Merge branch 'perf-tools-next' of git://git.kernel.org/pub/scm/linux/kernel/git/perf/perf-tools-next.gitNotice: this object is not reachable from any branch.

Notice: this object is not reachable from any branch.

230 files changed, 9699 insertions, 4548 deletions

diff --git a/MAINTAINERS b/MAINTAINERS
index 12bfd1e26a38a0..bcd94dc0ca299f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17310,6 +17310,7 @@ R:	Alexander Shishkin <alexander.shishkin@linux.intel.com>
 R:	Jiri Olsa <jolsa@kernel.org>
 R:	Ian Rogers <irogers@google.com>
 R:	Adrian Hunter <adrian.hunter@intel.com>
+R:	"Liang, Kan" <kan.liang@linux.intel.com>
 L:	linux-perf-users@vger.kernel.org
 L:	linux-kernel@vger.kernel.org
 S:	Supported
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index a38f8f9ba65729..3c7434329661c6 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -461,11 +461,15 @@
 
 /*
  * Extended auxiliary flags: Linux defined - for features scattered in various
- * CPUID levels like 0x80000022, etc.
+ * CPUID levels like 0x80000022, etc and Linux defined features.
  *
  * Reuse free bits when adding new feature flags!
  */
 #define X86_FEATURE_AMD_LBR_PMC_FREEZE	(21*32+ 0) /* AMD LBR and PMC Freeze */
+#define X86_FEATURE_CLEAR_BHB_LOOP	(21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */
+#define X86_FEATURE_BHI_CTRL		(21*32+ 2) /* "" BHI_DIS_S HW control available */
+#define X86_FEATURE_CLEAR_BHB_HW	(21*32+ 3) /* "" BHI_DIS_S HW control enabled */
+#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */
 
 /*
  * BUG word(s)
@@ -515,4 +519,5 @@
 #define X86_BUG_SRSO			X86_BUG(1*32 + 0) /* AMD SRSO bug */
 #define X86_BUG_DIV0			X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */
 #define X86_BUG_RFDS			X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */
+#define X86_BUG_BHI			X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/tools/arch/x86/include/asm/msr-index.h b/tools/arch/x86/include/asm/msr-index.h
index 05956bd8bacf50..e72c2b87295799 100644
--- a/tools/arch/x86/include/asm/msr-index.h
+++ b/tools/arch/x86/include/asm/msr-index.h
@@ -61,10 +61,13 @@
 #define SPEC_CTRL_SSBD			BIT(SPEC_CTRL_SSBD_SHIFT)	/* Speculative Store Bypass Disable */
 #define SPEC_CTRL_RRSBA_DIS_S_SHIFT	6	   /* Disable RRSBA behavior */
 #define SPEC_CTRL_RRSBA_DIS_S		BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT)
+#define SPEC_CTRL_BHI_DIS_S_SHIFT	10	   /* Disable Branch History Injection behavior */
+#define SPEC_CTRL_BHI_DIS_S		BIT(SPEC_CTRL_BHI_DIS_S_SHIFT)
 
 /* A mask for bits which the kernel toggles when controlling mitigations */
 #define SPEC_CTRL_MITIGATIONS_MASK	(SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \
-							| SPEC_CTRL_RRSBA_DIS_S)
+							| SPEC_CTRL_RRSBA_DIS_S \
+							| SPEC_CTRL_BHI_DIS_S)
 
 #define MSR_IA32_PRED_CMD		0x00000049 /* Prediction Command */
 #define PRED_CMD_IBPB			BIT(0)	   /* Indirect Branch Prediction Barrier */
@@ -163,6 +166,10 @@
 						 * are restricted to targets in
 						 * kernel.
 						 */
+#define ARCH_CAP_BHI_NO			BIT(20)	/*
+						 * CPU is not affected by Branch
+						 * History Injection.
+						 */
 #define ARCH_CAP_PBRSB_NO		BIT(24)	/*
 						 * Not susceptible to Post-Barrier
 						 * Return Stack Buffer Predictions.
diff --git a/tools/include/linux/bits.h b/tools/include/linux/bits.h
index 7c0cf5031abe87..0eb24d21aac214 100644
--- a/tools/include/linux/bits.h
+++ b/tools/include/linux/bits.h
@@ -4,6 +4,7 @@
 
 #include <linux/const.h>
 #include <vdso/bits.h>
+#include <uapi/linux/bits.h>
 #include <asm/bitsperlong.h>
 
 #define BIT_MASK(nr)		(UL(1) << ((nr) % BITS_PER_LONG))
@@ -30,15 +31,8 @@
 #define GENMASK_INPUT_CHECK(h, l) 0
 #endif
 
-#define __GENMASK(h, l) \
-	(((~UL(0)) - (UL(1) << (l)) + 1) & \
-	 (~UL(0) >> (BITS_PER_LONG - 1 - (h))))
 #define GENMASK(h, l) \
 	(GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l))
-
-#define __GENMASK_ULL(h, l) \
-	(((~ULL(0)) - (ULL(1) << (l)) + 1) & \
-	 (~ULL(0) >> (BITS_PER_LONG_LONG - 1 - (h))))
 #define GENMASK_ULL(h, l) \
 	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l))
 
diff --git a/tools/include/uapi/asm-generic/bitsperlong.h b/tools/include/uapi/asm-generic/bitsperlong.h
index 352cb81947b876..fadb3f857f2855 100644
--- a/tools/include/uapi/asm-generic/bitsperlong.h
+++ b/tools/include/uapi/asm-generic/bitsperlong.h
@@ -24,4 +24,8 @@
 #endif
 #endif
 
+#ifndef __BITS_PER_LONG_LONG
+#define __BITS_PER_LONG_LONG 64
+#endif
+
 #endif /* _UAPI__ASM_GENERIC_BITS_PER_LONG */
diff --git a/tools/include/uapi/asm-generic/fcntl.h b/tools/include/uapi/asm-generic/fcntl.h
deleted file mode 100644
index 1c7a0f6632c09e..00000000000000
--- a/tools/include/uapi/asm-generic/fcntl.h
+++ /dev/null
@@ -1,221 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _ASM_GENERIC_FCNTL_H
-#define _ASM_GENERIC_FCNTL_H
-
-#include <linux/types.h>
-
-/*
- * FMODE_EXEC is 0x20
- * FMODE_NONOTIFY is 0x4000000
- * These cannot be used by userspace O_* until internal and external open
- * flags are split.
- * -Eric Paris
- */
-
-/*
- * When introducing new O_* bits, please check its uniqueness in fcntl_init().
- */
-
-#define O_ACCMODE	00000003
-#define O_RDONLY	00000000
-#define O_WRONLY	00000001
-#define O_RDWR		00000002
-#ifndef O_CREAT
-#define O_CREAT		00000100	/* not fcntl */
-#endif
-#ifndef O_EXCL
-#define O_EXCL		00000200	/* not fcntl */
-#endif
-#ifndef O_NOCTTY
-#define O_NOCTTY	00000400	/* not fcntl */
-#endif
-#ifndef O_TRUNC
-#define O_TRUNC		00001000	/* not fcntl */
-#endif
-#ifndef O_APPEND
-#define O_APPEND	00002000
-#endif
-#ifndef O_NONBLOCK
-#define O_NONBLOCK	00004000
-#endif
-#ifndef O_DSYNC
-#define O_DSYNC		00010000	/* used to be O_SYNC, see below */
-#endif
-#ifndef FASYNC
-#define FASYNC		00020000	/* fcntl, for BSD compatibility */
-#endif
-#ifndef O_DIRECT
-#define O_DIRECT	00040000	/* direct disk access hint */
-#endif
-#ifndef O_LARGEFILE
-#define O_LARGEFILE	00100000
-#endif
-#ifndef O_DIRECTORY
-#define O_DIRECTORY	00200000	/* must be a directory */
-#endif
-#ifndef O_NOFOLLOW
-#define O_NOFOLLOW	00400000	/* don't follow links */
-#endif
-#ifndef O_NOATIME
-#define O_NOATIME	01000000
-#endif
-#ifndef O_CLOEXEC
-#define O_CLOEXEC	02000000	/* set close_on_exec */
-#endif
-
-/*
- * Before Linux 2.6.33 only O_DSYNC semantics were implemented, but using
- * the O_SYNC flag.  We continue to use the existing numerical value
- * for O_DSYNC semantics now, but using the correct symbolic name for it.
- * This new value is used to request true Posix O_SYNC semantics.  It is
- * defined in this strange way to make sure applications compiled against
- * new headers get at least O_DSYNC semantics on older kernels.
- *
- * This has the nice side-effect that we can simply test for O_DSYNC
- * wherever we do not care if O_DSYNC or O_SYNC is used.
- *
- * Note: __O_SYNC must never be used directly.
- */
-#ifndef O_SYNC
-#define __O_SYNC	04000000
-#define O_SYNC		(__O_SYNC|O_DSYNC)
-#endif
-
-#ifndef O_PATH
-#define O_PATH		010000000
-#endif
-
-#ifndef __O_TMPFILE
-#define __O_TMPFILE	020000000
-#endif
-
-/* a horrid kludge trying to make sure that this will fail on old kernels */
-#define O_TMPFILE (__O_TMPFILE | O_DIRECTORY)
-
-#ifndef O_NDELAY
-#define O_NDELAY	O_NONBLOCK
-#endif
-
-#define F_DUPFD		0	/* dup */
-#define F_GETFD		1	/* get close_on_exec */
-#define F_SETFD		2	/* set/clear close_on_exec */
-#define F_GETFL		3	/* get file->f_flags */
-#define F_SETFL		4	/* set file->f_flags */
-#ifndef F_GETLK
-#define F_GETLK		5
-#define F_SETLK		6
-#define F_SETLKW	7
-#endif
-#ifndef F_SETOWN
-#define F_SETOWN	8	/* for sockets. */
-#define F_GETOWN	9	/* for sockets. */
-#endif
-#ifndef F_SETSIG
-#define F_SETSIG	10	/* for sockets. */
-#define F_GETSIG	11	/* for sockets. */
-#endif
-
-#if __BITS_PER_LONG == 32 || defined(__KERNEL__)
-#ifndef F_GETLK64
-#define F_GETLK64	12	/*  using 'struct flock64' */
-#define F_SETLK64	13
-#define F_SETLKW64	14
-#endif
-#endif /* __BITS_PER_LONG == 32 || defined(__KERNEL__) */
-
-#ifndef F_SETOWN_EX
-#define F_SETOWN_EX	15
-#define F_GETOWN_EX	16
-#endif
-
-#ifndef F_GETOWNER_UIDS
-#define F_GETOWNER_UIDS	17
-#endif
-
-/*
- * Open File Description Locks
- *
- * Usually record locks held by a process are released on *any* close and are
- * not inherited across a fork().
- *
- * These cmd values will set locks that conflict with process-associated
- * record  locks, but are "owned" by the open file description, not the
- * process. This means that they are inherited across fork() like BSD (flock)
- * locks, and they are only released automatically when the last reference to
- * the open file against which they were acquired is put.
- */
-#define F_OFD_GETLK	36
-#define F_OFD_SETLK	37
-#define F_OFD_SETLKW	38
-
-#define F_OWNER_TID	0
-#define F_OWNER_PID	1
-#define F_OWNER_PGRP	2
-
-struct f_owner_ex {
-	int	type;
-	__kernel_pid_t	pid;
-};
-
-/* for F_[GET|SET]FL */
-#define FD_CLOEXEC	1	/* actually anything with low bit set goes */
-
-/* for posix fcntl() and lockf() */
-#ifndef F_RDLCK
-#define F_RDLCK		0
-#define F_WRLCK		1
-#define F_UNLCK		2
-#endif
-
-/* for old implementation of bsd flock () */
-#ifndef F_EXLCK
-#define F_EXLCK		4	/* or 3 */
-#define F_SHLCK		8	/* or 4 */
-#endif
-
-/* operations for bsd flock(), also used by the kernel implementation */
-#define LOCK_SH		1	/* shared lock */
-#define LOCK_EX		2	/* exclusive lock */
-#define LOCK_NB		4	/* or'd with one of the above to prevent
-				   blocking */
-#define LOCK_UN		8	/* remove lock */
-
-/*
- * LOCK_MAND support has been removed from the kernel. We leave the symbols
- * here to not break legacy builds, but these should not be used in new code.
- */
-#define LOCK_MAND	32	/* This is a mandatory flock ... */
-#define LOCK_READ	64	/* which allows concurrent read operations */
-#define LOCK_WRITE	128	/* which allows concurrent write operations */
-#define LOCK_RW		192	/* which allows concurrent read & write ops */
-
-#define F_LINUX_SPECIFIC_BASE	1024
-
-#ifndef HAVE_ARCH_STRUCT_FLOCK
-struct flock {
-	short	l_type;
-	short	l_whence;
-	__kernel_off_t	l_start;
-	__kernel_off_t	l_len;
-	__kernel_pid_t	l_pid;
-#ifdef	__ARCH_FLOCK_EXTRA_SYSID
-	__ARCH_FLOCK_EXTRA_SYSID
-#endif
-#ifdef	__ARCH_FLOCK_PAD
-	__ARCH_FLOCK_PAD
-#endif
-};
-
-struct flock64 {
-	short  l_type;
-	short  l_whence;
-	__kernel_loff_t l_start;
-	__kernel_loff_t l_len;
-	__kernel_pid_t  l_pid;
-#ifdef	__ARCH_FLOCK64_PAD
-	__ARCH_FLOCK64_PAD
-#endif
-};
-#endif /* HAVE_ARCH_STRUCT_FLOCK */
-
-#endif /* _ASM_GENERIC_FCNTL_H */
diff --git a/tools/include/uapi/linux/bits.h b/tools/include/uapi/linux/bits.h
new file mode 100644
index 00000000000000..3c2a101986a314
--- /dev/null
+++ b/tools/include/uapi/linux/bits.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+/* bits.h: Macros for dealing with bitmasks.  */
+
+#ifndef _UAPI_LINUX_BITS_H
+#define _UAPI_LINUX_BITS_H
+
+#define __GENMASK(h, l) \
+        (((~_UL(0)) - (_UL(1) << (l)) + 1) & \
+         (~_UL(0) >> (__BITS_PER_LONG - 1 - (h))))
+
+#define __GENMASK_ULL(h, l) \
+        (((~_ULL(0)) - (_ULL(1) << (l)) + 1) & \
+         (~_ULL(0) >> (__BITS_PER_LONG_LONG - 1 - (h))))
+
+#endif /* _UAPI_LINUX_BITS_H */
diff --git a/tools/include/uapi/linux/openat2.h b/tools/include/uapi/linux/openat2.h
deleted file mode 100644
index a5feb760494879..00000000000000
--- a/tools/include/uapi/linux/openat2.h
+++ /dev/null
@@ -1,43 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-#ifndef _UAPI_LINUX_OPENAT2_H
-#define _UAPI_LINUX_OPENAT2_H
-
-#include <linux/types.h>
-
-/*
- * Arguments for how openat2(2) should open the target path. If only @flags and
- * @mode are non-zero, then openat2(2) operates very similarly to openat(2).
- *
- * However, unlike openat(2), unknown or invalid bits in @flags result in
- * -EINVAL rather than being silently ignored. @mode must be zero unless one of
- * {O_CREAT, O_TMPFILE} are set.
- *
- * @flags: O_* flags.
- * @mode: O_CREAT/O_TMPFILE file mode.
- * @resolve: RESOLVE_* flags.
- */
-struct open_how {
-	__u64 flags;
-	__u64 mode;
-	__u64 resolve;
-};
-
-/* how->resolve flags for openat2(2). */
-#define RESOLVE_NO_XDEV		0x01 /* Block mount-point crossings
-					(includes bind-mounts). */
-#define RESOLVE_NO_MAGICLINKS	0x02 /* Block traversal through procfs-style
-					"magic-links". */
-#define RESOLVE_NO_SYMLINKS	0x04 /* Block traversal through all symlinks
-					(implies OEXT_NO_MAGICLINKS) */
-#define RESOLVE_BENEATH		0x08 /* Block "lexical" trickery like
-					"..", symlinks, and absolute
-					paths which escape the dirfd. */
-#define RESOLVE_IN_ROOT		0x10 /* Make all jumps to "/" and ".."
-					be scoped inside the dirfd
-					(similar to chroot(2)). */
-#define RESOLVE_CACHED		0x20 /* Only complete if resolution can be
-					completed through cached lookup. May
-					return -EAGAIN if that's not
-					possible. */
-
-#endif /* _UAPI_LINUX_OPENAT2_H */
diff --git a/tools/lib/perf/cpumap.c b/tools/lib/perf/cpumap.c
index 4adcd7920d033d..cae799ad44e136 100644
--- a/tools/lib/perf/cpumap.c
+++ b/tools/lib/perf/cpumap.c
@@ -18,9 +18,13 @@ void perf_cpu_map__set_nr(struct perf_cpu_map *map, int nr_cpus)
 
 struct perf_cpu_map *perf_cpu_map__alloc(int nr_cpus)
 {
-	RC_STRUCT(perf_cpu_map) *cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus);
+	RC_STRUCT(perf_cpu_map) *cpus;
 	struct perf_cpu_map *result;
 
+	if (nr_cpus == 0)
+		return NULL;
+
+	cpus = malloc(sizeof(*cpus) + sizeof(struct perf_cpu) * nr_cpus);
 	if (ADD_RC_CHK(result, cpus)) {
 		cpus->nr = nr_cpus;
 		refcount_set(&cpus->refcnt, 1);
@@ -316,6 +320,19 @@ bool perf_cpu_map__has_any_cpu_or_is_empty(const struct perf_cpu_map *map)
 	return map ? __perf_cpu_map__cpu(map, 0).cpu == -1 : true;
 }
 
+bool perf_cpu_map__is_any_cpu_or_is_empty(const struct perf_cpu_map *map)
+{
+	if (!map)
+		return true;
+
+	return __perf_cpu_map__nr(map) == 1 && __perf_cpu_map__cpu(map, 0).cpu == -1;
+}
+
+bool perf_cpu_map__is_empty(const struct perf_cpu_map *map)
+{
+	return map == NULL;
+}
+
 int perf_cpu_map__idx(const struct perf_cpu_map *cpus, struct perf_cpu cpu)
 {
 	int low, high;
@@ -372,6 +389,20 @@ bool perf_cpu_map__has_any_cpu(const struct perf_cpu_map *map)
 	return map && __perf_cpu_map__cpu(map, 0).cpu == -1;
 }
 
+struct perf_cpu perf_cpu_map__min(const struct perf_cpu_map *map)
+{
+	struct perf_cpu cpu, result = {
+		.cpu = -1
+	};
+	int idx;
+
+	perf_cpu_map__for_each_cpu_skip_any(cpu, idx, map) {
+		result = cpu;
+		break;
+	}
+	return result;
+}
+
 struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map)
 {
 	struct perf_cpu result = {
diff --git a/tools/lib/perf/include/perf/cpumap.h b/tools/lib/perf/include/perf/cpumap.h
index 228c6c629b0ce1..90457d17fb2f51 100644
--- a/tools/lib/perf/include/perf/cpumap.h
+++ b/tools/lib/perf/include/perf/cpumap.h
@@ -61,6 +61,22 @@ LIBPERF_API int perf_cpu_map__nr(const struct perf_cpu_map *cpus);
  * perf_cpu_map__has_any_cpu_or_is_empty - is map either empty or has the "any CPU"/dummy value.
  */
 LIBPERF_API bool perf_cpu_map__has_any_cpu_or_is_empty(const struct perf_cpu_map *map);
+/**
+ * perf_cpu_map__is_any_cpu_or_is_empty - is map either empty or the "any CPU"/dummy value.
+ */
+LIBPERF_API bool perf_cpu_map__is_any_cpu_or_is_empty(const struct perf_cpu_map *map);
+/**
+ * perf_cpu_map__is_empty - does the map contain no values and it doesn't
+ *                          contain the special "any CPU"/dummy value.
+ */
+LIBPERF_API bool perf_cpu_map__is_empty(const struct perf_cpu_map *map);
+/**
+ * perf_cpu_map__min - the minimum CPU value or -1 if empty or just the "any CPU"/dummy value.
+ */
+LIBPERF_API struct perf_cpu perf_cpu_map__min(const struct perf_cpu_map *map);
+/**
+ * perf_cpu_map__max - the maximum CPU value or -1 if empty or just the "any CPU"/dummy value.
+ */
 LIBPERF_API struct perf_cpu perf_cpu_map__max(const struct perf_cpu_map *map);
 LIBPERF_API bool perf_cpu_map__has(const struct perf_cpu_map *map, struct perf_cpu cpu);
 LIBPERF_API bool perf_cpu_map__equal(const struct perf_cpu_map *lhs,
diff --git a/tools/lib/perf/libperf.map b/tools/lib/perf/libperf.map
index 10b3f372264264..2aa79b69603268 100644
--- a/tools/lib/perf/libperf.map
+++ b/tools/lib/perf/libperf.map
@@ -10,6 +10,10 @@ LIBPERF_0.0.1 {
 		perf_cpu_map__nr;
 		perf_cpu_map__cpu;
 		perf_cpu_map__has_any_cpu_or_is_empty;
+		perf_cpu_map__is_any_cpu_or_is_empty;
+		perf_cpu_map__is_empty;
+		perf_cpu_map__has_any_cpu;
+		perf_cpu_map__min;
 		perf_cpu_map__max;
 		perf_cpu_map__has;
 		perf_thread_map__new_array;
diff --git a/tools/lib/perf/mmap.c b/tools/lib/perf/mmap.c
index 0c903c2372c978..c1a51d925e0e02 100644
--- a/tools/lib/perf/mmap.c
+++ b/tools/lib/perf/mmap.c
@@ -279,7 +279,7 @@ union perf_event *perf_mmap__read_event(struct perf_mmap *map)
 	if (!refcount_read(&map->refcnt))
 		return NULL;
 
-	/* non-overwirte doesn't pause the ringbuffer */
+	/* non-overwrite doesn't pause the ringbuffer */
 	if (!map->overwrite)
 		map->end = perf_mmap__read_head(map);
 
diff --git a/tools/lib/subcmd/run-command.c b/tools/lib/subcmd/run-command.c
index d435eb42354bfe..4e3a557a2f3741 100644
--- a/tools/lib/subcmd/run-command.c
+++ b/tools/lib/subcmd/run-command.c
@@ -165,43 +165,65 @@ int start_command(struct child_process *cmd)
 	return 0;
 }
 
-static int wait_or_whine(pid_t pid)
+static int wait_or_whine(struct child_process *cmd, bool block)
 {
-	char sbuf[STRERR_BUFSIZE];
+	bool finished = cmd->finished;
+	int result = cmd->finish_result;
 
-	for (;;) {
+	while (!finished) {
 		int status, code;
-		pid_t waiting = waitpid(pid, &status, 0);
+		pid_t waiting = waitpid(cmd->pid, &status, block ? 0 : WNOHANG);
+
+		if (!block && waiting == 0)
+			break;
+
+		if (waiting < 0 && errno == EINTR)
+			continue;
 
+		finished = true;
 		if (waiting < 0) {
-			if (errno == EINTR)
-				continue;
+			char sbuf[STRERR_BUFSIZE];
+
 			fprintf(stderr, " Error: waitpid failed (%s)",
 				str_error_r(errno, sbuf, sizeof(sbuf)));
-			return -ERR_RUN_COMMAND_WAITPID;
-		}
-		if (waiting != pid)
-			return -ERR_RUN_COMMAND_WAITPID_WRONG_PID;
-		if (WIFSIGNALED(status))
-			return -ERR_RUN_COMMAND_WAITPID_SIGNAL;
-
-		if (!WIFEXITED(status))
-			return -ERR_RUN_COMMAND_WAITPID_NOEXIT;
-		code = WEXITSTATUS(status);
-		switch (code) {
-		case 127:
-			return -ERR_RUN_COMMAND_EXEC;
-		case 0:
-			return 0;
-		default:
-			return -code;
+			result = -ERR_RUN_COMMAND_WAITPID;
+		} else if (waiting != cmd->pid) {
+			result = -ERR_RUN_COMMAND_WAITPID_WRONG_PID;
+		} else if (WIFSIGNALED(status)) {
+			result = -ERR_RUN_COMMAND_WAITPID_SIGNAL;
+		} else if (!WIFEXITED(status)) {
+			result = -ERR_RUN_COMMAND_WAITPID_NOEXIT;
+		} else {
+			code = WEXITSTATUS(status);
+			switch (code) {
+			case 127:
+				result = -ERR_RUN_COMMAND_EXEC;
+				break;
+			case 0:
+				result = 0;
+				break;
+			default:
+				result = -code;
+				break;
+			}
 		}
 	}
+	if (finished) {
+		cmd->finished = 1;
+		cmd->finish_result = result;
+	}
+	return result;
+}
+
+int check_if_command_finished(struct child_process *cmd)
+{
+	wait_or_whine(cmd, /*block=*/false);
+	return cmd->finished;
 }
 
 int finish_command(struct child_process *cmd)
 {
-	return wait_or_whine(cmd->pid);
+	return wait_or_whine(cmd, /*block=*/true);
 }
 
 int run_command(struct child_process *cmd)
diff --git a/tools/lib/subcmd/run-command.h b/tools/lib/subcmd/run-command.h
index d794138a797f4a..b2d39de6e690b5 100644
--- a/tools/lib/subcmd/run-command.h
+++ b/tools/lib/subcmd/run-command.h
@@ -41,17 +41,20 @@ struct child_process {
 	int err;
 	const char *dir;
 	const char *const *env;
+	int finish_result;
 	unsigned no_stdin:1;
 	unsigned no_stdout:1;
 	unsigned no_stderr:1;
 	unsigned exec_cmd:1; /* if this is to be external sub-command */
 	unsigned stdout_to_stderr:1;
+	unsigned finished:1;
 	void (*preexec_cb)(void);
 	 /* If set, call function in child rather than doing an exec. */
 	int (*no_exec_cmd)(struct child_process *process);
 };
 
 int start_command(struct child_process *);
+int check_if_command_finished(struct child_process *);
 int finish_command(struct child_process *);
 int run_command(struct child_process *);
 
diff --git a/tools/perf/Build b/tools/perf/Build
index aa762362283492..b0cb7ad8e6ac24 100644
--- a/tools/perf/Build
+++ b/tools/perf/Build
@@ -59,3 +59,17 @@ perf-y += ui/
 perf-y += scripts/
 
 gtk-y += ui/gtk/
+
+ifdef SHELLCHECK
+  SHELL_TESTS := $(wildcard *.sh)
+  TEST_LOGS := $(SHELL_TESTS:%=%.shellcheck_log)
+else
+  SHELL_TESTS :=
+  TEST_LOGS :=
+endif
+
+$(OUTPUT)%.shellcheck_log: %
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,test)shellcheck -s bash -a -S warning "$<" > $@ || (cat $@ && rm $@ && false)
+
+perf-y += $(TEST_LOGS)
diff --git a/tools/perf/Documentation/perf-arm-spe.txt b/tools/perf/Documentation/perf-arm-spe.txt
index bf03222e9a68e4..0a3eda482307a3 100644
--- a/tools/perf/Documentation/perf-arm-spe.txt
+++ b/tools/perf/Documentation/perf-arm-spe.txt
@@ -116,6 +116,15 @@ Depending on CPU model, the kernel may need to be booted with page table isolati
 (kpti=off). If KPTI needs to be disabled, this will fail with a console message "profiling buffer
 inaccessible. Try passing 'kpti=off' on the kernel command line".
 
+For the full criteria that determine whether KPTI needs to be forced off or not, see function
+unmap_kernel_at_el0() in the kernel sources. Common cases where it's not required
+are on the CPUs in kpti_safe_list, or on Arm v8.5+ where FEAT_E0PD is mandatory.
+
+The SPE interrupt must also be described by the firmware. If the module is loaded and KPTI is
+disabled (or isn't required to be disabled) but the SPE PMU still doesn't show in
+/sys/bus/event_source/devices/, then it's possible that the SPE interrupt isn't described by
+ACPI or DT. In this case no warning will be printed by the driver.
+
 Capturing SPE with perf command-line tools
 ------------------------------------------
 
@@ -199,7 +208,8 @@ Common errors
 
  - "Cannot find PMU `arm_spe'. Missing kernel support?"
 
-   Module not built or loaded, KPTI not disabled (see above), or running on a VM
+   Module not built or loaded, KPTI not disabled, interrupt not described by firmware,
+   or running on a VM. See 'Kernel Requirements' above.
 
  - "Arm SPE CONTEXT packets not found in the traces."
 
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index 3b12595193c9f4..6bf2468f59d31d 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -71,6 +71,7 @@ counted. The following modifiers exist:
  D - pin the event to the PMU
  W - group is weak and will fallback to non-group if not schedulable,
  e - group or event are exclusive and do not share the PMU
+ b - use BPF aggregration (see perf stat --bpf-counters)
 
 The 'p' modifier can be used for specifying how precise the instruction
 address should be. The 'p' modifier can be specified multiple times:
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index d8b863e01fe082..d2b1593ef7006c 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -121,6 +121,9 @@ OPTIONS
 	- type: Data type of sample memory access.
 	- typeoff: Offset in the data type of sample memory access.
 	- symoff: Offset in the symbol.
+	- weight1: Average value of event specific weight (1st field of weight_struct).
+	- weight2: Average value of event specific weight (2nd field of weight_struct).
+	- weight3: Average value of event specific weight (3rd field of weight_struct).
 
 	By default, comm, dso and symbol keys are used.
 	(i.e. --sort comm,dso,symbol)
@@ -198,7 +201,11 @@ OPTIONS
 --fields=::
 	Specify output field - multiple keys can be specified in CSV format.
 	Following fields are available:
-	overhead, overhead_sys, overhead_us, overhead_children, sample and period.
+	overhead, overhead_sys, overhead_us, overhead_children, sample, period,
+	weight1, weight2, weight3, ins_lat, p_stage_cyc and retire_lat.  The
+	last 3 names are alias for the corresponding weights.  When the weight
+	fields are used, they will show the average value of the weight.
+
 	Also it can contain any sort key(s).
 
 	By default, every sort keys not specified in -F will be appended
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 005e51df855e7c..ff086ef05a0c50 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -132,9 +132,9 @@ OPTIONS
         Comma separated list of fields to print. Options are:
         comm, tid, pid, time, cpu, event, trace, ip, sym, dso, dsoff, addr, symoff,
         srcline, period, iregs, uregs, brstack, brstacksym, flags, bpf-output,
-        brstackinsn, brstackinsnlen, brstackoff, callindent, insn, disasm,
+        brstackinsn, brstackinsnlen, brstackdisasm, brstackoff, callindent, insn, disasm,
         insnlen, synth, phys_addr, metric, misc, srccode, ipc, data_page_size,
-        code_page_size, ins_lat, machine_pid, vcpu, cgroup, retire_lat.
+        code_page_size, ins_lat, machine_pid, vcpu, cgroup, retire_lat,
 
         Field list can be prepended with the type, trace, sw or hw,
         to indicate to which event type the field list applies.
@@ -257,6 +257,9 @@ OPTIONS
 	can’t know the next sequential instruction after an unconditional branch unless
 	you calculate that based on its length.
 
+	brstackdisasm acts like brstackinsn, but will print disassembled instructions if
+	perf is built with the capstone library.
+
 	The brstackoff field will print an offset into a specific dso/binary.
 
 	With the metric option perf script can compute metrics for
diff --git a/tools/perf/Documentation/perf-test.txt b/tools/perf/Documentation/perf-test.txt
index 951a2f2628727a..9acb8d1f658890 100644
--- a/tools/perf/Documentation/perf-test.txt
+++ b/tools/perf/Documentation/perf-test.txt
@@ -31,9 +31,20 @@ OPTIONS
 --verbose::
 	Be more verbose.
 
+-S::
+--sequential::
+	Run tests one after the other, this is the default mode.
+
+-p:: 
+--parallel::
+	Run tests in parallel, speeds up the whole process but is not safe with
+	the current infrastructure, where some tests that compete for some resources,
+	for instance, 'perf probe' tests that add/remove probes or clean all probes, etc.
+
 -F::
 --dont-fork::
-	Do not fork child for each test, run all tests within single process.
+	Do not fork child for each test, run all tests within single process, this
+	sets sequential mode.
 
 --dso::
 	Specify a DSO for the "Symbols" test.
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 1fe8df97fe8840..7f1e016a92536c 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -182,6 +182,16 @@ endif
 FEATURE_CHECK_CFLAGS-libzstd := $(LIBZSTD_CFLAGS)
 FEATURE_CHECK_LDFLAGS-libzstd := $(LIBZSTD_LDFLAGS)
 
+# for linking with debug library, run like:
+# make DEBUG=1 LIBTRACEEVENT_DIR=/opt/libtraceevent/
+TRACEEVENTLIBS := -ltraceevent
+ifdef LIBTRACEEVENT_DIR
+  LIBTRACEEVENT_CFLAGS  := -I$(LIBTRACEEVENT_DIR)/include
+  LIBTRACEEVENT_LDFLAGS := -L$(LIBTRACEEVENT_DIR)/lib
+endif
+FEATURE_CHECK_CFLAGS-libtraceevent := $(LIBTRACEEVENT_CFLAGS)
+FEATURE_CHECK_LDFLAGS-libtraceevent := $(LIBTRACEEVENT_LDFLAGS) $(TRACEEVENTLIBS)
+
 FEATURE_CHECK_CFLAGS-bpf = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(SRCARCH)/include/uapi -I$(srctree)/tools/include/uapi
 # include ARCH specific config
 -include $(src-perf)/arch/$(SRCARCH)/Makefile
@@ -486,7 +496,10 @@ ifdef NO_DWARF
 endif
 
 ifeq ($(feature-scandirat), 1)
-  CFLAGS += -DHAVE_SCANDIRAT_SUPPORT
+  # Ignore having scandirat with memory sanitizer that lacks an interceptor.
+  ifeq ($(filter s% -fsanitize=memory%,$(EXTRA_CFLAGS),),)
+    CFLAGS += -DHAVE_SCANDIRAT_SUPPORT
+  endif
 endif
 
 ifeq ($(feature-sched_getcpu), 1)
@@ -1165,9 +1178,10 @@ endif
 ifneq ($(NO_LIBTRACEEVENT),1)
   $(call feature_check,libtraceevent)
   ifeq ($(feature-libtraceevent), 1)
-    CFLAGS += -DHAVE_LIBTRACEEVENT
-    EXTLIBS += -ltraceevent
-    LIBTRACEEVENT_VERSION := $(shell $(PKG_CONFIG) --modversion libtraceevent)
+    CFLAGS += -DHAVE_LIBTRACEEVENT $(LIBTRACEEVENT_CFLAGS)
+    LDFLAGS += $(LIBTRACEEVENT_LDFLAGS)
+    EXTLIBS += ${TRACEEVENTLIBS}
+    LIBTRACEEVENT_VERSION := $(shell PKG_CONFIG_PATH=$(LIBTRACEEVENT_DIR) $(PKG_CONFIG) --modversion libtraceevent)
     LIBTRACEEVENT_VERSION_1 := $(word 1, $(subst ., ,$(LIBTRACEEVENT_VERSION)))
     LIBTRACEEVENT_VERSION_2 := $(word 2, $(subst ., ,$(LIBTRACEEVENT_VERSION)))
     LIBTRACEEVENT_VERSION_3 := $(word 3, $(subst ., ,$(LIBTRACEEVENT_VERSION)))
@@ -1175,7 +1189,7 @@ ifneq ($(NO_LIBTRACEEVENT),1)
     CFLAGS += -DLIBTRACEEVENT_VERSION=$(LIBTRACEEVENT_VERSION_CPP)
     $(call detected,CONFIG_LIBTRACEEVENT)
   else
-    $(error ERROR: libtraceevent is missing. Please install libtraceevent-dev/libtraceevent-devel or build with NO_LIBTRACEEVENT=1)
+    $(error ERROR: libtraceevent is missing. Please install libtraceevent-dev/libtraceevent-devel and/or set LIBTRACEEVENT_DIR or build with NO_LIBTRACEEVENT=1)
   endif
 
   $(call feature_check,libtracefs)
@@ -1301,6 +1315,7 @@ ifeq ($(VF),1)
   $(call print_var,LIBUNWIND_DIR)
   $(call print_var,LIBDW_DIR)
   $(call print_var,JDIR)
+  $(call print_var,LIBTRACEEVENT_DIR)
 
   ifeq ($(dwarf-post-unwind),1)
     $(call feature_print_text,"DWARF post unwind library", $(dwarf-post-unwind-text)) $(info $(MSG))
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 04d89d2ed209b4..5c35c0d8930696 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -458,35 +458,53 @@ SHELL = $(SHELL_PATH)
 
 arm64_gen_sysreg_dir := $(srctree)/tools/arch/arm64/tools
 ifneq ($(OUTPUT),)
-  arm64_gen_sysreg_outdir := $(OUTPUT)
+  arm64_gen_sysreg_outdir := $(abspath $(OUTPUT))
 else
   arm64_gen_sysreg_outdir := $(CURDIR)
 endif
 
 arm64-sysreg-defs: FORCE
-	$(Q)$(MAKE) -C $(arm64_gen_sysreg_dir) O=$(arm64_gen_sysreg_outdir)
+	$(Q)$(MAKE) -C $(arm64_gen_sysreg_dir) O=$(arm64_gen_sysreg_outdir) \
+		prefix= subdir=
 
 arm64-sysreg-defs-clean:
 	$(call QUIET_CLEAN,arm64-sysreg-defs)
 	$(Q)$(MAKE) -C $(arm64_gen_sysreg_dir) O=$(arm64_gen_sysreg_outdir) \
-		clean > /dev/null
+		prefix= subdir= clean > /dev/null
 
 beauty_linux_dir := $(srctree)/tools/perf/trace/beauty/include/linux/
+beauty_uapi_linux_dir := $(srctree)/tools/perf/trace/beauty/include/uapi/linux/
+beauty_uapi_sound_dir := $(srctree)/tools/perf/trace/beauty/include/uapi/sound/
+beauty_arch_asm_dir := $(srctree)/tools/perf/trace/beauty/arch/x86/include/asm/
+beauty_x86_arch_asm_uapi_dir := $(srctree)/tools/perf/trace/beauty/arch/x86/include/uapi/asm/
+
 linux_uapi_dir := $(srctree)/tools/include/uapi/linux
 asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic
 arch_asm_uapi_dir := $(srctree)/tools/arch/$(SRCARCH)/include/uapi/asm/
-x86_arch_asm_uapi_dir := $(srctree)/tools/arch/x86/include/uapi/asm/
 x86_arch_asm_dir := $(srctree)/tools/arch/x86/include/asm/
 
 beauty_outdir := $(OUTPUT)trace/beauty/generated
 beauty_ioctl_outdir := $(beauty_outdir)/ioctl
-drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c
-drm_hdr_dir := $(srctree)/tools/include/uapi/drm
-drm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/drm_ioctl.sh
 
 # Create output directory if not already present
 $(shell [ -d '$(beauty_ioctl_outdir)' ] || mkdir -p '$(beauty_ioctl_outdir)')
 
+fs_at_flags_array := $(beauty_outdir)/fs_at_flags_array.c
+fs_at_flags_tbl := $(srctree)/tools/perf/trace/beauty/fs_at_flags.sh
+
+$(fs_at_flags_array): $(beauty_uapi_linux_dir)/fcntl.h $(fs_at_flags_tbl)
+	$(Q)$(SHELL) '$(fs_at_flags_tbl)' $(beauty_uapi_linux_dir) > $@
+
+clone_flags_array := $(beauty_outdir)/clone_flags_array.c
+clone_flags_tbl := $(srctree)/tools/perf/trace/beauty/clone.sh
+
+$(clone_flags_array): $(beauty_uapi_linux_dir)/sched.h $(clone_flags_tbl)
+	$(Q)$(SHELL) '$(clone_flags_tbl)' $(beauty_uapi_linux_dir) > $@
+
+drm_ioctl_array := $(beauty_ioctl_outdir)/drm_ioctl_array.c
+drm_hdr_dir := $(srctree)/tools/include/uapi/drm
+drm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/drm_ioctl.sh
+
 $(drm_ioctl_array): $(drm_hdr_dir)/drm.h $(drm_hdr_dir)/i915_drm.h $(drm_ioctl_tbl)
 	$(Q)$(SHELL) '$(drm_ioctl_tbl)' $(drm_hdr_dir) > $@
 
@@ -499,20 +517,20 @@ $(fadvise_advice_array): $(linux_uapi_dir)/in.h $(fadvise_advice_tbl)
 fsmount_arrays := $(beauty_outdir)/fsmount_arrays.c
 fsmount_tbls := $(srctree)/tools/perf/trace/beauty/fsmount.sh
 
-$(fsmount_arrays): $(linux_uapi_dir)/fs.h $(fsmount_tbls)
-	$(Q)$(SHELL) '$(fsmount_tbls)' $(linux_uapi_dir) > $@
+$(fsmount_arrays): $(beauty_uapi_linux_dir)/mount.h $(fsmount_tbls)
+	$(Q)$(SHELL) '$(fsmount_tbls)' $(beauty_uapi_linux_dir) > $@
 
 fspick_arrays := $(beauty_outdir)/fspick_arrays.c
 fspick_tbls := $(srctree)/tools/perf/trace/beauty/fspick.sh
 
-$(fspick_arrays): $(linux_uapi_dir)/fs.h $(fspick_tbls)
-	$(Q)$(SHELL) '$(fspick_tbls)' $(linux_uapi_dir) > $@
+$(fspick_arrays): $(beauty_uapi_linux_dir)/mount.h $(fspick_tbls)
+	$(Q)$(SHELL) '$(fspick_tbls)' $(beauty_uapi_linux_dir) > $@
 
 fsconfig_arrays := $(beauty_outdir)/fsconfig_arrays.c
 fsconfig_tbls := $(srctree)/tools/perf/trace/beauty/fsconfig.sh
 
-$(fsconfig_arrays): $(linux_uapi_dir)/fs.h $(fsconfig_tbls)
-	$(Q)$(SHELL) '$(fsconfig_tbls)' $(linux_uapi_dir) > $@
+$(fsconfig_arrays): $(beauty_uapi_linux_dir)/mount.h $(fsconfig_tbls)
+	$(Q)$(SHELL) '$(fsconfig_tbls)' $(beauty_uapi_linux_dir) > $@
 
 pkey_alloc_access_rights_array := $(beauty_outdir)/pkey_alloc_access_rights_array.c
 asm_generic_hdr_dir := $(srctree)/tools/include/uapi/asm-generic/
@@ -525,15 +543,15 @@ sndrv_ctl_ioctl_array := $(beauty_ioctl_outdir)/sndrv_ctl_ioctl_array.c
 sndrv_ctl_hdr_dir := $(srctree)/tools/include/uapi/sound
 sndrv_ctl_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
 
-$(sndrv_ctl_ioctl_array): $(sndrv_ctl_hdr_dir)/asound.h $(sndrv_ctl_ioctl_tbl)
-	$(Q)$(SHELL) '$(sndrv_ctl_ioctl_tbl)' $(sndrv_ctl_hdr_dir) > $@
+$(sndrv_ctl_ioctl_array): $(beauty_uapi_sound_dir)/asound.h $(sndrv_ctl_ioctl_tbl)
+	$(Q)$(SHELL) '$(sndrv_ctl_ioctl_tbl)' $(beauty_uapi_sound_dir) > $@
 
 sndrv_pcm_ioctl_array := $(beauty_ioctl_outdir)/sndrv_pcm_ioctl_array.c
 sndrv_pcm_hdr_dir := $(srctree)/tools/include/uapi/sound
 sndrv_pcm_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
 
-$(sndrv_pcm_ioctl_array): $(sndrv_pcm_hdr_dir)/asound.h $(sndrv_pcm_ioctl_tbl)
-	$(Q)$(SHELL) '$(sndrv_pcm_ioctl_tbl)' $(sndrv_pcm_hdr_dir) > $@
+$(sndrv_pcm_ioctl_array): $(beauty_uapi_sound_dir)/asound.h $(sndrv_pcm_ioctl_tbl)
+	$(Q)$(SHELL) '$(sndrv_pcm_ioctl_tbl)' $(beauty_uapi_sound_dir) > $@
 
 kcmp_type_array := $(beauty_outdir)/kcmp_type_array.c
 kcmp_hdr_dir := $(srctree)/tools/include/uapi/linux/
@@ -562,11 +580,10 @@ $(sockaddr_arrays): $(beauty_linux_dir)/socket.h $(sockaddr_tbl)
 	$(Q)$(SHELL) '$(sockaddr_tbl)' $(beauty_linux_dir) > $@
 
 vhost_virtio_ioctl_array := $(beauty_ioctl_outdir)/vhost_virtio_ioctl_array.c
-vhost_virtio_hdr_dir := $(srctree)/tools/include/uapi/linux
 vhost_virtio_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
 
-$(vhost_virtio_ioctl_array): $(vhost_virtio_hdr_dir)/vhost.h $(vhost_virtio_ioctl_tbl)
-	$(Q)$(SHELL) '$(vhost_virtio_ioctl_tbl)' $(vhost_virtio_hdr_dir) > $@
+$(vhost_virtio_ioctl_array): $(beauty_uapi_linux_dir)/vhost.h $(vhost_virtio_ioctl_tbl)
+	$(Q)$(SHELL) '$(vhost_virtio_ioctl_tbl)' $(beauty_uapi_linux_dir) > $@
 
 perf_ioctl_array := $(beauty_ioctl_outdir)/perf_ioctl_array.c
 perf_hdr_dir := $(srctree)/tools/include/uapi/linux
@@ -597,15 +614,14 @@ $(mremap_flags_array): $(linux_uapi_dir)/mman.h $(mremap_flags_tbl)
 mount_flags_array := $(beauty_outdir)/mount_flags_array.c
 mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh
 
-$(mount_flags_array): $(linux_uapi_dir)/fs.h $(mount_flags_tbl)
-	$(Q)$(SHELL) '$(mount_flags_tbl)' $(linux_uapi_dir) > $@
+$(mount_flags_array): $(beauty_uapi_linux_dir)/mount.h $(mount_flags_tbl)
+	$(Q)$(SHELL) '$(mount_flags_tbl)' $(beauty_uapi_linux_dir) > $@
 
 move_mount_flags_array := $(beauty_outdir)/move_mount_flags_array.c
 move_mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/move_mount_flags.sh
 
-$(move_mount_flags_array): $(linux_uapi_dir)/fs.h $(move_mount_flags_tbl)
-	$(Q)$(SHELL) '$(move_mount_flags_tbl)' $(linux_uapi_dir) > $@
-
+$(move_mount_flags_array): $(beauty_uapi_linux_dir)/mount.h $(move_mount_flags_tbl)
+	$(Q)$(SHELL) '$(move_mount_flags_tbl)' $(beauty_uapi_linux_dir) > $@
 
 mmap_prot_array := $(beauty_outdir)/mmap_prot_array.c
 mmap_prot_tbl := $(srctree)/tools/perf/trace/beauty/mmap_prot.sh
@@ -614,29 +630,28 @@ $(mmap_prot_array): $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-
 	$(Q)$(SHELL) '$(mmap_prot_tbl)' $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
 
 prctl_option_array := $(beauty_outdir)/prctl_option_array.c
-prctl_hdr_dir := $(srctree)/tools/include/uapi/linux/
 prctl_option_tbl := $(srctree)/tools/perf/trace/beauty/prctl_option.sh
 
-$(prctl_option_array): $(prctl_hdr_dir)/prctl.h $(prctl_option_tbl)
-	$(Q)$(SHELL) '$(prctl_option_tbl)' $(prctl_hdr_dir) > $@
+$(prctl_option_array): $(beauty_uapi_linux_dir)/prctl.h $(prctl_option_tbl)
+	$(Q)$(SHELL) '$(prctl_option_tbl)' $(beauty_uapi_linux_dir) > $@
 
 usbdevfs_ioctl_array := $(beauty_ioctl_outdir)/usbdevfs_ioctl_array.c
 usbdevfs_ioctl_tbl := $(srctree)/tools/perf/trace/beauty/usbdevfs_ioctl.sh
 
-$(usbdevfs_ioctl_array): $(linux_uapi_dir)/usbdevice_fs.h $(usbdevfs_ioctl_tbl)
-	$(Q)$(SHELL) '$(usbdevfs_ioctl_tbl)' $(linux_uapi_dir) > $@
+$(usbdevfs_ioctl_array): $(beauty_uapi_linux_dir)/usbdevice_fs.h $(usbdevfs_ioctl_tbl)
+	$(Q)$(SHELL) '$(usbdevfs_ioctl_tbl)' $(beauty_uapi_linux_dir) > $@
 
 x86_arch_prctl_code_array := $(beauty_outdir)/x86_arch_prctl_code_array.c
 x86_arch_prctl_code_tbl := $(srctree)/tools/perf/trace/beauty/x86_arch_prctl.sh
 
-$(x86_arch_prctl_code_array): $(x86_arch_asm_uapi_dir)/prctl.h $(x86_arch_prctl_code_tbl)
-	$(Q)$(SHELL) '$(x86_arch_prctl_code_tbl)' $(x86_arch_asm_uapi_dir) > $@
+$(x86_arch_prctl_code_array): $(beauty_x86_arch_asm_uapi_dir)/prctl.h $(x86_arch_prctl_code_tbl)
+	$(Q)$(SHELL) '$(x86_arch_prctl_code_tbl)' $(beauty_x86_arch_asm_uapi_dir) > $@
 
 x86_arch_irq_vectors_array := $(beauty_outdir)/x86_arch_irq_vectors_array.c
 x86_arch_irq_vectors_tbl := $(srctree)/tools/perf/trace/beauty/tracepoints/x86_irq_vectors.sh
 
-$(x86_arch_irq_vectors_array): $(x86_arch_asm_dir)/irq_vectors.h $(x86_arch_irq_vectors_tbl)
-	$(Q)$(SHELL) '$(x86_arch_irq_vectors_tbl)' $(x86_arch_asm_dir) > $@
+$(x86_arch_irq_vectors_array): $(beauty_arch_asm_dir)/irq_vectors.h $(x86_arch_irq_vectors_tbl)
+	$(Q)$(SHELL) '$(x86_arch_irq_vectors_tbl)' $(beauty_arch_asm_dir) > $@
 
 x86_arch_MSRs_array := $(beauty_outdir)/x86_arch_MSRs_array.c
 x86_arch_MSRs_tbl := $(srctree)/tools/perf/trace/beauty/tracepoints/x86_msr.sh
@@ -647,8 +662,8 @@ $(x86_arch_MSRs_array): $(x86_arch_asm_dir)/msr-index.h $(x86_arch_MSRs_tbl)
 rename_flags_array := $(beauty_outdir)/rename_flags_array.c
 rename_flags_tbl := $(srctree)/tools/perf/trace/beauty/rename_flags.sh
 
-$(rename_flags_array): $(linux_uapi_dir)/fs.h $(rename_flags_tbl)
-	$(Q)$(SHELL) '$(rename_flags_tbl)' $(linux_uapi_dir) > $@
+$(rename_flags_array): $(beauty_uapi_linux_dir)/fs.h $(rename_flags_tbl)
+	$(Q)$(SHELL) '$(rename_flags_tbl)' $(beauty_uapi_linux_dir) > $@
 
 arch_errno_name_array := $(beauty_outdir)/arch_errno_name_array.c
 arch_errno_hdr_dir := $(srctree)/tools
@@ -657,11 +672,17 @@ arch_errno_tbl := $(srctree)/tools/perf/trace/beauty/arch_errno_names.sh
 $(arch_errno_name_array): $(arch_errno_tbl)
 	$(Q)$(SHELL) '$(arch_errno_tbl)' '$(patsubst -%,,$(CC))' $(arch_errno_hdr_dir) > $@
 
+statx_mask_array := $(beauty_outdir)/statx_mask_array.c
+statx_mask_tbl := $(srctree)/tools/perf/trace/beauty/statx_mask.sh
+
+$(statx_mask_array): $(beauty_uapi_linux_dir)/stat.h $(statx_mask_tbl)
+	$(Q)$(SHELL) '$(statx_mask_tbl)' $(beauty_uapi_linux_dir) > $@
+
 sync_file_range_arrays := $(beauty_outdir)/sync_file_range_arrays.c
 sync_file_range_tbls := $(srctree)/tools/perf/trace/beauty/sync_file_range.sh
 
-$(sync_file_range_arrays): $(linux_uapi_dir)/fs.h $(sync_file_range_tbls)
-	$(Q)$(SHELL) '$(sync_file_range_tbls)' $(linux_uapi_dir) > $@
+$(sync_file_range_arrays): $(beauty_uapi_linux_dir)/fs.h $(sync_file_range_tbls)
+	$(Q)$(SHELL) '$(sync_file_range_tbls)' $(beauty_uapi_linux_dir) > $@
 
 TESTS_CORESIGHT_DIR := $(srctree)/tools/perf/tests/shell/coresight
 
@@ -762,6 +783,8 @@ build-dir   = $(or $(__build-dir),.)
 
 prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders \
 	arm64-sysreg-defs \
+	$(fs_at_flags_array) \
+	$(clone_flags_array) \
 	$(drm_ioctl_array) \
 	$(fadvise_advice_array) \
 	$(fsconfig_arrays) \
@@ -789,6 +812,7 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders \
 	$(x86_arch_prctl_code_array) \
 	$(rename_flags_array) \
 	$(arch_errno_name_array) \
+	$(statx_mask_array) \
 	$(sync_file_range_arrays) \
 	$(LIBAPI) \
 	$(LIBPERF) \
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index 77e6663c1703b8..07be32d99805c3 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -197,38 +197,37 @@ static int cs_etm_validate_timestamp(struct auxtrace_record *itr,
 static int cs_etm_validate_config(struct auxtrace_record *itr,
 				  struct evsel *evsel)
 {
-	int i, err = -EINVAL;
+	int idx, err = 0;
 	struct perf_cpu_map *event_cpus = evsel->evlist->core.user_requested_cpus;
-	struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus();
-
-	/* Set option of each CPU we have */
-	for (i = 0; i < cpu__max_cpu().cpu; i++) {
-		struct perf_cpu cpu = { .cpu = i, };
+	struct perf_cpu_map *intersect_cpus;
+	struct perf_cpu cpu;
 
-		/*
-		 * In per-cpu case, do the validation for CPUs to work with.
-		 * In per-thread case, the CPU map is empty.  Since the traced
-		 * program can run on any CPUs in this case, thus don't skip
-		 * validation.
-		 */
-		if (!perf_cpu_map__has_any_cpu_or_is_empty(event_cpus) &&
-		    !perf_cpu_map__has(event_cpus, cpu))
-			continue;
+	/*
+	 * Set option of each CPU we have. In per-cpu case, do the validation
+	 * for CPUs to work with. In per-thread case, the CPU map has the "any"
+	 * CPU value. Since the traced program can run on any CPUs in this case,
+	 * thus don't skip validation.
+	 */
+	if (!perf_cpu_map__has_any_cpu(event_cpus)) {
+		struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus();
 
-		if (!perf_cpu_map__has(online_cpus, cpu))
-			continue;
+		intersect_cpus = perf_cpu_map__intersect(event_cpus, online_cpus);
+		perf_cpu_map__put(online_cpus);
+	} else {
+		intersect_cpus = perf_cpu_map__new_online_cpus();
+	}
 
-		err = cs_etm_validate_context_id(itr, evsel, i);
+	perf_cpu_map__for_each_cpu_skip_any(cpu, idx, intersect_cpus) {
+		err = cs_etm_validate_context_id(itr, evsel, cpu.cpu);
 		if (err)
-			goto out;
-		err = cs_etm_validate_timestamp(itr, evsel, i);
+			break;
+
+		err = cs_etm_validate_timestamp(itr, evsel, cpu.cpu);
 		if (err)
-			goto out;
+			break;
 	}
 
-	err = 0;
-out:
-	perf_cpu_map__put(online_cpus);
+	perf_cpu_map__put(intersect_cpus);
 	return err;
 }
 
@@ -435,7 +434,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 	 * Also the case of per-cpu mmaps, need the contextID in order to be notified
 	 * when a context switch happened.
 	 */
-	if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
+	if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) {
 		evsel__set_config_if_unset(cs_etm_pmu, cs_etm_evsel,
 					   "timestamp", 1);
 		evsel__set_config_if_unset(cs_etm_pmu, cs_etm_evsel,
@@ -461,7 +460,7 @@ static int cs_etm_recording_options(struct auxtrace_record *itr,
 	evsel->core.attr.sample_period = 1;
 
 	/* In per-cpu case, always need the time of mmap events etc */
-	if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus))
+	if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus))
 		evsel__set_sample_bit(evsel, TIME);
 
 	err = cs_etm_validate_config(itr, cs_etm_evsel);
@@ -533,45 +532,31 @@ static size_t
 cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 		      struct evlist *evlist __maybe_unused)
 {
-	int i;
+	int idx;
 	int etmv3 = 0, etmv4 = 0, ete = 0;
 	struct perf_cpu_map *event_cpus = evlist->core.user_requested_cpus;
-	struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus();
-
-	/* cpu map is not empty, we have specific CPUs to work with */
-	if (!perf_cpu_map__has_any_cpu_or_is_empty(event_cpus)) {
-		for (i = 0; i < cpu__max_cpu().cpu; i++) {
-			struct perf_cpu cpu = { .cpu = i, };
+	struct perf_cpu_map *intersect_cpus;
+	struct perf_cpu cpu;
 
-			if (!perf_cpu_map__has(event_cpus, cpu) ||
-			    !perf_cpu_map__has(online_cpus, cpu))
-				continue;
+	if (!perf_cpu_map__has_any_cpu(event_cpus)) {
+		/* cpu map is not "any" CPU , we have specific CPUs to work with */
+		struct perf_cpu_map *online_cpus = perf_cpu_map__new_online_cpus();
 
-			if (cs_etm_is_ete(itr, i))
-				ete++;
-			else if (cs_etm_is_etmv4(itr, i))
-				etmv4++;
-			else
-				etmv3++;
-		}
+		intersect_cpus = perf_cpu_map__intersect(event_cpus, online_cpus);
+		perf_cpu_map__put(online_cpus);
 	} else {
-		/* get configuration for all CPUs in the system */
-		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))
-				ete++;
-			else if (cs_etm_is_etmv4(itr, i))
-				etmv4++;
-			else
-				etmv3++;
-		}
+		/* Event can be "any" CPU so count all online CPUs. */
+		intersect_cpus = perf_cpu_map__new_online_cpus();
 	}
-
-	perf_cpu_map__put(online_cpus);
+	perf_cpu_map__for_each_cpu_skip_any(cpu, idx, intersect_cpus) {
+		if (cs_etm_is_ete(itr, cpu.cpu))
+			ete++;
+		else if (cs_etm_is_etmv4(itr, cpu.cpu))
+			etmv4++;
+		else
+			etmv3++;
+	}
+	perf_cpu_map__put(intersect_cpus);
 
 	return (CS_ETM_HEADER_SIZE +
 	       (ete   * CS_ETE_PRIV_SIZE) +
@@ -813,16 +798,15 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 	if (!session->evlist->core.nr_mmaps)
 		return -EINVAL;
 
-	/* If the cpu_map is empty all online CPUs are involved */
-	if (perf_cpu_map__has_any_cpu_or_is_empty(event_cpus)) {
+	/* If the cpu_map has the "any" CPU all online CPUs are involved */
+	if (perf_cpu_map__has_any_cpu(event_cpus)) {
 		cpu_map = online_cpus;
 	} else {
 		/* Make sure all specified CPUs are online */
-		for (i = 0; i < perf_cpu_map__nr(event_cpus); i++) {
-			struct perf_cpu cpu = { .cpu = i, };
+		struct perf_cpu cpu;
 
-			if (perf_cpu_map__has(event_cpus, cpu) &&
-			    !perf_cpu_map__has(online_cpus, cpu))
+		perf_cpu_map__for_each_cpu(cpu, i, event_cpus) {
+			if (!perf_cpu_map__has(online_cpus, cpu))
 				return -EINVAL;
 		}
 
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 51ccbfd3d246d4..0b52e67edb3b47 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -232,7 +232,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	 * In the case of per-cpu mmaps, sample CPU for AUX event;
 	 * also enable the timestamp tracing for samples correlation.
 	 */
-	if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
+	if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) {
 		evsel__set_sample_bit(arm_spe_evsel, CPU);
 		evsel__set_config_if_unset(arm_spe_pmu, arm_spe_evsel,
 					   "ts_enable", 1);
@@ -265,7 +265,7 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 	tracking_evsel->core.attr.sample_period = 1;
 
 	/* In per-cpu case, always need the time of mmap events etc */
-	if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
+	if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) {
 		evsel__set_sample_bit(tracking_evsel, TIME);
 		evsel__set_sample_bit(tracking_evsel, CPU);
 
diff --git a/tools/perf/arch/arm64/util/header.c b/tools/perf/arch/arm64/util/header.c
index 97037499152ef7..741df3614a09ac 100644
--- a/tools/perf/arch/arm64/util/header.c
+++ b/tools/perf/arch/arm64/util/header.c
@@ -4,8 +4,6 @@
 #include <stdio.h>
 #include <stdlib.h>
 #include <perf/cpumap.h>
-#include <util/cpumap.h>
-#include <internal/cpumap.h>
 #include <api/fs/fs.h>
 #include <errno.h>
 #include "debug.h"
@@ -19,20 +17,18 @@
 static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus)
 {
 	const char *sysfs = sysfs__mountpoint();
-	int cpu;
-	int ret = EINVAL;
+	struct perf_cpu cpu;
+	int idx, ret = EINVAL;
 
 	if (!sysfs || sz < MIDR_SIZE)
 		return EINVAL;
 
-	cpus = perf_cpu_map__get(cpus);
-
-	for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) {
+	perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
 		char path[PATH_MAX];
 		FILE *file;
 
 		scnprintf(path, PATH_MAX, "%s/devices/system/cpu/cpu%d" MIDR,
-			  sysfs, RC_CHK_ACCESS(cpus)->map[cpu].cpu);
+			  sysfs, cpu.cpu);
 
 		file = fopen(path, "r");
 		if (!file) {
@@ -51,7 +47,6 @@ static int _get_cpuid(char *buf, size_t sz, struct perf_cpu_map *cpus)
 		break;
 	}
 
-	perf_cpu_map__put(cpus);
 	return ret;
 }
 
diff --git a/tools/perf/arch/x86/Build b/tools/perf/arch/x86/Build
index a7dd46a5b67850..ed37013b4289bb 100644
--- a/tools/perf/arch/x86/Build
+++ b/tools/perf/arch/x86/Build
@@ -1,2 +1,16 @@
 perf-y += util/
 perf-y += tests/
+
+ifdef SHELLCHECK
+  SHELL_TESTS := entry/syscalls/syscalltbl.sh
+  TEST_LOGS := $(SHELL_TESTS:%=%.shellcheck_log)
+else
+  SHELL_TESTS :=
+  TEST_LOGS :=
+endif
+
+$(OUTPUT)%.shellcheck_log: %
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,test)shellcheck -a -S warning "$<" > $@ || (cat $@ && rm $@ && false)
+
+perf-y += $(TEST_LOGS)
diff --git a/tools/perf/arch/x86/tests/Build b/tools/perf/arch/x86/tests/Build
index b87f46e5feea37..c1e3b7d3955440 100644
--- a/tools/perf/arch/x86/tests/Build
+++ b/tools/perf/arch/x86/tests/Build
@@ -10,3 +10,17 @@ perf-$(CONFIG_AUXTRACE) += insn-x86.o
 endif
 perf-$(CONFIG_X86_64) += bp-modify.o
 perf-y += amd-ibs-via-core-pmu.o
+
+ifdef SHELLCHECK
+  SHELL_TESTS := gen-insn-x86-dat.sh
+  TEST_LOGS := $(SHELL_TESTS:%=%.shellcheck_log)
+else
+  SHELL_TESTS :=
+  TEST_LOGS :=
+endif
+
+$(OUTPUT)%.shellcheck_log: %
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,test)shellcheck -a -S warning "$<" > $@ || (cat $@ && rm $@ && false)
+
+perf-y += $(TEST_LOGS)
diff --git a/tools/perf/arch/x86/tests/gen-insn-x86-dat.sh b/tools/perf/arch/x86/tests/gen-insn-x86-dat.sh
index 0d0a003a9c5eac..89c46532cd5c9d 100755
--- a/tools/perf/arch/x86/tests/gen-insn-x86-dat.sh
+++ b/tools/perf/arch/x86/tests/gen-insn-x86-dat.sh
@@ -11,7 +11,7 @@ if [ "$(uname -m)" != "x86_64" ]; then
 	exit 1
 fi
 
-cd $(dirname $0)
+cd "$(dirname $0)"
 
 trap 'echo "Might need a more recent version of binutils"' EXIT
 
diff --git a/tools/perf/arch/x86/util/intel-bts.c b/tools/perf/arch/x86/util/intel-bts.c
index af8ae4647585b4..34696f3d3d5dfc 100644
--- a/tools/perf/arch/x86/util/intel-bts.c
+++ b/tools/perf/arch/x86/util/intel-bts.c
@@ -143,7 +143,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
 	if (!opts->full_auxtrace)
 		return 0;
 
-	if (opts->full_auxtrace && !perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
+	if (opts->full_auxtrace && !perf_cpu_map__is_any_cpu_or_is_empty(cpus)) {
 		pr_err(INTEL_BTS_PMU_NAME " does not support per-cpu recording\n");
 		return -EINVAL;
 	}
@@ -224,7 +224,7 @@ static int intel_bts_recording_options(struct auxtrace_record *itr,
 		 * In the case of per-cpu mmaps, we need the CPU on the
 		 * AUX event.
 		 */
-		if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus))
+		if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus))
 			evsel__set_sample_bit(intel_bts_evsel, CPU);
 	}
 
diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
index d199619df3abe1..6de7e2d2107562 100644
--- a/tools/perf/arch/x86/util/intel-pt.c
+++ b/tools/perf/arch/x86/util/intel-pt.c
@@ -369,7 +369,7 @@ static int intel_pt_info_fill(struct auxtrace_record *itr,
 			ui__warning("Intel Processor Trace: TSC not available\n");
 	}
 
-	per_cpu_mmaps = !perf_cpu_map__has_any_cpu_or_is_empty(session->evlist->core.user_requested_cpus);
+	per_cpu_mmaps = !perf_cpu_map__is_any_cpu_or_is_empty(session->evlist->core.user_requested_cpus);
 
 	auxtrace_info->type = PERF_AUXTRACE_INTEL_PT;
 	auxtrace_info->priv[INTEL_PT_PMU_TYPE] = intel_pt_pmu->type;
@@ -774,7 +774,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 	 * Per-cpu recording needs sched_switch events to distinguish different
 	 * threads.
 	 */
-	if (have_timing_info && !perf_cpu_map__has_any_cpu_or_is_empty(cpus) &&
+	if (have_timing_info && !perf_cpu_map__is_any_cpu_or_is_empty(cpus) &&
 	    !record_opts__no_switch_events(opts)) {
 		if (perf_can_record_switch_events()) {
 			bool cpu_wide = !target__none(&opts->target) &&
@@ -832,7 +832,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 		 * In the case of per-cpu mmaps, we need the CPU on the
 		 * AUX event.
 		 */
-		if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus))
+		if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus))
 			evsel__set_sample_bit(intel_pt_evsel, CPU);
 	}
 
@@ -858,7 +858,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 			tracking_evsel->immediate = true;
 
 		/* In per-cpu case, always need the time of mmap events etc */
-		if (!perf_cpu_map__has_any_cpu_or_is_empty(cpus)) {
+		if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) {
 			evsel__set_sample_bit(tracking_evsel, TIME);
 			/* And the CPU for switch events */
 			evsel__set_sample_bit(tracking_evsel, CPU);
@@ -870,7 +870,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
 	 * Warn the user when we do not have enough information to decode i.e.
 	 * per-cpu with no sched_switch (except workload-only).
 	 */
-	if (!ptr->have_sched_switch && !perf_cpu_map__has_any_cpu_or_is_empty(cpus) &&
+	if (!ptr->have_sched_switch && !perf_cpu_map__is_any_cpu_or_is_empty(cpus) &&
 	    !target__none(&opts->target) &&
 	    !intel_pt_evsel->core.attr.exclude_user)
 		ui__warning("Intel Processor Trace decoding will not be possible except for kernel tracing!\n");
diff --git a/tools/perf/bench/bench.h b/tools/perf/bench/bench.h
index faa18e6d24671d..9f736423af53c3 100644
--- a/tools/perf/bench/bench.h
+++ b/tools/perf/bench/bench.h
@@ -46,6 +46,8 @@ int bench_breakpoint_enable(int argc, const char **argv);
 int bench_uprobe_baseline(int argc, const char **argv);
 int bench_uprobe_empty(int argc, const char **argv);
 int bench_uprobe_trace_printk(int argc, const char **argv);
+int bench_uprobe_empty_ret(int argc, const char **argv);
+int bench_uprobe_trace_printk_ret(int argc, const char **argv);
 int bench_pmu_scan(int argc, const char **argv);
 
 #define BENCH_FORMAT_DEFAULT_STR	"default"
diff --git a/tools/perf/bench/uprobe.c b/tools/perf/bench/uprobe.c
index 5c71fdc419dd7f..0b90275862e19f 100644
--- a/tools/perf/bench/uprobe.c
+++ b/tools/perf/bench/uprobe.c
@@ -26,9 +26,11 @@
 static int loops = LOOPS_DEFAULT;
 
 enum bench_uprobe {
-        BENCH_UPROBE__BASELINE,
-        BENCH_UPROBE__EMPTY,
-        BENCH_UPROBE__TRACE_PRINTK,
+	BENCH_UPROBE__BASELINE,
+	BENCH_UPROBE__EMPTY,
+	BENCH_UPROBE__TRACE_PRINTK,
+	BENCH_UPROBE__EMPTY_RET,
+	BENCH_UPROBE__TRACE_PRINTK_RET,
 };
 
 static const struct option options[] = {
@@ -47,7 +49,7 @@ static const char * const bench_uprobe_usage[] = {
 #define bench_uprobe__attach_uprobe(prog) \
 	skel->links.prog = bpf_program__attach_uprobe_opts(/*prog=*/skel->progs.prog, \
 							   /*pid=*/-1, \
-							   /*binary_path=*/"/lib64/libc.so.6", \
+							   /*binary_path=*/"libc.so.6", \
 							   /*func_offset=*/0, \
 							   /*opts=*/&uprobe_opts); \
 	if (!skel->links.prog) { \
@@ -81,6 +83,8 @@ static int bench_uprobe__setup_bpf_skel(enum bench_uprobe bench)
 	case BENCH_UPROBE__BASELINE:							break;
 	case BENCH_UPROBE__EMPTY:	 bench_uprobe__attach_uprobe(empty);		break;
 	case BENCH_UPROBE__TRACE_PRINTK: bench_uprobe__attach_uprobe(trace_printk);	break;
+	case BENCH_UPROBE__EMPTY_RET:	 bench_uprobe__attach_uprobe(empty_ret);	break;
+	case BENCH_UPROBE__TRACE_PRINTK_RET: bench_uprobe__attach_uprobe(trace_printk_ret); break;
 	default:
 		fprintf(stderr, "Invalid bench: %d\n", bench);
 		goto cleanup;
@@ -197,3 +201,13 @@ int bench_uprobe_trace_printk(int argc, const char **argv)
 {
 	return bench_uprobe(argc, argv, BENCH_UPROBE__TRACE_PRINTK);
 }
+
+int bench_uprobe_empty_ret(int argc, const char **argv)
+{
+	return bench_uprobe(argc, argv, BENCH_UPROBE__EMPTY_RET);
+}
+
+int bench_uprobe_trace_printk_ret(int argc, const char **argv)
+{
+	return bench_uprobe(argc, argv, BENCH_UPROBE__TRACE_PRINTK_RET);
+}
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index 6c1cc797692d94..83812b9d53638c 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -37,11 +37,13 @@
 #include "util/map_symbol.h"
 #include "util/branch.h"
 #include "util/util.h"
+#include "ui/progress.h"
 
 #include <dlfcn.h>
 #include <errno.h>
 #include <linux/bitmap.h>
 #include <linux/err.h>
+#include <inttypes.h>
 
 struct perf_annotate {
 	struct perf_tool tool;
@@ -327,77 +329,6 @@ static int hist_entry__tty_annotate(struct hist_entry *he,
 	return symbol__tty_annotate2(&he->ms, evsel);
 }
 
-static void print_annotated_data_header(struct hist_entry *he, struct evsel *evsel)
-{
-	struct dso *dso = map__dso(he->ms.map);
-	int nr_members = 1;
-	int nr_samples = he->stat.nr_events;
-
-	if (evsel__is_group_event(evsel)) {
-		struct hist_entry *pair;
-
-		list_for_each_entry(pair, &he->pairs.head, pairs.node)
-			nr_samples += pair->stat.nr_events;
-	}
-
-	printf("Annotate type: '%s' in %s (%d samples):\n",
-	       he->mem_type->self.type_name, dso->name, nr_samples);
-
-	if (evsel__is_group_event(evsel)) {
-		struct evsel *pos;
-		int i = 0;
-
-		for_each_group_evsel(pos, evsel)
-			printf(" event[%d] = %s\n", i++, pos->name);
-
-		nr_members = evsel->core.nr_members;
-	}
-
-	printf("============================================================================\n");
-	printf("%*s %10s %10s  %s\n", 11 * nr_members, "samples", "offset", "size", "field");
-}
-
-static void print_annotated_data_type(struct annotated_data_type *mem_type,
-				      struct annotated_member *member,
-				      struct evsel *evsel, int indent)
-{
-	struct annotated_member *child;
-	struct type_hist *h = mem_type->histograms[evsel->core.idx];
-	int i, nr_events = 1, samples = 0;
-
-	for (i = 0; i < member->size; i++)
-		samples += h->addr[member->offset + i].nr_samples;
-	printf(" %10d", samples);
-
-	if (evsel__is_group_event(evsel)) {
-		struct evsel *pos;
-
-		for_each_group_member(pos, evsel) {
-			h = mem_type->histograms[pos->core.idx];
-
-			samples = 0;
-			for (i = 0; i < member->size; i++)
-				samples += h->addr[member->offset + i].nr_samples;
-			printf(" %10d", samples);
-		}
-		nr_events = evsel->core.nr_members;
-	}
-
-	printf(" %10d %10d  %*s%s\t%s",
-	       member->offset, member->size, indent, "", member->type_name,
-	       member->var_name ?: "");
-
-	if (!list_empty(&member->children))
-		printf(" {\n");
-
-	list_for_each_entry(child, &member->children, node)
-		print_annotated_data_type(mem_type, child, evsel, indent + 4);
-
-	if (!list_empty(&member->children))
-		printf("%*s}", 11 * nr_events + 24 + indent, "");
-	printf(";\n");
-}
-
 static void print_annotate_data_stat(struct annotated_data_stat *s)
 {
 #define PRINT_STAT(fld) if (s->fld) printf("%10d : %s\n", s->fld, #fld)
@@ -430,6 +361,7 @@ static void print_annotate_data_stat(struct annotated_data_stat *s)
 	PRINT_STAT(no_typeinfo);
 	PRINT_STAT(invalid_size);
 	PRINT_STAT(bad_offset);
+	PRINT_STAT(insn_track);
 	printf("\n");
 
 #undef PRINT_STAT
@@ -537,10 +469,32 @@ find_next:
 					goto find_next;
 			}
 
-			print_annotated_data_header(he, evsel);
-			print_annotated_data_type(he->mem_type, &he->mem_type->self, evsel, 0);
-			printf("\n");
-			goto find_next;
+			if (use_browser == 1)
+				key = hist_entry__annotate_data_tui(he, evsel, NULL);
+			else
+				key = hist_entry__annotate_data_tty(he, evsel);
+
+			switch (key) {
+			case -1:
+				if (!ann->skip_missing)
+					return;
+				/* fall through */
+			case K_RIGHT:
+			case '>':
+				next = rb_next(nd);
+				break;
+			case K_LEFT:
+			case '<':
+				next = rb_prev(nd);
+				break;
+			default:
+				return;
+			}
+
+			if (use_browser == 0 || next != NULL)
+				nd = next;
+
+			continue;
 		}
 
 		if (use_browser == 2) {
@@ -632,13 +586,23 @@ static int __cmd_annotate(struct perf_annotate *ann)
 	evlist__for_each_entry(session->evlist, pos) {
 		struct hists *hists = evsel__hists(pos);
 		u32 nr_samples = hists->stats.nr_samples;
+		struct ui_progress prog;
 
 		if (nr_samples > 0) {
 			total_nr_samples += nr_samples;
-			hists__collapse_resort(hists, NULL);
+
+			ui_progress__init(&prog, nr_samples,
+					  "Merging related events...");
+			hists__collapse_resort(hists, &prog);
+			ui_progress__finish();
+
 			/* Don't sort callchain */
 			evsel__reset_sample_bit(pos, CALLCHAIN);
-			evsel__output_resort(pos, NULL);
+
+			ui_progress__init(&prog, nr_samples,
+					  "Sorting events for output...");
+			evsel__output_resort(pos, &prog);
+			ui_progress__finish();
 
 			/*
 			 * An event group needs to display other events too.
@@ -809,8 +773,6 @@ int cmd_annotate(int argc, const char **argv)
 		    "Enable symbol demangling"),
 	OPT_BOOLEAN(0, "demangle-kernel", &symbol_conf.demangle_kernel,
 		    "Enable kernel symbol demangling"),
-	OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
-		    "Show event group information together"),
 	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
 		    "Show a column with the sum of periods"),
 	OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
@@ -935,9 +897,7 @@ int cmd_annotate(int argc, const char **argv)
 		use_browser = 2;
 #endif
 
-	/* FIXME: only support stdio for now */
 	if (annotate.data_type) {
-		use_browser = 0;
 		annotate_opts.annotate_src = false;
 		symbol_conf.annotate_data_member = true;
 		symbol_conf.annotate_data_sample = true;
diff --git a/tools/perf/builtin-bench.c b/tools/perf/builtin-bench.c
index 1a8898d5b560f3..2c1a9f3d847a21 100644
--- a/tools/perf/builtin-bench.c
+++ b/tools/perf/builtin-bench.c
@@ -109,6 +109,8 @@ static struct bench uprobe_benchmarks[] = {
 	{ "baseline",	"Baseline libc usleep(1000) call",				bench_uprobe_baseline,	},
 	{ "empty",	"Attach empty BPF prog to uprobe on usleep, system wide",	bench_uprobe_empty,	},
 	{ "trace_printk", "Attach trace_printk BPF prog to uprobe on usleep syswide",	bench_uprobe_trace_printk,	},
+	{ "empty_ret",	"Attach empty BPF prog to uretprobe on usleep, system wide",	bench_uprobe_empty_ret,	},
+	{ "trace_printk_ret", "Attach trace_printk BPF prog to uretprobe on usleep syswide", bench_uprobe_trace_printk_ret,},
 	{ NULL,	NULL, NULL },
 };
 
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 16b40f5d43db06..1f1d17df9b9ac5 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -2050,7 +2050,7 @@ static int hpp_list__parse(struct perf_hpp_list *hpp_list,
 	perf_hpp__setup_output_field(hpp_list);
 
 	/*
-	 * We dont need other sorting keys other than those
+	 * We don't need other sorting keys other than those
 	 * we already specified. It also really slows down
 	 * the processing a lot with big number of output
 	 * fields, so switching this off for c2c.
@@ -2319,11 +2319,7 @@ static int setup_nodes(struct perf_session *session)
 
 		nodes[node] = set;
 
-		/* empty node, skip */
-		if (perf_cpu_map__has_any_cpu_or_is_empty(map))
-			continue;
-
-		perf_cpu_map__for_each_cpu(cpu, idx, map) {
+		perf_cpu_map__for_each_cpu_skip_any(cpu, idx, map) {
 			__set_bit(cpu.cpu, set);
 
 			if (WARN_ONCE(cpu2node[cpu.cpu] != -1, "node/cpu topology bug"))
diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
index eb3ef5c24b6625..ce5e28eaad9041 100644
--- a/tools/perf/builtin-inject.c
+++ b/tools/perf/builtin-inject.c
@@ -1187,23 +1187,28 @@ static int synthesize_build_id(struct perf_inject *inject, struct dso *dso, pid_
 					       process_build_id, machine);
 }
 
+static int guest_session__add_build_ids_cb(struct dso *dso, void *data)
+{
+	struct guest_session *gs = data;
+	struct perf_inject *inject = container_of(gs, struct perf_inject, guest_session);
+
+	if (!dso->has_build_id)
+		return 0;
+
+	return synthesize_build_id(inject, dso, gs->machine_pid);
+
+}
+
 static int guest_session__add_build_ids(struct guest_session *gs)
 {
 	struct perf_inject *inject = container_of(gs, struct perf_inject, guest_session);
-	struct machine *machine = &gs->session->machines.host;
-	struct dso *dso;
-	int ret;
 
 	/* Build IDs will be put in the Build ID feature section */
 	perf_header__set_feat(&inject->session->header, HEADER_BUILD_ID);
 
-	dsos__for_each_with_build_id(dso, &machine->dsos.head) {
-		ret = synthesize_build_id(inject, dso, gs->machine_pid);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
+	return dsos__for_each_dso(&gs->session->machines.host.dsos,
+				  guest_session__add_build_ids_cb,
+				  gs);
 }
 
 static int guest_session__ksymbol_event(struct perf_tool *tool,
@@ -2122,7 +2127,7 @@ static int __cmd_inject(struct perf_inject *inject)
 		 */
 		if (perf_header__has_feat(&session->header, HEADER_BUILD_ID) &&
 		    inject->have_auxtrace && !inject->itrace_synth_opts.set)
-			dsos__hit_all(session);
+			perf_session__dsos_hit_all(session);
 		/*
 		 * The AUX areas have been removed and replaced with
 		 * synthesized hardware events, so clear the feature flag.
diff --git a/tools/perf/builtin-kmem.c b/tools/perf/builtin-kmem.c
index 9714327fd0eadd..6fd95be5032b0e 100644
--- a/tools/perf/builtin-kmem.c
+++ b/tools/perf/builtin-kmem.c
@@ -1408,7 +1408,7 @@ static int __cmd_kmem(struct perf_session *session)
 	}
 
 	evlist__for_each_entry(session->evlist, evsel) {
-		if (!strcmp(evsel__name(evsel), "kmem:mm_page_alloc") &&
+		if (evsel__name_is(evsel, "kmem:mm_page_alloc") &&
 		    evsel__field(evsel, "pfn")) {
 			use_pfn = true;
 			break;
diff --git a/tools/perf/builtin-list.c b/tools/perf/builtin-list.c
index 02bf608d585ee6..5cab31231551da 100644
--- a/tools/perf/builtin-list.c
+++ b/tools/perf/builtin-list.c
@@ -22,6 +22,7 @@
 #include <subcmd/pager.h>
 #include <subcmd/parse-options.h>
 #include <linux/zalloc.h>
+#include <ctype.h>
 #include <stdarg.h>
 #include <stdio.h>
 
@@ -76,26 +77,38 @@ static void default_print_start(void *ps)
 
 static void default_print_end(void *print_state __maybe_unused) {}
 
+static const char *skip_spaces_or_commas(const char *str)
+{
+	while (isspace(*str) || *str == ',')
+		++str;
+	return str;
+}
+
 static void wordwrap(FILE *fp, const char *s, int start, int max, int corr)
 {
 	int column = start;
 	int n;
 	bool saw_newline = false;
+	bool comma = false;
 
 	while (*s) {
-		int wlen = strcspn(s, " \t\n");
+		int wlen = strcspn(s, " ,\t\n");
+		const char *sep = comma ? "," : " ";
 
 		if ((column + wlen >= max && column > start) || saw_newline) {
-			fprintf(fp, "\n%*s", start, "");
+			fprintf(fp, comma ? ",\n%*s" : "\n%*s", start, "");
 			column = start + corr;
 		}
-		n = fprintf(fp, "%s%.*s", column > start ? " " : "", wlen, s);
+		if (column <= start)
+			sep = "";
+		n = fprintf(fp, "%s%.*s", sep, wlen, s);
 		if (n <= 0)
 			break;
 		saw_newline = s[wlen] == '\n';
 		s += wlen;
+		comma = s[0] == ',';
 		column += n;
-		s = skip_spaces(s);
+		s = skip_spaces_or_commas(s);
 	}
 }
 
@@ -313,6 +326,9 @@ static void fix_escape_fprintf(FILE *fp, struct strbuf *buf, const char *fmt, ..
 					case '\n':
 						strbuf_addstr(buf, "\\n");
 						break;
+					case '\r':
+						strbuf_addstr(buf, "\\r");
+						break;
 					case '\\':
 						fallthrough;
 					case '\"':
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index ff7e1d6cfcd2e7..66a3de8ac66186 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -332,7 +332,7 @@ static int record__aio_complete(struct mmap *md, struct aiocb *cblock)
 	} else {
 		/*
 		 * aio write request may require restart with the
-		 * reminder if the kernel didn't write whole
+		 * remainder if the kernel didn't write whole
 		 * chunk at once.
 		 */
 		rem_off = cblock->aio_offset + written;
@@ -400,7 +400,7 @@ static int record__aio_pushfn(struct mmap *map, void *to, void *buf, size_t size
 	 *
 	 * Coping can be done in two steps in case the chunk of profiling data
 	 * crosses the upper bound of the kernel buffer. In this case we first move
-	 * part of data from map->start till the upper bound and then the reminder
+	 * part of data from map->start till the upper bound and then the remainder
 	 * from the beginning of the kernel buffer till the end of the data chunk.
 	 */
 
@@ -1355,8 +1355,6 @@ static int record__open(struct record *rec)
 	struct record_opts *opts = &rec->opts;
 	int rc = 0;
 
-	evlist__config(evlist, opts, &callchain_param);
-
 	evlist__for_each_entry(evlist, pos) {
 try_again:
 		if (evsel__open(pos, pos->core.cpus, pos->core.threads) < 0) {
@@ -1790,7 +1788,7 @@ record__finish_output(struct record *rec)
 		process_buildids(rec);
 
 		if (rec->buildid_all)
-			dsos__hit_all(rec->session);
+			perf_session__dsos_hit_all(rec->session);
 	}
 	perf_session__write_header(rec->session, rec->evlist, fd, true);
 
@@ -2483,6 +2481,8 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 
 	evlist__uniquify_name(rec->evlist);
 
+	evlist__config(rec->evlist, opts, &callchain_param);
+
 	/* Debug message used by test scripts */
 	pr_debug3("perf record opening and mmapping events\n");
 	if (record__open(rec) != 0) {
@@ -2881,10 +2881,10 @@ out_delete_session:
 	}
 #endif
 	zstd_fini(&session->zstd_data);
-	perf_session__delete(session);
-
 	if (!opts->no_bpf_event)
 		evlist__stop_sb_thread(rec->sb_evlist);
+
+	perf_session__delete(session);
 	return status;
 }
 
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index dcd93ee5fc24e3..dafba6e030ef70 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -172,7 +172,7 @@ static int hist_iter__report_callback(struct hist_entry_iter *iter,
 	struct mem_info *mi;
 	struct branch_info *bi;
 
-	if (!ui__has_annotation() && !rep->symbol_ipc && !rep->data_type)
+	if (!ui__has_annotation() && !rep->symbol_ipc)
 		return 0;
 
 	if (sort__mode == SORT_MODE__BRANCH) {
@@ -1694,6 +1694,11 @@ repeat:
 	else
 		use_browser = 0;
 
+	if (report.data_type && use_browser == 1) {
+		symbol_conf.annotate_data_member = true;
+		symbol_conf.annotate_data_sample = true;
+	}
+
 	if (sort_order && strstr(sort_order, "ipc")) {
 		parse_options_usage(report_usage, options, "s", 1);
 		goto error;
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index b248c433529a8f..0fce7d8986c074 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -2148,7 +2148,7 @@ static bool is_idle_sample(struct perf_sample *sample,
 			   struct evsel *evsel)
 {
 	/* pid 0 == swapper == idle task */
-	if (strcmp(evsel__name(evsel), "sched:sched_switch") == 0)
+	if (evsel__name_is(evsel, "sched:sched_switch"))
 		return evsel__intval(evsel, sample, "prev_pid") == 0;
 
 	return sample->pid == 0;
@@ -2375,7 +2375,7 @@ static bool timehist_skip_sample(struct perf_sched *sched,
 	}
 
 	if (sched->idle_hist) {
-		if (strcmp(evsel__name(evsel), "sched:sched_switch"))
+		if (!evsel__name_is(evsel, "sched:sched_switch"))
 			rc = true;
 		else if (evsel__intval(evsel, sample, "prev_pid") != 0 &&
 			 evsel__intval(evsel, sample, "next_pid") != 0)
@@ -2963,8 +2963,11 @@ static int timehist_check_attr(struct perf_sched *sched,
 			return -1;
 		}
 
-		if (sched->show_callchain && !evsel__has_callchain(evsel)) {
-			pr_info("Samples do not have callchains.\n");
+		/* only need to save callchain related to sched_switch event */
+		if (sched->show_callchain &&
+		    evsel__name_is(evsel, "sched:sched_switch") &&
+		    !evsel__has_callchain(evsel)) {
+			pr_info("Samples of sched_switch event do not have callchains.\n");
 			sched->show_callchain = 0;
 			symbol_conf.use_callchain = 0;
 		}
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index 37088cc0ff1b5f..647cb31a47c8f1 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -136,6 +136,7 @@ enum perf_output_field {
 	PERF_OUTPUT_RETIRE_LAT      = 1ULL << 40,
 	PERF_OUTPUT_DSOFF           = 1ULL << 41,
 	PERF_OUTPUT_DISASM          = 1ULL << 42,
+	PERF_OUTPUT_BRSTACKDISASM   = 1ULL << 43,
 };
 
 struct perf_script {
@@ -210,6 +211,7 @@ struct output_option {
 	{.str = "vcpu", .field = PERF_OUTPUT_VCPU},
 	{.str = "cgroup", .field = PERF_OUTPUT_CGROUP},
 	{.str = "retire_lat", .field = PERF_OUTPUT_RETIRE_LAT},
+	{.str = "brstackdisasm", .field = PERF_OUTPUT_BRSTACKDISASM},
 };
 
 enum {
@@ -510,7 +512,8 @@ static int evsel__check_attr(struct evsel *evsel, struct perf_session *session)
 		       "selected. Hence, no address to lookup the source line number.\n");
 		return -EINVAL;
 	}
-	if ((PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN)) && !allow_user_set &&
+	if ((PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN) || PRINT_FIELD(BRSTACKDISASM))
+	    && !allow_user_set &&
 	    !(evlist__combined_branch_type(session->evlist) & PERF_SAMPLE_BRANCH_ANY)) {
 		pr_err("Display of branch stack assembler requested, but non all-branch filter set\n"
 		       "Hint: run 'perf record -b ...'\n");
@@ -1162,6 +1165,31 @@ out:
 	return ret;
 }
 
+static int any_dump_insn(struct perf_event_attr *attr __maybe_unused,
+			 struct perf_insn *x, uint64_t ip,
+			 u8 *inbuf, int inlen, int *lenp,
+			 FILE *fp)
+{
+#ifdef HAVE_LIBCAPSTONE_SUPPORT
+	if (PRINT_FIELD(BRSTACKDISASM)) {
+		int printed = fprintf_insn_asm(x->machine, x->thread, x->cpumode, x->is64bit,
+					       (uint8_t *)inbuf, inlen, ip, lenp,
+					       PRINT_INSN_IMM_HEX, fp);
+
+		if (printed > 0)
+			return printed;
+	}
+#endif
+	return fprintf(fp, "%s", dump_insn(x, ip, inbuf, inlen, lenp));
+}
+
+static int add_padding(FILE *fp, int printed, int padding)
+{
+	if (printed >= 0 && printed < padding)
+		printed += fprintf(fp, "%*s", padding - printed, "");
+	return printed;
+}
+
 static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
 			    struct perf_insn *x, u8 *inbuf, int len,
 			    int insn, FILE *fp, int *total_cycles,
@@ -1169,8 +1197,10 @@ static int ip__fprintf_jump(uint64_t ip, struct branch_entry *en,
 			    struct thread *thread)
 {
 	int ilen = 0;
-	int printed = fprintf(fp, "\t%016" PRIx64 "\t%-30s\t", ip,
-			      dump_insn(x, ip, inbuf, len, &ilen));
+	int printed = fprintf(fp, "\t%016" PRIx64 "\t", ip);
+
+	printed += add_padding(fp, any_dump_insn(attr, x, ip, inbuf, len, &ilen, fp), 30);
+	printed += fprintf(fp, "\t");
 
 	if (PRINT_FIELD(BRSTACKINSNLEN))
 		printed += fprintf(fp, "ilen: %d\t", ilen);
@@ -1262,6 +1292,7 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 		nr = max_blocks + 1;
 
 	x.thread = thread;
+	x.machine = machine;
 	x.cpu = sample->cpu;
 
 	printed += fprintf(fp, "%c", '\n');
@@ -1312,8 +1343,8 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 				break;
 			} else {
 				ilen = 0;
-				printed += fprintf(fp, "\t%016" PRIx64 "\t%s", ip,
-						   dump_insn(&x, ip, buffer + off, len - off, &ilen));
+				printed += fprintf(fp, "\t%016" PRIx64 "\t", ip);
+				printed += any_dump_insn(attr, &x, ip, buffer + off, len - off, &ilen, fp);
 				if (PRINT_FIELD(BRSTACKINSNLEN))
 					printed += fprintf(fp, "\tilen: %d", ilen);
 				printed += fprintf(fp, "\n");
@@ -1360,8 +1391,8 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 		if (len <= 0)
 			goto out;
 		ilen = 0;
-		printed += fprintf(fp, "\t%016" PRIx64 "\t%s", sample->ip,
-			dump_insn(&x, sample->ip, buffer, len, &ilen));
+		printed += fprintf(fp, "\t%016" PRIx64 "\t", sample->ip);
+		printed += any_dump_insn(attr, &x, sample->ip, buffer, len, &ilen, fp);
 		if (PRINT_FIELD(BRSTACKINSNLEN))
 			printed += fprintf(fp, "\tilen: %d", ilen);
 		printed += fprintf(fp, "\n");
@@ -1371,8 +1402,8 @@ static int perf_sample__fprintf_brstackinsn(struct perf_sample *sample,
 	}
 	for (off = 0; off <= end - start; off += ilen) {
 		ilen = 0;
-		printed += fprintf(fp, "\t%016" PRIx64 "\t%s", start + off,
-				   dump_insn(&x, start + off, buffer + off, len - off, &ilen));
+		printed += fprintf(fp, "\t%016" PRIx64 "\t", start + off);
+		printed += any_dump_insn(attr, &x, start + off, buffer + off, len - off, &ilen, fp);
 		if (PRINT_FIELD(BRSTACKINSNLEN))
 			printed += fprintf(fp, "\tilen: %d", ilen);
 		printed += fprintf(fp, "\n");
@@ -1517,7 +1548,8 @@ void script_fetch_insn(struct perf_sample *sample, struct thread *thread,
 static int perf_sample__fprintf_insn(struct perf_sample *sample,
 				     struct perf_event_attr *attr,
 				     struct thread *thread,
-				     struct machine *machine, FILE *fp)
+				     struct machine *machine, FILE *fp,
+				     struct addr_location *al)
 {
 	int printed = 0;
 
@@ -1531,9 +1563,9 @@ static int perf_sample__fprintf_insn(struct perf_sample *sample,
 	}
 	if (PRINT_FIELD(DISASM) && sample->insn_len) {
 		printed += fprintf(fp, "\t\t");
-		printed += sample__fprintf_insn_asm(sample, thread, machine, fp);
+		printed += sample__fprintf_insn_asm(sample, thread, machine, fp, al);
 	}
-	if (PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN))
+	if (PRINT_FIELD(BRSTACKINSN) || PRINT_FIELD(BRSTACKINSNLEN) || PRINT_FIELD(BRSTACKDISASM))
 		printed += perf_sample__fprintf_brstackinsn(sample, thread, attr, machine, fp);
 
 	return printed;
@@ -1606,7 +1638,7 @@ static int perf_sample__fprintf_bts(struct perf_sample *sample,
 	if (print_srcline_last)
 		printed += map__fprintf_srcline(al->map, al->addr, "\n  ", fp);
 
-	printed += perf_sample__fprintf_insn(sample, attr, thread, machine, fp);
+	printed += perf_sample__fprintf_insn(sample, attr, thread, machine, fp, al);
 	printed += fprintf(fp, "\n");
 	if (PRINT_FIELD(SRCCODE)) {
 		int ret = map__fprintf_srccode(al->map, al->addr, stdout,
@@ -2259,7 +2291,7 @@ static void process_event(struct perf_script *script,
 
 	if (evsel__is_bpf_output(evsel) && PRINT_FIELD(BPF_OUTPUT))
 		perf_sample__fprintf_bpf_output(sample, fp);
-	perf_sample__fprintf_insn(sample, attr, thread, machine, fp);
+	perf_sample__fprintf_insn(sample, attr, thread, machine, fp, al);
 
 	if (PRINT_FIELD(PHYS_ADDR))
 		fprintf(fp, "%16" PRIx64, sample->phys_addr);
@@ -3471,7 +3503,7 @@ static int check_ev_match(char *dir_name, char *scriptname,
 
 			match = 0;
 			evlist__for_each_entry(session->evlist, pos) {
-				if (!strcmp(evsel__name(pos), evname)) {
+				if (evsel__name_is(pos, evname)) {
 					match = 1;
 					break;
 				}
@@ -3806,7 +3838,7 @@ static int parse_insn_trace(const struct option *opt __maybe_unused,
 	if (ret < 0)
 		return ret;
 
-	itrace_parse_synth_opts(opt, "i0ns", 0);
+	itrace_parse_synth_opts(opt, "i0nse", 0);
 	symbol_conf.nanosecs = true;
 	return 0;
 }
@@ -3939,7 +3971,7 @@ int cmd_script(int argc, const char **argv)
 		     "Fields: comm,tid,pid,time,cpu,event,trace,ip,sym,dso,dsoff,"
 		     "addr,symoff,srcline,period,iregs,uregs,brstack,"
 		     "brstacksym,flags,data_src,weight,bpf-output,brstackinsn,"
-		     "brstackinsnlen,brstackoff,callindent,insn,disasm,insnlen,synth,"
+		     "brstackinsnlen,brstackdisasm,brstackoff,callindent,insn,disasm,insnlen,synth,"
 		     "phys_addr,metric,misc,srccode,ipc,tod,data_page_size,"
 		     "code_page_size,ins_lat,machine_pid,vcpu,cgroup,retire_lat",
 		     parse_output_fields),
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 6bba1a89d03015..65a3dd7ffac30c 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -164,26 +164,6 @@ static struct perf_stat_config stat_config = {
 	.iostat_run		= false,
 };
 
-static bool cpus_map_matched(struct evsel *a, struct evsel *b)
-{
-	if (!a->core.cpus && !b->core.cpus)
-		return true;
-
-	if (!a->core.cpus || !b->core.cpus)
-		return false;
-
-	if (perf_cpu_map__nr(a->core.cpus) != perf_cpu_map__nr(b->core.cpus))
-		return false;
-
-	for (int i = 0; i < perf_cpu_map__nr(a->core.cpus); i++) {
-		if (perf_cpu_map__cpu(a->core.cpus, i).cpu !=
-		    perf_cpu_map__cpu(b->core.cpus, i).cpu)
-			return false;
-	}
-
-	return true;
-}
-
 static void evlist__check_cpu_maps(struct evlist *evlist)
 {
 	struct evsel *evsel, *warned_leader = NULL;
@@ -194,7 +174,7 @@ static void evlist__check_cpu_maps(struct evlist *evlist)
 		/* Check that leader matches cpus with each member. */
 		if (leader == evsel)
 			continue;
-		if (cpus_map_matched(leader, evsel))
+		if (perf_cpu_map__equal(leader->core.cpus, evsel->core.cpus))
 			continue;
 
 		/* If there's mismatch disable the group and warn user. */
@@ -1319,10 +1299,9 @@ static int cpu__get_cache_id_from_map(struct perf_cpu cpu, char *map)
 	 * be the first online CPU in the cache domain else use the
 	 * first online CPU of the cache domain as the ID.
 	 */
-	if (perf_cpu_map__has_any_cpu_or_is_empty(cpu_map))
+	id = perf_cpu_map__min(cpu_map).cpu;
+	if (id == -1)
 		id = cpu.cpu;
-	else
-		id = perf_cpu_map__cpu(cpu_map, 0).cpu;
 
