Merge branch 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf updates from Ingo Molnar:
 "The main kernel side changes were:

   - Modernize the kprobe and uprobe creation/destruction tooling ABIs:

     The existing text based APIs (kprobe_events and uprobe_events in
     tracefs), are naive, limited ABIs in that they require user-space
     to clean up after themselves, which is both difficult and fragile
     if the tool is buggy or exits unexpectedly. In other words they are
     not really suited for modern, robust tooling.

     So introduce a modern, file descriptor based ABI that does not have
     these limitations: introduce the 'perf_kprobe' and 'perf_uprobe'
     PMUs and extend the perf_event_open() syscall to create events with
     a kprobe/uprobe attached to them. These [k,u]probe are associated
     with this file descriptor, so they are not available in tracefs.

     (Song Liu)

   - Intel Cannon Lake CPU support (Harry Pan)

   - Intel PT cleanups (Alexander Shishkin)

   - Improve the performance of pinned/flexible event groups by using RB
     trees (Alexey Budankov)

   - Add PERF_EVENT_IOC_MODIFY_ATTRIBUTES which allows the modification
     of hardware breakpoints, which new ABI variant massively speeds up
     existing tooling that uses hardware breakpoints to instrument (and
     debug) memory usage.

     (Milind Chabbi, Jiri Olsa)

   - Various Intel PEBS handling fixes and improvements, and other Intel
     PMU improvements (Kan Liang)

   - Various perf core improvements and optimizations (Peter Zijlstra)

   - ... misc cleanups, fixes and updates.

  There's over 200 tooling commits, here's an (imperfect) list of
  highlights:

   - 'perf annotate' improvements:

      * Recognize and handle jumps to other functions as calls, which
        improves the navigation along jumps and back. (Arnaldo Carvalho
        de Melo)

      * Add the 'P' hotkey in TUI annotation to dump annotation output
        into a file, to ease e-mail reporting of annotation details.
        (Arnaldo Carvalho de Melo)

      * Add an IPC/cycles column to the TUI (Jin Yao)

      * Improve s390 assembly annotation (Thomas Richter)

      * Refactor the output formatting logic to better separate it into
        interactive and non-interactive features and add the --stdio2
        output variant to demonstrate this. (Arnaldo Carvalho de Melo)

   - 'perf script' improvements:

      * Add Python 3 support (Jaroslav Škarvada)

      * Add --show-round-event (Jiri Olsa)

   - 'perf c2c' improvements:

      * Add NUMA analysis support (Jiri Olsa)

   - 'perf trace' improvements:

      * Improve PowerPC support (Ravi Bangoria)

   - 'perf inject' improvements:

      * Integrate ARM CoreSight traces (Robert Walker)

   - 'perf stat' improvements:

      * Add the --interval-count option (yuzhoujian)

      * Add the --timeout option (yuzhoujian)

   - 'perf sched' improvements (Changbin Du)

   - Vendor events improvements :

      * Add IBM s390 vendor events (Thomas Richter)

      * Add and improve arm64 vendor events (John Garry, Ganapatrao
        Kulkarni)

      * Update POWER9 vendor events (Sukadev Bhattiprolu)

   - Intel PT tooling improvements (Adrian Hunter)

   - PMU handling improvements (Agustin Vega-Frias)

   - Record machine topology in perf.data (Jiri Olsa)

   - Various overwrite related cleanups (Kan Liang)

   - Add arm64 dwarf post unwind support (Kim Phillips, Jean Pihet)

   - ... and lots of other changes, cleanups and fixes, see the shortlog
     and Git history for details"

* 'perf-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (262 commits)
  perf/x86/intel: Enable C-state residency events for Cannon Lake
  perf/x86/intel: Add Cannon Lake support for RAPL profiling
  perf/x86/pt, coresight: Clean up address filter structure
  perf vendor events s390: Add JSON files for IBM z14
  perf vendor events s390: Add JSON files for IBM z13
  perf vendor events s390: Add JSON files for IBM zEC12 zBC12
  perf vendor events s390: Add JSON files for IBM z196
  perf vendor events s390: Add JSON files for IBM z10EC z10BC
  perf mmap: Be consistent when checking for an unmaped ring buffer
  perf mmap: Fix accessing unmapped mmap in perf_mmap__read_done()
  perf build: Fix check-headers.sh opts assignment
  perf/x86: Update rdpmc_always_available static key to the modern API
  perf annotate: Use absolute addresses to calculate jump target offsets
  perf annotate: Defer searching for comma in raw line till it is needed
  perf annotate: Support jumping from one function to another
  perf annotate: Add "_local" to jump/offset validation routines
  perf python: Reference Py_None before returning it
  perf annotate: Mark jumps to outher functions with the call arrow
  perf annotate: Pass function descriptor to its instruction parsing routines
  perf annotate: No need to calculate notes->start twice
  ...

177 files changed, 8122 insertions, 1920 deletions

diff --git a/tools/arch/powerpc/include/uapi/asm/unistd.h b/tools/arch/powerpc/include/uapi/asm/unistd.h
new file mode 100644
index 000000000000..389c36fd8299
--- /dev/null
+++ b/tools/arch/powerpc/include/uapi/asm/unistd.h
@@ -0,0 +1,402 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * This file contains the system call numbers.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#ifndef _UAPI_ASM_POWERPC_UNISTD_H_
+#define _UAPI_ASM_POWERPC_UNISTD_H_
+
+
+#define __NR_restart_syscall	  0
+#define __NR_exit		  1
+#define __NR_fork		  2
+#define __NR_read		  3
+#define __NR_write		  4
+#define __NR_open		  5
+#define __NR_close		  6
+#define __NR_waitpid		  7
+#define __NR_creat		  8
+#define __NR_link		  9
+#define __NR_unlink		 10
+#define __NR_execve		 11
+#define __NR_chdir		 12
+#define __NR_time		 13
+#define __NR_mknod		 14
+#define __NR_chmod		 15
+#define __NR_lchown		 16
+#define __NR_break		 17
+#define __NR_oldstat		 18
+#define __NR_lseek		 19
+#define __NR_getpid		 20
+#define __NR_mount		 21
+#define __NR_umount		 22
+#define __NR_setuid		 23
+#define __NR_getuid		 24
+#define __NR_stime		 25
+#define __NR_ptrace		 26
+#define __NR_alarm		 27
+#define __NR_oldfstat		 28
+#define __NR_pause		 29
+#define __NR_utime		 30
+#define __NR_stty		 31
+#define __NR_gtty		 32
+#define __NR_access		 33
+#define __NR_nice		 34
+#define __NR_ftime		 35
+#define __NR_sync		 36
+#define __NR_kill		 37
+#define __NR_rename		 38
+#define __NR_mkdir		 39
+#define __NR_rmdir		 40
+#define __NR_dup		 41
+#define __NR_pipe		 42
+#define __NR_times		 43
+#define __NR_prof		 44
+#define __NR_brk		 45
+#define __NR_setgid		 46
+#define __NR_getgid		 47
+#define __NR_signal		 48
+#define __NR_geteuid		 49
+#define __NR_getegid		 50
+#define __NR_acct		 51
+#define __NR_umount2		 52
+#define __NR_lock		 53
+#define __NR_ioctl		 54
+#define __NR_fcntl		 55
+#define __NR_mpx		 56
+#define __NR_setpgid		 57
+#define __NR_ulimit		 58
+#define __NR_oldolduname	 59
+#define __NR_umask		 60
+#define __NR_chroot		 61
+#define __NR_ustat		 62
+#define __NR_dup2		 63
+#define __NR_getppid		 64
+#define __NR_getpgrp		 65
+#define __NR_setsid		 66
+#define __NR_sigaction		 67
+#define __NR_sgetmask		 68
+#define __NR_ssetmask		 69
+#define __NR_setreuid		 70
+#define __NR_setregid		 71
+#define __NR_sigsuspend		 72
+#define __NR_sigpending		 73
+#define __NR_sethostname	 74
+#define __NR_setrlimit		 75
+#define __NR_getrlimit		 76
+#define __NR_getrusage		 77
+#define __NR_gettimeofday	 78
+#define __NR_settimeofday	 79
+#define __NR_getgroups		 80
+#define __NR_setgroups		 81
+#define __NR_select		 82
+#define __NR_symlink		 83
+#define __NR_oldlstat		 84
+#define __NR_readlink		 85
+#define __NR_uselib		 86
+#define __NR_swapon		 87
+#define __NR_reboot		 88
+#define __NR_readdir		 89
+#define __NR_mmap		 90
+#define __NR_munmap		 91
+#define __NR_truncate		 92
+#define __NR_ftruncate		 93
+#define __NR_fchmod		 94
+#define __NR_fchown		 95
+#define __NR_getpriority	 96
+#define __NR_setpriority	 97
+#define __NR_profil		 98
+#define __NR_statfs		 99
+#define __NR_fstatfs		100
+#define __NR_ioperm		101
+#define __NR_socketcall		102
+#define __NR_syslog		103
+#define __NR_setitimer		104
+#define __NR_getitimer		105
+#define __NR_stat		106
+#define __NR_lstat		107
+#define __NR_fstat		108
+#define __NR_olduname		109
+#define __NR_iopl		110
+#define __NR_vhangup		111
+#define __NR_idle		112
+#define __NR_vm86		113
+#define __NR_wait4		114
+#define __NR_swapoff		115
+#define __NR_sysinfo		116
+#define __NR_ipc		117
+#define __NR_fsync		118
+#define __NR_sigreturn		119
+#define __NR_clone		120
+#define __NR_setdomainname	121
+#define __NR_uname		122
+#define __NR_modify_ldt		123
+#define __NR_adjtimex		124
+#define __NR_mprotect		125
+#define __NR_sigprocmask	126
+#define __NR_create_module	127
+#define __NR_init_module	128
+#define __NR_delete_module	129
+#define __NR_get_kernel_syms	130
+#define __NR_quotactl		131
+#define __NR_getpgid		132
+#define __NR_fchdir		133
+#define __NR_bdflush		134
+#define __NR_sysfs		135
+#define __NR_personality	136
+#define __NR_afs_syscall	137 /* Syscall for Andrew File System */
+#define __NR_setfsuid		138
+#define __NR_setfsgid		139
+#define __NR__llseek		140
+#define __NR_getdents		141
+#define __NR__newselect		142
+#define __NR_flock		143
+#define __NR_msync		144
+#define __NR_readv		145
+#define __NR_writev		146
+#define __NR_getsid		147
+#define __NR_fdatasync		148
+#define __NR__sysctl		149
+#define __NR_mlock		150
+#define __NR_munlock		151
+#define __NR_mlockall		152
+#define __NR_munlockall		153
+#define __NR_sched_setparam		154
+#define __NR_sched_getparam		155
+#define __NR_sched_setscheduler		156
+#define __NR_sched_getscheduler		157
+#define __NR_sched_yield		158
+#define __NR_sched_get_priority_max	159
+#define __NR_sched_get_priority_min	160
+#define __NR_sched_rr_get_interval	161
+#define __NR_nanosleep		162
+#define __NR_mremap		163
+#define __NR_setresuid		164
+#define __NR_getresuid		165
+#define __NR_query_module	166
+#define __NR_poll		167
+#define __NR_nfsservctl		168
+#define __NR_setresgid		169
+#define __NR_getresgid		170
+#define __NR_prctl		171
+#define __NR_rt_sigreturn	172
+#define __NR_rt_sigaction	173
+#define __NR_rt_sigprocmask	174
+#define __NR_rt_sigpending	175
+#define __NR_rt_sigtimedwait	176
+#define __NR_rt_sigqueueinfo	177
+#define __NR_rt_sigsuspend	178
+#define __NR_pread64		179
+#define __NR_pwrite64		180
+#define __NR_chown		181
+#define __NR_getcwd		182
+#define __NR_capget		183
+#define __NR_capset		184
+#define __NR_sigaltstack	185
+#define __NR_sendfile		186
+#define __NR_getpmsg		187	/* some people actually want streams */
+#define __NR_putpmsg		188	/* some people actually want streams */
+#define __NR_vfork		189
+#define __NR_ugetrlimit		190	/* SuS compliant getrlimit */
+#define __NR_readahead		191
+#ifndef __powerpc64__			/* these are 32-bit only */
+#define __NR_mmap2		192
+#define __NR_truncate64		193
+#define __NR_ftruncate64	194
+#define __NR_stat64		195
+#define __NR_lstat64		196
+#define __NR_fstat64		197
+#endif
+#define __NR_pciconfig_read	198
+#define __NR_pciconfig_write	199
+#define __NR_pciconfig_iobase	200
+#define __NR_multiplexer	201
+#define __NR_getdents64		202
+#define __NR_pivot_root		203
+#ifndef __powerpc64__
+#define __NR_fcntl64		204
+#endif
+#define __NR_madvise		205
+#define __NR_mincore		206
+#define __NR_gettid		207
+#define __NR_tkill		208
+#define __NR_setxattr		209
+#define __NR_lsetxattr		210
+#define __NR_fsetxattr		211
+#define __NR_getxattr		212
+#define __NR_lgetxattr		213
+#define __NR_fgetxattr		214
+#define __NR_listxattr		215
+#define __NR_llistxattr		216
+#define __NR_flistxattr		217
+#define __NR_removexattr	218
+#define __NR_lremovexattr	219
+#define __NR_fremovexattr	220
+#define __NR_futex		221
+#define __NR_sched_setaffinity	222
+#define __NR_sched_getaffinity	223
+/* 224 currently unused */
+#define __NR_tuxcall		225
+#ifndef __powerpc64__
+#define __NR_sendfile64		226
+#endif
+#define __NR_io_setup		227
+#define __NR_io_destroy		228
+#define __NR_io_getevents	229
+#define __NR_io_submit		230
+#define __NR_io_cancel		231
+#define __NR_set_tid_address	232
+#define __NR_fadvise64		233
+#define __NR_exit_group		234
+#define __NR_lookup_dcookie	235
+#define __NR_epoll_create	236
+#define __NR_epoll_ctl		237
+#define __NR_epoll_wait		238
+#define __NR_remap_file_pages	239
+#define __NR_timer_create	240
+#define __NR_timer_settime	241
+#define __NR_timer_gettime	242
+#define __NR_timer_getoverrun	243
+#define __NR_timer_delete	244
+#define __NR_clock_settime	245
+#define __NR_clock_gettime	246
+#define __NR_clock_getres	247
+#define __NR_clock_nanosleep	248
+#define __NR_swapcontext	249
+#define __NR_tgkill		250
+#define __NR_utimes		251
+#define __NR_statfs64		252
+#define __NR_fstatfs64		253
+#ifndef __powerpc64__
+#define __NR_fadvise64_64	254
+#endif
+#define __NR_rtas		255
+#define __NR_sys_debug_setcontext 256
+/* Number 257 is reserved for vserver */
+#define __NR_migrate_pages	258
+#define __NR_mbind		259
+#define __NR_get_mempolicy	260
+#define __NR_set_mempolicy	261
+#define __NR_mq_open		262
+#define __NR_mq_unlink		263
+#define __NR_mq_timedsend	264
+#define __NR_mq_timedreceive	265
+#define __NR_mq_notify		266
+#define __NR_mq_getsetattr	267
+#define __NR_kexec_load		268
+#define __NR_add_key		269
+#define __NR_request_key	270
+#define __NR_keyctl		271
+#define __NR_waitid		272
+#define __NR_ioprio_set		273
+#define __NR_ioprio_get		274
+#define __NR_inotify_init	275
+#define __NR_inotify_add_watch	276
+#define __NR_inotify_rm_watch	277
+#define __NR_spu_run		278
+#define __NR_spu_create		279
+#define __NR_pselect6		280
+#define __NR_ppoll		281
+#define __NR_unshare		282
+#define __NR_splice		283
+#define __NR_tee		284
+#define __NR_vmsplice		285
+#define __NR_openat		286
+#define __NR_mkdirat		287
+#define __NR_mknodat		288
+#define __NR_fchownat		289
+#define __NR_futimesat		290
+#ifdef __powerpc64__
+#define __NR_newfstatat		291
+#else
+#define __NR_fstatat64		291
+#endif
+#define __NR_unlinkat		292
+#define __NR_renameat		293
+#define __NR_linkat		294
+#define __NR_symlinkat		295
+#define __NR_readlinkat		296
+#define __NR_fchmodat		297
+#define __NR_faccessat		298
+#define __NR_get_robust_list	299
+#define __NR_set_robust_list	300
+#define __NR_move_pages		301
+#define __NR_getcpu		302
+#define __NR_epoll_pwait	303
+#define __NR_utimensat		304
+#define __NR_signalfd		305
+#define __NR_timerfd_create	306
+#define __NR_eventfd		307
+#define __NR_sync_file_range2	308
+#define __NR_fallocate		309
+#define __NR_subpage_prot	310
+#define __NR_timerfd_settime	311
+#define __NR_timerfd_gettime	312
+#define __NR_signalfd4		313
+#define __NR_eventfd2		314
+#define __NR_epoll_create1	315
+#define __NR_dup3		316
+#define __NR_pipe2		317
+#define __NR_inotify_init1	318
+#define __NR_perf_event_open	319
+#define __NR_preadv		320
+#define __NR_pwritev		321
+#define __NR_rt_tgsigqueueinfo	322
+#define __NR_fanotify_init	323
+#define __NR_fanotify_mark	324
+#define __NR_prlimit64		325
+#define __NR_socket		326
+#define __NR_bind		327
+#define __NR_connect		328
+#define __NR_listen		329
+#define __NR_accept		330
+#define __NR_getsockname	331
+#define __NR_getpeername	332
+#define __NR_socketpair		333
+#define __NR_send		334
+#define __NR_sendto		335
+#define __NR_recv		336
+#define __NR_recvfrom		337
+#define __NR_shutdown		338
+#define __NR_setsockopt		339
+#define __NR_getsockopt		340
+#define __NR_sendmsg		341
+#define __NR_recvmsg		342
+#define __NR_recvmmsg		343
+#define __NR_accept4		344
+#define __NR_name_to_handle_at	345
+#define __NR_open_by_handle_at	346
+#define __NR_clock_adjtime	347
+#define __NR_syncfs		348
+#define __NR_sendmmsg		349
+#define __NR_setns		350
+#define __NR_process_vm_readv	351
+#define __NR_process_vm_writev	352
+#define __NR_finit_module	353
+#define __NR_kcmp		354
+#define __NR_sched_setattr	355
+#define __NR_sched_getattr	356
+#define __NR_renameat2		357
+#define __NR_seccomp		358
+#define __NR_getrandom		359
+#define __NR_memfd_create	360
+#define __NR_bpf		361
+#define __NR_execveat		362
+#define __NR_switch_endian	363
+#define __NR_userfaultfd	364
+#define __NR_membarrier		365
+#define __NR_mlock2		378
+#define __NR_copy_file_range	379
+#define __NR_preadv2		380
+#define __NR_pwritev2		381
+#define __NR_kexec_file_load	382
+#define __NR_statx		383
+#define __NR_pkey_alloc		384
+#define __NR_pkey_free		385
+#define __NR_pkey_mprotect	386
+
+#endif /* _UAPI_ASM_POWERPC_UNISTD_H_ */
diff --git a/tools/build/Makefile.feature b/tools/build/Makefile.feature
index c378f003b007..5b6dda3b1ca8 100644
--- a/tools/build/Makefile.feature
+++ b/tools/build/Makefile.feature
@@ -82,7 +82,11 @@ FEATURE_TESTS_EXTRA :=                  \
          liberty-z                      \
          libunwind-debug-frame          \
          libunwind-debug-frame-arm      \
-         libunwind-debug-frame-aarch64
+         libunwind-debug-frame-aarch64  \
+         cxx                            \
+         llvm                           \
+         llvm-version                   \
+         clang
 
 FEATURE_TESTS ?= $(FEATURE_TESTS_BASIC)
 
diff --git a/tools/build/feature/Makefile b/tools/build/feature/Makefile
index 0a490cb15149..dac9563b5470 100644
--- a/tools/build/feature/Makefile
+++ b/tools/build/feature/Makefile
@@ -54,7 +54,10 @@ FILES=                                          \
          test-jvmti.bin				\
          test-sched_getcpu.bin			\
          test-setns.bin				\
-         test-libopencsd.bin
+         test-libopencsd.bin			\
+         test-clang.bin				\
+         test-llvm.bin				\
+         test-llvm-version.bin
 
 FILES := $(addprefix $(OUTPUT),$(FILES))
 
@@ -257,11 +260,13 @@ $(OUTPUT)test-llvm.bin:
 		-I$(shell $(LLVM_CONFIG) --includedir) 		\
 		-L$(shell $(LLVM_CONFIG) --libdir)		\
 		$(shell $(LLVM_CONFIG) --libs Core BPF)		\
-		$(shell $(LLVM_CONFIG) --system-libs)
+		$(shell $(LLVM_CONFIG) --system-libs)		\
+		> $(@:.bin=.make.output) 2>&1
 
 $(OUTPUT)test-llvm-version.bin:
 	$(BUILDXX) -std=gnu++11 				\
-		-I$(shell $(LLVM_CONFIG) --includedir)
+		-I$(shell $(LLVM_CONFIG) --includedir)		\
+		> $(@:.bin=.make.output) 2>&1
 
 $(OUTPUT)test-clang.bin:
 	$(BUILDXX) -std=gnu++11 				\
@@ -271,7 +276,8 @@ $(OUTPUT)test-clang.bin:
 		  -lclangFrontend -lclangEdit -lclangLex	\
 		  -lclangAST -Wl,--end-group 			\
 		$(shell $(LLVM_CONFIG) --libs Core option)	\
-		$(shell $(LLVM_CONFIG) --system-libs)
+		$(shell $(LLVM_CONFIG) --system-libs)		\
+		> $(@:.bin=.make.output) 2>&1
 
 -include $(OUTPUT)*.d
 
diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h
index ca160270fdfa..63440cc8d618 100644
--- a/tools/include/linux/bitmap.h
+++ b/tools/include/linux/bitmap.h
@@ -98,7 +98,7 @@ static inline int test_and_set_bit(int nr, unsigned long *addr)
 
 /**
  * bitmap_alloc - Allocate bitmap
- * @nr: Bit to set
+ * @nbits: Number of bits
  */
 static inline unsigned long *bitmap_alloc(int nbits)
 {
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index e0739a1aa4b2..912b85b52344 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -380,10 +380,14 @@ struct perf_event_attr {
 	__u32			bp_type;
 	union {
 		__u64		bp_addr;
+		__u64		kprobe_func; /* for perf_kprobe */
+		__u64		uprobe_path; /* for perf_uprobe */
 		__u64		config1; /* extension of config */
 	};
 	union {
 		__u64		bp_len;
+		__u64		kprobe_addr; /* when kprobe_func == NULL */
+		__u64		probe_offset; /* for perf_[k,u]probe */
 		__u64		config2; /* extension of config1 */
 	};
 	__u64	branch_sample_type; /* enum perf_branch_sample_type */
@@ -444,17 +448,18 @@ struct perf_event_query_bpf {
 /*
  * Ioctls that can be done on a perf event fd:
  */
-#define PERF_EVENT_IOC_ENABLE		_IO ('$', 0)
-#define PERF_EVENT_IOC_DISABLE		_IO ('$', 1)
-#define PERF_EVENT_IOC_REFRESH		_IO ('$', 2)
-#define PERF_EVENT_IOC_RESET		_IO ('$', 3)
-#define PERF_EVENT_IOC_PERIOD		_IOW('$', 4, __u64)
-#define PERF_EVENT_IOC_SET_OUTPUT	_IO ('$', 5)
-#define PERF_EVENT_IOC_SET_FILTER	_IOW('$', 6, char *)
-#define PERF_EVENT_IOC_ID		_IOR('$', 7, __u64 *)
-#define PERF_EVENT_IOC_SET_BPF		_IOW('$', 8, __u32)
-#define PERF_EVENT_IOC_PAUSE_OUTPUT	_IOW('$', 9, __u32)
-#define PERF_EVENT_IOC_QUERY_BPF	_IOWR('$', 10, struct perf_event_query_bpf *)
+#define PERF_EVENT_IOC_ENABLE			_IO ('$', 0)
+#define PERF_EVENT_IOC_DISABLE			_IO ('$', 1)
+#define PERF_EVENT_IOC_REFRESH			_IO ('$', 2)
+#define PERF_EVENT_IOC_RESET			_IO ('$', 3)
+#define PERF_EVENT_IOC_PERIOD			_IOW('$', 4, __u64)
+#define PERF_EVENT_IOC_SET_OUTPUT		_IO ('$', 5)
+#define PERF_EVENT_IOC_SET_FILTER		_IOW('$', 6, char *)
+#define PERF_EVENT_IOC_ID			_IOR('$', 7, __u64 *)
+#define PERF_EVENT_IOC_SET_BPF			_IOW('$', 8, __u32)
+#define PERF_EVENT_IOC_PAUSE_OUTPUT		_IOW('$', 9, __u32)
+#define PERF_EVENT_IOC_QUERY_BPF		_IOWR('$', 10, struct perf_event_query_bpf *)
+#define PERF_EVENT_IOC_MODIFY_ATTRIBUTES	_IOW('$', 11, struct perf_event_attr *)
 
 enum perf_event_ioc_flags {
 	PERF_IOC_FLAG_GROUP		= 1U << 0,
diff --git a/tools/lib/api/fs/fs.c b/tools/lib/api/fs/fs.c
index b24afc0e6e81..6a12bbf39f7b 100644
--- a/tools/lib/api/fs/fs.c
+++ b/tools/lib/api/fs/fs.c
@@ -315,12 +315,8 @@ int filename__read_int(const char *filename, int *value)
 	return err;
 }
 
-/*
- * Parses @value out of @filename with strtoull.
- * By using 0 for base, the strtoull detects the
- * base automatically (see man strtoull).
- */
-int filename__read_ull(const char *filename, unsigned long long *value)
+static int filename__read_ull_base(const char *filename,
+				   unsigned long long *value, int base)
 {
 	char line[64];
 	int fd = open(filename, O_RDONLY), err = -1;
@@ -329,7 +325,7 @@ int filename__read_ull(const char *filename, unsigned long long *value)
 		return -1;
 
 	if (read(fd, line, sizeof(line)) > 0) {
-		*value = strtoull(line, NULL, 0);
+		*value = strtoull(line, NULL, base);
 		if (*value != ULLONG_MAX)
 			err = 0;
 	}
@@ -338,6 +334,25 @@ int filename__read_ull(const char *filename, unsigned long long *value)
 	return err;
 }
 
+/*
+ * Parses @value out of @filename with strtoull.
+ * By using 16 for base to treat the number as hex.
+ */
+int filename__read_xll(const char *filename, unsigned long long *value)
+{
+	return filename__read_ull_base(filename, value, 16);
+}
+
+/*
+ * Parses @value out of @filename with strtoull.
+ * By using 0 for base, the strtoull detects the
+ * base automatically (see man strtoull).
+ */
+int filename__read_ull(const char *filename, unsigned long long *value)
+{
+	return filename__read_ull_base(filename, value, 0);
+}
+
 #define STRERR_BUFSIZE  128     /* For the buffer size of strerror_r */
 
 int filename__read_str(const char *filename, char **buf, size_t *sizep)
@@ -417,7 +432,8 @@ int procfs__read_str(const char *entry, char **buf, size_t *sizep)
 	return filename__read_str(path, buf, sizep);
 }
 
-int sysfs__read_ull(const char *entry, unsigned long long *value)
+static int sysfs__read_ull_base(const char *entry,
+				unsigned long long *value, int base)
 {
 	char path[PATH_MAX];
 	const char *sysfs = sysfs__mountpoint();
@@ -427,7 +443,17 @@ int sysfs__read_ull(const char *entry, unsigned long long *value)
 
 	snprintf(path, sizeof(path), "%s/%s", sysfs, entry);
 
-	return filename__read_ull(path, value);
+	return filename__read_ull_base(path, value, base);
+}
+
+int sysfs__read_xll(const char *entry, unsigned long long *value)
+{
+	return sysfs__read_ull_base(entry, value, 16);
+}
+
+int sysfs__read_ull(const char *entry, unsigned long long *value)
+{
+	return sysfs__read_ull_base(entry, value, 0);
 }
 
 int sysfs__read_int(const char *entry, int *value)
diff --git a/tools/lib/api/fs/fs.h b/tools/lib/api/fs/fs.h
index dda49deefb52..92d03b8396b1 100644
--- a/tools/lib/api/fs/fs.h
+++ b/tools/lib/api/fs/fs.h
@@ -30,6 +30,7 @@ FS(bpf_fs)
 
 int filename__read_int(const char *filename, int *value);
 int filename__read_ull(const char *filename, unsigned long long *value);
+int filename__read_xll(const char *filename, unsigned long long *value);
 int filename__read_str(const char *filename, char **buf, size_t *sizep);
 
 int filename__write_int(const char *filename, int value);
@@ -39,6 +40,7 @@ int procfs__read_str(const char *entry, char **buf, size_t *sizep);
 int sysctl__read_int(const char *sysctl, int *value);
 int sysfs__read_int(const char *entry, int *value);
 int sysfs__read_ull(const char *entry, unsigned long long *value);
+int sysfs__read_xll(const char *entry, unsigned long long *value);
 int sysfs__read_str(const char *entry, char **buf, size_t *sizep);
 int sysfs__read_bool(const char *entry, bool *value);
 
diff --git a/tools/lib/str_error_r.c b/tools/lib/str_error_r.c
index d6d65537b0d9..6aad8308a0ac 100644
--- a/tools/lib/str_error_r.c
+++ b/tools/lib/str_error_r.c
@@ -22,6 +22,6 @@ char *str_error_r(int errnum, char *buf, size_t buflen)
 {
 	int err = strerror_r(errnum, buf, buflen);
 	if (err)
-		snprintf(buf, buflen, "INTERNAL ERROR: strerror_r(%d, %p, %zd)=%d", errnum, buf, buflen, err);
+		snprintf(buf, buflen, "INTERNAL ERROR: strerror_r(%d, [buf], %zd)=%d", errnum, buflen, err);
 	return buf;
 }
diff --git a/tools/lib/symbol/kallsyms.c b/tools/lib/symbol/kallsyms.c
index 914cb8e3d40b..689b6a130dd7 100644
--- a/tools/lib/symbol/kallsyms.c
+++ b/tools/lib/symbol/kallsyms.c
@@ -38,6 +38,10 @@ int kallsyms__parse(const char *filename, void *arg,
 
 		len = hex2u64(line, &start);
 
+		/* Skip the line if we failed to parse the address. */
+		if (!len)
+			continue;
+
 		len++;
 		if (len + 2 >= line_len)
 			continue;
diff --git a/tools/perf/Documentation/perf-annotate.txt b/tools/perf/Documentation/perf-annotate.txt
index c635eab6af54..749cc6055dac 100644
--- a/tools/perf/Documentation/perf-annotate.txt
+++ b/tools/perf/Documentation/perf-annotate.txt
@@ -21,7 +21,7 @@ If there is no debug info in the object, then annotated assembly is displayed.
 OPTIONS
 -------
 -i::
---input=::
+--input=<file>::
         Input file name. (default: perf.data unless stdin is a fifo)
 
 -d::
@@ -55,6 +55,9 @@ OPTIONS
 --vmlinux=<file>::
         vmlinux pathname.
 
+--ignore-vmlinux::
+	Ignore vmlinux files.
+
 -m::
 --modules::
         Load module symbols. WARNING: use only with -k and LIVE kernel.
@@ -69,7 +72,9 @@ OPTIONS
 
 --stdio:: Use the stdio interface.
 
---stdio-color::
+--stdio2:: Use the stdio2 interface, non-interactive, uses the TUI formatting.
+
+--stdio-color=<mode>::
 	'always', 'never' or 'auto', allowing configuring color output
 	via the command line, in addition to via "color.ui" .perfconfig.
 	Use '--stdio-color always' to generate color even when redirecting
@@ -84,7 +89,7 @@ OPTIONS
 --gtk:: Use the GTK interface.
 
 -C::
---cpu:: Only report samples for the list of CPUs provided. Multiple CPUs can
+--cpu=<cpu>:: Only report samples for the list of CPUs provided. Multiple CPUs can
 	be provided as a comma-separated list with no space: 0,1. Ranges of
 	CPUs are specified with -: 0-2. Default is to report samples on all
 	CPUs.
diff --git a/tools/perf/Documentation/perf-c2c.txt b/tools/perf/Documentation/perf-c2c.txt
index 822414235170..095aebdc5bb7 100644
--- a/tools/perf/Documentation/perf-c2c.txt
+++ b/tools/perf/Documentation/perf-c2c.txt
@@ -116,7 +116,7 @@ and calls standard perf record command.
 Following perf record options are configured by default:
 (check perf record man page for details)
 
-  -W,-d,--sample-cpu
+  -W,-d,--phys-data,--sample-cpu
 
 Unless specified otherwise with '-e' option, following events are monitored by
 default:
diff --git a/tools/perf/Documentation/perf-data.txt b/tools/perf/Documentation/perf-data.txt
index 90bb4aabe4f8..c87180764829 100644
--- a/tools/perf/Documentation/perf-data.txt
+++ b/tools/perf/Documentation/perf-data.txt
@@ -1,5 +1,5 @@
 perf-data(1)
-==============
+============
 
 NAME
 ----
diff --git a/tools/perf/Documentation/perf-ftrace.txt b/tools/perf/Documentation/perf-ftrace.txt
index 721a447f046e..b80c84307dc9 100644
--- a/tools/perf/Documentation/perf-ftrace.txt
+++ b/tools/perf/Documentation/perf-ftrace.txt
@@ -1,5 +1,5 @@
 perf-ftrace(1)
-=============
+==============
 
 NAME
 ----
diff --git a/tools/perf/Documentation/perf-kallsyms.txt b/tools/perf/Documentation/perf-kallsyms.txt
index cf9f4040ea5c..f3c620951f6e 100644
--- a/tools/perf/Documentation/perf-kallsyms.txt
+++ b/tools/perf/Documentation/perf-kallsyms.txt
@@ -1,5 +1,5 @@
 perf-kallsyms(1)
-==============
+================
 
 NAME
 ----
diff --git a/tools/perf/Documentation/perf-kmem.txt b/tools/perf/Documentation/perf-kmem.txt
index 479fc3261a50..85b8ac695c87 100644
--- a/tools/perf/Documentation/perf-kmem.txt
+++ b/tools/perf/Documentation/perf-kmem.txt
@@ -25,6 +25,10 @@ OPTIONS
 --input=<file>::
 	Select the input file (default: perf.data unless stdin is a fifo)
 
+-f::
+--force::
+	Don't do ownership validation
+
 -v::
 --verbose::
         Be more verbose. (show symbol address, etc)
@@ -61,7 +65,7 @@ OPTIONS
 	default, but this option shows live (currently allocated) pages
 	instead.  (This option works with --page option only)
 
---time::
+--time=<start>,<stop>::
 	Only analyze samples within given time window: <start>,<stop>. Times
 	have the format seconds.microseconds. If start is not given (i.e., time
 	string is ',x.y') then analysis starts at the beginning of the file. If
diff --git a/tools/perf/Documentation/perf-list.txt b/tools/perf/Documentation/perf-list.txt
index e2a897ae3596..2549c34a7895 100644
--- a/tools/perf/Documentation/perf-list.txt
+++ b/tools/perf/Documentation/perf-list.txt
@@ -141,7 +141,13 @@ on the first memory controller on socket 0 of a Intel Xeon system
 
 Each memory controller has its own PMU.  Measuring the complete system
 bandwidth would require specifying all imc PMUs (see perf list output),
-and adding the values together.
+and adding the values together. To simplify creation of multiple events,
+prefix and glob matching is supported in the PMU name, and the prefix
+'uncore_' is also ignored when performing the match. So the command above
+can be expanded to all memory controllers by using the syntaxes:
+
+  perf stat -C 0 -a imc/cas_count_read/,imc/cas_count_write/ -I 1000 ...
+  perf stat -C 0 -a *imc*/cas_count_read/,*imc*/cas_count_write/ -I 1000 ...
 
 This example measures the combined core power every second
 
diff --git a/tools/perf/Documentation/perf-mem.txt b/tools/perf/Documentation/perf-mem.txt
index 4be08a1e3f8d..b0211410969b 100644
--- a/tools/perf/Documentation/perf-mem.txt
+++ b/tools/perf/Documentation/perf-mem.txt
@@ -28,6 +28,10 @@ OPTIONS
 <command>...::
 	Any command you can specify in a shell.
 
+-f::
+--force::
+	Don't do ownership validation
+
 -t::
 --type=::
 	Select the memory operation type: load or store (default: load,store)
diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index 3eea6de35a38..cc37b3a4be76 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -191,9 +191,16 @@ OPTIONS
 -i::
 --no-inherit::
 	Child tasks do not inherit counters.
+
 -F::
 --freq=::
-	Profile at this frequency.
+	Profile at this frequency. Use 'max' to use the currently maximum
+	allowed frequency, i.e. the value in the kernel.perf_event_max_sample_rate
+	sysctl. Will throttle down to the currently maximum allowed frequency.
+	See --strict-freq.
+
+--strict-freq::
+	Fail if the specified frequency can't be used.
 
 -m::
 --mmap-pages=::
@@ -308,7 +315,11 @@ can be provided. Each cgroup is applied to the corresponding event, i.e., first
 to first event, second cgroup to second event and so on. It is possible to provide
 an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
 corresponding events, i.e., they always refer to events defined earlier on the command
-line.
+line. If the user wants to track multiple events for a specific cgroup, the user can
+use '-e e1 -e e2 -G foo,foo' or just use '-e e1 -e e2 -G foo'.
+
+If wanting to monitor, say, 'cycles' for a cgroup and also for system wide, this
+command line can be used: 'perf stat -e cycles -G cgroup_name -a -e cycles'.
 
 -b::
 --branch-any::
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 907e505b6309..e1a660e60849 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -296,6 +296,9 @@ OPTIONS
 --vmlinux=<file>::
         vmlinux pathname
 
+--ignore-vmlinux::
+	Ignore vmlinux files.
+
 --kallsyms=<file>::
         kallsyms pathname
 
@@ -354,7 +357,8 @@ OPTIONS
         Path to objdump binary.
 
 --group::
-	Show event group information together.
+	Show event group information together. It forces group output also
+	if there are no groups defined in data file.
 
 --demangle::
 	Demangle symbol names to human readable form. It's enabled by default,
@@ -367,7 +371,7 @@ OPTIONS
 	Use the data addresses of samples in addition to instruction addresses
 	to build the histograms.  To generate meaningful output, the perf.data
 	file must have been obtained using perf record -d -W and using a
-	special event -e cpu/mem-loads/ or -e cpu/mem-stores/. See
+	special event -e cpu/mem-loads/p or -e cpu/mem-stores/p. See
 	'perf mem' for simpler access.
 
 --percent-limit::
diff --git a/tools/perf/Documentation/perf-sched.txt b/tools/perf/Documentation/perf-sched.txt
index c7e50f263887..bb33601a823b 100644
--- a/tools/perf/Documentation/perf-sched.txt
+++ b/tools/perf/Documentation/perf-sched.txt
@@ -1,5 +1,5 @@
 perf-sched(1)
-==============
+=============
 
 NAME
 ----
diff --git a/tools/perf/Documentation/perf-script-perl.txt b/tools/perf/Documentation/perf-script-perl.txt
index 142606c0ec9c..5a1f68122f50 100644
--- a/tools/perf/Documentation/perf-script-perl.txt
+++ b/tools/perf/Documentation/perf-script-perl.txt
@@ -1,5 +1,5 @@
 perf-script-perl(1)
-==================
+===================
 
 NAME
 ----
diff --git a/tools/perf/Documentation/perf-script.txt b/tools/perf/Documentation/perf-script.txt
index 7730c1d2b5d3..36ec0257f8d3 100644
--- a/tools/perf/Documentation/perf-script.txt
+++ b/tools/perf/Documentation/perf-script.txt
@@ -303,6 +303,9 @@ OPTIONS
 --show-lost-events
 	Display lost events i.e. events of type PERF_RECORD_LOST.
 
+--show-round-events
+	Display finished round events i.e. events of type PERF_RECORD_FINISHED_ROUND.
+
 --demangle::
 	Demangle symbol names to human readable form. It's enabled by default,
 	disable with --no-demangle.
diff --git a/tools/perf/Documentation/perf-stat.txt b/tools/perf/Documentation/perf-stat.txt
index 823fce7674bb..f15b306be183 100644
--- a/tools/perf/Documentation/perf-stat.txt
+++ b/tools/perf/Documentation/perf-stat.txt
@@ -49,6 +49,13 @@ report::
 	  parameters are defined by corresponding entries in
 	  /sys/bus/event_source/devices/<pmu>/format/*
 
+	Note that the last two syntaxes support prefix and glob matching in
+	the PMU name to simplify creation of events accross multiple instances
+	of the same type of PMU in large systems (e.g. memory controller PMUs).
+	Multiple PMU instances are typical for uncore PMUs, so the prefix
+	'uncore_' is also ignored when performing this match.
+
+
 -i::
 --no-inherit::
         child tasks do not inherit counters
@@ -118,7 +125,11 @@ can be provided. Each cgroup is applied to the corresponding event, i.e., first
 to first event, second cgroup to second event and so on. It is possible to provide
 an empty cgroup (monitor all the time) using, e.g., -G foo,,bar. Cgroups must have
 corresponding events, i.e., they always refer to events defined earlier on the command
-line.
+line. If the user wants to track multiple events for a specific cgroup, the user can
+use '-e e1 -e e2 -G foo,foo' or just use '-e e1 -e e2 -G foo'.
+
+If wanting to monitor, say, 'cycles' for a cgroup and also for system wide, this
+command line can be used: 'perf stat -e cycles -G cgroup_name -a -e cycles'.
 
 -o file::
 --output file::
@@ -146,6 +157,16 @@ Print count deltas every N milliseconds (minimum: 10ms)
 The overhead percentage could be high in some cases, for instance with small, sub 100ms intervals.  Use with caution.
 	example: 'perf stat -I 1000 -e cycles -a sleep 5'
 
+--interval-count times::
+Print count deltas for fixed number of times.
+This option should be used together with "-I" option.
+	example: 'perf stat -I 1000 --interval-count 2 -e cycles -a'
+
+--timeout msecs::
+Stop the 'perf stat' session and print count deltas after N milliseconds (minimum: 10 ms).
+This option is not supported with the "-I" option.
+	example: 'perf stat --time 2000 -e cycles -a'
+
 --metric-only::
 Only print computed metrics. Print them in a single line.
 Don't show any raw values. Not supported with --per-thread.
@@ -246,6 +267,16 @@ taskset.
 --no-merge::
 Do not merge results from same PMUs.
 
+When multiple events are created from a single event specification,
+stat will, by default, aggregate the event counts and show the result
+in a single row. This option disables that behavior and shows
+the individual events and counts.
+
+Multiple events are created from a single event specification when:
+1. Prefix or glob matching is used for the PMU name.
+2. Aliases, which are listed immediately after the Kernel PMU events
+   by perf list, are used.
+
 --smi-cost::
 Measure SMI cost if msr/aperf/ and msr/smi/ events are supported.
 
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 8a32cc77bead..114fda12aa49 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -55,7 +55,9 @@ Default is to monitor all CPUS.
 
 -F <freq>::
 --freq=<freq>::
-	Profile at this frequency.
+	Profile at this frequency. Use 'max' to use the currently maximum
+	allowed frequency, i.e. the value in the kernel.perf_event_max_sample_rate
+	sysctl.
 
 -i::
 --inherit::
@@ -65,6 +67,9 @@ Default is to monitor all CPUS.
 --vmlinux=<path>::
 	Path to vmlinux.  Required for annotation functionality.
 
+--ignore-vmlinux::
+	Ignore vmlinux files.
+
 -m <pages>::
 --mmap-pages=<pages>::
 	Number of mmap data pages (must be a power of two) or size
diff --git a/tools/perf/Documentation/perf-trace.txt b/tools/perf/Documentation/perf-trace.txt
index 33a88e984e66..5a7035c5c523 100644
--- a/tools/perf/Documentation/perf-trace.txt
+++ b/tools/perf/Documentation/perf-trace.txt
@@ -63,6 +63,31 @@ filter out the startup phase of the program, which is often very different.
 --uid=::
         Record events in threads owned by uid. Name or number.
 
+-G::
+--cgroup::
+	Record events in threads in a cgroup.
+
+	Look for cgroups to set at the /sys/fs/cgroup/perf_event directory, then
+	remove the /sys/fs/cgroup/perf_event/ part and try:
+
+		perf trace -G A -e sched:*switch
+
+	Will set all raw_syscalls:sys_{enter,exit}, pgfault, vfs_getname, etc
+	_and_ sched:sched_switch to the 'A' cgroup, while:
+
+		perf trace -e sched:*switch -G A
+
+	will only set the sched:sched_switch event to the 'A' cgroup, all the
+	other events (raw_syscalls:sys_{enter,exit}, etc are left "without"
+	a cgroup (on the root cgroup, sys wide, etc).
+
+	Multiple cgroups:
+
+		perf trace -G A -e sched:*switch -G B
+
+	the syscall ones go to the 'A' cgroup, the sched:sched_switch goes
+	to the 'B' cgroup.
+
 --filter-pids=::
 	Filter out events for these pids and for 'trace' itself (comma separated list).
 
diff --git a/tools/perf/Documentation/perf.data-file-format.txt b/tools/perf/Documentation/perf.data-file-format.txt
index f7d85e89a98a..d00f0d51cab8 100644
--- a/tools/perf/Documentation/perf.data-file-format.txt
+++ b/tools/perf/Documentation/perf.data-file-format.txt
@@ -485,10 +485,5 @@ in pmu-tools parser. This allows to read perf.data from python and dump it.
 quipper
 
 The quipper C++ parser is available at
-https://chromium.googlesource.com/chromiumos/platform2
+http://github.com/google/perf_data_converter/tree/master/src/quipper
 
-It is under the chromiumos-wide-profiling/ subdirectory. This library can
-convert a perf data file to a protobuf and vice versa.
-
-Unfortunately this parser tends to be many versions behind and may not be able
-to parse data files generated by recent perf.
diff --git a/tools/perf/Makefile.config b/tools/perf/Makefile.config
index 0dfdaa9fa81e..98ff73648b51 100644
--- a/tools/perf/Makefile.config
+++ b/tools/perf/Makefile.config
@@ -27,6 +27,8 @@ NO_SYSCALL_TABLE := 1
 # Additional ARCH settings for ppc
 ifeq ($(SRCARCH),powerpc)
   NO_PERF_REGS := 0
+  NO_SYSCALL_TABLE := 0
+  CFLAGS += -I$(OUTPUT)arch/powerpc/include/generated
   LIBUNWIND_LIBS := -lunwind -lunwind-ppc64
 endif
 
@@ -73,7 +75,7 @@ endif
 # Disable it on all other architectures in case libdw unwind
 # support is detected in system. Add supported architectures
 # to the check.
-ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm powerpc s390))
+ifneq ($(SRCARCH),$(filter $(SRCARCH),x86 arm arm64 powerpc s390))
   NO_LIBDW_DWARF_UNWIND := 1
 endif
 
@@ -666,25 +668,10 @@ else
       ifneq ($(feature-libpython), 1)
         $(call disable-python,No 'Python.h' (for Python 2.x support) was found: disables Python support - please install python-devel/python-dev)
       else
-        ifneq ($(feature-libpython-version), 1)
-          $(warning Python 3 is not yet supported; please set)
-          $(warning PYTHON and/or PYTHON_CONFIG appropriately.)
-          $(warning If you also have Python 2 installed, then)
-          $(warning try something like:)
-          $(warning $(and ,))
-          $(warning $(and ,)  make PYTHON=python2)
-          $(warning $(and ,))
-          $(warning Otherwise, disable Python support entirely:)
-          $(warning $(and ,))
-          $(warning $(and ,)  make NO_LIBPYTHON=1)
-          $(warning $(and ,))
-          $(error   $(and ,))
-        else
-          LDFLAGS += $(PYTHON_EMBED_LDFLAGS)
-          EXTLIBS += $(PYTHON_EMBED_LIBADD)
-          LANG_BINDINGS += $(obj-perf)python/perf.so
-          $(call detected,CONFIG_LIBPYTHON)
-        endif
+         LDFLAGS += $(PYTHON_EMBED_LDFLAGS)
+         EXTLIBS += $(PYTHON_EMBED_LIBADD)
+         LANG_BINDINGS += $(obj-perf)python/perf.so
+         $(call detected,CONFIG_LIBPYTHON)
       endif
     endif
   endif
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 012328038594..f7517e1b73f8 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -296,7 +296,7 @@ PYTHON_EXTBUILD_LIB := $(PYTHON_EXTBUILD)lib/
 PYTHON_EXTBUILD_TMP := $(PYTHON_EXTBUILD)tmp/
 export PYTHON_EXTBUILD_LIB PYTHON_EXTBUILD_TMP
 
-python-clean := $(call QUIET_CLEAN, python) $(RM) -r $(PYTHON_EXTBUILD) $(OUTPUT)python/perf.so
+python-clean := $(call QUIET_CLEAN, python) $(RM) -r $(PYTHON_EXTBUILD) $(OUTPUT)python/perf*.so
 
 PYTHON_EXT_SRCS := $(shell grep -v ^\# util/python-ext-sources)
 PYTHON_EXT_DEPS := util/python-ext-sources util/setup.py $(LIBTRACEEVENT) $(LIBAPI)
@@ -473,7 +473,7 @@ $(OUTPUT)python/perf.so: $(PYTHON_EXT_SRCS) $(PYTHON_EXT_DEPS) $(LIBTRACEEVENT_D
 	  $(PYTHON_WORD) util/setup.py \
 	  --quiet build_ext; \
 	mkdir -p $(OUTPUT)python && \
-	cp $(PYTHON_EXTBUILD_LIB)perf.so $(OUTPUT)python/
+	cp $(PYTHON_EXTBUILD_LIB)perf*.so $(OUTPUT)python/
 
 please_set_SHELL_PATH_to_a_more_modern_shell:
 	$(Q)$$(:)
@@ -708,15 +708,15 @@ TAG_FILES= ../../include/uapi/linux/perf_event.h
 
 TAGS:
 	$(QUIET_GEN)$(RM) TAGS; \
-	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs etags -a $(TAG_FILES)
+	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print -o -name '*.cpp' -print | xargs etags -a $(TAG_FILES)
 
 tags:
 	$(QUIET_GEN)$(RM) tags; \
-	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs ctags -a $(TAG_FILES)
+	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print -o -name '*.cpp' -print | xargs ctags -a $(TAG_FILES)
 
 cscope:
 	$(QUIET_GEN)$(RM) cscope*; \
-	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print | xargs cscope -b $(TAG_FILES)
+	$(FIND) $(TAG_FOLDERS) -name '*.[hcS]' -print -o -name '*.cpp' -print | xargs cscope -b $(TAG_FILES)
 
 ### Testing rules
 
diff --git a/tools/perf/arch/arm/util/auxtrace.c b/tools/perf/arch/arm/util/auxtrace.c
index 2323581b157d..fa639e3e52ac 100644
--- a/tools/perf/arch/arm/util/auxtrace.c
+++ b/tools/perf/arch/arm/util/auxtrace.c
@@ -68,7 +68,7 @@ struct auxtrace_record
 	bool found_spe = false;
 	static struct perf_pmu **arm_spe_pmus = NULL;
 	static int nr_spes = 0;
-	int i;
+	int i = 0;
 
 	if (!evlist)
 		return NULL;
diff --git a/tools/perf/arch/arm/util/cs-etm.c b/tools/perf/arch/arm/util/cs-etm.c
index fbfc055d3f4d..5c655ad4621e 100644
--- a/tools/perf/arch/arm/util/cs-etm.c
+++ b/tools/perf/arch/arm/util/cs-etm.c
@@ -298,12 +298,17 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 {
 	int i;
 	int etmv3 = 0, etmv4 = 0;
-	const struct cpu_map *cpus = evlist->cpus;
+	struct cpu_map *event_cpus = evlist->cpus;
+	struct cpu_map *online_cpus = cpu_map__new(NULL);
 
 	/* cpu map is not empty, we have specific CPUs to work with */
-	if (!cpu_map__empty(cpus)) {
-		for (i = 0; i < cpu_map__nr(cpus); i++) {
-			if (cs_etm_is_etmv4(itr, cpus->map[i]))
+	if (!cpu_map__empty(event_cpus)) {
+		for (i = 0; i < cpu__max_cpu(); i++) {
+			if (!cpu_map__has(event_cpus, i) ||
+			    !cpu_map__has(online_cpus, i))
+				continue;
+
+			if (cs_etm_is_etmv4(itr, i))
 				etmv4++;
 			else
 				etmv3++;
@@ -311,6 +316,9 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 	} else {
 		/* get configuration for all CPUs in the system */
 		for (i = 0; i < cpu__max_cpu(); i++) {
+			if (!cpu_map__has(online_cpus, i))
+				continue;
+
 			if (cs_etm_is_etmv4(itr, i))
 				etmv4++;
 			else
@@ -318,6 +326,8 @@ cs_etm_info_priv_size(struct auxtrace_record *itr __maybe_unused,
 		}
 	}
 
+	cpu_map__put(online_cpus);
+
 	return (CS_ETM_HEADER_SIZE +
 	       (etmv4 * CS_ETMV4_PRIV_SIZE) +
 	       (etmv3 * CS_ETMV3_PRIV_SIZE));
@@ -447,7 +457,9 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 	int i;
 	u32 offset;
 	u64 nr_cpu, type;
-	const struct cpu_map *cpus = session->evlist->cpus;
+	struct cpu_map *cpu_map;
+	struct cpu_map *event_cpus = session->evlist->cpus;
+	struct cpu_map *online_cpus = cpu_map__new(NULL);
 	struct cs_etm_recording *ptr =
 			container_of(itr, struct cs_etm_recording, itr);
 	struct perf_pmu *cs_etm_pmu = ptr->cs_etm_pmu;
@@ -458,8 +470,21 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 	if (!session->evlist->nr_mmaps)
 		return -EINVAL;
 
-	/* If the cpu_map is empty all CPUs are involved */
-	nr_cpu = cpu_map__empty(cpus) ? cpu__max_cpu() : cpu_map__nr(cpus);
+	/* If the cpu_map is empty all online CPUs are involved */
+	if (cpu_map__empty(event_cpus)) {
+		cpu_map = online_cpus;
+	} else {
+		/* Make sure all specified CPUs are online */
+		for (i = 0; i < cpu_map__nr(event_cpus); i++) {
+			if (cpu_map__has(event_cpus, i) &&
+			    !cpu_map__has(online_cpus, i))
+				return -EINVAL;
+		}
+
+		cpu_map = event_cpus;
+	}
+
+	nr_cpu = cpu_map__nr(cpu_map);
 	/* Get PMU type as dynamically assigned by the core */
 	type = cs_etm_pmu->type;
 
@@ -472,15 +497,11 @@ static int cs_etm_info_fill(struct auxtrace_record *itr,
 
 	offset = CS_ETM_SNAPSHOT + 1;
 
-	/* cpu map is not empty, we have specific CPUs to work with */
-	if (!cpu_map__empty(cpus)) {
-		for (i = 0; i < cpu_map__nr(cpus) && offset < priv_size; i++)
-			cs_etm_get_metadata(cpus->map[i], &offset, itr, info);
-	} else {
-		/* get configuration for all CPUs in the system */
-		for (i = 0; i < cpu__max_cpu(); i++)
+	for (i = 0; i < cpu__max_cpu() && offset < priv_size; i++)
+		if (cpu_map__has(cpu_map, i))
 			cs_etm_get_metadata(i, &offset, itr, info);
-	}
+
+	cpu_map__put(online_cpus);
 
 	return 0;
 }
diff --git a/tools/perf/arch/arm64/include/arch-tests.h b/tools/perf/arch/arm64/include/arch-tests.h
new file mode 100644
index 000000000000..90ec4c8cb880
--- /dev/null
+++ b/tools/perf/arch/arm64/include/arch-tests.h
@@ -0,0 +1,12 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef ARCH_TESTS_H
+#define ARCH_TESTS_H
+
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+struct thread;
+struct perf_sample;
+#endif
+
+extern struct test arch_tests[];
+
+#endif
diff --git a/tools/perf/arch/arm64/tests/Build b/tools/perf/arch/arm64/tests/Build
index b30eff9bcc83..883c57ff0c08 100644
--- a/tools/perf/arch/arm64/tests/Build
+++ b/tools/perf/arch/arm64/tests/Build
@@ -1,2 +1,4 @@
 libperf-y += regs_load.o
 libperf-y += dwarf-unwind.o
+
+libperf-y += arch-tests.o
diff --git a/tools/perf/arch/arm64/tests/arch-tests.c b/tools/perf/arch/arm64/tests/arch-tests.c
new file mode 100644
index 000000000000..5b1543c98022
--- /dev/null
+++ b/tools/perf/arch/arm64/tests/arch-tests.c
@@ -0,0 +1,16 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <string.h>
+#include "tests/tests.h"
+#include "arch-tests.h"
+
+struct test arch_tests[] = {
+#ifdef HAVE_DWARF_UNWIND_SUPPORT
+	{
+		.desc = "DWARF unwind",
+		.func = test__dwarf_unwind,
+	},
+#endif
+	{
+		.func = NULL,
+	},
+};
diff --git a/tools/perf/arch/arm64/util/Build b/tools/perf/arch/arm64/util/Build
index c0b8dfef98ba..68f8a8eb3ad0 100644
--- a/tools/perf/arch/arm64/util/Build
+++ b/tools/perf/arch/arm64/util/Build
@@ -2,6 +2,7 @@ libperf-y += header.o
 libperf-y += sym-handling.o
 libperf-$(CONFIG_DWARF)     += dwarf-regs.o
 libperf-$(CONFIG_LOCAL_LIBUNWIND) += unwind-libunwind.o
+libperf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 
 libperf-$(CONFIG_AUXTRACE) += ../../arm/util/pmu.o \
 			      ../../arm/util/auxtrace.o \
diff --git a/tools/perf/arch/arm64/util/unwind-libdw.c b/tools/perf/arch/arm64/util/unwind-libdw.c
new file mode 100644
index 000000000000..7623d85e77f3
--- /dev/null
+++ b/tools/perf/arch/arm64/util/unwind-libdw.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <elfutils/libdwfl.h>
+#include "../../util/unwind-libdw.h"
+#include "../../util/perf_regs.h"
+#include "../../util/event.h"
+
+bool libdw__arch_set_initial_registers(Dwfl_Thread *thread, void *arg)
+{
+	struct unwind_info *ui = arg;
+	struct regs_dump *user_regs = &ui->sample->user_regs;
+	Dwarf_Word dwarf_regs[PERF_REG_ARM64_MAX], dwarf_pc;
+
+#define REG(r) ({						\
+	Dwarf_Word val = 0;					\
+	perf_reg_value(&val, user_regs, PERF_REG_ARM64_##r);	\
+	val;							\
+})
+
+	dwarf_regs[0]  = REG(X0);
+	dwarf_regs[1]  = REG(X1);
+	dwarf_regs[2]  = REG(X2);
+	dwarf_regs[3]  = REG(X3);
+	dwarf_regs[4]  = REG(X4);
+	dwarf_regs[5]  = REG(X5);
+	dwarf_regs[6]  = REG(X6);
+	dwarf_regs[7]  = REG(X7);
+	dwarf_regs[8]  = REG(X8);
+	dwarf_regs[9]  = REG(X9);
+	dwarf_regs[10] = REG(X10);
+	dwarf_regs[11] = REG(X11);
+	dwarf_regs[12] = REG(X12);
+	dwarf_regs[13] = REG(X13);
+	dwarf_regs[14] = REG(X14);
+	dwarf_regs[15] = REG(X15);
+	dwarf_regs[16] = REG(X16);
+	dwarf_regs[17] = REG(X17);
+	dwarf_regs[18] = REG(X18);
+	dwarf_regs[19] = REG(X19);
+	dwarf_regs[20] = REG(X20);
+	dwarf_regs[21] = REG(X21);
+	dwarf_regs[22] = REG(X22);
+	dwarf_regs[23] = REG(X23);
+	dwarf_regs[24] = REG(X24);
+	dwarf_regs[25] = REG(X25);
+	dwarf_regs[26] = REG(X26);
+	dwarf_regs[27] = REG(X27);
+	dwarf_regs[28] = REG(X28);
+	dwarf_regs[29] = REG(X29);
+	dwarf_regs[30] = REG(LR);
+	dwarf_regs[31] = REG(SP);
+
+	if (!dwfl_thread_state_registers(thread, 0, PERF_REG_ARM64_MAX,
+					 dwarf_regs))
+		return false;
+
+	dwarf_pc = REG(PC);
+	dwfl_thread_state_register_pc(thread, dwarf_pc);
+
+	return true;
+}
diff --git a/tools/perf/arch/powerpc/Makefile b/tools/perf/arch/powerpc/Makefile
index 42dab7c8f508..a111239df182 100644
--- a/tools/perf/arch/powerpc/Makefile
+++ b/tools/perf/arch/powerpc/Makefile
@@ -6,3 +6,28 @@ endif
 HAVE_KVM_STAT_SUPPORT := 1
 PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
 PERF_HAVE_JITDUMP := 1
+
+#
+# Syscall table generation for perf
+#
+
+out    := $(OUTPUT)arch/powerpc/include/generated/asm
+header32 := $(out)/syscalls_32.c
+header64 := $(out)/syscalls_64.c
+sysdef := $(srctree)/tools/arch/powerpc/include/uapi/asm/unistd.h
+sysprf := $(srctree)/tools/perf/arch/powerpc/entry/syscalls/
+systbl := $(sysprf)/mksyscalltbl
+
+# Create output directory if not already present
+_dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
+
+$(header64): $(sysdef) $(systbl)
+	$(Q)$(SHELL) '$(systbl)' '64' '$(CC)' $(sysdef) > $@
+
+$(header32): $(sysdef) $(systbl)
+	$(Q)$(SHELL) '$(systbl)' '32' '$(CC)' $(sysdef) > $@
+
+clean::
+	$(call QUIET_CLEAN, powerpc) $(RM) $(header32) $(header64)
+
+archheaders: $(header32) $(header64)
diff --git a/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl b/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl
new file mode 100755
index 000000000000..ef52e1dd694b
--- /dev/null
+++ b/tools/perf/arch/powerpc/entry/syscalls/mksyscalltbl
@@ -0,0 +1,37 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Generate system call table for perf. Derived from
+# s390 script.
+#
+# Copyright IBM Corp. 2017
+# Author(s):  Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
+# Changed by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
+
+wordsize=$1
+gcc=$2
+input=$3
+
+if ! test -r $input; then
+	echo "Could not read input file" >&2
+	exit 1
+fi
+
+create_table()
+{
+	local wordsize=$1
+	local max_nr
+
+	echo "static const char *syscalltbl_powerpc_${wordsize}[] = {"
+	while read sc nr; do
+		printf '\t[%d] = "%s",\n' $nr $sc
+		max_nr=$nr
+	done
+	echo '};'
+	echo "#define SYSCALLTBL_POWERPC_${wordsize}_MAX_ID $max_nr"
+}
+
+$gcc -m${wordsize} -E -dM -x c  $input	       \
+	|sed -ne 's/^#define __NR_//p' \
+	|sort -t' ' -k2 -nu	       \
+	|create_table ${wordsize}
diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c
index 8c72b44444cb..cee4e2f7c057 100644
--- a/tools/perf/arch/s390/annotate/instructions.c
+++ b/tools/perf/arch/s390/annotate/instructions.c
@@ -1,6 +1,113 @@
 // SPDX-License-Identifier: GPL-2.0
 #include <linux/compiler.h>
 
+static int s390_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 = {
+		.map = map,
+	};
+
+	tok = strchr(ops->raw, ',');
+	if (!tok)
+		return -1;
+
+	ops->target.addr = strtoull(tok + 1, &endptr, 16);
+
+	name = strchr(endptr, '<');
+	if (name == NULL)
+		return -1;
+
+	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;
+	target.addr = map__objdump_2mem(map, ops->target.addr);
+
+	if (map_groups__find_ams(&target) == 0 &&
+	    map__rip_2objdump(target.map, map->map_ip(target.map, target.addr)) == ops->target.addr)
+		ops->target.sym = target.sym;
+
+	return 0;
+}
+
+static int call__scnprintf(struct ins *ins, char *bf, size_t size,
+			   struct ins_operands *ops);
+
+static struct ins_ops s390_call_ops = {
+	.parse	   = s390_call__parse,
+	.scnprintf = call__scnprintf,
+};
+
+static int s390_mov__parse(struct arch *arch __maybe_unused,
+			   struct ins_operands *ops,
+			   struct map_symbol *ms __maybe_unused)
+{
+	char *s = strchr(ops->raw, ','), *target, *endptr;
+
+	if (s == NULL)
+		return -1;
+
+	*s = '\0';
+	ops->source.raw = strdup(ops->raw);
+	*s = ',';
+
+	if (ops->source.raw == NULL)
+		return -1;
+
+	target = ++s;
+	ops->target.raw = strdup(target);
+	if (ops->target.raw == NULL)
+		goto out_free_source;
+
+	ops->target.addr = strtoull(target, &endptr, 16);
+	if (endptr == target)
+		goto out_free_target;
+
+	s = strchr(endptr, '<');
+	if (s == NULL)
+		goto out_free_target;
+	endptr = strchr(s + 1, '>');
+	if (endptr == NULL)
+		goto out_free_target;
+
+	*endptr = '\0';
+	ops->target.name = strdup(s + 1);
+	*endptr = '>';
+	if (ops->target.name == NULL)
+		goto out_free_target;
+
+	return 0;
+
+out_free_target:
+	zfree(&ops->target.raw);
+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);
+
+static struct ins_ops s390_mov_ops = {
+	.parse	   = s390_mov__parse,
+	.scnprintf = mov__scnprintf,
+};
+
 static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *name)
 {
 	struct ins_ops *ops = NULL;
@@ -14,21 +121,54 @@ static struct ins_ops *s390__associate_ins_ops(struct arch *arch, const char *na
 	if (!strcmp(name, "bras") ||
 	    !strcmp(name, "brasl") ||
 	    !strcmp(name, "basr"))
-		ops = &call_ops;
+		ops = &s390_call_ops;
 	if (!strcmp(name, "br"))
 		ops = &ret_ops;
+	/* override load/store relative to PC */
+	if (!strcmp(name, "lrl") ||
+	    !strcmp(name, "lgrl") ||
+	    !strcmp(name, "lgfrl") ||
+	    !strcmp(name, "llgfrl") ||
+	    !strcmp(name, "strl") ||
+	    !strcmp(name, "stgrl"))
+		ops = &s390_mov_ops;
 
 	if (ops)
 		arch__associate_ins_ops(arch, name, ops);
 	return ops;
 }
 
+static int s390__cpuid_parse(struct arch *arch, char *cpuid)
+{
+	unsigned int family;
+	char model[16], model_c[16], cpumf_v[16], cpumf_a[16];
+	int ret;
+
+	/*
+	 * cpuid string format:
+	 * "IBM,family,model-capacity,model[,cpum_cf-version,cpum_cf-authorization]"
+	 */
+	ret = sscanf(cpuid, "%*[^,],%u,%[^,],%[^,],%[^,],%s", &family, model_c,
+		     model, cpumf_v, cpumf_a);
+	if (ret >= 2) {
+		arch->family = family;
+		arch->model = 0;
+		return 0;
+	}
+
+	return -1;
+}
+
 static int s390__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 {
+	int err = 0;
+
 	if (!arch->initialized) {
 		arch->initialized = true;
 		arch->associate_instruction_ops = s390__associate_ins_ops;
+		if (cpuid)
+			err = s390__cpuid_parse(arch, cpuid);
 	}
 
-	return 0;
+	return err;
 }
diff --git a/tools/perf/arch/s390/util/header.c b/tools/perf/arch/s390/util/header.c
index 9fa6c3e5782c..a4c30f1c70be 100644
--- a/tools/perf/arch/s390/util/header.c
+++ b/tools/perf/arch/s390/util/header.c
@@ -1,8 +1,9 @@
 /*
  * Implementation of get_cpuid().
  *
- * Copyright 2014 IBM Corp.
+ * Copyright IBM Corp. 2014, 2018
  * Author(s): Alexander Yarygin <yarygin@linux.vnet.ibm.com>
+ *	      Thomas Richter <tmricht@linux.vnet.ibm.com>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License (version 2 only)
@@ -13,16 +14,153 @@
 #include <unistd.h>
 #include <stdio.h>
 #include <string.h>
+#include <ctype.h>
 
