *             evlist. The encoded metric_ids are decoded.
+ * @metric_no_merge: is metric sharing explicitly disabled.
  * @fake_pmu: used when testing metrics not supported by the current CPU.
  * @ids: the event identifiers parsed from a metric.
  * @modifier: any modifiers added to the events.
  * @has_constraint: false if events should be placed in a weak group.
  * @out_evlist: the created list of events.
  */
-static int parse_ids(struct perf_pmu *fake_pmu, struct expr_parse_ctx *ids,
-		     const char *modifier, bool has_constraint, struct evlist **out_evlist)
+static int parse_ids(bool metric_no_merge, struct perf_pmu *fake_pmu,
+		     struct expr_parse_ctx *ids, const char *modifier,
+		     bool has_constraint, struct evlist **out_evlist)
 {
 	struct parse_events_error parse_error;
 	struct evlist *parsed_evlist;
@@ -1314,12 +1330,19 @@ static int parse_ids(struct perf_pmu *fake_pmu, struct expr_parse_ctx *ids,
 	int ret;
 
 	*out_evlist = NULL;
-	if (hashmap__size(ids->ids) == 0) {
+	if (!metric_no_merge || hashmap__size(ids->ids) == 0) {
 		char *tmp;
 		/*
-		 * No ids/events in the expression parsing context. Events may
-		 * have been removed because of constant evaluation, e.g.:
-		 *  event1 if #smt_on else 0
+		 * We may fail to share events between metrics because
+		 * duration_time isn't present in one metric. For example, a
+		 * ratio of cache misses doesn't need duration_time but the same
+		 * events may be used for a misses per second. Events without
+		 * sharing implies multiplexing, that is best avoided, so place
+		 * duration_time in every group.
+		 *
+		 * Also, there may be no ids/events in the expression parsing
+		 * context because of constant evaluation, e.g.:
+		 *    event1 if #smt_on else 0
 		 * Add a duration_time event to avoid a parse error on an empty
 		 * string.
 		 */
@@ -1387,7 +1410,8 @@ static int parse_groups(struct evlist *perf_evlist, const char *str,
 		ret = build_combined_expr_ctx(&metric_list, &combined);
 
 		if (!ret && combined && hashmap__size(combined->ids)) {
-			ret = parse_ids(fake_pmu, combined, /*modifier=*/NULL,
+			ret = parse_ids(metric_no_merge, fake_pmu, combined,
+					/*modifier=*/NULL,
 					/*has_constraint=*/true,
 					&combined_evlist);
 		}
@@ -1435,7 +1459,7 @@ static int parse_groups(struct evlist *perf_evlist, const char *str,
 			}
 		}
 		if (!metric_evlist) {
-			ret = parse_ids(fake_pmu, m->pctx, m->modifier,
+			ret = parse_ids(metric_no_merge, fake_pmu, m->pctx, m->modifier,
 					m->has_constraint, &m->evlist);
 			if (ret)
 				goto out;
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 23ecdba9e670..12261ed8c15b 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -94,7 +94,7 @@ static void perf_mmap__aio_free(struct mmap *map, int idx)
 	}
 }
 
-static int perf_mmap__aio_bind(struct mmap *map, int idx, int cpu, int affinity)
+static int perf_mmap__aio_bind(struct mmap *map, int idx, struct perf_cpu cpu, int affinity)
 {
 	void *data;
 	size_t mmap_len;
@@ -138,7 +138,7 @@ static void perf_mmap__aio_free(struct mmap *map, int idx)
 }
 
 static int perf_mmap__aio_bind(struct mmap *map __maybe_unused, int idx __maybe_unused,
-		int cpu __maybe_unused, int affinity __maybe_unused)
+		struct perf_cpu cpu __maybe_unused, int affinity __maybe_unused)
 {
 	return 0;
 }
@@ -240,7 +240,8 @@ void mmap__munmap(struct mmap *map)
 
 static void build_node_mask(int node, struct mmap_cpu_mask *mask)
 {
-	int c, cpu, nr_cpus;
+	int idx, nr_cpus;
+	struct perf_cpu cpu;
 	const struct perf_cpu_map *cpu_map = NULL;
 
 	cpu_map = cpu_map__online();
@@ -248,16 +249,16 @@ static void build_node_mask(int node, struct mmap_cpu_mask *mask)
 		return;
 
 	nr_cpus = perf_cpu_map__nr(cpu_map);
-	for (c = 0; c < nr_cpus; c++) {
-		cpu = cpu_map->map[c]; /* map c index to online cpu index */
+	for (idx = 0; idx < nr_cpus; idx++) {
+		cpu = cpu_map->map[idx]; /* map c index to online cpu index */
 		if (cpu__get_node(cpu) == node)
-			set_bit(cpu, mask->bits);
+			set_bit(cpu.cpu, mask->bits);
 	}
 }
 
 static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *mp)
 {
-	map->affinity_mask.nbits = cpu__max_cpu();
+	map->affinity_mask.nbits = cpu__max_cpu().cpu;
 	map->affinity_mask.bits = bitmap_zalloc(map->affinity_mask.nbits);
 	if (!map->affinity_mask.bits)
 		return -1;
@@ -265,12 +266,12 @@ static int perf_mmap__setup_affinity_mask(struct mmap *map, struct mmap_params *
 	if (mp->affinity == PERF_AFFINITY_NODE && cpu__max_node() > 1)
 		build_node_mask(cpu__get_node(map->core.cpu), &map->affinity_mask);
 	else if (mp->affinity == PERF_AFFINITY_CPU)
-		set_bit(map->core.cpu, map->affinity_mask.bits);
+		set_bit(map->core.cpu.cpu, map->affinity_mask.bits);
 
 	return 0;
 }
 
-int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu)
+int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, struct perf_cpu cpu)
 {
 	if (perf_mmap__mmap(&map->core, &mp->core, fd, cpu)) {
 		pr_debug2("failed to mmap perf event ring buffer, error %d\n",
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index 8e259b9610f8..83f6bd4d4082 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -7,6 +7,7 @@
 #include <linux/types.h>
 #include <linux/ring_buffer.h>
 #include <linux/bitops.h>
+#include <perf/cpumap.h>
 #include <stdbool.h>
 #include <pthread.h> // for cpu_set_t
 #ifdef HAVE_AIO_SUPPORT
@@ -52,7 +53,7 @@ struct mmap_params {
 	struct auxtrace_mmap_params auxtrace_mp;
 };
 
-int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, int cpu);
+int mmap__mmap(struct mmap *map, struct mmap_params *mp, int fd, struct perf_cpu cpu);
 void mmap__munmap(struct mmap *map);
 
 union perf_event *perf_mmap__read_forward(struct mmap *map);
diff --git a/tools/perf/util/namespaces.c b/tools/perf/util/namespaces.c
index 608b20c72a5c..48aa3217300b 100644
--- a/tools/perf/util/namespaces.c
+++ b/tools/perf/util/namespaces.c
@@ -60,17 +60,49 @@ void namespaces__free(struct namespaces *namespaces)
 	free(namespaces);
 }
 
+static int nsinfo__get_nspid(struct nsinfo *nsi, const char *path)
+{
+	FILE *f = NULL;
+	char *statln = NULL;
+	size_t linesz = 0;
+	char *nspid;
+
+	f = fopen(path, "r");
+	if (f == NULL)
+		return -1;
+
+	while (getline(&statln, &linesz, f) != -1) {
+		/* Use tgid if CONFIG_PID_NS is not defined. */
+		if (strstr(statln, "Tgid:") != NULL) {
+			nsi->tgid = (pid_t)strtol(strrchr(statln, '\t'),
+						     NULL, 10);
+			nsi->nstgid = nsi->tgid;
+		}
+
+		if (strstr(statln, "NStgid:") != NULL) {
+			nspid = strrchr(statln, '\t');
+			nsi->nstgid = (pid_t)strtol(nspid, NULL, 10);
+			/*
+			 * If innermost tgid is not the first, process is in a different
+			 * PID namespace.
+			 */
+			nsi->in_pidns = (statln + sizeof("NStgid:") - 1) != nspid;
+			break;
+		}
+	}
+
+	fclose(f);
+	free(statln);
+	return 0;
+}
+
 int nsinfo__init(struct nsinfo *nsi)
 {
 	char oldns[PATH_MAX];
 	char spath[PATH_MAX];
 	char *newns = NULL;
-	char *statln = NULL;
-	char *nspid;
 	struct stat old_stat;
 	struct stat new_stat;
-	FILE *f = NULL;
-	size_t linesz = 0;
 	int rv = -1;
 
 	if (snprintf(oldns, PATH_MAX, "/proc/self/ns/mnt") >= PATH_MAX)
@@ -100,34 +132,9 @@ int nsinfo__init(struct nsinfo *nsi)
 	if (snprintf(spath, PATH_MAX, "/proc/%d/status", nsi->pid) >= PATH_MAX)
 		goto out;
 
-	f = fopen(spath, "r");
-	if (f == NULL)
-		goto out;
-
-	while (getline(&statln, &linesz, f) != -1) {
-		/* Use tgid if CONFIG_PID_NS is not defined. */
-		if (strstr(statln, "Tgid:") != NULL) {
-			nsi->tgid = (pid_t)strtol(strrchr(statln, '\t'),
-						     NULL, 10);
-			nsi->nstgid = nsi->tgid;
-		}
-
-		if (strstr(statln, "NStgid:") != NULL) {
-			nspid = strrchr(statln, '\t');
-			nsi->nstgid = (pid_t)strtol(nspid, NULL, 10);
-			/* If innermost tgid is not the first, process is in a different
-			 * PID namespace.
-			 */
-			nsi->in_pidns = (statln + sizeof("NStgid:") - 1) != nspid;
-			break;
-		}
-	}
-	rv = 0;
+	rv = nsinfo__get_nspid(nsi, spath);
 
 out:
-	if (f != NULL)
-		(void) fclose(f);
-	free(statln);
 	free(newns);
 	return rv;
 }
@@ -299,3 +306,12 @@ int nsinfo__stat(const char *filename, struct stat *st, struct nsinfo *nsi)
 
 	return ret;
 }
+
+bool nsinfo__is_in_root_namespace(void)
+{
+	struct nsinfo nsi;
+
+	memset(&nsi, 0x0, sizeof(nsi));
+	nsinfo__get_nspid(&nsi, "/proc/self/status");
+	return !nsi.in_pidns;
+}
diff --git a/tools/perf/util/namespaces.h b/tools/perf/util/namespaces.h
index ad9775db7b9c..9ceea9643507 100644
--- a/tools/perf/util/namespaces.h
+++ b/tools/perf/util/namespaces.h
@@ -59,6 +59,8 @@ void nsinfo__mountns_exit(struct nscookie *nc);
 char *nsinfo__realpath(const char *path, struct nsinfo *nsi);
 int nsinfo__stat(const char *filename, struct stat *st, struct nsinfo *nsi);
 
+bool nsinfo__is_in_root_namespace(void);
+
 static inline void __nsinfo__zput(struct nsinfo **nsip)
 {
 	if (nsip) {
diff --git a/tools/perf/util/parse-events-hybrid.c b/tools/perf/util/parse-events-hybrid.c
index 9fc86971027b..284f8eabd3b9 100644
--- a/tools/perf/util/parse-events-hybrid.c
+++ b/tools/perf/util/parse-events-hybrid.c
@@ -63,10 +63,13 @@ static int create_event_hybrid(__u32 config_type, int *idx,
 static int pmu_cmp(struct parse_events_state *parse_state,
 		   struct perf_pmu *pmu)
 {
-	if (!parse_state->hybrid_pmu_name)
-		return 0;
+	if (parse_state->evlist && parse_state->evlist->hybrid_pmu_name)
+		return strcmp(parse_state->evlist->hybrid_pmu_name, pmu->name);
+
+	if (parse_state->hybrid_pmu_name)
+		return strcmp(parse_state->hybrid_pmu_name, pmu->name);
 
-	return strcmp(parse_state->hybrid_pmu_name, pmu->name);
+	return 0;
 }
 
 static int add_hw_hybrid(struct parse_events_state *parse_state,
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index ba74fdf74af9..acf20ce98ce9 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -1824,6 +1824,11 @@ out:
 	return ret;
 }
 
+__weak struct evsel *arch_evlist__leader(struct list_head *list)
+{
+	return list_first_entry(list, struct evsel, core.node);
+}
+
 void parse_events__set_leader(char *name, struct list_head *list,
 			      struct parse_events_state *parse_state)
 {
@@ -1837,9 +1842,10 @@ void parse_events__set_leader(char *name, struct list_head *list,
 	if (parse_events__set_leader_for_uncore_aliase(name, list, parse_state))
 		return;
 
-	__perf_evlist__set_leader(list);
-	leader = list_entry(list->next, struct evsel, core.node);
+	leader = arch_evlist__leader(list);
+	__perf_evlist__set_leader(list, &leader->core);
 	leader->group_name = name ? strdup(name) : NULL;
+	list_move(&leader->core.node, list);
 }
 
 /* list_event is assumed to point to malloc'ed memory */
diff --git a/tools/perf/util/perf_api_probe.c b/tools/perf/util/perf_api_probe.c
index 020411682a3c..734d006d9a8c 100644
--- a/tools/perf/util/perf_api_probe.c
+++ b/tools/perf/util/perf_api_probe.c
@@ -11,7 +11,7 @@
 
 typedef void (*setup_probe_fn_t)(struct evsel *evsel);
 
-static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
+static int perf_do_probe_api(setup_probe_fn_t fn, struct perf_cpu cpu, const char *str)
 {
 	struct evlist *evlist;
 	struct evsel *evsel;
@@ -29,7 +29,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
 	evsel = evlist__first(evlist);
 
 	while (1) {
-		fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags);
+		fd = sys_perf_event_open(&evsel->core.attr, pid, cpu.cpu, -1, flags);
 		if (fd < 0) {
 			if (pid == -1 && errno == EACCES) {
 				pid = 0;
@@ -43,7 +43,7 @@ static int perf_do_probe_api(setup_probe_fn_t fn, int cpu, const char *str)
 
 	fn(evsel);
 
-	fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1, flags);
+	fd = sys_perf_event_open(&evsel->core.attr, pid, cpu.cpu, -1, flags);
 	if (fd < 0) {
 		if (errno == EINVAL)
 			err = -EINVAL;
@@ -61,7 +61,8 @@ static bool perf_probe_api(setup_probe_fn_t fn)
 {
 	const char *try[] = {"cycles:u", "instructions:u", "cpu-clock:u", NULL};
 	struct perf_cpu_map *cpus;
-	int cpu, ret, i = 0;
+	struct perf_cpu cpu;
+	int ret, i = 0;
 
 	cpus = perf_cpu_map__new(NULL);
 	if (!cpus)
@@ -136,15 +137,17 @@ bool perf_can_record_cpu_wide(void)
 		.exclude_kernel = 1,
 	};
 	struct perf_cpu_map *cpus;
-	int cpu, fd;
+	struct perf_cpu cpu;
+	int fd;
 
 	cpus = perf_cpu_map__new(NULL);
 	if (!cpus)
 		return false;
+
 	cpu = cpus->map[0];
 	perf_cpu_map__put(cpus);
 
-	fd = sys_perf_event_open(&attr, -1, cpu, -1, 0);
+	fd = sys_perf_event_open(&attr, -1, cpu.cpu, -1, 0);
 	if (fd < 0)
 		return false;
 	close(fd);
diff --git a/tools/perf/util/perf_regs.c b/tools/perf/util/perf_regs.c
index 06a7461ba864..a982e40ee5a9 100644
--- a/tools/perf/util/perf_regs.c
+++ b/tools/perf/util/perf_regs.c
@@ -1,5 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <errno.h>
+#include <string.h>
 #include "perf_regs.h"
 #include "event.h"
 