 	/* Free the perf_cpu_map used to find the cache ID */
 	perf_cpu_map__put(cpu_map);
@@ -1642,7 +1621,7 @@ static int perf_stat_init_aggr_mode(void)
 	 * taking the highest cpu number to be the size of
 	 * the aggregation translate cpumap.
 	 */
-	if (!perf_cpu_map__has_any_cpu_or_is_empty(evsel_list->core.user_requested_cpus))
+	if (!perf_cpu_map__is_any_cpu_or_is_empty(evsel_list->core.user_requested_cpus))
 		nr = perf_cpu_map__max(evsel_list->core.user_requested_cpus).cpu;
 	else
 		nr = 0;
@@ -2106,6 +2085,7 @@ static int add_default_attributes(void)
 						stat_config.metric_no_threshold,
 						stat_config.user_requested_cpu_list,
 						stat_config.system_wide,
+						stat_config.hardware_aware_grouping,
 						&stat_config.metric_events);
 	}
 
@@ -2139,6 +2119,7 @@ static int add_default_attributes(void)
 						stat_config.metric_no_threshold,
 						stat_config.user_requested_cpu_list,
 						stat_config.system_wide,
+						stat_config.hardware_aware_grouping,
 						&stat_config.metric_events);
 	}
 
@@ -2173,6 +2154,7 @@ static int add_default_attributes(void)
 						/*metric_no_threshold=*/true,
 						stat_config.user_requested_cpu_list,
 						stat_config.system_wide,
+						stat_config.hardware_aware_grouping,
 						&stat_config.metric_events) < 0)
 			return -1;
 	}
@@ -2214,6 +2196,7 @@ static int add_default_attributes(void)
 							/*metric_no_threshold=*/true,
 							stat_config.user_requested_cpu_list,
 							stat_config.system_wide,
+							stat_config.hardware_aware_grouping,
 							&stat_config.metric_events) < 0)
 				return -1;
 
@@ -2334,7 +2317,7 @@ int process_stat_config_event(struct perf_session *session,
 
 	perf_event__read_stat_config(&stat_config, &event->stat_config);
 
-	if (perf_cpu_map__has_any_cpu_or_is_empty(st->cpus)) {
+	if (perf_cpu_map__is_empty(st->cpus)) {
 		if (st->aggr_mode != AGGR_UNSET)
 			pr_warning("warning: processing task data, aggregation mode not set\n");
 	} else if (st->aggr_mode != AGGR_UNSET) {
@@ -2748,6 +2731,7 @@ int cmd_stat(int argc, const char **argv)
 						stat_config.metric_no_threshold,
 						stat_config.user_requested_cpu_list,
 						stat_config.system_wide,
+						stat_config.hardware_aware_grouping,
 						&stat_config.metric_events);
 
 		zfree(&metrics);
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 90eaff8c0f6e3a..e5fef39c34bf40 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -947,6 +947,15 @@ static const struct syscall_fmt syscall_fmts[] = {
 	  .arg = { [1] = STRARRAY(op, epoll_ctl_ops), }, },
 	{ .name	    = "eventfd2",
 	  .arg = { [1] = { .scnprintf = SCA_EFD_FLAGS, /* flags */ }, }, },
+	{ .name     = "faccessat",
+	  .arg = { [0] = { .scnprintf = SCA_FDAT,	  /* dirfd */ },
+		   [1] = { .scnprintf = SCA_FILENAME,	  /* pathname */ },
+		   [2] = { .scnprintf = SCA_ACCMODE,	  /* mode */ }, }, },
+	{ .name     = "faccessat2",
+	  .arg = { [0] = { .scnprintf = SCA_FDAT,	  /* dirfd */ },
+		   [1] = { .scnprintf = SCA_FILENAME,	  /* pathname */ },
+		   [2] = { .scnprintf = SCA_ACCMODE,	  /* mode */ },
+		   [3] = { .scnprintf = SCA_FACCESSAT2_FLAGS, /* flags */ }, }, },
 	{ .name	    = "fchmodat",
 	  .arg = { [0] = { .scnprintf = SCA_FDAT, /* fd */ }, }, },
 	{ .name	    = "fchownat",
@@ -969,7 +978,6 @@ static const struct syscall_fmt syscall_fmts[] = {
 		   [1] = { .scnprintf = SCA_FILENAME,	  /* path */ },
 		   [2] = { .scnprintf = SCA_FSPICK_FLAGS, /* flags */ }, }, },
 	{ .name	    = "fstat", .alias = "newfstat", },
-	{ .name	    = "fstatat", .alias = "newfstatat", },
 	{ .name	    = "futex",
 	  .arg = { [1] = { .scnprintf = SCA_FUTEX_OP, /* op */ },
 		   [5] = { .scnprintf = SCA_FUTEX_VAL3, /* val3 */ }, }, },
@@ -1049,8 +1057,12 @@ static const struct syscall_fmt syscall_fmts[] = {
 	  .arg = { [3] = { .scnprintf = SCA_MREMAP_FLAGS, /* flags */ }, }, },
 	{ .name	    = "name_to_handle_at",
 	  .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
-	{ .name	    = "newfstatat",
-	  .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
+	{ .name	    = "nanosleep",
+	  .arg = { [0] = { .scnprintf = SCA_TIMESPEC,  /* req */ }, }, },
+	{ .name	    = "newfstatat", .alias = "fstatat",
+	  .arg = { [0] = { .scnprintf = SCA_FDAT,	  /* dirfd */ },
+		   [1] = { .scnprintf = SCA_FILENAME,	  /* pathname */ },
+		   [3] = { .scnprintf = SCA_FS_AT_FLAGS, /* flags */ }, }, },
 	{ .name	    = "open",
 	  .arg = { [1] = { .scnprintf = SCA_OPEN_FLAGS, /* flags */ }, }, },
 	{ .name	    = "open_by_handle_at",
@@ -1142,7 +1154,7 @@ static const struct syscall_fmt syscall_fmts[] = {
 	{ .name	    = "stat", .alias = "newstat", },
 	{ .name	    = "statx",
 	  .arg = { [0] = { .scnprintf = SCA_FDAT,	 /* fdat */ },
-		   [2] = { .scnprintf = SCA_STATX_FLAGS, /* flags */ } ,
+		   [2] = { .scnprintf = SCA_FS_AT_FLAGS, /* flags */ } ,
 		   [3] = { .scnprintf = SCA_STATX_MASK,	 /* mask */ }, }, },
 	{ .name	    = "swapoff",
 	  .arg = { [0] = { .scnprintf = SCA_FILENAME, /* specialfile */ }, }, },
@@ -1160,7 +1172,9 @@ static const struct syscall_fmt syscall_fmts[] = {
 	  .arg = { [0] = { .scnprintf = SCA_FILENAME, /* name */ }, }, },
 	{ .name	    = "uname", .alias = "newuname", },
 	{ .name	    = "unlinkat",
-	  .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
+	  .arg = { [0] = { .scnprintf = SCA_FDAT,	  /* dfd */ },
+		   [1] = { .scnprintf = SCA_FILENAME,	  /* pathname */ },
+		   [2] = { .scnprintf = SCA_FS_AT_FLAGS,  /* flags */ }, }, },
 	{ .name	    = "utimensat",
 	  .arg = { [0] = { .scnprintf = SCA_FDAT, /* dirfd */ }, }, },
 	{ .name	    = "wait4",	    .errpid = true,
@@ -4902,7 +4916,7 @@ int cmd_trace(int argc, const char **argv)
 		goto out;
 	}
 	trace.syscalls.events.bpf_output = evlist__last(trace.evlist);
-	assert(!strcmp(evsel__name(trace.syscalls.events.bpf_output), "__augmented_syscalls__"));
+	assert(evsel__name_is(trace.syscalls.events.bpf_output, "__augmented_syscalls__"));
 skip_augmentation:
 #endif
 	err = -1;
@@ -4959,7 +4973,7 @@ skip_augmentation:
 	 */
 	if (trace.syscalls.events.bpf_output) {
 		evlist__for_each_entry(trace.evlist, evsel) {
-			bool raw_syscalls_sys_exit = strcmp(evsel__name(evsel), "raw_syscalls:sys_exit") == 0;
+			bool raw_syscalls_sys_exit = evsel__name_is(evsel, "raw_syscalls:sys_exit");
 
 			if (raw_syscalls_sys_exit) {
 				trace.raw_augmented_syscalls = true;
diff --git a/tools/perf/builtin.h b/tools/perf/builtin.h
index f2ab5bae2150be..f4375deabfa395 100644
--- a/tools/perf/builtin.h
+++ b/tools/perf/builtin.h
@@ -2,8 +2,10 @@
 #ifndef BUILTIN_H
 #define BUILTIN_H
 
+struct cmdnames;
+
 void list_common_cmds_help(void);
-const char *help_unknown_cmd(const char *cmd);
+const char *help_unknown_cmd(const char *cmd, struct cmdnames *main_cmds);
 
 int cmd_annotate(int argc, const char **argv);
 int cmd_bench(int argc, const char **argv);
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 66ba33dbcef22b..672421b858ac1a 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -9,23 +9,15 @@ FILES=(
   "include/uapi/linux/const.h"
   "include/uapi/drm/drm.h"
   "include/uapi/drm/i915_drm.h"
+  "include/uapi/linux/bits.h"
   "include/uapi/linux/fadvise.h"
-  "include/uapi/linux/fcntl.h"
-  "include/uapi/linux/fs.h"
   "include/uapi/linux/fscrypt.h"
   "include/uapi/linux/kcmp.h"
   "include/uapi/linux/kvm.h"
   "include/uapi/linux/in.h"
-  "include/uapi/linux/mount.h"
-  "include/uapi/linux/openat2.h"
   "include/uapi/linux/perf_event.h"
-  "include/uapi/linux/prctl.h"
-  "include/uapi/linux/sched.h"
   "include/uapi/linux/seccomp.h"
   "include/uapi/linux/stat.h"
-  "include/uapi/linux/usbdevice_fs.h"
-  "include/uapi/linux/vhost.h"
-  "include/uapi/sound/asound.h"
   "include/linux/bits.h"
   "include/vdso/bits.h"
   "include/linux/const.h"
@@ -38,9 +30,7 @@ FILES=(
   "arch/x86/include/asm/cpufeatures.h"
   "arch/x86/include/asm/inat_types.h"
   "arch/x86/include/asm/emulate_prefix.h"
-  "arch/x86/include/asm/irq_vectors.h"
   "arch/x86/include/asm/msr-index.h"
-  "arch/x86/include/uapi/asm/prctl.h"
   "arch/x86/lib/x86-opcode-map.txt"
   "arch/x86/tools/gen-insn-attr-x86.awk"
   "arch/arm/include/uapi/asm/perf_regs.h"
@@ -97,7 +87,18 @@ SYNC_CHECK_FILES=(
 
 declare -a BEAUTY_FILES
 BEAUTY_FILES=(
+  "arch/x86/include/asm/irq_vectors.h"
+  "arch/x86/include/uapi/asm/prctl.h"
   "include/linux/socket.h"
+  "include/uapi/linux/fcntl.h"
+  "include/uapi/linux/fs.h"
+  "include/uapi/linux/mount.h"
+  "include/uapi/linux/prctl.h"
+  "include/uapi/linux/sched.h"
+  "include/uapi/linux/stat.h"
+  "include/uapi/linux/usbdevice_fs.h"
+  "include/uapi/linux/vhost.h"
+  "include/uapi/sound/asound.h"
 )
 
 declare -a FAILURES
diff --git a/tools/perf/perf-archive.sh b/tools/perf/perf-archive.sh
index f94795794b3614..6ed7e52ab88175 100755
--- a/tools/perf/perf-archive.sh
+++ b/tools/perf/perf-archive.sh
@@ -34,7 +34,7 @@ if [ $UNPACK -eq 1 ]; then
 		TARGET=`find . -regex "\./perf.*\.tar\.bz2"`
 		TARGET_NUM=`echo -n "$TARGET" | grep -c '^'`
 
-		if [ -z "$TARGET" -o $TARGET_NUM -gt 1 ]; then
+		if [ -z "$TARGET" ] || [ $TARGET_NUM -gt 1 ]; then
 			echo -e "Error: $TARGET_NUM files found for unpacking:\n$TARGET"
 			echo "Provide the requested file as an argument"
 			exit 1
diff --git a/tools/perf/perf-completion.sh b/tools/perf/perf-completion.sh
index f224d79b89e69f..69cba3c170d5ad 100644
--- a/tools/perf/perf-completion.sh
+++ b/tools/perf/perf-completion.sh
@@ -108,6 +108,8 @@ __perf__ltrim_colon_completions()
 
 __perfcomp ()
 {
+	# Expansion of spaces to array is deliberate.
+	# shellcheck disable=SC2207
 	COMPREPLY=( $( compgen -W "$1" -- "$2" ) )
 }
 
@@ -127,13 +129,13 @@ __perf_prev_skip_opts ()
 
 	let i=cword-1
 	cmds_=$($cmd $1 --list-cmds)
-	prev_skip_opts=()
+	prev_skip_opts=""
 	while [ $i -ge 0 ]; do
-		if [[ ${words[i]} == $1 ]]; then
+		if [[ ${words[i]} == "$1" ]]; then
 			return
 		fi
 		for cmd_ in $cmds_; do
-			if [[ ${words[i]} == $cmd_ ]]; then
+			if [[ ${words[i]} == "$cmd_" ]]; then
 				prev_skip_opts=${words[i]}
 				return
 			fi
@@ -164,9 +166,10 @@ __perf_main ()
 		$prev_skip_opts == @(record|stat|top) ]]; then
 
 		local cur1=${COMP_WORDS[COMP_CWORD]}
-		local raw_evts=$($cmd list --raw-dump hw sw cache tracepoint pmu sdt)
+		local raw_evts
 		local arr s tmp result cpu_evts
 
+		raw_evts=$($cmd list --raw-dump hw sw cache tracepoint pmu sdt)
 		# aarch64 doesn't have /sys/bus/event_source/devices/cpu/events
 		if [[ `uname -m` != aarch64 ]]; then
 			cpu_evts=$(ls /sys/bus/event_source/devices/cpu/events)
@@ -175,10 +178,12 @@ __perf_main ()
 		if [[ "$cur1" == */* && ${cur1#*/} =~ ^[A-Z] ]]; then
 			OLD_IFS="$IFS"
 			IFS=" "
+			# Expansion of spaces to array is deliberate.
+			# shellcheck disable=SC2206
 			arr=($raw_evts)
 			IFS="$OLD_IFS"
 
-			for s in ${arr[@]}
+			for s in "${arr[@]}"
 			do
 				if [[ "$s" == *cpu/* ]]; then
 					tmp=${s#*cpu/}
@@ -200,11 +205,13 @@ __perf_main ()
 		fi
 	elif [[ $prev == @("--pfm-events") &&
 		$prev_skip_opts == @(record|stat|top) ]]; then
-	        local evts=$($cmd list --raw-dump pfm)
+		local evts
+		evts=$($cmd list --raw-dump pfm)
 		__perfcomp "$evts" "$cur"
 	elif [[ $prev == @("-M"|"--metrics") &&
 		$prev_skip_opts == @(stat) ]]; then
-	        local metrics=$($cmd list --raw-dump metric metricgroup)
+		local metrics
+		metrics=$($cmd list --raw-dump metric metricgroup)
 		__perfcomp "$metrics" "$cur"
 	else
 		# List subcommands for perf commands
@@ -278,6 +285,8 @@ if [[ -n ${ZSH_VERSION-} ]]; then
 		let cword=CURRENT-1
 		emulate ksh -c __perf_main
 		let _ret && _default && _ret=0
+		# _ret is only assigned 0 or 1, disable inaccurate analysis.
+		# shellcheck disable=SC2152
 		return _ret
 	}
 
diff --git a/tools/perf/perf.c b/tools/perf/perf.c
index 921bee0a643707..bd3f80b5bb4623 100644
--- a/tools/perf/perf.c
+++ b/tools/perf/perf.c
@@ -18,6 +18,7 @@
 #include <subcmd/run-command.h>
 #include "util/parse-events.h"
 #include <subcmd/parse-options.h>
+#include <subcmd/help.h>
 #include "util/debug.h"
 #include "util/event.h"
 #include "util/util.h" // usage()
@@ -458,7 +459,7 @@ static int libperf_print(enum libperf_print_level level,
 
 int main(int argc, const char **argv)
 {
-	int err;
+	int err, done_help = 0;
 	const char *cmd;
 	char sbuf[STRERR_BUFSIZE];
 
@@ -557,22 +558,32 @@ int main(int argc, const char **argv)
 	pthread__block_sigwinch();
 
 	while (1) {
-		static int done_help;
-
 		run_argv(&argc, &argv);
 
 		if (errno != ENOENT)
 			break;
 
 		if (!done_help) {
-			cmd = argv[0] = help_unknown_cmd(cmd);
+			struct cmdnames main_cmds = {};
+
+			for (unsigned int i = 0; i < ARRAY_SIZE(commands); i++) {
+				add_cmdname(&main_cmds,
+					    commands[i].cmd,
+					    strlen(commands[i].cmd));
+			}
+			cmd = argv[0] = help_unknown_cmd(cmd, &main_cmds);
+			clean_cmdnames(&main_cmds);
 			done_help = 1;
+			if (!cmd)
+				break;
 		} else
 			break;
 	}
 