 #include "../../util/header.h"
+#include "../../util/util.h"
+
+#define SYSINFO_MANU	"Manufacturer:"
+#define SYSINFO_TYPE	"Type:"
+#define SYSINFO_MODEL	"Model:"
+#define SRVLVL_CPUMF	"CPU-MF:"
+#define SRVLVL_VERSION	"version="
+#define SRVLVL_AUTHORIZATION	"authorization="
+#define SYSINFO		"/proc/sysinfo"
+#define SRVLVL		"/proc/service_levels"
 
 int get_cpuid(char *buffer, size_t sz)
 {
-	const char *cpuid = "IBM/S390";
+	char *cp, *line = NULL, *line2;
+	char type[8], model[33], version[8], manufacturer[32], authorization[8];
+	int tpsize = 0, mdsize = 0, vssize = 0, mfsize = 0, atsize = 0;
+	int read;
+	unsigned long line_sz;
+	size_t nbytes;
+	FILE *sysinfo;
+
+	/*
+	 * Scan /proc/sysinfo line by line and read out values for
+	 * Manufacturer:, Type: and Model:, for example:
+	 * Manufacturer:    IBM
+	 * Type:            2964
+	 * Model:           702              N96
+	 * The first word is the Model Capacity and the second word is
+	 * Model (can be omitted). Both words have a maximum size of 16
+	 * bytes.
+	 */
+	memset(manufacturer, 0, sizeof(manufacturer));
+	memset(type, 0, sizeof(type));
+	memset(model, 0, sizeof(model));
+	memset(version, 0, sizeof(version));
+	memset(authorization, 0, sizeof(authorization));
+
+	sysinfo = fopen(SYSINFO, "r");
+	if (sysinfo == NULL)
+		return -1;
+
+	while ((read = getline(&line, &line_sz, sysinfo)) != -1) {
+		if (!strncmp(line, SYSINFO_MANU, strlen(SYSINFO_MANU))) {
+			line2 = line + strlen(SYSINFO_MANU);
+
+			while ((cp = strtok_r(line2, "\n ", &line2))) {
+				mfsize += scnprintf(manufacturer + mfsize,
+						    sizeof(manufacturer) - mfsize, "%s", cp);
+			}
+		}
+
+		if (!strncmp(line, SYSINFO_TYPE, strlen(SYSINFO_TYPE))) {
+			line2 = line + strlen(SYSINFO_TYPE);
 
-	if (strlen(cpuid) + 1 > sz)
+			while ((cp = strtok_r(line2, "\n ", &line2))) {
+				tpsize += scnprintf(type + tpsize,
+						    sizeof(type) - tpsize, "%s", cp);
+			}
+		}
+
+		if (!strncmp(line, SYSINFO_MODEL, strlen(SYSINFO_MODEL))) {
+			line2 = line + strlen(SYSINFO_MODEL);
+
+			while ((cp = strtok_r(line2, "\n ", &line2))) {
+				mdsize += scnprintf(model + mdsize, sizeof(model) - mdsize,
+						    "%s%s", model[0] ? "," : "", cp);
+			}
+			break;
+		}
+	}
+	fclose(sysinfo);
+
+	/* Missing manufacturer, type or model information should not happen */
+	if (!manufacturer[0] || !type[0] || !model[0])
 		return -1;
 
-	strcpy(buffer, cpuid);
-	return 0;
+	/*
+	 * Scan /proc/service_levels and return the CPU-MF counter facility
+	 * version number and authorization level.
+	 * Optional, does not exist on z/VM guests.
+	 */
+	sysinfo = fopen(SRVLVL, "r");
+	if (sysinfo == NULL)
+		goto skip_sysinfo;
+	while ((read = getline(&line, &line_sz, sysinfo)) != -1) {
+		if (strncmp(line, SRVLVL_CPUMF, strlen(SRVLVL_CPUMF)))
+			continue;
+
+		line2 = line + strlen(SRVLVL_CPUMF);
+		while ((cp = strtok_r(line2, "\n ", &line2))) {
+			if (!strncmp(cp, SRVLVL_VERSION,
+				     strlen(SRVLVL_VERSION))) {
+				char *sep = strchr(cp, '=');
+
+				vssize += scnprintf(version + vssize,
+						    sizeof(version) - vssize, "%s", sep + 1);
+			}
+			if (!strncmp(cp, SRVLVL_AUTHORIZATION,
+				     strlen(SRVLVL_AUTHORIZATION))) {
+				char *sep = strchr(cp, '=');
+
+				atsize += scnprintf(authorization + atsize,
+						    sizeof(authorization) - atsize, "%s", sep + 1);
+			}
+		}
+	}
+	fclose(sysinfo);
+
+skip_sysinfo:
+	free(line);
+
+	if (version[0] && authorization[0] )
+		nbytes = snprintf(buffer, sz, "%s,%s,%s,%s,%s",
+				  manufacturer, type, model, version,
+				  authorization);
+	else
+		nbytes = snprintf(buffer, sz, "%s,%s,%s", manufacturer, type,
+				  model);
+	return (nbytes >= sz) ? -1 : 0;
+}
+
+char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
+{
+	char *buf = malloc(128);
+
+	if (buf && get_cpuid(buf, 128) < 0)
+		zfree(&buf);
+	return buf;
+}
+
+/*
+ * Compare the cpuid string returned by get_cpuid() function
+ * with the name generated by the jevents file read from
+ * pmu-events/arch/s390/mapfile.csv.
+ *
+ * Parameter mapcpuid is the cpuid as stored in the
+ * pmu-events/arch/s390/mapfile.csv. This is just the type number.
+ * Parameter cpuid is the cpuid returned by function get_cpuid().
+ */
+int strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
+{
+	char *cp = strchr(cpuid, ',');
+
+	if (cp == NULL)
+		return -1;
+	return strncmp(cp + 1, mapcpuid, strlen(mapcpuid));
 }
diff --git a/tools/perf/arch/x86/tests/perf-time-to-tsc.c b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
index 06abe8108b33..7a7721604b86 100644
--- a/tools/perf/arch/x86/tests/perf-time-to-tsc.c
+++ b/tools/perf/arch/x86/tests/perf-time-to-tsc.c
@@ -60,6 +60,7 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 	union perf_event *event;
 	u64 test_tsc, comm1_tsc, comm2_tsc;
 	u64 test_time, comm1_time = 0, comm2_time = 0;
+	struct perf_mmap *md;
 
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	CHECK_NOT_NULL__(threads);
@@ -109,7 +110,11 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 	perf_evlist__disable(evlist);
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
-		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+		md = &evlist->mmap[i];
+		if (perf_mmap__read_init(md) < 0)
+			continue;
+
+		while ((event = perf_mmap__read_event(md)) != NULL) {
 			struct perf_sample sample;
 
 			if (event->header.type != PERF_RECORD_COMM ||
@@ -128,8 +133,9 @@ int test__perf_time_to_tsc(struct test *test __maybe_unused, int subtest __maybe
 				comm2_time = sample.time;
 			}
 next_event:
-			perf_evlist__mmap_consume(evlist, i);
+			perf_mmap__consume(md);
 		}
+		perf_mmap__read_done(md);
 	}
 
 	if (!comm1_time || !comm2_time)
diff --git a/tools/perf/arch/x86/util/auxtrace.c b/tools/perf/arch/x86/util/auxtrace.c
index 6aa3f2a38321..b135af62011c 100644
--- a/tools/perf/arch/x86/util/auxtrace.c
+++ b/tools/perf/arch/x86/util/auxtrace.c
@@ -37,15 +37,11 @@ struct auxtrace_record *auxtrace_record__init_intel(struct perf_evlist *evlist,
 	intel_pt_pmu = perf_pmu__find(INTEL_PT_PMU_NAME);
 	intel_bts_pmu = perf_pmu__find(INTEL_BTS_PMU_NAME);
 
-	if (evlist) {
-		evlist__for_each_entry(evlist, evsel) {
-			if (intel_pt_pmu &&
-			    evsel->attr.type == intel_pt_pmu->type)
-				found_pt = true;
-			if (intel_bts_pmu &&
-			    evsel->attr.type == intel_bts_pmu->type)
-				found_bts = true;
-		}
+	evlist__for_each_entry(evlist, evsel) {
+		if (intel_pt_pmu && evsel->attr.type == intel_pt_pmu->type)
+			found_pt = true;
+		if (intel_bts_pmu && evsel->attr.type == intel_bts_pmu->type)
+			found_bts = true;
 	}
 
 	if (found_pt && found_bts) {
diff --git a/tools/perf/builtin-annotate.c b/tools/perf/builtin-annotate.c
index f15731a3d438..51709a961496 100644
--- a/tools/perf/builtin-annotate.c
+++ b/tools/perf/builtin-annotate.c
@@ -40,10 +40,11 @@
 struct perf_annotate {
 	struct perf_tool tool;
 	struct perf_session *session;
-	bool	   use_tui, use_stdio, use_gtk;
+	bool	   use_tui, use_stdio, use_stdio2, use_gtk;
 	bool	   full_paths;
 	bool	   print_line;
 	bool	   skip_missing;
+	bool	   has_br_stack;
 	const char *sym_hist_filter;
 	const char *cpu_list;
 	DECLARE_BITMAP(cpu_bitmap, MAX_NR_CPUS);
@@ -146,16 +147,78 @@ static void process_branch_stack(struct branch_stack *bs, struct addr_location *
 	free(bi);
 }
 
+static int hist_iter__branch_callback(struct hist_entry_iter *iter,
+				      struct addr_location *al __maybe_unused,
+				      bool single __maybe_unused,
+				      void *arg __maybe_unused)
+{
+	struct hist_entry *he = iter->he;
+	struct branch_info *bi;
+	struct perf_sample *sample = iter->sample;
+	struct perf_evsel *evsel = iter->evsel;
+	int err;
+
+	hist__account_cycles(sample->branch_stack, al, sample, false);
+
+	bi = he->branch_info;
+	err = addr_map_symbol__inc_samples(&bi->from, sample, evsel->idx);
+
+	if (err)
+		goto out;
+
+	err = addr_map_symbol__inc_samples(&bi->to, sample, evsel->idx);
+
+out:
+	return err;
+}
+
+static int process_branch_callback(struct perf_evsel *evsel,
+				   struct perf_sample *sample,
+				   struct addr_location *al __maybe_unused,
+				   struct perf_annotate *ann,
+				   struct machine *machine)
+{
+	struct hist_entry_iter iter = {
+		.evsel		= evsel,
+		.sample		= sample,
+		.add_entry_cb	= hist_iter__branch_callback,
+		.hide_unresolved	= symbol_conf.hide_unresolved,
+		.ops		= &hist_iter_branch,
+	};
+
+	struct addr_location a;
+	int ret;
+
+	if (machine__resolve(machine, &a, sample) < 0)
+		return -1;
+
+	if (a.sym == NULL)
+		return 0;
+
+	if (a.map != NULL)
+		a.map->dso->hit = 1;
+
+	ret = hist_entry_iter__add(&iter, &a, PERF_MAX_STACK_DEPTH, ann);
+	return ret;
+}
+
+static bool has_annotation(struct perf_annotate *ann)
+{
+	return ui__has_annotation() || ann->use_stdio2;
+}
+
 static int perf_evsel__add_sample(struct perf_evsel *evsel,
 				  struct perf_sample *sample,
 				  struct addr_location *al,
-				  struct perf_annotate *ann)
+				  struct perf_annotate *ann,
+				  struct machine *machine)
 {
 	struct hists *hists = evsel__hists(evsel);
 	struct hist_entry *he;
 	int ret;
 
-	if (ann->sym_hist_filter != NULL &&
+	if ((!ann->has_br_stack || !has_annotation(ann)) &&
+	    ann->sym_hist_filter != NULL &&
 	    (al->sym == NULL ||
 	     strcmp(ann->sym_hist_filter, al->sym->name) != 0)) {
 		/* We're only interested in a symbol named sym_hist_filter */
@@ -178,6 +241,9 @@ static int perf_evsel__add_sample(struct perf_evsel *evsel,
 	 */
 	process_branch_stack(sample->branch_stack, al, sample);
 
+	if (ann->has_br_stack && has_annotation(ann))
+		return process_branch_callback(evsel, sample, al, ann, machine);
+
 	he = hists__add_entry(hists, al, NULL, NULL, NULL, sample, true);
 	if (he == NULL)
 		return -ENOMEM;
@@ -206,7 +272,8 @@ static int process_sample_event(struct perf_tool *tool,
 	if (ann->cpu_list && !test_bit(sample->cpu, ann->cpu_bitmap))
 		goto out_put;
 
-	if (!al.filtered && perf_evsel__add_sample(evsel, sample, &al, ann)) {
+	if (!al.filtered &&
+	    perf_evsel__add_sample(evsel, sample, &al, ann, machine)) {
 		pr_warning("problem incrementing symbol count, "
 			   "skipping event\n");
 		ret = -1;
@@ -220,8 +287,11 @@ static int hist_entry__tty_annotate(struct hist_entry *he,
 				    struct perf_evsel *evsel,
 				    struct perf_annotate *ann)
 {
-	return symbol__tty_annotate(he->ms.sym, he->ms.map, evsel,
-				    ann->print_line, ann->full_paths, 0, 0);
+	if (!ann->use_stdio2)
+		return symbol__tty_annotate(he->ms.sym, he->ms.map, evsel,
+					    ann->print_line, ann->full_paths, 0, 0);
+	return symbol__tty_annotate2(he->ms.sym, he->ms.map, evsel,
+				     ann->print_line, ann->full_paths);
 }
 
 static void hists__find_annotations(struct hists *hists,
@@ -238,6 +308,10 @@ static void hists__find_annotations(struct hists *hists,
 		if (he->ms.sym == NULL || he->ms.map->dso->annotate_warned)
 			goto find_next;
 
+		if (ann->sym_hist_filter &&
+		    (strcmp(he->ms.sym->name, ann->sym_hist_filter) != 0))
+			goto find_next;
+
 		notes = symbol__annotation(he->ms.sym);
 		if (notes->src == NULL) {
 find_next:
@@ -269,6 +343,7 @@ find_next:
 			nd = rb_next(nd);
 		} else if (use_browser == 1) {
 			key = hist_entry__tui_annotate(he, evsel, NULL);
+
 			switch (key) {
 			case -1:
 				if (!ann->skip_missing)
@@ -420,6 +495,9 @@ int cmd_annotate(int argc, const char **argv)
 	OPT_BOOLEAN(0, "gtk", &annotate.use_gtk, "Use the GTK interface"),
 	OPT_BOOLEAN(0, "tui", &annotate.use_tui, "Use the TUI interface"),
 	OPT_BOOLEAN(0, "stdio", &annotate.use_stdio, "Use the stdio interface"),
+	OPT_BOOLEAN(0, "stdio2", &annotate.use_stdio2, "Use the stdio interface"),
+	OPT_BOOLEAN(0, "ignore-vmlinux", &symbol_conf.ignore_vmlinux,
+                    "don't load vmlinux even if found"),
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
 	OPT_BOOLEAN('m', "modules", &symbol_conf.use_modules,
@@ -489,20 +567,22 @@ int cmd_annotate(int argc, const char **argv)
 	if (annotate.session == NULL)
 		return -1;
 
+	annotate.has_br_stack = perf_header__has_feat(&annotate.session->header,
+						      HEADER_BRANCH_STACK);
+
 	ret = symbol__annotation_init();
 	if (ret < 0)
 		goto out_delete;
 
+	annotation_config__init();
+
 	symbol_conf.try_vmlinux_path = true;
 
 	ret = symbol__init(&annotate.session->header.env);
 	if (ret < 0)
 		goto out_delete;
 
-	if (setup_sorting(NULL) < 0)
-		usage_with_options(annotate_usage, options);
-
-	if (annotate.use_stdio)
+	if (annotate.use_stdio || annotate.use_stdio2)
 		use_browser = 0;
 	else if (annotate.use_tui)
 		use_browser = 1;
@@ -511,6 +591,15 @@ int cmd_annotate(int argc, const char **argv)
 
 	setup_browser(true);
 
+	if ((use_browser == 1 || annotate.use_stdio2) && annotate.has_br_stack) {
+		sort__mode = SORT_MODE__BRANCH;
+		if (setup_sorting(annotate.session->evlist) < 0)
+			usage_with_options(annotate_usage, options);
+	} else {
+		if (setup_sorting(NULL) < 0)
+			usage_with_options(annotate_usage, options);
+	}
+
 	ret = __cmd_annotate(&annotate);
 
 out_delete:
diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
index 539c3d460158..2126bfbcb385 100644
--- a/tools/perf/builtin-c2c.c
+++ b/tools/perf/builtin-c2c.c
@@ -32,6 +32,7 @@
 #include "evsel.h"
 #include "ui/browsers/hists.h"
 #include "thread.h"
+#include "mem2node.h"
 
 struct c2c_hists {
 	struct hists		hists;
@@ -49,6 +50,7 @@ struct c2c_hist_entry {
 	struct c2c_hists	*hists;
 	struct c2c_stats	 stats;
 	unsigned long		*cpuset;
+	unsigned long		*nodeset;
 	struct c2c_stats	*node_stats;
 	unsigned int		 cacheline_idx;
 
@@ -59,6 +61,11 @@ struct c2c_hist_entry {
 	 * because of its callchain dynamic entry
 	 */
 	struct hist_entry	he;
+
+	unsigned long		 paddr;
+	unsigned long		 paddr_cnt;
+	bool			 paddr_zero;
+	char			*nodestr;
 };
 
 static char const *coalesce_default = "pid,iaddr";
@@ -66,6 +73,7 @@ static char const *coalesce_default = "pid,iaddr";
 struct perf_c2c {
 	struct perf_tool	tool;
 	struct c2c_hists	hists;
+	struct mem2node		mem2node;
 
 	unsigned long		**nodes;
 	int			 nodes_cnt;
@@ -123,6 +131,10 @@ static void *c2c_he_zalloc(size_t size)
 	if (!c2c_he->cpuset)
 		return NULL;
 
+	c2c_he->nodeset = bitmap_alloc(c2c.nodes_cnt);
+	if (!c2c_he->nodeset)
+		return NULL;
+
 	c2c_he->node_stats = zalloc(c2c.nodes_cnt * sizeof(*c2c_he->node_stats));
 	if (!c2c_he->node_stats)
 		return NULL;
@@ -145,6 +157,8 @@ static void c2c_he_free(void *he)
 	}
 
 	free(c2c_he->cpuset);
+	free(c2c_he->nodeset);
+	free(c2c_he->nodestr);
 	free(c2c_he->node_stats);
 	free(c2c_he);
 }
@@ -194,6 +208,28 @@ static void c2c_he__set_cpu(struct c2c_hist_entry *c2c_he,
 	set_bit(sample->cpu, c2c_he->cpuset);
 }
 
+static void c2c_he__set_node(struct c2c_hist_entry *c2c_he,
+			     struct perf_sample *sample)
+{
+	int node;
+
+	if (!sample->phys_addr) {
+		c2c_he->paddr_zero = true;
+		return;
+	}
+
+	node = mem2node__node(&c2c.mem2node, sample->phys_addr);
+	if (WARN_ONCE(node < 0, "WARNING: failed to find node\n"))
+		return;
+
+	set_bit(node, c2c_he->nodeset);
+
+	if (c2c_he->paddr != sample->phys_addr) {
+		c2c_he->paddr_cnt++;
+		c2c_he->paddr = sample->phys_addr;
+	}
+}
+
 static void compute_stats(struct c2c_hist_entry *c2c_he,
 			  struct c2c_stats *stats,
 			  u64 weight)
@@ -237,9 +273,12 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 	if (mi == NULL)
 		return -ENOMEM;
 
-	mi_dup = memdup(mi, sizeof(*mi));
-	if (!mi_dup)
-		goto free_mi;
+	/*
+	 * The mi object is released in hists__add_entry_ops,
+	 * if it gets sorted out into existing data, so we need
+	 * to take the copy now.
+	 */
+	mi_dup = mem_info__get(mi);
 
 	c2c_decode_stats(&stats, mi);
 
@@ -247,13 +286,14 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 				  &al, NULL, NULL, mi,
 				  sample, true);
 	if (he == NULL)
-		goto free_mi_dup;
+		goto free_mi;
 
 	c2c_he = container_of(he, struct c2c_hist_entry, he);
 	c2c_add_stats(&c2c_he->stats, &stats);
 	c2c_add_stats(&c2c_hists->stats, &stats);
 
 	c2c_he__set_cpu(c2c_he, sample);
+	c2c_he__set_node(c2c_he, sample);
 
 	hists__inc_nr_samples(&c2c_hists->hists, he->filtered);
 	ret = hist_entry__append_callchain(he, sample);
@@ -272,19 +312,15 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 
 		mi = mi_dup;
 
-		mi_dup = memdup(mi, sizeof(*mi));
-		if (!mi_dup)
-			goto free_mi;
-
 		c2c_hists = he__get_c2c_hists(he, c2c.cl_sort, 2);
 		if (!c2c_hists)
-			goto free_mi_dup;
+			goto free_mi;
 
 		he = hists__add_entry_ops(&c2c_hists->hists, &c2c_entry_ops,
 					  &al, NULL, NULL, mi,
 					  sample, true);
 		if (he == NULL)
-			goto free_mi_dup;
+			goto free_mi;
 
 		c2c_he = container_of(he, struct c2c_hist_entry, he);
 		c2c_add_stats(&c2c_he->stats, &stats);
@@ -294,6 +330,7 @@ static int process_sample_event(struct perf_tool *tool __maybe_unused,
 		compute_stats(c2c_he, &stats, sample->weight);
 
 		c2c_he__set_cpu(c2c_he, sample);
+		c2c_he__set_node(c2c_he, sample);
 
 		hists__inc_nr_samples(&c2c_hists->hists, he->filtered);
 		ret = hist_entry__append_callchain(he, sample);
@@ -303,10 +340,9 @@ out:
 	addr_location__put(&al);
 	return ret;
 
-free_mi_dup:
-	free(mi_dup);
 free_mi:
-	free(mi);
+	mem_info__put(mi_dup);
+	mem_info__put(mi);
 	ret = -ENOMEM;
 	goto out;
 }
@@ -457,6 +493,31 @@ static int dcacheline_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	return scnprintf(hpp->buf, hpp->size, "%*s", width, HEX_STR(buf, addr));
 }
 
+static int
+dcacheline_node_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		      struct hist_entry *he)
+{
+	struct c2c_hist_entry *c2c_he;
+	int width = c2c_width(fmt, hpp, he->hists);
+
+	c2c_he = container_of(he, struct c2c_hist_entry, he);
+	if (WARN_ON_ONCE(!c2c_he->nodestr))
+		return 0;
+
+	return scnprintf(hpp->buf, hpp->size, "%*s", width, c2c_he->nodestr);
+}
+
+static int
+dcacheline_node_count(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
+		      struct hist_entry *he)
+{
+	struct c2c_hist_entry *c2c_he;
+	int width = c2c_width(fmt, hpp, he->hists);
+
+	c2c_he = container_of(he, struct c2c_hist_entry, he);
+	return scnprintf(hpp->buf, hpp->size, "%*lu", width, c2c_he->paddr_cnt);
+}
+
 static int offset_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 			struct hist_entry *he)
 {
@@ -1202,23 +1263,47 @@ cl_idx_empty_entry(struct perf_hpp_fmt *fmt, struct perf_hpp *hpp,
 	}
 
 static struct c2c_dimension dim_dcacheline = {
-	.header		= HEADER_LOW("Cacheline"),
+	.header		= HEADER_SPAN("--- Cacheline ----", "Address", 2),
 	.name		= "dcacheline",
 	.cmp		= dcacheline_cmp,
 	.entry		= dcacheline_entry,
 	.width		= 18,
 };
 
-static struct c2c_header header_offset_tui = HEADER_LOW("Off");
+static struct c2c_dimension dim_dcacheline_node = {
+	.header		= HEADER_LOW("Node"),
+	.name		= "dcacheline_node",
+	.cmp		= empty_cmp,
+	.entry		= dcacheline_node_entry,
+	.width		= 4,
+};
+
+static struct c2c_dimension dim_dcacheline_count = {
+	.header		= HEADER_LOW("PA cnt"),
+	.name		= "dcacheline_count",
+	.cmp		= empty_cmp,
+	.entry		= dcacheline_node_count,
+	.width		= 6,
+};
+
+static struct c2c_header header_offset_tui = HEADER_SPAN("-----", "Off", 2);
 
 static struct c2c_dimension dim_offset = {
-	.header		= HEADER_BOTH("Data address", "Offset"),
+	.header		= HEADER_SPAN("--- Data address -", "Offset", 2),
 	.name		= "offset",
 	.cmp		= offset_cmp,
 	.entry		= offset_entry,
 	.width		= 18,
 };
 
+static struct c2c_dimension dim_offset_node = {
+	.header		= HEADER_LOW("Node"),
+	.name		= "offset_node",
+	.cmp		= empty_cmp,
+	.entry		= dcacheline_node_entry,
+	.width		= 4,
+};
+
 static struct c2c_dimension dim_iaddr = {
 	.header		= HEADER_LOW("Code address"),
 	.name		= "iaddr",
@@ -1538,7 +1623,10 @@ static struct c2c_dimension dim_dcacheline_num_empty = {
 
 static struct c2c_dimension *dimensions[] = {
 	&dim_dcacheline,
+	&dim_dcacheline_node,
+	&dim_dcacheline_count,
 	&dim_offset,
+	&dim_offset_node,
 	&dim_iaddr,
 	&dim_tot_hitm,
 	&dim_lcl_hitm,
@@ -1841,20 +1929,56 @@ static inline int valid_hitm_or_store(struct hist_entry *he)
 	return has_hitm || c2c_he->stats.store;
 }
 
-static void calc_width(struct hist_entry *he)
+static void set_node_width(struct c2c_hist_entry *c2c_he, int len)
+{
+	struct c2c_dimension *dim;
+
+	dim = &c2c.hists == c2c_he->hists ?
+	      &dim_dcacheline_node : &dim_offset_node;
+
+	if (len > dim->width)
+		dim->width = len;
+}
+
+static int set_nodestr(struct c2c_hist_entry *c2c_he)
+{
+	char buf[30];
+	int len;
+
+	if (c2c_he->nodestr)
+		return 0;
+
+	if (bitmap_weight(c2c_he->nodeset, c2c.nodes_cnt)) {
+		len = bitmap_scnprintf(c2c_he->nodeset, c2c.nodes_cnt,
+				      buf, sizeof(buf));
+	} else {
+		len = scnprintf(buf, sizeof(buf), "N/A");
+	}
+
+	set_node_width(c2c_he, len);
+	c2c_he->nodestr = strdup(buf);
+	return c2c_he->nodestr ? 0 : -ENOMEM;
+}
+
+static void calc_width(struct c2c_hist_entry *c2c_he)
 {
 	struct c2c_hists *c2c_hists;
 
-	c2c_hists = container_of(he->hists, struct c2c_hists, hists);
-	hists__calc_col_len(&c2c_hists->hists, he);
+	c2c_hists = container_of(c2c_he->he.hists, struct c2c_hists, hists);
+	hists__calc_col_len(&c2c_hists->hists, &c2c_he->he);
+	set_nodestr(c2c_he);
 }
 
 static int filter_cb(struct hist_entry *he)
 {
+	struct c2c_hist_entry *c2c_he;
+
+	c2c_he = container_of(he, struct c2c_hist_entry, he);
+
 	if (c2c.show_src && !he->srcline)
 		he->srcline = hist_entry__get_srcline(he);
 
-	calc_width(he);
+	calc_width(c2c_he);
 
 	if (!valid_hitm_or_store(he))
 		he->filtered = HIST_FILTER__C2C;
@@ -1871,12 +1995,11 @@ static int resort_cl_cb(struct hist_entry *he)
 	c2c_he = container_of(he, struct c2c_hist_entry, he);
 	c2c_hists = c2c_he->hists;
 
-	calc_width(he);
-
 	if (display && c2c_hists) {
 		static unsigned int idx;
 
 		c2c_he->cacheline_idx = idx++;
+		calc_width(c2c_he);
 
 		c2c_hists__reinit(c2c_hists, c2c.cl_output, c2c.cl_resort);
 
@@ -2350,14 +2473,66 @@ static void perf_c2c_display(struct perf_session *session)
 }
 #endif /* HAVE_SLANG_SUPPORT */
 
-static void ui_quirks(void)
+static char *fill_line(const char *orig, int len)
+{
+	int i, j, olen = strlen(orig);
+	char *buf;
+
+	buf = zalloc(len + 1);
+	if (!buf)
+		return NULL;
+
+	j = len / 2 - olen / 2;
+
+	for (i = 0; i < j - 1; i++)
+		buf[i] = '-';
+
+	buf[i++] = ' ';
+
+	strcpy(buf + i, orig);
+
+	i += olen;
+
+	buf[i++] = ' ';
+
+	for (; i < len; i++)
+		buf[i] = '-';
+
+	return buf;
+}
+
+static int ui_quirks(void)
 {
+	const char *nodestr = "Data address";
+	char *buf;
+
 	if (!c2c.use_stdio) {
 		dim_offset.width  = 5;
 		dim_offset.header = header_offset_tui;
+		nodestr = "CL";
 	}
 
 	dim_percent_hitm.header = percent_hitm_header[c2c.display];
+
+	/* Fix the zero line for dcacheline column. */
+	buf = fill_line("Cacheline", dim_dcacheline.width +
+				     dim_dcacheline_node.width +
+				     dim_dcacheline_count.width + 4);
+	if (!buf)
+		return -ENOMEM;
+
+	dim_dcacheline.header.line[0].text = buf;
+
+	/* Fix the zero line for offset column. */
+	buf = fill_line(nodestr, dim_offset.width +
+			         dim_offset_node.width +
+				 dim_dcacheline_count.width + 4);
+	if (!buf)
+		return -ENOMEM;
+
+	dim_offset.header.line[0].text = buf;
+
+	return 0;
 }
 
 #define CALLCHAIN_DEFAULT_OPT  "graph,0.5,caller,function,percent"
@@ -2473,7 +2648,7 @@ static int build_cl_output(char *cl_sort, bool no_source)
 		"percent_lcl_hitm,"
 		"percent_stores_l1hit,"
 		"percent_stores_l1miss,"
-		"offset,",
+		"offset,offset_node,dcacheline_count,",
 		add_pid   ? "pid," : "",
 		add_tid   ? "tid," : "",
 		add_iaddr ? "iaddr," : "",
@@ -2602,17 +2777,21 @@ static int perf_c2c__report(int argc, const char **argv)
 		goto out;
 	}
 
-	err = setup_callchain(session->evlist);
+	err = mem2node__init(&c2c.mem2node, &session->header.env);
 	if (err)
 		goto out_session;
 
+	err = setup_callchain(session->evlist);
+	if (err)
+		goto out_mem2node;
+
 	if (symbol__init(&session->header.env) < 0)
-		goto out_session;
+		goto out_mem2node;
 
 	/* No pipe support at the moment. */
 	if (perf_data__is_pipe(session->data)) {
 		pr_debug("No pipe support at the moment.\n");
-		goto out_session;
+		goto out_mem2node;
 	}
 
 	if (c2c.use_stdio)
@@ -2625,12 +2804,14 @@ static int perf_c2c__report(int argc, const char **argv)
 	err = perf_session__process_events(session);
 	if (err) {
 		pr_err("failed to process sample\n");
-		goto out_session;
+		goto out_mem2node;
 	}
 
 	c2c_hists__reinit(&c2c.hists,
 			"cl_idx,"
 			"dcacheline,"
+			"dcacheline_node,"
+			"dcacheline_count,"
 			"tot_recs,"
 			"percent_hitm,"
 			"tot_hitm,lcl_hitm,rmt_hitm,"
@@ -2652,10 +2833,15 @@ static int perf_c2c__report(int argc, const char **argv)
 
 	ui_progress__finish();
 
-	ui_quirks();
+	if (ui_quirks()) {
+		pr_err("failed to setup UI\n");
+		goto out_mem2node;
+	}
 
 	perf_c2c_display(session);
 
+out_mem2node:
+	mem2node__exit(&c2c.mem2node);
 out_session:
 	perf_session__delete(session);
 out:
@@ -2706,7 +2892,7 @@ static int perf_c2c__record(int argc, const char **argv)
 	argc = parse_options(argc, argv, options, record_mem_usage,
 			     PARSE_OPT_KEEP_UNKNOWN);
 
-	rec_argc = argc + 10; /* max number of arguments */
+	rec_argc = argc + 11; /* max number of arguments */
 	rec_argv = calloc(rec_argc + 1, sizeof(char *));
 	if (!rec_argv)
 		return -1;
@@ -2722,6 +2908,7 @@ static int perf_c2c__record(int argc, const char **argv)
 		rec_argv[i++] = "-W";
 
 	rec_argv[i++] = "-d";
+	rec_argv[i++] = "--phys-data";
 	rec_argv[i++] = "--sample-cpu";
 
 	for (j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
diff --git a/tools/perf/builtin-ftrace.c b/tools/perf/builtin-ftrace.c
index 25a42acabee1..f42f228e8899 100644
--- a/tools/perf/builtin-ftrace.c
+++ b/tools/perf/builtin-ftrace.c
@@ -72,6 +72,7 @@ static int __write_tracing_file(const char *name, const char *val, bool append)
 	ssize_t size = strlen(val);
 	int flags = O_WRONLY;
 	char errbuf[512];
+	char *val_copy;
 
 	file = get_tracing_file(name);
 	if (!file) {
@@ -91,12 +92,23 @@ static int __write_tracing_file(const char *name, const char *val, bool append)
 		goto out;
 	}
 
-	if (write(fd, val, size) == size)
+	/*
+	 * Copy the original value and append a '\n'. Without this,
+	 * the kernel can hide possible errors.
+	 */
+	val_copy = strdup(val);
+	if (!val_copy)
+		goto out_close;
+	val_copy[size] = '\n';
+
+	if (write(fd, val_copy, size + 1) == size + 1)
 		ret = 0;
 	else
 		pr_debug("write '%s' to tracing/%s failed: %s\n",
 			 val, name, str_error_r(errno, errbuf, sizeof(errbuf)));
 
+	free(val_copy);
+out_close:
 	close(fd);
 out:
 	put_tracing_file(file);
@@ -280,8 +292,10 @@ static int __cmd_ftrace(struct perf_ftrace *ftrace, int argc, const char **argv)
 	signal(SIGCHLD, sig_handler);
 	signal(SIGPIPE, sig_handler);
 
-	if (reset_tracing_files(ftrace) < 0)
+	if (reset_tracing_files(ftrace) < 0) {
+		pr_err("failed to reset ftrace\n");
 		goto out;
+	}
 
 	/* reset ftrace buffer */
 	if (write_tracing_file("trace", "0") < 0)
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 55d919dc5bc6..72e2ca096bf5 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -743,16 +743,23 @@ static bool verify_vcpu(int vcpu)
 static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 				   u64 *mmap_time)
 {
+	struct perf_evlist *evlist = kvm->evlist;
 	union perf_event *event;
+	struct perf_mmap *md;
 	u64 timestamp;
 	s64 n = 0;
 	int err;
 
 	*mmap_time = ULLONG_MAX;
-	while ((event = perf_evlist__mmap_read(kvm->evlist, idx)) != NULL) {
-		err = perf_evlist__parse_sample_timestamp(kvm->evlist, event, &timestamp);
+	md = &evlist->mmap[idx];
+	err = perf_mmap__read_init(md);
+	if (err < 0)
+		return (err == -EAGAIN) ? 0 : -1;
+
+	while ((event = perf_mmap__read_event(md)) != NULL) {
+		err = perf_evlist__parse_sample_timestamp(evlist, event, &timestamp);
 		if (err) {
-			perf_evlist__mmap_consume(kvm->evlist, idx);
+			perf_mmap__consume(md);
 			pr_err("Failed to parse sample\n");
 			return -1;
 		}
@@ -762,7 +769,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 		 * FIXME: Here we can't consume the event, as perf_session__queue_event will
 		 *        point to it, and it'll get possibly overwritten by the kernel.
 		 */
-		perf_evlist__mmap_consume(kvm->evlist, idx);
+		perf_mmap__consume(md);
 
 		if (err) {
 			pr_err("Failed to enqueue sample: %d\n", err);
@@ -779,6 +786,7 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
 			break;
 	}
 
+	perf_mmap__read_done(md);
 	return n;
 }
 
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index a217623fec2e..22ebeb92ac51 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -45,6 +45,7 @@
 
 #include <errno.h>
 #include <inttypes.h>
+#include <locale.h>
 #include <poll.h>
 #include <unistd.h>
 #include <sched.h>
@@ -70,7 +71,6 @@ struct record {
 	struct auxtrace_record	*itr;
 	struct perf_evlist	*evlist;
 	struct perf_session	*session;
-	const char		*progname;
 	int			realtime_prio;
 	bool			no_buildid;
 	bool			no_buildid_set;
@@ -273,6 +273,24 @@ static void record__read_auxtrace_snapshot(struct record *rec)
 	}
 }
 
+static int record__auxtrace_init(struct record *rec)
+{
+	int err;
+
+	if (!rec->itr) {
+		rec->itr = auxtrace_record__init(rec->evlist, &err);
+		if (err)
+			return err;
+	}
+
+	err = auxtrace_parse_snapshot_options(rec->itr, &rec->opts,
+					      rec->opts.auxtrace_snapshot_opts);
+	if (err)
+		return err;
+
+	return auxtrace_parse_filters(rec->evlist);
+}
+
 #else
 
 static inline
@@ -293,6 +311,11 @@ int auxtrace_record__snapshot_start(struct auxtrace_record *itr __maybe_unused)
 	return 0;
 }
 
+static int record__auxtrace_init(struct record *rec __maybe_unused)
+{
+	return 0;
+}
+
 #endif
 
 static int record__mmap_evlist(struct record *rec,
@@ -509,7 +532,7 @@ static int record__mmap_read_evlist(struct record *rec, struct perf_evlist *evli
 		struct auxtrace_mmap *mm = &maps[i].auxtrace_mmap;
 
 		if (maps[i].base) {
-			if (perf_mmap__push(&maps[i], overwrite, rec, record__pushfn) != 0) {
+			if (perf_mmap__push(&maps[i], rec, record__pushfn) != 0) {
 				rc = -1;
 				goto out;
 			}
@@ -731,13 +754,10 @@ static int record__synthesize(struct record *rec, bool tail)
 		return 0;
 
 	if (data->is_pipe) {
-		err = perf_event__synthesize_features(
-			tool, session, rec->evlist, process_synthesized_event);
-		if (err < 0) {
-			pr_err("Couldn't synthesize features.\n");
-			return err;
-		}
-
+		/*
+		 * We need to synthesize events first, because some
+		 * features works on top of them (on report side).
+		 */
 		err = perf_event__synthesize_attrs(tool, session,
 						   process_synthesized_event);
 		if (err < 0) {
@@ -745,6 +765,13 @@ static int record__synthesize(struct record *rec, bool tail)
 			goto out;
 		}
 
+		err = perf_event__synthesize_features(tool, session, rec->evlist,
+						      process_synthesized_event);
+		if (err < 0) {
+			pr_err("Couldn't synthesize features.\n");
+			return err;
+		}
+
 		if (have_tracepoints(&rec->evlist->entries)) {
 			/*
 			 * FIXME err <= 0 here actually means that
@@ -830,7 +857,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	int status = 0;
 	unsigned long waking = 0;
 	const bool forks = argc > 0;
-	struct machine *machine;
 	struct perf_tool *tool = &rec->tool;
 	struct record_opts *opts = &rec->opts;
 	struct perf_data *data = &rec->data;
@@ -838,8 +864,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	bool disabled = false, draining = false;
 	int fd;
 
-	rec->progname = argv[0];
-
 	atexit(record__sig_exit);
 	signal(SIGCHLD, sig_handler);
 	signal(SIGINT, sig_handler);
@@ -935,8 +959,6 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 		goto out_child;
 	}
 
-	machine = &session->machines.host;
-
 	err = record__synthesize(rec, false);
 	if (err < 0)
 		goto out_child;
@@ -964,6 +986,7 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
 	 * Let the child rip
 	 */
 	if (forks) {
+		struct machine *machine = &session->machines.host;
 		union perf_event *event;
 		pid_t tgid;
 
@@ -1260,10 +1283,12 @@ static int perf_record_config(const char *var, const char *value, void *cb)
 			return -1;
 		return 0;
 	}
-	if (!strcmp(var, "record.call-graph"))
-		var = "call-graph.record-mode"; /* fall-through */
+	if (!strcmp(var, "record.call-graph")) {
+		var = "call-graph.record-mode";
+		return perf_default_config(var, value, cb);
+	}
 
-	return perf_default_config(var, value, cb);
+	return 0;
 }
 
 struct clockid_map {
@@ -1551,7 +1576,11 @@ static struct option __record_options[] = {
 	OPT_BOOLEAN(0, "tail-synthesize", &record.opts.tail_synthesize,
 		    "synthesize non-sample events at the end of output"),
 	OPT_BOOLEAN(0, "overwrite", &record.opts.overwrite, "use overwrite mode"),
-	OPT_UINTEGER('F', "freq", &record.opts.user_freq, "profile at this frequency"),
+	OPT_BOOLEAN(0, "strict-freq", &record.opts.strict_freq,
+		    "Fail if the specified frequency can't be used"),
+	OPT_CALLBACK('F', "freq", &record.opts, "freq or 'max'",
+		     "profile at this frequency",
+		      record__parse_freq),
 	OPT_CALLBACK('m', "mmap-pages", &record.opts, "pages[,pages]",
 		     "number of mmap data pages and AUX area tracing mmap pages",
 		     record__parse_mmap_pages),
@@ -1660,6 +1689,8 @@ int cmd_record(int argc, const char **argv)
 	struct record *rec = &record;
 	char errbuf[BUFSIZ];
 
+	setlocale(LC_ALL, "");
+
 #ifndef HAVE_LIBBPF_SUPPORT
 # define set_nobuild(s, l, c) set_option_nobuild(record_options, s, l, "NO_LIBBPF=1", c)
 	set_nobuild('\0', "clang-path", true);
@@ -1720,17 +1751,6 @@ int cmd_record(int argc, const char **argv)
 		alarm(rec->switch_output.time);
 	}
 
-	if (!rec->itr) {
-		rec->itr = auxtrace_record__init(rec->evlist, &err);
-		if (err)
-			goto out;
-	}
-
-	err = auxtrace_parse_snapshot_options(rec->itr, &rec->opts,
-					      rec->opts.auxtrace_snapshot_opts);
-	if (err)
-		goto out;
-
 	/*
 	 * Allow aliases to facilitate the lookup of symbols for address
 	 * filters. Refer to auxtrace_parse_filters().
@@ -1739,7 +1759,7 @@ int cmd_record(int argc, const char **argv)
 
 	symbol__init(NULL);
 
-	err = auxtrace_parse_filters(rec->evlist);
+	err = record__auxtrace_init(rec);
 	if (err)
 		goto out;
 
@@ -1812,7 +1832,7 @@ int cmd_record(int argc, const char **argv)
 	err = target__validate(&rec->opts.target);
 	if (err) {
 		target__strerror(&rec->opts.target, err, errbuf, BUFSIZ);
-		ui__warning("%s", errbuf);
+		ui__warning("%s\n", errbuf);
 	}
 
 	err = target__parse_uid(&rec->opts.target);
diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
index 4ad5dc649716..0f198f6d9b77 100644
--- a/tools/perf/builtin-report.c
+++ b/tools/perf/builtin-report.c
@@ -68,6 +68,7 @@ struct report {
 	bool			header;
 	bool			header_only;
 	bool			nonany_branch_mode;
+	bool			group_set;
 	int			max_stack;
 	struct perf_read_values	show_threads_values;
 	const char		*pretty_printing_style;
@@ -193,6 +194,45 @@ out:
 	return err;
 }
 
+/*
+ * Events in data file are not collect in groups, but we still want
+ * the group display. Set the artificial group and set the leader's
+ * forced_leader flag to notify the display code.
+ */
+static void setup_forced_leader(struct report *report,
+				struct perf_evlist *evlist)
+{
+	if (report->group_set && !evlist->nr_groups) {
+		struct perf_evsel *leader = perf_evlist__first(evlist);
+
+		perf_evlist__set_leader(evlist);
+		leader->forced_leader = true;
+	}
+}
+
+static int process_feature_event(struct perf_tool *tool,
+				 union perf_event *event,
+				 struct perf_session *session __maybe_unused)
+{
+	struct report *rep = container_of(tool, struct report, tool);
+
+	if (event->feat.feat_id < HEADER_LAST_FEATURE)
+		return perf_event__process_feature(tool, event, session);
+
+	if (event->feat.feat_id != HEADER_LAST_FEATURE) {
+		pr_err("failed: wrong feature ID: %" PRIu64 "\n",
+		       event->feat.feat_id);
+		return -1;
+	}
+
+	/*
+	 * All features are received, we can force the
+	 * group if needed.
+	 */
+	setup_forced_leader(rep, session->evlist);
+	return 0;
+}
+
 static int process_sample_event(struct perf_tool *tool,
 				union perf_event *event,
 				struct perf_sample *sample,
@@ -400,8 +440,10 @@ static size_t hists__fprintf_nr_sample_events(struct hists *hists, struct report
 
 	nr_samples = convert_unit(nr_samples, &unit);
 	ret = fprintf(fp, "# Samples: %lu%c", nr_samples, unit);
-	if (evname != NULL)
-		ret += fprintf(fp, " of event '%s'", evname);
+	if (evname != NULL) {
+		ret += fprintf(fp, " of event%s '%s'",
+			       evsel->nr_members > 1 ? "s" : "", evname);
+	}
 
 	if (rep->time_str)
 		ret += fprintf(fp, " (time slices: %s)", rep->time_str);
@@ -614,6 +656,7 @@ static int stats_print(struct report *rep)
 static void tasks_setup(struct report *rep)
 {
 	memset(&rep->tool, 0, sizeof(rep->tool));
+	rep->tool.ordered_events = true;
 	if (rep->mmaps_mode) {
 		rep->tool.mmap = perf_event__process_mmap;
 		rep->tool.mmap2 = perf_event__process_mmap2;
@@ -954,7 +997,7 @@ int cmd_report(int argc, const char **argv)
 			.id_index	 = perf_event__process_id_index,
 			.auxtrace_info	 = perf_event__process_auxtrace_info,
 			.auxtrace	 = perf_event__process_auxtrace,
-			.feature	 = perf_event__process_feature,
+			.feature	 = process_feature_event,
 			.ordered_events	 = true,
 			.ordering_requires_timestamps = true,
 		},
@@ -975,6 +1018,8 @@ int cmd_report(int argc, const char **argv)
 	OPT_BOOLEAN(0, "mmaps", &report.mmaps_mode, "Display recorded tasks memory maps"),
 	OPT_STRING('k', "vmlinux", &symbol_conf.vmlinux_name,
 		   "file", "vmlinux pathname"),
+	OPT_BOOLEAN(0, "ignore-vmlinux", &symbol_conf.ignore_vmlinux,
+                    "don't load vmlinux even if found"),
 	OPT_STRING(0, "kallsyms", &symbol_conf.kallsyms_name,
 		   "file", "kallsyms pathname"),
 	OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
@@ -1056,7 +1101,7 @@ int cmd_report(int argc, const char **argv)
 		   "Specify disassembler style (e.g. -M intel for intel syntax)"),
 	OPT_BOOLEAN(0, "show-total-period", &symbol_conf.show_total_period,
 		    "Show a column with the sum of periods"),
-	OPT_BOOLEAN(0, "group", &symbol_conf.event_group,
+	OPT_BOOLEAN_SET(0, "group", &symbol_conf.event_group, &report.group_set,
 		    "Show event group information together"),
 	OPT_CALLBACK_NOOPT('b', "branch-stack", &branch_mode, "",
 		    "use branch records for per branch histogram filling",
@@ -1173,6 +1218,8 @@ repeat:
 	has_br_stack = perf_header__has_feat(&session->header,
 					     HEADER_BRANCH_STACK);
 
+	setup_forced_leader(&report, session->evlist);
+
 	if (itrace_synth_opts.last_branch)
 		has_br_stack = true;
 
@@ -1295,6 +1342,7 @@ repeat:
 			symbol_conf.priv_size += sizeof(u32);
 			symbol_conf.sort_by_name = true;
 		}
+		annotation_config__init();
 	}
 
 	if (symbol__init(&session->header.env) < 0)
@@ -1332,6 +1380,15 @@ repeat:
 		report.range_num = 1;
 	}
 
+	if (session->tevent.pevent &&
+	    pevent_set_function_resolver(session->tevent.pevent,
+					 machine__resolve_kernel_addr,
+					 &session->machines.host) < 0) {
+		pr_err("%s: failed to set libtraceevent function resolver\n",
+		       __func__);
+		return -1;
+	}
+
 	sort__setup_elide(stdout);
 
 	ret = __cmd_report(&report);
diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
index 83283fedb00f..4dfdee668b0c 100644
--- a/tools/perf/builtin-sched.c
+++ b/tools/perf/builtin-sched.c
@@ -254,6 +254,10 @@ struct thread_runtime {
 	u64 total_delay_time;
 
 	int last_state;
+
+	char shortname[3];
+	bool comm_changed;
+
 	u64 migrations;
 };
 
@@ -897,6 +901,37 @@ struct sort_dimension {
 	struct list_head	list;
 };
 
+/*
+ * handle runtime stats saved per thread
+ */
+static struct thread_runtime *thread__init_runtime(struct thread *thread)
+{
+	struct thread_runtime *r;
+
+	r = zalloc(sizeof(struct thread_runtime));
+	if (!r)
+		return NULL;
+
+	init_stats(&r->run_stats);
+	thread__set_priv(thread, r);
+
+	return r;
+}
+
+static struct thread_runtime *thread__get_runtime(struct thread *thread)
+{
+	struct thread_runtime *tr;
+
+	tr = thread__priv(thread);
+	if (tr == NULL) {
+		tr = thread__init_runtime(thread);
+		if (tr == NULL)
+			pr_debug("Failed to malloc memory for runtime data.\n");
+	}
+
+	return tr;
+}
+
 static int
 thread_lat_cmp(struct list_head *list, struct work_atoms *l, struct work_atoms *r)
 {
@@ -1480,6 +1515,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 {
 	const u32 next_pid = perf_evsel__intval(evsel, sample, "next_pid");
 	struct thread *sched_in;
+	struct thread_runtime *tr;
 	int new_shortname;
 	u64 timestamp0, timestamp = sample->time;
 	s64 delta;
@@ -1519,22 +1555,28 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 	if (sched_in == NULL)
 		return -1;
 
+	tr = thread__get_runtime(sched_in);
+	if (tr == NULL) {
+		thread__put(sched_in);
+		return -1;
+	}
+
 	sched->curr_thread[this_cpu] = thread__get(sched_in);
 
 	printf("  ");
 
 	new_shortname = 0;
-	if (!sched_in->shortname[0]) {
+	if (!tr->shortname[0]) {
 		if (!strcmp(thread__comm_str(sched_in), "swapper")) {
 			/*
 			 * Don't allocate a letter-number for swapper:0
 			 * as a shortname. Instead, we use '.' for it.
 			 */
-			sched_in->shortname[0] = '.';
-			sched_in->shortname[1] = ' ';
+			tr->shortname[0] = '.';
+			tr->shortname[1] = ' ';
 		} else {
-			sched_in->shortname[0] = sched->next_shortname1;
-			sched_in->shortname[1] = sched->next_shortname2;
+			tr->shortname[0] = sched->next_shortname1;
+			tr->shortname[1] = sched->next_shortname2;
 
 			if (sched->next_shortname1 < 'Z') {
 				sched->next_shortname1++;
@@ -1552,6 +1594,7 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 	for (i = 0; i < cpus_nr; i++) {
 		int cpu = sched->map.comp ? sched->map.comp_cpus[i] : i;
 		struct thread *curr_thread = sched->curr_thread[cpu];
+		struct thread_runtime *curr_tr;
 		const char *pid_color = color;
 		const char *cpu_color = color;
 
@@ -1569,9 +1612,14 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 		else
 			color_fprintf(stdout, cpu_color, "*");
 
-		if (sched->curr_thread[cpu])
-			color_fprintf(stdout, pid_color, "%2s ", sched->curr_thread[cpu]->shortname);
-		else
+		if (sched->curr_thread[cpu]) {
+			curr_tr = thread__get_runtime(sched->curr_thread[cpu]);
+			if (curr_tr == NULL) {
+				thread__put(sched_in);
+				return -1;
+			}
+			color_fprintf(stdout, pid_color, "%2s ", curr_tr->shortname);
+		} else
 			color_fprintf(stdout, color, "   ");
 	}
 
@@ -1580,14 +1628,15 @@ static int map_switch_event(struct perf_sched *sched, struct perf_evsel *evsel,
 
 	timestamp__scnprintf_usec(timestamp, stimestamp, sizeof(stimestamp));
 	color_fprintf(stdout, color, "  %12s secs ", stimestamp);
-	if (new_shortname || (verbose > 0 && sched_in->tid)) {
+	if (new_shortname || tr->comm_changed || (verbose > 0 && sched_in->tid)) {
 		const char *pid_color = color;
 
 		if (thread__has_color(sched_in))
 			pid_color = COLOR_PIDS;
 
 		color_fprintf(stdout, pid_color, "%s => %s:%d",
-		       sched_in->shortname, thread__comm_str(sched_in), sched_in->tid);
+		       tr->shortname, thread__comm_str(sched_in), sched_in->tid);
+		tr->comm_changed = false;
 	}
 
 	if (sched->map.comp && new_cpu)
@@ -1691,6 +1740,37 @@ static int perf_sched__process_tracepoint_sample(struct perf_tool *tool __maybe_
 	return err;
 }
 
+static int perf_sched__process_comm(struct perf_tool *tool __maybe_unused,
+				    union perf_event *event,
+				    struct perf_sample *sample,
+				    struct machine *machine)
+{
+	struct thread *thread;
+	struct thread_runtime *tr;
+	int err;
+
+	err = perf_event__process_comm(tool, event, sample, machine);
+	if (err)
+		return err;
+
+	thread = machine__find_thread(machine, sample->pid, sample->tid);
+	if (!thread) {
+		pr_err("Internal error: can't find thread\n");
+		return -1;
+	}
+
+	tr = thread__get_runtime(thread);
+	if (tr == NULL) {
+		thread__put(thread);
+		return -1;
+	}
+
+	tr->comm_changed = true;
+	thread__put(thread);
+
+	return 0;
+}
+
 static int perf_sched__read_events(struct perf_sched *sched)
 {
 	const struct perf_evsel_str_handler handlers[] = {
@@ -2200,37 +2280,6 @@ static void save_idle_callchain(struct idle_thread_runtime *itr,
 	callchain_cursor__copy(&itr->cursor, &callchain_cursor);
 }
 
-/*
- * handle runtime stats saved per thread
- */
-static struct thread_runtime *thread__init_runtime(struct thread *thread)
-{
-	struct thread_runtime *r;
-
-	r = zalloc(sizeof(struct thread_runtime));
-	if (!r)
-		return NULL;
-
-	init_stats(&r->run_stats);
-	thread__set_priv(thread, r);
-
-	return r;
-}
-
-static struct thread_runtime *thread__get_runtime(struct thread *thread)
-{
-	struct thread_runtime *tr;
-
-	tr = thread__priv(thread);
-	if (tr == NULL) {
-		tr = thread__init_runtime(thread);
-		if (tr == NULL)
-			pr_debug("Failed to malloc memory for runtime data.\n");
-	}
-
-	return tr;
-}
-
 static struct thread *timehist_get_thread(struct perf_sched *sched,
 					  struct perf_sample *sample,
 					  struct machine *machine,
@@ -3291,7 +3340,7 @@ int cmd_sched(int argc, const char **argv)
 	struct perf_sched sched = {
 		.tool = {
 			.sample		 = perf_sched__process_tracepoint_sample,
-			.comm		 = perf_event__process_comm,
+			.comm		 = perf_sched__process_comm,
 			.namespaces	 = perf_event__process_namespaces,
 			.lost		 = perf_event__process_lost,
 			.fork		 = perf_sched__process_fork_event,
diff --git a/tools/perf/builtin-script.c b/tools/perf/builtin-script.c
index ab19a6ee4093..313c42423393 100644
--- a/tools/perf/builtin-script.c
+++ b/tools/perf/builtin-script.c
@@ -1489,6 +1489,7 @@ struct perf_script {
 	bool			show_switch_events;
 	bool			show_namespace_events;
 	bool			show_lost_events;
+	bool			show_round_events;
 	bool			allocated;
 	bool			per_event_dump;
 	struct cpu_map		*cpus;
@@ -2104,6 +2105,16 @@ process_lost_event(struct perf_tool *tool,
 	return 0;
 }
 
+static int
+process_finished_round_event(struct perf_tool *tool __maybe_unused,
+			     union perf_event *event,
+			     struct ordered_events *oe __maybe_unused)
+
+{
+	perf_event__fprintf(event, stdout);
+	return 0;
+}
+
 static void sig_handler(int sig __maybe_unused)
 {
 	session_done = 1;
@@ -2200,6 +2211,10 @@ static int __cmd_script(struct perf_script *script)
 		script->tool.namespaces = process_namespaces_event;
 	if (script->show_lost_events)
 		script->tool.lost = process_lost_event;
+	if (script->show_round_events) {
+		script->tool.ordered_events = false;
+		script->tool.finished_round = process_finished_round_event;
+	}
 
 	if (perf_script__setup_per_event_dump(script)) {
 		pr_err("Couldn't create the per event dump files\n");
@@ -2659,8 +2674,8 @@ static int list_available_scripts(const struct option *opt __maybe_unused,
 	}
 
 	for_each_lang(scripts_path, scripts_dir, lang_dirent) {
-		snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
-			 lang_dirent->d_name);
+		scnprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
+			  lang_dirent->d_name);
 		lang_dir = opendir(lang_path);
 		if (!lang_dir)
 			continue;
@@ -2669,8 +2684,8 @@ static int list_available_scripts(const struct option *opt __maybe_unused,
 			script_root = get_script_root(script_dirent, REPORT_SUFFIX);
 			if (script_root) {
 				desc = script_desc__findnew(script_root);
-				snprintf(script_path, MAXPATHLEN, "%s/%s",
-					 lang_path, script_dirent->d_name);
+				scnprintf(script_path, MAXPATHLEN, "%s/%s",
+					  lang_path, script_dirent->d_name);
 				read_script_info(desc, script_path);
 				free(script_root);
 			}
@@ -2706,7 +2721,7 @@ static int check_ev_match(char *dir_name, char *scriptname,
 	int match, len;
 	FILE *fp;
 
-	sprintf(filename, "%s/bin/%s-record", dir_name, scriptname);
+	scnprintf(filename, MAXPATHLEN, "%s/bin/%s-record", dir_name, scriptname);
 
 	fp = fopen(filename, "r");
 	if (!fp)
@@ -2784,8 +2799,8 @@ int find_scripts(char **scripts_array, char **scripts_path_array)
 	}
 
 	for_each_lang(scripts_path, scripts_dir, lang_dirent) {
-		snprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path,
-			 lang_dirent->d_name);
+		scnprintf(lang_path, MAXPATHLEN, "%s/%s", scripts_path,
+			  lang_dirent->d_name);
 #ifdef NO_LIBPERL
 		if (strstr(lang_path, "perl"))
 			continue;
@@ -2840,8 +2855,8 @@ static char *get_script_path(const char *script_root, const char *suffix)
 		return NULL;
 
 	for_each_lang(scripts_path, scripts_dir, lang_dirent) {
-		snprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
-			 lang_dirent->d_name);
+		scnprintf(lang_path, MAXPATHLEN, "%s/%s/bin", scripts_path,
+			  lang_dirent->d_name);
 		lang_dir = opendir(lang_path);
 		if (!lang_dir)
 			continue;
@@ -2852,8 +2867,8 @@ static char *get_script_path(const char *script_root, const char *suffix)
 				free(__script_root);
 				closedir(lang_dir);
 				closedir(scripts_dir);
-				snprintf(script_path, MAXPATHLEN, "%s/%s",
-					 lang_path, script_dirent->d_name);
+				scnprintf(script_path, MAXPATHLEN, "%s/%s",
+					  lang_path, script_dirent->d_name);
 				return strdup(script_path);
 			}
 			free(__script_root);
@@ -3139,6 +3154,8 @@ int cmd_script(int argc, const char **argv)
 		    "Show namespace events (if recorded)"),
 	OPT_BOOLEAN('\0', "show-lost-events", &script.show_lost_events,
 		    "Show lost events (if recorded)"),
+	OPT_BOOLEAN('\0', "show-round-events", &script.show_round_events,
+		    "Show round events (if recorded)"),
 	OPT_BOOLEAN('\0', "per-event-dump", &script.per_event_dump,
 		    "Dump trace output to files named by the monitored events"),
 	OPT_BOOLEAN('f', "force", &symbol_conf.force, "don't complain, do it"),
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 54a4c152edb3..f5c454855908 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -168,6 +168,7 @@ static struct timespec		ref_time;
 static struct cpu_map		*aggr_map;
 static aggr_get_id_t		aggr_get_id;
 static bool			append_file;
+static bool			interval_count;
 static const char		*output_name;
 static int			output_fd;
 static int			print_free_counters_hint;
@@ -507,14 +508,13 @@ static int perf_stat_synthesize_config(bool is_pipe)
 
 #define FD(e, x, y) (*(int *)xyarray__entry(e->fd, x, y))
 
-static int __store_counter_ids(struct perf_evsel *counter,
-			       struct cpu_map *cpus,
-			       struct thread_map *threads)
+static int __store_counter_ids(struct perf_evsel *counter)
 {
 	int cpu, thread;
 
-	for (cpu = 0; cpu < cpus->nr; cpu++) {
-		for (thread = 0; thread < threads->nr; thread++) {
+	for (cpu = 0; cpu < xyarray__max_x(counter->fd); cpu++) {
+		for (thread = 0; thread < xyarray__max_y(counter->fd);
+		     thread++) {
 			int fd = FD(counter, cpu, thread);
 
 			if (perf_evlist__id_add_fd(evsel_list, counter,
@@ -534,7 +534,7 @@ static int store_counter_ids(struct perf_evsel *counter)
 	if (perf_evsel__alloc_id(counter, cpus->nr, threads->nr))
 		return -ENOMEM;
 
-	return __store_counter_ids(counter, cpus, threads);
+	return __store_counter_ids(counter);
 }
 
 static bool perf_evsel__should_store_id(struct perf_evsel *counter)
@@ -571,6 +571,8 @@ static struct perf_evsel *perf_evsel__reset_weak_group(struct perf_evsel *evsel)
 static int __run_perf_stat(int argc, const char **argv)
 {
 	int interval = stat_config.interval;
+	int times = stat_config.times;
+	int timeout = stat_config.timeout;
 	char msg[BUFSIZ];
 	unsigned long long t0, t1;
 	struct perf_evsel *counter;
@@ -584,6 +586,9 @@ static int __run_perf_stat(int argc, const char **argv)
 	if (interval) {
 		ts.tv_sec  = interval / USEC_PER_MSEC;
 		ts.tv_nsec = (interval % USEC_PER_MSEC) * NSEC_PER_MSEC;
+	} else if (timeout) {
+		ts.tv_sec  = timeout / USEC_PER_MSEC;
+		ts.tv_nsec = (timeout % USEC_PER_MSEC) * NSEC_PER_MSEC;
 	} else {
 		ts.tv_sec  = 1;
 		ts.tv_nsec = 0;
@@ -632,7 +637,19 @@ try_again:
                                 if (verbose > 0)
                                         ui__warning("%s\n", msg);
                                 goto try_again;
-                        }
+			} else if (target__has_per_thread(&target) &&
+				   evsel_list->threads &&
+				   evsel_list->threads->err_thread != -1) {
+				/*
+				 * For global --per-thread case, skip current
+				 * error thread.
+				 */
+				if (!thread_map__remove(evsel_list->threads,
+							evsel_list->threads->err_thread)) {
+					evsel_list->threads->err_thread = -1;
+					goto try_again;
+				}
+			}
 
 			perf_evsel__open_strerror(counter, &target,
 						  errno, msg, sizeof(msg));
@@ -696,10 +713,14 @@ try_again:
 		perf_evlist__start_workload(evsel_list);
 		enable_counters();
 
-		if (interval) {
+		if (interval || timeout) {
 			while (!waitpid(child_pid, &status, WNOHANG)) {
 				nanosleep(&ts, NULL);
+				if (timeout)
+					break;
 				process_interval();
+				if (interval_count && !(--times))
+					break;
 			}
 		}
 		waitpid(child_pid, &status, 0);
@@ -716,8 +737,13 @@ try_again:
 		enable_counters();
 		while (!done) {
 			nanosleep(&ts, NULL);
-			if (interval)
+			if (timeout)
+				break;
+			if (interval) {
 				process_interval();
+				if (interval_count && !(--times))
+					break;
+			}
 		}
 	}
 
@@ -1225,6 +1251,31 @@ static void aggr_update_shadow(void)
 	}
 }
 
+static void uniquify_event_name(struct perf_evsel *counter)
+{
+	char *new_name;
+	char *config;
+
+	if (!counter->pmu_name || !strncmp(counter->name, counter->pmu_name,
+					   strlen(counter->pmu_name)))
+		return;
+
+	config = strchr(counter->name, '/');
+	if (config) {
+		if (asprintf(&new_name,
+			     "%s%s", counter->pmu_name, config) > 0) {
+			free(counter->name);
+			counter->name = new_name;
+		}
+	} else {
+		if (asprintf(&new_name,
+			     "%s [%s]", counter->name, counter->pmu_name) > 0) {
+			free(counter->name);
+			counter->name = new_name;
+		}
+	}
+}
+
 static void collect_all_aliases(struct perf_evsel *counter,
 			    void (*cb)(struct perf_evsel *counter, void *data,
 				       bool first),
@@ -1253,7 +1304,9 @@ static bool collect_data(struct perf_evsel *counter,
 	if (counter->merged_stat)
 		return false;
 	cb(counter, data, true);
-	if (!no_merge && counter->auto_merge_stats)
+	if (no_merge)
+		uniquify_event_name(counter);
+	else if (counter->auto_merge_stats)
 		collect_all_aliases(counter, cb, data);
 	return true;
 }
@@ -1891,6 +1944,10 @@ static const struct option stat_options[] = {
 			"command to run after to the measured command"),
 	OPT_UINTEGER('I', "interval-print", &stat_config.interval,
 		    "print counts at regular interval in ms (>= 10)"),
+	OPT_INTEGER(0, "interval-count", &stat_config.times,
+		    "print counts for fixed number of times"),
+	OPT_UINTEGER(0, "timeout", &stat_config.timeout,
+		    "stop workload and print counts after a timeout period in ms (>= 10ms)"),
 	OPT_SET_UINT(0, "per-socket", &stat_config.aggr_mode,
 		     "aggregate counts per processor socket", AGGR_SOCKET),
 	OPT_SET_UINT(0, "per-core", &stat_config.aggr_mode,
@@ -2274,11 +2331,16 @@ static int add_default_attributes(void)
 		return 0;
 
 	if (transaction_run) {
+		struct parse_events_error errinfo;
+
 		if (pmu_have_event("cpu", "cycles-ct") &&
 		    pmu_have_event("cpu", "el-start"))
-			err = parse_events(evsel_list, transaction_attrs, NULL);
+			err = parse_events(evsel_list, transaction_attrs,
+					   &errinfo);
 		else
-			err = parse_events(evsel_list, transaction_limited_attrs, NULL);
+			err = parse_events(evsel_list,
+					   transaction_limited_attrs,
+					   &errinfo);
 		if (err) {
 			fprintf(stderr, "Cannot set up transaction events\n");
 			return -1;
@@ -2688,7 +2750,7 @@ int cmd_stat(int argc, const char **argv)
 	int status = -EINVAL, run_idx;
 	const char *mode;
 	FILE *output = stderr;
-	unsigned int interval;
+	unsigned int interval, timeout;
 	const char * const stat_subcommands[] = { "record", "report" };
 
 	setlocale(LC_ALL, "");
@@ -2719,6 +2781,7 @@ int cmd_stat(int argc, const char **argv)
 		return __cmd_report(argc, argv);
 
 	interval = stat_config.interval;
+	timeout = stat_config.timeout;
 
 	/*
 	 * For record command the -o is already taken care of.
@@ -2871,6 +2934,33 @@ int cmd_stat(int argc, const char **argv)
 				   "Please proceed with caution.\n");
 	}
 
+	if (stat_config.times && interval)
+		interval_count = true;
+	else if (stat_config.times && !interval) {
+		pr_err("interval-count option should be used together with "
+				"interval-print.\n");
+		parse_options_usage(stat_usage, stat_options, "interval-count", 0);
+		parse_options_usage(stat_usage, stat_options, "I", 1);
+		goto out;
+	}
+
+	if (timeout && timeout < 100) {
+		if (timeout < 10) {
+			pr_err("timeout must be >= 10ms.\n");
+			parse_options_usage(stat_usage, stat_options, "timeout", 0);
+			goto out;
+		} else
+			pr_warning("timeout < 100ms. "
+				   "The overhead percentage could be high in some cases. "
+				   "Please proceed with caution.\n");
+	}
+	if (timeout && interval) {
+		pr_err("timeout option is not supported with interval-print.\n");
+		parse_options_usage(stat_usage, stat_options, "timeout", 0);
+		parse_options_usage(stat_usage, stat_options, "I", 1);
+		goto out;
+	}
+
 	if (perf_evlist__alloc_stats(evsel_list, interval))
 		goto out;
 
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 35ac016fcb98..f39bd60d2708 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -817,14 +817,13 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 	struct perf_session *session = top->session;
 	union perf_event *event;
 	struct machine *machine;
-	u64 end, start;
 	int ret;
 
 	md = opts->overwrite ? &evlist->overwrite_mmap[idx] : &evlist->mmap[idx];
-	if (perf_mmap__read_init(md, opts->overwrite, &start, &end) < 0)
+	if (perf_mmap__read_init(md) < 0)
 		return;
 
-	while ((event = perf_mmap__read_event(md, opts->overwrite, &start, end)) != NULL) {
+	while ((event = perf_mmap__read_event(md)) != NULL) {
 		ret = perf_evlist__parse_sample(evlist, event, &sample);
 		if (ret) {
 			pr_err("Can't parse sample, err = %d\n", ret);
@@ -879,7 +878,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 		} else
 			++session->evlist->stats.nr_unknown_events;
 next_event:
-		perf_mmap__consume(md, opts->overwrite);
+		perf_mmap__consume(md);
 	}
 
 	perf_mmap__read_done(md);
@@ -1224,8 +1223,10 @@ parse_callchain_opt(const struct option *opt, const char *arg, int unset)
 
 static int perf_top_config(const char *var, const char *value, void *cb __maybe_unused)
 {
-	if (!strcmp(var, "top.call-graph"))
-		var = "call-graph.record-mode"; /* fall-through */
+	if (!strcmp(var, "top.call-graph")) {
+		var = "call-graph.record-mode";
+		return perf_default_config(var, value, cb);
+	}
 	if (!strcmp(var, "top.children")) {
 		symbol_conf.cumulate_callchain = perf_config_bool(var, value);
 		return 0;
@@ -1307,7 +1308,9 @@ int cmd_top(int argc, const char **argv)
 	OPT_STRING(0, "sym-annotate", &top.sym_filter, "symbol name",
 		    "symbol to annotate"),
 	OPT_BOOLEAN('z', "zero", &top.zero, "zero history across updates"),
-	OPT_UINTEGER('F', "freq", &opts->user_freq, "profile at this frequency"),
+	OPT_CALLBACK('F', "freq", &top.record_opts, "freq or 'max'",
+		     "profile at this frequency",
+		      record__parse_freq),
 	OPT_INTEGER('E', "entries", &top.print_entries,
 		    "display this many functions"),
 	OPT_BOOLEAN('U', "hide_user_symbols", &top.hide_user_symbols,
@@ -1490,6 +1493,8 @@ int cmd_top(int argc, const char **argv)
 	if (status < 0)
 		goto out_delete_evlist;
 
+	annotation_config__init();
+
 	symbol_conf.try_vmlinux_path = (symbol_conf.vmlinux_name == NULL);
 	if (symbol__init(NULL) < 0)
 		return -1;
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index e7f1b182fc15..87b95c9410b4 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -19,6 +19,7 @@
 #include <traceevent/event-parse.h>
 #include <api/fs/tracing_path.h>
 #include "builtin.h"
+#include "util/cgroup.h"
 #include "util/color.h"
 #include "util/debug.h"
 #include "util/env.h"
@@ -83,6 +84,7 @@ struct trace {
 	struct perf_evlist	*evlist;
 	struct machine		*host;
 	struct thread		*current;
+	struct cgroup		*cgroup;
 	u64			base_time;
 	FILE			*output;
 	unsigned long		nr_events;
@@ -2370,6 +2372,34 @@ static int trace__run(struct trace *trace, int argc, const char **argv)
 				   trace__sched_stat_runtime))
 		goto out_error_sched_stat_runtime;
 
+	/*
+	 * If a global cgroup was set, apply it to all the events without an
+	 * explicit cgroup. I.e.:
+	 *
+	 * 	trace -G A -e sched:*switch
+	 *
+	 * Will set all raw_syscalls:sys_{enter,exit}, pgfault, vfs_getname, etc
+	 * _and_ sched:sched_switch to the 'A' cgroup, while:
+	 *
+	 * trace -e sched:*switch -G A
+	 *
+	 * will only set the sched:sched_switch event to the 'A' cgroup, all the
+	 * other events (raw_syscalls:sys_{enter,exit}, etc are left "without"
+	 * a cgroup (on the root cgroup, sys wide, etc).
+	 *
+	 * Multiple cgroups:
+	 *
+	 * trace -G A -e sched:*switch -G B
+	 *
+	 * the syscall ones go to the 'A' cgroup, the sched:sched_switch goes
+	 * to the 'B' cgroup.
+	 *
+	 * evlist__set_default_cgroup() grabs a reference of the passed cgroup
+	 * only for the evsels still without a cgroup, i.e. evsel->cgroup == NULL.
+	 */
+	if (trace->cgroup)
+		evlist__set_default_cgroup(trace->evlist, trace->cgroup);
+
 	err = perf_evlist__create_maps(evlist, &trace->opts.target);
 	if (err < 0) {
 		fprintf(trace->output, "Problems parsing the target to trace, check your options!\n");
@@ -2472,8 +2502,13 @@ again:
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		union perf_event *event;
+		struct perf_mmap *md;
+
+		md = &evlist->mmap[i];
+		if (perf_mmap__read_init(md) < 0)
+			continue;
 
-		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+		while ((event = perf_mmap__read_event(md)) != NULL) {
 			struct perf_sample sample;
 
 			++trace->nr_events;
@@ -2486,7 +2521,7 @@ again:
 
 			trace__handle_event(trace, event, &sample);
 next_event:
-			perf_evlist__mmap_consume(evlist, i);
+			perf_mmap__consume(md);
 
 			if (interrupted)
 				goto out_disable;
@@ -2496,6 +2531,7 @@ next_event:
 				draining = true;
 			}
 		}
+		perf_mmap__read_done(md);
 	}
 
 	if (trace->nr_events == before) {
@@ -2533,6 +2569,7 @@ out_delete_evlist:
 	trace__symbols__exit(trace);
 
 	perf_evlist__delete(evlist);
+	cgroup__put(trace->cgroup);
 	trace->evlist = NULL;
 	trace->live = false;
 	return err;
@@ -2972,6 +3009,18 @@ out:
 	return err;
 }
 
+static int trace__parse_cgroups(const struct option *opt, const char *str, int unset)
+{
+	struct trace *trace = opt->value;
+
+	if (!list_empty(&trace->evlist->entries))
+		return parse_cgroups(opt, str, unset);
+
+	trace->cgroup = evlist__findnew_cgroup(trace->evlist, str);
+
+	return 0;
+}
+
 int cmd_trace(int argc, const char **argv)
 {
 	const char *trace_usage[] = {
@@ -3062,6 +3111,8 @@ int cmd_trace(int argc, const char **argv)
 			"print the PERF_RECORD_SAMPLE PERF_SAMPLE_ info, for debugging"),
 	OPT_UINTEGER(0, "proc-map-timeout", &trace.opts.proc_map_timeout,
 			"per thread proc mmap processing timeout in ms"),
+	OPT_CALLBACK('G', "cgroup", &trace, "name", "monitor event in cgroup name only",
+		     trace__parse_cgroups),
 	OPT_UINTEGER('D', "delay", &trace.opts.initial_delay,
 		     "ms to wait before starting measurement after program "
 		     "start"),
@@ -3088,6 +3139,11 @@ int cmd_trace(int argc, const char **argv)
 	argc = parse_options_subcommand(argc, argv, trace_options, trace_subcommands,
 				 trace_usage, PARSE_OPT_STOP_AT_NON_OPTION);
 
+	if ((nr_cgroups || trace.cgroup) && !trace.opts.target.system_wide) {
+		usage_with_options_msg(trace_usage, trace_options,
+				       "cgroup monitoring only available in system-wide mode");
+	}
+
 	err = bpf__setup_stdout(trace.evlist);
 	if (err) {
 		bpf__strerror_setup_stdout(trace.evlist, err, bf, sizeof(bf));
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index 790ec25919a0..9aff89bc7535 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -42,6 +42,7 @@ arch/parisc/include/uapi/asm/errno.h
 arch/powerpc/include/uapi/asm/errno.h
 arch/sparc/include/uapi/asm/errno.h
 arch/x86/include/uapi/asm/errno.h
+arch/powerpc/include/uapi/asm/unistd.h
 include/asm-generic/bitops/arch_hweight.h
 include/asm-generic/bitops/const_hweight.h
 include/asm-generic/bitops/__fls.h
@@ -58,6 +59,7 @@ check () {
   file=$1
 
   shift
+  opts=
   while [ -n "$*" ]; do
     opts="$opts \"$1\""
     shift
diff --git a/tools/perf/perf.h b/tools/perf/perf.h
index 57b9b342d533..8fec1abd0f1f 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -61,6 +61,7 @@ struct record_opts {
 	bool	     tail_synthesize;
 	bool	     overwrite;
 	bool	     ignore_missing_thread;
+	bool	     strict_freq;
 	bool	     sample_id;
 	unsigned int freq;
 	unsigned int mmap_pages;
@@ -83,4 +84,6 @@ struct record_opts {
 struct option;
 extern const char * const *record_usage;
 extern struct option *record_options;
+
+int record__parse_freq(const struct option *opt, const char *str, int unset);
 #endif
diff --git a/tools/perf/pmu-events/Build b/tools/perf/pmu-events/Build
index 999a4e878162..17783913d330 100644
--- a/tools/perf/pmu-events/Build
+++ b/tools/perf/pmu-events/Build
@@ -1,10 +1,12 @@
 hostprogs := jevents
 
 jevents-y	+= json.o jsmn.o jevents.o
+CHOSTFLAGS_jevents.o	= -I$(srctree)/tools/include
 pmu-events-y	+= pmu-events.o
 JDIR		=  pmu-events/arch/$(SRCARCH)
 JSON		=  $(shell [ -d $(JDIR) ] &&				\
 			find $(JDIR) -name '*.json' -o -name 'mapfile.csv')
+
 #
 # Locate/process JSON files in pmu-events/arch/
 # directory and create tables in pmu-events.c.
diff --git a/tools/perf/pmu-events/README b/tools/perf/pmu-events/README
index c2ee3e4417fe..e62b09b6a844 100644
--- a/tools/perf/pmu-events/README
+++ b/tools/perf/pmu-events/README
@@ -11,12 +11,17 @@ tree tools/perf/pmu-events/arch/foo.
 	- Regular files with '.json' extension in the name are assumed to be
 	  JSON files, each of which describes a set of PMU events.
 