@@ -20,6 +21,671 @@ uint64_t __weak arch__user_reg_mask(void)
 }
 
 #ifdef HAVE_PERF_REGS_SUPPORT
+
+#define perf_event_arm_regs perf_event_arm64_regs
+#include "../../arch/arm64/include/uapi/asm/perf_regs.h"
+#undef perf_event_arm_regs
+
+#include "../../arch/arm/include/uapi/asm/perf_regs.h"
+#include "../../arch/csky/include/uapi/asm/perf_regs.h"
+#include "../../arch/mips/include/uapi/asm/perf_regs.h"
+#include "../../arch/powerpc/include/uapi/asm/perf_regs.h"
+#include "../../arch/riscv/include/uapi/asm/perf_regs.h"
+#include "../../arch/s390/include/uapi/asm/perf_regs.h"
+#include "../../arch/x86/include/uapi/asm/perf_regs.h"
+
+static const char *__perf_reg_name_arm64(int id)
+{
+	switch (id) {
+	case PERF_REG_ARM64_X0:
+		return "x0";
+	case PERF_REG_ARM64_X1:
+		return "x1";
+	case PERF_REG_ARM64_X2:
+		return "x2";
+	case PERF_REG_ARM64_X3:
+		return "x3";
+	case PERF_REG_ARM64_X4:
+		return "x4";
+	case PERF_REG_ARM64_X5:
+		return "x5";
+	case PERF_REG_ARM64_X6:
+		return "x6";
+	case PERF_REG_ARM64_X7:
+		return "x7";
+	case PERF_REG_ARM64_X8:
+		return "x8";
+	case PERF_REG_ARM64_X9:
+		return "x9";
+	case PERF_REG_ARM64_X10:
+		return "x10";
+	case PERF_REG_ARM64_X11:
+		return "x11";
+	case PERF_REG_ARM64_X12:
+		return "x12";
+	case PERF_REG_ARM64_X13:
+		return "x13";
+	case PERF_REG_ARM64_X14:
+		return "x14";
+	case PERF_REG_ARM64_X15:
+		return "x15";
+	case PERF_REG_ARM64_X16:
+		return "x16";
+	case PERF_REG_ARM64_X17:
+		return "x17";
+	case PERF_REG_ARM64_X18:
+		return "x18";
+	case PERF_REG_ARM64_X19:
+		return "x19";
+	case PERF_REG_ARM64_X20:
+		return "x20";
+	case PERF_REG_ARM64_X21:
+		return "x21";
+	case PERF_REG_ARM64_X22:
+		return "x22";
+	case PERF_REG_ARM64_X23:
+		return "x23";
+	case PERF_REG_ARM64_X24:
+		return "x24";
+	case PERF_REG_ARM64_X25:
+		return "x25";
+	case PERF_REG_ARM64_X26:
+		return "x26";
+	case PERF_REG_ARM64_X27:
+		return "x27";
+	case PERF_REG_ARM64_X28:
+		return "x28";
+	case PERF_REG_ARM64_X29:
+		return "x29";
+	case PERF_REG_ARM64_SP:
+		return "sp";
+	case PERF_REG_ARM64_LR:
+		return "lr";
+	case PERF_REG_ARM64_PC:
+		return "pc";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+static const char *__perf_reg_name_arm(int id)
+{
+	switch (id) {
+	case PERF_REG_ARM_R0:
+		return "r0";
+	case PERF_REG_ARM_R1:
+		return "r1";
+	case PERF_REG_ARM_R2:
+		return "r2";
+	case PERF_REG_ARM_R3:
+		return "r3";
+	case PERF_REG_ARM_R4:
+		return "r4";
+	case PERF_REG_ARM_R5:
+		return "r5";
+	case PERF_REG_ARM_R6:
+		return "r6";
+	case PERF_REG_ARM_R7:
+		return "r7";
+	case PERF_REG_ARM_R8:
+		return "r8";
+	case PERF_REG_ARM_R9:
+		return "r9";
+	case PERF_REG_ARM_R10:
+		return "r10";
+	case PERF_REG_ARM_FP:
+		return "fp";
+	case PERF_REG_ARM_IP:
+		return "ip";
+	case PERF_REG_ARM_SP:
+		return "sp";
+	case PERF_REG_ARM_LR:
+		return "lr";
+	case PERF_REG_ARM_PC:
+		return "pc";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+static const char *__perf_reg_name_csky(int id)
+{
+	switch (id) {
+	case PERF_REG_CSKY_A0:
+		return "a0";
+	case PERF_REG_CSKY_A1:
+		return "a1";
+	case PERF_REG_CSKY_A2:
+		return "a2";
+	case PERF_REG_CSKY_A3:
+		return "a3";
+	case PERF_REG_CSKY_REGS0:
+		return "regs0";
+	case PERF_REG_CSKY_REGS1:
+		return "regs1";
+	case PERF_REG_CSKY_REGS2:
+		return "regs2";
+	case PERF_REG_CSKY_REGS3:
+		return "regs3";
+	case PERF_REG_CSKY_REGS4:
+		return "regs4";
+	case PERF_REG_CSKY_REGS5:
+		return "regs5";
+	case PERF_REG_CSKY_REGS6:
+		return "regs6";
+	case PERF_REG_CSKY_REGS7:
+		return "regs7";
+	case PERF_REG_CSKY_REGS8:
+		return "regs8";
+	case PERF_REG_CSKY_REGS9:
+		return "regs9";
+	case PERF_REG_CSKY_SP:
+		return "sp";
+	case PERF_REG_CSKY_LR:
+		return "lr";
+	case PERF_REG_CSKY_PC:
+		return "pc";
+#if defined(__CSKYABIV2__)
+	case PERF_REG_CSKY_EXREGS0:
+		return "exregs0";
+	case PERF_REG_CSKY_EXREGS1:
+		return "exregs1";
+	case PERF_REG_CSKY_EXREGS2:
+		return "exregs2";
+	case PERF_REG_CSKY_EXREGS3:
+		return "exregs3";
+	case PERF_REG_CSKY_EXREGS4:
+		return "exregs4";
+	case PERF_REG_CSKY_EXREGS5:
+		return "exregs5";
+	case PERF_REG_CSKY_EXREGS6:
+		return "exregs6";
+	case PERF_REG_CSKY_EXREGS7:
+		return "exregs7";
+	case PERF_REG_CSKY_EXREGS8:
+		return "exregs8";
+	case PERF_REG_CSKY_EXREGS9:
+		return "exregs9";
+	case PERF_REG_CSKY_EXREGS10:
+		return "exregs10";
+	case PERF_REG_CSKY_EXREGS11:
+		return "exregs11";
+	case PERF_REG_CSKY_EXREGS12:
+		return "exregs12";
+	case PERF_REG_CSKY_EXREGS13:
+		return "exregs13";
+	case PERF_REG_CSKY_EXREGS14:
+		return "exregs14";
+	case PERF_REG_CSKY_TLS:
+		return "tls";
+	case PERF_REG_CSKY_HI:
+		return "hi";
+	case PERF_REG_CSKY_LO:
+		return "lo";
+#endif
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+static const char *__perf_reg_name_mips(int id)
+{
+	switch (id) {
+	case PERF_REG_MIPS_PC:
+		return "PC";
+	case PERF_REG_MIPS_R1:
+		return "$1";
+	case PERF_REG_MIPS_R2:
+		return "$2";
+	case PERF_REG_MIPS_R3:
+		return "$3";
+	case PERF_REG_MIPS_R4:
+		return "$4";
+	case PERF_REG_MIPS_R5:
+		return "$5";
+	case PERF_REG_MIPS_R6:
+		return "$6";
+	case PERF_REG_MIPS_R7:
+		return "$7";
+	case PERF_REG_MIPS_R8:
+		return "$8";
+	case PERF_REG_MIPS_R9:
+		return "$9";
+	case PERF_REG_MIPS_R10:
+		return "$10";
+	case PERF_REG_MIPS_R11:
+		return "$11";
+	case PERF_REG_MIPS_R12:
+		return "$12";
+	case PERF_REG_MIPS_R13:
+		return "$13";
+	case PERF_REG_MIPS_R14:
+		return "$14";
+	case PERF_REG_MIPS_R15:
+		return "$15";
+	case PERF_REG_MIPS_R16:
+		return "$16";
+	case PERF_REG_MIPS_R17:
+		return "$17";
+	case PERF_REG_MIPS_R18:
+		return "$18";
+	case PERF_REG_MIPS_R19:
+		return "$19";
+	case PERF_REG_MIPS_R20:
+		return "$20";
+	case PERF_REG_MIPS_R21:
+		return "$21";
+	case PERF_REG_MIPS_R22:
+		return "$22";
+	case PERF_REG_MIPS_R23:
+		return "$23";
+	case PERF_REG_MIPS_R24:
+		return "$24";
+	case PERF_REG_MIPS_R25:
+		return "$25";
+	case PERF_REG_MIPS_R28:
+		return "$28";
+	case PERF_REG_MIPS_R29:
+		return "$29";
+	case PERF_REG_MIPS_R30:
+		return "$30";
+	case PERF_REG_MIPS_R31:
+		return "$31";
+	default:
+		break;
+	}
+	return NULL;
+}
+
+static const char *__perf_reg_name_powerpc(int id)
+{
+	switch (id) {
+	case PERF_REG_POWERPC_R0:
+		return "r0";
+	case PERF_REG_POWERPC_R1:
+		return "r1";
+	case PERF_REG_POWERPC_R2:
+		return "r2";
+	case PERF_REG_POWERPC_R3:
+		return "r3";
+	case PERF_REG_POWERPC_R4:
+		return "r4";
+	case PERF_REG_POWERPC_R5:
+		return "r5";
+	case PERF_REG_POWERPC_R6:
+		return "r6";
+	case PERF_REG_POWERPC_R7:
+		return "r7";
+	case PERF_REG_POWERPC_R8:
+		return "r8";
+	case PERF_REG_POWERPC_R9:
+		return "r9";
+	case PERF_REG_POWERPC_R10:
+		return "r10";
+	case PERF_REG_POWERPC_R11:
+		return "r11";
+	case PERF_REG_POWERPC_R12:
+		return "r12";
+	case PERF_REG_POWERPC_R13:
+		return "r13";
+	case PERF_REG_POWERPC_R14:
+		return "r14";
+	case PERF_REG_POWERPC_R15:
+		return "r15";
+	case PERF_REG_POWERPC_R16:
+		return "r16";
+	case PERF_REG_POWERPC_R17:
+		return "r17";
+	case PERF_REG_POWERPC_R18:
+		return "r18";
+	case PERF_REG_POWERPC_R19:
+		return "r19";
+	case PERF_REG_POWERPC_R20:
+		return "r20";
+	case PERF_REG_POWERPC_R21:
+		return "r21";
+	case PERF_REG_POWERPC_R22:
+		return "r22";
+	case PERF_REG_POWERPC_R23:
+		return "r23";
+	case PERF_REG_POWERPC_R24:
+		return "r24";
+	case PERF_REG_POWERPC_R25:
+		return "r25";
+	case PERF_REG_POWERPC_R26:
+		return "r26";
+	case PERF_REG_POWERPC_R27:
+		return "r27";
+	case PERF_REG_POWERPC_R28:
+		return "r28";
+	case PERF_REG_POWERPC_R29:
+		return "r29";
+	case PERF_REG_POWERPC_R30:
+		return "r30";
+	case PERF_REG_POWERPC_R31:
+		return "r31";
+	case PERF_REG_POWERPC_NIP:
+		return "nip";
+	case PERF_REG_POWERPC_MSR:
+		return "msr";
+	case PERF_REG_POWERPC_ORIG_R3:
+		return "orig_r3";
+	case PERF_REG_POWERPC_CTR:
+		return "ctr";
+	case PERF_REG_POWERPC_LINK:
+		return "link";
+	case PERF_REG_POWERPC_XER:
+		return "xer";
+	case PERF_REG_POWERPC_CCR:
+		return "ccr";
+	case PERF_REG_POWERPC_SOFTE:
+		return "softe";
+	case PERF_REG_POWERPC_TRAP:
+		return "trap";
+	case PERF_REG_POWERPC_DAR:
+		return "dar";
+	case PERF_REG_POWERPC_DSISR:
+		return "dsisr";
+	case PERF_REG_POWERPC_SIER:
+		return "sier";
+	case PERF_REG_POWERPC_MMCRA:
+		return "mmcra";
+	case PERF_REG_POWERPC_MMCR0:
+		return "mmcr0";
+	case PERF_REG_POWERPC_MMCR1:
+		return "mmcr1";
+	case PERF_REG_POWERPC_MMCR2:
+		return "mmcr2";
+	case PERF_REG_POWERPC_MMCR3:
+		return "mmcr3";
+	case PERF_REG_POWERPC_SIER2:
+		return "sier2";
+	case PERF_REG_POWERPC_SIER3:
+		return "sier3";
+	case PERF_REG_POWERPC_PMC1:
+		return "pmc1";
+	case PERF_REG_POWERPC_PMC2:
+		return "pmc2";
+	case PERF_REG_POWERPC_PMC3:
+		return "pmc3";
+	case PERF_REG_POWERPC_PMC4:
+		return "pmc4";
+	case PERF_REG_POWERPC_PMC5:
+		return "pmc5";
+	case PERF_REG_POWERPC_PMC6:
+		return "pmc6";
+	case PERF_REG_POWERPC_SDAR:
+		return "sdar";
+	case PERF_REG_POWERPC_SIAR:
+		return "siar";
+	default:
+		break;
+	}
+	return NULL;
+}
+
+static const char *__perf_reg_name_riscv(int id)
+{
+	switch (id) {
+	case PERF_REG_RISCV_PC:
+		return "pc";
+	case PERF_REG_RISCV_RA:
+		return "ra";
+	case PERF_REG_RISCV_SP:
+		return "sp";
+	case PERF_REG_RISCV_GP:
+		return "gp";
+	case PERF_REG_RISCV_TP:
+		return "tp";
+	case PERF_REG_RISCV_T0:
+		return "t0";
+	case PERF_REG_RISCV_T1:
+		return "t1";
+	case PERF_REG_RISCV_T2:
+		return "t2";
+	case PERF_REG_RISCV_S0:
+		return "s0";
+	case PERF_REG_RISCV_S1:
+		return "s1";
+	case PERF_REG_RISCV_A0:
+		return "a0";
+	case PERF_REG_RISCV_A1:
+		return "a1";
+	case PERF_REG_RISCV_A2:
+		return "a2";
+	case PERF_REG_RISCV_A3:
+		return "a3";
+	case PERF_REG_RISCV_A4:
+		return "a4";
+	case PERF_REG_RISCV_A5:
+		return "a5";
+	case PERF_REG_RISCV_A6:
+		return "a6";
+	case PERF_REG_RISCV_A7:
+		return "a7";
+	case PERF_REG_RISCV_S2:
+		return "s2";
+	case PERF_REG_RISCV_S3:
+		return "s3";
+	case PERF_REG_RISCV_S4:
+		return "s4";
+	case PERF_REG_RISCV_S5:
+		return "s5";
+	case PERF_REG_RISCV_S6:
+		return "s6";
+	case PERF_REG_RISCV_S7:
+		return "s7";
+	case PERF_REG_RISCV_S8:
+		return "s8";
+	case PERF_REG_RISCV_S9:
+		return "s9";
+	case PERF_REG_RISCV_S10:
+		return "s10";
+	case PERF_REG_RISCV_S11:
+		return "s11";
+	case PERF_REG_RISCV_T3:
+		return "t3";
+	case PERF_REG_RISCV_T4:
+		return "t4";
+	case PERF_REG_RISCV_T5:
+		return "t5";
+	case PERF_REG_RISCV_T6:
+		return "t6";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+static const char *__perf_reg_name_s390(int id)
+{
+	switch (id) {
+	case PERF_REG_S390_R0:
+		return "R0";
+	case PERF_REG_S390_R1:
+		return "R1";
+	case PERF_REG_S390_R2:
+		return "R2";
+	case PERF_REG_S390_R3:
+		return "R3";
+	case PERF_REG_S390_R4:
+		return "R4";
+	case PERF_REG_S390_R5:
+		return "R5";
+	case PERF_REG_S390_R6:
+		return "R6";
+	case PERF_REG_S390_R7:
+		return "R7";
+	case PERF_REG_S390_R8:
+		return "R8";
+	case PERF_REG_S390_R9:
+		return "R9";
+	case PERF_REG_S390_R10:
+		return "R10";
+	case PERF_REG_S390_R11:
+		return "R11";
+	case PERF_REG_S390_R12:
+		return "R12";
+	case PERF_REG_S390_R13:
+		return "R13";
+	case PERF_REG_S390_R14:
+		return "R14";
+	case PERF_REG_S390_R15:
+		return "R15";
+	case PERF_REG_S390_FP0:
+		return "FP0";
+	case PERF_REG_S390_FP1:
+		return "FP1";
+	case PERF_REG_S390_FP2:
+		return "FP2";
+	case PERF_REG_S390_FP3:
+		return "FP3";
+	case PERF_REG_S390_FP4:
+		return "FP4";
+	case PERF_REG_S390_FP5:
+		return "FP5";
+	case PERF_REG_S390_FP6:
+		return "FP6";
+	case PERF_REG_S390_FP7:
+		return "FP7";
+	case PERF_REG_S390_FP8:
+		return "FP8";
+	case PERF_REG_S390_FP9:
+		return "FP9";
+	case PERF_REG_S390_FP10:
+		return "FP10";
+	case PERF_REG_S390_FP11:
+		return "FP11";
+	case PERF_REG_S390_FP12:
+		return "FP12";
+	case PERF_REG_S390_FP13:
+		return "FP13";
+	case PERF_REG_S390_FP14:
+		return "FP14";
+	case PERF_REG_S390_FP15:
+		return "FP15";
+	case PERF_REG_S390_MASK:
+		return "MASK";
+	case PERF_REG_S390_PC:
+		return "PC";
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+static const char *__perf_reg_name_x86(int id)
+{
+	switch (id) {
+	case PERF_REG_X86_AX:
+		return "AX";
+	case PERF_REG_X86_BX:
+		return "BX";
+	case PERF_REG_X86_CX:
+		return "CX";
+	case PERF_REG_X86_DX:
+		return "DX";
+	case PERF_REG_X86_SI:
+		return "SI";
+	case PERF_REG_X86_DI:
+		return "DI";
+	case PERF_REG_X86_BP:
+		return "BP";
+	case PERF_REG_X86_SP:
+		return "SP";
+	case PERF_REG_X86_IP:
+		return "IP";
+	case PERF_REG_X86_FLAGS:
+		return "FLAGS";
+	case PERF_REG_X86_CS:
+		return "CS";
+	case PERF_REG_X86_SS:
+		return "SS";
+	case PERF_REG_X86_DS:
+		return "DS";
+	case PERF_REG_X86_ES:
+		return "ES";
+	case PERF_REG_X86_FS:
+		return "FS";
+	case PERF_REG_X86_GS:
+		return "GS";
+	case PERF_REG_X86_R8:
+		return "R8";
+	case PERF_REG_X86_R9:
+		return "R9";
+	case PERF_REG_X86_R10:
+		return "R10";
+	case PERF_REG_X86_R11:
+		return "R11";
+	case PERF_REG_X86_R12:
+		return "R12";
+	case PERF_REG_X86_R13:
+		return "R13";
+	case PERF_REG_X86_R14:
+		return "R14";
+	case PERF_REG_X86_R15:
+		return "R15";
+
+#define XMM(x) \
+	case PERF_REG_X86_XMM ## x:	\
+	case PERF_REG_X86_XMM ## x + 1:	\
+		return "XMM" #x;
+	XMM(0)
+	XMM(1)
+	XMM(2)
+	XMM(3)
+	XMM(4)
+	XMM(5)
+	XMM(6)
+	XMM(7)
+	XMM(8)
+	XMM(9)
+	XMM(10)
+	XMM(11)
+	XMM(12)
+	XMM(13)
+	XMM(14)
+	XMM(15)
+#undef XMM
+	default:
+		return NULL;
+	}
+
+	return NULL;
+}
+
+const char *perf_reg_name(int id, const char *arch)
+{
+	const char *reg_name = NULL;
+
+	if (!strcmp(arch, "csky"))
+		reg_name = __perf_reg_name_csky(id);
+	else if (!strcmp(arch, "mips"))
+		reg_name = __perf_reg_name_mips(id);
+	else if (!strcmp(arch, "powerpc"))
+		reg_name = __perf_reg_name_powerpc(id);
+	else if (!strcmp(arch, "riscv"))
+		reg_name = __perf_reg_name_riscv(id);
+	else if (!strcmp(arch, "s390"))
+		reg_name = __perf_reg_name_s390(id);
+	else if (!strcmp(arch, "x86"))
+		reg_name = __perf_reg_name_x86(id);
+	else if (!strcmp(arch, "arm"))
+		reg_name = __perf_reg_name_arm(id);
+	else if (!strcmp(arch, "arm64"))
+		reg_name = __perf_reg_name_arm64(id);
+
+	return reg_name ?: "unknown";
+}
+
 int perf_reg_value(u64 *valp, struct regs_dump *regs, int id)
 {
 	int i, idx = 0;
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index eeac181ebccf..ce1127af05e4 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -11,8 +11,11 @@ struct sample_reg {
 	const char *name;
 	uint64_t mask;
 };
-#define SMPL_REG(n, b) { .name = #n, .mask = 1ULL << (b) }
-#define SMPL_REG2(n, b) { .name = #n, .mask = 3ULL << (b) }
+
+#define SMPL_REG_MASK(b) (1ULL << (b))
+#define SMPL_REG(n, b) { .name = #n, .mask = SMPL_REG_MASK(b) }
+#define SMPL_REG2_MASK(b) (3ULL << (b))
+#define SMPL_REG2(n, b) { .name = #n, .mask = SMPL_REG2_MASK(b) }
 #define SMPL_REG_END { .name = NULL }
 