-	fprintf(stderr, "Failed to run command '%s': %s\n",
-		cmd, str_error_r(errno, sbuf, sizeof(sbuf)));
+	if (cmd) {
+		fprintf(stderr, "Failed to run command '%s': %s\n",
+			cmd, str_error_r(errno, sbuf, sizeof(sbuf)));
+	}
 out:
 	if (debug_fp)
 		fclose(debug_fp);
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/cache.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/cache.json
index 7a2b7b200f1449..ac75f12e27bf5a 100644
--- a/tools/perf/pmu-events/arch/arm64/ampere/ampereone/cache.json
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereone/cache.json
@@ -9,7 +9,9 @@
         "ArchStdEvent": "L1D_CACHE_REFILL_RD"
     },
     {
-        "ArchStdEvent": "L1D_CACHE_INVAL"
+        "ArchStdEvent": "L1D_CACHE_INVAL",
+        "Errata": "Errata AC03_CPU_41",
+        "BriefDescription": "L1D cache invalidate. Impacted by errata -"
     },
     {
         "ArchStdEvent": "L1D_TLB_REFILL_RD"
diff --git a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/cache.json b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/cache.json
index c50d8e930b05ee..f4bfe7083a6bad 100644
--- a/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/cache.json
+++ b/tools/perf/pmu-events/arch/arm64/ampere/ampereonex/cache.json
@@ -9,7 +9,9 @@
         "ArchStdEvent": "L1D_CACHE_REFILL_RD"
     },
     {
-        "ArchStdEvent": "L1D_CACHE_INVAL"
+        "ArchStdEvent": "L1D_CACHE_INVAL",
+        "Errata": "Errata AC04_CPU_1",
+        "BriefDescription": "L1D cache invalidate. Impacted by errata -"
     },
     {
         "ArchStdEvent": "L1D_TLB_REFILL_RD"
diff --git a/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json b/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json
index ec2ff78e2b5f2c..3ab1d3a6638c46 100644
--- a/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json
+++ b/tools/perf/pmu-events/arch/s390/cf_z16/transaction.json
@@ -2,71 +2,71 @@
   {
     "BriefDescription": "Transaction count",
     "MetricName": "transaction",
-    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL"
+    "MetricExpr": "TX_C_TEND + TX_NC_TEND + TX_NC_TABORT + TX_C_TABORT_SPECIAL + TX_C_TABORT_NO_SPECIAL if has_event(TX_C_TEND) else 0"
   },
   {
     "BriefDescription": "Cycles per Instruction",
     "MetricName": "cpi",
-    "MetricExpr": "CPU_CYCLES / INSTRUCTIONS"
+    "MetricExpr": "CPU_CYCLES / INSTRUCTIONS if has_event(INSTRUCTIONS) else 0"
   },
   {
     "BriefDescription": "Problem State Instruction Ratio",
     "MetricName": "prbstate",
-    "MetricExpr": "(PROBLEM_STATE_INSTRUCTIONS / INSTRUCTIONS) * 100"
+    "MetricExpr": "(PROBLEM_STATE_INSTRUCTIONS / INSTRUCTIONS) * 100 if has_event(INSTRUCTIONS) else 0"
   },
   {
     "BriefDescription": "Level One Miss per 100 Instructions",
     "MetricName": "l1mp",
-    "MetricExpr": "((L1I_DIR_WRITES + L1D_DIR_WRITES) / INSTRUCTIONS) * 100"
+    "MetricExpr": "((L1I_DIR_WRITES + L1D_DIR_WRITES) / INSTRUCTIONS) * 100 if has_event(INSTRUCTIONS) else 0"
   },
   {
     "BriefDescription": "Percentage sourced from Level 2 cache",
     "MetricName": "l2p",
-    "MetricExpr": "((DCW_REQ + DCW_REQ_IV + ICW_REQ + ICW_REQ_IV) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100"
+    "MetricExpr": "((DCW_REQ + DCW_REQ_IV + ICW_REQ + ICW_REQ_IV) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100 if has_event(DCW_REQ) else 0"
   },
   {
     "BriefDescription": "Percentage sourced from Level 3 on same chip cache",
     "MetricName": "l3p",
-    "MetricExpr": "((DCW_REQ_CHIP_HIT + DCW_ON_CHIP + DCW_ON_CHIP_IV + DCW_ON_CHIP_CHIP_HIT + ICW_REQ_CHIP_HIT + ICW_ON_CHIP + ICW_ON_CHIP_IV + ICW_ON_CHIP_CHIP_HIT) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100"
+    "MetricExpr": "((DCW_REQ_CHIP_HIT + DCW_ON_CHIP + DCW_ON_CHIP_IV + DCW_ON_CHIP_CHIP_HIT + ICW_REQ_CHIP_HIT + ICW_ON_CHIP + ICW_ON_CHIP_IV + ICW_ON_CHIP_CHIP_HIT) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100 if has_event(DCW_REQ_CHIP_HIT) else 0"
   },
   {
     "BriefDescription": "Percentage sourced from Level 4 Local cache on same book",
     "MetricName": "l4lp",
-    "MetricExpr": "((DCW_REQ_DRAWER_HIT + DCW_ON_CHIP_DRAWER_HIT + DCW_ON_MODULE + DCW_ON_DRAWER + IDCW_ON_MODULE_IV + IDCW_ON_MODULE_CHIP_HIT + IDCW_ON_MODULE_DRAWER_HIT + IDCW_ON_DRAWER_IV + IDCW_ON_DRAWER_CHIP_HIT + IDCW_ON_DRAWER_DRAWER_HIT + ICW_REQ_DRAWER_HIT + ICW_ON_CHIP_DRAWER_HIT + ICW_ON_MODULE + ICW_ON_DRAWER) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100"
+    "MetricExpr": "((DCW_REQ_DRAWER_HIT + DCW_ON_CHIP_DRAWER_HIT + DCW_ON_MODULE + DCW_ON_DRAWER + IDCW_ON_MODULE_IV + IDCW_ON_MODULE_CHIP_HIT + IDCW_ON_MODULE_DRAWER_HIT + IDCW_ON_DRAWER_IV + IDCW_ON_DRAWER_CHIP_HIT + IDCW_ON_DRAWER_DRAWER_HIT + ICW_REQ_DRAWER_HIT + ICW_ON_CHIP_DRAWER_HIT + ICW_ON_MODULE + ICW_ON_DRAWER) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100 if has_event(DCW_REQ_DRAWER_HIT) else 0"
   },
   {
     "BriefDescription": "Percentage sourced from Level 4 Remote cache on different book",
     "MetricName": "l4rp",
-    "MetricExpr": "((DCW_OFF_DRAWER + IDCW_OFF_DRAWER_IV + IDCW_OFF_DRAWER_CHIP_HIT + IDCW_OFF_DRAWER_DRAWER_HIT + ICW_OFF_DRAWER) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100"
+    "MetricExpr": "((DCW_OFF_DRAWER + IDCW_OFF_DRAWER_IV + IDCW_OFF_DRAWER_CHIP_HIT + IDCW_OFF_DRAWER_DRAWER_HIT + ICW_OFF_DRAWER) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100 if has_event(DCW_OFF_DRAWER) else 0"
   },
   {
     "BriefDescription": "Percentage sourced from memory",
     "MetricName": "memp",
-    "MetricExpr": "((DCW_ON_CHIP_MEMORY + DCW_ON_MODULE_MEMORY + DCW_ON_DRAWER_MEMORY + DCW_OFF_DRAWER_MEMORY + ICW_ON_CHIP_MEMORY + ICW_ON_MODULE_MEMORY + ICW_ON_DRAWER_MEMORY + ICW_OFF_DRAWER_MEMORY) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100"
+    "MetricExpr": "((DCW_ON_CHIP_MEMORY + DCW_ON_MODULE_MEMORY + DCW_ON_DRAWER_MEMORY + DCW_OFF_DRAWER_MEMORY + ICW_ON_CHIP_MEMORY + ICW_ON_MODULE_MEMORY + ICW_ON_DRAWER_MEMORY + ICW_OFF_DRAWER_MEMORY) / (L1I_DIR_WRITES + L1D_DIR_WRITES)) * 100 if has_event(DCW_ON_CHIP_MEMORY) else 0"
   },
   {
     "BriefDescription": "Cycles per Instructions from Finite cache/memory",
     "MetricName": "finite_cpi",
-    "MetricExpr": "L1C_TLB2_MISSES / INSTRUCTIONS"
+    "MetricExpr": "L1C_TLB2_MISSES / INSTRUCTIONS if has_event(L1C_TLB2_MISSES) else 0"
   },
   {
     "BriefDescription": "Estimated Instruction Complexity CPI infinite Level 1",
     "MetricName": "est_cpi",
-    "MetricExpr": "(CPU_CYCLES / INSTRUCTIONS) - (L1C_TLB2_MISSES / INSTRUCTIONS)"
+    "MetricExpr": "(CPU_CYCLES / INSTRUCTIONS) - (L1C_TLB2_MISSES / INSTRUCTIONS) if has_event(INSTRUCTIONS) else 0"
   },
   {
     "BriefDescription": "Estimated Sourcing Cycles per Level 1 Miss",
     "MetricName": "scpl1m",
-    "MetricExpr": "L1C_TLB2_MISSES / (L1I_DIR_WRITES + L1D_DIR_WRITES)"
+    "MetricExpr": "L1C_TLB2_MISSES / (L1I_DIR_WRITES + L1D_DIR_WRITES) if has_event(L1C_TLB2_MISSES) else 0"
   },
   {
     "BriefDescription": "Estimated TLB CPU percentage of Total CPU",
     "MetricName": "tlb_percent",
-    "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / CPU_CYCLES) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES)) * 100"
+    "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / CPU_CYCLES) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES)) * 100 if has_event(CPU_CYCLES) else 0"
   },
   {
     "BriefDescription": "Estimated Cycles per TLB Miss",
     "MetricName": "tlb_miss",
-    "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / (DTLB2_WRITES + ITLB2_WRITES)) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES))"
+    "MetricExpr": "((DTLB2_MISSES + ITLB2_MISSES) / (DTLB2_WRITES + ITLB2_WRITES)) * (L1C_TLB2_MISSES / (L1I_PENALTY_CYCLES + L1D_PENALTY_CYCLES)) if has_event(DTLB2_MISSES) else 0"
   }
 ]
diff --git a/tools/perf/pmu-events/arch/s390/mapfile.csv b/tools/perf/pmu-events/arch/s390/mapfile.csv
index a918e1af77a573..b22648d127517a 100644
--- a/tools/perf/pmu-events/arch/s390/mapfile.csv
+++ b/tools/perf/pmu-events/arch/s390/mapfile.csv
@@ -5,4 +5,4 @@ Family-model,Version,Filename,EventType
 ^IBM.296[45].*[13]\.[1-5].[[:xdigit:]]+$,1,cf_z13,core
 ^IBM.390[67].*[13]\.[1-5].[[:xdigit:]]+$,3,cf_z14,core
 ^IBM.856[12].*3\.6.[[:xdigit:]]+$,3,cf_z15,core
-^IBM.393[12].*3\.7.[[:xdigit:]]+$,3,cf_z16,core
+^IBM.393[12].*$,3,cf_z16,core
diff --git a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
index f2d378c9d68f7e..0aed533da88241 100644
--- a/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/broadwellx/bdx-metrics.json
@@ -732,9 +732,8 @@
     {
         "BriefDescription": "Average Parallel L2 cache miss data reads",
         "MetricExpr": "tma_info_memory_latency_data_l2_mlp",
-        "MetricGroup": "Memory_BW;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_data_l2_mlp",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Memory_BW;Offcore",
+        "MetricName": "tma_info_memory_data_l2_mlp"
     },
     {
         "BriefDescription": "",
@@ -745,9 +744,8 @@
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
         "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t"
     },
     {
         "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
@@ -764,9 +762,8 @@
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]",
         "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l2_cache_fill_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_l2_cache_fill_bw_2t"
     },
     {
         "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
@@ -807,9 +804,8 @@
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
         "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l3_cache_fill_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_l3_cache_fill_bw_2t"
     },
     {
         "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
@@ -838,16 +834,14 @@
     {
         "BriefDescription": "Average Latency for L2 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "MetricGroup": "Memory_Lat;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_load_l2_miss_latency",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Memory_Lat;Offcore",
+        "MetricName": "tma_info_memory_load_l2_miss_latency"
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
-        "MetricGroup": "Memory_BW;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_load_l2_mlp",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Memory_BW;Offcore",
+        "MetricName": "tma_info_memory_load_l2_mlp"
     },
     {
         "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
@@ -867,9 +861,8 @@
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
         "MetricExpr": "tma_info_memory_tlb_page_walks_utilization",
-        "MetricGroup": "Mem;MemoryTLB;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_page_walks_utilization",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryTLB",
+        "MetricName": "tma_info_memory_page_walks_utilization"
     },
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
index 7f88b156f73b6f..297046818efe26 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/clx-metrics.json
@@ -670,23 +670,20 @@
     {
         "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
         "MetricExpr": "(100 * (1 - tma_core_bound / (((EXE_ACTIVITY.EXE_BOUND_0_PORTS + tma_core_bound * RS_EVENTS.EMPTY_CYCLES) / CPU_CLK_UNHALTED.THREAD * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CPU_CLK_UNHALTED.THREAD * CPU_CLK_UNHALTED.THREAD + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / CPU_CLK_UNHALTED.THREAD if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / CPU_CLK_UNHALTED.THREAD) if tma_core_bound < (((EXE_ACTIVITY.EXE_BOUND_0_PORTS + tma_core_bound * RS_EVENTS.EMPTY_CYCLES) / CPU_CLK_UNHALTED.THREAD * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CPU_CLK_UNHALTED.THREAD * CPU_CLK_UNHALTED.THREAD + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / CPU_CLK_UNHALTED.THREAD if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / CPU_CLK_UNHALTED.THREAD) else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)",
-        "MetricGroup": "Cor;SMT;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_botlnk_core_bound_likely",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Cor;SMT",
+        "MetricName": "tma_info_botlnk_core_bound_likely"
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck.",
         "MetricExpr": "100 * (100 * (tma_fetch_latency * (DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD) / ((ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / CPU_CLK_UNHALTED.THREAD + ICACHE_TAG.STALLS / CPU_CLK_UNHALTED.THREAD + (INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD + 9 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD) + min(2 * IDQ.MS_SWITCHES / CPU_CLK_UNHALTED.THREAD, 1) + DECODE.LCP / CPU_CLK_UNHALTED.THREAD + DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb)))",
-        "MetricGroup": "DSBmiss;Fed;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_botlnk_dsb_misses",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "DSBmiss;Fed",
+        "MetricName": "tma_info_botlnk_dsb_misses"
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck.",
         "MetricExpr": "100 * (100 * (tma_fetch_latency * ((ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / CPU_CLK_UNHALTED.THREAD) / ((ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / CPU_CLK_UNHALTED.THREAD + ICACHE_TAG.STALLS / CPU_CLK_UNHALTED.THREAD + (INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD + 9 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD) + min(2 * IDQ.MS_SWITCHES / CPU_CLK_UNHALTED.THREAD, 1) + DECODE.LCP / CPU_CLK_UNHALTED.THREAD + DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD)))",
-        "MetricGroup": "Fed;FetchLat;IcMiss;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_botlnk_ic_misses",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Fed;FetchLat;IcMiss",
+        "MetricName": "tma_info_botlnk_ic_misses"
     },
     {
         "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
@@ -1045,9 +1042,8 @@
     {
         "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
         "MetricExpr": "tma_info_memory_tlb_code_stlb_mpki",
-        "MetricGroup": "Fed;MemoryTLB;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_code_stlb_mpki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Fed;MemoryTLB",
+        "MetricName": "tma_info_memory_code_stlb_mpki"
     },
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
@@ -1088,9 +1084,8 @@
     {
         "BriefDescription": "Average Parallel L2 cache miss data reads",
         "MetricExpr": "tma_info_memory_latency_data_l2_mlp",
-        "MetricGroup": "Memory_BW;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_data_l2_mlp",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Memory_BW;Offcore",
+        "MetricName": "tma_info_memory_data_l2_mlp"
     },
     {
         "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)",
@@ -1107,9 +1102,8 @@
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
         "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t"
     },
     {
         "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
@@ -1132,23 +1126,20 @@
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]",
         "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l2_cache_fill_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_l2_cache_fill_bw_2t"
     },
     {
         "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction",
         "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / INST_RETIRED.ANY",
-        "MetricGroup": "L2Evicts;Mem;Server;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l2_evictions_nonsilent_pki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "L2Evicts;Mem;Server",
+        "MetricName": "tma_info_memory_l2_evictions_nonsilent_pki"
     },
     {
         "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)",
         "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / INST_RETIRED.ANY",
-        "MetricGroup": "L2Evicts;Mem;Server;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l2_evictions_silent_pki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "L2Evicts;Mem;Server",
+        "MetricName": "tma_info_memory_l2_evictions_silent_pki"
     },
     {
         "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
@@ -1189,9 +1180,8 @@
     {
         "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]",
         "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l3_cache_access_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW;Offcore",
+        "MetricName": "tma_info_memory_l3_cache_access_bw_2t"
     },
     {
         "BriefDescription": "",
@@ -1202,9 +1192,8 @@
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
         "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l3_cache_fill_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_l3_cache_fill_bw_2t"
     },
     {
         "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
@@ -1233,16 +1222,14 @@
     {
         "BriefDescription": "Average Latency for L2 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "MetricGroup": "Memory_Lat;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_load_l2_miss_latency",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Memory_Lat;Offcore",
+        "MetricName": "tma_info_memory_load_l2_miss_latency"
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
-        "MetricGroup": "Memory_BW;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_load_l2_mlp",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Memory_BW;Offcore",
+        "MetricName": "tma_info_memory_load_l2_mlp"
     },
     {
         "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
@@ -1253,9 +1240,8 @@
     {
         "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
         "MetricExpr": "tma_info_memory_tlb_load_stlb_mpki",
-        "MetricGroup": "Mem;MemoryTLB;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_load_stlb_mpki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryTLB",
+        "MetricName": "tma_info_memory_load_stlb_mpki"
     },
     {
         "BriefDescription": "Un-cacheable retired load per kilo instruction",
@@ -1273,16 +1259,14 @@
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
         "MetricExpr": "tma_info_memory_tlb_page_walks_utilization",
-        "MetricGroup": "Mem;MemoryTLB;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_page_walks_utilization",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryTLB",
+        "MetricName": "tma_info_memory_page_walks_utilization"
     },
     {
         "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
         "MetricExpr": "tma_info_memory_tlb_store_stlb_mpki",
-        "MetricGroup": "Mem;MemoryTLB;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_store_stlb_mpki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryTLB",
+        "MetricName": "tma_info_memory_store_stlb_mpki"
     },
     {
         "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
@@ -1313,9 +1297,8 @@
     {
         "BriefDescription": "Un-cacheable retired load per kilo instruction",
         "MetricExpr": "1e3 * MEM_LOAD_MISC_RETIRED.UC / INST_RETIRED.ANY",
-        "MetricGroup": "Mem;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_uc_load_pki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem",
+        "MetricName": "tma_info_memory_uc_load_pki"
     },
     {
         "BriefDescription": "",
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/frontend.json b/tools/perf/pmu-events/arch/x86/cascadelakex/frontend.json
index 095904c7700198..d6f543471b2436 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/frontend.json
@@ -19,7 +19,7 @@
         "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches",
         "EventCode": "0xAB",
         "EventName": "DSB2MITE_SWITCHES.COUNT",
-        "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses.\nNote: Invoking MITE requires two or three cycles delay.",
+        "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses. Note: Invoking MITE requires two or three cycles delay.",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -267,11 +267,11 @@
         "UMask": "0x4"
     },
     {
-        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops [This event is alias to IDQ.DSB_CYCLES_OK]",
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 or more Uops [This event is alias to IDQ.DSB_CYCLES_OK]",
         "CounterMask": "4",
         "EventCode": "0x79",
         "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
-        "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.DSB_CYCLES_OK]",
+        "PublicDescription": "Counts the number of cycles 4 or more uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.DSB_CYCLES_OK]",
         "SampleAfterValue": "2000003",
         "UMask": "0x18"
     },
@@ -321,11 +321,11 @@
         "UMask": "0x18"
     },
     {
-        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]",
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 or more Uops [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]",
         "CounterMask": "4",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]",
+        "PublicDescription": "Counts the number of cycles 4 or more uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]",
         "SampleAfterValue": "2000003",
         "UMask": "0x18"
     },
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/memory.json b/tools/perf/pmu-events/arch/x86/cascadelakex/memory.json
index a00ad0aaf1bad7..c69b2c33334b5e 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/memory.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/memory.json
@@ -6866,7 +6866,7 @@
         "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).",
         "EventCode": "0xC9",
         "EventName": "RTM_RETIRED.ABORTED",
-        "PEBS": "1",
+        "PEBS": "2",
         "PublicDescription": "Number of times RTM abort was triggered.",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/other.json b/tools/perf/pmu-events/arch/x86/cascadelakex/other.json
index 3ab5e91a4c1c72..95d42ac3671787 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/other.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/other.json
@@ -19,7 +19,7 @@
         "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule.",
         "EventCode": "0x28",
         "EventName": "CORE_POWER.LVL2_TURBO_LICENSE",
-        "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server michroarchtecture).  This includes high current AVX 512-bit instructions.",
+        "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server microarchitecture).  This includes high current AVX 512-bit instructions.",
         "SampleAfterValue": "200003",
         "UMask": "0x20"
     },
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/pipeline.json b/tools/perf/pmu-events/arch/x86/cascadelakex/pipeline.json
index 66d686cc933e35..c50ddf5b40dd09 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/pipeline.json
@@ -396,7 +396,7 @@
         "Errata": "SKL091, SKL044",
         "EventCode": "0xC0",
         "EventName": "INST_RETIRED.NOP",
-        "PEBS": "1",
+        "PEBS": "2",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-interconnect.json
index 1a342dff1503ac..3fe9ce483bbef3 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/uncore-interconnect.json
@@ -38,7 +38,7 @@
         "EventCode": "0x10",
         "EventName": "UNC_I_COHERENT_OPS.CLFLUSH",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x80",
         "Unit": "IRP"
     },
@@ -47,7 +47,7 @@
         "EventCode": "0x10",
         "EventName": "UNC_I_COHERENT_OPS.CRD",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x2",
         "Unit": "IRP"
     },
@@ -56,7 +56,7 @@
         "EventCode": "0x10",
         "EventName": "UNC_I_COHERENT_OPS.DRD",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x4",
         "Unit": "IRP"
     },
@@ -65,7 +65,7 @@
         "EventCode": "0x10",
         "EventName": "UNC_I_COHERENT_OPS.PCIDCAHINT",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x20",
         "Unit": "IRP"
     },
@@ -74,7 +74,7 @@
         "EventCode": "0x10",
         "EventName": "UNC_I_COHERENT_OPS.PCIRDCUR",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x1",
         "Unit": "IRP"
     },
@@ -101,7 +101,7 @@
         "EventCode": "0x10",
         "EventName": "UNC_I_COHERENT_OPS.WBMTOI",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x40",
         "Unit": "IRP"
     },
@@ -500,7 +500,7 @@
         "EventCode": "0x11",
         "EventName": "UNC_I_TRANSACTIONS.WRITES",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore.  This can be filtered based on request type in addition to the source queue.  Note the special filtering equation.  We do OR-reduction on the request type.  If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Trackes only write requests.  Each write request should have a prefetch, so there is no need to explicitly track these requests.  For writes that are tickled and have to retry, the counter will be incremented for each retry.",
+        "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore.  This can be filtered based on request type in addition to the source queue.  Note the special filtering equation.  We do OR-reduction on the request type.  If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only write requests.  Each write request should have a prefetch, so there is no need to explicitly track these requests.  For writes that are tickled and have to retry, the counter will be incremented for each retry.",
         "UMask": "0x2",
         "Unit": "IRP"
     },
diff --git a/tools/perf/pmu-events/arch/x86/cascadelakex/virtual-memory.json b/tools/perf/pmu-events/arch/x86/cascadelakex/virtual-memory.json
index f59405877ae8bc..73feadaf767406 100644
--- a/tools/perf/pmu-events/arch/x86/cascadelakex/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/cascadelakex/virtual-memory.json
@@ -205,7 +205,7 @@
         "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake.",
         "EventCode": "0x85",
         "EventName": "ITLB_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture.",
+        "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake microarchitecture.",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json
index 9e53da55d0c118..93d99318a62390 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/frontend.json
@@ -267,7 +267,7 @@
         "CounterMask": "6",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json
index e8bf7c9c44e1a3..5420f529f49185 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/memory.json
@@ -264,6 +264,7 @@
         "BriefDescription": "Number of times an RTM execution aborted.",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED",
+        "PEBS": "1",
         "PublicDescription": "Counts the number of times RTM abort was triggered.",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json
index 1f8200fb896476..e2086bedeca809 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/pipeline.json
@@ -428,6 +428,7 @@
         "BriefDescription": "INST_RETIRED.MACRO_FUSED",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.MACRO_FUSED",
+        "PEBS": "1",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -435,6 +436,7 @@
         "BriefDescription": "Retired NOP instructions.",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.NOP",
+        "PEBS": "1",
         "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
@@ -451,6 +453,7 @@
         "BriefDescription": "Iterations of Repeat string retired instructions.",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.REP_ITERATION",
+        "PEBS": "1",
         "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-cache.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-cache.json
index 86a8f3b7fe1d6a..141dab46682e36 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-cache.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-cache.json
@@ -4198,6 +4198,42 @@
         "Unit": "CHA"
     },
     {
+        "BriefDescription": "ItoMCacheNear (partial write) transactions from an IO device that addresses memory on the local socket",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.   Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcd42ff04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "ItoMCacheNear (partial write) transactions from an IO device that addresses memory on a remote socket",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.   Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcd437f04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "ItoM (write) transactions from an IO device that addresses memory on the local socket",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOM_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.   Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcc42ff04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "ItoM (write) transactions from an IO device that addresses memory on a remote socket",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOM_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.   Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcc437f04",
+        "Unit": "CHA"
+    },
+    {
         "BriefDescription": "TOR Inserts; Misses from local IO",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS",
@@ -4207,7 +4243,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "TOR Inserts; ItoM misses from local IO",
+        "BriefDescription": "TOR Inserts : ItoM, indicating a full cacheline write request, from IO Devices that missed the LLC",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM",
         "PerPkg": "1",
@@ -4225,7 +4261,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "TOR Inserts; RdCur and FsRdCur misses from local IO",
+        "BriefDescription": "TOR Inserts; RdCur and FsRdCur requests from local IO that miss LLC",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR",
         "PerPkg": "1",
@@ -4252,6 +4288,24 @@
         "Unit": "CHA"
     },
     {
+        "BriefDescription": "PCIRDCUR (read) transactions from an IO device that addresses memory on a remote socket",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.   Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xc8f2ff04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "PCIRDCUR (read) transactions from an IO device that addresses memory on the local socket",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.   Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xc8f37f04",
+        "Unit": "CHA"
+    },
+    {
         "BriefDescription": "TOR Inserts; RFO from local IO",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IO_RFO",
@@ -5714,6 +5768,42 @@
         "Unit": "CHA"
     },
     {
+        "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC and targets local memory",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOMCACHENEAR_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.     Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcd42fe04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC and targets remote memory",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOMCACHENEAR_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.     Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcd437e04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "TOR Occupancy; ITOM misses from local IO and targets local memory",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.     Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcc42fe04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "TOR Occupancy; ITOM misses from local IO and targets remote memory",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.     Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcc437e04",
+        "Unit": "CHA"
+    },
+    {
         "BriefDescription": "TOR Occupancy; RdCur and FsRdCur misses from local IO",
         "EventCode": "0x36",
         "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR",
@@ -5723,6 +5813,24 @@
         "Unit": "CHA"
     },
     {
+        "BriefDescription": "TOR Occupancy; RdCur and FsRdCur misses from local IO and targets local memory",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.     Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xc8f2fe04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "TOR Occupancy; RdCur and FsRdCur misses from local IO and targets remote memory",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.     Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xc8f37e04",
+        "Unit": "CHA"
+    },
+    {
         "BriefDescription": "TOR Occupancy; RFO misses from local IO",
         "EventCode": "0x36",
         "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RFO",
diff --git a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-interconnect.json
index 65d088556bae8d..22bb490e96662d 100644
--- a/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/emeraldrapids/uncore-interconnect.json
@@ -4888,7 +4888,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (AD)",
+        "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO Ingress (V-EMIB) (AD)",
         "EventCode": "0x4B",
         "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.AD",
         "PerPkg": "1",
@@ -4897,7 +4897,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (AK)",
+        "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO Ingress (V-EMIB) (AK)",
         "EventCode": "0x4B",
         "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.AK",
         "PerPkg": "1",
@@ -4906,7 +4906,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (AKC)",
+        "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO Ingress (V-EMIB) (AKC)",
         "EventCode": "0x4B",
         "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.AKC",
         "PerPkg": "1",
@@ -4915,7 +4915,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (BL)",
+        "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO Ingress (V-EMIB) (BL)",
         "EventCode": "0x4B",
         "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.BL",
         "PerPkg": "1",
@@ -4924,7 +4924,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (IV)",
+        "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO Ingress (V-EMIB) (IV)",
         "EventCode": "0x4B",
         "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.IV",
         "PerPkg": "1",
@@ -5291,7 +5291,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0xe",
         "Unit": "UPI"
     },
@@ -5300,7 +5300,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x10e",
         "Unit": "UPI"
     },
@@ -5309,7 +5309,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0xf",
         "Unit": "UPI"
     },
@@ -5318,7 +5318,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x10f",
         "Unit": "UPI"
     },
@@ -5763,7 +5763,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0xe",
         "Unit": "UPI"
     },
@@ -5772,7 +5772,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x10e",
         "Unit": "UPI"
     },
@@ -5781,7 +5781,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0xf",
         "Unit": "UPI"
     },
@@ -5790,7 +5790,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x10f",
         "Unit": "UPI"
     },
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json b/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json
index daa0639bb1cabe..90292dc03d33e2 100644
--- a/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/grandridge/pipeline.json
@@ -249,10 +249,17 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.",
+        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]",
         "EventCode": "0x73",
         "EventName": "TOPDOWN_BAD_SPECULATION.ALL",
-        "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
+        "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]",
+        "SampleAfterValue": "1000003"
+    },
+    {
+        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL]",
+        "EventCode": "0x73",
+        "EventName": "TOPDOWN_BAD_SPECULATION.ALL_P",
+        "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL]",
         "SampleAfterValue": "1000003"
     },
     {
@@ -284,7 +291,7 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls",
+        "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL_P]",
         "EventCode": "0x74",
         "EventName": "TOPDOWN_BE_BOUND.ALL",
         "SampleAfterValue": "1000003"
@@ -297,6 +304,12 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL]",
+        "EventCode": "0x74",
+        "EventName": "TOPDOWN_BE_BOUND.ALL_P",
+        "SampleAfterValue": "1000003"
+    },
+    {
         "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to memory reservation stall (scheduler not being able to accept another uop).  This could be caused by RSV full or load/store buffer block.",
         "EventCode": "0x74",
         "EventName": "TOPDOWN_BE_BOUND.MEM_SCHEDULER",
@@ -318,6 +331,13 @@
         "UMask": "0x20"
     },
     {
+        "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to ROB full",
+        "EventCode": "0x74",
+        "EventName": "TOPDOWN_BE_BOUND.REORDER_BUFFER",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x40"
+    },
+    {
         "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to iq/jeu scoreboards or ms scb",
         "EventCode": "0x74",
         "EventName": "TOPDOWN_BE_BOUND.SERIALIZATION",
@@ -325,12 +345,18 @@
         "UMask": "0x10"
     },
     {
-        "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls",
+        "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls [This event is alias to TOPDOWN_FE_BOUND.ALL_P]",
         "EventCode": "0x71",
         "EventName": "TOPDOWN_FE_BOUND.ALL",
         "SampleAfterValue": "1000003"
     },
     {
+        "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls [This event is alias to TOPDOWN_FE_BOUND.ALL]",
+        "EventCode": "0x71",
+        "EventName": "TOPDOWN_FE_BOUND.ALL_P",
+        "SampleAfterValue": "1000003"
+    },
+    {
         "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BAClear",
         "EventCode": "0x71",
         "EventName": "TOPDOWN_FE_BOUND.BRANCH_DETECT",
@@ -402,13 +428,20 @@
         "UMask": "0x4"
     },
     {
-        "BriefDescription": "Counts the number of consumed retirement slots.  Similar to UOPS_RETIRED.ALL",
+        "BriefDescription": "Counts the number of consumed retirement slots.  Similar to UOPS_RETIRED.ALL [This event is alias to TOPDOWN_RETIRING.ALL_P]",
         "EventCode": "0x72",
         "EventName": "TOPDOWN_RETIRING.ALL",
         "PEBS": "1",
         "SampleAfterValue": "1000003"
     },
     {
+        "BriefDescription": "Counts the number of consumed retirement slots.  Similar to UOPS_RETIRED.ALL [This event is alias to TOPDOWN_RETIRING.ALL]",
+        "EventCode": "0x72",
+        "EventName": "TOPDOWN_RETIRING.ALL_P",
+        "PEBS": "1",
+        "SampleAfterValue": "1000003"
+    },
+    {
         "BriefDescription": "Counts the number of uops issued by the front end every cycle.",
         "EventCode": "0x0e",
         "EventName": "UOPS_ISSUED.ANY",
diff --git a/tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json b/tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json
index 74dfd9272cef87..36614429dd720a 100644
--- a/tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json
+++ b/tools/perf/pmu-events/arch/x86/grandridge/uncore-cache.json
@@ -5,7 +5,6 @@
         "EventName": "UNC_CHACMS_CLOCKTICKS",
         "PerPkg": "1",
         "PortMask": "0x000",
-        "PublicDescription": "UNC_CHACMS_CLOCKTICKS",
         "Unit": "CHACMS"
     },
     {
@@ -1217,6 +1216,15 @@
         "Unit": "CHA"
     },
     {
+        "BriefDescription": "TOR Occupancy for Data read opt from local IA that miss the cache",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT",
+        "PerPkg": "1",
+        "PublicDescription": "TOR Occupancy : DRd_Opts issued by iA Cores",
+        "UMask": "0xc827ff01",
+        "Unit": "CHA"
+    },
+    {
         "BriefDescription": "TOR Occupancy for Data read opt prefetch from local IA that miss the cache",
         "EventCode": "0x36",
         "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_DRD_OPT_PREF",
@@ -1253,6 +1261,15 @@
         "Unit": "CHA"
     },
     {
+        "BriefDescription": "TOR Occupancy for Data read opt from local IA that hit the cache",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT",
+        "PerPkg": "1",
+        "PublicDescription": "TOR Occupancy : DRd_Opts issued by iA Cores that hit the LLC",
+        "UMask": "0xc827fd01",
+        "Unit": "CHA"
+    },
+    {
         "BriefDescription": "TOR Occupancy for Data read opt prefetch from local IA that hit the cache",
         "EventCode": "0x36",
         "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_HIT_DRD_OPT_PREF",
@@ -1406,6 +1423,15 @@
         "Unit": "CHA"
     },
     {
+        "BriefDescription": "TOR Occupancy for Data read opt from local IA that miss the cache",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT",
+        "PerPkg": "1",
+        "PublicDescription": "TOR Occupancy : DRd_Opt issued by iA Cores that missed the LLC",
+        "UMask": "0xc827fe01",
+        "Unit": "CHA"
+    },
+    {
         "BriefDescription": "TOR Occupancy for Data read opt prefetch from local IA that miss the cache",
         "EventCode": "0x36",
         "EventName": "UNC_CHA_TOR_OCCUPANCY.IA_MISS_DRD_OPT_PREF",
diff --git a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
index 21e2cb5e31783d..83d50d80a148e3 100644
--- a/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/haswellx/hsx-metrics.json
@@ -618,9 +618,8 @@
     {
         "BriefDescription": "Average Parallel L2 cache miss data reads",
         "MetricExpr": "tma_info_memory_latency_data_l2_mlp",
-        "MetricGroup": "Memory_BW;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_data_l2_mlp",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Memory_BW;Offcore",
+        "MetricName": "tma_info_memory_data_l2_mlp"
     },
     {
         "BriefDescription": "",
@@ -631,9 +630,8 @@
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
         "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t"
     },
     {
         "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
@@ -650,9 +648,8 @@
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]",
         "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l2_cache_fill_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_l2_cache_fill_bw_2t"
     },
     {
         "BriefDescription": "L2 cache true misses per kilo instruction for retired demand loads",
@@ -669,9 +666,8 @@
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
         "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l3_cache_fill_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_l3_cache_fill_bw_2t"
     },
     {
         "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
@@ -700,16 +696,14 @@
     {
         "BriefDescription": "Average Latency for L2 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "MetricGroup": "Memory_Lat;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_load_l2_miss_latency",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Memory_Lat;Offcore",
+        "MetricName": "tma_info_memory_load_l2_miss_latency"
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
-        "MetricGroup": "Memory_BW;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_load_l2_mlp",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Memory_BW;Offcore",
+        "MetricName": "tma_info_memory_load_l2_mlp"
     },
     {
         "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
@@ -729,9 +723,8 @@
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
         "MetricExpr": "tma_info_memory_tlb_page_walks_utilization",
-        "MetricGroup": "Mem;MemoryTLB;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_page_walks_utilization",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryTLB",
+        "MetricName": "tma_info_memory_page_walks_utilization"
     },
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
diff --git a/tools/perf/pmu-events/arch/x86/icelakex/frontend.json b/tools/perf/pmu-events/arch/x86/icelakex/frontend.json
index f6edc4222f424f..66669d062e68a0 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/frontend.json
@@ -282,7 +282,7 @@
         "CounterMask": "5",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
diff --git a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
index c015b8277dc76d..769ba12bef876c 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/icx-metrics.json
@@ -667,23 +667,20 @@
     {
         "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
         "MetricExpr": "(100 * (1 - max(0, topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * INT_MISC.CLEARS_COUNT / slots - (CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * (topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * INT_MISC.CLEARS_COUNT / slots)) / (((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + max(0, topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * INT_MISC.CLEARS_COUNT / slots - (CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * (topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * INT_MISC.CLEARS_COUNT / slots)) * RS_EVENTS.EMPTY_CYCLES) / CPU_CLK_UNHALTED.THREAD * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CPU_CLK_UNHALTED.THREAD * CPU_CLK_UNHALTED.THREAD + (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * EXE_ACTIVITY.2_PORTS_UTIL)) / CPU_CLK_UNHALTED.THREAD if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * EXE_ACTIVITY.2_PORTS_UTIL) / CPU_CLK_UNHALTED.THREAD) if max(0, topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * INT_MISC.CLEARS_COUNT / slots - (CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * (topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * INT_MISC.CLEARS_COUNT / slots)) < (((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + max(0, topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * INT_MISC.CLEARS_COUNT / slots - (CYCLE_ACTIVITY.STALLS_MEM_ANY + EXE_ACTIVITY.BOUND_ON_STORES) / (CYCLE_ACTIVITY.STALLS_TOTAL + (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * EXE_ACTIVITY.2_PORTS_UTIL) + EXE_ACTIVITY.BOUND_ON_STORES) * (topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) + 5 * INT_MISC.CLEARS_COUNT / slots)) * RS_EVENTS.EMPTY_CYCLES) / CPU_CLK_UNHALTED.THREAD * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CPU_CLK_UNHALTED.THREAD * CPU_CLK_UNHALTED.THREAD + (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * EXE_ACTIVITY.2_PORTS_UTIL)) / CPU_CLK_UNHALTED.THREAD if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * EXE_ACTIVITY.2_PORTS_UTIL) / CPU_CLK_UNHALTED.THREAD) else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)",
-        "MetricGroup": "Cor;SMT;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_botlnk_core_bound_likely",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Cor;SMT",
+        "MetricName": "tma_info_botlnk_core_bound_likely"
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck.",
         "MetricExpr": "100 * (100 * ((5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING) / slots * (DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD) / (ICACHE_DATA.STALLS / CPU_CLK_UNHALTED.THREAD + ICACHE_TAG.STALLS / CPU_CLK_UNHALTED.THREAD + (INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD + 10 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD) + min(3 * IDQ.MS_SWITCHES / CPU_CLK_UNHALTED.THREAD, 1) + DECODE.LCP / CPU_CLK_UNHALTED.THREAD + DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD) + max(0, topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / slots - (5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING) / slots) * ((IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / (CPU_CLK_UNHALTED.DISTRIBUTED if #SMT_on else CPU_CLK_UNHALTED.THREAD) / 2) / ((IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / (CPU_CLK_UNHALTED.DISTRIBUTED if #SMT_on else CPU_CLK_UNHALTED.THREAD) / 2 + (IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / (CPU_CLK_UNHALTED.DISTRIBUTED if #SMT_on else CPU_CLK_UNHALTED.THREAD) / 2)))",
-        "MetricGroup": "DSBmiss;Fed;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_botlnk_dsb_misses",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "DSBmiss;Fed",
+        "MetricName": "tma_info_botlnk_dsb_misses"
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck.",
         "MetricExpr": "100 * (100 * ((5 * IDQ_UOPS_NOT_DELIVERED.CYCLES_0_UOPS_DELIV.CORE - INT_MISC.UOP_DROPPING) / slots * (ICACHE_DATA.STALLS / CPU_CLK_UNHALTED.THREAD) / (ICACHE_DATA.STALLS / CPU_CLK_UNHALTED.THREAD + ICACHE_TAG.STALLS / CPU_CLK_UNHALTED.THREAD + (INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD + 10 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD) + min(3 * IDQ.MS_SWITCHES / CPU_CLK_UNHALTED.THREAD, 1) + DECODE.LCP / CPU_CLK_UNHALTED.THREAD + DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD)))",
-        "MetricGroup": "Fed;FetchLat;IcMiss;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_botlnk_ic_misses",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Fed;FetchLat;IcMiss",
+        "MetricName": "tma_info_botlnk_ic_misses"
     },
     {
         "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
@@ -1045,16 +1042,14 @@
     {
         "BriefDescription": "\"Bus lock\" per kilo instruction",
         "MetricExpr": "tma_info_memory_mix_bus_lock_pki",
-        "MetricGroup": "Mem;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_bus_lock_pki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem",
+        "MetricName": "tma_info_memory_bus_lock_pki"
     },
     {
         "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
         "MetricExpr": "tma_info_memory_tlb_code_stlb_mpki",
-        "MetricGroup": "Fed;MemoryTLB;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_code_stlb_mpki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Fed;MemoryTLB",
+        "MetricName": "tma_info_memory_code_stlb_mpki"
     },
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
@@ -1095,9 +1090,8 @@
     {
         "BriefDescription": "Average Parallel L2 cache miss data reads",
         "MetricExpr": "tma_info_memory_latency_data_l2_mlp",
-        "MetricGroup": "Memory_BW;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_data_l2_mlp",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Memory_BW;Offcore",
+        "MetricName": "tma_info_memory_data_l2_mlp"
     },
     {
         "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)",
@@ -1114,9 +1108,8 @@
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
         "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t"
     },
     {
         "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
@@ -1139,23 +1132,20 @@
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]",
         "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l2_cache_fill_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_l2_cache_fill_bw_2t"
     },
     {
         "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction",
         "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / INST_RETIRED.ANY",
-        "MetricGroup": "L2Evicts;Mem;Server;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l2_evictions_nonsilent_pki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "L2Evicts;Mem;Server",
+        "MetricName": "tma_info_memory_l2_evictions_nonsilent_pki"
     },
     {
         "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)",
         "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / INST_RETIRED.ANY",
-        "MetricGroup": "L2Evicts;Mem;Server;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l2_evictions_silent_pki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "L2Evicts;Mem;Server",
+        "MetricName": "tma_info_memory_l2_evictions_silent_pki"
     },
     {
         "BriefDescription": "L2 cache hits per kilo instruction for all demand loads  (including speculative)",
@@ -1190,9 +1180,8 @@
     {
         "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]",
         "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l3_cache_access_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW;Offcore",
+        "MetricName": "tma_info_memory_l3_cache_access_bw_2t"
     },
     {
         "BriefDescription": "",
@@ -1203,9 +1192,8 @@
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
         "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l3_cache_fill_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_l3_cache_fill_bw_2t"
     },
     {
         "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
@@ -1240,23 +1228,20 @@
     {
         "BriefDescription": "Average Latency for L2 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "MetricGroup": "Memory_Lat;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_load_l2_miss_latency",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Memory_Lat;Offcore",
+        "MetricName": "tma_info_memory_load_l2_miss_latency"
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@",
-        "MetricGroup": "Memory_BW;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_load_l2_mlp",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Memory_BW;Offcore",
+        "MetricName": "tma_info_memory_load_l2_mlp"
     },
     {
         "BriefDescription": "Average Latency for L3 cache miss demand Loads",
         "MetricExpr": "cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,umask\\=0x10@ / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
-        "MetricGroup": "Memory_Lat;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_load_l3_miss_latency",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Memory_Lat;Offcore",
+        "MetricName": "tma_info_memory_load_l3_miss_latency"
     },
     {
         "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
@@ -1267,9 +1252,8 @@
     {
         "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
         "MetricExpr": "tma_info_memory_tlb_load_stlb_mpki",
-        "MetricGroup": "Mem;MemoryTLB;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_load_stlb_mpki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryTLB",
+        "MetricName": "tma_info_memory_load_stlb_mpki"
     },
     {
         "BriefDescription": "\"Bus lock\" per kilo instruction",
@@ -1293,16 +1277,14 @@
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
         "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (2 * (CPU_CLK_UNHALTED.DISTRIBUTED if #SMT_on else CPU_CLK_UNHALTED.THREAD))",
-        "MetricGroup": "Mem;MemoryTLB;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_page_walks_utilization",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryTLB",
+        "MetricName": "tma_info_memory_page_walks_utilization"
     },
     {
         "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
         "MetricExpr": "tma_info_memory_tlb_store_stlb_mpki",
-        "MetricGroup": "Mem;MemoryTLB;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_store_stlb_mpki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryTLB",
+        "MetricName": "tma_info_memory_store_stlb_mpki"
     },
     {
         "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
@@ -1332,9 +1314,8 @@
     {
         "BriefDescription": "Un-cacheable retired load per kilo instruction",
         "MetricExpr": "1e3 * MEM_LOAD_MISC_RETIRED.UC / INST_RETIRED.ANY",
-        "MetricGroup": "Mem;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_uc_load_pki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem",
+        "MetricName": "tma_info_memory_uc_load_pki"
     },
     {
         "BriefDescription": "",
diff --git a/tools/perf/pmu-events/arch/x86/icelakex/memory.json b/tools/perf/pmu-events/arch/x86/icelakex/memory.json
index f36ac04f8d76a5..875b584b84431e 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/memory.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/memory.json
@@ -319,6 +319,7 @@
         "BriefDescription": "Number of times an RTM execution aborted.",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED",
+        "PEBS": "1",
         "PublicDescription": "Counts the number of times RTM abort was triggered.",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
diff --git a/tools/perf/pmu-events/arch/x86/icelakex/uncore-cache.json b/tools/perf/pmu-events/arch/x86/icelakex/uncore-cache.json
index b6ce14ebf84418..a950ba3ddcb483 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/uncore-cache.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/uncore-cache.json
@@ -1580,7 +1580,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.CODE_READ",
+        "BriefDescription": "This event is deprecated.",
         "Deprecated": "1",
         "EventCode": "0x34",
         "EventName": "UNC_CHA_LLC_LOOKUP.CODE",
@@ -1677,7 +1677,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.DATA_READ",
+        "BriefDescription": "This event is deprecated.",
         "Deprecated": "1",
         "EventCode": "0x34",
         "EventName": "UNC_CHA_LLC_LOOKUP.DATA_READ_ALL",
@@ -6783,6 +6783,24 @@
         "Unit": "CHA"
     },
     {
+        "BriefDescription": "PCIRDCUR (read) transactions from an IO device that addresses memory on the local socket",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices and targets local memory : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.   Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xc8f2ff04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "PCIRDCUR (read) transactions from an IO device that addresses memory on a remote socket",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "TOR Inserts : PCIRdCurs issued by IO Devices and targets remote memory : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.   Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xc8f37f04",
+        "Unit": "CHA"
+    },
+    {
         "BriefDescription": "TOR Inserts : RFOs issued by IO Devices",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IO_RFO",
diff --git a/tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json
index a066a009c51178..6997e6f7d3664d 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/uncore-interconnect.json
@@ -13523,7 +13523,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0xe",
         "Unit": "UPI"
     },
@@ -13532,7 +13532,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x10e",
         "Unit": "UPI"
     },
@@ -13541,7 +13541,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0xf",
         "Unit": "UPI"
     },
@@ -13550,7 +13550,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x10f",
         "Unit": "UPI"
     },
@@ -13559,7 +13559,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.REQ",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Request : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Request : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x8",
         "Unit": "UPI"
     },
@@ -13568,7 +13568,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.REQ_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Request, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Request, Match Opcode : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x108",
         "Unit": "UPI"
     },
@@ -13577,7 +13577,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSPCNFLT",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Response - Conflict : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Response - Conflict : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x1aa",
         "Unit": "UPI"
     },
@@ -13586,7 +13586,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSPI",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Response - Invalid : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Response - Invalid : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x12a",
         "Unit": "UPI"
     },
@@ -13595,7 +13595,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_DATA",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Response - Data : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Response - Data : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0xc",
         "Unit": "UPI"
     },
@@ -13604,7 +13604,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_DATA_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Response - Data, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Response - Data, Match Opcode : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x10c",
         "Unit": "UPI"
     },
@@ -13613,7 +13613,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_NODATA",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Response - No Data : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Response - No Data : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0xa",
         "Unit": "UPI"
     },
@@ -13622,7 +13622,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.RSP_NODATA_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Response - No Data, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Response - No Data, Match Opcode : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x10a",
         "Unit": "UPI"
     },
@@ -13631,7 +13631,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.SNP",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Snoop : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Snoop : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x9",
         "Unit": "UPI"
     },
@@ -13640,7 +13640,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.SNP_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Snoop, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Snoop, Match Opcode : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x109",
         "Unit": "UPI"
     },
@@ -13649,7 +13649,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.WB",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Writeback : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Writeback : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0xd",
         "Unit": "UPI"
     },
@@ -13658,7 +13658,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.WB_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Writeback, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Writeback, Match Opcode : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x10d",
         "Unit": "UPI"
     },
@@ -14038,7 +14038,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0xe",
         "Unit": "UPI"
     },
@@ -14047,7 +14047,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x10e",
         "Unit": "UPI"
     },
@@ -14056,7 +14056,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0xf",
         "Unit": "UPI"
     },
@@ -14065,7 +14065,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x10f",
         "Unit": "UPI"
     },
@@ -14074,7 +14074,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.REQ",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Request : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Request : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x8",
         "Unit": "UPI"
     },
@@ -14083,7 +14083,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.REQ_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Request, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Request, Match Opcode : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x108",
         "Unit": "UPI"
     },
@@ -14092,7 +14092,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSPCNFLT",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Response - Conflict : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Response - Conflict : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x1aa",
         "Unit": "UPI"
     },
@@ -14101,7 +14101,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSPI",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Response - Invalid : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Response - Invalid : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x12a",
         "Unit": "UPI"
     },
@@ -14110,7 +14110,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_DATA",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Response - Data : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Response - Data : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0xc",
         "Unit": "UPI"
     },
@@ -14119,7 +14119,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_DATA_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Response - Data, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Response - Data, Match Opcode : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x10c",
         "Unit": "UPI"
     },
@@ -14128,7 +14128,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_NODATA",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Response - No Data : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Response - No Data : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0xa",
         "Unit": "UPI"
     },
@@ -14137,7 +14137,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.RSP_NODATA_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Response - No Data, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Response - No Data, Match Opcode : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x10a",
         "Unit": "UPI"
     },
@@ -14146,7 +14146,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.SNP",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Snoop : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Snoop : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x9",
         "Unit": "UPI"
     },
@@ -14155,7 +14155,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.SNP_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Snoop, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Snoop, Match Opcode : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x109",
         "Unit": "UPI"
     },
@@ -14164,7 +14164,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.WB",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Writeback : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Writeback : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0xd",
         "Unit": "UPI"
     },
@@ -14173,7 +14173,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.WB_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Writeback, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Writeback, Match Opcode : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x10d",
         "Unit": "UPI"
     },
diff --git a/tools/perf/pmu-events/arch/x86/icelakex/uncore-io.json b/tools/perf/pmu-events/arch/x86/icelakex/uncore-io.json
index 9cef8862c4283c..1b8a719b81a593 100644
--- a/tools/perf/pmu-events/arch/x86/icelakex/uncore-io.json
+++ b/tools/perf/pmu-events/arch/x86/icelakex/uncore-io.json
@@ -2477,17 +2477,6 @@
         "Unit": "IIO"
     },
     {
-        "BriefDescription": "Number requests sent to PCIe from main die : From IRP",
-        "EventCode": "0xC2",
-        "EventName": "UNC_IIO_NUM_REQ_FROM_CPU.IRP",
-        "FCMask": "0x07",
-        "PerPkg": "1",
-        "PortMask": "0xFF",
-        "PublicDescription": "Number requests sent to PCIe from main die : From IRP : Captures Posted/Non-posted allocations from IRP. i.e. either non-confined P2P traffic or from the CPU",
-        "UMask": "0x1",
-        "Unit": "IIO"
-    },
-    {
         "BriefDescription": "Number requests sent to PCIe from main die : From ITC",
         "EventCode": "0xC2",
         "EventName": "UNC_IIO_NUM_REQ_FROM_CPU.ITC",
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/cache.json b/tools/perf/pmu-events/arch/x86/lunarlake/cache.json
index 1823149067b5b4..fb48be357c4e7c 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/cache.json
@@ -31,7 +31,7 @@
         "EventCode": "0x2e",
         "EventName": "LONGEST_LAT_CACHE.REFERENCE",
         "PublicDescription": "Counts the number of cacheable memory requests that access the Last Level Cache (LLC). Requests include demand loads, reads for ownership (RFO), instruction fetches and L1 HW prefetches. If the platform has an L3 cache, the LLC is the L3 cache, otherwise it is the L2 cache. Counts on a per core basis.",
-        "SampleAfterValue": "1000003",
+        "SampleAfterValue": "200003",
         "UMask": "0x4f",
         "Unit": "cpu_atom"
     },
@@ -94,7 +94,7 @@
         "MSRIndex": "0x3F6",
         "MSRValue": "0x400",
         "PEBS": "2",
-        "SampleAfterValue": "1000003",
+        "SampleAfterValue": "200003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
     },
@@ -106,7 +106,7 @@
         "MSRIndex": "0x3F6",
         "MSRValue": "0x80",
         "PEBS": "2",
-        "SampleAfterValue": "1000003",
+        "SampleAfterValue": "200003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
     },
@@ -118,7 +118,7 @@
         "MSRIndex": "0x3F6",
         "MSRValue": "0x10",
         "PEBS": "2",
-        "SampleAfterValue": "1000003",
+        "SampleAfterValue": "200003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
     },
@@ -130,7 +130,7 @@
         "MSRIndex": "0x3F6",
         "MSRValue": "0x800",
         "PEBS": "2",
-        "SampleAfterValue": "1000003",
+        "SampleAfterValue": "200003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
     },
@@ -142,7 +142,7 @@
         "MSRIndex": "0x3F6",
         "MSRValue": "0x100",
         "PEBS": "2",
-        "SampleAfterValue": "1000003",
+        "SampleAfterValue": "200003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
     },
@@ -154,7 +154,7 @@
         "MSRIndex": "0x3F6",
         "MSRValue": "0x20",
         "PEBS": "2",
-        "SampleAfterValue": "1000003",
+        "SampleAfterValue": "200003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
     },
@@ -166,7 +166,7 @@
         "MSRIndex": "0x3F6",
         "MSRValue": "0x4",
         "PEBS": "2",
-        "SampleAfterValue": "1000003",
+        "SampleAfterValue": "200003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
     },
@@ -178,7 +178,7 @@
         "MSRIndex": "0x3F6",
         "MSRValue": "0x200",
         "PEBS": "2",
-        "SampleAfterValue": "1000003",
+        "SampleAfterValue": "200003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
     },
@@ -190,7 +190,7 @@
         "MSRIndex": "0x3F6",
         "MSRValue": "0x40",
         "PEBS": "2",
-        "SampleAfterValue": "1000003",
+        "SampleAfterValue": "200003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
     },
@@ -202,7 +202,7 @@
         "MSRIndex": "0x3F6",
         "MSRValue": "0x8",
         "PEBS": "2",
-        "SampleAfterValue": "1000003",
+        "SampleAfterValue": "200003",
         "UMask": "0x5",
         "Unit": "cpu_atom"
     },
@@ -212,7 +212,7 @@
         "EventCode": "0xd0",
         "EventName": "MEM_UOPS_RETIRED.STORE_LATENCY",
         "PEBS": "2",
-        "SampleAfterValue": "1000003",
+        "SampleAfterValue": "200003",
         "UMask": "0x6",
         "Unit": "cpu_atom"
     }
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json b/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json
index 5e4ef81b43d6fa..3a24934e8d6e9c 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/frontend.json
@@ -19,7 +19,7 @@
         "BriefDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.",
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CORE",
-        "PublicDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.\nSoftware can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
+        "PublicDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/memory.json b/tools/perf/pmu-events/arch/x86/lunarlake/memory.json
index 51d70ba00bd495..9c188d80b7b90b 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/memory.json
@@ -155,7 +155,7 @@
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3FBFC00001",
+        "MSRValue": "0xFE7F8000001",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
@@ -175,7 +175,7 @@
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x3FBFC00002",
+        "MSRValue": "0xFE7F8000002",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/other.json b/tools/perf/pmu-events/arch/x86/lunarlake/other.json
index 69adaed5686dd1..377f717db6cc10 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/other.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/other.json
@@ -24,7 +24,7 @@
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_DATA_RD.DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
+        "MSRValue": "0x1FBC000001",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
@@ -34,7 +34,7 @@
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_DATA_RD.DRAM",
         "MSRIndex": "0x1a6,0x1a7",
-        "MSRValue": "0x184000001",
+        "MSRValue": "0x1E780000001",
         "SampleAfterValue": "100003",
         "UMask": "0x1",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json b/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json
index 2bde664fdc0f8b..2c9f85ec8c4ad8 100644
--- a/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/lunarlake/pipeline.json
@@ -38,11 +38,19 @@
     {
         "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles",
         "EventName": "CPU_CLK_UNHALTED.CORE",
-        "SampleAfterValue": "1000003",
+        "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Core cycles when the core is not in a halt state.",
+        "EventName": "CPU_CLK_UNHALTED.CORE",
+        "PublicDescription": "Counts the number of core cycles while the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the programmable counters available for other events.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Counts the number of unhalted core clock cycles [This event is alias to CPU_CLK_UNHALTED.THREAD_P]",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.CORE_P",
@@ -50,9 +58,17 @@
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Thread cycles when thread is not in halt state [This event is alias to CPU_CLK_UNHALTED.THREAD_P]",
+        "EventCode": "0x3c",
+        "EventName": "CPU_CLK_UNHALTED.CORE_P",
+        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. [This event is alias to CPU_CLK_UNHALTED.THREAD_P]",
+        "SampleAfterValue": "2000003",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "Fixed Counter: Counts the number of unhalted reference clock cycles",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC",
-        "SampleAfterValue": "1000003",
+        "SampleAfterValue": "2000003",
         "UMask": "0x3",
         "Unit": "cpu_atom"
     },
@@ -65,6 +81,15 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of unhalted reference clock cycles",
+        "EventCode": "0x3c",
+        "EventName": "CPU_CLK_UNHALTED.REF_TSC_P",
+        "PublicDescription": "Counts the number of reference cycles that the core is not in a halt state. The core enters the halt state when it is running the HLT instruction. This event is not affected by core frequency changes and increments at a fixed frequency that is also used for the Time Stamp Counter (TSC). This event uses a programmable general purpose performance counter.",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Reference cycles when the core is not in halt state.",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.REF_TSC_P",
@@ -74,9 +99,16 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Core cycles when the thread is not in halt state",
+        "BriefDescription": "Fixed Counter: Counts the number of unhalted core clock cycles",
+        "EventName": "CPU_CLK_UNHALTED.THREAD",
+        "SampleAfterValue": "2000003",
+        "UMask": "0x2",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Core cycles when the thread is not in a halt state.",
         "EventName": "CPU_CLK_UNHALTED.THREAD",
-        "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the eight programmable counters available for other events.",
+        "PublicDescription": "Counts the number of core cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. This event is a component in many key event ratios. The core frequency may change from time to time due to transitions associated with Enhanced Intel SpeedStep Technology or TM2. For this reason this event may have a changing ratio with regards to time. When the core frequency is constant, this event can approximate elapsed time while the core was not in the halt state. It is counted on a dedicated fixed counter, leaving the programmable counters available for other events.",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -89,10 +121,10 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Thread cycles when thread is not in halt state",
+        "BriefDescription": "Thread cycles when thread is not in halt state [This event is alias to CPU_CLK_UNHALTED.CORE_P]",
         "EventCode": "0x3c",
         "EventName": "CPU_CLK_UNHALTED.THREAD_P",
-        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time.",
+        "PublicDescription": "This is an architectural event that counts the number of thread cycles while the thread is not in a halt state. The thread enters the halt state when it is running the HLT instruction. The core frequency may change from time to time due to power or thermal throttling. For this reason, this event may have a changing ratio with regards to wall clock time. [This event is alias to CPU_CLK_UNHALTED.CORE_P]",
         "SampleAfterValue": "2000003",
         "Unit": "cpu_core"
     },
@@ -100,7 +132,7 @@
         "BriefDescription": "Fixed Counter: Counts the number of instructions retired",
         "EventName": "INST_RETIRED.ANY",
         "PEBS": "1",
-        "SampleAfterValue": "1000003",
+        "SampleAfterValue": "2000003",
         "UMask": "0x1",
         "Unit": "cpu_atom"
     },
@@ -149,10 +181,28 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts the number of LBR entries recorded. Requires LBRs to be enabled in IA32_LBR_CTL.",
+        "EventCode": "0xe4",
+        "EventName": "MISC_RETIRED.LBR_INSERTS",
+        "PEBS": "1",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "LBR record is inserted",
+        "EventCode": "0xe4",
+        "EventName": "MISC_RETIRED.LBR_INSERTS",
+        "PEBS": "1",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_core"
+    },
+    {
         "BriefDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS",
-        "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.\nSoftware can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
+        "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
         "SampleAfterValue": "10000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -175,15 +225,21 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Fixed Counter: Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.",
+        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]",
+        "EventCode": "0x73",
         "EventName": "TOPDOWN_BAD_SPECULATION.ALL",
-        "PublicDescription": "Fixed Counter: Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.  Counts all issue slots blocked during this recovery window including relevant microcode flows and while uops are not yet available in the IQ. Also, includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
         "SampleAfterValue": "1000003",
-        "UMask": "0x5",
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls",
+        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL]",
+        "EventCode": "0x73",
+        "EventName": "TOPDOWN_BAD_SPECULATION.ALL_P",
+        "SampleAfterValue": "1000003",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL_P]",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN_BE_BOUND.ALL",
         "SampleAfterValue": "1000003",
@@ -191,6 +247,14 @@
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL]",
+        "EventCode": "0xa4",
+        "EventName": "TOPDOWN_BE_BOUND.ALL_P",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Fixed Counter: Counts the number of retirement slots not consumed due to front end stalls",
         "EventName": "TOPDOWN_FE_BOUND.ALL",
         "SampleAfterValue": "1000003",
@@ -198,7 +262,15 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Fixed Counter: Counts the number of consumed retirement slots.  Similar to UOPS_RETIRED.ALL",
+        "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls",
+        "EventCode": "0x9c",
+        "EventName": "TOPDOWN_FE_BOUND.ALL_P",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Fixed Counter: Counts the number of consumed retirement slots.",
         "EventName": "TOPDOWN_RETIRING.ALL",
         "PEBS": "1",
         "SampleAfterValue": "1000003",
@@ -206,10 +278,19 @@
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts the number of consumed retirement slots.",
+        "EventCode": "0xc2",
+        "EventName": "TOPDOWN_RETIRING.ALL_P",
+        "PEBS": "1",
+        "SampleAfterValue": "1000003",
+        "UMask": "0x2",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance  for example, as measured by the instructions-per-cycle metric.",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.SLOTS",
-        "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance  for example, as measured by the instructions-per-cycle metric.\nSoftware can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
+        "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance  for example, as measured by the instructions-per-cycle metric. Software can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/mapfile.csv b/tools/perf/pmu-events/arch/x86/mapfile.csv
index 5297d25f4e0333..c372e3594a69a4 100644
--- a/tools/perf/pmu-events/arch/x86/mapfile.csv
+++ b/tools/perf/pmu-events/arch/x86/mapfile.csv
@@ -5,33 +5,33 @@ GenuineIntel-6-(1C|26|27|35|36),v5,bonnell,core
 GenuineIntel-6-(3D|47),v29,broadwell,core
 GenuineIntel-6-56,v11,broadwellde,core
 GenuineIntel-6-4F,v22,broadwellx,core
-GenuineIntel-6-55-[56789ABCDEF],v1.20,cascadelakex,core
+GenuineIntel-6-55-[56789ABCDEF],v1.21,cascadelakex,core
 GenuineIntel-6-9[6C],v1.04,elkhartlake,core
-GenuineIntel-6-CF,v1.03,emeraldrapids,core
+GenuineIntel-6-CF,v1.06,emeraldrapids,core
 GenuineIntel-6-5[CF],v13,goldmont,core
 GenuineIntel-6-7A,v1.01,goldmontplus,core
-GenuineIntel-6-B6,v1.01,grandridge,core
+GenuineIntel-6-B6,v1.02,grandridge,core
 GenuineIntel-6-A[DE],v1.01,graniterapids,core
 GenuineIntel-6-(3C|45|46),v35,haswell,core
 GenuineIntel-6-3F,v28,haswellx,core
 GenuineIntel-6-7[DE],v1.21,icelake,core
-GenuineIntel-6-6[AC],v1.23,icelakex,core
+GenuineIntel-6-6[AC],v1.24,icelakex,core
 GenuineIntel-6-3A,v24,ivybridge,core
 GenuineIntel-6-3E,v24,ivytown,core
 GenuineIntel-6-2D,v24,jaketown,core
 GenuineIntel-6-(57|85),v16,knightslanding,core
-GenuineIntel-6-BD,v1.00,lunarlake,core
-GenuineIntel-6-A[AC],v1.07,meteorlake,core
+GenuineIntel-6-BD,v1.01,lunarlake,core
+GenuineIntel-6-A[AC],v1.08,meteorlake,core
 GenuineIntel-6-1[AEF],v4,nehalemep,core
 GenuineIntel-6-2E,v4,nehalemex,core
 GenuineIntel-6-A7,v1.02,rocketlake,core
 GenuineIntel-6-2A,v19,sandybridge,core
-GenuineIntel-6-8F,v1.17,sapphirerapids,core
-GenuineIntel-6-AF,v1.01,sierraforest,core
+GenuineIntel-6-8F,v1.20,sapphirerapids,core
+GenuineIntel-6-AF,v1.02,sierraforest,core
 GenuineIntel-6-(37|4A|4C|4D|5A),v15,silvermont,core
 GenuineIntel-6-(4E|5E|8E|9E|A5|A6),v58,skylake,core
-GenuineIntel-6-55-[01234],v1.32,skylakex,core
-GenuineIntel-6-86,v1.21,snowridgex,core
+GenuineIntel-6-55-[01234],v1.33,skylakex,core
+GenuineIntel-6-86,v1.22,snowridgex,core
 GenuineIntel-6-8[CD],v1.15,tigerlake,core
 GenuineIntel-6-2C,v5,westmereep-dp,core
 GenuineIntel-6-25,v4,westmereep-sp,core
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json
index 47861a6dd8e9a4..af7acb15f661ee 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/cache.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/cache.json
@@ -967,6 +967,16 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts demand data reads that were supplied by the L3 cache.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.L3_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F803C0001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HITM",
@@ -987,6 +997,16 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, but no data was forwarded.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_NO_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x4003C0001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts demand data reads that were supplied by the L3 cache where a snoop was sent, the snoop hit, and non-modified data was forwarded.",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_DATA_RD.L3_HIT.SNOOP_HIT_WITH_FWD",
@@ -1007,6 +1027,16 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.L3_HIT",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3F803C0002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by the L3 cache where a snoop was sent, the snoop hit, and modified data was forwarded.",
         "EventCode": "0xB7",
         "EventName": "OCR.DEMAND_RFO.L3_HIT.SNOOP_HITM",
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json
index 9da8689eda8148..f3b7b211afb538 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/frontend.json
@@ -378,7 +378,7 @@
         "CounterMask": "6",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.",
         "SampleAfterValue": "2000003",
         "UMask": "0x8",
         "Unit": "cpu_core"
@@ -455,7 +455,7 @@
         "BriefDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.",
         "EventCode": "0x9c",
         "EventName": "IDQ_BUBBLES.CORE",
-        "PublicDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations.\nThe count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
+        "PublicDescription": "This event counts a subset of the Topdown Slots event that were no operation was delivered to the back-end pipeline due to instruction fetch limitations when the back-end could have accepted more operations. Common examples include instruction cache misses or x86 instruction decode limitations. The count may be distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Frontend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
         "SampleAfterValue": "1000003",
         "UMask": "0x1",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json
index a5b83293f15782..617d0e255fd5b5 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/memory.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/memory.json
@@ -298,6 +298,16 @@
     },
     {
         "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FBFC00001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were not supplied by the L3 cache.",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_DATA_RD.L3_MISS",
         "MSRIndex": "0x1a6,0x1a7",
@@ -307,6 +317,16 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.L3_MISS",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x3FBFC00002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that were not supplied by the L3 cache.",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_RFO.L3_MISS",
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/other.json b/tools/perf/pmu-events/arch/x86/meteorlake/other.json
index 7effc1f271e77b..0bc2cb2eabb32c 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/other.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/other.json
@@ -19,6 +19,16 @@
     },
     {
         "BriefDescription": "Counts demand data reads that have any type of response.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that have any type of response.",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_DATA_RD.ANY_RESPONSE",
         "MSRIndex": "0x1a6,0x1a7",
@@ -29,6 +39,16 @@
     },
     {
         "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_DATA_RD.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000001",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts demand data reads that were supplied by DRAM.",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_DATA_RD.DRAM",
         "MSRIndex": "0x1a6,0x1a7",
@@ -38,6 +58,16 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x10002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts demand read for ownership (RFO) requests and software prefetches for exclusive ownership (PREFETCHW) that have any type of response.",
         "EventCode": "0x2A,0x2B",
         "EventName": "OCR.DEMAND_RFO.ANY_RESPONSE",
@@ -48,6 +78,16 @@
         "Unit": "cpu_core"
     },
     {
+        "BriefDescription": "Counts demand reads for ownership (RFO) and software prefetches for exclusive ownership (PREFETCHW) that were supplied by DRAM.",
+        "EventCode": "0xB7",
+        "EventName": "OCR.DEMAND_RFO.DRAM",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x184000002",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts streaming stores that have any type of response.",
         "EventCode": "0xB7",
         "EventName": "OCR.STREAMING_WR.ANY_RESPONSE",
@@ -97,7 +137,7 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state. For Tremont, UMWAIT and TPAUSE will only put the CPU into C0.1 activity state (not C0.2 activity state)",
+        "BriefDescription": "Counts the number of issue slots in a UMWAIT or TPAUSE instruction where no uop issues due to the instruction putting the CPU into the C0.1 activity state.",
         "EventCode": "0x75",
         "EventName": "SERIALIZATION.C01_MS_SCB",
         "SampleAfterValue": "200003",
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json
index 24bbfcebd2bed2..5ff4a7a322500e 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/pipeline.json
@@ -1067,7 +1067,7 @@
         "BriefDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.",
         "EventCode": "0xa4",
         "EventName": "TOPDOWN.BACKEND_BOUND_SLOTS",
-        "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions.\nThe count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
+        "PublicDescription": "This event counts a subset of the Topdown Slots event that were not consumed by the back-end pipeline due to lack of back-end resources, as a result of memory subsystem delays, execution units limitations, or other conditions. The count is distributed among unhalted logical processors (hyper-threads) who share the same physical core, in processors that support Intel Hyper-Threading Technology. Software can use this event as the numerator for the Backend Bound metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
         "SampleAfterValue": "10000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
@@ -1116,10 +1116,18 @@
         "Unit": "cpu_core"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.",
+        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]",
         "EventCode": "0x73",
         "EventName": "TOPDOWN_BAD_SPECULATION.ALL",
-        "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
+        "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]",
+        "SampleAfterValue": "1000003",
+        "Unit": "cpu_atom"
+    },
+    {
+        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL]",
+        "EventCode": "0x73",
+        "EventName": "TOPDOWN_BAD_SPECULATION.ALL_P",
+        "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL]",
         "SampleAfterValue": "1000003",
         "Unit": "cpu_atom"
     },
@@ -1156,7 +1164,7 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls",
+        "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL_P]",
         "EventCode": "0x74",
         "EventName": "TOPDOWN_BE_BOUND.ALL",
         "SampleAfterValue": "1000003",
@@ -1171,6 +1179,13 @@
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL]",
+        "EventCode": "0x74",
+        "EventName": "TOPDOWN_BE_BOUND.ALL_P",
+        "SampleAfterValue": "1000003",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to memory reservation stall (scheduler not being able to accept another uop).  This could be caused by RSV full or load/store buffer block.",
         "EventCode": "0x74",
         "EventName": "TOPDOWN_BE_BOUND.MEM_SCHEDULER",
@@ -1211,13 +1226,20 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls",
+        "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls [This event is alias to TOPDOWN_FE_BOUND.ALL_P]",
         "EventCode": "0x71",
         "EventName": "TOPDOWN_FE_BOUND.ALL",
         "SampleAfterValue": "1000003",
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls [This event is alias to TOPDOWN_FE_BOUND.ALL]",
+        "EventCode": "0x71",
+        "EventName": "TOPDOWN_FE_BOUND.ALL_P",
+        "SampleAfterValue": "1000003",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BAClear",
         "EventCode": "0x71",
         "EventName": "TOPDOWN_FE_BOUND.BRANCH_DETECT",
@@ -1299,7 +1321,7 @@
         "Unit": "cpu_atom"
     },
     {
-        "BriefDescription": "Counts the number of consumed retirement slots.  Similar to UOPS_RETIRED.ALL",
+        "BriefDescription": "Counts the number of consumed retirement slots.  Similar to UOPS_RETIRED.ALL [This event is alias to TOPDOWN_RETIRING.ALL_P]",
         "EventCode": "0x72",
         "EventName": "TOPDOWN_RETIRING.ALL",
         "PEBS": "1",
@@ -1307,6 +1329,14 @@
         "Unit": "cpu_atom"
     },
     {
+        "BriefDescription": "Counts the number of consumed retirement slots.  Similar to UOPS_RETIRED.ALL [This event is alias to TOPDOWN_RETIRING.ALL]",
+        "EventCode": "0x72",
+        "EventName": "TOPDOWN_RETIRING.ALL_P",
+        "PEBS": "1",
+        "SampleAfterValue": "1000003",
+        "Unit": "cpu_atom"
+    },
+    {
         "BriefDescription": "Number of non dec-by-all uops decoded by decoder",
         "EventCode": "0x76",
         "EventName": "UOPS_DECODED.DEC0_UOPS",
@@ -1591,7 +1621,7 @@
         "BriefDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance  for example, as measured by the instructions-per-cycle metric.",
         "EventCode": "0xc2",
         "EventName": "UOPS_RETIRED.SLOTS",
-        "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance  for example, as measured by the instructions-per-cycle metric.\nSoftware can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
+        "PublicDescription": "This event counts a subset of the Topdown Slots event that are utilized by operations that eventually get retired (committed) by the processor pipeline. Usually, this event positively correlates with higher performance  for example, as measured by the instructions-per-cycle metric. Software can use this event as the numerator for the Retiring metric (or top-level category) of the Top-down Microarchitecture Analysis method.",
         "SampleAfterValue": "2000003",
         "UMask": "0x2",
         "Unit": "cpu_core"
diff --git a/tools/perf/pmu-events/arch/x86/meteorlake/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/meteorlake/uncore-interconnect.json
index 08b5c7574cfcc3..901d8510f90fa5 100644
--- a/tools/perf/pmu-events/arch/x86/meteorlake/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/meteorlake/uncore-interconnect.json
@@ -1,5 +1,21 @@
 [
     {
+        "BriefDescription": "Each cycle counts number of coherent reads pending on data return from memory controller that were issued by any core.",
+        "EventCode": "0x85",
+        "EventName": "UNC_ARB_DAT_OCCUPANCY.RD",
+        "PerPkg": "1",
+        "UMask": "0x2",
+        "Unit": "ARB"
+    },
+    {
+        "BriefDescription": "Number of entries allocated. Account for Any type: e.g. Snoop,  etc.",
+        "EventCode": "0x84",
+        "EventName": "UNC_HAC_ARB_COH_TRK_REQUESTS.ALL",
+        "PerPkg": "1",
+        "UMask": "0x1",
+        "Unit": "HAC_ARB"
+    },
+    {
         "BriefDescription": "Number of all coherent Data Read entries. Doesn't include prefetches",
         "EventCode": "0x81",
         "EventName": "UNC_HAC_ARB_REQ_TRK_REQUEST.DRD",
@@ -9,7 +25,7 @@
     },
     {
         "BriefDescription": "Number of all CMI transactions",
-        "EventCode": "0x8a",
+        "EventCode": "0x8A",
         "EventName": "UNC_HAC_ARB_TRANSACTIONS.ALL",
         "PerPkg": "1",
         "UMask": "0x1",
@@ -17,7 +33,7 @@
     },
     {
         "BriefDescription": "Number of all CMI reads",
-        "EventCode": "0x8a",
+        "EventCode": "0x8A",
         "EventName": "UNC_HAC_ARB_TRANSACTIONS.READS",
         "PerPkg": "1",
         "UMask": "0x2",
@@ -25,7 +41,7 @@
     },
     {
         "BriefDescription": "Number of all CMI writes not including Mflush",
-        "EventCode": "0x8a",
+        "EventCode": "0x8A",
         "EventName": "UNC_HAC_ARB_TRANSACTIONS.WRITES",
         "PerPkg": "1",
         "UMask": "0x4",
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json
index 9606e76b98d6bb..b0447aad0dfc59 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/cache.json
@@ -432,6 +432,7 @@
         "BriefDescription": "Retired load instructions with remote Intel(R) Optane(TM) DC persistent memory as the data source where the data request missed all caches.",
         "EventCode": "0xd3",
         "EventName": "MEM_LOAD_L3_MISS_RETIRED.REMOTE_PMM",
+        "PEBS": "1",
         "PublicDescription": "Counts retired load instructions with remote Intel(R) Optane(TM) DC persistent memory as the data source and the data request missed L3.",
         "SampleAfterValue": "100007",
         "UMask": "0x10"
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json
index 9e53da55d0c118..93d99318a62390 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/frontend.json
@@ -267,7 +267,7 @@
         "CounterMask": "6",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the MITE (legacy decode pipeline) path. During these cycles uops are not being delivered from the Decode Stream Buffer (DSB).",
+        "PublicDescription": "Counts the number of cycles where optimal number of uops was delivered to the Instruction Decode Queue (IDQ) from the DSB (Decode Stream Buffer) path. Count includes uops that may 'bypass' the IDQ.",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
     },
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json
index e8bf7c9c44e1a3..5420f529f49185 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/memory.json
@@ -264,6 +264,7 @@
         "BriefDescription": "Number of times an RTM execution aborted.",
         "EventCode": "0xc9",
         "EventName": "RTM_RETIRED.ABORTED",
+        "PEBS": "1",
         "PublicDescription": "Counts the number of times RTM abort was triggered.",
         "SampleAfterValue": "100003",
         "UMask": "0x4"
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json
index 2cfe814d20151c..e2086bedeca809 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/pipeline.json
@@ -1,21 +1,5 @@
 [
     {
-        "BriefDescription": "AMX retired arithmetic BF16 operations.",
-        "EventCode": "0xce",
-        "EventName": "AMX_OPS_RETIRED.BF16",
-        "PublicDescription": "Number of AMX-based retired arithmetic bfloat16 (BF16) floating-point operations. Counts TDPBF16PS FP instructions. SW to use operation multiplier of 4",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x2"
-    },
-    {
-        "BriefDescription": "AMX retired arithmetic integer 8-bit operations.",
-        "EventCode": "0xce",
-        "EventName": "AMX_OPS_RETIRED.INT8",
-        "PublicDescription": "Number of AMX-based retired arithmetic integer operations of 8-bit width source operands. Counts TDPB[SS,UU,US,SU]D instructions. SW should use operation multiplier of 8.",
-        "SampleAfterValue": "1000003",
-        "UMask": "0x1"
-    },
-    {
         "BriefDescription": "This event is deprecated. Refer to new event ARITH.DIV_ACTIVE",
         "CounterMask": "1",
         "Deprecated": "1",
@@ -444,6 +428,7 @@
         "BriefDescription": "INST_RETIRED.MACRO_FUSED",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.MACRO_FUSED",
+        "PEBS": "1",
         "SampleAfterValue": "2000003",
         "UMask": "0x10"
     },
@@ -451,6 +436,7 @@
         "BriefDescription": "Retired NOP instructions.",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.NOP",
+        "PEBS": "1",
         "PublicDescription": "Counts all retired NOP or ENDBR32/64 instructions",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
@@ -467,6 +453,7 @@
         "BriefDescription": "Iterations of Repeat string retired instructions.",
         "EventCode": "0xc0",
         "EventName": "INST_RETIRED.REP_ITERATION",
+        "PEBS": "1",
         "PublicDescription": "Number of iterations of Repeat (REP) string retired instructions such as MOVS, CMPS, and SCAS. Each has a byte, word, and doubleword version and string instructions can be repeated using a repetition prefix, REP, that allows their architectural execution to be repeated a number of times as specified by the RCX register. Note the number of iterations is implementation-dependent.",
         "SampleAfterValue": "2000003",
         "UMask": "0x8"
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
index 6f0e6360e989e1..f8c0eac8b8282b 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/spr-metrics.json
@@ -727,23 +727,20 @@
     {
         "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
         "MetricExpr": "(100 * (1 - max(0, topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)) / (((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + cpu@RS.EMPTY\\,umask\\=0x1@) / CPU_CLK_UNHALTED.THREAD * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / CPU_CLK_UNHALTED.THREAD * CPU_CLK_UNHALTED.THREAD + (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * cpu@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@)) / CPU_CLK_UNHALTED.THREAD if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * cpu@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@) / CPU_CLK_UNHALTED.THREAD) if max(0, topdown\\-be\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - topdown\\-mem\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound)) < (((cpu@EXE_ACTIVITY.3_PORTS_UTIL\\,umask\\=0x80@ + cpu@RS.EMPTY\\,umask\\=0x1@) / CPU_CLK_UNHALTED.THREAD * (CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS) / CPU_CLK_UNHALTED.THREAD * CPU_CLK_UNHALTED.THREAD + (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * cpu@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@)) / CPU_CLK_UNHALTED.THREAD if ARITH.DIV_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - EXE_ACTIVITY.BOUND_ON_LOADS else (EXE_ACTIVITY.1_PORTS_UTIL + topdown\\-retiring / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) * cpu@EXE_ACTIVITY.2_PORTS_UTIL\\,umask\\=0xc@) / CPU_CLK_UNHALTED.THREAD) else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0) + 0 * slots",
-        "MetricGroup": "Cor;SMT;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_botlnk_core_bound_likely",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Cor;SMT",
+        "MetricName": "tma_info_botlnk_core_bound_likely"
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck.",
         "MetricExpr": "100 * (100 * ((topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / slots) * (DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD) / (ICACHE_DATA.STALLS / CPU_CLK_UNHALTED.THREAD + ICACHE_TAG.STALLS / CPU_CLK_UNHALTED.THREAD + (INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD + INT_MISC.UNKNOWN_BRANCH_CYCLES / CPU_CLK_UNHALTED.THREAD) + min(3 * cpu@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / CPU_CLK_UNHALTED.THREAD, 1) + DECODE.LCP / CPU_CLK_UNHALTED.THREAD + DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD) + max(0, topdown\\-fe\\-bound / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / slots - (topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / slots)) * ((IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / (CPU_CLK_UNHALTED.DISTRIBUTED if #SMT_on else CPU_CLK_UNHALTED.THREAD) / 2) / ((IDQ.MITE_CYCLES_ANY - IDQ.MITE_CYCLES_OK) / (CPU_CLK_UNHALTED.DISTRIBUTED if #SMT_on else CPU_CLK_UNHALTED.THREAD) / 2 + (IDQ.DSB_CYCLES_ANY - IDQ.DSB_CYCLES_OK) / (CPU_CLK_UNHALTED.DISTRIBUTED if #SMT_on else CPU_CLK_UNHALTED.THREAD) / 2)))",
-        "MetricGroup": "DSBmiss;Fed;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_botlnk_dsb_misses",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "DSBmiss;Fed",
+        "MetricName": "tma_info_botlnk_dsb_misses"
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck.",
         "MetricExpr": "100 * (100 * ((topdown\\-fetch\\-lat / (topdown\\-fe\\-bound + topdown\\-bad\\-spec + topdown\\-retiring + topdown\\-be\\-bound) - INT_MISC.UOP_DROPPING / slots) * (ICACHE_DATA.STALLS / CPU_CLK_UNHALTED.THREAD) / (ICACHE_DATA.STALLS / CPU_CLK_UNHALTED.THREAD + ICACHE_TAG.STALLS / CPU_CLK_UNHALTED.THREAD + (INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD + INT_MISC.UNKNOWN_BRANCH_CYCLES / CPU_CLK_UNHALTED.THREAD) + min(3 * cpu@UOPS_RETIRED.MS\\,cmask\\=0x1\\,edge\\=0x1@ / (UOPS_RETIRED.SLOTS / UOPS_ISSUED.ANY) / CPU_CLK_UNHALTED.THREAD, 1) + DECODE.LCP / CPU_CLK_UNHALTED.THREAD + DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD)))",
-        "MetricGroup": "Fed;FetchLat;IcMiss;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_botlnk_ic_misses",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Fed;FetchLat;IcMiss",
+        "MetricName": "tma_info_botlnk_ic_misses"
     },
     {
         "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
@@ -1113,16 +1110,14 @@
     {
         "BriefDescription": "\"Bus lock\" per kilo instruction",
         "MetricExpr": "tma_info_memory_mix_bus_lock_pki",
-        "MetricGroup": "Mem;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_bus_lock_pki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem",
+        "MetricName": "tma_info_memory_bus_lock_pki"
     },
     {
         "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
         "MetricExpr": "tma_info_memory_tlb_code_stlb_mpki",
-        "MetricGroup": "Fed;MemoryTLB;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_code_stlb_mpki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Fed;MemoryTLB",
+        "MetricName": "tma_info_memory_code_stlb_mpki"
     },
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
@@ -1163,9 +1158,8 @@
     {
         "BriefDescription": "Average Parallel L2 cache miss data reads",
         "MetricExpr": "tma_info_memory_latency_data_l2_mlp",
-        "MetricGroup": "Memory_BW;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_data_l2_mlp",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Memory_BW;Offcore",
+        "MetricName": "tma_info_memory_data_l2_mlp"
     },
     {
         "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)",
@@ -1182,9 +1176,8 @@
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
         "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t"
     },
     {
         "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
@@ -1207,23 +1200,20 @@
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]",
         "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l2_cache_fill_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_l2_cache_fill_bw_2t"
     },
     {
         "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction",
         "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / INST_RETIRED.ANY",
-        "MetricGroup": "L2Evicts;Mem;Server;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l2_evictions_nonsilent_pki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "L2Evicts;Mem;Server",
+        "MetricName": "tma_info_memory_l2_evictions_nonsilent_pki"
     },
     {
         "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)",
         "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / INST_RETIRED.ANY",
-        "MetricGroup": "L2Evicts;Mem;Server;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l2_evictions_silent_pki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "L2Evicts;Mem;Server",
+        "MetricName": "tma_info_memory_l2_evictions_silent_pki"
     },
     {
         "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
@@ -1264,9 +1254,8 @@
     {
         "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]",
         "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l3_cache_access_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW;Offcore",
+        "MetricName": "tma_info_memory_l3_cache_access_bw_2t"
     },
     {
         "BriefDescription": "",
@@ -1277,9 +1266,8 @@
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
         "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l3_cache_fill_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_l3_cache_fill_bw_2t"
     },
     {
         "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
@@ -1314,23 +1302,20 @@
     {
         "BriefDescription": "Average Latency for L2 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "MetricGroup": "Memory_Lat;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_load_l2_miss_latency",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Memory_Lat;Offcore",
+        "MetricName": "tma_info_memory_load_l2_miss_latency"
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / cpu@OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD\\,cmask\\=0x1@",
-        "MetricGroup": "Memory_BW;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_load_l2_mlp",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Memory_BW;Offcore",
+        "MetricName": "tma_info_memory_load_l2_mlp"
     },
     {
         "BriefDescription": "Average Latency for L3 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.L3_MISS_DEMAND_DATA_RD / OFFCORE_REQUESTS.L3_MISS_DEMAND_DATA_RD",
-        "MetricGroup": "Memory_Lat;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_load_l3_miss_latency",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Memory_Lat;Offcore",
+        "MetricName": "tma_info_memory_load_l3_miss_latency"
     },
     {
         "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
@@ -1341,9 +1326,8 @@
     {
         "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
         "MetricExpr": "tma_info_memory_tlb_load_stlb_mpki",
-        "MetricGroup": "Mem;MemoryTLB;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_load_stlb_mpki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryTLB",
+        "MetricName": "tma_info_memory_load_stlb_mpki"
     },
     {
         "BriefDescription": "\"Bus lock\" per kilo instruction",
@@ -1385,53 +1369,46 @@
     {
         "BriefDescription": "Off-core accesses per kilo instruction for modified write requests",
         "MetricExpr": "1e3 * OCR.MODIFIED_WRITE.ANY_RESPONSE / INST_RETIRED.ANY",
-        "MetricGroup": "Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_offcore_mwrite_any_pki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Offcore",
+        "MetricName": "tma_info_memory_offcore_mwrite_any_pki"
     },
     {
         "BriefDescription": "Off-core accesses per kilo instruction for reads-to-core requests (speculative; including in-core HW prefetches)",
         "MetricExpr": "1e3 * OCR.READS_TO_CORE.ANY_RESPONSE / INST_RETIRED.ANY",
-        "MetricGroup": "CacheHits;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_offcore_read_any_pki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "CacheHits;Offcore",
+        "MetricName": "tma_info_memory_offcore_read_any_pki"
     },
     {
         "BriefDescription": "L3 cache misses per kilo instruction for reads-to-core requests (speculative; including in-core HW prefetches)",
         "MetricExpr": "1e3 * OCR.READS_TO_CORE.L3_MISS / INST_RETIRED.ANY",
-        "MetricGroup": "Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_offcore_read_l3m_pki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Offcore",
+        "MetricName": "tma_info_memory_offcore_read_l3m_pki"
     },
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
         "MetricExpr": "(ITLB_MISSES.WALK_PENDING + DTLB_LOAD_MISSES.WALK_PENDING + DTLB_STORE_MISSES.WALK_PENDING) / (4 * (CPU_CLK_UNHALTED.DISTRIBUTED if #SMT_on else CPU_CLK_UNHALTED.THREAD))",
-        "MetricGroup": "Mem;MemoryTLB;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_page_walks_utilization",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryTLB",
+        "MetricName": "tma_info_memory_page_walks_utilization"
     },
     {
         "BriefDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket",
         "MetricExpr": "64 * OCR.READS_TO_CORE.DRAM / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "HPC;Mem;MemoryBW;SoC;TopdownL1;tma_L1_group",
+        "MetricGroup": "HPC;Mem;MemoryBW;SoC",
         "MetricName": "tma_info_memory_r2c_dram_bw",
-        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "Average DRAM BW for Reads-to-Core (R2C) covering for memory attached to local- and remote-socket. See R2C_Offcore_BW."
     },
     {
         "BriefDescription": "Average L3-cache miss BW for Reads-to-Core (R2C)",
         "MetricExpr": "64 * OCR.READS_TO_CORE.L3_MISS / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "HPC;Mem;MemoryBW;SoC;TopdownL1;tma_L1_group",
+        "MetricGroup": "HPC;Mem;MemoryBW;SoC",
         "MetricName": "tma_info_memory_r2c_l3m_bw",
-        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "Average L3-cache miss BW for Reads-to-Core (R2C). This covering going to DRAM or other memory off-chip memory tears. See R2C_Offcore_BW."
     },
     {
         "BriefDescription": "Average Off-core access BW for Reads-to-Core (R2C)",
         "MetricExpr": "64 * OCR.READS_TO_CORE.ANY_RESPONSE / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "HPC;Mem;MemoryBW;SoC;TopdownL1;tma_L1_group",
+        "MetricGroup": "HPC;Mem;MemoryBW;SoC",
         "MetricName": "tma_info_memory_r2c_offcore_bw",
-        "MetricgroupNoGroup": "TopdownL1",
         "PublicDescription": "Average Off-core access BW for Reads-to-Core (R2C). R2C account for demand or prefetch load/RFO/code access that fill data into the Core caches."
     },
     {
@@ -1458,9 +1435,8 @@
     {
         "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
         "MetricExpr": "tma_info_memory_tlb_store_stlb_mpki",
-        "MetricGroup": "Mem;MemoryTLB;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_store_stlb_mpki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryTLB",
+        "MetricName": "tma_info_memory_store_stlb_mpki"
     },
     {
         "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
@@ -1490,9 +1466,8 @@
     {
         "BriefDescription": "Un-cacheable retired load per kilo instruction",
         "MetricExpr": "1e3 * MEM_LOAD_MISC_RETIRED.UC / INST_RETIRED.ANY",
-        "MetricGroup": "Mem;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_uc_load_pki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem",
+        "MetricName": "tma_info_memory_uc_load_pki"
     },
     {
         "BriefDescription": "",
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cache.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cache.json
index cf6fa70f37c107..25a2b9695135b6 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cache.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-cache.json
@@ -4144,6 +4144,42 @@
         "Unit": "CHA"
     },
     {
+        "BriefDescription": "ItoMCacheNear (partial write) transactions from an IO device that addresses memory on the local socket",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.   Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcd42ff04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "ItoMCacheNear (partial write) transactions from an IO device that addresses memory on a remote socket",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOMCACHENEAR_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "TOR Inserts : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC : Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.   Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcd437f04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "ItoM (write) transactions from an IO device that addresses memory on the local socket",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOM_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.   Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcc42ff04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "ItoM (write) transactions from an IO device that addresses memory on a remote socket",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IO_ITOM_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.   Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcc437f04",
+        "Unit": "CHA"
+    },
+    {
         "BriefDescription": "TOR Inserts; Misses from local IO",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS",
@@ -4153,7 +4189,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "TOR Inserts; ItoM misses from local IO",
+        "BriefDescription": "TOR Inserts : ItoM, indicating a full cacheline write request, from IO Devices that missed the LLC",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_ITOM",
         "PerPkg": "1",
@@ -4171,7 +4207,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "TOR Inserts; RdCur and FsRdCur misses from local IO",
+        "BriefDescription": "TOR Inserts; RdCur and FsRdCur requests from local IO that miss LLC",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IO_MISS_PCIRDCUR",
         "PerPkg": "1",
@@ -4198,6 +4234,24 @@
         "Unit": "CHA"
     },
     {
+        "BriefDescription": "PCIRDCUR (read) transactions from an IO device that addresses memory on a remote socket",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.   Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xc8f2ff04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "PCIRDCUR (read) transactions from an IO device that addresses memory on the local socket",
+        "EventCode": "0x35",
+        "EventName": "UNC_CHA_TOR_INSERTS.IO_PCIRDCUR_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "Counts the number of entries successfully inserted into the TOR that match qualifications specified by the subevent.   Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xc8f37f04",
+        "Unit": "CHA"
+    },
+    {
         "BriefDescription": "TOR Inserts; RFO from local IO",
         "EventCode": "0x35",
         "EventName": "UNC_CHA_TOR_INSERTS.IO_RFO",
@@ -5566,6 +5620,42 @@
         "Unit": "CHA"
     },
     {
+        "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC and targets local memory",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOMCACHENEAR_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.     Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcd42fe04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "TOR Occupancy : ItoMCacheNears, indicating a partial write request, from IO Devices that missed the LLC and targets remote memory",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOMCACHENEAR_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.     Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcd437e04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "TOR Occupancy; ITOM misses from local IO and targets local memory",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.     Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcc42fe04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "TOR Occupancy; ITOM misses from local IO and targets remote memory",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_ITOM_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.     Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xcc437e04",
+        "Unit": "CHA"
+    },
+    {
         "BriefDescription": "TOR Occupancy; RdCur and FsRdCur misses from local IO",
         "EventCode": "0x36",
         "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR",
@@ -5575,6 +5665,24 @@
         "Unit": "CHA"
     },
     {
+        "BriefDescription": "TOR Occupancy; RdCur and FsRdCur misses from local IO and targets local memory",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR_LOCAL",
+        "PerPkg": "1",
+        "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.     Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xc8f2fe04",
+        "Unit": "CHA"
+    },
+    {
+        "BriefDescription": "TOR Occupancy; RdCur and FsRdCur misses from local IO and targets remote memory",
+        "EventCode": "0x36",
+        "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_PCIRDCUR_REMOTE",
+        "PerPkg": "1",
+        "PublicDescription": "For each cycle, this event accumulates the number of valid entries in the TOR that match qualifications specified by the subevent.     Does not include addressless requests such as locks and interrupts.",
+        "UMask": "0xc8f37e04",
+        "Unit": "CHA"
+    },
+    {
         "BriefDescription": "TOR Occupancy; RFO misses from local IO",
         "EventCode": "0x36",
         "EventName": "UNC_CHA_TOR_OCCUPANCY.IO_MISS_RFO",
diff --git a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json
index 65d088556bae8d..22bb490e96662d 100644
--- a/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/sapphirerapids/uncore-interconnect.json
@@ -4888,7 +4888,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (AD)",
+        "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO Ingress (V-EMIB) (AD)",
         "EventCode": "0x4B",
         "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.AD",
         "PerPkg": "1",
@@ -4897,7 +4897,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (AK)",
+        "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO Ingress (V-EMIB) (AK)",
         "EventCode": "0x4B",
         "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.AK",
         "PerPkg": "1",
@@ -4906,7 +4906,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (AKC)",
+        "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO Ingress (V-EMIB) (AKC)",
         "EventCode": "0x4B",
         "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.AKC",
         "PerPkg": "1",
@@ -4915,7 +4915,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (BL)",
+        "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO Ingress (V-EMIB) (BL)",
         "EventCode": "0x4B",
         "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.BL",
         "PerPkg": "1",
@@ -4924,7 +4924,7 @@
         "Unit": "MDF"
     },
     {
-        "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO\r\nIngress (V-EMIB) (IV)",
+        "BriefDescription": "Number of cycles incoming messages from the vertical ring that are bounced at the SBO Ingress (V-EMIB) (IV)",
         "EventCode": "0x4B",
         "EventName": "UNC_MDF_CRS_TxR_V_BOUNCES.IV",
         "PerPkg": "1",
@@ -5291,7 +5291,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0xe",
         "Unit": "UPI"
     },
@@ -5300,7 +5300,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCB_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x10e",
         "Unit": "UPI"
     },
@@ -5309,7 +5309,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0xf",
         "Unit": "UPI"
     },
@@ -5318,7 +5318,7 @@
         "EventCode": "0x05",
         "EventName": "UNC_UPI_RxL_BASIC_HDR_MATCH.NCS_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Receive path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Receive path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Receive path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x10f",
         "Unit": "UPI"
     },
@@ -5763,7 +5763,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0xe",
         "Unit": "UPI"
     },
@@ -5772,7 +5772,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCB_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Bypass, Match Opcode : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x10e",
         "Unit": "UPI"
     },
@@ -5781,7 +5781,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0xf",
         "Unit": "UPI"
     },
@@ -5790,7 +5790,7 @@
         "EventCode": "0x04",
         "EventName": "UNC_UPI_TxL_BASIC_HDR_MATCH.NCS_OPC",
         "PerPkg": "1",
-        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Transmit path of a UPI port.\r\nMatch based on UMask specific bits:\r\nZ: Message Class (3-bit)\r\nY: Message Class Enable\r\nW: Opcode (4-bit)\r\nV: Opcode Enable\r\nU: Local Enable\r\nT: Remote Enable\r\nS: Data Hdr Enable\r\nR: Non-Data Hdr Enable\r\nQ: Dual Slot Hdr Enable\r\nP: Single Slot Hdr Enable\r\nLink Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases.\r\nNote: If Message Class is disabled, we expect opcode to also be disabled.",
+        "PublicDescription": "Matches on Transmit path of a UPI Port : Non-Coherent Standard, Match Opcode : Matches on Transmit path of a UPI port. Match based on UMask specific bits: Z: Message Class (3-bit) Y: Message Class Enable W: Opcode (4-bit) V: Opcode Enable U: Local Enable T: Remote Enable S: Data Hdr Enable R: Non-Data Hdr Enable Q: Dual Slot Hdr Enable P: Single Slot Hdr Enable Link Layer control types are excluded (LL CTRL, slot NULL, LLCRD) even under specific opcode match_en cases. Note: If Message Class is disabled, we expect opcode to also be disabled.",
         "UMask": "0x10f",
         "Unit": "UPI"
     },
diff --git a/tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json b/tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json
index ba9843110f070d..90292dc03d33e2 100644
--- a/tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/sierraforest/pipeline.json
@@ -249,10 +249,17 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear.",
+        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]",
         "EventCode": "0x73",
         "EventName": "TOPDOWN_BAD_SPECULATION.ALL",
-        "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear.",
+        "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL_P]",
+        "SampleAfterValue": "1000003"
+    },
+    {
+        "BriefDescription": "Counts the number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL]",
+        "EventCode": "0x73",
+        "EventName": "TOPDOWN_BAD_SPECULATION.ALL_P",
+        "PublicDescription": "Counts the total number of issue slots that were not consumed by the backend because allocation is stalled due to a mispredicted jump or a machine clear. Only issue slots wasted due to fast nukes such as memory ordering nukes are counted. Other nukes are not accounted for. Counts all issue slots blocked during this recovery window, including relevant microcode flows, and while uops are not yet available in the instruction queue (IQ) or until an FE_BOUND event occurs besides OTHER and CISC. Also includes the issue slots that were consumed by the backend but were thrown away because they were younger than the mispredict or machine clear. [This event is alias to TOPDOWN_BAD_SPECULATION.ALL]",
         "SampleAfterValue": "1000003"
     },
     {
@@ -284,7 +291,7 @@
         "UMask": "0x1"
     },
     {
-        "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls",
+        "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL_P]",
         "EventCode": "0x74",
         "EventName": "TOPDOWN_BE_BOUND.ALL",
         "SampleAfterValue": "1000003"
@@ -297,6 +304,12 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "Counts the number of retirement slots not consumed due to backend stalls [This event is alias to TOPDOWN_BE_BOUND.ALL]",
+        "EventCode": "0x74",
+        "EventName": "TOPDOWN_BE_BOUND.ALL_P",
+        "SampleAfterValue": "1000003"
+    },
+    {
         "BriefDescription": "Counts the number of issue slots every cycle that were not consumed by the backend due to memory reservation stall (scheduler not being able to accept another uop).  This could be caused by RSV full or load/store buffer block.",
         "EventCode": "0x74",
         "EventName": "TOPDOWN_BE_BOUND.MEM_SCHEDULER",
@@ -332,12 +345,18 @@
         "UMask": "0x10"
     },
     {
-        "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls",
+        "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls [This event is alias to TOPDOWN_FE_BOUND.ALL_P]",
         "EventCode": "0x71",
         "EventName": "TOPDOWN_FE_BOUND.ALL",
         "SampleAfterValue": "1000003"
     },
     {
+        "BriefDescription": "Counts the number of retirement slots not consumed due to front end stalls [This event is alias to TOPDOWN_FE_BOUND.ALL]",
+        "EventCode": "0x71",
+        "EventName": "TOPDOWN_FE_BOUND.ALL_P",
+        "SampleAfterValue": "1000003"
+    },
+    {
         "BriefDescription": "Counts the number of issue slots every cycle that were not delivered by the frontend due to BAClear",
         "EventCode": "0x71",
         "EventName": "TOPDOWN_FE_BOUND.BRANCH_DETECT",
@@ -409,13 +428,20 @@
         "UMask": "0x4"
     },
     {
-        "BriefDescription": "Counts the number of consumed retirement slots.  Similar to UOPS_RETIRED.ALL",
+        "BriefDescription": "Counts the number of consumed retirement slots.  Similar to UOPS_RETIRED.ALL [This event is alias to TOPDOWN_RETIRING.ALL_P]",
         "EventCode": "0x72",
         "EventName": "TOPDOWN_RETIRING.ALL",
         "PEBS": "1",
         "SampleAfterValue": "1000003"
     },
     {
+        "BriefDescription": "Counts the number of consumed retirement slots.  Similar to UOPS_RETIRED.ALL [This event is alias to TOPDOWN_RETIRING.ALL]",
+        "EventCode": "0x72",
+        "EventName": "TOPDOWN_RETIRING.ALL_P",
+        "PEBS": "1",
+        "SampleAfterValue": "1000003"
+    },
+    {
         "BriefDescription": "Counts the number of uops issued by the front end every cycle.",
         "EventCode": "0x0e",
         "EventName": "UOPS_ISSUED.ANY",
diff --git a/tools/perf/pmu-events/arch/x86/skylake/frontend.json b/tools/perf/pmu-events/arch/x86/skylake/frontend.json
index 095904c7700198..d6f543471b2436 100644
--- a/tools/perf/pmu-events/arch/x86/skylake/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/skylake/frontend.json
@@ -19,7 +19,7 @@
         "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches",
         "EventCode": "0xAB",
         "EventName": "DSB2MITE_SWITCHES.COUNT",
-        "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses.\nNote: Invoking MITE requires two or three cycles delay.",
+        "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses. Note: Invoking MITE requires two or three cycles delay.",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -267,11 +267,11 @@
         "UMask": "0x4"
     },
     {
-        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops [This event is alias to IDQ.DSB_CYCLES_OK]",
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 or more Uops [This event is alias to IDQ.DSB_CYCLES_OK]",
         "CounterMask": "4",
         "EventCode": "0x79",
         "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
-        "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.DSB_CYCLES_OK]",
+        "PublicDescription": "Counts the number of cycles 4 or more uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.DSB_CYCLES_OK]",
         "SampleAfterValue": "2000003",
         "UMask": "0x18"
     },
@@ -321,11 +321,11 @@
         "UMask": "0x18"
     },
     {
-        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]",
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 or more Uops [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]",
         "CounterMask": "4",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]",
+        "PublicDescription": "Counts the number of cycles 4 or more uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]",
         "SampleAfterValue": "2000003",
         "UMask": "0x18"
     },
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/cache.json b/tools/perf/pmu-events/arch/x86/skylakex/cache.json
index d28d8822a51a81..14229f4b29d834 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/cache.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/cache.json
@@ -764,6 +764,15 @@
         "UMask": "0x1"
     },
     {
+        "BriefDescription": "OFFCORE_RESPONSE.ALL_READS.L3_HIT.HIT_OTHER_CORE_FWD hit in the L3 and the snoop to one of the sibling cores hits the line in E/S/F state and the line is forwarded.",
+        "EventCode": "0xB7, 0xBB",
+        "EventName": "OFFCORE_RESPONSE.ALL_READS.L3_HIT.HIT_OTHER_CORE_FWD",
+        "MSRIndex": "0x1a6,0x1a7",
+        "MSRValue": "0x8003C07F7",
+        "SampleAfterValue": "100003",
+        "UMask": "0x1"
+    },
+    {
         "BriefDescription": "Counts all demand & prefetch RFOs that have any response type.",
         "EventCode": "0xB7, 0xBB",
         "EventName": "OFFCORE_RESPONSE.ALL_RFO.ANY_RESPONSE",
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json
index 095904c7700198..d6f543471b2436 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/frontend.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/frontend.json
@@ -19,7 +19,7 @@
         "BriefDescription": "Decode Stream Buffer (DSB)-to-MITE switches",
         "EventCode": "0xAB",
         "EventName": "DSB2MITE_SWITCHES.COUNT",
-        "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses.\nNote: Invoking MITE requires two or three cycles delay.",
+        "PublicDescription": "This event counts the number of the Decode Stream Buffer (DSB)-to-MITE switches including all misses because of missing Decode Stream Buffer (DSB) cache and u-arch forced misses. Note: Invoking MITE requires two or three cycles delay.",
         "SampleAfterValue": "2000003",
         "UMask": "0x1"
     },
@@ -267,11 +267,11 @@
         "UMask": "0x4"
     },
     {
-        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops [This event is alias to IDQ.DSB_CYCLES_OK]",
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 or more Uops [This event is alias to IDQ.DSB_CYCLES_OK]",
         "CounterMask": "4",
         "EventCode": "0x79",
         "EventName": "IDQ.ALL_DSB_CYCLES_4_UOPS",
-        "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.DSB_CYCLES_OK]",
+        "PublicDescription": "Counts the number of cycles 4 or more uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.DSB_CYCLES_OK]",
         "SampleAfterValue": "2000003",
         "UMask": "0x18"
     },
@@ -321,11 +321,11 @@
         "UMask": "0x18"
     },
     {
-        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 Uops [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]",
+        "BriefDescription": "Cycles Decode Stream Buffer (DSB) is delivering 4 or more Uops [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]",
         "CounterMask": "4",
         "EventCode": "0x79",
         "EventName": "IDQ.DSB_CYCLES_OK",
-        "PublicDescription": "Counts the number of cycles 4 uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]",
+        "PublicDescription": "Counts the number of cycles 4 or more uops were delivered to Instruction Decode Queue (IDQ) from the Decode Stream Buffer (DSB) path. Count includes uops that may 'bypass' the IDQ. [This event is alias to IDQ.ALL_DSB_CYCLES_4_UOPS]",
         "SampleAfterValue": "2000003",
         "UMask": "0x18"
     },
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/memory.json b/tools/perf/pmu-events/arch/x86/skylakex/memory.json
index 2b797dbc75fe04..dba3cd6b3690e5 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/memory.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/memory.json
@@ -864,7 +864,7 @@
         "BriefDescription": "Number of times an RTM execution aborted due to any reasons (multiple categories may count as one).",
         "EventCode": "0xC9",
         "EventName": "RTM_RETIRED.ABORTED",
-        "PEBS": "1",
+        "PEBS": "2",
         "PublicDescription": "Number of times RTM abort was triggered.",
         "SampleAfterValue": "2000003",
         "UMask": "0x4"
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/other.json b/tools/perf/pmu-events/arch/x86/skylakex/other.json
index cda8a7a45f0c04..2511d722327a12 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/other.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/other.json
@@ -19,7 +19,7 @@
         "BriefDescription": "Core cycles where the core was running in a manner where Turbo may be clipped to the AVX512 turbo schedule.",
         "EventCode": "0x28",
         "EventName": "CORE_POWER.LVL2_TURBO_LICENSE",
-        "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server michroarchtecture).  This includes high current AVX 512-bit instructions.",
+        "PublicDescription": "Core cycles where the core was running with power-delivery for license level 2 (introduced in Skylake Server microarchitecture).  This includes high current AVX 512-bit instructions.",
         "SampleAfterValue": "200003",
         "UMask": "0x20"
     },
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json
index 66d686cc933e35..c50ddf5b40dd09 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/pipeline.json
@@ -396,7 +396,7 @@
         "Errata": "SKL091, SKL044",
         "EventCode": "0xC0",
         "EventName": "INST_RETIRED.NOP",
-        "PEBS": "1",
+        "PEBS": "2",
         "SampleAfterValue": "2000003",
         "UMask": "0x2"
     },
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
index 025e836a1c80dc..8126f952a30c85 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/skx-metrics.json
@@ -652,23 +652,20 @@
     {
         "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
         "MetricExpr": "(100 * (1 - tma_core_bound / (((EXE_ACTIVITY.EXE_BOUND_0_PORTS + tma_core_bound * RS_EVENTS.EMPTY_CYCLES) / CPU_CLK_UNHALTED.THREAD * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CPU_CLK_UNHALTED.THREAD * CPU_CLK_UNHALTED.THREAD + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / CPU_CLK_UNHALTED.THREAD if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / CPU_CLK_UNHALTED.THREAD) if tma_core_bound < (((EXE_ACTIVITY.EXE_BOUND_0_PORTS + tma_core_bound * RS_EVENTS.EMPTY_CYCLES) / CPU_CLK_UNHALTED.THREAD * (CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY) / CPU_CLK_UNHALTED.THREAD * CPU_CLK_UNHALTED.THREAD + (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL)) / CPU_CLK_UNHALTED.THREAD if ARITH.DIVIDER_ACTIVE < CYCLE_ACTIVITY.STALLS_TOTAL - CYCLE_ACTIVITY.STALLS_MEM_ANY else (EXE_ACTIVITY.1_PORTS_UTIL + tma_retiring * EXE_ACTIVITY.2_PORTS_UTIL) / CPU_CLK_UNHALTED.THREAD) else 1) if tma_info_system_smt_2t_utilization > 0.5 else 0)",
-        "MetricGroup": "Cor;SMT;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_botlnk_core_bound_likely",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Cor;SMT",
+        "MetricName": "tma_info_botlnk_core_bound_likely"
     },
     {
         "BriefDescription": "Total pipeline cost of DSB (uop cache) misses - subset of the Instruction_Fetch_BW Bottleneck.",
         "MetricExpr": "100 * (100 * (tma_fetch_latency * (DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD) / ((ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / CPU_CLK_UNHALTED.THREAD + ICACHE_TAG.STALLS / CPU_CLK_UNHALTED.THREAD + (INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD + 9 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD) + min(2 * IDQ.MS_SWITCHES / CPU_CLK_UNHALTED.THREAD, 1) + DECODE.LCP / CPU_CLK_UNHALTED.THREAD + DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD) + tma_fetch_bandwidth * tma_mite / (tma_mite + tma_dsb)))",
-        "MetricGroup": "DSBmiss;Fed;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_botlnk_dsb_misses",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "DSBmiss;Fed",
+        "MetricName": "tma_info_botlnk_dsb_misses"
     },
     {
         "BriefDescription": "Total pipeline cost of Instruction Cache misses - subset of the Big_Code Bottleneck.",
         "MetricExpr": "100 * (100 * (tma_fetch_latency * ((ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / CPU_CLK_UNHALTED.THREAD) / ((ICACHE_16B.IFDATA_STALL + 2 * cpu@ICACHE_16B.IFDATA_STALL\\,cmask\\=0x1\\,edge\\=0x1@) / CPU_CLK_UNHALTED.THREAD + ICACHE_TAG.STALLS / CPU_CLK_UNHALTED.THREAD + (INT_MISC.CLEAR_RESTEER_CYCLES / CPU_CLK_UNHALTED.THREAD + 9 * BACLEARS.ANY / CPU_CLK_UNHALTED.THREAD) + min(2 * IDQ.MS_SWITCHES / CPU_CLK_UNHALTED.THREAD, 1) + DECODE.LCP / CPU_CLK_UNHALTED.THREAD + DSB2MITE_SWITCHES.PENALTY_CYCLES / CPU_CLK_UNHALTED.THREAD)))",
-        "MetricGroup": "Fed;FetchLat;IcMiss;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_botlnk_ic_misses",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Fed;FetchLat;IcMiss",
+        "MetricName": "tma_info_botlnk_ic_misses"
     },
     {
         "BriefDescription": "Probability of Core Bound bottleneck hidden by SMT-profiling artifacts",
@@ -1021,9 +1018,8 @@
     {
         "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
         "MetricExpr": "tma_info_memory_tlb_code_stlb_mpki",
-        "MetricGroup": "Fed;MemoryTLB;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_code_stlb_mpki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Fed;MemoryTLB",
+        "MetricName": "tma_info_memory_code_stlb_mpki"
     },
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
@@ -1064,9 +1060,8 @@
     {
         "BriefDescription": "Average Parallel L2 cache miss data reads",
         "MetricExpr": "tma_info_memory_latency_data_l2_mlp",
-        "MetricGroup": "Memory_BW;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_data_l2_mlp",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Memory_BW;Offcore",
+        "MetricName": "tma_info_memory_data_l2_mlp"
     },
     {
         "BriefDescription": "Fill Buffer (FB) hits per kilo instructions for retired demand loads (L1D misses that merge into ongoing miss-handling entries)",
@@ -1083,9 +1078,8 @@
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L1 data cache [GB / sec]",
         "MetricExpr": "64 * L1D.REPLACEMENT / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_l1d_cache_fill_bw_2t"
     },
     {
         "BriefDescription": "L1 cache true misses per kilo instruction for retired demand loads",
@@ -1108,23 +1102,20 @@
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L2 cache [GB / sec]",
         "MetricExpr": "64 * L2_LINES_IN.ALL / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l2_cache_fill_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_l2_cache_fill_bw_2t"
     },
     {
         "BriefDescription": "Rate of non silent evictions from the L2 cache per Kilo instruction",
         "MetricExpr": "1e3 * L2_LINES_OUT.NON_SILENT / INST_RETIRED.ANY",
-        "MetricGroup": "L2Evicts;Mem;Server;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l2_evictions_nonsilent_pki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "L2Evicts;Mem;Server",
+        "MetricName": "tma_info_memory_l2_evictions_nonsilent_pki"
     },
     {
         "BriefDescription": "Rate of silent evictions from the L2 cache per Kilo instruction where the evicted lines are dropped (no writeback to L3 or memory)",
         "MetricExpr": "1e3 * L2_LINES_OUT.SILENT / INST_RETIRED.ANY",
-        "MetricGroup": "L2Evicts;Mem;Server;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l2_evictions_silent_pki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "L2Evicts;Mem;Server",
+        "MetricName": "tma_info_memory_l2_evictions_silent_pki"
     },
     {
         "BriefDescription": "L2 cache hits per kilo instruction for all request types (including speculative)",
@@ -1165,9 +1156,8 @@
     {
         "BriefDescription": "Average per-core data access bandwidth to the L3 cache [GB / sec]",
         "MetricExpr": "64 * OFFCORE_REQUESTS.ALL_REQUESTS / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l3_cache_access_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW;Offcore",
+        "MetricName": "tma_info_memory_l3_cache_access_bw_2t"
     },
     {
         "BriefDescription": "",
@@ -1178,9 +1168,8 @@
     {
         "BriefDescription": "Average per-core data fill bandwidth to the L3 cache [GB / sec]",
         "MetricExpr": "64 * LONGEST_LAT_CACHE.MISS / 1e9 / (duration_time * 1e3 / 1e3)",
-        "MetricGroup": "Mem;MemoryBW;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_l3_cache_fill_bw_2t",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryBW",
+        "MetricName": "tma_info_memory_l3_cache_fill_bw_2t"
     },
     {
         "BriefDescription": "L3 cache true misses per kilo instruction for retired demand loads",
@@ -1209,16 +1198,14 @@
     {
         "BriefDescription": "Average Latency for L2 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS.DEMAND_DATA_RD",
-        "MetricGroup": "Memory_Lat;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_load_l2_miss_latency",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Memory_Lat;Offcore",
+        "MetricName": "tma_info_memory_load_l2_miss_latency"
     },
     {
         "BriefDescription": "Average Parallel L2 cache miss demand Loads",
         "MetricExpr": "OFFCORE_REQUESTS_OUTSTANDING.DEMAND_DATA_RD / OFFCORE_REQUESTS_OUTSTANDING.CYCLES_WITH_DEMAND_DATA_RD",
-        "MetricGroup": "Memory_BW;Offcore;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_load_l2_mlp",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Memory_BW;Offcore",
+        "MetricName": "tma_info_memory_load_l2_mlp"
     },
     {
         "BriefDescription": "Actual Average Latency for L1 data-cache miss demand load operations (in core cycles)",
@@ -1229,9 +1216,8 @@
     {
         "BriefDescription": "STLB (2nd level TLB) data load speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
         "MetricExpr": "tma_info_memory_tlb_load_stlb_mpki",
-        "MetricGroup": "Mem;MemoryTLB;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_load_stlb_mpki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryTLB",
+        "MetricName": "tma_info_memory_load_stlb_mpki"
     },
     {
         "BriefDescription": "Un-cacheable retired load per kilo instruction",
@@ -1249,16 +1235,14 @@
     {
         "BriefDescription": "Utilization of the core's Page Walker(s) serving STLB misses triggered by instruction/Load/Store accesses",
         "MetricExpr": "tma_info_memory_tlb_page_walks_utilization",
-        "MetricGroup": "Mem;MemoryTLB;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_page_walks_utilization",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryTLB",
+        "MetricName": "tma_info_memory_page_walks_utilization"
     },
     {
         "BriefDescription": "STLB (2nd level TLB) data store speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
         "MetricExpr": "tma_info_memory_tlb_store_stlb_mpki",
-        "MetricGroup": "Mem;MemoryTLB;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_store_stlb_mpki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem;MemoryTLB",
+        "MetricName": "tma_info_memory_store_stlb_mpki"
     },
     {
         "BriefDescription": "STLB (2nd level TLB) code speculative misses per kilo instruction (misses of any page-size that complete the page walk)",
@@ -1289,9 +1273,8 @@
     {
         "BriefDescription": "Un-cacheable retired load per kilo instruction",
         "MetricExpr": "1e3 * MEM_LOAD_MISC_RETIRED.UC / INST_RETIRED.ANY",
-        "MetricGroup": "Mem;TopdownL1;tma_L1_group",
-        "MetricName": "tma_info_memory_uc_load_pki",
-        "MetricgroupNoGroup": "TopdownL1"
+        "MetricGroup": "Mem",
+        "MetricName": "tma_info_memory_uc_load_pki"
     },
     {
         "BriefDescription": "",
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-interconnect.json
index 3eece8a728b56b..f32d4d9d283a3f 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-interconnect.json
@@ -38,7 +38,7 @@
         "EventCode": "0x10",
         "EventName": "UNC_I_COHERENT_OPS.CLFLUSH",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x80",
         "Unit": "IRP"
     },
@@ -47,7 +47,7 @@
         "EventCode": "0x10",
         "EventName": "UNC_I_COHERENT_OPS.CRD",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x2",
         "Unit": "IRP"
     },
@@ -56,7 +56,7 @@
         "EventCode": "0x10",
         "EventName": "UNC_I_COHERENT_OPS.DRD",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x4",
         "Unit": "IRP"
     },
@@ -65,7 +65,7 @@
         "EventCode": "0x10",
         "EventName": "UNC_I_COHERENT_OPS.PCIDCAHINT",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x20",
         "Unit": "IRP"
     },
@@ -74,7 +74,7 @@
         "EventCode": "0x10",
         "EventName": "UNC_I_COHERENT_OPS.PCIRDCUR",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x1",
         "Unit": "IRP"
     },
@@ -101,7 +101,7 @@
         "EventCode": "0x10",
         "EventName": "UNC_I_COHERENT_OPS.WBMTOI",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x40",
         "Unit": "IRP"
     },
@@ -500,7 +500,7 @@
         "EventCode": "0x11",
         "EventName": "UNC_I_TRANSACTIONS.WRITES",
         "PerPkg": "1",
-        "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore.  This can be filtered based on request type in addition to the source queue.  Note the special filtering equation.  We do OR-reduction on the request type.  If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Trackes only write requests.  Each write request should have a prefetch, so there is no need to explicitly track these requests.  For writes that are tickled and have to retry, the counter will be incremented for each retry.",
+        "PublicDescription": "Counts the number of Inbound transactions from the IRP to the Uncore.  This can be filtered based on request type in addition to the source queue.  Note the special filtering equation.  We do OR-reduction on the request type.  If the SOURCE bit is set, then we also do AND qualification based on the source portID.; Tracks only write requests.  Each write request should have a prefetch, so there is no need to explicitly track these requests.  For writes that are tickled and have to retry, the counter will be incremented for each retry.",
         "UMask": "0x2",
         "Unit": "IRP"
     },
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/uncore-io.json b/tools/perf/pmu-events/arch/x86/skylakex/uncore-io.json
index 2a3a709018bb6b..743c91f3d2f0b7 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/uncore-io.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/uncore-io.json
@@ -34,7 +34,7 @@
         "EventCode": "0x1",
         "EventName": "UNC_IIO_CLOCKTICKS",
         "PerPkg": "1",
-        "PublicDescription": "Counts clockticks of the 1GHz trafiic controller clock in the IIO unit.",
+        "PublicDescription": "Counts clockticks of the 1GHz traffic controller clock in the IIO unit.",
         "Unit": "IIO"
     },
     {
diff --git a/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json b/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json
index f59405877ae8bc..73feadaf767406 100644
--- a/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json
+++ b/tools/perf/pmu-events/arch/x86/skylakex/virtual-memory.json
@@ -205,7 +205,7 @@
         "BriefDescription": "Counts 1 per cycle for each PMH that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake.",
         "EventCode": "0x85",
         "EventName": "ITLB_MISSES.WALK_PENDING",
-        "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake michroarchitecture.",
+        "PublicDescription": "Counts 1 per cycle for each PMH (Page Miss Handler) that is busy with a page walk for an instruction fetch request. EPT page walk duration are excluded in Skylake microarchitecture.",
         "SampleAfterValue": "100003",
         "UMask": "0x10"
     },
diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-cache.json b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-cache.json
index a68a5bb05c22b2..4090e4da1bd01e 100644
--- a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-cache.json
+++ b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-cache.json
@@ -1444,7 +1444,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.DATA_READ_LOCAL",
+        "BriefDescription": "This event is deprecated.",
         "Deprecated": "1",
         "EventCode": "0x34",
         "EventName": "UNC_CHA_LLC_LOOKUP.DMND_READ_LOCAL",
@@ -1638,7 +1638,7 @@
         "Unit": "CHA"
     },
     {
-        "BriefDescription": "This event is deprecated. Refer to new event UNC_CHA_LLC_LOOKUP.RFO_LOCAL",
+        "BriefDescription": "This event is deprecated.",
         "Deprecated": "1",
         "EventCode": "0x34",
         "EventName": "UNC_CHA_LLC_LOOKUP.RFO_PREF_LOCAL",
diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-interconnect.json b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-interconnect.json
index 7e2895f7fe3d4c..7cc3635b118b4e 100644
--- a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-interconnect.json
+++ b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-interconnect.json
@@ -38,7 +38,7 @@
         "EventCode": "0x10",
         "EventName": "UNC_I_COHERENT_OPS.CLFLUSH",
         "PerPkg": "1",
-        "PublicDescription": "Coherent Ops : CLFlush : Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Coherent Ops : CLFlush : Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x80",
         "Unit": "IRP"
     },
@@ -65,7 +65,7 @@
         "EventCode": "0x10",
         "EventName": "UNC_I_COHERENT_OPS.WBMTOI",
         "PerPkg": "1",
-        "PublicDescription": "Coherent Ops : WbMtoI : Counts the number of coherency related operations servied by the IRP",
+        "PublicDescription": "Coherent Ops : WbMtoI : Counts the number of coherency related operations serviced by the IRP",
         "UMask": "0x40",
         "Unit": "IRP"
     },
@@ -454,7 +454,7 @@
         "EventCode": "0x11",
         "EventName": "UNC_I_TRANSACTIONS.WRITES",
         "PerPkg": "1",
-        "PublicDescription": "Inbound Transaction Count : Writes : Counts the number of Inbound transactions from the IRP to the Uncore.  This can be filtered based on request type in addition to the source queue.  Note the special filtering equation.  We do OR-reduction on the request type.  If the SOURCE bit is set, then we also do AND qualification based on the source portID. : Trackes only write requests.  Each write request should have a prefetch, so there is no need to explicitly track these requests.  For writes that are tickled and have to retry, the counter will be incremented for each retry.",
+        "PublicDescription": "Inbound Transaction Count : Writes : Counts the number of Inbound transactions from the IRP to the Uncore.  This can be filtered based on request type in addition to the source queue.  Note the special filtering equation.  We do OR-reduction on the request type.  If the SOURCE bit is set, then we also do AND qualification based on the source portID. : Tracks only write requests.  Each write request should have a prefetch, so there is no need to explicitly track these requests.  For writes that are tickled and have to retry, the counter will be incremented for each retry.",
         "UMask": "0x2",
         "Unit": "IRP"
     },
diff --git a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-io.json b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-io.json
index ecdd6f0f8e8f6e..de156e499f5661 100644
--- a/tools/perf/pmu-events/arch/x86/snowridgex/uncore-io.json
+++ b/tools/perf/pmu-events/arch/x86/snowridgex/uncore-io.json
@@ -2506,17 +2506,6 @@
         "Unit": "IIO"
     },
     {
-        "BriefDescription": "Number requests sent to PCIe from main die : From IRP",
-        "EventCode": "0xC2",
-        "EventName": "UNC_IIO_NUM_REQ_FROM_CPU.IRP",
-        "FCMask": "0x07",
-        "PerPkg": "1",
-        "PortMask": "0xFF",
-        "PublicDescription": "Number requests sent to PCIe from main die : From IRP : Captures Posted/Non-posted allocations from IRP. i.e. either non-confined P2P traffic or from the CPU",
-        "UMask": "0x1",
-        "Unit": "IIO"
-    },
-    {
         "BriefDescription": "Number requests sent to PCIe from main die : From ITC",
         "EventCode": "0xC2",
         "EventName": "UNC_IIO_NUM_REQ_FROM_CPU.ITC",
diff --git a/tools/perf/scripts/python/parallel-perf.py b/tools/perf/scripts/python/parallel-perf.py
new file mode 100755
index 00000000000000..21f32ec5ed46df
--- /dev/null
+++ b/tools/perf/scripts/python/parallel-perf.py
@@ -0,0 +1,988 @@
+#!/usr/bin/env python3
+# SPDX-License-Identifier: GPL-2.0
+#
+# Run a perf script command multiple times in parallel, using perf script
+# options --cpu and --time so that each job processes a different chunk
+# of the data.
+#
+# Copyright (c) 2024, Intel Corporation.
+
+import subprocess
+import argparse
+import pathlib
+import shlex
+import time
+import copy
+import sys
+import os
+import re
+
+glb_prog_name = "parallel-perf.py"
+glb_min_interval = 10.0
+glb_min_samples = 64
+
+class Verbosity():
+
+	def __init__(self, quiet=False, verbose=False, debug=False):
+		self.normal    = True
+		self.verbose   = verbose
+		self.debug     = debug
+		self.self_test = True
+		if self.debug:
+			self.verbose = True
+		if self.verbose:
+			quiet = False
+		if quiet:
+			self.normal = False
+
+# Manage work (Start/Wait/Kill), as represented by a subprocess.Popen command
+class Work():
+
+	def __init__(self, cmd, pipe_to, output_dir="."):
+		self.popen = None
+		self.consumer = None
+		self.cmd = cmd
+		self.pipe_to = pipe_to
+		self.output_dir = output_dir
+		self.cmdout_name = f"{output_dir}/cmd.txt"
+		self.stdout_name = f"{output_dir}/out.txt"
+		self.stderr_name = f"{output_dir}/err.txt"
+
+	def Command(self):
+		sh_cmd = [ shlex.quote(x) for x in self.cmd ]
+		return " ".join(self.cmd)
+
+	def Stdout(self):
+		return open(self.stdout_name, "w")
+
+	def Stderr(self):
+		return open(self.stderr_name, "w")
+
+	def CreateOutputDir(self):
+		pathlib.Path(self.output_dir).mkdir(parents=True, exist_ok=True)
+
+	def Start(self):
+		if self.popen:
+			return
+		self.CreateOutputDir()
+		with open(self.cmdout_name, "w") as f:
+			f.write(self.Command())
+			f.write("\n")
+		stdout = self.Stdout()
+		stderr = self.Stderr()
+		if self.pipe_to:
+			self.popen = subprocess.Popen(self.cmd, stdout=subprocess.PIPE, stderr=stderr)
+			args = shlex.split(self.pipe_to)
+			self.consumer = subprocess.Popen(args, stdin=self.popen.stdout, stdout=stdout, stderr=stderr)
+		else:
+			self.popen = subprocess.Popen(self.cmd, stdout=stdout, stderr=stderr)
+
+	def RemoveEmptyErrFile(self):
+		if os.path.exists(self.stderr_name):
+			if os.path.getsize(self.stderr_name) == 0:
+				os.unlink(self.stderr_name)
+
+	def Errors(self):
+		if os.path.exists(self.stderr_name):
+			if os.path.getsize(self.stderr_name) != 0:
+				return [ f"Non-empty error file {self.stderr_name}" ]
+		return []
+
+	def TidyUp(self):
+		self.RemoveEmptyErrFile()
+
+	def RawPollWait(self, p, wait):
+		if wait:
+			return p.wait()
+		return p.poll()
+
+	def Poll(self, wait=False):
+		if not self.popen:
+			return None
+		result = self.RawPollWait(self.popen, wait)
+		if self.consumer:
+			res = result
+			result = self.RawPollWait(self.consumer, wait)
+			if result != None and res == None:
+				self.popen.kill()
+				result = None
+			elif result == 0 and res != None and res != 0:
+				result = res
+		if result != None:
+			self.TidyUp()
+		return result
+
+	def Wait(self):
+		return self.Poll(wait=True)
+
+	def Kill(self):
+		if not self.popen:
+			return
+		self.popen.kill()
+		if self.consumer:
+			self.consumer.kill()
+
+def KillWork(worklist, verbosity):
+	for w in worklist:
+		w.Kill()
+	for w in worklist:
+		w.Wait()
+
+def NumberOfCPUs():
+	return os.sysconf("SC_NPROCESSORS_ONLN")
+
+def NanoSecsToSecsStr(x):
+	if x == None:
+		return ""
+	x = str(x)
+	if len(x) < 10:
+		x = "0" * (10 - len(x)) + x
+	return x[:len(x) - 9] + "." + x[-9:]
+
+def InsertOptionAfter(cmd, option, after):
+	try:
+		pos = cmd.index(after)
+		cmd.insert(pos + 1, option)
+	except:
+		cmd.append(option)
+
+def CreateWorkList(cmd, pipe_to, output_dir, cpus, time_ranges_by_cpu):
+	max_len = len(str(cpus[-1]))
+	cpu_dir_fmt = f"cpu-%.{max_len}u"
+	worklist = []
+	pos = 0
+	for cpu in cpus:
+		if cpu >= 0:
+			cpu_dir = os.path.join(output_dir, cpu_dir_fmt % cpu)
+			cpu_option = f"--cpu={cpu}"
+		else:
+			cpu_dir = output_dir
+			cpu_option = None
+
+		tr_dir_fmt = "time-range"
+
+		if len(time_ranges_by_cpu) > 1:
+			time_ranges = time_ranges_by_cpu[pos]
+			tr_dir_fmt += f"-{pos}"
+			pos += 1
+		else:
+			time_ranges = time_ranges_by_cpu[0]
+
+		max_len = len(str(len(time_ranges)))
+		tr_dir_fmt += f"-%.{max_len}u"
+
+		i = 0
+		for r in time_ranges:
+			if r == [None, None]:
+				time_option = None
+				work_output_dir = cpu_dir
+			else:
+				time_option = "--time=" + NanoSecsToSecsStr(r[0]) + "," + NanoSecsToSecsStr(r[1])
+				work_output_dir = os.path.join(cpu_dir, tr_dir_fmt % i)
+				i += 1
+			work_cmd = list(cmd)
+			if time_option != None:
+				InsertOptionAfter(work_cmd, time_option, "script")
+			if cpu_option != None:
+				InsertOptionAfter(work_cmd, cpu_option, "script")
+			w = Work(work_cmd, pipe_to, work_output_dir)
+			worklist.append(w)
+	return worklist
+
+def DoRunWork(worklist, nr_jobs, verbosity):
+	nr_to_do = len(worklist)
+	not_started = list(worklist)
+	running = []
+	done = []
+	chg = False
+	while True:
+		nr_done = len(done)
+		if chg and verbosity.normal:
+			nr_run = len(running)
+			print(f"\rThere are {nr_to_do} jobs: {nr_done} completed, {nr_run} running", flush=True, end=" ")
+			if verbosity.verbose:
+				print()
+			chg = False
+		if nr_done == nr_to_do:
+			break
+		while len(running) < nr_jobs and len(not_started):
+			w = not_started.pop(0)
+			running.append(w)
+			if verbosity.verbose:
+				print("Starting:", w.Command())
+			w.Start()
+			chg = True
+		if len(running):
+			time.sleep(0.1)
+		finished = []
+		not_finished = []
+		while len(running):
+			w = running.pop(0)
+			r = w.Poll()
+			if r == None:
+				not_finished.append(w)
+				continue
+			if r == 0:
+				if verbosity.verbose:
+					print("Finished:", w.Command())
+				finished.append(w)
+				chg = True
+				continue
+			if verbosity.normal and not verbosity.verbose:
+				print()
+			print("Job failed!\n    return code:", r, "\n    command:    ", w.Command())
+			if w.pipe_to:
+				print("    piped to:   ", w.pipe_to)
+			print("Killing outstanding jobs")
+			KillWork(not_finished, verbosity)
+			KillWork(running, verbosity)
+			return False
+		running = not_finished
+		done += finished
+	errorlist = []
+	for w in worklist:
+		errorlist += w.Errors()
+	if len(errorlist):
+		print("Errors:")
+		for e in errorlist:
+			print(e)
+	elif verbosity.normal:
+		print("\r"," "*50, "\rAll jobs finished successfully", flush=True)
+	return True
+
+def RunWork(worklist, nr_jobs=NumberOfCPUs(), verbosity=Verbosity()):
+	try:
+		return DoRunWork(worklist, nr_jobs, verbosity)
+	except:
+		for w in worklist:
+			w.Kill()
+		raise
+	return True
+
+def ReadHeader(perf, file_name):
+	return subprocess.Popen([perf, "script", "--header-only", "--input", file_name], stdout=subprocess.PIPE).stdout.read().decode("utf-8")
+
+def ParseHeader(hdr):
+	result = {}
+	lines = hdr.split("\n")
+	for line in lines:
+		if ":" in line and line[0] == "#":
+			pos = line.index(":")
+			name = line[1:pos-1].strip()
+			value = line[pos+1:].strip()
+			if name in result:
+				orig_name = name
+				nr = 2
+				while True:
+					name = f"{orig_name} {nr}"
+					if name not in result:
+						break
+					nr += 1
+			result[name] = value
+	return result
+
+def HeaderField(hdr_dict, hdr_fld):
+	if hdr_fld not in hdr_dict:
+		raise Exception(f"'{hdr_fld}' missing from header information")
+	return hdr_dict[hdr_fld]
+
+# Represent the position of an option within a command string
+# and provide the option value and/or remove the option
+class OptPos():
+
+	def Init(self, opt_element=-1, value_element=-1, opt_pos=-1, value_pos=-1, error=None):
+		self.opt_element = opt_element		# list element that contains option
+		self.value_element = value_element	# list element that contains option value
+		self.opt_pos = opt_pos			# string position of option
+		self.value_pos = value_pos		# string position of value
+		self.error = error			# error message string
+
+	def __init__(self, args, short_name, long_name, default=None):
+		self.args = list(args)
+		self.default = default
+		n = 2 + len(long_name)
+		m = len(short_name)
+		pos = -1
+		for opt in args:
+			pos += 1
+			if m and opt[:2] == f"-{short_name}":
+				if len(opt) == 2:
+					if pos + 1 < len(args):
+						self.Init(pos, pos + 1, 0, 0)
+					else:
+						self.Init(error = f"-{short_name} option missing value")
+				else:
+					self.Init(pos, pos, 0, 2)
+				return
+			if opt[:n] == f"--{long_name}":
+				if len(opt) == n:
+					if pos + 1 < len(args):
+						self.Init(pos, pos + 1, 0, 0)
+					else:
+						self.Init(error = f"--{long_name} option missing value")
+				elif opt[n] == "=":
+					self.Init(pos, pos, 0, n + 1)
+				else:
+					self.Init(error = f"--{long_name} option expected '='")
+				return
+			if m and opt[:1] == "-" and opt[:2] != "--" and short_name in opt:
+				ipos = opt.index(short_name)
+				if "-" in opt[1:]:
+					hpos = opt[1:].index("-")
+					if hpos < ipos:
+						continue
+				if ipos + 1 == len(opt):
+					if pos + 1 < len(args):
+						self.Init(pos, pos + 1, ipos, 0)
+					else:
+						self.Init(error = f"-{short_name} option missing value")
+				else:
+					self.Init(pos, pos, ipos, ipos + 1)
+				return
+		self.Init()
+
+	def Value(self):
+		if self.opt_element >= 0:
+			if self.opt_element != self.value_element:
+				return self.args[self.value_element]
+			else:
+				return self.args[self.value_element][self.value_pos:]
+		return self.default
+
+	def Remove(self, args):
+		if self.opt_element == -1:
+			return
+		if self.opt_element != self.value_element:
+			del args[self.value_element]
+		if self.opt_pos:
+			args[self.opt_element] = args[self.opt_element][:self.opt_pos]
+		else:
+			del args[self.opt_element]
+
+def DetermineInputFileName(cmd):
+	p = OptPos(cmd, "i", "input", "perf.data")
+	if p.error:
+		raise Exception(f"perf command {p.error}")
+	file_name = p.Value()
+	if not os.path.exists(file_name):
+		raise Exception(f"perf command input file '{file_name}' not found")
+	return file_name
+
+def ReadOption(args, short_name, long_name, err_prefix, remove=False):
+	p = OptPos(args, short_name, long_name)
+	if p.error:
+		raise Exception(f"{err_prefix}{p.error}")
+	value = p.Value()
+	if remove:
+		p.Remove(args)
+	return value
+
+def ExtractOption(args, short_name, long_name, err_prefix):
+	return ReadOption(args, short_name, long_name, err_prefix, True)
+
+def ReadPerfOption(args, short_name, long_name):
+	return ReadOption(args, short_name, long_name, "perf command ")
+
+def ExtractPerfOption(args, short_name, long_name):
+	return ExtractOption(args, short_name, long_name, "perf command ")
+
+def PerfDoubleQuickCommands(cmd, file_name):
+	cpu_str = ReadPerfOption(cmd, "C", "cpu")
+	time_str = ReadPerfOption(cmd, "", "time")
+	# Use double-quick sampling to determine trace data density
+	times_cmd = ["perf", "script", "--ns", "--input", file_name, "--itrace=qqi"]
+	if cpu_str != None and cpu_str != "":
+		times_cmd.append(f"--cpu={cpu_str}")
+	if time_str != None and time_str != "":
+		times_cmd.append(f"--time={time_str}")
+	cnts_cmd = list(times_cmd)
+	cnts_cmd.append("-Fcpu")
+	times_cmd.append("-Fcpu,time")
+	return cnts_cmd, times_cmd
+
+class CPUTimeRange():
+	def __init__(self, cpu):
+		self.cpu = cpu
+		self.sample_cnt = 0
+		self.time_ranges = None
+		self.interval = 0
+		self.interval_remaining = 0
+		self.remaining = 0
+		self.tr_pos = 0
+
+def CalcTimeRangesByCPU(line, cpu, cpu_time_ranges, max_time):
+	cpu_time_range = cpu_time_ranges[cpu]
+	cpu_time_range.remaining -= 1
+	cpu_time_range.interval_remaining -= 1
+	if cpu_time_range.remaining == 0:
+		cpu_time_range.time_ranges[cpu_time_range.tr_pos][1] = max_time
+		return
+	if cpu_time_range.interval_remaining == 0:
+		time = TimeVal(line[1][:-1], 0)
+		time_ranges = cpu_time_range.time_ranges
+		time_ranges[cpu_time_range.tr_pos][1] = time - 1
+		time_ranges.append([time, max_time])
+		cpu_time_range.tr_pos += 1
+		cpu_time_range.interval_remaining = cpu_time_range.interval
+
+def CountSamplesByCPU(line, cpu, cpu_time_ranges):
+	try:
+		cpu_time_ranges[cpu].sample_cnt += 1
+	except:
+		print("exception")
+		print("cpu", cpu)
+		print("len(cpu_time_ranges)", len(cpu_time_ranges))
+		raise
+
+def ProcessCommandOutputLines(cmd, per_cpu, fn, *x):
+	# Assume CPU number is at beginning of line and enclosed by []
+	pat = re.compile(r"\s*\[[0-9]+\]")
+	p = subprocess.Popen(cmd, stdout=subprocess.PIPE)
+	while True:
+		if line := p.stdout.readline():
+			line = line.decode("utf-8")
+			if pat.match(line):
+				line = line.split()
+				if per_cpu:
+					# Assumes CPU number is enclosed by []
+					cpu = int(line[0][1:-1])
+				else:
+					cpu = 0
+				fn(line, cpu, *x)
+		else:
+			break
+	p.wait()
+
+def IntersectTimeRanges(new_time_ranges, time_ranges):
+	pos = 0
+	new_pos = 0
+	# Can assume len(time_ranges) != 0 and len(new_time_ranges) != 0
+	# Note also, there *must* be at least one intersection.
+	while pos < len(time_ranges) and new_pos < len(new_time_ranges):
+		# new end < old start => no intersection, remove new
+		if new_time_ranges[new_pos][1] < time_ranges[pos][0]:
+			del new_time_ranges[new_pos]
+			continue
+		# new start > old end => no intersection, check next
+		if new_time_ranges[new_pos][0] > time_ranges[pos][1]:
+			pos += 1
+			if pos < len(time_ranges):
+				continue
+			# no next, so remove remaining
+			while new_pos < len(new_time_ranges):
+				del new_time_ranges[new_pos]
+			return
+		# Found an intersection
+		# new start < old start => adjust new start = old start
+		if new_time_ranges[new_pos][0] < time_ranges[pos][0]:
+			new_time_ranges[new_pos][0] = time_ranges[pos][0]
+		# new end > old end => keep the overlap, insert the remainder
+		if new_time_ranges[new_pos][1] > time_ranges[pos][1]:
+			r = [ time_ranges[pos][1] + 1, new_time_ranges[new_pos][1] ]
+			new_time_ranges[new_pos][1] = time_ranges[pos][1]
+			new_pos += 1
+			new_time_ranges.insert(new_pos, r)
+			continue
+		# new [start, end] is within old [start, end]
+		new_pos += 1
+
+def SplitTimeRangesByTraceDataDensity(time_ranges, cpus, nr, cmd, file_name, per_cpu, min_size, min_interval, verbosity):
+	if verbosity.normal:
+		print("\rAnalyzing...", flush=True, end=" ")
+		if verbosity.verbose:
+			print()
+	cnts_cmd, times_cmd = PerfDoubleQuickCommands(cmd, file_name)
+
+	nr_cpus = cpus[-1] + 1 if per_cpu else 1
+	if per_cpu:
+		nr_cpus = cpus[-1] + 1
+		cpu_time_ranges = [ CPUTimeRange(cpu) for cpu in range(nr_cpus) ]
+	else:
+		nr_cpus = 1
+		cpu_time_ranges = [ CPUTimeRange(-1) ]
+
+	if verbosity.debug:
+		print("nr_cpus", nr_cpus)
+		print("cnts_cmd", cnts_cmd)
+		print("times_cmd", times_cmd)
+
+	# Count the number of "double quick" samples per CPU
+	ProcessCommandOutputLines(cnts_cmd, per_cpu, CountSamplesByCPU, cpu_time_ranges)
+
+	tot = 0
+	mx = 0
+	for cpu_time_range in cpu_time_ranges:
+		cnt = cpu_time_range.sample_cnt
+		tot += cnt
+		if cnt > mx:
+			mx = cnt
+		if verbosity.debug:
+			print("cpu:", cpu_time_range.cpu, "sample_cnt", cnt)
+
+	if min_size < 1:
+		min_size = 1
+
+	if mx < min_size:
+		# Too little data to be worth splitting
+		if verbosity.debug:
+			print("Too little data to split by time")
+		if nr == 0:
+			nr = 1
+		return [ SplitTimeRangesIntoN(time_ranges, nr, min_interval) ]
+
+	if nr:
+		divisor = nr
+		min_size = 1
+	else:
+		divisor = NumberOfCPUs()
+
+	interval = int(round(tot / divisor, 0))
+	if interval < min_size:
+		interval = min_size
+
+	if verbosity.debug:
+		print("divisor", divisor)
+		print("min_size", min_size)
+		print("interval", interval)
+
+	min_time = time_ranges[0][0]
+	max_time = time_ranges[-1][1]
+
+	for cpu_time_range in cpu_time_ranges:
+		cnt = cpu_time_range.sample_cnt
+		if cnt == 0:
+			cpu_time_range.time_ranges = copy.deepcopy(time_ranges)
+			continue
+		# Adjust target interval for CPU to give approximately equal interval sizes
+		# Determine number of intervals, rounding to nearest integer
+		n = int(round(cnt / interval, 0))
+		if n < 1:
+			n = 1
+		# Determine interval size, rounding up
+		d, m = divmod(cnt, n)
+		if m:
+			d += 1
+		cpu_time_range.interval = d
+		cpu_time_range.interval_remaining = d
+		cpu_time_range.remaining = cnt
+		# Init. time ranges for each CPU with the start time
+		cpu_time_range.time_ranges = [ [min_time, max_time] ]
+
+	# Set time ranges so that the same number of "double quick" samples
+	# will fall into each time range.
+	ProcessCommandOutputLines(times_cmd, per_cpu, CalcTimeRangesByCPU, cpu_time_ranges, max_time)
+
+	for cpu_time_range in cpu_time_ranges:
+		if cpu_time_range.sample_cnt:
+			IntersectTimeRanges(cpu_time_range.time_ranges, time_ranges)
+
+	return [cpu_time_ranges[cpu].time_ranges for cpu in cpus]
+
+def SplitSingleTimeRangeIntoN(time_range, n):
+	if n <= 1:
+		return [time_range]
+	start = time_range[0]
+	end   = time_range[1]
+	duration = int((end - start + 1) / n)
+	if duration < 1:
+		return [time_range]
+	time_ranges = []
+	for i in range(n):
+		time_ranges.append([start, start + duration - 1])
+		start += duration
+	time_ranges[-1][1] = end
+	return time_ranges
+
+def TimeRangeDuration(r):
+	return r[1] - r[0] + 1
+
+def TotalDuration(time_ranges):
+	duration = 0
+	for r in time_ranges:
+		duration += TimeRangeDuration(r)
+	return duration
+
+def SplitTimeRangesByInterval(time_ranges, interval):
+	new_ranges = []
+	for r in time_ranges:
+		duration = TimeRangeDuration(r)
+		n = duration / interval
+		n = int(round(n, 0))
+		new_ranges += SplitSingleTimeRangeIntoN(r, n)
+	return new_ranges
+
+def SplitTimeRangesIntoN(time_ranges, n, min_interval):
+	if n <= len(time_ranges):
+		return time_ranges
+	duration = TotalDuration(time_ranges)
+	interval = duration / n
+	if interval < min_interval:
+		interval = min_interval
+	return SplitTimeRangesByInterval(time_ranges, interval)
+
+def RecombineTimeRanges(tr):
+	new_tr = copy.deepcopy(tr)
+	n = len(new_tr)
+	i = 1
+	while i < len(new_tr):
+		# if prev end + 1 == cur start, combine them
+		if new_tr[i - 1][1] + 1 == new_tr[i][0]:
+			new_tr[i][0] = new_tr[i - 1][0]
+			del new_tr[i - 1]
+		else:
+			i += 1
+	return new_tr
+
+def OpenTimeRangeEnds(time_ranges, min_time, max_time):
+	if time_ranges[0][0] <= min_time:
+		time_ranges[0][0] = None
+	if time_ranges[-1][1] >= max_time:
+		time_ranges[-1][1] = None
+
+def BadTimeStr(time_str):
+	raise Exception(f"perf command bad time option: '{time_str}'\nCheck also 'time of first sample' and 'time of last sample' in perf script --header-only")
+
+def ValidateTimeRanges(time_ranges, time_str):
+	n = len(time_ranges)
+	for i in range(n):
+		start = time_ranges[i][0]
+		end   = time_ranges[i][1]
+		if i != 0 and start <= time_ranges[i - 1][1]:
+			BadTimeStr(time_str)
+		if start > end:
+			BadTimeStr(time_str)
+
+def TimeVal(s, dflt):
+	s = s.strip()
+	if s == "":
+		return dflt
+	a = s.split(".")
+	if len(a) > 2:
+		raise Exception(f"Bad time value'{s}'")
+	x = int(a[0])
+	if x < 0:
+		raise Exception("Negative time not allowed")
+	x *= 1000000000
+	if len(a) > 1:
+		x += int((a[1] + "000000000")[:9])
+	return x
+
+def BadCPUStr(cpu_str):
+	raise Exception(f"perf command bad cpu option: '{cpu_str}'\nCheck also 'nrcpus avail' in perf script --header-only")
+
+def ParseTimeStr(time_str, min_time, max_time):
+	if time_str == None or time_str == "":
+		return [[min_time, max_time]]
+	time_ranges = []
+	for r in time_str.split():
+		a = r.split(",")
+		if len(a) != 2:
+			BadTimeStr(time_str)
+		try:
+			start = TimeVal(a[0], min_time)
+			end   = TimeVal(a[1], max_time)
+		except:
+			BadTimeStr(time_str)
+		time_ranges.append([start, end])
+	ValidateTimeRanges(time_ranges, time_str)
+	return time_ranges
+
+def ParseCPUStr(cpu_str, nr_cpus):
+	if cpu_str == None or cpu_str == "":
+		return [-1]
+	cpus = []
+	for r in cpu_str.split(","):
+		a = r.split("-")
+		if len(a) < 1 or len(a) > 2:
+			BadCPUStr(cpu_str)
+		try:
+			start = int(a[0].strip())
+			if len(a) > 1:
+				end = int(a[1].strip())
+			else:
+				end = start
+		except:
+			BadCPUStr(cpu_str)
+		if start < 0 or end < 0 or end < start or end >= nr_cpus:
+			BadCPUStr(cpu_str)
+		cpus.extend(range(start, end + 1))
+	cpus = list(set(cpus)) # Remove duplicates
+	cpus.sort()
+	return cpus
+
+class ParallelPerf():
+
+	def __init__(self, a):
+		for arg_name in vars(a):
+			setattr(self, arg_name, getattr(a, arg_name))
+		self.orig_nr = self.nr
+		self.orig_cmd = list(self.cmd)
+		self.perf = self.cmd[0]
+		if os.path.exists(self.output_dir):
+			raise Exception(f"Output '{self.output_dir}' already exists")
+		if self.jobs < 0 or self.nr < 0 or self.interval < 0:
+			raise Exception("Bad options (negative values): try -h option for help")
+		if self.nr != 0 and self.interval != 0:
+			raise Exception("Cannot specify number of time subdivisions and time interval")
+		if self.jobs == 0:
+			self.jobs = NumberOfCPUs()
+		if self.nr == 0 and self.interval == 0:
+			if self.per_cpu:
+				self.nr = 1
+			else:
+				self.nr = self.jobs
+
+	def Init(self):
+		if self.verbosity.debug:
+			print("cmd", self.cmd)
+		self.file_name = DetermineInputFileName(self.cmd)
+		self.hdr = ReadHeader(self.perf, self.file_name)
+		self.hdr_dict = ParseHeader(self.hdr)
+		self.cmd_line = HeaderField(self.hdr_dict, "cmdline")
+
+	def ExtractTimeInfo(self):
+		self.min_time = TimeVal(HeaderField(self.hdr_dict, "time of first sample"), 0)
+		self.max_time = TimeVal(HeaderField(self.hdr_dict, "time of last sample"), 0)
+		self.time_str = ExtractPerfOption(self.cmd, "", "time")
+		self.time_ranges = ParseTimeStr(self.time_str, self.min_time, self.max_time)
+		if self.verbosity.debug:
+			print("time_ranges", self.time_ranges)
+
+	def ExtractCPUInfo(self):
+		if self.per_cpu:
+			nr_cpus = int(HeaderField(self.hdr_dict, "nrcpus avail"))
+			self.cpu_str = ExtractPerfOption(self.cmd, "C", "cpu")
+			if self.cpu_str == None or self.cpu_str == "":
+				self.cpus = [ x for x in range(nr_cpus) ]
+			else:
+				self.cpus = ParseCPUStr(self.cpu_str, nr_cpus)
+		else:
+			self.cpu_str = None
+			self.cpus = [-1]
+		if self.verbosity.debug:
+			print("cpus", self.cpus)
+
+	def IsIntelPT(self):
+		return self.cmd_line.find("intel_pt") >= 0
+
+	def SplitTimeRanges(self):
+		if self.IsIntelPT() and self.interval == 0:
+			self.split_time_ranges_for_each_cpu = \
+				SplitTimeRangesByTraceDataDensity(self.time_ranges, self.cpus, self.orig_nr,
+								  self.orig_cmd, self.file_name, self.per_cpu,
+								  self.min_size, self.min_interval, self.verbosity)
+		elif self.nr:
+			self.split_time_ranges_for_each_cpu = [ SplitTimeRangesIntoN(self.time_ranges, self.nr, self.min_interval) ]
+		else:
+			self.split_time_ranges_for_each_cpu = [ SplitTimeRangesByInterval(self.time_ranges, self.interval) ]
+
+	def CheckTimeRanges(self):
+		for tr in self.split_time_ranges_for_each_cpu:
+			# Re-combined time ranges should be the same
+			new_tr = RecombineTimeRanges(tr)
+			if new_tr != self.time_ranges:
+				if self.verbosity.debug:
+					print("tr", tr)
+					print("new_tr", new_tr)
+				raise Exception("Self test failed!")
+
+	def OpenTimeRangeEnds(self):
+		for time_ranges in self.split_time_ranges_for_each_cpu:
+			OpenTimeRangeEnds(time_ranges, self.min_time, self.max_time)
+
+	def CreateWorkList(self):
+		self.worklist = CreateWorkList(self.cmd, self.pipe_to, self.output_dir, self.cpus, self.split_time_ranges_for_each_cpu)
+
+	def PerfDataRecordedPerCPU(self):
+		if "--per-thread" in self.cmd_line.split():
+			return False
+		return True
+
+	def DefaultToPerCPU(self):
+		# --no-per-cpu option takes precedence
+		if self.no_per_cpu:
+			return False
+		if not self.PerfDataRecordedPerCPU():
+			return False
+		# Default to per-cpu for Intel PT data that was recorded per-cpu,
+		# because decoding can be done for each CPU separately.
+		if self.IsIntelPT():
+			return True
+		return False
+
+	def Config(self):
+		self.Init()
+		self.ExtractTimeInfo()
+		if not self.per_cpu:
+			self.per_cpu = self.DefaultToPerCPU()
+		if self.verbosity.debug:
+			print("per_cpu", self.per_cpu)
+		self.ExtractCPUInfo()
+		self.SplitTimeRanges()
+		if self.verbosity.self_test:
+			self.CheckTimeRanges()
+		# Prefer open-ended time range to starting / ending with min_time / max_time resp.
+		self.OpenTimeRangeEnds()
+		self.CreateWorkList()
+
+	def Run(self):
+		if self.dry_run:
+			print(len(self.worklist),"jobs:")
+			for w in self.worklist:
+				print(w.Command())
+			return True
+		result = RunWork(self.worklist, self.jobs, verbosity=self.verbosity)
+		if self.verbosity.verbose:
+			print(glb_prog_name, "done")
+		return result
+
+def RunParallelPerf(a):
+	pp = ParallelPerf(a)
+	pp.Config()
+	return pp.Run()
+
+def Main(args):
+	ap = argparse.ArgumentParser(
+		prog=glb_prog_name, formatter_class = argparse.RawDescriptionHelpFormatter,
+		description =
+"""
+Run a perf script command multiple times in parallel, using perf script options
+--cpu and --time so that each job processes a different chunk of the data.
+""",
+		epilog =
+"""
+Follow the options by '--' and then the perf script command e.g.
+
+	$ perf record -a -- sleep 10
+	$ parallel-perf.py --nr=4 -- perf script --ns
+	All jobs finished successfully
+	$ tree parallel-perf-output/
+	parallel-perf-output/
+	├── time-range-0
+	│   ├── cmd.txt
+	│   └── out.txt
+	├── time-range-1
+	│   ├── cmd.txt
+	│   └── out.txt
+	├── time-range-2
+	│   ├── cmd.txt
+	│   └── out.txt
+	└── time-range-3
+	    ├── cmd.txt
+	    └── out.txt
+	$ find parallel-perf-output -name cmd.txt | sort | xargs grep -H .
+	parallel-perf-output/time-range-0/cmd.txt:perf script --time=,9466.504461499 --ns
+	parallel-perf-output/time-range-1/cmd.txt:perf script --time=9466.504461500,9469.005396999 --ns
+	parallel-perf-output/time-range-2/cmd.txt:perf script --time=9469.005397000,9471.506332499 --ns
+	parallel-perf-output/time-range-3/cmd.txt:perf script --time=9471.506332500, --ns
+
+Any perf script command can be used, including the use of perf script options
+--dlfilter and --script, so that the benefit of running parallel jobs
+naturally extends to them also.
+
+If option --pipe-to is used, standard output is first piped through that
+command. Beware, if the command fails (e.g. grep with no matches), it will be
+considered a fatal error.
+
+Final standard output is redirected to files named out.txt in separate
+subdirectories under the output directory. Similarly, standard error is
+written to files named err.txt. In addition, files named cmd.txt contain the
+corresponding perf script command. After processing, err.txt files are removed
+if they are empty.
+
+If any job exits with a non-zero exit code, then all jobs are killed and no
+more are started. A message is printed if any job results in a non-empty
+err.txt file.
+
+There is a separate output subdirectory for each time range. If the --per-cpu
+option is used, these are further grouped under cpu-n subdirectories, e.g.
+
+	$ parallel-perf.py --per-cpu --nr=2 -- perf script --ns --cpu=0,1
+	All jobs finished successfully
+	$ tree parallel-perf-output
+	parallel-perf-output/
+	├── cpu-0
+	│   ├── time-range-0
+	│   │   ├── cmd.txt
+	│   │   └── out.txt
+	│   └── time-range-1
+	│       ├── cmd.txt
+	│       └── out.txt
+	└── cpu-1
+	    ├── time-range-0
+	    │   ├── cmd.txt
+	    │   └── out.txt
+	    └── time-range-1
+	        ├── cmd.txt
+	        └── out.txt
+	$ find parallel-perf-output -name cmd.txt | sort | xargs grep -H .
+	parallel-perf-output/cpu-0/time-range-0/cmd.txt:perf script --cpu=0 --time=,9469.005396999 --ns
+	parallel-perf-output/cpu-0/time-range-1/cmd.txt:perf script --cpu=0 --time=9469.005397000, --ns
+	parallel-perf-output/cpu-1/time-range-0/cmd.txt:perf script --cpu=1 --time=,9469.005396999 --ns
+	parallel-perf-output/cpu-1/time-range-1/cmd.txt:perf script --cpu=1 --time=9469.005397000, --ns
+
+Subdivisions of time range, and cpus if the --per-cpu option is used, are
+expressed by the --time and --cpu perf script options respectively. If the
+supplied perf script command has a --time option, then that time range is
+subdivided, otherwise the time range given by 'time of first sample' to
+'time of last sample' is used (refer perf script --header-only). Similarly, the
+supplied perf script command may provide a --cpu option, and only those CPUs
+will be processed.
+
+To prevent time intervals becoming too small, the --min-interval option can
+be used.
+
+Note there is special handling for processing Intel PT traces. If an interval is
+not specified and the perf record command contained the intel_pt event, then the
+time range will be subdivided in order to produce subdivisions that contain
+approximately the same amount of trace data. That is accomplished by counting
+double-quick (--itrace=qqi) samples, and choosing time ranges that encompass
+approximately the same number of samples. In that case, time ranges may not be
+the same for each CPU processed. For Intel PT, --per-cpu is the default, but
+that can be overridden by --no-per-cpu. Note, for Intel PT, double-quick
+decoding produces 1 sample for each PSB synchronization packet, which in turn
+come after a certain number of bytes output, determined by psb_period (refer
+perf Intel PT documentation). The minimum number of double-quick samples that
+will define a time range can be set by the --min_size option, which defaults to
+64.
+""")
+	ap.add_argument("-o", "--output-dir", default="parallel-perf-output", help="output directory (default 'parallel-perf-output')")
+	ap.add_argument("-j", "--jobs", type=int, default=0, help="maximum number of jobs to run in parallel at one time (default is the number of CPUs)")
+	ap.add_argument("-n", "--nr", type=int, default=0, help="number of time subdivisions (default is the number of jobs)")
+	ap.add_argument("-i", "--interval", type=float, default=0, help="subdivide the time range using this time interval (in seconds e.g. 0.1 for a tenth of a second)")
+	ap.add_argument("-c", "--per-cpu", action="store_true", help="process data for each CPU in parallel")
+	ap.add_argument("-m", "--min-interval", type=float, default=glb_min_interval, help=f"minimum interval (default {glb_min_interval} seconds)")
+	ap.add_argument("-p", "--pipe-to", help="command to pipe output to (optional)")
+	ap.add_argument("-N", "--no-per-cpu", action="store_true", help="do not process data for each CPU in parallel")
+	ap.add_argument("-b", "--min_size", type=int, default=glb_min_samples, help="minimum data size (for Intel PT in PSBs)")
+	ap.add_argument("-D", "--dry-run", action="store_true", help="do not run any jobs, just show the perf script commands")
+	ap.add_argument("-q", "--quiet", action="store_true", help="do not print any messages except errors")
+	ap.add_argument("-v", "--verbose", action="store_true", help="print more messages")
+	ap.add_argument("-d", "--debug", action="store_true", help="print debugging messages")
+	cmd_line = list(args)
+	try:
+		split_pos = cmd_line.index("--")
+		cmd = cmd_line[split_pos + 1:]
+		args = cmd_line[:split_pos]
+	except:
+		cmd = None
+		args = cmd_line
+	a = ap.parse_args(args=args[1:])
+	a.cmd = cmd
+	a.verbosity = Verbosity(a.quiet, a.verbose, a.debug)
+	try:
+		if a.cmd == None:
+			if len(args) <= 1:
+				ap.print_help()
+				return True
+			raise Exception("Command line must contain '--' before perf command")
+		return RunParallelPerf(a)
+	except Exception as e:
+		print("Fatal error: ", str(e))
+		if a.debug:
+			raise
+		return False
+
+if __name__ == "__main__":
+	if not Main(sys.argv):
+		sys.exit(1)
diff --git a/tools/perf/tests/bitmap.c b/tools/perf/tests/bitmap.c
index 0173f5402a35b9..98956e0e076559 100644
--- a/tools/perf/tests/bitmap.c
+++ b/tools/perf/tests/bitmap.c
@@ -11,18 +11,19 @@
 static unsigned long *get_bitmap(const char *str, int nbits)
 {
 	struct perf_cpu_map *map = perf_cpu_map__new(str);
-	unsigned long *bm = NULL;
-	int i;
+	unsigned long *bm;
 
 	bm = bitmap_zalloc(nbits);
 
 	if (map && bm) {
-		for (i = 0; i < perf_cpu_map__nr(map); i++)
-			__set_bit(perf_cpu_map__cpu(map, i).cpu, bm);
+		int i;
+		struct perf_cpu cpu;
+
+		perf_cpu_map__for_each_cpu(cpu, i, map)
+			__set_bit(cpu.cpu, bm);
 	}
 
-	if (map)
-		perf_cpu_map__put(map);
+	perf_cpu_map__put(map);
 	return bm;
 }
 
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index d13ee7683d9d83..c3d84b67ca8e77 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -39,7 +39,10 @@
  * making them easier to debug.
  */
 static bool dont_fork;
-/* Fork the tests in parallel and then wait for their completion. */
+/* Don't fork the tests in parallel and wait for their completion. */
+static bool sequential = true;
+/* Do it in parallel, lacks infrastructure to avoid running tests that clash for resources,
+ * So leave it as the developers choice to enable while working on the needed infra */
 static bool parallel;
 const char *dso_to_test;
 const char *test_objdump_path = "objdump";
@@ -274,11 +277,8 @@ static int finish_test(struct child_test *child_test, int width)
 	struct test_suite *t = child_test->test;
 	int i = child_test->test_num;
 	int subi = child_test->subtest;
-	int out = child_test->process.out;
 	int err = child_test->process.err;
-	bool out_done = out <= 0;
 	bool err_done = err <= 0;
-	struct strbuf out_output = STRBUF_INIT;
 	struct strbuf err_output = STRBUF_INIT;
 	int ret;
 
@@ -290,11 +290,9 @@ static int finish_test(struct child_test *child_test, int width)
 		pr_info("%3d: %-*s:\n", i + 1, width, test_description(t, -1));
 
 	/*
-	 * Busy loop reading from the child's stdout and stderr that are set to
-	 * be non-blocking until EOF.
+	 * Busy loop reading from the child's stdout/stderr that are set to be
+	 * non-blocking until EOF.
 	 */
-	if (!out_done)
-		fcntl(out, F_SETFL, O_NONBLOCK);
 	if (!err_done)
 		fcntl(err, F_SETFL, O_NONBLOCK);
 	if (verbose > 1) {
@@ -303,11 +301,8 @@ static int finish_test(struct child_test *child_test, int width)
 		else
 			pr_info("%3d: %s:\n", i + 1, test_description(t, -1));
 	}
-	while (!out_done || !err_done) {
-		struct pollfd pfds[2] = {
-			{ .fd = out,
-			  .events = POLLIN | POLLERR | POLLHUP | POLLNVAL,
-			},
+	while (!err_done) {
+		struct pollfd pfds[1] = {
 			{ .fd = err,
 			  .events = POLLIN | POLLERR | POLLHUP | POLLNVAL,
 			},
@@ -315,23 +310,9 @@ static int finish_test(struct child_test *child_test, int width)
 		char buf[512];
 		ssize_t len;
 
-		/* Poll to avoid excessive spinning, timeout set for 1000ms. */
-		poll(pfds, ARRAY_SIZE(pfds), /*timeout=*/1000);
-		if (!out_done && pfds[0].revents) {
-			errno = 0;
-			len = read(out, buf, sizeof(buf) - 1);
-
-			if (len <= 0) {
-				out_done = errno != EAGAIN;
-			} else {
-				buf[len] = '\0';
-				if (verbose > 1)
-					fprintf(stdout, "%s", buf);
-				else
-					strbuf_addstr(&out_output, buf);
-			}
-		}
-		if (!err_done && pfds[1].revents) {
+		/* Poll to avoid excessive spinning, timeout set for 100ms. */
+		poll(pfds, ARRAY_SIZE(pfds), /*timeout=*/100);
+		if (!err_done && pfds[0].revents) {
 			errno = 0;
 			len = read(err, buf, sizeof(buf) - 1);
 
@@ -354,14 +335,10 @@ static int finish_test(struct child_test *child_test, int width)
 			pr_info("%3d.%1d: %s:\n", i + 1, subi + 1, test_description(t, subi));
 		else
 			pr_info("%3d: %s:\n", i + 1, test_description(t, -1));
-		fprintf(stdout, "%s", out_output.buf);
 		fprintf(stderr, "%s", err_output.buf);
 	}
-	strbuf_release(&out_output);
 	strbuf_release(&err_output);
 	print_test_result(t, i, subi, ret, width);
-	if (out > 0)
-		close(out);
 	if (err > 0)
 		close(err);
 	return 0;
@@ -394,12 +371,13 @@ static int start_test(struct test_suite *test, int i, int subi, struct child_tes
 		(*child)->process.no_stdout = 1;
 		(*child)->process.no_stderr = 1;
 	} else {
+		(*child)->process.stdout_to_stderr = 1;
 		(*child)->process.out = -1;
 		(*child)->process.err = -1;
 	}
 	(*child)->process.no_exec_cmd = run_test_child;
 	err = start_command(&(*child)->process);
-	if (err || parallel)
+	if (err || !sequential)
 		return  err;
 	return finish_test(*child, width);
 }
@@ -465,7 +443,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 			int err = start_test(t, curr, -1, &child_tests[child_test_num++], width);
 
 			if (err) {
-				/* TODO: if parallel waitpid the already forked children. */
+				/* TODO: if !sequential waitpid the already forked children. */
 				free(child_tests);
 				return err;
 			}
@@ -485,7 +463,7 @@ static int __cmd_test(int argc, const char *argv[], struct intlist *skiplist)
 		}
 	}
 	for (i = 0; i < child_test_num; i++) {
-		if (parallel) {
+		if (!sequential) {
 			int ret  = finish_test(child_tests[i], width);
 
 			if (ret)
@@ -561,8 +539,9 @@ int cmd_test(int argc, const char **argv)
 		    "be more verbose (show symbol address, etc)"),
 	OPT_BOOLEAN('F', "dont-fork", &dont_fork,
 		    "Do not fork for testcase"),
-	OPT_BOOLEAN('p', "parallel", &parallel,
-		    "Run the tests altogether in parallel"),
+	OPT_BOOLEAN('p', "parallel", &parallel, "Run the tests in parallel"),
+	OPT_BOOLEAN('S', "sequential", &sequential,
+		    "Run the tests one after another rather than in parallel"),
 	OPT_STRING('w', "workload", &workload, "work", "workload to run for testing"),
 	OPT_STRING(0, "dso", &dso_to_test, "dso", "dso to test"),
 	OPT_STRING(0, "objdump", &test_objdump_path, "path",
@@ -589,6 +568,11 @@ int cmd_test(int argc, const char **argv)
 	if (workload)
 		return run_workload(workload, argc, argv);
 
+	if (dont_fork)
+		sequential = true;
+	else if (parallel)
+		sequential = false;
+
 	symbol_conf.priv_size = sizeof(int);
 	symbol_conf.try_vmlinux_path = true;
 
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 7a3a7bbbec7146..29d2f3ee4e10fb 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -637,11 +637,11 @@ static int do_test_code_reading(bool try_kcore)
 
 		evlist__config(evlist, &opts, NULL);
 
-		evsel = evlist__first(evlist);
-
-		evsel->core.attr.comm = 1;
-		evsel->core.attr.disabled = 1;
-		evsel->core.attr.enable_on_exec = 0;
+		evlist__for_each_entry(evlist, evsel) {
+			evsel->core.attr.comm = 1;
+			evsel->core.attr.disabled = 1;
+			evsel->core.attr.enable_on_exec = 0;
+		}
 
 		ret = evlist__open(evlist);
 		if (ret < 0) {
diff --git a/tools/perf/tests/config-fragments/config b/tools/perf/tests/config-fragments/config
index c340b3195fcaa3..4fca12851016d1 100644
--- a/tools/perf/tests/config-fragments/config
+++ b/tools/perf/tests/config-fragments/config
@@ -9,3 +9,6 @@ CONFIG_GENERIC_TRACER=y
 CONFIG_FTRACE=y
 CONFIG_FTRACE_SYSCALLS=y
 CONFIG_BRANCH_PROFILE_NONE=y
+CONFIG_KPROBES=y
+CONFIG_KPROBE_EVENTS=y
+CONFIG_UPROBE_EVENTS=y
diff --git a/tools/perf/tests/evsel-roundtrip-name.c b/tools/perf/tests/evsel-roundtrip-name.c
index 15ff86f9da0b1d..1922cac13a2453 100644
--- a/tools/perf/tests/evsel-roundtrip-name.c
+++ b/tools/perf/tests/evsel-roundtrip-name.c
@@ -37,7 +37,7 @@ static int perf_evsel__roundtrip_cache_name_test(void)
 					continue;
 				}
 				evlist__for_each_entry(evlist, evsel) {
-					if (strcmp(evsel__name(evsel), name)) {
+					if (!evsel__name_is(evsel, name)) {
 						pr_debug("%s != %s\n", evsel__name(evsel), name);
 						ret = TEST_FAIL;
 					}
@@ -71,7 +71,7 @@ static int perf_evsel__name_array_test(const char *const names[], int nr_names)
 			continue;
 		}
 		evlist__for_each_entry(evlist, evsel) {
-			if (strcmp(evsel__name(evsel), names[i])) {
+			if (!evsel__name_is(evsel, names[i])) {
 				pr_debug("%s != %s\n", evsel__name(evsel), names[i]);
 				ret = TEST_FAIL;
 			}
diff --git a/tools/perf/tests/parse-events.c b/tools/perf/tests/parse-events.c
index feb5727584d141..993e482f094c2d 100644
--- a/tools/perf/tests/parse-events.c
+++ b/tools/perf/tests/parse-events.c
@@ -470,8 +470,7 @@ static int test__checkevent_breakpoint_modifier(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
-	TEST_ASSERT_VAL("wrong name",
-			!strcmp(evsel__name(evsel), "mem:0:u"));
+	TEST_ASSERT_VAL("wrong name", evsel__name_is(evsel, "mem:0:u"));
 
 	return test__checkevent_breakpoint(evlist);
 }
@@ -484,8 +483,7 @@ static int test__checkevent_breakpoint_x_modifier(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
-	TEST_ASSERT_VAL("wrong name",
-			!strcmp(evsel__name(evsel), "mem:0:x:k"));
+	TEST_ASSERT_VAL("wrong name", evsel__name_is(evsel, "mem:0:x:k"));
 
 	return test__checkevent_breakpoint_x(evlist);
 }
@@ -498,8 +496,7 @@ static int test__checkevent_breakpoint_r_modifier(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip);
-	TEST_ASSERT_VAL("wrong name",
-			!strcmp(evsel__name(evsel), "mem:0:r:hp"));
+	TEST_ASSERT_VAL("wrong name", evsel__name_is(evsel, "mem:0:r:hp"));
 
 	return test__checkevent_breakpoint_r(evlist);
 }
@@ -512,8 +509,7 @@ static int test__checkevent_breakpoint_w_modifier(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip);
-	TEST_ASSERT_VAL("wrong name",
-			!strcmp(evsel__name(evsel), "mem:0:w:up"));
+	TEST_ASSERT_VAL("wrong name", evsel__name_is(evsel, "mem:0:w:up"));
 
 	return test__checkevent_breakpoint_w(evlist);
 }
@@ -526,8 +522,7 @@ static int test__checkevent_breakpoint_rw_modifier(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip);
-	TEST_ASSERT_VAL("wrong name",
-			!strcmp(evsel__name(evsel), "mem:0:rw:kp"));
+	TEST_ASSERT_VAL("wrong name", evsel__name_is(evsel, "mem:0:rw:kp"));
 
 	return test__checkevent_breakpoint_rw(evlist);
 }
@@ -540,8 +535,7 @@ static int test__checkevent_breakpoint_modifier_name(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
-	TEST_ASSERT_VAL("wrong name",
-			!strcmp(evsel__name(evsel), "breakpoint"));
+	TEST_ASSERT_VAL("wrong name", evsel__name_is(evsel, "breakpoint"));
 
 	return test__checkevent_breakpoint(evlist);
 }
@@ -554,8 +548,7 @@ static int test__checkevent_breakpoint_x_modifier_name(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", !evsel->core.attr.precise_ip);
-	TEST_ASSERT_VAL("wrong name",
-			!strcmp(evsel__name(evsel), "breakpoint"));
+	TEST_ASSERT_VAL("wrong name", evsel__name_is(evsel, "breakpoint"));
 
 	return test__checkevent_breakpoint_x(evlist);
 }
@@ -568,8 +561,7 @@ static int test__checkevent_breakpoint_r_modifier_name(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", !evsel->core.attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip);
-	TEST_ASSERT_VAL("wrong name",
-			!strcmp(evsel__name(evsel), "breakpoint"));
+	TEST_ASSERT_VAL("wrong name", evsel__name_is(evsel, "breakpoint"));
 
 	return test__checkevent_breakpoint_r(evlist);
 }
@@ -582,8 +574,7 @@ static int test__checkevent_breakpoint_w_modifier_name(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip);
-	TEST_ASSERT_VAL("wrong name",
-			!strcmp(evsel__name(evsel), "breakpoint"));
+	TEST_ASSERT_VAL("wrong name", evsel__name_is(evsel, "breakpoint"));
 
 	return test__checkevent_breakpoint_w(evlist);
 }
@@ -596,8 +587,7 @@ static int test__checkevent_breakpoint_rw_modifier_name(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong exclude_kernel", !evsel->core.attr.exclude_kernel);
 	TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
 	TEST_ASSERT_VAL("wrong precise_ip", evsel->core.attr.precise_ip);
-	TEST_ASSERT_VAL("wrong name",
-			!strcmp(evsel__name(evsel), "breakpoint"));
+	TEST_ASSERT_VAL("wrong name", evsel__name_is(evsel, "breakpoint"));
 
 	return test__checkevent_breakpoint_rw(evlist);
 }
@@ -609,12 +599,12 @@ static int test__checkevent_breakpoint_2_events(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
 
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->core.attr.type);
-	TEST_ASSERT_VAL("wrong name", !strcmp(evsel__name(evsel), "breakpoint1"));
+	TEST_ASSERT_VAL("wrong name", evsel__name_is(evsel, "breakpoint1"));
 
 	evsel = evsel__next(evsel);
 
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_BREAKPOINT == evsel->core.attr.type);
-	TEST_ASSERT_VAL("wrong name", !strcmp(evsel__name(evsel), "breakpoint2"));
+	TEST_ASSERT_VAL("wrong name", evsel__name_is(evsel, "breakpoint2"));
 
 	return TEST_OK;
 }
@@ -691,15 +681,14 @@ static int test__checkevent_pmu_name(struct evlist *evlist)
 	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config", test_config(evsel, 1));
-	TEST_ASSERT_VAL("wrong name", !strcmp(evsel__name(evsel), "krava"));
+	TEST_ASSERT_VAL("wrong name", evsel__name_is(evsel, "krava"));
 