-	- Regular files with basename starting with 'mapfile.csv' are assumed
-	  to be a CSV file that maps a specific CPU to its set of PMU events.
-	  (see below for mapfile format)
+	- The CSV file that maps a specific CPU to its set of PMU events is to
+	  be named 'mapfile.csv' (see below for mapfile format).
 
 	- Directories are traversed, but all other files are ignored.
 
+	- To reduce JSON event duplication per architecture, platform JSONs may
+	  use "ArchStdEvent" keyword to dereference an "Architecture standard
+	  events", defined in architecture standard JSONs.
+	  Architecture standard JSONs must be located in the architecture root
+	  folder. Matching is based on the "EventName" field.
+
 The PMU events supported by a CPU model are expected to grouped into topics
 such as Pipelining, Cache, Memory, Floating-point etc. All events for a topic
 should be placed in a separate JSON file - where the file name identifies
@@ -29,6 +34,10 @@ sub directory. Thus for the Silvermont X86 CPU:
 	Cache.json 	Memory.json 	Virtual-Memory.json
 	Frontend.json 	Pipeline.json
 
+The JSONs folder for a CPU model/family may be placed in the root arch
+folder, or may be placed in a vendor sub-folder under the arch folder
+for instances where the arch and vendor are not the same.
+
 Using the JSON files and the mapfile, 'jevents' generates the C source file,
 'pmu-events.c', which encodes the two sets of tables:
 
diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/branch.json
index 3b6208763e50..0b0e6b26605b 100644
--- a/tools/perf/pmu-events/arch/arm64/cortex-a53/branch.json
+++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/branch.json
@@ -1,25 +1,23 @@
 [
-  {,
-    "EventCode": "0x7A",
-    "EventName": "BR_INDIRECT_SPEC",
-    "BriefDescription": "Branch speculatively executed - Indirect branch"
+  {
+    "ArchStdEvent":  "BR_INDIRECT_SPEC",
   },
-  {,
+  {
     "EventCode": "0xC9",
     "EventName": "BR_COND",
     "BriefDescription": "Conditional branch executed"
   },
-  {,
+  {
     "EventCode": "0xCA",
     "EventName": "BR_INDIRECT_MISPRED",
     "BriefDescription": "Indirect branch mispredicted"
   },
-  {,
+  {
     "EventCode": "0xCB",
     "EventName": "BR_INDIRECT_MISPRED_ADDR",
     "BriefDescription": "Indirect branch mispredicted because of address miscompare"
   },
-  {,
+  {
     "EventCode": "0xCC",
     "EventName": "BR_COND_MISPRED",
     "BriefDescription": "Conditional branch mispredicted"
diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/bus.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/bus.json
new file mode 100644
index 000000000000..ce33b2553277
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/bus.json
@@ -0,0 +1,8 @@
+[
+  {
+        "ArchStdEvent": "BUS_ACCESS_RD",
+  },
+  {
+        "ArchStdEvent": "BUS_ACCESS_WR",
+  }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/cache.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/cache.json
new file mode 100644
index 000000000000..5dfbec43c9f9
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/cache.json
@@ -0,0 +1,27 @@
+[
+  {
+        "EventCode": "0xC2",
+        "EventName": "PREFETCH_LINEFILL",
+        "BriefDescription": "Linefill because of prefetch"
+  },
+  {
+        "EventCode": "0xC3",
+        "EventName": "PREFETCH_LINEFILL_DROP",
+        "BriefDescription": "Instruction Cache Throttle occurred"
+  },
+  {
+        "EventCode": "0xC4",
+        "EventName": "READ_ALLOC_ENTER",
+        "BriefDescription": "Entering read allocate mode"
+  },
+  {
+        "EventCode": "0xC5",
+        "EventName": "READ_ALLOC",
+        "BriefDescription": "Read allocate mode"
+  },
+  {
+        "EventCode": "0xC8",
+        "EventName": "EXT_SNOOP",
+        "BriefDescription": "SCU Snooped data from another CPU for this CPU"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/memory.json
index 480d9f7460ab..25ae642ba381 100644
--- a/tools/perf/pmu-events/arch/arm64/cortex-a53/memory.json
+++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/memory.json
@@ -1,20 +1,10 @@
 [
-  {,
-    "EventCode": "0x60",
-    "EventName": "BUS_ACCESS_LD",
-    "BriefDescription": "Bus access - Read"
-  },
-  {,
-    "EventCode": "0x61",
-    "EventName": "BUS_ACCESS_ST",
-    "BriefDescription": "Bus access - Write"
-  },
-  {,
+  {
     "EventCode": "0xC0",
     "EventName": "EXT_MEM_REQ",
     "BriefDescription": "External memory request"
   },
-  {,
+  {
     "EventCode": "0xC1",
     "EventName": "EXT_MEM_REQ_NC",
     "BriefDescription": "Non-cacheable external memory request"
diff --git a/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/other.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/other.json
new file mode 100644
index 000000000000..6cc6cbd7bf0b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/other.json
@@ -0,0 +1,28 @@
+[
+  {
+        "ArchStdEvent": "EXC_IRQ",
+  },
+  {
+        "ArchStdEvent": "EXC_FIQ",
+  },
+  {
+        "EventCode": "0xC6",
+        "EventName": "PRE_DECODE_ERR",
+        "BriefDescription": "Pre-decode error"
+  },
+  {
+        "EventCode": "0xD0",
+        "EventName": "L1I_CACHE_ERR",
+        "BriefDescription": "L1 Instruction Cache (data or tag) memory error"
+  },
+  {
+        "EventCode": "0xD1",
+        "EventName": "L1D_CACHE_ERR",
+        "BriefDescription": "L1 Data Cache (data, tag or dirty) memory error, correctable or non-correctable"
+  },
+  {
+        "EventCode": "0xD2",
+        "EventName": "TLB_ERR",
+        "BriefDescription": "TLB memory error"
+  }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/pipeline.json
index 3149fb90555a..f45a6b5d0025 100644
--- a/tools/perf/pmu-events/arch/arm64/cortex-a53/pipeline.json
+++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/pipeline.json
@@ -1,50 +1,50 @@
 [
-  {,
+  {
     "EventCode": "0xC7",
     "EventName": "STALL_SB_FULL",
     "BriefDescription": "Data Write operation that stalls the pipeline because the store buffer is full"
   },
-  {,
+  {
     "EventCode": "0xE0",
     "EventName": "OTHER_IQ_DEP_STALL",
     "BriefDescription": "Cycles that the DPU IQ is empty and that is not because of a recent micro-TLB miss, instruction cache miss or pre-decode error"
   },
-  {,
+  {
     "EventCode": "0xE1",
     "EventName": "IC_DEP_STALL",
     "BriefDescription": "Cycles the DPU IQ is empty and there is an instruction cache miss being processed"
   },
-  {,
+  {
     "EventCode": "0xE2",
     "EventName": "IUTLB_DEP_STALL",
     "BriefDescription": "Cycles the DPU IQ is empty and there is an instruction micro-TLB miss being processed"
   },
-  {,
+  {
     "EventCode": "0xE3",
     "EventName": "DECODE_DEP_STALL",
     "BriefDescription": "Cycles the DPU IQ is empty and there is a pre-decode error being processed"
   },
-  {,
+  {
     "EventCode": "0xE4",
     "EventName": "OTHER_INTERLOCK_STALL",
     "BriefDescription": "Cycles there is an interlock other than  Advanced SIMD/Floating-point instructions or load/store instruction"
   },
-  {,
+  {
     "EventCode": "0xE5",
     "EventName": "AGU_DEP_STALL",
     "BriefDescription": "Cycles there is an interlock for a load/store instruction waiting for data to calculate the address in the AGU"
   },
-  {,
+  {
     "EventCode": "0xE6",
     "EventName": "SIMD_DEP_STALL",
     "BriefDescription": "Cycles there is an interlock for an Advanced SIMD/Floating-point operation."
   },
-  {,
+  {
     "EventCode": "0xE7",
     "EventName": "LD_DEP_STALL",
     "BriefDescription": "Cycles there is a stall in the Wr stage because of a load miss"
   },
-  {,
+  {
     "EventCode": "0xE8",
     "EventName": "ST_DEP_STALL",
     "BriefDescription": "Cycles there is a stall in the Wr stage because of a store"
diff --git a/tools/perf/pmu-events/arch/arm64/armv8-recommended.json b/tools/perf/pmu-events/arch/arm64/armv8-recommended.json
new file mode 100644
index 000000000000..6328828c018c
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/armv8-recommended.json
@@ -0,0 +1,452 @@
+[
+    {
+        "PublicDescription": "Attributable Level 1 data cache access, read",
+        "EventCode": "0x40",
+        "EventName": "L1D_CACHE_RD",
+        "BriefDescription": "L1D cache access, read"
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data cache access, write",
+        "EventCode": "0x41",
+        "EventName": "L1D_CACHE_WR",
+        "BriefDescription": "L1D cache access, write"
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data cache refill, read",
+        "EventCode": "0x42",
+        "EventName": "L1D_CACHE_REFILL_RD",
+        "BriefDescription": "L1D cache refill, read"
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data cache refill, write",
+        "EventCode": "0x43",
+        "EventName": "L1D_CACHE_REFILL_WR",
+        "BriefDescription": "L1D cache refill, write"
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data cache refill, inner",
+        "EventCode": "0x44",
+        "EventName": "L1D_CACHE_REFILL_INNER",
+        "BriefDescription": "L1D cache refill, inner"
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data cache refill, outer",
+        "EventCode": "0x45",
+        "EventName": "L1D_CACHE_REFILL_OUTER",
+        "BriefDescription": "L1D cache refill, outer"
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data cache Write-Back, victim",
+        "EventCode": "0x46",
+        "EventName": "L1D_CACHE_WB_VICTIM",
+        "BriefDescription": "L1D cache Write-Back, victim"
+    },
+    {
+        "PublicDescription": "Level 1 data cache Write-Back, cleaning and coherency",
+        "EventCode": "0x47",
+        "EventName": "L1D_CACHE_WB_CLEAN",
+        "BriefDescription": "L1D cache Write-Back, cleaning and coherency"
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data cache invalidate",
+        "EventCode": "0x48",
+        "EventName": "L1D_CACHE_INVAL",
+        "BriefDescription": "L1D cache invalidate"
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data TLB refill, read",
+        "EventCode": "0x4C",
+        "EventName": "L1D_TLB_REFILL_RD",
+        "BriefDescription": "L1D tlb refill, read"
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data TLB refill, write",
+        "EventCode": "0x4D",
+        "EventName": "L1D_TLB_REFILL_WR",
+        "BriefDescription": "L1D tlb refill, write"
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data or unified TLB access, read",
+        "EventCode": "0x4E",
+        "EventName": "L1D_TLB_RD",
+        "BriefDescription": "L1D tlb access, read"
+    },
+    {
+        "PublicDescription": "Attributable Level 1 data or unified TLB access, write",
+        "EventCode": "0x4F",
+        "EventName": "L1D_TLB_WR",
+        "BriefDescription": "L1D tlb access, write"
+    },
+    {
+        "PublicDescription": "Attributable Level 2 data cache access, read",
+        "EventCode": "0x50",
+        "EventName": "L2D_CACHE_RD",
+        "BriefDescription": "L2D cache access, read"
+    },
+    {
+        "PublicDescription": "Attributable Level 2 data cache access, write",
+        "EventCode": "0x51",
+        "EventName": "L2D_CACHE_WR",
+        "BriefDescription": "L2D cache access, write"
+    },
+    {
+        "PublicDescription": "Attributable Level 2 data cache refill, read",
+        "EventCode": "0x52",
+        "EventName": "L2D_CACHE_REFILL_RD",
+        "BriefDescription": "L2D cache refill, read"
+    },
+    {
+        "PublicDescription": "Attributable Level 2 data cache refill, write",
+        "EventCode": "0x53",
+        "EventName": "L2D_CACHE_REFILL_WR",
+        "BriefDescription": "L2D cache refill, write"
+    },
+    {
+        "PublicDescription": "Attributable Level 2 data cache Write-Back, victim",
+        "EventCode": "0x56",
+        "EventName": "L2D_CACHE_WB_VICTIM",
+        "BriefDescription": "L2D cache Write-Back, victim"
+    },
+    {
+        "PublicDescription": "Level 2 data cache Write-Back, cleaning and coherency",
+        "EventCode": "0x57",
+        "EventName": "L2D_CACHE_WB_CLEAN",
+        "BriefDescription": "L2D cache Write-Back, cleaning and coherency"
+    },
+    {
+        "PublicDescription": "Attributable Level 2 data cache invalidate",
+        "EventCode": "0x58",
+        "EventName": "L2D_CACHE_INVAL",
+        "BriefDescription": "L2D cache invalidate"
+    },
+    {
+        "PublicDescription": "Attributable Level 2 data or unified TLB refill, read",
+        "EventCode": "0x5c",
+        "EventName": "L2D_TLB_REFILL_RD",
+        "BriefDescription": "L2D cache refill, read"
+    },
+    {
+        "PublicDescription": "Attributable Level 2 data or unified TLB refill, write",
+        "EventCode": "0x5d",
+        "EventName": "L2D_TLB_REFILL_WR",
+        "BriefDescription": "L2D cache refill, write"
+    },
+    {
+        "PublicDescription": "Attributable Level 2 data or unified TLB access, read",
+        "EventCode": "0x5e",
+        "EventName": "L2D_TLB_RD",
+        "BriefDescription": "L2D cache access, read"
+    },
+    {
+        "PublicDescription": "Attributable Level 2 data or unified TLB access, write",
+        "EventCode": "0x5f",
+        "EventName": "L2D_TLB_WR",
+        "BriefDescription": "L2D cache access, write"
+    },
+    {
+        "PublicDescription": "Bus access read",
+        "EventCode": "0x60",
+        "EventName": "BUS_ACCESS_RD",
+        "BriefDescription": "Bus access read"
+   },
+   {
+        "PublicDescription": "Bus access write",
+        "EventCode": "0x61",
+        "EventName": "BUS_ACCESS_WR",
+        "BriefDescription": "Bus access write"
+   }
+   {
+        "PublicDescription": "Bus access, Normal, Cacheable, Shareable",
+        "EventCode": "0x62",
+        "EventName": "BUS_ACCESS_SHARED",
+        "BriefDescription": "Bus access, Normal, Cacheable, Shareable"
+   }
+   {
+        "PublicDescription": "Bus access, not Normal, Cacheable, Shareable",
+        "EventCode": "0x63",
+        "EventName": "BUS_ACCESS_NOT_SHARED",
+        "BriefDescription": "Bus access, not Normal, Cacheable, Shareable"
+   }
+   {
+        "PublicDescription": "Bus access, Normal",
+        "EventCode": "0x64",
+        "EventName": "BUS_ACCESS_NORMAL",
+        "BriefDescription": "Bus access, Normal"
+   }
+   {
+        "PublicDescription": "Bus access, peripheral",
+        "EventCode": "0x65",
+        "EventName": "BUS_ACCESS_PERIPH",
+        "BriefDescription": "Bus access, peripheral"
+   }
+   {
+        "PublicDescription": "Data memory access, read",
+        "EventCode": "0x66",
+        "EventName": "MEM_ACCESS_RD",
+        "BriefDescription": "Data memory access, read"
+   }
+   {
+        "PublicDescription": "Data memory access, write",
+        "EventCode": "0x67",
+        "EventName": "MEM_ACCESS_WR",
+        "BriefDescription": "Data memory access, write"
+   }
+   {
+        "PublicDescription": "Unaligned access, read",
+        "EventCode": "0x68",
+        "EventName": "UNALIGNED_LD_SPEC",
+        "BriefDescription": "Unaligned access, read"
+   }
+   {
+        "PublicDescription": "Unaligned access, write",
+        "EventCode": "0x69",
+        "EventName": "UNALIGNED_ST_SPEC",
+        "BriefDescription": "Unaligned access, write"
+   }
+   {
+        "PublicDescription": "Unaligned access",
+        "EventCode": "0x6a",
+        "EventName": "UNALIGNED_LDST_SPEC",
+        "BriefDescription": "Unaligned access"
+   }
+   {
+        "PublicDescription": "Exclusive operation speculatively executed, LDREX or LDX",
+        "EventCode": "0x6c",
+        "EventName": "LDREX_SPEC",
+        "BriefDescription": "Exclusive operation speculatively executed, LDREX or LDX"
+   }
+   {
+        "PublicDescription": "Exclusive operation speculatively executed, STREX or STX pass",
+        "EventCode": "0x6d",
+        "EventName": "STREX_PASS_SPEC",
+        "BriefDescription": "Exclusive operation speculatively executed, STREX or STX pass"
+   }
+   {
+        "PublicDescription": "Exclusive operation speculatively executed, STREX or STX fail",
+        "EventCode": "0x6e",
+        "EventName": "STREX_FAIL_SPEC",
+        "BriefDescription": "Exclusive operation speculatively executed, STREX or STX fail"
+   }
+   {
+        "PublicDescription": "Exclusive operation speculatively executed, STREX or STX",
+        "EventCode": "0x6f",
+        "EventName": "STREX_SPEC",
+        "BriefDescription": "Exclusive operation speculatively executed, STREX or STX"
+   }
+   {
+        "PublicDescription": "Operation speculatively executed, load",
+        "EventCode": "0x70",
+        "EventName": "LD_SPEC",
+        "BriefDescription": "Operation speculatively executed, load"
+   }
+   {
+        "PublicDescription": "Operation speculatively executed, store"
+        "EventCode": "0x71",
+        "EventName": "ST_SPEC",
+        "BriefDescription": "Operation speculatively executed, store"
+   }
+   {
+        "PublicDescription": "Operation speculatively executed, load or store",
+        "EventCode": "0x72",
+        "EventName": "LDST_SPEC",
+        "BriefDescription": "Operation speculatively executed, load or store"
+   }
+   {
+        "PublicDescription": "Operation speculatively executed, integer data processing",
+        "EventCode": "0x73",
+        "EventName": "DP_SPEC",
+        "BriefDescription": "Operation speculatively executed, integer data processing"
+   }
+   {
+        "PublicDescription": "Operation speculatively executed, Advanced SIMD instruction",
+        "EventCode": "0x74",
+        "EventName": "ASE_SPEC",
+        "BriefDescription": "Operation speculatively executed, Advanced SIMD instruction",
+   }
+   {
+        "PublicDescription": "Operation speculatively executed, floating-point instruction",
+        "EventCode": "0x75",
+        "EventName": "VFP_SPEC",
+        "BriefDescription": "Operation speculatively executed, floating-point instruction"
+   }
+   {
+        "PublicDescription": "Operation speculatively executed, software change of the PC",
+        "EventCode": "0x76",
+        "EventName": "PC_WRITE_SPEC",
+        "BriefDescription": "Operation speculatively executed, software change of the PC"
+   }
+   {
+        "PublicDescription": "Operation speculatively executed, Cryptographic instruction",
+        "EventCode": "0x77",
+        "EventName": "CRYPTO_SPEC",
+        "BriefDescription": "Operation speculatively executed, Cryptographic instruction"
+   }
+   {
+        "PublicDescription": "Branch speculatively executed, immediate branch"
+        "EventCode": "0x78",
+        "EventName": "BR_IMMED_SPEC",
+        "BriefDescription": "Branch speculatively executed, immediate branch"
+   }
+   {
+        "PublicDescription": "Branch speculatively executed, procedure return"
+        "EventCode": "0x79",
+        "EventName": "BR_RETURN_SPEC",
+        "BriefDescription": "Branch speculatively executed, procedure return"
+   }
+   {
+        "PublicDescription": "Branch speculatively executed, indirect branch"
+        "EventCode": "0x7a",
+        "EventName": "BR_INDIRECT_SPEC",
+        "BriefDescription": "Branch speculatively executed, indirect branch"
+   }
+   {
+        "PublicDescription": "Barrier speculatively executed, ISB"
+        "EventCode": "0x7c",
+        "EventName": "ISB_SPEC",
+        "BriefDescription": "Barrier speculatively executed, ISB"
+   }
+   {
+        "PublicDescription": "Barrier speculatively executed, DSB"
+        "EventCode": "0x7d",
+        "EventName": "DSB_SPEC",
+        "BriefDescription": "Barrier speculatively executed, DSB"
+   }
+   {
+        "PublicDescription": "Barrier speculatively executed, DMB"
+        "EventCode": "0x7e",
+        "EventName": "DMB_SPEC",
+        "BriefDescription": "Barrier speculatively executed, DMB"
+   }
+   {
+        "PublicDescription": "Exception taken, Other synchronous"
+        "EventCode": "0x81",
+        "EventName": "EXC_UNDEF",
+        "BriefDescription": "Exception taken, Other synchronous"
+   }
+   {
+        "PublicDescription": "Exception taken, Supervisor Call"
+        "EventCode": "0x82",
+        "EventName": "EXC_SVC",
+        "BriefDescription": "Exception taken, Supervisor Call"
+   }
+   {
+        "PublicDescription": "Exception taken, Instruction Abort"
+        "EventCode": "0x83",
+        "EventName": "EXC_PABORT",
+        "BriefDescription": "Exception taken, Instruction Abort"
+   }
+   {
+        "PublicDescription": "Exception taken, Data Abort and SError"
+        "EventCode": "0x84",
+        "EventName": "EXC_DABORT",
+        "BriefDescription": "Exception taken, Data Abort and SError"
+   }
+   {
+        "PublicDescription": "Exception taken, IRQ"
+        "EventCode": "0x86",
+        "EventName": "EXC_IRQ",
+        "BriefDescription": "Exception taken, IRQ"
+   }
+   {
+        "PublicDescription": "Exception taken, FIQ"
+        "EventCode": "0x87",
+        "EventName": "EXC_FIQ",
+        "BriefDescription": "Exception taken, FIQ"
+   }
+   {
+        "PublicDescription": "Exception taken, Secure Monitor Call"
+        "EventCode": "0x88",
+        "EventName": "EXC_SMC",
+        "BriefDescription": "Exception taken, Secure Monitor Call"
+   }
+   {
+        "PublicDescription": "Exception taken, Hypervisor Call"
+        "EventCode": "0x8a",
+        "EventName": "EXC_HVC",
+        "BriefDescription": "Exception taken, Hypervisor Call"
+   }
+   {
+        "PublicDescription": "Exception taken, Instruction Abort not taken locally"
+        "EventCode": "0x8b",
+        "EventName": "EXC_TRAP_PABORT",
+        "BriefDescription": "Exception taken, Instruction Abort not taken locally"
+   }
+   {
+        "PublicDescription": "Exception taken, Data Abort or SError not taken locally"
+        "EventCode": "0x8c",
+        "EventName": "EXC_TRAP_DABORT",
+        "BriefDescription": "Exception taken, Data Abort or SError not taken locally"
+   }
+   {
+        "PublicDescription": "Exception taken, Other traps not taken locally"
+        "EventCode": "0x8d",
+        "EventName": "EXC_TRAP_OTHER",
+        "BriefDescription": "Exception taken, Other traps not taken locally"
+   }
+   {
+        "PublicDescription": "Exception taken, IRQ not taken locally"
+        "EventCode": "0x8e",
+        "EventName": "EXC_TRAP_IRQ",
+        "BriefDescription": "Exception taken, IRQ not taken locally"
+   }
+   {
+        "PublicDescription": "Exception taken, FIQ not taken locally"
+        "EventCode": "0x8f",
+        "EventName": "EXC_TRAP_FIQ",
+        "BriefDescription": "Exception taken, FIQ not taken locally"
+   }
+   {
+        "PublicDescription": "Release consistency operation speculatively executed, Load-Acquire"
+        "EventCode": "0x90",
+        "EventName": "RC_LD_SPEC",
+        "BriefDescription": "Release consistency operation speculatively executed, Load-Acquire"
+   }
+   {
+        "PublicDescription": "Release consistency operation speculatively executed, Store-Release"
+        "EventCode": "0x91",
+        "EventName": "RC_ST_SPEC",
+        "BriefDescription": "Release consistency operation speculatively executed, Store-Release"
+   }
+   {
+        "PublicDescription": "Attributable Level 3 data or unified cache access, read"
+        "EventCode": "0xa0",
+        "EventName": "L3D_CACHE_RD",
+        "BriefDescription": "Attributable Level 3 data or unified cache access, read"
+   }
+   {
+        "PublicDescription": "Attributable Level 3 data or unified cache access, write"
+        "EventCode": "0xa1",
+        "EventName": "L3D_CACHE_WR",
+        "BriefDescription": "Attributable Level 3 data or unified cache access, write"
+   }
+   {
+        "PublicDescription": "Attributable Level 3 data or unified cache refill, read"
+        "EventCode": "0xa2",
+        "EventName": "L3D_CACHE_REFILL_RD",
+        "BriefDescription": "Attributable Level 3 data or unified cache refill, read"
+   }
+   {
+        "PublicDescription": "Attributable Level 3 data or unified cache refill, write"
+        "EventCode": "0xa3",
+        "EventName": "L3D_CACHE_REFILL_WR",
+        "BriefDescription": "Attributable Level 3 data or unified cache refill, write"
+   }
+   {
+        "PublicDescription": "Attributable Level 3 data or unified cache Write-Back, victim"
+        "EventCode": "0xa6",
+        "EventName": "L3D_CACHE_WB_VICTIM",
+        "BriefDescription": "Attributable Level 3 data or unified cache Write-Back, victim"
+   }
+   {
+        "PublicDescription": "Attributable Level 3 data or unified cache Write-Back, cache clean"
+        "EventCode": "0xa7",
+        "EventName": "L3D_CACHE_WB_CLEAN",
+        "BriefDescription": "Attributable Level 3 data or unified cache Write-Back, cache clean"
+   }
+   {
+        "PublicDescription": "Attributable Level 3 data or unified cache access, invalidate"
+        "EventCode": "0xa8",
+        "EventName": "L3D_CACHE_INVAL",
+        "BriefDescription": "Attributable Level 3 data or unified cache access, invalidate"
+   }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2-imp-def.json b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2-imp-def.json
deleted file mode 100644
index 2db45c40ebc7..000000000000
--- a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2-imp-def.json
+++ /dev/null
@@ -1,62 +0,0 @@
-[
-    {
-        "PublicDescription": "Attributable Level 1 data cache access, read",
-        "EventCode": "0x40",
-        "EventName": "l1d_cache_rd",
-        "BriefDescription": "L1D cache read",
-    },
-    {
-        "PublicDescription": "Attributable Level 1 data cache access, write ",
-        "EventCode": "0x41",
-        "EventName": "l1d_cache_wr",
-        "BriefDescription": "L1D cache write",
-    },
-    {
-        "PublicDescription": "Attributable Level 1 data cache refill, read",
-        "EventCode": "0x42",
-        "EventName": "l1d_cache_refill_rd",
-        "BriefDescription": "L1D cache refill read",
-    },
-    {
-        "PublicDescription": "Attributable Level 1 data cache refill, write",
-        "EventCode": "0x43",
-        "EventName": "l1d_cache_refill_wr",
-        "BriefDescription": "L1D refill write",
-    },
-    {
-        "PublicDescription": "Attributable Level 1 data TLB refill, read",
-        "EventCode": "0x4C",
-        "EventName": "l1d_tlb_refill_rd",
-        "BriefDescription": "L1D tlb refill read",
-    },
-    {
-        "PublicDescription": "Attributable Level 1 data TLB refill, write",
-        "EventCode": "0x4D",
-        "EventName": "l1d_tlb_refill_wr",
-        "BriefDescription": "L1D tlb refill write",
-    },
-    {
-        "PublicDescription": "Attributable Level 1 data or unified TLB access, read",
-        "EventCode": "0x4E",
-        "EventName": "l1d_tlb_rd",
-        "BriefDescription": "L1D tlb read",
-    },
-    {
-        "PublicDescription": "Attributable Level 1 data or unified TLB access, write",
-        "EventCode": "0x4F",
-        "EventName": "l1d_tlb_wr",
-        "BriefDescription": "L1D tlb write",
-    },
-    {
-        "PublicDescription": "Bus access read",
-        "EventCode": "0x60",
-        "EventName": "bus_access_rd",
-        "BriefDescription": "Bus access read",
-   },
-   {
-        "PublicDescription": "Bus access write",
-        "EventCode": "0x61",
-        "EventName": "bus_access_wr",
-        "BriefDescription": "Bus access write",
-   }
-]
diff --git a/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
new file mode 100644
index 000000000000..bc03c06c3918
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/cavium/thunderx2/core-imp-def.json
@@ -0,0 +1,32 @@
+[
+    {
+        "ArchStdEvent": "L1D_CACHE_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WR",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_WR",
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_WR",
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_WR",
+    },
+    {
+        "ArchStdEvent": "BUS_ACCESS_RD",
+   },
+   {
+        "ArchStdEvent": "BUS_ACCESS_WR",
+   }
+]
diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json
deleted file mode 100644
index 480d9f7460ab..000000000000
--- a/tools/perf/pmu-events/arch/arm64/cortex-a53/bus.json
+++ /dev/null
@@ -1,22 +0,0 @@
-[
-  {,
-    "EventCode": "0x60",
-    "EventName": "BUS_ACCESS_LD",
-    "BriefDescription": "Bus access - Read"
-  },
-  {,
-    "EventCode": "0x61",
-    "EventName": "BUS_ACCESS_ST",
-    "BriefDescription": "Bus access - Write"
-  },
-  {,
-    "EventCode": "0xC0",
-    "EventName": "EXT_MEM_REQ",
-    "BriefDescription": "External memory request"
-  },
-  {,
-    "EventCode": "0xC1",
-    "EventName": "EXT_MEM_REQ_NC",
-    "BriefDescription": "Non-cacheable external memory request"
-  }
-]
diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json
deleted file mode 100644
index 11baad6344b9..000000000000
--- a/tools/perf/pmu-events/arch/arm64/cortex-a53/cache.json
+++ /dev/null
@@ -1,27 +0,0 @@
-[
-  {,
-    "EventCode": "0xC2",
-    "EventName": "PREFETCH_LINEFILL",
-    "BriefDescription": "Linefill because of prefetch"
-  },
-  {,
-    "EventCode": "0xC3",
-    "EventName": "PREFETCH_LINEFILL_DROP",
-    "BriefDescription": "Instruction Cache Throttle occurred"
-  },
-  {,
-    "EventCode": "0xC4",
-    "EventName": "READ_ALLOC_ENTER",
-    "BriefDescription": "Entering read allocate mode"
-  },
-  {,
-    "EventCode": "0xC5",
-    "EventName": "READ_ALLOC",
-    "BriefDescription": "Read allocate mode"
-  },
-  {,
-    "EventCode": "0xC8",
-    "EventName": "EXT_SNOOP",
-    "BriefDescription": "SCU Snooped data from another CPU for this CPU"
-  }
-]
diff --git a/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json b/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json
deleted file mode 100644
index 73a22402d003..000000000000
--- a/tools/perf/pmu-events/arch/arm64/cortex-a53/other.json
+++ /dev/null
@@ -1,32 +0,0 @@
-[
-  {,
-    "EventCode": "0x86",
-    "EventName": "EXC_IRQ",
-    "BriefDescription": "Exception taken, IRQ"
-  },
-  {,
-    "EventCode": "0x87",
-    "EventName": "EXC_FIQ",
-    "BriefDescription": "Exception taken, FIQ"
-  },
-  {,
-    "EventCode": "0xC6",
-    "EventName": "PRE_DECODE_ERR",
-    "BriefDescription": "Pre-decode error"
-  },
-  {,
-    "EventCode": "0xD0",
-    "EventName": "L1I_CACHE_ERR",
-    "BriefDescription": "L1 Instruction Cache (data or tag) memory error"
-  },
-  {,
-    "EventCode": "0xD1",
-    "EventName": "L1D_CACHE_ERR",
-    "BriefDescription": "L1 Data Cache (data, tag or dirty) memory error, correctable or non-correctable"
-  },
-  {,
-    "EventCode": "0xD2",
-    "EventName": "TLB_ERR",
-    "BriefDescription": "TLB memory error"
-  }
-]
diff --git a/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/core-imp-def.json b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/core-imp-def.json
new file mode 100644
index 000000000000..9f0f15d15f75
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/hisilicon/hip08/core-imp-def.json
@@ -0,0 +1,122 @@
+[
+    {
+        "ArchStdEvent": "L1D_CACHE_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WR",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_REFILL_WR",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_VICTIM",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_WB_CLEAN",
+    },
+    {
+        "ArchStdEvent": "L1D_CACHE_INVAL",
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_REFILL_WR",
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_RD",
+    },
+    {
+        "ArchStdEvent": "L1D_TLB_WR",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WR",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL_RD",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_REFILL_WR",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB_VICTIM",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_WB_CLEAN",
+    },
+    {
+        "ArchStdEvent": "L2D_CACHE_INVAL",
+    },
+    {
+        "PublicDescription": "Level 1 instruction cache prefetch access count",
+        "EventCode": "0x102e",
+        "EventName": "L1I_CACHE_PRF",
+        "BriefDescription": "L1I cache prefetch access count",
+    },
+    {
+        "PublicDescription": "Level 1 instruction cache miss due to prefetch access count",
+        "EventCode": "0x102f",
+        "EventName": "L1I_CACHE_PRF_REFILL",
+        "BriefDescription": "L1I cache miss due to prefetch access count",
+    },
+    {
+        "PublicDescription": "Instruction queue is empty",
+        "EventCode": "0x1043",
+        "EventName": "IQ_IS_EMPTY",
+        "BriefDescription": "Instruction queue is empty",
+    },
+    {
+        "PublicDescription": "Instruction fetch stall cycles",
+        "EventCode": "0x1044",
+        "EventName": "IF_IS_STALL",
+        "BriefDescription": "Instruction fetch stall cycles",
+    },
+    {
+        "PublicDescription": "Instructions can receive, but not send",
+        "EventCode": "0x2014",
+        "EventName": "FETCH_BUBBLE",
+        "BriefDescription": "Instructions can receive, but not send",
+    },
+    {
+        "PublicDescription": "Prefetch request from LSU",
+        "EventCode": "0x6013",
+        "EventName": "PRF_REQ",
+        "BriefDescription": "Prefetch request from LSU",
+    },
+    {
+        "PublicDescription": "Hit on prefetched data",
+        "EventCode": "0x6014",
+        "EventName": "HIT_ON_PRF",
+        "BriefDescription": "Hit on prefetched data",
+    },
+    {
+        "PublicDescription": "Cycles of that the number of issuing micro operations are less than 4",
+        "EventCode": "0x7001",
+        "EventName": "EXE_STALL_CYCLE",
+        "BriefDescription": "Cycles of that the number of issue ups are less than 4",
+    },
+    {
+        "PublicDescription": "No any micro operation is issued and meanwhile any load operation is not resolved",
+        "EventCode": "0x7004",
+        "EventName": "MEM_STALL_ANYLOAD",
+        "BriefDescription": "No any micro operation is issued and meanwhile any load operation is not resolved",
+    },
+    {
+        "PublicDescription": "No any micro operation is issued and meanwhile there is any load operation missing L1 cache and pending data refill",
+        "EventCode": "0x7006",
+        "EventName": "MEM_STALL_L1MISS",
+        "BriefDescription": "No any micro operation is issued and meanwhile there is any load operation missing L1 cache and pending data refill",
+    },
+    {
+        "PublicDescription": "No any micro operation is issued and meanwhile there is any load operation missing both L1 and L2 cache and pending data refill from L3 cache",
+        "EventCode": "0x7007",
+        "EventName": "MEM_STALL_L2MISS",
+        "BriefDescription": "No any micro operation is issued and meanwhile there is any load operation missing both L1 and L2 cache and pending data refill from L3 cache",
+    },
+]
diff --git a/tools/perf/pmu-events/arch/arm64/mapfile.csv b/tools/perf/pmu-events/arch/arm64/mapfile.csv
index e61c9ca6cf9e..f03e26ecb658 100644
--- a/tools/perf/pmu-events/arch/arm64/mapfile.csv
+++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv
@@ -12,5 +12,7 @@
 #
 #
 #Family-model,Version,Filename,EventType
-0x00000000420f5160,v1,cavium,core
-0x00000000410fd03[[:xdigit:]],v1,cortex-a53,core
+0x00000000410fd03[[:xdigit:]],v1,arm/cortex-a53,core
+0x00000000420f5160,v1,cavium/thunderx2,core
+0x00000000430f0af0,v1,cavium/thunderx2,core
+0x00000000480fd010,v1,hisilicon/hip08,core
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/cache.json b/tools/perf/pmu-events/arch/powerpc/power9/cache.json
index 7945c5196c43..851072105054 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/cache.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/cache.json
@@ -20,11 +20,6 @@
     "BriefDescription": "Finish stall due to a scalar fixed point or CR instruction in the execution pipeline. These instructions get routed to the ALU, ALU2, and DIV pipes"
   },
   {,
-    "EventCode": "0x1D15C",
-    "EventName": "PM_MRK_DTLB_MISS_1G",
-    "BriefDescription": "Marked Data TLB reload (after a miss) page size 2M. Implies radix translation was used"
-  },
-  {,
     "EventCode": "0x4D12A",
     "EventName": "PM_MRK_DATA_FROM_RL4_CYC",
     "BriefDescription": "Duration in cycles to reload from another chip's L4 on the same Node or Group ( Remote) due to a marked load"
@@ -80,21 +75,6 @@
     "BriefDescription": "Threshold counter exceed a count of 4096"
   },
   {,
-    "EventCode": "0x3D156",
-    "EventName": "PM_MRK_DTLB_MISS_64K",
-    "BriefDescription": "Marked Data TLB Miss page size 64K"
-  },
-  {,
-    "EventCode": "0x4C15E",
-    "EventName": "PM_MRK_DTLB_MISS_16M",
-    "BriefDescription": "Marked Data TLB Miss page size 16M"
-  },
-  {,
-    "EventCode": "0x2D15E",
-    "EventName": "PM_MRK_DTLB_MISS_16G",
-    "BriefDescription": "Marked Data TLB Miss page size 16G"
-  },
-  {,
     "EventCode": "0x3F14A",
     "EventName": "PM_MRK_DPTEG_FROM_RMEM",
     "BriefDescription": "A Page Table Entry was loaded into the TLB from another chip's memory on the same Node or Group ( Remote) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
@@ -123,10 +103,5 @@
     "EventCode": "0x1002A",
     "EventName": "PM_CMPLU_STALL_LARX",
     "BriefDescription": "Finish stall because the NTF instruction was a larx waiting to be satisfied"
-  },
-  {,
-    "EventCode": "0x1C058",
-    "EventName": "PM_DTLB_MISS_16G",
-    "BriefDescription": "Data TLB Miss page size 16G"
   }
 ]
\ No newline at end of file
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/frontend.json b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
index bd8361b5fd6a..f9fa84b16fb5 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/frontend.json
@@ -155,11 +155,6 @@
     "BriefDescription": "Duration in cycles to reload with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a marked load"
   },
   {,
-    "EventCode": "0x3C056",
-    "EventName": "PM_DTLB_MISS_64K",
-    "BriefDescription": "Data TLB Miss page size 64K"
-  },
-  {,
     "EventCode": "0x30060",
     "EventName": "PM_TM_TRANS_RUN_INST",
     "BriefDescription": "Run instructions completed in transactional state (gated by the run latch)"
@@ -345,11 +340,6 @@
     "BriefDescription": "Larx finished"
   },
   {,
-    "EventCode": "0x4C056",
-    "EventName": "PM_DTLB_MISS_16M",
-    "BriefDescription": "Data TLB Miss page size 16M"
-  },
-  {,
     "EventCode": "0x1003A",
     "EventName": "PM_CMPLU_STALL_LSU_FIN",
     "BriefDescription": "Finish stall because the NTF instruction was an LSU op (other than a load or a store) with all its dependencies met and just going through the LSU pipe to finish"
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/marked.json b/tools/perf/pmu-events/arch/powerpc/power9/marked.json
index 22f9f32060a8..b1954c38bab1 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/marked.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/marked.json
@@ -530,11 +530,6 @@
     "BriefDescription": "Counts all Icache reloads includes demand, prefetch, prefetch turned into demand and demand turned into prefetch"
   },
   {,
-    "EventCode": "0x4003C",
-    "EventName": "PM_DISP_HELD_SYNC_HOLD",
-    "BriefDescription": "Cycles in which dispatch is held because of a synchronizing instruction in the pipeline"
-  },
-  {,
     "EventCode": "0x3003C",
     "EventName": "PM_CMPLU_STALL_NESTED_TEND",
     "BriefDescription": "Completion stall because the ISU is updating the TEXASR to keep track of the nested tend and decrement the TEXASR nested level. This is a short delay"
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/memory.json b/tools/perf/pmu-events/arch/powerpc/power9/memory.json
index 9960d1c0dd44..2e2ebc700c74 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/memory.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/memory.json
@@ -45,11 +45,6 @@
     "BriefDescription": "count of Loads completed"
   },
   {,
-    "EventCode": "0x2D156",
-    "EventName": "PM_MRK_DTLB_MISS_4K",
-    "BriefDescription": "Marked Data TLB Miss page size 4k"
-  },
-  {,
     "EventCode": "0x4C042",
     "EventName": "PM_DATA_FROM_L3",
     "BriefDescription": "The processor's data cache was reloaded from local core's L3 due to a demand load"
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/other.json b/tools/perf/pmu-events/arch/powerpc/power9/other.json
index 5ce312973f1e..48cf4f920b3f 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/other.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/other.json
@@ -70,6 +70,11 @@
     "BriefDescription": "Cycles thread running at priority level 0 or 1"
   },
   {,
+    "EventCode": "0x4C054",
+    "EventName": "PM_DERAT_MISS_16G_1G",
+    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16G (hpt mode) or 1G (radix mode)"
+  },
+  {,
     "EventCode": "0x2084",
     "EventName": "PM_FLUSH_HB_RESTORE_CYC",
     "BriefDescription": "Cycles in which no new instructions can be dispatched to the ICT after a flush.  History buffer recovery"
@@ -107,12 +112,12 @@
   {,
     "EventCode": "0x360B2",
     "EventName": "PM_L3_GRP_GUESS_WRONG_LOW",
-    "BriefDescription": "Initial scope=group (GS or NNS) but data from outside group (far or rem). Prediction too Low"
+    "BriefDescription": "Prefetch scope predictor selected GS or NNS, but was wrong because scope was LNS"
   },
   {,
     "EventCode": "0x168A6",
     "EventName": "PM_TM_CAM_OVERFLOW",
-    "BriefDescription": "L3 TM cam overflow during L2 co of SC"
+    "BriefDescription": "L3 TM CAM is full when a L2 castout of TM_SC line occurs.  Line is pushed to memory"
   },
   {,
     "EventCode": "0xE8B0",
@@ -150,11 +155,6 @@
     "BriefDescription": "All ISU rejects"
   },
   {,
-    "EventCode": "0x460A6",
-    "EventName": "PM_RD_FORMING_SC",
-    "BriefDescription": "Read forming SC"
-  },
-  {,
     "EventCode": "0x468A0",
     "EventName": "PM_L3_PF_OFF_CHIP_MEM",
     "BriefDescription": "L3 PF from Off chip memory"
@@ -187,7 +187,7 @@
   {,
     "EventCode": "0x368A6",
     "EventName": "PM_SNP_TM_HIT_T",
-    "BriefDescription": "Snp TM sthit T/Tn/Te"
+    "BriefDescription": "TM snoop that is a store hits line in L3 in T, Tn or Te state (shared modified)"
   },
   {,
     "EventCode": "0x3001A",
@@ -205,6 +205,11 @@
     "BriefDescription": "Duration in cycles to reload with Modified (M) data from another core's ECO L3 on the same chip due to a marked load"
   },
   {,
+    "EventCode": "0xF0B4",
+    "EventName": "PM_DC_PREF_CONS_ALLOC",
+    "BriefDescription": "Prefetch stream allocated in the conservative phase by either the hardware prefetch mechanism or software prefetch. The sum of this pair subtracted from the total number of allocs will give the total allocs in normal phase"
+  },
+  {,
     "EventCode": "0xF894",
     "EventName": "PM_LSU3_L1_CAM_CANCEL",
     "BriefDescription": "ls3 l1 tm cam cancel"
@@ -227,7 +232,12 @@
   {,
     "EventCode": "0x468A6",
     "EventName": "PM_RD_CLEARING_SC",
-    "BriefDescription": "Read clearing SC"
+    "BriefDescription": "Core TM load hits line in L3 in TM_SC state and causes it to be invalidated"
+  },
+  {,
+    "EventCode": "0xD0B0",
+    "EventName": "PM_HWSYNC",
+    "BriefDescription": ""
   },
   {,
     "EventCode": "0x168B0",
@@ -265,6 +275,11 @@
     "BriefDescription": "Prefetch stream allocated by the hardware prefetch mechanism"
   },
   {,
+    "EventCode": "0xF0BC",
+    "EventName": "PM_LS2_UNALIGNED_ST",
+    "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size.  If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
     "EventCode": "0xD0AC",
     "EventName": "PM_SRQ_SYNC_CYC",
     "BriefDescription": "A sync is in the S2Q (edge detect to count)"
@@ -275,6 +290,11 @@
     "BriefDescription": "Marked instruction was reloaded from a location beyond the local chiplet"
   },
   {,
+    "EventCode": "0x58A8",
+    "EventName": "PM_DECODE_HOLD_ICT_FULL",
+    "BriefDescription": "Counts the number of cycles in which the IFU was not able to decode and transmit one or more instructions because all itags were in use.  This means the ICT is full for this thread"
+  },
+  {,
     "EventCode": "0x26082",
     "EventName": "PM_L2_IC_INV",
     "BriefDescription": "I-cache Invalidates sent over the realod bus to the core"
@@ -365,6 +385,16 @@
     "BriefDescription": "Duration in cycles to reload either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a marked load"
   },
   {,
+    "EventCode": "0xF888",
+    "EventName": "PM_LSU1_STORE_REJECT",
+    "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met"
+  },
+  {,
+    "EventCode": "0xC098",
+    "EventName": "PM_LS2_UNALIGNED_LD",
+    "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size.  If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
     "EventCode": "0x20058",
     "EventName": "PM_DARQ1_10_12_ENTRIES",
     "BriefDescription": "Cycles in which 10 or  more DARQ1 entries (out of 12) are in use"
@@ -372,7 +402,7 @@
   {,
     "EventCode": "0x360A6",
     "EventName": "PM_SNP_TM_HIT_M",
-    "BriefDescription": "Snp TM st hit M/Mu"
+    "BriefDescription": "TM snoop that is a store hits line in L3 in M or Mu state (exclusive modified)"
   },
   {,
     "EventCode": "0x5898",
@@ -395,9 +425,9 @@
     "BriefDescription": "A data line was written to the L1 due to a hardware or software prefetch"
   },
   {,
-    "EventCode": "0xF888",
-    "EventName": "PM_LSU1_STORE_REJECT",
-    "BriefDescription": "All internal store rejects cause the instruction to go back to the SRQ and go to sleep until woken up to try again after the condition has been met"
+    "EventCode": "0x2608E",
+    "EventName": "PM_TM_LD_CONF",
+    "BriefDescription": "TM Load (fav or non-fav) ran into conflict (failed)"
   },
   {,
     "EventCode": "0x1D144",
@@ -422,7 +452,7 @@
   {,
     "EventCode": "0x26884",
     "EventName": "PM_DSIDE_MRU_TOUCH",
-    "BriefDescription": "D-side L2 MRU touch sent to L2"
+    "BriefDescription": "D-side L2 MRU touch commands sent to the L2"
   },
   {,
     "EventCode": "0x30134",
@@ -440,6 +470,16 @@
     "BriefDescription": "XL-form branch was mispredicted due to the predicted target address missing from EAT.  The EAT forces a mispredict in this case since there is no predicated target to validate.  This is a rare case that may occur when the EAT is full and a branch is issued"
   },
   {,
+    "EventCode": "0xC094",
+    "EventName": "PM_LS0_UNALIGNED_LD",
+    "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size.  If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
+    "EventCode": "0xF8BC",
+    "EventName": "PM_LS3_UNALIGNED_ST",
+    "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size.  If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
     "EventCode": "0x460AE",
     "EventName": "PM_L3_P2_CO_RTY",
     "BriefDescription": "L3 CO received retry port 2 (memory only), every retry counted"
@@ -492,7 +532,7 @@
   {,
     "EventCode": "0xC880",
     "EventName": "PM_LS1_LD_VECTOR_FIN",
-    "BriefDescription": ""
+    "BriefDescription": "LS1 finished load vector op"
   },
   {,
     "EventCode": "0x2894",
@@ -515,6 +555,11 @@
     "BriefDescription": "Marked derat reload (miss) for any page size"
   },
   {,
+    "EventCode": "0x160A0",
+    "EventName": "PM_L3_PF_MISS_L3",
+    "BriefDescription": "L3 PF missed in L3"
+  },
+  {,
     "EventCode": "0x1C04A",
     "EventName": "PM_DATA_FROM_RL2L3_SHR",
     "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a demand load"
@@ -565,11 +610,21 @@
     "BriefDescription": "L2 guess local (LNS) and guess was not correct (ie data not on chip)"
   },
   {,
+    "EventCode": "0xC888",
+    "EventName": "PM_LSU_DTLB_MISS_64K",
+    "BriefDescription": "Data TLB Miss page size 64K"
+  },
+  {,
     "EventCode": "0xE0A4",
     "EventName": "PM_TMA_REQ_L2",
     "BriefDescription": "addrs only req to L2 only on the first one,Indication that Load footprint is not expanding"
   },
   {,
+    "EventCode": "0xC088",
+    "EventName": "PM_LSU_DTLB_MISS_4K",
+    "BriefDescription": "Data TLB Miss page size 4K"
+  },
+  {,
     "EventCode": "0x3C042",
     "EventName": "PM_DATA_FROM_L3_DISP_CONFLICT",
     "BriefDescription": "The processor's data cache was reloaded from local core's L3 with dispatch conflict due to a demand load"
@@ -602,7 +657,7 @@
   {,
     "EventCode": "0x26084",
     "EventName": "PM_L2_RCLD_DISP_FAIL_OTHER",
-    "BriefDescription": "All I-or-D side load dispatch attempts for this thread that failed due to reason other than address collision (excludes i_l2mru_tch_reqs)"
+    "BriefDescription": "All D-side-Ld or I-side-instruction-fetch dispatch attempts for this thread that failed due to reasons other than an address collision conflicts with an L2 machines (e.g. Read-Claim/Snoop machine not available)"
   },
   {,
     "EventCode": "0x101E4",
@@ -647,12 +702,12 @@
   {,
     "EventCode": "0x46080",
     "EventName": "PM_L2_DISP_ALL_L2MISS",
-    "BriefDescription": "All successful Ld/St dispatches for this thread that were an L2 miss (excludes i_l2mru_tch_reqs)"
+    "BriefDescription": "All successful D-side-Ld/St or I-side-instruction-fetch dispatches for this thread that were an L2 miss"
   },
   {,
-    "EventCode": "0x160A0",
-    "EventName": "PM_L3_PF_MISS_L3",
-    "BriefDescription": "L3 PF missed in L3"
+    "EventCode": "0xF8B8",
+    "EventName": "PM_LS1_UNALIGNED_ST",
+    "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size.  If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
   },
   {,
     "EventCode": "0x408C",
@@ -667,7 +722,7 @@
   {,
     "EventCode": "0x160B2",
     "EventName": "PM_L3_LOC_GUESS_CORRECT",
-    "BriefDescription": "initial scope=node/chip (LNS) and data from local node (local) (pred successful) - always PFs only"
+    "BriefDescription": "Prefetch scope predictor selected LNS and was correct"
   },
   {,
     "EventCode": "0x48B4",
@@ -767,7 +822,7 @@
   {,
     "EventCode": "0x36082",
     "EventName": "PM_L2_LD_DISP",
-    "BriefDescription": "All successful I-or-D side load dispatches for this thread (excludes i_l2mru_tch_reqs)"
+    "BriefDescription": "All successful D-side-Ld or I-side-instruction-fetch dispatches for this thread"
   },
   {,
     "EventCode": "0xF8B0",
@@ -787,7 +842,7 @@
   {,
     "EventCode": "0x16884",
     "EventName": "PM_L2_RCLD_DISP_FAIL_ADDR",
-    "BriefDescription": "All I-od-D side load dispatch attempts for this thread that failed due to address collision with RC/CO/SN/SQ machine (excludes i_l2mru_tch_reqs)"
+    "BriefDescription": "All D-side-Ld or I-side-instruction-fetch dispatch attempts for this thread that failed due to an address collision conflicts with an L2 machines already working on this line (e.g. ld-hit-stq or Read-claim/Castout/Snoop machines)"
   },
   {,
     "EventCode": "0x460A0",
@@ -830,6 +885,11 @@
     "BriefDescription": "Instruction prefetch requests"
   },
   {,
+    "EventCode": "0xC898",
+    "EventName": "PM_LS3_UNALIGNED_LD",
+    "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size.  If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
     "EventCode": "0x488C",
     "EventName": "PM_IC_PREF_WRITE",
     "BriefDescription": "Instruction prefetch written into IL1"
@@ -837,7 +897,7 @@
   {,
     "EventCode": "0xF89C",
     "EventName": "PM_XLATE_MISS",
-    "BriefDescription": "The LSU requested a line from L2 for translation.  It may be satisfied from any source beyond L2.  Includes speculative instructions"
+    "BriefDescription": "The LSU requested a line from L2 for translation.  It may be satisfied from any source beyond L2.  Includes speculative instructions. Includes instruction, prefetch and demand"
   },
   {,
     "EventCode": "0x14158",
@@ -850,9 +910,14 @@
     "BriefDescription": "Duration in cycles to reload with Shared (S) data from another core's L3 on the same chip due to a marked load"
   },
   {,
+    "EventCode": "0xC88C",
+    "EventName": "PM_LSU_DTLB_MISS_16G_1G",
+    "BriefDescription": "Data TLB Miss page size 16G (HPT) or 1G (Radix)"
+  },
+  {,
     "EventCode": "0x268A6",
     "EventName": "PM_TM_RST_SC",
-    "BriefDescription": "TM-snp rst RM SC"
+    "BriefDescription": "TM snoop hits line in L3 that is TM_SC state and causes it to be invalidated"
   },
   {,
     "EventCode": "0x468A4",
@@ -917,7 +982,7 @@
   {,
     "EventCode": "0x46086",
     "EventName": "PM_L2_SN_M_RD_DONE",
-    "BriefDescription": "SNP dispatched for a read and was M (true M)"
+    "BriefDescription": "Snoop dispatched for a read and was M (true M)"
   },
   {,
     "EventCode": "0x40154",
@@ -980,14 +1045,9 @@
     "BriefDescription": "Link stack predicts right address"
   },
   {,
-    "EventCode": "0x4C05A",
-    "EventName": "PM_DTLB_MISS_1G",
-    "BriefDescription": "Data TLB reload (after a miss) page size 1G. Implies radix translation was used"
-  },
-  {,
     "EventCode": "0x36886",
     "EventName": "PM_L2_SN_SX_I_DONE",
-    "BriefDescription": "SNP dispatched and went from Sx to Ix"
+    "BriefDescription": "Snoop dispatched and went from Sx to Ix"
   },
   {,
     "EventCode": "0x4E04A",
@@ -1000,11 +1060,6 @@
     "BriefDescription": "Duration in cycles to reload from another chip's L4 on a different Node or Group (Distant) due to a marked load"
   },
   {,
-    "EventCode": "0x2608E",
-    "EventName": "PM_TM_LD_CONF",
-    "BriefDescription": "TM Load (fav or non-fav) ran into conflict (failed)"
-  },
-  {,
     "EventCode": "0x4080",
     "EventName": "PM_INST_FROM_L1",
     "BriefDescription": "Instruction fetches from L1.  L1 instruction hit"
@@ -1037,7 +1092,7 @@
   {,
     "EventCode": "0x260A6",
     "EventName": "PM_NON_TM_RST_SC",
-    "BriefDescription": "Non-TM snp rst TM SC"
+    "BriefDescription": "Non-TM snoop hits line in L3 that is TM_SC state and causes it to be invalidated"
   },
   {,
     "EventCode": "0x3608A",
@@ -1065,11 +1120,6 @@
     "BriefDescription": "Branch mispredict flushes.  Includes target and address misprecition"
   },
   {,
-    "EventCode": "0x508C",
-    "EventName": "PM_SHL_CREATED",
-    "BriefDescription": "Store-Hit-Load Table Entry Created"
-  },
-  {,
     "EventCode": "0x1504C",
     "EventName": "PM_IPTEG_FROM_LL4",
     "BriefDescription": "A Page Table Entry was loaded into the TLB from the local chip's L4 cache due to a instruction side request"
@@ -1107,7 +1157,7 @@
   {,
     "EventCode": "0x2608A",
     "EventName": "PM_ISIDE_DISP_FAIL_ADDR",
-    "BriefDescription": "All I-side dispatch attempts for this thread that failed due to a addr collision with another machine (excludes i_l2mru_tch_reqs)"
+    "BriefDescription": "All I-side-instruction-fetch dispatch attempts for this thread that failed due to an address collision conflict with an L2 machine already working on this line (e.g. ld-hit-stq or RC/CO/SN machines)"
   },
   {,
     "EventCode": "0x50B4",
@@ -1180,9 +1230,9 @@
     "BriefDescription": "Number of stcx instructions finished. This includes instructions in the speculative path of a branch that may be flushed"
   },
   {,
-    "EventCode": "0xE0B8",
-    "EventName": "PM_LS2_TM_DISALLOW",
-    "BriefDescription": "A TM-ineligible instruction tries to execute inside a transaction and the LSU disallows it"
+    "EventCode": "0xD8AC",
+    "EventName": "PM_LWSYNC",
+    "BriefDescription": ""
   },
   {,
     "EventCode": "0x2094",
@@ -1210,6 +1260,11 @@
     "BriefDescription": "Ict empty for this thread due to dispatch holds because the History Buffer was full. Could be GPR/VSR/VMR/FPR/CR/XVF; CR; XVF (XER/VSCR/FPSCR)"
   },
   {,
+    "EventCode": "0xC894",
+    "EventName": "PM_LS1_UNALIGNED_LD",
+    "BriefDescription": "Load instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the load of that size.  If the load wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
     "EventCode": "0x360A2",
     "EventName": "PM_L3_L2_CO_HIT",
     "BriefDescription": "L2 CO hits"
@@ -1292,7 +1347,7 @@
   {,
     "EventCode": "0xC084",
     "EventName": "PM_LS2_LD_VECTOR_FIN",
-    "BriefDescription": ""
+    "BriefDescription": "LS2 finished load vector op"
   },
   {,
     "EventCode": "0x1608E",
@@ -1345,6 +1400,11 @@
     "BriefDescription": "Continuous 16 cycle (2to1) window where this signals rotates thru sampling each SN machine busy. PMU uses this wave to then do 16 cyc count to sample total number of machs running"
   },
   {,
+    "EventCode": "0x36084",
+    "EventName": "PM_L2_RCST_DISP",
+    "BriefDescription": "All D-side store dispatch attempts for this thread"
+  },
+  {,
     "EventCode": "0x46084",
     "EventName": "PM_L2_RCST_DISP_FAIL_OTHER",
     "BriefDescription": "All D-side store dispatch attempts for this thread that failed due to reason other than address collision"
@@ -1355,11 +1415,6 @@
     "BriefDescription": "A demand load referenced a line in an active strided prefetch stream. The stream could have been allocated through the hardware prefetch mechanism or through software."
   },
   {,
-    "EventCode": "0x36084",
-    "EventName": "PM_L2_RCST_DISP",
-    "BriefDescription": "All D-side store dispatch attempts for this thread"
-  },
-  {,
     "EventCode": "0x45054",
     "EventName": "PM_FMA_CMPL",
     "BriefDescription": "two flops operation completed (fmadd, fnmadd, fmsub, fnmsub) Scalar instructions only. "
@@ -1372,7 +1427,7 @@
   {,
     "EventCode": "0x36080",
     "EventName": "PM_L2_INST",
-    "BriefDescription": "All successful I-side dispatches for this thread   (excludes i_l2mru_tch reqs)"
+    "BriefDescription": "All successful I-side-instruction-fetch (e.g. i-demand, i-prefetch) dispatches for this thread"
   },
   {,
     "EventCode": "0x3504C",
@@ -1387,7 +1442,7 @@
   {,
     "EventCode": "0x1688A",
     "EventName": "PM_ISIDE_DISP",
-    "BriefDescription": "All I-side dispatch attempts for this thread (excludes i_l2mru_tch_reqs)"
+    "BriefDescription": "All I-side-instruction-fetch dispatch attempts for this thread"
   },
   {,
     "EventCode": "0x468AA",
@@ -1420,6 +1475,11 @@
     "BriefDescription": "Load tm hit in L1"
   },
   {,
+    "EventCode": "0xE0B8",
+    "EventName": "PM_LS2_TM_DISALLOW",
+    "BriefDescription": "A TM-ineligible instruction tries to execute inside a transaction and the LSU disallows it"
+  },
+  {,
     "EventCode": "0x44044",
     "EventName": "PM_INST_FROM_L31_ECO_MOD",
     "BriefDescription": "The processor's Instruction cache was reloaded with Modified (M) data from another core's ECO L3 on the same chip due to an instruction fetch (not prefetch)"
@@ -1467,7 +1527,7 @@
   {,
     "EventCode": "0x36086",
     "EventName": "PM_L2_RC_ST_DONE",
-    "BriefDescription": "RC did store to line that was Tx or Sx"
+    "BriefDescription": "Read-claim machine did store to line that was in Tx or Sx (Tagged or Shared state)"
   },
   {,
     "EventCode": "0xE8AC",
@@ -1500,6 +1560,11 @@
     "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 without conflict due to a instruction side request"
   },
   {,
+    "EventCode": "0x460A6",
+    "EventName": "PM_RD_FORMING_SC",
+    "BriefDescription": "Doesn't occur"
+  },
+  {,
     "EventCode": "0x35042",
     "EventName": "PM_IPTEG_FROM_L3_DISP_CONFLICT",
     "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 with dispatch conflict due to a instruction side request"
@@ -1527,7 +1592,7 @@
   {,
     "EventCode": "0x36882",
     "EventName": "PM_L2_LD_HIT",
-    "BriefDescription": "All successful I-or-D side load dispatches for this thread that were L2 hits (excludes i_l2mru_tch_reqs)"
+    "BriefDescription": "All successful D-side-Ld or I-side-instruction-fetch dispatches for this thread that were L2 hits"
   },
   {,
     "EventCode": "0x168AC",
@@ -1555,11 +1620,6 @@
     "BriefDescription": "ProbeNops dispatched"
   },
   {,
-    "EventCode": "0x58A8",
-    "EventName": "PM_DECODE_HOLD_ICT_FULL",
-    "BriefDescription": "Counts the number of cycles in which the IFU was not able to decode and transmit one or more instructions because all itags were in use.  This means the ICT is full for this thread"
-  },
-  {,
     "EventCode": "0x10052",
     "EventName": "PM_GRP_PUMP_MPRED_RTY",
     "BriefDescription": "Final Pump Scope (Group) ended up larger than Initial Pump Scope (Chip) for all data types excluding data prefetch (demand load,inst prefetch,inst fetch,xlate)"
@@ -1572,7 +1632,7 @@
   {,
     "EventCode": "0x2688A",
     "EventName": "PM_ISIDE_DISP_FAIL_OTHER",
-    "BriefDescription": "All I-side dispatch attempts for this thread that failed due to a reason other than addrs collision (excludes i_l2mru_tch_reqs)"
+    "BriefDescription": "All I-side-instruction-fetch dispatch attempts for this thread that failed due to reasons other than an address collision conflict with an L2 machine (e.g. no available RC/CO machines)"
   },
   {,
     "EventCode": "0x2001A",
@@ -1652,12 +1712,12 @@
   {,
     "EventCode": "0x46880",
     "EventName": "PM_ISIDE_MRU_TOUCH",
-    "BriefDescription": "I-side L2 MRU touch sent to L2 for this thread"
+    "BriefDescription": "I-side L2 MRU touch sent to L2 for this thread I-side L2 MRU touch commands sent to the L2 for this thread"
   },
   {,
-    "EventCode": "0x1C05C",
-    "EventName": "PM_DTLB_MISS_2M",
-    "BriefDescription": "Data TLB reload (after a miss) page size 2M. Implies radix translation was used"
+    "EventCode": "0x508C",
+    "EventName": "PM_SHL_CREATED",
+    "BriefDescription": "Store-Hit-Load Table Entry Created"
   },
   {,
     "EventCode": "0x50B8",
@@ -1672,7 +1732,7 @@
   {,
     "EventCode": "0x268B2",
     "EventName": "PM_L3_LOC_GUESS_WRONG",
-    "BriefDescription": "Initial scope=node (LNS) but data from out side local node (near or far or rem). Prediction too Low"
+    "BriefDescription": "Prefetch scope predictor selected LNS, but was wrong"
   },
   {,
     "EventCode": "0x36088",
@@ -1685,6 +1745,11 @@
     "BriefDescription": "L3 PF received retry port 2, every retry counted"
   },
   {,
+    "EventCode": "0xD8B0",
+    "EventName": "PM_PTESYNC",
+    "BriefDescription": ""
+  },
+  {,
     "EventCode": "0x26086",
     "EventName": "PM_CO_TM_SC_FOOTPRINT",
     "BriefDescription": "L2 did a cleanifdirty CO to the L3 (ie created an SC line in the L3) OR L2 TM_store hit dirty HPC line and L3 indicated SC line formed in L3 on RDR bus"
@@ -1740,6 +1805,11 @@
     "BriefDescription": "All successful D-Side Store dispatches that were an L2 miss for this thread"
   },
   {,
+    "EventCode": "0xF8B4",
+    "EventName": "PM_DC_PREF_XCONS_ALLOC",
+    "BriefDescription": "Prefetch stream allocated in the Ultra conservative phase by either the hardware prefetch mechanism or software prefetch"
+  },
+  {,
     "EventCode": "0x35048",
     "EventName": "PM_IPTEG_FROM_DL2L3_SHR",
     "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on a different Node or Group (Distant), as this chip due to a instruction side request"
@@ -1782,7 +1852,7 @@
   {,
     "EventCode": "0x460B2",
     "EventName": "PM_L3_SYS_GUESS_WRONG",
-    "BriefDescription": "Initial scope=system (VGS or RNS) but data from local or near. Prediction too high"
+    "BriefDescription": "Prefetch scope predictor selected VGS or RNS, but was wrong"
   },
   {,
     "EventCode": "0x58B8",
@@ -1800,11 +1870,6 @@
     "BriefDescription": "Completion time tabortnoncd, tabortcd, treclaim"
   },
   {,
-    "EventCode": "0x4C054",
-    "EventName": "PM_DERAT_MISS_16G",
-    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16G"
-  },
-  {,
     "EventCode": "0x268A0",
     "EventName": "PM_L3_CO_L31",
     "BriefDescription": "L3 CO to L3.1 OR of port 0 and 1 (lossy = may undercount if two cresps come in the same cyc)"
@@ -1862,7 +1927,7 @@
   {,
     "EventCode": "0x368B2",
     "EventName": "PM_L3_GRP_GUESS_WRONG_HIGH",
-    "BriefDescription": "Initial scope=group (GS or NNS) but data from local node. Prediction too high"
+    "BriefDescription": "Prefetch scope predictor selected GS or NNS, but was wrong because scope was VGS or RNS"
   },
   {,
     "EventCode": "0xE8BC",
@@ -1897,7 +1962,7 @@
   {,
     "EventCode": "0x260B2",
     "EventName": "PM_L3_SYS_GUESS_CORRECT",
-    "BriefDescription": "Initial scope=system (VGS or RNS) and data from outside group (far or rem)(pred successful)"
+    "BriefDescription": "Prefetch scope predictor selected VGS or RNS and was correct"
   },
   {,
     "EventCode": "0x1D146",
@@ -1915,6 +1980,11 @@
     "BriefDescription": "RC requests that were on group (aka nodel) pump attempts"
   },
   {,
+    "EventCode": "0xC08C",
+    "EventName": "PM_LSU_DTLB_MISS_16M_2M",
+    "BriefDescription": "Data TLB Miss page size 16M (HPT) or 2M (Radix)"
+  },
+  {,
     "EventCode": "0x16080",
     "EventName": "PM_L2_LD",
     "BriefDescription": "All successful D-side Load dispatches for this thread (L2 miss + L2 hits)"
@@ -1927,7 +1997,7 @@
   {,
     "EventCode": "0xC080",
     "EventName": "PM_LS0_LD_VECTOR_FIN",
-    "BriefDescription": ""
+    "BriefDescription": "LS0 finished load vector op"
   },
   {,
     "EventCode": "0x368B0",
@@ -2000,6 +2070,11 @@
     "BriefDescription": "Conditional Branch Completed in which the HW correctly predicted the direction as taken.  Counted at completion time"
   },
   {,
+    "EventCode": "0xF0B8",
+    "EventName": "PM_LS0_UNALIGNED_ST",
+    "BriefDescription": "Store instructions whose data crosses a double-word boundary, which causes it to require an additional slice than than what normally would be required of the Store of that size.  If the Store wraps from slice 3 to slice 0, thee is an additional 3-cycle penalty"
+  },
+  {,
     "EventCode": "0x20132",
     "EventName": "PM_MRK_DFU_FIN",
     "BriefDescription": "Decimal Unit marked Instruction Finish"
@@ -2007,7 +2082,7 @@
   {,
     "EventCode": "0x160A6",
     "EventName": "PM_TM_SC_CO",
-    "BriefDescription": "L3 castout TM SC line"
+    "BriefDescription": "L3 castout of line that was StoreCopy (original value of speculatively written line) in a Transaction"
   },
   {,
     "EventCode": "0xC8B0",
@@ -2017,7 +2092,7 @@
   {,
     "EventCode": "0x16084",
     "EventName": "PM_L2_RCLD_DISP",
-    "BriefDescription": "All I-or-D side load dispatch attempts for this thread (excludes i_l2mru_tch_reqs)"
+    "BriefDescription": "All D-side-Ld or I-side-instruction-fetch dispatch attempts for this thread"
   },
   {,
     "EventCode": "0x3F150",
@@ -2122,12 +2197,12 @@
   {,
     "EventCode": "0x46082",
     "EventName": "PM_L2_ST_DISP",
-    "BriefDescription": "All successful D-side store dispatches for this thread (L2 miss + L2 hits)"
+    "BriefDescription": "All successful D-side store dispatches for this thread"
   },
   {,
     "EventCode": "0x36880",
     "EventName": "PM_L2_INST_MISS",
-    "BriefDescription": "All successful I-side dispatches that were an L2 miss for this thread (excludes i_l2mru_tch reqs)"
+    "BriefDescription": "All successful I-side-instruction-fetch (e.g. i-demand, i-prefetch) dispatches for this thread that were an L2 miss"
   },
   {,
     "EventCode": "0xE084",
@@ -2217,7 +2292,7 @@
   {,
     "EventCode": "0xC884",
     "EventName": "PM_LS3_LD_VECTOR_FIN",
-    "BriefDescription": ""
+    "BriefDescription": "LS3 finished load vector op"
   },
   {,
     "EventCode": "0x360A8",
@@ -2242,7 +2317,7 @@
   {,
     "EventCode": "0x168B2",
     "EventName": "PM_L3_GRP_GUESS_CORRECT",
-    "BriefDescription": "Initial scope=group (GS or NNS) and data from same group (near) (pred successful)"
+    "BriefDescription": "Prefetch scope predictor selected GS or NNS and was correct"
   },
   {,
     "EventCode": "0x48A4",
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json
index 5af1abbe82c4..b4772f54a271 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/pipeline.json
@@ -65,11 +65,6 @@
     "BriefDescription": "Dispatch Held"
   },
   {,
-    "EventCode": "0x3D154",
-    "EventName": "PM_MRK_DERAT_MISS_16M",
-    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 16M"
-  },
-  {,
     "EventCode": "0x200F8",
     "EventName": "PM_EXT_INT",
     "BriefDescription": "external interrupt"
@@ -120,6 +115,11 @@
     "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L3 without dispatch conflicts hit on Mepf state. due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
   },
   {,
+    "EventCode": "0x4C15C",
+    "EventName": "PM_MRK_DERAT_MISS_16G_1G",
+    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 16G (hpt mode) and 1G (radix mode)"
+  },
+  {,
     "EventCode": "0x10024",
     "EventName": "PM_PMC5_OVERFLOW",
     "BriefDescription": "Overflow from counter 5"
@@ -155,11 +155,6 @@
     "BriefDescription": "Ict empty for this thread due to Icache Miss"
   },
   {,
-    "EventCode": "0x3D152",
-    "EventName": "PM_MRK_DERAT_MISS_1G",
-    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 1G. Implies radix translation"
-  },
-  {,
     "EventCode": "0x4F14A",
     "EventName": "PM_MRK_DPTEG_FROM_OFF_CHIP_CACHE",
     "BriefDescription": "A Page Table Entry was loaded into the TLB either shared or modified data from another core's L2/L3 on a different chip (remote or distant) due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
@@ -185,11 +180,6 @@
     "BriefDescription": "A Page Table Entry was loaded into the TLB from local core's L2 without conflict due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
   },
   {,
-    "EventCode": "0x2C05A",
-    "EventName": "PM_DERAT_MISS_1G",
-    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 1G. Implies radix translation"
-  },
-  {,
     "EventCode": "0x1F058",
     "EventName": "PM_RADIX_PWC_L2_PTE_FROM_L2",
     "BriefDescription": "A Page Table Entry was reloaded to a level 2 page walk cache from the core's L2 data cache. This implies that level 3 and level 4 PWC accesses were not necessary for this translation"
@@ -240,11 +230,6 @@
     "BriefDescription": "Data PTEG reload"
   },
   {,
-    "EventCode": "0x2D152",
-    "EventName": "PM_MRK_DERAT_MISS_2M",
-    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 2M. Implies radix translation"
-  },
-  {,
     "EventCode": "0x2C046",
     "EventName": "PM_DATA_FROM_RL2L3_MOD",
     "BriefDescription": "The processor's data cache was reloaded with Modified (M) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a demand load"
@@ -290,6 +275,11 @@
     "BriefDescription": "Finish stall because the NTF instruction was issued to the Decimal Floating Point execution pipe and waiting to finish. Includes decimal floating point instructions + 128 bit binary floating point instructions. Not qualified by multicycle"
   },
   {,
+    "EventCode": "0x3C054",
+    "EventName": "PM_DERAT_MISS_16M_2M",
+    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16M (HPT mode) or 2M (Radix mode)"
+  },
+  {,
     "EventCode": "0x4C04C",
     "EventName": "PM_DATA_FROM_DMEM",
     "BriefDescription": "The processor's data cache was reloaded from another chip's memory on the same Node or Group (Distant) due to a demand load"
@@ -360,11 +350,6 @@
     "BriefDescription": "The processor's Instruction cache was reloaded from a memory location including L4 from local remote or distant due to an instruction fetch (not prefetch)"
   },
   {,
-    "EventCode": "0x1C05A",
-    "EventName": "PM_DERAT_MISS_2M",
-    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 2M. Implies radix translation"
-  },
-  {,
     "EventCode": "0x30024",
     "EventName": "PM_PMC6_OVERFLOW",
     "BriefDescription": "Overflow from counter 6"
@@ -375,6 +360,11 @@
     "BriefDescription": "Branch Instruction Finished"
   },
   {,
+    "EventCode": "0x3D154",
+    "EventName": "PM_MRK_DERAT_MISS_16M_2M",
+    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 16M (hpt mode) or 2M (radix mode)"
+  },
+  {,
     "EventCode": "0x30020",
     "EventName": "PM_PMC2_REWIND",
     "BriefDescription": "PMC2 Rewind Event (did not match condition)"
@@ -410,11 +400,6 @@
     "BriefDescription": "A Page Table Entry was loaded into the TLB with Modified (M) data from another core's L3 on the same chip due to a marked data side request. When using Radix Page Translation, this count excludes PDE reloads. Only PTE reloads are included"
   },
   {,
-    "EventCode": "0x4C15C",
-    "EventName": "PM_MRK_DERAT_MISS_16G",
-    "BriefDescription": "Marked Data ERAT Miss (Data TLB Access) page size 16G"
-  },
-  {,
     "EventCode": "0x14052",
     "EventName": "PM_INST_GRP_PUMP_MPRED_RTY",
     "BriefDescription": "Final Pump Scope (Group) ended up larger than Initial Pump Scope (Chip) for an instruction fetch"
@@ -445,11 +430,6 @@
     "BriefDescription": "Icache miss demand cycles"
   },
   {,
-    "EventCode": "0x3C054",
-    "EventName": "PM_DERAT_MISS_16M",
-    "BriefDescription": "Data ERAT Miss (Data TLB Access) page size 16M"
-  },
-  {,
     "EventCode": "0x2D14E",
     "EventName": "PM_MRK_DATA_FROM_L21_SHR",
     "BriefDescription": "The processor's data cache was reloaded with Shared (S) data from another core's L2 on the same chip due to a marked load"
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/pmc.json b/tools/perf/pmu-events/arch/powerpc/power9/pmc.json
index d0b89f930567..8b3b0f3be664 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/pmc.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/pmc.json
@@ -10,11 +10,6 @@
     "BriefDescription": "Local memory above threshold for LSU medium"
   },
   {,
-    "EventCode": "0x2C056",
-    "EventName": "PM_DTLB_MISS_4K",
-    "BriefDescription": "Data TLB Miss page size 4k"
-  },
-  {,
     "EventCode": "0x40118",
     "EventName": "PM_MRK_DCACHE_RELOAD_INTV",
     "BriefDescription": "Combined Intervention event"
diff --git a/tools/perf/pmu-events/arch/powerpc/power9/translation.json b/tools/perf/pmu-events/arch/powerpc/power9/translation.json
index bc8e03d7a6b0..b27642676244 100644
--- a/tools/perf/pmu-events/arch/powerpc/power9/translation.json
+++ b/tools/perf/pmu-events/arch/powerpc/power9/translation.json
@@ -30,11 +30,6 @@
     "BriefDescription": "Store finish count. Includes speculative activity"
   },
   {,
-    "EventCode": "0x44042",
-    "EventName": "PM_INST_FROM_L3",
-    "BriefDescription": "The processor's Instruction cache was reloaded from local core's L3 due to an instruction fetch (not prefetch)"
-  },
-  {,
     "EventCode": "0x1504A",
     "EventName": "PM_IPTEG_FROM_RL2L3_SHR",
     "BriefDescription": "A Page Table Entry was loaded into the TLB with Shared (S) data from another chip's L2 or L3 on the same Node or Group (Remote), as this chip due to a instruction side request"
@@ -125,6 +120,11 @@
     "BriefDescription": "PMC1 Rewind Value saved"
   },
   {,
+    "EventCode": "0x44042",
+    "EventName": "PM_INST_FROM_L3",
+    "BriefDescription": "The processor's Instruction cache was reloaded from local core's L3 due to an instruction fetch (not prefetch)"
+  },
+  {,
     "EventCode": "0x200FE",
     "EventName": "PM_DATA_FROM_L2MISS",
     "BriefDescription": "Demand LD - L2 Miss (not L2 hit)"
diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/basic.json b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json
new file mode 100644
index 000000000000..8bf16759ca53
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/basic.json
@@ -0,0 +1,74 @@
+[
+	{
+		"EventCode": "0",
+		"EventName": "CPU_CYCLES",
+		"BriefDescription": "CPU Cycles",
+		"PublicDescription": "Cycle Count"
+	},
+	{
+		"EventCode": "1",
+		"EventName": "INSTRUCTIONS",
+		"BriefDescription": "Instructions",
+		"PublicDescription": "Instruction Count"
+	},
+	{
+		"EventCode": "2",
+		"EventName": "L1I_DIR_WRITES",
+		"BriefDescription": "L1I Directory Writes",
+		"PublicDescription": "Level-1 I-Cache Directory Write Count"
+	},
+	{
+		"EventCode": "3",
+		"EventName": "L1I_PENALTY_CYCLES",
+		"BriefDescription": "L1I Penalty Cycles",
+		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
+	},
+	{
+		"EventCode": "4",
+		"EventName": "L1D_DIR_WRITES",
+		"BriefDescription": "L1D Directory Writes",
+		"PublicDescription": "Level-1 D-Cache Directory Write Count"
+	},
+	{
+		"EventCode": "5",
+		"EventName": "L1D_PENALTY_CYCLES",
+		"BriefDescription": "L1D Penalty Cycles",
+		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
+	},
+	{
+		"EventCode": "32",
+		"EventName": "PROBLEM_STATE_CPU_CYCLES",
+		"BriefDescription": "Problem-State CPU Cycles",
+		"PublicDescription": "Problem-State Cycle Count"
+	},
+	{
+		"EventCode": "33",
+		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
+		"BriefDescription": "Problem-State Instructions",
+		"PublicDescription": "Problem-State Instruction Count"
+	},
+	{
+		"EventCode": "34",
+		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
+		"BriefDescription": "Problem-State L1I Directory Writes",
+		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
+	},
+	{
+		"EventCode": "35",
+		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
+		"BriefDescription": "Problem-State L1I Penalty Cycles",
+		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
+	},
+	{
+		"EventCode": "36",
+		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
+		"BriefDescription": "Problem-State L1D Directory Writes",
+		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
+	},
+	{
+		"EventCode": "37",
+		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
+		"BriefDescription": "Problem-State L1D Penalty Cycles",
+		"PublicDescription": "Problem-State Level-1 D-Cache Penalty Cycle Count"
+	},
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json
new file mode 100644
index 000000000000..7e5b72492141
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/crypto.json
@@ -0,0 +1,98 @@
+[
+	{
+		"EventCode": "64",
+		"EventName": "PRNG_FUNCTIONS",
+		"BriefDescription": "PRNG Functions",
+		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
+	},
+	{
+		"EventCode": "65",
+		"EventName": "PRNG_CYCLES",
+		"BriefDescription": "PRNG Cycles",
+		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
+	},
+	{
+		"EventCode": "66",
+		"EventName": "PRNG_BLOCKED_FUNCTIONS",
+		"BriefDescription": "PRNG Blocked Functions",
+		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "67",
+		"EventName": "PRNG_BLOCKED_CYCLES",
+		"BriefDescription": "PRNG Blocked Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "68",
+		"EventName": "SHA_FUNCTIONS",
+		"BriefDescription": "SHA Functions",
+		"PublicDescription": "Total number of SHA functions issued by the CPU"
+	},
+	{
+		"EventCode": "69",
+		"EventName": "SHA_CYCLES",
+		"BriefDescription": "SHA Cycles",
+		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
+	},
+	{
+		"EventCode": "70",
+		"EventName": "SHA_BLOCKED_FUNCTIONS",
+		"BriefDescription": "SHA Blocked Functions",
+		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "71",
+		"EventName": "SHA_BLOCKED_CYCLES",
+		"BriefDescription": "SHA Bloced Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "72",
+		"EventName": "DEA_FUNCTIONS",
+		"BriefDescription": "DEA Functions",
+		"PublicDescription": "Total number of the DEA functions issued by the CPU"
+	},
+	{
+		"EventCode": "73",
+		"EventName": "DEA_CYCLES",
+		"BriefDescription": "DEA Cycles",
+		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
+	},
+	{
+		"EventCode": "74",
+		"EventName": "DEA_BLOCKED_FUNCTIONS",
+		"BriefDescription": "DEA Blocked Functions",
+		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "75",
+		"EventName": "DEA_BLOCKED_CYCLES",
+		"BriefDescription": "DEA Blocked Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "76",
+		"EventName": "AES_FUNCTIONS",
+		"BriefDescription": "AES Functions",
+		"PublicDescription": "Total number of AES functions issued by the CPU"
+	},
+	{
+		"EventCode": "77",
+		"EventName": "AES_CYCLES",
+		"BriefDescription": "AES Cycles",
+		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
+	},
+	{
+		"EventCode": "78",
+		"EventName": "AES_BLOCKED_FUNCTIONS",
+		"BriefDescription": "AES Blocked Functions",
+		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "79",
+		"EventName": "AES_BLOCKED_CYCLES",
+		"BriefDescription": "AES Blocked Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z10/extended.json b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json
new file mode 100644
index 000000000000..0feedb40f30f
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z10/extended.json
@@ -0,0 +1,110 @@
+[
+	{
+		"EventCode": "128",
+		"EventName": "L1I_L2_SOURCED_WRITES",
+		"BriefDescription": "L1I L2 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 (L1.5) cache"
+	},
+	{
+		"EventCode": "129",
+		"EventName": "L1D_L2_SOURCED_WRITES",
+		"BriefDescription": "L1D L2 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from the Level-2 (L1.5) cache"
+	},
+	{
+		"EventCode": "130",
+		"EventName": "L1I_L3_LOCAL_WRITES",
+		"BriefDescription": "L1I L3 Local Writes",
+		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from the Level-3 cache that is on the same book as the Instruction cache (Local L2 cache)"
+	},
+	{
+		"EventCode": "131",
+		"EventName": "L1D_L3_LOCAL_WRITES",
+		"BriefDescription": "L1D L3 Local Writes",
+		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installtion cache line was source from the Level-3 cache that is on the same book as the Data cache (Local L2 cache)"
+	},
+	{
+		"EventCode": "132",
+		"EventName": "L1I_L3_REMOTE_WRITES",
+		"BriefDescription": "L1I L3 Remote Writes",
+		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Instruction cache (Remote L2 cache)"
+	},
+	{
+		"EventCode": "133",
+		"EventName": "L1D_L3_REMOTE_WRITES",
+		"BriefDescription": "L1D L3 Remote Writes",
+		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from a Level-3 cache that is not on the same book as the Data cache (Remote L2 cache)"
+	},
+	{
+		"EventCode": "134",
+		"EventName": "L1D_LMEM_SOURCED_WRITES",
+		"BriefDescription": "L1D Local Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
+	},
+	{
+		"EventCode": "135",
+		"EventName": "L1I_LMEM_SOURCED_WRITES",
+		"BriefDescription": "L1I Local Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the s ame book as the Instruction cache (Local Memory)"
+	},
+	{
+		"EventCode": "136",
+		"EventName": "L1D_RO_EXCL_WRITES",
+		"BriefDescription": "L1D Read-only Exclusive Writes",
+		"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
+	},
+	{
+		"EventCode": "137",
+		"EventName": "L1I_CACHELINE_INVALIDATES",
+		"BriefDescription": "L1I Cacheline Invalidates",
+		"PublicDescription": "A cache line in the Level-1 I-Cache has been invalidated by a store on the same CPU as the Level-1 I-Cache"
+	},
+	{
+		"EventCode": "138",
+		"EventName": "ITLB1_WRITES",
+		"BriefDescription": "ITLB1 Writes",
+		"PublicDescription": "A translation entry has been written into the Level-1 Instruction Translation Lookaside Buffer"
+	},
+	{
+		"EventCode": "139",
+		"EventName": "DTLB1_WRITES",
+		"BriefDescription": "DTLB1 Writes",
+		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
+	},
+	{
+		"EventCode": "140",
+		"EventName": "TLB2_PTE_WRITES",
+		"BriefDescription": "TLB2 PTE Writes",
+		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
+	},
+	{
+		"EventCode": "141",
+		"EventName": "TLB2_CRSTE_WRITES",
+		"BriefDescription": "TLB2 CRSTE Writes",
+		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
+	},
+	{
+		"EventCode": "142",
+		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
+		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
+		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
+	},
+	{
+		"EventCode": "145",
+		"EventName": "ITLB1_MISSES",
+		"BriefDescription": "ITLB1 Misses",
+		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress"
+	},
+	{
+		"EventCode": "146",
+		"EventName": "DTLB1_MISSES",
+		"BriefDescription": "DTLB1 Misses",
+		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle an DTLB1 miss is in progress"
+	},
+	{
+		"EventCode": "147",
+		"EventName": "L2C_STORES_SENT",
+		"BriefDescription": "L2C Stores Sent",
+		"PublicDescription": "Incremented by one for every store sent to Level-2 (L1.5) cache"
+	},
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/basic.json b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json
new file mode 100644
index 000000000000..8bf16759ca53
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/basic.json
@@ -0,0 +1,74 @@
+[
+	{
+		"EventCode": "0",
+		"EventName": "CPU_CYCLES",
+		"BriefDescription": "CPU Cycles",
+		"PublicDescription": "Cycle Count"
+	},
+	{
+		"EventCode": "1",
+		"EventName": "INSTRUCTIONS",
+		"BriefDescription": "Instructions",
+		"PublicDescription": "Instruction Count"
+	},
+	{
+		"EventCode": "2",
+		"EventName": "L1I_DIR_WRITES",
+		"BriefDescription": "L1I Directory Writes",
+		"PublicDescription": "Level-1 I-Cache Directory Write Count"
+	},
+	{
+		"EventCode": "3",
+		"EventName": "L1I_PENALTY_CYCLES",
+		"BriefDescription": "L1I Penalty Cycles",
+		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
+	},
+	{
+		"EventCode": "4",
+		"EventName": "L1D_DIR_WRITES",
+		"BriefDescription": "L1D Directory Writes",
+		"PublicDescription": "Level-1 D-Cache Directory Write Count"
+	},
+	{
+		"EventCode": "5",
+		"EventName": "L1D_PENALTY_CYCLES",
+		"BriefDescription": "L1D Penalty Cycles",
+		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
+	},
+	{
+		"EventCode": "32",
+		"EventName": "PROBLEM_STATE_CPU_CYCLES",
+		"BriefDescription": "Problem-State CPU Cycles",
+		"PublicDescription": "Problem-State Cycle Count"
+	},
+	{
+		"EventCode": "33",
+		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
+		"BriefDescription": "Problem-State Instructions",
+		"PublicDescription": "Problem-State Instruction Count"
+	},
+	{
+		"EventCode": "34",
+		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
+		"BriefDescription": "Problem-State L1I Directory Writes",
+		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
+	},
+	{
+		"EventCode": "35",
+		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
+		"BriefDescription": "Problem-State L1I Penalty Cycles",
+		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
+	},
+	{
+		"EventCode": "36",
+		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
+		"BriefDescription": "Problem-State L1D Directory Writes",
+		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
+	},
+	{
+		"EventCode": "37",
+		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
+		"BriefDescription": "Problem-State L1D Penalty Cycles",
+		"PublicDescription": "Problem-State Level-1 D-Cache Penalty Cycle Count"
+	},
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json
new file mode 100644
index 000000000000..7e5b72492141
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/crypto.json
@@ -0,0 +1,98 @@
+[
+	{
+		"EventCode": "64",
+		"EventName": "PRNG_FUNCTIONS",
+		"BriefDescription": "PRNG Functions",
+		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
+	},
+	{
+		"EventCode": "65",
+		"EventName": "PRNG_CYCLES",
+		"BriefDescription": "PRNG Cycles",
+		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
+	},
+	{
+		"EventCode": "66",
+		"EventName": "PRNG_BLOCKED_FUNCTIONS",
+		"BriefDescription": "PRNG Blocked Functions",
+		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "67",
+		"EventName": "PRNG_BLOCKED_CYCLES",
+		"BriefDescription": "PRNG Blocked Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "68",
+		"EventName": "SHA_FUNCTIONS",
+		"BriefDescription": "SHA Functions",
+		"PublicDescription": "Total number of SHA functions issued by the CPU"
+	},
+	{
+		"EventCode": "69",
+		"EventName": "SHA_CYCLES",
+		"BriefDescription": "SHA Cycles",
+		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
+	},
+	{
+		"EventCode": "70",
+		"EventName": "SHA_BLOCKED_FUNCTIONS",
+		"BriefDescription": "SHA Blocked Functions",
+		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "71",
+		"EventName": "SHA_BLOCKED_CYCLES",
+		"BriefDescription": "SHA Bloced Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "72",
+		"EventName": "DEA_FUNCTIONS",
+		"BriefDescription": "DEA Functions",
+		"PublicDescription": "Total number of the DEA functions issued by the CPU"
+	},
+	{
+		"EventCode": "73",
+		"EventName": "DEA_CYCLES",
+		"BriefDescription": "DEA Cycles",
+		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
+	},
+	{
+		"EventCode": "74",
+		"EventName": "DEA_BLOCKED_FUNCTIONS",
+		"BriefDescription": "DEA Blocked Functions",
+		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "75",
+		"EventName": "DEA_BLOCKED_CYCLES",
+		"BriefDescription": "DEA Blocked Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "76",
+		"EventName": "AES_FUNCTIONS",
+		"BriefDescription": "AES Functions",
+		"PublicDescription": "Total number of AES functions issued by the CPU"
+	},
+	{
+		"EventCode": "77",
+		"EventName": "AES_CYCLES",
+		"BriefDescription": "AES Cycles",
+		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
+	},
+	{
+		"EventCode": "78",
+		"EventName": "AES_BLOCKED_FUNCTIONS",
+		"BriefDescription": "AES Blocked Functions",
+		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "79",
+		"EventName": "AES_BLOCKED_CYCLES",
+		"BriefDescription": "AES Blocked Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z13/extended.json b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
new file mode 100644
index 000000000000..9a002b6967f1
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z13/extended.json
@@ -0,0 +1,338 @@
+[
+	{
+		"EventCode": "128",
+		"EventName": "L1D_RO_EXCL_WRITES",
+		"BriefDescription": "L1D Read-only Exclusive Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line."
+	},
+	{
+		"EventCode": "129",
+		"EventName": "DTLB1_WRITES",
+		"BriefDescription": "DTLB1 Writes",
+		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
+	},
+	{
+		"EventCode": "130",
+		"EventName": "DTLB1_MISSES",
+		"BriefDescription": "DTLB1 Misses",
+		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
+	},
+	{
+		"EventCode": "131",
+		"EventName": "DTLB1_HPAGE_WRITES",
+		"BriefDescription": "DTLB1 One-Megabyte Page Writes",
+		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
+	},
+	{
+		"EventCode": "132",
+		"EventName": "DTLB1_GPAGE_WRITES",
+		"BriefDescription": "DTLB1 Two-Gigabyte Page Writes",
+		"PublicDescription": "Counter:132	Name:DTLB1_GPAGE_WRITES A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a two-gigabyte page."
+	},
+	{
+		"EventCode": "133",
+		"EventName": "L1D_L2D_SOURCED_WRITES",
+		"BriefDescription": "L1D L2D Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
+	},
+	{
+		"EventCode": "134",
+		"EventName": "ITLB1_WRITES",
+		"BriefDescription": "ITLB1 Writes",
+		"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
+	},
+	{
+		"EventCode": "135",
+		"EventName": "ITLB1_MISSES",
+		"BriefDescription": "ITLB1 Misses",
+		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle an ITLB1 miss is in progress"
+	},
+	{
+		"EventCode": "136",
+		"EventName": "L1I_L2I_SOURCED_WRITES",
+		"BriefDescription": "L1I L2I Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
+	},
+	{
+		"EventCode": "137",
+		"EventName": "TLB2_PTE_WRITES",
+		"BriefDescription": "TLB2 PTE Writes",
+		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
+	},
+	{
+		"EventCode": "138",
+		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
+		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
+		"PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays for a one-megabyte large page translation"
+	},
+	{
+		"EventCode": "139",
+		"EventName": "TLB2_CRSTE_WRITES",
+		"BriefDescription": "TLB2 CRSTE Writes",
+		"PublicDescription": "A translation entry has been written to the Level-2 TLB Combined Region Segment Table Entry arrays"
+	},
+	{
+		"EventCode": "140",
+		"EventName": "TX_C_TEND",
+		"BriefDescription": "Completed TEND instructions in constrained TX mode",
+		"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
+	},
+	{
+		"EventCode": "141",
+		"EventName": "TX_NC_TEND",
+		"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
+		"PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode"
+	},
+	{
+		"EventCode": "143",
+		"EventName": "L1C_TLB1_MISSES",
+		"BriefDescription": "L1C TLB1 Misses",
+		"PublicDescription": "Increments by one for any cycle where a Level-1 cache or Level-1 TLB miss is in progress."
+	},
+	{
+		"EventCode": "144",
+		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "145",
+		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "146",
+		"EventName": "L1D_ONNODE_L4_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Node L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-4 cache"
+	},
+	{
+		"EventCode": "147",
+		"EventName": "L1D_ONNODE_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1D On-Node L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "148",
+		"EventName": "L1D_ONNODE_L3_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Node L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "149",
+		"EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Drawer L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache"
+	},
+	{
+		"EventCode": "150",
+		"EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1D On-Drawer L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "151",
+		"EventName": "L1D_ONDRAWER_L3_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Drawer L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "152",
+		"EventName": "L1D_OFFDRAWER_SCOL_L4_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Drawer Same-Column L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache"
+	},
+	{
+		"EventCode": "153",
+		"EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "154",
+		"EventName": "L1D_OFFDRAWER_SCOL_L3_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Drawer Same-Column L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "155",
+		"EventName": "L1D_OFFDRAWER_FCOL_L4_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache"
+	},
+	{
+		"EventCode": "156",
+		"EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "157",
+		"EventName": "L1D_OFFDRAWER_FCOL_L3_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Drawer Far-Column L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "158",
+		"EventName": "L1D_ONNODE_MEM_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Node Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Node memory"
+	},
+	{
+		"EventCode": "159",
+		"EventName": "L1D_ONDRAWER_MEM_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Drawer Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory"
+	},
+	{
+		"EventCode": "160",
+		"EventName": "L1D_OFFDRAWER_MEM_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Drawer Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer memory"
+	},
+	{
+		"EventCode": "161",
+		"EventName": "L1D_ONCHIP_MEM_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Chip Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory"
+	},
+	{
+		"EventCode": "162",
+		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "163",
+		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "164",
+		"EventName": "L1I_ONNODE_L4_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Chip L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-4 cache"
+	},
+	{
+		"EventCode": "165",
+		"EventName": "L1I_ONNODE_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1I On-Node L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "166",
+		"EventName": "L1I_ONNODE_L3_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Node L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Node Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "167",
+		"EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Drawer L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-4 cache"
+	},
+	{
+		"EventCode": "168",
+		"EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1I On-Drawer L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "169",
+		"EventName": "L1I_ONDRAWER_L3_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Drawer L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Drawer Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "170",
+		"EventName": "L1I_OFFDRAWER_SCOL_L4_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Drawer Same-Column L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-4 cache"
+	},
+	{
+		"EventCode": "171",
+		"EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "172",
+		"EventName": "L1I_OFFDRAWER_SCOL_L3_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Drawer Same-Column L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Same-Column Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "173",
+		"EventName": "L1I_OFFDRAWER_FCOL_L4_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Drawer Far-Column L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-4 cache"
+	},
+	{
+		"EventCode": "174",
+		"EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "175",
+		"EventName": "L1I_OFFDRAWER_FCOL_L3_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Drawer Far-Column L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Far-Column Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "176",
+		"EventName": "L1I_ONNODE_MEM_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Node Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Node memory"
+	},
+	{
+		"EventCode": "177",
+		"EventName": "L1I_ONDRAWER_MEM_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Drawer Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory"
+	},
+	{
+		"EventCode": "178",
+		"EventName": "L1I_OFFDRAWER_MEM_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Drawer Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer memory"
+	},
+	{
+		"EventCode": "179",
+		"EventName": "L1I_ONCHIP_MEM_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Chip Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Chip memory"
+	},
+	{
+		"EventCode": "218",
+		"EventName": "TX_NC_TABORT",
+		"BriefDescription": "Aborted transactions in non-constrained TX mode",
+		"PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode"
+	},
+	{
+		"EventCode": "219",
+		"EventName": "TX_C_TABORT_NO_SPECIAL",
+		"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
+		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
+	},
+	{
+		"EventCode": "220",
+		"EventName": "TX_C_TABORT_SPECIAL",
+		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
+		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
+	},
+	{
+		"EventCode": "448",
+		"EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
+		"BriefDescription": "Cycle count with one thread active",
+		"PublicDescription": "Cycle count with one thread active"
+	},
+	{
+		"EventCode": "449",
+		"EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE",
+		"BriefDescription": "Cycle count with two threads active",
+		"PublicDescription": "Cycle count with two threads active"
+	},
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/basic.json b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json
new file mode 100644
index 000000000000..8f653c9d899d
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/basic.json
@@ -0,0 +1,50 @@
+[
+	{
+		"EventCode": "0",
+		"EventName": "CPU_CYCLES",
+		"BriefDescription": "CPU Cycles",
+		"PublicDescription": "Cycle Count"
+	},
+	{
+		"EventCode": "1",
+		"EventName": "INSTRUCTIONS",
+		"BriefDescription": "Instructions",
+		"PublicDescription": "Instruction Count"
+	},
+	{
+		"EventCode": "2",
+		"EventName": "L1I_DIR_WRITES",
+		"BriefDescription": "L1I Directory Writes",
+		"PublicDescription": "Level-1 I-Cache Directory Write Count"
+	},
+	{
+		"EventCode": "3",
+		"EventName": "L1I_PENALTY_CYCLES",
+		"BriefDescription": "L1I Penalty Cycles",
+		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
+	},
+	{
+		"EventCode": "4",
+		"EventName": "L1D_DIR_WRITES",
+		"BriefDescription": "L1D Directory Writes",
+		"PublicDescription": "Level-1 D-Cache Directory Write Count"
+	},
+	{
+		"EventCode": "5",
+		"EventName": "L1D_PENALTY_CYCLES",
+		"BriefDescription": "L1D Penalty Cycles",
+		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
+	},
+	{
+		"EventCode": "32",
+		"EventName": "PROBLEM_STATE_CPU_CYCLES",
+		"BriefDescription": "Problem-State CPU Cycles",
+		"PublicDescription": "Problem-State Cycle Count"
+	},
+	{
+		"EventCode": "33",
+		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
+		"BriefDescription": "Problem-State Instructions",
+		"PublicDescription": "Problem-State Instruction Count"
+	},
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json
new file mode 100644
index 000000000000..7e5b72492141
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/crypto.json
@@ -0,0 +1,98 @@
+[
+	{
+		"EventCode": "64",
+		"EventName": "PRNG_FUNCTIONS",
+		"BriefDescription": "PRNG Functions",
+		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
+	},
+	{
+		"EventCode": "65",
+		"EventName": "PRNG_CYCLES",
+		"BriefDescription": "PRNG Cycles",
+		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
+	},
+	{
+		"EventCode": "66",
+		"EventName": "PRNG_BLOCKED_FUNCTIONS",
+		"BriefDescription": "PRNG Blocked Functions",
+		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "67",
+		"EventName": "PRNG_BLOCKED_CYCLES",
+		"BriefDescription": "PRNG Blocked Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "68",
+		"EventName": "SHA_FUNCTIONS",
+		"BriefDescription": "SHA Functions",
+		"PublicDescription": "Total number of SHA functions issued by the CPU"
+	},
+	{
+		"EventCode": "69",
+		"EventName": "SHA_CYCLES",
+		"BriefDescription": "SHA Cycles",
+		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
+	},
+	{
+		"EventCode": "70",
+		"EventName": "SHA_BLOCKED_FUNCTIONS",
+		"BriefDescription": "SHA Blocked Functions",
+		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "71",
+		"EventName": "SHA_BLOCKED_CYCLES",
+		"BriefDescription": "SHA Bloced Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "72",
+		"EventName": "DEA_FUNCTIONS",
+		"BriefDescription": "DEA Functions",
+		"PublicDescription": "Total number of the DEA functions issued by the CPU"
+	},
+	{
+		"EventCode": "73",
+		"EventName": "DEA_CYCLES",
+		"BriefDescription": "DEA Cycles",
+		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
+	},
+	{
+		"EventCode": "74",
+		"EventName": "DEA_BLOCKED_FUNCTIONS",
+		"BriefDescription": "DEA Blocked Functions",
+		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "75",
+		"EventName": "DEA_BLOCKED_CYCLES",
+		"BriefDescription": "DEA Blocked Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "76",
+		"EventName": "AES_FUNCTIONS",
+		"BriefDescription": "AES Functions",
+		"PublicDescription": "Total number of AES functions issued by the CPU"
+	},
+	{
+		"EventCode": "77",
+		"EventName": "AES_CYCLES",
+		"BriefDescription": "AES Cycles",
+		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
+	},
+	{
+		"EventCode": "78",
+		"EventName": "AES_BLOCKED_FUNCTIONS",
+		"BriefDescription": "AES Blocked Functions",
+		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "79",
+		"EventName": "AES_BLOCKED_CYCLES",
+		"BriefDescription": "AES Blocked Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z14/extended.json b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
new file mode 100644
index 000000000000..aa4dfb46b65b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z14/extended.json
@@ -0,0 +1,320 @@
+[
+	{
+		"EventCode": "128",
+		"EventName": "L1D_RO_EXCL_WRITES",
+		"BriefDescription": "L1D Read-only Exclusive Writes",
+		"PublicDescription": "Counter:128	Name:L1D_RO_EXCL_WRITES A directory write to the Level-1 Data cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
+	},
+	{
+		"EventCode": "129",
+		"EventName": "DTLB2_WRITES",
+		"BriefDescription": "DTLB2 Writes",
+		"PublicDescription": "A translation has been written into The Translation Lookaside Buffer 2 (TLB2) and the request was made by the data cache"
+	},
+	{
+		"EventCode": "130",
+		"EventName": "DTLB2_MISSES",
+		"BriefDescription": "DTLB2 Misses",
+		"PublicDescription": "A TLB2 miss is in progress for a request made by the data cache. Incremented by one for every TLB2 miss in progress for the Level-1 Data cache on this cycle"
+	},
+	{
+		"EventCode": "131",
+		"EventName": "DTLB2_HPAGE_WRITES",
+		"BriefDescription": "DTLB2 One-Megabyte Page Writes",
+		"PublicDescription": "A translation entry was written into the Combined Region and Segment Table Entry array in the Level-2 TLB for a one-megabyte page or a Last Host Translation was done"
+	},
+	{
+		"EventCode": "132",
+		"EventName": "DTLB2_GPAGE_WRITES",
+		"BriefDescription": "DTLB2 Two-Gigabyte Page Writes",
+		"PublicDescription": "A translation entry for a two-gigabyte page was written into the Level-2 TLB"
+	},
+	{
+		"EventCode": "133",
+		"EventName": "L1D_L2D_SOURCED_WRITES",
+		"BriefDescription": "L1D L2D Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
+	},
+	{
+		"EventCode": "134",
+		"EventName": "ITLB2_WRITES",
+		"BriefDescription": "ITLB2 Writes",
+		"PublicDescription": "A translation entry has been written into the Translation Lookaside Buffer 2 (TLB2) and the request was made by the instruction cache"
+	},
+	{
+		"EventCode": "135",
+		"EventName": "ITLB2_MISSES",
+		"BriefDescription": "ITLB2 Misses",
+		"PublicDescription": "A TLB2 miss is in progress for a request made by the instruction cache. Incremented by one for every TLB2 miss in progress for the Level-1 Instruction cache in a cycle"
+	},
+	{
+		"EventCode": "136",
+		"EventName": "L1I_L2I_SOURCED_WRITES",
+		"BriefDescription": "L1I L2I Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
+	},
+	{
+		"EventCode": "137",
+		"EventName": "TLB2_PTE_WRITES",
+		"BriefDescription": "TLB2 PTE Writes",
+		"PublicDescription": "A translation entry was written into the Page Table Entry array in the Level-2 TLB"
+	},
+	{
+		"EventCode": "138",
+		"EventName": "TLB2_CRSTE_WRITES",
+		"BriefDescription": "TLB2 CRSTE Writes",
+		"PublicDescription": "Translation entries were written into the Combined Region and Segment Table Entry array and the Page Table Entry array in the Level-2 TLB"
+	},
+	{
+		"EventCode": "139",
+		"EventName": "TLB2_ENGINES_BUSY",
+		"BriefDescription": "TLB2 Engines Busy",
+		"PublicDescription": "The number of Level-2 TLB translation engines busy in a cycle"
+	},
+	{
+		"EventCode": "140",
+		"EventName": "TX_C_TEND",
+		"BriefDescription": "Completed TEND instructions in constrained TX mode",
+		"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
+	},
+	{
+		"EventCode": "141",
+		"EventName": "TX_NC_TEND",
+		"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
+		"PublicDescription": "A TEND instruction has completed in a non-constrained transactional-execution mode"
+	},
+	{
+		"EventCode": "143",
+		"EventName": "L1C_TLB2_MISSES",
+		"BriefDescription": "L1C TLB2 Misses",
+		"PublicDescription": "Increments by one for any cycle where a level-1 cache or level-2 TLB miss is in progress"
+	},
+	{
+		"EventCode": "144",
+		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "145",
+		"EventName": "L1D_ONCHIP_MEMORY_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Chip Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip memory"
+	},
+	{
+		"EventCode": "146",
+		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Chip Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "147",
+		"EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Cluster L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Cluster Level-3 cache withountervention"
+	},
+	{
+		"EventCode": "148",
+		"EventName": "L1D_ONCLUSTER_MEMORY_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Cluster Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster memory"
+	},
+	{
+		"EventCode": "149",
+		"EventName": "L1D_ONCLUSTER_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1D On-Cluster L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "150",
+		"EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Cluster L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "151",
+		"EventName": "L1D_OFFCLUSTER_MEMORY_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Cluster Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Cluster memory"
+	},
+	{
+		"EventCode": "152",
+		"EventName": "L1D_OFFCLUSTER_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1D Off-Cluster L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "153",
+		"EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Drawer L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "154",
+		"EventName": "L1D_OFFDRAWER_MEMORY_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Drawer Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer memory"
+	},
+	{
+		"EventCode": "155",
+		"EventName": "L1D_OFFDRAWER_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1D Off-Drawer L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "156",
+		"EventName": "L1D_ONDRAWER_L4_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Drawer L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
+	},
+	{
+		"EventCode": "157",
+		"EventName": "L1D_OFFDRAWER_L4_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Drawer L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
+	},
+	{
+		"EventCode": "158",
+		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_RO",
+		"BriefDescription": "L1D On-Chip L3 Sourced Writes read-only",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from On-Chip L3 but a read-only invalidate was done to remove other copies of the cache line"
+	},
+	{
+		"EventCode": "162",
+		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "163",
+		"EventName": "L1I_ONCHIP_MEMORY_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Chip Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from On-Chip memory"
+	},
+	{
+		"EventCode": "164",
+		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache ine was sourced from an On-Chip Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "165",
+		"EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Cluster L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "166",
+		"EventName": "L1I_ONCLUSTER_MEMORY_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Cluster Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On-Cluster memory"
+	},
+	{
+		"EventCode": "167",
+		"EventName": "L1I_ONCLUSTER_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1I On-Cluster L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Cluster Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "168",
+		"EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Cluster L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "169",
+		"EventName": "L1I_OFFCLUSTER_MEMORY_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Cluster Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Cluster memory"
+	},
+	{
+		"EventCode": "170",
+		"EventName": "L1I_OFFCLUSTER_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1I Off-Cluster L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Cluster Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "171",
+		"EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Drawer L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "172",
+		"EventName": "L1I_OFFDRAWER_MEMORY_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Drawer Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer memory"
+	},
+	{
+		"EventCode": "173",
+		"EventName": "L1I_OFFDRAWER_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1I Off-Drawer L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off-Drawer Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "174",
+		"EventName": "L1I_ONDRAWER_L4_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Drawer L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from On-Drawer Level-4 cache"
+	},
+	{
+		"EventCode": "175",
+		"EventName": "L1I_OFFDRAWER_L4_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Drawer L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from Off-Drawer Level-4 cache"
+	},
+	{
+		"EventCode": "224",
+		"EventName": "BCD_DFP_EXECUTION_SLOTS",
+		"BriefDescription": "BCD DFP Execution Slots",
+		"PublicDescription": "Count of floating point execution slots used for finished Binary Coded Decimal to Decimal Floating Point conversions. Instructions: CDZT, CXZT, CZDT, CZXT"
+	},
+	{
+		"EventCode": "225",
+		"EventName": "VX_BCD_EXECUTION_SLOTS",
+		"BriefDescription": "VX BCD Execution Slots",
+		"PublicDescription": "Count of floating point execution slots used for finished vector arithmetic Binary Coded Decimal instructions. Instructions: VAP, VSP, VMPVMSP, VDP, VSDP, VRP, VLIP, VSRP, VPSOPVCP, VTP, VPKZ, VUPKZ, VCVB, VCVBG, VCVDVCVDG"
+	},
+	{
+		"EventCode": "226",
+		"EventName": "DECIMAL_INSTRUCTIONS",
+		"BriefDescription": "Decimal Instructions",
+		"PublicDescription": "Decimal instructions dispatched. Instructions: CVB, CVD, AP, CP, DP, ED, EDMK, MP, SRP, SP, ZAP"
+	},
+	{
+		"EventCode": "232",
+		"EventName": "LAST_HOST_TRANSLATIONS",
+		"BriefDescription": "Last host translation done",
+		"PublicDescription": "Last Host Translation done"
+	},
+	{
+		"EventCode": "243",
+		"EventName": "TX_NC_TABORT",
+		"BriefDescription": "Aborted transactions in non-constrained TX mode",
+		"PublicDescription": "A transaction abort has occurred in a non-constrained transactional-execution mode"
+	},
+	{
+		"EventCode": "244",
+		"EventName": "TX_C_TABORT_NO_SPECIAL",
+		"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
+		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
+	},
+	{
+		"EventCode": "245",
+		"EventName": "TX_C_TABORT_SPECIAL",
+		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
+		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
+	},
+	{
+		"EventCode": "448",
+		"EventName": "MT_DIAG_CYCLES_ONE_THR_ACTIVE",
+		"BriefDescription": "Cycle count with one thread active",
+		"PublicDescription": "Cycle count with one thread active"
+	},
+	{
+		"EventCode": "449",
+		"EventName": "MT_DIAG_CYCLES_TWO_THR_ACTIVE",
+		"BriefDescription": "Cycle count with two threads active",
+		"PublicDescription": "Cycle count with two threads active"
+	},
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/basic.json b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json
new file mode 100644
index 000000000000..8bf16759ca53
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/basic.json
@@ -0,0 +1,74 @@
+[
+	{
+		"EventCode": "0",
+		"EventName": "CPU_CYCLES",
+		"BriefDescription": "CPU Cycles",
+		"PublicDescription": "Cycle Count"
+	},
+	{
+		"EventCode": "1",
+		"EventName": "INSTRUCTIONS",
+		"BriefDescription": "Instructions",
+		"PublicDescription": "Instruction Count"
+	},
+	{
+		"EventCode": "2",
+		"EventName": "L1I_DIR_WRITES",
+		"BriefDescription": "L1I Directory Writes",
+		"PublicDescription": "Level-1 I-Cache Directory Write Count"
+	},
+	{
+		"EventCode": "3",
+		"EventName": "L1I_PENALTY_CYCLES",
+		"BriefDescription": "L1I Penalty Cycles",
+		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
+	},
+	{
+		"EventCode": "4",
+		"EventName": "L1D_DIR_WRITES",
+		"BriefDescription": "L1D Directory Writes",
+		"PublicDescription": "Level-1 D-Cache Directory Write Count"
+	},
+	{
+		"EventCode": "5",
+		"EventName": "L1D_PENALTY_CYCLES",
+		"BriefDescription": "L1D Penalty Cycles",
+		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
+	},
+	{
+		"EventCode": "32",
+		"EventName": "PROBLEM_STATE_CPU_CYCLES",
+		"BriefDescription": "Problem-State CPU Cycles",
+		"PublicDescription": "Problem-State Cycle Count"
+	},
+	{
+		"EventCode": "33",
+		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
+		"BriefDescription": "Problem-State Instructions",
+		"PublicDescription": "Problem-State Instruction Count"
+	},
+	{
+		"EventCode": "34",
+		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
+		"BriefDescription": "Problem-State L1I Directory Writes",
+		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
+	},
+	{
+		"EventCode": "35",
+		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
+		"BriefDescription": "Problem-State L1I Penalty Cycles",
+		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
+	},
+	{
+		"EventCode": "36",
+		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
+		"BriefDescription": "Problem-State L1D Directory Writes",
+		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
+	},
+	{
+		"EventCode": "37",
+		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
+		"BriefDescription": "Problem-State L1D Penalty Cycles",
+		"PublicDescription": "Problem-State Level-1 D-Cache Penalty Cycle Count"
+	},
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json
new file mode 100644
index 000000000000..7e5b72492141
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/crypto.json
@@ -0,0 +1,98 @@
+[
+	{
+		"EventCode": "64",
+		"EventName": "PRNG_FUNCTIONS",
+		"BriefDescription": "PRNG Functions",
+		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
+	},
+	{
+		"EventCode": "65",
+		"EventName": "PRNG_CYCLES",
+		"BriefDescription": "PRNG Cycles",
+		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
+	},
+	{
+		"EventCode": "66",
+		"EventName": "PRNG_BLOCKED_FUNCTIONS",
+		"BriefDescription": "PRNG Blocked Functions",
+		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "67",
+		"EventName": "PRNG_BLOCKED_CYCLES",
+		"BriefDescription": "PRNG Blocked Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "68",
+		"EventName": "SHA_FUNCTIONS",
+		"BriefDescription": "SHA Functions",
+		"PublicDescription": "Total number of SHA functions issued by the CPU"
+	},
+	{
+		"EventCode": "69",
+		"EventName": "SHA_CYCLES",
+		"BriefDescription": "SHA Cycles",
+		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
+	},
+	{
+		"EventCode": "70",
+		"EventName": "SHA_BLOCKED_FUNCTIONS",
+		"BriefDescription": "SHA Blocked Functions",
+		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "71",
+		"EventName": "SHA_BLOCKED_CYCLES",
+		"BriefDescription": "SHA Bloced Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "72",
+		"EventName": "DEA_FUNCTIONS",
+		"BriefDescription": "DEA Functions",
+		"PublicDescription": "Total number of the DEA functions issued by the CPU"
+	},
+	{
+		"EventCode": "73",
+		"EventName": "DEA_CYCLES",
+		"BriefDescription": "DEA Cycles",
+		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
+	},
+	{
+		"EventCode": "74",
+		"EventName": "DEA_BLOCKED_FUNCTIONS",
+		"BriefDescription": "DEA Blocked Functions",
+		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "75",
+		"EventName": "DEA_BLOCKED_CYCLES",
+		"BriefDescription": "DEA Blocked Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "76",
+		"EventName": "AES_FUNCTIONS",
+		"BriefDescription": "AES Functions",
+		"PublicDescription": "Total number of AES functions issued by the CPU"
+	},
+	{
+		"EventCode": "77",
+		"EventName": "AES_CYCLES",
+		"BriefDescription": "AES Cycles",
+		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
+	},
+	{
+		"EventCode": "78",
+		"EventName": "AES_BLOCKED_FUNCTIONS",
+		"BriefDescription": "AES Blocked Functions",
+		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "79",
+		"EventName": "AES_BLOCKED_CYCLES",
+		"BriefDescription": "AES Blocked Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_z196/extended.json b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json
new file mode 100644
index 000000000000..b6d7fec7c2e7
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_z196/extended.json
@@ -0,0 +1,146 @@
+[
+	{
+		"EventCode": "128",
+		"EventName": "L1D_L2_SOURCED_WRITES",
+		"BriefDescription": "L1D L2 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from the Level-2 cache"
+	},
+	{
+		"EventCode": "129",
+		"EventName": "L1I_L2_SOURCED_WRITES",
+		"BriefDescription": "L1I L2 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from the Level-2 cache"
+	},
+	{
+		"EventCode": "130",
+		"EventName": "DTLB1_MISSES",
+		"BriefDescription": "DTLB1 Misses",
+		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
+	},
+	{
+		"EventCode": "131",
+		"EventName": "ITLB1_MISSES",
+		"BriefDescription": "ITLB1 Misses",
+		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress."
+	},
+	{
+		"EventCode": "133",
+		"EventName": "L2C_STORES_SENT",
+		"BriefDescription": "L2C Stores Sent",
+		"PublicDescription": "Incremented by one for every store sent to Level-2 cache"
+	},
+	{
+		"EventCode": "134",
+		"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Book L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache"
+	},
+	{
+		"EventCode": "135",
+		"EventName": "L1D_ONBOOK_L4_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Book L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Book Level-4 cache"
+	},
+	{
+		"EventCode": "136",
+		"EventName": "L1I_ONBOOK_L4_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Book L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Book Level-4 cache"
+	},
+	{
+		"EventCode": "137",
+		"EventName": "L1D_RO_EXCL_WRITES",
+		"BriefDescription": "L1D Read-only Exclusive Writes",
+		"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
+	},
+	{
+		"EventCode": "138",
+		"EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Book L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
+	},
+	{
+		"EventCode": "139",
+		"EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Book L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
+	},
+	{
+		"EventCode": "140",
+		"EventName": "DTLB1_HPAGE_WRITES",
+		"BriefDescription": "DTLB1 One-Megabyte Page Writes",
+		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
+	},
+	{
+		"EventCode": "141",
+		"EventName": "L1D_LMEM_SOURCED_WRITES",
+		"BriefDescription": "L1D Local Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 D-Cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
+	},
+	{
+		"EventCode": "142",
+		"EventName": "L1I_LMEM_SOURCED_WRITES",
+		"BriefDescription": "L1I Local Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 I-Cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)"
+	},
+	{
+		"EventCode": "143",
+		"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Book L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Book Level-3 cache"
+	},
+	{
+		"EventCode": "144",
+		"EventName": "DTLB1_WRITES",
+		"BriefDescription": "DTLB1 Writes",
+		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
+	},
+	{
+		"EventCode": "145",
+		"EventName": "ITLB1_WRITES",
+		"BriefDescription": "ITLB1 Writes",
+		"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
+	},
+	{
+		"EventCode": "146",
+		"EventName": "TLB2_PTE_WRITES",
+		"BriefDescription": "TLB2 PTE Writes",
+		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
+	},
+	{
+		"EventCode": "147",
+		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
+		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
+		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
+	},
+	{
+		"EventCode": "148",
+		"EventName": "TLB2_CRSTE_WRITES",
+		"BriefDescription": "TLB2 CRSTE Writes",
+		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
+	},
+	{
+		"EventCode": "150",
+		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache"
+	},
+	{
+		"EventCode": "152",
+		"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Chip L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 D-Cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache"
+	},
+	{
+		"EventCode": "153",
+		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an On Chip Level-3 cache"
+	},
+	{
+		"EventCode": "155",
+		"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Chip L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 I-Cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache"
+	},
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json
new file mode 100644
index 000000000000..8bf16759ca53
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/basic.json
@@ -0,0 +1,74 @@
+[
+	{
+		"EventCode": "0",
+		"EventName": "CPU_CYCLES",
+		"BriefDescription": "CPU Cycles",
+		"PublicDescription": "Cycle Count"
+	},
+	{
+		"EventCode": "1",
+		"EventName": "INSTRUCTIONS",
+		"BriefDescription": "Instructions",
+		"PublicDescription": "Instruction Count"
+	},
+	{
+		"EventCode": "2",
+		"EventName": "L1I_DIR_WRITES",
+		"BriefDescription": "L1I Directory Writes",
+		"PublicDescription": "Level-1 I-Cache Directory Write Count"
+	},
+	{
+		"EventCode": "3",
+		"EventName": "L1I_PENALTY_CYCLES",
+		"BriefDescription": "L1I Penalty Cycles",
+		"PublicDescription": "Level-1 I-Cache Penalty Cycle Count"
+	},
+	{
+		"EventCode": "4",
+		"EventName": "L1D_DIR_WRITES",
+		"BriefDescription": "L1D Directory Writes",
+		"PublicDescription": "Level-1 D-Cache Directory Write Count"
+	},
+	{
+		"EventCode": "5",
+		"EventName": "L1D_PENALTY_CYCLES",
+		"BriefDescription": "L1D Penalty Cycles",
+		"PublicDescription": "Level-1 D-Cache Penalty Cycle Count"
+	},
+	{
+		"EventCode": "32",
+		"EventName": "PROBLEM_STATE_CPU_CYCLES",
+		"BriefDescription": "Problem-State CPU Cycles",
+		"PublicDescription": "Problem-State Cycle Count"
+	},
+	{
+		"EventCode": "33",
+		"EventName": "PROBLEM_STATE_INSTRUCTIONS",
+		"BriefDescription": "Problem-State Instructions",
+		"PublicDescription": "Problem-State Instruction Count"
+	},
+	{
+		"EventCode": "34",
+		"EventName": "PROBLEM_STATE_L1I_DIR_WRITES",
+		"BriefDescription": "Problem-State L1I Directory Writes",
+		"PublicDescription": "Problem-State Level-1 I-Cache Directory Write Count"
+	},
+	{
+		"EventCode": "35",
+		"EventName": "PROBLEM_STATE_L1I_PENALTY_CYCLES",
+		"BriefDescription": "Problem-State L1I Penalty Cycles",
+		"PublicDescription": "Problem-State Level-1 I-Cache Penalty Cycle Count"
+	},
+	{
+		"EventCode": "36",
+		"EventName": "PROBLEM_STATE_L1D_DIR_WRITES",
+		"BriefDescription": "Problem-State L1D Directory Writes",
+		"PublicDescription": "Problem-State Level-1 D-Cache Directory Write Count"
+	},
+	{
+		"EventCode": "37",
+		"EventName": "PROBLEM_STATE_L1D_PENALTY_CYCLES",
+		"BriefDescription": "Problem-State L1D Penalty Cycles",
+		"PublicDescription": "Problem-State Level-1 D-Cache Penalty Cycle Count"
+	},
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json
new file mode 100644
index 000000000000..7e5b72492141
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/crypto.json
@@ -0,0 +1,98 @@
+[
+	{
+		"EventCode": "64",
+		"EventName": "PRNG_FUNCTIONS",
+		"BriefDescription": "PRNG Functions",
+		"PublicDescription": "Total number of the PRNG functions issued by the CPU"
+	},
+	{
+		"EventCode": "65",
+		"EventName": "PRNG_CYCLES",
+		"BriefDescription": "PRNG Cycles",
+		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing PRNG functions issued by the CPU"
+	},
+	{
+		"EventCode": "66",
+		"EventName": "PRNG_BLOCKED_FUNCTIONS",
+		"BriefDescription": "PRNG Blocked Functions",
+		"PublicDescription": "Total number of the PRNG functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "67",
+		"EventName": "PRNG_BLOCKED_CYCLES",
+		"BriefDescription": "PRNG Blocked Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the PRNG functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "68",
+		"EventName": "SHA_FUNCTIONS",
+		"BriefDescription": "SHA Functions",
+		"PublicDescription": "Total number of SHA functions issued by the CPU"
+	},
+	{
+		"EventCode": "69",
+		"EventName": "SHA_CYCLES",
+		"BriefDescription": "SHA Cycles",
+		"PublicDescription": "Total number of CPU cycles when the SHA coprocessor is busy performing the SHA functions issued by the CPU"
+	},
+	{
+		"EventCode": "70",
+		"EventName": "SHA_BLOCKED_FUNCTIONS",
+		"BriefDescription": "SHA Blocked Functions",
+		"PublicDescription": "Total number of the SHA functions that are issued by the CPU and are blocked because the SHA coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "71",
+		"EventName": "SHA_BLOCKED_CYCLES",
+		"BriefDescription": "SHA Bloced Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the SHA functions issued by the CPU because the SHA coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "72",
+		"EventName": "DEA_FUNCTIONS",
+		"BriefDescription": "DEA Functions",
+		"PublicDescription": "Total number of the DEA functions issued by the CPU"
+	},
+	{
+		"EventCode": "73",
+		"EventName": "DEA_CYCLES",
+		"BriefDescription": "DEA Cycles",
+		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the DEA functions issued by the CPU"
+	},
+	{
+		"EventCode": "74",
+		"EventName": "DEA_BLOCKED_FUNCTIONS",
+		"BriefDescription": "DEA Blocked Functions",
+		"PublicDescription": "Total number of the DEA functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "75",
+		"EventName": "DEA_BLOCKED_CYCLES",
+		"BriefDescription": "DEA Blocked Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the DEA functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "76",
+		"EventName": "AES_FUNCTIONS",
+		"BriefDescription": "AES Functions",
+		"PublicDescription": "Total number of AES functions issued by the CPU"
+	},
+	{
+		"EventCode": "77",
+		"EventName": "AES_CYCLES",
+		"BriefDescription": "AES Cycles",
+		"PublicDescription": "Total number of CPU cycles when the DEA/AES coprocessor is busy performing the AES functions issued by the CPU"
+	},
+	{
+		"EventCode": "78",
+		"EventName": "AES_BLOCKED_FUNCTIONS",
+		"BriefDescription": "AES Blocked Functions",
+		"PublicDescription": "Total number of AES functions that are issued by the CPU and are blocked because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+	{
+		"EventCode": "79",
+		"EventName": "AES_BLOCKED_CYCLES",
+		"BriefDescription": "AES Blocked Cycles",
+		"PublicDescription": "Total number of CPU cycles blocked for the AES functions issued by the CPU because the DEA/AES coprocessor is busy performing a function issued by another CPU"
+	},
+]
diff --git a/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json
new file mode 100644
index 000000000000..8682126aabb2
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/cf_zec12/extended.json
@@ -0,0 +1,212 @@
+[
+	{
+		"EventCode": "128",
+		"EventName": "DTLB1_MISSES",
+		"BriefDescription": "DTLB1 Misses",
+		"PublicDescription": "Level-1 Data TLB miss in progress. Incremented by one for every cycle a DTLB1 miss is in progress."
+	},
+	{
+		"EventCode": "129",
+		"EventName": "ITLB1_MISSES",
+		"BriefDescription": "ITLB1 Misses",
+		"PublicDescription": "Level-1 Instruction TLB miss in progress. Incremented by one for every cycle a ITLB1 miss is in progress."
+	},
+	{
+		"EventCode": "130",
+		"EventName": "L1D_L2I_SOURCED_WRITES",
+		"BriefDescription": "L1D L2I Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
+	},
+	{
+		"EventCode": "131",
+		"EventName": "L1I_L2I_SOURCED_WRITES",
+		"BriefDescription": "L1I L2I Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from the Level-2 Instruction cache"
+	},
+	{
+		"EventCode": "132",
+		"EventName": "L1D_L2D_SOURCED_WRITES",
+		"BriefDescription": "L1D L2D Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from the Level-2 Data cache"
+	},
+	{
+		"EventCode": "133",
+		"EventName": "DTLB1_WRITES",
+		"BriefDescription": "DTLB1 Writes",
+		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer"
+	},
+	{
+		"EventCode": "135",
+		"EventName": "L1D_LMEM_SOURCED_WRITES",
+		"BriefDescription": "L1D Local Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache where the installed cache line was sourced from memory that is attached to the same book as the Data cache (Local Memory)"
+	},
+	{
+		"EventCode": "137",
+		"EventName": "L1I_LMEM_SOURCED_WRITES",
+		"BriefDescription": "L1I Local Memory Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache where the installed cache line was sourced from memory that is attached to the same book as the Instruction cache (Local Memory)"
+	},
+	{
+		"EventCode": "138",
+		"EventName": "L1D_RO_EXCL_WRITES",
+		"BriefDescription": "L1D Read-only Exclusive Writes",
+		"PublicDescription": "A directory write to the Level-1 D-Cache where the line was originally in a Read-Only state in the cache but has been updated to be in the Exclusive state that allows stores to the cache line"
+	},
+	{
+		"EventCode": "139",
+		"EventName": "DTLB1_HPAGE_WRITES",
+		"BriefDescription": "DTLB1 One-Megabyte Page Writes",
+		"PublicDescription": "A translation entry has been written to the Level-1 Data Translation Lookaside Buffer for a one-megabyte page"
+	},
+	{
+		"EventCode": "140",
+		"EventName": "ITLB1_WRITES",
+		"BriefDescription": "ITLB1 Writes",
+		"PublicDescription": "A translation entry has been written to the Level-1 Instruction Translation Lookaside Buffer"
+	},
+	{
+		"EventCode": "141",
+		"EventName": "TLB2_PTE_WRITES",
+		"BriefDescription": "TLB2 PTE Writes",
+		"PublicDescription": "A translation entry has been written to the Level-2 TLB Page Table Entry arrays"
+	},
+	{
+		"EventCode": "142",
+		"EventName": "TLB2_CRSTE_HPAGE_WRITES",
+		"BriefDescription": "TLB2 CRSTE One-Megabyte Page Writes",
+		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays for a one-megabyte large page translation"
+	},
+	{
+		"EventCode": "143",
+		"EventName": "TLB2_CRSTE_WRITES",
+		"BriefDescription": "TLB2 CRSTE Writes",
+		"PublicDescription": "A translation entry has been written to the Level-2 TLB Common Region Segment Table Entry arrays"
+	},
+	{
+		"EventCode": "144",
+		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Chip L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "145",
+		"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Chip L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "146",
+		"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Book L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "147",
+		"EventName": "L1D_ONBOOK_L4_SOURCED_WRITES",
+		"BriefDescription": "L1D On-Book L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an On Book Level-4 cache"
+	},
+	{
+		"EventCode": "148",
+		"EventName": "L1D_OFFBOOK_L4_SOURCED_WRITES",
+		"BriefDescription": "L1D Off-Book L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
+	},
+	{
+		"EventCode": "149",
+		"EventName": "TX_NC_TEND",
+		"BriefDescription": "Completed TEND instructions in non-constrained TX mode",
+		"PublicDescription": "A TEND instruction has completed in a nonconstrained transactional-execution mode"
+	},
+	{
+		"EventCode": "150",
+		"EventName": "L1D_ONCHIP_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1D On-Chip L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from a On Chip Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "151",
+		"EventName": "L1D_OFFCHIP_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1D Off-Chip L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "152",
+		"EventName": "L1D_OFFBOOK_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1D Off-Book L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Data cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "153",
+		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Chip L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "154",
+		"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Chip L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "155",
+		"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Book L3 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache without intervention"
+	},
+	{
+		"EventCode": "156",
+		"EventName": "L1I_ONBOOK_L4_SOURCED_WRITES",
+		"BriefDescription": "L1I On-Book L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Book Level-4 cache"
+	},
+	{
+		"EventCode": "157",
+		"EventName": "L1I_OFFBOOK_L4_SOURCED_WRITES",
+		"BriefDescription": "L1I Off-Book L4 Sourced Writes",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-4 cache"
+	},
+	{
+		"EventCode": "158",
+		"EventName": "TX_C_TEND",
+		"BriefDescription": "Completed TEND instructions in constrained TX mode",
+		"PublicDescription": "A TEND instruction has completed in a constrained transactional-execution mode"
+	},
+	{
+		"EventCode": "159",
+		"EventName": "L1I_ONCHIP_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1I On-Chip L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an On Chip Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "160",
+		"EventName": "L1I_OFFCHIP_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1I Off-Chip L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Chip/On Book Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "161",
+		"EventName": "L1I_OFFBOOK_L3_SOURCED_WRITES_IV",
+		"BriefDescription": "L1I Off-Book L3 Sourced Writes with Intervention",
+		"PublicDescription": "A directory write to the Level-1 Instruction cache directory where the returned cache line was sourced from an Off Book Level-3 cache with intervention"
+	},
+	{
+		"EventCode": "177",
+		"EventName": "TX_NC_TABORT",
+		"BriefDescription": "Aborted transactions in non-constrained TX mode",
+		"PublicDescription": "A transaction abort has occurred in a nonconstrained transactional-execution mode"
+	},
+	{
+		"EventCode": "178",
+		"EventName": "TX_C_TABORT_NO_SPECIAL",
+		"BriefDescription": "Aborted transactions in constrained TX mode not using special completion logic",
+		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is not using any special logic to allow the transaction to complete"
+	},
+	{
+		"EventCode": "179",
+		"EventName": "TX_C_TABORT_SPECIAL",
+		"BriefDescription": "Aborted transactions in constrained TX mode using special completion logic",
+		"PublicDescription": "A transaction abort has occurred in a constrained transactional-execution mode and the CPU is using special logic to allow the transaction to complete"
+	},
+]
diff --git a/tools/perf/pmu-events/arch/s390/mapfile.csv b/tools/perf/pmu-events/arch/s390/mapfile.csv
new file mode 100644
index 000000000000..ca7682748a4b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/s390/mapfile.csv
@@ -0,0 +1,6 @@
+Family-model,Version,Filename,EventType
+209[78],1,cf_z10,core
+281[78],1,cf_z196,core
+282[78],1,cf_zec12,core
+296[45],1,cf_z13,core
+3906,3,cf_z14,core
diff --git a/tools/perf/pmu-events/jevents.c b/tools/perf/pmu-events/jevents.c
index b578aa26e375..db3a594ee1e4 100644
--- a/tools/perf/pmu-events/jevents.c
+++ b/tools/perf/pmu-events/jevents.c
@@ -39,11 +39,13 @@
 #include <unistd.h>
 #include <stdarg.h>
 #include <libgen.h>
+#include <limits.h>
 #include <dirent.h>
 #include <sys/time.h>			/* getrlimit */
 #include <sys/resource.h>		/* getrlimit */
 #include <ftw.h>
 #include <sys/stat.h>
+#include <linux/list.h>
 #include "jsmn.h"
 #include "json.h"
 #include "jevents.h"
@@ -249,31 +251,25 @@ static const char *field_to_perf(struct map *table, char *map, jsmntok_t *val)
 	jsmntok_t *loc = (t);					\
 	if (!(t)->start && (t) > tokens)			\
 		loc = (t) - 1;					\
-		pr_err("%s:%d: " m ", got %s\n", fn,		\
-			json_line(map, loc),			\
-			json_name(t));				\
+	pr_err("%s:%d: " m ", got %s\n", fn,			\
+	       json_line(map, loc),				\
+	       json_name(t));					\
+	err = -EIO;						\
 	goto out_free;						\
 } } while (0)
 