 enum {
@@ -31,22 +34,16 @@ extern const struct sample_reg sample_reg_masks[];
 
 #define DWARF_MINIMAL_REGS ((1ULL << PERF_REG_IP) | (1ULL << PERF_REG_SP))
 
+const char *perf_reg_name(int id, const char *arch);
 int perf_reg_value(u64 *valp, struct regs_dump *regs, int id);
 
-static inline const char *perf_reg_name(int id)
-{
-	const char *reg_name = __perf_reg_name(id);
-
-	return reg_name ?: "unknown";
-}
-
 #else
 #define PERF_REGS_MASK	0
 #define PERF_REGS_MAX	0
 
 #define DWARF_MINIMAL_REGS PERF_REGS_MASK
 
-static inline const char *perf_reg_name(int id __maybe_unused)
+static inline const char *perf_reg_name(int id __maybe_unused, const char *arch __maybe_unused)
 {
 	return "unknown";
 }
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 82c7f034d91a..f3e5131f183c 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -1059,7 +1059,7 @@ static struct mmap *get_md(struct evlist *evlist, int cpu)
 	for (i = 0; i < evlist->core.nr_mmaps; i++) {
 		struct mmap *md = &evlist->mmap[i];
 
-		if (md->core.cpu == cpu)
+		if (md->core.cpu.cpu == cpu)
 			return md;
 	}
 
@@ -1445,7 +1445,7 @@ error:
  * Dummy, to avoid dragging all the test_attr infrastructure in the python
  * binding.
  */
-void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
+void test_attr__open(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu,
                      int fd, int group_fd, unsigned long flags)
 {
 }
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index bff669b615ee..20461f174991 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -106,7 +106,7 @@ void evlist__config(struct evlist *evlist, struct record_opts *opts, struct call
 	if (opts->group)
 		evlist__set_leader(evlist);
 
-	if (evlist->core.cpus->map[0] < 0)
+	if (evlist->core.cpus->map[0].cpu < 0)
 		opts->no_inherit = true;
 
 	use_comm_exec = perf_can_comm_exec();
@@ -229,7 +229,8 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str)
 {
 	struct evlist *temp_evlist;
 	struct evsel *evsel;
-	int err, fd, cpu;
+	int err, fd;
+	struct perf_cpu cpu = { .cpu = 0 };
 	bool ret = false;
 	pid_t pid = -1;
 
@@ -246,14 +247,16 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str)
 	if (!evlist || perf_cpu_map__empty(evlist->core.cpus)) {
 		struct perf_cpu_map *cpus = perf_cpu_map__new(NULL);
 
-		cpu =  cpus ? cpus->map[0] : 0;
+		if (cpus)
+			cpu =  cpus->map[0];
+
 		perf_cpu_map__put(cpus);
 	} else {
 		cpu = evlist->core.cpus->map[0];
 	}
 
 	while (1) {
-		fd = sys_perf_event_open(&evsel->core.attr, pid, cpu, -1,
+		fd = sys_perf_event_open(&evsel->core.attr, pid, cpu.cpu, -1,
 					 perf_event_open_cloexec_flag());
 		if (fd < 0) {
 			if (pid == -1 && errno == EACCES) {
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index d1f1501ce7fc..f5ad0e62227a 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -36,6 +36,7 @@
 #include "../debug.h"
 #include "../dso.h"
 #include "../callchain.h"
+#include "../env.h"
 #include "../evsel.h"
 #include "../event.h"
 #include "../thread.h"
@@ -687,7 +688,7 @@ static void set_sample_datasrc_in_dict(PyObject *dict,
 			_PyUnicode_FromString(decode));
 }
 
-static void regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size)
+static void regs_map(struct regs_dump *regs, uint64_t mask, const char *arch, char *bf, int size)
 {
 	unsigned int i = 0, r;
 	int printed = 0;
@@ -702,7 +703,7 @@ static void regs_map(struct regs_dump *regs, uint64_t mask, char *bf, int size)
 
 		printed += scnprintf(bf + printed, size - printed,
 				     "%5s:0x%" PRIx64 " ",
-				     perf_reg_name(r), val);
+				     perf_reg_name(r, arch), val);
 	}
 }
 
@@ -711,6 +712,7 @@ static void set_regs_in_dict(PyObject *dict,
 			     struct evsel *evsel)
 {
 	struct perf_event_attr *attr = &evsel->core.attr;
+	const char *arch = perf_env__arch(evsel__env(evsel));
 
 	/*
 	 * Here value 28 is a constant size which can be used to print
@@ -722,12 +724,12 @@ static void set_regs_in_dict(PyObject *dict,
 	int size = __sw_hweight64(attr->sample_regs_intr) * 28;
 	char bf[size];
 
-	regs_map(&sample->intr_regs, attr->sample_regs_intr, bf, sizeof(bf));
+	regs_map(&sample->intr_regs, attr->sample_regs_intr, arch, bf, sizeof(bf));
 
 	pydict_set_item_string_decref(dict, "iregs",
 			_PyUnicode_FromString(bf));
 
-	regs_map(&sample->user_regs, attr->sample_regs_user, bf, sizeof(bf));
+	regs_map(&sample->user_regs, attr->sample_regs_user, arch, bf, sizeof(bf));
 
 	pydict_set_item_string_decref(dict, "uregs",
 			_PyUnicode_FromString(bf));
@@ -1555,7 +1557,7 @@ static void get_handler_name(char *str, size_t size,
 }
 
 static void
-process_stat(struct evsel *counter, int cpu, int thread, u64 tstamp,
+process_stat(struct evsel *counter, struct perf_cpu cpu, int thread, u64 tstamp,
 	     struct perf_counts_values *count)
 {
 	PyObject *handler, *t;
@@ -1575,7 +1577,7 @@ process_stat(struct evsel *counter, int cpu, int thread, u64 tstamp,
 		return;
 	}
 
-	PyTuple_SetItem(t, n++, _PyLong_FromLong(cpu));
+	PyTuple_SetItem(t, n++, _PyLong_FromLong(cpu.cpu));
 	PyTuple_SetItem(t, n++, _PyLong_FromLong(thread));
 
 	tuple_set_u64(t, n++, tstamp);
@@ -1599,7 +1601,7 @@ static void python_process_stat(struct perf_stat_config *config,
 	int cpu, thread;
 
 	if (config->aggr_mode == AGGR_GLOBAL) {
-		process_stat(counter, -1, -1, tstamp,
+		process_stat(counter, (struct perf_cpu){ .cpu = -1 }, -1, tstamp,
 			     &counter->counts->aggr);
 		return;
 	}
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index d8857d1b6d7c..f19348dddd55 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -15,6 +15,7 @@
 #include "map_symbol.h"
 #include "branch.h"
 #include "debug.h"
+#include "env.h"
 #include "evlist.h"
 #include "evsel.h"
 #include "memswap.h"
@@ -1168,7 +1169,7 @@ static void branch_stack__printf(struct perf_sample *sample, bool callstack)
 	}
 }
 
-static void regs_dump__printf(u64 mask, u64 *regs)
+static void regs_dump__printf(u64 mask, u64 *regs, const char *arch)
 {
 	unsigned rid, i = 0;
 
@@ -1176,7 +1177,7 @@ static void regs_dump__printf(u64 mask, u64 *regs)
 		u64 val = regs[i++];
 
 		printf(".... %-5s 0x%016" PRIx64 "\n",
-		       perf_reg_name(rid), val);
+		       perf_reg_name(rid, arch), val);
 	}
 }
 
@@ -1194,7 +1195,7 @@ static inline const char *regs_dump_abi(struct regs_dump *d)
 	return regs_abi[d->abi];
 }
 
-static void regs__printf(const char *type, struct regs_dump *regs)
+static void regs__printf(const char *type, struct regs_dump *regs, const char *arch)
 {
 	u64 mask = regs->mask;
 
@@ -1203,23 +1204,23 @@ static void regs__printf(const char *type, struct regs_dump *regs)
 	       mask,
 	       regs_dump_abi(regs));
 
-	regs_dump__printf(mask, regs->regs);
+	regs_dump__printf(mask, regs->regs, arch);
 }
 
-static void regs_user__printf(struct perf_sample *sample)
+static void regs_user__printf(struct perf_sample *sample, const char *arch)
 {
 	struct regs_dump *user_regs = &sample->user_regs;
 
 	if (user_regs->regs)
-		regs__printf("user", user_regs);
+		regs__printf("user", user_regs, arch);
 }
 