 	/* cpu/config=2/u" */
 	evsel = evsel__next(evsel);
 	TEST_ASSERT_VAL("wrong number of entries", 2 == evlist->core.nr_entries);
 	TEST_ASSERT_VAL("wrong type", PERF_TYPE_RAW == evsel->core.attr.type);
 	TEST_ASSERT_VAL("wrong config", test_config(evsel, 2));
-	TEST_ASSERT_VAL("wrong name",
-			!strcmp(evsel__name(evsel), "cpu/config=2/u"));
+	TEST_ASSERT_VAL("wrong name", evsel__name_is(evsel, "cpu/config=2/u"));
 
 	return TEST_OK;
 }
@@ -953,8 +942,8 @@ static int test__group2(struct evlist *evlist)
 			continue;
 		}
 		if (evsel->core.attr.type == PERF_TYPE_HARDWARE &&
-		    test_config(evsel, PERF_COUNT_HW_CACHE_REFERENCES)) {
-			/* cache-references + :u modifier */
+		    test_config(evsel, PERF_COUNT_HW_BRANCH_INSTRUCTIONS)) {
+			/* branches + :u modifier */
 			TEST_ASSERT_VAL("wrong exclude_user", !evsel->core.attr.exclude_user);
 			TEST_ASSERT_VAL("wrong exclude_kernel", evsel->core.attr.exclude_kernel);
 			TEST_ASSERT_VAL("wrong exclude_hv", evsel->core.attr.exclude_hv);
@@ -2043,7 +2032,7 @@ static const struct evlist_test test__events[] = {
 		/* 8 */
 	},
 	{
-		.name  = "{faults:k,cache-references}:u,cycles:k",
+		.name  = "{faults:k,branches}:u,cycles:k",
 		.check = test__group2,
 		/* 9 */
 	},
diff --git a/tools/perf/tests/shell/annotate.sh b/tools/perf/tests/shell/annotate.sh
new file mode 100755
index 00000000000000..1db1e8113d9943
--- /dev/null
+++ b/tools/perf/tests/shell/annotate.sh
@@ -0,0 +1,83 @@
+#!/bin/sh
+# perf annotate basic tests
+# SPDX-License-Identifier: GPL-2.0
+
+set -e
+
+shelldir=$(dirname "$0")
+
+# shellcheck source=lib/perf_has_symbol.sh
+. "${shelldir}"/lib/perf_has_symbol.sh
+
+testsym="noploop"
+
+skip_test_missing_symbol ${testsym}
+
+err=0
+perfdata=$(mktemp /tmp/__perf_test.perf.data.XXXXX)
+testprog="perf test -w noploop"
+# disassembly format: "percent : offset: instruction (operands ...)"
+disasm_regex="[0-9]*\.[0-9]* *: *\w*: *\w*"
+
+cleanup() {
+  rm -rf "${perfdata}"
+  rm -rf "${perfdata}".old
+
+  trap - EXIT TERM INT
+}
+
+trap_cleanup() {
+  cleanup
+  exit 1
+}
+trap trap_cleanup EXIT TERM INT
+
+test_basic() {
+  echo "Basic perf annotate test"
+  if ! perf record -o "${perfdata}" ${testprog} 2> /dev/null
+  then
+    echo "Basic annotate [Failed: perf record]"
+    err=1
+    return
+  fi
+
+  # check if it has the target symbol
+  if ! perf annotate -i "${perfdata}" 2> /dev/null | grep "${testsym}"
+  then
+    echo "Basic annotate [Failed: missing target symbol]"
+    err=1
+    return
+  fi
+
+  # check if it has the disassembly lines
+  if ! perf annotate -i "${perfdata}" 2> /dev/null | grep "${disasm_regex}"
+  then
+    echo "Basic annotate [Failed: missing disasm output from default disassembler]"
+    err=1
+    return
+  fi
+
+  # check again with a target symbol name
+  if ! perf annotate -i "${perfdata}" "${testsym}" 2> /dev/null | \
+	  grep -m 3 "${disasm_regex}"
+  then
+    echo "Basic annotate [Failed: missing disasm output when specifying the target symbol]"
+    err=1
+    return
+  fi
+
+  # check one more with external objdump tool (forced by --objdump option)
+  if ! perf annotate -i "${perfdata}" --objdump=objdump 2> /dev/null | \
+	  grep -m 3 "${disasm_regex}"
+  then
+    echo "Basic annotate [Failed: missing disasm output from non default disassembler (using --objdump)]"
+    err=1
+    return
+  fi
+  echo "Basic annotate test [Success]"
+}
+
+test_basic
+
+cleanup
+exit $err
diff --git a/tools/perf/tests/shell/base_probe/test_adding_kernel.sh b/tools/perf/tests/shell/base_probe/test_adding_kernel.sh
index a5d707efad85cb..63bb8974b38e0b 100755
--- a/tools/perf/tests/shell/base_probe/test_adding_kernel.sh
+++ b/tools/perf/tests/shell/base_probe/test_adding_kernel.sh
@@ -1,4 +1,5 @@
 #!/bin/bash
+# Add 'perf probe's, list and remove them
 # SPDX-License-Identifier: GPL-2.0
 
 #
diff --git a/tools/perf/tests/shell/lib/stat_output.sh b/tools/perf/tests/shell/lib/stat_output.sh
index c81d6a9f7983d3..9a176ceae4a3c3 100644
--- a/tools/perf/tests/shell/lib/stat_output.sh
+++ b/tools/perf/tests/shell/lib/stat_output.sh
@@ -79,7 +79,7 @@ check_per_thread()
 		echo "[Skip] paranoid and not root"
 		return
 	fi
-	perf stat --per-thread -a $2 true
+	perf stat --per-thread -p $$ $2 true
 	commachecker --per-thread
 	echo "[Success]"
 }
diff --git a/tools/perf/tests/shell/script.sh b/tools/perf/tests/shell/script.sh
index fa4d71e2e72a61..c1a60365366201 100755
--- a/tools/perf/tests/shell/script.sh
+++ b/tools/perf/tests/shell/script.sh
@@ -17,7 +17,7 @@ cleanup()
 	sane=$(echo "${temp_dir}" | cut -b 1-21)
 	if [ "${sane}" = "/tmp/perf-test-script" ] ; then
 		echo "--- Cleaning up ---"
-		rm -f "${temp_dir}/"*
+		rm -rf "${temp_dir:?}/"*
 		rmdir "${temp_dir}"
 	fi
 }
@@ -65,7 +65,31 @@ _end_of_file_
 	echo "DB test [Success]"
 }
 
+test_parallel_perf()
+{
+	echo "parallel-perf test"
+	if ! python3 --version >/dev/null 2>&1 ; then
+		echo "SKIP: no python3"
+		err=2
+		return
+	fi
+	pp=$(dirname "$0")/../../scripts/python/parallel-perf.py
+	if [ ! -f "${pp}" ] ; then
+		echo "SKIP: parallel-perf.py script not found "
+		err=2
+		return
+	fi
+	perf_data="${temp_dir}/pp-perf.data"
+	output1_dir="${temp_dir}/output1"
+	output2_dir="${temp_dir}/output2"
+	perf record -o "${perf_data}" --sample-cpu uname
+	python3 "${pp}" -o "${output1_dir}" --jobs 4 --verbose -- perf script -i "${perf_data}"
+	python3 "${pp}" -o "${output2_dir}" --jobs 4 --verbose --per-cpu -- perf script -i "${perf_data}"
+	echo "parallel-perf test [Success]"
+}
+
 test_db
+test_parallel_perf
 
 cleanup
 
diff --git a/tools/perf/tests/shell/stat+json_output.sh b/tools/perf/tests/shell/stat+json_output.sh
index 2b9c6212dffc6f..6b630d33c32878 100755
--- a/tools/perf/tests/shell/stat+json_output.sh
+++ b/tools/perf/tests/shell/stat+json_output.sh
@@ -105,7 +105,7 @@ check_per_thread()
 		echo "[Skip] paranoia and not root"
 		return
 	fi
-	perf stat -j --per-thread -a -o "${stat_output}" true
+	perf stat -j --per-thread -p $$ -o "${stat_output}" true
 	$PYTHON $pythonchecker --per-thread --file "${stat_output}"
 	echo "[Success]"
 }
diff --git a/tools/perf/tests/shell/stat_bpf_counters.sh b/tools/perf/tests/shell/stat_bpf_counters.sh
index 2d920987477468..61f8149d854e12 100755
--- a/tools/perf/tests/shell/stat_bpf_counters.sh
+++ b/tools/perf/tests/shell/stat_bpf_counters.sh
@@ -4,21 +4,59 @@
 
 set -e
 
+workload="perf bench sched messaging -g 1 -l 100 -t"
+
 # check whether $2 is within +/- 20% of $1
 compare_number()
 {
-       first_num=$1
-       second_num=$2
-
-       # upper bound is first_num * 120%
-       upper=$(expr $first_num + $first_num / 5 )
-       # lower bound is first_num * 80%
-       lower=$(expr $first_num - $first_num / 5 )
-
-       if [ $second_num -gt $upper ] || [ $second_num -lt $lower ]; then
-               echo "The difference between $first_num and $second_num are greater than 20%."
-               exit 1
-       fi
+	first_num=$1
+	second_num=$2
+
+	# upper bound is first_num * 120%
+	upper=$(expr $first_num + $first_num / 5 )
+	# lower bound is first_num * 80%
+	lower=$(expr $first_num - $first_num / 5 )
+
+	if [ $second_num -gt $upper ] || [ $second_num -lt $lower ]; then
+		echo "The difference between $first_num and $second_num are greater than 20%."
+		exit 1
+	fi
+}
+
+check_counts()
+{
+	base_cycles=$1
+	bpf_cycles=$2
+
+	if [ "$base_cycles" = "<not" ]; then
+		echo "Skipping: cycles event not counted"
+		exit 2
+	fi
+	if [ "$bpf_cycles" = "<not" ]; then
+		echo "Failed: cycles not counted with --bpf-counters"
+		exit 1
+	fi
+}
+
+test_bpf_counters()
+{
+	printf "Testing --bpf-counters "
+	base_cycles=$(perf stat --no-big-num -e cycles -- $workload 2>&1 | awk '/cycles/ {print $1}')
+	bpf_cycles=$(perf stat --no-big-num --bpf-counters -e cycles -- $workload  2>&1 | awk '/cycles/ {print $1}')
+	check_counts $base_cycles $bpf_cycles
+	compare_number $base_cycles $bpf_cycles
+	echo "[Success]"
+}
+
+test_bpf_modifier()
+{
+	printf "Testing bpf event modifier "
+	stat_output=$(perf stat --no-big-num -e cycles/name=base_cycles/,cycles/name=bpf_cycles/b -- $workload 2>&1)
+	base_cycles=$(echo "$stat_output"| awk '/base_cycles/ {print $1}')
+	bpf_cycles=$(echo "$stat_output"| awk '/bpf_cycles/ {print $1}')
+	check_counts $base_cycles $bpf_cycles
+	compare_number $base_cycles $bpf_cycles
+	echo "[Success]"
 }
 
 # skip if --bpf-counters is not supported
@@ -30,16 +68,7 @@ if ! perf stat -e cycles --bpf-counters true > /dev/null 2>&1; then
 	exit 2
 fi
 
-base_cycles=$(perf stat --no-big-num -e cycles -- perf bench sched messaging -g 1 -l 100 -t 2>&1 | awk '/cycles/ {print $1}')
-if [ "$base_cycles" = "<not" ]; then
-	echo "Skipping: cycles event not counted"
-	exit 2
-fi
-bpf_cycles=$(perf stat --no-big-num --bpf-counters -e cycles -- perf bench sched messaging -g 1 -l 100 -t 2>&1 | awk '/cycles/ {print $1}')
-if [ "$bpf_cycles" = "<not" ]; then
-	echo "Failed: cycles not counted with --bpf-counters"
-	exit 1
-fi
+test_bpf_counters
+test_bpf_modifier
 
-compare_number $base_cycles $bpf_cycles
 exit 0
diff --git a/tools/perf/tests/shell/test_arm_callgraph_fp.sh b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
index 83b53591b1eacc..61898e25661607 100755
--- a/tools/perf/tests/shell/test_arm_callgraph_fp.sh
+++ b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
@@ -6,7 +6,9 @@ shelldir=$(dirname "$0")
 # shellcheck source=lib/perf_has_symbol.sh
 . "${shelldir}"/lib/perf_has_symbol.sh
 
-lscpu | grep -q "aarch64" || exit 2
+if [ "$(uname -m)" != "aarch64" ]; then
+	exit 2
+fi
 
 if perf version --build-options | grep HAVE_DWARF_UNWIND_SUPPORT | grep -q OFF
 then
diff --git a/tools/perf/tests/shell/test_arm_coresight.sh b/tools/perf/tests/shell/test_arm_coresight.sh
index 65dd852071250a..3302ea0b96723b 100755
--- a/tools/perf/tests/shell/test_arm_coresight.sh
+++ b/tools/perf/tests/shell/test_arm_coresight.sh
@@ -188,7 +188,7 @@ arm_cs_etm_snapshot_test() {
 
 arm_cs_etm_basic_test() {
 	echo "Recording trace with '$*'"
-	perf record -o ${perfdata} "$@" -- ls > /dev/null 2>&1
+	perf record -o ${perfdata} "$@" -m,8M -- ls > /dev/null 2>&1
 
 	perf_script_branch_samples ls &&
 	perf_report_branch_samples ls &&
diff --git a/tools/perf/tests/topology.c b/tools/perf/tests/topology.c
index 2a842f53fbb575..a8cb5ba898ab3a 100644
--- a/tools/perf/tests/topology.c
+++ b/tools/perf/tests/topology.c
@@ -68,6 +68,7 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
 	};
 	int i;
 	struct aggr_cpu_id id;
+	struct perf_cpu cpu;
 
 	session = perf_session__new(&data, NULL);
 	TEST_ASSERT_VAL("can't get session", !IS_ERR(session));
@@ -113,8 +114,7 @@ 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++) {
-		struct perf_cpu cpu = { .cpu = i };
-
+		cpu.cpu = i;
 		if (!perf_cpu_map__has(map, cpu))
 			continue;
 		pr_debug("CPU %d, core %d, socket %d\n", i,
@@ -123,48 +123,48 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
 	}
 
 	// Test that CPU ID contains socket, die, core and CPU
-	for (i = 0; i < perf_cpu_map__nr(map); i++) {
-		id = aggr_cpu_id__cpu(perf_cpu_map__cpu(map, i), NULL);
+	perf_cpu_map__for_each_cpu(cpu, i, map) {
+		id = aggr_cpu_id__cpu(cpu, NULL);
 		TEST_ASSERT_VAL("Cpu map - CPU ID doesn't match",
-				perf_cpu_map__cpu(map, i).cpu == id.cpu.cpu);
+				cpu.cpu == id.cpu.cpu);
 
 		TEST_ASSERT_VAL("Cpu map - Core ID doesn't match",
-			session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].core_id == id.core);
+			session->header.env.cpu[cpu.cpu].core_id == id.core);
 		TEST_ASSERT_VAL("Cpu map - Socket ID doesn't match",
-			session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].socket_id ==
+			session->header.env.cpu[cpu.cpu].socket_id ==
 			id.socket);
 
 		TEST_ASSERT_VAL("Cpu map - Die ID doesn't match",
-			session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].die_id == id.die);
+			session->header.env.cpu[cpu.cpu].die_id == id.die);
 		TEST_ASSERT_VAL("Cpu map - Node ID is set", id.node == -1);
 		TEST_ASSERT_VAL("Cpu map - Thread IDX is set", id.thread_idx == -1);
 	}
 
 	// Test that core ID contains socket, die and core
-	for (i = 0; i < perf_cpu_map__nr(map); i++) {
-		id = aggr_cpu_id__core(perf_cpu_map__cpu(map, i), NULL);
+	perf_cpu_map__for_each_cpu(cpu, i, map) {
+		id = aggr_cpu_id__core(cpu, NULL);
 		TEST_ASSERT_VAL("Core map - Core ID doesn't match",
-			session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].core_id == id.core);
+			session->header.env.cpu[cpu.cpu].core_id == id.core);
 
 		TEST_ASSERT_VAL("Core map - Socket ID doesn't match",
-			session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].socket_id ==
+			session->header.env.cpu[cpu.cpu].socket_id ==
 			id.socket);
 
 		TEST_ASSERT_VAL("Core map - Die ID doesn't match",
-			session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].die_id == id.die);
+			session->header.env.cpu[cpu.cpu].die_id == id.die);
 		TEST_ASSERT_VAL("Core map - Node ID is set", id.node == -1);
 		TEST_ASSERT_VAL("Core map - Thread IDX is set", id.thread_idx == -1);
 	}
 
 	// Test that die ID contains socket and die
-	for (i = 0; i < perf_cpu_map__nr(map); i++) {
-		id = aggr_cpu_id__die(perf_cpu_map__cpu(map, i), NULL);
+	perf_cpu_map__for_each_cpu(cpu, i, map) {
+		id = aggr_cpu_id__die(cpu, NULL);
 		TEST_ASSERT_VAL("Die map - Socket ID doesn't match",
-			session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].socket_id ==
+			session->header.env.cpu[cpu.cpu].socket_id ==
 			id.socket);
 
 		TEST_ASSERT_VAL("Die map - Die ID doesn't match",
-			session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].die_id == id.die);
+			session->header.env.cpu[cpu.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);
@@ -173,10 +173,10 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
 	}
 
 	// Test that socket ID contains only socket
-	for (i = 0; i < perf_cpu_map__nr(map); i++) {
-		id = aggr_cpu_id__socket(perf_cpu_map__cpu(map, i), NULL);
+	perf_cpu_map__for_each_cpu(cpu, i, map) {
+		id = aggr_cpu_id__socket(cpu, NULL);
 		TEST_ASSERT_VAL("Socket map - Socket ID doesn't match",
-			session->header.env.cpu[perf_cpu_map__cpu(map, i).cpu].socket_id ==
+			session->header.env.cpu[cpu.cpu].socket_id ==
 			id.socket);
 
 		TEST_ASSERT_VAL("Socket map - Node ID is set", id.node == -1);
@@ -187,10 +187,10 @@ static int check_cpu_topology(char *path, struct perf_cpu_map *map)
 	}
 
 	// Test that node ID contains only node
-	for (i = 0; i < perf_cpu_map__nr(map); i++) {
-		id = aggr_cpu_id__node(perf_cpu_map__cpu(map, i), NULL);
+	perf_cpu_map__for_each_cpu(cpu, i, map) {
+		id = aggr_cpu_id__node(cpu, NULL);
 		TEST_ASSERT_VAL("Node map - Node ID doesn't match",
-				cpu__get_node(perf_cpu_map__cpu(map, i)) == id.node);
+				cpu__get_node(cpu) == 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);
diff --git a/tools/perf/tests/workloads/datasym.c b/tools/perf/tests/workloads/datasym.c
index ddd40bc63448ae..8e08fc75a973e5 100644
--- a/tools/perf/tests/workloads/datasym.c
+++ b/tools/perf/tests/workloads/datasym.c
@@ -16,6 +16,22 @@ static int datasym(int argc __maybe_unused, const char **argv __maybe_unused)
 {
 	for (;;) {
 		buf1.data1++;
+		if (buf1.data1 == 123) {
+			/*
+			 * Add some 'noise' in the loop to work around errata
+			 * 1694299 on Arm N1.
+			 *
+			 * Bias exists in SPE sampling which can cause the load
+			 * and store instructions to be skipped entirely. This
+			 * comes and goes randomly depending on the offset the
+			 * linker places the datasym loop at in the Perf binary.
+			 * With an extra branch in the middle of the loop that
+			 * isn't always taken, the instruction stream is no
+			 * longer a continuous repeating pattern that interacts
+			 * badly with the bias.
+			 */
+			buf1.data1++;
+		}
 		buf1.data2 += buf1.data1;
 	}
 	return 0;
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
index d11ce256f51140..cb3c1399ff4091 100644
--- a/tools/perf/trace/beauty/Build
+++ b/tools/perf/trace/beauty/Build
@@ -1,6 +1,7 @@
 perf-y += clone.o
 perf-y += fcntl.o
 perf-y += flock.o
+perf-y += fs_at_flags.o
 perf-y += fsmount.o
 perf-y += fspick.o
 ifeq ($(SRCARCH),$(filter $(SRCARCH),x86))
@@ -19,3 +20,17 @@ perf-y += statx.o
 perf-y += sync_file_range.o
 perf-y += timespec.o
 perf-y += tracepoints/
+
+ifdef SHELLCHECK
+  SHELL_TESTS := $(wildcard trace/beauty/*.sh)
+  TEST_LOGS := $(SHELL_TESTS:trace/beauty/%=%.shellcheck_log)
+else
+  SHELL_TESTS :=
+  TEST_LOGS :=
+endif
+
+$(OUTPUT)%.shellcheck_log: %
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,test)shellcheck -s bash -a -S warning "$<" > $@ || (cat $@ && rm $@ && false)
+
+perf-y += $(TEST_LOGS)
diff --git a/tools/arch/x86/include/asm/irq_vectors.h b/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h
index d18bfb238f660f..d18bfb238f660f 100644
--- a/tools/arch/x86/include/asm/irq_vectors.h
+++ b/tools/perf/trace/beauty/arch/x86/include/asm/irq_vectors.h
diff --git a/tools/arch/x86/include/uapi/asm/prctl.h b/tools/perf/trace/beauty/arch/x86/include/uapi/asm/prctl.h
index 384e2cc6ac190d..384e2cc6ac190d 100644
--- a/tools/arch/x86/include/uapi/asm/prctl.h
+++ b/tools/perf/trace/beauty/arch/x86/include/uapi/asm/prctl.h
diff --git a/tools/perf/trace/beauty/arch_errno_names.sh b/tools/perf/trace/beauty/arch_errno_names.sh
index 7df4bf5b55a3cc..30d3889b295771 100755
--- a/tools/perf/trace/beauty/arch_errno_names.sh
+++ b/tools/perf/trace/beauty/arch_errno_names.sh
@@ -60,10 +60,12 @@ create_arch_errno_table_func()
 	printf 'arch_syscalls__strerrno_t *arch_syscalls__strerrno_function(const char *arch)\n'
 	printf '{\n'
 	for arch in $archlist; do
-		printf '\tif (!strcmp(arch, "%s"))\n' $(arch_string "$arch")
-		printf '\t\treturn errno_to_name__%s;\n' $(arch_string "$arch")
+		arch_str=$(arch_string "$arch")
+		printf '\tif (!strcmp(arch, "%s"))\n' "$arch_str"
+		printf '\t\treturn errno_to_name__%s;\n' "$arch_str"
 	done
-	printf '\treturn errno_to_name__%s;\n' $(arch_string "$default")
+	arch_str=$(arch_string "$default")
+	printf '\treturn errno_to_name__%s;\n' "$arch_str"
 	printf '}\n'
 }
 
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 9feb794f5c6e15..78d10d92d351f8 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -234,8 +234,11 @@ size_t syscall_arg__scnprintf_socket_protocol(char *bf, size_t size, struct sysc
 size_t syscall_arg__scnprintf_socket_level(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_SK_LEVEL syscall_arg__scnprintf_socket_level
 
-size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg);
-#define SCA_STATX_FLAGS syscall_arg__scnprintf_statx_flags
+size_t syscall_arg__scnprintf_fs_at_flags(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_FS_AT_FLAGS syscall_arg__scnprintf_fs_at_flags
+
+size_t syscall_arg__scnprintf_faccessat2_flags(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_FACCESSAT2_FLAGS syscall_arg__scnprintf_faccessat2_flags
 
 size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_STATX_MASK syscall_arg__scnprintf_statx_mask
diff --git a/tools/perf/trace/beauty/clone.c b/tools/perf/trace/beauty/clone.c
index f4db894e0af6d1..c9fa8f7e82b909 100644
--- a/tools/perf/trace/beauty/clone.c
+++ b/tools/perf/trace/beauty/clone.c
@@ -7,52 +7,16 @@
 
 #include "trace/beauty/beauty.h"
 #include <linux/kernel.h>
+#include <linux/log2.h>
 #include <sys/types.h>
-#include <uapi/linux/sched.h>
+#include <sched.h>
 
 static size_t clone__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix)
 {
-	const char *prefix = "CLONE_";
-	int printed = 0;
+#include "trace/beauty/generated/clone_flags_array.c"
+	static DEFINE_STRARRAY(clone_flags, "CLONE_");
 
-#define	P_FLAG(n) \
-	if (flags & CLONE_##n) { \
-		printed += scnprintf(bf + printed, size - printed, "%s%s%s", printed ? "|" : "", show_prefix ? prefix : "", #n); \
-		flags &= ~CLONE_##n; \
-	}
-
-	P_FLAG(VM);
-	P_FLAG(FS);
-	P_FLAG(FILES);
-	P_FLAG(SIGHAND);
-	P_FLAG(PIDFD);
-	P_FLAG(PTRACE);
-	P_FLAG(VFORK);
-	P_FLAG(PARENT);
-	P_FLAG(THREAD);
-	P_FLAG(NEWNS);
-	P_FLAG(SYSVSEM);
-	P_FLAG(SETTLS);
-	P_FLAG(PARENT_SETTID);
-	P_FLAG(CHILD_CLEARTID);
-	P_FLAG(DETACHED);
-	P_FLAG(UNTRACED);
-	P_FLAG(CHILD_SETTID);
-	P_FLAG(NEWCGROUP);
-	P_FLAG(NEWUTS);
-	P_FLAG(NEWIPC);
-	P_FLAG(NEWUSER);
-	P_FLAG(NEWPID);
-	P_FLAG(NEWNET);
-	P_FLAG(IO);
-	P_FLAG(CLEAR_SIGHAND);
-	P_FLAG(INTO_CGROUP);
-#undef P_FLAG
-
-	if (flags)
-		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
-
-	return printed;
+	return strarray__scnprintf_flags(&strarray__clone_flags, bf, size, show_prefix, flags);
 }
 
 size_t syscall_arg__scnprintf_clone_flags(char *bf, size_t size, struct syscall_arg *arg)
diff --git a/tools/perf/trace/beauty/clone.sh b/tools/perf/trace/beauty/clone.sh
new file mode 100755
index 00000000000000..18b6c0d7569372
--- /dev/null
+++ b/tools/perf/trace/beauty/clone.sh
@@ -0,0 +1,17 @@
+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+
+if [ $# -ne 1 ] ; then
+	beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux/
+else
+	beauty_uapi_linux_dir=$1
+fi
+
+linux_sched=${beauty_uapi_linux_dir}/sched.h
+
+printf "static const char *clone_flags[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+CLONE_([^_]+[[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*'
+grep -E $regex ${linux_sched} | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/fcntl.c b/tools/perf/trace/beauty/fcntl.c
index 56ef83b3d130b5..d075904dcccedc 100644
--- a/tools/perf/trace/beauty/fcntl.c
+++ b/tools/perf/trace/beauty/fcntl.c
@@ -7,7 +7,7 @@
 
 #include "trace/beauty/beauty.h"
 #include <linux/kernel.h>
-#include <uapi/linux/fcntl.h>
+#include <linux/fcntl.h>
 
 static size_t fcntl__scnprintf_getfd(unsigned long val, char *bf, size_t size, bool show_prefix)
 {
diff --git a/tools/perf/trace/beauty/flock.c b/tools/perf/trace/beauty/flock.c
index c14274edd6d9de..a6514a6f07cfa0 100644
--- a/tools/perf/trace/beauty/flock.c
+++ b/tools/perf/trace/beauty/flock.c
@@ -2,7 +2,7 @@
 
 #include "trace/beauty/beauty.h"
 #include <linux/kernel.h>
-#include <uapi/linux/fcntl.h>
+#include <linux/fcntl.h>
 
 #ifndef LOCK_MAND
 #define LOCK_MAND	 32
diff --git a/tools/perf/trace/beauty/fs_at_flags.c b/tools/perf/trace/beauty/fs_at_flags.c
new file mode 100644
index 00000000000000..c200669cb944a4
--- /dev/null
+++ b/tools/perf/trace/beauty/fs_at_flags.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * trace/beauty/fs_at_flags.c
+ *
+ *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+
+#include "trace/beauty/beauty.h"
+#include <sys/types.h>
+#include <linux/fcntl.h>
+#include <linux/log2.h>
+
+/*
+ * uapi/linux/fcntl.h does not keep a copy in tools headers directory,
+ * for system with kernel versions before v5.8, need to sync AT_EACCESS macro.
+ */
+#ifndef AT_EACCESS
+#define AT_EACCESS 0x200
+#endif
+
+#include "trace/beauty/generated/fs_at_flags_array.c"
+static DEFINE_STRARRAY(fs_at_flags, "AT_");
+
+static size_t fs_at__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix)
+{
+	return strarray__scnprintf_flags(&strarray__fs_at_flags, bf, size, show_prefix, flags);
+}
+
+size_t syscall_arg__scnprintf_fs_at_flags(char *bf, size_t size, struct syscall_arg *arg)
+{
+	bool show_prefix = arg->show_string_prefix;
+	int flags = arg->val;
+
+	return fs_at__scnprintf_flags(flags, bf, size, show_prefix);
+}
+
+static size_t faccessat2__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix)
+{
+	int printed = 0;
+
+	// AT_EACCESS is the same as AT_REMOVEDIR, that is in fs_at_flags_array,
+	// special case it here.
+	if (flags & AT_EACCESS) {
+		flags &= ~AT_EACCESS;
+		printed += scnprintf(bf + printed, size - printed, "%sEACCESS%s",
+				     show_prefix ? strarray__fs_at_flags.prefix : "", flags ? "|" : "");
+	}
+
+	return strarray__scnprintf_flags(&strarray__fs_at_flags, bf + printed, size - printed, show_prefix, flags);
+}
+
+size_t syscall_arg__scnprintf_faccessat2_flags(char *bf, size_t size, struct syscall_arg *arg)
+{
+	bool show_prefix = arg->show_string_prefix;
+	int flags = arg->val;
+
+	return faccessat2__scnprintf_flags(flags, bf, size, show_prefix);
+}
diff --git a/tools/perf/trace/beauty/fs_at_flags.sh b/tools/perf/trace/beauty/fs_at_flags.sh
new file mode 100755
index 00000000000000..456f59addf7410
--- /dev/null
+++ b/tools/perf/trace/beauty/fs_at_flags.sh
@@ -0,0 +1,21 @@
+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+
+if [ $# -ne 1 ] ; then
+	beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux/
+else
+	beauty_uapi_linux_dir=$1
+fi
+
+linux_fcntl=${beauty_uapi_linux_dir}/fcntl.h
+
+printf "static const char *fs_at_flags[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+AT_([^_]+[[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*'
+# AT_EACCESS is only meaningful to faccessat, so we will special case it there...
+# AT_STATX_SYNC_TYPE is not a bit, its a mask of AT_STATX_SYNC_AS_STAT, AT_STATX_FORCE_SYNC and AT_STATX_DONT_SYNC
+grep -E $regex ${linux_fcntl} | \
+	grep -v AT_EACCESS | \
+	grep -v AT_STATX_SYNC_TYPE | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/fsconfig.sh b/tools/perf/trace/beauty/fsconfig.sh
index bc6ef7bb7a5f93..09cee79de00ca3 100755
--- a/tools/perf/trace/beauty/fsconfig.sh
+++ b/tools/perf/trace/beauty/fsconfig.sh
@@ -2,12 +2,12 @@
 # SPDX-License-Identifier: LGPL-2.1
 
 if [ $# -ne 1 ] ; then
-	linux_header_dir=tools/include/uapi/linux
+	beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux/
 else
-	linux_header_dir=$1
+	beauty_uapi_linux_dir=$1
 fi
 
-linux_mount=${linux_header_dir}/mount.h
+linux_mount=${beauty_uapi_linux_dir}/mount.h
 
 printf "static const char *fsconfig_cmds[] = {\n"
 ms='[[:space:]]*'
diff --git a/tools/perf/trace/beauty/fsmount.c b/tools/perf/trace/beauty/fsmount.c
index 30c8c082a3c3b3..28c2c16fc1a80d 100644
--- a/tools/perf/trace/beauty/fsmount.c
+++ b/tools/perf/trace/beauty/fsmount.c
@@ -7,7 +7,14 @@
 
 #include "trace/beauty/beauty.h"
 #include <linux/log2.h>
-#include <uapi/linux/mount.h>
+#include <sys/mount.h>
+
+#ifndef MOUNT_ATTR__ATIME
+#define MOUNT_ATTR__ATIME	0x00000070 /* Setting on how atime should be updated */
+#endif
+#ifndef MOUNT_ATTR_RELATIME
+#define MOUNT_ATTR_RELATIME	0x00000000 /* - Update atime relative to mtime/ctime. */
+#endif
 
 static size_t fsmount__scnprintf_attr_flags(unsigned long flags, char *bf, size_t size, bool show_prefix)
 {
diff --git a/tools/perf/trace/beauty/fsmount.sh b/tools/perf/trace/beauty/fsmount.sh
index cba8897a751fd4..6b67a54cdeee64 100755
--- a/tools/perf/trace/beauty/fsmount.sh
+++ b/tools/perf/trace/beauty/fsmount.sh
@@ -2,12 +2,12 @@
 # SPDX-License-Identifier: LGPL-2.1
 
 if [ $# -ne 1 ] ; then
-	linux_header_dir=tools/include/uapi/linux
+	beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux/
 else
-	linux_header_dir=$1
+	beauty_uapi_linux_dir=$1
 fi
 
-linux_mount=${linux_header_dir}/mount.h
+linux_mount=${beauty_uapi_linux_dir}/mount.h
 
 # Remove MOUNT_ATTR_RELATIME as it is zeros, handle it a special way in the beautifier
 # Only handle MOUNT_ATTR_ followed by a capital letter/num as __ is special case
diff --git a/tools/perf/trace/beauty/fspick.sh b/tools/perf/trace/beauty/fspick.sh
index 1f088329b96ef0..0d9951c22b952e 100755
--- a/tools/perf/trace/beauty/fspick.sh
+++ b/tools/perf/trace/beauty/fspick.sh
@@ -2,12 +2,12 @@
 # SPDX-License-Identifier: LGPL-2.1
 
 if [ $# -ne 1 ] ; then
-	linux_header_dir=tools/include/uapi/linux
+	beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux/
 else
-	linux_header_dir=$1
+	beauty_uapi_linux_dir=$1
 fi
 
-linux_mount=${linux_header_dir}/mount.h
+linux_mount=${beauty_uapi_linux_dir}/mount.h
 
 printf "static const char *fspick_flags[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+FSPICK_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*'
diff --git a/tools/include/uapi/linux/fcntl.h b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
index 282e90aeb163c0..282e90aeb163c0 100644
--- a/tools/include/uapi/linux/fcntl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fcntl.h
diff --git a/tools/include/uapi/linux/fs.h b/tools/perf/trace/beauty/include/uapi/linux/fs.h
index 45e4e64fd6643c..45e4e64fd6643c 100644
--- a/tools/include/uapi/linux/fs.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/fs.h
diff --git a/tools/include/uapi/linux/mount.h b/tools/perf/trace/beauty/include/uapi/linux/mount.h
index ad5478dbad0073..ad5478dbad0073 100644
--- a/tools/include/uapi/linux/mount.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/mount.h
diff --git a/tools/include/uapi/linux/prctl.h b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
index 370ed14b1ae092..370ed14b1ae092 100644
--- a/tools/include/uapi/linux/prctl.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/prctl.h
diff --git a/tools/include/uapi/linux/sched.h b/tools/perf/trace/beauty/include/uapi/linux/sched.h
index 3bac0a8ceab26e..3bac0a8ceab26e 100644
--- a/tools/include/uapi/linux/sched.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/sched.h
diff --git a/tools/perf/trace/beauty/include/uapi/linux/stat.h b/tools/perf/trace/beauty/include/uapi/linux/stat.h
new file mode 100644
index 00000000000000..2f2ee82d55175d
--- /dev/null
+++ b/tools/perf/trace/beauty/include/uapi/linux/stat.h
@@ -0,0 +1,195 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef _UAPI_LINUX_STAT_H
+#define _UAPI_LINUX_STAT_H
+
+#include <linux/types.h>
+
+#if defined(__KERNEL__) || !defined(__GLIBC__) || (__GLIBC__ < 2)
+
+#define S_IFMT  00170000
+#define S_IFSOCK 0140000
+#define S_IFLNK	 0120000
+#define S_IFREG  0100000
+#define S_IFBLK  0060000
+#define S_IFDIR  0040000
+#define S_IFCHR  0020000
+#define S_IFIFO  0010000
+#define S_ISUID  0004000
+#define S_ISGID  0002000
+#define S_ISVTX  0001000
+
+#define S_ISLNK(m)	(((m) & S_IFMT) == S_IFLNK)
+#define S_ISREG(m)	(((m) & S_IFMT) == S_IFREG)
+#define S_ISDIR(m)	(((m) & S_IFMT) == S_IFDIR)
+#define S_ISCHR(m)	(((m) & S_IFMT) == S_IFCHR)
+#define S_ISBLK(m)	(((m) & S_IFMT) == S_IFBLK)
+#define S_ISFIFO(m)	(((m) & S_IFMT) == S_IFIFO)
+#define S_ISSOCK(m)	(((m) & S_IFMT) == S_IFSOCK)
+
+#define S_IRWXU 00700
+#define S_IRUSR 00400
+#define S_IWUSR 00200
+#define S_IXUSR 00100
+
+#define S_IRWXG 00070
+#define S_IRGRP 00040
+#define S_IWGRP 00020
+#define S_IXGRP 00010
+
+#define S_IRWXO 00007
+#define S_IROTH 00004
+#define S_IWOTH 00002
+#define S_IXOTH 00001
+
+#endif
+
+/*
+ * Timestamp structure for the timestamps in struct statx.
+ *
+ * tv_sec holds the number of seconds before (negative) or after (positive)
+ * 00:00:00 1st January 1970 UTC.
+ *
+ * tv_nsec holds a number of nanoseconds (0..999,999,999) after the tv_sec time.
+ *
+ * __reserved is held in case we need a yet finer resolution.
+ */
+struct statx_timestamp {
+	__s64	tv_sec;
+	__u32	tv_nsec;
+	__s32	__reserved;
+};
+
+/*
+ * Structures for the extended file attribute retrieval system call
+ * (statx()).
+ *
+ * The caller passes a mask of what they're specifically interested in as a
+ * parameter to statx().  What statx() actually got will be indicated in
+ * st_mask upon return.
+ *
+ * For each bit in the mask argument:
+ *
+ * - if the datum is not supported:
+ *
+ *   - the bit will be cleared, and
+ *
+ *   - the datum will be set to an appropriate fabricated value if one is
+ *     available (eg. CIFS can take a default uid and gid), otherwise
+ *
+ *   - the field will be cleared;
+ *
+ * - otherwise, if explicitly requested:
+ *
+ *   - the datum will be synchronised to the server if AT_STATX_FORCE_SYNC is
+ *     set or if the datum is considered out of date, and
+ *
+ *   - the field will be filled in and the bit will be set;
+ *
+ * - otherwise, if not requested, but available in approximate form without any
+ *   effort, it will be filled in anyway, and the bit will be set upon return
+ *   (it might not be up to date, however, and no attempt will be made to
+ *   synchronise the internal state first);
+ *
+ * - otherwise the field and the bit will be cleared before returning.
+ *
+ * Items in STATX_BASIC_STATS may be marked unavailable on return, but they
+ * will have values installed for compatibility purposes so that stat() and
+ * co. can be emulated in userspace.
+ */
+struct statx {
+	/* 0x00 */
+	__u32	stx_mask;	/* What results were written [uncond] */
+	__u32	stx_blksize;	/* Preferred general I/O size [uncond] */
+	__u64	stx_attributes;	/* Flags conveying information about the file [uncond] */
+	/* 0x10 */
+	__u32	stx_nlink;	/* Number of hard links */
+	__u32	stx_uid;	/* User ID of owner */
+	__u32	stx_gid;	/* Group ID of owner */
+	__u16	stx_mode;	/* File mode */
+	__u16	__spare0[1];
+	/* 0x20 */
+	__u64	stx_ino;	/* Inode number */
+	__u64	stx_size;	/* File size */
+	__u64	stx_blocks;	/* Number of 512-byte blocks allocated */
+	__u64	stx_attributes_mask; /* Mask to show what's supported in stx_attributes */
+	/* 0x40 */
+	struct statx_timestamp	stx_atime;	/* Last access time */
+	struct statx_timestamp	stx_btime;	/* File creation time */
+	struct statx_timestamp	stx_ctime;	/* Last attribute change time */
+	struct statx_timestamp	stx_mtime;	/* Last data modification time */
+	/* 0x80 */
+	__u32	stx_rdev_major;	/* Device ID of special file [if bdev/cdev] */
+	__u32	stx_rdev_minor;
+	__u32	stx_dev_major;	/* ID of device containing file [uncond] */
+	__u32	stx_dev_minor;
+	/* 0x90 */
+	__u64	stx_mnt_id;
+	__u32	stx_dio_mem_align;	/* Memory buffer alignment for direct I/O */
+	__u32	stx_dio_offset_align;	/* File offset alignment for direct I/O */
+	/* 0xa0 */
+	__u64	__spare3[12];	/* Spare space for future expansion */
+	/* 0x100 */
+};
+
+/*
+ * Flags to be stx_mask
+ *
+ * Query request/result mask for statx() and struct statx::stx_mask.
+ *
+ * These bits should be set in the mask argument of statx() to request
+ * particular items when calling statx().
+ */
+#define STATX_TYPE		0x00000001U	/* Want/got stx_mode & S_IFMT */
+#define STATX_MODE		0x00000002U	/* Want/got stx_mode & ~S_IFMT */
+#define STATX_NLINK		0x00000004U	/* Want/got stx_nlink */
+#define STATX_UID		0x00000008U	/* Want/got stx_uid */
+#define STATX_GID		0x00000010U	/* Want/got stx_gid */
+#define STATX_ATIME		0x00000020U	/* Want/got stx_atime */
+#define STATX_MTIME		0x00000040U	/* Want/got stx_mtime */
+#define STATX_CTIME		0x00000080U	/* Want/got stx_ctime */
+#define STATX_INO		0x00000100U	/* Want/got stx_ino */
+#define STATX_SIZE		0x00000200U	/* Want/got stx_size */
+#define STATX_BLOCKS		0x00000400U	/* Want/got stx_blocks */
+#define STATX_BASIC_STATS	0x000007ffU	/* The stuff in the normal stat struct */
+#define STATX_BTIME		0x00000800U	/* Want/got stx_btime */
+#define STATX_MNT_ID		0x00001000U	/* Got stx_mnt_id */
+#define STATX_DIOALIGN		0x00002000U	/* Want/got direct I/O alignment info */
+#define STATX_MNT_ID_UNIQUE	0x00004000U	/* Want/got extended stx_mount_id */
+
+#define STATX__RESERVED		0x80000000U	/* Reserved for future struct statx expansion */
+
+#ifndef __KERNEL__
+/*
+ * This is deprecated, and shall remain the same value in the future.  To avoid
+ * confusion please use the equivalent (STATX_BASIC_STATS | STATX_BTIME)
+ * instead.
+ */
+#define STATX_ALL		0x00000fffU
+#endif
+
+/*
+ * Attributes to be found in stx_attributes and masked in stx_attributes_mask.
+ *
+ * These give information about the features or the state of a file that might
+ * be of use to ordinary userspace programs such as GUIs or ls rather than
+ * specialised tools.
+ *
+ * Note that the flags marked [I] correspond to the FS_IOC_SETFLAGS flags
+ * semantically.  Where possible, the numerical value is picked to correspond
+ * also.  Note that the DAX attribute indicates that the file is in the CPU
+ * direct access state.  It does not correspond to the per-inode flag that
+ * some filesystems support.
+ *
+ */
+#define STATX_ATTR_COMPRESSED		0x00000004 /* [I] File is compressed by the fs */
+#define STATX_ATTR_IMMUTABLE		0x00000010 /* [I] File is marked immutable */
+#define STATX_ATTR_APPEND		0x00000020 /* [I] File is append-only */
+#define STATX_ATTR_NODUMP		0x00000040 /* [I] File is not to be dumped */
+#define STATX_ATTR_ENCRYPTED		0x00000800 /* [I] File requires key to decrypt in fs */
+#define STATX_ATTR_AUTOMOUNT		0x00001000 /* Dir: Automount trigger */
+#define STATX_ATTR_MOUNT_ROOT		0x00002000 /* Root of a mount */
+#define STATX_ATTR_VERITY		0x00100000 /* [I] Verity protected file */
+#define STATX_ATTR_DAX			0x00200000 /* File is currently in DAX state */
+
+
+#endif /* _UAPI_LINUX_STAT_H */
diff --git a/tools/include/uapi/linux/usbdevice_fs.h b/tools/perf/trace/beauty/include/uapi/linux/usbdevice_fs.h
index 74a84e02422ab8..74a84e02422ab8 100644
--- a/tools/include/uapi/linux/usbdevice_fs.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/usbdevice_fs.h
diff --git a/tools/include/uapi/linux/vhost.h b/tools/perf/trace/beauty/include/uapi/linux/vhost.h
index 649560c685f13b..b95dd84eef2db2 100644
--- a/tools/include/uapi/linux/vhost.h
+++ b/tools/perf/trace/beauty/include/uapi/linux/vhost.h
@@ -179,12 +179,6 @@
 /* Get the config size */
 #define VHOST_VDPA_GET_CONFIG_SIZE	_IOR(VHOST_VIRTIO, 0x79, __u32)
 
-/* Get the count of all virtqueues */
-#define VHOST_VDPA_GET_VQS_COUNT	_IOR(VHOST_VIRTIO, 0x80, __u32)
-
-/* Get the number of virtqueue groups. */
-#define VHOST_VDPA_GET_GROUP_NUM	_IOR(VHOST_VIRTIO, 0x81, __u32)
-
 /* Get the number of address spaces. */
 #define VHOST_VDPA_GET_AS_NUM		_IOR(VHOST_VIRTIO, 0x7A, unsigned int)
 
@@ -227,4 +221,18 @@
  */
 #define VHOST_VDPA_GET_VRING_DESC_GROUP	_IOWR(VHOST_VIRTIO, 0x7F,	\
 					      struct vhost_vring_state)
+
+
+/* Get the count of all virtqueues */
+#define VHOST_VDPA_GET_VQS_COUNT	_IOR(VHOST_VIRTIO, 0x80, __u32)
+
+/* Get the number of virtqueue groups. */
+#define VHOST_VDPA_GET_GROUP_NUM	_IOR(VHOST_VIRTIO, 0x81, __u32)
+
+/* Get the queue size of a specific virtqueue.
+ * userspace set the vring index in vhost_vring_state.index
+ * kernel set the queue size in vhost_vring_state.num
+ */
+#define VHOST_VDPA_GET_VRING_SIZE	_IOWR(VHOST_VIRTIO, 0x82,	\
+					      struct vhost_vring_state)
 #endif
diff --git a/tools/include/uapi/sound/asound.h b/tools/perf/trace/beauty/include/uapi/sound/asound.h
index 628d46a0da92eb..628d46a0da92eb 100644
--- a/tools/include/uapi/sound/asound.h
+++ b/tools/perf/trace/beauty/include/uapi/sound/asound.h
diff --git a/tools/perf/trace/beauty/mount_flags.sh b/tools/perf/trace/beauty/mount_flags.sh
index 730099a9a67c1e..ff578f7b451b5a 100755
--- a/tools/perf/trace/beauty/mount_flags.sh
+++ b/tools/perf/trace/beauty/mount_flags.sh
@@ -1,15 +1,15 @@
 #!/bin/sh
 # SPDX-License-Identifier: LGPL-2.1
 
-[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+[ $# -eq 1 ] && beauty_uapi_linux_dir=$1 || beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux/
 
 printf "static const char *mount_flags[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MS_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*'
-grep -E $regex ${header_dir}/mount.h | grep -E -v '(MSK|VERBOSE|MGC_VAL)\>' | \
+grep -E $regex ${beauty_uapi_linux_dir}/mount.h | grep -E -v '(MSK|VERBOSE|MGC_VAL)\>' | \
 	sed -r "s/$regex/\2 \2 \1/g" | sort -n | \
 	xargs printf "\t[%s ? (ilog2(%s) + 1) : 0] = \"%s\",\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MS_([[:alnum:]_]+)[[:space:]]+\(1<<([[:digit:]]+)\)[[:space:]]*.*'
-grep -E $regex ${header_dir}/mount.h | \
+grep -E $regex ${beauty_uapi_linux_dir}/mount.h | \
 	sed -r "s/$regex/\2 \1/g" | \
 	xargs printf "\t[%s + 1] = \"%s\",\n"
 printf "};\n"
diff --git a/tools/perf/trace/beauty/move_mount_flags.sh b/tools/perf/trace/beauty/move_mount_flags.sh
index ce5e632d14484b..c0dde9020bc38c 100755
--- a/tools/perf/trace/beauty/move_mount_flags.sh
+++ b/tools/perf/trace/beauty/move_mount_flags.sh
@@ -2,12 +2,12 @@
 # SPDX-License-Identifier: LGPL-2.1
 
 if [ $# -ne 1 ] ; then
-	linux_header_dir=tools/include/uapi/linux
+	beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux/
 else
-	linux_header_dir=$1
+	beauty_uapi_linux_dir=$1
 fi
 
-linux_mount=${linux_header_dir}/mount.h
+linux_mount=${beauty_uapi_linux_dir}/mount.h
 
 printf "static const char *move_mount_flags[] = {\n"
 regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MOVE_MOUNT_([^_]+[[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*'
diff --git a/tools/perf/trace/beauty/prctl.c b/tools/perf/trace/beauty/prctl.c
index 6fe5ad5f5d3a4e..7d1aa9fd03da52 100644
--- a/tools/perf/trace/beauty/prctl.c
+++ b/tools/perf/trace/beauty/prctl.c
@@ -7,7 +7,7 @@
 
 #include "trace/beauty/beauty.h"
 #include <linux/kernel.h>
-#include <uapi/linux/prctl.h>
+#include <linux/prctl.h>
 
 #include "trace/beauty/generated/prctl_option_array.c"
 
diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh
index 9455d9672f140d..e049f5e9c01116 100755
--- a/tools/perf/trace/beauty/prctl_option.sh
+++ b/tools/perf/trace/beauty/prctl_option.sh
@@ -1,18 +1,18 @@
 #!/bin/sh
 # SPDX-License-Identifier: LGPL-2.1
 
-[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+[ $# -eq 1 ] && beauty_uapi_linux_dir=$1 || beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux/
 
 printf "static const char *prctl_options[] = {\n"
 regex='^#define[[:space:]]{1}PR_(\w+)[[:space:]]*([[:xdigit:]]+)([[:space:]]*/.*)?$'
-grep -E $regex ${header_dir}/prctl.h | grep -v PR_SET_PTRACER | \
+grep -E $regex ${beauty_uapi_linux_dir}/prctl.h | grep -v PR_SET_PTRACER | \
 	sed -E "s%$regex%\2 \1%g"	| \
 	sort -n | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
 
 printf "static const char *prctl_set_mm_options[] = {\n"
 regex='^#[[:space:]]+define[[:space:]]+PR_SET_MM_(\w+)[[:space:]]*([[:digit:]]+).*'
-grep -E $regex ${header_dir}/prctl.h | \
+grep -E $regex ${beauty_uapi_linux_dir}/prctl.h | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort -n | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
diff --git a/tools/perf/trace/beauty/rename_flags.sh b/tools/perf/trace/beauty/rename_flags.sh
index 94bf7f45d28e6b..702411dd7a1c2f 100755
--- a/tools/perf/trace/beauty/rename_flags.sh
+++ b/tools/perf/trace/beauty/rename_flags.sh
@@ -2,7 +2,7 @@
 # Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
 # SPDX-License-Identifier: LGPL-2.1
 
-[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/perf/trace/beauty/include/uapi/linux/
 
 fs_header=${header_dir}/fs.h
 
diff --git a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
index e0803b95759324..572939a1288455 100755
--- a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
@@ -1,9 +1,9 @@
 #!/bin/sh
 # SPDX-License-Identifier: LGPL-2.1
 
-[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
+[ $# -eq 1 ] && beauty_uapi_sound_dir=$1 || beauty_uapi_sound_dir=tools/perf/trace/beauty/include/uapi/sound/
 
 printf "static const char *sndrv_ctl_ioctl_cmds[] = {\n"
-grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $header_dir/asound.h | \
+grep "^#define[\t ]\+SNDRV_CTL_IOCTL_" $beauty_uapi_sound_dir/asound.h | \
 	sed -r 's/^#define +SNDRV_CTL_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.U., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
index 7a464a7bf91399..33afae9a1c07ca 100755
--- a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
@@ -1,9 +1,9 @@
 #!/bin/sh
 # SPDX-License-Identifier: LGPL-2.1
 
-[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
+[ $# -eq 1 ] && beauty_uapi_sound_dir=$1 || beauty_uapi_sound_dir=tools/perf/trace/beauty/include/uapi/sound/
 
 printf "static const char *sndrv_pcm_ioctl_cmds[] = {\n"
-grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $header_dir/asound.h | \
+grep "^#define[\t ]\+SNDRV_PCM_IOCTL_" $beauty_uapi_sound_dir/asound.h | \
 	sed -r 's/^#define +SNDRV_PCM_IOCTL_([A-Z0-9_]+)[\t ]+_IO[RW]*\( *.A., *(0x[[:xdigit:]]+),?.*/\t[\2] = \"\1\",/g'
 printf "};\n"
diff --git a/tools/perf/trace/beauty/statx.c b/tools/perf/trace/beauty/statx.c
index dc5943a6352d91..24843e614b935f 100644
--- a/tools/perf/trace/beauty/statx.c
+++ b/tools/perf/trace/beauty/statx.c
@@ -6,73 +6,20 @@
  */
 
 #include "trace/beauty/beauty.h"
-#include <linux/kernel.h>
 #include <sys/types.h>
-#include <uapi/linux/fcntl.h>
-#include <uapi/linux/stat.h>
+#include <linux/log2.h>
 
-size_t syscall_arg__scnprintf_statx_flags(char *bf, size_t size, struct syscall_arg *arg)
+static size_t statx__scnprintf_mask(unsigned long mask, char *bf, size_t size, bool show_prefix)
 {
-	bool show_prefix = arg->show_string_prefix;
-	const char *prefix = "AT_";
-	int printed = 0, flags = arg->val;
-
-	if (flags == 0)
-		return scnprintf(bf, size, "%s%s", show_prefix ? "AT_STATX_" : "", "SYNC_AS_STAT");
-#define	P_FLAG(n) \
-	if (flags & AT_##n) { \
-		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", show_prefix ? prefix : "", #n); \
-		flags &= ~AT_##n; \
-	}
-
-	P_FLAG(SYMLINK_NOFOLLOW);
-	P_FLAG(REMOVEDIR);
-	P_FLAG(SYMLINK_FOLLOW);
-	P_FLAG(NO_AUTOMOUNT);
-	P_FLAG(EMPTY_PATH);
-	P_FLAG(STATX_FORCE_SYNC);
-	P_FLAG(STATX_DONT_SYNC);
-
-#undef P_FLAG
-
-	if (flags)
-		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
-
-	return printed;
+	#include "trace/beauty/generated/statx_mask_array.c"
+	static DEFINE_STRARRAY(statx_mask, "STATX_");
+	return strarray__scnprintf_flags(&strarray__statx_mask, bf, size, show_prefix, mask);
 }
 
 size_t syscall_arg__scnprintf_statx_mask(char *bf, size_t size, struct syscall_arg *arg)
 {
 	bool show_prefix = arg->show_string_prefix;
-	const char *prefix = "STATX_";
-	int printed = 0, flags = arg->val;
-
-#define	P_FLAG(n) \
-	if (flags & STATX_##n) { \
-		printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", show_prefix ? prefix : "", #n); \
-		flags &= ~STATX_##n; \
-	}
-
-	P_FLAG(TYPE);
-	P_FLAG(MODE);
-	P_FLAG(NLINK);
-	P_FLAG(UID);
-	P_FLAG(GID);
-	P_FLAG(ATIME);
-	P_FLAG(MTIME);
-	P_FLAG(CTIME);
-	P_FLAG(INO);
-	P_FLAG(SIZE);
-	P_FLAG(BLOCKS);
-	P_FLAG(BTIME);
-	P_FLAG(MNT_ID);
-	P_FLAG(DIOALIGN);
-	P_FLAG(MNT_ID_UNIQUE);
-
-#undef P_FLAG
-
-	if (flags)
-		printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
+	int mask = arg->val;
 
-	return printed;
+	return statx__scnprintf_mask(mask, bf, size, show_prefix);
 }
diff --git a/tools/perf/trace/beauty/statx_mask.sh b/tools/perf/trace/beauty/statx_mask.sh
new file mode 100755
index 00000000000000..18c802ed0c7157
--- /dev/null
+++ b/tools/perf/trace/beauty/statx_mask.sh
@@ -0,0 +1,23 @@
+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+
+if [ $# -ne 1 ] ; then
+	beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux/
+else
+	beauty_uapi_linux_dir=$1
+fi
+
+linux_stat=${beauty_uapi_linux_dir}/stat.h
+
+printf "static const char *statx_mask[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+STATX_([^_]+[[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*'
+# STATX_BASIC_STATS its a bitmask formed by the mask in the normal stat struct
+# STATX_ALL is another bitmask and deprecated
+# STATX_ATTR_*: Attributes to be found in stx_attributes and masked in stx_attributes_mask
+grep -E $regex ${linux_stat} | \
+	grep -v STATX_ALL | \
+	grep -v STATX_BASIC_STATS | \
+	grep -v '\<STATX_ATTR_' | \
+	sed -r "s/$regex/\2 \1/g"	| \
+	xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/sync_file_range.c b/tools/perf/trace/beauty/sync_file_range.c
index 1c425f04047dbb..3e8f50ff4fc701 100644
--- a/tools/perf/trace/beauty/sync_file_range.c
+++ b/tools/perf/trace/beauty/sync_file_range.c
@@ -7,7 +7,16 @@
 
 #include "trace/beauty/beauty.h"
 #include <linux/log2.h>
-#include <uapi/linux/fs.h>
+#include <linux/fs.h>
+
+#ifndef SYNC_FILE_RANGE_WRITE_AND_WAIT
+#define SYNC_FILE_RANGE_WAIT_BEFORE     1
+#define SYNC_FILE_RANGE_WRITE           2
+#define SYNC_FILE_RANGE_WAIT_AFTER      4
+#define SYNC_FILE_RANGE_WRITE_AND_WAIT  (SYNC_FILE_RANGE_WRITE | \
+                                         SYNC_FILE_RANGE_WAIT_BEFORE | \
+                                         SYNC_FILE_RANGE_WAIT_AFTER)
+#endif
 
 static size_t sync_file_range__scnprintf_flags(unsigned long flags, char *bf, size_t size, bool show_prefix)
 {
diff --git a/tools/perf/trace/beauty/sync_file_range.sh b/tools/perf/trace/beauty/sync_file_range.sh
index 90bf633be87990..b1084c4cab636b 100755
--- a/tools/perf/trace/beauty/sync_file_range.sh
+++ b/tools/perf/trace/beauty/sync_file_range.sh
@@ -2,7 +2,7 @@
 # SPDX-License-Identifier: LGPL-2.1
 
 if [ $# -ne 1 ] ; then
-	linux_header_dir=tools/include/uapi/linux
+	linux_header_dir=tools/perf/trace/beauty/include/uapi/linux/
 else
 	linux_header_dir=$1
 fi
diff --git a/tools/perf/trace/beauty/tracepoints/x86_irq_vectors.sh b/tools/perf/trace/beauty/tracepoints/x86_irq_vectors.sh
index 87dc68c7de0c29..d8e927dd2bb75c 100755
--- a/tools/perf/trace/beauty/tracepoints/x86_irq_vectors.sh
+++ b/tools/perf/trace/beauty/tracepoints/x86_irq_vectors.sh
@@ -3,12 +3,12 @@
 # (C) 2019, Arnaldo Carvalho de Melo <acme@redhat.com>
 
 if [ $# -ne 1 ] ; then
-	arch_x86_header_dir=tools/arch/x86/include/asm/
+	beauty_arch_asm_dir=tools/perf/trace/beauty/arch/x86/include/asm/
 else
-	arch_x86_header_dir=$1
+	beauty_arch_asm_dir=$1
 fi
 
-x86_irq_vectors=${arch_x86_header_dir}/irq_vectors.h
+x86_irq_vectors=${beauty_arch_asm_dir}/irq_vectors.h
 
 # FIRST_EXTERNAL_VECTOR is not that useful, find what is its number
 # and then replace whatever is using it and that is useful, which at
diff --git a/tools/perf/trace/beauty/usbdevfs_ioctl.sh b/tools/perf/trace/beauty/usbdevfs_ioctl.sh
index b39cfb3720b806..12a30a9a8e0c8f 100755
--- a/tools/perf/trace/beauty/usbdevfs_ioctl.sh
+++ b/tools/perf/trace/beauty/usbdevfs_ioctl.sh
@@ -1,21 +1,21 @@
 #!/bin/sh
 # SPDX-License-Identifier: LGPL-2.1
 
-[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+[ $# -eq 1 ] && beauty_uapi_linux_dir=$1 || beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux/
 
 # also as:
 # #define USBDEVFS_CONNINFO_EX(len)  _IOC(_IOC_READ, 'U', 32, len)
 
 printf "static const char *usbdevfs_ioctl_cmds[] = {\n"
 regex="^#[[:space:]]*define[[:space:]]+USBDEVFS_(\w+)(\(\w+\))?[[:space:]]+_IO[CWR]{0,2}\([[:space:]]*(_IOC_\w+,[[:space:]]*)?'U'[[:space:]]*,[[:space:]]*([[:digit:]]+).*"
-grep -E "$regex" ${header_dir}/usbdevice_fs.h | grep -E -v 'USBDEVFS_\w+32[[:space:]]' | \
+grep -E "$regex" ${beauty_uapi_linux_dir}/usbdevice_fs.h | grep -E -v 'USBDEVFS_\w+32[[:space:]]' | \
 	sed -r "s/$regex/\4 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n\n"
 printf "#if 0\n"
 printf "static const char *usbdevfs_ioctl_32_cmds[] = {\n"
 regex="^#[[:space:]]*define[[:space:]]+USBDEVFS_(\w+)[[:space:]]+_IO[WR]{0,2}\([[:space:]]*'U'[[:space:]]*,[[:space:]]*([[:digit:]]+).*"
-grep -E $regex ${header_dir}/usbdevice_fs.h | grep -E 'USBDEVFS_\w+32[[:space:]]' | \
+grep -E $regex ${beauty_uapi_linux_dir}/usbdevice_fs.h | grep -E 'USBDEVFS_\w+32[[:space:]]' | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
diff --git a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
index 2dd0a3b1f55aac..e4f395e7650a0b 100755
--- a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
+++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -1,18 +1,18 @@
 #!/bin/sh
 # SPDX-License-Identifier: LGPL-2.1
 
-[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+[ $# -eq 1 ] && beauty_uapi_linux_dir=$1 || beauty_uapi_linux_dir=tools/perf/trace/beauty/include/uapi/linux
 
 printf "static const char *vhost_virtio_ioctl_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-grep -E $regex ${header_dir}/vhost.h | \
+grep -E $regex ${beauty_uapi_linux_dir}/vhost.h | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
 
 printf "static const char *vhost_virtio_ioctl_read_cmds[] = {\n"
 regex='^#[[:space:]]*define[[:space:]]+VHOST_(\w+)[[:space:]]+_IOW?R\([[:space:]]*VHOST_VIRTIO[[:space:]]*,[[:space:]]*(0x[[:xdigit:]]+).*'
-grep -E $regex ${header_dir}/vhost.h | \
+grep -E $regex ${beauty_uapi_linux_dir}/vhost.h | \
 	sed -r "s/$regex/\2 \1/g"	| \
 	sort | xargs printf "\t[%s] = \"%s\",\n"
 printf "};\n"
diff --git a/tools/perf/trace/beauty/x86_arch_prctl.sh b/tools/perf/trace/beauty/x86_arch_prctl.sh
index b1596df251f0aa..b714ffa3cb7a4e 100755
--- a/tools/perf/trace/beauty/x86_arch_prctl.sh
+++ b/tools/perf/trace/beauty/x86_arch_prctl.sh
@@ -2,9 +2,9 @@
 # Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
 # SPDX-License-Identifier: LGPL-2.1
 
-[ $# -eq 1 ] && x86_header_dir=$1 || x86_header_dir=tools/arch/x86/include/uapi/asm/
+[ $# -eq 1 ] && beauty_x86_arch_asm_uapi_dir=$1 || beauty_x86_arch_asm_uapi_dir=tools/perf/trace/beauty/arch/x86/include/uapi/asm/
 
-prctl_arch_header=${x86_header_dir}/prctl.h
+prctl_arch_header=${beauty_x86_arch_asm_uapi_dir}/prctl.h
 
 print_range () {
 	idx=$1
diff --git a/tools/perf/ui/browsers/Build b/tools/perf/ui/browsers/Build
index 7a1d5ddaf6888c..2608b5da316768 100644
--- a/tools/perf/ui/browsers/Build
+++ b/tools/perf/ui/browsers/Build
@@ -1,4 +1,5 @@
 perf-y += annotate.o
+perf-y += annotate-data.o
 perf-y += hists.o
 perf-y += map.o
 perf-y += scripts.o
diff --git a/tools/perf/ui/browsers/annotate-data.c b/tools/perf/ui/browsers/annotate-data.c
new file mode 100644
index 00000000000000..a4a0f042f201a3
--- /dev/null
+++ b/tools/perf/ui/browsers/annotate-data.c
@@ -0,0 +1,312 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <inttypes.h>
+#include <string.h>
+#include <sys/ttydefaults.h>
+
+#include "ui/browser.h"
+#include "ui/helpline.h"
+#include "ui/keysyms.h"
+#include "ui/ui.h"
+#include "util/annotate.h"
+#include "util/annotate-data.h"
+#include "util/evsel.h"
+#include "util/evlist.h"
+#include "util/sort.h"
+
+struct annotated_data_browser {
+	struct ui_browser b;
+	struct list_head entries;
+	int nr_events;
+};
+
+struct browser_entry {
+	struct list_head node;
+	struct annotated_member *data;
+	struct type_hist_entry *hists;
+	int indent;
+};
+
+static struct annotated_data_browser *get_browser(struct ui_browser *uib)
+{
+	return container_of(uib, struct annotated_data_browser, b);
+}
+
+static void update_hist_entry(struct type_hist_entry *dst,
+			      struct type_hist_entry *src)
+{
+	dst->nr_samples += src->nr_samples;
+	dst->period += src->period;
+}
+
+static int get_member_overhead(struct annotated_data_type *adt,
+			       struct browser_entry *entry,
+			       struct evsel *leader)
+{
+	struct annotated_member *member = entry->data;
+	int i, k;
+
+	for (i = 0; i < member->size; i++) {
+		struct type_hist *h;
+		struct evsel *evsel;
+		int offset = member->offset + i;
+
+		for_each_group_evsel(evsel, leader) {
+			h = adt->histograms[evsel->core.idx];
+			k = evsel__group_idx(evsel);
+			update_hist_entry(&entry->hists[k], &h->addr[offset]);
+		}
+	}
+	return 0;
+}
+
+static int add_child_entries(struct annotated_data_browser *browser,
+			     struct annotated_data_type *adt,
+			     struct annotated_member *member,
+			     struct evsel *evsel, int indent)
+{
+	struct annotated_member *pos;
+	struct browser_entry *entry;
+	int nr_entries = 0;
+
+	entry = zalloc(sizeof(*entry));
+	if (entry == NULL)
+		return -1;
+
+	entry->hists = calloc(browser->nr_events, sizeof(*entry->hists));
+	if (entry->hists == NULL) {
+		free(entry);
+		return -1;
+	}
+
+	entry->data = member;
+	entry->indent = indent;
+	if (get_member_overhead(adt, entry, evsel) < 0) {
+		free(entry);
+		return -1;
+	}
+
+	list_add_tail(&entry->node, &browser->entries);
+	nr_entries++;
+
+	list_for_each_entry(pos, &member->children, node) {
+		int nr = add_child_entries(browser, adt, pos, evsel, indent + 1);
+
+		if (nr < 0)
+			return nr;
+
+		nr_entries += nr;
+	}
+
+	/* add an entry for the closing bracket ("}") */
+	if (!list_empty(&member->children)) {
+		entry = zalloc(sizeof(*entry));
+		if (entry == NULL)
+			return -1;
+
+		entry->indent = indent;
+		list_add_tail(&entry->node, &browser->entries);
+		nr_entries++;
+	}
+
+	return nr_entries;
+}
+
+static int annotated_data_browser__collect_entries(struct annotated_data_browser *browser)
+{
+	struct hist_entry *he = browser->b.priv;
+	struct annotated_data_type *adt = he->mem_type;
+	struct evsel *evsel = hists_to_evsel(he->hists);
+
+	INIT_LIST_HEAD(&browser->entries);
+	browser->b.entries = &browser->entries;
+	browser->b.nr_entries = add_child_entries(browser, adt, &adt->self,
+						  evsel, /*indent=*/0);
+	return 0;
+}
+
+static void annotated_data_browser__delete_entries(struct annotated_data_browser *browser)
+{
+	struct browser_entry *pos, *tmp;
+
+	list_for_each_entry_safe(pos, tmp, &browser->entries, node) {
+		list_del_init(&pos->node);
+		free(pos->hists);
+		free(pos);
+	}
+}
+
+static unsigned int browser__refresh(struct ui_browser *uib)
+{
+	return ui_browser__list_head_refresh(uib);
+}
+
+static int browser__show(struct ui_browser *uib)
+{
+	struct hist_entry *he = uib->priv;
+	struct annotated_data_type *adt = he->mem_type;
+	struct annotated_data_browser *browser = get_browser(uib);
+	const char *help = "Press 'h' for help on key bindings";
+	char title[256];
+
+	snprintf(title, sizeof(title), "Annotate type: '%s' (%d samples)",
+		 adt->self.type_name, he->stat.nr_events);
+
+	if (ui_browser__show(uib, title, help) < 0)
+		return -1;
+
+	/* second line header */
+	ui_browser__gotorc_title(uib, 0, 0);
+	ui_browser__set_color(uib, HE_COLORSET_ROOT);
+
+	if (symbol_conf.show_total_period)
+		strcpy(title, "Period");
+	else if (symbol_conf.show_nr_samples)
+		strcpy(title, "Samples");
+	else
+		strcpy(title, "Percent");
+
+	ui_browser__printf(uib, "%*s %10s %10s %10s  %s",
+			   11 * (browser->nr_events - 1), "",
+			   title, "Offset", "Size", "Field");
+	ui_browser__write_nstring(uib, "", uib->width);
+	return 0;
+}
+
+static void browser__write_overhead(struct ui_browser *uib,
+				    struct type_hist *total,
+				    struct type_hist_entry *hist, int row)
+{
+	u64 period = hist->period;
+	double percent = total->period ? (100.0 * period / total->period) : 0;
+	bool current = ui_browser__is_current_entry(uib, row);
+	int nr_samples = 0;
+
+	ui_browser__set_percent_color(uib, percent, current);
+
+	if (symbol_conf.show_total_period)
+		ui_browser__printf(uib, " %10" PRIu64, period);
+	else if (symbol_conf.show_nr_samples)
+		ui_browser__printf(uib, " %10d", nr_samples);
+	else
+		ui_browser__printf(uib, " %10.2f", percent);
+
+	ui_browser__set_percent_color(uib, 0, current);
+}
+
+static void browser__write(struct ui_browser *uib, void *entry, int row)
+{
+	struct annotated_data_browser *browser = get_browser(uib);
+	struct browser_entry *be = entry;
+	struct annotated_member *member = be->data;
+	struct hist_entry *he = uib->priv;
+	struct annotated_data_type *adt = he->mem_type;
+	struct evsel *leader = hists_to_evsel(he->hists);
+	struct evsel *evsel;
+
+	if (member == NULL) {
+		bool current = ui_browser__is_current_entry(uib, row);
+
+		/* print the closing bracket */
+		ui_browser__set_percent_color(uib, 0, current);
+		ui_browser__write_nstring(uib, "", 11 * browser->nr_events);
+		ui_browser__printf(uib, " %10s %10s  %*s};",
+				   "", "", be->indent * 4, "");
+		ui_browser__write_nstring(uib, "", uib->width);
+		return;
+	}
+
+	/* print the number */
+	for_each_group_evsel(evsel, leader) {
+		struct type_hist *h = adt->histograms[evsel->core.idx];
+		int idx = evsel__group_idx(evsel);
+
+		browser__write_overhead(uib, h, &be->hists[idx], row);
+	}
+
+	/* print type info */
+	if (be->indent == 0 && !member->var_name) {
+		ui_browser__printf(uib, " %10d %10d  %s%s",
+				   member->offset, member->size,
+				   member->type_name,
+				   list_empty(&member->children) ? ";" : " {");
+	} else {
+		ui_browser__printf(uib, " %10d %10d  %*s%s\t%s%s",
+				   member->offset, member->size,
+				   be->indent * 4, "", member->type_name,
+				   member->var_name ?: "",
+				   list_empty(&member->children) ? ";" : " {");
+	}
+	/* fill the rest */
+	ui_browser__write_nstring(uib, "", uib->width);
+}
+
+static int annotated_data_browser__run(struct annotated_data_browser *browser,
+				       struct evsel *evsel __maybe_unused,
+				       struct hist_browser_timer *hbt)
+{
+	int delay_secs = hbt ? hbt->refresh : 0;
+	int key;
+
+	if (browser__show(&browser->b) < 0)
+		return -1;
+
+	while (1) {
+		key = ui_browser__run(&browser->b, delay_secs);
+
+		switch (key) {
+		case K_TIMER:
+			if (hbt)
+				hbt->timer(hbt->arg);
+			continue;
+		case K_F1:
+		case 'h':
+			ui_browser__help_window(&browser->b,
+		"UP/DOWN/PGUP\n"
+		"PGDN/SPACE    Navigate\n"
+		"</>           Move to prev/next symbol\n"
+		"q/ESC/CTRL+C  Exit\n\n");
+			continue;
+		case K_LEFT:
+		case '<':
+		case '>':
+		case K_ESC:
+		case 'q':
+		case CTRL('c'):
+			goto out;
+		default:
+			continue;
+		}
+	}
+out:
+	ui_browser__hide(&browser->b);
+	return key;
+}
+
+int hist_entry__annotate_data_tui(struct hist_entry *he, struct evsel *evsel,
+				  struct hist_browser_timer *hbt)
+{
+	struct annotated_data_browser browser = {
+		.b = {
+			.refresh = browser__refresh,
+			.seek	 = ui_browser__list_head_seek,
+			.write	 = browser__write,
+			.priv	 = he,
+			.extra_title_lines = 1,
+		},
+		.nr_events = 1,
+	};
+	int ret;
+
+	ui_helpline__push("Press ESC to exit");
+
+	if (evsel__is_group_event(evsel))
+		browser.nr_events = evsel->core.nr_members;
+
+	ret = annotated_data_browser__collect_entries(&browser);
+	if (ret == 0)
+		ret = annotated_data_browser__run(&browser, evsel, hbt);
+
+	annotated_data_browser__delete_entries(&browser);
+
+	return ret;
+}
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 4790c735599bdd..0dd429cf612c04 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -49,7 +49,7 @@ static int ui_browser__jumps_percent_color(struct ui_browser *browser, int nr, b
 
 	if (current && (!browser->use_navkeypressed || browser->navkeypressed))
 		return HE_COLORSET_SELECTED;
-	if (nr == notes->max_jump_sources)
+	if (nr == notes->src->max_jump_sources)
 		return HE_COLORSET_TOP;
 	if (nr > 1)
 		return HE_COLORSET_MEDIUM;
@@ -186,7 +186,7 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 	 *  name right after the '<' token and probably treating this like a
 	 *  'call' instruction.
 	 */
-	target = notes->src->offsets[cursor->ops.target.offset];
+	target = annotated_source__get_line(notes->src, cursor->ops.target.offset);
 	if (target == NULL) {
 		ui_helpline__printf("WARN: jump target inconsistency, press 'o', notes->offsets[%#x] = NULL\n",
 				    cursor->ops.target.offset);
@@ -205,13 +205,13 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 
 	ui_browser__set_color(browser, HE_COLORSET_JUMP_ARROWS);
 	__ui_browser__line_arrow(browser,
-				 pcnt_width + 2 + notes->widths.addr + width,
+				 pcnt_width + 2 + notes->src->widths.addr + width,
 				 from, to);
 
 	diff = is_fused(ab, cursor);
 	if (diff > 0) {
 		ui_browser__mark_fused(browser,
-				       pcnt_width + 3 + notes->widths.addr + width,
+				       pcnt_width + 3 + notes->src->widths.addr + width,
 				       from - diff, diff, to > from);
 	}
 }
@@ -977,13 +977,13 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
 			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;
+			return -1;
 		}
 	}
 
 	ui_helpline__push("Press ESC to exit");
 
-	browser.b.width = notes->src->max_line_len;
+	browser.b.width = notes->src->widths.max_line_len;
 	browser.b.nr_entries = notes->src->nr_entries;
 	browser.b.entries = &notes->src->source,
 	browser.b.width += 18; /* Percentage */
@@ -996,8 +996,5 @@ int symbol__tui_annotate(struct map_symbol *ms, struct evsel *evsel,
 	if(not_annotated)
 		annotated_source__purge(notes->src);
 
-out_free_offsets:
-	if(not_annotated)
-		zfree(&notes->src->offsets);
 	return ret;
 }
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 0c02b3a8e121ff..71b32591d61a65 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -38,6 +38,7 @@
 #include "../ui.h"
 #include "map.h"
 #include "annotate.h"
+#include "annotate-data.h"
 #include "srcline.h"
 #include "string2.h"
 #include "units.h"
@@ -2506,6 +2507,32 @@ add_annotate_opt(struct hist_browser *browser __maybe_unused,
 }
 
 static int
+do_annotate_type(struct hist_browser *browser, struct popup_action *act)
+{
+	struct hist_entry *he = browser->he_selection;
+
+	hist_entry__annotate_data_tui(he, act->evsel, browser->hbt);
+	ui_browser__handle_resize(&browser->b);
+	return 0;
+}
+
+static int
+add_annotate_type_opt(struct hist_browser *browser,
+		      struct popup_action *act, char **optstr,
+		      struct hist_entry *he)
+{
+	if (he == NULL || he->mem_type == NULL || he->mem_type->histograms == NULL)
+		return 0;
+
+	if (asprintf(optstr, "Annotate type %s", he->mem_type->self.type_name) < 0)
+		return 0;
+
+	act->evsel = hists_to_evsel(browser->hists);
+	act->fn = do_annotate_type;
+	return 1;
+}
+
+static int
 do_zoom_thread(struct hist_browser *browser, struct popup_action *act)
 {
 	struct thread *thread = act->thread;
@@ -3307,6 +3334,10 @@ do_hotkey:		 // key came straight from options ui__popup_menu()
 						       browser->he_selection->ip);
 		}
 skip_annotation:
+		nr_options += add_annotate_type_opt(browser,
+						    &actions[nr_options],
+						    &options[nr_options],
+						    browser->he_selection);
 		nr_options += add_thread_opt(browser, &actions[nr_options],
 					     &options[nr_options], thread);
 		nr_options += add_dso_opt(browser, &actions[nr_options],
diff --git a/tools/perf/ui/hist.c b/tools/perf/ui/hist.c
index 2bf959d0835430..685ba2a54fd8e2 100644
--- a/tools/perf/ui/hist.c
+++ b/tools/perf/ui/hist.c
@@ -25,7 +25,7 @@
 
 static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 		      hpp_field_fn get_field, const char *fmt, int len,
-		      hpp_snprint_fn print_fn, bool fmt_percent)
+		      hpp_snprint_fn print_fn, enum perf_hpp_fmt_type fmtype)
 {
 	int ret;
 	struct hists *hists = he->hists;
@@ -33,7 +33,7 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 	char *buf = hpp->buf;
 	size_t size = hpp->size;
 
-	if (fmt_percent) {
+	if (fmtype == PERF_HPP_FMT_TYPE__PERCENT) {
 		double percent = 0.0;
 		u64 total = hists__total_period(hists);
 
@@ -41,8 +41,16 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 			percent = 100.0 * get_field(he) / total;
 
 		ret = hpp__call_print_fn(hpp, print_fn, fmt, len, percent);
-	} else
+	} else if (fmtype == PERF_HPP_FMT_TYPE__AVERAGE) {
+		double average = 0;
+
+		if (he->stat.nr_events)
+			average = 1.0 * get_field(he) / he->stat.nr_events;
+
+		ret = hpp__call_print_fn(hpp, print_fn, fmt, len, average);
+	} else {
 		ret = hpp__call_print_fn(hpp, print_fn, fmt, len, get_field(he));
+	}
 
 	if (evsel__is_group_event(evsel)) {
 		int prev_idx, idx_delta;
@@ -54,6 +62,7 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 		list_for_each_entry(pair, &he->pairs.head, pairs.node) {
 			u64 period = get_field(pair);
 			u64 total = hists__total_period(pair->hists);
+			int nr_samples = pair->stat.nr_events;
 
 			if (!total)
 				continue;
@@ -66,7 +75,7 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 				 * zero-fill group members in the middle which
 				 * have no sample
 				 */
-				if (fmt_percent) {
+				if (fmtype != PERF_HPP_FMT_TYPE__RAW) {
 					ret += hpp__call_print_fn(hpp, print_fn,
 								  fmt, len, 0.0);
 				} else {
@@ -75,9 +84,14 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 				}
 			}
 
-			if (fmt_percent) {
+			if (fmtype == PERF_HPP_FMT_TYPE__PERCENT) {
 				ret += hpp__call_print_fn(hpp, print_fn, fmt, len,
 							  100.0 * period / total);
+			} else if (fmtype == PERF_HPP_FMT_TYPE__AVERAGE) {
+				double avg = nr_samples ? (period / nr_samples) : 0;
+
+				ret += hpp__call_print_fn(hpp, print_fn, fmt,
+							  len, avg);
 			} else {
 				ret += hpp__call_print_fn(hpp, print_fn, fmt,
 							  len, period);
@@ -92,7 +106,7 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 			/*
 			 * zero-fill group members at last which have no sample
 			 */
-			if (fmt_percent) {
+			if (fmtype != PERF_HPP_FMT_TYPE__RAW) {
 				ret += hpp__call_print_fn(hpp, print_fn,
 							  fmt, len, 0.0);
 			} else {
@@ -114,33 +128,35 @@ static int __hpp__fmt(struct perf_hpp *hpp, struct hist_entry *he,
 
 int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	     struct hist_entry *he, hpp_field_fn get_field,
-	     const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent)
+	     const char *fmtstr, hpp_snprint_fn print_fn,
+	     enum perf_hpp_fmt_type fmtype)
 {
 	int len = fmt->user_len ?: fmt->len;
 
 	if (symbol_conf.field_sep) {
 		return __hpp__fmt(hpp, he, get_field, fmtstr, 1,
-				  print_fn, fmt_percent);
+				  print_fn, fmtype);
 	}
 
-	if (fmt_percent)
+	if (fmtype == PERF_HPP_FMT_TYPE__PERCENT)
 		len -= 2; /* 2 for a space and a % sign */
 	else
 		len -= 1;
 
-	return  __hpp__fmt(hpp, he, get_field, fmtstr, len, print_fn, fmt_percent);
+	return  __hpp__fmt(hpp, he, get_field, fmtstr, len, print_fn, fmtype);
 }
 
 int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 		 struct hist_entry *he, hpp_field_fn get_field,
-		 const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent)
+		 const char *fmtstr, hpp_snprint_fn print_fn,
+		 enum perf_hpp_fmt_type fmtype)
 {
 	if (!symbol_conf.cumulate_callchain) {
 		int len = fmt->user_len ?: fmt->len;
 		return snprintf(hpp->buf, hpp->size, " %*s", len - 1, "N/A");
 	}
 
-	return hpp__fmt(fmt, hpp, he, get_field, fmtstr, print_fn, fmt_percent);
+	return hpp__fmt(fmt, hpp, he, get_field, fmtstr, print_fn, fmtype);
 }
 
 static int field_cmp(u64 field_a, u64 field_b)
@@ -350,7 +366,7 @@ static int hpp__color_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
 	return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%",		\
-			hpp_color_scnprintf, true);				\
+			hpp_color_scnprintf, PERF_HPP_FMT_TYPE__PERCENT);	\
 }
 
 #define __HPP_ENTRY_PERCENT_FN(_type, _field)					\
@@ -358,7 +374,7 @@ static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
 	return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.2f%%",		\
-			hpp_entry_scnprintf, true);				\
+			hpp_entry_scnprintf, PERF_HPP_FMT_TYPE__PERCENT);	\
 }
 
 #define __HPP_SORT_FN(_type, _field)						\
@@ -378,7 +394,7 @@ static int hpp__color_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
 	return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%", 	\
-			    hpp_color_scnprintf, true);				\
+			    hpp_color_scnprintf, PERF_HPP_FMT_TYPE__PERCENT);	\
 }
 
 #define __HPP_ENTRY_ACC_PERCENT_FN(_type, _field)				\
@@ -386,7 +402,7 @@ static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
 	return hpp__fmt_acc(fmt, hpp, he, he_get_acc_##_field, " %*.2f%%",	\
-			    hpp_entry_scnprintf, true);				\
+			    hpp_entry_scnprintf, PERF_HPP_FMT_TYPE__PERCENT);	\
 }
 
 #define __HPP_SORT_ACC_FN(_type, _field)					\
@@ -406,7 +422,7 @@ static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,				\
 			      struct perf_hpp *hpp, struct hist_entry *he) 	\
 {										\
 	return hpp__fmt(fmt, hpp, he, he_get_raw_##_field, " %*"PRIu64, 	\
-			hpp_entry_scnprintf, false);				\
+			hpp_entry_scnprintf, PERF_HPP_FMT_TYPE__RAW);		\
 }
 
 #define __HPP_SORT_RAW_FN(_type, _field)					\
@@ -416,6 +432,26 @@ static int64_t hpp__sort_##_type(struct perf_hpp_fmt *fmt __maybe_unused, 	\
 	return __hpp__sort(a, b, he_get_raw_##_field);				\
 }
 
+#define __HPP_ENTRY_AVERAGE_FN(_type, _field)					\
+static u64 he_get_##_field(struct hist_entry *he)				\
+{										\
+	return he->stat._field;							\
+}										\
+										\
+static int hpp__entry_##_type(struct perf_hpp_fmt *fmt,				\
+			      struct perf_hpp *hpp, struct hist_entry *he) 	\
+{										\
+	return hpp__fmt(fmt, hpp, he, he_get_##_field, " %*.1f",		\
+			hpp_entry_scnprintf, PERF_HPP_FMT_TYPE__AVERAGE);	\
+}
+
+#define __HPP_SORT_AVERAGE_FN(_type, _field)					\
+static int64_t hpp__sort_##_type(struct perf_hpp_fmt *fmt __maybe_unused, 	\
+				 struct hist_entry *a, struct hist_entry *b) 	\
+{										\
+	return __hpp__sort(a, b, he_get_##_field);				\
+}
+
 
 #define HPP_PERCENT_FNS(_type, _field)					\
 __HPP_COLOR_PERCENT_FN(_type, _field)					\
@@ -431,6 +467,10 @@ __HPP_SORT_ACC_FN(_type, _field)
 __HPP_ENTRY_RAW_FN(_type, _field)					\
 __HPP_SORT_RAW_FN(_type, _field)
 
+#define HPP_AVERAGE_FNS(_type, _field)					\
+__HPP_ENTRY_AVERAGE_FN(_type, _field)					\
+__HPP_SORT_AVERAGE_FN(_type, _field)
+
 HPP_PERCENT_FNS(overhead, period)
 HPP_PERCENT_FNS(overhead_sys, period_sys)
 HPP_PERCENT_FNS(overhead_us, period_us)
@@ -441,6 +481,10 @@ HPP_PERCENT_ACC_FNS(overhead_acc, period)
 HPP_RAW_FNS(samples, nr_events)
 HPP_RAW_FNS(period, period)
 
+HPP_AVERAGE_FNS(weight1, weight1)
+HPP_AVERAGE_FNS(weight2, weight2)
+HPP_AVERAGE_FNS(weight3, weight3)
+
 static int64_t hpp__nop_cmp(struct perf_hpp_fmt *fmt __maybe_unused,
 			    struct hist_entry *a __maybe_unused,
 			    struct hist_entry *b __maybe_unused)
@@ -510,7 +554,10 @@ struct perf_hpp_fmt perf_hpp__format[] = {
 	HPP__COLOR_PRINT_FNS("guest usr", overhead_guest_us, OVERHEAD_GUEST_US),
 	HPP__COLOR_ACC_PRINT_FNS("Children", overhead_acc, OVERHEAD_ACC),
 	HPP__PRINT_FNS("Samples", samples, SAMPLES),
-	HPP__PRINT_FNS("Period", period, PERIOD)
+	HPP__PRINT_FNS("Period", period, PERIOD),
+	HPP__PRINT_FNS("Weight1", weight1, WEIGHT1),
+	HPP__PRINT_FNS("Weight2", weight2, WEIGHT2),
+	HPP__PRINT_FNS("Weight3", weight3, WEIGHT3),
 };
 
 struct perf_hpp_list perf_hpp_list = {
@@ -526,6 +573,7 @@ struct perf_hpp_list perf_hpp_list = {
 #undef HPP_PERCENT_FNS
 #undef HPP_PERCENT_ACC_FNS
 #undef HPP_RAW_FNS
+#undef HPP_AVERAGE_FNS
 
 #undef __HPP_HEADER_FN
 #undef __HPP_WIDTH_FN
@@ -534,9 +582,11 @@ struct perf_hpp_list perf_hpp_list = {
 #undef __HPP_COLOR_ACC_PERCENT_FN
 #undef __HPP_ENTRY_ACC_PERCENT_FN
 #undef __HPP_ENTRY_RAW_FN
+#undef __HPP_ENTRY_AVERAGE_FN
 #undef __HPP_SORT_FN
 #undef __HPP_SORT_ACC_FN
 #undef __HPP_SORT_RAW_FN
+#undef __HPP_SORT_AVERAGE_FN
 
 static void fmt_free(struct perf_hpp_fmt *fmt)
 {
@@ -785,6 +835,12 @@ void perf_hpp__reset_width(struct perf_hpp_fmt *fmt, struct hists *hists)
 		fmt->len = 12;
 		break;
 
+	case PERF_HPP__WEIGHT1:
+	case PERF_HPP__WEIGHT2:
+	case PERF_HPP__WEIGHT3:
+		fmt->len = 8;
+		break;
+
 	default:
 		break;
 	}
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index e0a723e2450386..292170a99ab6ed 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -12,6 +12,7 @@ perf-y += config.o
 perf-y += copyfile.o
 perf-y += ctype.o
 perf-y += db-export.o
+perf-y += disasm.o
 perf-y += env.o
 perf-y += event.o
 perf-y += evlist.o
@@ -388,3 +389,17 @@ $(OUTPUT)util/vsprintf.o: ../lib/vsprintf.c FORCE
 $(OUTPUT)util/list_sort.o: ../lib/list_sort.c FORCE
 	$(call rule_mkdir)
 	$(call if_changed_dep,cc_o_c)
+
+ifdef SHELLCHECK
+  SHELL_TESTS := generate-cmdlist.sh
+  TEST_LOGS := $(SHELL_TESTS:%=%.shellcheck_log)
+else
+  SHELL_TESTS :=
+  TEST_LOGS :=
+endif
+
+$(OUTPUT)%.shellcheck_log: %
+	$(call rule_mkdir)
+	$(Q)$(call echo-cmd,test)shellcheck -a -S warning "$<" > $@ || (cat $@ && rm $@ && false)
+
+perf-y += $(TEST_LOGS)
diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
index 30c4d19fcf112f..12d5faff3b7af5 100644
--- a/tools/perf/util/annotate-data.c
+++ b/tools/perf/util/annotate-data.c
@@ -19,9 +19,200 @@
 #include "evlist.h"
 #include "map.h"
 #include "map_symbol.h"
+#include "sort.h"
 #include "strbuf.h"
 #include "symbol.h"
 #include "symbol_conf.h"
+#include "thread.h"
+
+/* register number of the stack pointer */
+#define X86_REG_SP 7
+
+enum type_state_kind {
+	TSR_KIND_INVALID = 0,
+	TSR_KIND_TYPE,
+	TSR_KIND_PERCPU_BASE,
+	TSR_KIND_CONST,
+	TSR_KIND_POINTER,
+	TSR_KIND_CANARY,
+};
+
+#define pr_debug_dtp(fmt, ...)					\
+do {								\
+	if (debug_type_profile)					\
+		pr_info(fmt, ##__VA_ARGS__);			\
+	else							\
+		pr_debug3(fmt, ##__VA_ARGS__);			\
+} while (0)
+
+static void pr_debug_type_name(Dwarf_Die *die, enum type_state_kind kind)
+{
+	struct strbuf sb;
+	char *str;
+	Dwarf_Word size = 0;
+
+	if (!debug_type_profile && verbose < 3)
+		return;
+
+	switch (kind) {
+	case TSR_KIND_INVALID:
+		pr_info("\n");
+		return;
+	case TSR_KIND_PERCPU_BASE:
+		pr_info(" percpu base\n");
+		return;
+	case TSR_KIND_CONST:
+		pr_info(" constant\n");
+		return;
+	case TSR_KIND_POINTER:
+		pr_info(" pointer");
+		/* it also prints the type info */
+		break;
+	case TSR_KIND_CANARY:
+		pr_info(" stack canary\n");
+		return;
+	case TSR_KIND_TYPE:
+	default:
+		break;
+	}
+
+	dwarf_aggregate_size(die, &size);
+
+	strbuf_init(&sb, 32);
+	die_get_typename_from_type(die, &sb);
+	str = strbuf_detach(&sb, NULL);
+	pr_info(" type='%s' size=%#lx (die:%#lx)\n",
+		str, (long)size, (long)dwarf_dieoffset(die));
+	free(str);
+}
+
+static void pr_debug_location(Dwarf_Die *die, u64 pc, int reg)
+{
+	ptrdiff_t off = 0;
+	Dwarf_Attribute attr;
+	Dwarf_Addr base, start, end;
+	Dwarf_Op *ops;
+	size_t nops;
+
+	if (!debug_type_profile && verbose < 3)
+		return;
+
+	if (dwarf_attr(die, DW_AT_location, &attr) == NULL)
+		return;
+
+	while ((off = dwarf_getlocations(&attr, off, &base, &start, &end, &ops, &nops)) > 0) {
+		if (reg != DWARF_REG_PC && end < pc)
+			continue;
+		if (reg != DWARF_REG_PC && start > pc)
+			break;
+
+		pr_info(" variable location: ");
+		switch (ops->atom) {
+		case DW_OP_reg0 ...DW_OP_reg31:
+			pr_info("reg%d\n", ops->atom - DW_OP_reg0);
+			break;
+		case DW_OP_breg0 ...DW_OP_breg31:
+			pr_info("base=reg%d, offset=%#lx\n",
+				ops->atom - DW_OP_breg0, (long)ops->number);
+			break;
+		case DW_OP_regx:
+			pr_info("reg%ld\n", (long)ops->number);
+			break;
+		case DW_OP_bregx:
+			pr_info("base=reg%ld, offset=%#lx\n",
+				(long)ops->number, (long)ops->number2);
+			break;
+		case DW_OP_fbreg:
+			pr_info("use frame base, offset=%#lx\n", (long)ops->number);
+			break;
+		case DW_OP_addr:
+			pr_info("address=%#lx\n", (long)ops->number);
+			break;
+		default:
+			pr_info("unknown: code=%#x, number=%#lx\n",
+				ops->atom, (long)ops->number);
+			break;
+		}
+		break;
+	}
+}
+
+/*
+ * Type information in a register, valid when @ok is true.
+ * The @caller_saved registers are invalidated after a function call.
+ */
+struct type_state_reg {
+	Dwarf_Die type;
+	u32 imm_value;
+	bool ok;
+	bool caller_saved;
+	u8 kind;
+};
+
+/* Type information in a stack location, dynamically allocated */
+struct type_state_stack {
+	struct list_head list;
+	Dwarf_Die type;
+	int offset;
+	int size;
+	bool compound;
+	u8 kind;
+};
+
+/* FIXME: This should be arch-dependent */
+#define TYPE_STATE_MAX_REGS  16
+
+/*
+ * State table to maintain type info in each register and stack location.
+ * It'll be updated when new variable is allocated or type info is moved
+ * to a new location (register or stack).  As it'd be used with the
+ * shortest path of basic blocks, it only maintains a single table.
+ */
+struct type_state {
+	/* state of general purpose registers */
+	struct type_state_reg regs[TYPE_STATE_MAX_REGS];
+	/* state of stack location */
+	struct list_head stack_vars;
+	/* return value register */
+	int ret_reg;
+	/* stack pointer register */
+	int stack_reg;
+};
+
+static bool has_reg_type(struct type_state *state, int reg)
+{
+	return (unsigned)reg < ARRAY_SIZE(state->regs);
+}
+
+static void init_type_state(struct type_state *state, struct arch *arch)
+{
+	memset(state, 0, sizeof(*state));
+	INIT_LIST_HEAD(&state->stack_vars);
+
+	if (arch__is(arch, "x86")) {
+		state->regs[0].caller_saved = true;
+		state->regs[1].caller_saved = true;
+		state->regs[2].caller_saved = true;
+		state->regs[4].caller_saved = true;
+		state->regs[5].caller_saved = true;
+		state->regs[8].caller_saved = true;
+		state->regs[9].caller_saved = true;
+		state->regs[10].caller_saved = true;
+		state->regs[11].caller_saved = true;
+		state->ret_reg = 0;
+		state->stack_reg = X86_REG_SP;
+	}
+}
+
+static void exit_type_state(struct type_state *state)
+{
+	struct type_state_stack *stack, *tmp;
+
+	list_for_each_entry_safe(stack, tmp, &state->stack_vars, list) {
+		list_del(&stack->list);
+		free(stack);
+	}
+}
 
 /*
  * Compare type name and size to maintain them in a tree.
@@ -194,14 +385,22 @@ static bool find_cu_die(struct debuginfo *di, u64 pc, Dwarf_Die *cu_die)
 }
 
 /* The type info will be saved in @type_die */
-static int check_variable(Dwarf_Die *var_die, Dwarf_Die *type_die, int offset,
-			  bool is_pointer)
+static int check_variable(struct data_loc_info *dloc, Dwarf_Die *var_die,
+			  Dwarf_Die *type_die, int reg, int offset, bool is_fbreg)
 {
 	Dwarf_Word size;
+	bool is_pointer = true;
+
+	if (reg == DWARF_REG_PC)
+		is_pointer = false;
+	else if (reg == dloc->fbreg || is_fbreg)
+		is_pointer = false;
+	else if (arch__is(dloc->arch, "x86") && reg == X86_REG_SP)
+		is_pointer = false;
 
 	/* Get the type of the variable */
 	if (die_get_real_type(var_die, type_die) == NULL) {
-		pr_debug("variable has no type\n");
+		pr_debug_dtp("variable has no type\n");
 		ann_data_stat.no_typeinfo++;
 		return -1;
 	}
@@ -215,7 +414,7 @@ static int check_variable(Dwarf_Die *var_die, Dwarf_Die *type_die, int offset,
 		if ((dwarf_tag(type_die) != DW_TAG_pointer_type &&
 		     dwarf_tag(type_die) != DW_TAG_array_type) ||
 		    die_get_real_type(type_die, type_die) == NULL) {
-			pr_debug("no pointer or no type\n");
+			pr_debug_dtp("no pointer or no type\n");
 			ann_data_stat.no_typeinfo++;
 			return -1;
 		}
@@ -223,14 +422,15 @@ static int check_variable(Dwarf_Die *var_die, Dwarf_Die *type_die, int offset,
 
 	/* Get the size of the actual type */
 	if (dwarf_aggregate_size(type_die, &size) < 0) {
-		pr_debug("type size is unknown\n");
+		pr_debug_dtp("type size is unknown\n");
 		ann_data_stat.invalid_size++;
 		return -1;
 	}
 
 	/* Minimal sanity check */
 	if ((unsigned)offset >= size) {
-		pr_debug("offset: %d is bigger than size: %" PRIu64 "\n", offset, size);
+		pr_debug_dtp("offset: %d is bigger than size: %"PRIu64"\n",
+			     offset, size);
 		ann_data_stat.bad_offset++;
 		return -1;
 	}
@@ -238,23 +438,1096 @@ static int check_variable(Dwarf_Die *var_die, Dwarf_Die *type_die, int offset,
 	return 0;
 }
 