-#define TOPIC_DEPTH 256
-static char *topic_array[TOPIC_DEPTH];
-static int   topic_level;
+static char *topic;
 
 static char *get_topic(void)
 {
-	char *tp_old, *tp = NULL;
+	char *tp;
 	int i;
 
-	for (i = 0; i < topic_level + 1; i++) {
-		int n;
-
-		tp_old = tp;
-		n = asprintf(&tp, "%s%s", tp ?: "", topic_array[i]);
-		if (n < 0) {
-			pr_info("%s: asprintf() error %s\n", prog);
-			return NULL;
-		}
-		free(tp_old);
+	/* tp is free'd in process_one_file() */
+	i = asprintf(&tp, "%s", topic);
+	if (i < 0) {
+		pr_info("%s: asprintf() error %s\n", prog);
+		return NULL;
 	}
 
 	for (i = 0; i < (int) strlen(tp); i++) {
@@ -290,25 +286,15 @@ static char *get_topic(void)
 	return tp;
 }
 
-static int add_topic(int level, char *bname)
+static int add_topic(char *bname)
 {
-	char *topic;
-
-	level -= 2;
-
-	if (level >= TOPIC_DEPTH)
-		return -EINVAL;
-
+	free(topic);
 	topic = strdup(bname);
 	if (!topic) {
 		pr_info("%s: strdup() error %s for file %s\n", prog,
 				strerror(errno), bname);
 		return -ENOMEM;
 	}
-
-	free(topic_array[topic_level]);
-	topic_array[topic_level] = topic;
-	topic_level              = level;
 	return 0;
 }
 
@@ -366,6 +352,81 @@ static int print_events_table_entry(void *data, char *name, char *event,
 	return 0;
 }
 
+struct event_struct {
+	struct list_head list;
+	char *name;
+	char *event;
+	char *desc;
+	char *long_desc;
+	char *pmu;
+	char *unit;
+	char *perpkg;
+	char *metric_expr;
+	char *metric_name;
+	char *metric_group;
+};
+
+#define ADD_EVENT_FIELD(field) do { if (field) {		\
+	es->field = strdup(field);				\
+	if (!es->field)						\
+		goto out_free;					\
+} } while (0)
+
+#define FREE_EVENT_FIELD(field) free(es->field)
+
+#define TRY_FIXUP_FIELD(field) do { if (es->field && !*field) {\
+	*field = strdup(es->field);				\
+	if (!*field)						\
+		return -ENOMEM;					\
+} } while (0)
+
+#define FOR_ALL_EVENT_STRUCT_FIELDS(op) do {			\
+	op(name);						\
+	op(event);						\
+	op(desc);						\
+	op(long_desc);						\
+	op(pmu);						\
+	op(unit);						\
+	op(perpkg);						\
+	op(metric_expr);					\
+	op(metric_name);					\
+	op(metric_group);					\
+} while (0)
+
+static LIST_HEAD(arch_std_events);
+
+static void free_arch_std_events(void)
+{
+	struct event_struct *es, *next;
+
+	list_for_each_entry_safe(es, next, &arch_std_events, list) {
+		FOR_ALL_EVENT_STRUCT_FIELDS(FREE_EVENT_FIELD);
+		list_del(&es->list);
+		free(es);
+	}
+}
+
+static int save_arch_std_events(void *data, char *name, char *event,
+				char *desc, char *long_desc, char *pmu,
+				char *unit, char *perpkg, char *metric_expr,
+				char *metric_name, char *metric_group)
+{
+	struct event_struct *es;
+	struct stat *sb = data;
+
+	es = malloc(sizeof(*es));
+	if (!es)
+		return -ENOMEM;
+	memset(es, 0, sizeof(*es));
+	FOR_ALL_EVENT_STRUCT_FIELDS(ADD_EVENT_FIELD);
+	list_add_tail(&es->list, &arch_std_events);
+	return 0;
+out_free:
+	FOR_ALL_EVENT_STRUCT_FIELDS(FREE_EVENT_FIELD);
+	free(es);
+	return -ENOMEM;
+}
+
 static void print_events_table_suffix(FILE *outfp)
 {
 	fprintf(outfp, "{\n");
@@ -407,6 +468,32 @@ static char *real_event(const char *name, char *event)
 	return event;
 }
 
+static int
+try_fixup(const char *fn, char *arch_std, char **event, char **desc,
+	  char **name, char **long_desc, char **pmu, char **filter,
+	  char **perpkg, char **unit, char **metric_expr, char **metric_name,
+	  char **metric_group, unsigned long long eventcode)
+{
+	/* try to find matching event from arch standard values */
+	struct event_struct *es;
+
+	list_for_each_entry(es, &arch_std_events, list) {
+		if (!strcmp(arch_std, es->name)) {
+			if (!eventcode && es->event) {
+				/* allow EventCode to be overridden */
+				free(*event);
+				*event = NULL;
+			}
+			FOR_ALL_EVENT_STRUCT_FIELDS(TRY_FIXUP_FIELD);
+			return 0;
+		}
+	}
+
+	pr_err("%s: could not find matching %s for %s\n",
+					prog, arch_std, fn);
+	return -1;
+}
+
 /* Call func with each event in the json file */
 int json_events(const char *fn,
 	  int (*func)(void *data, char *name, char *event, char *desc,
@@ -416,7 +503,7 @@ int json_events(const char *fn,
 		      char *metric_name, char *metric_group),
 	  void *data)
 {
-	int err = -EIO;
+	int err;
 	size_t size;
 	jsmntok_t *tokens, *tok;
 	int i, j, len;
@@ -442,6 +529,7 @@ int json_events(const char *fn,
 		char *metric_expr = NULL;
 		char *metric_name = NULL;
 		char *metric_group = NULL;
+		char *arch_std = NULL;
 		unsigned long long eventcode = 0;
 		struct msrmap *msr = NULL;
 		jsmntok_t *msrval = NULL;
@@ -527,6 +615,10 @@ int json_events(const char *fn,
 				addfield(map, &metric_expr, "", "", val);
 				for (s = metric_expr; *s; s++)
 					*s = tolower(*s);
+			} else if (json_streq(map, field, "ArchStdEvent")) {
+				addfield(map, &arch_std, "", "", val);
+				for (s = arch_std; *s; s++)
+					*s = tolower(*s);
 			}
 			/* ignore unknown fields */
 		}
@@ -551,8 +643,21 @@ int json_events(const char *fn,
 		if (name)
 			fixname(name);
 
+		if (arch_std) {
+			/*
+			 * An arch standard event is referenced, so try to
+			 * fixup any unassigned values.
+			 */
+			err = try_fixup(fn, arch_std, &event, &desc, &name,
+					&long_desc, &pmu, &filter, &perpkg,
+					&unit, &metric_expr, &metric_name,
+					&metric_group, eventcode);
+			if (err)
+				goto free_strings;
+		}
 		err = func(data, name, real_event(name, event), desc, long_desc,
 			   pmu, unit, perpkg, metric_expr, metric_name, metric_group);
+free_strings:
 		free(event);
 		free(desc);
 		free(name);
@@ -565,6 +670,8 @@ int json_events(const char *fn,
 		free(metric_expr);
 		free(metric_name);
 		free(metric_group);
+		free(arch_std);
+
 		if (err)
 			break;
 		tok += j;
@@ -588,7 +695,7 @@ static char *file_name_to_table_name(char *fname)
 	 * Derive rest of table name from basename of the JSON file,
 	 * replacing hyphens and stripping out .json suffix.
 	 */
-	n = asprintf(&tblname, "pme_%s", basename(fname));
+	n = asprintf(&tblname, "pme_%s", fname);
 	if (n < 0) {
 		pr_info("%s: asprintf() error %s for file %s\n", prog,
 				strerror(errno), fname);
@@ -598,7 +705,7 @@ static char *file_name_to_table_name(char *fname)
 	for (i = 0; i < strlen(tblname); i++) {
 		c = tblname[i];
 
-		if (c == '-')
+		if (c == '-' || c == '/')
 			tblname[i] = '_';
 		else if (c == '.') {
 			tblname[i] = '\0';
@@ -755,25 +862,106 @@ static int get_maxfds(void)
 static FILE *eventsfp;
 static char *mapfile;
 
+static int is_leaf_dir(const char *fpath)
+{
+	DIR *d;
+	struct dirent *dir;
+	int res = 1;
+
+	d = opendir(fpath);
+	if (!d)
+		return 0;
+
+	while ((dir = readdir(d)) != NULL) {
+		if (!strcmp(dir->d_name, ".") || !strcmp(dir->d_name, ".."))
+			continue;
+
+		if (dir->d_type == DT_DIR) {
+			res = 0;
+			break;
+		} else if (dir->d_type == DT_UNKNOWN) {
+			char path[PATH_MAX];
+			struct stat st;
+
+			sprintf(path, "%s/%s", fpath, dir->d_name);
+			if (stat(path, &st))
+				break;
+
+			if (S_ISDIR(st.st_mode)) {
+				res = 0;
+				break;
+			}
+		}
+	}
+
+	closedir(d);
+
+	return res;
+}
+
+static int is_json_file(const char *name)
+{
+	const char *suffix;
+
+	if (strlen(name) < 5)
+		return 0;
+
+	suffix = name + strlen(name) - 5;
+
+	if (strncmp(suffix, ".json", 5) == 0)
+		return 1;
+	return 0;
+}
+
+static int preprocess_arch_std_files(const char *fpath, const struct stat *sb,
+				int typeflag, struct FTW *ftwbuf)
+{
+	int level = ftwbuf->level;
+	int is_file = typeflag == FTW_F;
+
+	if (level == 1 && is_file && is_json_file(fpath))
+		return json_events(fpath, save_arch_std_events, (void *)sb);
+
+	return 0;
+}
+
 static int process_one_file(const char *fpath, const struct stat *sb,
 			    int typeflag, struct FTW *ftwbuf)
 {
-	char *tblname, *bname  = (char *) fpath + ftwbuf->base;
+	char *tblname, *bname;
 	int is_dir  = typeflag == FTW_D;
 	int is_file = typeflag == FTW_F;
 	int level   = ftwbuf->level;
 	int err = 0;
 
+	if (level == 2 && is_dir) {
+		/*
+		 * For level 2 directory, bname will include parent name,
+		 * like vendor/platform. So search back from platform dir
+		 * to find this.
+		 */
+		bname = (char *) fpath + ftwbuf->base - 2;
+		for (;;) {
+			if (*bname == '/')
+				break;
+			bname--;
+		}
+		bname++;
+	} else
+		bname = (char *) fpath + ftwbuf->base;
+
 	pr_debug("%s %d %7jd %-20s %s\n",
 		 is_file ? "f" : is_dir ? "d" : "x",
 		 level, sb->st_size, bname, fpath);
 
-	/* base dir */
-	if (level == 0)
+	/* base dir or too deep */
+	if (level == 0 || level > 3)
 		return 0;
 
+
 	/* model directory, reset topic */
-	if (level == 1 && is_dir) {
+	if ((level == 1 && is_dir && is_leaf_dir(fpath)) ||
+	    (level == 2 && is_dir)) {
 		if (close_table)
 			print_events_table_suffix(eventsfp);
 
@@ -798,16 +986,10 @@ static int process_one_file(const char *fpath, const struct stat *sb,
 	 * after processing all JSON files (so we can write out the
 	 * mapping table after all PMU events tables).
 	 *
-	 * TODO: Allow for multiple mapfiles? Punt for now.
 	 */
 	if (level == 1 && is_file) {
-		if (!strncmp(bname, "mapfile.csv", 11)) {
-			if (mapfile) {
-				pr_info("%s: Many mapfiles? Using %s, ignoring %s\n",
-						prog, mapfile, fpath);
-			} else {
-				mapfile = strdup(fpath);
-			}
+		if (!strcmp(bname, "mapfile.csv")) {
+			mapfile = strdup(fpath);
 			return 0;
 		}
 
@@ -820,16 +1002,14 @@ static int process_one_file(const char *fpath, const struct stat *sb,
 	 * ignore it. It could be a readme.txt for instance.
 	 */
 	if (is_file) {
-		char *suffix = bname + strlen(bname) - 5;
-
-		if (strncmp(suffix, ".json", 5)) {
+		if (!is_json_file(bname)) {
 			pr_info("%s: Ignoring file without .json suffix %s\n", prog,
 				fpath);
 			return 0;
 		}
 	}
 
-	if (level > 1 && add_topic(level, bname))
+	if (level > 1 && add_topic(bname))
 		return -ENOMEM;
 
 	/*
@@ -928,12 +1108,26 @@ int main(int argc, char *argv[])
 
 	maxfds = get_maxfds();
 	mapfile = NULL;
+	rc = nftw(ldirname, preprocess_arch_std_files, maxfds, 0);
+	if (rc && verbose) {
+		pr_info("%s: Error preprocessing arch standard files %s\n",
+			prog, ldirname);
+		goto empty_map;
+	} else if (rc < 0) {
+		/* Make build fail */
+		free_arch_std_events();
+		return 1;
+	} else if (rc) {
+		goto empty_map;
+	}
+
 	rc = nftw(ldirname, process_one_file, maxfds, 0);
 	if (rc && verbose) {
 		pr_info("%s: Error walking file tree %s\n", prog, ldirname);
 		goto empty_map;
 	} else if (rc < 0) {
 		/* Make build fail */
+		free_arch_std_events();
 		return 1;
 	} else if (rc) {
 		goto empty_map;
@@ -958,5 +1152,6 @@ int main(int argc, char *argv[])
 empty_map:
 	fclose(eventsfp);
 	create_empty_mapping(output_file);
+	free_arch_std_events();
 	return 0;
 }
diff --git a/tools/perf/python/twatch.py b/tools/perf/python/twatch.py
index c235c22b107a..0a29c5c3079f 100755
--- a/tools/perf/python/twatch.py
+++ b/tools/perf/python/twatch.py
@@ -42,10 +42,10 @@ def main(context_switch = 0, thread = -1):
 			event = evlist.read_on_cpu(cpu)
 			if not event:
 				continue
-			print "cpu: %2d, pid: %4d, tid: %4d" % (event.sample_cpu,
-								event.sample_pid,
-								event.sample_tid),
-			print event
+			print("cpu: {0}, pid: {1}, tid: {2} {3}".format(event.sample_cpu,
+                                                                        event.sample_pid,
+                                                                        event.sample_tid,
+                                                                        event))
 
 if __name__ == '__main__':
     """
diff --git a/tools/perf/scripts/python/Perf-Trace-Util/Context.c b/tools/perf/scripts/python/Perf-Trace-Util/Context.c
index fcd1dd667906..1a0d27757eec 100644
--- a/tools/perf/scripts/python/Perf-Trace-Util/Context.c
+++ b/tools/perf/scripts/python/Perf-Trace-Util/Context.c
@@ -23,7 +23,17 @@
 #include "../../../perf.h"
 #include "../../../util/trace-event.h"
 
+#if PY_MAJOR_VERSION < 3
+#define _PyCapsule_GetPointer(arg1, arg2) \
+  PyCObject_AsVoidPtr(arg1)
+
 PyMODINIT_FUNC initperf_trace_context(void);
+#else
+#define _PyCapsule_GetPointer(arg1, arg2) \
+  PyCapsule_GetPointer((arg1), (arg2))
+
+PyMODINIT_FUNC PyInit_perf_trace_context(void);
+#endif
 
 static PyObject *perf_trace_context_common_pc(PyObject *obj, PyObject *args)
 {
@@ -34,7 +44,7 @@ static PyObject *perf_trace_context_common_pc(PyObject *obj, PyObject *args)
 	if (!PyArg_ParseTuple(args, "O", &context))
 		return NULL;
 
-	scripting_context = PyCObject_AsVoidPtr(context);
+	scripting_context = _PyCapsule_GetPointer(context, NULL);
 	retval = common_pc(scripting_context);
 
 	return Py_BuildValue("i", retval);
@@ -50,7 +60,7 @@ static PyObject *perf_trace_context_common_flags(PyObject *obj,
 	if (!PyArg_ParseTuple(args, "O", &context))
 		return NULL;
 
-	scripting_context = PyCObject_AsVoidPtr(context);
+	scripting_context = _PyCapsule_GetPointer(context, NULL);
 	retval = common_flags(scripting_context);
 
 	return Py_BuildValue("i", retval);
@@ -66,7 +76,7 @@ static PyObject *perf_trace_context_common_lock_depth(PyObject *obj,
 	if (!PyArg_ParseTuple(args, "O", &context))
 		return NULL;
 
-	scripting_context = PyCObject_AsVoidPtr(context);
+	scripting_context = _PyCapsule_GetPointer(context, NULL);
 	retval = common_lock_depth(scripting_context);
 
 	return Py_BuildValue("i", retval);
@@ -82,7 +92,25 @@ static PyMethodDef ContextMethods[] = {
 	{ NULL, NULL, 0, NULL}
 };
 
+#if PY_MAJOR_VERSION < 3
 PyMODINIT_FUNC initperf_trace_context(void)
 {
 	(void) Py_InitModule("perf_trace_context", ContextMethods);
 }
+#else
+PyMODINIT_FUNC PyInit_perf_trace_context(void)
+{
+	static struct PyModuleDef moduledef = {
+		PyModuleDef_HEAD_INIT,
+		"perf_trace_context",	/* m_name */
+		"",			/* m_doc */
+		-1,			/* m_size */
+		ContextMethods,		/* m_methods */
+		NULL,			/* m_reload */
+		NULL,			/* m_traverse */
+		NULL,			/* m_clear */
+		NULL,			/* m_free */
+	};
+	return PyModule_Create(&moduledef);
+}
+#endif
diff --git a/tools/perf/tests/Build b/tools/perf/tests/Build
index 87bf3edb037c..6c108fa79ae3 100644
--- a/tools/perf/tests/Build
+++ b/tools/perf/tests/Build
@@ -20,6 +20,7 @@ perf-y += hists_cumulate.o
 perf-y += python-use.o
 perf-y += bp_signal.o
 perf-y += bp_signal_overflow.o
+perf-y += bp_account.o
 perf-y += task-exit.o
 perf-y += sw-clock.o
 perf-y += mmap-thread-lookup.o
@@ -47,6 +48,7 @@ perf-y += bitmap.o
 perf-y += perf-hooks.o
 perf-y += clang.o
 perf-y += unit_number__scnprintf.o
+perf-y += mem2node.o
 
 $(OUTPUT)tests/llvm-src-base.c: tests/bpf-script-example.c tests/Build
 	$(call rule_mkdir)
diff --git a/tools/perf/tests/attr.c b/tools/perf/tests/attr.c
index 97f64ad7fa08..05dfe11c2f9e 100644
--- a/tools/perf/tests/attr.c
+++ b/tools/perf/tests/attr.c
@@ -170,8 +170,8 @@ static int run_dir(const char *d, const char *perf)
 	if (verbose > 0)
 		vcnt++;
 
-	snprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %.*s",
-		 d, d, perf, vcnt, v);
+	scnprintf(cmd, 3*PATH_MAX, PYTHON " %s/attr.py -d %s/attr/ -p %s %.*s",
+		  d, d, perf, vcnt, v);
 
 	return system(cmd) ? TEST_FAIL : TEST_OK;
 }
diff --git a/tools/perf/tests/backward-ring-buffer.c b/tools/perf/tests/backward-ring-buffer.c
index e0b1b414d466..6d598cc071ae 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -33,10 +33,9 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count,
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		struct perf_mmap *map = &evlist->overwrite_mmap[i];
 		union perf_event *event;
-		u64 start, end;
 
-		perf_mmap__read_init(map, true, &start, &end);
-		while ((event = perf_mmap__read_event(map, true, &start, end)) != NULL) {
+		perf_mmap__read_init(map);
+		while ((event = perf_mmap__read_event(map)) != NULL) {
 			const u32 type = event->header.type;
 
 			switch (type) {
diff --git a/tools/perf/tests/bp_account.c b/tools/perf/tests/bp_account.c
new file mode 100644
index 000000000000..a20cbc445426
--- /dev/null
+++ b/tools/perf/tests/bp_account.c
@@ -0,0 +1,193 @@
+/*
+ * Powerpc needs __SANE_USERSPACE_TYPES__ before <linux/types.h> to select
+ * 'int-ll64.h' and avoid compile warnings when printing __u64 with %llu.
+ */
+#define __SANE_USERSPACE_TYPES__
+
+#include <stdlib.h>
+#include <stdio.h>
+#include <unistd.h>
+#include <string.h>
+#include <sys/ioctl.h>
+#include <time.h>
+#include <fcntl.h>
+#include <signal.h>
+#include <sys/mman.h>
+#include <linux/compiler.h>
+#include <linux/hw_breakpoint.h>
+#include <sys/ioctl.h>
+
+#include "tests.h"
+#include "debug.h"
+#include "perf.h"
+#include "cloexec.h"
+
+volatile long the_var;
+
+static noinline int test_function(void)
+{
+	return 0;
+}
+
+static int __event(bool is_x, void *addr, struct perf_event_attr *attr)
+{
+	int fd;
+
+	memset(attr, 0, sizeof(struct perf_event_attr));
+	attr->type = PERF_TYPE_BREAKPOINT;
+	attr->size = sizeof(struct perf_event_attr);
+
+	attr->config = 0;
+	attr->bp_type = is_x ? HW_BREAKPOINT_X : HW_BREAKPOINT_W;
+	attr->bp_addr = (unsigned long) addr;
+	attr->bp_len = sizeof(long);
+
+	attr->sample_period = 1;
+	attr->sample_type = PERF_SAMPLE_IP;
+
+	attr->exclude_kernel = 1;
+	attr->exclude_hv = 1;
+
+	fd = sys_perf_event_open(attr, -1, 0, -1,
+				 perf_event_open_cloexec_flag());
+	if (fd < 0) {
+		pr_debug("failed opening event %llx\n", attr->config);
+		return TEST_FAIL;
+	}
+
+	return fd;
+}
+
+static int wp_event(void *addr, struct perf_event_attr *attr)
+{
+	return __event(false, addr, attr);
+}
+
+static int bp_event(void *addr, struct perf_event_attr *attr)
+{
+	return __event(true, addr, attr);
+}
+
+static int bp_accounting(int wp_cnt, int share)
+{
+	struct perf_event_attr attr, attr_mod, attr_new;
+	int i, fd[wp_cnt], fd_wp, ret;
+
+	for (i = 0; i < wp_cnt; i++) {
+		fd[i] = wp_event((void *)&the_var, &attr);
+		TEST_ASSERT_VAL("failed to create wp\n", fd[i] != -1);
+		pr_debug("wp %d created\n", i);
+	}
+
+	attr_mod = attr;
+	attr_mod.bp_type = HW_BREAKPOINT_X;
+	attr_mod.bp_addr = (unsigned long) test_function;
+
+	ret = ioctl(fd[0], PERF_EVENT_IOC_MODIFY_ATTRIBUTES, &attr_mod);
+	TEST_ASSERT_VAL("failed to modify wp\n", ret == 0);
+
+	pr_debug("wp 0 modified to bp\n");
+
+	if (!share) {
+		fd_wp = wp_event((void *)&the_var, &attr_new);
+		TEST_ASSERT_VAL("failed to create max wp\n", fd_wp != -1);
+		pr_debug("wp max created\n");
+	}
+
+	for (i = 0; i < wp_cnt; i++)
+		close(fd[i]);
+
+	return 0;
+}
+
+static int detect_cnt(bool is_x)
+{
+	struct perf_event_attr attr;
+	void *addr = is_x ? (void *)test_function : (void *)&the_var;
+	int fd[100], cnt = 0, i;
+
+	while (1) {
+		if (cnt == 100) {
+			pr_debug("way too many debug registers, fix the test\n");
+			return 0;
+		}
+		fd[cnt] = __event(is_x, addr, &attr);
+
+		if (fd[cnt] < 0)
+			break;
+		cnt++;
+	}
+
+	for (i = 0; i < cnt; i++)
+		close(fd[i]);
+
+	return cnt;
+}
+
+static int detect_ioctl(void)
+{
+	struct perf_event_attr attr;
+	int fd, ret = 1;
+
+	fd = wp_event((void *) &the_var, &attr);
+	if (fd > 0) {
+		ret = ioctl(fd, PERF_EVENT_IOC_MODIFY_ATTRIBUTES, &attr);
+		close(fd);
+	}
+
+	return ret ? 0 : 1;
+}
+
+static int detect_share(int wp_cnt, int bp_cnt)
+{
+	struct perf_event_attr attr;
+	int i, fd[wp_cnt + bp_cnt], ret;
+
+	for (i = 0; i < wp_cnt; i++) {
+		fd[i] = wp_event((void *)&the_var, &attr);
+		TEST_ASSERT_VAL("failed to create wp\n", fd[i] != -1);
+	}
+
+	for (; i < (bp_cnt + wp_cnt); i++) {
+		fd[i] = bp_event((void *)test_function, &attr);
+		if (fd[i] == -1)
+			break;
+	}
+
+	ret = i != (bp_cnt + wp_cnt);
+
+	while (i--)
+		close(fd[i]);
+
+	return ret;
+}
+
+/*
+ * This test does following:
+ *   - detects the number of watch/break-points,
+ *     skip test if any is missing
+ *   - detects PERF_EVENT_IOC_MODIFY_ATTRIBUTES ioctl,
+ *     skip test if it's missing
+ *   - detects if watchpoints and breakpoints share
+ *     same slots
+ *   - create all possible watchpoints on cpu 0
+ *   - change one of it to breakpoint
+ *   - in case wp and bp do not share slots,
+ *     we create another watchpoint to ensure
+ *     the slot accounting is correct
+ */
+int test__bp_accounting(struct test *test __maybe_unused, int subtest __maybe_unused)
+{
+	int has_ioctl = detect_ioctl();
+	int wp_cnt = detect_cnt(false);
+	int bp_cnt = detect_cnt(true);
+	int share  = detect_share(wp_cnt, bp_cnt);
+
+	pr_debug("watchpoints count %d, breakpoints count %d, has_ioctl %d, share %d\n",
+		 wp_cnt, bp_cnt, has_ioctl, share);
+
+	if (!wp_cnt || !bp_cnt || !has_ioctl)
+		return TEST_SKIP;
+
+	return bp_accounting(wp_cnt, share);
+}
diff --git a/tools/perf/tests/bpf.c b/tools/perf/tests/bpf.c
index e8399beca62b..79b54f8ddebf 100644
--- a/tools/perf/tests/bpf.c
+++ b/tools/perf/tests/bpf.c
@@ -176,13 +176,19 @@ static int do_test(struct bpf_object *obj, int (*func)(void),
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		union perf_event *event;
+		struct perf_mmap *md;
 
-		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+		md = &evlist->mmap[i];
+		if (perf_mmap__read_init(md) < 0)
+			continue;
+
+		while ((event = perf_mmap__read_event(md)) != NULL) {
 			const u32 type = event->header.type;
 
 			if (type == PERF_RECORD_SAMPLE)
 				count ++;
 		}
+		perf_mmap__read_done(md);
 	}
 
 	if (count != expect) {
diff --git a/tools/perf/tests/builtin-test.c b/tools/perf/tests/builtin-test.c
index fafa014240cd..625f5a6772af 100644
--- a/tools/perf/tests/builtin-test.c
+++ b/tools/perf/tests/builtin-test.c
@@ -116,6 +116,10 @@ static struct test generic_tests[] = {
 		.is_supported = test__bp_signal_is_supported,
 	},
 	{
+		.desc = "Breakpoint accounting",
+		.func = test__bp_accounting,
+	},
+	{
 		.desc = "Number of exit events of a simple workload",
 		.func = test__task_exit,
 	},
@@ -271,6 +275,10 @@ static struct test generic_tests[] = {
 		.func = test__unit_number__scnprint,
 	},
 	{
+		.desc = "mem2node",
+		.func = test__mem2node,
+	},
+	{
 		.func = NULL,
 	},
 };
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 3bf7b145b826..99936352df4f 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -409,15 +409,21 @@ static int process_events(struct machine *machine, struct perf_evlist *evlist,
 			  struct state *state)
 {
 	union perf_event *event;
+	struct perf_mmap *md;
 	int i, ret;
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
-		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+		md = &evlist->mmap[i];
+		if (perf_mmap__read_init(md) < 0)
+			continue;
+
+		while ((event = perf_mmap__read_event(md)) != NULL) {
 			ret = process_event(machine, evlist, event, state);
-			perf_evlist__mmap_consume(evlist, i);
+			perf_mmap__consume(md);
 			if (ret < 0)
 				return ret;
 		}
+		perf_mmap__read_done(md);
 	}
 	return 0;
 }
@@ -482,6 +488,34 @@ static void fs_something(void)
 	}
 }
 
+static const char *do_determine_event(bool excl_kernel)
+{
+	const char *event = excl_kernel ? "cycles:u" : "cycles";
+
+#ifdef __s390x__
+	char cpuid[128], model[16], model_c[16], cpum_cf_v[16];
+	unsigned int family;
+	int ret, cpum_cf_a;
+
+	if (get_cpuid(cpuid, sizeof(cpuid)))
+		goto out_clocks;
+	ret = sscanf(cpuid, "%*[^,],%u,%[^,],%[^,],%[^,],%x", &family, model_c,
+		     model, cpum_cf_v, &cpum_cf_a);
+	if (ret != 5)		 /* Not available */
+		goto out_clocks;
+	if (excl_kernel && (cpum_cf_a & 4))
+		return event;
+	if (!excl_kernel && (cpum_cf_a & 2))
+		return event;
+
+	/* Fall through: missing authorization */
+out_clocks:
+	event = excl_kernel ? "cpu-clock:u" : "cpu-clock";
+
+#endif
+	return event;
+}
+
 static void do_something(void)
 {
 	fs_something();
@@ -592,10 +626,7 @@ static int do_test_code_reading(bool try_kcore)
 
 		perf_evlist__set_maps(evlist, cpus, threads);
 
-		if (excl_kernel)
-			str = "cycles:u";
-		else
-			str = "cycles";
+		str = do_determine_event(excl_kernel);
 		pr_debug("Parsing event '%s'\n", str);
 		ret = parse_events(evlist, str, NULL);
 		if (ret < 0) {
diff --git a/tools/perf/tests/dwarf-unwind.c b/tools/perf/tests/dwarf-unwind.c
index 260418969120..2f008067d989 100644
--- a/tools/perf/tests/dwarf-unwind.c
+++ b/tools/perf/tests/dwarf-unwind.c
@@ -37,6 +37,19 @@ static int init_live_machine(struct machine *machine)
 						  mmap_handler, machine, true, 500);
 }
 
+/*
+ * We need to keep these functions global, despite the
+ * fact that they are used only locally in this object,
+ * in order to keep them around even if the binary is
+ * stripped. If they are gone, the unwind check for
+ * symbol fails.
+ */
+int test_dwarf_unwind__thread(struct thread *thread);
+int test_dwarf_unwind__compare(void *p1, void *p2);
+int test_dwarf_unwind__krava_3(struct thread *thread);
+int test_dwarf_unwind__krava_2(struct thread *thread);
+int test_dwarf_unwind__krava_1(struct thread *thread);
+
 #define MAX_STACK 8
 
 static int unwind_entry(struct unwind_entry *entry, void *arg)
@@ -45,12 +58,12 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	char *symbol = entry->sym ? entry->sym->name : NULL;
 	static const char *funcs[MAX_STACK] = {
 		"test__arch_unwind_sample",
-		"unwind_thread",
-		"compare",
+		"test_dwarf_unwind__thread",
+		"test_dwarf_unwind__compare",
 		"bsearch",
-		"krava_3",
-		"krava_2",
-		"krava_1",
+		"test_dwarf_unwind__krava_3",
+		"test_dwarf_unwind__krava_2",
+		"test_dwarf_unwind__krava_1",
 		"test__dwarf_unwind"
 	};
 	/*
@@ -77,7 +90,7 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	return strcmp((const char *) symbol, funcs[idx]);
 }
 
-static noinline int unwind_thread(struct thread *thread)
+noinline int test_dwarf_unwind__thread(struct thread *thread)
 {
 	struct perf_sample sample;
 	unsigned long cnt = 0;
@@ -108,7 +121,7 @@ static noinline int unwind_thread(struct thread *thread)
 
 static int global_unwind_retval = -INT_MAX;
 
-static noinline int compare(void *p1, void *p2)
+noinline int test_dwarf_unwind__compare(void *p1, void *p2)
 {
 	/* Any possible value should be 'thread' */
 	struct thread *thread = *(struct thread **)p1;
@@ -117,17 +130,17 @@ static noinline int compare(void *p1, void *p2)
 		/* Call unwinder twice for both callchain orders. */
 		callchain_param.order = ORDER_CALLER;
 
-		global_unwind_retval = unwind_thread(thread);
+		global_unwind_retval = test_dwarf_unwind__thread(thread);
 		if (!global_unwind_retval) {
 			callchain_param.order = ORDER_CALLEE;
-			global_unwind_retval = unwind_thread(thread);
+			global_unwind_retval = test_dwarf_unwind__thread(thread);
 		}
 	}
 
 	return p1 - p2;
 }
 
-static noinline int krava_3(struct thread *thread)
+noinline int test_dwarf_unwind__krava_3(struct thread *thread)
 {
 	struct thread *array[2] = {thread, thread};
 	void *fp = &bsearch;
@@ -141,18 +154,19 @@ static noinline int krava_3(struct thread *thread)
 			size_t, int (*)(void *, void *));
 
 	_bsearch = fp;
-	_bsearch(array, &thread, 2, sizeof(struct thread **), compare);
+	_bsearch(array, &thread, 2, sizeof(struct thread **),
+		 test_dwarf_unwind__compare);
 	return global_unwind_retval;
 }
 
-static noinline int krava_2(struct thread *thread)
+noinline int test_dwarf_unwind__krava_2(struct thread *thread)
 {
-	return krava_3(thread);
+	return test_dwarf_unwind__krava_3(thread);
 }
 
-static noinline int krava_1(struct thread *thread)
+noinline int test_dwarf_unwind__krava_1(struct thread *thread)
 {
-	return krava_2(thread);
+	return test_dwarf_unwind__krava_2(thread);
 }
 
 int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unused)
@@ -189,7 +203,7 @@ int test__dwarf_unwind(struct test *test __maybe_unused, int subtest __maybe_unu
 		goto out;
 	}
 
-	err = krava_1(thread);
+	err = test_dwarf_unwind__krava_1(thread);
 	thread__put(thread);
 
  out:
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index c46530918938..17c46f3e6f1e 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -27,18 +27,23 @@
 static int find_comm(struct perf_evlist *evlist, const char *comm)
 {
 	union perf_event *event;
+	struct perf_mmap *md;
 	int i, found;
 
 	found = 0;
 	for (i = 0; i < evlist->nr_mmaps; i++) {
-		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+		md = &evlist->mmap[i];
+		if (perf_mmap__read_init(md) < 0)
+			continue;
+		while ((event = perf_mmap__read_event(md)) != NULL) {
 			if (event->header.type == PERF_RECORD_COMM &&
 			    (pid_t)event->comm.pid == getpid() &&
 			    (pid_t)event->comm.tid == getpid() &&
 			    strcmp(event->comm.comm, comm) == 0)
 				found += 1;
-			perf_evlist__mmap_consume(evlist, i);
+			perf_mmap__consume(md);
 		}
+		perf_mmap__read_done(md);
 	}
 	return found;
 }
diff --git a/tools/perf/tests/mem.c b/tools/perf/tests/mem.c
index 21952e1e6e6d..0f82ee9fd3f7 100644
--- a/tools/perf/tests/mem.c
+++ b/tools/perf/tests/mem.c
@@ -16,7 +16,7 @@ static int check(union perf_mem_data_src data_src,
 
 	n = perf_mem__snp_scnprintf(out, sizeof out, &mi);
 	n += perf_mem__lvl_scnprintf(out + n, sizeof out - n, &mi);
-	snprintf(failure, sizeof failure, "unexpected %s", out);
+	scnprintf(failure, sizeof failure, "unexpected %s", out);
 	TEST_ASSERT_VAL(failure, !strcmp(string, out));
 	return 0;
 }
diff --git a/tools/perf/tests/mem2node.c b/tools/perf/tests/mem2node.c
new file mode 100644
index 000000000000..0c3c87f86e03
--- /dev/null
+++ b/tools/perf/tests/mem2node.c
@@ -0,0 +1,75 @@
+#include <linux/compiler.h>
+#include <linux/bitmap.h>
+#include "cpumap.h"
+#include "mem2node.h"
+#include "tests.h"
+
+static struct node {
+	int		 node;
+	const char 	*map;
+} test_nodes[] = {
+	{ .node = 0, .map = "0"     },
+	{ .node = 1, .map = "1-2"   },
+	{ .node = 3, .map = "5-7,9" },
+};
+
+#define T TEST_ASSERT_VAL
+
+static unsigned long *get_bitmap(const char *str, int nbits)
+{
+	struct cpu_map *map = cpu_map__new(str);
+	unsigned long *bm = NULL;
+	int i;
+
+	bm = bitmap_alloc(nbits);
+
+	if (map && bm) {
+		bitmap_zero(bm, nbits);
+
+		for (i = 0; i < map->nr; i++) {
+			set_bit(map->map[i], bm);
+		}
+	}
+
+	if (map)
+		cpu_map__put(map);
+	else
+		free(bm);
+
+	return bm && map ? bm : NULL;
+}
+
+int test__mem2node(struct test *t __maybe_unused, int subtest __maybe_unused)
+{
+	struct mem2node map;
+	struct memory_node nodes[3];
+	struct perf_env env = {
+		.memory_nodes    = (struct memory_node *) &nodes[0],
+		.nr_memory_nodes = ARRAY_SIZE(nodes),
+		.memory_bsize    = 0x100,
+	};
+	unsigned int i;
+
+	for (i = 0; i < ARRAY_SIZE(nodes); i++) {
+		nodes[i].node = test_nodes[i].node;
+		nodes[i].size = 10;
+
+		T("failed: alloc bitmap",
+		  (nodes[i].set = get_bitmap(test_nodes[i].map, 10)));
+	}
+
+	T("failed: mem2node__init", !mem2node__init(&map, &env));
+	T("failed: mem2node__node",  0 == mem2node__node(&map,   0x50));
+	T("failed: mem2node__node",  1 == mem2node__node(&map,  0x100));
+	T("failed: mem2node__node",  1 == mem2node__node(&map,  0x250));
+	T("failed: mem2node__node",  3 == mem2node__node(&map,  0x500));
+	T("failed: mem2node__node",  3 == mem2node__node(&map,  0x650));
+	T("failed: mem2node__node", -1 == mem2node__node(&map,  0x450));
+	T("failed: mem2node__node", -1 == mem2node__node(&map, 0x1050));
+
+	for (i = 0; i < ARRAY_SIZE(nodes); i++)
+		free(nodes[i].set);
+
+	mem2node__exit(&map);
+	return 0;
+}
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index c0e971da965c..bb8e6bcb0d96 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -38,6 +38,7 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 		     expected_nr_events[nsyscalls], i, j;
 	struct perf_evsel *evsels[nsyscalls], *evsel;
 	char sbuf[STRERR_BUFSIZE];
+	struct perf_mmap *md;
 
 	threads = thread_map__new(-1, getpid(), UINT_MAX);
 	if (threads == NULL) {
@@ -106,7 +107,11 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 			++foo;
 		}
 
-	while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
+	md = &evlist->mmap[0];
+	if (perf_mmap__read_init(md) < 0)
+		goto out_init;
+
+	while ((event = perf_mmap__read_event(md)) != NULL) {
 		struct perf_sample sample;
 
 		if (event->header.type != PERF_RECORD_SAMPLE) {
@@ -129,9 +134,11 @@ int test__basic_mmap(struct test *test __maybe_unused, int subtest __maybe_unuse
 			goto out_delete_evlist;
 		}
 		nr_events[evsel->idx]++;
-		perf_evlist__mmap_consume(evlist, 0);
+		perf_mmap__consume(md);
 	}
+	perf_mmap__read_done(md);
 
+out_init:
 	err = 0;
 	evlist__for_each_entry(evlist, evsel) {
 		if (nr_events[evsel->idx] != expected_nr_events[evsel->idx]) {
diff --git a/tools/perf/tests/openat-syscall-tp-fields.c b/tools/perf/tests/openat-syscall-tp-fields.c
index 43519267b93b..344dc3ac2469 100644
--- a/tools/perf/tests/openat-syscall-tp-fields.c
+++ b/tools/perf/tests/openat-syscall-tp-fields.c
@@ -86,8 +86,13 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
 
 		for (i = 0; i < evlist->nr_mmaps; i++) {
 			union perf_event *event;
+			struct perf_mmap *md;
 
-			while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+			md = &evlist->mmap[i];
+			if (perf_mmap__read_init(md) < 0)
+				continue;
+
+			while ((event = perf_mmap__read_event(md)) != NULL) {
 				const u32 type = event->header.type;
 				int tp_flags;
 				struct perf_sample sample;
@@ -95,7 +100,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
 				++nr_events;
 
 				if (type != PERF_RECORD_SAMPLE) {
-					perf_evlist__mmap_consume(evlist, i);
+					perf_mmap__consume(md);
 					continue;
 				}
 
@@ -115,6 +120,7 @@ int test__syscall_openat_tp_fields(struct test *test __maybe_unused, int subtest
 
 				goto out_ok;
 			}
+			perf_mmap__read_done(md);
 		}
 
 		if (nr_events == before)
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index 0afafab85238..34394cc05077 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -164,8 +164,13 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 
 		for (i = 0; i < evlist->nr_mmaps; i++) {
 			union perf_event *event;
+			struct perf_mmap *md;
 
-			while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+			md = &evlist->mmap[i];
+			if (perf_mmap__read_init(md) < 0)
+				continue;
+
+			while ((event = perf_mmap__read_event(md)) != NULL) {
 				const u32 type = event->header.type;
 				const char *name = perf_event__name(type);
 
@@ -266,8 +271,9 @@ int test__PERF_RECORD(struct test *test __maybe_unused, int subtest __maybe_unus
 					++errs;
 				}
 
-				perf_evlist__mmap_consume(evlist, i);
+				perf_mmap__consume(md);
 			}
+			perf_mmap__read_done(md);
 		}
 
 		/*
diff --git a/tools/perf/tests/pmu.c b/tools/perf/tests/pmu.c
index 9abca267afa9..7bedf8608fdd 100644
--- a/tools/perf/tests/pmu.c
+++ b/tools/perf/tests/pmu.c
@@ -98,7 +98,7 @@ static char *test_format_dir_get(void)
 		struct test_format *format = &test_formats[i];
 		FILE *file;
 
-		snprintf(name, PATH_MAX, "%s/%s", dir, format->name);
+		scnprintf(name, PATH_MAX, "%s/%s", dir, format->name);
 
 		file = fopen(name, "w");
 		if (!file)
diff --git a/tools/perf/tests/shell/lib/probe_vfs_getname.sh b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
index 30a950c9d407..1c16e56cd93e 100644
--- a/tools/perf/tests/shell/lib/probe_vfs_getname.sh
+++ b/tools/perf/tests/shell/lib/probe_vfs_getname.sh
@@ -5,7 +5,7 @@ had_vfs_getname=$?
 
 cleanup_probe_vfs_getname() {
 	if [ $had_vfs_getname -eq 1 ] ; then
-		perf probe -q -d probe:vfs_getname
+		perf probe -q -d probe:vfs_getname*
 	fi
 }
 
diff --git a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
index c446c894b297..1ecc1f0ff84a 100755
--- a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -15,30 +15,28 @@ nm -g $libc 2>/dev/null | fgrep -q inet_pton || exit 254
 
 trace_libc_inet_pton_backtrace() {
 	idx=0
-	expected[0]="PING.*bytes"
-	expected[1]="64 bytes from ::1.*"
-	expected[2]=".*ping statistics.*"
-	expected[3]=".*packets transmitted.*"
-	expected[4]="rtt min.*"
-	expected[5]="[0-9]+\.[0-9]+[[:space:]]+probe_libc:inet_pton:\([[:xdigit:]]+\)"
-	expected[6]=".*inet_pton[[:space:]]\($libc\)$"
+	expected[0]="ping[][0-9 \.:]+probe_libc:inet_pton: \([[:xdigit:]]+\)"
+	expected[1]=".*inet_pton[[:space:]]\($libc\)$"
 	case "$(uname -m)" in
 	s390x)
 		eventattr='call-graph=dwarf'
-		expected[7]="gaih_inet[[:space:]]\(inlined\)$"
-		expected[8]="__GI_getaddrinfo[[:space:]]\(inlined\)$"
-		expected[9]="main[[:space:]]\(.*/bin/ping.*\)$"
-		expected[10]="__libc_start_main[[:space:]]\($libc\)$"
-		expected[11]="_start[[:space:]]\(.*/bin/ping.*\)$"
+		expected[2]="gaih_inet.*[[:space:]]\($libc|inlined\)$"
+		expected[3]="__GI_getaddrinfo[[:space:]]\($libc|inlined\)$"
+		expected[4]="main[[:space:]]\(.*/bin/ping.*\)$"
+		expected[5]="__libc_start_main[[:space:]]\($libc\)$"
+		expected[6]="_start[[:space:]]\(.*/bin/ping.*\)$"
 		;;
 	*)
 		eventattr='max-stack=3'
-		expected[7]="getaddrinfo[[:space:]]\($libc\)$"
-		expected[8]=".*\(.*/bin/ping.*\)$"
+		expected[2]="getaddrinfo[[:space:]]\($libc\)$"
+		expected[3]=".*\(.*/bin/ping.*\)$"
 		;;
 	esac
 
-	perf trace --no-syscalls -e probe_libc:inet_pton/$eventattr/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do
+	file=`mktemp -u /tmp/perf.data.XXX`
+
+	perf record -e probe_libc:inet_pton/$eventattr/ -o $file ping -6 -c 1 ::1 > /dev/null 2>&1
+	perf script -i $file | while read line ; do
 		echo $line
 		echo "$line" | egrep -q "${expected[$idx]}"
 		if [ $? -ne 0 ] ; then
@@ -48,6 +46,11 @@ trace_libc_inet_pton_backtrace() {
 		let idx+=1
 		[ -z "${expected[$idx]}" ] && break
 	done
+
+	# If any statements are executed from this point onwards,
+	# the exit code of the last among these will be reflected
+	# in err below. If the exit code is 0, the test will pass
+	# even if the perf script output does not match.
 }
 
 # Check for IPv6 interface existence
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index f6c72f915d48..f9490b237893 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -39,6 +39,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 	};
 	struct cpu_map *cpus;
 	struct thread_map *threads;
+	struct perf_mmap *md;
 
 	attr.sample_freq = 500;
 
@@ -93,7 +94,11 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 
 	perf_evlist__disable(evlist);
 
-	while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
+	md = &evlist->mmap[0];
+	if (perf_mmap__read_init(md) < 0)
+		goto out_init;
+
+	while ((event = perf_mmap__read_event(md)) != NULL) {
 		struct perf_sample sample;
 
 		if (event->header.type != PERF_RECORD_SAMPLE)
@@ -108,9 +113,11 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
 		total_periods += sample.period;
 		nr_samples++;
 next_event:
-		perf_evlist__mmap_consume(evlist, 0);
+		perf_mmap__consume(md);
 	}
+	perf_mmap__read_done(md);
 
+out_init:
 	if ((u64) nr_samples == total_periods) {
 		pr_debug("All (%d) samples have period value of 1!\n",
 			 nr_samples);
diff --git a/tools/perf/tests/switch-tracking.c b/tools/perf/tests/switch-tracking.c
index 33e00295a972..9b5be51e5e7b 100644
--- a/tools/perf/tests/switch-tracking.c
+++ b/tools/perf/tests/switch-tracking.c
@@ -258,16 +258,22 @@ static int process_events(struct perf_evlist *evlist,
 	unsigned pos, cnt = 0;
 	LIST_HEAD(events);
 	struct event_node *events_array, *node;
+	struct perf_mmap *md;
 	int i, ret;
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
-		while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
+		md = &evlist->mmap[i];
+		if (perf_mmap__read_init(md) < 0)
+			continue;
+
+		while ((event = perf_mmap__read_event(md)) != NULL) {
 			cnt += 1;
 			ret = add_event(evlist, &events, event);
-			perf_evlist__mmap_consume(evlist, i);
+			 perf_mmap__consume(md);
 			if (ret < 0)
 				goto out_free_nodes;
 		}
+		perf_mmap__read_done(md);
 	}
 
 	events_array = calloc(cnt, sizeof(struct event_node));
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 01b62b81751b..e92fa6029ac7 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -47,6 +47,7 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 	char sbuf[STRERR_BUFSIZE];
 	struct cpu_map *cpus;
 	struct thread_map *threads;
+	struct perf_mmap *md;
 
 	signal(SIGCHLD, sig_handler);
 
@@ -110,13 +111,19 @@ int test__task_exit(struct test *test __maybe_unused, int subtest __maybe_unused
 	perf_evlist__start_workload(evlist);
 
 retry:
-	while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
+	md = &evlist->mmap[0];
+	if (perf_mmap__read_init(md) < 0)
+		goto out_init;
+
+	while ((event = perf_mmap__read_event(md)) != NULL) {
 		if (event->header.type == PERF_RECORD_EXIT)
 			nr_exit++;
 
-		perf_evlist__mmap_consume(evlist, 0);
+		perf_mmap__consume(md);
 	}
+	perf_mmap__read_done(md);
 
+out_init:
 	if (!exited || !nr_exit) {
 		perf_evlist__poll(evlist, -1);
 		goto retry;
diff --git a/tools/perf/tests/tests.h b/tools/perf/tests/tests.h
index 2862b80bc288..a9760e790563 100644
--- a/tools/perf/tests/tests.h
+++ b/tools/perf/tests/tests.h
@@ -58,6 +58,7 @@ int test__hists_link(struct test *test, int subtest);
 int test__python_use(struct test *test, int subtest);
 int test__bp_signal(struct test *test, int subtest);
 int test__bp_signal_overflow(struct test *test, int subtest);
+int test__bp_accounting(struct test *test, int subtest);
 int test__task_exit(struct test *test, int subtest);
 int test__mem(struct test *test, int subtest);
 int test__sw_clock_freq(struct test *test, int subtest);
@@ -102,6 +103,7 @@ int test__clang(struct test *test, int subtest);
 const char *test__clang_subtest_get_desc(int subtest);
 int test__clang_subtest_get_nr(void);
 int test__unit_number__scnprint(struct test *test, int subtest);
+int test__mem2node(struct test *t, int subtest);
 
 bool test__bp_signal_is_supported(void);
 
diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
index f6789fb029d6..1e5adb65632a 100644
--- a/tools/perf/tests/vmlinux-kallsyms.c
+++ b/tools/perf/tests/vmlinux-kallsyms.c
@@ -56,7 +56,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
 	 * be compacted against the list of modules found in the "vmlinux"
 	 * code and with the one got from /proc/modules from the "kallsyms" code.
 	 */
-	if (__machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type, true) <= 0) {
+	if (machine__load_kallsyms(&kallsyms, "/proc/kallsyms", type) <= 0) {
 		pr_debug("dso__load_kallsyms ");
 		goto out;
 	}
@@ -125,7 +125,7 @@ int test__vmlinux_matches_kallsyms(struct test *test __maybe_unused, int subtest
 
 		if (pair && UM(pair->start) == mem_start) {
 next_pair:
-			if (strcmp(sym->name, pair->name) == 0) {
+			if (arch__compare_symbol_names(sym->name, pair->name) == 0) {
 				/*
 				 * kallsyms don't have the symbol end, so we
 				 * set that by using the next symbol start - 1,
diff --git a/tools/perf/ui/browser.c b/tools/perf/ui/browser.c
index 63399af3049f..9f6ce29b83b4 100644
--- a/tools/perf/ui/browser.c
+++ b/tools/perf/ui/browser.c
@@ -56,12 +56,17 @@ void ui_browser__write_nstring(struct ui_browser *browser __maybe_unused, const
 	slsmg_write_nstring(msg, width);
 }
 
+void ui_browser__vprintf(struct ui_browser *browser __maybe_unused, const char *fmt, va_list args)
+{
+	slsmg_vprintf(fmt, args);
+}
+
 void ui_browser__printf(struct ui_browser *browser __maybe_unused, const char *fmt, ...)
 {
 	va_list args;
 
 	va_start(args, fmt);
-	slsmg_vprintf(fmt, args);
+	ui_browser__vprintf(browser, fmt, args);
 	va_end(args);
 }
 
@@ -779,6 +784,4 @@ void ui_browser__init(void)
 		struct ui_browser_colorset *c = &ui_browser__colorsets[i++];
 		sltt_set_color(c->colorset, c->name, c->fg, c->bg);
 	}
-
-	annotate_browser__init();
 }
diff --git a/tools/perf/ui/browser.h b/tools/perf/ui/browser.h
index 03e1734412b9..70057178ee34 100644
--- a/tools/perf/ui/browser.h
+++ b/tools/perf/ui/browser.h
@@ -3,6 +3,7 @@
 #define _PERF_UI_BROWSER_H_ 1
 
 #include <linux/types.h>
+#include <stdarg.h>
 
 #define HE_COLORSET_TOP		50
 #define HE_COLORSET_MEDIUM	51
@@ -40,6 +41,7 @@ void ui_browser__reset_index(struct ui_browser *browser);
 void ui_browser__gotorc(struct ui_browser *browser, int y, int x);
 void ui_browser__write_nstring(struct ui_browser *browser, const char *msg,
 			       unsigned int width);
+void ui_browser__vprintf(struct ui_browser *browser, const char *fmt, va_list args);
 void ui_browser__printf(struct ui_browser *browser, const char *fmt, ...);
 void ui_browser__write_graph(struct ui_browser *browser, int graph);
 void __ui_browser__line_arrow(struct ui_browser *browser, unsigned int column,
@@ -77,5 +79,4 @@ void ui_browser__list_head_seek(struct ui_browser *browser, off_t offset, int wh
 unsigned int ui_browser__list_head_refresh(struct ui_browser *browser);
 
 void ui_browser__init(void);
-void annotate_browser__init(void);
 #endif /* _PERF_UI_BROWSER_H_ */
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index fbf927cf775d..c02fb437ac8e 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -9,7 +9,6 @@
 #include "../../util/sort.h"
 #include "../../util/symbol.h"
 #include "../../util/evsel.h"
-#include "../../util/config.h"
 #include "../../util/evlist.h"
 #include <inttypes.h>
 #include <pthread.h>
@@ -22,28 +21,6 @@ struct disasm_line_samples {
 	struct sym_hist_entry he;
 };
 
-#define IPC_WIDTH 6
-#define CYCLES_WIDTH 6
-
-struct browser_line {
-	u32	idx;
-	int	idx_asm;
-	int	jump_sources;
-};
-
-static struct annotate_browser_opt {
-	bool hide_src_code,
-	     use_offset,
-	     jump_arrows,
-	     show_linenr,
-	     show_nr_jumps,
-	     show_nr_samples,
-	     show_total_period;
-} annotate_browser__opts = {
-	.use_offset	= true,
-	.jump_arrows	= true,
-};
-
 struct arch;
 
 struct annotate_browser {
@@ -51,245 +28,98 @@ struct annotate_browser {
 	struct rb_root		    entries;
 	struct rb_node		   *curr_hot;
 	struct annotation_line	   *selection;
-	struct annotation_line	  **offsets;
 	struct arch		   *arch;
-	int			    nr_events;
-	u64			    start;
-	int			    nr_asm_entries;
-	int			    nr_entries;
-	int			    max_jump_sources;
-	int			    nr_jumps;
 	bool			    searching_backwards;
-	bool			    have_cycles;
-	u8			    addr_width;
-	u8			    jumps_width;
-	u8			    target_width;
-	u8			    min_addr_width;
-	u8			    max_addr_width;
 	char			    search_bf[128];
 };
 
-static inline struct browser_line *browser_line(struct annotation_line *al)
+static inline struct annotation *browser__annotation(struct ui_browser *browser)
 {
-	void *ptr = al;
-
-	ptr = container_of(al, struct disasm_line, al);
-	return ptr - sizeof(struct browser_line);
+	struct map_symbol *ms = browser->priv;
+	return symbol__annotation(ms->sym);
 }
 
-static bool disasm_line__filter(struct ui_browser *browser __maybe_unused,
-				void *entry)
+static bool disasm_line__filter(struct ui_browser *browser, void *entry)
 {
-	if (annotate_browser__opts.hide_src_code) {
-		struct annotation_line *al = list_entry(entry, struct annotation_line, node);
-
-		return al->offset == -1;
-	}
-
-	return false;
+	struct annotation *notes = browser__annotation(browser);
+	struct annotation_line *al = list_entry(entry, struct annotation_line, node);
+	return annotation_line__filter(al, notes);
 }
 
-static int annotate_browser__jumps_percent_color(struct annotate_browser *browser,
-						 int nr, bool current)
+static int ui_browser__jumps_percent_color(struct ui_browser *browser, int nr, bool current)
 {
-	if (current && (!browser->b.use_navkeypressed || browser->b.navkeypressed))
+	struct annotation *notes = browser__annotation(browser);
+
+	if (current && (!browser->use_navkeypressed || browser->navkeypressed))
 		return HE_COLORSET_SELECTED;
-	if (nr == browser->max_jump_sources)
+	if (nr == notes->max_jump_sources)
 		return HE_COLORSET_TOP;
 	if (nr > 1)
 		return HE_COLORSET_MEDIUM;
 	return HE_COLORSET_NORMAL;
 }
 
-static int annotate_browser__set_jumps_percent_color(struct annotate_browser *browser,
-						     int nr, bool current)
+static int ui_browser__set_jumps_percent_color(void *browser, int nr, bool current)
 {
-	 int color = annotate_browser__jumps_percent_color(browser, nr, current);
-	 return ui_browser__set_color(&browser->b, color);
+	 int color = ui_browser__jumps_percent_color(browser, nr, current);
+	 return ui_browser__set_color(browser, color);
 }
 
-static int annotate_browser__pcnt_width(struct annotate_browser *ab)
+static int annotate_browser__set_color(void *browser, int color)
 {
-	return (annotate_browser__opts.show_total_period ? 12 : 7) * ab->nr_events;
+	return ui_browser__set_color(browser, color);
 }
 
-static int annotate_browser__cycles_width(struct annotate_browser *ab)
+static void annotate_browser__write_graph(void *browser, int graph)
 {
-	return ab->have_cycles ? IPC_WIDTH + CYCLES_WIDTH : 0;
+	ui_browser__write_graph(browser, graph);
 }
 
-static void disasm_line__write(struct disasm_line *dl, struct ui_browser *browser,
-			       char *bf, size_t size)
+static void annotate_browser__set_percent_color(void *browser, double percent, bool current)
 {
-	if (dl->ins.ops && dl->ins.ops->scnprintf) {
-		if (ins__is_jump(&dl->ins)) {
-			bool fwd = dl->ops.target.offset > dl->al.offset;
-
-			ui_browser__write_graph(browser, fwd ? SLSMG_DARROW_CHAR :
-							    SLSMG_UARROW_CHAR);
-			SLsmg_write_char(' ');
-		} else if (ins__is_call(&dl->ins)) {
-			ui_browser__write_graph(browser, SLSMG_RARROW_CHAR);
-			SLsmg_write_char(' ');
-		} else if (ins__is_ret(&dl->ins)) {
-			ui_browser__write_graph(browser, SLSMG_LARROW_CHAR);
-			SLsmg_write_char(' ');
-		} else {
-			ui_browser__write_nstring(browser, " ", 2);
-		}
-	} else {
-		ui_browser__write_nstring(browser, " ", 2);
-	}
+	ui_browser__set_percent_color(browser, percent, current);
+}
 
-	disasm_line__scnprintf(dl, bf, size, !annotate_browser__opts.use_offset);
+static void annotate_browser__printf(void *browser, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	ui_browser__vprintf(browser, fmt, args);
+	va_end(args);
 }
 
 static void annotate_browser__write(struct ui_browser *browser, void *entry, int row)
 {
 	struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
+	struct annotation *notes = browser__annotation(browser);
 	struct annotation_line *al = list_entry(entry, struct annotation_line, node);
-	struct browser_line *bl = browser_line(al);
-	bool current_entry = ui_browser__is_current_entry(browser, row);
-	bool change_color = (!annotate_browser__opts.hide_src_code &&
-			     (!current_entry || (browser->use_navkeypressed &&
-					         !browser->navkeypressed)));
-	int width = browser->width, printed;
-	int i, pcnt_width = annotate_browser__pcnt_width(ab),
-	       cycles_width = annotate_browser__cycles_width(ab);
-	double percent_max = 0.0;
-	char bf[256];
-	bool show_title = false;
-
-	for (i = 0; i < ab->nr_events; i++) {
-		if (al->samples[i].percent > percent_max)
-			percent_max = al->samples[i].percent;
-	}
-
-	if ((row == 0) && (al->offset == -1 || percent_max == 0.0)) {
-		if (ab->have_cycles) {
-			if (al->ipc == 0.0 && al->cycles == 0)
-				show_title = true;
-		} else
-			show_title = true;
-	}
-
-	if (al->offset != -1 && percent_max != 0.0) {
-		for (i = 0; i < ab->nr_events; i++) {
-			ui_browser__set_percent_color(browser,
-						al->samples[i].percent,
-						current_entry);
-			if (annotate_browser__opts.show_total_period) {
-				ui_browser__printf(browser, "%11" PRIu64 " ",
-						   al->samples[i].he.period);
-			} else if (annotate_browser__opts.show_nr_samples) {
-				ui_browser__printf(browser, "%6" PRIu64 " ",
-						   al->samples[i].he.nr_samples);
-			} else {
-				ui_browser__printf(browser, "%6.2f ",
-						   al->samples[i].percent);
-			}
-		}
-	} else {
-		ui_browser__set_percent_color(browser, 0, current_entry);
-
-		if (!show_title)
-			ui_browser__write_nstring(browser, " ", pcnt_width);
-		else {
-			ui_browser__printf(browser, "%*s", pcnt_width,
-					   annotate_browser__opts.show_total_period ? "Period" :
-					   annotate_browser__opts.show_nr_samples ? "Samples" : "Percent");
-		}
-	}
-	if (ab->have_cycles) {
-		if (al->ipc)
-			ui_browser__printf(browser, "%*.2f ", IPC_WIDTH - 1, al->ipc);
-		else if (!show_title)
-			ui_browser__write_nstring(browser, " ", IPC_WIDTH);
-		else
-			ui_browser__printf(browser, "%*s ", IPC_WIDTH - 1, "IPC");
-
-		if (al->cycles)
-			ui_browser__printf(browser, "%*" PRIu64 " ",
-					   CYCLES_WIDTH - 1, al->cycles);
-		else if (!show_title)
-			ui_browser__write_nstring(browser, " ", CYCLES_WIDTH);
-		else
-			ui_browser__printf(browser, "%*s ", CYCLES_WIDTH - 1, "Cycle");
-	}
-
-	SLsmg_write_char(' ');
+	struct annotation_write_ops ops = {
+		.first_line		 = row == 0,
+		.current_entry		 = ui_browser__is_current_entry(browser, row),
+		.change_color		 = (!notes->options->hide_src_code &&
+					    (!ops.current_entry ||
+					     (browser->use_navkeypressed &&
+					      !browser->navkeypressed))),
+		.width			 = browser->width,
+		.obj			 = browser,
+		.set_color		 = annotate_browser__set_color,
+		.set_percent_color	 = annotate_browser__set_percent_color,
+		.set_jumps_percent_color = ui_browser__set_jumps_percent_color,
+		.printf			 = annotate_browser__printf,
+		.write_graph		 = annotate_browser__write_graph,
+	};
 