-static void regs_intr__printf(struct perf_sample *sample)
+static void regs_intr__printf(struct perf_sample *sample, const char *arch)
 {
 	struct regs_dump *intr_regs = &sample->intr_regs;
 
 	if (intr_regs->regs)
-		regs__printf("intr", intr_regs);
+		regs__printf("intr", intr_regs, arch);
 }
 
 static void stack_user__printf(struct stack_dump *dump)
@@ -1304,7 +1305,7 @@ char *get_page_size_name(u64 size, char *str)
 }
 
 static void dump_sample(struct evsel *evsel, union perf_event *event,
-			struct perf_sample *sample)
+			struct perf_sample *sample, const char *arch)
 {
 	u64 sample_type;
 	char str[PAGE_SIZE_NAME_LEN];
@@ -1325,10 +1326,10 @@ static void dump_sample(struct evsel *evsel, union perf_event *event,
 		branch_stack__printf(sample, evsel__has_branch_callstack(evsel));
 
 	if (sample_type & PERF_SAMPLE_REGS_USER)
-		regs_user__printf(sample);
+		regs_user__printf(sample, arch);
 
 	if (sample_type & PERF_SAMPLE_REGS_INTR)
-		regs_intr__printf(sample);
+		regs_intr__printf(sample, arch);
 
 	if (sample_type & PERF_SAMPLE_STACK_USER)
 		stack_user__printf(&sample->user_stack);
@@ -1502,7 +1503,7 @@ static int machines__deliver_event(struct machines *machines,
 			++evlist->stats.nr_unknown_id;
 			return 0;
 		}
-		dump_sample(evsel, event, sample);
+		dump_sample(evsel, event, sample, perf_env__arch(machine->env));
 		if (machine == NULL) {
 			++evlist->stats.nr_unprocessable_samples;
 			return 0;
@@ -2537,15 +2538,15 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 	}
 
 	for (i = 0; i < map->nr; i++) {
-		int cpu = map->map[i];
+		struct perf_cpu cpu = map->map[i];
 
-		if (cpu >= nr_cpus) {
+		if (cpu.cpu >= nr_cpus) {
 			pr_err("Requested CPU %d too large. "
-			       "Consider raising MAX_NR_CPUS\n", cpu);
+			       "Consider raising MAX_NR_CPUS\n", cpu.cpu);
 			goto out_delete_map;
 		}
 
-		set_bit(cpu, cpu_bitmap);
+		set_bit(cpu.cpu, cpu_bitmap);
 	}
 
 	err = 0;
@@ -2597,7 +2598,7 @@ int perf_event__process_id_index(struct perf_session *session,
 		if (!sid)
 			return -ENOENT;
 		sid->idx = e->idx;
-		sid->cpu = e->cpu;
+		sid->cpu.cpu = e->cpu;
 		sid->tid = e->tid;
 	}
 	return 0;
diff --git a/tools/perf/util/smt.c b/tools/perf/util/smt.c
index 34f1b1b1176c..2b0a36ebf27a 100644
--- a/tools/perf/util/smt.c
+++ b/tools/perf/util/smt.c
@@ -5,6 +5,56 @@
 #include "api/fs/fs.h"
 #include "smt.h"
 
+/**
+ * hweight_str - Returns the number of bits set in str. Stops at first non-hex
+ *	       or ',' character.
+ */
+static int hweight_str(char *str)
+{
+	int result = 0;
+
+	while (*str) {
+		switch (*str++) {
+		case '0':
+		case ',':
+			break;
+		case '1':
+		case '2':
+		case '4':
+		case '8':
+			result++;
+			break;
+		case '3':
+		case '5':
+		case '6':
+		case '9':
+		case 'a':
+		case 'A':
+		case 'c':
+		case 'C':
+			result += 2;
+			break;
+		case '7':
+		case 'b':
+		case 'B':
+		case 'd':
+		case 'D':
+		case 'e':
+		case 'E':
+			result += 3;
+			break;
+		case 'f':
+		case 'F':
+			result += 4;
+			break;
+		default:
+			goto done;
+		}
+	}
+done:
+	return result;
+}
+
 int smt_on(void)
 {
 	static bool cached;
@@ -15,9 +65,12 @@ int smt_on(void)
 	if (cached)
 		return cached_result;
 
-	if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) >= 0)
-		goto done;
+	if (sysfs__read_int("devices/system/cpu/smt/active", &cached_result) >= 0) {
+		cached = true;
+		return cached_result;
+	}
 
+	cached_result = 0;
 	ncpu = sysconf(_SC_NPROCESSORS_CONF);
 	for (cpu = 0; cpu < ncpu; cpu++) {
 		unsigned long long siblings;
@@ -26,27 +79,21 @@ int smt_on(void)
 		char fn[256];
 
 		snprintf(fn, sizeof fn,
-			"devices/system/cpu/cpu%d/topology/core_cpus", cpu);
+			"devices/system/cpu/cpu%d/topology/thread_siblings", cpu);
 		if (sysfs__read_str(fn, &str, &strlen) < 0) {
 			snprintf(fn, sizeof fn,
-				"devices/system/cpu/cpu%d/topology/thread_siblings",
-				cpu);
+				"devices/system/cpu/cpu%d/topology/core_cpus", cpu);
 			if (sysfs__read_str(fn, &str, &strlen) < 0)
 				continue;
 		}
 		/* Entry is hex, but does not have 0x, so need custom parser */
-		siblings = strtoull(str, NULL, 16);
+		siblings = hweight_str(str);
 		free(str);
-		if (hweight64(siblings) > 1) {
+		if (siblings > 1) {
 			cached_result = 1;
-			cached = true;
 			break;
 		}
 	}
-	if (!cached) {
-		cached_result = 0;
-done:
-		cached = true;
-	}
+	cached = true;
 	return cached_result;
 }
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index d9a106f0edb2..cfba8c337783 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -37,7 +37,7 @@ const char	default_parent_pattern[] = "^sys_|^do_page_fault";
 const char	*parent_pattern = default_parent_pattern;
 const char	*default_sort_order = "comm,dso,symbol";
 const char	default_branch_sort_order[] = "comm,dso_from,symbol_from,symbol_to,cycles";
-const char	default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat,p_stage_cyc";
+const char	default_mem_sort_order[] = "local_weight,mem,sym,dso,symbol_daddr,dso_daddr,snoop,tlb,locked,blocked,local_ins_lat,local_p_stage_cyc";
 const char	default_top_sort_order[] = "dso,symbol";
 const char	default_diff_sort_order[] = "dso,symbol";
 const char	default_tracepoint_sort_order[] = "trace";
@@ -46,8 +46,8 @@ const char	*field_order;
 regex_t		ignore_callees_regex;
 int		have_ignore_callees = 0;
 enum sort_mode	sort__mode = SORT_MODE__NORMAL;
-const char	*dynamic_headers[] = {"local_ins_lat", "p_stage_cyc"};
-const char	*arch_specific_sort_keys[] = {"p_stage_cyc"};
+static const char *const dynamic_headers[] = {"local_ins_lat", "ins_lat", "local_p_stage_cyc", "p_stage_cyc"};
+static const char *const arch_specific_sort_keys[] = {"local_p_stage_cyc", "p_stage_cyc"};
 
 /*
  * Replaces all occurrences of a char used with the:
@@ -1392,22 +1392,37 @@ struct sort_entry sort_global_ins_lat = {
 };
 
 static int64_t
-sort__global_p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right)
+sort__p_stage_cyc_cmp(struct hist_entry *left, struct hist_entry *right)
 {
 	return left->p_stage_cyc - right->p_stage_cyc;
 }
 
+static int hist_entry__global_p_stage_cyc_snprintf(struct hist_entry *he, char *bf,
+					size_t size, unsigned int width)
+{
+	return repsep_snprintf(bf, size, "%-*u", width,
+			he->p_stage_cyc * he->stat.nr_events);
+}
+
+
 static int hist_entry__p_stage_cyc_snprintf(struct hist_entry *he, char *bf,
 					size_t size, unsigned int width)
 {
 	return repsep_snprintf(bf, size, "%-*u", width, he->p_stage_cyc);
 }
 
-struct sort_entry sort_p_stage_cyc = {
-	.se_header      = "Pipeline Stage Cycle",
-	.se_cmp         = sort__global_p_stage_cyc_cmp,
+struct sort_entry sort_local_p_stage_cyc = {
+	.se_header      = "Local Pipeline Stage Cycle",
+	.se_cmp         = sort__p_stage_cyc_cmp,
 	.se_snprintf	= hist_entry__p_stage_cyc_snprintf,
-	.se_width_idx	= HISTC_P_STAGE_CYC,
+	.se_width_idx	= HISTC_LOCAL_P_STAGE_CYC,
+};
+
+struct sort_entry sort_global_p_stage_cyc = {
+	.se_header      = "Pipeline Stage Cycle",
+	.se_cmp         = sort__p_stage_cyc_cmp,
+	.se_snprintf    = hist_entry__global_p_stage_cyc_snprintf,
+	.se_width_idx   = HISTC_GLOBAL_P_STAGE_CYC,
 };
 
 struct sort_entry sort_mem_daddr_sym = {
@@ -1858,7 +1873,8 @@ static struct sort_dimension common_sort_dimensions[] = {
 	DIM(SORT_CODE_PAGE_SIZE, "code_page_size", sort_code_page_size),
 	DIM(SORT_LOCAL_INS_LAT, "local_ins_lat", sort_local_ins_lat),
 	DIM(SORT_GLOBAL_INS_LAT, "ins_lat", sort_global_ins_lat),
-	DIM(SORT_PIPELINE_STAGE_CYC, "p_stage_cyc", sort_p_stage_cyc),
+	DIM(SORT_LOCAL_PIPELINE_STAGE_CYC, "local_p_stage_cyc", sort_local_p_stage_cyc),
+	DIM(SORT_GLOBAL_PIPELINE_STAGE_CYC, "p_stage_cyc", sort_global_p_stage_cyc),
 };
 
 #undef DIM
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 7b7145501933..f994261888e1 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -235,7 +235,8 @@ enum sort_type {
 	SORT_CODE_PAGE_SIZE,
 	SORT_LOCAL_INS_LAT,
 	SORT_GLOBAL_INS_LAT,
-	SORT_PIPELINE_STAGE_CYC,
+	SORT_LOCAL_PIPELINE_STAGE_CYC,
+	SORT_GLOBAL_PIPELINE_STAGE_CYC,
 
 	/* branch stack specific sort keys */
 	__SORT_BRANCH_STACK,
diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
index 588601000f3f..5db83e51ceef 100644
--- a/tools/perf/util/stat-display.c
+++ b/tools/perf/util/stat-display.c
@@ -4,6 +4,7 @@
 #include <linux/string.h>
 #include <linux/time64.h>
 #include <math.h>
+#include <perf/cpumap.h>
 #include "color.h"
 #include "counts.h"
 #include "evlist.h"
@@ -120,11 +121,10 @@ static void aggr_printout(struct perf_stat_config *config,
 				id.die,
 				config->csv_output ? 0 : -3,
 				id.core, config->csv_sep);
-		} else if (id.core > -1) {
+		} else if (id.cpu.cpu > -1) {
 			fprintf(config->output, "CPU%*d%s",
 				config->csv_output ? 0 : -7,
-				evsel__cpus(evsel)->map[id.core],
-				config->csv_sep);
+				id.cpu.cpu, config->csv_sep);
 		}
 		break;
 	case AGGR_THREAD:
@@ -327,26 +327,24 @@ static void print_metric_header(struct perf_stat_config *config,
 		fprintf(os->fh, "%*s ", config->metric_only_len, unit);
 }
 
-static int first_shadow_cpu(struct perf_stat_config *config,
-			    struct evsel *evsel, struct aggr_cpu_id id)
+static int first_shadow_cpu_map_idx(struct perf_stat_config *config,
+				struct evsel *evsel, const struct aggr_cpu_id *id)
 {
-	struct evlist *evlist = evsel->evlist;
-	int i;
+	struct perf_cpu_map *cpus = evsel__cpus(evsel);
+	struct perf_cpu cpu;
+	int idx;
 
 	if (config->aggr_mode == AGGR_NONE)
-		return id.core;
+		return perf_cpu_map__idx(cpus, id->cpu);
 
 	if (!config->aggr_get_id)
 		return 0;
 
-	for (i = 0; i < evsel__nr_cpus(evsel); i++) {
-		int cpu2 = evsel__cpus(evsel)->map[i];
+	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+		struct aggr_cpu_id cpu_id = config->aggr_get_id(config, cpu);
 
-		if (cpu_map__compare_aggr_cpu_id(
-					config->aggr_get_id(config, evlist->core.cpus, cpu2),
-					id)) {
-			return cpu2;
-		}
+		if (aggr_cpu_id__equal(&cpu_id, id))
+			return idx;
 	}
 	return 0;
 }
@@ -505,7 +503,7 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int
 	}
 
 	perf_stat__print_shadow_stats(config, counter, uval,
-				first_shadow_cpu(config, counter, id),
+				first_shadow_cpu_map_idx(config, counter, &id),
 				&out, &config->metric_events, st);
 	if (!config->csv_output && !config->metric_only) {
 		print_noise(config, counter, noise);
@@ -516,23 +514,26 @@ static void printout(struct perf_stat_config *config, struct aggr_cpu_id id, int
 static void aggr_update_shadow(struct perf_stat_config *config,
 			       struct evlist *evlist)
 {
-	int cpu, s;
+	int idx, s;
+	struct perf_cpu cpu;
 	struct aggr_cpu_id s2, id;
 	u64 val;
 	struct evsel *counter;
+	struct perf_cpu_map *cpus;
 
 	for (s = 0; s < config->aggr_map->nr; s++) {
 		id = config->aggr_map->map[s];
 		evlist__for_each_entry(evlist, counter) {
+			cpus = evsel__cpus(counter);
 			val = 0;
-			for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
-				s2 = config->aggr_get_id(config, evlist->core.cpus, cpu);
-				if (!cpu_map__compare_aggr_cpu_id(s2, id))
+			perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+				s2 = config->aggr_get_id(config, cpu);
+				if (!aggr_cpu_id__equal(&s2, &id))
 					continue;
-				val += perf_counts(counter->counts, cpu, 0)->val;
+				val += perf_counts(counter->counts, idx, 0)->val;
 			}
 			perf_stat__update_shadow_stats(counter, val,
-					first_shadow_cpu(config, counter, id),
+					first_shadow_cpu_map_idx(config, counter, &id),
 					&rt_stat);
 		}
 	}
@@ -627,25 +628,28 @@ struct aggr_data {
 	u64 ena, run, val;
 	struct aggr_cpu_id id;
 	int nr;
-	int cpu;
+	int cpu_map_idx;
 };
 
 static void aggr_cb(struct perf_stat_config *config,
 		    struct evsel *counter, void *data, bool first)
 {
 	struct aggr_data *ad = data;
-	int cpu;
+	int idx;
+	struct perf_cpu cpu;
+	struct perf_cpu_map *cpus;
 	struct aggr_cpu_id s2;
 
-	for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
+	cpus = evsel__cpus(counter);
+	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
 		struct perf_counts_values *counts;
 