+static struct type_state_stack *find_stack_state(struct type_state *state,
+						 int offset)
+{
+	struct type_state_stack *stack;
+
+	list_for_each_entry(stack, &state->stack_vars, list) {
+		if (offset == stack->offset)
+			return stack;
+
+		if (stack->compound && stack->offset < offset &&
+		    offset < stack->offset + stack->size)
+			return stack;
+	}
+	return NULL;
+}
+
+static void set_stack_state(struct type_state_stack *stack, int offset, u8 kind,
+			    Dwarf_Die *type_die)
+{
+	int tag;
+	Dwarf_Word size;
+
+	if (dwarf_aggregate_size(type_die, &size) < 0)
+		size = 0;
+
+	tag = dwarf_tag(type_die);
+
+	stack->type = *type_die;
+	stack->size = size;
+	stack->offset = offset;
+	stack->kind = kind;
+
+	switch (tag) {
+	case DW_TAG_structure_type:
+	case DW_TAG_union_type:
+		stack->compound = (kind != TSR_KIND_POINTER);
+		break;
+	default:
+		stack->compound = false;
+		break;
+	}
+}
+
+static struct type_state_stack *findnew_stack_state(struct type_state *state,
+						    int offset, u8 kind,
+						    Dwarf_Die *type_die)
+{
+	struct type_state_stack *stack = find_stack_state(state, offset);
+
+	if (stack) {
+		set_stack_state(stack, offset, kind, type_die);
+		return stack;
+	}
+
+	stack = malloc(sizeof(*stack));
+	if (stack) {
+		set_stack_state(stack, offset, kind, type_die);
+		list_add(&stack->list, &state->stack_vars);
+	}
+	return stack;
+}
+
+/* Maintain a cache for quick global variable lookup */
+struct global_var_entry {
+	struct rb_node node;
+	char *name;
+	u64 start;
+	u64 end;
+	u64 die_offset;
+};
+
+static int global_var_cmp(const void *_key, const struct rb_node *node)
+{
+	const u64 addr = (uintptr_t)_key;
+	struct global_var_entry *gvar;
+
+	gvar = rb_entry(node, struct global_var_entry, node);
+
+	if (gvar->start <= addr && addr < gvar->end)
+		return 0;
+	return gvar->start > addr ? -1 : 1;
+}
+
+static bool global_var_less(struct rb_node *node_a, const struct rb_node *node_b)
+{
+	struct global_var_entry *gvar_a, *gvar_b;
+
+	gvar_a = rb_entry(node_a, struct global_var_entry, node);
+	gvar_b = rb_entry(node_b, struct global_var_entry, node);
+
+	return gvar_a->start < gvar_b->start;
+}
+
+static struct global_var_entry *global_var__find(struct data_loc_info *dloc, u64 addr)
+{
+	struct dso *dso = map__dso(dloc->ms->map);
+	struct rb_node *node;
+
+	node = rb_find((void *)(uintptr_t)addr, &dso->global_vars, global_var_cmp);
+	if (node == NULL)
+		return NULL;
+
+	return rb_entry(node, struct global_var_entry, node);
+}
+
+static bool global_var__add(struct data_loc_info *dloc, u64 addr,
+			    const char *name, Dwarf_Die *type_die)
+{
+	struct dso *dso = map__dso(dloc->ms->map);
+	struct global_var_entry *gvar;
+	Dwarf_Word size;
+
+	if (dwarf_aggregate_size(type_die, &size) < 0)
+		return false;
+
+	gvar = malloc(sizeof(*gvar));
+	if (gvar == NULL)
+		return false;
+
+	gvar->name = strdup(name);
+	if (gvar->name == NULL) {
+		free(gvar);
+		return false;
+	}
+
+	gvar->start = addr;
+	gvar->end = addr + size;
+	gvar->die_offset = dwarf_dieoffset(type_die);
+
+	rb_add(&gvar->node, &dso->global_vars, global_var_less);
+	return true;
+}
+
+void global_var_type__tree_delete(struct rb_root *root)
+{
+	struct global_var_entry *gvar;
+
+	while (!RB_EMPTY_ROOT(root)) {
+		struct rb_node *node = rb_first(root);
+
+		rb_erase(node, root);
+		gvar = rb_entry(node, struct global_var_entry, node);
+		free(gvar->name);
+		free(gvar);
+	}
+}
+
+static bool get_global_var_info(struct data_loc_info *dloc, u64 addr,
+				const char **var_name, int *var_offset)
+{
+	struct addr_location al;
+	struct symbol *sym;
+	u64 mem_addr;
+
+	/* Kernel symbols might be relocated */
+	mem_addr = addr + map__reloc(dloc->ms->map);
+
+	addr_location__init(&al);
+	sym = thread__find_symbol_fb(dloc->thread, dloc->cpumode,
+				     mem_addr, &al);
+	if (sym) {
+		*var_name = sym->name;
+		/* Calculate type offset from the start of variable */
+		*var_offset = mem_addr - map__unmap_ip(al.map, sym->start);
+	} else {
+		*var_name = NULL;
+	}
+	addr_location__exit(&al);
+	if (*var_name == NULL)
+		return false;
+
+	return true;
+}
+
+static bool get_global_var_type(Dwarf_Die *cu_die, struct data_loc_info *dloc,
+				u64 ip, u64 var_addr, int *var_offset,
+				Dwarf_Die *type_die)
+{
+	u64 pc;
+	int offset;
+	const char *var_name = NULL;
+	struct global_var_entry *gvar;
+	Dwarf_Die var_die;
+
+	gvar = global_var__find(dloc, var_addr);
+	if (gvar) {
+		if (!dwarf_offdie(dloc->di->dbg, gvar->die_offset, type_die))
+			return false;
+
+		*var_offset = var_addr - gvar->start;
+		return true;
+	}
+
+	/* Try to get the variable by address first */
+	if (die_find_variable_by_addr(cu_die, var_addr, &var_die, &offset) &&
+	    check_variable(dloc, &var_die, type_die, DWARF_REG_PC, offset,
+			   /*is_fbreg=*/false) == 0) {
+		var_name = dwarf_diename(&var_die);
+		*var_offset = offset;
+		goto ok;
+	}
+
+	if (!get_global_var_info(dloc, var_addr, &var_name, var_offset))
+		return false;
+
+	pc = map__rip_2objdump(dloc->ms->map, ip);
+
+	/* Try to get the name of global variable */
+	if (die_find_variable_at(cu_die, var_name, pc, &var_die) &&
+	    check_variable(dloc, &var_die, type_die, DWARF_REG_PC, *var_offset,
+			   /*is_fbreg=*/false) == 0)
+		goto ok;
+
+	return false;
+
+ok:
+	/* The address should point to the start of the variable */
+	global_var__add(dloc, var_addr - *var_offset, var_name, type_die);
+	return true;
+}
+
+/**
+ * update_var_state - Update type state using given variables
+ * @state: type state table
+ * @dloc: data location info
+ * @addr: instruction address to match with variable
+ * @insn_offset: instruction offset (for debug)
+ * @var_types: list of variables with type info
+ *
+ * This function fills the @state table using @var_types info.  Each variable
+ * is used only at the given location and updates an entry in the table.
+ */
+static void update_var_state(struct type_state *state, struct data_loc_info *dloc,
+			     u64 addr, u64 insn_offset, struct die_var_type *var_types)
+{
+	Dwarf_Die mem_die;
+	struct die_var_type *var;
+	int fbreg = dloc->fbreg;
+	int fb_offset = 0;
+
+	if (dloc->fb_cfa) {
+		if (die_get_cfa(dloc->di->dbg, addr, &fbreg, &fb_offset) < 0)
+			fbreg = -1;
+	}
+
+	for (var = var_types; var != NULL; var = var->next) {
+		if (var->addr != addr)
+			continue;
+		/* Get the type DIE using the offset */
+		if (!dwarf_offdie(dloc->di->dbg, var->die_off, &mem_die))
+			continue;
+
+		if (var->reg == DWARF_REG_FB) {
+			findnew_stack_state(state, var->offset, TSR_KIND_TYPE,
+					    &mem_die);
+
+			pr_debug_dtp("var [%"PRIx64"] -%#x(stack)",
+				     insn_offset, -var->offset);
+			pr_debug_type_name(&mem_die, TSR_KIND_TYPE);
+		} else if (var->reg == fbreg) {
+			findnew_stack_state(state, var->offset - fb_offset,
+					    TSR_KIND_TYPE, &mem_die);
+
+			pr_debug_dtp("var [%"PRIx64"] -%#x(stack)",
+				     insn_offset, -var->offset + fb_offset);
+			pr_debug_type_name(&mem_die, TSR_KIND_TYPE);
+		} else if (has_reg_type(state, var->reg) && var->offset == 0) {
+			struct type_state_reg *reg;
+
+			reg = &state->regs[var->reg];
+			reg->type = mem_die;
+			reg->kind = TSR_KIND_TYPE;
+			reg->ok = true;
+
+			pr_debug_dtp("var [%"PRIx64"] reg%d",
+				     insn_offset, var->reg);
+			pr_debug_type_name(&mem_die, TSR_KIND_TYPE);
+		}
+	}
+}
+
+static void update_insn_state_x86(struct type_state *state,
+				  struct data_loc_info *dloc, Dwarf_Die *cu_die,
+				  struct disasm_line *dl)
+{
+	struct annotated_insn_loc loc;
+	struct annotated_op_loc *src = &loc.ops[INSN_OP_SOURCE];
+	struct annotated_op_loc *dst = &loc.ops[INSN_OP_TARGET];
+	struct type_state_reg *tsr;
+	Dwarf_Die type_die;
+	u32 insn_offset = dl->al.offset;
+	int fbreg = dloc->fbreg;
+	int fboff = 0;
+
+	if (annotate_get_insn_location(dloc->arch, dl, &loc) < 0)
+		return;
+
+	if (ins__is_call(&dl->ins)) {
+		struct symbol *func = dl->ops.target.sym;
+
+		if (func == NULL)
+			return;
+
+		/* __fentry__ will preserve all registers */
+		if (!strcmp(func->name, "__fentry__"))
+			return;
+
+		pr_debug_dtp("call [%x] %s\n", insn_offset, func->name);
+
+		/* Otherwise invalidate caller-saved registers after call */
+		for (unsigned i = 0; i < ARRAY_SIZE(state->regs); i++) {
+			if (state->regs[i].caller_saved)
+				state->regs[i].ok = false;
+		}
+
+		/* Update register with the return type (if any) */
+		if (die_find_func_rettype(cu_die, func->name, &type_die)) {
+			tsr = &state->regs[state->ret_reg];
+			tsr->type = type_die;
+			tsr->kind = TSR_KIND_TYPE;
+			tsr->ok = true;
+
+			pr_debug_dtp("call [%x] return -> reg%d",
+				     insn_offset, state->ret_reg);
+			pr_debug_type_name(&type_die, tsr->kind);
+		}
+		return;
+	}
+
+	if (!strncmp(dl->ins.name, "add", 3)) {
+		u64 imm_value = -1ULL;
+		int offset;
+		const char *var_name = NULL;
+		struct map_symbol *ms = dloc->ms;
+		u64 ip = ms->sym->start + dl->al.offset;
+
+		if (!has_reg_type(state, dst->reg1))
+			return;
+
+		tsr = &state->regs[dst->reg1];
+
+		if (src->imm)
+			imm_value = src->offset;
+		else if (has_reg_type(state, src->reg1) &&
+			 state->regs[src->reg1].kind == TSR_KIND_CONST)
+			imm_value = state->regs[src->reg1].imm_value;
+		else if (src->reg1 == DWARF_REG_PC) {
+			u64 var_addr = annotate_calc_pcrel(dloc->ms, ip,
+							   src->offset, dl);
+
+			if (get_global_var_info(dloc, var_addr,
+						&var_name, &offset) &&
+			    !strcmp(var_name, "this_cpu_off") &&
+			    tsr->kind == TSR_KIND_CONST) {
+				tsr->kind = TSR_KIND_PERCPU_BASE;
+				imm_value = tsr->imm_value;
+			}
+		}
+		else
+			return;
+
+		if (tsr->kind != TSR_KIND_PERCPU_BASE)
+			return;
+
+		if (get_global_var_type(cu_die, dloc, ip, imm_value, &offset,
+					&type_die) && offset == 0) {
+			/*
+			 * This is not a pointer type, but it should be treated
+			 * as a pointer.
+			 */
+			tsr->type = type_die;
+			tsr->kind = TSR_KIND_POINTER;
+			tsr->ok = true;
+
+			pr_debug_dtp("add [%x] percpu %#"PRIx64" -> reg%d",
+				     insn_offset, imm_value, dst->reg1);
+			pr_debug_type_name(&tsr->type, tsr->kind);
+		}
+		return;
+	}
+
+	if (strncmp(dl->ins.name, "mov", 3))
+		return;
+
+	if (dloc->fb_cfa) {
+		u64 ip = dloc->ms->sym->start + dl->al.offset;
+		u64 pc = map__rip_2objdump(dloc->ms->map, ip);
+
+		if (die_get_cfa(dloc->di->dbg, pc, &fbreg, &fboff) < 0)
+			fbreg = -1;
+	}
+
+	/* Case 1. register to register or segment:offset to register transfers */
+	if (!src->mem_ref && !dst->mem_ref) {
+		if (!has_reg_type(state, dst->reg1))
+			return;
+
+		tsr = &state->regs[dst->reg1];
+		if (map__dso(dloc->ms->map)->kernel &&
+		    src->segment == INSN_SEG_X86_GS && src->imm) {
+			u64 ip = dloc->ms->sym->start + dl->al.offset;
+			u64 var_addr;
+			int offset;
+
+			/*
+			 * In kernel, %gs points to a per-cpu region for the
+			 * current CPU.  Access with a constant offset should
+			 * be treated as a global variable access.
+			 */
+			var_addr = src->offset;
+
+			if (var_addr == 40) {
+				tsr->kind = TSR_KIND_CANARY;
+				tsr->ok = true;
+
+				pr_debug_dtp("mov [%x] stack canary -> reg%d\n",
+					     insn_offset, dst->reg1);
+				return;
+			}
+
+			if (!get_global_var_type(cu_die, dloc, ip, var_addr,
+						 &offset, &type_die) ||
+			    !die_get_member_type(&type_die, offset, &type_die)) {
+				tsr->ok = false;
+				return;
+			}
+
+			tsr->type = type_die;
+			tsr->kind = TSR_KIND_TYPE;
+			tsr->ok = true;
+
+			pr_debug_dtp("mov [%x] this-cpu addr=%#"PRIx64" -> reg%d",
+				     insn_offset, var_addr, dst->reg1);
+			pr_debug_type_name(&tsr->type, tsr->kind);
+			return;
+		}
+
+		if (src->imm) {
+			tsr->kind = TSR_KIND_CONST;
+			tsr->imm_value = src->offset;
+			tsr->ok = true;
+
+			pr_debug_dtp("mov [%x] imm=%#x -> reg%d\n",
+				     insn_offset, tsr->imm_value, dst->reg1);
+			return;
+		}
+
+		if (!has_reg_type(state, src->reg1) ||
+		    !state->regs[src->reg1].ok) {
+			tsr->ok = false;
+			return;
+		}
+
+		tsr->type = state->regs[src->reg1].type;
+		tsr->kind = state->regs[src->reg1].kind;
+		tsr->ok = true;
+
+		pr_debug_dtp("mov [%x] reg%d -> reg%d",
+			     insn_offset, src->reg1, dst->reg1);
+		pr_debug_type_name(&tsr->type, tsr->kind);
+	}
+	/* Case 2. memory to register transers */
+	if (src->mem_ref && !dst->mem_ref) {
+		int sreg = src->reg1;
+
+		if (!has_reg_type(state, dst->reg1))
+			return;
+
+		tsr = &state->regs[dst->reg1];
+
+retry:
+		/* Check stack variables with offset */
+		if (sreg == fbreg) {
+			struct type_state_stack *stack;
+			int offset = src->offset - fboff;
+
+			stack = find_stack_state(state, offset);
+			if (stack == NULL) {
+				tsr->ok = false;
+				return;
+			} else if (!stack->compound) {
+				tsr->type = stack->type;
+				tsr->kind = stack->kind;
+				tsr->ok = true;
+			} else if (die_get_member_type(&stack->type,
+						       offset - stack->offset,
+						       &type_die)) {
+				tsr->type = type_die;
+				tsr->kind = TSR_KIND_TYPE;
+				tsr->ok = true;
+			} else {
+				tsr->ok = false;
+				return;
+			}
+
+			pr_debug_dtp("mov [%x] -%#x(stack) -> reg%d",
+				     insn_offset, -offset, dst->reg1);
+			pr_debug_type_name(&tsr->type, tsr->kind);
+		}
+		/* And then dereference the pointer if it has one */
+		else if (has_reg_type(state, sreg) && state->regs[sreg].ok &&
+			 state->regs[sreg].kind == TSR_KIND_TYPE &&
+			 die_deref_ptr_type(&state->regs[sreg].type,
+					    src->offset, &type_die)) {
+			tsr->type = type_die;
+			tsr->kind = TSR_KIND_TYPE;
+			tsr->ok = true;
+
+			pr_debug_dtp("mov [%x] %#x(reg%d) -> reg%d",
+				     insn_offset, src->offset, sreg, dst->reg1);
+			pr_debug_type_name(&tsr->type, tsr->kind);
+		}
+		/* Or check if it's a global variable */
+		else if (sreg == DWARF_REG_PC) {
+			struct map_symbol *ms = dloc->ms;
+			u64 ip = ms->sym->start + dl->al.offset;
+			u64 addr;
+			int offset;
+
+			addr = annotate_calc_pcrel(ms, ip, src->offset, dl);
+
+			if (!get_global_var_type(cu_die, dloc, ip, addr, &offset,
+						 &type_die) ||
+			    !die_get_member_type(&type_die, offset, &type_die)) {
+				tsr->ok = false;
+				return;
+			}
+
+			tsr->type = type_die;
+			tsr->kind = TSR_KIND_TYPE;
+			tsr->ok = true;
+
+			pr_debug_dtp("mov [%x] global addr=%"PRIx64" -> reg%d",
+				     insn_offset, addr, dst->reg1);
+			pr_debug_type_name(&type_die, tsr->kind);
+		}
+		/* And check percpu access with base register */
+		else if (has_reg_type(state, sreg) &&
+			 state->regs[sreg].kind == TSR_KIND_PERCPU_BASE) {
+			u64 ip = dloc->ms->sym->start + dl->al.offset;
+			int offset;
+
+			/*
+			 * In kernel, %gs points to a per-cpu region for the
+			 * current CPU.  Access with a constant offset should
+			 * be treated as a global variable access.
+			 */
+			if (get_global_var_type(cu_die, dloc, ip, src->offset,
+						&offset, &type_die) &&
+			    die_get_member_type(&type_die, offset, &type_die)) {
+				tsr->type = type_die;
+				tsr->kind = TSR_KIND_TYPE;
+				tsr->ok = true;
+
+				pr_debug_dtp("mov [%x] percpu %#x(reg%d) -> reg%d",
+					     insn_offset, src->offset, sreg, dst->reg1);
+				pr_debug_type_name(&tsr->type, tsr->kind);
+			} else {
+				tsr->ok = false;
+			}
+		}
+		/* And then dereference the calculated pointer if it has one */
+		else if (has_reg_type(state, sreg) && state->regs[sreg].ok &&
+			 state->regs[sreg].kind == TSR_KIND_POINTER &&
+			 die_get_member_type(&state->regs[sreg].type,
+					     src->offset, &type_die)) {
+			tsr->type = type_die;
+			tsr->kind = TSR_KIND_TYPE;
+			tsr->ok = true;
+
+			pr_debug_dtp("mov [%x] pointer %#x(reg%d) -> reg%d",
+				     insn_offset, src->offset, sreg, dst->reg1);
+			pr_debug_type_name(&tsr->type, tsr->kind);
+		}
+		/* Or try another register if any */
+		else if (src->multi_regs && sreg == src->reg1 &&
+			 src->reg1 != src->reg2) {
+			sreg = src->reg2;
+			goto retry;
+		}
+		else {
+			int offset;
+			const char *var_name = NULL;
+
+			/* it might be per-cpu variable (in kernel) access */
+			if (src->offset < 0) {
+				if (get_global_var_info(dloc, (s64)src->offset,
+							&var_name, &offset) &&
+				    !strcmp(var_name, "__per_cpu_offset")) {
+					tsr->kind = TSR_KIND_PERCPU_BASE;
+
+					pr_debug_dtp("mov [%x] percpu base reg%d\n",
+						     insn_offset, dst->reg1);
+				}
+			}
+
+			tsr->ok = false;
+		}
+	}
+	/* Case 3. register to memory transfers */
+	if (!src->mem_ref && dst->mem_ref) {
+		if (!has_reg_type(state, src->reg1) ||
+		    !state->regs[src->reg1].ok)
+			return;
+
+		/* Check stack variables with offset */
+		if (dst->reg1 == fbreg) {
+			struct type_state_stack *stack;
+			int offset = dst->offset - fboff;
+
+			tsr = &state->regs[src->reg1];
+
+			stack = find_stack_state(state, offset);
+			if (stack) {
+				/*
+				 * The source register is likely to hold a type
+				 * of member if it's a compound type.  Do not
+				 * update the stack variable type since we can
+				 * get the member type later by using the
+				 * die_get_member_type().
+				 */
+				if (!stack->compound)
+					set_stack_state(stack, offset, tsr->kind,
+							&tsr->type);
+			} else {
+				findnew_stack_state(state, offset, tsr->kind,
+						    &tsr->type);
+			}
+
+			pr_debug_dtp("mov [%x] reg%d -> -%#x(stack)",
+				     insn_offset, src->reg1, -offset);
+			pr_debug_type_name(&tsr->type, tsr->kind);
+		}
+		/*
+		 * Ignore other transfers since it'd set a value in a struct
+		 * and won't change the type.
+		 */
+	}
+	/* Case 4. memory to memory transfers (not handled for now) */
+}
+
+/**
+ * update_insn_state - Update type state for an instruction
+ * @state: type state table
+ * @dloc: data location info
+ * @cu_die: compile unit debug entry
+ * @dl: disasm line for the instruction
+ *
+ * This function updates the @state table for the target operand of the
+ * instruction at @dl if it transfers the type like MOV on x86.  Since it
+ * tracks the type, it won't care about the values like in arithmetic
+ * instructions like ADD/SUB/MUL/DIV and INC/DEC.
+ *
+ * Note that ops->reg2 is only available when both mem_ref and multi_regs
+ * are true.
+ */
+static void update_insn_state(struct type_state *state, struct data_loc_info *dloc,
+			      Dwarf_Die *cu_die, struct disasm_line *dl)
+{
+	if (arch__is(dloc->arch, "x86"))
+		update_insn_state_x86(state, dloc, cu_die, dl);
+}
+
+/*
+ * Prepend this_blocks (from the outer scope) to full_blocks, removing
+ * duplicate disasm line.
+ */
+static void prepend_basic_blocks(struct list_head *this_blocks,
+				 struct list_head *full_blocks)
+{
+	struct annotated_basic_block *first_bb, *last_bb;
+
+	last_bb = list_last_entry(this_blocks, typeof(*last_bb), list);
+	first_bb = list_first_entry(full_blocks, typeof(*first_bb), list);
+
+	if (list_empty(full_blocks))
+		goto out;
+
+	/* Last insn in this_blocks should be same as first insn in full_blocks */
+	if (last_bb->end != first_bb->begin) {
+		pr_debug("prepend basic blocks: mismatched disasm line %"PRIx64" -> %"PRIx64"\n",
+			 last_bb->end->al.offset, first_bb->begin->al.offset);
+		goto out;
+	}
+
+	/* Is the basic block have only one disasm_line? */
+	if (last_bb->begin == last_bb->end) {
+		list_del(&last_bb->list);
+		free(last_bb);
+		goto out;
+	}
+
+	/* Point to the insn before the last when adding this block to full_blocks */
+	last_bb->end = list_prev_entry(last_bb->end, al.node);
+
+out:
+	list_splice(this_blocks, full_blocks);
+}
+
+static void delete_basic_blocks(struct list_head *basic_blocks)
+{
+	struct annotated_basic_block *bb, *tmp;
+
+	list_for_each_entry_safe(bb, tmp, basic_blocks, list) {
+		list_del(&bb->list);
+		free(bb);
+	}
+}
+
+/* Make sure all variables have a valid start address */
+static void fixup_var_address(struct die_var_type *var_types, u64 addr)
+{
+	while (var_types) {
+		/*
+		 * Some variables have no address range meaning it's always
+		 * available in the whole scope.  Let's adjust the start
+		 * address to the start of the scope.
+		 */
+		if (var_types->addr == 0)
+			var_types->addr = addr;
+
+		var_types = var_types->next;
+	}
+}
+
+static void delete_var_types(struct die_var_type *var_types)
+{
+	while (var_types) {
+		struct die_var_type *next = var_types->next;
+
+		free(var_types);
+		var_types = next;
+	}
+}
+
+/* should match to is_stack_canary() in util/annotate.c */
+static void setup_stack_canary(struct data_loc_info *dloc)
+{
+	if (arch__is(dloc->arch, "x86")) {
+		dloc->op->segment = INSN_SEG_X86_GS;
+		dloc->op->imm = true;
+		dloc->op->offset = 40;
+	}
+}
+
+/*
+ * It's at the target address, check if it has a matching type.
+ * It returns 1 if found, 0 if not or -1 if not found but no need to
+ * repeat the search.  The last case is for per-cpu variables which
+ * are similar to global variables and no additional info is needed.
+ */
+static int check_matching_type(struct type_state *state,
+			       struct data_loc_info *dloc, int reg,
+			       Dwarf_Die *cu_die, Dwarf_Die *type_die)
+{
+	Dwarf_Word size;
+	u32 insn_offset = dloc->ip - dloc->ms->sym->start;
+
+	pr_debug_dtp("chk [%x] reg%d offset=%#x ok=%d kind=%d",
+		     insn_offset, reg, dloc->op->offset,
+		     state->regs[reg].ok, state->regs[reg].kind);
+
+	if (state->regs[reg].ok && state->regs[reg].kind == TSR_KIND_TYPE) {
+		int tag = dwarf_tag(&state->regs[reg].type);
+
+		pr_debug_dtp("\n");
+
+		/*
+		 * Normal registers should hold a pointer (or array) to
+		 * dereference a memory location.
+		 */
+		if (tag != DW_TAG_pointer_type && tag != DW_TAG_array_type)
+			return -1;
+
+		/* Remove the pointer and get the target type */
+		if (die_get_real_type(&state->regs[reg].type, type_die) == NULL)
+			return -1;
+
+		dloc->type_offset = dloc->op->offset;
+
+		/* Get the size of the actual type */
+		if (dwarf_aggregate_size(type_die, &size) < 0 ||
+		    (unsigned)dloc->type_offset >= size)
+			return -1;
+
+		return 1;
+	}
+
+	if (reg == dloc->fbreg) {
+		struct type_state_stack *stack;
+
+		pr_debug_dtp(" fbreg\n");
+
+		stack = find_stack_state(state, dloc->type_offset);
+		if (stack == NULL)
+			return 0;
+
+		if (stack->kind == TSR_KIND_CANARY) {
+			setup_stack_canary(dloc);
+			return -1;
+		}
+
+		*type_die = stack->type;
+		/* Update the type offset from the start of slot */
+		dloc->type_offset -= stack->offset;
+
+		return 1;
+	}
+
+	if (dloc->fb_cfa) {
+		struct type_state_stack *stack;
+		u64 pc = map__rip_2objdump(dloc->ms->map, dloc->ip);
+		int fbreg, fboff;
+
+		pr_debug_dtp(" cfa\n");
+
+		if (die_get_cfa(dloc->di->dbg, pc, &fbreg, &fboff) < 0)
+			fbreg = -1;
+
+		if (reg != fbreg)
+			return 0;
+
+		stack = find_stack_state(state, dloc->type_offset - fboff);
+		if (stack == NULL)
+			return 0;
+
+		if (stack->kind == TSR_KIND_CANARY) {
+			setup_stack_canary(dloc);
+			return -1;
+		}
+
+		*type_die = stack->type;
+		/* Update the type offset from the start of slot */
+		dloc->type_offset -= fboff + stack->offset;
+
+		return 1;
+	}
+
+	if (state->regs[reg].kind == TSR_KIND_PERCPU_BASE) {
+		u64 var_addr = dloc->op->offset;
+		int var_offset;
+
+		pr_debug_dtp(" percpu var\n");
+
+		if (get_global_var_type(cu_die, dloc, dloc->ip, var_addr,
+					&var_offset, type_die)) {
+			dloc->type_offset = var_offset;
+			return 1;
+		}
+		/* No need to retry per-cpu (global) variables */
+		return -1;
+	}
+
+	if (state->regs[reg].ok && state->regs[reg].kind == TSR_KIND_POINTER) {
+		pr_debug_dtp(" percpu ptr\n");
+
+		/*
+		 * It's actaully pointer but the address was calculated using
+		 * some arithmetic.  So it points to the actual type already.
+		 */
+		*type_die = state->regs[reg].type;
+
+		dloc->type_offset = dloc->op->offset;
+
+		/* Get the size of the actual type */
+		if (dwarf_aggregate_size(type_die, &size) < 0 ||
+		    (unsigned)dloc->type_offset >= size)
+			return -1;
+
+		return 1;
+	}
+
+	if (state->regs[reg].ok && state->regs[reg].kind == TSR_KIND_CANARY) {
+		pr_debug_dtp(" stack canary\n");
+
+		/*
+		 * This is a saved value of the stack canary which will be handled
+		 * in the outer logic when it returns failure here.  Pretend it's
+		 * from the stack canary directly.
+		 */
+		setup_stack_canary(dloc);
+
+		return -1;
+	}
+
+	if (map__dso(dloc->ms->map)->kernel && arch__is(dloc->arch, "x86")) {
+		u64 addr;
+		int offset;
+
+		/* Direct this-cpu access like "%gs:0x34740" */
+		if (dloc->op->segment == INSN_SEG_X86_GS && dloc->op->imm) {
+			pr_debug_dtp(" this-cpu var\n");
+
+			addr = dloc->op->offset;
+
+			if (get_global_var_type(cu_die, dloc, dloc->ip, addr,
+						&offset, type_die)) {
+				dloc->type_offset = offset;
+				return 1;
+			}
+			return -1;
+		}
+
+		/* Access to per-cpu base like "-0x7dcf0500(,%rdx,8)" */
+		if (dloc->op->offset < 0 && reg != state->stack_reg) {
+			const char *var_name = NULL;
+
+			addr = (s64) dloc->op->offset;
+
+			if (get_global_var_info(dloc, addr, &var_name, &offset) &&
+			    !strcmp(var_name, "__per_cpu_offset") && offset == 0 &&
+			    get_global_var_type(cu_die, dloc, dloc->ip, addr,
+						&offset, type_die)) {
+				pr_debug_dtp(" percpu base\n");
+
+				dloc->type_offset = offset;
+				return 1;
+			}
+			pr_debug_dtp(" negative offset\n");
+			return -1;
+		}
+	}
+
+	pr_debug_dtp("\n");
+	return 0;
+}
+
+/* Iterate instructions in basic blocks and update type table */
+static int find_data_type_insn(struct data_loc_info *dloc, int reg,
+			       struct list_head *basic_blocks,
+			       struct die_var_type *var_types,
+			       Dwarf_Die *cu_die, Dwarf_Die *type_die)
+{
+	struct type_state state;
+	struct symbol *sym = dloc->ms->sym;
+	struct annotation *notes = symbol__annotation(sym);
+	struct annotated_basic_block *bb;
+	int ret = 0;
+
+	init_type_state(&state, dloc->arch);
+
+	list_for_each_entry(bb, basic_blocks, list) {
+		struct disasm_line *dl = bb->begin;
+
+		BUG_ON(bb->begin->al.offset == -1 || bb->end->al.offset == -1);
+
+		pr_debug_dtp("bb: [%"PRIx64" - %"PRIx64"]\n",
+			     bb->begin->al.offset, bb->end->al.offset);
+
+		list_for_each_entry_from(dl, &notes->src->source, al.node) {
+			u64 this_ip = sym->start + dl->al.offset;
+			u64 addr = map__rip_2objdump(dloc->ms->map, this_ip);
+
+			/* Skip comment or debug info lines */
+			if (dl->al.offset == -1)
+				continue;
+
+			/* Update variable type at this address */
+			update_var_state(&state, dloc, addr, dl->al.offset, var_types);
+
+			if (this_ip == dloc->ip) {
+				ret = check_matching_type(&state, dloc, reg,
+							  cu_die, type_die);
+				goto out;
+			}
+
+			/* Update type table after processing the instruction */
+			update_insn_state(&state, dloc, cu_die, dl);
+			if (dl == bb->end)
+				break;
+		}
+	}
+
+out:
+	exit_type_state(&state);
+	return ret;
+}
+
+/*
+ * Construct a list of basic blocks for each scope with variables and try to find
+ * the data type by updating a type state table through instructions.
+ */
+static int find_data_type_block(struct data_loc_info *dloc, int reg,
+				Dwarf_Die *cu_die, Dwarf_Die *scopes,
+				int nr_scopes, Dwarf_Die *type_die)
+{
+	LIST_HEAD(basic_blocks);
+	struct die_var_type *var_types = NULL;
+	u64 src_ip, dst_ip, prev_dst_ip;
+	int ret = -1;
+
+	/* TODO: other architecture support */
+	if (!arch__is(dloc->arch, "x86"))
+		return -1;
+
+	prev_dst_ip = dst_ip = dloc->ip;
+	for (int i = nr_scopes - 1; i >= 0; i--) {
+		Dwarf_Addr base, start, end;
+		LIST_HEAD(this_blocks);
+		int found;
+
+		if (dwarf_ranges(&scopes[i], 0, &base, &start, &end) < 0)
+			break;
+
+		pr_debug_dtp("scope: [%d/%d] (die:%lx)\n",
+			     i + 1, nr_scopes, (long)dwarf_dieoffset(&scopes[i]));
+		src_ip = map__objdump_2rip(dloc->ms->map, start);
+
+again:
+		/* Get basic blocks for this scope */
+		if (annotate_get_basic_blocks(dloc->ms->sym, src_ip, dst_ip,
+					      &this_blocks) < 0) {
+			/* Try previous block if they are not connected */
+			if (prev_dst_ip != dst_ip) {
+				dst_ip = prev_dst_ip;
+				goto again;
+			}
+
+			pr_debug_dtp("cannot find a basic block from %"PRIx64" to %"PRIx64"\n",
+				     src_ip - dloc->ms->sym->start,
+				     dst_ip - dloc->ms->sym->start);
+			continue;
+		}
+		prepend_basic_blocks(&this_blocks, &basic_blocks);
+
+		/* Get variable info for this scope and add to var_types list */
+		die_collect_vars(&scopes[i], &var_types);
+		fixup_var_address(var_types, start);
+
+		/* Find from start of this scope to the target instruction */
+		found = find_data_type_insn(dloc, reg, &basic_blocks, var_types,
+					    cu_die, type_die);
+		if (found > 0) {
+			pr_debug_dtp("found by insn track: %#x(reg%d) type-offset=%#x\n",
+				     dloc->op->offset, reg, dloc->type_offset);
+			pr_debug_type_name(type_die, TSR_KIND_TYPE);
+			ret = 0;
+			break;
+		}
+
+		if (found < 0)
+			break;
+
+		/* Go up to the next scope and find blocks to the start */
+		prev_dst_ip = dst_ip;
+		dst_ip = src_ip;
+	}
+
+	delete_basic_blocks(&basic_blocks);
+	delete_var_types(var_types);
+	return ret;
+}
+
 /* The result will be saved in @type_die */
-static int find_data_type_die(struct debuginfo *di, u64 pc, u64 addr,
-			      const char *var_name, struct annotated_op_loc *loc,
-			      Dwarf_Die *type_die)
+static int find_data_type_die(struct data_loc_info *dloc, Dwarf_Die *type_die)
 {
+	struct annotated_op_loc *loc = dloc->op;
 	Dwarf_Die cu_die, var_die;
 	Dwarf_Die *scopes = NULL;
 	int reg, offset;
 	int ret = -1;
 	int i, nr_scopes;
 	int fbreg = -1;
-	bool is_fbreg = false;
 	int fb_offset = 0;
+	bool is_fbreg = false;
+	u64 pc;
+	char buf[64];
+
+	if (dloc->op->multi_regs)
+		snprintf(buf, sizeof(buf), "reg%d, reg%d", dloc->op->reg1, dloc->op->reg2);
+	else if (dloc->op->reg1 == DWARF_REG_PC)
+		snprintf(buf, sizeof(buf), "PC");
+	else
+		snprintf(buf, sizeof(buf), "reg%d", dloc->op->reg1);
+
+	pr_debug_dtp("-----------------------------------------------------------\n");
+	pr_debug_dtp("find data type for %#x(%s) at %s+%#"PRIx64"\n",
+		     dloc->op->offset, buf, dloc->ms->sym->name,
+		     dloc->ip - dloc->ms->sym->start);
+
+	/*
+	 * IP is a relative instruction address from the start of the map, as
+	 * it can be randomized/relocated, it needs to translate to PC which is
+	 * a file address for DWARF processing.
+	 */
+	pc = map__rip_2objdump(dloc->ms->map, dloc->ip);
 
 	/* Get a compile_unit for this address */
-	if (!find_cu_die(di, pc, &cu_die)) {
-		pr_debug("cannot find CU for address %" PRIx64 "\n", pc);
+	if (!find_cu_die(dloc->di, pc, &cu_die)) {
+		pr_debug_dtp("cannot find CU for address %"PRIx64"\n", pc);
 		ann_data_stat.no_cuinfo++;
 		return -1;
 	}
@@ -262,19 +1535,18 @@ static int find_data_type_die(struct debuginfo *di, u64 pc, u64 addr,
 	reg = loc->reg1;
 	offset = loc->offset;
 
-	if (reg == DWARF_REG_PC) {
-		if (die_find_variable_by_addr(&cu_die, pc, addr, &var_die, &offset)) {
-			ret = check_variable(&var_die, type_die, offset,
-					     /*is_pointer=*/false);
-			loc->offset = offset;
-			goto out;
-		}
+	pr_debug_dtp("CU for %s (die:%#lx)\n",
+		     dwarf_diename(&cu_die), (long)dwarf_dieoffset(&cu_die));
 
-		if (var_name && die_find_variable_at(&cu_die, var_name, pc,
-						     &var_die)) {
-			ret = check_variable(&var_die, type_die, 0,
-					     /*is_pointer=*/false);
-			/* loc->offset will be updated by the caller */
+	if (reg == DWARF_REG_PC) {
+		if (get_global_var_type(&cu_die, dloc, dloc->ip, dloc->var_addr,
+					&offset, type_die)) {
+			dloc->type_offset = offset;
+
+			pr_debug_dtp("found by addr=%#"PRIx64" type_offset=%#x\n",
+				     dloc->var_addr, offset);
+			pr_debug_type_name(type_die, TSR_KIND_TYPE);
+			ret = 0;
 			goto out;
 		}
 	}
@@ -291,16 +1563,20 @@ static int find_data_type_die(struct debuginfo *di, u64 pc, u64 addr,
 		    dwarf_formblock(&attr, &block) == 0 && block.length == 1) {
 			switch (*block.data) {
 			case DW_OP_reg0 ... DW_OP_reg31:
-				fbreg = *block.data - DW_OP_reg0;
+				fbreg = dloc->fbreg = *block.data - DW_OP_reg0;
 				break;
 			case DW_OP_call_frame_cfa:
-				if (die_get_cfa(di->dbg, pc, &fbreg,
+				dloc->fb_cfa = true;
+				if (die_get_cfa(dloc->di->dbg, pc, &fbreg,
 						&fb_offset) < 0)
 					fbreg = -1;
 				break;
 			default:
 				break;
 			}
+
+			pr_debug_dtp("frame base: cfa=%d fbreg=%d\n",
+				     dloc->fb_cfa, fbreg);
 		}
 	}
 
@@ -312,7 +1588,7 @@ retry:
 	/* Search from the inner-most scope to the outer */
 	for (i = nr_scopes - 1; i >= 0; i--) {
 		if (reg == DWARF_REG_PC) {
-			if (!die_find_variable_by_addr(&scopes[i], pc, addr,
+			if (!die_find_variable_by_addr(&scopes[i], dloc->var_addr,
 						       &var_die, &offset))
 				continue;
 		} else {
@@ -323,19 +1599,51 @@ retry:
 		}
 
 		/* Found a variable, see if it's correct */
-		ret = check_variable(&var_die, type_die, offset,
-				     reg != DWARF_REG_PC && !is_fbreg);
-		loc->offset = offset;
+		ret = check_variable(dloc, &var_die, type_die, reg, offset, is_fbreg);
+		if (ret == 0) {
+			pr_debug_dtp("found \"%s\" in scope=%d/%d (die: %#lx) ",
+				     dwarf_diename(&var_die), i+1, nr_scopes,
+				     (long)dwarf_dieoffset(&scopes[i]));
+			if (reg == DWARF_REG_PC) {
+				pr_debug_dtp("addr=%#"PRIx64" type_offset=%#x\n",
+					     dloc->var_addr, offset);
+			} else if (reg == DWARF_REG_FB || is_fbreg) {
+				pr_debug_dtp("stack_offset=%#x type_offset=%#x\n",
+					     fb_offset, offset);
+			} else {
+				pr_debug_dtp("type_offset=%#x\n", offset);
+			}
+			pr_debug_location(&var_die, pc, reg);
+			pr_debug_type_name(type_die, TSR_KIND_TYPE);
+		} else {
+			pr_debug_dtp("check variable \"%s\" failed (die: %#lx)\n",
+				     dwarf_diename(&var_die),
+				     (long)dwarf_dieoffset(&var_die));
+			pr_debug_location(&var_die, pc, reg);
+			pr_debug_type_name(type_die, TSR_KIND_TYPE);
+		}
+		dloc->type_offset = offset;
 		goto out;
 	}
 
+	if (reg != DWARF_REG_PC) {
+		ret = find_data_type_block(dloc, reg, &cu_die, scopes,
+					   nr_scopes, type_die);
+		if (ret == 0) {
+			ann_data_stat.insn_track++;
+			goto out;
+		}
+	}
+
 	if (loc->multi_regs && reg == loc->reg1 && loc->reg1 != loc->reg2) {
 		reg = loc->reg2;
 		goto retry;
 	}
 
-	if (ret < 0)
+	if (ret < 0) {
+		pr_debug_dtp("no variable found\n");
 		ann_data_stat.no_var++;
+	}
 
 out:
 	free(scopes);
@@ -344,50 +1652,45 @@ out:
 
 /**
  * find_data_type - Return a data type at the location
- * @ms: map and symbol at the location
- * @ip: instruction address of the memory access
- * @loc: instruction operand location
- * @addr: data address of the memory access
- * @var_name: global variable name
+ * @dloc: data location
  *
  * This functions searches the debug information of the binary to get the data
- * type it accesses.  The exact location is expressed by (@ip, reg, offset)
- * for pointer variables or (@ip, @addr) for global variables.  Note that global
- * variables might update the @loc->offset after finding the start of the variable.
- * If it cannot find a global variable by address, it tried to fine a declaration
- * of the variable using @var_name.  In that case, @loc->offset won't be updated.
+ * type it accesses.  The exact location is expressed by (ip, reg, offset)
+ * for pointer variables or (ip, addr) for global variables.  Note that global
+ * variables might update the @dloc->type_offset after finding the start of the
+ * variable.  If it cannot find a global variable by address, it tried to find
+ * a declaration of the variable using var_name.  In that case, @dloc->offset
+ * won't be updated.
  *
  * It return %NULL if not found.
  */
-struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
-					   struct annotated_op_loc *loc, u64 addr,
-					   const char *var_name)
+struct annotated_data_type *find_data_type(struct data_loc_info *dloc)
 {
 	struct annotated_data_type *result = NULL;
-	struct dso *dso = map__dso(ms->map);
-	struct debuginfo *di;
+	struct dso *dso = map__dso(dloc->ms->map);
 	Dwarf_Die type_die;
-	u64 pc;
 
-	di = debuginfo__new(dso->long_name);
-	if (di == NULL) {
-		pr_debug("cannot get the debug info\n");
+	dloc->di = debuginfo__new(dso->long_name);
+	if (dloc->di == NULL) {
+		pr_debug_dtp("cannot get the debug info\n");
 		return NULL;
 	}
 
 	/*
-	 * IP is a relative instruction address from the start of the map, as
-	 * it can be randomized/relocated, it needs to translate to PC which is
-	 * a file address for DWARF processing.
+	 * The type offset is the same as instruction offset by default.
+	 * But when finding a global variable, the offset won't be valid.
 	 */
-	pc = map__rip_2objdump(ms->map, ip);
-	if (find_data_type_die(di, pc, addr, var_name, loc, &type_die) < 0)
+	dloc->type_offset = dloc->op->offset;
+
+	dloc->fbreg = -1;
+
+	if (find_data_type_die(dloc, &type_die) < 0)
 		goto out;
 
 	result = dso__findnew_data_type(dso, &type_die);
 
 out:
-	debuginfo__delete(di);
+	debuginfo__delete(dloc->di);
 	return result;
 }
 
@@ -484,3 +1787,115 @@ int annotated_data_type__update_samples(struct annotated_data_type *adt,
 	h->addr[offset].period += period;
 	return 0;
 }
+
+static void print_annotated_data_header(struct hist_entry *he, struct evsel *evsel)
+{
+	struct dso *dso = map__dso(he->ms.map);
+	int nr_members = 1;
+	int nr_samples = he->stat.nr_events;
+	int width = 7;
+	const char *val_hdr = "Percent";
+
+	if (evsel__is_group_event(evsel)) {
+		struct hist_entry *pair;
+
+		list_for_each_entry(pair, &he->pairs.head, pairs.node)
+			nr_samples += pair->stat.nr_events;
+	}
+
+	printf("Annotate type: '%s' in %s (%d samples):\n",
+	       he->mem_type->self.type_name, dso->name, nr_samples);
+
+	if (evsel__is_group_event(evsel)) {
+		struct evsel *pos;
+		int i = 0;
+
+		for_each_group_evsel(pos, evsel)
+			printf(" event[%d] = %s\n", i++, pos->name);
+
+		nr_members = evsel->core.nr_members;
+	}
+
+	if (symbol_conf.show_total_period) {
+		width = 11;
+		val_hdr = "Period";
+	} else if (symbol_conf.show_nr_samples) {
+		width = 7;
+		val_hdr = "Samples";
+	}
+
+	printf("============================================================================\n");
+	printf("%*s %10s %10s  %s\n", (width + 1) * nr_members, val_hdr,
+	       "offset", "size", "field");
+}
+
+static void print_annotated_data_value(struct type_hist *h, u64 period, int nr_samples)
+{
+	double percent = h->period ? (100.0 * period / h->period) : 0;
+	const char *color = get_percent_color(percent);
+
+	if (symbol_conf.show_total_period)
+		color_fprintf(stdout, color, " %11" PRIu64, period);
+	else if (symbol_conf.show_nr_samples)
+		color_fprintf(stdout, color, " %7d", nr_samples);
+	else
+		color_fprintf(stdout, color, " %7.2f", percent);
+}
+
+static void print_annotated_data_type(struct annotated_data_type *mem_type,
+				      struct annotated_member *member,
+				      struct evsel *evsel, int indent)
+{
+	struct annotated_member *child;
+	struct type_hist *h = mem_type->histograms[evsel->core.idx];
+	int i, nr_events = 1, samples = 0;
+	u64 period = 0;
+	int width = symbol_conf.show_total_period ? 11 : 7;
+
+	for (i = 0; i < member->size; i++) {
+		samples += h->addr[member->offset + i].nr_samples;
+		period += h->addr[member->offset + i].period;
+	}
+	print_annotated_data_value(h, period, samples);
+
+	if (evsel__is_group_event(evsel)) {
+		struct evsel *pos;
+
+		for_each_group_member(pos, evsel) {
+			h = mem_type->histograms[pos->core.idx];
+
+			samples = 0;
+			period = 0;
+			for (i = 0; i < member->size; i++) {
+				samples += h->addr[member->offset + i].nr_samples;
+				period += h->addr[member->offset + i].period;
+			}
+			print_annotated_data_value(h, period, samples);
+		}
+		nr_events = evsel->core.nr_members;
+	}
+
+	printf(" %10d %10d  %*s%s\t%s",
+	       member->offset, member->size, indent, "", member->type_name,
+	       member->var_name ?: "");
+
+	if (!list_empty(&member->children))
+		printf(" {\n");
+
+	list_for_each_entry(child, &member->children, node)
+		print_annotated_data_type(mem_type, child, evsel, indent + 4);
+
+	if (!list_empty(&member->children))
+		printf("%*s}", (width + 1) * nr_events + 24 + indent, "");
+	printf(";\n");
+}
+
+int hist_entry__annotate_data_tty(struct hist_entry *he, struct evsel *evsel)
+{
+	print_annotated_data_header(he, evsel);
+	print_annotated_data_type(he->mem_type, &he->mem_type->self, evsel, 0);
+	printf("\n");
+
+	/* move to the next entry */
+	return '>';
+}
diff --git a/tools/perf/util/annotate-data.h b/tools/perf/util/annotate-data.h
index 1b0db8e8c40e6b..0a57d9f5ee7812 100644
--- a/tools/perf/util/annotate-data.h
+++ b/tools/perf/util/annotate-data.h
@@ -8,8 +8,12 @@
 #include <linux/types.h>
 
 struct annotated_op_loc;
+struct debuginfo;
 struct evsel;
+struct hist_browser_timer;
+struct hist_entry;
 struct map_symbol;
+struct thread;
 
 /**
  * struct annotated_member - Type of member field
@@ -71,6 +75,40 @@ struct annotated_data_type {
 
 extern struct annotated_data_type unknown_type;
 extern struct annotated_data_type stackop_type;
+extern struct annotated_data_type canary_type;
+
+/**
+ * struct data_loc_info - Data location information
+ * @arch: CPU architecture info
+ * @thread: Thread info
+ * @ms: Map and Symbol info
+ * @ip: Instruction address
+ * @var_addr: Data address (for global variables)
+ * @cpumode: CPU execution mode
+ * @op: Instruction operand location (regs and offset)
+ * @di: Debug info
+ * @fbreg: Frame base register
+ * @fb_cfa: Whether the frame needs to check CFA
+ * @type_offset: Final offset in the type
+ */
+struct data_loc_info {
+	/* These are input field, should be filled by caller */
+	struct arch *arch;
+	struct thread *thread;
+	struct map_symbol *ms;
+	u64 ip;
+	u64 var_addr;
+	u8 cpumode;
+	struct annotated_op_loc *op;
+
+	/* These are used internally */
+	struct debuginfo *di;
+	int fbreg;
+	bool fb_cfa;
+
+	/* This is for the result */
+	int type_offset;
+};
 
 /**
  * struct annotated_data_stat - Debug statistics
@@ -100,15 +138,14 @@ struct annotated_data_stat {
 	int no_typeinfo;
 	int invalid_size;
 	int bad_offset;
+	int insn_track;
 };
 extern struct annotated_data_stat ann_data_stat;
 
 #ifdef HAVE_DWARF_SUPPORT
 
 /* Returns data type at the location (ip, reg, offset) */
-struct annotated_data_type *find_data_type(struct map_symbol *ms, u64 ip,
-					   struct annotated_op_loc *loc, u64 addr,
-					   const char *var_name);
+struct annotated_data_type *find_data_type(struct data_loc_info *dloc);
 
 /* Update type access histogram at the given offset */
 int annotated_data_type__update_samples(struct annotated_data_type *adt,
@@ -118,12 +155,15 @@ int annotated_data_type__update_samples(struct annotated_data_type *adt,
 /* Release all data type information in the tree */
 void annotated_data_type__tree_delete(struct rb_root *root);
 
+/* Release all global variable information in the tree */
+void global_var_type__tree_delete(struct rb_root *root);
+
+int hist_entry__annotate_data_tty(struct hist_entry *he, struct evsel *evsel);
+
 #else /* HAVE_DWARF_SUPPORT */
 
 static inline struct annotated_data_type *
-find_data_type(struct map_symbol *ms __maybe_unused, u64 ip __maybe_unused,
-	       struct annotated_op_loc *loc __maybe_unused,
-	       u64 addr __maybe_unused, const char *var_name __maybe_unused)
+find_data_type(struct data_loc_info *dloc __maybe_unused)
 {
 	return NULL;
 }
@@ -142,6 +182,28 @@ static inline void annotated_data_type__tree_delete(struct rb_root *root __maybe
 {
 }
 
+static inline void global_var_type__tree_delete(struct rb_root *root __maybe_unused)
+{
+}
+
+static inline int hist_entry__annotate_data_tty(struct hist_entry *he __maybe_unused,
+						struct evsel *evsel __maybe_unused)
+{
+	return -1;
+}
+
 #endif /* HAVE_DWARF_SUPPORT */
 
+#ifdef HAVE_SLANG_SUPPORT
+int hist_entry__annotate_data_tui(struct hist_entry *he, struct evsel *evsel,
+				  struct hist_browser_timer *hbt);
+#else
+static inline int hist_entry__annotate_data_tui(struct hist_entry *he __maybe_unused,
+						struct evsel *evsel __maybe_unused,
+						struct hist_browser_timer *hbt __maybe_unused)
+{
+	return -1;
+}
+#endif /* HAVE_SLANG_SUPPORT */
+
 #endif /* _PERF_ANNOTATE_DATA_H */
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 50ca92255ff62a..f5b6b5e5e7571e 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -16,6 +16,7 @@
 #include "build-id.h"
 #include "color.h"
 #include "config.h"
+#include "disasm.h"
 #include "dso.h"
 #include "env.h"
 #include "map.h"
@@ -64,47 +65,6 @@
 /* global annotation options */
 struct annotation_options annotate_opts;
 
-static regex_t	 file_lineno;
-
-static struct ins_ops *ins__find(struct arch *arch, const char *name);
-static void ins__sort(struct arch *arch);
-static int disasm_line__parse(char *line, const char **namep, char **rawp);
-static int call__scnprintf(struct ins *ins, char *bf, size_t size,
-			  struct ins_operands *ops, int max_ins_name);
-static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
-			  struct ins_operands *ops, int max_ins_name);
-
-struct arch {
-	const char	*name;
-	struct ins	*instructions;
-	size_t		nr_instructions;
-	size_t		nr_instructions_allocated;
-	struct ins_ops  *(*associate_instruction_ops)(struct arch *arch, const char *name);
-	bool		sorted_instructions;
-	bool		initialized;
-	const char	*insn_suffix;
-	void		*priv;
-	unsigned int	model;
-	unsigned int	family;
-	int		(*init)(struct arch *arch, char *cpuid);
-	bool		(*ins_is_fused)(struct arch *arch, const char *ins1,
-					const char *ins2);
-	struct		{
-		char comment_char;
-		char skip_functions_char;
-		char register_char;
-		char memory_ref_char;
-	} objdump;
-};
-
-static struct ins_ops call_ops;
-static struct ins_ops dec_ops;
-static struct ins_ops jump_ops;
-static struct ins_ops mov_ops;
-static struct ins_ops nop_ops;
-static struct ins_ops lock_ops;
-static struct ins_ops ret_ops;
-
 /* Data type collection debug statistics */
 struct annotated_data_stat ann_data_stat;
 LIST_HEAD(ann_insn_stat);
@@ -117,753 +77,13 @@ struct annotated_data_type stackop_type = {
 	},
 };
 
-static int arch__grow_instructions(struct arch *arch)
-{
-	struct ins *new_instructions;
-	size_t new_nr_allocated;
-
-	if (arch->nr_instructions_allocated == 0 && arch->instructions)
-		goto grow_from_non_allocated_table;
-
-	new_nr_allocated = arch->nr_instructions_allocated + 128;
-	new_instructions = realloc(arch->instructions, new_nr_allocated * sizeof(struct ins));
-	if (new_instructions == NULL)
-		return -1;
-
-out_update_instructions:
-	arch->instructions = new_instructions;
-	arch->nr_instructions_allocated = new_nr_allocated;
-	return 0;
-
-grow_from_non_allocated_table:
-	new_nr_allocated = arch->nr_instructions + 128;
-	new_instructions = calloc(new_nr_allocated, sizeof(struct ins));
-	if (new_instructions == NULL)
-		return -1;
-
-	memcpy(new_instructions, arch->instructions, arch->nr_instructions);
-	goto out_update_instructions;
-}
-
-static int arch__associate_ins_ops(struct arch* arch, const char *name, struct ins_ops *ops)
-{
-	struct ins *ins;
-
-	if (arch->nr_instructions == arch->nr_instructions_allocated &&
-	    arch__grow_instructions(arch))
-		return -1;
-
-	ins = &arch->instructions[arch->nr_instructions];
-	ins->name = strdup(name);
-	if (!ins->name)
-		return -1;
-
-	ins->ops  = ops;
-	arch->nr_instructions++;
-
-	ins__sort(arch);
-	return 0;
-}
-
-#include "arch/arc/annotate/instructions.c"
-#include "arch/arm/annotate/instructions.c"
-#include "arch/arm64/annotate/instructions.c"
-#include "arch/csky/annotate/instructions.c"
-#include "arch/loongarch/annotate/instructions.c"
-#include "arch/mips/annotate/instructions.c"
-#include "arch/x86/annotate/instructions.c"
-#include "arch/powerpc/annotate/instructions.c"
-#include "arch/riscv64/annotate/instructions.c"
-#include "arch/s390/annotate/instructions.c"
-#include "arch/sparc/annotate/instructions.c"
-
-static struct arch architectures[] = {
-	{
-		.name = "arc",
-		.init = arc__annotate_init,
-	},
-	{
-		.name = "arm",
-		.init = arm__annotate_init,
-	},
-	{
-		.name = "arm64",
-		.init = arm64__annotate_init,
-	},
-	{
-		.name = "csky",
-		.init = csky__annotate_init,
-	},
-	{
-		.name = "mips",
-		.init = mips__annotate_init,
-		.objdump = {
-			.comment_char = '#',
-		},
-	},
-	{
-		.name = "x86",
-		.init = x86__annotate_init,
-		.instructions = x86__instructions,
-		.nr_instructions = ARRAY_SIZE(x86__instructions),
-		.insn_suffix = "bwlq",
-		.objdump =  {
-			.comment_char = '#',
-			.register_char = '%',
-			.memory_ref_char = '(',
-		},
-	},
-	{
-		.name = "powerpc",
-		.init = powerpc__annotate_init,
-	},
-	{
-		.name = "riscv64",
-		.init = riscv64__annotate_init,
-	},
-	{
-		.name = "s390",
-		.init = s390__annotate_init,
-		.objdump =  {
-			.comment_char = '#',
-		},
-	},
-	{
-		.name = "sparc",
-		.init = sparc__annotate_init,
-		.objdump = {
-			.comment_char = '#',
-		},
-	},
-	{
-		.name = "loongarch",
-		.init = loongarch__annotate_init,
-		.objdump = {
-			.comment_char = '#',
-		},
+struct annotated_data_type canary_type = {
+	.self = {
+		.type_name = (char *)"(stack canary)",
+		.children = LIST_HEAD_INIT(canary_type.self.children),
 	},
 };
 
-static void ins__delete(struct ins_operands *ops)
-{
-	if (ops == NULL)
-		return;
-	zfree(&ops->source.raw);
-	zfree(&ops->source.name);
-	zfree(&ops->target.raw);
-	zfree(&ops->target.name);
-}
-
-static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size,
-			      struct ins_operands *ops, int max_ins_name)
-{
-	return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->raw);
-}
-
-int ins__scnprintf(struct ins *ins, char *bf, size_t size,
-		   struct ins_operands *ops, int max_ins_name)
-{
-	if (ins->ops->scnprintf)
-		return ins->ops->scnprintf(ins, bf, size, ops, max_ins_name);
-
-	return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
-}
-
-bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2)
-{
-	if (!arch || !arch->ins_is_fused)
-		return false;
-
-	return arch->ins_is_fused(arch, ins1, ins2);
-}
-
-static int call__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
-{
-	char *endptr, *tok, *name;
-	struct map *map = ms->map;
-	struct addr_map_symbol target = {
-		.ms = { .map = map, },
-	};
-
-	ops->target.addr = strtoull(ops->raw, &endptr, 16);
-
-	name = strchr(endptr, '<');
-	if (name == NULL)
-		goto indirect_call;
-
-	name++;
-
-	if (arch->objdump.skip_functions_char &&
-	    strchr(name, arch->objdump.skip_functions_char))
-		return -1;
-
-	tok = strchr(name, '>');
-	if (tok == NULL)
-		return -1;
-
-	*tok = '\0';
-	ops->target.name = strdup(name);
-	*tok = '>';
-
-	if (ops->target.name == NULL)
-		return -1;
-find_target:
-	target.addr = map__objdump_2mem(map, ops->target.addr);
-
-	if (maps__find_ams(ms->maps, &target) == 0 &&
-	    map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr)
-		ops->target.sym = target.ms.sym;
-
-	return 0;
-
-indirect_call:
-	tok = strchr(endptr, '*');
-	if (tok != NULL) {
-		endptr++;
-
-		/* Indirect call can use a non-rip register and offset: callq  *0x8(%rbx).
-		 * Do not parse such instruction.  */
-		if (strstr(endptr, "(%r") == NULL)
-			ops->target.addr = strtoull(endptr, NULL, 16);
-	}
-	goto find_target;
-}
-
-static int call__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops, int max_ins_name)
-{
-	if (ops->target.sym)
-		return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.sym->name);
-
-	if (ops->target.addr == 0)
-		return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
-
-	if (ops->target.name)
-		return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.name);
-
-	return scnprintf(bf, size, "%-*s *%" PRIx64, max_ins_name, ins->name, ops->target.addr);
-}
-
-static struct ins_ops call_ops = {
-	.parse	   = call__parse,
-	.scnprintf = call__scnprintf,
-};
-
-bool ins__is_call(const struct ins *ins)
-{
-	return ins->ops == &call_ops || ins->ops == &s390_call_ops || ins->ops == &loongarch_call_ops;
-}
-
-/*
- * Prevents from matching commas in the comment section, e.g.:
- * ffff200008446e70:       b.cs    ffff2000084470f4 <generic_exec_single+0x314>  // b.hs, b.nlast
- *
- * and skip comma as part of function arguments, e.g.:
- * 1d8b4ac <linemap_lookup(line_maps const*, unsigned int)+0xcc>
- */
-static inline const char *validate_comma(const char *c, struct ins_operands *ops)
-{
-	if (ops->jump.raw_comment && c > ops->jump.raw_comment)
-		return NULL;
-
-	if (ops->jump.raw_func_start && c > ops->jump.raw_func_start)
-		return NULL;
-
-	return c;
-}
-
-static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
-{
-	struct map *map = ms->map;
-	struct symbol *sym = ms->sym;
-	struct addr_map_symbol target = {
-		.ms = { .map = map, },
-	};
-	const char *c = strchr(ops->raw, ',');
-	u64 start, end;
-
-	ops->jump.raw_comment = strchr(ops->raw, arch->objdump.comment_char);
-	ops->jump.raw_func_start = strchr(ops->raw, '<');
-
-	c = validate_comma(c, ops);
-
-	/*
-	 * Examples of lines to parse for the _cpp_lex_token@@Base
-	 * function:
-	 *
-	 * 1159e6c: jne    115aa32 <_cpp_lex_token@@Base+0xf92>
-	 * 1159e8b: jne    c469be <cpp_named_operator2name@@Base+0xa72>
-	 *
-	 * The first is a jump to an offset inside the same function,
-	 * the second is to another function, i.e. that 0xa72 is an
-	 * offset in the cpp_named_operator2name@@base function.
-	 */
-	/*
-	 * skip over possible up to 2 operands to get to address, e.g.:
-	 * tbnz	 w0, #26, ffff0000083cd190 <security_file_permission+0xd0>
-	 */
-	if (c++ != NULL) {
-		ops->target.addr = strtoull(c, NULL, 16);
-		if (!ops->target.addr) {
-			c = strchr(c, ',');
-			c = validate_comma(c, ops);
-			if (c++ != NULL)
-				ops->target.addr = strtoull(c, NULL, 16);
-		}
-	} else {
-		ops->target.addr = strtoull(ops->raw, NULL, 16);
-	}
-
-	target.addr = map__objdump_2mem(map, ops->target.addr);
-	start = map__unmap_ip(map, sym->start);
-	end = map__unmap_ip(map, sym->end);
-
-	ops->target.outside = target.addr < start || target.addr > end;
-
-	/*
-	 * FIXME: things like this in _cpp_lex_token (gcc's cc1 program):
-
-		cpp_named_operator2name@@Base+0xa72
-
-	 * Point to a place that is after the cpp_named_operator2name
-	 * boundaries, i.e.  in the ELF symbol table for cc1
-	 * cpp_named_operator2name is marked as being 32-bytes long, but it in
-	 * fact is much larger than that, so we seem to need a symbols__find()
-	 * routine that looks for >= current->start and  < next_symbol->start,
-	 * possibly just for C++ objects?
-	 *
-	 * For now lets just make some progress by marking jumps to outside the
-	 * current function as call like.
-	 *
-	 * Actual navigation will come next, with further understanding of how
-	 * the symbol searching and disassembly should be done.
-	 */
-	if (maps__find_ams(ms->maps, &target) == 0 &&
-	    map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr)
-		ops->target.sym = target.ms.sym;
-
-	if (!ops->target.outside) {
-		ops->target.offset = target.addr - start;
-		ops->target.offset_avail = true;
-	} else {
-		ops->target.offset_avail = false;
-	}
-
-	return 0;
-}
-
-static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops, int max_ins_name)
-{
-	const char *c;
-
-	if (!ops->target.addr || ops->target.offset < 0)
-		return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
-
-	if (ops->target.outside && ops->target.sym != NULL)
-		return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.sym->name);
-
-	c = strchr(ops->raw, ',');
-	c = validate_comma(c, ops);
-
-	if (c != NULL) {
-		const char *c2 = strchr(c + 1, ',');
-
-		c2 = validate_comma(c2, ops);
-		/* check for 3-op insn */
-		if (c2 != NULL)
-			c = c2;
-		c++;
-
-		/* mirror arch objdump's space-after-comma style */
-		if (*c == ' ')
-			c++;
-	}
-
-	return scnprintf(bf, size, "%-*s %.*s%" PRIx64, max_ins_name,
-			 ins->name, c ? c - ops->raw : 0, ops->raw,
-			 ops->target.offset);
-}
-
-static void jump__delete(struct ins_operands *ops __maybe_unused)
-{
-	/*
-	 * The ops->jump.raw_comment and ops->jump.raw_func_start belong to the
-	 * raw string, don't free them.
-	 */
-}
-
-static struct ins_ops jump_ops = {
-	.free	   = jump__delete,
-	.parse	   = jump__parse,
-	.scnprintf = jump__scnprintf,
-};
-
-bool ins__is_jump(const struct ins *ins)
-{
-	return ins->ops == &jump_ops || ins->ops == &loongarch_jump_ops;
-}
-
-static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep)
-{
-	char *endptr, *name, *t;
-
-	if (strstr(raw, "(%rip)") == NULL)
-		return 0;
-
-	*addrp = strtoull(comment, &endptr, 16);
-	if (endptr == comment)
-		return 0;
-	name = strchr(endptr, '<');
-	if (name == NULL)
-		return -1;
-
-	name++;
-
-	t = strchr(name, '>');
-	if (t == NULL)
-		return 0;
-
-	*t = '\0';
-	*namep = strdup(name);
-	*t = '>';
-
-	return 0;
-}
-
-static int lock__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
-{
-	ops->locked.ops = zalloc(sizeof(*ops->locked.ops));
-	if (ops->locked.ops == NULL)
-		return 0;
-
-	if (disasm_line__parse(ops->raw, &ops->locked.ins.name, &ops->locked.ops->raw) < 0)
-		goto out_free_ops;
-
-	ops->locked.ins.ops = ins__find(arch, ops->locked.ins.name);
-
-	if (ops->locked.ins.ops == NULL)
-		goto out_free_ops;
-
-	if (ops->locked.ins.ops->parse &&
-	    ops->locked.ins.ops->parse(arch, ops->locked.ops, ms) < 0)
-		goto out_free_ops;
-
-	return 0;
-
-out_free_ops:
-	zfree(&ops->locked.ops);
-	return 0;
-}
-
-static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops, int max_ins_name)
-{
-	int printed;
-
-	if (ops->locked.ins.ops == NULL)
-		return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
-
-	printed = scnprintf(bf, size, "%-*s ", max_ins_name, ins->name);
-	return printed + ins__scnprintf(&ops->locked.ins, bf + printed,
-					size - printed, ops->locked.ops, max_ins_name);
-}
-
-static void lock__delete(struct ins_operands *ops)
-{
-	struct ins *ins = &ops->locked.ins;
-
-	if (ins->ops && ins->ops->free)
-		ins->ops->free(ops->locked.ops);
-	else
-		ins__delete(ops->locked.ops);
-
-	zfree(&ops->locked.ops);
-	zfree(&ops->target.raw);
-	zfree(&ops->target.name);
-}
-
-static struct ins_ops lock_ops = {
-	.free	   = lock__delete,
-	.parse	   = lock__parse,
-	.scnprintf = lock__scnprintf,
-};
-
-/*
- * Check if the operand has more than one registers like x86 SIB addressing:
- *   0x1234(%rax, %rbx, 8)
- *
- * But it doesn't care segment selectors like %gs:0x5678(%rcx), so just check
- * the input string after 'memory_ref_char' if exists.
- */
-static bool check_multi_regs(struct arch *arch, const char *op)
-{
-	int count = 0;
-
-	if (arch->objdump.register_char == 0)
-		return false;
-
-	if (arch->objdump.memory_ref_char) {
-		op = strchr(op, arch->objdump.memory_ref_char);
-		if (op == NULL)
-			return false;
-	}
-
-	while ((op = strchr(op, arch->objdump.register_char)) != NULL) {
-		count++;
-		op++;
-	}
-
-	return count > 1;
-}
-
-static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms __maybe_unused)
-{
-	char *s = strchr(ops->raw, ','), *target, *comment, prev;
-
-	if (s == NULL)
-		return -1;
-
-	*s = '\0';
-
-	/*
-	 * x86 SIB addressing has something like 0x8(%rax, %rcx, 1)
-	 * then it needs to have the closing parenthesis.
-	 */
-	if (strchr(ops->raw, '(')) {
-		*s = ',';
-		s = strchr(ops->raw, ')');
-		if (s == NULL || s[1] != ',')
-			return -1;
-		*++s = '\0';
-	}
-
-	ops->source.raw = strdup(ops->raw);
-	*s = ',';
-
-	if (ops->source.raw == NULL)
-		return -1;
-
-	ops->source.multi_regs = check_multi_regs(arch, ops->source.raw);
-
-	target = skip_spaces(++s);
-	comment = strchr(s, arch->objdump.comment_char);
-
-	if (comment != NULL)
-		s = comment - 1;
-	else
-		s = strchr(s, '\0') - 1;
-
-	while (s > target && isspace(s[0]))
-		--s;
-	s++;
-	prev = *s;
-	*s = '\0';
-
-	ops->target.raw = strdup(target);
-	*s = prev;
-
-	if (ops->target.raw == NULL)
-		goto out_free_source;
-
-	ops->target.multi_regs = check_multi_regs(arch, ops->target.raw);
-
-	if (comment == NULL)
-		return 0;
-
-	comment = skip_spaces(comment);
-	comment__symbol(ops->source.raw, comment + 1, &ops->source.addr, &ops->source.name);
-	comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
-
-	return 0;
-
-out_free_source:
-	zfree(&ops->source.raw);
-	return -1;
-}
-
-static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops, int max_ins_name)
-{
-	return scnprintf(bf, size, "%-*s %s,%s", max_ins_name, ins->name,
-			 ops->source.name ?: ops->source.raw,
-			 ops->target.name ?: ops->target.raw);
-}
-
-static struct ins_ops mov_ops = {
-	.parse	   = mov__parse,
-	.scnprintf = mov__scnprintf,
-};
-
-static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms __maybe_unused)
-{
-	char *target, *comment, *s, prev;
-
-	target = s = ops->raw;
-
-	while (s[0] != '\0' && !isspace(s[0]))
-		++s;
-	prev = *s;
-	*s = '\0';
-
-	ops->target.raw = strdup(target);
-	*s = prev;
-
-	if (ops->target.raw == NULL)
-		return -1;
-
-	comment = strchr(s, arch->objdump.comment_char);
-	if (comment == NULL)
-		return 0;
-
-	comment = skip_spaces(comment);
-	comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
-
-	return 0;
-}
-
-static int dec__scnprintf(struct ins *ins, char *bf, size_t size,
-			   struct ins_operands *ops, int max_ins_name)
-{
-	return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name,
-			 ops->target.name ?: ops->target.raw);
-}
-
-static struct ins_ops dec_ops = {
-	.parse	   = dec__parse,
-	.scnprintf = dec__scnprintf,
-};
-
-static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size,
-			  struct ins_operands *ops __maybe_unused, int max_ins_name)
-{
-	return scnprintf(bf, size, "%-*s", max_ins_name, "nop");
-}
-
-static struct ins_ops nop_ops = {
-	.scnprintf = nop__scnprintf,
-};
-
-static struct ins_ops ret_ops = {
-	.scnprintf = ins__raw_scnprintf,
-};
-
-bool ins__is_ret(const struct ins *ins)
-{
-	return ins->ops == &ret_ops;
-}
-
-bool ins__is_lock(const struct ins *ins)
-{
-	return ins->ops == &lock_ops;
-}
-
-static int ins__key_cmp(const void *name, const void *insp)
-{
-	const struct ins *ins = insp;
-
-	return strcmp(name, ins->name);
-}
-
-static int ins__cmp(const void *a, const void *b)
-{
-	const struct ins *ia = a;
-	const struct ins *ib = b;
-
-	return strcmp(ia->name, ib->name);
-}
-
-static void ins__sort(struct arch *arch)
-{
-	const int nmemb = arch->nr_instructions;
-
-	qsort(arch->instructions, nmemb, sizeof(struct ins), ins__cmp);
-}
-
-static struct ins_ops *__ins__find(struct arch *arch, const char *name)
-{
-	struct ins *ins;
-	const int nmemb = arch->nr_instructions;
-
-	if (!arch->sorted_instructions) {
-		ins__sort(arch);
-		arch->sorted_instructions = true;
-	}
-
-	ins = bsearch(name, arch->instructions, nmemb, sizeof(struct ins), ins__key_cmp);
-	if (ins)
-		return ins->ops;
-
-	if (arch->insn_suffix) {
-		char tmp[32];
-		char suffix;
-		size_t len = strlen(name);
-
-		if (len == 0 || len >= sizeof(tmp))
-			return NULL;
-
-		suffix = name[len - 1];
-		if (strchr(arch->insn_suffix, suffix) == NULL)
-			return NULL;
-
-		strcpy(tmp, name);
-		tmp[len - 1] = '\0'; /* remove the suffix and check again */
-
-		ins = bsearch(tmp, arch->instructions, nmemb, sizeof(struct ins), ins__key_cmp);
-	}
-	return ins ? ins->ops : NULL;
-}
-
-static struct ins_ops *ins__find(struct arch *arch, const char *name)
-{
-	struct ins_ops *ops = __ins__find(arch, name);
-
-	if (!ops && arch->associate_instruction_ops)
-		ops = arch->associate_instruction_ops(arch, name);
-
-	return ops;
-}
-
-static int arch__key_cmp(const void *name, const void *archp)
-{
-	const struct arch *arch = archp;
-
-	return strcmp(name, arch->name);
-}
-
-static int arch__cmp(const void *a, const void *b)
-{
-	const struct arch *aa = a;
-	const struct arch *ab = b;
-
-	return strcmp(aa->name, ab->name);
-}
-
-static void arch__sort(void)
-{
-	const int nmemb = ARRAY_SIZE(architectures);
-
-	qsort(architectures, nmemb, sizeof(struct arch), arch__cmp);
-}
-
-static struct arch *arch__find(const char *name)
-{
-	const int nmemb = ARRAY_SIZE(architectures);
-	static bool sorted;
-
-	if (!sorted) {
-		arch__sort();
-		sorted = true;
-	}
-
-	return bsearch(name, architectures, nmemb, sizeof(struct arch), arch__key_cmp);
-}
-
-bool arch__is(struct arch *arch, const char *name)
-{
-	return !strcmp(arch->name, name);
-}
-
 /* symbol histogram: key = offset << 16 | evsel->core.idx */
 static size_t sym_hist_hash(long key, void *ctx __maybe_unused)
 {
@@ -1149,14 +369,33 @@ int addr_map_symbol__account_cycles(struct addr_map_symbol *ams,
 	return err;
 }
 
+struct annotation_line *annotated_source__get_line(struct annotated_source *src,
+						   s64 offset)
+{
+	struct annotation_line *al;
+
+	list_for_each_entry(al, &src->source, node) {
+		if (al->offset == offset)
+			return al;
+	}
+	return NULL;
+}
+
 static unsigned annotation__count_insn(struct annotation *notes, u64 start, u64 end)
 {
+	struct annotation_line *al;
 	unsigned n_insn = 0;
-	u64 offset;
 
-	for (offset = start; offset <= end; offset++) {
-		if (notes->src->offsets[offset])
-			n_insn++;
+	al = annotated_source__get_line(notes->src, start);
+	if (al == NULL)
+		return 0;
+
+	list_for_each_entry_from(al, &notes->src->source, node) {
+		if (al->offset == -1)
+			continue;
+		if ((u64)al->offset > end)
+			break;
+		n_insn++;
 	}
 	return n_insn;
 }
@@ -1173,10 +412,10 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64
 {
 	unsigned n_insn;
 	unsigned int cover_insn = 0;
-	u64 offset;
 
 	n_insn = annotation__count_insn(notes, start, end);
 	if (n_insn && ch->num && ch->cycles) {
+		struct annotation_line *al;
 		struct annotated_branch *branch;
 		float ipc = n_insn / ((double)ch->cycles / (double)ch->num);
 
@@ -1184,10 +423,16 @@ static void annotation__count_and_fill(struct annotation *notes, u64 start, u64
 		if (ch->reset >= 0x7fff)
 			return;
 
-		for (offset = start; offset <= end; offset++) {
-			struct annotation_line *al = notes->src->offsets[offset];
+		al = annotated_source__get_line(notes->src, start);
+		if (al == NULL)
+			return;
 
-			if (al && al->cycles && al->cycles->ipc == 0.0) {
+		list_for_each_entry_from(al, &notes->src->source, node) {
+			if (al->offset == -1)
+				continue;
+			if ((u64)al->offset > end)
+				break;
+			if (al->cycles && al->cycles->ipc == 0.0) {
 				al->cycles->ipc = ipc;
 				cover_insn++;
 			}
@@ -1223,7 +468,7 @@ static int annotation__compute_ipc(struct annotation *notes, size_t size)
 		if (ch && ch->cycles) {
 			struct annotation_line *al;
 
-			al = notes->src->offsets[offset];
+			al = annotated_source__get_line(notes->src, offset);
 			if (al && al->cycles == NULL) {
 				al->cycles = zalloc(sizeof(*al->cycles));
 				if (al->cycles == NULL) {
@@ -1246,7 +491,9 @@ static int annotation__compute_ipc(struct annotation *notes, size_t size)
 			struct cyc_hist *ch = &notes->branch->cycles_hist[offset];
 
 			if (ch && ch->cycles) {
-				struct annotation_line *al = notes->src->offsets[offset];
+				struct annotation_line *al;
+
+				al = annotated_source__get_line(notes->src, offset);
 				if (al)
 					zfree(&al->cycles);
 			}
@@ -1269,142 +516,6 @@ int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *samp
 	return symbol__inc_addr_samples(&he->ms, evsel, ip, sample);
 }
 
-static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map_symbol *ms)
-{
-	dl->ins.ops = ins__find(arch, dl->ins.name);
-
-	if (!dl->ins.ops)
-		return;
-
-	if (dl->ins.ops->parse && dl->ins.ops->parse(arch, &dl->ops, ms) < 0)
-		dl->ins.ops = NULL;
-}
-
-static int disasm_line__parse(char *line, const char **namep, char **rawp)
-{
-	char tmp, *name = skip_spaces(line);
-
-	if (name[0] == '\0')
-		return -1;
-
-	*rawp = name + 1;
-
-	while ((*rawp)[0] != '\0' && !isspace((*rawp)[0]))
-		++*rawp;
-
-	tmp = (*rawp)[0];
-	(*rawp)[0] = '\0';
-	*namep = strdup(name);
-
-	if (*namep == NULL)
-		goto out;
-
-	(*rawp)[0] = tmp;
-	*rawp = strim(*rawp);
-
-	return 0;
-
-out:
-	return -1;
-}
-
-struct annotate_args {
-	struct arch		  *arch;
-	struct map_symbol	  ms;
-	struct evsel		  *evsel;
-	struct annotation_options *options;
-	s64			  offset;
-	char			  *line;
-	int			  line_nr;
-	char			  *fileloc;
-};
-
-static void annotation_line__init(struct annotation_line *al,
-				  struct annotate_args *args,
-				  int nr)
-{
-	al->offset = args->offset;
-	al->line = strdup(args->line);
-	al->line_nr = args->line_nr;
-	al->fileloc = args->fileloc;
-	al->data_nr = nr;
-}
-
-static void annotation_line__exit(struct annotation_line *al)
-{
-	zfree_srcline(&al->path);
-	zfree(&al->line);
-	zfree(&al->cycles);
-}
-
-static size_t disasm_line_size(int nr)
-{
-	struct annotation_line *al;
-
-	return (sizeof(struct disasm_line) + (sizeof(al->data[0]) * nr));
-}
-
-/*
- * Allocating the disasm annotation line data with
- * following structure:
- *
- *    -------------------------------------------
- *    struct disasm_line | struct annotation_line
- *    -------------------------------------------
- *
- * We have 'struct annotation_line' member as last member
- * of 'struct disasm_line' to have an easy access.
- */
-static struct disasm_line *disasm_line__new(struct annotate_args *args)
-{
-	struct disasm_line *dl = NULL;
-	int nr = 1;
-
-	if (evsel__is_group_event(args->evsel))
-		nr = args->evsel->core.nr_members;
-
-	dl = zalloc(disasm_line_size(nr));
-	if (!dl)
-		return NULL;
-
-	annotation_line__init(&dl->al, args, nr);
-	if (dl->al.line == NULL)
-		goto out_delete;
-
-	if (args->offset != -1) {
-		if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
-			goto out_free_line;
-
-		disasm_line__init_ins(dl, args->arch, &args->ms);
-	}
-
-	return dl;
-
-out_free_line:
-	zfree(&dl->al.line);
-out_delete:
-	free(dl);
-	return NULL;
-}
-
-void disasm_line__free(struct disasm_line *dl)
-{
-	if (dl->ins.ops && dl->ins.ops->free)
-		dl->ins.ops->free(&dl->ops);
-	else
-		ins__delete(&dl->ops);
-	zfree(&dl->ins.name);
-	annotation_line__exit(&dl->al);
-	free(dl);
-}
-
-int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name)
-{
-	if (raw || !dl->ins.ops)
-		return scnprintf(bf, size, "%-*s %s", max_ins_name, dl->ins.name, dl->ops.raw);
-
-	return ins__scnprintf(&dl->ins, bf, size, &dl->ops, max_ins_name);
-}
 
 void annotation__exit(struct annotation *notes)
 {
@@ -1464,8 +575,7 @@ bool annotation__trylock(struct annotation *notes)
 	return mutex_trylock(mutex);
 }
 
-
-static void annotation_line__add(struct annotation_line *al, struct list_head *head)
+void annotation_line__add(struct annotation_line *al, struct list_head *head)
 {
 	list_add_tail(&al->node, head);
 }
@@ -1675,673 +785,6 @@ annotation_line__print(struct annotation_line *al, struct symbol *sym, u64 start
 	return 0;
 }
 
-/*
- * symbol__parse_objdump_line() parses objdump output (with -d --no-show-raw)
- * which looks like following
- *
- *  0000000000415500 <_init>:
- *    415500:       sub    $0x8,%rsp
- *    415504:       mov    0x2f5ad5(%rip),%rax        # 70afe0 <_DYNAMIC+0x2f8>
- *    41550b:       test   %rax,%rax
- *    41550e:       je     415515 <_init+0x15>
- *    415510:       callq  416e70 <__gmon_start__@plt>
- *    415515:       add    $0x8,%rsp
- *    415519:       retq
- *
- * it will be parsed and saved into struct disasm_line as
- *  <offset>       <name>  <ops.raw>
- *
- * The offset will be a relative offset from the start of the symbol and -1
- * means that it's not a disassembly line so should be treated differently.
- * The ops.raw part will be parsed further according to type of the instruction.
- */
-static int symbol__parse_objdump_line(struct symbol *sym,
-				      struct annotate_args *args,
-				      char *parsed_line, int *line_nr, char **fileloc)
-{
-	struct map *map = args->ms.map;
-	struct annotation *notes = symbol__annotation(sym);
-	struct disasm_line *dl;
-	char *tmp;
-	s64 line_ip, offset = -1;
-	regmatch_t match[2];
-
-	/* /filename:linenr ? Save line number and ignore. */
-	if (regexec(&file_lineno, parsed_line, 2, match, 0) == 0) {
-		*line_nr = atoi(parsed_line + match[1].rm_so);
-		free(*fileloc);
-		*fileloc = strdup(parsed_line);
-		return 0;
-	}
-
-	/* Process hex address followed by ':'. */
-	line_ip = strtoull(parsed_line, &tmp, 16);
-	if (parsed_line != tmp && tmp[0] == ':' && tmp[1] != '\0') {
-		u64 start = map__rip_2objdump(map, sym->start),
-		    end = map__rip_2objdump(map, sym->end);
-
-		offset = line_ip - start;
-		if ((u64)line_ip < start || (u64)line_ip >= end)
-			offset = -1;
-		else
-			parsed_line = tmp + 1;
-	}
-
-	args->offset  = offset;
-	args->line    = parsed_line;
-	args->line_nr = *line_nr;
-	args->fileloc = *fileloc;
-	args->ms.sym  = sym;
-
-	dl = disasm_line__new(args);
-	(*line_nr)++;
-
-	if (dl == NULL)
-		return -1;
-
-	if (!disasm_line__has_local_offset(dl)) {
-		dl->ops.target.offset = dl->ops.target.addr -
-					map__rip_2objdump(map, sym->start);
-		dl->ops.target.offset_avail = true;
-	}
-
-	/* kcore has no symbols, so add the call target symbol */
-	if (dl->ins.ops && ins__is_call(&dl->ins) && !dl->ops.target.sym) {
-		struct addr_map_symbol target = {
-			.addr = dl->ops.target.addr,
-			.ms = { .map = map, },
-		};
-
-		if (!maps__find_ams(args->ms.maps, &target) &&
-		    target.ms.sym->start == target.al_addr)
-			dl->ops.target.sym = target.ms.sym;
-	}
-
-	annotation_line__add(&dl->al, &notes->src->source);
-	return 0;
-}
-
-static __attribute__((constructor)) void symbol__init_regexpr(void)
-{
-	regcomp(&file_lineno, "^/[^:]+:([0-9]+)", REG_EXTENDED);
-}
-
-static void delete_last_nop(struct symbol *sym)
-{
-	struct annotation *notes = symbol__annotation(sym);
-	struct list_head *list = &notes->src->source;
-	struct disasm_line *dl;
-
-	while (!list_empty(list)) {
-		dl = list_entry(list->prev, struct disasm_line, al.node);
-
-		if (dl->ins.ops) {
-			if (dl->ins.ops != &nop_ops)
-				return;
-		} else {
-			if (!strstr(dl->al.line, " nop ") &&
-			    !strstr(dl->al.line, " nopl ") &&
-			    !strstr(dl->al.line, " nopw "))
-				return;
-		}
-
-		list_del_init(&dl->al.node);
-		disasm_line__free(dl);
-	}
-}
-
-int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, size_t buflen)
-{
-	struct dso *dso = map__dso(ms->map);
-
-	BUG_ON(buflen == 0);
-
-	if (errnum >= 0) {
-		str_error_r(errnum, buf, buflen);
-		return 0;
-	}
-
-	switch (errnum) {
-	case SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX: {
-		char bf[SBUILD_ID_SIZE + 15] = " with build id ";
-		char *build_id_msg = NULL;
-
-		if (dso->has_build_id) {
-			build_id__sprintf(&dso->bid, bf + 15);
-			build_id_msg = bf;
-		}
-		scnprintf(buf, buflen,
-			  "No vmlinux file%s\nwas found in the path.\n\n"
-			  "Note that annotation using /proc/kcore requires CAP_SYS_RAWIO capability.\n\n"
-			  "Please use:\n\n"
-			  "  perf buildid-cache -vu vmlinux\n\n"
-			  "or:\n\n"
-			  "  --vmlinux vmlinux\n", build_id_msg ?: "");
-	}
-		break;
-	case SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF:
-		scnprintf(buf, buflen, "Please link with binutils's libopcode to enable BPF annotation");
-		break;
-	case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP:
-		scnprintf(buf, buflen, "Problems with arch specific instruction name regular expressions.");
-		break;
-	case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING:
-		scnprintf(buf, buflen, "Problems while parsing the CPUID in the arch specific initialization.");
-		break;
-	case SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE:
-		scnprintf(buf, buflen, "Invalid BPF file: %s.", dso->long_name);
-		break;
-	case SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF:
-		scnprintf(buf, buflen, "The %s BPF file has no BTF section, compile with -g or use pahole -J.",
-			  dso->long_name);
-		break;
-	default:
-		scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum);
-		break;
-	}
-
-	return 0;
-}
-
-static int dso__disassemble_filename(struct dso *dso, char *filename, size_t filename_size)
-{
-	char linkname[PATH_MAX];
-	char *build_id_filename;
-	char *build_id_path = NULL;
-	char *pos;
-	int len;
-
-	if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
-	    !dso__is_kcore(dso))
-		return SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX;
-
-	build_id_filename = dso__build_id_filename(dso, NULL, 0, false);
-	if (build_id_filename) {
-		__symbol__join_symfs(filename, filename_size, build_id_filename);
-		free(build_id_filename);
-	} else {
-		if (dso->has_build_id)
-			return ENOMEM;
-		goto fallback;
-	}
-
-	build_id_path = strdup(filename);
-	if (!build_id_path)
-		return ENOMEM;
-
-	/*
-	 * old style build-id cache has name of XX/XXXXXXX.. while
-	 * new style has XX/XXXXXXX../{elf,kallsyms,vdso}.
-	 * extract the build-id part of dirname in the new style only.
-	 */
-	pos = strrchr(build_id_path, '/');
-	if (pos && strlen(pos) < SBUILD_ID_SIZE - 2)
-		dirname(build_id_path);
-
-	if (dso__is_kcore(dso))
-		goto fallback;
-
-	len = readlink(build_id_path, linkname, sizeof(linkname) - 1);
-	if (len < 0)
-		goto fallback;
-
-	linkname[len] = '\0';
-	if (strstr(linkname, DSO__NAME_KALLSYMS) ||
-		access(filename, R_OK)) {
-fallback:
-		/*
-		 * If we don't have build-ids or the build-id file isn't in the
-		 * cache, or is just a kallsyms file, well, lets hope that this
-		 * DSO is the same as when 'perf record' ran.
-		 */
-		if (dso->kernel && dso->long_name[0] == '/')
-			snprintf(filename, filename_size, "%s", dso->long_name);
-		else
-			__symbol__join_symfs(filename, filename_size, dso->long_name);
-
-		mutex_lock(&dso->lock);
-		if (access(filename, R_OK) && errno == ENOENT && dso->nsinfo) {
-			char *new_name = dso__filename_with_chroot(dso, filename);
-			if (new_name) {
-				strlcpy(filename, new_name, filename_size);
-				free(new_name);
-			}
-		}
-		mutex_unlock(&dso->lock);
-	}
-
-	free(build_id_path);
-	return 0;
-}
-
-#if defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
-#define PACKAGE "perf"
-#include <bfd.h>
-#include <dis-asm.h>
-#include <bpf/bpf.h>
-#include <bpf/btf.h>
-#include <bpf/libbpf.h>
-#include <linux/btf.h>
-#include <tools/dis-asm-compat.h>
-
-static int symbol__disassemble_bpf(struct symbol *sym,
-				   struct annotate_args *args)
-{
-	struct annotation *notes = symbol__annotation(sym);
-	struct bpf_prog_linfo *prog_linfo = NULL;
-	struct bpf_prog_info_node *info_node;
-	int len = sym->end - sym->start;
-	disassembler_ftype disassemble;
-	struct map *map = args->ms.map;
-	struct perf_bpil *info_linear;
-	struct disassemble_info info;
-	struct dso *dso = map__dso(map);
-	int pc = 0, count, sub_id;
-	struct btf *btf = NULL;
-	char tpath[PATH_MAX];
-	size_t buf_size;
-	int nr_skip = 0;
-	char *buf;
-	bfd *bfdf;
-	int ret;
-	FILE *s;
-
-	if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO)
-		return SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE;
-
-	pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__,
-		  sym->name, sym->start, sym->end - sym->start);
-
-	memset(tpath, 0, sizeof(tpath));
-	perf_exe(tpath, sizeof(tpath));
-
-	bfdf = bfd_openr(tpath, NULL);
-	if (bfdf == NULL)
-		abort();
-
-	if (!bfd_check_format(bfdf, bfd_object))
-		abort();
-
-	s = open_memstream(&buf, &buf_size);
-	if (!s) {
-		ret = errno;
-		goto out;
-	}
-	init_disassemble_info_compat(&info, s,
-				     (fprintf_ftype) fprintf,
-				     fprintf_styled);
-	info.arch = bfd_get_arch(bfdf);
-	info.mach = bfd_get_mach(bfdf);
-
-	info_node = perf_env__find_bpf_prog_info(dso->bpf_prog.env,
-						 dso->bpf_prog.id);
-	if (!info_node) {
-		ret = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF;
-		goto out;
-	}
-	info_linear = info_node->info_linear;
-	sub_id = dso->bpf_prog.sub_id;
-
-	info.buffer = (void *)(uintptr_t)(info_linear->info.jited_prog_insns);
-	info.buffer_length = info_linear->info.jited_prog_len;
-
-	if (info_linear->info.nr_line_info)
-		prog_linfo = bpf_prog_linfo__new(&info_linear->info);
-
-	if (info_linear->info.btf_id) {
-		struct btf_node *node;
-
-		node = perf_env__find_btf(dso->bpf_prog.env,
-					  info_linear->info.btf_id);
-		if (node)
-			btf = btf__new((__u8 *)(node->data),
-				       node->data_size);
-	}
-
-	disassemble_init_for_target(&info);
-
-#ifdef DISASM_FOUR_ARGS_SIGNATURE
-	disassemble = disassembler(info.arch,
-				   bfd_big_endian(bfdf),
-				   info.mach,
-				   bfdf);
-#else
-	disassemble = disassembler(bfdf);
-#endif
-	if (disassemble == NULL)
-		abort();
-
-	fflush(s);
-	do {
-		const struct bpf_line_info *linfo = NULL;
-		struct disasm_line *dl;
-		size_t prev_buf_size;
-		const char *srcline;
-		u64 addr;
-
-		addr = pc + ((u64 *)(uintptr_t)(info_linear->info.jited_ksyms))[sub_id];
-		count = disassemble(pc, &info);
-
-		if (prog_linfo)
-			linfo = bpf_prog_linfo__lfind_addr_func(prog_linfo,
-								addr, sub_id,
-								nr_skip);
-
-		if (linfo && btf) {
-			srcline = btf__name_by_offset(btf, linfo->line_off);
-			nr_skip++;
-		} else
-			srcline = NULL;
-
-		fprintf(s, "\n");
-		prev_buf_size = buf_size;
-		fflush(s);
-
-		if (!annotate_opts.hide_src_code && srcline) {
-			args->offset = -1;
-			args->line = strdup(srcline);
-			args->line_nr = 0;
-			args->fileloc = NULL;
-			args->ms.sym  = sym;
-			dl = disasm_line__new(args);
-			if (dl) {
-				annotation_line__add(&dl->al,
-						     &notes->src->source);
-			}
-		}
-
-		args->offset = pc;
-		args->line = buf + prev_buf_size;
-		args->line_nr = 0;
-		args->fileloc = NULL;
-		args->ms.sym  = sym;
-		dl = disasm_line__new(args);
-		if (dl)
-			annotation_line__add(&dl->al, &notes->src->source);
-
-		pc += count;
-	} while (count > 0 && pc < len);
-
-	ret = 0;
-out:
-	free(prog_linfo);
-	btf__free(btf);
-	fclose(s);
-	bfd_close(bfdf);
-	return ret;
-}
-#else // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
-static int symbol__disassemble_bpf(struct symbol *sym __maybe_unused,
-				   struct annotate_args *args __maybe_unused)
-{
-	return SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF;
-}
-#endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
-
-static int
-symbol__disassemble_bpf_image(struct symbol *sym,
-			      struct annotate_args *args)
-{
-	struct annotation *notes = symbol__annotation(sym);
-	struct disasm_line *dl;
-
-	args->offset = -1;
-	args->line = strdup("to be implemented");
-	args->line_nr = 0;
-	args->fileloc = NULL;
-	dl = disasm_line__new(args);
-	if (dl)
-		annotation_line__add(&dl->al, &notes->src->source);
-
-	zfree(&args->line);
-	return 0;
-}
-
-/*
- * Possibly create a new version of line with tabs expanded. Returns the
- * existing or new line, storage is updated if a new line is allocated. If
- * allocation fails then NULL is returned.
- */
-static char *expand_tabs(char *line, char **storage, size_t *storage_len)
-{
-	size_t i, src, dst, len, new_storage_len, num_tabs;
-	char *new_line;
-	size_t line_len = strlen(line);
-
-	for (num_tabs = 0, i = 0; i < line_len; i++)
-		if (line[i] == '\t')
-			num_tabs++;
-
-	if (num_tabs == 0)
-		return line;
-
-	/*
-	 * Space for the line and '\0', less the leading and trailing
-	 * spaces. Each tab may introduce 7 additional spaces.
-	 */
-	new_storage_len = line_len + 1 + (num_tabs * 7);
-
-	new_line = malloc(new_storage_len);
-	if (new_line == NULL) {
-		pr_err("Failure allocating memory for tab expansion\n");
-		return NULL;
-	}
-
-	/*
-	 * Copy regions starting at src and expand tabs. If there are two
-	 * adjacent tabs then 'src == i', the memcpy is of size 0 and the spaces
-	 * are inserted.
-	 */
-	for (i = 0, src = 0, dst = 0; i < line_len && num_tabs; i++) {
-		if (line[i] == '\t') {
-			len = i - src;
-			memcpy(&new_line[dst], &line[src], len);
-			dst += len;
-			new_line[dst++] = ' ';
-			while (dst % 8 != 0)
-				new_line[dst++] = ' ';
-			src = i + 1;
-			num_tabs--;
-		}
-	}
-
-	/* Expand the last region. */
-	len = line_len - src;
-	memcpy(&new_line[dst], &line[src], len);
-	dst += len;
-	new_line[dst] = '\0';
-
-	free(*storage);
-	*storage = new_line;
-	*storage_len = new_storage_len;
-	return new_line;
-
-}
-
-static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
-{
-	struct annotation_options *opts = &annotate_opts;
-	struct map *map = args->ms.map;
-	struct dso *dso = map__dso(map);
-	char *command;
-	FILE *file;
-	char symfs_filename[PATH_MAX];
-	struct kcore_extract kce;
-	bool delete_extract = false;
-	bool decomp = false;
-	int lineno = 0;
-	char *fileloc = NULL;
-	int nline;
-	char *line;
-	size_t line_len;
-	const char *objdump_argv[] = {
-		"/bin/sh",
-		"-c",
-		NULL, /* Will be the objdump command to run. */
-		"--",
-		NULL, /* Will be the symfs path. */
-		NULL,
-	};
-	struct child_process objdump_process;
-	int err = dso__disassemble_filename(dso, symfs_filename, sizeof(symfs_filename));
-
-	if (err)
-		return err;
-
-	pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
-		 symfs_filename, sym->name, map__unmap_ip(map, sym->start),
-		 map__unmap_ip(map, sym->end));
-
-	pr_debug("annotating [%p] %30s : [%p] %30s\n",
-		 dso, dso->long_name, sym, sym->name);
-
-	if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) {
-		return symbol__disassemble_bpf(sym, args);
-	} else if (dso->binary_type == DSO_BINARY_TYPE__BPF_IMAGE) {
-		return symbol__disassemble_bpf_image(sym, args);
-	} else if (dso__is_kcore(dso)) {
-		kce.kcore_filename = symfs_filename;
-		kce.addr = map__rip_2objdump(map, sym->start);
-		kce.offs = sym->start;
-		kce.len = sym->end - sym->start;
-		if (!kcore_extract__create(&kce)) {
-			delete_extract = true;
-			strlcpy(symfs_filename, kce.extract_filename,
-				sizeof(symfs_filename));
-		}
-	} else if (dso__needs_decompress(dso)) {
-		char tmp[KMOD_DECOMP_LEN];
-
-		if (dso__decompress_kmodule_path(dso, symfs_filename,
-						 tmp, sizeof(tmp)) < 0)
-			return -1;
-
-		decomp = true;
-		strcpy(symfs_filename, tmp);
-	}
-
-	err = asprintf(&command,
-		 "%s %s%s --start-address=0x%016" PRIx64
-		 " --stop-address=0x%016" PRIx64
-		 " %s -d %s %s %s %c%s%c %s%s -C \"$1\"",
-		 opts->objdump_path ?: "objdump",
-		 opts->disassembler_style ? "-M " : "",
-		 opts->disassembler_style ?: "",
-		 map__rip_2objdump(map, sym->start),
-		 map__rip_2objdump(map, sym->end),
-		 opts->show_linenr ? "-l" : "",
-		 opts->show_asm_raw ? "" : "--no-show-raw-insn",
-		 opts->annotate_src ? "-S" : "",
-		 opts->prefix ? "--prefix " : "",
-		 opts->prefix ? '"' : ' ',
-		 opts->prefix ?: "",
-		 opts->prefix ? '"' : ' ',
-		 opts->prefix_strip ? "--prefix-strip=" : "",
-		 opts->prefix_strip ?: "");
-
-	if (err < 0) {
-		pr_err("Failure allocating memory for the command to run\n");
-		goto out_remove_tmp;
-	}
-
-	pr_debug("Executing: %s\n", command);
-
-	objdump_argv[2] = command;
-	objdump_argv[4] = symfs_filename;
-
-	/* Create a pipe to read from for stdout */
-	memset(&objdump_process, 0, sizeof(objdump_process));
-	objdump_process.argv = objdump_argv;
-	objdump_process.out = -1;
-	objdump_process.err = -1;
-	objdump_process.no_stderr = 1;
-	if (start_command(&objdump_process)) {
-		pr_err("Failure starting to run %s\n", command);
-		err = -1;
-		goto out_free_command;
-	}
-
-	file = fdopen(objdump_process.out, "r");
-	if (!file) {
-		pr_err("Failure creating FILE stream for %s\n", command);
-		/*
-		 * If we were using debug info should retry with
-		 * original binary.
-		 */
-		err = -1;
-		goto out_close_stdout;
-	}
-
-	/* Storage for getline. */
-	line = NULL;
-	line_len = 0;
-
-	nline = 0;
-	while (!feof(file)) {
-		const char *match;
-		char *expanded_line;
-
-		if (getline(&line, &line_len, file) < 0 || !line)
-			break;
-
-		/* Skip lines containing "filename:" */
-		match = strstr(line, symfs_filename);
-		if (match && match[strlen(symfs_filename)] == ':')
-			continue;
-
-		expanded_line = strim(line);
-		expanded_line = expand_tabs(expanded_line, &line, &line_len);
-		if (!expanded_line)
-			break;
-
-		/*
-		 * The source code line number (lineno) needs to be kept in
-		 * across calls to symbol__parse_objdump_line(), so that it
-		 * can associate it with the instructions till the next one.
-		 * See disasm_line__new() and struct disasm_line::line_nr.
-		 */
-		if (symbol__parse_objdump_line(sym, args, expanded_line,
-					       &lineno, &fileloc) < 0)
-			break;
-		nline++;
-	}
-	free(line);
-	free(fileloc);
-
-	err = finish_command(&objdump_process);
-	if (err)
-		pr_err("Error running %s\n", command);
-
-	if (nline == 0) {
-		err = -1;
-		pr_err("No output from %s\n", command);
-	}
-
-	/*
-	 * kallsyms does not have symbol sizes so there may a nop at the end.
-	 * Remove it.
-	 */
-	if (dso__is_kcore(dso))
-		delete_last_nop(sym);
-
-	fclose(file);
-
-out_close_stdout:
-	close(objdump_process.out);
-
-out_free_command:
-	free(command);
-
-out_remove_tmp:
-	if (decomp)
-		unlink(symfs_filename);
-
-	if (delete_extract)
-		kcore_extract__delete(&kce);
-
-	return err;
-}
-
 static void calc_percent(struct annotation *notes,
 			 struct evsel *evsel,
 			 struct annotation_data *data,
@@ -2422,8 +865,10 @@ static int evsel__get_arch(struct evsel *evsel, struct arch **parch)
 	struct arch *arch;
 	int err;
 