 	/* The scroll bar isn't being used */
 	if (!browser->navkeypressed)
-		width += 1;
-
-	if (!*al->line)
-		ui_browser__write_nstring(browser, " ", width - pcnt_width - cycles_width);
-	else if (al->offset == -1) {
-		if (al->line_nr && annotate_browser__opts.show_linenr)
-			printed = scnprintf(bf, sizeof(bf), "%-*d ",
-					ab->addr_width + 1, al->line_nr);
-		else
-			printed = scnprintf(bf, sizeof(bf), "%*s  ",
-				    ab->addr_width, " ");
-		ui_browser__write_nstring(browser, bf, printed);
-		ui_browser__write_nstring(browser, al->line, width - printed - pcnt_width - cycles_width + 1);
-	} else {
-		u64 addr = al->offset;
-		int color = -1;
-
-		if (!annotate_browser__opts.use_offset)
-			addr += ab->start;
-
-		if (!annotate_browser__opts.use_offset) {
-			printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr);
-		} else {
-			if (bl->jump_sources) {
-				if (annotate_browser__opts.show_nr_jumps) {
-					int prev;
-					printed = scnprintf(bf, sizeof(bf), "%*d ",
-							    ab->jumps_width,
-							    bl->jump_sources);
-					prev = annotate_browser__set_jumps_percent_color(ab, bl->jump_sources,
-											 current_entry);
-					ui_browser__write_nstring(browser, bf, printed);
-					ui_browser__set_color(browser, prev);
-				}
-
-				printed = scnprintf(bf, sizeof(bf), "%*" PRIx64 ": ",
-						    ab->target_width, addr);
-			} else {
-				printed = scnprintf(bf, sizeof(bf), "%*s  ",
-						    ab->addr_width, " ");
-			}
-		}
-
-		if (change_color)
-			color = ui_browser__set_color(browser, HE_COLORSET_ADDR);
-		ui_browser__write_nstring(browser, bf, printed);
-		if (change_color)
-			ui_browser__set_color(browser, color);
+		ops.width += 1;
 
-		disasm_line__write(disasm_line(al), browser, bf, sizeof(bf));
+	annotation_line__write(al, notes, &ops);
 
-		ui_browser__write_nstring(browser, bf, width - pcnt_width - cycles_width - 3 - printed);
-	}
-
-	if (current_entry)
+	if (ops.current_entry)
 		ab->selection = al;
 }
 
-static bool disasm_line__is_valid_jump(struct disasm_line *dl, struct symbol *sym)
-{
-	if (!dl || !dl->ins.ops || !ins__is_jump(&dl->ins)
-	    || !disasm_line__has_offset(dl)
-	    || dl->ops.target.offset < 0
-	    || dl->ops.target.offset >= (s64)symbol__size(sym))
-		return false;
-
-	return true;
-}
-
 static bool is_fused(struct annotate_browser *ab, struct disasm_line *cursor)
 {
 	struct disasm_line *pos = list_prev_entry(cursor, al.node);
@@ -314,17 +144,18 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 	struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
 	struct disasm_line *cursor = disasm_line(ab->selection);
 	struct annotation_line *target;
-	struct browser_line *btarget, *bcursor;
 	unsigned int from, to;
 	struct map_symbol *ms = ab->b.priv;
 	struct symbol *sym = ms->sym;
-	u8 pcnt_width = annotate_browser__pcnt_width(ab);
+	struct annotation *notes = symbol__annotation(sym);
+	u8 pcnt_width = annotation__pcnt_width(notes);
+	int width;
 
 	/* PLT symbols contain external offsets */
 	if (strstr(sym->name, "@plt"))
 		return;
 
-	if (!disasm_line__is_valid_jump(cursor, sym))
+	if (!disasm_line__is_valid_local_jump(cursor, sym))
 		return;
 
 	/*
@@ -347,31 +178,31 @@ 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 = ab->offsets[cursor->ops.target.offset];
+	target = notes->offsets[cursor->ops.target.offset];
 	if (target == NULL) {
-		ui_helpline__printf("WARN: jump target inconsistency, press 'o', ab->offsets[%#x] = NULL\n",
+		ui_helpline__printf("WARN: jump target inconsistency, press 'o', notes->offsets[%#x] = NULL\n",
 				    cursor->ops.target.offset);
 		return;
 	}
 
-	bcursor = browser_line(&cursor->al);
-	btarget = browser_line(target);
-
-	if (annotate_browser__opts.hide_src_code) {
-		from = bcursor->idx_asm;
-		to = btarget->idx_asm;
+	if (notes->options->hide_src_code) {
+		from = cursor->al.idx_asm;
+		to = target->idx_asm;
 	} else {
-		from = (u64)bcursor->idx;
-		to = (u64)btarget->idx;
+		from = (u64)cursor->al.idx;
+		to = (u64)target->idx;
 	}
 
+	width = annotation__cycles_width(notes);
+
 	ui_browser__set_color(browser, HE_COLORSET_JUMP_ARROWS);
-	__ui_browser__line_arrow(browser, pcnt_width + 2 + ab->addr_width,
+	__ui_browser__line_arrow(browser,
+				 pcnt_width + 2 + notes->widths.addr + width,
 				 from, to);
 
 	if (is_fused(ab, cursor)) {
 		ui_browser__mark_fused(browser,
-				       pcnt_width + 3 + ab->addr_width,
+				       pcnt_width + 3 + notes->widths.addr + width,
 				       from - 1,
 				       to > from ? true : false);
 	}
@@ -379,11 +210,11 @@ static void annotate_browser__draw_current_jump(struct ui_browser *browser)
 
 static unsigned int annotate_browser__refresh(struct ui_browser *browser)
 {
-	struct annotate_browser *ab = container_of(browser, struct annotate_browser, b);
+	struct annotation *notes = browser__annotation(browser);
 	int ret = ui_browser__list_head_refresh(browser);
-	int pcnt_width = annotate_browser__pcnt_width(ab);
+	int pcnt_width = annotation__pcnt_width(notes);
 
-	if (annotate_browser__opts.jump_arrows)
+	if (notes->options->jump_arrows)
 		annotate_browser__draw_current_jump(browser);
 
 	ui_browser__set_color(browser, HE_COLORSET_NORMAL);
@@ -425,6 +256,7 @@ static void disasm_rb_tree__insert(struct rb_root *root, struct annotation_line
 static void annotate_browser__set_top(struct annotate_browser *browser,
 				      struct annotation_line *pos, u32 idx)
 {
+	struct annotation *notes = browser__annotation(&browser->b);
 	unsigned back;
 
 	ui_browser__refresh_dimensions(&browser->b);
@@ -434,7 +266,7 @@ static void annotate_browser__set_top(struct annotate_browser *browser,
 	while (browser->b.top_idx != 0 && back != 0) {
 		pos = list_entry(pos->node.prev, struct annotation_line, node);
 
-		if (disasm_line__filter(&browser->b, &pos->node))
+		if (annotation_line__filter(pos, notes))
 			continue;
 
 		--browser->b.top_idx;
@@ -448,16 +280,12 @@ static void annotate_browser__set_top(struct annotate_browser *browser,
 static void annotate_browser__set_rb_top(struct annotate_browser *browser,
 					 struct rb_node *nd)
 {
-	struct browser_line *bpos;
-	struct annotation_line *pos;
-	u32 idx;
-
-	pos = rb_entry(nd, struct annotation_line, rb_node);
-	bpos = browser_line(pos);
+	struct annotation *notes = browser__annotation(&browser->b);
+	struct annotation_line * pos = rb_entry(nd, struct annotation_line, rb_node);
+	u32 idx = pos->idx;
 
-	idx = bpos->idx;
-	if (annotate_browser__opts.hide_src_code)
-		idx = bpos->idx_asm;
+	if (notes->options->hide_src_code)
+		idx = pos->idx_asm;
 	annotate_browser__set_top(browser, pos, idx);
 	browser->curr_hot = nd;
 }
@@ -505,47 +333,47 @@ static void annotate_browser__calc_percent(struct annotate_browser *browser,
 
 static bool annotate_browser__toggle_source(struct annotate_browser *browser)
 {
+	struct annotation *notes = browser__annotation(&browser->b);
 	struct annotation_line *al;
-	struct browser_line *bl;
 	off_t offset = browser->b.index - browser->b.top_idx;
 
 	browser->b.seek(&browser->b, offset, SEEK_CUR);
 	al = list_entry(browser->b.top, struct annotation_line, node);
-	bl = browser_line(al);
 
-	if (annotate_browser__opts.hide_src_code) {
-		if (bl->idx_asm < offset)
-			offset = bl->idx;
+	if (notes->options->hide_src_code) {
+		if (al->idx_asm < offset)
+			offset = al->idx;
 
-		browser->b.nr_entries = browser->nr_entries;
-		annotate_browser__opts.hide_src_code = false;
+		browser->b.nr_entries = notes->nr_entries;
+		notes->options->hide_src_code = false;
 		browser->b.seek(&browser->b, -offset, SEEK_CUR);
-		browser->b.top_idx = bl->idx - offset;
-		browser->b.index = bl->idx;
+		browser->b.top_idx = al->idx - offset;
+		browser->b.index = al->idx;
 	} else {
-		if (bl->idx_asm < 0) {
+		if (al->idx_asm < 0) {
 			ui_helpline__puts("Only available for assembly lines.");
 			browser->b.seek(&browser->b, -offset, SEEK_CUR);
 			return false;
 		}
 
-		if (bl->idx_asm < offset)
-			offset = bl->idx_asm;
+		if (al->idx_asm < offset)
+			offset = al->idx_asm;
 
-		browser->b.nr_entries = browser->nr_asm_entries;
-		annotate_browser__opts.hide_src_code = true;
+		browser->b.nr_entries = notes->nr_asm_entries;
+		notes->options->hide_src_code = true;
 		browser->b.seek(&browser->b, -offset, SEEK_CUR);
-		browser->b.top_idx = bl->idx_asm - offset;
-		browser->b.index = bl->idx_asm;
+		browser->b.top_idx = al->idx_asm - offset;
+		browser->b.index = al->idx_asm;
 	}
 
 	return true;
 }
 
-static void annotate_browser__init_asm_mode(struct annotate_browser *browser)
+static void ui_browser__init_asm_mode(struct ui_browser *browser)
 {
-	ui_browser__reset_index(&browser->b);
-	browser->b.nr_entries = browser->nr_asm_entries;
+	struct annotation *notes = browser__annotation(browser);
+	ui_browser__reset_index(browser);
+	browser->nr_entries = notes->nr_asm_entries;
 }
 
 #define SYM_TITLE_MAX_SIZE (PATH_MAX + 64)
@@ -556,6 +384,15 @@ static int sym_title(struct symbol *sym, struct map *map, char *title,
 	return snprintf(title, sz, "%s  %s", sym->name, map->dso->long_name);
 }
 
+/*
+ * This can be called from external jumps, i.e. jumps from one functon
+ * to another, like from the kernel's entry_SYSCALL_64 function to the
+ * swapgs_restore_regs_and_return_to_usermode() function.
+ *
+ * So all we check here is that dl->ops.target.sym is set, if it is, just
+ * go to that function and when exiting from its disassembly, come back
+ * to the calling function.
+ */
 static bool annotate_browser__callq(struct annotate_browser *browser,
 				    struct perf_evsel *evsel,
 				    struct hist_browser_timer *hbt)
@@ -563,35 +400,25 @@ static bool annotate_browser__callq(struct annotate_browser *browser,
 	struct map_symbol *ms = browser->b.priv;
 	struct disasm_line *dl = disasm_line(browser->selection);
 	struct annotation *notes;
-	struct addr_map_symbol target = {
-		.map = ms->map,
-		.addr = map__objdump_2mem(ms->map, dl->ops.target.addr),
-	};
 	char title[SYM_TITLE_MAX_SIZE];
 
-	if (!ins__is_call(&dl->ins))
-		return false;
-
-	if (map_groups__find_ams(&target) ||
-	    map__rip_2objdump(target.map, target.map->map_ip(target.map,
-							     target.addr)) !=
-	    dl->ops.target.addr) {
+	if (!dl->ops.target.sym) {
 		ui_helpline__puts("The called function was not found.");
 		return true;
 	}
 
-	notes = symbol__annotation(target.sym);
+	notes = symbol__annotation(dl->ops.target.sym);
 	pthread_mutex_lock(&notes->lock);
 
-	if (notes->src == NULL && symbol__alloc_hist(target.sym) < 0) {
+	if (notes->src == NULL && symbol__alloc_hist(dl->ops.target.sym) < 0) {
 		pthread_mutex_unlock(&notes->lock);
 		ui__warning("Not enough memory for annotating '%s' symbol!\n",
-			    target.sym->name);
+			    dl->ops.target.sym->name);
 		return true;
 	}
 
 	pthread_mutex_unlock(&notes->lock);
-	symbol__tui_annotate(target.sym, target.map, evsel, hbt);
+	symbol__tui_annotate(dl->ops.target.sym, ms->map, evsel, hbt);
 	sym_title(ms->sym, ms->map, title, sizeof(title));
 	ui_browser__show_title(&browser->b, title);
 	return true;
@@ -601,23 +428,23 @@ static
 struct disasm_line *annotate_browser__find_offset(struct annotate_browser *browser,
 					  s64 offset, s64 *idx)
 {
-	struct map_symbol *ms = browser->b.priv;
-	struct symbol *sym = ms->sym;
-	struct annotation *notes = symbol__annotation(sym);
+	struct annotation *notes = browser__annotation(&browser->b);
 	struct disasm_line *pos;
 
 	*idx = 0;
 	list_for_each_entry(pos, &notes->src->source, al.node) {
 		if (pos->al.offset == offset)
 			return pos;
-		if (!disasm_line__filter(&browser->b, &pos->al.node))
+		if (!annotation_line__filter(&pos->al, notes))
 			++*idx;
 	}
 
 	return NULL;
 }
 
-static bool annotate_browser__jump(struct annotate_browser *browser)
+static bool annotate_browser__jump(struct annotate_browser *browser,
+				   struct perf_evsel *evsel,
+				   struct hist_browser_timer *hbt)
 {
 	struct disasm_line *dl = disasm_line(browser->selection);
 	u64 offset;
@@ -626,6 +453,11 @@ static bool annotate_browser__jump(struct annotate_browser *browser)
 	if (!ins__is_jump(&dl->ins))
 		return false;
 
+	if (dl->ops.target.outside) {
+		annotate_browser__callq(browser, evsel, hbt);
+		return true;
+	}
+
 	offset = dl->ops.target.offset;
 	dl = annotate_browser__find_offset(browser, offset, &idx);
 	if (dl == NULL) {
@@ -642,14 +474,12 @@ static
 struct annotation_line *annotate_browser__find_string(struct annotate_browser *browser,
 					  char *s, s64 *idx)
 {
-	struct map_symbol *ms = browser->b.priv;
-	struct symbol *sym = ms->sym;
-	struct annotation *notes = symbol__annotation(sym);
+	struct annotation *notes = browser__annotation(&browser->b);
 	struct annotation_line *al = browser->selection;
 
 	*idx = browser->b.index;
 	list_for_each_entry_continue(al, &notes->src->source, node) {
-		if (disasm_line__filter(&browser->b, &al->node))
+		if (annotation_line__filter(al, notes))
 			continue;
 
 		++*idx;
@@ -681,14 +511,12 @@ static
 struct annotation_line *annotate_browser__find_string_reverse(struct annotate_browser *browser,
 						  char *s, s64 *idx)
 {
-	struct map_symbol *ms = browser->b.priv;
-	struct symbol *sym = ms->sym;
-	struct annotation *notes = symbol__annotation(sym);
+	struct annotation *notes = browser__annotation(&browser->b);
 	struct annotation_line *al = browser->selection;
 
 	*idx = browser->b.index;
 	list_for_each_entry_continue_reverse(al, &notes->src->source, node) {
-		if (disasm_line__filter(&browser->b, &al->node))
+		if (annotation_line__filter(al, notes))
 			continue;
 
 		--*idx;
@@ -764,19 +592,6 @@ bool annotate_browser__continue_search_reverse(struct annotate_browser *browser,
 	return __annotate_browser__search_reverse(browser);
 }
 
-static void annotate_browser__update_addr_width(struct annotate_browser *browser)
-{
-	if (annotate_browser__opts.use_offset)
-		browser->target_width = browser->min_addr_width;
-	else
-		browser->target_width = browser->max_addr_width;
-
-	browser->addr_width = browser->target_width;
-
-	if (annotate_browser__opts.show_nr_jumps)
-		browser->addr_width += browser->jumps_width + 1;
-}
-
 static int annotate_browser__run(struct annotate_browser *browser,
 				 struct perf_evsel *evsel,
 				 struct hist_browser_timer *hbt)
@@ -784,6 +599,7 @@ static int annotate_browser__run(struct annotate_browser *browser,
 	struct rb_node *nd = NULL;
 	struct map_symbol *ms = browser->b.priv;
 	struct symbol *sym = ms->sym;
+	struct annotation *notes = symbol__annotation(ms->sym);
 	const char *help = "Press 'h' for help on key bindings";
 	int delay_secs = hbt ? hbt->refresh : 0;
 	int key;
@@ -858,6 +674,7 @@ static int annotate_browser__run(struct annotate_browser *browser,
 		"t             Circulate percent, total period, samples view\n"
 		"/             Search string\n"
 		"k             Toggle line numbers\n"
+		"P             Print to [symbol_name].annotation file.\n"
 		"r             Run available scripts\n"
 		"?             Search string backwards\n");
 			continue;
@@ -867,8 +684,7 @@ static int annotate_browser__run(struct annotate_browser *browser,
 				continue;
 			}
 		case 'k':
-			annotate_browser__opts.show_linenr =
-				!annotate_browser__opts.show_linenr;
+			notes->options->show_linenr = !notes->options->show_linenr;
 			break;
 		case 'H':
 			nd = browser->curr_hot;
@@ -878,15 +694,15 @@ static int annotate_browser__run(struct annotate_browser *browser,
 				ui_helpline__puts(help);
 			continue;
 		case 'o':
-			annotate_browser__opts.use_offset = !annotate_browser__opts.use_offset;
-			annotate_browser__update_addr_width(browser);
+			notes->options->use_offset = !notes->options->use_offset;
+			annotation__update_column_widths(notes);
 			continue;
 		case 'j':
-			annotate_browser__opts.jump_arrows = !annotate_browser__opts.jump_arrows;
+			notes->options->jump_arrows = !notes->options->jump_arrows;
 			continue;
 		case 'J':
-			annotate_browser__opts.show_nr_jumps = !annotate_browser__opts.show_nr_jumps;
-			annotate_browser__update_addr_width(browser);
+			notes->options->show_nr_jumps = !notes->options->show_nr_jumps;
+			annotation__update_column_widths(notes);
 			continue;
 		case '/':
 			if (annotate_browser__search(browser, delay_secs)) {
@@ -912,7 +728,7 @@ show_help:
 					   browser->b.height,
 					   browser->b.index,
 					   browser->b.top_idx,
-					   browser->nr_asm_entries);
+					   notes->nr_asm_entries);
 		}
 			continue;
 		case K_ENTER:
@@ -928,22 +744,25 @@ show_help:
 				goto show_sup_ins;
 			else if (ins__is_ret(&dl->ins))
 				goto out;
-			else if (!(annotate_browser__jump(browser) ||
+			else if (!(annotate_browser__jump(browser, evsel, hbt) ||
 				     annotate_browser__callq(browser, evsel, hbt))) {
 show_sup_ins:
 				ui_helpline__puts("Actions are only available for function call/return & jump/branch instructions.");
 			}
 			continue;
 		}
+		case 'P':
+			map_symbol__annotation_dump(ms, evsel);
+			continue;
 		case 't':
-			if (annotate_browser__opts.show_total_period) {
-				annotate_browser__opts.show_total_period = false;
-				annotate_browser__opts.show_nr_samples = true;
-			} else if (annotate_browser__opts.show_nr_samples)
-				annotate_browser__opts.show_nr_samples = false;
+			if (notes->options->show_total_period) {
+				notes->options->show_total_period = false;
+				notes->options->show_nr_samples = true;
+			} else if (notes->options->show_nr_samples)
+				notes->options->show_nr_samples = false;
 			else
-				annotate_browser__opts.show_total_period = true;
-			annotate_browser__update_addr_width(browser);
+				notes->options->show_total_period = true;
+			annotation__update_column_widths(notes);
 			continue;
 		case K_LEFT:
 		case K_ESC:
@@ -965,12 +784,6 @@ out:
 int map_symbol__tui_annotate(struct map_symbol *ms, struct perf_evsel *evsel,
 			     struct hist_browser_timer *hbt)
 {
-	/* Set default value for show_total_period and show_nr_samples  */
-	annotate_browser__opts.show_total_period =
-		symbol_conf.show_total_period;
-	annotate_browser__opts.show_nr_samples =
-		symbol_conf.show_nr_samples;
-
 	return symbol__tui_annotate(ms->sym, ms->map, evsel, hbt);
 }
 
@@ -984,129 +797,11 @@ int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
 	return map_symbol__tui_annotate(&he->ms, evsel, hbt);
 }
 
-
-static unsigned count_insn(struct annotate_browser *browser, u64 start, u64 end)
-{
-	unsigned n_insn = 0;
-	u64 offset;
-
-	for (offset = start; offset <= end; offset++) {
-		if (browser->offsets[offset])
-			n_insn++;
-	}
-	return n_insn;
-}
-
-static void count_and_fill(struct annotate_browser *browser, u64 start, u64 end,
-			   struct cyc_hist *ch)
-{
-	unsigned n_insn;
-	u64 offset;
-
-	n_insn = count_insn(browser, start, end);
-	if (n_insn && ch->num && ch->cycles) {
-		float ipc = n_insn / ((double)ch->cycles / (double)ch->num);
-
-		/* Hide data when there are too many overlaps. */
-		if (ch->reset >= 0x7fff || ch->reset >= ch->num / 2)
-			return;
-
-		for (offset = start; offset <= end; offset++) {
-			struct annotation_line *al = browser->offsets[offset];
-
-			if (al)
-				al->ipc = ipc;
-		}
-	}
-}
-
-/*
- * This should probably be in util/annotate.c to share with the tty
- * annotate, but right now we need the per byte offsets arrays,
- * which are only here.
- */
-static void annotate__compute_ipc(struct annotate_browser *browser, size_t size,
-			   struct symbol *sym)
-{
-	u64 offset;
-	struct annotation *notes = symbol__annotation(sym);
-
-	if (!notes->src || !notes->src->cycles_hist)
-		return;
-
-	pthread_mutex_lock(&notes->lock);
-	for (offset = 0; offset < size; ++offset) {
-		struct cyc_hist *ch;
-
-		ch = &notes->src->cycles_hist[offset];
-		if (ch && ch->cycles) {
-			struct annotation_line *al;
-
-			if (ch->have_start)
-				count_and_fill(browser, ch->start, offset, ch);
-			al = browser->offsets[offset];
-			if (al && ch->num_aggr)
-				al->cycles = ch->cycles_aggr / ch->num_aggr;
-			browser->have_cycles = true;
-		}
-	}
-	pthread_mutex_unlock(&notes->lock);
-}
-
-static void annotate_browser__mark_jump_targets(struct annotate_browser *browser,
-						size_t size)
-{
-	u64 offset;
-	struct map_symbol *ms = browser->b.priv;
-	struct symbol *sym = ms->sym;
-
-	/* PLT symbols contain external offsets */
-	if (strstr(sym->name, "@plt"))
-		return;
-
-	for (offset = 0; offset < size; ++offset) {
-		struct annotation_line *al = browser->offsets[offset];
-		struct disasm_line *dl;
-		struct browser_line *blt;
-
-		dl = disasm_line(al);
-
-		if (!disasm_line__is_valid_jump(dl, sym))
-			continue;
-
-		al = browser->offsets[dl->ops.target.offset];
-
-		/*
- 		 * FIXME: Oops, no jump target? Buggy disassembler? Or do we
- 		 * have to adjust to the previous offset?
- 		 */
-		if (al == NULL)
-			continue;
-
-		blt = browser_line(al);
-		if (++blt->jump_sources > browser->max_jump_sources)
-			browser->max_jump_sources = blt->jump_sources;
-
-		++browser->nr_jumps;
-	}
-}
-
-static inline int width_jumps(int n)
-{
-	if (n >= 100)
-		return 5;
-	if (n / 10)
-		return 2;
-	return 1;
-}
-
 int symbol__tui_annotate(struct symbol *sym, struct map *map,
 			 struct perf_evsel *evsel,
 			 struct hist_browser_timer *hbt)
 {
-	struct annotation_line *al;
-	struct annotation *notes;
-	size_t size;
+	struct annotation *notes = symbol__annotation(sym);
 	struct map_symbol ms = {
 		.map = map,
 		.sym = sym,
@@ -1122,26 +817,14 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 		},
 	};
 	int ret = -1, err;
-	int nr_pcnt = 1;
 
 	if (sym == NULL)
 		return -1;
 
-	size = symbol__size(sym);
-
 	if (map->dso->annotate_warned)
 		return -1;
 
-	browser.offsets = zalloc(size * sizeof(struct annotation_line *));
-	if (browser.offsets == NULL) {
-		ui__error("Not enough memory!");
-		return -1;
-	}
-
-	if (perf_evsel__is_group_event(evsel))
-		nr_pcnt = evsel->nr_members;
-
-	err = symbol__annotate(sym, map, evsel, sizeof(struct browser_line), &browser.arch);
+	err = symbol__annotate2(sym, map, evsel, &annotation__default_options, &browser.arch);
 	if (err) {
 		char msg[BUFSIZ];
 		symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
@@ -1149,110 +832,21 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 		goto out_free_offsets;
 	}
 
-	symbol__calc_percent(sym, evsel);
-
 	ui_helpline__push("Press ESC to exit");
 
-	notes = symbol__annotation(sym);
-	browser.start = map__rip_2objdump(map, sym->start);
-
-	list_for_each_entry(al, &notes->src->source, node) {
-		struct browser_line *bpos;
-		size_t line_len = strlen(al->line);
-
-		if (browser.b.width < line_len)
-			browser.b.width = line_len;
-		bpos = browser_line(al);
-		bpos->idx = browser.nr_entries++;
-		if (al->offset != -1) {
-			bpos->idx_asm = browser.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 < (s64)size)
-				browser.offsets[al->offset] = al;
-		} else
-			bpos->idx_asm = -1;
-	}
-
-	annotate_browser__mark_jump_targets(&browser, size);
-	annotate__compute_ipc(&browser, size, sym);
-
-	browser.addr_width = browser.target_width = browser.min_addr_width = hex_width(size);
-	browser.max_addr_width = hex_width(sym->end);
-	browser.jumps_width = width_jumps(browser.max_jump_sources);
-	browser.nr_events = nr_pcnt;
-	browser.b.nr_entries = browser.nr_entries;
+	browser.b.width = notes->max_line_len;
+	browser.b.nr_entries = notes->nr_entries;
 	browser.b.entries = &notes->src->source,
 	browser.b.width += 18; /* Percentage */
 
-	if (annotate_browser__opts.hide_src_code)
-		annotate_browser__init_asm_mode(&browser);
-
-	annotate_browser__update_addr_width(&browser);
+	if (notes->options->hide_src_code)
+		ui_browser__init_asm_mode(&browser.b);
 
 	ret = annotate_browser__run(&browser, evsel, hbt);
 
 	annotated_source__purge(notes->src);
 
 out_free_offsets:
-	free(browser.offsets);
+	zfree(&notes->offsets);
 	return ret;
 }
-
-#define ANNOTATE_CFG(n) \
-	{ .name = #n, .value = &annotate_browser__opts.n, }
-
-/*
- * Keep the entries sorted, they are bsearch'ed
- */
-static struct annotate_config {
-	const char *name;
-	bool *value;
-} annotate__configs[] = {
-	ANNOTATE_CFG(hide_src_code),
-	ANNOTATE_CFG(jump_arrows),
-	ANNOTATE_CFG(show_linenr),
-	ANNOTATE_CFG(show_nr_jumps),
-	ANNOTATE_CFG(show_nr_samples),
-	ANNOTATE_CFG(show_total_period),
-	ANNOTATE_CFG(use_offset),
-};
-
-#undef ANNOTATE_CFG
-
-static int annotate_config__cmp(const void *name, const void *cfgp)
-{
-	const struct annotate_config *cfg = cfgp;
-
-	return strcmp(name, cfg->name);
-}
-
-static int annotate__config(const char *var, const char *value,
-			    void *data __maybe_unused)
-{
-	struct annotate_config *cfg;
-	const char *name;
-
-	if (!strstarts(var, "annotate."))
-		return 0;
-
-	name = var + 9;
-	cfg = bsearch(name, annotate__configs, ARRAY_SIZE(annotate__configs),
-		      sizeof(struct annotate_config), annotate_config__cmp);
-
-	if (cfg == NULL)
-		ui__warning("%s variable unknown, ignoring...", var);
-	else
-		*cfg->value = perf_config_bool(name, value);
-	return 0;
-}
-
-void annotate_browser__init(void)
-{
-	perf_config(annotate__config, NULL);
-}
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 6495ee55d9c3..8b4e82548f8e 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -2223,7 +2223,7 @@ static int perf_evsel_browser_title(struct hist_browser *browser,
 	u64 nr_events = hists->stats.total_period;
 	struct perf_evsel *evsel = hists_to_evsel(hists);
 	const char *ev_name = perf_evsel__name(evsel);
-	char buf[512];
+	char buf[512], sample_freq_str[64] = "";
 	size_t buflen = sizeof(buf);
 	char ref[30] = " show reference callgraph, ";
 	bool enable_ref = false;
@@ -2255,10 +2255,15 @@ static int perf_evsel_browser_title(struct hist_browser *browser,
 	if (symbol_conf.show_ref_callgraph &&
 	    strstr(ev_name, "call-graph=no"))
 		enable_ref = true;
+
+	if (!is_report_browser(hbt))
+		scnprintf(sample_freq_str, sizeof(sample_freq_str), " %d Hz,", evsel->attr.sample_freq);
+
 	nr_samples = convert_unit(nr_samples, &unit);
 	printed = scnprintf(bf, size,
-			   "Samples: %lu%c of event '%s',%sEvent count (approx.): %" PRIu64,
-			   nr_samples, unit, ev_name, enable_ref ? ref : " ", nr_events);
+			   "Samples: %lu%c of event%s '%s',%s%sEvent count (approx.): %" PRIu64,
+			   nr_samples, unit, evsel->nr_members > 1 ? "s" : "",
+			   ev_name, sample_freq_str, enable_ref ? ref : " ", nr_events);
 
 
 	if (hists->uid_filter_str)
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 25dd1e0ecc58..6832fcb2e6ff 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -840,15 +840,11 @@ size_t events_stats__fprintf(struct events_stats *stats, FILE *fp)
 	for (i = 0; i < PERF_RECORD_HEADER_MAX; ++i) {
 		const char *name;
 
-		if (stats->nr_events[i] == 0)
-			continue;
-
 		name = perf_event__name(i);
 		if (!strcmp(name, "UNKNOWN"))
 			continue;
 
-		ret += fprintf(fp, "%16s events: %10d\n", name,
-			       stats->nr_events[i]);
+		ret += fprintf(fp, "%16s events: %10d\n", name, stats->nr_events[i]);
 	}
 
 	return ret;
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index ea0a452550b0..8052373bcd6a 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -106,6 +106,7 @@ libperf-y += units.o
 libperf-y += time-utils.o
 libperf-y += expr-bison.o
 libperf-y += branch.o
+libperf-y += mem2node.o
 
 libperf-$(CONFIG_LIBBPF) += bpf-loader.o
 libperf-$(CONFIG_BPF_PROLOGUE) += bpf-prologue.o
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 28b233c3dcbe..3a428d7c59b9 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -14,6 +14,7 @@
 #include "sort.h"
 #include "build-id.h"
 #include "color.h"
+#include "config.h"
 #include "cache.h"
 #include "symbol.h"
 #include "debug.h"
@@ -27,8 +28,25 @@
 #include <linux/bitops.h>
 #include <linux/kernel.h>
 
+/* FIXME: For the HE_COLORSET */
+#include "ui/browser.h"
+
+/*
+ * FIXME: Using the same values as slang.h,
+ * but that header may not be available everywhere
+ */
+#define LARROW_CHAR	((unsigned char)',')
+#define RARROW_CHAR	((unsigned char)'+')
+#define DARROW_CHAR	((unsigned char)'.')
+#define UARROW_CHAR	((unsigned char)'-')
+
 #include "sane_ctype.h"
 
+struct annotation_options annotation__default_options = {
+	.use_offset     = true,
+	.jump_arrows    = true,
+};
+
 const char 	*disassembler_style;
 const char	*objdump_path;
 static regex_t	 file_lineno;
@@ -184,9 +202,13 @@ bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2)
 	return arch->ins_is_fused(arch, ins1, ins2);
 }
 
-static int call__parse(struct arch *arch, struct ins_operands *ops, struct map *map)
+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 = {
+		.map = map,
+	};
 
 	ops->target.addr = strtoull(ops->raw, &endptr, 16);
 
@@ -208,32 +230,36 @@ static int call__parse(struct arch *arch, struct ins_operands *ops, struct map *
 	ops->target.name = strdup(name);
 	*tok = '>';
 
-	return ops->target.name == NULL ? -1 : 0;
+	if (ops->target.name == NULL)
+		return -1;
+find_target:
+	target.addr = map__objdump_2mem(map, ops->target.addr);
 
-indirect_call:
-	tok = strchr(endptr, '*');
-	if (tok == NULL) {
-		struct symbol *sym = map__find_symbol(map, map->map_ip(map, ops->target.addr));
-		if (sym != NULL)
-			ops->target.name = strdup(sym->name);
-		else
-			ops->target.addr = 0;
-		return 0;
-	}
+	if (map_groups__find_ams(&target) == 0 &&
+	    map__rip_2objdump(target.map, map->map_ip(target.map, target.addr)) == ops->target.addr)
+		ops->target.sym = target.sym;
 
-	ops->target.addr = strtoull(tok + 1, NULL, 16);
 	return 0;
+
+indirect_call:
+	tok = strchr(endptr, '*');
+	if (tok != NULL)
+		ops->target.addr = strtoull(tok + 1, NULL, 16);
+	goto find_target;
 }
 
 static int call__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
-	if (ops->target.name)
-		return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.name);
+	if (ops->target.sym)
+		return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.sym->name);
 
 	if (ops->target.addr == 0)
 		return ins__raw_scnprintf(ins, bf, size, ops);
 
+	if (ops->target.name)
+		return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.name);
+
 	return scnprintf(bf, size, "%-6s *%" PRIx64, ins->name, ops->target.addr);
 }
 
@@ -244,14 +270,29 @@ static struct ins_ops call_ops = {
 
 bool ins__is_call(const struct ins *ins)
 {
-	return ins->ops == &call_ops;
+	return ins->ops == &call_ops || ins->ops == &s390_call_ops;
 }
 
-static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map *map __maybe_unused)
+static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms)
 {
-	const char *s = strchr(ops->raw, '+');
+	struct map *map = ms->map;
+	struct symbol *sym = ms->sym;
+	struct addr_map_symbol target = {
+		.map = map,
+	};
 	const char *c = strchr(ops->raw, ',');
-
+	u64 start, end;
+	/*
+	 * 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>
@@ -267,8 +308,36 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op
 		ops->target.addr = strtoull(ops->raw, NULL, 16);
 	}
 
-	if (s++ != NULL) {
-		ops->target.offset = strtoull(s, 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 (map_groups__find_ams(&target) == 0 &&
+	    map__rip_2objdump(target.map, map->map_ip(target.map, target.addr)) == ops->target.addr)
+		ops->target.sym = target.sym;
+
+	if (!ops->target.outside) {
+		ops->target.offset = target.addr - start;
 		ops->target.offset_avail = true;
 	} else {
 		ops->target.offset_avail = false;
@@ -280,11 +349,15 @@ static int jump__parse(struct arch *arch __maybe_unused, struct ins_operands *op
 static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
-	const char *c = strchr(ops->raw, ',');
+	const char *c;
 
 	if (!ops->target.addr || ops->target.offset < 0)
 		return ins__raw_scnprintf(ins, bf, size, ops);
 
+	if (ops->target.outside && ops->target.sym != NULL)
+		return scnprintf(bf, size, "%-6s %s", ins->name, ops->target.sym->name);
+
+	c = strchr(ops->raw, ',');
 	if (c != NULL) {
 		const char *c2 = strchr(c + 1, ',');
 
@@ -340,7 +413,7 @@ static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep)
 	return 0;
 }
 
-static int lock__parse(struct arch *arch, struct ins_operands *ops, struct map *map)
+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)
@@ -355,7 +428,7 @@ static int lock__parse(struct arch *arch, struct ins_operands *ops, struct map *
 		goto out_free_ops;
 
 	if (ops->locked.ins.ops->parse &&
-	    ops->locked.ins.ops->parse(arch, ops->locked.ops, map) < 0)
+	    ops->locked.ins.ops->parse(arch, ops->locked.ops, ms) < 0)
 		goto out_free_ops;
 
 	return 0;
@@ -398,7 +471,7 @@ static struct ins_ops lock_ops = {
 	.scnprintf = lock__scnprintf,
 };
 
-static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map *map __maybe_unused)
+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;
 
@@ -459,7 +532,7 @@ static struct ins_ops mov_ops = {
 	.scnprintf = mov__scnprintf,
 };
 
-static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map *map __maybe_unused)
+static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms __maybe_unused)
 {
 	char *target, *comment, *s, prev;
 
@@ -826,6 +899,66 @@ int addr_map_symbol__account_cycles(struct addr_map_symbol *ams,
 	return err;
 }
 
+static unsigned annotation__count_insn(struct annotation *notes, u64 start, u64 end)
+{
+	unsigned n_insn = 0;
+	u64 offset;
+
+	for (offset = start; offset <= end; offset++) {
+		if (notes->offsets[offset])
+			n_insn++;
+	}
+	return n_insn;
+}
+
+static void annotation__count_and_fill(struct annotation *notes, u64 start, u64 end, struct cyc_hist *ch)
+{
+	unsigned n_insn;
+	u64 offset;
+
+	n_insn = annotation__count_insn(notes, start, end);
+	if (n_insn && ch->num && ch->cycles) {
+		float ipc = n_insn / ((double)ch->cycles / (double)ch->num);
+
+		/* Hide data when there are too many overlaps. */
+		if (ch->reset >= 0x7fff || ch->reset >= ch->num / 2)
+			return;
+
+		for (offset = start; offset <= end; offset++) {
+			struct annotation_line *al = notes->offsets[offset];
+
+			if (al)
+				al->ipc = ipc;
+		}
+	}
+}
+
+void annotation__compute_ipc(struct annotation *notes, size_t size)
+{
+	u64 offset;
+
+	if (!notes->src || !notes->src->cycles_hist)
+		return;
+
+	pthread_mutex_lock(&notes->lock);
+	for (offset = 0; offset < size; ++offset) {
+		struct cyc_hist *ch;
+
+		ch = &notes->src->cycles_hist[offset];
+		if (ch && ch->cycles) {
+			struct annotation_line *al;
+
+			if (ch->have_start)
+				annotation__count_and_fill(notes, ch->start, offset, ch);
+			al = notes->offsets[offset];
+			if (al && ch->num_aggr)
+				al->cycles = ch->cycles_aggr / ch->num_aggr;
+			notes->have_cycles = true;
+		}
+	}
+	pthread_mutex_unlock(&notes->lock);
+}
+
 int addr_map_symbol__inc_samples(struct addr_map_symbol *ams, struct perf_sample *sample,
 				 int evidx)
 {
@@ -838,14 +971,14 @@ int hist_entry__inc_addr_samples(struct hist_entry *he, struct perf_sample *samp
 	return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip, sample);
 }
 
-static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map *map)
+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, map) < 0)
+	if (dl->ins.ops->parse && dl->ins.ops->parse(arch, &dl->ops, ms) < 0)
 		dl->ins.ops = NULL;
 }
 
@@ -882,7 +1015,7 @@ out_free_name:
 struct annotate_args {
 	size_t			 privsize;
 	struct arch		*arch;
-	struct map		*map;
+	struct map_symbol	 ms;
 	struct perf_evsel	*evsel;
 	s64			 offset;
 	char			*line;
@@ -964,7 +1097,7 @@ static struct disasm_line *disasm_line__new(struct annotate_args *args)
 			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->map);
+			disasm_line__init_ins(dl, args->arch, &args->ms);
 		}
 	}
 
@@ -1222,7 +1355,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, FILE *file,
 				      struct annotate_args *args,
 				      int *line_nr)
 {
-	struct map *map = args->map;
+	struct map *map = args->ms.map;
 	struct annotation *notes = symbol__annotation(sym);
 	struct disasm_line *dl;
 	char *line = NULL, *parsed_line, *tmp, *tmp2;
@@ -1269,6 +1402,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, FILE *file,
 	args->offset  = offset;
 	args->line    = parsed_line;
 	args->line_nr = *line_nr;
+	args->ms.sym  = sym;
 
 	dl = disasm_line__new(args);
 	free(line);
@@ -1277,14 +1411,14 @@ static int symbol__parse_objdump_line(struct symbol *sym, FILE *file,
 	if (dl == NULL)
 		return -1;
 
-	if (!disasm_line__has_offset(dl)) {
+	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 name */
-	if (dl->ins.ops && ins__is_call(&dl->ins) && !dl->ops.target.name) {
+	/* 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 = {
 			.map = map,
 			.addr = dl->ops.target.addr,
@@ -1292,7 +1426,7 @@ static int symbol__parse_objdump_line(struct symbol *sym, FILE *file,
 
 		if (!map_groups__find_ams(&target) &&
 		    target.sym->start == target.al_addr)
-			dl->ops.target.name = strdup(target.sym->name);
+			dl->ops.target.sym = target.sym;
 	}
 
 	annotation_line__add(&dl->al, &notes->src->source);
@@ -1421,9 +1555,9 @@ fallback:
 
 static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 {
-	struct map *map = args->map;
+	struct map *map = args->ms.map;
 	struct dso *dso = map->dso;
-	char command[PATH_MAX * 2];
+	char *command;
 	FILE *file;
 	char symfs_filename[PATH_MAX];
 	struct kcore_extract kce;
@@ -1464,7 +1598,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 		strcpy(symfs_filename, tmp);
 	}
 
-	snprintf(command, sizeof(command),
+	err = asprintf(&command,
 		 "%s %s%s --start-address=0x%016" PRIx64
 		 " --stop-address=0x%016" PRIx64
 		 " -l -d %s %s -C \"%s\" 2>/dev/null|grep -v \"%s:\"|expand",
@@ -1477,12 +1611,17 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 		 symbol_conf.annotate_src ? "-S" : "",
 		 symfs_filename, symfs_filename);
 
+	if (err < 0) {
+		pr_err("Failure allocating memory for the command to run\n");
+		goto out_remove_tmp;
+	}
+
 	pr_debug("Executing: %s\n", command);
 
 	err = -1;
 	if (pipe(stdout_fd) < 0) {
 		pr_err("Failure creating the pipe to run %s\n", command);
-		goto out_remove_tmp;
+		goto out_free_command;
 	}
 
 	pid = fork();
@@ -1509,7 +1648,7 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 		 * If we were using debug info should retry with
 		 * original binary.
 		 */
-		goto out_remove_tmp;
+		goto out_free_command;
 	}
 
 	nline = 0;
@@ -1537,6 +1676,8 @@ static int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 
 	fclose(file);
 	err = 0;
+out_free_command:
+	free(command);
 out_remove_tmp:
 	close(stdout_fd[0]);
 
@@ -1550,7 +1691,7 @@ out:
 
 out_close_stdout:
 	close(stdout_fd[1]);
-	goto out_remove_tmp;
+	goto out_free_command;
 }
 
 static void calc_percent(struct sym_hist *hist,
@@ -1613,7 +1754,6 @@ int symbol__annotate(struct symbol *sym, struct map *map,
 {
 	struct annotate_args args = {
 		.privsize	= privsize,
-		.map		= map,
 		.evsel		= evsel,
 	};
 	struct perf_env *env = perf_evsel__env(evsel);
@@ -1639,6 +1779,9 @@ int symbol__annotate(struct symbol *sym, struct map *map,
 		}
 	}
 
+	args.ms.map = map;
+	args.ms.sym = sym;
+
 	return symbol__disassemble(sym, &args);
 }
 
@@ -1879,6 +2022,103 @@ int symbol__annotate_printf(struct symbol *sym, struct map *map,
 	return more;
 }
 
+static void FILE__set_percent_color(void *fp __maybe_unused,
+				    double percent __maybe_unused,
+				    bool current __maybe_unused)
+{
+}
+
+static int FILE__set_jumps_percent_color(void *fp __maybe_unused,
+					 int nr __maybe_unused, bool current __maybe_unused)
+{
+	return 0;
+}
+
+static int FILE__set_color(void *fp __maybe_unused, int color __maybe_unused)
+{
+	return 0;
+}
+
+static void FILE__printf(void *fp, const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	vfprintf(fp, fmt, args);
+	va_end(args);
+}
+
+static void FILE__write_graph(void *fp, int graph)
+{
+	const char *s;
+	switch (graph) {
+
+	case DARROW_CHAR: s = "↓"; break;
+	case UARROW_CHAR: s = "↑"; break;
+	case LARROW_CHAR: s = "←"; break;
+	case RARROW_CHAR: s = "→"; break;
+	default:		s = "?"; break;
+	}
+
+	fputs(s, fp);
+}
+
+int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct annotation_write_ops ops = {
+		.first_line		 = true,
+		.obj			 = fp,
+		.set_color		 = FILE__set_color,
+		.set_percent_color	 = FILE__set_percent_color,
+		.set_jumps_percent_color = FILE__set_jumps_percent_color,
+		.printf			 = FILE__printf,
+		.write_graph		 = FILE__write_graph,
+	};
+	struct annotation_line *al;
+
+	list_for_each_entry(al, &notes->src->source, node) {
+		if (annotation_line__filter(al, notes))
+			continue;
+		annotation_line__write(al, notes, &ops);
+		fputc('\n', fp);
+		ops.first_line = false;
+	}
+
+	return 0;
+}
+
+int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel)
+{
+	const char *ev_name = perf_evsel__name(evsel);
+	char buf[1024];
+	char *filename;
+	int err = -1;
+	FILE *fp;
+
+	if (asprintf(&filename, "%s.annotation", ms->sym->name) < 0)
+		return -1;
+
+	fp = fopen(filename, "w");
+	if (fp == NULL)
+		goto out_free_filename;
+
+	if (perf_evsel__is_group_event(evsel)) {
+		perf_evsel__group_desc(evsel, buf, sizeof(buf));
+		ev_name = buf;
+	}
+
+	fprintf(fp, "%s() %s\nEvent: %s\n\n",
+		ms->sym->name, ms->map->dso->long_name, ev_name);
+	symbol__annotate_fprintf2(ms->sym, fp);
+
+	fclose(fp);
+	err = 0;
+out_free_filename:
+	free(filename);
+	return err;
+}
+
 void symbol__annotate_zero_histogram(struct symbol *sym, int evidx)
 {
 	struct annotation *notes = symbol__annotation(sym);
@@ -1938,8 +2178,109 @@ size_t disasm__fprintf(struct list_head *head, FILE *fp)
 	return printed;
 }
 
+bool disasm_line__is_valid_local_jump(struct disasm_line *dl, struct symbol *sym)
+{
+	if (!dl || !dl->ins.ops || !ins__is_jump(&dl->ins) ||
+	    !disasm_line__has_local_offset(dl) || dl->ops.target.offset < 0 ||
+	    dl->ops.target.offset >= (s64)symbol__size(sym))
+		return false;
+
+	return true;
+}
+
+void annotation__mark_jump_targets(struct annotation *notes, struct symbol *sym)
+{
+	u64 offset, size = symbol__size(sym);
+
+	/* PLT symbols contain external offsets */
+	if (strstr(sym->name, "@plt"))
+		return;
+
+	for (offset = 0; offset < size; ++offset) {
+		struct annotation_line *al = notes->offsets[offset];
+		struct disasm_line *dl;
+
+		dl = disasm_line(al);
+
+		if (!disasm_line__is_valid_local_jump(dl, sym))
+			continue;
+
+		al = notes->offsets[dl->ops.target.offset];
+
+		/*
+		 * FIXME: Oops, no jump target? Buggy disassembler? Or do we
+		 * have to adjust to the previous offset?
+		 */
+		if (al == NULL)
+			continue;
+
+		if (++al->jump_sources > notes->max_jump_sources)
+			notes->max_jump_sources = al->jump_sources;
+
+		++notes->nr_jumps;
+	}
+}
+
+void annotation__set_offsets(struct annotation *notes, s64 size)
+{
+	struct annotation_line *al;
+
+	notes->max_line_len = 0;
+
+	list_for_each_entry(al, &notes->src->source, node) {
+		size_t line_len = strlen(al->line);
+
+		if (notes->max_line_len < line_len)
+			notes->max_line_len = line_len;
+		al->idx = notes->nr_entries++;
+		if (al->offset != -1) {
+			al->idx_asm = notes->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->offsets[al->offset] = al;
+		} else
+			al->idx_asm = -1;
+	}
+}
+
+static inline int width_jumps(int n)
+{
+	if (n >= 100)
+		return 5;
+	if (n / 10)
+		return 2;
+	return 1;
+}
+
+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);
+}
+
+void annotation__update_column_widths(struct annotation *notes)
+{
+	if (notes->options->use_offset)
+		notes->widths.target = notes->widths.min_addr;
+	else
+		notes->widths.target = notes->widths.max_addr;
+
+	notes->widths.addr = notes->widths.target;
+
+	if (notes->options->show_nr_jumps)
+		notes->widths.addr += notes->widths.jumps + 1;
+}
+
 static void annotation__calc_lines(struct annotation *notes, struct map *map,
-				  struct rb_root *root, u64 start)
+				  struct rb_root *root)
 {
 	struct annotation_line *al;
 	struct rb_root tmp_root = RB_ROOT;
@@ -1960,8 +2301,8 @@ static void annotation__calc_lines(struct annotation *notes, struct map *map,
 		if (percent_max <= 0.5)
 			continue;
 
-		al->path = get_srcline(map->dso, start + al->offset, NULL,
-				       false, true, start + al->offset);
+		al->path = get_srcline(map->dso, notes->start + al->offset, NULL,
+				       false, true, notes->start + al->offset);
 		insert_source_line(&tmp_root, al);
 	}
 
@@ -1972,9 +2313,40 @@ static void symbol__calc_lines(struct symbol *sym, struct map *map,
 			      struct rb_root *root)
 {
 	struct annotation *notes = symbol__annotation(sym);
-	u64 start = map__rip_2objdump(map, sym->start);
 
-	annotation__calc_lines(notes, map, root, start);
+	annotation__calc_lines(notes, map, root);
+}
+
+int symbol__tty_annotate2(struct symbol *sym, struct map *map,
+			  struct perf_evsel *evsel, bool print_lines,
+			  bool full_paths)
+{
+	struct dso *dso = map->dso;
+	struct rb_root source_line = RB_ROOT;
+	struct annotation_options opts = annotation__default_options;
+	const char *ev_name = perf_evsel__name(evsel);
+	char buf[1024];
+
+	if (symbol__annotate2(sym, map, evsel, &opts, NULL) < 0)
+		return -1;
+
+	if (print_lines) {
+		srcline_full_filename = full_paths;
+		symbol__calc_lines(sym, map, &source_line);
+		print_summary(&source_line, dso->long_name);
+	}
+
+	if (perf_evsel__is_group_event(evsel)) {
+		perf_evsel__group_desc(evsel, buf, sizeof(buf));
+		ev_name = buf;
+	}
+
+	fprintf(stdout, "%s() %s\nEvent: %s\n\n", sym->name, dso->long_name, ev_name);
+	symbol__annotate_fprintf2(sym, stdout);
+
+	annotated_source__purge(symbol__annotation(sym)->src);
+
+	return 0;
 }
 
 int symbol__tty_annotate(struct symbol *sym, struct map *map,
@@ -2007,3 +2379,276 @@ bool ui__has_annotation(void)
 {
 	return use_browser == 1 && perf_hpp_list.sym;
 }
+
+
+double annotation_line__max_percent(struct annotation_line *al, struct annotation *notes)
+{
+	double percent_max = 0.0;
+	int i;
+
+	for (i = 0; i < notes->nr_events; i++) {
+		if (al->samples[i].percent > percent_max)
+			percent_max = al->samples[i].percent;
+	}
+
+	return percent_max;
+}
+
+static void disasm_line__write(struct disasm_line *dl, struct annotation *notes,
+			       void *obj, char *bf, size_t size,
+			       void (*obj__printf)(void *obj, const char *fmt, ...),
+			       void (*obj__write_graph)(void *obj, int graph))
+{
+	if (dl->ins.ops && dl->ins.ops->scnprintf) {
+		if (ins__is_jump(&dl->ins)) {
+			bool fwd;
+
+			if (dl->ops.target.outside)
+				goto call_like;
+			fwd = dl->ops.target.offset > dl->al.offset;
+			obj__write_graph(obj, fwd ? DARROW_CHAR : UARROW_CHAR);
+			obj__printf(obj, " ");
+		} else if (ins__is_call(&dl->ins)) {
+call_like:
+			obj__write_graph(obj, RARROW_CHAR);
+			obj__printf(obj, " ");
+		} else if (ins__is_ret(&dl->ins)) {
+			obj__write_graph(obj, LARROW_CHAR);
+			obj__printf(obj, " ");
+		} else {
+			obj__printf(obj, "  ");
+		}
+	} else {
+		obj__printf(obj, "  ");
+	}
+
+	disasm_line__scnprintf(dl, bf, size, !notes->options->use_offset);
+}
+
+static void __annotation_line__write(struct annotation_line *al, struct annotation *notes,
+				     bool first_line, bool current_entry, bool change_color, int width,
+				     void *obj,
+				     int  (*obj__set_color)(void *obj, int color),
+				     void (*obj__set_percent_color)(void *obj, double percent, bool current),
+				     int  (*obj__set_jumps_percent_color)(void *obj, int nr, bool current),
+				     void (*obj__printf)(void *obj, const char *fmt, ...),
+				     void (*obj__write_graph)(void *obj, int graph))
+
+{
+	double percent_max = annotation_line__max_percent(al, notes);
+	int pcnt_width = annotation__pcnt_width(notes),
+	    cycles_width = annotation__cycles_width(notes);
+	bool show_title = false;
+	char bf[256];
+	int printed;
+
+	if (first_line && (al->offset == -1 || percent_max == 0.0)) {
+		if (notes->have_cycles) {
+			if (al->ipc == 0.0 && al->cycles == 0)
+				show_title = true;
+		} else
+			show_title = true;
+	}
+
+	if (al->offset != -1 && percent_max != 0.0) {
+		int i;
+
+		for (i = 0; i < notes->nr_events; i++) {
+			obj__set_percent_color(obj, al->samples[i].percent, current_entry);
+			if (notes->options->show_total_period) {
+				obj__printf(obj, "%11" PRIu64 " ", al->samples[i].he.period);
+			} else if (notes->options->show_nr_samples) {
+				obj__printf(obj, "%6" PRIu64 " ",
+						   al->samples[i].he.nr_samples);
+			} else {
+				obj__printf(obj, "%6.2f ",
+						   al->samples[i].percent);
+			}
+		}
+	} else {
+		obj__set_percent_color(obj, 0, current_entry);
+
+		if (!show_title)
+			obj__printf(obj, "%-*s", pcnt_width, " ");
+		else {
+			obj__printf(obj, "%-*s", pcnt_width,
+					   notes->options->show_total_period ? "Period" :
+					   notes->options->show_nr_samples ? "Samples" : "Percent");
+		}
+	}
+
+	if (notes->have_cycles) {
+		if (al->ipc)
+			obj__printf(obj, "%*.2f ", ANNOTATION__IPC_WIDTH - 1, al->ipc);
+		else if (!show_title)
+			obj__printf(obj, "%*s", ANNOTATION__IPC_WIDTH, " ");
+		else
+			obj__printf(obj, "%*s ", ANNOTATION__IPC_WIDTH - 1, "IPC");
+
+		if (al->cycles)
+			obj__printf(obj, "%*" PRIu64 " ",
+					   ANNOTATION__CYCLES_WIDTH - 1, al->cycles);
+		else if (!show_title)
+			obj__printf(obj, "%*s", ANNOTATION__CYCLES_WIDTH, " ");
+		else
+			obj__printf(obj, "%*s ", ANNOTATION__CYCLES_WIDTH - 1, "Cycle");
+	}
+
+	obj__printf(obj, " ");
+
+	if (!*al->line)
+		obj__printf(obj, "%-*s", width - pcnt_width - cycles_width, " ");
+	else if (al->offset == -1) {
+		if (al->line_nr && notes->options->show_linenr)
+			printed = scnprintf(bf, sizeof(bf), "%-*d ", notes->widths.addr + 1, al->line_nr);
+		else
+			printed = scnprintf(bf, sizeof(bf), "%-*s  ", notes->widths.addr, " ");
+		obj__printf(obj, bf);
+		obj__printf(obj, "%-*s", width - printed - pcnt_width - cycles_width + 1, al->line);
+	} else {
+		u64 addr = al->offset;
+		int color = -1;
+
+		if (!notes->options->use_offset)
+			addr += notes->start;
+
+		if (!notes->options->use_offset) {
+			printed = scnprintf(bf, sizeof(bf), "%" PRIx64 ": ", addr);
+		} else {
+			if (al->jump_sources) {
+				if (notes->options->show_nr_jumps) {
+					int prev;
+					printed = scnprintf(bf, sizeof(bf), "%*d ",
+							    notes->widths.jumps,
+							    al->jump_sources);
+					prev = obj__set_jumps_percent_color(obj, al->jump_sources,
+									    current_entry);
+					obj__printf(obj, bf);
+					obj__set_color(obj, prev);
+				}
+
+				printed = scnprintf(bf, sizeof(bf), "%*" PRIx64 ": ",
+						    notes->widths.target, addr);
+			} else {
+				printed = scnprintf(bf, sizeof(bf), "%-*s  ",
+						    notes->widths.addr, " ");
+			}
+		}
+
+		if (change_color)
+			color = obj__set_color(obj, HE_COLORSET_ADDR);
+		obj__printf(obj, bf);
+		if (change_color)
+			obj__set_color(obj, color);
+
+		disasm_line__write(disasm_line(al), notes, obj, bf, sizeof(bf), obj__printf, obj__write_graph);
+
+		obj__printf(obj, "%-*s", width - pcnt_width - cycles_width - 3 - printed, bf);
+	}
+
+}
+
+void annotation_line__write(struct annotation_line *al, struct annotation *notes,
+			    struct annotation_write_ops *ops)
+{
+	__annotation_line__write(al, notes, ops->first_line, ops->current_entry,
+				 ops->change_color, ops->width, ops->obj,
+				 ops->set_color, ops->set_percent_color,
+				 ops->set_jumps_percent_color, ops->printf,
+				 ops->write_graph);
+}
+
+int symbol__annotate2(struct symbol *sym, struct map *map, struct perf_evsel *evsel,
+		      struct annotation_options *options, struct arch **parch)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	size_t size = symbol__size(sym);
+	int nr_pcnt = 1, err;
+
+	notes->offsets = zalloc(size * sizeof(struct annotation_line *));
+	if (notes->offsets == NULL)
+		return -1;
+
+	if (perf_evsel__is_group_event(evsel))
+		nr_pcnt = evsel->nr_members;
+
+	err = symbol__annotate(sym, map, evsel, 0, parch);
+	if (err)
+		goto out_free_offsets;
+
+	notes->options = options;
+
+	symbol__calc_percent(sym, evsel);
+
+	notes->start = map__rip_2objdump(map, sym->start);
+
+	annotation__set_offsets(notes, size);
+	annotation__mark_jump_targets(notes, sym);
+	annotation__compute_ipc(notes, size);
+	annotation__init_column_widths(notes, sym);
+	notes->nr_events = nr_pcnt;
+
+	annotation__update_column_widths(notes);
+
+	return 0;
+
+out_free_offsets:
+	zfree(&notes->offsets);
+	return -1;
+}
+
+#define ANNOTATION__CFG(n) \
+	{ .name = #n, .value = &annotation__default_options.n, }
+
+/*
+ * Keep the entries sorted, they are bsearch'ed
+ */
+static struct annotation_config {
+	const char *name;
+	bool *value;
+} annotation__configs[] = {
+	ANNOTATION__CFG(hide_src_code),
+	ANNOTATION__CFG(jump_arrows),
+	ANNOTATION__CFG(show_linenr),
+	ANNOTATION__CFG(show_nr_jumps),
+	ANNOTATION__CFG(show_nr_samples),
+	ANNOTATION__CFG(show_total_period),
+	ANNOTATION__CFG(use_offset),
+};
+
+#undef ANNOTATION__CFG
+
+static int annotation_config__cmp(const void *name, const void *cfgp)
+{
+	const struct annotation_config *cfg = cfgp;
+
+	return strcmp(name, cfg->name);
+}
+
+static int annotation__config(const char *var, const char *value,
+			    void *data __maybe_unused)
+{
+	struct annotation_config *cfg;
+	const char *name;
+
+	if (!strstarts(var, "annotate."))
+		return 0;
+
+	name = var + 9;
+	cfg = bsearch(name, annotation__configs, ARRAY_SIZE(annotation__configs),
+		      sizeof(struct annotation_config), annotation_config__cmp);
+
+	if (cfg == NULL)
+		pr_debug("%s variable unknown, ignoring...", var);
+	else
+		*cfg->value = perf_config_bool(name, value);
+	return 0;
+}
+
+void annotation_config__init(void)
+{
+	perf_config(annotation__config, NULL);
+
+	annotation__default_options.show_total_period = symbol_conf.show_total_period;
+	annotation__default_options.show_nr_samples   = symbol_conf.show_nr_samples;
+}
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index ce427445671f..ff7e3df31efa 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -24,9 +24,11 @@ struct ins_operands {
 	struct {
 		char	*raw;
 		char	*name;
+		struct symbol *sym;
 		u64	addr;
 		s64	offset;
 		bool	offset_avail;
+		bool	outside;
 	} target;
 	union {
 		struct {
@@ -45,7 +47,7 @@ struct arch;
 
 struct ins_ops {
 	void (*free)(struct ins_operands *ops);
-	int (*parse)(struct arch *arch, struct ins_operands *ops, struct map *map);
+	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);
 };
@@ -57,6 +59,21 @@ bool ins__is_lock(const struct ins *ins);
 int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops);
 bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
 
+#define ANNOTATION__IPC_WIDTH 6
+#define ANNOTATION__CYCLES_WIDTH 6
+
+struct annotation_options {
+	bool hide_src_code,
+	     use_offset,
+	     jump_arrows,
+	     show_linenr,
+	     show_nr_jumps,
+	     show_nr_samples,
+	     show_total_period;
+};
+
+extern struct annotation_options annotation__default_options;
+
 struct annotation;
 
 struct sym_hist_entry {
@@ -76,10 +93,13 @@ struct annotation_line {
 	s64			 offset;
 	char			*line;
 	int			 line_nr;
+	int			 jump_sources;
 	float			 ipc;
 	u64			 cycles;
 	size_t			 privsize;
 	char			*path;
+	u32			 idx;
+	int			 idx_asm;
 	int			 samples_nr;
 	struct annotation_data	 samples[0];
 };
@@ -97,14 +117,40 @@ static inline struct disasm_line *disasm_line(struct annotation_line *al)
 	return al ? container_of(al, struct disasm_line, al) : NULL;
 }
 
-static inline bool disasm_line__has_offset(const struct disasm_line *dl)
+/*
+ * Is this offset in the same function as the line it is used?
+ * asm functions jump to other functions, for instance.
+ */
+static inline bool disasm_line__has_local_offset(const struct disasm_line *dl)
 {
-	return dl->ops.target.offset_avail;
+	return dl->ops.target.offset_avail && !dl->ops.target.outside;
 }
 
+/*
+ * Can we draw an arrow from the jump to its target, for instance? I.e.
+ * is the jump and its target in the same function?
+ */
+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);
+
+struct annotation_write_ops {
+	bool first_line, current_entry, change_color;
+	int  width;
+	void *obj;
+	int  (*set_color)(void *obj, int color);
+	void (*set_percent_color)(void *obj, double percent, bool current);
+	int  (*set_jumps_percent_color)(void *obj, int nr, bool current);
+	void (*printf)(void *obj, const char *fmt, ...);
+	void (*write_graph)(void *obj, int graph);
+};
+
+double annotation_line__max_percent(struct annotation_line *al, struct annotation *notes);
+void annotation_line__write(struct annotation_line *al, struct annotation *notes,
+			    struct annotation_write_ops *ops);
+
 int disasm_line__scnprintf(struct disasm_line *dl, char *bf, size_t size, bool raw);
 size_t disasm__fprintf(struct list_head *head, FILE *fp);
 void symbol__calc_percent(struct symbol *sym, struct perf_evsel *evsel);
@@ -150,9 +196,47 @@ struct annotated_source {
 struct annotation {
 	pthread_mutex_t		lock;
 	u64			max_coverage;
+	u64			start;
+	struct annotation_options *options;
+	struct annotation_line	**offsets;
+	int			nr_events;
+	int			nr_jumps;
+	int			max_jump_sources;
+	int			nr_entries;
+	int			nr_asm_entries;
+	u16			max_line_len;
+	struct {
+		u8		addr;
+		u8		jumps;
+		u8		target;
+		u8		min_addr;
+		u8		max_addr;
+	} widths;
+	bool			have_cycles;
 	struct annotated_source *src;
 };
 
+static inline int annotation__cycles_width(struct annotation *notes)
+{
+	return notes->have_cycles ? ANNOTATION__IPC_WIDTH + ANNOTATION__CYCLES_WIDTH : 0;
+}
+
+static inline int annotation__pcnt_width(struct annotation *notes)
+{
+	return (notes->options->show_total_period ? 12 : 7) * notes->nr_events;
+}
+
+static inline bool annotation_line__filter(struct annotation_line *al, struct annotation *notes)
+{
+	return notes->options->hide_src_code && al->offset == -1;
+}
+
+void annotation__set_offsets(struct annotation *notes, s64 size);
+void annotation__compute_ipc(struct annotation *notes, size_t 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);
+
 static inline struct sym_hist *annotation__histogram(struct annotation *notes, int idx)
 {
 	return (((void *)&notes->src->histograms) +
@@ -180,6 +264,10 @@ void symbol__annotate_zero_histograms(struct symbol *sym);
 int symbol__annotate(struct symbol *sym, struct map *map,
 		     struct perf_evsel *evsel, size_t privsize,
 		     struct arch **parch);
+int symbol__annotate2(struct symbol *sym, struct map *map,
+		      struct perf_evsel *evsel,
+		      struct annotation_options *options,
+		      struct arch **parch);
 
 enum symbol_disassemble_errno {
 	SYMBOL_ANNOTATE_ERRNO__SUCCESS		= 0,
@@ -204,16 +292,23 @@ int symbol__strerror_disassemble(struct symbol *sym, struct map *map,
 int symbol__annotate_printf(struct symbol *sym, struct map *map,
 			    struct perf_evsel *evsel, bool full_paths,
 			    int min_pcnt, int max_lines, int context);
+int symbol__annotate_fprintf2(struct symbol *sym, FILE *fp);
 void symbol__annotate_zero_histogram(struct symbol *sym, int evidx);
 void symbol__annotate_decay_histogram(struct symbol *sym, int evidx);
 void annotated_source__purge(struct annotated_source *as);
 
+int map_symbol__annotation_dump(struct map_symbol *ms, struct perf_evsel *evsel);
+
 bool ui__has_annotation(void);
 
 int symbol__tty_annotate(struct symbol *sym, struct map *map,
 			 struct perf_evsel *evsel, bool print_lines,
 			 bool full_paths, int min_pcnt, int max_lines);
 