-		s2 = config->aggr_get_id(config, evsel__cpus(counter), cpu);
-		if (!cpu_map__compare_aggr_cpu_id(s2, ad->id))
+		s2 = config->aggr_get_id(config, cpu);
+		if (!aggr_cpu_id__equal(&s2, &ad->id))
 			continue;
 		if (first)
 			ad->nr++;
-		counts = perf_counts(counter->counts, cpu, 0);
+		counts = perf_counts(counter->counts, idx, 0);
 		/*
 		 * When any result is bad, make them all to give
 		 * consistent output in interval mode.
@@ -665,7 +669,7 @@ static void aggr_cb(struct perf_stat_config *config,
 static void print_counter_aggrdata(struct perf_stat_config *config,
 				   struct evsel *counter, int s,
 				   char *prefix, bool metric_only,
-				   bool *first, int cpu)
+				   bool *first, struct perf_cpu cpu)
 {
 	struct aggr_data ad;
 	FILE *output = config->output;
@@ -695,10 +699,9 @@ static void print_counter_aggrdata(struct perf_stat_config *config,
 		fprintf(output, "%s", prefix);
 
 	uval = val * counter->scale;
-	if (cpu != -1) {
-		id = cpu_map__empty_aggr_cpu_id();
-		id.core = cpu;
-	}
+	if (cpu.cpu != -1)
+		id = aggr_cpu_id__cpu(cpu, /*data=*/NULL);
+
 	printout(config, id, nr, counter, uval,
 		 prefix, run, ena, 1.0, &rt_stat);
 	if (!metric_only)
@@ -731,8 +734,8 @@ static void print_aggr(struct perf_stat_config *config,
 		first = true;
 		evlist__for_each_entry(evlist, counter) {
 			print_counter_aggrdata(config, counter, s,
-					       prefix, metric_only,
-					       &first, -1);
+					prefix, metric_only,
+					&first, (struct perf_cpu){ .cpu = -1 });
 		}
 		if (metric_only)
 			fputc('\n', output);
@@ -778,7 +781,7 @@ static struct perf_aggr_thread_value *sort_aggr_thread(
 			continue;
 
 		buf[i].counter = counter;
-		buf[i].id = cpu_map__empty_aggr_cpu_id();
+		buf[i].id = aggr_cpu_id__empty();
 		buf[i].id.thread = thread;
 		buf[i].uval = uval;
 		buf[i].val = val;
@@ -866,7 +869,7 @@ static void print_counter_aggr(struct perf_stat_config *config,
 		fprintf(output, "%s", prefix);
 
 	uval = cd.avg * counter->scale;
-	printout(config, cpu_map__empty_aggr_cpu_id(), 0, counter, uval, prefix, cd.avg_running,
+	printout(config, aggr_cpu_id__empty(), 0, counter, uval, prefix, cd.avg_running,
 		 cd.avg_enabled, cd.avg, &rt_stat);
 	if (!metric_only)
 		fprintf(output, "\n");
@@ -878,9 +881,9 @@ static void counter_cb(struct perf_stat_config *config __maybe_unused,
 {
 	struct aggr_data *ad = data;
 
-	ad->val += perf_counts(counter->counts, ad->cpu, 0)->val;
-	ad->ena += perf_counts(counter->counts, ad->cpu, 0)->ena;
-	ad->run += perf_counts(counter->counts, ad->cpu, 0)->run;
+	ad->val += perf_counts(counter->counts, ad->cpu_map_idx, 0)->val;
+	ad->ena += perf_counts(counter->counts, ad->cpu_map_idx, 0)->ena;
+	ad->run += perf_counts(counter->counts, ad->cpu_map_idx, 0)->run;
 }
 
 /*
@@ -893,11 +896,12 @@ static void print_counter(struct perf_stat_config *config,
 	FILE *output = config->output;
 	u64 ena, run, val;
 	double uval;
-	int cpu;
+	int idx;
+	struct perf_cpu cpu;
 	struct aggr_cpu_id id;
 
-	for (cpu = 0; cpu < evsel__nr_cpus(counter); cpu++) {
-		struct aggr_data ad = { .cpu = cpu };
+	perf_cpu_map__for_each_cpu(cpu, idx, evsel__cpus(counter)) {
+		struct aggr_data ad = { .cpu_map_idx = idx };
 
 		if (!collect_data(config, counter, counter_cb, &ad))
 			return;
@@ -909,8 +913,7 @@ static void print_counter(struct perf_stat_config *config,
 			fprintf(output, "%s", prefix);
 
 		uval = val * counter->scale;
-		id = cpu_map__empty_aggr_cpu_id();
-		id.core = cpu;
+		id = aggr_cpu_id__cpu(cpu, /*data=*/NULL);
 		printout(config, id, 0, counter, uval, prefix,
 			 run, ena, 1.0, &rt_stat);
 
@@ -922,29 +925,32 @@ static void print_no_aggr_metric(struct perf_stat_config *config,
 				 struct evlist *evlist,
 				 char *prefix)
 {
-	int cpu;
-	int nrcpus = 0;
-	struct evsel *counter;
-	u64 ena, run, val;
-	double uval;
-	struct aggr_cpu_id id;
+	int all_idx;
+	struct perf_cpu cpu;
 
-	nrcpus = evlist->core.cpus->nr;
-	for (cpu = 0; cpu < nrcpus; cpu++) {
+	perf_cpu_map__for_each_cpu(cpu, all_idx, evlist->core.cpus) {
+		struct evsel *counter;
 		bool first = true;
 
 		if (prefix)
 			fputs(prefix, config->output);
 		evlist__for_each_entry(evlist, counter) {
-			id = cpu_map__empty_aggr_cpu_id();
-			id.core = cpu;
+			u64 ena, run, val;
+			double uval;
+			struct aggr_cpu_id id;
+			int counter_idx = perf_cpu_map__idx(evsel__cpus(counter), cpu);
+
+			if (counter_idx < 0)
+				continue;
+
+			id = aggr_cpu_id__cpu(cpu, /*data=*/NULL);
 			if (first) {
 				aggr_printout(config, counter, id, 0);
 				first = false;
 			}
-			val = perf_counts(counter->counts, cpu, 0)->val;
-			ena = perf_counts(counter->counts, cpu, 0)->ena;
-			run = perf_counts(counter->counts, cpu, 0)->run;
+			val = perf_counts(counter->counts, counter_idx, 0)->val;
+			ena = perf_counts(counter->counts, counter_idx, 0)->ena;
+			run = perf_counts(counter->counts, counter_idx, 0)->run;
 
 			uval = val * counter->scale;
 			printout(config, id, 0, counter, uval, prefix,
@@ -1208,19 +1214,23 @@ static void print_percore_thread(struct perf_stat_config *config,
 {
 	int s;
 	struct aggr_cpu_id s2, id;
+	struct perf_cpu_map *cpus;
 	bool first = true;
+	int idx;
+	struct perf_cpu cpu;
 
-	for (int i = 0; i < evsel__nr_cpus(counter); i++) {
-		s2 = config->aggr_get_id(config, evsel__cpus(counter), i);
+	cpus = evsel__cpus(counter);
+	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+		s2 = config->aggr_get_id(config, cpu);
 		for (s = 0; s < config->aggr_map->nr; s++) {
 			id = config->aggr_map->map[s];
-			if (cpu_map__compare_aggr_cpu_id(s2, id))
+			if (aggr_cpu_id__equal(&s2, &id))
 				break;
 		}
 
 		print_counter_aggrdata(config, counter, s,
 				       prefix, false,
-				       &first, i);
+				       &first, cpu);
 	}
 }
 
@@ -1243,8 +1253,8 @@ static void print_percore(struct perf_stat_config *config,
 			fprintf(output, "%s", prefix);
 
 		print_counter_aggrdata(config, counter, s,
-				       prefix, metric_only,
-				       &first, -1);
+				prefix, metric_only,
+				&first, (struct perf_cpu){ .cpu = -1 });
 	}
 
 	if (metric_only)
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 5c7308efa768..10af7804e482 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -32,7 +32,7 @@ struct saved_value {
 	struct evsel *evsel;
 	enum stat_type type;
 	int ctx;
-	int cpu;
+	int cpu_map_idx;
 	struct cgroup *cgrp;
 	struct runtime_stat *stat;
 	struct stats stats;
@@ -47,8 +47,8 @@ static int saved_value_cmp(struct rb_node *rb_node, const void *entry)
 					     rb_node);
 	const struct saved_value *b = entry;
 
-	if (a->cpu != b->cpu)
-		return a->cpu - b->cpu;
+	if (a->cpu_map_idx != b->cpu_map_idx)
+		return a->cpu_map_idx - b->cpu_map_idx;
 
 	/*
 	 * Previously the rbtree was used to link generic metrics.
@@ -105,7 +105,7 @@ static void saved_value_delete(struct rblist *rblist __maybe_unused,
 }
 
 static struct saved_value *saved_value_lookup(struct evsel *evsel,
-					      int cpu,
+					      int cpu_map_idx,
 					      bool create,
 					      enum stat_type type,
 					      int ctx,
@@ -115,7 +115,7 @@ static struct saved_value *saved_value_lookup(struct evsel *evsel,
 	struct rblist *rblist;
 	struct rb_node *nd;
 	struct saved_value dm = {
-		.cpu = cpu,
+		.cpu_map_idx = cpu_map_idx,
 		.evsel = evsel,
 		.type = type,
 		.ctx = ctx,
@@ -213,10 +213,10 @@ struct runtime_stat_data {
 
 static void update_runtime_stat(struct runtime_stat *st,
 				enum stat_type type,
-				int cpu, u64 count,
+				int cpu_map_idx, u64 count,
 				struct runtime_stat_data *rsd)
 {
-	struct saved_value *v = saved_value_lookup(NULL, cpu, true, type,
+	struct saved_value *v = saved_value_lookup(NULL, cpu_map_idx, true, type,
 						   rsd->ctx, st, rsd->cgrp);
 
 	if (v)
@@ -229,7 +229,7 @@ static void update_runtime_stat(struct runtime_stat *st,
  * instruction rates, etc:
  */
 void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
-				    int cpu, struct runtime_stat *st)
+				    int cpu_map_idx, struct runtime_stat *st)
 {
 	u64 count_ns = count;
 	struct saved_value *v;
@@ -241,88 +241,88 @@ void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
 	count *= counter->scale;
 
 	if (evsel__is_clock(counter))
-		update_runtime_stat(st, STAT_NSECS, cpu, count_ns, &rsd);
+		update_runtime_stat(st, STAT_NSECS, cpu_map_idx, count_ns, &rsd);
 	else if (evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
-		update_runtime_stat(st, STAT_CYCLES, cpu, count, &rsd);
+		update_runtime_stat(st, STAT_CYCLES, cpu_map_idx, count, &rsd);
 	else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
-		update_runtime_stat(st, STAT_CYCLES_IN_TX, cpu, count, &rsd);
+		update_runtime_stat(st, STAT_CYCLES_IN_TX, cpu_map_idx, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TRANSACTION_START))
-		update_runtime_stat(st, STAT_TRANSACTION, cpu, count, &rsd);
+		update_runtime_stat(st, STAT_TRANSACTION, cpu_map_idx, count, &rsd);
 	else if (perf_stat_evsel__is(counter, ELISION_START))
-		update_runtime_stat(st, STAT_ELISION, cpu, count, &rsd);
+		update_runtime_stat(st, STAT_ELISION, cpu_map_idx, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_TOTAL_SLOTS))
 		update_runtime_stat(st, STAT_TOPDOWN_TOTAL_SLOTS,
-				    cpu, count, &rsd);
+				    cpu_map_idx, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_ISSUED))
 		update_runtime_stat(st, STAT_TOPDOWN_SLOTS_ISSUED,
-				    cpu, count, &rsd);
+				    cpu_map_idx, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_SLOTS_RETIRED))
 		update_runtime_stat(st, STAT_TOPDOWN_SLOTS_RETIRED,
-				    cpu, count, &rsd);
+				    cpu_map_idx, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_BUBBLES))
 		update_runtime_stat(st, STAT_TOPDOWN_FETCH_BUBBLES,
-				    cpu, count, &rsd);
+				    cpu_map_idx, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_RECOVERY_BUBBLES))
 		update_runtime_stat(st, STAT_TOPDOWN_RECOVERY_BUBBLES,
-				    cpu, count, &rsd);
+				    cpu_map_idx, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_RETIRING))
 		update_runtime_stat(st, STAT_TOPDOWN_RETIRING,
-				    cpu, count, &rsd);
+				    cpu_map_idx, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_BAD_SPEC))
 		update_runtime_stat(st, STAT_TOPDOWN_BAD_SPEC,
-				    cpu, count, &rsd);
+				    cpu_map_idx, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_FE_BOUND))
 		update_runtime_stat(st, STAT_TOPDOWN_FE_BOUND,
-				    cpu, count, &rsd);
+				    cpu_map_idx, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_BE_BOUND))
 		update_runtime_stat(st, STAT_TOPDOWN_BE_BOUND,
-				    cpu, count, &rsd);
+				    cpu_map_idx, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_HEAVY_OPS))
 		update_runtime_stat(st, STAT_TOPDOWN_HEAVY_OPS,
-				    cpu, count, &rsd);
+				    cpu_map_idx, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_BR_MISPREDICT))
 		update_runtime_stat(st, STAT_TOPDOWN_BR_MISPREDICT,
-				    cpu, count, &rsd);
+				    cpu_map_idx, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_FETCH_LAT))
 		update_runtime_stat(st, STAT_TOPDOWN_FETCH_LAT,
-				    cpu, count, &rsd);
+				    cpu_map_idx, count, &rsd);
 	else if (perf_stat_evsel__is(counter, TOPDOWN_MEM_BOUND))
 		update_runtime_stat(st, STAT_TOPDOWN_MEM_BOUND,
-				    cpu, count, &rsd);
+				    cpu_map_idx, count, &rsd);
 	else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_FRONTEND))
 		update_runtime_stat(st, STAT_STALLED_CYCLES_FRONT,
-				    cpu, count, &rsd);
+				    cpu_map_idx, count, &rsd);
 	else if (evsel__match(counter, HARDWARE, HW_STALLED_CYCLES_BACKEND))
 		update_runtime_stat(st, STAT_STALLED_CYCLES_BACK,
-				    cpu, count, &rsd);
+				    cpu_map_idx, count, &rsd);
 	else if (evsel__match(counter, HARDWARE, HW_BRANCH_INSTRUCTIONS))
-		update_runtime_stat(st, STAT_BRANCHES, cpu, count, &rsd);
+		update_runtime_stat(st, STAT_BRANCHES, cpu_map_idx, count, &rsd);
 	else if (evsel__match(counter, HARDWARE, HW_CACHE_REFERENCES))
-		update_runtime_stat(st, STAT_CACHEREFS, cpu, count, &rsd);
+		update_runtime_stat(st, STAT_CACHEREFS, cpu_map_idx, count, &rsd);
 	else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1D))
-		update_runtime_stat(st, STAT_L1_DCACHE, cpu, count, &rsd);
+		update_runtime_stat(st, STAT_L1_DCACHE, cpu_map_idx, count, &rsd);
 	else if (evsel__match(counter, HW_CACHE, HW_CACHE_L1I))
-		update_runtime_stat(st, STAT_L1_ICACHE, cpu, count, &rsd);
+		update_runtime_stat(st, STAT_L1_ICACHE, cpu_map_idx, count, &rsd);
 	else if (evsel__match(counter, HW_CACHE, HW_CACHE_LL))
-		update_runtime_stat(st, STAT_LL_CACHE, cpu, count, &rsd);
+		update_runtime_stat(st, STAT_LL_CACHE, cpu_map_idx, count, &rsd);
 	else if (evsel__match(counter, HW_CACHE, HW_CACHE_DTLB))
-		update_runtime_stat(st, STAT_DTLB_CACHE, cpu, count, &rsd);
+		update_runtime_stat(st, STAT_DTLB_CACHE, cpu_map_idx, count, &rsd);
 	else if (evsel__match(counter, HW_CACHE, HW_CACHE_ITLB))
-		update_runtime_stat(st, STAT_ITLB_CACHE, cpu, count, &rsd);
+		update_runtime_stat(st, STAT_ITLB_CACHE, cpu_map_idx, count, &rsd);
 	else if (perf_stat_evsel__is(counter, SMI_NUM))
-		update_runtime_stat(st, STAT_SMI_NUM, cpu, count, &rsd);
+		update_runtime_stat(st, STAT_SMI_NUM, cpu_map_idx, count, &rsd);
 	else if (perf_stat_evsel__is(counter, APERF))
-		update_runtime_stat(st, STAT_APERF, cpu, count, &rsd);
+		update_runtime_stat(st, STAT_APERF, cpu_map_idx, count, &rsd);
 
 	if (counter->collect_stat) {
-		v = saved_value_lookup(counter, cpu, true, STAT_NONE, 0, st,
+		v = saved_value_lookup(counter, cpu_map_idx, true, STAT_NONE, 0, st,
 				       rsd.cgrp);
 		update_stats(&v->stats, count);
 		if (counter->metric_leader)
 			v->metric_total += count;
 	} else if (counter->metric_leader) {
 		v = saved_value_lookup(counter->metric_leader,
-				       cpu, true, STAT_NONE, 0, st, rsd.cgrp);
+				       cpu_map_idx, true, STAT_NONE, 0, st, rsd.cgrp);
 		v->metric_total += count;
 		v->metric_other++;
 	}
@@ -464,12 +464,12 @@ void perf_stat__collect_metric_expr(struct evlist *evsel_list)
 }
 
 static double runtime_stat_avg(struct runtime_stat *st,
-			       enum stat_type type, int cpu,
+			       enum stat_type type, int cpu_map_idx,
 			       struct runtime_stat_data *rsd)
 {
 	struct saved_value *v;
 