-	if (!arch_name)
+	if (!arch_name) {
+		*parch = NULL;
 		return errno;
+	}
 
 	*parch = arch = arch__find(arch_name);
 	if (arch == NULL) {
@@ -2461,15 +906,22 @@ int symbol__annotate(struct map_symbol *ms, struct evsel *evsel,
 	if (parch)
 		*parch = arch;
 
-	if (!list_empty(&notes->src->source))
+	if (notes->src && !list_empty(&notes->src->source))
 		return 0;
 
 	args.arch = arch;
 	args.ms = *ms;
+
+	if (notes->src == NULL) {
+		notes->src = annotated_source__new();
+		if (notes->src == NULL)
+			return -1;
+	}
+
 	if (annotate_opts.full_addr)
-		notes->start = map__objdump_2mem(ms->map, ms->sym->start);
+		notes->src->start = map__objdump_2mem(ms->map, ms->sym->start);
 	else
-		notes->start = map__rip_2objdump(ms->map, ms->sym->start);
+		notes->src->start = map__rip_2objdump(ms->map, ms->sym->start);
 
 	return symbol__disassemble(sym, &args);
 }
@@ -2838,13 +1290,16 @@ void symbol__annotate_decay_histogram(struct symbol *sym, int evidx)
 {
 	struct annotation *notes = symbol__annotation(sym);
 	struct sym_hist *h = annotation__histogram(notes, evidx);
-	int len = symbol__size(sym), offset;
+	struct annotation_line *al;
 
 	h->nr_samples = 0;
-	for (offset = 0; offset < len; ++offset) {
+	list_for_each_entry(al, &notes->src->source, node) {
 		struct sym_hist_entry *entry;
 
-		entry = annotated_source__hist_entry(notes->src, evidx, offset);
+		if (al->offset == -1)
+			continue;
+
+		entry = annotated_source__hist_entry(notes->src, evidx, al->offset);
 		if (entry == NULL)
 			continue;
 
@@ -2901,64 +1356,56 @@ bool disasm_line__is_valid_local_jump(struct disasm_line *dl, struct symbol *sym
 	return true;
 }
 
-void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym)
+static void
+annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym)
 {
-	u64 offset, size = symbol__size(sym);
+	struct annotation_line *al;
 
 	/* PLT symbols contain external offsets */
 	if (strstr(sym->name, "@plt"))
 		return;
 
-	for (offset = 0; offset < size; ++offset) {
-		struct annotation_line *al = notes->src->offsets[offset];
+	list_for_each_entry(al, &notes->src->source, node) {
 		struct disasm_line *dl;
+		struct annotation_line *target;
 
 		dl = disasm_line(al);
 
 		if (!disasm_line__is_valid_local_jump(dl, sym))
 			continue;
 
-		al = notes->src->offsets[dl->ops.target.offset];
-
+		target = annotated_source__get_line(notes->src,
+						    dl->ops.target.offset);
 		/*
 		 * FIXME: Oops, no jump target? Buggy disassembler? Or do we
 		 * have to adjust to the previous offset?
 		 */
-		if (al == NULL)
+		if (target == NULL)
 			continue;
 
-		if (++al->jump_sources > notes->max_jump_sources)
-			notes->max_jump_sources = al->jump_sources;
+		if (++target->jump_sources > notes->src->max_jump_sources)
+			notes->src->max_jump_sources = target->jump_sources;
 	}
 }
 
-void annotation__set_offsets(struct annotation *notes, s64 size)
+static void annotation__set_index(struct annotation *notes)
 {
 	struct annotation_line *al;
 	struct annotated_source *src = notes->src;
 
-	src->max_line_len = 0;
+	src->widths.max_line_len = 0;
 	src->nr_entries = 0;
 	src->nr_asm_entries = 0;
 
 	list_for_each_entry(al, &src->source, node) {
 		size_t line_len = strlen(al->line);
 
-		if (src->max_line_len < line_len)
-			src->max_line_len = line_len;
+		if (src->widths.max_line_len < line_len)
+			src->widths.max_line_len = line_len;
 		al->idx = src->nr_entries++;
-		if (al->offset != -1) {
+		if (al->offset != -1)
 			al->idx_asm = src->nr_asm_entries++;
-			/*
-			 * FIXME: short term bandaid to cope with assembly
-			 * routines that comes with labels in the same column
-			 * as the address in objdump, sigh.
-			 *
-			 * E.g. copy_user_generic_unrolled
- 			 */
-			if (al->offset < size)
-				notes->src->offsets[al->offset] = al;
-		} else
+		else
 			al->idx_asm = -1;
 	}
 }
@@ -2989,28 +1436,29 @@ static int annotation__max_ins_name(struct annotation *notes)
 	return max_name;
 }
 
-void annotation__init_column_widths(struct annotation *notes, struct symbol *sym)
+static void
+annotation__init_column_widths(struct annotation *notes, struct symbol *sym)
 {
-	notes->widths.addr = notes->widths.target =
-		notes->widths.min_addr = hex_width(symbol__size(sym));
-	notes->widths.max_addr = hex_width(sym->end);
-	notes->widths.jumps = width_jumps(notes->max_jump_sources);
-	notes->widths.max_ins_name = annotation__max_ins_name(notes);
+	notes->src->widths.addr = notes->src->widths.target =
+		notes->src->widths.min_addr = hex_width(symbol__size(sym));
+	notes->src->widths.max_addr = hex_width(sym->end);
+	notes->src->widths.jumps = width_jumps(notes->src->max_jump_sources);
+	notes->src->widths.max_ins_name = annotation__max_ins_name(notes);
 }
 
 void annotation__update_column_widths(struct annotation *notes)
 {
 	if (annotate_opts.use_offset)
-		notes->widths.target = notes->widths.min_addr;
+		notes->src->widths.target = notes->src->widths.min_addr;
 	else if (annotate_opts.full_addr)
-		notes->widths.target = BITS_PER_LONG / 4;
+		notes->src->widths.target = BITS_PER_LONG / 4;
 	else
-		notes->widths.target = notes->widths.max_addr;
+		notes->src->widths.target = notes->src->widths.max_addr;
 
-	notes->widths.addr = notes->widths.target;
+	notes->src->widths.addr = notes->src->widths.target;
 
 	if (annotate_opts.show_nr_jumps)
-		notes->widths.addr += notes->widths.jumps + 1;
+		notes->src->widths.addr += notes->src->widths.jumps + 1;
 }
 
 void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *ms)
@@ -3018,14 +1466,14 @@ void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *m
 	annotate_opts.full_addr = !annotate_opts.full_addr;
 
 	if (annotate_opts.full_addr)
-		notes->start = map__objdump_2mem(ms->map, ms->sym->start);
+		notes->src->start = map__objdump_2mem(ms->map, ms->sym->start);
 	else
-		notes->start = map__rip_2objdump(ms->map, ms->sym->start);
+		notes->src->start = map__rip_2objdump(ms->map, ms->sym->start);
 
 	annotation__update_column_widths(notes);
 }
 
-static void annotation__calc_lines(struct annotation *notes, struct map *map,
+static void annotation__calc_lines(struct annotation *notes, struct map_symbol *ms,
 				   struct rb_root *root)
 {
 	struct annotation_line *al;
@@ -3033,6 +1481,7 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map,
 
 	list_for_each_entry(al, &notes->src->source, node) {
 		double percent_max = 0.0;
+		u64 addr;
 		int i;
 
 		for (i = 0; i < al->data_nr; i++) {
@@ -3048,8 +1497,9 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map,
 		if (percent_max <= 0.5)
 			continue;
 
-		al->path = get_srcline(map__dso(map), notes->start + al->offset, NULL,
-				       false, true, notes->start + al->offset);
+		addr = map__rip_2objdump(ms->map, ms->sym->start);
+		al->path = get_srcline(map__dso(ms->map), addr + al->offset, NULL,
+				       false, true, ms->sym->start + al->offset);
 		insert_source_line(&tmp_root, al);
 	}
 
@@ -3060,7 +1510,7 @@ static void symbol__calc_lines(struct map_symbol *ms, struct rb_root *root)
 {
 	struct annotation *notes = symbol__annotation(ms->sym);
 
-	annotation__calc_lines(notes, ms->map, root);
+	annotation__calc_lines(notes, ms, root);
 }
 
 int symbol__tty_annotate2(struct map_symbol *ms, struct evsel *evsel)
@@ -3144,7 +1594,7 @@ static double annotation_line__max_percent(struct annotation_line *al,
 	double percent_max = 0.0;
 	int i;
 
-	for (i = 0; i < notes->nr_events; i++) {
+	for (i = 0; i < notes->src->nr_events; i++) {
 		double percent;
 
 		percent = annotation_data__percent(&al->data[i],
@@ -3185,7 +1635,8 @@ call_like:
 		obj__printf(obj, "  ");
 	}
 
-	disasm_line__scnprintf(dl, bf, size, !annotate_opts.use_offset, notes->widths.max_ins_name);
+	disasm_line__scnprintf(dl, bf, size, !annotate_opts.use_offset,
+			       notes->src->widths.max_ins_name);
 }
 
 static void ipc_coverage_string(char *bf, int size, struct annotation *notes)
@@ -3233,7 +1684,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 	if (al->offset != -1 && percent_max != 0.0) {
 		int i;
 
-		for (i = 0; i < notes->nr_events; i++) {
+		for (i = 0; i < notes->src->nr_events; i++) {
 			double percent;
 
 			percent = annotation_data__percent(&al->data[i], percent_type);
@@ -3313,9 +1764,11 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 		obj__printf(obj, "%-*s", width - pcnt_width - cycles_width, " ");
 	else if (al->offset == -1) {
 		if (al->line_nr && annotate_opts.show_linenr)
-			printed = scnprintf(bf, sizeof(bf), "%-*d ", notes->widths.addr + 1, al->line_nr);
+			printed = scnprintf(bf, sizeof(bf), "%-*d ",
+					    notes->src->widths.addr + 1, al->line_nr);
 		else
-			printed = scnprintf(bf, sizeof(bf), "%-*s  ", notes->widths.addr, " ");
+			printed = scnprintf(bf, sizeof(bf), "%-*s  ",
+					    notes->src->widths.addr, " ");
 		obj__printf(obj, bf);
 		obj__printf(obj, "%-*s", width - printed - pcnt_width - cycles_width + 1, al->line);
 	} else {
@@ -3323,7 +1776,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 		int color = -1;
 
 		if (!annotate_opts.use_offset)
-			addr += notes->start;
+			addr += notes->src->start;
 
 		if (!annotate_opts.use_offset) {
 			printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr);
@@ -3333,7 +1786,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 				if (annotate_opts.show_nr_jumps) {
 					int prev;
 					printed = scnprintf(bf, sizeof(bf), "%*d ",
-							    notes->widths.jumps,
+							    notes->src->widths.jumps,
 							    al->jump_sources);
 					prev = obj__set_jumps_percent_color(obj, al->jump_sources,
 									    current_entry);
@@ -3342,7 +1795,7 @@ static void __annotation_line__write(struct annotation_line *al, struct annotati
 				}
 print_addr:
 				printed = scnprintf(bf, sizeof(bf), "%*" PRIx64 ": ",
-						    notes->widths.target, addr);
+						    notes->src->widths.target, addr);
 			} else if (ins__is_call(&disasm_line(al)->ins) &&
 				   annotate_opts.offset_level >= ANNOTATION__OFFSET_CALL) {
 				goto print_addr;
@@ -3350,7 +1803,7 @@ print_addr:
 				goto print_addr;
 			} else {
 				printed = scnprintf(bf, sizeof(bf), "%-*s  ",
-						    notes->widths.addr, " ");
+						    notes->src->widths.addr, " ");
 			}
 		}
 
@@ -3386,37 +1839,29 @@ int symbol__annotate2(struct map_symbol *ms, struct evsel *evsel,
 	size_t size = symbol__size(sym);
 	int nr_pcnt = 1, err;
 
-	notes->src->offsets = zalloc(size * sizeof(struct annotation_line *));
-	if (notes->src->offsets == NULL)
-		return ENOMEM;
-
 	if (evsel__is_group_event(evsel))
 		nr_pcnt = evsel->core.nr_members;
 
 	err = symbol__annotate(ms, evsel, parch);
 	if (err)
-		goto out_free_offsets;
+		return err;
 
 	symbol__calc_percent(sym, evsel);
 
-	annotation__set_offsets(notes, size);
+	annotation__set_index(notes);
 	annotation__mark_jump_targets(notes, sym);
 
 	err = annotation__compute_ipc(notes, size);
 	if (err)
-		goto out_free_offsets;
+		return err;
 
 	annotation__init_column_widths(notes, sym);
-	notes->nr_events = nr_pcnt;
+	notes->src->nr_events = nr_pcnt;
 
 	annotation__update_column_widths(notes);
 	sym->annotate2 = 1;
 
 	return 0;
-
-out_free_offsets:
-	zfree(&notes->src->offsets);
-	return err;
 }
 
 static int annotation__config(const char *var, const char *value, void *data)
@@ -3588,6 +2033,12 @@ static int extract_reg_offset(struct arch *arch, const char *str,
 	 * %gs:0x18(%rbx).  In that case it should skip the part.
 	 */
 	if (*str == arch->objdump.register_char) {
+		if (arch__is(arch, "x86")) {
+			/* FIXME: Handle other segment registers */
+			if (!strncmp(str, "%gs:", 4))
+				op_loc->segment = INSN_SEG_X86_GS;
+		}
+
 		while (*str && !isdigit(*str) &&
 		       *str != arch->objdump.memory_ref_char)
 			str++;
@@ -3653,7 +2104,7 @@ int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
 	struct annotated_op_loc *op_loc;
 	int i;
 
-	if (!strcmp(dl->ins.name, "lock"))
+	if (ins__is_lock(&dl->ins))
 		ops = dl->ops.locked.ops;
 	else
 		ops = &dl->ops;
@@ -3684,40 +2135,40 @@ int annotate_get_insn_location(struct arch *arch, struct disasm_line *dl,
 			op_loc->multi_regs = multi_regs;
 			extract_reg_offset(arch, insn_str, op_loc);
 		} else {
-			char *s = strdup(insn_str);
+			char *s, *p = NULL;
+
+			if (arch__is(arch, "x86")) {
+				/* FIXME: Handle other segment registers */
+				if (!strncmp(insn_str, "%gs:", 4)) {
+					op_loc->segment = INSN_SEG_X86_GS;
+					op_loc->offset = strtol(insn_str + 4,
+								&p, 0);
+					if (p && p != insn_str + 4)
+						op_loc->imm = true;
+					continue;
+				}
+			}
+
+			s = strdup(insn_str);
+			if (s == NULL)
+				return -1;
 
-			if (s) {
+			if (*s == arch->objdump.register_char)
 				op_loc->reg1 = get_dwarf_regnum(s, 0);
-				free(s);
+			else if (*s == arch->objdump.imm_char) {
+				op_loc->offset = strtol(s + 1, &p, 0);
+				if (p && p != s + 1)
+					op_loc->imm = true;
 			}
+			free(s);
 		}
 	}
 
 	return 0;
 }
 
-static void symbol__ensure_annotate(struct map_symbol *ms, struct evsel *evsel)
-{
-	struct disasm_line *dl, *tmp_dl;
-	struct annotation *notes;
-
-	notes = symbol__annotation(ms->sym);
-	if (!list_empty(&notes->src->source))
-		return;
-
-	if (symbol__annotate(ms, evsel, NULL) < 0)
-		return;
-
-	/* remove non-insn disasm lines for simplicity */
-	list_for_each_entry_safe(dl, tmp_dl, &notes->src->source, al.node) {
-		if (dl->al.offset == -1) {
-			list_del(&dl->al.node);
-			free(dl);
-		}
-	}
-}
-
-static struct disasm_line *find_disasm_line(struct symbol *sym, u64 ip)
+static struct disasm_line *find_disasm_line(struct symbol *sym, u64 ip,
+					    bool allow_update)
 {
 	struct disasm_line *dl;
 	struct annotation *notes;
@@ -3725,12 +2176,16 @@ static struct disasm_line *find_disasm_line(struct symbol *sym, u64 ip)
 	notes = symbol__annotation(sym);
 
 	list_for_each_entry(dl, &notes->src->source, al.node) {
+		if (dl->al.offset == -1)
+			continue;
+
 		if (sym->start + dl->al.offset == ip) {
 			/*
 			 * llvm-objdump places "lock" in a separate line and
 			 * in that case, we want to get the next line.
 			 */
-			if (!strcmp(dl->ins.name, "lock") && *dl->ops.raw == '\0') {
+			if (ins__is_lock(&dl->ins) &&
+			    *dl->ops.raw == '\0' && allow_update) {
 				ip++;
 				continue;
 			}
@@ -3776,6 +2231,58 @@ static bool is_stack_operation(struct arch *arch, struct disasm_line *dl)
 	return false;
 }
 
+static bool is_stack_canary(struct arch *arch, struct annotated_op_loc *loc)
+{
+	/* On x86_64, %gs:40 is used for stack canary */
+	if (arch__is(arch, "x86")) {
+		if (loc->segment == INSN_SEG_X86_GS && loc->imm &&
+		    loc->offset == 40)
+			return true;
+	}
+
+	return false;
+}
+
+static struct disasm_line *
+annotation__prev_asm_line(struct annotation *notes, struct disasm_line *curr)
+{
+	struct list_head *sources = &notes->src->source;
+	struct disasm_line *prev;
+
+	if (curr == list_first_entry(sources, struct disasm_line, al.node))
+		return NULL;
+
+	prev = list_prev_entry(curr, al.node);
+	while (prev->al.offset == -1 &&
+	       prev != list_first_entry(sources, struct disasm_line, al.node))
+		prev = list_prev_entry(prev, al.node);
+
+	if (prev->al.offset == -1)
+		return NULL;
+
+	return prev;
+}
+
+static struct disasm_line *
+annotation__next_asm_line(struct annotation *notes, struct disasm_line *curr)
+{
+	struct list_head *sources = &notes->src->source;
+	struct disasm_line *next;
+
+	if (curr == list_last_entry(sources, struct disasm_line, al.node))
+		return NULL;
+
+	next = list_next_entry(curr, al.node);
+	while (next->al.offset == -1 &&
+	       next != list_last_entry(sources, struct disasm_line, al.node))
+		next = list_next_entry(next, al.node);
+
+	if (next->al.offset == -1)
+		return NULL;
+
+	return next;
+}
+
 u64 annotate_calc_pcrel(struct map_symbol *ms, u64 ip, int offset,
 			struct disasm_line *dl)
 {
@@ -3791,12 +2298,12 @@ u64 annotate_calc_pcrel(struct map_symbol *ms, u64 ip, int offset,
 	 * disasm_line.  If it's the last one, we can use symbol's end
 	 * address directly.
 	 */
-	if (&dl->al.node == notes->src->source.prev)
+	next = annotation__next_asm_line(notes, dl);
+	if (next == NULL)
 		addr = ms->sym->end + offset;
-	else {
-		next = list_next_entry(dl, al.node);
+	else
 		addr = ip + (next->al.offset - dl->al.offset) + offset;
-	}
+
 	return map__rip_2objdump(ms->map, addr);
 }
 
@@ -3819,9 +2326,7 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 	struct annotated_op_loc *op_loc;
 	struct annotated_data_type *mem_type;
 	struct annotated_item_stat *istat;
-	u64 ip = he->ip, addr = 0;
-	const char *var_name = NULL;
-	int var_offset;
+	u64 ip = he->ip;
 	int i;
 
 	ann_data_stat.total++;
@@ -3836,19 +2341,17 @@ struct annotated_data_type *hist_entry__get_data_type(struct hist_entry *he)
 		return NULL;
 	}
 
-	if (evsel__get_arch(evsel, &arch) < 0) {
+	/* Make sure it has the disasm of the function */
+	if (symbol__annotate(ms, evsel, &arch) < 0) {
 		ann_data_stat.no_insn++;
 		return NULL;
 	}
 
-	/* Make sure it runs objdump to get disasm of the function */
-	symbol__ensure_annotate(ms, evsel);
-
 	/*
 	 * Get a disasm to extract the location from the insn.
 	 * This is too slow...
 	 */
-	dl = find_disasm_line(ms->sym, ip);
+	dl = find_disasm_line(ms->sym, ip, /*allow_update=*/true);
 	if (dl == NULL) {
 		ann_data_stat.no_insn++;
 		return NULL;
@@ -3874,51 +2377,55 @@ retry:
 	}
 
 	for_each_insn_op_loc(&loc, i, op_loc) {
-		if (!op_loc->mem_ref)
+		struct data_loc_info dloc = {
+			.arch = arch,
+			.thread = he->thread,
+			.ms = ms,
+			/* Recalculate IP for LOCK prefix or insn fusion */
+			.ip = ms->sym->start + dl->al.offset,
+			.cpumode = he->cpumode,
+			.op = op_loc,
+		};
+
+		if (!op_loc->mem_ref && op_loc->segment == INSN_SEG_NONE)
 			continue;
 
 		/* Recalculate IP because of LOCK prefix or insn fusion */
 		ip = ms->sym->start + dl->al.offset;
 
-		var_offset = op_loc->offset;
-
 		/* PC-relative addressing */
 		if (op_loc->reg1 == DWARF_REG_PC) {
-			struct addr_location al;
-			struct symbol *var;
-			u64 map_addr;
-
-			addr = annotate_calc_pcrel(ms, ip, op_loc->offset, dl);
-			/* Kernel symbols might be relocated */
-			map_addr = addr + map__reloc(ms->map);
-
-			addr_location__init(&al);
-			var = thread__find_symbol_fb(he->thread, he->cpumode,
-						     map_addr, &al);
-			if (var) {
-				var_name = var->name;
-				/* Calculate type offset from the start of variable */
-				var_offset = map_addr - map__unmap_ip(al.map, var->start);
-			}
-			addr_location__exit(&al);
+			dloc.var_addr = annotate_calc_pcrel(ms, dloc.ip,
+							    op_loc->offset, dl);
+		}
+
+		/* This CPU access in kernel - pretend PC-relative addressing */
+		if (map__dso(ms->map)->kernel && arch__is(arch, "x86") &&
+		    op_loc->segment == INSN_SEG_X86_GS && op_loc->imm) {
+			dloc.var_addr = op_loc->offset;
+			op_loc->reg1 = DWARF_REG_PC;
+		}
+
+		mem_type = find_data_type(&dloc);
+
+		if (mem_type == NULL && is_stack_canary(arch, op_loc)) {
+			istat->good++;
+			he->mem_type_off = 0;
+			return &canary_type;
 		}
 
-		mem_type = find_data_type(ms, ip, op_loc, addr, var_name);
 		if (mem_type)
 			istat->good++;
 		else
 			istat->bad++;
 
-		if (mem_type && var_name)
-			op_loc->offset = var_offset;
-
 		if (symbol_conf.annotate_data_sample) {
 			annotated_data_type__update_samples(mem_type, evsel,
-							    op_loc->offset,
+							    dloc.type_offset,
 							    he->stat.nr_events,
 							    he->stat.period);
 		}
-		he->mem_type_off = op_loc->offset;
+		he->mem_type_off = dloc.type_offset;
 		return mem_type;
 	}
 
@@ -3927,10 +2434,13 @@ retry:
 	 * from the previous instruction.
 	 */
 	if (dl->al.offset > 0) {
+		struct annotation *notes;
 		struct disasm_line *prev_dl;
 
-		prev_dl = list_prev_entry(dl, al.node);
-		if (ins__is_fused(arch, prev_dl->ins.name, dl->ins.name)) {
+		notes = symbol__annotation(ms->sym);
+		prev_dl = annotation__prev_asm_line(notes, dl);
+
+		if (prev_dl && ins__is_fused(arch, prev_dl->ins.name, dl->ins.name)) {
 			dl = prev_dl;
 			goto retry;
 		}
@@ -3940,3 +2450,227 @@ retry:
 	istat->bad++;
 	return NULL;
 }
+
+/* Basic block traversal (BFS) data structure */
+struct basic_block_data {
+	struct list_head queue;
+	struct list_head visited;
+};
+
+/*
+ * During the traversal, it needs to know the parent block where the current
+ * block block started from.  Note that single basic block can be parent of
+ * two child basic blocks (in case of condition jump).
+ */
+struct basic_block_link {
+	struct list_head node;
+	struct basic_block_link *parent;
+	struct annotated_basic_block *bb;
+};
+
+/* Check any of basic block in the list already has the offset */
+static bool basic_block_has_offset(struct list_head *head, s64 offset)
+{
+	struct basic_block_link *link;
+
+	list_for_each_entry(link, head, node) {
+		s64 begin_offset = link->bb->begin->al.offset;
+		s64 end_offset = link->bb->end->al.offset;
+
+		if (begin_offset <= offset && offset <= end_offset)
+			return true;
+	}
+	return false;
+}
+
+static bool is_new_basic_block(struct basic_block_data *bb_data,
+			       struct disasm_line *dl)
+{
+	s64 offset = dl->al.offset;
+
+	if (basic_block_has_offset(&bb_data->visited, offset))
+		return false;
+	if (basic_block_has_offset(&bb_data->queue, offset))
+		return false;
+	return true;
+}
+
+/* Add a basic block starting from dl and link it to the parent */
+static int add_basic_block(struct basic_block_data *bb_data,
+			   struct basic_block_link *parent,
+			   struct disasm_line *dl)
+{
+	struct annotated_basic_block *bb;
+	struct basic_block_link *link;
+
+	if (dl == NULL)
+		return -1;
+
+	if (!is_new_basic_block(bb_data, dl))
+		return 0;
+
+	bb = zalloc(sizeof(*bb));
+	if (bb == NULL)
+		return -1;
+
+	bb->begin = dl;
+	bb->end = dl;
+	INIT_LIST_HEAD(&bb->list);
+
+	link = malloc(sizeof(*link));
+	if (link == NULL) {
+		free(bb);
+		return -1;
+	}
+
+	link->bb = bb;
+	link->parent = parent;
+	list_add_tail(&link->node, &bb_data->queue);
+	return 0;
+}
+
+/* Returns true when it finds the target in the current basic block */
+static bool process_basic_block(struct basic_block_data *bb_data,
+				struct basic_block_link *link,
+				struct symbol *sym, u64 target)
+{
+	struct disasm_line *dl, *next_dl, *last_dl;
+	struct annotation *notes = symbol__annotation(sym);
+	bool found = false;
+
+	dl = link->bb->begin;
+	/* Check if it's already visited */
+	if (basic_block_has_offset(&bb_data->visited, dl->al.offset))
+		return false;
+
+	last_dl = list_last_entry(&notes->src->source,
+				  struct disasm_line, al.node);
+	if (last_dl->al.offset == -1)
+		last_dl = annotation__prev_asm_line(notes, last_dl);
+
+	if (last_dl == NULL)
+		return false;
+
+	list_for_each_entry_from(dl, &notes->src->source, al.node) {
+		/* Skip comment or debug info line */
+		if (dl->al.offset == -1)
+			continue;
+		/* Found the target instruction */
+		if (sym->start + dl->al.offset == target) {
+			found = true;
+			break;
+		}
+		/* End of the function, finish the block */
+		if (dl == last_dl)
+			break;
+		/* 'return' instruction finishes the block */
+		if (ins__is_ret(&dl->ins))
+			break;
+		/* normal instructions are part of the basic block */
+		if (!ins__is_jump(&dl->ins))
+			continue;
+		/* jump to a different function, tail call or return */
+		if (dl->ops.target.outside)
+			break;
+		/* jump instruction creates new basic block(s) */
+		next_dl = find_disasm_line(sym, sym->start + dl->ops.target.offset,
+					   /*allow_update=*/false);
+		if (next_dl)
+			add_basic_block(bb_data, link, next_dl);
+
+		/*
+		 * FIXME: determine conditional jumps properly.
+		 * Conditional jumps create another basic block with the
+		 * next disasm line.
+		 */
+		if (!strstr(dl->ins.name, "jmp")) {
+			next_dl = annotation__next_asm_line(notes, dl);
+			if (next_dl)
+				add_basic_block(bb_data, link, next_dl);
+		}
+		break;
+
+	}
+	link->bb->end = dl;
+	return found;
+}
+
+/*
+ * It founds a target basic block, build a proper linked list of basic blocks
+ * by following the link recursively.
+ */
+static void link_found_basic_blocks(struct basic_block_link *link,
+				    struct list_head *head)
+{
+	while (link) {
+		struct basic_block_link *parent = link->parent;
+
+		list_move(&link->bb->list, head);
+		list_del(&link->node);
+		free(link);
+
+		link = parent;
+	}
+}
+
+static void delete_basic_blocks(struct basic_block_data *bb_data)
+{
+	struct basic_block_link *link, *tmp;
+
+	list_for_each_entry_safe(link, tmp, &bb_data->queue, node) {
+		list_del(&link->node);
+		free(link->bb);
+		free(link);
+	}
+
+	list_for_each_entry_safe(link, tmp, &bb_data->visited, node) {
+		list_del(&link->node);
+		free(link->bb);
+		free(link);
+	}
+}
+
+/**
+ * annotate_get_basic_blocks - Get basic blocks for given address range
+ * @sym: symbol to annotate
+ * @src: source address
+ * @dst: destination address
+ * @head: list head to save basic blocks
+ *
+ * This function traverses disasm_lines from @src to @dst and save them in a
+ * list of annotated_basic_block to @head.  It uses BFS to find the shortest
+ * path between two.  The basic_block_link is to maintain parent links so
+ * that it can build a list of blocks from the start.
+ */
+int annotate_get_basic_blocks(struct symbol *sym, s64 src, s64 dst,
+			      struct list_head *head)
+{
+	struct basic_block_data bb_data = {
+		.queue = LIST_HEAD_INIT(bb_data.queue),
+		.visited = LIST_HEAD_INIT(bb_data.visited),
+	};
+	struct basic_block_link *link;
+	struct disasm_line *dl;
+	int ret = -1;
+
+	dl = find_disasm_line(sym, src, /*allow_update=*/false);
+	if (dl == NULL)
+		return -1;
+
+	if (add_basic_block(&bb_data, /*parent=*/NULL, dl) < 0)
+		return -1;
+
+	/* Find shortest path from src to dst using BFS */
+	while (!list_empty(&bb_data.queue)) {
+		link = list_first_entry(&bb_data.queue, struct basic_block_link, node);
+
+		if (process_basic_block(&bb_data, link, sym, dst)) {
+			link_found_basic_blocks(link, head);
+			ret = 0;
+			break;
+		}
+		list_move(&link->node, &bb_data.visited);
+	}
+	delete_basic_blocks(&bb_data);
+	return ret;
+}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 13cc659e508c79..d5c821c22f79e5 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -13,10 +13,10 @@
 #include "mutex.h"
 #include "spark.h"
 #include "hashmap.h"
+#include "disasm.h"
 
 struct hist_browser_timer;
 struct hist_entry;
-struct ins_ops;
 struct map;
 struct map_symbol;
 struct addr_map_symbol;
@@ -26,59 +26,6 @@ struct evsel;
 struct symbol;
 struct annotated_data_type;
 
-struct ins {
-	const char     *name;
-	struct ins_ops *ops;
-};
-
-struct ins_operands {
-	char	*raw;
-	struct {
-		char	*raw;
-		char	*name;
-		struct symbol *sym;
-		u64	addr;
-		s64	offset;
-		bool	offset_avail;
-		bool	outside;
-		bool	multi_regs;
-	} target;
-	union {
-		struct {
-			char	*raw;
-			char	*name;
-			u64	addr;
-			bool	multi_regs;
-		} source;
-		struct {
-			struct ins	    ins;
-			struct ins_operands *ops;
-		} locked;
-		struct {
-			char	*raw_comment;
-			char	*raw_func_start;
-		} jump;
-	};
-};
-
-struct arch;
-
-bool arch__is(struct arch *arch, const char *name);
-
-struct ins_ops {
-	void (*free)(struct ins_operands *ops);
-	int (*parse)(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms);
-	int (*scnprintf)(struct ins *ins, char *bf, size_t size,
-			 struct ins_operands *ops, int max_ins_name);
-};
-
-bool ins__is_jump(const struct ins *ins);
-bool ins__is_call(const struct ins *ins);
-bool ins__is_ret(const struct ins *ins);
-bool ins__is_lock(const struct ins *ins);
-int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops, int max_ins_name);
-bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
-
 #define ANNOTATION__IPC_WIDTH 6
 #define ANNOTATION__CYCLES_WIDTH 6
 #define ANNOTATION__MINMAX_CYCLES_WIDTH 19
@@ -171,6 +118,8 @@ struct disasm_line {
 	struct annotation_line	 al;
 };
 
+void annotation_line__add(struct annotation_line *al, struct list_head *head);
+
 static inline double annotation_data__percent(struct annotation_data *data,
 					      unsigned int which)
 {
@@ -212,7 +161,6 @@ static inline bool disasm_line__has_local_offset(const struct disasm_line *dl)
  */
 bool disasm_line__is_valid_local_jump(struct disasm_line *dl, struct symbol *sym);
 
-void disasm_line__free(struct disasm_line *dl);
 struct annotation_line *
 annotation_line__next(struct annotation_line *pos, struct list_head *head);
 
@@ -235,7 +183,6 @@ int __annotation__scnprintf_samples_period(struct annotation *notes,
 					   struct evsel *evsel,
 					   bool show_freq);
 
-int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name);
 size_t disasm__fprintf(struct list_head *head, FILE *fp);
 void symbol__calc_percent(struct symbol *sym, struct evsel *evsel);
 
@@ -299,12 +246,14 @@ struct cyc_hist {
  * 		  we have more than a group in a evlist, where we will want
  * 		  to see each group separately, that is why symbol__annotate2()
  * 		  sets src->nr_histograms to evsel->nr_members.
- * @offsets: Array of annotation_line to be accessed by offset.
  * @samples: Hash map of sym_hist_entry.  Keyed by event index and offset in symbol.
+ * @nr_events: Number of events in the current output.
  * @nr_entries: Number of annotated_line in the source list.
  * @nr_asm_entries: Number of annotated_line with actual asm instruction in the
  * 		    source list.
- * @max_line_len: Maximum length of objdump output in an annotated_line.
+ * @max_jump_sources: Maximum number of jump instructions targeting to the same
+ * 		      instruction.
+ * @widths: Precalculated width of each column in the TUI output.
  *
  * disasm_lines are allocated, percentages calculated and all sorted by percentage
  * when the annotation is about to be presented, so the percentages are for
@@ -315,14 +264,27 @@ struct cyc_hist {
 struct annotated_source {
 	struct list_head	source;
 	struct sym_hist		*histograms;
-	struct annotation_line	**offsets;
 	struct hashmap	   	*samples;
 	int    			nr_histograms;
+	int    			nr_events;
 	int			nr_entries;
 	int			nr_asm_entries;
-	u16			max_line_len;
+	int			max_jump_sources;
+	u64			start;
+	struct {
+		u8		addr;
+		u8		jumps;
+		u8		target;
+		u8		min_addr;
+		u8		max_addr;
+		u8		max_ins_name;
+		u16		max_line_len;
+	} widths;
 };
 
+struct annotation_line *annotated_source__get_line(struct annotated_source *src,
+						   s64 offset);
+
 /**
  * struct annotated_branch - basic block and IPC information for a symbol.
  *
@@ -351,17 +313,6 @@ struct annotated_branch {
 };
 
 struct LOCKABLE annotation {
-	u64			start;
-	int			nr_events;
-	int			max_jump_sources;
-	struct {
-		u8		addr;
-		u8		jumps;
-		u8		target;
-		u8		min_addr;
-		u8		max_addr;
-		u8		max_ins_name;
-	} widths;
 	struct annotated_source *src;
 	struct annotated_branch *branch;
 };
@@ -385,7 +336,7 @@ static inline int annotation__cycles_width(struct annotation *notes)
 
 static inline int annotation__pcnt_width(struct annotation *notes)
 {
-	return (symbol_conf.show_total_period ? 12 : 7) * notes->nr_events;
+	return (symbol_conf.show_total_period ? 12 : 7) * notes->src->nr_events;
 }
 
 static inline bool annotation_line__filter(struct annotation_line *al)
@@ -393,10 +344,7 @@ static inline bool annotation_line__filter(struct annotation_line *al)
 	return annotate_opts.hide_src_code && al->offset == -1;
 }
 
-void annotation__set_offsets(struct annotation *notes, s64 size);
-void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym);
 void annotation__update_column_widths(struct annotation *notes);
-void annotation__init_column_widths(struct annotation *notes, struct symbol *sym);
 void annotation__toggle_full_addr(struct annotation *notes, struct map_symbol *ms);
 
 static inline struct sym_hist *annotated_source__histogram(struct annotated_source *src, int idx)
@@ -511,15 +459,19 @@ int annotate_check_args(void);
  * @reg1: First register in the operand
  * @reg2: Second register in the operand
  * @offset: Memory access offset in the operand
+ * @segment: Segment selector register
  * @mem_ref: Whether the operand accesses memory
  * @multi_regs: Whether the second register is used
+ * @imm: Whether the operand is an immediate value (in offset)
  */
 struct annotated_op_loc {
 	int reg1;
 	int reg2;
 	int offset;
+	u8 segment;
 	bool mem_ref;
 	bool multi_regs;
+	bool imm;
 };
 
 enum annotated_insn_ops {
@@ -529,6 +481,17 @@ enum annotated_insn_ops {
 	INSN_OP_MAX,
 };
 
+enum annotated_x86_segment {
+	INSN_SEG_NONE = 0,
+
+	INSN_SEG_X86_CS,
+	INSN_SEG_X86_DS,
+	INSN_SEG_X86_ES,
+	INSN_SEG_X86_FS,
+	INSN_SEG_X86_GS,
+	INSN_SEG_X86_SS,
+};
+
 /**
  * struct annotated_insn_loc - Location info of instruction
  * @ops: Array of location info for source and target operands
@@ -561,4 +524,20 @@ extern struct list_head ann_insn_stat;
 u64 annotate_calc_pcrel(struct map_symbol *ms, u64 ip, int offset,
 			struct disasm_line *dl);
 
+/**
+ * struct annotated_basic_block - Basic block of instructions
+ * @list: List node
+ * @begin: start instruction in the block
+ * @end: end instruction in the block
+ */
+struct annotated_basic_block {
+	struct list_head list;
+	struct disasm_line *begin;
+	struct disasm_line *end;
+};
+
+/* Get a list of basic blocks from src to dst addresses */
+int annotate_get_basic_blocks(struct symbol *sym, s64 src, s64 dst,
+			      struct list_head *head);
+
 #endif	/* __PERF_ANNOTATE_H */
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 3684e6009b6350..cfa2153d4611dd 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -174,7 +174,7 @@ void auxtrace_mmap_params__set_idx(struct auxtrace_mmap_params *mp,
 				   struct evlist *evlist,
 				   struct evsel *evsel, int idx)
 {
-	bool per_cpu = !perf_cpu_map__has_any_cpu_or_is_empty(evlist->core.user_requested_cpus);
+	bool per_cpu = !perf_cpu_map__has_any_cpu(evlist->core.user_requested_cpus);
 
 	mp->mmap_needed = evsel->needs_auxtrace_mmap;
 
@@ -648,7 +648,7 @@ int auxtrace_parse_snapshot_options(struct auxtrace_record *itr,
 
 static int evlist__enable_event_idx(struct evlist *evlist, struct evsel *evsel, int idx)
 {
-	bool per_cpu_mmaps = !perf_cpu_map__has_any_cpu_or_is_empty(evlist->core.user_requested_cpus);
+	bool per_cpu_mmaps = !perf_cpu_map__has_any_cpu(evlist->core.user_requested_cpus);
 
 	if (per_cpu_mmaps) {
 		struct perf_cpu evlist_cpu = perf_cpu_map__cpu(evlist->core.all_cpus, idx);
@@ -1466,6 +1466,7 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts,
 	char *endptr;
 	bool period_type_set = false;
 	bool period_set = false;
+	bool iy = false;
 
 	synth_opts->set = true;
 
@@ -1484,6 +1485,7 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts,
 		switch (*p++) {
 		case 'i':
 		case 'y':
+			iy = true;
 			if (p[-1] == 'y')
 				synth_opts->cycles = true;
 			else
@@ -1649,7 +1651,7 @@ int itrace_do_parse_synth_opts(struct itrace_synth_opts *synth_opts,
 		}
 	}
 out:
-	if (synth_opts->instructions || synth_opts->cycles) {
+	if (iy) {
 		if (!period_type_set)
 			synth_opts->period_type =
 					PERF_ITRACE_DEFAULT_PERIOD_TYPE;
diff --git a/tools/perf/util/bpf_kwork.c b/tools/perf/util/bpf_kwork.c
index 6eb2c78fd7f4a3..44f0f708a15d6a 100644
--- a/tools/perf/util/bpf_kwork.c
+++ b/tools/perf/util/bpf_kwork.c
@@ -147,12 +147,12 @@ static bool valid_kwork_class_type(enum kwork_class_type type)
 
 static int setup_filters(struct perf_kwork *kwork)
 {
-	u8 val = 1;
-	int i, nr_cpus, key, fd;
-	struct perf_cpu_map *map;
-
 	if (kwork->cpu_list != NULL) {
-		fd = bpf_map__fd(skel->maps.perf_kwork_cpu_filter);
+		int idx, nr_cpus;
+		struct perf_cpu_map *map;
+		struct perf_cpu cpu;
+		int fd = bpf_map__fd(skel->maps.perf_kwork_cpu_filter);
+
 		if (fd < 0) {
 			pr_debug("Invalid cpu filter fd\n");
 			return -1;
@@ -165,8 +165,8 @@ static int setup_filters(struct perf_kwork *kwork)
 		}
 
 		nr_cpus = libbpf_num_possible_cpus();
-		for (i = 0; i < perf_cpu_map__nr(map); i++) {
-			struct perf_cpu cpu = perf_cpu_map__cpu(map, i);
+		perf_cpu_map__for_each_cpu(cpu, idx, map) {
+			u8 val = 1;
 
 			if (cpu.cpu >= nr_cpus) {
 				perf_cpu_map__put(map);
@@ -181,6 +181,8 @@ static int setup_filters(struct perf_kwork *kwork)
 	}
 
 	if (kwork->profile_name != NULL) {
+		int key, fd;
+
 		if (strlen(kwork->profile_name) >= MAX_KWORKNAME) {
 			pr_err("Requested name filter %s too large, limit to %d\n",
 			       kwork->profile_name, MAX_KWORKNAME - 1);
diff --git a/tools/perf/util/bpf_kwork_top.c b/tools/perf/util/bpf_kwork_top.c
index 035e02272790a3..22a3b00a1e23f9 100644
--- a/tools/perf/util/bpf_kwork_top.c
+++ b/tools/perf/util/bpf_kwork_top.c
@@ -122,11 +122,11 @@ static bool valid_kwork_class_type(enum kwork_class_type type)
 
 static int setup_filters(struct perf_kwork *kwork)
 {
-	u8 val = 1;
-	int i, nr_cpus, fd;
-	struct perf_cpu_map *map;
-
 	if (kwork->cpu_list) {
+		int idx, nr_cpus, fd;
+		struct perf_cpu_map *map;
+		struct perf_cpu cpu;
+
 		fd = bpf_map__fd(skel->maps.kwork_top_cpu_filter);
 		if (fd < 0) {
 			pr_debug("Invalid cpu filter fd\n");
@@ -140,8 +140,8 @@ static int setup_filters(struct perf_kwork *kwork)
 		}
 
 		nr_cpus = libbpf_num_possible_cpus();
-		for (i = 0; i < perf_cpu_map__nr(map); i++) {
-			struct perf_cpu cpu = perf_cpu_map__cpu(map, i);
+		perf_cpu_map__for_each_cpu(cpu, idx, map) {
+			u8 val = 1;
 
 			if (cpu.cpu >= nr_cpus) {
 				perf_cpu_map__put(map);
diff --git a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
index 2872f9bc07850b..0acbd74e8c7609 100644
--- a/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
+++ b/tools/perf/util/bpf_skel/augmented_raw_syscalls.bpf.c
@@ -341,6 +341,27 @@ failure:
 	return 1; /* Failure: don't filter */
 }
 
+SEC("tp/syscalls/sys_enter_nanosleep")
+int sys_enter_nanosleep(struct syscall_enter_args *args)
+{
+	struct augmented_args_payload *augmented_args = augmented_args_payload();
+	const void *req_arg = (const void *)args->args[0];
+	unsigned int len = sizeof(augmented_args->args);
+	__u32 size = sizeof(struct timespec64);
+
+        if (augmented_args == NULL)
+		goto failure;
+
+	if (size > sizeof(augmented_args->__data))
+                goto failure;
+
+	bpf_probe_read_user(&augmented_args->__data, size, req_arg);
+
+	return augmented__output(args, augmented_args, len + size);
+failure:
+	return 1; /* Failure: don't filter */
+}
+
 static pid_t getpid(void)
 {
 	return bpf_get_current_pid_tgid();
diff --git a/tools/perf/util/bpf_skel/bench_uprobe.bpf.c b/tools/perf/util/bpf_skel/bench_uprobe.bpf.c
index 2c55896bb33c31..a01c7f791fcde4 100644
--- a/tools/perf/util/bpf_skel/bench_uprobe.bpf.c
+++ b/tools/perf/util/bpf_skel/bench_uprobe.bpf.c
@@ -4,6 +4,7 @@
 #include <bpf/bpf_tracing.h>
 
 unsigned int nr_uprobes;
+unsigned int nr_uretprobes;
 
 SEC("uprobe")
 int BPF_UPROBE(empty)
@@ -20,4 +21,19 @@ int BPF_UPROBE(trace_printk)
 	return 0;
 }
 
+SEC("uretprobe")
+int BPF_URETPROBE(empty_ret)
+{
+	return 0;
+}
+
+SEC("uretprobe")
+int BPF_URETPROBE(trace_printk_ret)
+{
+	char fmt[] = "perf bench uretprobe %u";
+
+	bpf_trace_printk(fmt, sizeof(fmt), ++nr_uretprobes);
+	return 0;
+}
+
 char LICENSE[] SEC("license") = "Dual BSD/GPL";
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 03c64b85383b8b..864bc26b6b4610 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -327,48 +327,56 @@ static int write_buildid(const char *name, size_t name_len, struct build_id *bid
 	return write_padded(fd, name, name_len + 1, len);
 }
 
-static int machine__write_buildid_table(struct machine *machine,
-					struct feat_fd *fd)
+struct machine__write_buildid_table_cb_args {
+	struct machine *machine;
+	struct feat_fd *fd;
+	u16 kmisc, umisc;
+};
+
+static int machine__write_buildid_table_cb(struct dso *dso, void *data)
 {
-	int err = 0;
-	struct dso *pos;
-	u16 kmisc = PERF_RECORD_MISC_KERNEL,
-	    umisc = PERF_RECORD_MISC_USER;
+	struct machine__write_buildid_table_cb_args *args = data;
+	const char *name;
+	size_t name_len;
+	bool in_kernel = false;
 
-	if (!machine__is_host(machine)) {
-		kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
-		umisc = PERF_RECORD_MISC_GUEST_USER;
-	}
+	if (!dso->has_build_id)
+		return 0;
 
-	dsos__for_each_with_build_id(pos, &machine->dsos.head) {
-		const char *name;
-		size_t name_len;
-		bool in_kernel = false;
+	if (!dso->hit && !dso__is_vdso(dso))
+		return 0;
 
-		if (!pos->hit && !dso__is_vdso(pos))
-			continue;
+	if (dso__is_vdso(dso)) {
+		name = dso->short_name;
+		name_len = dso->short_name_len;
+	} else if (dso__is_kcore(dso)) {
+		name = args->machine->mmap_name;
+		name_len = strlen(name);
+	} else {
+		name = dso->long_name;
+		name_len = dso->long_name_len;
+	}
 
-		if (dso__is_vdso(pos)) {
-			name = pos->short_name;
-			name_len = pos->short_name_len;
-		} else if (dso__is_kcore(pos)) {
-			name = machine->mmap_name;
-			name_len = strlen(name);
-		} else {
-			name = pos->long_name;
-			name_len = pos->long_name_len;
-		}
+	in_kernel = dso->kernel || is_kernel_module(name, PERF_RECORD_MISC_CPUMODE_UNKNOWN);
+	return write_buildid(name, name_len, &dso->bid, args->machine->pid,
+			     in_kernel ? args->kmisc : args->umisc, args->fd);
+}
 
-		in_kernel = pos->kernel ||
-				is_kernel_module(name,
-					PERF_RECORD_MISC_CPUMODE_UNKNOWN);
-		err = write_buildid(name, name_len, &pos->bid, machine->pid,
-				    in_kernel ? kmisc : umisc, fd);
-		if (err)
-			break;
+static int machine__write_buildid_table(struct machine *machine, struct feat_fd *fd)
+{
+	struct machine__write_buildid_table_cb_args args = {
+		.machine = machine,
+		.fd = fd,
+		.kmisc = PERF_RECORD_MISC_KERNEL,
+		.umisc = PERF_RECORD_MISC_USER,
+	};
+
+	if (!machine__is_host(machine)) {
+		args.kmisc = PERF_RECORD_MISC_GUEST_KERNEL;
+		args.umisc = PERF_RECORD_MISC_GUEST_USER;
 	}
 
-	return err;
+	return dsos__for_each_dso(&machine->dsos, machine__write_buildid_table_cb, &args);
 }
 
 int perf_session__write_buildid_table(struct perf_session *session,
@@ -390,42 +398,6 @@ int perf_session__write_buildid_table(struct perf_session *session,
 	return err;
 }
 
-static int __dsos__hit_all(struct list_head *head)
-{
-	struct dso *pos;
-
-	list_for_each_entry(pos, head, node)
-		pos->hit = true;
-
-	return 0;
-}
-
-static int machine__hit_all_dsos(struct machine *machine)
-{
-	return __dsos__hit_all(&machine->dsos.head);
-}
-
-int dsos__hit_all(struct perf_session *session)
-{
-	struct rb_node *nd;
-	int err;
-
-	err = machine__hit_all_dsos(&session->machines.host);
-	if (err)
-		return err;
-
-	for (nd = rb_first_cached(&session->machines.guests); nd;
-	     nd = rb_next(nd)) {
-		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-
-		err = machine__hit_all_dsos(pos);
-		if (err)
-			return err;
-	}
-
-	return 0;
-}
-
 void disable_buildid_cache(void)
 {
 	no_buildid_cache = true;
@@ -992,7 +964,7 @@ int perf_session__cache_build_ids(struct perf_session *session)
 
 static bool machine__read_build_ids(struct machine *machine, bool with_hits)
 {
-	return __dsos__read_build_ids(&machine->dsos.head, with_hits);
+	return dsos__read_build_ids(&machine->dsos, with_hits);
 }
 
 bool perf_session__read_build_ids(struct perf_session *session, bool with_hits)
diff --git a/tools/perf/util/build-id.h b/tools/perf/util/build-id.h
index 4e3a1169379b8c..3fa8bffb07cae4 100644
--- a/tools/perf/util/build-id.h
+++ b/tools/perf/util/build-id.h
@@ -39,8 +39,6 @@ int build_id__mark_dso_hit(struct perf_tool *tool, union perf_event *event,
 			   struct perf_sample *sample, struct evsel *evsel,
 			   struct machine *machine);
 
-int dsos__hit_all(struct perf_session *session);
-
 int perf_event__inject_buildid(struct perf_tool *tool, union perf_event *event,
 			       struct perf_sample *sample, struct evsel *evsel,
 			       struct machine *machine);
diff --git a/tools/perf/util/cpumap.c b/tools/perf/util/cpumap.c
index 356e30c42cd838..6a270d640acb90 100644
--- a/tools/perf/util/cpumap.c
+++ b/tools/perf/util/cpumap.c
@@ -655,10 +655,10 @@ static char hex_char(unsigned char val)
 
 size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size)
 {
-	int i, cpu;
+	int idx;
 	char *ptr = buf;
 	unsigned char *bitmap;
-	struct perf_cpu last_cpu = perf_cpu_map__cpu(map, perf_cpu_map__nr(map) - 1);
+	struct perf_cpu c, last_cpu = perf_cpu_map__max(map);
 
 	if (buf == NULL)
 		return 0;
@@ -669,12 +669,10 @@ size_t cpu_map__snprint_mask(struct perf_cpu_map *map, char *buf, size_t size)
 		return 0;
 	}
 
-	for (i = 0; i < perf_cpu_map__nr(map); i++) {
-		cpu = perf_cpu_map__cpu(map, i).cpu;
-		bitmap[cpu / 8] |= 1 << (cpu % 8);
-	}
+	perf_cpu_map__for_each_cpu(c, idx, map)
+		bitmap[c.cpu / 8] |= 1 << (c.cpu % 8);
 
-	for (cpu = last_cpu.cpu / 4 * 4; cpu >= 0; cpu -= 4) {
+	for (int cpu = last_cpu.cpu / 4 * 4; cpu >= 0; cpu -= 4) {
 		unsigned char bits = bitmap[cpu / 8];
 
 		if (cpu % 8)
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index c39ee0fcb8cf1d..d633d15329fa09 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -41,6 +41,7 @@ static int redirect_to_stderr;
 int debug_data_convert;
 static FILE *_debug_file;
 bool debug_display_time;
+int debug_type_profile;
 
 FILE *debug_file(void)
 {
@@ -231,6 +232,7 @@ static struct sublevel_option debug_opts[] = {
 	{ .name = "data-convert",	.value_ptr = &debug_data_convert },
 	{ .name = "perf-event-open",	.value_ptr = &debug_peo_args },
 	{ .name = "kmaps",		.value_ptr = &debug_kmaps },
+	{ .name = "type-profile",	.value_ptr = &debug_type_profile },
 	{ .name = NULL, }
 };
 
@@ -270,6 +272,7 @@ int perf_quiet_option(void)
 	redirect_to_stderr = 0;
 	debug_peo_args = 0;
 	debug_kmaps = 0;
+	debug_type_profile = 0;
 
 	return 0;
 }
diff --git a/tools/perf/util/debug.h b/tools/perf/util/debug.h
index 35a7a5ae762e6f..a4026d1fd6a311 100644
--- a/tools/perf/util/debug.h
+++ b/tools/perf/util/debug.h
@@ -14,6 +14,7 @@ extern int debug_peo_args;
 extern bool quiet, dump_trace;
 extern int debug_ordered_events;
 extern int debug_data_convert;
+extern int debug_type_profile;
 
 #ifndef pr_fmt
 #define pr_fmt(fmt) fmt
diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
new file mode 100644
index 00000000000000..6d1125e687b71e
--- /dev/null
+++ b/tools/perf/util/disasm.c
@@ -0,0 +1,1837 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <ctype.h>
+#include <errno.h>
+#include <fcntl.h>
+#include <inttypes.h>
+#include <libgen.h>
+#include <regex.h>
+#include <stdlib.h>
+#include <unistd.h>
+
+#include <linux/string.h>
+#include <subcmd/run-command.h>
+
+#include "annotate.h"
+#include "build-id.h"
+#include "debug.h"
+#include "disasm.h"
+#include "dso.h"
+#include "env.h"
+#include "evsel.h"
+#include "map.h"
+#include "maps.h"
+#include "namespaces.h"
+#include "srcline.h"
+#include "symbol.h"
+#include "util.h"
+
+static regex_t	 file_lineno;
+
+/* These can be referred from the arch-dependent code */
+static struct ins_ops call_ops;
+static struct ins_ops dec_ops;
+static struct ins_ops jump_ops;
+static struct ins_ops mov_ops;
+static struct ins_ops nop_ops;
+static struct ins_ops lock_ops;
+static struct ins_ops ret_ops;
+
+static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops, int max_ins_name);
+static int call__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops, int max_ins_name);
+
+static void ins__sort(struct arch *arch);
+static int disasm_line__parse(char *line, const char **namep, char **rawp);
+
+static __attribute__((constructor)) void symbol__init_regexpr(void)
+{
+	regcomp(&file_lineno, "^/[^:]+:([0-9]+)", REG_EXTENDED);
+}
+
+static int arch__grow_instructions(struct arch *arch)
+{
+	struct ins *new_instructions;
+	size_t new_nr_allocated;
+
+	if (arch->nr_instructions_allocated == 0 && arch->instructions)
+		goto grow_from_non_allocated_table;
+
+	new_nr_allocated = arch->nr_instructions_allocated + 128;
+	new_instructions = realloc(arch->instructions, new_nr_allocated * sizeof(struct ins));
+	if (new_instructions == NULL)
+		return -1;
+
+out_update_instructions:
+	arch->instructions = new_instructions;
+	arch->nr_instructions_allocated = new_nr_allocated;
+	return 0;
+
+grow_from_non_allocated_table:
+	new_nr_allocated = arch->nr_instructions + 128;
+	new_instructions = calloc(new_nr_allocated, sizeof(struct ins));
+	if (new_instructions == NULL)
+		return -1;
+
+	memcpy(new_instructions, arch->instructions, arch->nr_instructions);
+	goto out_update_instructions;
+}
+
+static int arch__associate_ins_ops(struct arch* arch, const char *name, struct ins_ops *ops)
+{
+	struct ins *ins;
+
+	if (arch->nr_instructions == arch->nr_instructions_allocated &&
+	    arch__grow_instructions(arch))
+		return -1;
+
+	ins = &arch->instructions[arch->nr_instructions];
+	ins->name = strdup(name);
+	if (!ins->name)
+		return -1;
+
+	ins->ops  = ops;
+	arch->nr_instructions++;
+
+	ins__sort(arch);
+	return 0;
+}
+
+#include "arch/arc/annotate/instructions.c"
+#include "arch/arm/annotate/instructions.c"
+#include "arch/arm64/annotate/instructions.c"
+#include "arch/csky/annotate/instructions.c"
+#include "arch/loongarch/annotate/instructions.c"
+#include "arch/mips/annotate/instructions.c"
+#include "arch/x86/annotate/instructions.c"
+#include "arch/powerpc/annotate/instructions.c"
+#include "arch/riscv64/annotate/instructions.c"
+#include "arch/s390/annotate/instructions.c"
+#include "arch/sparc/annotate/instructions.c"
+
+static struct arch architectures[] = {
+	{
+		.name = "arc",
+		.init = arc__annotate_init,
+	},
+	{
+		.name = "arm",
+		.init = arm__annotate_init,
+	},
+	{
+		.name = "arm64",
+		.init = arm64__annotate_init,
+	},
+	{
+		.name = "csky",
+		.init = csky__annotate_init,
+	},
+	{
+		.name = "mips",
+		.init = mips__annotate_init,
+		.objdump = {
+			.comment_char = '#',
+		},
+	},
+	{
+		.name = "x86",
+		.init = x86__annotate_init,
+		.instructions = x86__instructions,
+		.nr_instructions = ARRAY_SIZE(x86__instructions),
+		.insn_suffix = "bwlq",
+		.objdump =  {
+			.comment_char = '#',
+			.register_char = '%',
+			.memory_ref_char = '(',
+			.imm_char = '$',
+		},
+	},
+	{
+		.name = "powerpc",
+		.init = powerpc__annotate_init,
+	},
+	{
+		.name = "riscv64",
+		.init = riscv64__annotate_init,
+	},
+	{
+		.name = "s390",
+		.init = s390__annotate_init,
+		.objdump =  {
+			.comment_char = '#',
+		},
+	},
+	{
+		.name = "sparc",
+		.init = sparc__annotate_init,
+		.objdump = {
+			.comment_char = '#',
+		},
+	},
+	{
+		.name = "loongarch",
+		.init = loongarch__annotate_init,
+		.objdump = {
+			.comment_char = '#',
+		},
+	},
+};
+
+static int arch__key_cmp(const void *name, const void *archp)
+{
+	const struct arch *arch = archp;
+
+	return strcmp(name, arch->name);
+}
+
+static int arch__cmp(const void *a, const void *b)
+{
+	const struct arch *aa = a;
+	const struct arch *ab = b;
+
+	return strcmp(aa->name, ab->name);
+}
+
+static void arch__sort(void)
+{
+	const int nmemb = ARRAY_SIZE(architectures);
+
+	qsort(architectures, nmemb, sizeof(struct arch), arch__cmp);
+}
+
+struct arch *arch__find(const char *name)
+{
+	const int nmemb = ARRAY_SIZE(architectures);
+	static bool sorted;
+
+	if (!sorted) {
+		arch__sort();
+		sorted = true;
+	}
+
+	return bsearch(name, architectures, nmemb, sizeof(struct arch), arch__key_cmp);
+}
+
+bool arch__is(struct arch *arch, const char *name)
+{
+	return !strcmp(arch->name, name);
+}
+
+static void ins_ops__delete(struct ins_operands *ops)
+{
+	if (ops == NULL)
+		return;
+	zfree(&ops->source.raw);
+	zfree(&ops->source.name);
+	zfree(&ops->target.raw);
+	zfree(&ops->target.name);
+}
+
+static int ins__raw_scnprintf(struct ins *ins, char *bf, size_t size,
+			      struct ins_operands *ops, int max_ins_name)
+{
+	return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->raw);
+}
+
+int ins__scnprintf(struct ins *ins, char *bf, size_t size,
+		   struct ins_operands *ops, int max_ins_name)
+{
+	if (ins->ops->scnprintf)
+		return ins->ops->scnprintf(ins, bf, size, ops, max_ins_name);
+
+	return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
+}
+
+bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2)
+{
+	if (!arch || !arch->ins_is_fused)
+		return false;
+
+	return arch->ins_is_fused(arch, ins1, ins2);
+}
+
+static int call__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
+{
+	char *endptr, *tok, *name;
+	struct map *map = ms->map;
+	struct addr_map_symbol target = {
+		.ms = { .map = map, },
+	};
+
+	ops->target.addr = strtoull(ops->raw, &endptr, 16);
+
+	name = strchr(endptr, '<');
+	if (name == NULL)
+		goto indirect_call;
+
+	name++;
+
+	if (arch->objdump.skip_functions_char &&
+	    strchr(name, arch->objdump.skip_functions_char))
+		return -1;
+
+	tok = strchr(name, '>');
+	if (tok == NULL)
+		return -1;
+
+	*tok = '\0';
+	ops->target.name = strdup(name);
+	*tok = '>';
+
+	if (ops->target.name == NULL)
+		return -1;
+find_target:
+	target.addr = map__objdump_2mem(map, ops->target.addr);
+
+	if (maps__find_ams(ms->maps, &target) == 0 &&
+	    map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr)
+		ops->target.sym = target.ms.sym;
+
+	return 0;
+
+indirect_call:
+	tok = strchr(endptr, '*');
+	if (tok != NULL) {
+		endptr++;
+
+		/* Indirect call can use a non-rip register and offset: callq  *0x8(%rbx).
+		 * Do not parse such instruction.  */
+		if (strstr(endptr, "(%r") == NULL)
+			ops->target.addr = strtoull(endptr, NULL, 16);
+	}
+	goto find_target;
+}
+
+static int call__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops, int max_ins_name)
+{
+	if (ops->target.sym)
+		return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.sym->name);
+
+	if (ops->target.addr == 0)
+		return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
+
+	if (ops->target.name)
+		return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.name);
+
+	return scnprintf(bf, size, "%-*s *%" PRIx64, max_ins_name, ins->name, ops->target.addr);
+}
+
+static struct ins_ops call_ops = {
+	.parse	   = call__parse,
+	.scnprintf = call__scnprintf,
+};
+
+bool ins__is_call(const struct ins *ins)
+{
+	return ins->ops == &call_ops || ins->ops == &s390_call_ops || ins->ops == &loongarch_call_ops;
+}
+
+/*
+ * Prevents from matching commas in the comment section, e.g.:
+ * ffff200008446e70:       b.cs    ffff2000084470f4 <generic_exec_single+0x314>  // b.hs, b.nlast
+ *
+ * and skip comma as part of function arguments, e.g.:
+ * 1d8b4ac <linemap_lookup(line_maps const*, unsigned int)+0xcc>
+ */
+static inline const char *validate_comma(const char *c, struct ins_operands *ops)
+{
+	if (ops->jump.raw_comment && c > ops->jump.raw_comment)
+		return NULL;
+
+	if (ops->jump.raw_func_start && c > ops->jump.raw_func_start)
+		return NULL;
+
+	return c;
+}
+
+static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
+{
+	struct map *map = ms->map;
+	struct symbol *sym = ms->sym;
+	struct addr_map_symbol target = {
+		.ms = { .map = map, },
+	};
+	const char *c = strchr(ops->raw, ',');
+	u64 start, end;
+
+	ops->jump.raw_comment = strchr(ops->raw, arch->objdump.comment_char);
+	ops->jump.raw_func_start = strchr(ops->raw, '<');
+
+	c = validate_comma(c, ops);
+
+	/*
+	 * Examples of lines to parse for the _cpp_lex_token@@Base
+	 * function:
+	 *
+	 * 1159e6c: jne    115aa32 <_cpp_lex_token@@Base+0xf92>
+	 * 1159e8b: jne    c469be <cpp_named_operator2name@@Base+0xa72>
+	 *
+	 * The first is a jump to an offset inside the same function,
+	 * the second is to another function, i.e. that 0xa72 is an
+	 * offset in the cpp_named_operator2name@@base function.
+	 */
+	/*
+	 * skip over possible up to 2 operands to get to address, e.g.:
+	 * tbnz	 w0, #26, ffff0000083cd190 <security_file_permission+0xd0>
+	 */
+	if (c++ != NULL) {
+		ops->target.addr = strtoull(c, NULL, 16);
+		if (!ops->target.addr) {
+			c = strchr(c, ',');
+			c = validate_comma(c, ops);
+			if (c++ != NULL)
+				ops->target.addr = strtoull(c, NULL, 16);
+		}
+	} else {
+		ops->target.addr = strtoull(ops->raw, NULL, 16);
+	}
+
+	target.addr = map__objdump_2mem(map, ops->target.addr);
+	start = map__unmap_ip(map, sym->start);
+	end = map__unmap_ip(map, sym->end);
+
+	ops->target.outside = target.addr < start || target.addr > end;
+
+	/*
+	 * FIXME: things like this in _cpp_lex_token (gcc's cc1 program):
+
+		cpp_named_operator2name@@Base+0xa72
+
+	 * Point to a place that is after the cpp_named_operator2name
+	 * boundaries, i.e.  in the ELF symbol table for cc1
+	 * cpp_named_operator2name is marked as being 32-bytes long, but it in
+	 * fact is much larger than that, so we seem to need a symbols__find()
+	 * routine that looks for >= current->start and  < next_symbol->start,
+	 * possibly just for C++ objects?
+	 *
+	 * For now lets just make some progress by marking jumps to outside the
+	 * current function as call like.
+	 *
+	 * Actual navigation will come next, with further understanding of how
+	 * the symbol searching and disassembly should be done.
+	 */
+	if (maps__find_ams(ms->maps, &target) == 0 &&
+	    map__rip_2objdump(target.ms.map, map__map_ip(target.ms.map, target.addr)) == ops->target.addr)
+		ops->target.sym = target.ms.sym;
+
+	if (!ops->target.outside) {
+		ops->target.offset = target.addr - start;
+		ops->target.offset_avail = true;
+	} else {
+		ops->target.offset_avail = false;
+	}
+
+	return 0;
+}
+
+static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops, int max_ins_name)
+{
+	const char *c;
+
+	if (!ops->target.addr || ops->target.offset < 0)
+		return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
+
+	if (ops->target.outside && ops->target.sym != NULL)
+		return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name, ops->target.sym->name);
+
+	c = strchr(ops->raw, ',');
+	c = validate_comma(c, ops);
+
+	if (c != NULL) {
+		const char *c2 = strchr(c + 1, ',');
+
+		c2 = validate_comma(c2, ops);
+		/* check for 3-op insn */
+		if (c2 != NULL)
+			c = c2;
+		c++;
+
+		/* mirror arch objdump's space-after-comma style */
+		if (*c == ' ')
+			c++;
+	}
+
+	return scnprintf(bf, size, "%-*s %.*s%" PRIx64, max_ins_name,
+			 ins->name, c ? c - ops->raw : 0, ops->raw,
+			 ops->target.offset);
+}
+
+static void jump__delete(struct ins_operands *ops __maybe_unused)
+{
+	/*
+	 * The ops->jump.raw_comment and ops->jump.raw_func_start belong to the
+	 * raw string, don't free them.
+	 */
+}
+
+static struct ins_ops jump_ops = {
+	.free	   = jump__delete,
+	.parse	   = jump__parse,
+	.scnprintf = jump__scnprintf,
+};
+
+bool ins__is_jump(const struct ins *ins)
+{
+	return ins->ops == &jump_ops || ins->ops == &loongarch_jump_ops;
+}
+
+static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep)
+{
+	char *endptr, *name, *t;
+
+	if (strstr(raw, "(%rip)") == NULL)
+		return 0;
+
+	*addrp = strtoull(comment, &endptr, 16);
+	if (endptr == comment)
+		return 0;
+	name = strchr(endptr, '<');
+	if (name == NULL)
+		return -1;
+
+	name++;
+
+	t = strchr(name, '>');
+	if (t == NULL)
+		return 0;
+
+	*t = '\0';
+	*namep = strdup(name);
+	*t = '>';
+
+	return 0;
+}
+
+static int lock__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
+{
+	ops->locked.ops = zalloc(sizeof(*ops->locked.ops));
+	if (ops->locked.ops == NULL)
+		return 0;
+
+	if (disasm_line__parse(ops->raw, &ops->locked.ins.name, &ops->locked.ops->raw) < 0)
+		goto out_free_ops;
+
+	ops->locked.ins.ops = ins__find(arch, ops->locked.ins.name);
+
+	if (ops->locked.ins.ops == NULL)
+		goto out_free_ops;
+
+	if (ops->locked.ins.ops->parse &&
+	    ops->locked.ins.ops->parse(arch, ops->locked.ops, ms) < 0)
+		goto out_free_ops;
+
+	return 0;
+
+out_free_ops:
+	zfree(&ops->locked.ops);
+	return 0;
+}
+
+static int lock__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops, int max_ins_name)
+{
+	int printed;
+
+	if (ops->locked.ins.ops == NULL)
+		return ins__raw_scnprintf(ins, bf, size, ops, max_ins_name);
+
+	printed = scnprintf(bf, size, "%-*s ", max_ins_name, ins->name);
+	return printed + ins__scnprintf(&ops->locked.ins, bf + printed,
+					size - printed, ops->locked.ops, max_ins_name);
+}
+
+static void lock__delete(struct ins_operands *ops)
+{
+	struct ins *ins = &ops->locked.ins;
+
+	if (ins->ops && ins->ops->free)
+		ins->ops->free(ops->locked.ops);
+	else
+		ins_ops__delete(ops->locked.ops);
+
+	zfree(&ops->locked.ops);
+	zfree(&ops->target.raw);
+	zfree(&ops->target.name);
+}
+
+static struct ins_ops lock_ops = {
+	.free	   = lock__delete,
+	.parse	   = lock__parse,
+	.scnprintf = lock__scnprintf,
+};
+
+/*
+ * Check if the operand has more than one registers like x86 SIB addressing:
+ *   0x1234(%rax, %rbx, 8)
+ *
+ * But it doesn't care segment selectors like %gs:0x5678(%rcx), so just check
+ * the input string after 'memory_ref_char' if exists.
+ */
+static bool check_multi_regs(struct arch *arch, const char *op)
+{
+	int count = 0;
+
+	if (arch->objdump.register_char == 0)
+		return false;
+
+	if (arch->objdump.memory_ref_char) {
+		op = strchr(op, arch->objdump.memory_ref_char);
+		if (op == NULL)
+			return false;
+	}
+
+	while ((op = strchr(op, arch->objdump.register_char)) != NULL) {
+		count++;
+		op++;
+	}
+
+	return count > 1;
+}
+
+static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms __maybe_unused)
+{
+	char *s = strchr(ops->raw, ','), *target, *comment, prev;
+
+	if (s == NULL)
+		return -1;
+
+	*s = '\0';
+
+	/*
+	 * x86 SIB addressing has something like 0x8(%rax, %rcx, 1)
+	 * then it needs to have the closing parenthesis.
+	 */
+	if (strchr(ops->raw, '(')) {
+		*s = ',';
+		s = strchr(ops->raw, ')');
+		if (s == NULL || s[1] != ',')
+			return -1;
+		*++s = '\0';
+	}
+
+	ops->source.raw = strdup(ops->raw);
+	*s = ',';
+
+	if (ops->source.raw == NULL)
+		return -1;
+
+	ops->source.multi_regs = check_multi_regs(arch, ops->source.raw);
+
+	target = skip_spaces(++s);
+	comment = strchr(s, arch->objdump.comment_char);
+
+	if (comment != NULL)
+		s = comment - 1;
+	else
+		s = strchr(s, '\0') - 1;
+
+	while (s > target && isspace(s[0]))
+		--s;
+	s++;
+	prev = *s;
+	*s = '\0';
+
+	ops->target.raw = strdup(target);
+	*s = prev;
+
+	if (ops->target.raw == NULL)
+		goto out_free_source;
+
+	ops->target.multi_regs = check_multi_regs(arch, ops->target.raw);
+
+	if (comment == NULL)
+		return 0;
+
+	comment = skip_spaces(comment);
+	comment__symbol(ops->source.raw, comment + 1, &ops->source.addr, &ops->source.name);
+	comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
+
+	return 0;
+
+out_free_source:
+	zfree(&ops->source.raw);
+	return -1;
+}
+
+static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops, int max_ins_name)
+{
+	return scnprintf(bf, size, "%-*s %s,%s", max_ins_name, ins->name,
+			 ops->source.name ?: ops->source.raw,
+			 ops->target.name ?: ops->target.raw);
+}
+
+static struct ins_ops mov_ops = {
+	.parse	   = mov__parse,
+	.scnprintf = mov__scnprintf,
+};
+
+static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms __maybe_unused)
+{
+	char *target, *comment, *s, prev;
+
+	target = s = ops->raw;
+
+	while (s[0] != '\0' && !isspace(s[0]))
+		++s;
+	prev = *s;
+	*s = '\0';
+
+	ops->target.raw = strdup(target);
+	*s = prev;
+
+	if (ops->target.raw == NULL)
+		return -1;
+
+	comment = strchr(s, arch->objdump.comment_char);
+	if (comment == NULL)
+		return 0;
+
+	comment = skip_spaces(comment);
+	comment__symbol(ops->target.raw, comment + 1, &ops->target.addr, &ops->target.name);
+
+	return 0;
+}
+
+static int dec__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops, int max_ins_name)
+{
+	return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name,
+			 ops->target.name ?: ops->target.raw);
+}
+
+static struct ins_ops dec_ops = {
+	.parse	   = dec__parse,
+	.scnprintf = dec__scnprintf,
+};
+
+static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size,
+			  struct ins_operands *ops __maybe_unused, int max_ins_name)
+{
+	return scnprintf(bf, size, "%-*s", max_ins_name, "nop");
+}
+
+static struct ins_ops nop_ops = {
+	.scnprintf = nop__scnprintf,
+};
+
+static struct ins_ops ret_ops = {
+	.scnprintf = ins__raw_scnprintf,
+};
+
+bool ins__is_nop(const struct ins *ins)
+{
+	return ins->ops == &nop_ops;
+}
+
+bool ins__is_ret(const struct ins *ins)
+{
+	return ins->ops == &ret_ops;
+}
+
+bool ins__is_lock(const struct ins *ins)
+{
+	return ins->ops == &lock_ops;
+}
+
+static int ins__key_cmp(const void *name, const void *insp)
+{
+	const struct ins *ins = insp;
+
+	return strcmp(name, ins->name);
+}
+
+static int ins__cmp(const void *a, const void *b)
+{
+	const struct ins *ia = a;
+	const struct ins *ib = b;
+
+	return strcmp(ia->name, ib->name);
+}
+
+static void ins__sort(struct arch *arch)
+{
+	const int nmemb = arch->nr_instructions;
+
+	qsort(arch->instructions, nmemb, sizeof(struct ins), ins__cmp);
+}
+
+static struct ins_ops *__ins__find(struct arch *arch, const char *name)
+{
+	struct ins *ins;
+	const int nmemb = arch->nr_instructions;
+
+	if (!arch->sorted_instructions) {
+		ins__sort(arch);
+		arch->sorted_instructions = true;
+	}
+
+	ins = bsearch(name, arch->instructions, nmemb, sizeof(struct ins), ins__key_cmp);
+	if (ins)
+		return ins->ops;
+
+	if (arch->insn_suffix) {
+		char tmp[32];
+		char suffix;
+		size_t len = strlen(name);
+
+		if (len == 0 || len >= sizeof(tmp))
+			return NULL;
+
+		suffix = name[len - 1];
+		if (strchr(arch->insn_suffix, suffix) == NULL)
+			return NULL;
+
+		strcpy(tmp, name);
+		tmp[len - 1] = '\0'; /* remove the suffix and check again */
+
+		ins = bsearch(tmp, arch->instructions, nmemb, sizeof(struct ins), ins__key_cmp);
+	}
+	return ins ? ins->ops : NULL;
+}
+
+struct ins_ops *ins__find(struct arch *arch, const char *name)
+{
+	struct ins_ops *ops = __ins__find(arch, name);
+
+	if (!ops && arch->associate_instruction_ops)
+		ops = arch->associate_instruction_ops(arch, name);
+
+	return ops;
+}
+
+static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map_symbol *ms)
+{
+	dl->ins.ops = ins__find(arch, dl->ins.name);
+
+	if (!dl->ins.ops)
+		return;
+
+	if (dl->ins.ops->parse && dl->ins.ops->parse(arch, &dl->ops, ms) < 0)
+		dl->ins.ops = NULL;
+}
+
+static int disasm_line__parse(char *line, const char **namep, char **rawp)
+{
+	char tmp, *name = skip_spaces(line);
+
+	if (name[0] == '\0')
+		return -1;
+
+	*rawp = name + 1;
+
+	while ((*rawp)[0] != '\0' && !isspace((*rawp)[0]))
+		++*rawp;
+
+	tmp = (*rawp)[0];
+	(*rawp)[0] = '\0';
+	*namep = strdup(name);
+
+	if (*namep == NULL)
+		goto out;
+
+	(*rawp)[0] = tmp;
+	*rawp = strim(*rawp);
+
+	return 0;
+
+out:
+	return -1;
+}
+
+static void annotation_line__init(struct annotation_line *al,
+				  struct annotate_args *args,
+				  int nr)
+{
+	al->offset = args->offset;
+	al->line = strdup(args->line);
+	al->line_nr = args->line_nr;
+	al->fileloc = args->fileloc;
+	al->data_nr = nr;
+}
+
+static void annotation_line__exit(struct annotation_line *al)
+{
+	zfree_srcline(&al->path);
+	zfree(&al->line);
+	zfree(&al->cycles);
+}
+
+static size_t disasm_line_size(int nr)
+{
+	struct annotation_line *al;
+
+	return (sizeof(struct disasm_line) + (sizeof(al->data[0]) * nr));
+}
+
+/*
+ * Allocating the disasm annotation line data with
+ * following structure:
+ *
+ *    -------------------------------------------
+ *    struct disasm_line | struct annotation_line
+ *    -------------------------------------------
+ *
+ * We have 'struct annotation_line' member as last member
+ * of 'struct disasm_line' to have an easy access.
+ */
+struct disasm_line *disasm_line__new(struct annotate_args *args)
+{
+	struct disasm_line *dl = NULL;
+	int nr = 1;
+
+	if (evsel__is_group_event(args->evsel))
+		nr = args->evsel->core.nr_members;
+
+	dl = zalloc(disasm_line_size(nr));
+	if (!dl)
+		return NULL;
+
+	annotation_line__init(&dl->al, args, nr);
+	if (dl->al.line == NULL)
+		goto out_delete;
+
+	if (args->offset != -1) {
+		if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
+			goto out_free_line;
+
+		disasm_line__init_ins(dl, args->arch, &args->ms);
+	}
+
+	return dl;
+
+out_free_line:
+	zfree(&dl->al.line);
+out_delete:
+	free(dl);
+	return NULL;
+}
+
+void disasm_line__free(struct disasm_line *dl)
+{
+	if (dl->ins.ops && dl->ins.ops->free)
+		dl->ins.ops->free(&dl->ops);
+	else
+		ins_ops__delete(&dl->ops);
+	zfree(&dl->ins.name);
+	annotation_line__exit(&dl->al);
+	free(dl);
+}
+
+int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw, int max_ins_name)
+{
+	if (raw || !dl->ins.ops)
+		return scnprintf(bf, size, "%-*s %s", max_ins_name, dl->ins.name, dl->ops.raw);
+
+	return ins__scnprintf(&dl->ins, bf, size, &dl->ops, max_ins_name);
+}
+
+/*
+ * symbol__parse_objdump_line() parses objdump output (with -d --no-show-raw)
+ * which looks like following
+ *
+ *  0000000000415500 <_init>:
+ *    415500:       sub    $0x8,%rsp
+ *    415504:       mov    0x2f5ad5(%rip),%rax        # 70afe0 <_DYNAMIC+0x2f8>
+ *    41550b:       test   %rax,%rax
+ *    41550e:       je     415515 <_init+0x15>
+ *    415510:       callq  416e70 <__gmon_start__@plt>
+ *    415515:       add    $0x8,%rsp
+ *    415519:       retq
+ *
+ * it will be parsed and saved into struct disasm_line as
+ *  <offset>       <name>  <ops.raw>
+ *
+ * The offset will be a relative offset from the start of the symbol and -1
+ * means that it's not a disassembly line so should be treated differently.
+ * The ops.raw part will be parsed further according to type of the instruction.
+ */
+static int symbol__parse_objdump_line(struct symbol *sym,
+				      struct annotate_args *args,
+				      char *parsed_line, int *line_nr, char **fileloc)
+{
+	struct map *map = args->ms.map;
+	struct annotation *notes = symbol__annotation(sym);
+	struct disasm_line *dl;
+	char *tmp;
+	s64 line_ip, offset = -1;
+	regmatch_t match[2];
+
+	/* /filename:linenr ? Save line number and ignore. */
+	if (regexec(&file_lineno, parsed_line, 2, match, 0) == 0) {
+		*line_nr = atoi(parsed_line + match[1].rm_so);
+		free(*fileloc);
+		*fileloc = strdup(parsed_line);
+		return 0;
+	}
+
+	/* Process hex address followed by ':'. */
+	line_ip = strtoull(parsed_line, &tmp, 16);
+	if (parsed_line != tmp && tmp[0] == ':' && tmp[1] != '\0') {
+		u64 start = map__rip_2objdump(map, sym->start),
+		    end = map__rip_2objdump(map, sym->end);
+
+		offset = line_ip - start;
+		if ((u64)line_ip < start || (u64)line_ip >= end)
+			offset = -1;
+		else
+			parsed_line = tmp + 1;
+	}
+
+	args->offset  = offset;
+	args->line    = parsed_line;
+	args->line_nr = *line_nr;
+	args->fileloc = *fileloc;
+	args->ms.sym  = sym;
+
+	dl = disasm_line__new(args);
+	(*line_nr)++;
+
+	if (dl == NULL)
+		return -1;
+
+	if (!disasm_line__has_local_offset(dl)) {
+		dl->ops.target.offset = dl->ops.target.addr -
+					map__rip_2objdump(map, sym->start);
+		dl->ops.target.offset_avail = true;
+	}
+
+	/* kcore has no symbols, so add the call target symbol */
+	if (dl->ins.ops && ins__is_call(&dl->ins) && !dl->ops.target.sym) {
+		struct addr_map_symbol target = {
+			.addr = dl->ops.target.addr,
+			.ms = { .map = map, },
+		};
+
+		if (!maps__find_ams(args->ms.maps, &target) &&
+		    target.ms.sym->start == target.al_addr)
+			dl->ops.target.sym = target.ms.sym;
+	}
+
+	annotation_line__add(&dl->al, &notes->src->source);
+	return 0;
+}
+
+static void delete_last_nop(struct symbol *sym)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct list_head *list = &notes->src->source;
+	struct disasm_line *dl;
+
+	while (!list_empty(list)) {
+		dl = list_entry(list->prev, struct disasm_line, al.node);
+
+		if (dl->ins.ops) {
+			if (!ins__is_nop(&dl->ins))
+				return;
+		} else {
+			if (!strstr(dl->al.line, " nop ") &&
+			    !strstr(dl->al.line, " nopl ") &&
+			    !strstr(dl->al.line, " nopw "))
+				return;
+		}
+
+		list_del_init(&dl->al.node);
+		disasm_line__free(dl);
+	}
+}
+
+int symbol__strerror_disassemble(struct map_symbol *ms, int errnum, char *buf, size_t buflen)
+{
+	struct dso *dso = map__dso(ms->map);
+
+	BUG_ON(buflen == 0);
+
+	if (errnum >= 0) {
+		str_error_r(errnum, buf, buflen);
+		return 0;
+	}
+
+	switch (errnum) {
+	case SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX: {
+		char bf[SBUILD_ID_SIZE + 15] = " with build id ";
+		char *build_id_msg = NULL;
+
+		if (dso->has_build_id) {
+			build_id__sprintf(&dso->bid, bf + 15);
+			build_id_msg = bf;
+		}
+		scnprintf(buf, buflen,
+			  "No vmlinux file%s\nwas found in the path.\n\n"
+			  "Note that annotation using /proc/kcore requires CAP_SYS_RAWIO capability.\n\n"
+			  "Please use:\n\n"
+			  "  perf buildid-cache -vu vmlinux\n\n"
+			  "or:\n\n"
+			  "  --vmlinux vmlinux\n", build_id_msg ?: "");
+	}
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF:
+		scnprintf(buf, buflen, "Please link with binutils's libopcode to enable BPF annotation");
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_REGEXP:
+		scnprintf(buf, buflen, "Problems with arch specific instruction name regular expressions.");
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__ARCH_INIT_CPUID_PARSING:
+		scnprintf(buf, buflen, "Problems while parsing the CPUID in the arch specific initialization.");
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE:
+		scnprintf(buf, buflen, "Invalid BPF file: %s.", dso->long_name);
+		break;
+	case SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF:
+		scnprintf(buf, buflen, "The %s BPF file has no BTF section, compile with -g or use pahole -J.",
+			  dso->long_name);
+		break;
+	default:
+		scnprintf(buf, buflen, "Internal error: Invalid %d error code\n", errnum);
+		break;
+	}
+
+	return 0;
+}
+
+static int dso__disassemble_filename(struct dso *dso, char *filename, size_t filename_size)
+{
+	char linkname[PATH_MAX];
+	char *build_id_filename;
+	char *build_id_path = NULL;
+	char *pos;
+	int len;
+
+	if (dso->symtab_type == DSO_BINARY_TYPE__KALLSYMS &&
+	    !dso__is_kcore(dso))
+		return SYMBOL_ANNOTATE_ERRNO__NO_VMLINUX;
+
+	build_id_filename = dso__build_id_filename(dso, NULL, 0, false);
+	if (build_id_filename) {
+		__symbol__join_symfs(filename, filename_size, build_id_filename);
+		free(build_id_filename);
+	} else {
+		if (dso->has_build_id)
+			return ENOMEM;
+		goto fallback;
+	}
+
+	build_id_path = strdup(filename);
+	if (!build_id_path)
+		return ENOMEM;
+
+	/*
+	 * old style build-id cache has name of XX/XXXXXXX.. while
+	 * new style has XX/XXXXXXX../{elf,kallsyms,vdso}.
+	 * extract the build-id part of dirname in the new style only.
+	 */
+	pos = strrchr(build_id_path, '/');
+	if (pos && strlen(pos) < SBUILD_ID_SIZE - 2)
+		dirname(build_id_path);
+
+	if (dso__is_kcore(dso))
+		goto fallback;
+
+	len = readlink(build_id_path, linkname, sizeof(linkname) - 1);
+	if (len < 0)
+		goto fallback;
+
+	linkname[len] = '\0';
+	if (strstr(linkname, DSO__NAME_KALLSYMS) ||
+		access(filename, R_OK)) {
+fallback:
+		/*
+		 * If we don't have build-ids or the build-id file isn't in the
+		 * cache, or is just a kallsyms file, well, lets hope that this
+		 * DSO is the same as when 'perf record' ran.
+		 */
+		if (dso->kernel && dso->long_name[0] == '/')
+			snprintf(filename, filename_size, "%s", dso->long_name);
+		else
+			__symbol__join_symfs(filename, filename_size, dso->long_name);
+
+		mutex_lock(&dso->lock);
+		if (access(filename, R_OK) && errno == ENOENT && dso->nsinfo) {
+			char *new_name = dso__filename_with_chroot(dso, filename);
+			if (new_name) {
+				strlcpy(filename, new_name, filename_size);
+				free(new_name);
+			}
+		}
+		mutex_unlock(&dso->lock);
+	} else if (dso->binary_type == DSO_BINARY_TYPE__NOT_FOUND) {
+		dso->binary_type = DSO_BINARY_TYPE__BUILD_ID_CACHE;
+	}
+
+	free(build_id_path);
+	return 0;
+}
+
+#if defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
+#define PACKAGE "perf"
+#include <bfd.h>
+#include <dis-asm.h>
+#include <bpf/bpf.h>
+#include <bpf/btf.h>
+#include <bpf/libbpf.h>
+#include <linux/btf.h>
+#include <tools/dis-asm-compat.h>
+
+#include "bpf-event.h"
+#include "bpf-utils.h"
+
+static int symbol__disassemble_bpf(struct symbol *sym,
+				   struct annotate_args *args)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct bpf_prog_linfo *prog_linfo = NULL;
+	struct bpf_prog_info_node *info_node;
+	int len = sym->end - sym->start;
+	disassembler_ftype disassemble;
+	struct map *map = args->ms.map;
+	struct perf_bpil *info_linear;
+	struct disassemble_info info;
+	struct dso *dso = map__dso(map);
+	int pc = 0, count, sub_id;
+	struct btf *btf = NULL;
+	char tpath[PATH_MAX];
+	size_t buf_size;
+	int nr_skip = 0;
+	char *buf;
+	bfd *bfdf;
+	int ret;
+	FILE *s;
+
+	if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO)
+		return SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE;
+
+	pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__,
+		  sym->name, sym->start, sym->end - sym->start);
+
+	memset(tpath, 0, sizeof(tpath));
+	perf_exe(tpath, sizeof(tpath));
+
+	bfdf = bfd_openr(tpath, NULL);
+	if (bfdf == NULL)
+		abort();
+
+	if (!bfd_check_format(bfdf, bfd_object))
+		abort();
+
+	s = open_memstream(&buf, &buf_size);
+	if (!s) {
+		ret = errno;
+		goto out;
+	}
+	init_disassemble_info_compat(&info, s,
+				     (fprintf_ftype) fprintf,
+				     fprintf_styled);
+	info.arch = bfd_get_arch(bfdf);
+	info.mach = bfd_get_mach(bfdf);
+
+	info_node = perf_env__find_bpf_prog_info(dso->bpf_prog.env,
+						 dso->bpf_prog.id);
+	if (!info_node) {
+		ret = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF;
+		goto out;
+	}
+	info_linear = info_node->info_linear;
+	sub_id = dso->bpf_prog.sub_id;
+
+	info.buffer = (void *)(uintptr_t)(info_linear->info.jited_prog_insns);
+	info.buffer_length = info_linear->info.jited_prog_len;
+
+	if (info_linear->info.nr_line_info)
+		prog_linfo = bpf_prog_linfo__new(&info_linear->info);
+
+	if (info_linear->info.btf_id) {
+		struct btf_node *node;
+
+		node = perf_env__find_btf(dso->bpf_prog.env,
+					  info_linear->info.btf_id);
+		if (node)
+			btf = btf__new((__u8 *)(node->data),
+				       node->data_size);
+	}
+
+	disassemble_init_for_target(&info);
+
+#ifdef DISASM_FOUR_ARGS_SIGNATURE
+	disassemble = disassembler(info.arch,
+				   bfd_big_endian(bfdf),
+				   info.mach,
+				   bfdf);
+#else
+	disassemble = disassembler(bfdf);
+#endif
+	if (disassemble == NULL)
+		abort();
+
+	fflush(s);
+	do {
+		const struct bpf_line_info *linfo = NULL;
+		struct disasm_line *dl;
+		size_t prev_buf_size;
+		const char *srcline;
+		u64 addr;
+
+		addr = pc + ((u64 *)(uintptr_t)(info_linear->info.jited_ksyms))[sub_id];
+		count = disassemble(pc, &info);
+
+		if (prog_linfo)
+			linfo = bpf_prog_linfo__lfind_addr_func(prog_linfo,
+								addr, sub_id,
+								nr_skip);
+
+		if (linfo && btf) {
+			srcline = btf__name_by_offset(btf, linfo->line_off);
+			nr_skip++;
+		} else
+			srcline = NULL;
+
+		fprintf(s, "\n");
+		prev_buf_size = buf_size;
+		fflush(s);
+
+		if (!annotate_opts.hide_src_code && srcline) {
+			args->offset = -1;
+			args->line = strdup(srcline);
+			args->line_nr = 0;
+			args->fileloc = NULL;
+			args->ms.sym  = sym;
+			dl = disasm_line__new(args);
+			if (dl) {
+				annotation_line__add(&dl->al,
+						     &notes->src->source);
+			}
+		}
+
+		args->offset = pc;
+		args->line = buf + prev_buf_size;
+		args->line_nr = 0;
+		args->fileloc = NULL;
+		args->ms.sym  = sym;
+		dl = disasm_line__new(args);
+		if (dl)
+			annotation_line__add(&dl->al, &notes->src->source);
+
+		pc += count;
+	} while (count > 0 && pc < len);
+
+	ret = 0;
+out:
+	free(prog_linfo);
+	btf__free(btf);
+	fclose(s);
+	bfd_close(bfdf);
+	return ret;
+}
+#else // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
+static int symbol__disassemble_bpf(struct symbol *sym __maybe_unused,
+				   struct annotate_args *args __maybe_unused)
+{
+	return SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF;
+}
+#endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
+
+static int
+symbol__disassemble_bpf_image(struct symbol *sym,
+			      struct annotate_args *args)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct disasm_line *dl;
+
+	args->offset = -1;
+	args->line = strdup("to be implemented");
+	args->line_nr = 0;
+	args->fileloc = NULL;
+	dl = disasm_line__new(args);
+	if (dl)
+		annotation_line__add(&dl->al, &notes->src->source);
+
+	zfree(&args->line);
+	return 0;
+}
+
+#ifdef HAVE_LIBCAPSTONE_SUPPORT
+#include <capstone/capstone.h>
+
+static int open_capstone_handle(struct annotate_args *args, bool is_64bit,
+				csh *handle)
+{
+	struct annotation_options *opt = args->options;
+	cs_mode mode = is_64bit ? CS_MODE_64 : CS_MODE_32;
+
+	/* TODO: support more architectures */
+	if (!arch__is(args->arch, "x86"))
+		return -1;
+
+	if (cs_open(CS_ARCH_X86, mode, handle) != CS_ERR_OK)
+		return -1;
+
+	if (!opt->disassembler_style ||
+	    !strcmp(opt->disassembler_style, "att"))
+		cs_option(*handle, CS_OPT_SYNTAX, CS_OPT_SYNTAX_ATT);
+
+	/*
+	 * Resolving address operands to symbols is implemented
+	 * on x86 by investigating instruction details.
+	 */
+	cs_option(*handle, CS_OPT_DETAIL, CS_OPT_ON);
+
+	return 0;
+}
+
+struct find_file_offset_data {
+	u64 ip;
+	u64 offset;
+};
+
+/* This will be called for each PHDR in an ELF binary */
+static int find_file_offset(u64 start, u64 len, u64 pgoff, void *arg)
+{
+	struct find_file_offset_data *data = arg;
+
+	if (start <= data->ip && data->ip < start + len) {
+		data->offset = pgoff + data->ip - start;
+		return 1;
+	}
+	return 0;
+}
+
+static void print_capstone_detail(cs_insn *insn, char *buf, size_t len,
+				  struct annotate_args *args, u64 addr)
+{
+	int i;
+	struct map *map = args->ms.map;
+	struct symbol *sym;
+
+	/* TODO: support more architectures */
+	if (!arch__is(args->arch, "x86"))
+		return;
+
+	if (insn->detail == NULL)
+		return;
+
+	for (i = 0; i < insn->detail->x86.op_count; i++) {
+		cs_x86_op *op = &insn->detail->x86.operands[i];
+		u64 orig_addr;
+
+		if (op->type != X86_OP_MEM)
+			continue;
+
+		/* only print RIP-based global symbols for now */
+		if (op->mem.base != X86_REG_RIP)
+			continue;
+
+		/* get the target address */
+		orig_addr = addr + insn->size + op->mem.disp;
+		addr = map__objdump_2mem(map, orig_addr);
+
+		if (map__dso(map)->kernel) {
+			/*
+			 * The kernel maps can be splitted into sections,
+			 * let's find the map first and the search the symbol.
+			 */
+			map = maps__find(map__kmaps(map), addr);
+			if (map == NULL)
+				continue;
+		}
+
+		/* convert it to map-relative address for search */
+		addr = map__map_ip(map, addr);
+
+		sym = map__find_symbol(map, addr);
+		if (sym == NULL)
+			continue;
+
+		if (addr == sym->start) {
+			scnprintf(buf, len, "\t# %"PRIx64" <%s>",
+				  orig_addr, sym->name);
+		} else {
+			scnprintf(buf, len, "\t# %"PRIx64" <%s+%#"PRIx64">",
+				  orig_addr, sym->name, addr - sym->start);
+		}
+		break;
+	}
+}
+
+static int symbol__disassemble_capstone(char *filename, struct symbol *sym,
+					struct annotate_args *args)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct map *map = args->ms.map;
+	struct dso *dso = map__dso(map);
+	struct nscookie nsc;
+	u64 start = map__rip_2objdump(map, sym->start);
+	u64 end = map__rip_2objdump(map, sym->end);
+	u64 len = end - start;
+	u64 offset;
+	int i, fd, count;
+	bool is_64bit = false;
+	bool needs_cs_close = false;
+	u8 *buf = NULL;
+	struct find_file_offset_data data = {
+		.ip = start,
+	};
+	csh handle;
+	cs_insn *insn;
+	char disasm_buf[512];
+	struct disasm_line *dl;
+
+	if (args->options->objdump_path)
+		return -1;
+
+	nsinfo__mountns_enter(dso->nsinfo, &nsc);
+	fd = open(filename, O_RDONLY);
+	nsinfo__mountns_exit(&nsc);
+	if (fd < 0)
+		return -1;
+
+	if (file__read_maps(fd, /*exe=*/true, find_file_offset, &data,
+			    &is_64bit) == 0)
+		goto err;
+
+	if (open_capstone_handle(args, is_64bit, &handle) < 0)
+		goto err;
+
+	needs_cs_close = true;
+
+	buf = malloc(len);
+	if (buf == NULL)
+		goto err;
+
+	count = pread(fd, buf, len, data.offset);
+	close(fd);
+	fd = -1;
+
+	if ((u64)count != len)
+		goto err;
+
+	/* add the function address and name */
+	scnprintf(disasm_buf, sizeof(disasm_buf), "%#"PRIx64" <%s>:",
+		  start, sym->name);
+
+	args->offset = -1;
+	args->line = disasm_buf;
+	args->line_nr = 0;
+	args->fileloc = NULL;
+	args->ms.sym = sym;
+
+	dl = disasm_line__new(args);
+	if (dl == NULL)
+		goto err;
+
+	annotation_line__add(&dl->al, &notes->src->source);
+
+	count = cs_disasm(handle, buf, len, start, len, &insn);
+	for (i = 0, offset = 0; i < count; i++) {
+		int printed;
+
+		printed = scnprintf(disasm_buf, sizeof(disasm_buf),
+				    "       %-7s %s",
+				    insn[i].mnemonic, insn[i].op_str);
+		print_capstone_detail(&insn[i], disasm_buf + printed,
+				      sizeof(disasm_buf) - printed, args,
+				      start + offset);
+
+		args->offset = offset;
+		args->line = disasm_buf;
+
+		dl = disasm_line__new(args);
+		if (dl == NULL)
+			goto err;
+
+		annotation_line__add(&dl->al, &notes->src->source);
+
+		offset += insn[i].size;
+	}
+
+	/* It failed in the middle: probably due to unknown instructions */
+	if (offset != len) {
+		struct list_head *list = &notes->src->source;
+
+		/* Discard all lines and fallback to objdump */
+		while (!list_empty(list)) {
+			dl = list_first_entry(list, struct disasm_line, al.node);
+
+			list_del_init(&dl->al.node);
+			disasm_line__free(dl);
+		}
+		count = -1;
+	}
+
+out:
+	if (needs_cs_close)
+		cs_close(&handle);
+	free(buf);
+	return count < 0 ? count : 0;
+
+err:
+	if (fd >= 0)
+		close(fd);
+	if (needs_cs_close) {
+		struct disasm_line *tmp;
+
+		/*
+		 * It probably failed in the middle of the above loop.
+		 * Release any resources it might add.
+		 */
+		list_for_each_entry_safe(dl, tmp, &notes->src->source, al.node) {
+			list_del(&dl->al.node);
+			free(dl);
+		}
+	}
+	count = -1;
+	goto out;
+}
+#endif
+
+/*
+ * Possibly create a new version of line with tabs expanded. Returns the
+ * existing or new line, storage is updated if a new line is allocated. If
+ * allocation fails then NULL is returned.
+ */
+static char *expand_tabs(char *line, char **storage, size_t *storage_len)
+{
+	size_t i, src, dst, len, new_storage_len, num_tabs;
+	char *new_line;
+	size_t line_len = strlen(line);
+
+	for (num_tabs = 0, i = 0; i < line_len; i++)
+		if (line[i] == '\t')
+			num_tabs++;
+
+	if (num_tabs == 0)
+		return line;
+
+	/*
+	 * Space for the line and '\0', less the leading and trailing
+	 * spaces. Each tab may introduce 7 additional spaces.
+	 */
+	new_storage_len = line_len + 1 + (num_tabs * 7);
+
+	new_line = malloc(new_storage_len);
+	if (new_line == NULL) {
+		pr_err("Failure allocating memory for tab expansion\n");
+		return NULL;
+	}
+
+	/*
+	 * Copy regions starting at src and expand tabs. If there are two
+	 * adjacent tabs then 'src == i', the memcpy is of size 0 and the spaces
+	 * are inserted.
+	 */
+	for (i = 0, src = 0, dst = 0; i < line_len && num_tabs; i++) {
+		if (line[i] == '\t') {
+			len = i - src;
+			memcpy(&new_line[dst], &line[src], len);
+			dst += len;
+			new_line[dst++] = ' ';
+			while (dst % 8 != 0)
+				new_line[dst++] = ' ';
+			src = i + 1;
+			num_tabs--;
+		}
+	}
+
+	/* Expand the last region. */
+	len = line_len - src;
+	memcpy(&new_line[dst], &line[src], len);
+	dst += len;
+	new_line[dst] = '\0';
+
+	free(*storage);
+	*storage = new_line;
+	*storage_len = new_storage_len;
+	return new_line;
+}
+
+int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
+{
+	struct annotation_options *opts = &annotate_opts;
+	struct map *map = args->ms.map;
+	struct dso *dso = map__dso(map);
+	char *command;
+	FILE *file;
+	char symfs_filename[PATH_MAX];
+	struct kcore_extract kce;
+	bool delete_extract = false;
+	bool decomp = false;
+	int lineno = 0;
+	char *fileloc = NULL;
+	int nline;
+	char *line;
+	size_t line_len;
+	const char *objdump_argv[] = {
+		"/bin/sh",
+		"-c",
+		NULL, /* Will be the objdump command to run. */
+		"--",
+		NULL, /* Will be the symfs path. */
+		NULL,
+	};
+	struct child_process objdump_process;
+	int err = dso__disassemble_filename(dso, symfs_filename, sizeof(symfs_filename));
+
+	if (err)
+		return err;
+
+	pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
+		 symfs_filename, sym->name, map__unmap_ip(map, sym->start),
+		 map__unmap_ip(map, sym->end));
+
+	pr_debug("annotating [%p] %30s : [%p] %30s\n",
+		 dso, dso->long_name, sym, sym->name);
+
+	if (dso->binary_type == DSO_BINARY_TYPE__BPF_PROG_INFO) {
+		return symbol__disassemble_bpf(sym, args);
+	} else if (dso->binary_type == DSO_BINARY_TYPE__BPF_IMAGE) {
+		return symbol__disassemble_bpf_image(sym, args);
+	} else if (dso->binary_type == DSO_BINARY_TYPE__NOT_FOUND) {
+		return -1;
+	} else if (dso__is_kcore(dso)) {
+		kce.kcore_filename = symfs_filename;
+		kce.addr = map__rip_2objdump(map, sym->start);
+		kce.offs = sym->start;
+		kce.len = sym->end - sym->start;
+		if (!kcore_extract__create(&kce)) {
+			delete_extract = true;
+			strlcpy(symfs_filename, kce.extract_filename,
+				sizeof(symfs_filename));
+		}
+	} else if (dso__needs_decompress(dso)) {
+		char tmp[KMOD_DECOMP_LEN];
+
+		if (dso__decompress_kmodule_path(dso, symfs_filename,
+						 tmp, sizeof(tmp)) < 0)
+			return -1;
+
+		decomp = true;
+		strcpy(symfs_filename, tmp);
+	}
+
+#ifdef HAVE_LIBCAPSTONE_SUPPORT
+	err = symbol__disassemble_capstone(symfs_filename, sym, args);
+	if (err == 0)
+		goto out_remove_tmp;
+#endif
+
+	err = asprintf(&command,
+		 "%s %s%s --start-address=0x%016" PRIx64
+		 " --stop-address=0x%016" PRIx64
+		 " %s -d %s %s %s %c%s%c %s%s -C \"$1\"",
+		 opts->objdump_path ?: "objdump",
+		 opts->disassembler_style ? "-M " : "",
+		 opts->disassembler_style ?: "",
+		 map__rip_2objdump(map, sym->start),
+		 map__rip_2objdump(map, sym->end),
+		 opts->show_linenr ? "-l" : "",
+		 opts->show_asm_raw ? "" : "--no-show-raw-insn",
+		 opts->annotate_src ? "-S" : "",
+		 opts->prefix ? "--prefix " : "",
+		 opts->prefix ? '"' : ' ',
+		 opts->prefix ?: "",
+		 opts->prefix ? '"' : ' ',
+		 opts->prefix_strip ? "--prefix-strip=" : "",
+		 opts->prefix_strip ?: "");
+
+	if (err < 0) {
+		pr_err("Failure allocating memory for the command to run\n");
+		goto out_remove_tmp;
+	}
+
+	pr_debug("Executing: %s\n", command);
+
+	objdump_argv[2] = command;
+	objdump_argv[4] = symfs_filename;
+
+	/* Create a pipe to read from for stdout */
+	memset(&objdump_process, 0, sizeof(objdump_process));
+	objdump_process.argv = objdump_argv;
+	objdump_process.out = -1;
+	objdump_process.err = -1;
+	objdump_process.no_stderr = 1;
+	if (start_command(&objdump_process)) {
+		pr_err("Failure starting to run %s\n", command);
+		err = -1;
+		goto out_free_command;
+	}
+
+	file = fdopen(objdump_process.out, "r");
+	if (!file) {
+		pr_err("Failure creating FILE stream for %s\n", command);
+		/*
+		 * If we were using debug info should retry with
+		 * original binary.
+		 */
+		err = -1;
+		goto out_close_stdout;
+	}
+
+	/* Storage for getline. */
+	line = NULL;
+	line_len = 0;
+
+	nline = 0;
+	while (!feof(file)) {
+		const char *match;
+		char *expanded_line;
+
+		if (getline(&line, &line_len, file) < 0 || !line)
+			break;
+
+		/* Skip lines containing "filename:" */
+		match = strstr(line, symfs_filename);
+		if (match && match[strlen(symfs_filename)] == ':')
+			continue;
+
+		expanded_line = strim(line);
+		expanded_line = expand_tabs(expanded_line, &line, &line_len);
+		if (!expanded_line)
+			break;
+
+		/*
+		 * The source code line number (lineno) needs to be kept in
+		 * across calls to symbol__parse_objdump_line(), so that it
+		 * can associate it with the instructions till the next one.
+		 * See disasm_line__new() and struct disasm_line::line_nr.
+		 */
+		if (symbol__parse_objdump_line(sym, args, expanded_line,
+					       &lineno, &fileloc) < 0)
+			break;
+		nline++;
+	}
+	free(line);
+	free(fileloc);
+
+	err = finish_command(&objdump_process);
+	if (err)
+		pr_err("Error running %s\n", command);
+
+	if (nline == 0) {
+		err = -1;
+		pr_err("No output from %s\n", command);
+	}
+
+	/*
+	 * kallsyms does not have symbol sizes so there may a nop at the end.
+	 * Remove it.
+	 */
+	if (dso__is_kcore(dso))
+		delete_last_nop(sym);
+
+	fclose(file);
+
+out_close_stdout:
+	close(objdump_process.out);
+
+out_free_command:
+	free(command);
+
+out_remove_tmp:
+	if (decomp)
+		unlink(symfs_filename);
+
+	if (delete_extract)
+		kcore_extract__delete(&kce);
+
+	return err;
+}
diff --git a/tools/perf/util/disasm.h b/tools/perf/util/disasm.h
new file mode 100644
index 00000000000000..3d381a0435201a
--- /dev/null
+++ b/tools/perf/util/disasm.h
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef __PERF_UTIL_DISASM_H
+#define __PERF_UTIL_DISASM_H
+
+#include "map_symbol.h"
+
+struct annotation_options;
+struct disasm_line;
+struct ins;
+struct evsel;
+struct symbol;
+
+struct arch {
+	const char	*name;
+	struct ins	*instructions;
+	size_t		nr_instructions;
+	size_t		nr_instructions_allocated;
+	struct ins_ops  *(*associate_instruction_ops)(struct arch *arch, const char *name);
+	bool		sorted_instructions;
+	bool		initialized;
+	const char	*insn_suffix;
+	void		*priv;
+	unsigned int	model;
+	unsigned int	family;
+	int		(*init)(struct arch *arch, char *cpuid);
+	bool		(*ins_is_fused)(struct arch *arch, const char *ins1,
+					const char *ins2);
+	struct		{
+		char comment_char;
+		char skip_functions_char;
+		char register_char;
+		char memory_ref_char;
+		char imm_char;
+	} objdump;
+};
+
+struct ins {
+	const char     *name;
+	struct ins_ops *ops;
+};
+
+struct ins_operands {
+	char	*raw;
+	struct {
+		char	*raw;
+		char	*name;
+		struct symbol *sym;
+		u64	addr;
+		s64	offset;
+		bool	offset_avail;
+		bool	outside;
+		bool	multi_regs;
+	} target;
+	union {
+		struct {
+			char	*raw;
+			char	*name;
+			u64	addr;
+			bool	multi_regs;
+		} source;
+		struct {
+			struct ins	    ins;
+			struct ins_operands *ops;
+		} locked;
+		struct {
+			char	*raw_comment;
+			char	*raw_func_start;
+		} jump;
+	};
+};
+
+struct ins_ops {
+	void (*free)(struct ins_operands *ops);
+	int (*parse)(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms);
+	int (*scnprintf)(struct ins *ins, char *bf, size_t size,
+			 struct ins_operands *ops, int max_ins_name);
+};
+
+struct annotate_args {
+	struct arch		  *arch;
+	struct map_symbol	  ms;
+	struct evsel		  *evsel;
+	struct annotation_options *options;
+	s64			  offset;
+	char			  *line;
+	int			  line_nr;
+	char			  *fileloc;
+};
+
+struct arch *arch__find(const char *name);
+bool arch__is(struct arch *arch, const char *name);
+
+struct ins_ops *ins__find(struct arch *arch, const char *name);
+int ins__scnprintf(struct ins *ins, char *bf, size_t size,
+		   struct ins_operands *ops, int max_ins_name);
+
+bool ins__is_call(const struct ins *ins);
+bool ins__is_jump(const struct ins *ins);
+bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
+bool ins__is_nop(const struct ins *ins);
+bool ins__is_ret(const struct ins *ins);
+bool ins__is_lock(const struct ins *ins);
+
+struct disasm_line *disasm_line__new(struct annotate_args *args);
+void disasm_line__free(struct disasm_line *dl);
+
+int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size,
+			   bool raw, int max_ins_name);
+
+int symbol__disassemble(struct symbol *sym, struct annotate_args *args);
+
+#endif /* __PERF_UTIL_DISASM_H */
diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
index 22fd5fa806ed8f..ad562743d769eb 100644
--- a/tools/perf/util/dso.c
+++ b/tools/perf/util/dso.c
@@ -1269,6 +1269,67 @@ static void dso__set_long_name_id(struct dso *dso, const char *name, struct dso_
 		__dsos__findnew_link_by_longname_id(root, dso, NULL, id);
 }
 