+int symbol__tty_annotate2(struct symbol *sym, struct map *map,
+			  struct perf_evsel *evsel, bool print_lines,
+			  bool full_paths);
+
 #ifdef HAVE_SLANG_SUPPORT
 int symbol__tui_annotate(struct symbol *sym, struct map *map,
 			 struct perf_evsel *evsel,
@@ -231,4 +326,6 @@ static inline int symbol__tui_annotate(struct symbol *sym __maybe_unused,
 
 extern const char	*disassembler_style;
 
+void annotation_config__init(void);
+
 #endif	/* __PERF_ANNOTATE_H */
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 6470ea2aa25e..fb357a00dd86 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -233,9 +233,9 @@ static void *auxtrace_copy_data(u64 size, struct perf_session *session)
 	return p;
 }
 
-static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
-				       unsigned int idx,
-				       struct auxtrace_buffer *buffer)
+static int auxtrace_queues__queue_buffer(struct auxtrace_queues *queues,
+					 unsigned int idx,
+					 struct auxtrace_buffer *buffer)
 {
 	struct auxtrace_queue *queue;
 	int err;
@@ -286,7 +286,7 @@ static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues,
 			return -ENOMEM;
 		b->size = BUFFER_LIMIT_FOR_32_BIT;
 		b->consecutive = consecutive;
-		err = auxtrace_queues__add_buffer(queues, idx, b);
+		err = auxtrace_queues__queue_buffer(queues, idx, b);
 		if (err) {
 			auxtrace_buffer__free(b);
 			return err;
@@ -302,11 +302,14 @@ static int auxtrace_queues__split_buffer(struct auxtrace_queues *queues,
 	return 0;
 }
 
-static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues,
-					     struct perf_session *session,
-					     unsigned int idx,
-					     struct auxtrace_buffer *buffer)
+static int auxtrace_queues__add_buffer(struct auxtrace_queues *queues,
+				       struct perf_session *session,
+				       unsigned int idx,
+				       struct auxtrace_buffer *buffer,
+				       struct auxtrace_buffer **buffer_ptr)
 {
+	int err;
+
 	if (session->one_mmap) {
 		buffer->data = buffer->data_offset - session->one_mmap_offset +
 			       session->one_mmap_addr;
@@ -317,14 +320,20 @@ static int auxtrace_queues__add_event_buffer(struct auxtrace_queues *queues,
 		buffer->data_needs_freeing = true;
 	} else if (BITS_PER_LONG == 32 &&
 		   buffer->size > BUFFER_LIMIT_FOR_32_BIT) {
-		int err;
-
 		err = auxtrace_queues__split_buffer(queues, idx, buffer);
 		if (err)
 			return err;
 	}
 
-	return auxtrace_queues__add_buffer(queues, idx, buffer);
+	err = auxtrace_queues__queue_buffer(queues, idx, buffer);
+	if (err)
+		return err;
+
+	/* FIXME: Doesn't work for split buffer */
+	if (buffer_ptr)
+		*buffer_ptr = buffer;
+
+	return 0;
 }
 
 static bool filter_cpu(struct perf_session *session, int cpu)
@@ -359,13 +368,11 @@ int auxtrace_queues__add_event(struct auxtrace_queues *queues,
 	buffer->size = event->auxtrace.size;
 	idx = event->auxtrace.idx;
 
-	err = auxtrace_queues__add_event_buffer(queues, session, idx, buffer);
+	err = auxtrace_queues__add_buffer(queues, session, idx, buffer,
+					  buffer_ptr);
 	if (err)
 		goto out_err;
 
-	if (buffer_ptr)
-		*buffer_ptr = buffer;
-
 	return 0;
 
 out_err:
diff --git a/tools/perf/util/auxtrace.h b/tools/perf/util/auxtrace.h
index 453c148d2158..e731f55da072 100644
--- a/tools/perf/util/auxtrace.h
+++ b/tools/perf/util/auxtrace.h
@@ -130,6 +130,7 @@ struct auxtrace_index {
 /**
  * struct auxtrace - session callbacks to allow AUX area data decoding.
  * @process_event: lets the decoder see all session events
+ * @process_auxtrace_event: process a PERF_RECORD_AUXTRACE event
  * @flush_events: process any remaining data
  * @free_events: free resources associated with event processing
  * @free: free resources associated with the session
@@ -301,6 +302,7 @@ struct auxtrace_mmap_params {
  * @parse_snapshot_options: parse snapshot options
  * @reference: provide a 64-bit reference number for auxtrace_event
  * @read_finish: called after reading from an auxtrace mmap
+ * @alignment: alignment (if any) for AUX area data
  */
 struct auxtrace_record {
 	int (*recording_options)(struct auxtrace_record *itr,
diff --git a/tools/perf/util/build-id.c b/tools/perf/util/build-id.c
index 7f8553630c4d..537eadd81914 100644
--- a/tools/perf/util/build-id.c
+++ b/tools/perf/util/build-id.c
@@ -316,7 +316,6 @@ static int machine__write_buildid_table(struct machine *machine,
 					struct feat_fd *fd)
 {
 	int err = 0;
-	char nm[PATH_MAX];
 	struct dso *pos;
 	u16 kmisc = PERF_RECORD_MISC_KERNEL,
 	    umisc = PERF_RECORD_MISC_USER;
@@ -338,9 +337,8 @@ static int machine__write_buildid_table(struct machine *machine,
 			name = pos->short_name;
 			name_len = pos->short_name_len;
 		} else if (dso__is_kcore(pos)) {
-			machine__mmap_name(machine, nm, sizeof(nm));
-			name = nm;
-			name_len = strlen(nm);
+			name = machine->mmap_name;
+			name_len = strlen(name);
 		} else {
 			name = pos->long_name;
 			name_len = pos->long_name_len;
@@ -813,12 +811,10 @@ static int dso__cache_build_id(struct dso *dso, struct machine *machine)
 	bool is_kallsyms = dso__is_kallsyms(dso);
 	bool is_vdso = dso__is_vdso(dso);
 	const char *name = dso->long_name;
-	char nm[PATH_MAX];
 
 	if (dso__is_kcore(dso)) {
 		is_kallsyms = true;
-		machine__mmap_name(machine, nm, sizeof(nm));
-		name = nm;
+		name = machine->mmap_name;
 	}
 	return build_id_cache__add_b(dso->build_id, sizeof(dso->build_id), name,
 				     dso->nsinfo, is_kallsyms, is_vdso);
diff --git a/tools/perf/util/cgroup.c b/tools/perf/util/cgroup.c
index 984f69144f87..decb91f9da82 100644
--- a/tools/perf/util/cgroup.c
+++ b/tools/perf/util/cgroup.c
@@ -71,7 +71,7 @@ cgroupfs_find_mountpoint(char *buf, size_t maxlen)
 	return -1;
 }
 
-static int open_cgroup(char *name)
+static int open_cgroup(const char *name)
 {
 	char path[PATH_MAX + 1];
 	char mnt[PATH_MAX + 1];
@@ -81,7 +81,7 @@ static int open_cgroup(char *name)
 	if (cgroupfs_find_mountpoint(mnt, PATH_MAX + 1))
 		return -1;
 
-	snprintf(path, PATH_MAX, "%s/%s", mnt, name);
+	scnprintf(path, PATH_MAX, "%s/%s", mnt, name);
 
 	fd = open(path, O_RDONLY);
 	if (fd == -1)
@@ -90,41 +90,64 @@ static int open_cgroup(char *name)
 	return fd;
 }
 
-static int add_cgroup(struct perf_evlist *evlist, char *str)
+static struct cgroup *evlist__find_cgroup(struct perf_evlist *evlist, const char *str)
 {
 	struct perf_evsel *counter;
-	struct cgroup_sel *cgrp = NULL;
-	int n;
+	struct cgroup *cgrp = NULL;
 	/*
 	 * check if cgrp is already defined, if so we reuse it
 	 */
 	evlist__for_each_entry(evlist, counter) {
-		cgrp = counter->cgrp;
-		if (!cgrp)
+		if (!counter->cgrp)
 			continue;
-		if (!strcmp(cgrp->name, str)) {
-			refcount_inc(&cgrp->refcnt);
+		if (!strcmp(counter->cgrp->name, str)) {
+			cgrp = cgroup__get(counter->cgrp);
 			break;
 		}
-
-		cgrp = NULL;
 	}
 
-	if (!cgrp) {
-		cgrp = zalloc(sizeof(*cgrp));
-		if (!cgrp)
-			return -1;
+	return cgrp;
+}
 
-		cgrp->name = str;
-		refcount_set(&cgrp->refcnt, 1);
+static struct cgroup *cgroup__new(const char *name)
+{
+	struct cgroup *cgroup = zalloc(sizeof(*cgroup));
 
-		cgrp->fd = open_cgroup(str);
-		if (cgrp->fd == -1) {
-			free(cgrp);
-			return -1;
-		}
+	if (cgroup != NULL) {
+		refcount_set(&cgroup->refcnt, 1);
+
+		cgroup->name = strdup(name);
+		if (!cgroup->name)
+			goto out_err;
+		cgroup->fd = open_cgroup(name);
+		if (cgroup->fd == -1)
+			goto out_free_name;
 	}
 
+	return cgroup;
+
+out_free_name:
+	free(cgroup->name);
+out_err:
+	free(cgroup);
+	return NULL;
+}
+
+struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, const char *name)
+{
+	struct cgroup *cgroup = evlist__find_cgroup(evlist, name);
+
+	return cgroup ?: cgroup__new(name);
+}
+
+static int add_cgroup(struct perf_evlist *evlist, const char *str)
+{
+	struct perf_evsel *counter;
+	struct cgroup *cgrp = evlist__findnew_cgroup(evlist, str);
+	int n;
+
+	if (!cgrp)
+		return -1;
 	/*
 	 * find corresponding event
 	 * if add cgroup N, then need to find event N
@@ -135,31 +158,58 @@ static int add_cgroup(struct perf_evlist *evlist, char *str)
 			goto found;
 		n++;
 	}
-	if (refcount_dec_and_test(&cgrp->refcnt))
-		free(cgrp);
 
+	cgroup__put(cgrp);
 	return -1;
 found:
 	counter->cgrp = cgrp;
 	return 0;
 }
 
-void close_cgroup(struct cgroup_sel *cgrp)
+static void cgroup__delete(struct cgroup *cgroup)
+{
+	close(cgroup->fd);
+	zfree(&cgroup->name);
+	free(cgroup);
+}
+
+void cgroup__put(struct cgroup *cgrp)
 {
 	if (cgrp && refcount_dec_and_test(&cgrp->refcnt)) {
-		close(cgrp->fd);
-		zfree(&cgrp->name);
-		free(cgrp);
+		cgroup__delete(cgrp);
 	}
 }
 
-int parse_cgroups(const struct option *opt __maybe_unused, const char *str,
+struct cgroup *cgroup__get(struct cgroup *cgroup)
+{
+       if (cgroup)
+		refcount_inc(&cgroup->refcnt);
+       return cgroup;
+}
+
+static void evsel__set_default_cgroup(struct perf_evsel *evsel, struct cgroup *cgroup)
+{
+	if (evsel->cgrp == NULL)
+		evsel->cgrp = cgroup__get(cgroup);
+}
+
+void evlist__set_default_cgroup(struct perf_evlist *evlist, struct cgroup *cgroup)
+{
+	struct perf_evsel *evsel;
+
+	evlist__for_each_entry(evlist, evsel)
+		evsel__set_default_cgroup(evsel, cgroup);
+}
+
+int parse_cgroups(const struct option *opt, const char *str,
 		  int unset __maybe_unused)
 {
 	struct perf_evlist *evlist = *(struct perf_evlist **)opt->value;
+	struct perf_evsel *counter;
+	struct cgroup *cgrp = NULL;
 	const char *p, *e, *eos = str + strlen(str);
 	char *s;
-	int ret;
+	int ret, i;
 
 	if (list_empty(&evlist->entries)) {
 		fprintf(stderr, "must define events before cgroups\n");
@@ -177,10 +227,9 @@ int parse_cgroups(const struct option *opt __maybe_unused, const char *str,
 			if (!s)
 				return -1;
 			ret = add_cgroup(evlist, s);
-			if (ret) {
-				free(s);
+			free(s);
+			if (ret)
 				return -1;
-			}
 		}
 		/* nr_cgroups is increased een for empty cgroups */
 		nr_cgroups++;
@@ -188,5 +237,18 @@ int parse_cgroups(const struct option *opt __maybe_unused, const char *str,
 			break;
 		str = p+1;
 	}
+	/* for the case one cgroup combine to multiple events */
+	i = 0;
+	if (nr_cgroups == 1) {
+		evlist__for_each_entry(evlist, counter) {
+			if (i == 0)
+				cgrp = counter->cgrp;
+			else {
+				counter->cgrp = cgrp;
+				refcount_inc(&cgrp->refcnt);
+			}
+			i++;
+		}
+	}
 	return 0;
 }
diff --git a/tools/perf/util/cgroup.h b/tools/perf/util/cgroup.h
index afafc87e9201..f033a80c1b14 100644
--- a/tools/perf/util/cgroup.h
+++ b/tools/perf/util/cgroup.h
@@ -6,7 +6,7 @@
 
 struct option;
 
-struct cgroup_sel {
+struct cgroup {
 	char *name;
 	int fd;
 	refcount_t refcnt;
@@ -14,7 +14,16 @@ struct cgroup_sel {
 
 
 extern int nr_cgroups; /* number of explicit cgroups defined */
-void close_cgroup(struct cgroup_sel *cgrp);
+
+struct cgroup *cgroup__get(struct cgroup *cgroup);
+void cgroup__put(struct cgroup *cgroup);
+
+struct perf_evlist;
+
+struct cgroup *evlist__findnew_cgroup(struct perf_evlist *evlist, const char *name);
+
+void evlist__set_default_cgroup(struct perf_evlist *evlist, struct cgroup *cgroup);
+
 int parse_cgroups(const struct option *opt, const char *str, int unset);
 
 #endif /* __CGROUP_H__ */
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
index 1fb01849f1c7..640af88331b4 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.c
@@ -78,6 +78,8 @@ int cs_etm_decoder__reset(struct cs_etm_decoder *decoder)
 {
 	ocsd_datapath_resp_t dp_ret;
 
+	decoder->prev_return = OCSD_RESP_CONT;
+
 	dp_ret = ocsd_dt_process_data(decoder->dcd_tree, OCSD_OP_RESET,
 				      0, 0, NULL, NULL);
 	if (OCSD_DATA_RESP_IS_FATAL(dp_ret))
@@ -253,16 +255,16 @@ static void cs_etm_decoder__clear_buffer(struct cs_etm_decoder *decoder)
 	decoder->packet_count = 0;
 	for (i = 0; i < MAX_BUFFER; i++) {
 		decoder->packet_buffer[i].start_addr = 0xdeadbeefdeadbeefUL;
-		decoder->packet_buffer[i].end_addr   = 0xdeadbeefdeadbeefUL;
-		decoder->packet_buffer[i].exc	     = false;
-		decoder->packet_buffer[i].exc_ret    = false;
-		decoder->packet_buffer[i].cpu	     = INT_MIN;
+		decoder->packet_buffer[i].end_addr = 0xdeadbeefdeadbeefUL;
+		decoder->packet_buffer[i].last_instr_taken_branch = false;
+		decoder->packet_buffer[i].exc = false;
+		decoder->packet_buffer[i].exc_ret = false;
+		decoder->packet_buffer[i].cpu = INT_MIN;
 	}
 }
 
 static ocsd_datapath_resp_t
 cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
-			      const ocsd_generic_trace_elem *elem,
 			      const u8 trace_chan_id,
 			      enum cs_etm_sample_type sample_type)
 {
@@ -278,18 +280,16 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
 		return OCSD_RESP_FATAL_SYS_ERR;
 
 	et = decoder->tail;
+	et = (et + 1) & (MAX_BUFFER - 1);
+	decoder->tail = et;
+	decoder->packet_count++;
+
 	decoder->packet_buffer[et].sample_type = sample_type;
-	decoder->packet_buffer[et].start_addr = elem->st_addr;
-	decoder->packet_buffer[et].end_addr = elem->en_addr;
 	decoder->packet_buffer[et].exc = false;
 	decoder->packet_buffer[et].exc_ret = false;
 	decoder->packet_buffer[et].cpu = *((int *)inode->priv);
-
-	/* Wrap around if need be */
-	et = (et + 1) & (MAX_BUFFER - 1);
-
-	decoder->tail = et;
-	decoder->packet_count++;
+	decoder->packet_buffer[et].start_addr = 0xdeadbeefdeadbeefUL;
+	decoder->packet_buffer[et].end_addr = 0xdeadbeefdeadbeefUL;
 
 	if (decoder->packet_count == MAX_BUFFER - 1)
 		return OCSD_RESP_WAIT;
@@ -297,6 +297,47 @@ cs_etm_decoder__buffer_packet(struct cs_etm_decoder *decoder,
 	return OCSD_RESP_CONT;
 }
 
+static ocsd_datapath_resp_t
+cs_etm_decoder__buffer_range(struct cs_etm_decoder *decoder,
+			     const ocsd_generic_trace_elem *elem,
+			     const uint8_t trace_chan_id)
+{
+	int ret = 0;
+	struct cs_etm_packet *packet;
+
+	ret = cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
+					    CS_ETM_RANGE);
+	if (ret != OCSD_RESP_CONT && ret != OCSD_RESP_WAIT)
+		return ret;
+
+	packet = &decoder->packet_buffer[decoder->tail];
+
+	packet->start_addr = elem->st_addr;
+	packet->end_addr = elem->en_addr;
+	switch (elem->last_i_type) {
+	case OCSD_INSTR_BR:
+	case OCSD_INSTR_BR_INDIRECT:
+		packet->last_instr_taken_branch = elem->last_instr_exec;
+		break;
+	case OCSD_INSTR_ISB:
+	case OCSD_INSTR_DSB_DMB:
+	case OCSD_INSTR_OTHER:
+	default:
+		packet->last_instr_taken_branch = false;
+		break;
+	}
+
+	return ret;
+}
+
+static ocsd_datapath_resp_t
+cs_etm_decoder__buffer_trace_on(struct cs_etm_decoder *decoder,
+				const uint8_t trace_chan_id)
+{
+	return cs_etm_decoder__buffer_packet(decoder, trace_chan_id,
+					     CS_ETM_TRACE_ON);
+}
+
 static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
 				const void *context,
 				const ocsd_trc_index_t indx __maybe_unused,
@@ -313,12 +354,13 @@ static ocsd_datapath_resp_t cs_etm_decoder__gen_trace_elem_printer(
 		decoder->trace_on = false;
 		break;
 	case OCSD_GEN_TRC_ELEM_TRACE_ON:
+		resp = cs_etm_decoder__buffer_trace_on(decoder,
+						       trace_chan_id);
 		decoder->trace_on = true;
 		break;
 	case OCSD_GEN_TRC_ELEM_INSTR_RANGE:
-		resp = cs_etm_decoder__buffer_packet(decoder, elem,
-						     trace_chan_id,
-						     CS_ETM_RANGE);
+		resp = cs_etm_decoder__buffer_range(decoder, elem,
+						    trace_chan_id);
 		break;
 	case OCSD_GEN_TRC_ELEM_EXCEPTION:
 		decoder->packet_buffer[decoder->tail].exc = true;
diff --git a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
index 3d2e6205d186..743f5f444304 100644
--- a/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
+++ b/tools/perf/util/cs-etm-decoder/cs-etm-decoder.h
@@ -24,12 +24,14 @@ struct cs_etm_buffer {
 
 enum cs_etm_sample_type {
 	CS_ETM_RANGE = 1 << 0,
+	CS_ETM_TRACE_ON = 1 << 1,
 };
 
 struct cs_etm_packet {
 	enum cs_etm_sample_type sample_type;
 	u64 start_addr;
 	u64 end_addr;
+	u8 last_instr_taken_branch;
 	u8 exc;
 	u8 exc_ret;
 	int cpu;
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index b9f0a53dfa65..1b0d422373be 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -32,6 +32,14 @@
 
 #define MAX_TIMESTAMP (~0ULL)
 
+/*
+ * A64 instructions are always 4 bytes
+ *
+ * Only A64 is supported, so can use this constant for converting between
+ * addresses and instruction counts, calculting offsets etc
+ */
+#define A64_INSTR_SIZE 4
+
 struct cs_etm_auxtrace {
 	struct auxtrace auxtrace;
 	struct auxtrace_queues queues;
@@ -45,11 +53,15 @@ struct cs_etm_auxtrace {
 	u8 snapshot_mode;
 	u8 data_queued;
 	u8 sample_branches;
+	u8 sample_instructions;
 
 	int num_cpu;
 	u32 auxtrace_type;
 	u64 branches_sample_type;
 	u64 branches_id;
+	u64 instructions_sample_type;
+	u64 instructions_sample_period;
+	u64 instructions_id;
 	u64 **metadata;
 	u64 kernel_start;
 	unsigned int pmu_type;
@@ -68,6 +80,12 @@ struct cs_etm_queue {
 	u64 time;
 	u64 timestamp;
 	u64 offset;
+	u64 period_instructions;
+	struct branch_stack *last_branch;
+	struct branch_stack *last_branch_rb;
+	size_t last_branch_pos;
+	struct cs_etm_packet *prev_packet;
+	struct cs_etm_packet *packet;
 };
 
 static int cs_etm__update_queues(struct cs_etm_auxtrace *etm);
@@ -174,6 +192,16 @@ static void cs_etm__free_queue(void *priv)
 {
 	struct cs_etm_queue *etmq = priv;
 
+	if (!etmq)
+		return;
+
+	thread__zput(etmq->thread);
+	cs_etm_decoder__free(etmq->decoder);
+	zfree(&etmq->event_buf);
+	zfree(&etmq->last_branch);
+	zfree(&etmq->last_branch_rb);
+	zfree(&etmq->prev_packet);
+	zfree(&etmq->packet);
 	free(etmq);
 }
 
@@ -270,11 +298,35 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
 	struct cs_etm_decoder_params d_params;
 	struct cs_etm_trace_params  *t_params;
 	struct cs_etm_queue *etmq;
+	size_t szp = sizeof(struct cs_etm_packet);
 
 	etmq = zalloc(sizeof(*etmq));
 	if (!etmq)
 		return NULL;
 
+	etmq->packet = zalloc(szp);
+	if (!etmq->packet)
+		goto out_free;
+
+	if (etm->synth_opts.last_branch || etm->sample_branches) {
+		etmq->prev_packet = zalloc(szp);
+		if (!etmq->prev_packet)
+			goto out_free;
+	}
+
+	if (etm->synth_opts.last_branch) {
+		size_t sz = sizeof(struct branch_stack);
+
+		sz += etm->synth_opts.last_branch_sz *
+		      sizeof(struct branch_entry);
+		etmq->last_branch = zalloc(sz);
+		if (!etmq->last_branch)
+			goto out_free;
+		etmq->last_branch_rb = zalloc(sz);
+		if (!etmq->last_branch_rb)
+			goto out_free;
+	}
+
 	etmq->event_buf = malloc(PERF_SAMPLE_MAX_SIZE);
 	if (!etmq->event_buf)
 		goto out_free;
@@ -329,6 +381,7 @@ static struct cs_etm_queue *cs_etm__alloc_queue(struct cs_etm_auxtrace *etm,
 		goto out_free_decoder;
 
 	etmq->offset = 0;
+	etmq->period_instructions = 0;
 
 	return etmq;
 
@@ -336,6 +389,10 @@ out_free_decoder:
 	cs_etm_decoder__free(etmq->decoder);
 out_free:
 	zfree(&etmq->event_buf);
+	zfree(&etmq->last_branch);
+	zfree(&etmq->last_branch_rb);
+	zfree(&etmq->prev_packet);
+	zfree(&etmq->packet);
 	free(etmq);
 
 	return NULL;
@@ -389,6 +446,129 @@ static int cs_etm__update_queues(struct cs_etm_auxtrace *etm)
 	return 0;
 }
 
+static inline void cs_etm__copy_last_branch_rb(struct cs_etm_queue *etmq)
+{
+	struct branch_stack *bs_src = etmq->last_branch_rb;
+	struct branch_stack *bs_dst = etmq->last_branch;
+	size_t nr = 0;
+
+	/*
+	 * Set the number of records before early exit: ->nr is used to
+	 * determine how many branches to copy from ->entries.
+	 */
+	bs_dst->nr = bs_src->nr;
+
+	/*
+	 * Early exit when there is nothing to copy.
+	 */
+	if (!bs_src->nr)
+		return;
+
+	/*
+	 * As bs_src->entries is a circular buffer, we need to copy from it in
+	 * two steps.  First, copy the branches from the most recently inserted
+	 * branch ->last_branch_pos until the end of bs_src->entries buffer.
+	 */
+	nr = etmq->etm->synth_opts.last_branch_sz - etmq->last_branch_pos;
+	memcpy(&bs_dst->entries[0],
+	       &bs_src->entries[etmq->last_branch_pos],
+	       sizeof(struct branch_entry) * nr);
+
+	/*
+	 * If we wrapped around at least once, the branches from the beginning
+	 * of the bs_src->entries buffer and until the ->last_branch_pos element
+	 * are older valid branches: copy them over.  The total number of
+	 * branches copied over will be equal to the number of branches asked by
+	 * the user in last_branch_sz.
+	 */
+	if (bs_src->nr >= etmq->etm->synth_opts.last_branch_sz) {
+		memcpy(&bs_dst->entries[nr],
+		       &bs_src->entries[0],
+		       sizeof(struct branch_entry) * etmq->last_branch_pos);
+	}
+}
+
+static inline void cs_etm__reset_last_branch_rb(struct cs_etm_queue *etmq)
+{
+	etmq->last_branch_pos = 0;
+	etmq->last_branch_rb->nr = 0;
+}
+
+static inline u64 cs_etm__last_executed_instr(struct cs_etm_packet *packet)
+{
+	/*
+	 * The packet records the execution range with an exclusive end address
+	 *
+	 * A64 instructions are constant size, so the last executed
+	 * instruction is A64_INSTR_SIZE before the end address
+	 * Will need to do instruction level decode for T32 instructions as
+	 * they can be variable size (not yet supported).
+	 */
+	return packet->end_addr - A64_INSTR_SIZE;
+}
+
+static inline u64 cs_etm__instr_count(const struct cs_etm_packet *packet)
+{
+	/*
+	 * Only A64 instructions are currently supported, so can get
+	 * instruction count by dividing.
+	 * Will need to do instruction level decode for T32 instructions as
+	 * they can be variable size (not yet supported).
+	 */
+	return (packet->end_addr - packet->start_addr) / A64_INSTR_SIZE;
+}
+
+static inline u64 cs_etm__instr_addr(const struct cs_etm_packet *packet,
+				     u64 offset)
+{
+	/*
+	 * Only A64 instructions are currently supported, so can get
+	 * instruction address by muliplying.
+	 * Will need to do instruction level decode for T32 instructions as
+	 * they can be variable size (not yet supported).
+	 */
+	return packet->start_addr + offset * A64_INSTR_SIZE;
+}
+
+static void cs_etm__update_last_branch_rb(struct cs_etm_queue *etmq)
+{
+	struct branch_stack *bs = etmq->last_branch_rb;
+	struct branch_entry *be;
+
+	/*
+	 * The branches are recorded in a circular buffer in reverse
+	 * chronological order: we start recording from the last element of the
+	 * buffer down.  After writing the first element of the stack, move the
+	 * insert position back to the end of the buffer.
+	 */
+	if (!etmq->last_branch_pos)
+		etmq->last_branch_pos = etmq->etm->synth_opts.last_branch_sz;
+
+	etmq->last_branch_pos -= 1;
+
+	be       = &bs->entries[etmq->last_branch_pos];
+	be->from = cs_etm__last_executed_instr(etmq->prev_packet);
+	be->to	 = etmq->packet->start_addr;
+	/* No support for mispredict */
+	be->flags.mispred = 0;
+	be->flags.predicted = 1;
+
+	/*
+	 * Increment bs->nr until reaching the number of last branches asked by
+	 * the user on the command line.
+	 */
+	if (bs->nr < etmq->etm->synth_opts.last_branch_sz)
+		bs->nr += 1;
+}
+
+static int cs_etm__inject_event(union perf_event *event,
+			       struct perf_sample *sample, u64 type)
+{
+	event->header.size = perf_event__sample_event_size(sample, type, 0);
+	return perf_event__synthesize_sample(event, type, 0, sample);
+}
+
+
 static int
 cs_etm__get_trace(struct cs_etm_buffer *buff, struct cs_etm_queue *etmq)
 {
@@ -453,35 +633,105 @@ static void  cs_etm__set_pid_tid_cpu(struct cs_etm_auxtrace *etm,
 	}
 }
 
+static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
+					    u64 addr, u64 period)
+{
+	int ret = 0;
+	struct cs_etm_auxtrace *etm = etmq->etm;
+	union perf_event *event = etmq->event_buf;
+	struct perf_sample sample = {.ip = 0,};
+
+	event->sample.header.type = PERF_RECORD_SAMPLE;
+	event->sample.header.misc = PERF_RECORD_MISC_USER;
+	event->sample.header.size = sizeof(struct perf_event_header);
+
+	sample.ip = addr;
+	sample.pid = etmq->pid;
+	sample.tid = etmq->tid;
+	sample.id = etmq->etm->instructions_id;
+	sample.stream_id = etmq->etm->instructions_id;
+	sample.period = period;
+	sample.cpu = etmq->packet->cpu;
+	sample.flags = 0;
+	sample.insn_len = 1;
+	sample.cpumode = event->header.misc;
+
+	if (etm->synth_opts.last_branch) {
+		cs_etm__copy_last_branch_rb(etmq);
+		sample.branch_stack = etmq->last_branch;
+	}
+
+	if (etm->synth_opts.inject) {
+		ret = cs_etm__inject_event(event, &sample,
+					   etm->instructions_sample_type);
+		if (ret)
+			return ret;
+	}
+
+	ret = perf_session__deliver_synth_event(etm->session, event, &sample);
+
+	if (ret)
+		pr_err(
+			"CS ETM Trace: failed to deliver instruction event, error %d\n",
+			ret);
+
+	if (etm->synth_opts.last_branch)
+		cs_etm__reset_last_branch_rb(etmq);
+
+	return ret;
+}
+
 /*
  * The cs etm packet encodes an instruction range between a branch target
  * and the next taken branch. Generate sample accordingly.
  */
-static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq,
-				       struct cs_etm_packet *packet)
+static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
 {
 	int ret = 0;
 	struct cs_etm_auxtrace *etm = etmq->etm;
 	struct perf_sample sample = {.ip = 0,};
 	union perf_event *event = etmq->event_buf;
-	u64 start_addr = packet->start_addr;
-	u64 end_addr = packet->end_addr;
+	struct dummy_branch_stack {
+		u64			nr;
+		struct branch_entry	entries;
+	} dummy_bs;
 
 	event->sample.header.type = PERF_RECORD_SAMPLE;
 	event->sample.header.misc = PERF_RECORD_MISC_USER;
 	event->sample.header.size = sizeof(struct perf_event_header);
 
-	sample.ip = start_addr;
+	sample.ip = cs_etm__last_executed_instr(etmq->prev_packet);
 	sample.pid = etmq->pid;
 	sample.tid = etmq->tid;
-	sample.addr = end_addr;
+	sample.addr = etmq->packet->start_addr;
 	sample.id = etmq->etm->branches_id;
 	sample.stream_id = etmq->etm->branches_id;
 	sample.period = 1;
-	sample.cpu = packet->cpu;
+	sample.cpu = etmq->packet->cpu;
 	sample.flags = 0;
 	sample.cpumode = PERF_RECORD_MISC_USER;
 
+	/*
+	 * perf report cannot handle events without a branch stack
+	 */
+	if (etm->synth_opts.last_branch) {
+		dummy_bs = (struct dummy_branch_stack){
+			.nr = 1,
+			.entries = {
+				.from = sample.ip,
+				.to = sample.addr,
+			},
+		};
+		sample.branch_stack = (struct branch_stack *)&dummy_bs;
+	}
+
+	if (etm->synth_opts.inject) {
+		ret = cs_etm__inject_event(event, &sample,
+					   etm->branches_sample_type);
+		if (ret)
+			return ret;
+	}
+
 	ret = perf_session__deliver_synth_event(etm->session, event, &sample);
 
 	if (ret)
@@ -578,6 +828,24 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm,
 		etm->sample_branches = true;
 		etm->branches_sample_type = attr.sample_type;
 		etm->branches_id = id;
+		id += 1;
+		attr.sample_type &= ~(u64)PERF_SAMPLE_ADDR;
+	}
+
+	if (etm->synth_opts.last_branch)
+		attr.sample_type |= PERF_SAMPLE_BRANCH_STACK;
+
+	if (etm->synth_opts.instructions) {
+		attr.config = PERF_COUNT_HW_INSTRUCTIONS;
+		attr.sample_period = etm->synth_opts.period;
+		etm->instructions_sample_period = attr.sample_period;
+		err = cs_etm__synth_event(session, &attr, id);
+		if (err)
+			return err;
+		etm->sample_instructions = true;
+		etm->instructions_sample_type = attr.sample_type;
+		etm->instructions_id = id;
+		id += 1;
 	}
 
 	return 0;
@@ -585,25 +853,108 @@ static int cs_etm__synth_events(struct cs_etm_auxtrace *etm,
 
 static int cs_etm__sample(struct cs_etm_queue *etmq)
 {
+	struct cs_etm_auxtrace *etm = etmq->etm;
+	struct cs_etm_packet *tmp;
 	int ret;
-	struct cs_etm_packet packet;
+	u64 instrs_executed;
 
-	while (1) {
-		ret = cs_etm_decoder__get_packet(etmq->decoder, &packet);
-		if (ret <= 0)
+	instrs_executed = cs_etm__instr_count(etmq->packet);
+	etmq->period_instructions += instrs_executed;
+
+	/*
+	 * Record a branch when the last instruction in
+	 * PREV_PACKET is a branch.
+	 */
+	if (etm->synth_opts.last_branch &&
+	    etmq->prev_packet &&
+	    etmq->prev_packet->sample_type == CS_ETM_RANGE &&
+	    etmq->prev_packet->last_instr_taken_branch)
+		cs_etm__update_last_branch_rb(etmq);
+
+	if (etm->sample_instructions &&
+	    etmq->period_instructions >= etm->instructions_sample_period) {
+		/*
+		 * Emit instruction sample periodically
+		 * TODO: allow period to be defined in cycles and clock time
+		 */
+
+		/* Get number of instructions executed after the sample point */
+		u64 instrs_over = etmq->period_instructions -
+			etm->instructions_sample_period;
+
+		/*
+		 * Calculate the address of the sampled instruction (-1 as
+		 * sample is reported as though instruction has just been
+		 * executed, but PC has not advanced to next instruction)
+		 */
+		u64 offset = (instrs_executed - instrs_over - 1);
+		u64 addr = cs_etm__instr_addr(etmq->packet, offset);
+
+		ret = cs_etm__synth_instruction_sample(
+			etmq, addr, etm->instructions_sample_period);
+		if (ret)
+			return ret;
+
+		/* Carry remaining instructions into next sample period */
+		etmq->period_instructions = instrs_over;
+	}
+
+	if (etm->sample_branches &&
+	    etmq->prev_packet &&
+	    etmq->prev_packet->sample_type == CS_ETM_RANGE &&
+	    etmq->prev_packet->last_instr_taken_branch) {
+		ret = cs_etm__synth_branch_sample(etmq);
+		if (ret)
 			return ret;
+	}
 
+	if (etm->sample_branches || etm->synth_opts.last_branch) {
 		/*
-		 * If the packet contains an instruction range, generate an
-		 * instruction sequence event.
+		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
+		 * the next incoming packet.
 		 */
-		if (packet.sample_type & CS_ETM_RANGE)
-			cs_etm__synth_branch_sample(etmq, &packet);
+		tmp = etmq->packet;
+		etmq->packet = etmq->prev_packet;
+		etmq->prev_packet = tmp;
 	}
 
 	return 0;
 }
 
+static int cs_etm__flush(struct cs_etm_queue *etmq)
+{
+	int err = 0;
+	struct cs_etm_packet *tmp;
+
+	if (etmq->etm->synth_opts.last_branch &&
+	    etmq->prev_packet &&
+	    etmq->prev_packet->sample_type == CS_ETM_RANGE) {
+		/*
+		 * Generate a last branch event for the branches left in the
+		 * circular buffer at the end of the trace.
+		 *
+		 * Use the address of the end of the last reported execution
+		 * range
+		 */
+		u64 addr = cs_etm__last_executed_instr(etmq->prev_packet);
+
+		err = cs_etm__synth_instruction_sample(
+			etmq, addr,
+			etmq->period_instructions);
+		etmq->period_instructions = 0;
+
+		/*
+		 * Swap PACKET with PREV_PACKET: PACKET becomes PREV_PACKET for
+		 * the next incoming packet.
+		 */
+		tmp = etmq->packet;
+		etmq->packet = etmq->prev_packet;
+		etmq->prev_packet = tmp;
+	}
+
+	return err;
+}
+
 static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
 {
 	struct cs_etm_auxtrace *etm = etmq->etm;
@@ -615,45 +966,72 @@ static int cs_etm__run_decoder(struct cs_etm_queue *etmq)
 		etm->kernel_start = machine__kernel_start(etm->machine);
 
 	/* Go through each buffer in the queue and decode them one by one */
-more:
-	buffer_used = 0;
-	memset(&buffer, 0, sizeof(buffer));
-	err = cs_etm__get_trace(&buffer, etmq);
-	if (err <= 0)
-		return err;
-	/*
-	 * We cannot assume consecutive blocks in the data file are contiguous,
-	 * reset the decoder to force re-sync.
-	 */
-	err = cs_etm_decoder__reset(etmq->decoder);
-	if (err != 0)
-		return err;
-
-	/* Run trace decoder until buffer consumed or end of trace */
-	do {
-		processed = 0;
-
-		err = cs_etm_decoder__process_data_block(
-						etmq->decoder,
-						etmq->offset,
-						&buffer.buf[buffer_used],
-						buffer.len - buffer_used,
-						&processed);
-
-		if (err)
+	while (1) {
+		buffer_used = 0;
+		memset(&buffer, 0, sizeof(buffer));
+		err = cs_etm__get_trace(&buffer, etmq);
+		if (err <= 0)
 			return err;
-
-		etmq->offset += processed;
-		buffer_used += processed;
-
 		/*
-		 * Nothing to do with an error condition, let's hope the next
-		 * chunk will be better.
+		 * We cannot assume consecutive blocks in the data file are
+		 * contiguous, reset the decoder to force re-sync.
 		 */
-		err = cs_etm__sample(etmq);
-	} while (buffer.len > buffer_used);
+		err = cs_etm_decoder__reset(etmq->decoder);
+		if (err != 0)
+			return err;
+
+		/* Run trace decoder until buffer consumed or end of trace */
+		do {
+			processed = 0;
+			err = cs_etm_decoder__process_data_block(
+				etmq->decoder,
+				etmq->offset,
+				&buffer.buf[buffer_used],
+				buffer.len - buffer_used,
+				&processed);
+			if (err)
+				return err;
+
+			etmq->offset += processed;
+			buffer_used += processed;
+
+			/* Process each packet in this chunk */
+			while (1) {
+				err = cs_etm_decoder__get_packet(etmq->decoder,
+								 etmq->packet);
+				if (err <= 0)
+					/*
+					 * Stop processing this chunk on
+					 * end of data or error
+					 */
+					break;
+
+				switch (etmq->packet->sample_type) {
+				case CS_ETM_RANGE:
+					/*
+					 * If the packet contains an instruction
+					 * range, generate instruction sequence
+					 * events.
+					 */
+					cs_etm__sample(etmq);
+					break;
+				case CS_ETM_TRACE_ON:
+					/*
+					 * Discontinuity in trace, flush
+					 * previous branch stack
+					 */
+					cs_etm__flush(etmq);
+					break;
+				default:
+					break;
+				}
+			}
+		} while (buffer.len > buffer_used);
 
-goto more;
+		if (err == 0)
+			/* Flush any remaining branch stack entries */
+			err = cs_etm__flush(etmq);
+	}
 
 	return err;
 }
diff --git a/tools/perf/util/debug.c b/tools/perf/util/debug.c
index f3a71db83947..3d6459626c2a 100644
--- a/tools/perf/util/debug.c
+++ b/tools/perf/util/debug.c
@@ -232,7 +232,6 @@ int perf_quiet_option(void)
 		var++;
 	}
 
-	quiet = true;
 	return 0;
 }
 
diff --git a/tools/perf/util/env.c b/tools/perf/util/env.c
index 6d311868d850..4c842762e3f2 100644
--- a/tools/perf/util/env.c
+++ b/tools/perf/util/env.c
@@ -32,6 +32,10 @@ void perf_env__exit(struct perf_env *env)
 	for (i = 0; i < env->caches_cnt; i++)
 		cpu_cache_level__free(&env->caches[i]);
 	zfree(&env->caches);
+
+	for (i = 0; i < env->nr_memory_nodes; i++)
+		free(env->memory_nodes[i].set);
+	zfree(&env->memory_nodes);
 }
 
 int perf_env__set_cmdline(struct perf_env *env, int argc, const char *argv[])
diff --git a/tools/perf/util/env.h b/tools/perf/util/env.h
index bf970f57dce0..c4ef2e523367 100644
--- a/tools/perf/util/env.h
+++ b/tools/perf/util/env.h
@@ -27,6 +27,12 @@ struct numa_node {
 	struct cpu_map	*map;
 };
 
+struct memory_node {
+	u64		 node;
+	u64		 size;
+	unsigned long	*set;
+};
+
 struct perf_env {
 	char			*hostname;
 	char			*os_release;
@@ -43,6 +49,7 @@ struct perf_env {
 	int			nr_sibling_cores;
 	int			nr_sibling_threads;
 	int			nr_numa_nodes;
+	int			nr_memory_nodes;
 	int			nr_pmu_mappings;
 	int			nr_groups;
 	char			*cmdline;
@@ -54,6 +61,8 @@ struct perf_env {
 	struct cpu_cache_level	*caches;
 	int			 caches_cnt;
 	struct numa_node	*numa_nodes;
+	struct memory_node	*memory_nodes;
+	unsigned long long	 memory_bsize;
 };
 
 extern struct perf_env perf_env;
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 44e603c27944..f0a6cbd033cc 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -894,8 +894,6 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 				       struct machine *machine)
 {
 	size_t size;
-	const char *mmap_name;
-	char name_buff[PATH_MAX];
 	struct map *map = machine__kernel_map(machine);
 	struct kmap *kmap;
 	int err;
@@ -918,7 +916,6 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 		return -1;
 	}
 
-	mmap_name = machine__mmap_name(machine, name_buff, sizeof(name_buff));
 	if (machine__is_host(machine)) {
 		/*
 		 * kernel uses PERF_RECORD_MISC_USER for user space maps,
@@ -931,7 +928,7 @@ int perf_event__synthesize_kernel_mmap(struct perf_tool *tool,
 
 	kmap = map__kmap(map);
 	size = snprintf(event->mmap.filename, sizeof(event->mmap.filename),
-			"%s%s", mmap_name, kmap->ref_reloc_sym->name) + 1;
+			"%s%s", machine->mmap_name, kmap->ref_reloc_sym->name) + 1;
 	size = PERF_ALIGN(size, sizeof(u64));
 	event->mmap.header.type = PERF_RECORD_MMAP;
 	event->mmap.header.size = (sizeof(event->mmap) -
@@ -1591,17 +1588,6 @@ int machine__resolve(struct machine *machine, struct addr_location *al,
 		return -1;
 
 	dump_printf(" ... thread: %s:%d\n", thread__comm_str(thread), thread->tid);
-	/*
-	 * Have we already created the kernel maps for this machine?
-	 *
-	 * This should have happened earlier, when we processed the kernel MMAP
-	 * events, but for older perf.data files there was no such thing, so do
-	 * it now.
-	 */
-	if (sample->cpumode == PERF_RECORD_MISC_KERNEL &&
-	    machine__kernel_map(machine) == NULL)
-		machine__create_kernel_maps(machine);
-
 	thread__find_addr_map(thread, sample->cpumode, MAP__FUNCTION, sample->ip, al);
 	dump_printf(" ...... dso: %s\n",
 		    al->map ? al->map->dso->long_name :
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index e5fc14e53c05..a59281d64368 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -702,29 +702,6 @@ static int perf_evlist__resume(struct perf_evlist *evlist)
 	return perf_evlist__set_paused(evlist, false);
 }
 
-union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist, int idx)
-{
-	struct perf_mmap *md = &evlist->mmap[idx];
-
-	/*
-	 * Check messup is required for forward overwritable ring buffer:
-	 * memory pointed by md->prev can be overwritten in this case.
-	 * No need for read-write ring buffer: kernel stop outputting when
-	 * it hit md->prev (perf_mmap__consume()).
-	 */
-	return perf_mmap__read_forward(md);
-}
-
-union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
-{
-	return perf_evlist__mmap_read_forward(evlist, idx);
-}
-
-void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
-{
-	perf_mmap__consume(&evlist->mmap[idx], false);
-}
-
 static void perf_evlist__munmap_nofree(struct perf_evlist *evlist)
 {
 	int i;
@@ -745,7 +722,8 @@ void perf_evlist__munmap(struct perf_evlist *evlist)
 	zfree(&evlist->overwrite_mmap);
 }
 
-static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist)
+static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist,
+						 bool overwrite)
 {
 	int i;
 	struct perf_mmap *map;
@@ -759,9 +737,10 @@ static struct perf_mmap *perf_evlist__alloc_mmap(struct perf_evlist *evlist)
 
 	for (i = 0; i < evlist->nr_mmaps; i++) {
 		map[i].fd = -1;
+		map[i].overwrite = overwrite;
 		/*
 		 * When the perf_mmap() call is made we grab one refcount, plus
-		 * one extra to let perf_evlist__mmap_consume() get the last
+		 * one extra to let perf_mmap__consume() get the last
 		 * events after all real references (perf_mmap__get()) are
 		 * dropped.
 		 *
@@ -802,7 +781,7 @@ static int perf_evlist__mmap_per_evsel(struct perf_evlist *evlist, int idx,
 			maps = evlist->overwrite_mmap;
 
 			if (!maps) {
-				maps = perf_evlist__alloc_mmap(evlist);
+				maps = perf_evlist__alloc_mmap(evlist, true);
 				if (!maps)
 					return -1;
 				evlist->overwrite_mmap = maps;
@@ -1052,7 +1031,7 @@ int perf_evlist__mmap_ex(struct perf_evlist *evlist, unsigned int pages,
 	struct mmap_params mp;
 
 	if (!evlist->mmap)
-		evlist->mmap = perf_evlist__alloc_mmap(evlist);
+		evlist->mmap = perf_evlist__alloc_mmap(evlist, false);
 	if (!evlist->mmap)
 		return -ENOMEM;
 
@@ -1086,11 +1065,30 @@ int perf_evlist__mmap(struct perf_evlist *evlist, unsigned int pages)
 
 int perf_evlist__create_maps(struct perf_evlist *evlist, struct target *target)
 {
+	bool all_threads = (target->per_thread && target->system_wide);
 	struct cpu_map *cpus;
 	struct thread_map *threads;
 
+	/*
+	 * If specify '-a' and '--per-thread' to perf record, perf record
+	 * will override '--per-thread'. target->per_thread = false and
+	 * target->system_wide = true.
+	 *
+	 * If specify '--per-thread' only to perf record,
+	 * target->per_thread = true and target->system_wide = false.
+	 *
+	 * So target->per_thread && target->system_wide is false.
+	 * For perf record, thread_map__new_str doesn't call
+	 * thread_map__new_all_cpus. That will keep perf record's
+	 * current behavior.
+	 *
+	 * For perf stat, it allows the case that target->per_thread and
+	 * target->system_wide are all true. It means to collect system-wide
+	 * per-thread data. thread_map__new_str will call
+	 * thread_map__new_all_cpus to enumerate all threads.
+	 */
 	threads = thread_map__new_str(target->pid, target->tid, target->uid,
-				      target->per_thread);
+				      all_threads);
 
 	if (!threads)
 		return -1;
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 336b838e6957..6c41b2f78713 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -129,10 +129,6 @@ struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id);
 
 void perf_evlist__toggle_bkw_mmap(struct perf_evlist *evlist, enum bkw_mmap_state state);
 
-union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx);
-
-union perf_event *perf_evlist__mmap_read_forward(struct perf_evlist *evlist,
-						 int idx);
 void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx);
 
 int perf_evlist__open(struct perf_evlist *evlist);
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index ef351688b797..1ac8d9236efd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -244,6 +244,7 @@ void perf_evsel__init(struct perf_evsel *evsel,
 	evsel->metric_name   = NULL;
 	evsel->metric_events = NULL;
 	evsel->collect_stat  = false;
+	evsel->pmu_name      = NULL;
 }
 
 struct perf_evsel *perf_evsel__new_idx(struct perf_event_attr *attr, int idx)
@@ -621,22 +622,34 @@ const char *perf_evsel__group_name(struct perf_evsel *evsel)
 	return evsel->group_name ?: "anon group";
 }
 
+/*
+ * Returns the group details for the specified leader,
+ * with following rules.
+ *
+ *  For record -e '{cycles,instructions}'
+ *    'anon group { cycles:u, instructions:u }'
+ *
+ *  For record -e 'cycles,instructions' and report --group
+ *    'cycles:u, instructions:u'
+ */
 int perf_evsel__group_desc(struct perf_evsel *evsel, char *buf, size_t size)
 {
-	int ret;
+	int ret = 0;
 	struct perf_evsel *pos;
 	const char *group_name = perf_evsel__group_name(evsel);
 
-	ret = scnprintf(buf, size, "%s", group_name);
+	if (!evsel->forced_leader)
+		ret = scnprintf(buf, size, "%s { ", group_name);
 
-	ret += scnprintf(buf + ret, size - ret, " { %s",
+	ret += scnprintf(buf + ret, size - ret, "%s",
 			 perf_evsel__name(evsel));
 
 	for_each_group_member(pos, evsel)
 		ret += scnprintf(buf + ret, size - ret, ", %s",
 				 perf_evsel__name(pos));
 
-	ret += scnprintf(buf + ret, size - ret, " }");
+	if (!evsel->forced_leader)
+		ret += scnprintf(buf + ret, size - ret, " }");
 
 	return ret;
 }
@@ -1233,7 +1246,7 @@ void perf_evsel__exit(struct perf_evsel *evsel)
 	perf_evsel__free_fd(evsel);
 	perf_evsel__free_id(evsel);
 	perf_evsel__free_config_terms(evsel);
-	close_cgroup(evsel->cgrp);
+	cgroup__put(evsel->cgrp);
 	cpu_map__put(evsel->cpus);
 	cpu_map__put(evsel->own_cpus);
 	thread_map__put(evsel->threads);
@@ -1915,6 +1928,9 @@ try_fallback:
 		goto fallback_missing_features;
 	}
 out_close:
+	if (err)
+		threads->err_thread = thread;
+
 	do {
 		while (--thread >= 0) {
 			close(FD(evsel, cpu, thread));
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index a7487c6d1866..d3ee3af618ef 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -30,7 +30,7 @@ struct perf_sample_id {
 	u64			period;
 };
 
-struct cgroup_sel;
+struct cgroup;
 
 /*
  * The 'struct perf_evsel_config_term' is used to pass event
@@ -107,7 +107,7 @@ struct perf_evsel {
 	struct perf_stat_evsel  *stats;
 	void			*priv;
 	u64			db_id;
-	struct cgroup_sel	*cgrp;
+	struct cgroup		*cgrp;
 	void			*handler;
 	struct cpu_map		*cpus;
 	struct cpu_map		*own_cpus;
@@ -125,6 +125,7 @@ struct perf_evsel {
 	bool			per_pkg;
 	bool			precise_max;
 	bool			ignore_missing_thread;
+	bool			forced_leader;
 	/* parse modifier helper */
 	int			exclude_GH;
 	int			nr_members;
@@ -142,6 +143,7 @@ struct perf_evsel {
 	struct perf_evsel	**metric_events;
 	bool			collect_stat;
 	bool			weak_group;
+	const char		*pmu_name;
 };
 
 union u64_swap {
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index a326e0d8b5b6..121df1683c36 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -17,6 +17,7 @@
 #include <sys/stat.h>
 #include <sys/utsname.h>
 #include <linux/time64.h>
+#include <dirent.h>
 
 #include "evlist.h"
 #include "evsel.h"
@@ -37,6 +38,7 @@
 #include "asm/bug.h"
 #include "tool.h"
 #include "time-utils.h"
+#include "units.h"
 
 #include "sane_ctype.h"
 
@@ -132,6 +134,25 @@ int do_write(struct feat_fd *ff, const void *buf, size_t size)
 }
 
 /* Return: 0 if succeded, -ERR if failed. */
+static int do_write_bitmap(struct feat_fd *ff, unsigned long *set, u64 size)
+{
+	u64 *p = (u64 *) set;
+	int i, ret;
+
+	ret = do_write(ff, &size, sizeof(size));
+	if (ret < 0)
+		return ret;
+
+	for (i = 0; (u64) i < BITS_TO_U64(size); i++) {
+		ret = do_write(ff, p + i, sizeof(*p));
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+/* Return: 0 if succeded, -ERR if failed. */
 int write_padded(struct feat_fd *ff, const void *bf,
 		 size_t count, size_t count_aligned)
 {
@@ -243,6 +264,38 @@ static char *do_read_string(struct feat_fd *ff)
 	return NULL;
 }
 
+/* Return: 0 if succeded, -ERR if failed. */
+static int do_read_bitmap(struct feat_fd *ff, unsigned long **pset, u64 *psize)
+{
+	unsigned long *set;
+	u64 size, *p;
+	int i, ret;
+
+	ret = do_read_u64(ff, &size);
+	if (ret)
+		return ret;
+
+	set = bitmap_alloc(size);
+	if (!set)
+		return -ENOMEM;
+
+	bitmap_zero(set, size);
+
+	p = (u64 *) set;
+
+	for (i = 0; (u64) i < BITS_TO_U64(size); i++) {
+		ret = do_read_u64(ff, p + i);
+		if (ret < 0) {
+			free(set);
+			return ret;
+		}
+	}
+
+	*pset  = set;
+	*psize = size;
+	return 0;
+}
+
 static int write_tracing_data(struct feat_fd *ff,
 			      struct perf_evlist *evlist)
 {
@@ -1196,6 +1249,176 @@ static int write_sample_time(struct feat_fd *ff,
 			sizeof(evlist->last_sample_time));
 }
 
+
+static int memory_node__read(struct memory_node *n, unsigned long idx)
+{
+	unsigned int phys, size = 0;
+	char path[PATH_MAX];
+	struct dirent *ent;
+	DIR *dir;
+
+#define for_each_memory(mem, dir)					\
+	while ((ent = readdir(dir)))					\
+		if (strcmp(ent->d_name, ".") &&				\
+		    strcmp(ent->d_name, "..") &&			\
+		    sscanf(ent->d_name, "memory%u", &mem) == 1)
+
+	scnprintf(path, PATH_MAX,
+		  "%s/devices/system/node/node%lu",
+		  sysfs__mountpoint(), idx);
+
+	dir = opendir(path);
+	if (!dir) {
+		pr_warning("failed: cant' open memory sysfs data\n");
+		return -1;
+	}
+
+	for_each_memory(phys, dir) {
+		size = max(phys, size);
+	}
+
+	size++;
+
+	n->set = bitmap_alloc(size);
+	if (!n->set) {
+		closedir(dir);
+		return -ENOMEM;
+	}
+
+	bitmap_zero(n->set, size);
+	n->node = idx;
+	n->size = size;
+
+	rewinddir(dir);
+
+	for_each_memory(phys, dir) {
+		set_bit(phys, n->set);
+	}
+
+	closedir(dir);
+	return 0;
+}
+
+static int memory_node__sort(const void *a, const void *b)
+{
+	const struct memory_node *na = a;
+	const struct memory_node *nb = b;
+
+	return na->node - nb->node;
+}
+
+static int build_mem_topology(struct memory_node *nodes, u64 size, u64 *cntp)
+{
+	char path[PATH_MAX];
+	struct dirent *ent;
+	DIR *dir;
+	u64 cnt = 0;
+	int ret = 0;
+
+	scnprintf(path, PATH_MAX, "%s/devices/system/node/",
+		  sysfs__mountpoint());
+
+	dir = opendir(path);
+	if (!dir) {
+		pr_warning("failed: can't open node sysfs data\n");
+		return -1;
+	}
+
+	while (!ret && (ent = readdir(dir))) {
+		unsigned int idx;
+		int r;
+
+		if (!strcmp(ent->d_name, ".") ||
+		    !strcmp(ent->d_name, ".."))
+			continue;
+
+		r = sscanf(ent->d_name, "node%u", &idx);
+		if (r != 1)
+			continue;
+
+		if (WARN_ONCE(cnt >= size,
+			      "failed to write MEM_TOPOLOGY, way too many nodes\n"))
+			return -1;
+
+		ret = memory_node__read(&nodes[cnt++], idx);
+	}
+
+	*cntp = cnt;
+	closedir(dir);
+
+	if (!ret)
+		qsort(nodes, cnt, sizeof(nodes[0]), memory_node__sort);
+
+	return ret;
+}
+
+#define MAX_MEMORY_NODES 2000
+
+/*
+ * The MEM_TOPOLOGY holds physical memory map for every
+ * node in system. The format of data is as follows:
+ *
+ *  0 - version          | for future changes
+ *  8 - block_size_bytes | /sys/devices/system/memory/block_size_bytes
+ * 16 - count            | number of nodes
+ *
+ * For each node we store map of physical indexes for
+ * each node:
+ *
+ * 32 - node id          | node index
+ * 40 - size             | size of bitmap
+ * 48 - bitmap           | bitmap of memory indexes that belongs to node
+ */
+static int write_mem_topology(struct feat_fd *ff __maybe_unused,
+			      struct perf_evlist *evlist __maybe_unused)
+{
+	static struct memory_node nodes[MAX_MEMORY_NODES];
+	u64 bsize, version = 1, i, nr;
+	int ret;
+
+	ret = sysfs__read_xll("devices/system/memory/block_size_bytes",
+			      (unsigned long long *) &bsize);
+	if (ret)
+		return ret;
+
+	ret = build_mem_topology(&nodes[0], MAX_MEMORY_NODES, &nr);
+	if (ret)
+		return ret;
+
+	ret = do_write(ff, &version, sizeof(version));
+	if (ret < 0)
+		goto out;
+
+	ret = do_write(ff, &bsize, sizeof(bsize));
+	if (ret < 0)
+		goto out;
+
+	ret = do_write(ff, &nr, sizeof(nr));
+	if (ret < 0)
+		goto out;
+
+	for (i = 0; i < nr; i++) {
+		struct memory_node *n = &nodes[i];
+
+		#define _W(v)						\
+			ret = do_write(ff, &n->v, sizeof(n->v));	\
+			if (ret < 0)					\
+				goto out;
+
+		_W(node)
+		_W(size)
+
+		#undef _W
+
+		ret = do_write_bitmap(ff, n->set, n->size);
+		if (ret < 0)
+			goto out;
+	}
+
+out:
+	return ret;
+}
+
 static void print_hostname(struct feat_fd *ff, FILE *fp)
 {
 	fprintf(fp, "# hostname : %s\n", ff->ph->env.hostname);
@@ -1543,6 +1766,35 @@ static void print_sample_time(struct feat_fd *ff, FILE *fp)
 	fprintf(fp, "# sample duration : %10.3f ms\n", d);
 }
 
+static void memory_node__fprintf(struct memory_node *n,
+				 unsigned long long bsize, FILE *fp)
+{
+	char buf_map[100], buf_size[50];
+	unsigned long long size;
+
+	size = bsize * bitmap_weight(n->set, n->size);
+	unit_number__scnprintf(buf_size, 50, size);
+
+	bitmap_scnprintf(n->set, n->size, buf_map, 100);
+	fprintf(fp, "#  %3" PRIu64 " [%s]: %s\n", n->node, buf_size, buf_map);
+}
+
+static void print_mem_topology(struct feat_fd *ff, FILE *fp)
+{
+	struct memory_node *nodes;
+	int i, nr;
+
+	nodes = ff->ph->env.memory_nodes;
+	nr    = ff->ph->env.nr_memory_nodes;
+
+	fprintf(fp, "# memory nodes (nr %d, block size 0x%llx):\n",
+		nr, ff->ph->env.memory_bsize);
+
+	for (i = 0; i < nr; i++) {
+		memory_node__fprintf(&nodes[i], ff->ph->env.memory_bsize, fp);
+	}
+}
+
 static int __event_process_build_id(struct build_id_event *bev,
 				    char *filename,
 				    struct perf_session *session)
@@ -2205,6 +2457,58 @@ static int process_sample_time(struct feat_fd *ff, void *data __maybe_unused)
 	return 0;
 }
 
+static int process_mem_topology(struct feat_fd *ff,
+				void *data __maybe_unused)
+{
+	struct memory_node *nodes;
+	u64 version, i, nr, bsize;
+	int ret = -1;
+
+	if (do_read_u64(ff, &version))
+		return -1;
+
+	if (version != 1)
+		return -1;
+
+	if (do_read_u64(ff, &bsize))
+		return -1;
+
+	if (do_read_u64(ff, &nr))
+		return -1;
+
+	nodes = zalloc(sizeof(*nodes) * nr);
+	if (!nodes)
+		return -1;
+
+	for (i = 0; i < nr; i++) {
+		struct memory_node n;
+
+		#define _R(v)				\
+			if (do_read_u64(ff, &n.v))	\
+				goto out;		\
+
+		_R(node)
+		_R(size)
+
+		#undef _R
+
+		if (do_read_bitmap(ff, &n.set, &n.size))
+			goto out;
+
+		nodes[i] = n;
+	}
+
+	ff->ph->env.memory_bsize    = bsize;
+	ff->ph->env.memory_nodes    = nodes;
+	ff->ph->env.nr_memory_nodes = nr;
+	ret = 0;
+
+out:
+	if (ret)
+		free(nodes);
+	return ret;
+}
+
 struct feature_ops {
 	int (*write)(struct feat_fd *ff, struct perf_evlist *evlist);
 	void (*print)(struct feat_fd *ff, FILE *fp);
@@ -2263,6 +2567,7 @@ static const struct feature_ops feat_ops[HEADER_LAST_FEATURE] = {
 	FEAT_OPN(STAT,		stat,		false),
 	FEAT_OPN(CACHE,		cache,		true),
 	FEAT_OPR(SAMPLE_TIME,	sample_time,	false),
+	FEAT_OPR(MEM_TOPOLOGY,	mem_topology,	true),
 };
 
 struct header_print_data {
@@ -2318,7 +2623,12 @@ int perf_header__fprintf_info(struct perf_session *session, FILE *fp, bool full)
 	if (ret == -1)
 		return -1;
 
-	fprintf(fp, "# captured on: %s", ctime(&st.st_ctime));
+	fprintf(fp, "# captured on    : %s", ctime(&st.st_ctime));
+
+	fprintf(fp, "# header version : %u\n", header->version);
+	fprintf(fp, "# data offset    : %" PRIu64 "\n", header->data_offset);
+	fprintf(fp, "# data size      : %" PRIu64 "\n", header->data_size);
+	fprintf(fp, "# feat offset    : %" PRIu64 "\n", header->feat_offset);
 
 	perf_header__process_sections(header, fd, &hd,
 				      perf_file_section__fprintf_info);
@@ -3105,8 +3415,17 @@ int perf_event__synthesize_features(struct perf_tool *tool,
 			return ret;
 		}
 	}
+
+	/* Send HEADER_LAST_FEATURE mark. */
+	fe = ff.buf;
+	fe->feat_id     = HEADER_LAST_FEATURE;
+	fe->header.type = PERF_RECORD_HEADER_FEATURE;
+	fe->header.size = sizeof(*fe);
+
+	ret = process(tool, ff.buf, NULL, NULL);
+
 	free(ff.buf);
-	return 0;
+	return ret;
 }
 
 int perf_event__process_feature(struct perf_tool *tool,
diff --git a/tools/perf/util/header.h b/tools/perf/util/header.h
index f28aaaa3a440..90d4577a92dc 100644
--- a/tools/perf/util/header.h
+++ b/tools/perf/util/header.h
@@ -36,6 +36,7 @@ enum {
 	HEADER_STAT,
 	HEADER_CACHE,
 	HEADER_SAMPLE_TIME,
+	HEADER_MEM_TOPOLOGY,
 	HEADER_LAST_FEATURE,
 	HEADER_FEAT_BITS	= 256,
 };
@@ -174,4 +175,5 @@ int write_padded(struct feat_fd *fd, const void *bf,
 int get_cpuid(char *buffer, size_t sz);
 
 char *get_cpuid_str(struct perf_pmu *pmu __maybe_unused);
+int strcmp_cpuid_str(const char *s1, const char *s2);
 #endif /* __PERF_HEADER_H */
diff --git a/tools/perf/util/hist.c b/tools/perf/util/hist.c
index b6140950301e..7d968892ee39 100644
--- a/tools/perf/util/hist.c
+++ b/tools/perf/util/hist.c
@@ -536,7 +536,7 @@ static struct hist_entry *hists__findnew_entry(struct hists *hists,
 			 * This mem info was allocated from sample__resolve_mem
 			 * and will not be used anymore.
 			 */
-			zfree(&entry->mem_info);
+			mem_info__zput(entry->mem_info);
 
 			/* If the map of an existing hist_entry has
 			 * become out-of-date due to an exec() or
@@ -879,7 +879,7 @@ iter_prepare_cumulative_entry(struct hist_entry_iter *iter,
 	 * cumulated only one time to prevent entries more than 100%
 	 * overhead.
 	 */
-	he_cache = malloc(sizeof(*he_cache) * (iter->max_stack + 1));
+	he_cache = malloc(sizeof(*he_cache) * (callchain_cursor.nr + 1));
 	if (he_cache == NULL)
 		return -ENOMEM;
 
@@ -1045,8 +1045,6 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 	if (err)
 		return err;
 
-	iter->max_stack = max_stack_depth;
-
 	err = iter->ops->prepare_entry(iter, al);
 	if (err)
 		goto out;
@@ -1141,7 +1139,7 @@ void hist_entry__delete(struct hist_entry *he)
 	if (he->mem_info) {
 		map__zput(he->mem_info->iaddr.map);
 		map__zput(he->mem_info->daddr.map);
-		zfree(&he->mem_info);
+		mem_info__zput(he->mem_info);
 	}
 
 	zfree(&he->stat_acc);
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 02721b579746..e869cad4d89f 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -107,7 +107,6 @@ struct hist_entry_iter {
 	int curr;
 
 	bool hide_unresolved;
-	int max_stack;
 
 	struct perf_evsel *evsel;
 	struct perf_sample *sample;
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 aa1593ce551d..f9157aed1289 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.c
@@ -1378,6 +1378,7 @@ static int intel_pt_overflow(struct intel_pt_decoder *decoder)
 	intel_pt_clear_tx_flags(decoder);
 	decoder->have_tma = false;
 	decoder->cbr = 0;
+	decoder->timestamp_insn_cnt = 0;
 	decoder->pkt_state = INTEL_PT_STATE_ERR_RESYNC;
 	decoder->overflow = true;
 	return -EOVERFLOW;
@@ -1616,6 +1617,7 @@ static int intel_pt_walk_fup_tip(struct intel_pt_decoder *decoder)
 		case INTEL_PT_PWRX:
 			intel_pt_log("ERROR: Missing TIP after FUP\n");
 			decoder->pkt_state = INTEL_PT_STATE_ERR3;
+			decoder->pkt_step = 0;
 			return -ENOENT;
 
 		case INTEL_PT_OVF:
@@ -2390,14 +2392,6 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder)
 	return &decoder->state;
 }
 