-	v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp);
+	v = saved_value_lookup(NULL, cpu_map_idx, false, type, rsd->ctx, st, rsd->cgrp);
 	if (!v)
 		return 0.0;
 
@@ -477,12 +477,12 @@ static double runtime_stat_avg(struct runtime_stat *st,
 }
 
 static double runtime_stat_n(struct runtime_stat *st,
-			     enum stat_type type, int cpu,
+			     enum stat_type type, int cpu_map_idx,
 			     struct runtime_stat_data *rsd)
 {
 	struct saved_value *v;
 
-	v = saved_value_lookup(NULL, cpu, false, type, rsd->ctx, st, rsd->cgrp);
+	v = saved_value_lookup(NULL, cpu_map_idx, false, type, rsd->ctx, st, rsd->cgrp);
 	if (!v)
 		return 0.0;
 
@@ -490,7 +490,7 @@ static double runtime_stat_n(struct runtime_stat *st,
 }
 
 static void print_stalled_cycles_frontend(struct perf_stat_config *config,
-					  int cpu, double avg,
+					  int cpu_map_idx, double avg,
 					  struct perf_stat_output_ctx *out,
 					  struct runtime_stat *st,
 					  struct runtime_stat_data *rsd)
@@ -498,7 +498,7 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config,
 	double total, ratio = 0.0;
 	const char *color;
 
-	total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
+	total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -513,7 +513,7 @@ static void print_stalled_cycles_frontend(struct perf_stat_config *config,
 }
 
 static void print_stalled_cycles_backend(struct perf_stat_config *config,
-					 int cpu, double avg,
+					 int cpu_map_idx, double avg,
 					 struct perf_stat_output_ctx *out,
 					 struct runtime_stat *st,
 					 struct runtime_stat_data *rsd)
@@ -521,7 +521,7 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config,
 	double total, ratio = 0.0;
 	const char *color;
 
-	total = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
+	total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -532,7 +532,7 @@ static void print_stalled_cycles_backend(struct perf_stat_config *config,
 }
 
 static void print_branch_misses(struct perf_stat_config *config,
-				int cpu, double avg,
+				int cpu_map_idx, double avg,
 				struct perf_stat_output_ctx *out,
 				struct runtime_stat *st,
 				struct runtime_stat_data *rsd)
@@ -540,7 +540,7 @@ static void print_branch_misses(struct perf_stat_config *config,
 	double total, ratio = 0.0;
 	const char *color;
 
-	total = runtime_stat_avg(st, STAT_BRANCHES, cpu, rsd);
+	total = runtime_stat_avg(st, STAT_BRANCHES, cpu_map_idx, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -551,7 +551,7 @@ static void print_branch_misses(struct perf_stat_config *config,
 }
 
 static void print_l1_dcache_misses(struct perf_stat_config *config,
-				   int cpu, double avg,
+				   int cpu_map_idx, double avg,
 				   struct perf_stat_output_ctx *out,
 				   struct runtime_stat *st,
 				   struct runtime_stat_data *rsd)
@@ -559,7 +559,7 @@ static void print_l1_dcache_misses(struct perf_stat_config *config,
 	double total, ratio = 0.0;
 	const char *color;
 
-	total = runtime_stat_avg(st, STAT_L1_DCACHE, cpu, rsd);
+	total = runtime_stat_avg(st, STAT_L1_DCACHE, cpu_map_idx, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -570,7 +570,7 @@ static void print_l1_dcache_misses(struct perf_stat_config *config,
 }
 
 static void print_l1_icache_misses(struct perf_stat_config *config,
-				   int cpu, double avg,
+				   int cpu_map_idx, double avg,
 				   struct perf_stat_output_ctx *out,
 				   struct runtime_stat *st,
 				   struct runtime_stat_data *rsd)
@@ -578,7 +578,7 @@ static void print_l1_icache_misses(struct perf_stat_config *config,
 	double total, ratio = 0.0;
 	const char *color;
 
-	total = runtime_stat_avg(st, STAT_L1_ICACHE, cpu, rsd);
+	total = runtime_stat_avg(st, STAT_L1_ICACHE, cpu_map_idx, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -588,7 +588,7 @@ static void print_l1_icache_misses(struct perf_stat_config *config,
 }
 
 static void print_dtlb_cache_misses(struct perf_stat_config *config,
-				    int cpu, double avg,
+				    int cpu_map_idx, double avg,
 				    struct perf_stat_output_ctx *out,
 				    struct runtime_stat *st,
 				    struct runtime_stat_data *rsd)
@@ -596,7 +596,7 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config,
 	double total, ratio = 0.0;
 	const char *color;
 
-	total = runtime_stat_avg(st, STAT_DTLB_CACHE, cpu, rsd);
+	total = runtime_stat_avg(st, STAT_DTLB_CACHE, cpu_map_idx, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -606,7 +606,7 @@ static void print_dtlb_cache_misses(struct perf_stat_config *config,
 }
 
 static void print_itlb_cache_misses(struct perf_stat_config *config,
-				    int cpu, double avg,
+				    int cpu_map_idx, double avg,
 				    struct perf_stat_output_ctx *out,
 				    struct runtime_stat *st,
 				    struct runtime_stat_data *rsd)
@@ -614,7 +614,7 @@ static void print_itlb_cache_misses(struct perf_stat_config *config,
 	double total, ratio = 0.0;
 	const char *color;
 
-	total = runtime_stat_avg(st, STAT_ITLB_CACHE, cpu, rsd);
+	total = runtime_stat_avg(st, STAT_ITLB_CACHE, cpu_map_idx, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -624,7 +624,7 @@ static void print_itlb_cache_misses(struct perf_stat_config *config,
 }
 
 static void print_ll_cache_misses(struct perf_stat_config *config,
-				  int cpu, double avg,
+				  int cpu_map_idx, double avg,
 				  struct perf_stat_output_ctx *out,
 				  struct runtime_stat *st,
 				  struct runtime_stat_data *rsd)
@@ -632,7 +632,7 @@ static void print_ll_cache_misses(struct perf_stat_config *config,
 	double total, ratio = 0.0;
 	const char *color;
 
-	total = runtime_stat_avg(st, STAT_LL_CACHE, cpu, rsd);
+	total = runtime_stat_avg(st, STAT_LL_CACHE, cpu_map_idx, rsd);
 
 	if (total)
 		ratio = avg / total * 100.0;
@@ -690,61 +690,61 @@ static double sanitize_val(double x)
 	return x;
 }
 
-static double td_total_slots(int cpu, struct runtime_stat *st,
+static double td_total_slots(int cpu_map_idx, struct runtime_stat *st,
 			     struct runtime_stat_data *rsd)
 {
-	return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, cpu, rsd);
+	return runtime_stat_avg(st, STAT_TOPDOWN_TOTAL_SLOTS, cpu_map_idx, rsd);
 }
 
-static double td_bad_spec(int cpu, struct runtime_stat *st,
+static double td_bad_spec(int cpu_map_idx, struct runtime_stat *st,
 			  struct runtime_stat_data *rsd)
 {
 	double bad_spec = 0;
 	double total_slots;
 	double total;
 
-	total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, cpu, rsd) -
-		runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, cpu, rsd) +
-		runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, cpu, rsd);
+	total = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_ISSUED, cpu_map_idx, rsd) -
+		runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED, cpu_map_idx, rsd) +
+		runtime_stat_avg(st, STAT_TOPDOWN_RECOVERY_BUBBLES, cpu_map_idx, rsd);
 
-	total_slots = td_total_slots(cpu, st, rsd);
+	total_slots = td_total_slots(cpu_map_idx, st, rsd);
 	if (total_slots)
 		bad_spec = total / total_slots;
 	return sanitize_val(bad_spec);
 }
 
-static double td_retiring(int cpu, struct runtime_stat *st,
+static double td_retiring(int cpu_map_idx, struct runtime_stat *st,
 			  struct runtime_stat_data *rsd)
 {
 	double retiring = 0;
-	double total_slots = td_total_slots(cpu, st, rsd);
+	double total_slots = td_total_slots(cpu_map_idx, st, rsd);
 	double ret_slots = runtime_stat_avg(st, STAT_TOPDOWN_SLOTS_RETIRED,
-					    cpu, rsd);
+					    cpu_map_idx, rsd);
 
 	if (total_slots)
 		retiring = ret_slots / total_slots;
 	return retiring;
 }
 
-static double td_fe_bound(int cpu, struct runtime_stat *st,
+static double td_fe_bound(int cpu_map_idx, struct runtime_stat *st,
 			  struct runtime_stat_data *rsd)
 {
 	double fe_bound = 0;
-	double total_slots = td_total_slots(cpu, st, rsd);
+	double total_slots = td_total_slots(cpu_map_idx, st, rsd);
 	double fetch_bub = runtime_stat_avg(st, STAT_TOPDOWN_FETCH_BUBBLES,
-					    cpu, rsd);
+					    cpu_map_idx, rsd);
 
 	if (total_slots)
 		fe_bound = fetch_bub / total_slots;
 	return fe_bound;
 }
 
-static double td_be_bound(int cpu, struct runtime_stat *st,
+static double td_be_bound(int cpu_map_idx, struct runtime_stat *st,
 			  struct runtime_stat_data *rsd)
 {
-	double sum = (td_fe_bound(cpu, st, rsd) +
-		      td_bad_spec(cpu, st, rsd) +
-		      td_retiring(cpu, st, rsd));
+	double sum = (td_fe_bound(cpu_map_idx, st, rsd) +
+		      td_bad_spec(cpu_map_idx, st, rsd) +
+		      td_retiring(cpu_map_idx, st, rsd));
 	if (sum == 0)
 		return 0;
 	return sanitize_val(1.0 - sum);
@@ -755,15 +755,15 @@ static double td_be_bound(int cpu, struct runtime_stat *st,
  * the ratios we need to recreate the sum.
  */
 
-static double td_metric_ratio(int cpu, enum stat_type type,
+static double td_metric_ratio(int cpu_map_idx, enum stat_type type,
 			      struct runtime_stat *stat,
 			      struct runtime_stat_data *rsd)
 {
-	double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) +
-		runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) +
-		runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) +
-		runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd);
-	double d = runtime_stat_avg(stat, type, cpu, rsd);
+	double sum = runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu_map_idx, rsd) +
+		runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu_map_idx, rsd) +
+		runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu_map_idx, rsd) +
+		runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu_map_idx, rsd);
+	double d = runtime_stat_avg(stat, type, cpu_map_idx, rsd);
 
 	if (sum)
 		return d / sum;
@@ -775,23 +775,23 @@ static double td_metric_ratio(int cpu, enum stat_type type,
  * We allow two missing.
  */
 
-static bool full_td(int cpu, struct runtime_stat *stat,
+static bool full_td(int cpu_map_idx, struct runtime_stat *stat,
 		    struct runtime_stat_data *rsd)
 {
 	int c = 0;
 
-	if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu, rsd) > 0)
+	if (runtime_stat_avg(stat, STAT_TOPDOWN_RETIRING, cpu_map_idx, rsd) > 0)
 		c++;
-	if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu, rsd) > 0)
+	if (runtime_stat_avg(stat, STAT_TOPDOWN_BE_BOUND, cpu_map_idx, rsd) > 0)
 		c++;
-	if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu, rsd) > 0)
+	if (runtime_stat_avg(stat, STAT_TOPDOWN_FE_BOUND, cpu_map_idx, rsd) > 0)
 		c++;
-	if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu, rsd) > 0)
+	if (runtime_stat_avg(stat, STAT_TOPDOWN_BAD_SPEC, cpu_map_idx, rsd) > 0)
 		c++;
 	return c >= 2;
 }
 
-static void print_smi_cost(struct perf_stat_config *config, int cpu,
+static void print_smi_cost(struct perf_stat_config *config, int cpu_map_idx,
 			   struct perf_stat_output_ctx *out,
 			   struct runtime_stat *st,
 			   struct runtime_stat_data *rsd)
@@ -799,9 +799,9 @@ static void print_smi_cost(struct perf_stat_config *config, int cpu,
 	double smi_num, aperf, cycles, cost = 0.0;
 	const char *color = NULL;
 
-	smi_num = runtime_stat_avg(st, STAT_SMI_NUM, cpu, rsd);
-	aperf = runtime_stat_avg(st, STAT_APERF, cpu, rsd);
-	cycles = runtime_stat_avg(st, STAT_CYCLES, cpu, rsd);
+	smi_num = runtime_stat_avg(st, STAT_SMI_NUM, cpu_map_idx, rsd);
+	aperf = runtime_stat_avg(st, STAT_APERF, cpu_map_idx, rsd);
+	cycles = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, rsd);
 
 	if ((cycles == 0) || (aperf == 0))
 		return;
@@ -818,7 +818,7 @@ static void print_smi_cost(struct perf_stat_config *config, int cpu,
 static int prepare_metric(struct evsel **metric_events,
 			  struct metric_ref *metric_refs,
 			  struct expr_parse_ctx *pctx,
-			  int cpu,
+			  int cpu_map_idx,
 			  struct runtime_stat *st)
 {
 	double scale;
@@ -836,7 +836,7 @@ static int prepare_metric(struct evsel **metric_events,
 			scale = 1e-9;
 			source_count = 1;
 		} else {
-			v = saved_value_lookup(metric_events[i], cpu, false,
+			v = saved_value_lookup(metric_events[i], cpu_map_idx, false,
 					       STAT_NONE, 0, st,
 					       metric_events[i]->cgrp);
 			if (!v)
@@ -874,7 +874,7 @@ static void generic_metric(struct perf_stat_config *config,
 			   const char *metric_name,
 			   const char *metric_unit,
 			   int runtime,
-			   int cpu,
+			   int cpu_map_idx,
 			   struct perf_stat_output_ctx *out,
 			   struct runtime_stat *st)
 {
@@ -889,7 +889,7 @@ static void generic_metric(struct perf_stat_config *config,
 		return;
 
 	pctx->runtime = runtime;
-	i = prepare_metric(metric_events, metric_refs, pctx, cpu, st);
+	i = prepare_metric(metric_events, metric_refs, pctx, cpu_map_idx, st);
 	if (i < 0) {
 		expr__ctx_free(pctx);
 		return;
@@ -934,7 +934,7 @@ static void generic_metric(struct perf_stat_config *config,
 	expr__ctx_free(pctx);
 }
 
-double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st)
+double test_generic_metric(struct metric_expr *mexp, int cpu_map_idx, struct runtime_stat *st)
 {
 	struct expr_parse_ctx *pctx;
 	double ratio = 0.0;
@@ -943,7 +943,7 @@ double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_sta
 	if (!pctx)
 		return NAN;
 