+static int __dso_id__cmp(struct dso_id *a, struct dso_id *b)
+{
+	if (a->maj > b->maj) return -1;
+	if (a->maj < b->maj) return 1;
+
+	if (a->min > b->min) return -1;
+	if (a->min < b->min) return 1;
+
+	if (a->ino > b->ino) return -1;
+	if (a->ino < b->ino) return 1;
+
+	/*
+	 * Synthesized MMAP events have zero ino_generation, avoid comparing
+	 * them with MMAP events with actual ino_generation.
+	 *
+	 * I found it harmful because the mismatch resulted in a new
+	 * dso that did not have a build ID whereas the original dso did have a
+	 * build ID. The build ID was essential because the object was not found
+	 * otherwise. - Adrian
+	 */
+	if (a->ino_generation && b->ino_generation) {
+		if (a->ino_generation > b->ino_generation) return -1;
+		if (a->ino_generation < b->ino_generation) return 1;
+	}
+
+	return 0;
+}
+
+bool dso_id__empty(struct dso_id *id)
+{
+	if (!id)
+		return true;
+
+	return !id->maj && !id->min && !id->ino && !id->ino_generation;
+}
+
+void dso__inject_id(struct dso *dso, struct dso_id *id)
+{
+	dso->id.maj = id->maj;
+	dso->id.min = id->min;
+	dso->id.ino = id->ino;
+	dso->id.ino_generation = id->ino_generation;
+}
+
+int dso_id__cmp(struct dso_id *a, struct dso_id *b)
+{
+	/*
+	 * The second is always dso->id, so zeroes if not set, assume passing
+	 * NULL for a means a zeroed id
+	 */
+	if (dso_id__empty(a) || dso_id__empty(b))
+		return 0;
+
+	return __dso_id__cmp(a, b);
+}
+
+int dso__cmp_id(struct dso *a, struct dso *b)
+{
+	return __dso_id__cmp(&a->id, &b->id);
+}
+
 void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated)
 {
 	dso__set_long_name_id(dso, name, NULL, name_allocated);
@@ -1329,6 +1390,7 @@ struct dso *dso__new_id(const char *name, struct dso_id *id)
 		dso->inlined_nodes = RB_ROOT_CACHED;
 		dso->srclines = RB_ROOT_CACHED;
 		dso->data_types = RB_ROOT;
+		dso->global_vars = RB_ROOT;
 		dso->data.fd = -1;
 		dso->data.status = DSO_DATA_STATUS_UNKNOWN;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
@@ -1373,6 +1435,7 @@ void dso__delete(struct dso *dso)
 	dso->symbol_names_len = 0;
 	zfree(&dso->symbol_names);
 	annotated_data_type__tree_delete(&dso->data_types);
+	global_var_type__tree_delete(&dso->global_vars);
 
 	if (dso->short_name_allocated) {
 		zfree((char **)&dso->short_name);
diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
index ce9f3849a773cc..2c295438226d7a 100644
--- a/tools/perf/util/dso.h
+++ b/tools/perf/util/dso.h
@@ -154,72 +154,73 @@ struct dso {
 	size_t		 symbol_names_len;
 	struct rb_root_cached inlined_nodes;
 	struct rb_root_cached srclines;
-	struct rb_root	data_types;
+	struct rb_root	 data_types;
+	struct rb_root	 global_vars;
 
 	struct {
 		u64		addr;
 		struct symbol	*symbol;
 	} last_find_result;
-	void		 *a2l;
-	char		 *symsrc_filename;
-	unsigned int	 a2l_fails;
-	enum dso_space_type	kernel;
-	bool			is_kmod;
-	enum dso_swap_type	needs_swap;
-	enum dso_binary_type	symtab_type;
-	enum dso_binary_type	binary_type;
-	enum dso_load_errno	load_errno;
-	u8		 adjust_symbols:1;
-	u8		 has_build_id:1;
-	u8		 header_build_id:1;
-	u8		 has_srcline:1;
-	u8		 hit:1;
-	u8		 annotate_warned:1;
-	u8		 auxtrace_warned:1;
-	u8		 short_name_allocated:1;
-	u8		 long_name_allocated:1;
-	u8		 is_64_bit:1;
-	bool		 sorted_by_name;
-	bool		 loaded;
-	u8		 rel;
 	struct build_id	 bid;
 	u64		 text_offset;
 	u64		 text_end;
 	const char	 *short_name;
 	const char	 *long_name;
-	u16		 long_name_len;
-	u16		 short_name_len;
+	void		 *a2l;
+	char		 *symsrc_filename;
+#if defined(__powerpc__)
 	void		*dwfl;			/* DWARF debug info */
+#endif
+	struct nsinfo	*nsinfo;
 	struct auxtrace_cache *auxtrace_cache;
-	int		 comp;
-
+	union { /* Tool specific area */
+		void	 *priv;
+		u64	 db_id;
+	};
+	/* bpf prog information */
+	struct {
+		struct perf_env	*env;
+		u32		id;
+		u32		sub_id;
+	} bpf_prog;
 	/* dso data file */
 	struct {
 		struct rb_root	 cache;
-		int		 fd;
-		int		 status;
-		u32		 status_seen;
-		u64		 file_size;
 		struct list_head open_entry;
+		u64		 file_size;
 		u64		 elf_base_addr;
 		u64		 debug_frame_offset;
 		u64		 eh_frame_hdr_addr;
 		u64		 eh_frame_hdr_offset;
+		int		 fd;
+		int		 status;
+		u32		 status_seen;
 	} data;
-	/* bpf prog information */
-	struct {
-		u32		id;
-		u32		sub_id;
-		struct perf_env	*env;
-	} bpf_prog;
-
-	union { /* Tool specific area */
-		void	 *priv;
-		u64	 db_id;
-	};
-	struct nsinfo	*nsinfo;
 	struct dso_id	 id;
+	unsigned int	 a2l_fails;
+	int		 comp;
 	refcount_t	 refcnt;
+	enum dso_load_errno	load_errno;
+	u16		 long_name_len;
+	u16		 short_name_len;
+	enum dso_binary_type	symtab_type:8;
+	enum dso_binary_type	binary_type:8;
+	enum dso_space_type	kernel:2;
+	enum dso_swap_type	needs_swap:2;
+	bool			is_kmod:1;
+	u8		 adjust_symbols:1;
+	u8		 has_build_id:1;
+	u8		 header_build_id:1;
+	u8		 has_srcline:1;
+	u8		 hit:1;
+	u8		 annotate_warned:1;
+	u8		 auxtrace_warned:1;
+	u8		 short_name_allocated:1;
+	u8		 long_name_allocated:1;
+	u8		 is_64_bit:1;
+	bool		 sorted_by_name;
+	bool		 loaded;
+	u8		 rel;
 	char		 name[];
 };
 
@@ -232,17 +233,14 @@ struct dso {
 #define dso__for_each_symbol(dso, pos, n)	\
 	symbols__for_each_entry(&(dso)->symbols, pos, n)
 
-#define dsos__for_each_with_build_id(pos, head)	\
-	list_for_each_entry(pos, head, node)	\
-		if (!pos->has_build_id)		\
-			continue;		\
-		else
-
 static inline void dso__set_loaded(struct dso *dso)
 {
 	dso->loaded = true;
 }
 
+int dso_id__cmp(struct dso_id *a, struct dso_id *b);
+bool dso_id__empty(struct dso_id *id);
+
 struct dso *dso__new_id(const char *name, struct dso_id *id);
 struct dso *dso__new(const char *name);
 void dso__delete(struct dso *dso);
@@ -250,6 +248,7 @@ void dso__delete(struct dso *dso);
 int dso__cmp_id(struct dso *a, struct dso *b);
 void dso__set_short_name(struct dso *dso, const char *name, bool name_allocated);
 void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated);
+void dso__inject_id(struct dso *dso, struct dso_id *id);
 
 int dso__name_len(const struct dso *dso);
 
@@ -411,4 +410,7 @@ int dso__strerror_load(struct dso *dso, char *buf, size_t buflen);
 
 void reset_fd_limit(void);
 
+u64 dso__find_global_type(struct dso *dso, u64 addr);
+u64 dso__findnew_global_type(struct dso *dso, u64 addr, u64 offset);
+
 #endif /* __PERF_DSO */
diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c
index cf80aa42dd07b0..b7fbfb877ae365 100644
--- a/tools/perf/util/dsos.c
+++ b/tools/perf/util/dsos.c
@@ -12,98 +12,94 @@
 #include <symbol.h> // filename__read_build_id
 #include <unistd.h>
 
-static int __dso_id__cmp(struct dso_id *a, struct dso_id *b)
+void dsos__init(struct dsos *dsos)
 {
-	if (a->maj > b->maj) return -1;
-	if (a->maj < b->maj) return 1;
+	INIT_LIST_HEAD(&dsos->head);
+	dsos->root = RB_ROOT;
+	init_rwsem(&dsos->lock);
+}
 
-	if (a->min > b->min) return -1;
-	if (a->min < b->min) return 1;
+static void dsos__purge(struct dsos *dsos)
+{
+	struct dso *pos, *n;
 
-	if (a->ino > b->ino) return -1;
-	if (a->ino < b->ino) return 1;
+	down_write(&dsos->lock);
 
-	/*
-	 * Synthesized MMAP events have zero ino_generation, avoid comparing
-	 * them with MMAP events with actual ino_generation.
-	 *
-	 * I found it harmful because the mismatch resulted in a new
-	 * dso that did not have a build ID whereas the original dso did have a
-	 * build ID. The build ID was essential because the object was not found
-	 * otherwise. - Adrian
-	 */
-	if (a->ino_generation && b->ino_generation) {
-		if (a->ino_generation > b->ino_generation) return -1;
-		if (a->ino_generation < b->ino_generation) return 1;
+	list_for_each_entry_safe(pos, n, &dsos->head, node) {
+		RB_CLEAR_NODE(&pos->rb_node);
+		pos->root = NULL;
+		list_del_init(&pos->node);
+		dso__put(pos);
 	}
 
-	return 0;
+	up_write(&dsos->lock);
 }
 
-static bool dso_id__empty(struct dso_id *id)
+void dsos__exit(struct dsos *dsos)
 {
-	if (!id)
-		return true;
-
-	return !id->maj && !id->min && !id->ino && !id->ino_generation;
+	dsos__purge(dsos);
+	exit_rwsem(&dsos->lock);
 }
 
-static void dso__inject_id(struct dso *dso, struct dso_id *id)
-{
-	dso->id.maj = id->maj;
-	dso->id.min = id->min;
-	dso->id.ino = id->ino;
-	dso->id.ino_generation = id->ino_generation;
-}
 
-static int dso_id__cmp(struct dso_id *a, struct dso_id *b)
+static int __dsos__for_each_dso(struct dsos *dsos,
+				int (*cb)(struct dso *dso, void *data),
+				void *data)
 {
-	/*
-	 * The second is always dso->id, so zeroes if not set, assume passing
-	 * NULL for a means a zeroed id
-	 */
-	if (dso_id__empty(a) || dso_id__empty(b))
-		return 0;
+	struct dso *dso;
 
-	return __dso_id__cmp(a, b);
-}
+	list_for_each_entry(dso, &dsos->head, node) {
+		int err;
 
-int dso__cmp_id(struct dso *a, struct dso *b)
-{
-	return __dso_id__cmp(&a->id, &b->id);
+		err = cb(dso, data);
+		if (err)
+			return err;
+	}
+	return 0;
 }
 
-bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
+struct dsos__read_build_ids_cb_args {
+	bool with_hits;
+	bool have_build_id;
+};
+
+static int dsos__read_build_ids_cb(struct dso *dso, void *data)
 {
-	bool have_build_id = false;
-	struct dso *pos;
+	struct dsos__read_build_ids_cb_args *args = data;
 	struct nscookie nsc;
 
-	list_for_each_entry(pos, head, node) {
-		if (with_hits && !pos->hit && !dso__is_vdso(pos))
-			continue;
-		if (pos->has_build_id) {
-			have_build_id = true;
-			continue;
-		}
-		nsinfo__mountns_enter(pos->nsinfo, &nsc);
-		if (filename__read_build_id(pos->long_name, &pos->bid) > 0) {
-			have_build_id	  = true;
-			pos->has_build_id = true;
-		} else if (errno == ENOENT && pos->nsinfo) {
-			char *new_name = dso__filename_with_chroot(pos, pos->long_name);
-
-			if (new_name && filename__read_build_id(new_name,
-								&pos->bid) > 0) {
-				have_build_id = true;
-				pos->has_build_id = true;
-			}
-			free(new_name);
+	if (args->with_hits && !dso->hit && !dso__is_vdso(dso))
+		return 0;
+	if (dso->has_build_id) {
+		args->have_build_id = true;
+		return 0;
+	}
+	nsinfo__mountns_enter(dso->nsinfo, &nsc);
+	if (filename__read_build_id(dso->long_name, &dso->bid) > 0) {
+		args->have_build_id = true;
+		dso->has_build_id = true;
+	} else if (errno == ENOENT && dso->nsinfo) {
+		char *new_name = dso__filename_with_chroot(dso, dso->long_name);
+
+		if (new_name && filename__read_build_id(new_name, &dso->bid) > 0) {
+			args->have_build_id = true;
+			dso->has_build_id = true;
 		}
-		nsinfo__mountns_exit(&nsc);
+		free(new_name);
 	}
+	nsinfo__mountns_exit(&nsc);
+	return 0;
+}
 
-	return have_build_id;
+bool dsos__read_build_ids(struct dsos *dsos, bool with_hits)
+{
+	struct dsos__read_build_ids_cb_args args = {
+		.with_hits = with_hits,
+		.have_build_id = false,
+	};
+
+	dsos__for_each_dso(dsos, dsos__read_build_ids_cb, &args);
+	return args.have_build_id;
 }
 
 static int __dso__cmp_long_name(const char *long_name, struct dso_id *id, struct dso *b)
@@ -136,6 +132,7 @@ struct dso *__dsos__findnew_link_by_longname_id(struct rb_root *root, struct dso
 
 	if (!name)
 		name = dso->long_name;
+
 	/*
 	 * Find node with the matching name
 	 */
@@ -151,7 +148,7 @@ struct dso *__dsos__findnew_link_by_longname_id(struct rb_root *root, struct dso
 			 * at the end of the list of duplicates.
 			 */
 			if (!dso || (dso == this))
-				return this;	/* Find matching dso */
+				return dso__get(this);	/* Find matching dso */
 			/*
 			 * The core kernel DSOs may have duplicated long name.
 			 * In this case, the short name should be different.
@@ -216,22 +213,50 @@ static struct dso *__dsos__findnew_by_longname_id(struct rb_root *root, const ch
 	return __dsos__findnew_link_by_longname_id(root, NULL, name, id);
 }
 
+struct dsos__find_id_cb_args {
+	const char *name;
+	struct dso_id *id;
+	struct dso *res;
+};
+
+static int dsos__find_id_cb(struct dso *dso, void *data)
+{
+	struct dsos__find_id_cb_args *args = data;
+
+	if (__dso__cmp_short_name(args->name, args->id, dso) == 0) {
+		args->res = dso__get(dso);
+		return 1;
+	}
+	return 0;
+
+}
+
 static struct dso *__dsos__find_id(struct dsos *dsos, const char *name, struct dso_id *id, bool cmp_short)
 {
-	struct dso *pos;
+	struct dso *res;
 
 	if (cmp_short) {
-		list_for_each_entry(pos, &dsos->head, node)
-			if (__dso__cmp_short_name(name, id, pos) == 0)
-				return pos;
-		return NULL;
+		struct dsos__find_id_cb_args args = {
+			.name = name,
+			.id = id,
+			.res = NULL,
+		};
+
+		__dsos__for_each_dso(dsos, dsos__find_id_cb, &args);
+		return args.res;
 	}
-	return __dsos__findnew_by_longname_id(&dsos->root, name, id);
+	res = __dsos__findnew_by_longname_id(&dsos->root, name, id);
+	return res;
 }
 
-struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
+struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
 {
-	return __dsos__find_id(dsos, name, NULL, cmp_short);
+	struct dso *res;
+
+	down_read(&dsos->lock);
+	res = __dsos__find_id(dsos, name, NULL, cmp_short);
+	up_read(&dsos->lock);
+	return res;
 }
 
 static void dso__set_basename(struct dso *dso)
@@ -273,8 +298,6 @@ static struct dso *__dsos__addnew_id(struct dsos *dsos, const char *name, struct
 	if (dso != NULL) {
 		__dsos__add(dsos, dso);
 		dso__set_basename(dso);
-		/* Put dso here because __dsos_add already got it */
-		dso__put(dso);
 	}
 	return dso;
 }
@@ -298,36 +321,142 @@ struct dso *dsos__findnew_id(struct dsos *dsos, const char *name, struct dso_id
 {
 	struct dso *dso;
 	down_write(&dsos->lock);
-	dso = dso__get(__dsos__findnew_id(dsos, name, id));
+	dso = __dsos__findnew_id(dsos, name, id);
 	up_write(&dsos->lock);
 	return dso;
 }
 
-size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
-			       bool (skip)(struct dso *dso, int parm), int parm)
+struct dsos__fprintf_buildid_cb_args {
+	FILE *fp;
+	bool (*skip)(struct dso *dso, int parm);
+	int parm;
+	size_t ret;
+};
+
+static int dsos__fprintf_buildid_cb(struct dso *dso, void *data)
 {
-	struct dso *pos;
-	size_t ret = 0;
+	struct dsos__fprintf_buildid_cb_args *args = data;
+	char sbuild_id[SBUILD_ID_SIZE];
 
-	list_for_each_entry(pos, head, node) {
-		char sbuild_id[SBUILD_ID_SIZE];
+	if (args->skip && args->skip(dso, args->parm))
+		return 0;
+	build_id__sprintf(&dso->bid, sbuild_id);
+	args->ret += fprintf(args->fp, "%-40s %s\n", sbuild_id, dso->long_name);
+	return 0;
+}
 
-		if (skip && skip(pos, parm))
-			continue;
-		build_id__sprintf(&pos->bid, sbuild_id);
-		ret += fprintf(fp, "%-40s %s\n", sbuild_id, pos->long_name);
-	}
-	return ret;
+size_t dsos__fprintf_buildid(struct dsos *dsos, FILE *fp,
+			       bool (*skip)(struct dso *dso, int parm), int parm)
+{
+	struct dsos__fprintf_buildid_cb_args args = {
+		.fp = fp,
+		.skip = skip,
+		.parm = parm,
+		.ret = 0,
+	};
+
+	dsos__for_each_dso(dsos, dsos__fprintf_buildid_cb, &args);
+	return args.ret;
 }
 
-size_t __dsos__fprintf(struct list_head *head, FILE *fp)
+struct dsos__fprintf_cb_args {
+	FILE *fp;
+	size_t ret;
+};
+
+static int dsos__fprintf_cb(struct dso *dso, void *data)
 {
-	struct dso *pos;
-	size_t ret = 0;
+	struct dsos__fprintf_cb_args *args = data;
+
+	args->ret += dso__fprintf(dso, args->fp);
+	return 0;
+}
+
+size_t dsos__fprintf(struct dsos *dsos, FILE *fp)
+{
+	struct dsos__fprintf_cb_args args = {
+		.fp = fp,
+		.ret = 0,
+	};
+
+	dsos__for_each_dso(dsos, dsos__fprintf_cb, &args);
+	return args.ret;
+}
+
+static int dsos__hit_all_cb(struct dso *dso, void *data __maybe_unused)
+{
+	dso->hit = true;
+	return 0;
+}
+
+int dsos__hit_all(struct dsos *dsos)
+{
+	return dsos__for_each_dso(dsos, dsos__hit_all_cb, NULL);
+}
+
+struct dso *dsos__findnew_module_dso(struct dsos *dsos,
+				     struct machine *machine,
+				     struct kmod_path *m,
+				     const char *filename)
+{
+	struct dso *dso;
+
+	down_write(&dsos->lock);
+
+	dso = __dsos__find_id(dsos, m->name, NULL, /*cmp_short=*/true);
+	if (!dso) {
+		dso = __dsos__addnew(dsos, m->name);
+		if (dso == NULL)
+			goto out_unlock;
 
-	list_for_each_entry(pos, head, node) {
-		ret += dso__fprintf(pos, fp);
+		dso__set_module_info(dso, m, machine);
+		dso__set_long_name(dso, strdup(filename), true);
+		dso->kernel = DSO_SPACE__KERNEL;
 	}
 
-	return ret;
+out_unlock:
+	up_write(&dsos->lock);
+	return dso;
+}
+
+static int dsos__find_kernel_dso_cb(struct dso *dso, void *data)
+{
+	struct dso **res = data;
+	/*
+	 * The cpumode passed to is_kernel_module is not the cpumode of *this*
+	 * event. If we insist on passing correct cpumode to is_kernel_module,
+	 * we should record the cpumode when we adding this dso to the linked
+	 * list.
+	 *
+	 * However we don't really need passing correct cpumode.  We know the
+	 * correct cpumode must be kernel mode (if not, we should not link it
+	 * onto kernel_dsos list).
+	 *
+	 * Therefore, we pass PERF_RECORD_MISC_CPUMODE_UNKNOWN.
+	 * is_kernel_module() treats it as a kernel cpumode.
+	 */
+	if (!dso->kernel ||
+	    is_kernel_module(dso->long_name, PERF_RECORD_MISC_CPUMODE_UNKNOWN))
+		return 0;
+
+	*res = dso__get(dso);
+	return 1;
+}
+
+struct dso *dsos__find_kernel_dso(struct dsos *dsos)
+{
+	struct dso *res = NULL;
+
+	dsos__for_each_dso(dsos, dsos__find_kernel_dso_cb, &res);
+	return res;
+}
+
+int dsos__for_each_dso(struct dsos *dsos, int (*cb)(struct dso *dso, void *data), void *data)
+{
+	int err;
+
+	down_read(&dsos->lock);
+	err = __dsos__for_each_dso(dsos, cb, data);
+	up_read(&dsos->lock);
+	return err;
 }
diff --git a/tools/perf/util/dsos.h b/tools/perf/util/dsos.h
index 5dbec2bc6966d4..50bd5152347552 100644
--- a/tools/perf/util/dsos.h
+++ b/tools/perf/util/dsos.h
@@ -10,6 +10,8 @@
 
 struct dso;
 struct dso_id;
+struct kmod_path;
+struct machine;
 
 /*
  * DSOs are put into both a list for fast iteration and rbtree for fast
@@ -21,20 +23,32 @@ struct dsos {
 	struct rw_semaphore lock;
 };
 
+void dsos__init(struct dsos *dsos);
+void dsos__exit(struct dsos *dsos);
+
 void __dsos__add(struct dsos *dsos, struct dso *dso);
 void dsos__add(struct dsos *dsos, struct dso *dso);
 struct dso *__dsos__addnew(struct dsos *dsos, const char *name);
-struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short);
+struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short);
 
 struct dso *dsos__findnew_id(struct dsos *dsos, const char *name, struct dso_id *id);
  
+bool dsos__read_build_ids(struct dsos *dsos, bool with_hits);
+
 struct dso *__dsos__findnew_link_by_longname_id(struct rb_root *root, struct dso *dso,
 						const char *name, struct dso_id *id);
 
-bool __dsos__read_build_ids(struct list_head *head, bool with_hits);
-
-size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
+size_t dsos__fprintf_buildid(struct dsos *dsos, FILE *fp,
 			       bool (skip)(struct dso *dso, int parm), int parm);
-size_t __dsos__fprintf(struct list_head *head, FILE *fp);
+size_t dsos__fprintf(struct dsos *dsos, FILE *fp);
+
+int dsos__hit_all(struct dsos *dsos);
+
+struct dso *dsos__findnew_module_dso(struct dsos *dsos, struct machine *machine,
+				     struct kmod_path *m, const char *filename);
+
+struct dso *dsos__find_kernel_dso(struct dsos *dsos);
+
+int dsos__for_each_dso(struct dsos *dsos, int (*cb)(struct dso *dso, void *data), void *data);
 
 #endif /* __PERF_DSOS */
diff --git a/tools/perf/util/dump-insn.h b/tools/perf/util/dump-insn.h
index 65012506153093..4a7797dd6d0924 100644
--- a/tools/perf/util/dump-insn.h
+++ b/tools/perf/util/dump-insn.h
@@ -11,6 +11,7 @@ struct thread;
 struct perf_insn {
 	/* Initialized by callers: */
 	struct thread *thread;
+	struct machine *machine;
 	u8	      cpumode;
 	bool	      is64bit;
 	int	      cpu;
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index 2791126069b4f8..40cfbdfe2d752e 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -9,6 +9,7 @@
 #include <stdlib.h>
 #include "debug.h"
 #include "dwarf-aux.h"
+#include "dwarf-regs.h"
 #include "strbuf.h"
 #include "string2.h"
 
@@ -696,6 +697,49 @@ Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
 	return die_mem;
 }
 
+static int __die_find_func_rettype_cb(Dwarf_Die *die_mem, void *data)
+{
+	const char *func_name;
+
+	if (dwarf_tag(die_mem) != DW_TAG_subprogram)
+		return DIE_FIND_CB_SIBLING;
+
+	func_name = dwarf_diename(die_mem);
+	if (func_name && !strcmp(func_name, data))
+		return DIE_FIND_CB_END;
+
+	return DIE_FIND_CB_SIBLING;
+}
+
+/**
+ * die_find_func_rettype - Search a return type of function
+ * @cu_die: a CU DIE
+ * @name: target function name
+ * @die_mem: a buffer for result DIE
+ *
+ * Search a non-inlined function which matches to @name and stores the
+ * return type of the function to @die_mem and returns it if found.
+ * Returns NULL if failed.  Note that it doesn't needs to find a
+ * definition of the function, so it doesn't match with address.
+ * Most likely, it can find a declaration at the top level.  Thus the
+ * callback function continues to sibling entries only.
+ */
+Dwarf_Die *die_find_func_rettype(Dwarf_Die *cu_die, const char *name,
+				 Dwarf_Die *die_mem)
+{
+	Dwarf_Die tmp_die;
+
+	cu_die = die_find_child(cu_die, __die_find_func_rettype_cb,
+				(void *)name, &tmp_die);
+	if (!cu_die)
+		return NULL;
+
+	if (die_get_real_type(&tmp_die, die_mem) == NULL)
+		return NULL;
+
+	return die_mem;
+}
+
 struct __instance_walk_param {
 	void    *addr;
 	int	(*callback)(Dwarf_Die *, void *);
@@ -1136,6 +1180,43 @@ int die_get_varname(Dwarf_Die *vr_die, struct strbuf *buf)
 	return ret < 0 ? ret : strbuf_addf(buf, "\t%s", dwarf_diename(vr_die));
 }
 
+#if defined(HAVE_DWARF_GETLOCATIONS_SUPPORT) || defined(HAVE_DWARF_CFI_SUPPORT)
+static int reg_from_dwarf_op(Dwarf_Op *op)
+{
+	switch (op->atom) {
+	case DW_OP_reg0 ... DW_OP_reg31:
+		return op->atom - DW_OP_reg0;
+	case DW_OP_breg0 ... DW_OP_breg31:
+		return op->atom - DW_OP_breg0;
+	case DW_OP_regx:
+	case DW_OP_bregx:
+		return op->number;
+	case DW_OP_fbreg:
+		return DWARF_REG_FB;
+	default:
+		break;
+	}
+	return -1;
+}
+
+static int offset_from_dwarf_op(Dwarf_Op *op)
+{
+	switch (op->atom) {
+	case DW_OP_reg0 ... DW_OP_reg31:
+	case DW_OP_regx:
+		return 0;
+	case DW_OP_breg0 ... DW_OP_breg31:
+	case DW_OP_fbreg:
+		return op->number;
+	case DW_OP_bregx:
+		return op->number2;
+	default:
+		break;
+	}
+	return -1;
+}
+#endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT || HAVE_DWARF_CFI_SUPPORT */
+
 #ifdef HAVE_DWARF_GETLOCATIONS_SUPPORT
 /**
  * die_get_var_innermost_scope - Get innermost scope range of given variable DIE
@@ -1280,7 +1361,7 @@ struct find_var_data {
 #define DWARF_OP_DIRECT_REGS  32
 
 static bool match_var_offset(Dwarf_Die *die_mem, struct find_var_data *data,
-			     u64 addr_offset, u64 addr_type)
+			     u64 addr_offset, u64 addr_type, bool is_pointer)
 {
 	Dwarf_Die type_die;
 	Dwarf_Word size;
@@ -1291,9 +1372,18 @@ static bool match_var_offset(Dwarf_Die *die_mem, struct find_var_data *data,
 		return true;
 	}
 
+	if (addr_offset < addr_type)
+		return false;
+
 	if (die_get_real_type(die_mem, &type_die) == NULL)
 		return false;
 
+	if (is_pointer && dwarf_tag(&type_die) == DW_TAG_pointer_type) {
+		/* Get the target type of the pointer */
+		if (die_get_real_type(&type_die, &type_die) == NULL)
+			return false;
+	}
+
 	if (dwarf_aggregate_size(&type_die, &size) < 0)
 		return false;
 
@@ -1359,33 +1449,39 @@ static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg)
 
 		/* Local variables accessed using frame base register */
 		if (data->is_fbreg && ops->atom == DW_OP_fbreg &&
-		    data->offset >= (int)ops->number &&
 		    check_allowed_ops(ops, nops) &&
-		    match_var_offset(die_mem, data, data->offset, ops->number))
+		    match_var_offset(die_mem, data, data->offset, ops->number,
+				     /*is_pointer=*/false))
 			return DIE_FIND_CB_END;
 
 		/* Only match with a simple case */
 		if (data->reg < DWARF_OP_DIRECT_REGS) {
 			/* pointer variables saved in a register 0 to 31 */
 			if (ops->atom == (DW_OP_reg0 + data->reg) &&
-			    check_allowed_ops(ops, nops))
+			    check_allowed_ops(ops, nops) &&
+			    match_var_offset(die_mem, data, data->offset, 0,
+					     /*is_pointer=*/true))
 				return DIE_FIND_CB_END;
 
 			/* Local variables accessed by a register + offset */
 			if (ops->atom == (DW_OP_breg0 + data->reg) &&
 			    check_allowed_ops(ops, nops) &&
-			    match_var_offset(die_mem, data, data->offset, ops->number))
+			    match_var_offset(die_mem, data, data->offset, ops->number,
+					     /*is_pointer=*/false))
 				return DIE_FIND_CB_END;
 		} else {
 			/* pointer variables saved in a register 32 or above */
 			if (ops->atom == DW_OP_regx && ops->number == data->reg &&
-			    check_allowed_ops(ops, nops))
+			    check_allowed_ops(ops, nops) &&
+			    match_var_offset(die_mem, data, data->offset, 0,
+					     /*is_pointer=*/true))
 				return DIE_FIND_CB_END;
 
 			/* Local variables accessed by a register + offset */
 			if (ops->atom == DW_OP_bregx && data->reg == ops->number &&
 			    check_allowed_ops(ops, nops) &&
-			    match_var_offset(die_mem, data, data->offset, ops->number2))
+			    match_var_offset(die_mem, data, data->offset, ops->number2,
+					     /*is_poitner=*/false))
 				return DIE_FIND_CB_END;
 		}
 	}
@@ -1443,11 +1539,9 @@ static int __die_find_var_addr_cb(Dwarf_Die *die_mem, void *arg)
 		if (ops->atom != DW_OP_addr)
 			continue;
 
-		if (data->addr < ops->number)
-			continue;
-
 		if (check_allowed_ops(ops, nops) &&
-		    match_var_offset(die_mem, data, data->addr, ops->number))
+		    match_var_offset(die_mem, data, data->addr, ops->number,
+				     /*is_pointer=*/false))
 			return DIE_FIND_CB_END;
 	}
 	return DIE_FIND_CB_SIBLING;
@@ -1456,7 +1550,6 @@ static int __die_find_var_addr_cb(Dwarf_Die *die_mem, void *arg)
 /**
  * die_find_variable_by_addr - Find variable located at given address
  * @sc_die: a scope DIE
- * @pc: the program address to find
  * @addr: the data address to find
  * @die_mem: a buffer to save the resulting DIE
  * @offset: the offset in the resulting type
@@ -1464,12 +1557,10 @@ static int __die_find_var_addr_cb(Dwarf_Die *die_mem, void *arg)
  * Find the variable DIE located at the given address (in PC-relative mode).
  * This is usually for global variables.
  */
-Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr pc,
-				     Dwarf_Addr addr, Dwarf_Die *die_mem,
-				     int *offset)
+Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr addr,
+				     Dwarf_Die *die_mem, int *offset)
 {
 	struct find_var_data data = {
-		.pc = pc,
 		.addr = addr,
 	};
 	Dwarf_Die *result;
@@ -1479,41 +1570,69 @@ Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr pc,
 		*offset = data.offset;
 	return result;
 }
-#endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
 
-#ifdef HAVE_DWARF_CFI_SUPPORT
-static int reg_from_dwarf_op(Dwarf_Op *op)
+static int __die_collect_vars_cb(Dwarf_Die *die_mem, void *arg)
 {
-	switch (op->atom) {
-	case DW_OP_reg0 ... DW_OP_reg31:
-		return op->atom - DW_OP_reg0;
-	case DW_OP_breg0 ... DW_OP_breg31:
-		return op->atom - DW_OP_breg0;
-	case DW_OP_regx:
-	case DW_OP_bregx:
-		return op->number;
-	default:
-		break;
-	}
-	return -1;
+	struct die_var_type **var_types = arg;
+	Dwarf_Die type_die;
+	int tag = dwarf_tag(die_mem);
+	Dwarf_Attribute attr;
+	Dwarf_Addr base, start, end;
+	Dwarf_Op *ops;
+	size_t nops;
+	struct die_var_type *vt;
+
+	if (tag != DW_TAG_variable && tag != DW_TAG_formal_parameter)
+		return DIE_FIND_CB_SIBLING;
+
+	if (dwarf_attr(die_mem, DW_AT_location, &attr) == NULL)
+		return DIE_FIND_CB_SIBLING;
+
+	/*
+	 * Only collect the first location as it can reconstruct the
+	 * remaining state by following the instructions.
+	 * start = 0 means it covers the whole range.
+	 */
+	if (dwarf_getlocations(&attr, 0, &base, &start, &end, &ops, &nops) <= 0)
+		return DIE_FIND_CB_SIBLING;
+
+	if (die_get_real_type(die_mem, &type_die) == NULL)
+		return DIE_FIND_CB_SIBLING;
+
+	vt = malloc(sizeof(*vt));
+	if (vt == NULL)
+		return DIE_FIND_CB_END;
+
+	vt->die_off = dwarf_dieoffset(&type_die);
+	vt->addr = start;
+	vt->reg = reg_from_dwarf_op(ops);
+	vt->offset = offset_from_dwarf_op(ops);
+	vt->next = *var_types;
+	*var_types = vt;
+
+	return DIE_FIND_CB_SIBLING;
 }
 
-static int offset_from_dwarf_op(Dwarf_Op *op)
+/**
+ * die_collect_vars - Save all variables and parameters
+ * @sc_die: a scope DIE
+ * @var_types: a pointer to save the resulting list
+ *
+ * Save all variables and parameters in the @sc_die and save them to @var_types.
+ * The @var_types is a singly-linked list containing type and location info.
+ * Actual type can be retrieved using dwarf_offdie() with 'die_off' later.
+ *
+ * Callers should free @var_types.
+ */
+void die_collect_vars(Dwarf_Die *sc_die, struct die_var_type **var_types)
 {
-	switch (op->atom) {
-	case DW_OP_reg0 ... DW_OP_reg31:
-	case DW_OP_regx:
-		return 0;
-	case DW_OP_breg0 ... DW_OP_breg31:
-		return op->number;
-	case DW_OP_bregx:
-		return op->number2;
-	default:
-		break;
-	}
-	return -1;
+	Dwarf_Die die_mem;
+
+	die_find_child(sc_die, __die_collect_vars_cb, (void *)var_types, &die_mem);
 }
+#endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
 
+#ifdef HAVE_DWARF_CFI_SUPPORT
 /**
  * die_get_cfa - Get frame base information
  * @dwarf: a Dwarf info
@@ -1779,3 +1898,116 @@ int die_get_scopes(Dwarf_Die *cu_die, Dwarf_Addr pc, Dwarf_Die **scopes)
 	*scopes = data.scopes;
 	return data.nr;
 }
+
+static int __die_find_member_offset_cb(Dwarf_Die *die_mem, void *arg)
+{
+	Dwarf_Die type_die;
+	Dwarf_Word size, loc;
+	Dwarf_Word offset = (long)arg;
+	int tag = dwarf_tag(die_mem);
+
+	if (tag != DW_TAG_member)
+		return DIE_FIND_CB_SIBLING;
+
+	/* Unions might not have location */
+	if (die_get_data_member_location(die_mem, &loc) < 0)
+		loc = 0;
+
+	if (offset == loc)
+		return DIE_FIND_CB_END;
+
+	if (die_get_real_type(die_mem, &type_die) == NULL) {
+		// TODO: add a pr_debug_dtp() later for this unlikely failure
+		return DIE_FIND_CB_SIBLING;
+	}
+
+	if (dwarf_aggregate_size(&type_die, &size) < 0)
+		size = 0;
+
+	if (loc < offset && offset < (loc + size))
+		return DIE_FIND_CB_END;
+
+	return DIE_FIND_CB_SIBLING;
+}
+
+/**
+ * die_get_member_type - Return type info of struct member
+ * @type_die: a type DIE
+ * @offset: offset in the type
+ * @die_mem: a buffer to save the resulting DIE
+ *
+ * This function returns a type of a member in @type_die where it's located at
+ * @offset if it's a struct.  For now, it just returns the first matching
+ * member in a union.  For other types, it'd return the given type directly
+ * if it's within the size of the type or NULL otherwise.
+ */
+Dwarf_Die *die_get_member_type(Dwarf_Die *type_die, int offset,
+			       Dwarf_Die *die_mem)
+{
+	Dwarf_Die *member;
+	Dwarf_Die mb_type;
+	int tag;
+
+	tag = dwarf_tag(type_die);
+	/* If it's not a compound type, return the type directly */
+	if (tag != DW_TAG_structure_type && tag != DW_TAG_union_type) {
+		Dwarf_Word size;
+
+		if (dwarf_aggregate_size(type_die, &size) < 0)
+			size = 0;
+
+		if ((unsigned)offset >= size)
+			return NULL;
+
+		*die_mem = *type_die;
+		return die_mem;
+	}
+
+	mb_type = *type_die;
+	/* TODO: Handle union types better? */
+	while (tag == DW_TAG_structure_type || tag == DW_TAG_union_type) {
+		member = die_find_child(&mb_type, __die_find_member_offset_cb,
+					(void *)(long)offset, die_mem);
+		if (member == NULL)
+			return NULL;
+
+		if (die_get_real_type(member, &mb_type) == NULL)
+			return NULL;
+
+		tag = dwarf_tag(&mb_type);
+
+		if (tag == DW_TAG_structure_type || tag == DW_TAG_union_type) {
+			Dwarf_Word loc;
+
+			/* Update offset for the start of the member struct */
+			if (die_get_data_member_location(member, &loc) == 0)
+				offset -= loc;
+		}
+	}
+	*die_mem = mb_type;
+	return die_mem;
+}
+
+/**
+ * die_deref_ptr_type - Return type info for pointer access
+ * @ptr_die: a pointer type DIE
+ * @offset: access offset for the pointer
+ * @die_mem: a buffer to save the resulting DIE
+ *
+ * This function follows the pointer in @ptr_die with given @offset
+ * and saves the resulting type in @die_mem.  If the pointer points
+ * a struct type, actual member at the offset would be returned.
+ */
+Dwarf_Die *die_deref_ptr_type(Dwarf_Die *ptr_die, int offset,
+			      Dwarf_Die *die_mem)
+{
+	Dwarf_Die type_die;
+
+	if (dwarf_tag(ptr_die) != DW_TAG_pointer_type)
+		return NULL;
+
+	if (die_get_real_type(ptr_die, &type_die) == NULL)
+		return NULL;
+
+	return die_get_member_type(&type_die, offset, die_mem);
+}
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index 85dd527ae1f70d..b0f25fbf966828 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -94,6 +94,10 @@ Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
 Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
 			       Dwarf_Die *die_mem);
 
+/* Search a non-inlined function by name and returns its return type */
+Dwarf_Die *die_find_func_rettype(Dwarf_Die *sp_die, const char *name,
+				 Dwarf_Die *die_mem);
+
 /* Walk on the instances of given DIE */
 int die_walk_instances(Dwarf_Die *in_die,
 		       int (*callback)(Dwarf_Die *, void *), void *data);
@@ -135,6 +139,21 @@ void die_skip_prologue(Dwarf_Die *sp_die, Dwarf_Die *cu_die,
 /* Get the list of including scopes */
 int die_get_scopes(Dwarf_Die *cu_die, Dwarf_Addr pc, Dwarf_Die **scopes);
 
+/* Variable type information */
+struct die_var_type {
+	struct die_var_type *next;
+	u64 die_off;
+	u64 addr;
+	int reg;
+	int offset;
+};
+
+/* Return type info of a member at offset */
+Dwarf_Die *die_get_member_type(Dwarf_Die *type_die, int offset, Dwarf_Die *die_mem);
+
+/* Return type info where the pointer and offset point to */
+Dwarf_Die *die_deref_ptr_type(Dwarf_Die *ptr_die, int offset, Dwarf_Die *die_mem);
+
 #ifdef HAVE_DWARF_GETLOCATIONS_SUPPORT
 
 /* Get byte offset range of given variable DIE */
@@ -146,9 +165,11 @@ Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die, Dwarf_Addr pc, int reg,
 				    Dwarf_Die *die_mem);
 
 /* Find a (global) variable located in the 'addr' */
-Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr pc,
-				     Dwarf_Addr addr, Dwarf_Die *die_mem,
-				     int *offset);
+Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die, Dwarf_Addr addr,
+				     Dwarf_Die *die_mem, int *offset);
+
+/* Save all variables and parameters in this scope */
+void die_collect_vars(Dwarf_Die *sc_die, struct die_var_type **var_types);
 
 #else /*  HAVE_DWARF_GETLOCATIONS_SUPPORT */
 
@@ -170,7 +191,6 @@ static inline Dwarf_Die *die_find_variable_by_reg(Dwarf_Die *sc_die __maybe_unus
 }
 
 static inline Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die __maybe_unused,
-						   Dwarf_Addr pc __maybe_unused,
 						   Dwarf_Addr addr __maybe_unused,
 						   Dwarf_Die *die_mem __maybe_unused,
 						   int *offset __maybe_unused)
@@ -178,6 +198,11 @@ static inline Dwarf_Die *die_find_variable_by_addr(Dwarf_Die *sc_die __maybe_unu
 	return NULL;
 }
 
+static inline void die_collect_vars(Dwarf_Die *sc_die __maybe_unused,
+				    struct die_var_type **var_types __maybe_unused)
+{
+}
+
 #endif /* HAVE_DWARF_GETLOCATIONS_SUPPORT */
 
 #ifdef HAVE_DWARF_CFI_SUPPORT
diff --git a/tools/perf/util/genelf.h b/tools/perf/util/genelf.h
index 5f18d20ea903a2..4e2e4f40e134fd 100644
--- a/tools/perf/util/genelf.h
+++ b/tools/perf/util/genelf.h
@@ -43,6 +43,9 @@ int jit_add_debug_info(Elf *e, uint64_t code_addr, void *debug, int nr_debug_ent
 #elif defined(__riscv) && __riscv_xlen == 64
 #define GEN_ELF_ARCH	EM_RISCV
 #define GEN_ELF_CLASS	ELFCLASS64
+#elif defined(__riscv) && __riscv_xlen == 32
+#define GEN_ELF_ARCH	EM_RISCV
+#define GEN_ELF_CLASS	ELFCLASS32
 #elif defined(__loongarch__)
 #define GEN_ELF_ARCH	EM_LOONGARCH
 #define GEN_ELF_CLASS	ELFCLASS64
diff --git a/tools/perf/util/help-unknown-cmd.c b/tools/perf/util/help-unknown-cmd.c
index eab99ea6ac01e6..a0a46e34f8d142 100644
--- a/tools/perf/util/help-unknown-cmd.c
+++ b/tools/perf/util/help-unknown-cmd.c
@@ -52,46 +52,48 @@ static int add_cmd_list(struct cmdnames *cmds, struct cmdnames *old)
 	return 0;
 }
 
-const char *help_unknown_cmd(const char *cmd)
+const char *help_unknown_cmd(const char *cmd, struct cmdnames *main_cmds)
 {
 	unsigned int i, n = 0, best_similarity = 0;
-	struct cmdnames main_cmds, other_cmds;
+	struct cmdnames other_cmds;
 
-	memset(&main_cmds, 0, sizeof(main_cmds));
-	memset(&other_cmds, 0, sizeof(main_cmds));
+	memset(&other_cmds, 0, sizeof(other_cmds));
 
 	perf_config(perf_unknown_cmd_config, NULL);
 
-	load_command_list("perf-", &main_cmds, &other_cmds);
+	load_command_list("perf-", main_cmds, &other_cmds);
 
-	if (add_cmd_list(&main_cmds, &other_cmds) < 0) {
+	if (add_cmd_list(main_cmds, &other_cmds) < 0) {
 		fprintf(stderr, "ERROR: Failed to allocate command list for unknown command.\n");
 		goto end;
 	}
-	qsort(main_cmds.names, main_cmds.cnt,
-	      sizeof(main_cmds.names), cmdname_compare);
-	uniq(&main_cmds);
+	qsort(main_cmds->names, main_cmds->cnt,
+	      sizeof(main_cmds->names), cmdname_compare);
+	uniq(main_cmds);
 
-	if (main_cmds.cnt) {
+	if (main_cmds->cnt) {
 		/* This reuses cmdname->len for similarity index */
-		for (i = 0; i < main_cmds.cnt; ++i)
-			main_cmds.names[i]->len =
-				levenshtein(cmd, main_cmds.names[i]->name, 0, 2, 1, 4);
-
-		qsort(main_cmds.names, main_cmds.cnt,
-		      sizeof(*main_cmds.names), levenshtein_compare);
+		for (i = 0; i < main_cmds->cnt; ++i) {
+			main_cmds->names[i]->len =
+				levenshtein(cmd, main_cmds->names[i]->name,
+					/*swap_penalty=*/0,
+					/*substition_penality=*/2,
+					/*insertion_penality=*/1,
+					/*deletion_penalty=*/1);
+		}
+		qsort(main_cmds->names, main_cmds->cnt,
+		      sizeof(*main_cmds->names), levenshtein_compare);
 
-		best_similarity = main_cmds.names[0]->len;
+		best_similarity = main_cmds->names[0]->len;
 		n = 1;
-		while (n < main_cmds.cnt && best_similarity == main_cmds.names[n]->len)
+		while (n < main_cmds->cnt && best_similarity == main_cmds->names[n]->len)
 			++n;
 	}
 
 	if (autocorrect && n == 1) {
-		const char *assumed = main_cmds.names[0]->name;
+		const char *assumed = main_cmds->names[0]->name;
 
-		main_cmds.names[0] = NULL;
-		clean_cmdnames(&main_cmds);
+		main_cmds->names[0] = NULL;
 		clean_cmdnames(&other_cmds);
 		fprintf(stderr, "WARNING: You called a perf program named '%s', "
 			"which does not exist.\n"
@@ -107,15 +109,14 @@ const char *help_unknown_cmd(const char *cmd)
 
 	fprintf(stderr, "perf: '%s' is not a perf-command. See 'perf --help'.\n", cmd);
 
-	if (main_cmds.cnt && best_similarity < 6) {
+	if (main_cmds->cnt && best_similarity < 6) {
 		fprintf(stderr, "\nDid you mean %s?\n",
 			n < 2 ? "this": "one of these");
 
 		for (i = 0; i < n; i++)
-			fprintf(stderr, "\t%s\n", main_cmds.names[i]->name);
+			fprintf(stderr, "\t%s\n", main_cmds->names[i]->name);
 	}
 end:
-	clean_cmdnames(&main_cmds);
 	clean_cmdnames(&other_cmds);
-	exit(1);
+	return NULL;
 }
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index fa359180ebf8fc..9d43f8ae412d85 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -308,6 +308,9 @@ static void he_stat__add_stat(struct he_stat *dest, struct he_stat *src)
 	dest->period_us		+= src->period_us;
 	dest->period_guest_sys	+= src->period_guest_sys;
 	dest->period_guest_us	+= src->period_guest_us;
+	dest->weight1		+= src->weight1;
+	dest->weight2		+= src->weight2;
+	dest->weight3		+= src->weight3;
 	dest->nr_events		+= src->nr_events;
 }
 
@@ -315,7 +318,9 @@ static void he_stat__decay(struct he_stat *he_stat)
 {
 	he_stat->period = (he_stat->period * 7) / 8;
 	he_stat->nr_events = (he_stat->nr_events * 7) / 8;
-	/* XXX need decay for weight too? */
+	he_stat->weight1 = (he_stat->weight1 * 7) / 8;
+	he_stat->weight2 = (he_stat->weight2 * 7) / 8;
+	he_stat->weight3 = (he_stat->weight3 * 7) / 8;
 }
 
 static void hists__delete_entry(struct hists *hists, struct hist_entry *he);
@@ -614,7 +619,7 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 		cmp = hist_entry__cmp(he, entry);
 		if (!cmp) {
 			if (sample_self) {
-				he_stat__add_period(&he->stat, period);
+				he_stat__add_stat(&he->stat, &entry->stat);
 				hist_entry__add_callchain_period(he, period);
 			}
 			if (symbol_conf.cumulate_callchain)
@@ -731,6 +736,9 @@ __hists__add_entry(struct hists *hists,
 		.stat = {
 			.nr_events = 1,
 			.period	= sample->period,
+			.weight1 = sample->weight,
+			.weight2 = sample->ins_lat,
+			.weight3 = sample->p_stage_cyc,
 		},
 		.parent = sym_parent,
 		.filtered = symbol__parent_filter(sym_parent) | al->filtered,
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 4a0aea0c9e00e0..5260822b9773e1 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -4,21 +4,22 @@
 
 #include <linux/rbtree.h>
 #include <linux/types.h>
-#include "evsel.h"
+#include "callchain.h"
 #include "color.h"
 #include "events_stats.h"
+#include "evsel.h"
+#include "map_symbol.h"
 #include "mutex.h"
+#include "sample.h"
+#include "spark.h"
+#include "stat.h"
 
-struct hist_entry;
-struct hist_entry_ops;
 struct addr_location;
-struct map_symbol;
 struct mem_info;
 struct kvm_info;
 struct branch_info;
 struct branch_stack;
 struct block_info;
-struct symbol;
 struct ui_progress;
 
 enum hist_filter {
@@ -150,6 +151,162 @@ extern const struct hist_iter_ops hist_iter_branch;
 extern const struct hist_iter_ops hist_iter_mem;
 extern const struct hist_iter_ops hist_iter_cumulative;
 
+struct res_sample {
+	u64 time;
+	int cpu;
+	int tid;
+};
+
+struct he_stat {
+	u64			period;
+	u64			period_sys;
+	u64			period_us;
+	u64			period_guest_sys;
+	u64			period_guest_us;
+	u64			weight1;
+	u64			weight2;
+	u64			weight3;
+	u32			nr_events;
+};
+
+struct namespace_id {
+	u64			dev;
+	u64			ino;
+};
+
+struct hist_entry_diff {
+	bool	computed;
+	union {
+		/* PERF_HPP__DELTA */
+		double	period_ratio_delta;
+
+		/* PERF_HPP__RATIO */
+		double	period_ratio;
+
+		/* HISTC_WEIGHTED_DIFF */
+		s64	wdiff;
+
+		/* PERF_HPP_DIFF__CYCLES */
+		s64	cycles;
+	};
+	struct stats	stats;
+	unsigned long	svals[NUM_SPARKS];
+};
+
+struct hist_entry_ops {
+	void	*(*new)(size_t size);
+	void	(*free)(void *ptr);
+};
+
+/**
+ * struct hist_entry - histogram entry
+ *
+ * @row_offset - offset from the first callchain expanded to appear on screen
+ * @nr_rows - rows expanded in callchain, recalculated on folding/unfolding
+ */
+struct hist_entry {
+	struct rb_node		rb_node_in;
+	struct rb_node		rb_node;
+	union {
+		struct list_head node;
+		struct list_head head;
+	} pairs;
+	struct he_stat		stat;
+	struct he_stat		*stat_acc;
+	struct map_symbol	ms;
+	struct thread		*thread;
+	struct comm		*comm;
+	struct namespace_id	cgroup_id;
+	u64			cgroup;
+	u64			ip;
+	u64			transaction;
+	s32			socket;
+	s32			cpu;
+	u64			code_page_size;
+	u64			weight;
+	u64			ins_lat;
+	u64			p_stage_cyc;
+	u8			cpumode;
+	u8			depth;
+	int			mem_type_off;
+	struct simd_flags	simd_flags;
+
+	/* We are added by hists__add_dummy_entry. */
+	bool			dummy;
+	bool			leaf;
+
+	char			level;
+	u8			filtered;
+
+	u16			callchain_size;
+	union {
+		/*
+		 * Since perf diff only supports the stdio output, TUI
+		 * fields are only accessed from perf report (or perf
+		 * top).  So make it a union to reduce memory usage.
+		 */
+		struct hist_entry_diff	diff;
+		struct /* for TUI */ {
+			u16	row_offset;
+			u16	nr_rows;
+			bool	init_have_children;
+			bool	unfolded;
+			bool	has_children;
+			bool	has_no_entry;
+		};
+	};
+	char			*srcline;
+	char			*srcfile;
+	struct symbol		*parent;
+	struct branch_info	*branch_info;
+	long			time;
+	struct hists		*hists;
+	struct mem_info		*mem_info;
+	struct block_info	*block_info;
+	struct kvm_info		*kvm_info;
+	void			*raw_data;
+	u32			raw_size;
+	int			num_res;
+	struct res_sample	*res_samples;
+	void			*trace_output;
+	struct perf_hpp_list	*hpp_list;
+	struct hist_entry	*parent_he;
+	struct hist_entry_ops	*ops;
+	struct annotated_data_type *mem_type;
+	union {
+		/* this is for hierarchical entry structure */
+		struct {
+			struct rb_root_cached	hroot_in;
+			struct rb_root_cached   hroot_out;
+		};				/* non-leaf entries */
+		struct rb_root	sorted_chain;	/* leaf entry has callchains */
+	};
+	struct callchain_root	callchain[0]; /* must be last member */
+};
+
+static __pure inline bool hist_entry__has_callchains(struct hist_entry *he)
+{
+	return he->callchain_size != 0;
+}
+
+static inline bool hist_entry__has_pairs(struct hist_entry *he)
+{
+	return !list_empty(&he->pairs.node);
+}
+
+static inline struct hist_entry *hist_entry__next_pair(struct hist_entry *he)
+{
+	if (hist_entry__has_pairs(he))
+		return list_entry(he->pairs.node.next, struct hist_entry, pairs.node);
+	return NULL;
+}
+
+static inline void hist_entry__add_pair(struct hist_entry *pair,
+					struct hist_entry *he)
+{
+	list_add_tail(&pair->pairs.node, &he->pairs.head);
+}
+
 struct hist_entry *hists__add_entry(struct hists *hists,
 				    struct addr_location *al,
 				    struct symbol *parent,
@@ -186,6 +343,8 @@ int hist_entry__sort_snprintf(struct hist_entry *he, char *bf, size_t size,
 			      struct hists *hists);
 int hist_entry__snprintf_alignment(struct hist_entry *he, struct perf_hpp *hpp,
 				   struct perf_hpp_fmt *fmt, int printed);
+int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, size_t size,
+			     unsigned int width);
 void hist_entry__delete(struct hist_entry *he);
 
 typedef int (*hists__resort_cb_t)(struct hist_entry *he, void *arg);
@@ -238,6 +397,20 @@ void hists__match(struct hists *leader, struct hists *other);
 int hists__link(struct hists *leader, struct hists *other);
 int hists__unlink(struct hists *hists);
 
+static inline float hist_entry__get_percent_limit(struct hist_entry *he)
+{
+	u64 period = he->stat.period;
+	u64 total_period = hists__total_period(he->hists);
+
+	if (unlikely(total_period == 0))
+		return 0;
+
+	if (symbol_conf.cumulate_callchain)
+		period = he->stat_acc->period;
+
+	return period * 100.0 / total_period;
+}
+
 struct hists_evsel {
 	struct evsel evsel;
 	struct hists	  hists;
@@ -377,6 +550,9 @@ enum {
 	PERF_HPP__OVERHEAD_ACC,
 	PERF_HPP__SAMPLES,
 	PERF_HPP__PERIOD,
+	PERF_HPP__WEIGHT1,
+	PERF_HPP__WEIGHT2,
+	PERF_HPP__WEIGHT3,
 
 	PERF_HPP__MAX_INDEX
 };
@@ -423,16 +599,24 @@ void perf_hpp__reset_sort_width(struct perf_hpp_fmt *fmt, struct hists *hists);
 void perf_hpp__set_user_width(const char *width_list_str);
 void hists__reset_column_width(struct hists *hists);
 
+enum perf_hpp_fmt_type {
+	PERF_HPP_FMT_TYPE__RAW,
+	PERF_HPP_FMT_TYPE__PERCENT,
+	PERF_HPP_FMT_TYPE__AVERAGE,
+};
+
 typedef u64 (*hpp_field_fn)(struct hist_entry *he);
 typedef int (*hpp_callback_fn)(struct perf_hpp *hpp, bool front);
 typedef int (*hpp_snprint_fn)(struct perf_hpp *hpp, const char *fmt, ...);
 
 int hpp__fmt(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	     struct hist_entry *he, hpp_field_fn get_field,
-	     const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent);
+	     const char *fmtstr, hpp_snprint_fn print_fn,
+	     enum perf_hpp_fmt_type fmtype);
 int hpp__fmt_acc(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 		 struct hist_entry *he, hpp_field_fn get_field,
-		 const char *fmtstr, hpp_snprint_fn print_fn, bool fmt_percent);
+		 const char *fmtstr, hpp_snprint_fn print_fn,
+		 enum perf_hpp_fmt_type fmtype);
 
 static inline void advance_hpp(struct perf_hpp *hpp, int inc)
 {
@@ -460,15 +644,20 @@ struct hist_browser_timer {
 	int refresh;
 };
 
-struct res_sample;
-
 enum rstype {
 	A_NORMAL,
 	A_ASM,
 	A_SOURCE
 };
 
-struct block_hist;
+struct block_hist {
+	struct hists		block_hists;
+	struct perf_hpp_list	block_list;
+	struct perf_hpp_fmt	block_fmt;
+	int			block_idx;
+	bool			valid;
+	struct hist_entry	he;
+};
 
 #ifdef HAVE_SLANG_SUPPORT
 #include "../ui/keysyms.h"
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
index b450178e3420ba..e733f6b1f7ac58 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1319,6 +1319,8 @@ static bool intel_pt_fup_event(struct intel_pt_decoder *decoder, bool no_tip)
 	bool ret = false;
 
 	decoder->state.type &= ~INTEL_PT_BRANCH;
+	decoder->state.insn_op = INTEL_PT_OP_OTHER;
+	decoder->state.insn_len = 0;
 
 	if (decoder->set_fup_cfe_ip || decoder->set_fup_cfe) {
 		bool ip = decoder->set_fup_cfe_ip;
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index f38893e0b03692..4db9a098f59262 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -764,6 +764,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 
 	addr_location__init(&al);
 	intel_pt_insn->length = 0;
+	intel_pt_insn->op = INTEL_PT_OP_OTHER;
 
 	if (to_ip && *ip == to_ip)
 		goto out_no_cache;
@@ -898,6 +899,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
 
 			if (to_ip && *ip == to_ip) {
 				intel_pt_insn->length = 0;
+				intel_pt_insn->op = INTEL_PT_OP_OTHER;
 				goto out_no_cache;
 			}
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 527517db31821f..c5c895131bca90 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -48,13 +48,6 @@ static struct dso *machine__kernel_dso(struct machine *machine)
 	return map__dso(machine->vmlinux_map);
 }
 
-static void dsos__init(struct dsos *dsos)
-{
-	INIT_LIST_HEAD(&dsos->head);
-	dsos->root = RB_ROOT;
-	init_rwsem(&dsos->lock);
-}
-
 static int machine__set_mmap_name(struct machine *machine)
 {
 	if (machine__is_host(machine))
@@ -165,28 +158,6 @@ struct machine *machine__new_kallsyms(void)
 	return machine;
 }
 
-static void dsos__purge(struct dsos *dsos)
-{
-	struct dso *pos, *n;
-
-	down_write(&dsos->lock);
-
-	list_for_each_entry_safe(pos, n, &dsos->head, node) {
-		RB_CLEAR_NODE(&pos->rb_node);
-		pos->root = NULL;
-		list_del_init(&pos->node);
-		dso__put(pos);
-	}
-
-	up_write(&dsos->lock);
-}
-
-static void dsos__exit(struct dsos *dsos)
-{
-	dsos__purge(dsos);
-	exit_rwsem(&dsos->lock);
-}
-
 void machine__delete_threads(struct machine *machine)
 {
 	threads__remove_all_threads(&machine->threads);
@@ -675,31 +646,6 @@ int machine__process_lost_samples_event(struct machine *machine __maybe_unused,
 	return 0;
 }
 
-static struct dso *machine__findnew_module_dso(struct machine *machine,
-					       struct kmod_path *m,
-					       const char *filename)
-{
-	struct dso *dso;
-
-	down_write(&machine->dsos.lock);
-
-	dso = __dsos__find(&machine->dsos, m->name, true);
-	if (!dso) {
-		dso = __dsos__addnew(&machine->dsos, m->name);
-		if (dso == NULL)
-			goto out_unlock;
-
-		dso__set_module_info(dso, m, machine);
-		dso__set_long_name(dso, strdup(filename), true);
-		dso->kernel = DSO_SPACE__KERNEL;
-	}
-
-	dso__get(dso);
-out_unlock:
-	up_write(&machine->dsos.lock);
-	return dso;
-}
-
 int machine__process_aux_event(struct machine *machine __maybe_unused,
 			       union perf_event *event)
 {
@@ -883,7 +829,7 @@ static struct map *machine__addnew_module_map(struct machine *machine, u64 start
 	if (kmod_path__parse_name(&m, filename))
 		return NULL;
 
-	dso = machine__findnew_module_dso(machine, &m, filename);
+	dso = dsos__findnew_module_dso(&machine->dsos, machine, &m, filename);
 	if (dso == NULL)
 		goto out;
 
@@ -907,11 +853,11 @@ out:
 size_t machines__fprintf_dsos(struct machines *machines, FILE *fp)
 {
 	struct rb_node *nd;
-	size_t ret = __dsos__fprintf(&machines->host.dsos.head, fp);
+	size_t ret = dsos__fprintf(&machines->host.dsos, fp);
 
 	for (nd = rb_first_cached(&machines->guests); nd; nd = rb_next(nd)) {
 		struct machine *pos = rb_entry(nd, struct machine, rb_node);
-		ret += __dsos__fprintf(&pos->dsos.head, fp);
+		ret += dsos__fprintf(&pos->dsos, fp);
 	}
 
 	return ret;
@@ -920,7 +866,7 @@ size_t machines__fprintf_dsos(struct machines *machines, FILE *fp)
 size_t machine__fprintf_dsos_buildid(struct machine *m, FILE *fp,
 				     bool (skip)(struct dso *dso, int parm), int parm)
 {
-	return __dsos__fprintf_buildid(&m->dsos.head, fp, skip, parm);
+	return dsos__fprintf_buildid(&m->dsos, fp, skip, parm);
 }
 
 size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp,
@@ -1549,8 +1495,8 @@ static int machine__update_kernel_mmap(struct machine *machine,
 	updated = map__get(orig);
 
 	machine->vmlinux_map = updated;
-	machine__set_kernel_mmap(machine, start, end);
 	maps__remove(machine__kernel_maps(machine), orig);
+	machine__set_kernel_mmap(machine, start, end);
 	err = maps__insert(machine__kernel_maps(machine), updated);
 	map__put(orig);
 
@@ -1616,16 +1562,14 @@ out_put:
 	return ret;
 }
 
-static bool machine__uses_kcore(struct machine *machine)
+static int machine__uses_kcore_cb(struct dso *dso, void *data __maybe_unused)
 {
-	struct dso *dso;
-
-	list_for_each_entry(dso, &machine->dsos.head, node) {
-		if (dso__is_kcore(dso))
-			return true;
-	}
+	return dso__is_kcore(dso) ? 1 : 0;
+}
 
-	return false;
+static bool machine__uses_kcore(struct machine *machine)
+{
+	return dsos__for_each_dso(&machine->dsos, machine__uses_kcore_cb, NULL) != 0 ? true : false;
 }
 
 static bool perf_event__is_extra_kernel_mmap(struct machine *machine,
@@ -1692,40 +1636,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		 * Should be there already, from the build-id table in
 		 * the header.
 		 */
-		struct dso *kernel = NULL;
-		struct dso *dso;
-
-		down_read(&machine->dsos.lock);
-
-		list_for_each_entry(dso, &machine->dsos.head, node) {
-
-			/*
-			 * The cpumode passed to is_kernel_module is not the
-			 * cpumode of *this* event. If we insist on passing
-			 * correct cpumode to is_kernel_module, we should
-			 * record the cpumode when we adding this dso to the
-			 * linked list.
-			 *
-			 * However we don't really need passing correct
-			 * cpumode.  We know the correct cpumode must be kernel
-			 * mode (if not, we should not link it onto kernel_dsos
-			 * list).
-			 *
-			 * Therefore, we pass PERF_RECORD_MISC_CPUMODE_UNKNOWN.
-			 * is_kernel_module() treats it as a kernel cpumode.
-			 */
-
-			if (!dso->kernel ||
-			    is_kernel_module(dso->long_name,
-					     PERF_RECORD_MISC_CPUMODE_UNKNOWN))
-				continue;
-
-
-			kernel = dso__get(dso);
-			break;
-		}
-
-		up_read(&machine->dsos.lock);
+		struct dso *kernel = dsos__find_kernel_dso(&machine->dsos);
 
 		if (kernel == NULL)
 			kernel = machine__findnew_dso(machine, machine->mmap_name);
@@ -3224,16 +3135,28 @@ char *machine__resolve_kernel_addr(void *vmachine, unsigned long long *addrp, ch
 	return sym->name;
 }
 
+struct machine__for_each_dso_cb_args {
+	struct machine *machine;
+	machine__dso_t fn;
+	void *priv;
+};
+
+static int machine__for_each_dso_cb(struct dso *dso, void *data)
+{
+	struct machine__for_each_dso_cb_args *args = data;
+
+	return args->fn(dso, args->machine, args->priv);
+}
+
 int machine__for_each_dso(struct machine *machine, machine__dso_t fn, void *priv)
 {
-	struct dso *pos;
-	int err = 0;
+	struct machine__for_each_dso_cb_args args = {
+		.machine = machine,
+		.fn = fn,
+		.priv = priv,
+	};
 
-	list_for_each_entry(pos, &machine->dsos.head, node) {
-		if (fn(pos, machine, priv))
-			err = -1;
-	}
-	return err;
+	return dsos__for_each_dso(&machine->dsos, machine__for_each_dso_cb, &args);
 }
 
 int machine__for_each_kernel_map(struct machine *machine, machine__map_t fn, void *priv)
@@ -3266,6 +3189,17 @@ bool machine__is_lock_function(struct machine *machine, u64 addr)
 
 		sym = machine__find_kernel_symbol_by_name(machine, "__lock_text_end", &kmap);
 		machine->lock.text_end = map__unmap_ip(kmap, sym->start);
+
+		sym = machine__find_kernel_symbol_by_name(machine, "__traceiter_contention_begin", &kmap);
+		if (sym) {
+			machine->traceiter.text_start = map__unmap_ip(kmap, sym->start);
+			machine->traceiter.text_end = map__unmap_ip(kmap, sym->end);
+		}
+		sym = machine__find_kernel_symbol_by_name(machine, "trace_contention_begin", &kmap);
+		if (sym) {
+			machine->trace.text_start = map__unmap_ip(kmap, sym->start);
+			machine->trace.text_end = map__unmap_ip(kmap, sym->end);
+		}
 	}
 
 	/* failed to get kernel symbols */
@@ -3280,5 +3214,23 @@ bool machine__is_lock_function(struct machine *machine, u64 addr)
 	if (machine->lock.text_start <= addr && addr < machine->lock.text_end)
 		return true;
 
+	/* traceiter functions currently don't have their own section
+	 * but we consider them lock functions
+	 */
+	if (machine->traceiter.text_start != 0) {
+		if (machine->traceiter.text_start <= addr && addr < machine->traceiter.text_end)
+			return true;
+	}
+
+	if (machine->trace.text_start != 0) {
+		if (machine->trace.text_start <= addr && addr < machine->trace.text_end)
+			return true;
+	}
+
 	return false;
 }
+
+int machine__hit_all_dsos(struct machine *machine)
+{
+	return dsos__hit_all(&machine->dsos);
+}
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index e28c787616fe4e..82a47bac80233e 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -49,7 +49,7 @@ struct machine {
 	struct {
 		u64	  text_start;
 		u64	  text_end;
-	} sched, lock;
+	} sched, lock, traceiter, trace;
 	pid_t		  *current_tid;
 	size_t		  current_tid_sz;
 	union { /* Tool specific area */
@@ -306,4 +306,6 @@ int machine__map_x86_64_entry_trampolines(struct machine *machine,
 int machine__resolve(struct machine *machine, struct addr_location *al,
 		     struct perf_sample *sample);
 
+int machine__hit_all_dsos(struct machine *machine);
+
 #endif /* __PERF_MACHINE_H */
diff --git a/tools/perf/util/map.c b/tools/perf/util/map.c
index 14a5ea70d81e11..cca871959f87ab 100644
--- a/tools/perf/util/map.c
+++ b/tools/perf/util/map.c
@@ -196,9 +196,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 			 * reading the header will have the build ID set and all future mmaps will
 			 * have it missing.
 			 */
-			down_read(&machine->dsos.lock);
-			header_bid_dso = __dsos__find(&machine->dsos, filename, false);
-			up_read(&machine->dsos.lock);
+			header_bid_dso = dsos__find(&machine->dsos, filename, false);
 			if (header_bid_dso && header_bid_dso->header_build_id) {
 				dso__set_build_id(dso, &header_bid_dso->bid);
 				dso->header_build_id = 1;
@@ -587,6 +585,23 @@ u64 map__objdump_2mem(struct map *map, u64 ip)
 	return ip + map__reloc(map);
 }
 
+/* convert objdump address to relative address.  (To be removed) */
+u64 map__objdump_2rip(struct map *map, u64 ip)
+{
+	const struct dso *dso = map__dso(map);
+
+	if (!dso->adjust_symbols)
+		return ip;
+
+	if (dso->rel)
+		return ip + map__pgoff(map);
+
+	if (dso->kernel == DSO_SPACE__USER)
+		return ip - dso->text_offset;
+
+	return map__map_ip(map, ip + map__reloc(map));
+}
+
 bool map__contains_symbol(const struct map *map, const struct symbol *sym)
 {
 	u64 ip = map__unmap_ip(map, sym->start);
diff --git a/tools/perf/util/map.h b/tools/perf/util/map.h
index 49756716cb1327..65e2609fa1b1ad 100644
--- a/tools/perf/util/map.h
+++ b/tools/perf/util/map.h
@@ -132,6 +132,9 @@ u64 map__rip_2objdump(struct map *map, u64 rip);
 /* objdump address -> memory address */
 u64 map__objdump_2mem(struct map *map, u64 ip);
 
+/* objdump address -> rip */
+u64 map__objdump_2rip(struct map *map, u64 ip);
+
 struct symbol;
 struct thread;
 
diff --git a/tools/perf/util/metricgroup.c b/tools/perf/util/metricgroup.c
index 79ef6095ab2891..9be40652461792 100644
--- a/tools/perf/util/metricgroup.c
+++ b/tools/perf/util/metricgroup.c
@@ -455,7 +455,7 @@ static int metricgroup__add_to_mep_groups(const struct pmu_metric *pm,
 	const char *g;
 	char *omg, *mg;
 
-	mg = strdup(pm->metric_group ?: "No_group");
+	mg = strdup(pm->metric_group ?: pm->metric_name);
 	if (!mg)
 		return -ENOMEM;
 	omg = mg;
@@ -466,7 +466,7 @@ static int metricgroup__add_to_mep_groups(const struct pmu_metric *pm,
 		if (strlen(g))
 			me = mep_lookup(groups, g, pm->metric_name);
 		else
-			me = mep_lookup(groups, "No_group", pm->metric_name);
+			me = mep_lookup(groups, pm->metric_name, pm->metric_name);
 
 		if (me) {
 			me->metric_desc = pm->desc;
@@ -1690,12 +1690,15 @@ int metricgroup__parse_groups(struct evlist *perf_evlist,
 			      bool metric_no_threshold,
 			      const char *user_requested_cpu_list,
 			      bool system_wide,
+			      bool hardware_aware_grouping,
 			      struct rblist *metric_events)
 {
 	const struct pmu_metrics_table *table = pmu_metrics_table__find();
 
 	if (!table)
 		return -EINVAL;
+	if (hardware_aware_grouping)
+		pr_debug("Use hardware aware grouping instead of traditional metric grouping method\n");
 
 	return parse_groups(perf_evlist, pmu, str, metric_no_group, metric_no_merge,
 			    metric_no_threshold, user_requested_cpu_list, system_wide,
diff --git a/tools/perf/util/metricgroup.h b/tools/perf/util/metricgroup.h
index d5325c6ec8e114..779f6ede1b5114 100644
--- a/tools/perf/util/metricgroup.h
+++ b/tools/perf/util/metricgroup.h
@@ -77,6 +77,7 @@ int metricgroup__parse_groups(struct evlist *perf_evlist,
 			      bool metric_no_threshold,
 			      const char *user_requested_cpu_list,
 			      bool system_wide,
+			      bool hardware_aware_grouping,
 			      struct rblist *metric_events);
 int metricgroup__parse_groups_test(struct evlist *evlist,
 				   const struct pmu_metrics_table *table,
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 6f8b0fa176891f..0f308b4db2b972 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -34,11 +34,12 @@
 #ifdef PARSER_DEBUG
 extern int parse_events_debug;
 #endif
-static int get_config_terms(struct parse_events_terms *head_config, struct list_head *head_terms);
+static int get_config_terms(const struct parse_events_terms *head_config,
+			    struct list_head *head_terms);
 static int parse_events_terms__copy(const struct parse_events_terms *src,
 				    struct parse_events_terms *dest);
 
-struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = {
+const struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = {
 	[PERF_COUNT_HW_CPU_CYCLES] = {
 		.symbol = "cpu-cycles",
 		.alias  = "cycles",
@@ -81,7 +82,7 @@ struct event_symbol event_symbols_hw[PERF_COUNT_HW_MAX] = {
 	},
 };
 
-struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
+const struct event_symbol event_symbols_sw[PERF_COUNT_SW_MAX] = {
 	[PERF_COUNT_SW_CPU_CLOCK] = {
 		.symbol = "cpu-clock",
 		.alias  = "",
@@ -154,7 +155,7 @@ const char *event_type(int type)
 	return "unknown";
 }
 
-static char *get_config_str(struct parse_events_terms *head_terms,
+static char *get_config_str(const struct parse_events_terms *head_terms,
 			    enum parse_events__term_type type_term)
 {
 	struct parse_events_term *term;
@@ -169,12 +170,12 @@ static char *get_config_str(struct parse_events_terms *head_terms,
 	return NULL;
 }
 
-static char *get_config_metric_id(struct parse_events_terms *head_terms)
+static char *get_config_metric_id(const struct parse_events_terms *head_terms)
 {
 	return get_config_str(head_terms, PARSE_EVENTS__TERM_TYPE_METRIC_ID);
 }
 
-static char *get_config_name(struct parse_events_terms *head_terms)
+static char *get_config_name(const struct parse_events_terms *head_terms)
 {
 	return get_config_str(head_terms, PARSE_EVENTS__TERM_TYPE_NAME);
 }
@@ -358,7 +359,7 @@ static int config_term_common(struct perf_event_attr *attr,
 			      struct parse_events_term *term,
 			      struct parse_events_error *err);
 static int config_attr(struct perf_event_attr *attr,
-		       struct parse_events_terms *head,
+		       const struct parse_events_terms *head,
 		       struct parse_events_error *err,
 		       config_term_func_t config_term);
 
@@ -442,17 +443,21 @@ bool parse_events__filter_pmu(const struct parse_events_state *parse_state,
 	return strcmp(parse_state->pmu_filter, pmu->name) != 0;
 }
 
+static int parse_events_add_pmu(struct parse_events_state *parse_state,
+				struct list_head *list, struct perf_pmu *pmu,
+				const struct parse_events_terms *const_parsed_terms,
+				bool auto_merge_stats);
+
 int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 			   struct parse_events_state *parse_state,
-			   struct parse_events_terms *head_config)
+			   struct parse_events_terms *parsed_terms)
 {
 	struct perf_pmu *pmu = NULL;
 	bool found_supported = false;
-	const char *config_name = get_config_name(head_config);
-	const char *metric_id = get_config_metric_id(head_config);
+	const char *config_name = get_config_name(parsed_terms);
+	const char *metric_id = get_config_metric_id(parsed_terms);
 
-	/* Legacy cache events are only supported by core PMUs. */
-	while ((pmu = perf_pmus__scan_core(pmu)) != NULL) {
+	while ((pmu = perf_pmus__scan(pmu)) != NULL) {
 		LIST_HEAD(config_terms);
 		struct perf_event_attr attr;
 		int ret;
@@ -460,6 +465,24 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 		if (parse_events__filter_pmu(parse_state, pmu))
 			continue;
 
+		if (perf_pmu__have_event(pmu, name)) {
+			/*
+			 * The PMU has the event so add as not a legacy cache
+			 * event.
+			 */
+			ret = parse_events_add_pmu(parse_state, list, pmu,
+						   parsed_terms,
+						   perf_pmu__auto_merge_stats(pmu));
+			if (ret)
+				return ret;
+			continue;
+		}
+
+		if (!pmu->is_core) {
+			/* Legacy cache events are only supported by core PMUs. */
+			continue;
+		}
+
 		memset(&attr, 0, sizeof(attr));
 		attr.type = PERF_TYPE_HW_CACHE;
 
@@ -469,11 +492,12 @@ int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 
 		found_supported = true;
 
-		if (head_config) {
-			if (config_attr(&attr, head_config, parse_state->error, config_term_common))
+		if (parsed_terms) {
+			if (config_attr(&attr, parsed_terms, parse_state->error,
+					config_term_common))
 				return -EINVAL;
 
-			if (get_config_terms(head_config, &config_terms))
+			if (get_config_terms(parsed_terms, &config_terms))
 				return -ENOMEM;
 		}
 
@@ -1085,7 +1109,7 @@ static int config_term_tracepoint(struct perf_event_attr *attr,
 #endif
 
 static int config_attr(struct perf_event_attr *attr,
-		       struct parse_events_terms *head,
+		       const struct parse_events_terms *head,
 		       struct parse_events_error *err,
 		       config_term_func_t config_term)
 {
@@ -1098,7 +1122,8 @@ static int config_attr(struct perf_event_attr *attr,
 	return 0;
 }
 
-static int get_config_terms(struct parse_events_terms *head_config, struct list_head *head_terms)
+static int get_config_terms(const struct parse_events_terms *head_config,
+			    struct list_head *head_terms)
 {
 #define ADD_CONFIG_TERM(__type, __weak)				\
 	struct evsel_config_term *__t;			\
@@ -1302,7 +1327,7 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,
 static int __parse_events_add_numeric(struct parse_events_state *parse_state,
 				struct list_head *list,
 				struct perf_pmu *pmu, u32 type, u32 extended_type,
-				u64 config, struct parse_events_terms *head_config)
+				u64 config, const struct parse_events_terms *head_config)
 {
 	struct perf_event_attr attr;
 	LIST_HEAD(config_terms);
@@ -1338,7 +1363,7 @@ static int __parse_events_add_numeric(struct parse_events_state *parse_state,
 int parse_events_add_numeric(struct parse_events_state *parse_state,
 			     struct list_head *list,
 			     u32 type, u64 config,
-			     struct parse_events_terms *head_config,
+			     const struct parse_events_terms *head_config,
 			     bool wildcard)
 {
 	struct perf_pmu *pmu = NULL;
@@ -1385,56 +1410,34 @@ static bool config_term_percore(struct list_head *config_terms)
 	return false;
 }
 
-int parse_events_add_pmu(struct parse_events_state *parse_state,
-			 struct list_head *list, const char *name,
-			 const struct parse_events_terms *const_parsed_terms,
-			 bool auto_merge_stats, void *loc_)
+static int parse_events_add_pmu(struct parse_events_state *parse_state,
+				struct list_head *list, struct perf_pmu *pmu,
+				const struct parse_events_terms *const_parsed_terms,
+				bool auto_merge_stats)
 {
 	struct perf_event_attr attr;
 	struct perf_pmu_info info;
-	struct perf_pmu *pmu;
 	struct evsel *evsel;
 	struct parse_events_error *err = parse_state->error;
-	YYLTYPE *loc = loc_;
 	LIST_HEAD(config_terms);
 	struct parse_events_terms parsed_terms;
 	bool alias_rewrote_terms = false;
 
-	pmu = parse_state->fake_pmu ?: perf_pmus__find(name);
-
-	if (!pmu) {
-		char *err_str;
-
-		if (asprintf(&err_str,
-				"Cannot find PMU `%s'. Missing kernel support?",
-				name) >= 0)
-			parse_events_error__handle(err, loc->first_column, err_str, NULL);
-		return -EINVAL;
-	}
-
-	parse_events_terms__init(&parsed_terms);
-	if (const_parsed_terms) {
-		int ret = parse_events_terms__copy(const_parsed_terms, &parsed_terms);
-
-		if (ret)
-			return ret;
-	}
-
 	if (verbose > 1) {
 		struct strbuf sb;
 
 		strbuf_init(&sb, /*hint=*/ 0);
-		if (pmu->selectable && list_empty(&parsed_terms.terms)) {
-			strbuf_addf(&sb, "%s//", name);
+		if (pmu->selectable && const_parsed_terms &&
+		    list_empty(&const_parsed_terms->terms)) {
+			strbuf_addf(&sb, "%s//", pmu->name);
 		} else {
-			strbuf_addf(&sb, "%s/", name);
-			parse_events_terms__to_strbuf(&parsed_terms, &sb);
+			strbuf_addf(&sb, "%s/", pmu->name);
+			parse_events_terms__to_strbuf(const_parsed_terms, &sb);
 			strbuf_addch(&sb, '/');
 		}
 		fprintf(stderr, "Attempt to add: %s\n", sb.buf);
 		strbuf_release(&sb);
 	}
-	fix_raw(&parsed_terms, pmu);
 
 	memset(&attr, 0, sizeof(attr));
 	if (pmu->perf_event_attr_init_default)
@@ -1442,7 +1445,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 
 	attr.type = pmu->type;
 
-	if (list_empty(&parsed_terms.terms)) {
+	if (!const_parsed_terms || list_empty(&const_parsed_terms->terms)) {
 		evsel = __add_event(list, &parse_state->idx, &attr,
 				    /*init_attr=*/true, /*name=*/NULL,
 				    /*metric_id=*/NULL, pmu,
@@ -1451,6 +1454,15 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 		return evsel ? 0 : -ENOMEM;
 	}
 
+	parse_events_terms__init(&parsed_terms);
+	if (const_parsed_terms) {
+		int ret = parse_events_terms__copy(const_parsed_terms, &parsed_terms);
+
+		if (ret)
+			return ret;
+	}
+	fix_raw(&parsed_terms, pmu);
+
 	/* Configure attr/terms with a known PMU, this will set hardcoded terms. */
 	if (config_attr(&attr, &parsed_terms, parse_state->error, config_term_pmu)) {
 		parse_events_terms__exit(&parsed_terms);
@@ -1469,7 +1481,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 
 		strbuf_init(&sb, /*hint=*/ 0);
 		parse_events_terms__to_strbuf(&parsed_terms, &sb);
-		fprintf(stderr, "..after resolving event: %s/%s/\n", name, sb.buf);
+		fprintf(stderr, "..after resolving event: %s/%s/\n", pmu->name, sb.buf);
 		strbuf_release(&sb);
 	}
 