-	if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, cpu, st) < 0)
+	if (prepare_metric(mexp->metric_events, mexp->metric_refs, pctx, cpu_map_idx, st) < 0)
 		goto out;
 
 	if (expr__parse(&ratio, pctx, mexp->metric_expr))
@@ -956,7 +956,7 @@ out:
 
 void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 				   struct evsel *evsel,
-				   double avg, int cpu,
+				   double avg, int cpu_map_idx,
 				   struct perf_stat_output_ctx *out,
 				   struct rblist *metric_events,
 				   struct runtime_stat *st)
@@ -975,7 +975,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 	if (config->iostat_run) {
 		iostat_print_metric(config, evsel, out);
 	} else if (evsel__match(evsel, HARDWARE, HW_INSTRUCTIONS)) {
-		total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
+		total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, &rsd);
 
 		if (total) {
 			ratio = avg / total;
@@ -985,11 +985,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 			print_metric(config, ctxp, NULL, NULL, "insn per cycle", 0);
 		}
 
-		total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT, cpu, &rsd);
+		total = runtime_stat_avg(st, STAT_STALLED_CYCLES_FRONT, cpu_map_idx, &rsd);
 
 		total = max(total, runtime_stat_avg(st,
 						    STAT_STALLED_CYCLES_BACK,
-						    cpu, &rsd));
+						    cpu_map_idx, &rsd));
 
 		if (total && avg) {
 			out->new_line(config, ctxp);
@@ -999,8 +999,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					ratio);
 		}
 	} else if (evsel__match(evsel, HARDWARE, HW_BRANCH_MISSES)) {
-		if (runtime_stat_n(st, STAT_BRANCHES, cpu, &rsd) != 0)
-			print_branch_misses(config, cpu, avg, out, st, &rsd);
+		if (runtime_stat_n(st, STAT_BRANCHES, cpu_map_idx, &rsd) != 0)
+			print_branch_misses(config, cpu_map_idx, avg, out, st, &rsd);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all branches", 0);
 	} else if (
@@ -1009,8 +1009,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
-		if (runtime_stat_n(st, STAT_L1_DCACHE, cpu, &rsd) != 0)
-			print_l1_dcache_misses(config, cpu, avg, out, st, &rsd);
+		if (runtime_stat_n(st, STAT_L1_DCACHE, cpu_map_idx, &rsd) != 0)
+			print_l1_dcache_misses(config, cpu_map_idx, avg, out, st, &rsd);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all L1-dcache accesses", 0);
 	} else if (
@@ -1019,8 +1019,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
-		if (runtime_stat_n(st, STAT_L1_ICACHE, cpu, &rsd) != 0)
-			print_l1_icache_misses(config, cpu, avg, out, st, &rsd);
+		if (runtime_stat_n(st, STAT_L1_ICACHE, cpu_map_idx, &rsd) != 0)
+			print_l1_icache_misses(config, cpu_map_idx, avg, out, st, &rsd);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all L1-icache accesses", 0);
 	} else if (
@@ -1029,8 +1029,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
-		if (runtime_stat_n(st, STAT_DTLB_CACHE, cpu, &rsd) != 0)
-			print_dtlb_cache_misses(config, cpu, avg, out, st, &rsd);
+		if (runtime_stat_n(st, STAT_DTLB_CACHE, cpu_map_idx, &rsd) != 0)
+			print_dtlb_cache_misses(config, cpu_map_idx, avg, out, st, &rsd);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all dTLB cache accesses", 0);
 	} else if (
@@ -1039,8 +1039,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
-		if (runtime_stat_n(st, STAT_ITLB_CACHE, cpu, &rsd) != 0)
-			print_itlb_cache_misses(config, cpu, avg, out, st, &rsd);
+		if (runtime_stat_n(st, STAT_ITLB_CACHE, cpu_map_idx, &rsd) != 0)
+			print_itlb_cache_misses(config, cpu_map_idx, avg, out, st, &rsd);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all iTLB cache accesses", 0);
 	} else if (
@@ -1049,27 +1049,27 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 					((PERF_COUNT_HW_CACHE_OP_READ) << 8) |
 					 ((PERF_COUNT_HW_CACHE_RESULT_MISS) << 16))) {
 
-		if (runtime_stat_n(st, STAT_LL_CACHE, cpu, &rsd) != 0)
-			print_ll_cache_misses(config, cpu, avg, out, st, &rsd);
+		if (runtime_stat_n(st, STAT_LL_CACHE, cpu_map_idx, &rsd) != 0)
+			print_ll_cache_misses(config, cpu_map_idx, avg, out, st, &rsd);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all LL-cache accesses", 0);
 	} else if (evsel__match(evsel, HARDWARE, HW_CACHE_MISSES)) {
-		total = runtime_stat_avg(st, STAT_CACHEREFS, cpu, &rsd);
+		total = runtime_stat_avg(st, STAT_CACHEREFS, cpu_map_idx, &rsd);
 
 		if (total)
 			ratio = avg * 100 / total;
 
-		if (runtime_stat_n(st, STAT_CACHEREFS, cpu, &rsd) != 0)
+		if (runtime_stat_n(st, STAT_CACHEREFS, cpu_map_idx, &rsd) != 0)
 			print_metric(config, ctxp, NULL, "%8.3f %%",
 				     "of all cache refs", ratio);
 		else
 			print_metric(config, ctxp, NULL, NULL, "of all cache refs", 0);
 	} else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_FRONTEND)) {
-		print_stalled_cycles_frontend(config, cpu, avg, out, st, &rsd);
+		print_stalled_cycles_frontend(config, cpu_map_idx, avg, out, st, &rsd);
 	} else if (evsel__match(evsel, HARDWARE, HW_STALLED_CYCLES_BACKEND)) {
-		print_stalled_cycles_backend(config, cpu, avg, out, st, &rsd);
+		print_stalled_cycles_backend(config, cpu_map_idx, avg, out, st, &rsd);
 	} else if (evsel__match(evsel, HARDWARE, HW_CPU_CYCLES)) {
-		total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd);
+		total = runtime_stat_avg(st, STAT_NSECS, cpu_map_idx, &rsd);
 
 		if (total) {
 			ratio = avg / total;
@@ -1078,7 +1078,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 			print_metric(config, ctxp, NULL, NULL, "Ghz", 0);
 		}
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX)) {
-		total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
+		total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, &rsd);
 
 		if (total)
 			print_metric(config, ctxp, NULL,
@@ -1088,8 +1088,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 			print_metric(config, ctxp, NULL, NULL, "transactional cycles",
 				     0);
 	} else if (perf_stat_evsel__is(evsel, CYCLES_IN_TX_CP)) {
-		total = runtime_stat_avg(st, STAT_CYCLES, cpu, &rsd);
-		total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
+		total = runtime_stat_avg(st, STAT_CYCLES, cpu_map_idx, &rsd);
+		total2 = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu_map_idx, &rsd);
 
 		if (total2 < avg)
 			total2 = avg;
@@ -1099,19 +1099,19 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		else
 			print_metric(config, ctxp, NULL, NULL, "aborted cycles", 0);
 	} else if (perf_stat_evsel__is(evsel, TRANSACTION_START)) {
-		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
+		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu_map_idx, &rsd);
 
 		if (avg)
 			ratio = total / avg;
 
-		if (runtime_stat_n(st, STAT_CYCLES_IN_TX, cpu, &rsd) != 0)
+		if (runtime_stat_n(st, STAT_CYCLES_IN_TX, cpu_map_idx, &rsd) != 0)
 			print_metric(config, ctxp, NULL, "%8.0f",
 				     "cycles / transaction", ratio);
 		else
 			print_metric(config, ctxp, NULL, NULL, "cycles / transaction",
 				      0);
 	} else if (perf_stat_evsel__is(evsel, ELISION_START)) {
-		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu, &rsd);
+		total = runtime_stat_avg(st, STAT_CYCLES_IN_TX, cpu_map_idx, &rsd);
 
 		if (avg)
 			ratio = total / avg;
@@ -1124,28 +1124,28 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		else
 			print_metric(config, ctxp, NULL, NULL, "CPUs utilized", 0);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_BUBBLES)) {
-		double fe_bound = td_fe_bound(cpu, st, &rsd);
+		double fe_bound = td_fe_bound(cpu_map_idx, st, &rsd);
 
 		if (fe_bound > 0.2)
 			color = PERF_COLOR_RED;
 		print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
 				fe_bound * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_RETIRED)) {
-		double retiring = td_retiring(cpu, st, &rsd);
+		double retiring = td_retiring(cpu_map_idx, st, &rsd);
 
 		if (retiring > 0.7)
 			color = PERF_COLOR_GREEN;
 		print_metric(config, ctxp, color, "%8.1f%%", "retiring",
 				retiring * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_RECOVERY_BUBBLES)) {
-		double bad_spec = td_bad_spec(cpu, st, &rsd);
+		double bad_spec = td_bad_spec(cpu_map_idx, st, &rsd);
 
 		if (bad_spec > 0.1)
 			color = PERF_COLOR_RED;
 		print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
 				bad_spec * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_SLOTS_ISSUED)) {
-		double be_bound = td_be_bound(cpu, st, &rsd);
+		double be_bound = td_be_bound(cpu_map_idx, st, &rsd);
 		const char *name = "backend bound";
 		static int have_recovery_bubbles = -1;
 
@@ -1158,14 +1158,14 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 
 		if (be_bound > 0.2)
 			color = PERF_COLOR_RED;
-		if (td_total_slots(cpu, st, &rsd) > 0)
+		if (td_total_slots(cpu_map_idx, st, &rsd) > 0)
 			print_metric(config, ctxp, color, "%8.1f%%", name,
 					be_bound * 100.);
 		else
 			print_metric(config, ctxp, NULL, NULL, name, 0);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_RETIRING) &&
-		   full_td(cpu, st, &rsd)) {
-		double retiring = td_metric_ratio(cpu,
+		   full_td(cpu_map_idx, st, &rsd)) {
+		double retiring = td_metric_ratio(cpu_map_idx,
 						  STAT_TOPDOWN_RETIRING, st,
 						  &rsd);
 		if (retiring > 0.7)
@@ -1173,8 +1173,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		print_metric(config, ctxp, color, "%8.1f%%", "retiring",
 				retiring * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FE_BOUND) &&
-		   full_td(cpu, st, &rsd)) {
-		double fe_bound = td_metric_ratio(cpu,
+		   full_td(cpu_map_idx, st, &rsd)) {
+		double fe_bound = td_metric_ratio(cpu_map_idx,
 						  STAT_TOPDOWN_FE_BOUND, st,
 						  &rsd);
 		if (fe_bound > 0.2)
@@ -1182,8 +1182,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		print_metric(config, ctxp, color, "%8.1f%%", "frontend bound",
 				fe_bound * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_BE_BOUND) &&
-		   full_td(cpu, st, &rsd)) {
-		double be_bound = td_metric_ratio(cpu,
+		   full_td(cpu_map_idx, st, &rsd)) {
+		double be_bound = td_metric_ratio(cpu_map_idx,
 						  STAT_TOPDOWN_BE_BOUND, st,
 						  &rsd);
 		if (be_bound > 0.2)
@@ -1191,8 +1191,8 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		print_metric(config, ctxp, color, "%8.1f%%", "backend bound",
 				be_bound * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_BAD_SPEC) &&
-		   full_td(cpu, st, &rsd)) {
-		double bad_spec = td_metric_ratio(cpu,
+		   full_td(cpu_map_idx, st, &rsd)) {
+		double bad_spec = td_metric_ratio(cpu_map_idx,
 						  STAT_TOPDOWN_BAD_SPEC, st,
 						  &rsd);
 		if (bad_spec > 0.1)
@@ -1200,11 +1200,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		print_metric(config, ctxp, color, "%8.1f%%", "bad speculation",
 				bad_spec * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_HEAVY_OPS) &&
-			full_td(cpu, st, &rsd) && (config->topdown_level > 1)) {
-		double retiring = td_metric_ratio(cpu,
+			full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
+		double retiring = td_metric_ratio(cpu_map_idx,
 						  STAT_TOPDOWN_RETIRING, st,
 						  &rsd);
-		double heavy_ops = td_metric_ratio(cpu,
+		double heavy_ops = td_metric_ratio(cpu_map_idx,
 						   STAT_TOPDOWN_HEAVY_OPS, st,
 						   &rsd);
 		double light_ops = retiring - heavy_ops;
@@ -1220,11 +1220,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		print_metric(config, ctxp, color, "%8.1f%%", "light operations",
 				light_ops * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_BR_MISPREDICT) &&
-			full_td(cpu, st, &rsd) && (config->topdown_level > 1)) {
-		double bad_spec = td_metric_ratio(cpu,
+			full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
+		double bad_spec = td_metric_ratio(cpu_map_idx,
 						  STAT_TOPDOWN_BAD_SPEC, st,
 						  &rsd);
-		double br_mis = td_metric_ratio(cpu,
+		double br_mis = td_metric_ratio(cpu_map_idx,
 						STAT_TOPDOWN_BR_MISPREDICT, st,
 						&rsd);
 		double m_clears = bad_spec - br_mis;
@@ -1240,11 +1240,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		print_metric(config, ctxp, color, "%8.1f%%", "machine clears",
 				m_clears * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_FETCH_LAT) &&
-			full_td(cpu, st, &rsd) && (config->topdown_level > 1)) {
-		double fe_bound = td_metric_ratio(cpu,
+			full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
+		double fe_bound = td_metric_ratio(cpu_map_idx,
 						  STAT_TOPDOWN_FE_BOUND, st,
 						  &rsd);
-		double fetch_lat = td_metric_ratio(cpu,
+		double fetch_lat = td_metric_ratio(cpu_map_idx,
 						   STAT_TOPDOWN_FETCH_LAT, st,
 						   &rsd);
 		double fetch_bw = fe_bound - fetch_lat;
@@ -1260,11 +1260,11 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 		print_metric(config, ctxp, color, "%8.1f%%", "fetch bandwidth",
 				fetch_bw * 100.);
 	} else if (perf_stat_evsel__is(evsel, TOPDOWN_MEM_BOUND) &&
-			full_td(cpu, st, &rsd) && (config->topdown_level > 1)) {
-		double be_bound = td_metric_ratio(cpu,
+			full_td(cpu_map_idx, st, &rsd) && (config->topdown_level > 1)) {
+		double be_bound = td_metric_ratio(cpu_map_idx,
 						  STAT_TOPDOWN_BE_BOUND, st,
 						  &rsd);
-		double mem_bound = td_metric_ratio(cpu,
+		double mem_bound = td_metric_ratio(cpu_map_idx,
 						   STAT_TOPDOWN_MEM_BOUND, st,
 						   &rsd);
 		double core_bound = be_bound - mem_bound;
@@ -1281,12 +1281,12 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 				core_bound * 100.);
 	} else if (evsel->metric_expr) {
 		generic_metric(config, evsel->metric_expr, evsel->metric_events, NULL,
-				evsel->name, evsel->metric_name, NULL, 1, cpu, out, st);
-	} else if (runtime_stat_n(st, STAT_NSECS, cpu, &rsd) != 0) {
+				evsel->name, evsel->metric_name, NULL, 1, cpu_map_idx, out, st);
+	} else if (runtime_stat_n(st, STAT_NSECS, cpu_map_idx, &rsd) != 0) {
 		char unit = ' ';
 		char unit_buf[10] = "/sec";
 
-		total = runtime_stat_avg(st, STAT_NSECS, cpu, &rsd);
+		total = runtime_stat_avg(st, STAT_NSECS, cpu_map_idx, &rsd);
 		if (total)
 			ratio = convert_unit_double(1000000000.0 * avg / total, &unit);
 
@@ -1294,7 +1294,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 			snprintf(unit_buf, sizeof(unit_buf), "%c/sec", unit);
 		print_metric(config, ctxp, NULL, "%8.3f", unit_buf, ratio);
 	} else if (perf_stat_evsel__is(evsel, SMI_NUM)) {
-		print_smi_cost(config, cpu, out, st, &rsd);
+		print_smi_cost(config, cpu_map_idx, out, st, &rsd);
 	} else {
 		num = 0;
 	}
@@ -1307,7 +1307,7 @@ void perf_stat__print_shadow_stats(struct perf_stat_config *config,
 				out->new_line(config, ctxp);
 			generic_metric(config, mexp->metric_expr, mexp->metric_events,
 					mexp->metric_refs, evsel->name, mexp->metric_name,
-					mexp->metric_unit, mexp->runtime, cpu, out, st);
+					mexp->metric_unit, mexp->runtime, cpu_map_idx, out, st);
 		}
 	}
 	if (num == 0)
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 09ea334586f2..ee6f03481215 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -152,11 +152,13 @@ static void evsel__free_stat_priv(struct evsel *evsel)
 	zfree(&evsel->stats);
 }
 
-static int evsel__alloc_prev_raw_counts(struct evsel *evsel, int ncpus, int nthreads)
+static int evsel__alloc_prev_raw_counts(struct evsel *evsel)
 {
+	int cpu_map_nr = evsel__nr_cpus(evsel);
+	int nthreads = perf_thread_map__nr(evsel->core.threads);
 	struct perf_counts *counts;
 
-	counts = perf_counts__new(ncpus, nthreads);
+	counts = perf_counts__new(cpu_map_nr, nthreads);
 	if (counts)
 		evsel->prev_raw_counts = counts;
 
@@ -177,12 +179,9 @@ static void evsel__reset_prev_raw_counts(struct evsel *evsel)
 
 static int evsel__alloc_stats(struct evsel *evsel, bool alloc_raw)
 {
-	int ncpus = evsel__nr_cpus(evsel);
-	int nthreads = perf_thread_map__nr(evsel->core.threads);
-
 	if (evsel__alloc_stat_priv(evsel) < 0 ||
-	    evsel__alloc_counts(evsel, ncpus, nthreads) < 0 ||
-	    (alloc_raw && evsel__alloc_prev_raw_counts(evsel, ncpus, nthreads) < 0))
+	    evsel__alloc_counts(evsel) < 0 ||
+	    (alloc_raw && evsel__alloc_prev_raw_counts(evsel) < 0))
 		return -ENOMEM;
 
 	return 0;
@@ -293,11 +292,12 @@ static bool pkg_id_equal(const void *__key1, const void *__key2,
 	return *key1 == *key2;
 }
 
-static int check_per_pkg(struct evsel *counter,
-			 struct perf_counts_values *vals, int cpu, bool *skip)
+static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals,
+			 int cpu_map_idx, bool *skip)
 {
 	struct hashmap *mask = counter->per_pkg_mask;
 	struct perf_cpu_map *cpus = evsel__cpus(counter);
+	struct perf_cpu cpu = perf_cpu_map__cpu(cpus, cpu_map_idx);
 	int s, d, ret = 0;
 	uint64_t *key;
 
@@ -328,7 +328,7 @@ static int check_per_pkg(struct evsel *counter,
 	if (!(vals->run && vals->ena))
 		return 0;
 
-	s = cpu_map__get_socket(cpus, cpu, NULL).socket;
+	s = cpu__get_socket_id(cpu);
 	if (s < 0)
 		return -1;
 
@@ -336,7 +336,7 @@ static int check_per_pkg(struct evsel *counter,
 	 * On multi-die system, die_id > 0. On no-die system, die_id = 0.
 	 * We use hashmap(socket, die) to check the used socket+die pair.
 	 */
-	d = cpu_map__get_die(cpus, cpu, NULL).die;
+	d = cpu__get_die_id(cpu);
 	if (d < 0)
 		return -1;
 
@@ -345,9 +345,10 @@ static int check_per_pkg(struct evsel *counter,
 		return -ENOMEM;
 
 	*key = (uint64_t)d << 32 | s;
-	if (hashmap__find(mask, (void *)key, NULL))
+	if (hashmap__find(mask, (void *)key, NULL)) {
 		*skip = true;
-	else
+		free(key);
+	} else
 		ret = hashmap__add(mask, (void *)key, (void *)1);
 
 	return ret;
@@ -355,14 +356,14 @@ static int check_per_pkg(struct evsel *counter,
 
 static int
 process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
-		       int cpu, int thread,
+		       int cpu_map_idx, int thread,
 		       struct perf_counts_values *count)
 {
 	struct perf_counts_values *aggr = &evsel->counts->aggr;
 	static struct perf_counts_values zero;
 	bool skip = false;
 
-	if (check_per_pkg(evsel, count, cpu, &skip)) {
+	if (check_per_pkg(evsel, count, cpu_map_idx, &skip)) {
 		pr_err("failed to read per-pkg counter\n");
 		return -1;
 	}
@@ -378,11 +379,11 @@ process_counter_values(struct perf_stat_config *config, struct evsel *evsel,
 	case AGGR_NODE:
 	case AGGR_NONE:
 		if (!evsel->snapshot)
-			evsel__compute_deltas(evsel, cpu, thread, count);
+			evsel__compute_deltas(evsel, cpu_map_idx, thread, count);
 		perf_counts_values__scale(count, config->scale, NULL);
 		if ((config->aggr_mode == AGGR_NONE) && (!evsel->percore)) {
 			perf_stat__update_shadow_stats(evsel, count->val,
-						       cpu, &rt_stat);
+						       cpu_map_idx, &rt_stat);
 		}
 
 		if (config->aggr_mode == AGGR_THREAD) {
@@ -411,15 +412,15 @@ static int process_counter_maps(struct perf_stat_config *config,
 {
 	int nthreads = perf_thread_map__nr(counter->core.threads);
 	int ncpus = evsel__nr_cpus(counter);
-	int cpu, thread;
+	int idx, thread;
 
 	if (counter->core.system_wide)
 		nthreads = 1;
 
 	for (thread = 0; thread < nthreads; thread++) {
-		for (cpu = 0; cpu < ncpus; cpu++) {
-			if (process_counter_values(config, counter, cpu, thread,
-						   perf_counts(counter->counts, cpu, thread)))
+		for (idx = 0; idx < ncpus; idx++) {
+			if (process_counter_values(config, counter, idx, thread,
+						   perf_counts(counter->counts, idx, thread)))
 				return -1;
 		}
 	}
@@ -531,7 +532,7 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp)
 int create_perf_stat_counter(struct evsel *evsel,
 			     struct perf_stat_config *config,
 			     struct target *target,
-			     int cpu)
+			     int cpu_map_idx)
 {
 	struct perf_event_attr *attr = &evsel->core.attr;
 	struct evsel *leader = evsel__leader(evsel);
@@ -585,7 +586,7 @@ int create_perf_stat_counter(struct evsel *evsel,
 	}
 
 	if (target__has_cpu(target) && !target__has_per_thread(target))
-		return evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu);
+		return evsel__open_per_cpu(evsel, evsel__cpus(evsel), cpu_map_idx);
 
 	return evsel__open_per_thread(evsel, evsel->core.threads);
 }
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index 32c8527de347..335d19cc3063 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -108,8 +108,7 @@ struct runtime_stat {
 	struct rblist value_list;
 };
 
-typedef struct aggr_cpu_id (*aggr_get_id_t)(struct perf_stat_config *config,
-			     struct perf_cpu_map *m, int cpu);
+typedef struct aggr_cpu_id (*aggr_get_id_t)(struct perf_stat_config *config, struct perf_cpu cpu);
 
 struct perf_stat_config {
 	enum aggr_mode		 aggr_mode;
@@ -209,7 +208,7 @@ void perf_stat__init_shadow_stats(void);
 void perf_stat__reset_shadow_stats(void);
 void perf_stat__reset_shadow_per_stat(struct runtime_stat *st);
 void perf_stat__update_shadow_stats(struct evsel *counter, u64 count,
-				    int cpu, struct runtime_stat *st);
+				    int cpu_map_idx, struct runtime_stat *st);
 struct perf_stat_output_ctx {
 	void *ctx;
 	print_metric_t print_metric;
@@ -249,10 +248,10 @@ size_t perf_event__fprintf_stat_config(union perf_event *event, FILE *fp);
 int create_perf_stat_counter(struct evsel *evsel,
 			     struct perf_stat_config *config,
 			     struct target *target,
-			     int cpu);
+			     int cpu_map_idx);
 void evlist__print_counters(struct evlist *evlist, struct perf_stat_config *config,
 			    struct target *_target, struct timespec *ts, int argc, const char **argv);
 
 struct metric_expr;
-double test_generic_metric(struct metric_expr *mexp, int cpu, struct runtime_stat *st);
+double test_generic_metric(struct metric_expr *mexp, int cpu_map_idx, struct runtime_stat *st);
 #endif
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 96f941e01681..4c9f211249db 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -728,7 +728,7 @@ static int str_to_bitmap(char *s, cpumask_t *b, int nr_cpus)
 	int i;
 	int ret = 0;
 	struct perf_cpu_map *m;
-	int c;
+	struct perf_cpu c;
 
 	m = perf_cpu_map__new(s);
 	if (!m)
@@ -736,12 +736,12 @@ static int str_to_bitmap(char *s, cpumask_t *b, int nr_cpus)
 
 	for (i = 0; i < m->nr; i++) {
 		c = m->map[i];
-		if (c >= nr_cpus) {
+		if (c.cpu >= nr_cpus) {
 			ret = -1;
 			break;
 		}
 
-		set_bit(c, cpumask_bits(b));
+		set_bit(c.cpu, cpumask_bits(b));
 	}
 
 	perf_cpu_map__put(m);
diff --git a/tools/perf/util/synthetic-events.c b/tools/perf/util/synthetic-events.c
index 198982109f0f..c9ba8050cc2b 100644
--- a/tools/perf/util/synthetic-events.c
+++ b/tools/perf/util/synthetic-events.c
@@ -1191,7 +1191,7 @@ static void synthesize_cpus(struct cpu_map_entries *cpus,
 	cpus->nr = map->nr;
 
 	for (i = 0; i < map->nr; i++)
-		cpus->cpu[i] = map->map[i];
+		cpus->cpu[i] = map->map[i].cpu;
 }
 
 static void synthesize_mask(struct perf_record_record_cpu_map *mask,
@@ -1203,7 +1203,7 @@ static void synthesize_mask(struct perf_record_record_cpu_map *mask,
 	mask->long_size = sizeof(long);
 
 	for (i = 0; i < map->nr; i++)
-		set_bit(map->map[i], mask->mask);
+		set_bit(map->map[i].cpu, mask->mask);
 }
 
 static size_t cpus_size(struct perf_cpu_map *map)
@@ -1219,7 +1219,7 @@ static size_t mask_size(struct perf_cpu_map *map, int *max)
 
 	for (i = 0; i < map->nr; i++) {
 		/* bit position of the cpu is + 1 */
-		int bit = map->map[i] + 1;
+		int bit = map->map[i].cpu + 1;
 
 		if (bit > *max)
 			*max = bit;
@@ -1354,7 +1354,7 @@ int perf_event__synthesize_stat_config(struct perf_tool *tool,
 }
 
 int perf_event__synthesize_stat(struct perf_tool *tool,
-				u32 cpu, u32 thread, u64 id,
+				struct perf_cpu cpu, u32 thread, u64 id,
 				struct perf_counts_values *count,
 				perf_event__handler_t process,
 				struct machine *machine)
@@ -1366,7 +1366,7 @@ int perf_event__synthesize_stat(struct perf_tool *tool,
 	event.header.misc = 0;
 
 	event.id        = id;
-	event.cpu       = cpu;
+	event.cpu       = cpu.cpu;
 	event.thread    = thread;
 	event.val       = count->val;
 	event.ena       = count->ena;
@@ -1763,7 +1763,7 @@ int perf_event__synthesize_id_index(struct perf_tool *tool, perf_event__handler_
 			}
 
 			e->idx = sid->idx;
-			e->cpu = sid->cpu;
+			e->cpu = sid->cpu.cpu;
 			e->tid = sid->tid;
 		}
 	}
diff --git a/tools/perf/util/synthetic-events.h b/tools/perf/util/synthetic-events.h
index c931433bacbf..78a0450db164 100644
--- a/tools/perf/util/synthetic-events.h
+++ b/tools/perf/util/synthetic-events.h
@@ -6,6 +6,7 @@
 #include <sys/types.h> // pid_t
 #include <linux/compiler.h>
 #include <linux/types.h>
+#include <perf/cpumap.h>
 
 struct auxtrace_record;
 struct dso;
@@ -63,7 +64,7 @@ int perf_event__synthesize_sample(union perf_event *event, u64 type, u64 read_fo
 int perf_event__synthesize_stat_config(struct perf_tool *tool, struct perf_stat_config *config, perf_event__handler_t process, struct machine *machine);
 int perf_event__synthesize_stat_events(struct perf_stat_config *config, struct perf_tool *tool, struct evlist *evlist, perf_event__handler_t process, bool attrs);
 int perf_event__synthesize_stat_round(struct perf_tool *tool, u64 time, u64 type, perf_event__handler_t process, struct machine *machine);
-int perf_event__synthesize_stat(struct perf_tool *tool, u32 cpu, u32 thread, u64 id, struct perf_counts_values *count, perf_event__handler_t process, struct machine *machine);
+int perf_event__synthesize_stat(struct perf_tool *tool, struct perf_cpu cpu, u32 thread, u64 id, struct perf_counts_values *count, perf_event__handler_t process, struct machine *machine);
 int perf_event__synthesize_thread_map2(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine);
 int perf_event__synthesize_thread_map(struct perf_tool *tool, struct perf_thread_map *threads, perf_event__handler_t process, struct machine *machine, bool needs_mmap, bool mmap_data);
 int perf_event__synthesize_threads(struct perf_tool *tool, perf_event__handler_t process, struct machine *machine, bool needs_mmap, bool mmap_data, unsigned int nr_threads_synthesize);
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index df3c4671be72..fb4f6616b5fa 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -416,3 +416,18 @@ char *perf_exe(char *buf, int len)
 	}
 	return strcpy(buf, "perf");
 }
+
+void perf_debuginfod_setup(struct perf_debuginfod *di)
+{
+	/*
+	 * By default '!di->set' we clear DEBUGINFOD_URLS, so debuginfod
+	 * processing is not triggered, otherwise we set it to 'di->urls'
+	 * value. If 'di->urls' is "system" we keep DEBUGINFOD_URLS value.
+	 */
+	if (!di->set)
+		setenv("DEBUGINFOD_URLS", "", 1);
+	else if (di->urls && strcmp(di->urls, "system"))
+		setenv("DEBUGINFOD_URLS", di->urls, 1);
+
+	pr_debug("DEBUGINFOD_URLS=%s\n", getenv("DEBUGINFOD_URLS"));
+}
diff --git a/tools/perf/util/util.h b/tools/perf/util/util.h
index 9f0d36ba77f2..7b625cbd2dd8 100644
--- a/tools/perf/util/util.h
+++ b/tools/perf/util/util.h
@@ -11,6 +11,9 @@
 #include <stddef.h>
 #include <linux/compiler.h>
 #include <sys/types.h>
+#ifndef __cplusplus
+#include <internal/cpumap.h>
+#endif
 
 /* General helper functions */
 void usage(const char *err) __noreturn;
@@ -66,6 +69,12 @@ extern bool test_attr__enabled;
 void test_attr__ready(void);
 void test_attr__init(void);
 struct perf_event_attr;
-void test_attr__open(struct perf_event_attr *attr, pid_t pid, int cpu,
+void test_attr__open(struct perf_event_attr *attr, pid_t pid, struct perf_cpu cpu,
 		     int fd, int group_fd, unsigned long flags);
+
+struct perf_debuginfod {
+	const char	*urls;
+	bool		 set;
+};
+void perf_debuginfod_setup(struct perf_debuginfod *di);
 #endif /* GIT_COMPAT_UTIL_H */