@@ -1531,7 +1543,7 @@ int parse_events_add_pmu(struct parse_events_state *parse_state,
 }
 
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
-			       const char *event_name,
+			       const char *event_name, u64 hw_config,
 			       const struct parse_events_terms *const_parsed_terms,
 			       struct list_head **listp, void *loc_)
 {
@@ -1539,8 +1551,8 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 	struct list_head *list = NULL;
 	struct perf_pmu *pmu = NULL;
 	YYLTYPE *loc = loc_;
-	int ok = 0;
-	const char *config;
+	int ok = 0, core_ok = 0;
+	const char *tmp;
 	struct parse_events_terms parsed_terms;
 
 	*listp = NULL;
@@ -1553,15 +1565,15 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 			return ret;
 	}
 
-	config = strdup(event_name);
-	if (!config)
+	tmp = strdup(event_name);
+	if (!tmp)
 		goto out_err;
 
 	if (parse_events_term__num(&term,
 				   PARSE_EVENTS__TERM_TYPE_USER,
-				   config, /*num=*/1, /*novalue=*/true,
+				   tmp, /*num=*/1, /*novalue=*/true,
 				   loc, /*loc_val=*/NULL) < 0) {
-		zfree(&config);
+		zfree(&tmp);
 		goto out_err;
 	}
 	list_add_tail(&term->list, &parsed_terms.terms);
@@ -1583,8 +1595,8 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 			continue;
 
 		auto_merge_stats = perf_pmu__auto_merge_stats(pmu);
-		if (!parse_events_add_pmu(parse_state, list, pmu->name,
-					  &parsed_terms, auto_merge_stats, loc)) {
+		if (!parse_events_add_pmu(parse_state, list, pmu,
+					  &parsed_terms, auto_merge_stats)) {
 			struct strbuf sb;
 
 			strbuf_init(&sb, /*hint=*/ 0);
@@ -1592,12 +1604,14 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 			pr_debug("%s -> %s/%s/\n", event_name, pmu->name, sb.buf);
 			strbuf_release(&sb);
 			ok++;
+			if (pmu->is_core)
+				core_ok++;
 		}
 	}
 
 	if (parse_state->fake_pmu) {
-		if (!parse_events_add_pmu(parse_state, list, event_name, &parsed_terms,
-					  /*auto_merge_stats=*/true, loc)) {
+		if (!parse_events_add_pmu(parse_state, list, parse_state->fake_pmu, &parsed_terms,
+					  /*auto_merge_stats=*/true)) {
 			struct strbuf sb;
 
 			strbuf_init(&sb, /*hint=*/ 0);
@@ -1608,6 +1622,18 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 		}
 	}
 
+	if (hw_config != PERF_COUNT_HW_MAX && !core_ok) {
+		/*
+		 * The event wasn't found on core PMUs but it has a hardware
+		 * config version to try.
+		 */
+		if (!parse_events_add_numeric(parse_state, list,
+						PERF_TYPE_HARDWARE, hw_config,
+						const_parsed_terms,
+						/*wildcard=*/true))
+			ok++;
+	}
+
 out_err:
 	parse_events_terms__exit(&parsed_terms);
 	if (ok)
@@ -1618,10 +1644,60 @@ out_err:
 	return ok ? 0 : -1;
 }
 
-int parse_events__modifier_group(struct list_head *list,
-				 char *event_mod)
+int parse_events_multi_pmu_add_or_add_pmu(struct parse_events_state *parse_state,
+					const char *event_or_pmu,
+					const struct parse_events_terms *const_parsed_terms,
+					struct list_head **listp,
+					void *loc_)
 {
-	return parse_events__modifier_event(list, event_mod, true);
+	YYLTYPE *loc = loc_;
+	struct perf_pmu *pmu;
+	int ok = 0;
+	char *help;
+
+	*listp = malloc(sizeof(**listp));
+	if (!*listp)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(*listp);
+
+	/* Attempt to add to list assuming event_or_pmu is a PMU name. */
+	pmu = parse_state->fake_pmu ?: perf_pmus__find(event_or_pmu);
+	if (pmu && !parse_events_add_pmu(parse_state, *listp, pmu, const_parsed_terms,
+					/*auto_merge_stats=*/false))
+		return 0;
+
+	pmu = NULL;
+	/* Failed to add, try wildcard expansion of event_or_pmu as a PMU name. */
+	while ((pmu = perf_pmus__scan(pmu)) != NULL) {
+		if (!parse_events__filter_pmu(parse_state, pmu) &&
+		    perf_pmu__match(pmu, event_or_pmu)) {
+			bool auto_merge_stats = perf_pmu__auto_merge_stats(pmu);
+
+			if (!parse_events_add_pmu(parse_state, *listp, pmu,
+						  const_parsed_terms,
+						  auto_merge_stats)) {
+				ok++;
+				parse_state->wild_card_pmus = true;
+			}
+		}
+	}
+	if (ok)
+		return 0;
+
+	/* Failure to add, assume event_or_pmu is an event name. */
+	zfree(listp);
+	if (!parse_events_multi_pmu_add(parse_state, event_or_pmu, PERF_COUNT_HW_MAX,
+					const_parsed_terms, listp, loc))
+		return 0;
+
+	if (asprintf(&help, "Unable to find PMU or event on a PMU of '%s'", event_or_pmu) < 0)
+		help = NULL;
+	parse_events_error__handle(parse_state->error, loc->first_column,
+				strdup("Bad event or PMU"),
+				help);
+	zfree(listp);
+	return -EINVAL;
 }
 
 void parse_events__set_leader(char *name, struct list_head *list)
@@ -1635,213 +1711,146 @@ void parse_events__set_leader(char *name, struct list_head *list)
 
 	leader = list_first_entry(list, struct evsel, core.node);
 	__perf_evlist__set_leader(list, &leader->core);
+	zfree(&leader->group_name);
 	leader->group_name = name;
 }
 
-/* list_event is assumed to point to malloc'ed memory */
-void parse_events_update_lists(struct list_head *list_event,
-			       struct list_head *list_all)
+static int parse_events__modifier_list(struct parse_events_state *parse_state,
+				       YYLTYPE *loc,
+				       struct list_head *list,
+				       struct parse_events_modifier mod,
+				       bool group)
 {
-	/*
-	 * Called for single event definition. Update the
-	 * 'all event' list, and reinit the 'single event'
-	 * list, for next event definition.
-	 */
-	list_splice_tail(list_event, list_all);
-	free(list_event);
-}
-
-struct event_modifier {
-	int eu;
-	int ek;
-	int eh;
-	int eH;
-	int eG;
-	int eI;
-	int precise;
-	int precise_max;
-	int exclude_GH;
-	int sample_read;
-	int pinned;
-	int weak;
-	int exclusive;
-	int bpf_counter;
-};
+	struct evsel *evsel;
 
-static int get_event_modifier(struct event_modifier *mod, char *str,
-			       struct evsel *evsel)
-{
-	int eu = evsel ? evsel->core.attr.exclude_user : 0;
-	int ek = evsel ? evsel->core.attr.exclude_kernel : 0;
-	int eh = evsel ? evsel->core.attr.exclude_hv : 0;
-	int eH = evsel ? evsel->core.attr.exclude_host : 0;
-	int eG = evsel ? evsel->core.attr.exclude_guest : 0;
-	int eI = evsel ? evsel->core.attr.exclude_idle : 0;
-	int precise = evsel ? evsel->core.attr.precise_ip : 0;
-	int precise_max = 0;
-	int sample_read = 0;
-	int pinned = evsel ? evsel->core.attr.pinned : 0;
-	int exclusive = evsel ? evsel->core.attr.exclusive : 0;
-
-	int exclude = eu | ek | eh;
-	int exclude_GH = evsel ? evsel->exclude_GH : 0;
-	int weak = 0;
-	int bpf_counter = 0;
-
-	memset(mod, 0, sizeof(*mod));
-
-	while (*str) {
-		if (*str == 'u') {
+	if (!group && mod.weak) {
+		parse_events_error__handle(parse_state->error, loc->first_column,
+					   strdup("Weak modifier is for use with groups"), NULL);
+		return -EINVAL;
+	}
+
+	__evlist__for_each_entry(list, evsel) {
+		/* Translate modifiers into the equivalent evsel excludes. */
+		int eu = group ? evsel->core.attr.exclude_user : 0;
+		int ek = group ? evsel->core.attr.exclude_kernel : 0;
+		int eh = group ? evsel->core.attr.exclude_hv : 0;
+		int eH = group ? evsel->core.attr.exclude_host : 0;
+		int eG = group ? evsel->core.attr.exclude_guest : 0;
+		int exclude = eu | ek | eh;
+		int exclude_GH = group ? evsel->exclude_GH : 0;
+
+		if (mod.precise) {
+			/* use of precise requires exclude_guest */
+			eG = 1;
+		}
+		if (mod.user) {
 			if (!exclude)
 				exclude = eu = ek = eh = 1;
 			if (!exclude_GH && !perf_guest)
 				eG = 1;
 			eu = 0;
-		} else if (*str == 'k') {
+		}
+		if (mod.kernel) {
 			if (!exclude)
 				exclude = eu = ek = eh = 1;
 			ek = 0;
-		} else if (*str == 'h') {
+		}
+		if (mod.hypervisor) {
 			if (!exclude)
 				exclude = eu = ek = eh = 1;
 			eh = 0;
-		} else if (*str == 'G') {
+		}
+		if (mod.guest) {
 			if (!exclude_GH)
 				exclude_GH = eG = eH = 1;
 			eG = 0;
-		} else if (*str == 'H') {
+		}
+		if (mod.host) {
 			if (!exclude_GH)
 				exclude_GH = eG = eH = 1;
 			eH = 0;
-		} else if (*str == 'I') {
-			eI = 1;
-		} else if (*str == 'p') {
-			precise++;
-			/* use of precise requires exclude_guest */
-			if (!exclude_GH)
-				eG = 1;
-		} else if (*str == 'P') {
-			precise_max = 1;
-		} else if (*str == 'S') {
-			sample_read = 1;
-		} else if (*str == 'D') {
-			pinned = 1;
-		} else if (*str == 'e') {
-			exclusive = 1;
-		} else if (*str == 'W') {
-			weak = 1;
-		} else if (*str == 'b') {
-			bpf_counter = 1;
-		} else
-			break;
-
-		++str;
+		}
+		evsel->core.attr.exclude_user   = eu;
+		evsel->core.attr.exclude_kernel = ek;
+		evsel->core.attr.exclude_hv     = eh;
+		evsel->core.attr.exclude_host   = eH;
+		evsel->core.attr.exclude_guest  = eG;
+		evsel->exclude_GH               = exclude_GH;
+
+		/* Simple modifiers copied to the evsel. */
+		if (mod.precise) {
+			u8 precise = evsel->core.attr.precise_ip + mod.precise;
+			/*
+			 * precise ip:
+			 *
+			 *  0 - SAMPLE_IP can have arbitrary skid
+			 *  1 - SAMPLE_IP must have constant skid
+			 *  2 - SAMPLE_IP requested to have 0 skid
+			 *  3 - SAMPLE_IP must have 0 skid
+			 *
+			 *  See also PERF_RECORD_MISC_EXACT_IP
+			 */
+			if (precise > 3) {
+				char *help;
+
+				if (asprintf(&help,
+					     "Maximum combined precise value is 3, adding precision to \"%s\"",
+					     evsel__name(evsel)) > 0) {
+					parse_events_error__handle(parse_state->error,
+								   loc->first_column,
+								   help, NULL);
+				}
+				return -EINVAL;
+			}
+			evsel->core.attr.precise_ip = precise;
+		}
+		if (mod.precise_max)
+			evsel->precise_max = 1;
+		if (mod.non_idle)
+			evsel->core.attr.exclude_idle = 1;
+		if (mod.sample_read)
+			evsel->sample_read = 1;
+		if (mod.pinned && evsel__is_group_leader(evsel))
+			evsel->core.attr.pinned = 1;
+		if (mod.exclusive && evsel__is_group_leader(evsel))
+			evsel->core.attr.exclusive = 1;
+		if (mod.weak)
+			evsel->weak_group = true;
+		if (mod.bpf)
+			evsel->bpf_counter = true;
 	}
-
-	/*
-	 * precise ip:
-	 *
-	 *  0 - SAMPLE_IP can have arbitrary skid
-	 *  1 - SAMPLE_IP must have constant skid
-	 *  2 - SAMPLE_IP requested to have 0 skid
-	 *  3 - SAMPLE_IP must have 0 skid
-	 *
-	 *  See also PERF_RECORD_MISC_EXACT_IP
-	 */
-	if (precise > 3)
-		return -EINVAL;
-
-	mod->eu = eu;
-	mod->ek = ek;
-	mod->eh = eh;
-	mod->eH = eH;
-	mod->eG = eG;
-	mod->eI = eI;
-	mod->precise = precise;
-	mod->precise_max = precise_max;
-	mod->exclude_GH = exclude_GH;
-	mod->sample_read = sample_read;
-	mod->pinned = pinned;
-	mod->weak = weak;
-	mod->bpf_counter = bpf_counter;
-	mod->exclusive = exclusive;
-
 	return 0;
 }
 
-/*
- * Basic modifier sanity check to validate it contains only one
- * instance of any modifier (apart from 'p') present.
- */
-static int check_modifier(char *str)
+int parse_events__modifier_group(struct parse_events_state *parse_state, void *loc,
+				 struct list_head *list,
+				 struct parse_events_modifier mod)
 {
-	char *p = str;
-
-	/* The sizeof includes 0 byte as well. */
-	if (strlen(str) > (sizeof("ukhGHpppPSDIWeb") - 1))
-		return -1;
-
-	while (*p) {
-		if (*p != 'p' && strchr(p + 1, *p))
-			return -1;
-		p++;
-	}
-
-	return 0;
+	return parse_events__modifier_list(parse_state, loc, list, mod, /*group=*/true);
 }
 
-int parse_events__modifier_event(struct list_head *list, char *str, bool add)
+int parse_events__modifier_event(struct parse_events_state *parse_state, void *loc,
+				 struct list_head *list,
+				 struct parse_events_modifier mod)
 {
-	struct evsel *evsel;
-	struct event_modifier mod;
-
-	if (str == NULL)
-		return 0;
-
-	if (check_modifier(str))
-		return -EINVAL;
-
-	if (!add && get_event_modifier(&mod, str, NULL))
-		return -EINVAL;
-
-	__evlist__for_each_entry(list, evsel) {
-		if (add && get_event_modifier(&mod, str, evsel))
-			return -EINVAL;
-
-		evsel->core.attr.exclude_user   = mod.eu;
-		evsel->core.attr.exclude_kernel = mod.ek;
-		evsel->core.attr.exclude_hv     = mod.eh;
-		evsel->core.attr.precise_ip     = mod.precise;
-		evsel->core.attr.exclude_host   = mod.eH;
-		evsel->core.attr.exclude_guest  = mod.eG;
-		evsel->core.attr.exclude_idle   = mod.eI;
-		evsel->exclude_GH          = mod.exclude_GH;
-		evsel->sample_read         = mod.sample_read;
-		evsel->precise_max         = mod.precise_max;
-		evsel->weak_group	   = mod.weak;
-		evsel->bpf_counter	   = mod.bpf_counter;
-
-		if (evsel__is_group_leader(evsel)) {
-			evsel->core.attr.pinned = mod.pinned;
-			evsel->core.attr.exclusive = mod.exclusive;
-		}
-	}
-
-	return 0;
+	return parse_events__modifier_list(parse_state, loc, list, mod, /*group=*/false);
 }
 
-int parse_events_name(struct list_head *list, const char *name)
+int parse_events__set_default_name(struct list_head *list, char *name)
 {
 	struct evsel *evsel;
+	bool used_name = false;
 
 	__evlist__for_each_entry(list, evsel) {
 		if (!evsel->name) {
-			evsel->name = strdup(name);
+			evsel->name = used_name ? strdup(name) : name;
+			used_name = true;
 			if (!evsel->name)
 				return -ENOMEM;
 		}
 	}
-
+	if (!used_name)
+		free(name);
 	return 0;
 }
 
@@ -2691,15 +2700,6 @@ int parse_events_terms__to_strbuf(const struct parse_events_terms *terms, struct
 	return 0;
 }
 
-void parse_events_evlist_error(struct parse_events_state *parse_state,
-			       int idx, const char *str)
-{
-	if (!parse_state->error)
-		return;
-
-	parse_events_error__handle(parse_state->error, idx, strdup(str), NULL);
-}
-
 static void config_terms_list(char *buf, size_t buf_sz)
 {
 	int i;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 809359e8544ef3..5695308efab981 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -186,9 +186,28 @@ void parse_events_terms__init(struct parse_events_terms *terms);
 void parse_events_terms__exit(struct parse_events_terms *terms);
 int parse_events_terms(struct parse_events_terms *terms, const char *str, FILE *input);
 int parse_events_terms__to_strbuf(const struct parse_events_terms *terms, struct strbuf *sb);
-int parse_events__modifier_event(struct list_head *list, char *str, bool add);
-int parse_events__modifier_group(struct list_head *list, char *event_mod);
-int parse_events_name(struct list_head *list, const char *name);
+
+struct parse_events_modifier {
+	u8 precise;	/* Number of repeated 'p' for precision. */
+	bool precise_max : 1;	/* 'P' */
+	bool non_idle : 1;	/* 'I' */
+	bool sample_read : 1;	/* 'S' */
+	bool pinned : 1;	/* 'D' */
+	bool exclusive : 1;	/* 'e' */
+	bool weak : 1;		/* 'W' */
+	bool bpf : 1;		/* 'b' */
+	bool user : 1;		/* 'u' */
+	bool kernel : 1;	/* 'k' */
+	bool hypervisor : 1;	/* 'h' */
+	bool guest : 1;		/* 'G' */
+	bool host : 1;		/* 'H' */
+};
+
+int parse_events__modifier_event(struct parse_events_state *parse_state, void *loc,
+				 struct list_head *list, struct parse_events_modifier mod);
+int parse_events__modifier_group(struct parse_events_state *parse_state, void *loc,
+				 struct list_head *list, struct parse_events_modifier mod);
+int parse_events__set_default_name(struct list_head *list, char *name);
 int parse_events_add_tracepoint(struct list_head *list, int *idx,
 				const char *sys, const char *event,
 				struct parse_events_error *error,
@@ -196,45 +215,43 @@ int parse_events_add_tracepoint(struct list_head *list, int *idx,
 int parse_events_add_numeric(struct parse_events_state *parse_state,
 			     struct list_head *list,
 			     u32 type, u64 config,
-			     struct parse_events_terms *head_config,
+			     const struct parse_events_terms *head_config,
 			     bool wildcard);
 int parse_events_add_tool(struct parse_events_state *parse_state,
 			  struct list_head *list,
 			  int tool_event);
 int parse_events_add_cache(struct list_head *list, int *idx, const char *name,
 			   struct parse_events_state *parse_state,
-			   struct parse_events_terms *head_config);
+			   struct parse_events_terms *parsed_terms);
 int parse_events__decode_legacy_cache(const char *name, int pmu_type, __u64 *config);
 int parse_events_add_breakpoint(struct parse_events_state *parse_state,
 				struct list_head *list,
 				u64 addr, char *type, u64 len,
 				struct parse_events_terms *head_config);
-int parse_events_add_pmu(struct parse_events_state *parse_state,
-			 struct list_head *list, const char *name,
-			 const struct parse_events_terms *const_parsed_terms,
-			bool auto_merge_stats, void *loc);
 
 struct evsel *parse_events__add_event(int idx, struct perf_event_attr *attr,
 				      const char *name, const char *metric_id,
 				      struct perf_pmu *pmu);
 
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
-			       const char *event_name,
+			       const char *event_name, u64 hw_config,
 			       const struct parse_events_terms *const_parsed_terms,
 			       struct list_head **listp, void *loc);
 
+int parse_events_multi_pmu_add_or_add_pmu(struct parse_events_state *parse_state,
+					const char *event_or_pmu,
+					const struct parse_events_terms *const_parsed_terms,
+					struct list_head **listp,
+					void *loc_);
+
 void parse_events__set_leader(char *name, struct list_head *list);
-void parse_events_update_lists(struct list_head *list_event,
-			       struct list_head *list_all);
-void parse_events_evlist_error(struct parse_events_state *parse_state,
-			       int idx, const char *str);
 
 struct event_symbol {
 	const char	*symbol;
 	const char	*alias;
 };
-extern struct event_symbol event_symbols_hw[];
-extern struct event_symbol event_symbols_sw[];
+extern const struct event_symbol event_symbols_hw[];
+extern const struct event_symbol event_symbols_sw[];
 
 char *parse_events_formats_error_string(char *additional_terms);
 
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index e86c45675e1d50..08ea2d845dc361 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -18,26 +18,34 @@
 
 char *parse_events_get_text(yyscan_t yyscanner);
 YYSTYPE *parse_events_get_lval(yyscan_t yyscanner);
+int parse_events_get_column(yyscan_t yyscanner);
+int parse_events_get_leng(yyscan_t yyscanner);
 
-static int __value(YYSTYPE *yylval, char *str, int base, int token)
+static int get_column(yyscan_t scanner)
 {
-	u64 num;
-
-	errno = 0;
-	num = strtoull(str, NULL, base);
-	if (errno)
-		return PE_ERROR;
-
-	yylval->num = num;
-	return token;
+	return parse_events_get_column(scanner) - parse_events_get_leng(scanner);
 }
 
-static int value(yyscan_t scanner, int base)
+static int value(struct parse_events_state *parse_state, yyscan_t scanner, int base)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
 	char *text = parse_events_get_text(scanner);
+	u64 num;
 
-	return __value(yylval, text, base, PE_VALUE);
+	errno = 0;
+	num = strtoull(text, NULL, base);
+	if (errno) {
+		struct parse_events_error *error = parse_state->error;
+		char *help = NULL;
+
+		if (asprintf(&help, "Bad base %d number \"%s\"", base, text) > 0)
+			parse_events_error__handle(error, get_column(scanner), help , NULL);
+
+		return PE_ERROR;
+	}
+
+	yylval->num = num;
+	return PE_VALUE;
 }
 
 static int str(yyscan_t scanner, int token)
@@ -88,6 +96,11 @@ static int drv_str(yyscan_t scanner, int token)
 	return token;
 }
 
+/*
+ * Use yyless to return all the characaters to the input. Update the column for
+ * location debugging. If __alloc is non-zero set yylval to the text for the
+ * returned token's value.
+ */
 #define REWIND(__alloc)				\
 do {								\
 	YYSTYPE *__yylval = parse_events_get_lval(yyscanner);	\
@@ -100,12 +113,12 @@ do {								\
 	yyless(0);						\
 } while (0)
 
-static int sym(yyscan_t scanner, int type, int config)
+static int sym(yyscan_t scanner, int config)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
 
-	yylval->num = (type << 16) + config;
-	return type == PERF_TYPE_HARDWARE ? PE_VALUE_SYM_HW : PE_VALUE_SYM_SW;
+	yylval->num = config;
+	return PE_VALUE_SYM_SW;
 }
 
 static int tool(yyscan_t scanner, enum perf_tool_event event)
@@ -124,16 +137,87 @@ static int term(yyscan_t scanner, enum parse_events__term_type type)
 	return PE_TERM;
 }
 
-static int hw_term(yyscan_t scanner, int config)
+static int hw(yyscan_t scanner, int config)
 {
 	YYSTYPE *yylval = parse_events_get_lval(scanner);
 	char *text = parse_events_get_text(scanner);
 
-	yylval->hardware_term.str = strdup(text);
-	yylval->hardware_term.num = PERF_TYPE_HARDWARE + config;
+	yylval->hardware_event.str = strdup(text);
+	yylval->hardware_event.num = config;
 	return PE_TERM_HW;
 }
 
+static void modifiers_error(struct parse_events_state *parse_state, yyscan_t scanner,
+			    int pos, char mod_char, const char *mod_name)
+{
+	struct parse_events_error *error = parse_state->error;
+	char *help = NULL;
+
+	if (asprintf(&help, "Duplicate modifier '%c' (%s)", mod_char, mod_name) > 0)
+		parse_events_error__handle(error, get_column(scanner) + pos, help , NULL);
+}
+
+static int modifiers(struct parse_events_state *parse_state, yyscan_t scanner)
+{
+	YYSTYPE *yylval = parse_events_get_lval(scanner);
+	char *text = parse_events_get_text(scanner);
+	struct parse_events_modifier mod = { .precise = 0, };
+
+	for (size_t i = 0, n = strlen(text); i < n; i++) {
+#define CASE(c, field)							\
+		case c:							\
+			if (mod.field) {				\
+				modifiers_error(parse_state, scanner, i, c, #field); \
+				return PE_ERROR;			\
+			}						\
+			mod.field = true;				\
+			break
+
+		switch (text[i]) {
+		CASE('u', user);
+		CASE('k', kernel);
+		CASE('h', hypervisor);
+		CASE('I', non_idle);
+		CASE('G', guest);
+		CASE('H', host);
+		case 'p':
+			mod.precise++;
+			/*
+			 * precise ip:
+			 *
+			 *  0 - SAMPLE_IP can have arbitrary skid
+			 *  1 - SAMPLE_IP must have constant skid
+			 *  2 - SAMPLE_IP requested to have 0 skid
+			 *  3 - SAMPLE_IP must have 0 skid
+			 *
+			 *  See also PERF_RECORD_MISC_EXACT_IP
+			 */
+			if (mod.precise > 3) {
+				struct parse_events_error *error = parse_state->error;
+				char *help = strdup("Maximum precise value is 3");
+
+				if (help) {
+					parse_events_error__handle(error, get_column(scanner) + i,
+								   help , NULL);
+				}
+				return PE_ERROR;
+			}
+			break;
+		CASE('P', precise_max);
+		CASE('S', sample_read);
+		CASE('D', pinned);
+		CASE('W', weak);
+		CASE('e', exclusive);
+		CASE('b', bpf);
+		default:
+			return PE_ERROR;
+		}
+#undef CASE
+	}
+	yylval->mod = mod;
+	return PE_MODIFIER_EVENT;
+}
+
 #define YY_USER_ACTION					\
 do {							\
 	yylloc->last_column  = yylloc->first_column;	\
@@ -166,7 +250,7 @@ drv_cfg_term	[a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)?
  * If you add a modifier you need to update check_modifier().
  * Also, the letters in modifier_event must not be in modifier_bp.
  */
-modifier_event	[ukhpPGHSDIWeb]+
+modifier_event	[ukhpPGHSDIWeb]{1,15}
 modifier_bp	[rwx]{1,3}
 lc_type 	(L1-dcache|l1-d|l1d|L1-data|L1-icache|l1-i|l1i|L1-instruction|LLC|L2|dTLB|d-tlb|Data-TLB|iTLB|i-tlb|Instruction-TLB|branch|branches|bpu|btb|bpc|node)
 lc_op_result	(load|loads|read|store|stores|write|prefetch|prefetches|speculative-read|speculative-load|refs|Reference|ops|access|misses|miss)
@@ -246,16 +330,16 @@ percore			{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_PERCORE); }
 aux-output		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_OUTPUT); }
 aux-sample-size		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_AUX_SAMPLE_SIZE); }
 metric-id		{ return term(yyscanner, PARSE_EVENTS__TERM_TYPE_METRIC_ID); }
-cpu-cycles|cycles				{ return hw_term(yyscanner, PERF_COUNT_HW_CPU_CYCLES); }
-stalled-cycles-frontend|idle-cycles-frontend	{ return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
-stalled-cycles-backend|idle-cycles-backend	{ return hw_term(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
-instructions					{ return hw_term(yyscanner, PERF_COUNT_HW_INSTRUCTIONS); }
-cache-references				{ return hw_term(yyscanner, PERF_COUNT_HW_CACHE_REFERENCES); }
-cache-misses					{ return hw_term(yyscanner, PERF_COUNT_HW_CACHE_MISSES); }
-branch-instructions|branches			{ return hw_term(yyscanner, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
-branch-misses					{ return hw_term(yyscanner, PERF_COUNT_HW_BRANCH_MISSES); }
-bus-cycles					{ return hw_term(yyscanner, PERF_COUNT_HW_BUS_CYCLES); }
-ref-cycles					{ return hw_term(yyscanner, PERF_COUNT_HW_REF_CPU_CYCLES); }
+cpu-cycles|cycles				{ return hw(yyscanner, PERF_COUNT_HW_CPU_CYCLES); }
+stalled-cycles-frontend|idle-cycles-frontend	{ return hw(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
+stalled-cycles-backend|idle-cycles-backend	{ return hw(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
+instructions					{ return hw(yyscanner, PERF_COUNT_HW_INSTRUCTIONS); }
+cache-references				{ return hw(yyscanner, PERF_COUNT_HW_CACHE_REFERENCES); }
+cache-misses					{ return hw(yyscanner, PERF_COUNT_HW_CACHE_MISSES); }
+branch-instructions|branches			{ return hw(yyscanner, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
+branch-misses					{ return hw(yyscanner, PERF_COUNT_HW_BRANCH_MISSES); }
+bus-cycles					{ return hw(yyscanner, PERF_COUNT_HW_BUS_CYCLES); }
+ref-cycles					{ return hw(yyscanner, PERF_COUNT_HW_REF_CPU_CYCLES); }
 r{num_raw_hex}		{ return str(yyscanner, PE_RAW); }
 r0x{num_raw_hex}	{ return str(yyscanner, PE_RAW); }
 ,			{ return ','; }
@@ -283,8 +367,8 @@ r0x{num_raw_hex}	{ return str(yyscanner, PE_RAW); }
 	 */
 "/"/{digit}		{ return PE_BP_SLASH; }
 "/"/{non_digit}		{ BEGIN(config); return '/'; }
-{num_dec}		{ return value(yyscanner, 10); }
-{num_hex}		{ return value(yyscanner, 16); }
+{num_dec}		{ return value(_parse_state, yyscanner, 10); }
+{num_hex}		{ return value(_parse_state, yyscanner, 16); }
 	/*
 	 * We need to separate 'mem:' scanner part, in order to get specific
 	 * modifier bits parsed out. Otherwise we would need to handle PE_NAME
@@ -299,41 +383,41 @@ r0x{num_raw_hex}	{ return str(yyscanner, PE_RAW); }
 <<EOF>>			{ BEGIN(INITIAL); }
 }
 
-cpu-cycles|cycles				{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CPU_CYCLES); }
-stalled-cycles-frontend|idle-cycles-frontend	{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
-stalled-cycles-backend|idle-cycles-backend	{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
-instructions					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_INSTRUCTIONS); }
-cache-references				{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_REFERENCES); }
-cache-misses					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_CACHE_MISSES); }
-branch-instructions|branches			{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
-branch-misses					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BRANCH_MISSES); }
-bus-cycles					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_BUS_CYCLES); }
-ref-cycles					{ return sym(yyscanner, PERF_TYPE_HARDWARE, PERF_COUNT_HW_REF_CPU_CYCLES); }
-cpu-clock					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_CLOCK); }
-task-clock					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_TASK_CLOCK); }
-page-faults|faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS); }
-minor-faults					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MIN); }
-major-faults					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_PAGE_FAULTS_MAJ); }
-context-switches|cs				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CONTEXT_SWITCHES); }
-cpu-migrations|migrations			{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CPU_MIGRATIONS); }
-alignment-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
-emulation-faults				{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_EMULATION_FAULTS); }
-dummy						{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_DUMMY); }
+cpu-cycles|cycles				{ return hw(yyscanner, PERF_COUNT_HW_CPU_CYCLES); }
+stalled-cycles-frontend|idle-cycles-frontend	{ return hw(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_FRONTEND); }
+stalled-cycles-backend|idle-cycles-backend	{ return hw(yyscanner, PERF_COUNT_HW_STALLED_CYCLES_BACKEND); }
+instructions					{ return hw(yyscanner, PERF_COUNT_HW_INSTRUCTIONS); }
+cache-references				{ return hw(yyscanner, PERF_COUNT_HW_CACHE_REFERENCES); }
+cache-misses					{ return hw(yyscanner, PERF_COUNT_HW_CACHE_MISSES); }
+branch-instructions|branches			{ return hw(yyscanner, PERF_COUNT_HW_BRANCH_INSTRUCTIONS); }
+branch-misses					{ return hw(yyscanner, PERF_COUNT_HW_BRANCH_MISSES); }
+bus-cycles					{ return hw(yyscanner, PERF_COUNT_HW_BUS_CYCLES); }
+ref-cycles					{ return hw(yyscanner, PERF_COUNT_HW_REF_CPU_CYCLES); }
+cpu-clock					{ return sym(yyscanner, PERF_COUNT_SW_CPU_CLOCK); }
+task-clock					{ return sym(yyscanner, PERF_COUNT_SW_TASK_CLOCK); }
+page-faults|faults				{ return sym(yyscanner, PERF_COUNT_SW_PAGE_FAULTS); }
+minor-faults					{ return sym(yyscanner, PERF_COUNT_SW_PAGE_FAULTS_MIN); }
+major-faults					{ return sym(yyscanner, PERF_COUNT_SW_PAGE_FAULTS_MAJ); }
+context-switches|cs				{ return sym(yyscanner, PERF_COUNT_SW_CONTEXT_SWITCHES); }
+cpu-migrations|migrations			{ return sym(yyscanner, PERF_COUNT_SW_CPU_MIGRATIONS); }
+alignment-faults				{ return sym(yyscanner, PERF_COUNT_SW_ALIGNMENT_FAULTS); }
+emulation-faults				{ return sym(yyscanner, PERF_COUNT_SW_EMULATION_FAULTS); }
+dummy						{ return sym(yyscanner, PERF_COUNT_SW_DUMMY); }
 duration_time					{ return tool(yyscanner, PERF_TOOL_DURATION_TIME); }
 user_time						{ return tool(yyscanner, PERF_TOOL_USER_TIME); }
 system_time						{ return tool(yyscanner, PERF_TOOL_SYSTEM_TIME); }
-bpf-output					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_BPF_OUTPUT); }
-cgroup-switches					{ return sym(yyscanner, PERF_TYPE_SOFTWARE, PERF_COUNT_SW_CGROUP_SWITCHES); }
+bpf-output					{ return sym(yyscanner, PERF_COUNT_SW_BPF_OUTPUT); }
+cgroup-switches					{ return sym(yyscanner, PERF_COUNT_SW_CGROUP_SWITCHES); }
 
 {lc_type}			{ return str(yyscanner, PE_LEGACY_CACHE); }
 {lc_type}-{lc_op_result}	{ return str(yyscanner, PE_LEGACY_CACHE); }
 {lc_type}-{lc_op_result}-{lc_op_result}	{ return str(yyscanner, PE_LEGACY_CACHE); }
 mem:			{ BEGIN(mem); return PE_PREFIX_MEM; }
 r{num_raw_hex}		{ return str(yyscanner, PE_RAW); }
-{num_dec}		{ return value(yyscanner, 10); }
-{num_hex}		{ return value(yyscanner, 16); }
+{num_dec}		{ return value(_parse_state, yyscanner, 10); }
+{num_hex}		{ return value(_parse_state, yyscanner, 16); }
 
-{modifier_event}	{ return str(yyscanner, PE_MODIFIER_EVENT); }
+{modifier_event}	{ return modifiers(_parse_state, yyscanner); }
 {name}			{ return str(yyscanner, PE_NAME); }
 {name_tag}		{ return str(yyscanner, PE_NAME); }
 "/"			{ BEGIN(config); return '/'; }
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index d70f5d84af92d1..68b3b06c7ff06b 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -55,7 +55,7 @@ static void free_list_evsel(struct list_head* list_evsel)
 %}
 
 %token PE_START_EVENTS PE_START_TERMS
-%token PE_VALUE PE_VALUE_SYM_HW PE_VALUE_SYM_SW PE_TERM
+%token PE_VALUE PE_VALUE_SYM_SW PE_TERM
 %token PE_VALUE_SYM_TOOL
 %token PE_EVENT_NAME
 %token PE_RAW PE_NAME
@@ -66,15 +66,13 @@ static void free_list_evsel(struct list_head* list_evsel)
 %token PE_DRV_CFG_TERM
 %token PE_TERM_HW
 %type <num> PE_VALUE
-%type <num> PE_VALUE_SYM_HW
 %type <num> PE_VALUE_SYM_SW
 %type <num> PE_VALUE_SYM_TOOL
+%type <mod> PE_MODIFIER_EVENT
 %type <term_type> PE_TERM
-%type <num> value_sym
 %type <str> PE_RAW
 %type <str> PE_NAME
 %type <str> PE_LEGACY_CACHE
-%type <str> PE_MODIFIER_EVENT
 %type <str> PE_MODIFIER_BP
 %type <str> PE_EVENT_NAME
 %type <str> PE_DRV_CFG_TERM
@@ -87,6 +85,7 @@ static void free_list_evsel(struct list_head* list_evsel)
 %type <list_terms> opt_pmu_config
 %destructor { parse_events_terms__delete ($$); } <list_terms>
 %type <list_evsel> event_pmu
+%type <list_evsel> event_legacy_hardware
 %type <list_evsel> event_legacy_symbol
 %type <list_evsel> event_legacy_cache
 %type <list_evsel> event_legacy_mem
@@ -104,13 +103,14 @@ static void free_list_evsel(struct list_head* list_evsel)
 %destructor { free_list_evsel ($$); } <list_evsel>
 %type <tracepoint_name> tracepoint_name
 %destructor { free ($$.sys); free ($$.event); } <tracepoint_name>
-%type <hardware_term> PE_TERM_HW
-%destructor { free ($$.str); } <hardware_term>
+%type <hardware_event> PE_TERM_HW
+%destructor { free ($$.str); } <hardware_event>
 
 %union
 {
 	char *str;
 	u64 num;
+	struct parse_events_modifier mod;
 	enum parse_events__term_type term_type;
 	struct list_head *list_evsel;
 	struct parse_events_terms *list_terms;
@@ -119,13 +119,17 @@ static void free_list_evsel(struct list_head* list_evsel)
 		char *sys;
 		char *event;
 	} tracepoint_name;
-	struct hardware_term {
+	struct hardware_event {
 		char *str;
 		u64 num;
-	} hardware_term;
+	} hardware_event;
 }
 %%
 
+ /*
+  * Entry points. We are either parsing events or terminals. Just terminal
+  * parsing is used for parsing events in sysfs.
+  */
 start:
 PE_START_EVENTS start_events
 |
@@ -133,31 +137,36 @@ PE_START_TERMS  start_terms
 
 start_events: groups
 {
+	/* Take the parsed events, groups.. and place into parse_state. */
+	struct list_head *groups  = $1;
 	struct parse_events_state *parse_state = _parse_state;
 
-	/* frees $1 */
-	parse_events_update_lists($1, &parse_state->list);
+	list_splice_tail(groups, &parse_state->list);
+	free(groups);
 }
 
-groups:
+groups: /* A list of groups or events. */
 groups ',' group
 {
-	struct list_head *list  = $1;
-	struct list_head *group = $3;
+	/* Merge group into the list of events/groups. */
+	struct list_head *groups  = $1;
+	struct list_head *group  = $3;
 
-	/* frees $3 */
-	parse_events_update_lists(group, list);
-	$$ = list;
+	list_splice_tail(group, groups);
+	free(group);
+	$$ = groups;
 }
 |
 groups ',' event
 {
-	struct list_head *list  = $1;
+	/* Merge event into the list of events/groups. */
+	struct list_head *groups  = $1;
 	struct list_head *event = $3;
 
-	/* frees $3 */
-	parse_events_update_lists(event, list);
-	$$ = list;
+
+	list_splice_tail(event, groups);
+	free(event);
+	$$ = groups;
 }
 |
 group
@@ -167,20 +176,13 @@ event
 group:
 group_def ':' PE_MODIFIER_EVENT
 {
+	/* Apply the modifier to the events in the group_def. */
 	struct list_head *list = $1;
 	int err;
 
-	err = parse_events__modifier_group(list, $3);
-	free($3);
-	if (err) {
-		struct parse_events_state *parse_state = _parse_state;
-		struct parse_events_error *error = parse_state->error;
-
-		parse_events_error__handle(error, @3.first_column,
-					   strdup("Bad modifier"), NULL);
-		free_list_evsel(list);
+	err = parse_events__modifier_group(_parse_state, &@3, list, $3);
+	if (err)
 		YYABORT;
-	}
 	$$ = list;
 }
 |
@@ -191,7 +193,10 @@ PE_NAME '{' events '}'
 {
 	struct list_head *list = $3;
 
-	/* Takes ownership of $1. */
+	/*
+	 * Set the first entry of list to be the leader. Set the group name on
+	 * the leader to $1 taking ownership.
+	 */
 	parse_events__set_leader($1, list);
 	$$ = list;
 }
@@ -200,6 +205,7 @@ PE_NAME '{' events '}'
 {
 	struct list_head *list = $2;
 
+	/* Set the first entry of list to be the leader clearing the group name. */
 	parse_events__set_leader(NULL, list);
 	$$ = list;
 }
@@ -207,12 +213,12 @@ PE_NAME '{' events '}'
 events:
 events ',' event
 {
+	struct list_head *events  = $1;
 	struct list_head *event = $3;
-	struct list_head *list  = $1;
 
-	/* frees $3 */
-	parse_events_update_lists(event, list);
-	$$ = list;
+	list_splice_tail(event, events);
+	free(event);
+	$$ = events;
 }
 |
 event
@@ -230,17 +236,9 @@ event_name PE_MODIFIER_EVENT
 	 * (there could be more events added for multiple tracepoint
 	 * definitions via '*?'.
 	 */
-	err = parse_events__modifier_event(list, $2, false);
-	free($2);
-	if (err) {
-		struct parse_events_state *parse_state = _parse_state;
-		struct parse_events_error *error = parse_state->error;
-
-		parse_events_error__handle(error, @2.first_column,
-					   strdup("Bad modifier"), NULL);
-		free_list_evsel(list);
+	err = parse_events__modifier_event(_parse_state, &@2, list, $2);
+	if (err)
 		YYABORT;
-	}
 	$$ = list;
 }
 |
@@ -249,10 +247,14 @@ event_name
 event_name:
 PE_EVENT_NAME event_def
 {
-	int err;
+	/*
+	 * When an event is parsed the text is rewound and the entire text of
+	 * the event is set to the str of PE_EVENT_NAME token matched here. If
+	 * no name was on an event via a term, set the name to the entire text
+	 * taking ownership of the allocation.
+	 */
+	int err = parse_events__set_default_name($2, $1);
 
-	err = parse_events_name($2, $1);
-	free($1);
 	if (err) {
 		free_list_evsel($2);
 		YYNOMEM;
@@ -263,6 +265,7 @@ PE_EVENT_NAME event_def
 event_def
 
 event_def: event_pmu |
+	   event_legacy_hardware |
 	   event_legacy_symbol |
 	   event_legacy_cache sep_dc |
 	   event_legacy_mem sep_dc |
@@ -273,78 +276,15 @@ event_def: event_pmu |
 event_pmu:
 PE_NAME opt_pmu_config
 {
-	struct parse_events_state *parse_state = _parse_state;
 	/* List of created evsels. */
 	struct list_head *list = NULL;
-	char *pattern = NULL;
+	int err = parse_events_multi_pmu_add_or_add_pmu(_parse_state, $1, $2, &list, &@1);
 
-#define CLEANUP						\
-	do {						\
-		parse_events_terms__delete($2);		\
-		free(list);				\
-		free($1);				\
-		free(pattern);				\
-	} while(0)
-
-	list = alloc_list();
-	if (!list) {
-		CLEANUP;
-		YYNOMEM;
-	}
-	/* Attempt to add to list assuming $1 is a PMU name. */
-	if (parse_events_add_pmu(parse_state, list, $1, $2, /*auto_merge_stats=*/false, &@1)) {
-		struct perf_pmu *pmu = NULL;
-		int ok = 0;
-
-		/* Failure to add, try wildcard expansion of $1 as a PMU name. */
-		if (asprintf(&pattern, "%s*", $1) < 0) {
-			CLEANUP;
-			YYNOMEM;
-		}
-
-		while ((pmu = perf_pmus__scan(pmu)) != NULL) {
-			const char *name = pmu->name;
-
-			if (parse_events__filter_pmu(parse_state, pmu))
-				continue;
-
-			if (!strncmp(name, "uncore_", 7) &&
-			    strncmp($1, "uncore_", 7))
-				name += 7;
-			if (!perf_pmu__match(pattern, name, $1) ||
-			    !perf_pmu__match(pattern, pmu->alias_name, $1)) {
-				bool auto_merge_stats = perf_pmu__auto_merge_stats(pmu);
-
-				if (!parse_events_add_pmu(parse_state, list, pmu->name, $2,
-							  auto_merge_stats, &@1)) {
-					ok++;
-					parse_state->wild_card_pmus = true;
-				}
-			}
-		}
-
-		if (!ok) {
-			/* Failure to add, assume $1 is an event name. */
-			zfree(&list);
-			ok = !parse_events_multi_pmu_add(parse_state, $1, $2, &list, &@1);
-		}
-		if (!ok) {
-			struct parse_events_error *error = parse_state->error;
-			char *help;
-
-			if (asprintf(&help, "Unable to find PMU or event on a PMU of '%s'", $1) < 0)
-				help = NULL;
-			parse_events_error__handle(error, @1.first_column,
-						   strdup("Bad event or PMU"),
-						   help);
-			CLEANUP;
-			YYABORT;
-		}
-	}
+	parse_events_terms__delete($2);
+	free($1);
+	if (err)
+		PE_ABORT(err);
 	$$ = list;
-	list = NULL;
-	CLEANUP;
-#undef CLEANUP
 }
 |
 PE_NAME sep_dc
@@ -352,7 +292,7 @@ PE_NAME sep_dc
 	struct list_head *list;
 	int err;
 
-	err = parse_events_multi_pmu_add(_parse_state, $1, NULL, &list, &@1);
+	err = parse_events_multi_pmu_add(_parse_state, $1, PERF_COUNT_HW_MAX, NULL, &list, &@1);
 	if (err < 0) {
 		struct parse_events_state *parse_state = _parse_state;
 		struct parse_events_error *error = parse_state->error;
@@ -368,24 +308,45 @@ PE_NAME sep_dc
 	$$ = list;
 }
 
-value_sym:
-PE_VALUE_SYM_HW
+event_legacy_hardware:
+PE_TERM_HW opt_pmu_config
+{
+	/* List of created evsels. */
+	struct list_head *list = NULL;
+	int err = parse_events_multi_pmu_add(_parse_state, $1.str, $1.num, $2, &list, &@1);
+
+	free($1.str);
+	parse_events_terms__delete($2);
+	if (err)
+		PE_ABORT(err);
+
+	$$ = list;
+}
 |
-PE_VALUE_SYM_SW
+PE_TERM_HW sep_dc
+{
+	struct list_head *list;
+	int err;
+
+	err = parse_events_multi_pmu_add(_parse_state, $1.str, $1.num, NULL, &list, &@1);
+	free($1.str);
+	if (err)
+		PE_ABORT(err);
+	$$ = list;
+}
 
 event_legacy_symbol:
-value_sym '/' event_config '/'
+PE_VALUE_SYM_SW '/' event_config '/'
 {
 	struct list_head *list;
-	int type = $1 >> 16;
-	int config = $1 & 255;
 	int err;
-	bool wildcard = (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE);
 
 	list = alloc_list();
 	if (!list)
 		YYNOMEM;
-	err = parse_events_add_numeric(_parse_state, list, type, config, $3, wildcard);
+	err = parse_events_add_numeric(_parse_state, list,
+				/*type=*/PERF_TYPE_SOFTWARE, /*config=*/$1,
+				$3, /*wildcard=*/false);
 	parse_events_terms__delete($3);
 	if (err) {
 		free_list_evsel(list);
@@ -394,18 +355,17 @@ value_sym '/' event_config '/'
 	$$ = list;
 }
 |
-value_sym sep_slash_slash_dc
+PE_VALUE_SYM_SW sep_slash_slash_dc
 {
 	struct list_head *list;
-	int type = $1 >> 16;
-	int config = $1 & 255;
-	bool wildcard = (type == PERF_TYPE_HARDWARE || type == PERF_TYPE_HW_CACHE);
 	int err;
 
 	list = alloc_list();
 	if (!list)
 		YYNOMEM;
-	err = parse_events_add_numeric(_parse_state, list, type, config, /*head_config=*/NULL, wildcard);
+	err = parse_events_add_numeric(_parse_state, list,
+				/*type=*/PERF_TYPE_SOFTWARE, /*config=*/$1,
+				/*head_config=*/NULL, /*wildcard=*/false);
 	if (err)
 		PE_ABORT(err);
 	$$ = list;
@@ -666,6 +626,11 @@ event_term
 }
 
 name_or_raw: PE_RAW | PE_NAME | PE_LEGACY_CACHE
+|
+PE_TERM_HW
+{
+	$$ = $1.str;
+}
 
 event_term:
 PE_RAW
@@ -707,20 +672,6 @@ name_or_raw '=' PE_VALUE
 	$$ = term;
 }
 |
-name_or_raw '=' PE_TERM_HW
-{
-	struct parse_events_term *term;
-	int err = parse_events_term__str(&term, PARSE_EVENTS__TERM_TYPE_USER,
-					 $1, $3.str, &@1, &@3);
-
-	if (err) {
-		free($1);
-		free($3.str);
-		PE_ABORT(err);
-	}
-	$$ = term;
-}
-|
 PE_LEGACY_CACHE
 {
 	struct parse_events_term *term;
@@ -773,18 +724,6 @@ PE_TERM '=' name_or_raw
 	$$ = term;
 }
 |
-PE_TERM '=' PE_TERM_HW
-{
-	struct parse_events_term *term;
-	int err = parse_events_term__str(&term, $1, /*config=*/NULL, $3.str, &@1, &@3);
-
-	if (err) {
-		free($3.str);
-		PE_ABORT(err);
-	}
-	$$ = term;
-}
-|
 PE_TERM '=' PE_TERM
 {
 	struct parse_events_term *term;
@@ -845,9 +784,15 @@ sep_slash_slash_dc: '/' '/' | ':' |
 
 %%
 
-void parse_events_error(YYLTYPE *loc, void *parse_state,
+void parse_events_error(YYLTYPE *loc, void *_parse_state,
 			void *scanner __maybe_unused,
 			char const *msg __maybe_unused)
 {
-	parse_events_evlist_error(parse_state, loc->last_column, "parser error");
+	struct parse_events_state *parse_state = _parse_state;
+
+	if (!parse_state->error || !list_empty(&parse_state->error->list))
+		return;
+
+	parse_events_error__handle(parse_state->error, loc->last_column,
+				   strdup("Unrecognized input"), NULL);
 }
diff --git a/tools/perf/util/perf_event_attr_fprintf.c b/tools/perf/util/perf_event_attr_fprintf.c
index 8f04d3b7f3ec78..59fbbba7969740 100644
--- a/tools/perf/util/perf_event_attr_fprintf.c
+++ b/tools/perf/util/perf_event_attr_fprintf.c
@@ -7,6 +7,8 @@
 #include <linux/types.h>
 #include <linux/perf_event.h>
 #include "util/evsel_fprintf.h"
+#include "util/pmu.h"
+#include "util/pmus.h"
 #include "trace-event.h"
 
 struct bit_names {
@@ -75,9 +77,12 @@ static void __p_read_format(char *buf, size_t size, u64 value)
 }
 
 #define ENUM_ID_TO_STR_CASE(x) case x: return (#x);
-static const char *stringify_perf_type_id(u64 value)
+static const char *stringify_perf_type_id(struct perf_pmu *pmu, u32 type)
 {
-	switch (value) {
+	if (pmu)
+		return pmu->name;
+
+	switch (type) {
 	ENUM_ID_TO_STR_CASE(PERF_TYPE_HARDWARE)
 	ENUM_ID_TO_STR_CASE(PERF_TYPE_SOFTWARE)
 	ENUM_ID_TO_STR_CASE(PERF_TYPE_TRACEPOINT)
@@ -175,9 +180,9 @@ do {								\
 #define print_id_unsigned(_s)	PRINT_ID(_s, "%"PRIu64)
 #define print_id_hex(_s)	PRINT_ID(_s, "%#"PRIx64)
 
-static void __p_type_id(char *buf, size_t size, u64 value)
+static void __p_type_id(struct perf_pmu *pmu, char *buf, size_t size, u64 value)
 {
-	print_id_unsigned(stringify_perf_type_id(value));
+	print_id_unsigned(stringify_perf_type_id(pmu, value));
 }
 
 static void __p_config_hw_id(char *buf, size_t size, u64 value)
@@ -217,8 +222,14 @@ static void __p_config_tracepoint_id(char *buf, size_t size, u64 value)
 }
 #endif
 
-static void __p_config_id(char *buf, size_t size, u32 type, u64 value)
+static void __p_config_id(struct perf_pmu *pmu, char *buf, size_t size, u32 type, u64 value)
 {
+	const char *name = perf_pmu__name_from_config(pmu, value);
+
+	if (name) {
+		print_id_hex(name);
+		return;
+	}
 	switch (type) {
 	case PERF_TYPE_HARDWARE:
 		return __p_config_hw_id(buf, size, value);
@@ -246,8 +257,8 @@ static void __p_config_id(char *buf, size_t size, u32 type, u64 value)
 #define p_sample_type(val)	__p_sample_type(buf, BUF_SIZE, val)
 #define p_branch_sample_type(val) __p_branch_sample_type(buf, BUF_SIZE, val)
 #define p_read_format(val)	__p_read_format(buf, BUF_SIZE, val)
-#define p_type_id(val)		__p_type_id(buf, BUF_SIZE, val)
-#define p_config_id(val)	__p_config_id(buf, BUF_SIZE, attr->type, val)
+#define p_type_id(val)		__p_type_id(pmu, buf, BUF_SIZE, val)
+#define p_config_id(val)	__p_config_id(pmu, buf, BUF_SIZE, attr->type, val)
 
 #define PRINT_ATTRn(_n, _f, _p, _a)			\
 do {							\
@@ -262,6 +273,7 @@ do {							\
 int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 			     attr__fprintf_f attr__fprintf, void *priv)
 {
+	struct perf_pmu *pmu = perf_pmus__find_by_type(attr->type);
 	char buf[BUF_SIZE];
 	int ret = 0;
 
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index f39cbbc1a7ec1d..74dd5bd49d9a86 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -518,7 +518,8 @@ static int perf_pmu__new_alias(struct perf_pmu *pmu, const char *name,
 		unit = pe->unit;
 		perpkg = pe->perpkg;
 		deprecated = pe->deprecated;
-		pmu_name = pe->pmu;
+		if (pe->pmu && strcmp(pe->pmu, "default_core"))
+			pmu_name = pe->pmu;
 	}
 
 	alias = zalloc(sizeof(*alias));
@@ -1602,6 +1603,62 @@ bool perf_pmu__has_format(const struct perf_pmu *pmu, const char *name)
 	return false;
 }
 
+int perf_pmu__for_each_format(struct perf_pmu *pmu, void *state, pmu_format_callback cb)
+{
+	static const char *const terms[] = {
+		"config=0..0xffffffffffffffff",
+		"config1=0..0xffffffffffffffff",
+		"config2=0..0xffffffffffffffff",
+		"config3=0..0xffffffffffffffff",
+		"name=string",
+		"period=number",
+		"freq=number",
+		"branch_type=(u|k|hv|any|...)",
+		"time",
+		"call-graph=(fp|dwarf|lbr)",
+		"stack-size=number",
+		"max-stack=number",
+		"nr=number",
+		"inherit",
+		"no-inherit",
+		"overwrite",
+		"no-overwrite",
+		"percore",
+		"aux-output",
+		"aux-sample-size=number",
+	};
+	struct perf_pmu_format *format;
+	int ret;
+
+	/*
+	 * max-events and driver-config are missing above as are the internal
+	 * types user, metric-id, raw, legacy cache and hardware. Assert against
+	 * the enum parse_events__term_type so they are kept in sync.
+	 */
+	_Static_assert(ARRAY_SIZE(terms) == __PARSE_EVENTS__TERM_TYPE_NR - 6,
+		       "perf_pmu__for_each_format()'s terms must be kept in sync with enum parse_events__term_type");
+	list_for_each_entry(format, &pmu->format, list) {
+		perf_pmu_format__load(pmu, format);
+		ret = cb(state, format->name, (int)format->value, format->bits);
+		if (ret)
+			return ret;
+	}
+	if (!pmu->is_core)
+		return 0;
+
+	for (size_t i = 0; i < ARRAY_SIZE(terms); i++) {
+		int config = PERF_PMU_FORMAT_VALUE_CONFIG;
+
+		if (i < PERF_PMU_FORMAT_VALUE_CONFIG_END)
+			config = i;
+
+		ret = cb(state, terms[i], config, /*bits=*/NULL);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
 bool is_pmu_core(const char *name)
 {
 	return !strcmp(name, "cpu") || !strcmp(name, "cpum_cf") || is_sysfs_pmu_core(name);
@@ -1696,8 +1753,12 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus,
 	pmu_add_cpu_aliases(pmu);
 	list_for_each_entry(event, &pmu->aliases, list) {
 		size_t buf_used;
+		int pmu_name_len;
 
 		info.pmu_name = event->pmu_name ?: pmu->name;
+		pmu_name_len = skip_duplicate_pmus
+			? pmu_name_len_no_suffix(info.pmu_name, /*num=*/NULL)
+			: (int)strlen(info.pmu_name);
 		info.alias = NULL;
 		if (event->desc) {
 			info.name = event->name;
@@ -1722,7 +1783,7 @@ int perf_pmu__for_each_event(struct perf_pmu *pmu, bool skip_duplicate_pmus,
 		info.encoding_desc = buf + buf_used;
 		parse_events_terms__to_strbuf(&event->terms, &sb);
 		buf_used += snprintf(buf + buf_used, sizeof(buf) - buf_used,
-				"%s/%s/", info.pmu_name, sb.buf) + 1;
+				"%.*s/%s/", pmu_name_len, info.pmu_name, sb.buf) + 1;
 		info.topic = event->topic;
 		info.str = sb.buf;
 		info.deprecated = event->deprecated;
@@ -2003,18 +2064,29 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
 		   name ?: "N/A", buf, config_name, config);
 }
 
-int perf_pmu__match(const char *pattern, const char *name, const char *tok)
+bool perf_pmu__match(const struct perf_pmu *pmu, const char *tok)
 {
-	if (!name)
-		return -1;
+	const char *name = pmu->name;
+	bool need_fnmatch = strchr(tok, '*') != NULL;
 
-	if (fnmatch(pattern, name, 0))
-		return -1;
+	if (!strncmp(tok, "uncore_", 7))
+		tok += 7;
+	if (!strncmp(name, "uncore_", 7))
+		name += 7;
 
-	if (tok && !perf_pmu__match_ignoring_suffix(name, tok))
-		return -1;
+	if (perf_pmu__match_ignoring_suffix(name, tok) ||
+	    (need_fnmatch && !fnmatch(tok, name, 0)))
+		return true;
 
-	return 0;
+	name = pmu->alias_name;
+	if (!name)
+		return false;
+
+	if (!strncmp(name, "uncore_", 7))
+		name += 7;
+
+	return perf_pmu__match_ignoring_suffix(name, tok) ||
+		(need_fnmatch && !fnmatch(tok, name, 0));
 }
 
 double __weak perf_pmu__cpu_slots_per_cycle(void)
@@ -2085,3 +2157,21 @@ void perf_pmu__delete(struct perf_pmu *pmu)
 	zfree(&pmu->id);
 	free(pmu);
 }
+
+const char *perf_pmu__name_from_config(struct perf_pmu *pmu, u64 config)
+{
+	struct perf_pmu_alias *event;
+
+	if (!pmu)
+		return NULL;
+
+	pmu_add_cpu_aliases(pmu);
+	list_for_each_entry(event, &pmu->aliases, list) {
+		struct perf_event_attr attr = {.config = 0,};
+		int ret = perf_pmu__config(pmu, &attr, &event->terms, NULL);
+
+		if (ret == 0 && config == attr.config)
+			return event->name;
+	}
+	return NULL;
+}
diff --git a/tools/perf/util/pmu.h b/tools/perf/util/pmu.h
index e35d985206db51..93d03bd3ecbeb2 100644
--- a/tools/perf/util/pmu.h
+++ b/tools/perf/util/pmu.h
@@ -196,6 +196,8 @@ struct pmu_event_info {
 };
 
 typedef int (*pmu_event_callback)(void *state, struct pmu_event_info *info);
+typedef int (*pmu_format_callback)(void *state, const char *name, int config,
+				   const unsigned long *bits);
 
 void pmu_add_sys_aliases(struct perf_pmu *pmu);
 int perf_pmu__config(struct perf_pmu *pmu, struct perf_event_attr *attr,
@@ -215,6 +217,7 @@ int perf_pmu__find_event(struct perf_pmu *pmu, const char *event, void *state, p
 int perf_pmu__format_parse(struct perf_pmu *pmu, int dirfd, bool eager_load);
 void perf_pmu_format__set_value(void *format, int config, unsigned long *bits);
 bool perf_pmu__has_format(const struct perf_pmu *pmu, const char *name);
+int perf_pmu__for_each_format(struct perf_pmu *pmu, void *state, pmu_format_callback cb);
 
 bool is_pmu_core(const char *name);
 bool perf_pmu__supports_legacy_cache(const struct perf_pmu *pmu);
@@ -260,7 +263,7 @@ void perf_pmu__warn_invalid_config(struct perf_pmu *pmu, __u64 config,
 				   const char *config_name);
 void perf_pmu__warn_invalid_formats(struct perf_pmu *pmu);
 
-int perf_pmu__match(const char *pattern, const char *name, const char *tok);
+bool perf_pmu__match(const struct perf_pmu *pmu, const char *tok);
 
 double perf_pmu__cpu_slots_per_cycle(void);
 int perf_pmu__event_source_devices_scnprintf(char *pathname, size_t size);
@@ -273,5 +276,6 @@ struct perf_pmu *perf_pmu__lookup(struct list_head *pmus, int dirfd, const char
 struct perf_pmu *perf_pmu__create_placeholder_core_pmu(struct list_head *core_pmus);
 void perf_pmu__delete(struct perf_pmu *pmu);
 struct perf_pmu *perf_pmus__find_core_pmu(void);
+const char *perf_pmu__name_from_config(struct perf_pmu *pmu, u64 config);
 
 #endif /* __PMU_H */
diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
index 16505071d362f4..2fd369e45832b6 100644
--- a/tools/perf/util/pmus.c
+++ b/tools/perf/util/pmus.c
@@ -16,6 +16,7 @@
 #include "pmus.h"
 #include "pmu.h"
 #include "print-events.h"
+#include "strbuf.h"
 
 /*
  * core_pmus:  A PMU belongs to core_pmus if it's name is "cpu" or it's sysfs
@@ -503,6 +504,99 @@ void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *p
 	zfree(&aliases);
 }
 
+struct build_format_string_args {
+	struct strbuf short_string;
+	struct strbuf long_string;
+	int num_formats;
+};
+
+static int build_format_string(void *state, const char *name, int config,
+			       const unsigned long *bits)
+{
+	struct build_format_string_args *args = state;
+	unsigned int num_bits;
+	int ret1, ret2 = 0;
+
+	(void)config;
+	args->num_formats++;
+	if (args->num_formats > 1) {
+		strbuf_addch(&args->long_string, ',');
+		if (args->num_formats < 4)
+			strbuf_addch(&args->short_string, ',');
+	}
+	num_bits = bits ? bitmap_weight(bits, PERF_PMU_FORMAT_BITS) : 0;
+	if (num_bits <= 1) {
+		ret1 = strbuf_addf(&args->long_string, "%s", name);
+		if (args->num_formats < 4)
+			ret2 = strbuf_addf(&args->short_string, "%s", name);
+	} else if (num_bits > 8) {
+		ret1 = strbuf_addf(&args->long_string, "%s=0..0x%llx", name,
+				   ULLONG_MAX >> (64 - num_bits));
+		if (args->num_formats < 4) {
+			ret2 = strbuf_addf(&args->short_string, "%s=0..0x%llx", name,
+					   ULLONG_MAX >> (64 - num_bits));
+		}
+	} else {
+		ret1 = strbuf_addf(&args->long_string, "%s=0..%llu", name,
+				  ULLONG_MAX >> (64 - num_bits));
+		if (args->num_formats < 4) {
+			ret2 = strbuf_addf(&args->short_string, "%s=0..%llu", name,
+					   ULLONG_MAX >> (64 - num_bits));
+		}
+	}
+	return ret1 < 0 ? ret1 : (ret2 < 0 ? ret2 : 0);
+}
+
+void perf_pmus__print_raw_pmu_events(const struct print_callbacks *print_cb, void *print_state)
+{
+	bool skip_duplicate_pmus = print_cb->skip_duplicate_pmus(print_state);
+	struct perf_pmu *(*scan_fn)(struct perf_pmu *);
+	struct perf_pmu *pmu = NULL;
+
+	if (skip_duplicate_pmus)
+		scan_fn = perf_pmus__scan_skip_duplicates;
+	else
+		scan_fn = perf_pmus__scan;
+
+	while ((pmu = scan_fn(pmu)) != NULL) {
+		struct build_format_string_args format_args = {
+			.short_string = STRBUF_INIT,
+			.long_string = STRBUF_INIT,
+			.num_formats = 0,
+		};
+		int len = pmu_name_len_no_suffix(pmu->name, /*num=*/NULL);
+		const char *desc = "(see 'man perf-list' or 'man perf-record' on how to encode it)";
+
+		if (!pmu->is_core)
+			desc = NULL;
+
+		strbuf_addf(&format_args.short_string, "%.*s/", len, pmu->name);
+		strbuf_addf(&format_args.long_string, "%.*s/", len, pmu->name);
+		perf_pmu__for_each_format(pmu, &format_args, build_format_string);
+
+		if (format_args.num_formats > 3)
+			strbuf_addf(&format_args.short_string, ",.../modifier");
+		else
+			strbuf_addf(&format_args.short_string, "/modifier");
+
+		strbuf_addf(&format_args.long_string, "/modifier");
+		print_cb->print_event(print_state,
+				/*topic=*/NULL,
+				/*pmu_name=*/NULL,
+				format_args.short_string.buf,
+				/*event_alias=*/NULL,
+				/*scale_unit=*/NULL,
+				/*deprecated=*/false,
+				"Raw event descriptor",
+				desc,
+				/*long_desc=*/NULL,
+				format_args.long_string.buf);
+
+		strbuf_release(&format_args.short_string);
+		strbuf_release(&format_args.long_string);
+	}
+}
+
 bool perf_pmus__have_event(const char *pname, const char *name)
 {
 	struct perf_pmu *pmu = perf_pmus__find(pname);
diff --git a/tools/perf/util/pmus.h b/tools/perf/util/pmus.h
index 94d2a08d894b7d..eec599d8aebda6 100644
--- a/tools/perf/util/pmus.h
+++ b/tools/perf/util/pmus.h
@@ -18,6 +18,7 @@ struct perf_pmu *perf_pmus__scan_core(struct perf_pmu *pmu);
 const struct perf_pmu *perf_pmus__pmu_for_pmu_filter(const char *str);
 
 void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *print_state);
+void perf_pmus__print_raw_pmu_events(const struct print_callbacks *print_cb, void *print_state);
 bool perf_pmus__have_event(const char *pname, const char *name);
 int perf_pmus__num_core_pmus(void);
 bool perf_pmus__supports_extended_type(void);
diff --git a/tools/perf/util/print-events.c b/tools/perf/util/print-events.c
index 7b54e93854428a..3f38c27f015761 100644
--- a/tools/perf/util/print-events.c
+++ b/tools/perf/util/print-events.c
@@ -9,6 +9,7 @@
 #include <unistd.h>
 
 #include <api/fs/tracing_path.h>
+#include <api/io.h>
 #include <linux/stddef.h>
 #include <linux/perf_event.h>
 #include <linux/zalloc.h>
@@ -38,7 +39,7 @@ static const char * const event_type_descriptors[] = {
 	"Software event",
 	"Tracepoint event",
 	"Hardware cache event",
-	"Raw hardware event descriptor",
+	"Raw event descriptor",
 	"Hardware breakpoint",
 };
 
@@ -92,34 +93,48 @@ void print_tracepoint_events(const struct print_callbacks *print_cb __maybe_unus
 
 		evt_items = scandirat(events_fd, sys_dirent->d_name, &evt_namelist, NULL, alphasort);
 		for (int j = 0; j < evt_items; j++) {
+			/*
+			 * Buffer sized at twice the max filename length + 1
+			 * separator + 1 \0 terminator.
+			 */
+			char buf[NAME_MAX * 2 + 2];
+			/* 16 possible hex digits and 22 other characters and \0. */
+			char encoding[16 + 22];
 			struct dirent *evt_dirent = evt_namelist[j];
-			char evt_path[MAXPATHLEN];
-			int evt_fd;
+			struct io id;
+			__u64 config;
 
 			if (evt_dirent->d_type != DT_DIR ||
 			    !strcmp(evt_dirent->d_name, ".") ||
 			    !strcmp(evt_dirent->d_name, ".."))
 				goto next_evt;
 
-			snprintf(evt_path, sizeof(evt_path), "%s/id", evt_dirent->d_name);
-			evt_fd = openat(dir_fd, evt_path, O_RDONLY);
-			if (evt_fd < 0)
+			snprintf(buf, sizeof(buf), "%s/id", evt_dirent->d_name);
+			io__init(&id, openat(dir_fd, buf, O_RDONLY), buf, sizeof(buf));
+
+			if (id.fd < 0)
+				goto next_evt;
+
+			if (io__get_dec(&id, &config) < 0) {
+				close(id.fd);
 				goto next_evt;
-			close(evt_fd);
+			}
+			close(id.fd);
 
-			snprintf(evt_path, MAXPATHLEN, "%s:%s",
+			snprintf(buf, sizeof(buf), "%s:%s",
 				 sys_dirent->d_name, evt_dirent->d_name);
+			snprintf(encoding, sizeof(encoding), "tracepoint/config=0x%llx/", config);
 			print_cb->print_event(print_state,
 					/*topic=*/NULL,
-					/*pmu_name=*/NULL,
-					evt_path,
+					/*pmu_name=*/NULL, /* really "tracepoint" */
+					/*event_name=*/buf,
 					/*event_alias=*/NULL,
 					/*scale_unit=*/NULL,
 					/*deprecated=*/false,
 					"Tracepoint event",
 					/*desc=*/NULL,
 					/*long_desc=*/NULL,
-					/*encoding_desc=*/NULL);
+					encoding);
 next_evt:
 			free(evt_namelist[j]);
 		}
@@ -401,8 +416,6 @@ void print_symbol_events(const struct print_callbacks *print_cb, void *print_sta
  */
 void print_events(const struct print_callbacks *print_cb, void *print_state)
 {
-	char *tmp;
-
 	print_symbol_events(print_cb, print_state, PERF_TYPE_HARDWARE,
 			event_symbols_hw, PERF_COUNT_HW_MAX);
 	print_symbol_events(print_cb, print_state, PERF_TYPE_SOFTWARE,
@@ -426,21 +439,7 @@ void print_events(const struct print_callbacks *print_cb, void *print_state)
 			/*long_desc=*/NULL,
 			/*encoding_desc=*/NULL);
 
-	if (asprintf(&tmp, "%s/t1=v1[,t2=v2,t3 ...]/modifier",
-		     perf_pmus__scan_core(/*pmu=*/NULL)->name) > 0) {
-		print_cb->print_event(print_state,
-				/*topic=*/NULL,
-				/*pmu_name=*/NULL,
-				tmp,
-				/*event_alias=*/NULL,
-				/*scale_unit=*/NULL,
-				/*deprecated=*/false,
-				event_type_descriptors[PERF_TYPE_RAW],
-				"(see 'man perf-list' on how to encode it)",
-				/*long_desc=*/NULL,
-				/*encoding_desc=*/NULL);
-		free(tmp);
-	}
+	perf_pmus__print_raw_pmu_events(print_cb, print_state);
 
 	print_cb->print_event(print_state,
 			/*topic=*/NULL,
diff --git a/tools/perf/util/print_insn.c b/tools/perf/util/print_insn.c
index 459e0e93d7b1b2..aab11d8e1b1d2a 100644
--- a/tools/perf/util/print_insn.c
+++ b/tools/perf/util/print_insn.c
@@ -4,6 +4,7 @@
  *
  * Author(s): Changbin Du <changbin.du@huawei.com>
  */
+#include <inttypes.h>
 #include <string.h>
 #include <stdbool.h>
 #include "debug.h"
@@ -12,6 +13,9 @@
 #include "machine.h"
 #include "thread.h"
 #include "print_insn.h"
+#include "dump-insn.h"
+#include "map.h"
+#include "dso.h"
 
 size_t sample__fprintf_insn_raw(struct perf_sample *sample, FILE *fp)
 {
@@ -28,12 +32,12 @@ size_t sample__fprintf_insn_raw(struct perf_sample *sample, FILE *fp)
 #ifdef HAVE_LIBCAPSTONE_SUPPORT
 #include <capstone/capstone.h>
 
-static int capstone_init(struct machine *machine, csh *cs_handle)
+static int capstone_init(struct machine *machine, csh *cs_handle, bool is64)
 {
 	cs_arch arch;
 	cs_mode mode;
 
-	if (machine__is(machine, "x86_64")) {
+	if (machine__is(machine, "x86_64") && is64) {
 		arch = CS_ARCH_X86;
 		mode = CS_MODE_64;
 	} else if (machine__normalized_is(machine, "x86")) {
@@ -69,8 +73,8 @@ static int capstone_init(struct machine *machine, csh *cs_handle)
 	return 0;
 }
 
-static size_t print_insn_x86(struct perf_sample *sample, struct thread *thread,
-			     cs_insn *insn, FILE *fp)
+static size_t print_insn_x86(struct thread *thread, u8 cpumode, cs_insn *insn,
+			     int print_opts, FILE *fp)
 {
 	struct addr_location al;
 	size_t printed = 0;
@@ -80,9 +84,11 @@ static size_t print_insn_x86(struct perf_sample *sample, struct thread *thread,
 
 		addr_location__init(&al);
 		if (op->type == X86_OP_IMM &&
-		    thread__find_symbol(thread, sample->cpumode, op->imm, &al)) {
+		    thread__find_symbol(thread, cpumode, op->imm, &al)) {
 			printed += fprintf(fp, "%s ", insn[0].mnemonic);
 			printed += symbol__fprintf_symname_offs(al.sym, &al, fp);
+			if (print_opts & PRINT_INSN_IMM_HEX)
+				printed += fprintf(fp, " [%#" PRIx64 "]", op->imm);
 			addr_location__exit(&al);
 			return printed;
 		}
@@ -93,42 +99,71 @@ static size_t print_insn_x86(struct perf_sample *sample, struct thread *thread,
 	return printed;
 }
 
-size_t sample__fprintf_insn_asm(struct perf_sample *sample, struct thread *thread,
-				struct machine *machine, FILE *fp)
+static bool is64bitip(struct machine *machine, struct addr_location *al)
 {
-	csh cs_handle;
+	const struct dso *dso = al->map ? map__dso(al->map) : NULL;
+
+	if (dso)
+		return dso->is_64_bit;
+
+	return machine__is(machine, "x86_64") ||
+		machine__normalized_is(machine, "arm64") ||
+		machine__normalized_is(machine, "s390");
+}
+
+ssize_t fprintf_insn_asm(struct machine *machine, struct thread *thread, u8 cpumode,
+			 bool is64bit, const uint8_t *code, size_t code_size,
+			 uint64_t ip, int *lenp, int print_opts, FILE *fp)
+{
+	size_t printed;
 	cs_insn *insn;
+	csh cs_handle;
 	size_t count;
-	size_t printed = 0;
 	int ret;
 
 	/* TODO: Try to initiate capstone only once but need a proper place. */
-	ret = capstone_init(machine, &cs_handle);
-	if (ret < 0) {
-		/* fallback */
-		return sample__fprintf_insn_raw(sample, fp);
-	}
+	ret = capstone_init(machine, &cs_handle, is64bit);
+	if (ret < 0)
+		return ret;
 
-	count = cs_disasm(cs_handle, (uint8_t *)sample->insn, sample->insn_len,
-			  sample->ip, 1, &insn);
+	count = cs_disasm(cs_handle, code, code_size, ip, 1, &insn);
 	if (count > 0) {
 		if (machine__normalized_is(machine, "x86"))
-			printed += print_insn_x86(sample, thread, &insn[0], fp);
+			printed = print_insn_x86(thread, cpumode, &insn[0], print_opts, fp);
 		else
-			printed += fprintf(fp, "%s %s", insn[0].mnemonic, insn[0].op_str);
+			printed = fprintf(fp, "%s %s", insn[0].mnemonic, insn[0].op_str);
+		if (lenp)
+			*lenp = insn->size;
 		cs_free(insn, count);
 	} else {
-		printed += fprintf(fp, "illegal instruction");
+		printed = -1;
 	}
 
 	cs_close(&cs_handle);
 	return printed;
 }
+
+size_t sample__fprintf_insn_asm(struct perf_sample *sample, struct thread *thread,
+				struct machine *machine, FILE *fp,
+				struct addr_location *al)
+{
+	bool is64bit = is64bitip(machine, al);
+	ssize_t printed;
+
+	printed = fprintf_insn_asm(machine, thread, sample->cpumode, is64bit,
+				   (uint8_t *)sample->insn, sample->insn_len,
+				   sample->ip, NULL, 0, fp);
+	if (printed < 0)
+		return sample__fprintf_insn_raw(sample, fp);
+
+	return printed;
+}
 #else
 size_t sample__fprintf_insn_asm(struct perf_sample *sample __maybe_unused,
 				struct thread *thread __maybe_unused,
 				struct machine *machine __maybe_unused,
-				FILE *fp __maybe_unused)
+				FILE *fp __maybe_unused,
+				struct addr_location *al __maybe_unused)
 {
 	return 0;
 }
diff --git a/tools/perf/util/print_insn.h b/tools/perf/util/print_insn.h
index 465bdcfcc2fd6e..07d11af3fc1cbe 100644
--- a/tools/perf/util/print_insn.h
+++ b/tools/perf/util/print_insn.h
@@ -8,9 +8,15 @@
 struct perf_sample;
 struct thread;
 struct machine;
+struct perf_insn;
+
+#define PRINT_INSN_IMM_HEX		(1<<0)
 
 size_t sample__fprintf_insn_asm(struct perf_sample *sample, struct thread *thread,
-				struct machine *machine, FILE *fp);
+				struct machine *machine, FILE *fp, struct addr_location *al);
 size_t sample__fprintf_insn_raw(struct perf_sample *sample, FILE *fp);
+ssize_t fprintf_insn_asm(struct machine *machine, struct thread *thread, u8 cpumode,
+			 bool is64bit, const uint8_t *code, size_t code_size,
+			 uint64_t ip, int *lenp, int print_opts, FILE *fp);
 
 #endif /* PERF_PRINT_INSN_H */
diff --git a/tools/perf/util/probe-event.c b/tools/perf/util/probe-event.c
index 2a0ad9ecf0a20e..8a73c9464b709b 100644
--- a/tools/perf/util/probe-event.c
+++ b/tools/perf/util/probe-event.c
@@ -11,6 +11,7 @@
 #include <sys/stat.h>
 #include <fcntl.h>
 #include <errno.h>
+#include <libgen.h>
 #include <stdio.h>
 #include <unistd.h>
 #include <stdlib.h>
@@ -235,7 +236,7 @@ static int convert_exec_to_group(const char *exec, char **result)
 		}
 	}
 
-	ret = e_snprintf(buf, 64, "%s_%s", PERFPROBE_GROUP, ptr1);
+	ret = e_snprintf(buf, sizeof(buf), "%s_%s", PERFPROBE_GROUP, ptr1);
 	if (ret < 0)
 		goto out;
 
@@ -2757,7 +2758,7 @@ static int get_new_event_name(char *buf, size_t len, const char *base,
 	/* Try no suffix number */
 	ret = e_snprintf(buf, len, "%s%s", nbase, ret_event ? "__return" : "");
 	if (ret < 0) {
-		pr_debug("snprintf() failed: %d\n", ret);
+		pr_warning("snprintf() failed: %d; the event name nbase='%s' is too long\n", ret, nbase);
 		goto out;
 	}
 	if (!strlist__has_entry(namelist, buf))
@@ -2866,7 +2867,7 @@ static int probe_trace_event__set_name(struct probe_trace_event *tev,
 		group = PERFPROBE_GROUP;
 
 	/* Get an unused new event name */
-	ret = get_new_event_name(buf, 64, event, namelist,
+	ret = get_new_event_name(buf, sizeof(buf), event, namelist,
 				 tev->point.retprobe, allow_suffix);
 	if (ret < 0)
 		return ret;
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 075c0f79b1b92d..0aeb97c11c0306 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -103,6 +103,16 @@ int perf_pmu__scan_file(const struct perf_pmu *pmu, const char *name, const char
 	return EOF;
 }
 
+const char *perf_pmu__name_from_config(struct perf_pmu *pmu __maybe_unused, u64 config __maybe_unused)
+{
+	return NULL;
+}
+
+struct perf_pmu *perf_pmus__find_by_type(unsigned int type __maybe_unused)
+{
+	return NULL;
+}
+
 int perf_pmus__num_core_pmus(void)
 {
 	return 1;
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 87e817b3cf7e9d..e867de8ddaaa41 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -237,7 +237,7 @@ bool evlist__can_select_event(struct evlist *evlist, const char *str)
 
 	evsel = evlist__last(temp_evlist);
 
-	if (!evlist || perf_cpu_map__has_any_cpu_or_is_empty(evlist->core.user_requested_cpus)) {
+	if (!evlist || perf_cpu_map__is_any_cpu_or_is_empty(evlist->core.user_requested_cpus)) {
 		struct perf_cpu_map *cpus = perf_cpu_map__new_online_cpus();
 
 		if (cpus)
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index b4f0f60e60a63f..8aa301948de579 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -1699,13 +1699,15 @@ static void python_process_stat(struct perf_stat_config *config,
 {
 	struct perf_thread_map *threads = counter->core.threads;
 	struct perf_cpu_map *cpus = counter->core.cpus;
-	int cpu, thread;
 
-	for (thread = 0; thread < perf_thread_map__nr(threads); thread++) {
-		for (cpu = 0; cpu < perf_cpu_map__nr(cpus); cpu++) {
-			process_stat(counter, perf_cpu_map__cpu(cpus, cpu),
+	for (int thread = 0; thread < perf_thread_map__nr(threads); thread++) {
+		int idx;
+		struct perf_cpu cpu;
+
+		perf_cpu_map__for_each_cpu(cpu, idx, cpus) {
+			process_stat(counter, cpu,
 				     perf_thread_map__pid(threads, thread), tstamp,
-				     perf_counts(counter->counts, cpu, thread));
+				     perf_counts(counter->counts, idx, thread));
 		}
 	}
 }
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 06d0bd7fb45999..a10343b9dcd419 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -2749,6 +2749,7 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 	int i, err = -1;
 	struct perf_cpu_map *map;
 	int nr_cpus = min(session->header.env.nr_cpus_avail, MAX_NR_CPUS);
+	struct perf_cpu cpu;
 
 	for (i = 0; i < PERF_TYPE_MAX; ++i) {
 		struct evsel *evsel;
@@ -2770,9 +2771,7 @@ int perf_session__cpu_bitmap(struct perf_session *session,
 		return -1;
 	}
 
-	for (i = 0; i < perf_cpu_map__nr(map); i++) {
-		struct perf_cpu cpu = perf_cpu_map__cpu(map, i);
-
+	perf_cpu_map__for_each_cpu(cpu, i, map) {
 		if (cpu.cpu >= nr_cpus) {
 			pr_err("Requested CPU %d too large. "
 			       "Consider raising MAX_NR_CPUS\n", cpu.cpu);
@@ -2917,3 +2916,24 @@ int perf_event__process_id_index(struct perf_session *session,
 	}
 	return 0;
 }
+
+int perf_session__dsos_hit_all(struct perf_session *session)
+{
+	struct rb_node *nd;
+	int err;
+
+	err = machine__hit_all_dsos(&session->machines.host);
+	if (err)
+		return err;
+
+	for (nd = rb_first_cached(&session->machines.guests); nd;
+	     nd = rb_next(nd)) {
+		struct machine *pos = rb_entry(nd, struct machine, rb_node);
+
+		err = machine__hit_all_dsos(pos);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
diff --git a/tools/perf/util/session.h b/tools/perf/util/session.h
index 5064c6ec11e731..3b0256e977a6c1 100644
--- a/tools/perf/util/session.h
+++ b/tools/perf/util/session.h
@@ -156,6 +156,8 @@ int perf_session__deliver_synth_event(struct perf_session *session,
 				      union perf_event *event,
 				      struct perf_sample *sample);
 
+int perf_session__dsos_hit_all(struct perf_session *session);
+
 int perf_event__process_id_index(struct perf_session *session,
 				 union perf_event *event);
 
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 92a1bd695e8aa3..add8601c57fd47 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -2441,6 +2441,13 @@ static struct hpp_dimension hpp_sort_dimensions[] = {
 	DIM(PERF_HPP__OVERHEAD_ACC, "overhead_children"),
 	DIM(PERF_HPP__SAMPLES, "sample"),
 	DIM(PERF_HPP__PERIOD, "period"),
+	DIM(PERF_HPP__WEIGHT1, "weight1"),
+	DIM(PERF_HPP__WEIGHT2, "weight2"),
+	DIM(PERF_HPP__WEIGHT3, "weight3"),
+	/* aliases for weight_struct */
+	DIM(PERF_HPP__WEIGHT2, "ins_lat"),
+	DIM(PERF_HPP__WEIGHT3, "retire_lat"),
+	DIM(PERF_HPP__WEIGHT3, "p_stage_cyc"),
 };
 
 #undef DIM
@@ -3743,26 +3750,29 @@ void sort__setup_elide(FILE *output)
 	}
 }
 
-int output_field_add(struct perf_hpp_list *list, char *tok)
+int output_field_add(struct perf_hpp_list *list, const char *tok)
 {
 	unsigned int i;
 
-	for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) {
-		struct sort_dimension *sd = &common_sort_dimensions[i];
+	for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
+		struct hpp_dimension *hd = &hpp_sort_dimensions[i];
 
-		if (!sd->name || strncasecmp(tok, sd->name, strlen(tok)))
+		if (strncasecmp(tok, hd->name, strlen(tok)))
 			continue;
 
-		return __sort_dimension__add_output(list, sd);
+		if (!strcasecmp(tok, "weight"))
+			ui__warning("--fields weight shows the average value unlike in the --sort key.\n");
+
+		return __hpp_dimension__add_output(list, hd);
 	}
 
-	for (i = 0; i < ARRAY_SIZE(hpp_sort_dimensions); i++) {
-		struct hpp_dimension *hd = &hpp_sort_dimensions[i];
+	for (i = 0; i < ARRAY_SIZE(common_sort_dimensions); i++) {
+		struct sort_dimension *sd = &common_sort_dimensions[i];
 
-		if (strncasecmp(tok, hd->name, strlen(tok)))
+		if (!sd->name || strncasecmp(tok, sd->name, strlen(tok)))
 			continue;
 
-		return __hpp_dimension__add_output(list, hd);
+		return __sort_dimension__add_output(list, sd);
 	}
 
 	for (i = 0; i < ARRAY_SIZE(bstack_sort_dimensions); i++) {
diff --git a/tools/perf/util/sort.h b/tools/perf/util/sort.h
index 6f6b4189a38978..0bd0ee3ae76bd3 100644
--- a/tools/perf/util/sort.h
+++ b/tools/perf/util/sort.h
@@ -3,19 +3,9 @@
 #define __PERF_SORT_H
 #include <regex.h>
 #include <stdbool.h>
-#include <linux/list.h>
-#include <linux/rbtree.h>
-#include "map_symbol.h"
-#include "symbol_conf.h"
-#include "callchain.h"
-#include "values.h"
 #include "hist.h"
-#include "stat.h"
-#include "spark.h"
 
 struct option;
-struct thread;
-struct annotated_data_type;
 
 extern regex_t parent_regex;
 extern const char *sort_order;
@@ -39,175 +29,6 @@ extern struct sort_entry sort_type;
 extern const char default_mem_sort_order[];
 extern bool chk_double_cl;
 
-struct res_sample {
-	u64 time;
-	int cpu;
-	int tid;
-};
-
-struct he_stat {
-	u64			period;
-	u64			period_sys;
-	u64			period_us;
-	u64			period_guest_sys;
-	u64			period_guest_us;
-	u32			nr_events;
-};
-
-struct namespace_id {
-	u64			dev;
-	u64			ino;
-};
-
-struct hist_entry_diff {
-	bool	computed;
-	union {
-		/* PERF_HPP__DELTA */
-		double	period_ratio_delta;
-
-		/* PERF_HPP__RATIO */
-		double	period_ratio;
-
-		/* HISTC_WEIGHTED_DIFF */
-		s64	wdiff;
-
-		/* PERF_HPP_DIFF__CYCLES */
-		s64	cycles;
-	};
-	struct stats	stats;
-	unsigned long	svals[NUM_SPARKS];
-};
-
-struct hist_entry_ops {
-	void	*(*new)(size_t size);
-	void	(*free)(void *ptr);
-};
-
-/**
- * struct hist_entry - histogram entry
- *
- * @row_offset - offset from the first callchain expanded to appear on screen
- * @nr_rows - rows expanded in callchain, recalculated on folding/unfolding
- */
-struct hist_entry {
-	struct rb_node		rb_node_in;
-	struct rb_node		rb_node;
-	union {
-		struct list_head node;
-		struct list_head head;
-	} pairs;
-	struct he_stat		stat;
-	struct he_stat		*stat_acc;
-	struct map_symbol	ms;
-	struct thread		*thread;
-	struct comm		*comm;
-	struct namespace_id	cgroup_id;
-	u64			cgroup;
-	u64			ip;
-	u64			transaction;
-	s32			socket;
-	s32			cpu;
-	u64			code_page_size;
-	u64			weight;
-	u64			ins_lat;
-	u64			p_stage_cyc;
-	u8			cpumode;
-	u8			depth;
-	int			mem_type_off;
-	struct simd_flags	simd_flags;
-
-	/* We are added by hists__add_dummy_entry. */
-	bool			dummy;
-	bool			leaf;
-
-	char			level;
-	u8			filtered;
-
-	u16			callchain_size;
-	union {
-		/*
-		 * Since perf diff only supports the stdio output, TUI
-		 * fields are only accessed from perf report (or perf
-		 * top).  So make it a union to reduce memory usage.
-		 */
-		struct hist_entry_diff	diff;
-		struct /* for TUI */ {
-			u16	row_offset;
-			u16	nr_rows;
-			bool	init_have_children;
-			bool	unfolded;
-			bool	has_children;
-			bool	has_no_entry;
-		};
-	};
-	char			*srcline;
-	char			*srcfile;
-	struct symbol		*parent;
-	struct branch_info	*branch_info;
-	long			time;
-	struct hists		*hists;
-	struct mem_info		*mem_info;
-	struct block_info	*block_info;
-	struct kvm_info		*kvm_info;
-	void			*raw_data;
-	u32			raw_size;
-	int			num_res;
-	struct res_sample	*res_samples;
-	void			*trace_output;
-	struct perf_hpp_list	*hpp_list;
-	struct hist_entry	*parent_he;
-	struct hist_entry_ops	*ops;
-	struct annotated_data_type *mem_type;
-	union {
-		/* this is for hierarchical entry structure */
-		struct {
-			struct rb_root_cached	hroot_in;
-			struct rb_root_cached   hroot_out;
-		};				/* non-leaf entries */
-		struct rb_root	sorted_chain;	/* leaf entry has callchains */
-	};
-	struct callchain_root	callchain[0]; /* must be last member */
-};
-
-static __pure inline bool hist_entry__has_callchains(struct hist_entry *he)
-{
-	return he->callchain_size != 0;
-}
-
-int hist_entry__sym_snprintf(struct hist_entry *he, char *bf, size_t size, unsigned int width);
-
-static inline bool hist_entry__has_pairs(struct hist_entry *he)
-{
-	return !list_empty(&he->pairs.node);
-}
-
-static inline struct hist_entry *hist_entry__next_pair(struct hist_entry *he)
-{
-	if (hist_entry__has_pairs(he))
-		return list_entry(he->pairs.node.next, struct hist_entry, pairs.node);
-	return NULL;
-}
-
-static inline void hist_entry__add_pair(struct hist_entry *pair,
-					struct hist_entry *he)
-{
-	list_add_tail(&pair->pairs.node, &he->pairs.head);
-}
-
-static inline float hist_entry__get_percent_limit(struct hist_entry *he)
-{
-	u64 period = he->stat.period;
-	u64 total_period = hists__total_period(he->hists);
-
-	if (unlikely(total_period == 0))
-		return 0;
-
-	if (symbol_conf.cumulate_callchain)
-		period = he->stat_acc->period;
-
-	return period * 100.0 / total_period;
-}
-
 enum sort_mode {
 	SORT_MODE__NORMAL,
 	SORT_MODE__BRANCH,
@@ -299,15 +120,6 @@ struct sort_entry {
 	u8	se_width_idx;
 };
 
-struct block_hist {
-	struct hists		block_hists;
-	struct perf_hpp_list	block_list;
-	struct perf_hpp_fmt	block_fmt;
-	int			block_idx;
-	bool			valid;
-	struct hist_entry	he;
-};
-
 extern struct sort_entry sort_thread;
 
 struct evlist;
@@ -329,7 +141,7 @@ void reset_dimensions(void);
 int sort_dimension__add(struct perf_hpp_list *list, const char *tok,
 			struct evlist *evlist,
 			int level);
-int output_field_add(struct perf_hpp_list *list, char *tok);
+int output_field_add(struct perf_hpp_list *list, const char *tok);
 int64_t
 sort__iaddr_cmp(struct hist_entry *left, struct hist_entry *right);
 int64_t
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index b0bcf92f0f9c37..0bd5467389e462 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -315,7 +315,7 @@ static int check_per_pkg(struct evsel *counter, struct perf_counts_values *vals,
 	if (!counter->per_pkg)
 		return 0;
 
-	if (perf_cpu_map__has_any_cpu_or_is_empty(cpus))
+	if (perf_cpu_map__is_any_cpu_or_is_empty(cpus))
 		return 0;
 
 	if (!mask) {
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index d6e5c8787ba23a..fd7a187551bd1e 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -87,6 +87,7 @@ struct perf_stat_config {
 	bool			 metric_no_group;
 	bool			 metric_no_merge;
 	bool			 metric_no_threshold;
+	bool			 hardware_aware_grouping;
 	bool			 stop_read_counter;
 	bool			 iostat_run;
 	char			 *user_requested_cpu_list;
diff --git a/tools/perf/util/svghelper.c b/tools/perf/util/svghelper.c
index 1892e9b6aa7ff5..2b04f47f4db0f0 100644
--- a/tools/perf/util/svghelper.c
+++ b/tools/perf/util/svghelper.c
@@ -725,26 +725,24 @@ static void scan_core_topology(int *map, struct topology *t, int nr_cpus)
 
 static int str_to_bitmap(char *s, cpumask_t *b, int nr_cpus)
 {
-	int i;
-	int ret = 0;
-	struct perf_cpu_map *m;
-	struct perf_cpu c;
+	int idx, ret = 0;
+	struct perf_cpu_map *map;
+	struct perf_cpu cpu;
 
-	m = perf_cpu_map__new(s);
-	if (!m)
+	map = perf_cpu_map__new(s);
+	if (!map)
 		return -1;
 
-	for (i = 0; i < perf_cpu_map__nr(m); i++) {
-		c = perf_cpu_map__cpu(m, i);
-		if (c.cpu >= nr_cpus) {
+	perf_cpu_map__for_each_cpu(cpu, idx, map) {
+		if (cpu.cpu >= nr_cpus) {
 			ret = -1;
 			break;
 		}
 
-		__set_bit(c.cpu, cpumask_bits(b));
+		__set_bit(cpu.cpu, cpumask_bits(b));
 	}
 
-	perf_cpu_map__put(m);
+	perf_cpu_map__put(map);
 
 	return ret;
 }
diff --git a/tools/perf/util/values.h b/tools/perf/util/values.h
index 8c41f22f42cfbb..791c1ad606c290 100644
--- a/tools/perf/util/values.h
+++ b/tools/perf/util/values.h
@@ -2,6 +2,7 @@
 #ifndef __PERF_VALUES_H
 #define __PERF_VALUES_H
 
+#include <stdio.h>
 #include <linux/types.h>
 
 struct perf_read_values {
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index df8963796187dc..35532dcbff743d 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -133,8 +133,6 @@ static struct dso *__machine__addnew_vdso(struct machine *machine, const char *s
 	if (dso != NULL) {
 		__dsos__add(&machine->dsos, dso);
 		dso__set_long_name(dso, long_name, false);
-		/* Put dso here because __dsos_add already got it */
-		dso__put(dso);
 	}
 
 	return dso;
@@ -252,17 +250,15 @@ static struct dso *__machine__findnew_compat(struct machine *machine,
 	const char *file_name;
 	struct dso *dso;
 
-	dso = __dsos__find(&machine->dsos, vdso_file->dso_name, true);
+	dso = dsos__find(&machine->dsos, vdso_file->dso_name, true);
 	if (dso)
-		goto out;
+		return dso;
 
 	file_name = vdso__get_compat_file(vdso_file);
 	if (!file_name)
-		goto out;
+		return NULL;
 
-	dso = __machine__addnew_vdso(machine, vdso_file->dso_name, file_name);
-out:
-	return dso;
+	return __machine__addnew_vdso(machine, vdso_file->dso_name, file_name);
 }
 
 static int __machine__findnew_vdso_compat(struct machine *machine,
@@ -308,21 +304,21 @@ static struct dso *machine__find_vdso(struct machine *machine,
 	dso_type = machine__thread_dso_type(machine, thread);
 	switch (dso_type) {
 	case DSO__TYPE_32BIT:
-		dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO32, true);
+		dso = dsos__find(&machine->dsos, DSO__NAME_VDSO32, true);
 		if (!dso) {
-			dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO,
-					   true);
+			dso = dsos__find(&machine->dsos, DSO__NAME_VDSO,
+					 true);
 			if (dso && dso_type != dso__type(dso, machine))
 				dso = NULL;
 		}
 		break;
 	case DSO__TYPE_X32BIT:
-		dso = __dsos__find(&machine->dsos, DSO__NAME_VDSOX32, true);
+		dso = dsos__find(&machine->dsos, DSO__NAME_VDSOX32, true);
 		break;
 	case DSO__TYPE_64BIT:
 	case DSO__TYPE_UNKNOWN:
 	default:
-		dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO, true);
+		dso = dsos__find(&machine->dsos, DSO__NAME_VDSO, true);
 		break;
 	}
 
@@ -334,37 +330,33 @@ struct dso *machine__findnew_vdso(struct machine *machine,
 {
 	struct vdso_info *vdso_info;
 	struct dso *dso = NULL;
+	char *file;
 
-	down_write(&machine->dsos.lock);
 	if (!machine->vdso_info)
 		machine->vdso_info = vdso_info__new();
 
 	vdso_info = machine->vdso_info;
 	if (!vdso_info)
-		goto out_unlock;
+		return NULL;
 
 	dso = machine__find_vdso(machine, thread);
 	if (dso)
-		goto out_unlock;
+		return dso;
 
 #if BITS_PER_LONG == 64
 	if (__machine__findnew_vdso_compat(machine, thread, vdso_info, &dso))
-		goto out_unlock;
+		return dso;
 #endif
 
-	dso = __dsos__find(&machine->dsos, DSO__NAME_VDSO, true);
-	if (!dso) {
-		char *file;
+	dso = dsos__find(&machine->dsos, DSO__NAME_VDSO, true);
+	if (dso)
+		return dso;
 
-		file = get_file(&vdso_info->vdso);
-		if (file)
-			dso = __machine__addnew_vdso(machine, DSO__NAME_VDSO, file);
-	}
+	file = get_file(&vdso_info->vdso);
+	if (!file)
+		return NULL;
 
-out_unlock:
-	dso__get(dso);
-	up_write(&machine->dsos.lock);
-	return dso;
+	return __machine__addnew_vdso(machine, DSO__NAME_VDSO, file);
 }
 
 bool dso__is_vdso(struct dso *dso)