-static bool intel_pt_at_psb(unsigned char *buf, size_t len)
-{
-	if (len < INTEL_PT_PSB_LEN)
-		return false;
-	return memmem(buf, INTEL_PT_PSB_LEN, INTEL_PT_PSB_STR,
-		      INTEL_PT_PSB_LEN);
-}
-
 /**
  * intel_pt_next_psb - move buffer pointer to the start of the next PSB packet.
  * @buf: pointer to buffer pointer
@@ -2486,6 +2480,7 @@ static unsigned char *intel_pt_last_psb(unsigned char *buf, size_t len)
  * @buf: buffer
  * @len: size of buffer
  * @tsc: TSC value returned
+ * @rem: returns remaining size when TSC is found
  *
  * Find a TSC packet in @buf and return the TSC value.  This function assumes
  * that @buf starts at a PSB and that PSB+ will contain TSC and so stops if a
@@ -2493,7 +2488,8 @@ static unsigned char *intel_pt_last_psb(unsigned char *buf, size_t len)
  *
  * Return: %true if TSC is found, false otherwise.
  */
-static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc)
+static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc,
+			      size_t *rem)
 {
 	struct intel_pt_pkt packet;
 	int ret;
@@ -2504,6 +2500,7 @@ static bool intel_pt_next_tsc(unsigned char *buf, size_t len, uint64_t *tsc)
 			return false;
 		if (packet.type == INTEL_PT_TSC) {
 			*tsc = packet.payload;
+			*rem = len;
 			return true;
 		}
 		if (packet.type == INTEL_PT_PSBEND)
@@ -2554,6 +2551,8 @@ static int intel_pt_tsc_cmp(uint64_t tsc1, uint64_t tsc2)
  * @len_a: size of first buffer
  * @buf_b: second buffer
  * @len_b: size of second buffer
+ * @consecutive: returns true if there is data in buf_b that is consecutive
+ *               to buf_a
  *
  * If the trace contains TSC we can look at the last TSC of @buf_a and the
  * first TSC of @buf_b in order to determine if the buffers overlap, and then
@@ -2566,33 +2565,41 @@ static int intel_pt_tsc_cmp(uint64_t tsc1, uint64_t tsc2)
 static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a,
 						size_t len_a,
 						unsigned char *buf_b,
-						size_t len_b)
+						size_t len_b, bool *consecutive)
 {
 	uint64_t tsc_a, tsc_b;
 	unsigned char *p;
-	size_t len;
+	size_t len, rem_a, rem_b;
 
 	p = intel_pt_last_psb(buf_a, len_a);
 	if (!p)
 		return buf_b; /* No PSB in buf_a => no overlap */
 
 	len = len_a - (p - buf_a);
-	if (!intel_pt_next_tsc(p, len, &tsc_a)) {
+	if (!intel_pt_next_tsc(p, len, &tsc_a, &rem_a)) {
 		/* The last PSB+ in buf_a is incomplete, so go back one more */
 		len_a -= len;
 		p = intel_pt_last_psb(buf_a, len_a);
 		if (!p)
 			return buf_b; /* No full PSB+ => assume no overlap */
 		len = len_a - (p - buf_a);
-		if (!intel_pt_next_tsc(p, len, &tsc_a))
+		if (!intel_pt_next_tsc(p, len, &tsc_a, &rem_a))
 			return buf_b; /* No TSC in buf_a => assume no overlap */
 	}
 
 	while (1) {
 		/* Ignore PSB+ with no TSC */
-		if (intel_pt_next_tsc(buf_b, len_b, &tsc_b) &&
-		    intel_pt_tsc_cmp(tsc_a, tsc_b) < 0)
-			return buf_b; /* tsc_a < tsc_b => no overlap */
+		if (intel_pt_next_tsc(buf_b, len_b, &tsc_b, &rem_b)) {
+			int cmp = intel_pt_tsc_cmp(tsc_a, tsc_b);
+
+			/* Same TSC, so buffers are consecutive */
+			if (!cmp && rem_b >= rem_a) {
+				*consecutive = true;
+				return buf_b + len_b - (rem_b - rem_a);
+			}
+			if (cmp < 0)
+				return buf_b; /* tsc_a < tsc_b => no overlap */
+		}
 
 		if (!intel_pt_step_psb(&buf_b, &len_b))
 			return buf_b + len_b; /* No PSB in buf_b => no data */
@@ -2606,6 +2613,8 @@ static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a,
  * @buf_b: second buffer
  * @len_b: size of second buffer
  * @have_tsc: can use TSC packets to detect overlap
+ * @consecutive: returns true if there is data in buf_b that is consecutive
+ *               to buf_a
  *
  * When trace samples or snapshots are recorded there is the possibility that
  * the data overlaps.  Note that, for the purposes of decoding, data is only
@@ -2616,7 +2625,7 @@ static unsigned char *intel_pt_find_overlap_tsc(unsigned char *buf_a,
  */
 unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
 				     unsigned char *buf_b, size_t len_b,
-				     bool have_tsc)
+				     bool have_tsc, bool *consecutive)
 {
 	unsigned char *found;
 
@@ -2628,7 +2637,8 @@ unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
 		return buf_b; /* No overlap */
 
 	if (have_tsc) {
-		found = intel_pt_find_overlap_tsc(buf_a, len_a, buf_b, len_b);
+		found = intel_pt_find_overlap_tsc(buf_a, len_a, buf_b, len_b,
+						  consecutive);
 		if (found)
 			return found;
 	}
@@ -2643,28 +2653,16 @@ unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
 	}
 
 	/* Now len_b >= len_a */
-	if (len_b > len_a) {
-		/* The leftover buffer 'b' must start at a PSB */
-		while (!intel_pt_at_psb(buf_b + len_a, len_b - len_a)) {
-			if (!intel_pt_step_psb(&buf_a, &len_a))
-				return buf_b; /* No overlap */
-		}
-	}
-
 	while (1) {
 		/* Potential overlap so check the bytes */
 		found = memmem(buf_a, len_a, buf_b, len_a);
-		if (found)
+		if (found) {
+			*consecutive = true;
 			return buf_b + len_a;
+		}
 
 		/* Try again at next PSB in buffer 'a' */
 		if (!intel_pt_step_psb(&buf_a, &len_a))
 			return buf_b; /* No overlap */
-
-		/* The leftover buffer 'b' must start at a PSB */
-		while (!intel_pt_at_psb(buf_b + len_a, len_b - len_a)) {
-			if (!intel_pt_step_psb(&buf_a, &len_a))
-				return buf_b; /* No overlap */
-		}
 	}
 }
diff --git a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
index 921b22e8ca0e..fc1752d50019 100644
--- a/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
+++ b/tools/perf/util/intel-pt-decoder/intel-pt-decoder.h
@@ -117,7 +117,7 @@ const struct intel_pt_state *intel_pt_decode(struct intel_pt_decoder *decoder);
 
 unsigned char *intel_pt_find_overlap(unsigned char *buf_a, size_t len_a,
 				     unsigned char *buf_b, size_t len_b,
-				     bool have_tsc);
+				     bool have_tsc, bool *consecutive);
 
 int intel_pt__strerror(int code, char *buf, size_t buflen);
 
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index 3773d9c54f45..0effaff57020 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -132,6 +132,7 @@ struct intel_pt_queue {
 	struct intel_pt *pt;
 	unsigned int queue_nr;
 	struct auxtrace_buffer *buffer;
+	struct auxtrace_buffer *old_buffer;
 	void *decoder;
 	const struct intel_pt_state *state;
 	struct ip_callchain *chain;
@@ -143,6 +144,7 @@ struct intel_pt_queue {
 	bool stop;
 	bool step_through_buffers;
 	bool use_buffer_pid_tid;
+	bool sync_switch;
 	pid_t pid, tid;
 	int cpu;
 	int switch_state;
@@ -207,49 +209,28 @@ static void intel_pt_dump_event(struct intel_pt *pt, unsigned char *buf,
 static int intel_pt_do_fix_overlap(struct intel_pt *pt, struct auxtrace_buffer *a,
 				   struct auxtrace_buffer *b)
 {
+	bool consecutive = false;
 	void *start;
 
 	start = intel_pt_find_overlap(a->data, a->size, b->data, b->size,
-				      pt->have_tsc);
+				      pt->have_tsc, &consecutive);
 	if (!start)
 		return -EINVAL;
 	b->use_size = b->data + b->size - start;
 	b->use_data = start;
+	if (b->use_size && consecutive)
+		b->consecutive = true;
 	return 0;
 }
 
-static void intel_pt_use_buffer_pid_tid(struct intel_pt_queue *ptq,
-					struct auxtrace_queue *queue,
-					struct auxtrace_buffer *buffer)
-{
-	if (queue->cpu == -1 && buffer->cpu != -1)
-		ptq->cpu = buffer->cpu;
-
-	ptq->pid = buffer->pid;
-	ptq->tid = buffer->tid;
-
-	intel_pt_log("queue %u cpu %d pid %d tid %d\n",
-		     ptq->queue_nr, ptq->cpu, ptq->pid, ptq->tid);
-
-	thread__zput(ptq->thread);
-
-	if (ptq->tid != -1) {
-		if (ptq->pid != -1)
-			ptq->thread = machine__findnew_thread(ptq->pt->machine,
-							      ptq->pid,
-							      ptq->tid);
-		else
-			ptq->thread = machine__find_thread(ptq->pt->machine, -1,
-							   ptq->tid);
-	}
-}
-
 /* This function assumes data is processed sequentially only */
 static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
 {
 	struct intel_pt_queue *ptq = data;
-	struct auxtrace_buffer *buffer = ptq->buffer, *old_buffer = buffer;
+	struct auxtrace_buffer *buffer = ptq->buffer;
+	struct auxtrace_buffer *old_buffer = ptq->old_buffer;
 	struct auxtrace_queue *queue;
+	bool might_overlap;
 
 	if (ptq->stop) {
 		b->len = 0;
@@ -257,7 +238,7 @@ static int intel_pt_get_trace(struct intel_pt_buffer *b, void *data)
 	}
 
 	queue = &ptq->pt->queues.queue_array[ptq->queue_nr];
-next:
+
 	buffer = auxtrace_buffer__next(queue, buffer);
 	if (!buffer) {
 		if (old_buffer)
@@ -276,7 +257,8 @@ next:
 			return -ENOMEM;
 	}
 
-	if (ptq->pt->snapshot_mode && !buffer->consecutive && old_buffer &&
+	might_overlap = ptq->pt->snapshot_mode || ptq->pt->sampling_mode;
+	if (might_overlap && !buffer->consecutive && old_buffer &&
 	    intel_pt_do_fix_overlap(ptq->pt, old_buffer, buffer))
 		return -ENOMEM;
 
@@ -289,33 +271,24 @@ next:
 	}
 	b->ref_timestamp = buffer->reference;
 
-	/*
-	 * If in snapshot mode and the buffer has no usable data, get next
-	 * buffer and again check overlap against old_buffer.
-	 */
-	if (ptq->pt->snapshot_mode && !b->len)
-		goto next;
-
-	if (old_buffer)
-		auxtrace_buffer__drop_data(old_buffer);
-
-	if (!old_buffer || ptq->pt->sampling_mode || (ptq->pt->snapshot_mode &&
-						      !buffer->consecutive)) {
+	if (!old_buffer || (might_overlap && !buffer->consecutive)) {
 		b->consecutive = false;
 		b->trace_nr = buffer->buffer_nr + 1;
 	} else {
 		b->consecutive = true;
 	}
 
-	if (ptq->use_buffer_pid_tid && (ptq->pid != buffer->pid ||
-					ptq->tid != buffer->tid))
-		intel_pt_use_buffer_pid_tid(ptq, queue, buffer);
-
 	if (ptq->step_through_buffers)
 		ptq->stop = true;
 
-	if (!b->len)
+	if (b->len) {
+		if (old_buffer)
+			auxtrace_buffer__drop_data(old_buffer);
+		ptq->old_buffer = buffer;
+	} else {
+		auxtrace_buffer__drop_data(buffer);
 		return intel_pt_get_trace(b, data);
+	}
 
 	return 0;
 }
@@ -954,16 +927,15 @@ static int intel_pt_setup_queue(struct intel_pt *pt,
 			ptq->cpu = queue->cpu;
 		ptq->tid = queue->tid;
 
-		if (pt->sampling_mode) {
-			if (pt->timeless_decoding)
-				ptq->step_through_buffers = true;
-			if (pt->timeless_decoding || !pt->have_sched_switch)
-				ptq->use_buffer_pid_tid = true;
-		}
+		if (pt->sampling_mode && !pt->snapshot_mode &&
+		    pt->timeless_decoding)
+			ptq->step_through_buffers = true;
+
+		ptq->sync_switch = pt->sync_switch;
 	}
 
 	if (!ptq->on_heap &&
-	    (!pt->sync_switch ||
+	    (!ptq->sync_switch ||
 	     ptq->switch_state != INTEL_PT_SS_EXPECTING_SWITCH_EVENT)) {
 		const struct intel_pt_state *state;
 		int ret;
@@ -1546,7 +1518,7 @@ static int intel_pt_sample(struct intel_pt_queue *ptq)
 	if (pt->synth_opts.last_branch)
 		intel_pt_update_last_branch_rb(ptq);
 
-	if (!pt->sync_switch)
+	if (!ptq->sync_switch)
 		return 0;
 
 	if (intel_pt_is_switch_ip(ptq, state->to_ip)) {
@@ -1627,6 +1599,21 @@ static u64 intel_pt_switch_ip(struct intel_pt *pt, u64 *ptss_ip)
 	return switch_ip;
 }
 
+static void intel_pt_enable_sync_switch(struct intel_pt *pt)
+{
+	unsigned int i;
+
+	pt->sync_switch = true;
+
+	for (i = 0; i < pt->queues.nr_queues; i++) {
+		struct auxtrace_queue *queue = &pt->queues.queue_array[i];
+		struct intel_pt_queue *ptq = queue->priv;
+
+		if (ptq)
+			ptq->sync_switch = true;
+	}
+}
+
 static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 {
 	const struct intel_pt_state *state = ptq->state;
@@ -1643,7 +1630,7 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 			if (pt->switch_ip) {
 				intel_pt_log("switch_ip: %"PRIx64" ptss_ip: %"PRIx64"\n",
 					     pt->switch_ip, pt->ptss_ip);
-				pt->sync_switch = true;
+				intel_pt_enable_sync_switch(pt);
 			}
 		}
 	}
@@ -1659,9 +1646,9 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 		if (state->err) {
 			if (state->err == INTEL_PT_ERR_NODATA)
 				return 1;
-			if (pt->sync_switch &&
+			if (ptq->sync_switch &&
 			    state->from_ip >= pt->kernel_start) {
-				pt->sync_switch = false;
+				ptq->sync_switch = false;
 				intel_pt_next_tid(pt, ptq);
 			}
 			if (pt->synth_opts.errors) {
@@ -1687,7 +1674,7 @@ static int intel_pt_run_decoder(struct intel_pt_queue *ptq, u64 *timestamp)
 				     state->timestamp, state->est_timestamp);
 			ptq->timestamp = state->est_timestamp;
 		/* Use estimated TSC in unknown switch state */
-		} else if (pt->sync_switch &&
+		} else if (ptq->sync_switch &&
 			   ptq->switch_state == INTEL_PT_SS_UNKNOWN &&
 			   intel_pt_is_switch_ip(ptq, state->to_ip) &&
 			   ptq->next_tid == -1) {
@@ -1834,7 +1821,7 @@ static int intel_pt_sync_switch(struct intel_pt *pt, int cpu, pid_t tid,
 		return 1;
 
 	ptq = intel_pt_cpu_to_ptq(pt, cpu);
-	if (!ptq)
+	if (!ptq || !ptq->sync_switch)
 		return 1;
 
 	switch (ptq->switch_state) {
@@ -2075,9 +2062,6 @@ static int intel_pt_process_auxtrace_event(struct perf_session *session,
 	struct intel_pt *pt = container_of(session->auxtrace, struct intel_pt,
 					   auxtrace);
 
-	if (pt->sampling_mode)
-		return 0;
-
 	if (!pt->data_queued) {
 		struct auxtrace_buffer *buffer;
 		off_t data_offset;
diff --git a/tools/perf/util/llvm-utils.c b/tools/perf/util/llvm-utils.c
index 4952b429caa7..1cca0a2fa641 100644
--- a/tools/perf/util/llvm-utils.c
+++ b/tools/perf/util/llvm-utils.c
@@ -433,6 +433,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 	char serr[STRERR_BUFSIZE];
 	char *kbuild_dir = NULL, *kbuild_include_opts = NULL;
 	const char *template = llvm_param.clang_bpf_cmd_template;
+	char *command_echo, *command_out;
 
 	if (path[0] != '-' && realpath(path, abspath) == NULL) {
 		err = errno;
@@ -487,6 +488,16 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 		      (path[0] == '-') ? path : abspath);
 
 	pr_debug("llvm compiling command template: %s\n", template);
+
+	if (asprintf(&command_echo, "echo -n \"%s\"", template) < 0)
+		goto errout;
+
+	err = read_from_pipe(command_echo, (void **) &command_out, NULL);
+	if (err)
+		goto errout;
+
+	pr_debug("llvm compiling command : %s\n", command_out);
+
 	err = read_from_pipe(template, &obj_buf, &obj_buf_sz);
 	if (err) {
 		pr_err("ERROR:\tunable to compile %s\n", path);
@@ -497,6 +508,8 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 		goto errout;
 	}
 
+	free(command_echo);
+	free(command_out);
 	free(kbuild_dir);
 	free(kbuild_include_opts);
 
@@ -509,6 +522,7 @@ int llvm__compile_bpf(const char *path, void **p_obj_buf,
 		*p_obj_buf_sz = obj_buf_sz;
 	return 0;
 errout:
+	free(command_echo);
 	free(kbuild_dir);
 	free(kbuild_include_opts);
 	free(obj_buf);
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index b05a67464c03..2eca8478e24f 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -48,8 +48,23 @@ static void machine__threads_init(struct machine *machine)
 	}
 }
 
+static int machine__set_mmap_name(struct machine *machine)
+{
+	if (machine__is_host(machine))
+		machine->mmap_name = strdup("[kernel.kallsyms]");
+	else if (machine__is_default_guest(machine))
+		machine->mmap_name = strdup("[guest.kernel.kallsyms]");
+	else if (asprintf(&machine->mmap_name, "[guest.kernel.kallsyms.%d]",
+			  machine->pid) < 0)
+		machine->mmap_name = NULL;
+
+	return machine->mmap_name ? 0 : -ENOMEM;
+}
+
 int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 {
+	int err = -ENOMEM;
+
 	memset(machine, 0, sizeof(*machine));
 	map_groups__init(&machine->kmaps, machine);
 	RB_CLEAR_NODE(&machine->rb_node);
@@ -73,13 +88,16 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	if (machine->root_dir == NULL)
 		return -ENOMEM;
 
+	if (machine__set_mmap_name(machine))
+		goto out;
+
 	if (pid != HOST_KERNEL_ID) {
 		struct thread *thread = machine__findnew_thread(machine, -1,
 								pid);
 		char comm[64];
 
 		if (thread == NULL)
-			return -ENOMEM;
+			goto out;
 
 		snprintf(comm, sizeof(comm), "[guest/%d]", pid);
 		thread__set_comm(thread, comm, 0);
@@ -87,7 +105,13 @@ int machine__init(struct machine *machine, const char *root_dir, pid_t pid)
 	}
 
 	machine->current_tid = NULL;
+	err = 0;
 
+out:
+	if (err) {
+		zfree(&machine->root_dir);
+		zfree(&machine->mmap_name);
+	}
 	return 0;
 }
 
@@ -119,7 +143,7 @@ struct machine *machine__new_kallsyms(void)
 	 *    ask for not using the kcore parsing code, once this one is fixed
 	 *    to create a map per module.
 	 */
-	if (machine && __machine__load_kallsyms(machine, "/proc/kallsyms", MAP__FUNCTION, true) <= 0) {
+	if (machine && machine__load_kallsyms(machine, "/proc/kallsyms", MAP__FUNCTION) <= 0) {
 		machine__delete(machine);
 		machine = NULL;
 	}
@@ -180,6 +204,7 @@ void machine__exit(struct machine *machine)
 	dsos__exit(&machine->dsos);
 	machine__exit_vdso(machine);
 	zfree(&machine->root_dir);
+	zfree(&machine->mmap_name);
 	zfree(&machine->current_tid);
 
 	for (i = 0; i < THREADS__TABLE_SIZE; i++) {
@@ -322,20 +347,6 @@ void machines__process_guests(struct machines *machines,
 	}
 }
 
-char *machine__mmap_name(struct machine *machine, char *bf, size_t size)
-{
-	if (machine__is_host(machine))
-		snprintf(bf, size, "[%s]", "kernel.kallsyms");
-	else if (machine__is_default_guest(machine))
-		snprintf(bf, size, "[%s]", "guest.kernel.kallsyms");
-	else {
-		snprintf(bf, size, "[%s.%d]", "guest.kernel.kallsyms",
-			 machine->pid);
-	}
-
-	return bf;
-}
-
 void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size)
 {
 	struct rb_node *node;
@@ -771,24 +782,18 @@ size_t machine__fprintf(struct machine *machine, FILE *fp)
 
 static struct dso *machine__get_kernel(struct machine *machine)
 {
-	const char *vmlinux_name = NULL;
+	const char *vmlinux_name = machine->mmap_name;
 	struct dso *kernel;
 
 	if (machine__is_host(machine)) {
-		vmlinux_name = symbol_conf.vmlinux_name;
-		if (!vmlinux_name)
-			vmlinux_name = DSO__NAME_KALLSYMS;
+		if (symbol_conf.vmlinux_name)
+			vmlinux_name = symbol_conf.vmlinux_name;
 
 		kernel = machine__findnew_kernel(machine, vmlinux_name,
 						 "[kernel]", DSO_TYPE_KERNEL);
 	} else {
-		char bf[PATH_MAX];
-
-		if (machine__is_default_guest(machine))
+		if (symbol_conf.default_guest_vmlinux_name)
 			vmlinux_name = symbol_conf.default_guest_vmlinux_name;
-		if (!vmlinux_name)
-			vmlinux_name = machine__mmap_name(machine, bf,
-							  sizeof(bf));
 
 		kernel = machine__findnew_kernel(machine, vmlinux_name,
 						 "[guest.kernel]",
@@ -849,13 +854,10 @@ static int machine__get_running_kernel_start(struct machine *machine,
 	return 0;
 }
 
-int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
+static int
+__machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 {
 	int type;
-	u64 start = 0;
-
-	if (machine__get_running_kernel_start(machine, NULL, &start))
-		return -1;
 
 	/* In case of renewal the kernel map, destroy previous one */
 	machine__destroy_kernel_maps(machine);
@@ -864,7 +866,7 @@ int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel)
 		struct kmap *kmap;
 		struct map *map;
 
-		machine->vmlinux_maps[type] = map__new2(start, kernel, type);
+		machine->vmlinux_maps[type] = map__new2(0, kernel, type);
 		if (machine->vmlinux_maps[type] == NULL)
 			return -1;
 
@@ -987,11 +989,11 @@ int machines__create_kernel_maps(struct machines *machines, pid_t pid)
 	return machine__create_kernel_maps(machine);
 }
 
-int __machine__load_kallsyms(struct machine *machine, const char *filename,
-			     enum map_type type, bool no_kcore)
+int machine__load_kallsyms(struct machine *machine, const char *filename,
+			     enum map_type type)
 {
 	struct map *map = machine__kernel_map(machine);
-	int ret = __dso__load_kallsyms(map->dso, filename, map, no_kcore);
+	int ret = __dso__load_kallsyms(map->dso, filename, map, true);
 
 	if (ret > 0) {
 		dso__set_loaded(map->dso, type);
@@ -1006,12 +1008,6 @@ int __machine__load_kallsyms(struct machine *machine, const char *filename,
 	return ret;
 }
 
-int machine__load_kallsyms(struct machine *machine, const char *filename,
-			   enum map_type type)
-{
-	return __machine__load_kallsyms(machine, filename, type, false);
-}
-
 int machine__load_vmlinux_path(struct machine *machine, enum map_type type)
 {
 	struct map *map = machine__kernel_map(machine);
@@ -1215,6 +1211,24 @@ static int machine__create_modules(struct machine *machine)
 	return 0;
 }
 
+static void machine__set_kernel_mmap(struct machine *machine,
+				     u64 start, u64 end)
+{
+	int i;
+
+	for (i = 0; i < MAP__NR_TYPES; i++) {
+		machine->vmlinux_maps[i]->start = start;
+		machine->vmlinux_maps[i]->end   = end;
+
+		/*
+		 * Be a bit paranoid here, some perf.data file came with
+		 * a zero sized synthesized MMAP event for the kernel.
+		 */
+		if (start == 0 && end == 0)
+			machine->vmlinux_maps[i]->end = ~0ULL;
+	}
+}
+
 int machine__create_kernel_maps(struct machine *machine)
 {
 	struct dso *kernel = machine__get_kernel(machine);
@@ -1239,40 +1253,22 @@ int machine__create_kernel_maps(struct machine *machine)
 				 "continuing anyway...\n", machine->pid);
 	}
 
-	/*
-	 * Now that we have all the maps created, just set the ->end of them:
-	 */
-	map_groups__fixup_end(&machine->kmaps);
-
 	if (!machine__get_running_kernel_start(machine, &name, &addr)) {
 		if (name &&
 		    maps__set_kallsyms_ref_reloc_sym(machine->vmlinux_maps, name, addr)) {
 			machine__destroy_kernel_maps(machine);
 			return -1;
 		}
+		machine__set_kernel_mmap(machine, addr, 0);
 	}
 
+	/*
+	 * Now that we have all the maps created, just set the ->end of them:
+	 */
+	map_groups__fixup_end(&machine->kmaps);
 	return 0;
 }
 
-static void machine__set_kernel_mmap_len(struct machine *machine,
-					 union perf_event *event)
-{
-	int i;
-
-	for (i = 0; i < MAP__NR_TYPES; i++) {
-		machine->vmlinux_maps[i]->start = event->mmap.start;
-		machine->vmlinux_maps[i]->end   = (event->mmap.start +
-						   event->mmap.len);
-		/*
-		 * Be a bit paranoid here, some perf.data file came with
-		 * a zero sized synthesized MMAP event for the kernel.
-		 */
-		if (machine->vmlinux_maps[i]->end == 0)
-			machine->vmlinux_maps[i]->end = ~0ULL;
-	}
-}
-
 static bool machine__uses_kcore(struct machine *machine)
 {
 	struct dso *dso;
@@ -1289,7 +1285,6 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 					      union perf_event *event)
 {
 	struct map *map;
-	char kmmap_prefix[PATH_MAX];
 	enum dso_kernel_type kernel_type;
 	bool is_kernel_mmap;
 
@@ -1297,15 +1292,14 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 	if (machine__uses_kcore(machine))
 		return 0;
 
-	machine__mmap_name(machine, kmmap_prefix, sizeof(kmmap_prefix));
 	if (machine__is_host(machine))
 		kernel_type = DSO_TYPE_KERNEL;
 	else
 		kernel_type = DSO_TYPE_GUEST_KERNEL;
 
 	is_kernel_mmap = memcmp(event->mmap.filename,
-				kmmap_prefix,
-				strlen(kmmap_prefix) - 1) == 0;
+				machine->mmap_name,
+				strlen(machine->mmap_name) - 1) == 0;
 	if (event->mmap.filename[0] == '/' ||
 	    (!is_kernel_mmap && event->mmap.filename[0] == '[')) {
 		map = machine__findnew_module_map(machine, event->mmap.start,
@@ -1316,7 +1310,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		map->end = map->start + event->mmap.len;
 	} else if (is_kernel_mmap) {
 		const char *symbol_name = (event->mmap.filename +
-				strlen(kmmap_prefix));
+				strlen(machine->mmap_name));
 		/*
 		 * Should be there already, from the build-id table in
 		 * the header.
@@ -1357,7 +1351,7 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		up_read(&machine->dsos.lock);
 
 		if (kernel == NULL)
-			kernel = machine__findnew_dso(machine, kmmap_prefix);
+			kernel = machine__findnew_dso(machine, machine->mmap_name);
 		if (kernel == NULL)
 			goto out_problem;
 
@@ -1370,7 +1364,8 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 		if (strstr(kernel->long_name, "vmlinux"))
 			dso__set_short_name(kernel, "[kernel.vmlinux]", false);
 
-		machine__set_kernel_mmap_len(machine, event);
+		machine__set_kernel_mmap(machine, event->mmap.start,
+					 event->mmap.start + event->mmap.len);
 
 		/*
 		 * Avoid using a zero address (kptr_restrict) for the ref reloc
@@ -1700,7 +1695,7 @@ static void ip__resolve_data(struct thread *thread,
 struct mem_info *sample__resolve_mem(struct perf_sample *sample,
 				     struct addr_location *al)
 {
-	struct mem_info *mi = zalloc(sizeof(*mi));
+	struct mem_info *mi = mem_info__new();
 
 	if (!mi)
 		return NULL;
diff --git a/tools/perf/util/machine.h b/tools/perf/util/machine.h
index 5ce860b64c74..66cc200ef86f 100644
--- a/tools/perf/util/machine.h
+++ b/tools/perf/util/machine.h
@@ -43,6 +43,7 @@ struct machine {
 	bool		  comm_exec;
 	bool		  kptr_restrict_warned;
 	char		  *root_dir;
+	char		  *mmap_name;
 	struct threads    threads[THREADS__TABLE_SIZE];
 	struct vdso_info  *vdso_info;
 	struct perf_env   *env;
@@ -142,8 +143,6 @@ struct machine *machines__find(struct machines *machines, pid_t pid);
 struct machine *machines__findnew(struct machines *machines, pid_t pid);
 
 void machines__set_id_hdr_size(struct machines *machines, u16 id_hdr_size);
-char *machine__mmap_name(struct machine *machine, char *bf, size_t size);
-
 void machines__set_comm_exec(struct machines *machines, bool comm_exec);
 
 struct machine *machine__new_host(void);
@@ -226,8 +225,6 @@ struct map *machine__findnew_module_map(struct machine *machine, u64 start,
 					const char *filename);
 int arch__fix_module_text_start(u64 *start, const char *name);
 
-int __machine__load_kallsyms(struct machine *machine, const char *filename,
-			     enum map_type type, bool no_kcore);
 int machine__load_kallsyms(struct machine *machine, const char *filename,
 			   enum map_type type);
 int machine__load_vmlinux_path(struct machine *machine, enum map_type type);
@@ -239,7 +236,6 @@ size_t machines__fprintf_dsos_buildid(struct machines *machines, FILE *fp,
 				     bool (skip)(struct dso *dso, int parm), int parm);
 
 void machine__destroy_kernel_maps(struct machine *machine);
-int __machine__create_kernel_maps(struct machine *machine, struct dso *kernel);
 int machine__create_kernel_maps(struct machine *machine);
 
 int machines__create_kernel_maps(struct machines *machines, pid_t pid);
diff --git a/tools/perf/util/mem2node.c b/tools/perf/util/mem2node.c
new file mode 100644
index 000000000000..c6fd81c02586
--- /dev/null
+++ b/tools/perf/util/mem2node.c
@@ -0,0 +1,134 @@
+#include <errno.h>
+#include <inttypes.h>
+#include <linux/bitmap.h>
+#include "mem2node.h"
+#include "util.h"
+
+struct phys_entry {
+	struct rb_node	rb_node;
+	u64	start;
+	u64	end;
+	u64	node;
+};
+
+static void phys_entry__insert(struct phys_entry *entry, struct rb_root *root)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_node *parent = NULL;
+	struct phys_entry *e;
+
+	while (*p != NULL) {
+		parent = *p;
+		e = rb_entry(parent, struct phys_entry, rb_node);
+
+		if (entry->start < e->start)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&entry->rb_node, parent, p);
+	rb_insert_color(&entry->rb_node, root);
+}
+
+static void
+phys_entry__init(struct phys_entry *entry, u64 start, u64 bsize, u64 node)
+{
+	entry->start = start;
+	entry->end   = start + bsize;
+	entry->node  = node;
+	RB_CLEAR_NODE(&entry->rb_node);
+}
+
+int mem2node__init(struct mem2node *map, struct perf_env *env)
+{
+	struct memory_node *n, *nodes = &env->memory_nodes[0];
+	struct phys_entry *entries, *tmp_entries;
+	u64 bsize = env->memory_bsize;
+	int i, j = 0, max = 0;
+
+	memset(map, 0x0, sizeof(*map));
+	map->root = RB_ROOT;
+
+	for (i = 0; i < env->nr_memory_nodes; i++) {
+		n = &nodes[i];
+		max += bitmap_weight(n->set, n->size);
+	}
+
+	entries = zalloc(sizeof(*entries) * max);
+	if (!entries)
+		return -ENOMEM;
+
+	for (i = 0; i < env->nr_memory_nodes; i++) {
+		u64 bit;
+
+		n = &nodes[i];
+
+		for (bit = 0; bit < n->size; bit++) {
+			u64 start;
+
+			if (!test_bit(bit, n->set))
+				continue;
+
+			start = bit * bsize;
+
+			/*
+			 * Merge nearby areas, we walk in order
+			 * through the bitmap, so no need to sort.
+			 */
+			if (j > 0) {
+				struct phys_entry *prev = &entries[j - 1];
+
+				if ((prev->end == start) &&
+				    (prev->node == n->node)) {
+					prev->end += bsize;
+					continue;
+				}
+			}
+
+			phys_entry__init(&entries[j++], start, bsize, n->node);
+		}
+	}
+
+	/* Cut unused entries, due to merging. */
+	tmp_entries = realloc(entries, sizeof(*entries) * j);
+	if (tmp_entries)
+		entries = tmp_entries;
+
+	for (i = 0; i < j; i++) {
+		pr_debug("mem2node %03" PRIu64 " [0x%016" PRIx64 "-0x%016" PRIx64 "]\n",
+			 entries[i].node, entries[i].start, entries[i].end);
+
+		phys_entry__insert(&entries[i], &map->root);
+	}
+
+	map->entries = entries;
+	return 0;
+}
+
+void mem2node__exit(struct mem2node *map)
+{
+	zfree(&map->entries);
+}
+
+int mem2node__node(struct mem2node *map, u64 addr)
+{
+	struct rb_node **p, *parent = NULL;
+	struct phys_entry *entry;
+
+	p = &map->root.rb_node;
+	while (*p != NULL) {
+		parent = *p;
+		entry = rb_entry(parent, struct phys_entry, rb_node);
+		if (addr < entry->start)
+			p = &(*p)->rb_left;
+		else if (addr >= entry->end)
+			p = &(*p)->rb_right;
+		else
+			goto out;
+	}
+
+	entry = NULL;
+out:
+	return entry ? (int) entry->node : -1;
+}
diff --git a/tools/perf/util/mem2node.h b/tools/perf/util/mem2node.h
new file mode 100644
index 000000000000..59c4752a2181
--- /dev/null
+++ b/tools/perf/util/mem2node.h
@@ -0,0 +1,19 @@
+#ifndef __MEM2NODE_H
+#define __MEM2NODE_H
+
+#include <linux/rbtree.h>
+#include "env.h"
+
+struct phys_entry;
+
+struct mem2node {
+	struct rb_root		 root;
+	struct phys_entry	*entries;
+	int			 cnt;
+};
+
+int  mem2node__init(struct mem2node *map, struct perf_env *env);
+void mem2node__exit(struct mem2node *map);
+int  mem2node__node(struct mem2node *map, u64 addr);
+
+#endif /* __MEM2NODE_H */
diff --git a/tools/perf/util/mmap.c b/tools/perf/util/mmap.c
index 91531a7c8fbf..fc832676a798 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -64,25 +64,6 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map,
 }
 
 /*
- * legacy interface for mmap read.
- * Don't use it. Use perf_mmap__read_event().
- */
-union perf_event *perf_mmap__read_forward(struct perf_mmap *map)
-{
-	u64 head;
-
-	/*
-	 * Check if event was unmapped due to a POLLHUP/POLLERR.
-	 */
-	if (!refcount_read(&map->refcnt))
-		return NULL;
-
-	head = perf_mmap__read_head(map);
-
-	return perf_mmap__read(map, &map->prev, head);
-}
-
-/*
  * Read event from ring buffer one by one.
  * Return one event for each call.
  *
@@ -94,9 +75,7 @@ union perf_event *perf_mmap__read_forward(struct perf_mmap *map)
  * }
  * perf_mmap__read_done()
  */
-union perf_event *perf_mmap__read_event(struct perf_mmap *map,
-					bool overwrite,
-					u64 *startp, u64 end)
+union perf_event *perf_mmap__read_event(struct perf_mmap *map)
 {
 	union perf_event *event;
 
@@ -106,17 +85,14 @@ union perf_event *perf_mmap__read_event(struct perf_mmap *map,
 	if (!refcount_read(&map->refcnt))
 		return NULL;
 
-	if (startp == NULL)
-		return NULL;
-
 	/* non-overwirte doesn't pause the ringbuffer */
-	if (!overwrite)
-		end = perf_mmap__read_head(map);
+	if (!map->overwrite)
+		map->end = perf_mmap__read_head(map);
 
-	event = perf_mmap__read(map, startp, end);
+	event = perf_mmap__read(map, &map->start, map->end);
 
-	if (!overwrite)
-		map->prev = *startp;
+	if (!map->overwrite)
+		map->prev = map->start;
 
 	return event;
 }
@@ -139,9 +115,9 @@ void perf_mmap__put(struct perf_mmap *map)
 		perf_mmap__munmap(map);
 }
 
-void perf_mmap__consume(struct perf_mmap *map, bool overwrite)
+void perf_mmap__consume(struct perf_mmap *map)
 {
-	if (!overwrite) {
+	if (!map->overwrite) {
 		u64 old = map->prev;
 
 		perf_mmap__write_tail(map, old);
@@ -191,7 +167,7 @@ void perf_mmap__munmap(struct perf_mmap *map)
 int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd)
 {
 	/*
-	 * The last one will be done at perf_evlist__mmap_consume(), so that we
+	 * The last one will be done at perf_mmap__consume(), so that we
 	 * make sure we don't prevent tools from consuming every last event in
 	 * the ring buffer.
 	 *
@@ -223,19 +199,18 @@ int perf_mmap__mmap(struct perf_mmap *map, struct mmap_params *mp, int fd)
 	return 0;
 }
 
-static int overwrite_rb_find_range(void *buf, int mask, u64 head, u64 *start, u64 *end)
+static int overwrite_rb_find_range(void *buf, int mask, u64 *start, u64 *end)
 {
 	struct perf_event_header *pheader;
-	u64 evt_head = head;
+	u64 evt_head = *start;
 	int size = mask + 1;
 
-	pr_debug2("overwrite_rb_find_range: buf=%p, head=%"PRIx64"\n", buf, head);
-	pheader = (struct perf_event_header *)(buf + (head & mask));
-	*start = head;
+	pr_debug2("%s: buf=%p, start=%"PRIx64"\n", __func__, buf, *start);
+	pheader = (struct perf_event_header *)(buf + (*start & mask));
 	while (true) {
-		if (evt_head - head >= (unsigned int)size) {
+		if (evt_head - *start >= (unsigned int)size) {
 			pr_debug("Finished reading overwrite ring buffer: rewind\n");
-			if (evt_head - head > (unsigned int)size)
+			if (evt_head - *start > (unsigned int)size)
 				evt_head -= pheader->size;
 			*end = evt_head;
 			return 0;
@@ -259,27 +234,26 @@ static int overwrite_rb_find_range(void *buf, int mask, u64 head, u64 *start, u6
 /*
  * Report the start and end of the available data in ringbuffer
  */
-int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
-			 u64 *startp, u64 *endp)
+static int __perf_mmap__read_init(struct perf_mmap *md)
 {
 	u64 head = perf_mmap__read_head(md);
 	u64 old = md->prev;
 	unsigned char *data = md->base + page_size;
 	unsigned long size;
 
-	*startp = overwrite ? head : old;
-	*endp = overwrite ? old : head;
+	md->start = md->overwrite ? head : old;
+	md->end = md->overwrite ? old : head;
 
-	if (*startp == *endp)
+	if (md->start == md->end)
 		return -EAGAIN;
 
-	size = *endp - *startp;
+	size = md->end - md->start;
 	if (size > (unsigned long)(md->mask) + 1) {
-		if (!overwrite) {
+		if (!md->overwrite) {
 			WARN_ONCE(1, "failed to keep up with mmap data. (warn only once)\n");
 
 			md->prev = head;
-			perf_mmap__consume(md, overwrite);
+			perf_mmap__consume(md);
 			return -EAGAIN;
 		}
 
@@ -287,33 +261,43 @@ int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
 		 * Backward ring buffer is full. We still have a chance to read
 		 * most of data from it.
 		 */
-		if (overwrite_rb_find_range(data, md->mask, head, startp, endp))
+		if (overwrite_rb_find_range(data, md->mask, &md->start, &md->end))
 			return -EINVAL;
 	}
 
 	return 0;
 }
 
-int perf_mmap__push(struct perf_mmap *md, bool overwrite,
-		    void *to, int push(void *to, void *buf, size_t size))
+int perf_mmap__read_init(struct perf_mmap *map)
+{
+	/*
+	 * Check if event was unmapped due to a POLLHUP/POLLERR.
+	 */
+	if (!refcount_read(&map->refcnt))
+		return -ENOENT;
+
+	return __perf_mmap__read_init(map);
+}
+
+int perf_mmap__push(struct perf_mmap *md, void *to,
+		    int push(void *to, void *buf, size_t size))
 {
 	u64 head = perf_mmap__read_head(md);
-	u64 end, start;
 	unsigned char *data = md->base + page_size;
 	unsigned long size;
 	void *buf;
 	int rc = 0;
 
-	rc = perf_mmap__read_init(md, overwrite, &start, &end);
+	rc = perf_mmap__read_init(md);
 	if (rc < 0)
 		return (rc == -EAGAIN) ? 0 : -1;
 
-	size = end - start;
+	size = md->end - md->start;
 
-	if ((start & md->mask) + size != (end & md->mask)) {
-		buf = &data[start & md->mask];
-		size = md->mask + 1 - (start & md->mask);
-		start += size;
+	if ((md->start & md->mask) + size != (md->end & md->mask)) {
+		buf = &data[md->start & md->mask];
+		size = md->mask + 1 - (md->start & md->mask);
+		md->start += size;
 
 		if (push(to, buf, size) < 0) {
 			rc = -1;
@@ -321,9 +305,9 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite,
 		}
 	}
 
-	buf = &data[start & md->mask];
-	size = end - start;
-	start += size;
+	buf = &data[md->start & md->mask];
+	size = md->end - md->start;
+	md->start += size;
 
 	if (push(to, buf, size) < 0) {
 		rc = -1;
@@ -331,7 +315,7 @@ int perf_mmap__push(struct perf_mmap *md, bool overwrite,
 	}
 
 	md->prev = head;
-	perf_mmap__consume(md, overwrite);
+	perf_mmap__consume(md);
 out:
 	return rc;
 }
@@ -344,5 +328,11 @@ out:
  */
 void perf_mmap__read_done(struct perf_mmap *map)
 {
+	/*
+	 * Check if event was unmapped due to a POLLHUP/POLLERR.
+	 */
+	if (!refcount_read(&map->refcnt))
+		return;
+
 	map->prev = perf_mmap__read_head(map);
 }
diff --git a/tools/perf/util/mmap.h b/tools/perf/util/mmap.h
index ec7d3a24e276..d82294db1295 100644
--- a/tools/perf/util/mmap.h
+++ b/tools/perf/util/mmap.h
@@ -20,6 +20,9 @@ struct perf_mmap {
 	int		 fd;
 	refcount_t	 refcnt;
 	u64		 prev;
+	u64		 start;
+	u64		 end;
+	bool		 overwrite;
 	struct auxtrace_mmap auxtrace_mmap;
 	char		 event_copy[PERF_SAMPLE_MAX_SIZE] __aligned(8);
 };
@@ -63,7 +66,7 @@ void perf_mmap__munmap(struct perf_mmap *map);
 void perf_mmap__get(struct perf_mmap *map);
 void perf_mmap__put(struct perf_mmap *map);
 
-void perf_mmap__consume(struct perf_mmap *map, bool overwrite);
+void perf_mmap__consume(struct perf_mmap *map);
 
 static inline u64 perf_mmap__read_head(struct perf_mmap *mm)
 {
@@ -86,16 +89,13 @@ static inline void perf_mmap__write_tail(struct perf_mmap *md, u64 tail)
 
 union perf_event *perf_mmap__read_forward(struct perf_mmap *map);
 
-union perf_event *perf_mmap__read_event(struct perf_mmap *map,
-					bool overwrite,
-					u64 *startp, u64 end);
+union perf_event *perf_mmap__read_event(struct perf_mmap *map);
 
-int perf_mmap__push(struct perf_mmap *md, bool backward,
-		    void *to, int push(void *to, void *buf, size_t size));
+int perf_mmap__push(struct perf_mmap *md, void *to,
+		    int push(void *to, void *buf, size_t size));
 
 size_t perf_mmap__mmap_len(struct perf_mmap *map);
 
-int perf_mmap__read_init(struct perf_mmap *md, bool overwrite,
-			 u64 *startp, u64 *endp);
+int perf_mmap__read_init(struct perf_mmap *md);
 void perf_mmap__read_done(struct perf_mmap *map);
 #endif /*__PERF_MMAP_H */
diff --git a/tools/perf/util/parse-events.c b/tools/perf/util/parse-events.c
index 34589c427e52..2fb0272146d8 100644
--- a/tools/perf/util/parse-events.c
+++ b/tools/perf/util/parse-events.c
@@ -206,8 +206,8 @@ struct tracepoint_path *tracepoint_id_to_path(u64 config)
 
 		for_each_event(sys_dirent, evt_dir, evt_dirent) {
 
-			snprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path,
-				 evt_dirent->d_name);
+			scnprintf(evt_path, MAXPATHLEN, "%s/%s/id", dir_path,
+				  evt_dirent->d_name);
 			fd = open(evt_path, O_RDONLY);
 			if (fd < 0)
 				continue;
@@ -1217,7 +1217,7 @@ int parse_events_add_numeric(struct parse_events_state *parse_state,
 			 get_config_name(head_config), &config_terms);
 }
 
-static int __parse_events_add_pmu(struct parse_events_state *parse_state,
+int parse_events_add_pmu(struct parse_events_state *parse_state,
 			 struct list_head *list, char *name,
 			 struct list_head *head_config, bool auto_merge_stats)
 {
@@ -1247,7 +1247,12 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 	if (!head_config) {
 		attr.type = pmu->type;
 		evsel = __add_event(list, &parse_state->idx, &attr, NULL, pmu, NULL, auto_merge_stats);
-		return evsel ? 0 : -ENOMEM;
+		if (evsel) {
+			evsel->pmu_name = name;
+			return 0;
+		} else {
+			return -ENOMEM;
+		}
 	}
 
 	if (perf_pmu__check_alias(pmu, head_config, &info))
@@ -1276,18 +1281,12 @@ static int __parse_events_add_pmu(struct parse_events_state *parse_state,
 		evsel->snapshot = info.snapshot;
 		evsel->metric_expr = info.metric_expr;
 		evsel->metric_name = info.metric_name;
+		evsel->pmu_name = name;
 	}
 
 	return evsel ? 0 : -ENOMEM;
 }
 
-int parse_events_add_pmu(struct parse_events_state *parse_state,
-			 struct list_head *list, char *name,
-			 struct list_head *head_config)
-{
-	return __parse_events_add_pmu(parse_state, list, name, head_config, false);
-}
-
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 			       char *str, struct list_head **listp)
 {
@@ -1317,8 +1316,8 @@ int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 					return -1;
 				list_add_tail(&term->list, head);
 
-				if (!__parse_events_add_pmu(parse_state, list,
-							    pmu->name, head, true)) {
+				if (!parse_events_add_pmu(parse_state, list,
+							  pmu->name, head, true)) {
 					pr_debug("%s -> %s/%s/\n", str,
 						 pmu->name, alias->str);
 					ok++;
diff --git a/tools/perf/util/parse-events.h b/tools/perf/util/parse-events.h
index 88108cd11b4c..5015cfd58277 100644
--- a/tools/perf/util/parse-events.h
+++ b/tools/perf/util/parse-events.h
@@ -167,7 +167,7 @@ int parse_events_add_breakpoint(struct list_head *list, int *idx,
 				void *ptr, char *type, u64 len);
 int parse_events_add_pmu(struct parse_events_state *parse_state,
 			 struct list_head *list, char *name,
-			 struct list_head *head_config);
+			 struct list_head *head_config, bool auto_merge_stats);
 
 int parse_events_multi_pmu_add(struct parse_events_state *parse_state,
 			       char *str,
diff --git a/tools/perf/util/parse-events.l b/tools/perf/util/parse-events.l
index 655ecff636a8..a1a01b1ac8b8 100644
--- a/tools/perf/util/parse-events.l
+++ b/tools/perf/util/parse-events.l
@@ -175,7 +175,7 @@ bpf_source	[^,{}]+\.c[a-zA-Z0-9._]*
 num_dec		[0-9]+
 num_hex		0x[a-fA-F0-9]+
 num_raw_hex	[a-fA-F0-9]+
-name		[a-zA-Z_*?][a-zA-Z0-9_*?.]*
+name		[a-zA-Z_*?\[\]][a-zA-Z0-9_*?.\[\]]*
 name_minus	[a-zA-Z_*?][a-zA-Z0-9\-_*?.:]*
 drv_cfg_term	[a-zA-Z0-9_\.]+(=[a-zA-Z0-9_*?\.:]+)?
 /* If you add a modifier you need to update check_modifier() */
diff --git a/tools/perf/util/parse-events.y b/tools/perf/util/parse-events.y
index e81a20ea8d7d..7afeb80cc39e 100644
--- a/tools/perf/util/parse-events.y
+++ b/tools/perf/util/parse-events.y
@@ -8,6 +8,7 @@
 
 #define YYDEBUG 1
 
+#include <fnmatch.h>
 #include <linux/compiler.h>
 #include <linux/list.h>
 #include <linux/types.h>
@@ -231,9 +232,13 @@ PE_NAME opt_event_config
 		YYABORT;
 
 	ALLOC_LIST(list);
-	if (parse_events_add_pmu(_parse_state, list, $1, $2)) {
+	if (parse_events_add_pmu(_parse_state, list, $1, $2, false)) {
 		struct perf_pmu *pmu = NULL;
 		int ok = 0;
+		char *pattern;
+
+		if (asprintf(&pattern, "%s*", $1) < 0)
+			YYABORT;
 
 		while ((pmu = perf_pmu__scan(pmu)) != NULL) {
 			char *name = pmu->name;
@@ -241,14 +246,19 @@ PE_NAME opt_event_config
 			if (!strncmp(name, "uncore_", 7) &&
 			    strncmp($1, "uncore_", 7))
 				name += 7;
-			if (!strncmp($1, name, strlen($1))) {
-				if (parse_events_copy_term_list(orig_terms, &terms))
+			if (!fnmatch(pattern, name, 0)) {
+				if (parse_events_copy_term_list(orig_terms, &terms)) {
+					free(pattern);
 					YYABORT;
-				if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms))
+				}
+				if (!parse_events_add_pmu(_parse_state, list, pmu->name, terms, true))
 					ok++;
 				parse_events_terms__delete(terms);
 			}
 		}
+
+		free(pattern);
+
 		if (!ok)
 			YYABORT;
 	}
diff --git a/tools/perf/util/pmu.c b/tools/perf/util/pmu.c
index 57e38fdf0b34..064bdcb7bd78 100644
--- a/tools/perf/util/pmu.c
+++ b/tools/perf/util/pmu.c
@@ -351,7 +351,7 @@ static int pmu_aliases_parse(char *dir, struct list_head *head)
 		if (pmu_alias_info_file(name))
 			continue;
 
-		snprintf(path, PATH_MAX, "%s/%s", dir, name);
+		scnprintf(path, PATH_MAX, "%s/%s", dir, name);
 
 		file = fopen(path, "r");
 		if (!file) {
@@ -576,6 +576,34 @@ char * __weak get_cpuid_str(struct perf_pmu *pmu __maybe_unused)
 	return NULL;
 }
 
+/* Return zero when the cpuid from the mapfile.csv matches the
+ * cpuid string generated on this platform.
+ * Otherwise return non-zero.
+ */
+int __weak strcmp_cpuid_str(const char *mapcpuid, const char *cpuid)
+{
+	regex_t re;
+	regmatch_t pmatch[1];
+	int match;
+
+	if (regcomp(&re, mapcpuid, REG_EXTENDED) != 0) {
+		/* Warn unable to generate match particular string. */
+		pr_info("Invalid regular expression %s\n", mapcpuid);
+		return 1;
+	}
+
+	match = !regexec(&re, cpuid, 1, pmatch, 0);
+	regfree(&re);
+	if (match) {
+		size_t match_len = (pmatch[0].rm_eo - pmatch[0].rm_so);
+
+		/* Verify the entire string matched. */
+		if (match_len == strlen(cpuid))
+			return 0;
+	}
+	return 1;
+}
+
 static char *perf_pmu__getcpuid(struct perf_pmu *pmu)
 {
 	char *cpuid;
@@ -610,31 +638,14 @@ struct pmu_events_map *perf_pmu__find_map(struct perf_pmu *pmu)
 
 	i = 0;
 	for (;;) {
-		regex_t re;
-		regmatch_t pmatch[1];
-		int match;
-
 		map = &pmu_events_map[i++];
 		if (!map->table) {
 			map = NULL;
 			break;
 		}
 
-		if (regcomp(&re, map->cpuid, REG_EXTENDED) != 0) {
-			/* Warn unable to generate match particular string. */
-			pr_info("Invalid regular expression %s\n", map->cpuid);
+		if (!strcmp_cpuid_str(map->cpuid, cpuid))
 			break;
-		}
-
-		match = !regexec(&re, cpuid, 1, pmatch, 0);
-		regfree(&re);
-		if (match) {
-			size_t match_len = (pmatch[0].rm_eo - pmatch[0].rm_so);
-
-			/* Verify the entire string matched. */
-			if (match_len == strlen(cpuid))
-				break;
-		}
 	}
 	free(cpuid);
 	return map;
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index a5731de0e5eb..c37fbef1711d 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -423,20 +423,20 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 		pr_warning("Failed to get the type of %s.\n", varname);
 		return -ENOENT;
 	}
-	pr_debug2("Var real type: (%x)\n", (unsigned)dwarf_dieoffset(&type));
+	pr_debug2("Var real type: %s (%x)\n", dwarf_diename(&type),
+		  (unsigned)dwarf_dieoffset(&type));
 	tag = dwarf_tag(&type);
 
 	if (field->name[0] == '[' &&
 	    (tag == DW_TAG_array_type || tag == DW_TAG_pointer_type)) {
-		if (field->next)
-			/* Save original type for next field */
-			memcpy(die_mem, &type, sizeof(*die_mem));
+		/* Save original type for next field or type */
+		memcpy(die_mem, &type, sizeof(*die_mem));
 		/* Get the type of this array */
 		if (die_get_real_type(&type, &type) == NULL) {
 			pr_warning("Failed to get the type of %s.\n", varname);
 			return -ENOENT;
 		}
-		pr_debug2("Array real type: (%x)\n",
+		pr_debug2("Array real type: %s (%x)\n", dwarf_diename(&type),
 			 (unsigned)dwarf_dieoffset(&type));
 		if (tag == DW_TAG_pointer_type) {
 			ref = zalloc(sizeof(struct probe_trace_arg_ref));
@@ -448,9 +448,6 @@ static int convert_variable_fields(Dwarf_Die *vr_die, const char *varname,
 				*ref_ptr = ref;
 		}
 		ref->offset += dwarf_bytesize(&type) * field->index;
-		if (!field->next)
-			/* Save vr_die for converting types */
-			memcpy(die_mem, vr_die, sizeof(*die_mem));
 		goto next;
 	} else if (tag == DW_TAG_pointer_type) {
 		/* Check the pointer and dereference */
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index b1e999bd21ef..863b61478edd 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -12,6 +12,30 @@
 #include "print_binary.h"
 #include "thread_map.h"
 
+#if PY_MAJOR_VERSION < 3
+#define _PyUnicode_FromString(arg) \
+  PyString_FromString(arg)
+#define _PyUnicode_AsString(arg) \
+  PyString_AsString(arg)
+#define _PyUnicode_FromFormat(...) \
+  PyString_FromFormat(__VA_ARGS__)
+#define _PyLong_FromLong(arg) \
+  PyInt_FromLong(arg)
+
+#else
+
+#define _PyUnicode_FromString(arg) \
+  PyUnicode_FromString(arg)
+#define _PyUnicode_FromFormat(...) \
+  PyUnicode_FromFormat(__VA_ARGS__)
+#define _PyLong_FromLong(arg) \
+  PyLong_FromLong(arg)
+#endif
+
+#ifndef Py_TYPE
+#define Py_TYPE(ob) (((PyObject*)(ob))->ob_type)
+#endif
+
 /*
  * Provide these two so that we don't have to link against callchain.c and
  * start dragging hist.c, etc.
@@ -49,7 +73,11 @@ int eprintf(int level, int var, const char *fmt, ...)
 # define PyVarObject_HEAD_INIT(type, size) PyObject_HEAD_INIT(type) size,
 #endif
 
+#if PY_MAJOR_VERSION < 3
 PyMODINIT_FUNC initperf(void);
+#else
+PyMODINIT_FUNC PyInit_perf(void);
+#endif
 
 #define member_def(type, member, ptype, help) \
 	{ #member, ptype, \
@@ -107,7 +135,7 @@ static PyObject *pyrf_mmap_event__repr(struct pyrf_event *pevent)
 		     pevent->event.mmap.pgoff, pevent->event.mmap.filename) < 0) {
 		ret = PyErr_NoMemory();
 	} else {
-		ret = PyString_FromString(s);
+		ret = _PyUnicode_FromString(s);
 		free(s);
 	}
 	return ret;
@@ -138,7 +166,7 @@ static PyMemberDef pyrf_task_event__members[] = {
 
 static PyObject *pyrf_task_event__repr(struct pyrf_event *pevent)
 {
-	return PyString_FromFormat("{ type: %s, pid: %u, ppid: %u, tid: %u, "
+	return _PyUnicode_FromFormat("{ type: %s, pid: %u, ppid: %u, tid: %u, "
 				   "ptid: %u, time: %" PRIu64 "}",
 				   pevent->event.header.type == PERF_RECORD_FORK ? "fork" : "exit",
 				   pevent->event.fork.pid,
@@ -171,7 +199,7 @@ static PyMemberDef pyrf_comm_event__members[] = {
 
 static PyObject *pyrf_comm_event__repr(struct pyrf_event *pevent)
 {
-	return PyString_FromFormat("{ type: comm, pid: %u, tid: %u, comm: %s }",
+	return _PyUnicode_FromFormat("{ type: comm, pid: %u, tid: %u, comm: %s }",
 				   pevent->event.comm.pid,
 				   pevent->event.comm.tid,
 				   pevent->event.comm.comm);
@@ -202,7 +230,7 @@ static PyObject *pyrf_throttle_event__repr(struct pyrf_event *pevent)
 {
 	struct throttle_event *te = (struct throttle_event *)(&pevent->event.header + 1);
 
-	return PyString_FromFormat("{ type: %sthrottle, time: %" PRIu64 ", id: %" PRIu64
+	return _PyUnicode_FromFormat("{ type: %sthrottle, time: %" PRIu64 ", id: %" PRIu64
 				   ", stream_id: %" PRIu64 " }",
 				   pevent->event.header.type == PERF_RECORD_THROTTLE ? "" : "un",
 				   te->time, te->id, te->stream_id);
@@ -237,7 +265,7 @@ static PyObject *pyrf_lost_event__repr(struct pyrf_event *pevent)
 		     pevent->event.lost.id, pevent->event.lost.lost) < 0) {
 		ret = PyErr_NoMemory();
 	} else {
-		ret = PyString_FromString(s);
+		ret = _PyUnicode_FromString(s);
 		free(s);
 	}
 	return ret;
@@ -264,7 +292,7 @@ static PyMemberDef pyrf_read_event__members[] = {
 
 static PyObject *pyrf_read_event__repr(struct pyrf_event *pevent)
 {
-	return PyString_FromFormat("{ type: read, pid: %u, tid: %u }",
+	return _PyUnicode_FromFormat("{ type: read, pid: %u, tid: %u }",
 				   pevent->event.read.pid,
 				   pevent->event.read.tid);
 	/*
@@ -299,7 +327,7 @@ static PyObject *pyrf_sample_event__repr(struct pyrf_event *pevent)
 	if (asprintf(&s, "{ type: sample }") < 0) {
 		ret = PyErr_NoMemory();
 	} else {
-		ret = PyString_FromString(s);
+		ret = _PyUnicode_FromString(s);
 		free(s);
 	}
 	return ret;
@@ -330,7 +358,7 @@ tracepoint_field(struct pyrf_event *pe, struct format_field *field)
 		}
 		if (field->flags & FIELD_IS_STRING &&
 		    is_printable_array(data + offset, len)) {
-			ret = PyString_FromString((char *)data + offset);
+			ret = _PyUnicode_FromString((char *)data + offset);
 		} else {
 			ret = PyByteArray_FromStringAndSize((const char *) data + offset, len);
 			field->flags &= ~FIELD_IS_STRING;
@@ -352,7 +380,7 @@ tracepoint_field(struct pyrf_event *pe, struct format_field *field)
 static PyObject*
 get_tracepoint_field(struct pyrf_event *pevent, PyObject *attr_name)
 {
-	const char *str = PyString_AsString(PyObject_Str(attr_name));
+	const char *str = _PyUnicode_AsString(PyObject_Str(attr_name));
 	struct perf_evsel *evsel = pevent->evsel;
 	struct format_field *field;
 
@@ -416,7 +444,7 @@ static PyObject *pyrf_context_switch_event__repr(struct pyrf_event *pevent)
 		     !!(pevent->event.header.misc & PERF_RECORD_MISC_SWITCH_OUT)) < 0) {
 		ret = PyErr_NoMemory();
 	} else {
-		ret = PyString_FromString(s);
+		ret = _PyUnicode_FromString(s);
 		free(s);
 	}
 	return ret;
@@ -528,7 +556,7 @@ static int pyrf_cpu_map__init(struct pyrf_cpu_map *pcpus,
 static void pyrf_cpu_map__delete(struct pyrf_cpu_map *pcpus)
 {
 	cpu_map__put(pcpus->cpus);
-	pcpus->ob_type->tp_free((PyObject*)pcpus);
+	Py_TYPE(pcpus)->tp_free((PyObject*)pcpus);
 }
 
 static Py_ssize_t pyrf_cpu_map__length(PyObject *obj)
@@ -597,7 +625,7 @@ static int pyrf_thread_map__init(struct pyrf_thread_map *pthreads,
 static void pyrf_thread_map__delete(struct pyrf_thread_map *pthreads)
 {
 	thread_map__put(pthreads->threads);
-	pthreads->ob_type->tp_free((PyObject*)pthreads);
+	Py_TYPE(pthreads)->tp_free((PyObject*)pthreads);
 }
 
 static Py_ssize_t pyrf_thread_map__length(PyObject *obj)
@@ -759,7 +787,7 @@ static int pyrf_evsel__init(struct pyrf_evsel *pevsel,
 static void pyrf_evsel__delete(struct pyrf_evsel *pevsel)
 {
 	perf_evsel__exit(&pevsel->evsel);
-	pevsel->ob_type->tp_free((PyObject*)pevsel);
+	Py_TYPE(pevsel)->tp_free((PyObject*)pevsel);
 }
 
 static PyObject *pyrf_evsel__open(struct pyrf_evsel *pevsel,
@@ -850,7 +878,7 @@ static int pyrf_evlist__init(struct pyrf_evlist *pevlist,
 static void pyrf_evlist__delete(struct pyrf_evlist *pevlist)
 {
 	perf_evlist__exit(&pevlist->evlist);
-	pevlist->ob_type->tp_free((PyObject*)pevlist);
+	Py_TYPE(pevlist)->tp_free((PyObject*)pevlist);
 }
 
 static PyObject *pyrf_evlist__mmap(struct pyrf_evlist *pevlist,
@@ -902,12 +930,16 @@ static PyObject *pyrf_evlist__get_pollfd(struct pyrf_evlist *pevlist,
 
 	for (i = 0; i < evlist->pollfd.nr; ++i) {
 		PyObject *file;
+#if PY_MAJOR_VERSION < 3
 		FILE *fp = fdopen(evlist->pollfd.entries[i].fd, "r");
 
 		if (fp == NULL)
 			goto free_list;
 
 		file = PyFile_FromFile(fp, "perf", "r", NULL);
+#else
+		file = PyFile_FromFd(evlist->pollfd.entries[i].fd, "perf", "r", -1, NULL, NULL, NULL, 1);
+#endif
 		if (file == NULL)
 			goto free_list;
 
@@ -951,13 +983,18 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 	union perf_event *event;
 	int sample_id_all = 1, cpu;
 	static char *kwlist[] = { "cpu", "sample_id_all", NULL };
+	struct perf_mmap *md;
 	int err;
 
 	if (!PyArg_ParseTupleAndKeywords(args, kwargs, "i|i", kwlist,
 					 &cpu, &sample_id_all))
 		return NULL;
 
-	event = perf_evlist__mmap_read(evlist, cpu);
+	md = &evlist->mmap[cpu];
+	if (perf_mmap__read_init(md) < 0)
+		goto end;
+
+	event = perf_mmap__read_event(md);
 	if (event != NULL) {
 		PyObject *pyevent = pyrf_event__new(event);
 		struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
@@ -967,22 +1004,24 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
 			return PyErr_NoMemory();
 
 		evsel = perf_evlist__event2evsel(evlist, event);
-		if (!evsel)
+		if (!evsel) {
+			Py_INCREF(Py_None);
 			return Py_None;
+		}
 
 		pevent->evsel = evsel;
 
 		err = perf_evsel__parse_sample(evsel, event, &pevent->sample);
 
 		/* Consume the even only after we parsed it out. */
-		perf_evlist__mmap_consume(evlist, cpu);
+		perf_mmap__consume(md);
 
 		if (err)
 			return PyErr_Format(PyExc_OSError,
 					    "perf: can't parse sample, err=%d", err);
 		return pyevent;
 	}
-
+end:
 	Py_INCREF(Py_None);
 	return Py_None;
 }
@@ -1194,9 +1233,9 @@ static PyObject *pyrf__tracepoint(struct pyrf_evsel *pevsel,
 
 	tp_format = trace_event__tp_format(sys, name);
 	if (IS_ERR(tp_format))
-		return PyInt_FromLong(-1);
+		return _PyLong_FromLong(-1);
 
-	return PyInt_FromLong(tp_format->id);
+	return _PyLong_FromLong(tp_format->id);
 }
 
 static PyMethodDef perf__methods[] = {
@@ -1209,11 +1248,31 @@ static PyMethodDef perf__methods[] = {
 	{ .ml_name = NULL, }
 };
 
+#if PY_MAJOR_VERSION < 3
 PyMODINIT_FUNC initperf(void)
+#else
+PyMODINIT_FUNC PyInit_perf(void)
+#endif
 {
 	PyObject *obj;
 	int i;
-	PyObject *dict, *module = Py_InitModule("perf", perf__methods);
+	PyObject *dict;
+#if PY_MAJOR_VERSION < 3
+	PyObject *module = Py_InitModule("perf", perf__methods);
+#else
+	static struct PyModuleDef moduledef = {
+		PyModuleDef_HEAD_INIT,
+		"perf",			/* m_name */
+		"",			/* m_doc */
+		-1,			/* m_size */
+		perf__methods,		/* m_methods */
+		NULL,			/* m_reload */
+		NULL,			/* m_traverse */
+		NULL,			/* m_clear */
+		NULL,			/* m_free */
+	};
+	PyObject *module = PyModule_Create(&moduledef);
+#endif
 
 	if (module == NULL ||
 	    pyrf_event__setup_types() < 0 ||
@@ -1221,7 +1280,11 @@ PyMODINIT_FUNC initperf(void)
 	    pyrf_evsel__setup_types() < 0 ||
 	    pyrf_thread_map__setup_types() < 0 ||
 	    pyrf_cpu_map__setup_types() < 0)
+#if PY_MAJOR_VERSION < 3
 		return;
+#else
+		return module;
+#endif
 
 	/* The page_size is placed in util object. */
 	page_size = sysconf(_SC_PAGE_SIZE);
@@ -1270,7 +1333,7 @@ PyMODINIT_FUNC initperf(void)
 		goto error;
 
 	for (i = 0; perf__constants[i].name != NULL; i++) {
-		obj = PyInt_FromLong(perf__constants[i].value);
+		obj = _PyLong_FromLong(perf__constants[i].value);
 		if (obj == NULL)
 			goto error;
 		PyDict_SetItemString(dict, perf__constants[i].name, obj);
@@ -1280,6 +1343,9 @@ PyMODINIT_FUNC initperf(void)
 error:
 	if (PyErr_Occurred())
 		PyErr_SetString(PyExc_ImportError, "perf: Init failed!");
+#if PY_MAJOR_VERSION >= 3
+	return module;
+#endif
 }
 
 /*
diff --git a/tools/perf/util/record.c b/tools/perf/util/record.c
index 6f09e4962dad..9cfc7bf16531 100644
--- a/tools/perf/util/record.c
+++ b/tools/perf/util/record.c
@@ -5,6 +5,7 @@
 #include "parse-events.h"
 #include <errno.h>
 #include <api/fs/fs.h>
+#include <subcmd/parse-options.h>
 #include "util.h"
 #include "cloexec.h"
 
@@ -219,11 +220,21 @@ static int record_opts__config_freq(struct record_opts *opts)
 	 * User specified frequency is over current maximum.
 	 */
 	if (user_freq && (max_rate < opts->freq)) {
-		pr_err("Maximum frequency rate (%u) reached.\n"
-		   "Please use -F freq option with lower value or consider\n"
-		   "tweaking /proc/sys/kernel/perf_event_max_sample_rate.\n",
-		   max_rate);
-		return -1;
+		if (opts->strict_freq) {
+			pr_err("error: Maximum frequency rate (%'u Hz) exceeded.\n"
+			       "       Please use -F freq option with a lower value or consider\n"
+			       "       tweaking /proc/sys/kernel/perf_event_max_sample_rate.\n",
+			       max_rate);
+			return -1;
+		} else {
+			pr_warning("warning: Maximum frequency rate (%'u Hz) exceeded, throttling from %'u Hz to %'u Hz.\n"
+				   "         The limit can be raised via /proc/sys/kernel/perf_event_max_sample_rate.\n"
+				   "         The kernel will lower it when perf's interrupts take too long.\n"
+				   "         Use --strict-freq to disable this throttling, refusing to record.\n",
+				   max_rate, opts->freq, max_rate);
+
+			opts->freq = max_rate;
+		}
 	}
 
 	/*
@@ -291,3 +302,25 @@ out_delete:
 	perf_evlist__delete(temp_evlist);
 	return ret;
 }
+
+int record__parse_freq(const struct option *opt, const char *str, int unset __maybe_unused)
+{
+	unsigned int freq;
+	struct record_opts *opts = opt->value;
+
+	if (!str)
+		return -EINVAL;
+
+	if (strcasecmp(str, "max") == 0) {
+		if (get_max_rate(&freq)) {
+			pr_err("couldn't read /proc/sys/kernel/perf_event_max_sample_rate\n");
+			return -1;
+		}
+		pr_info("info: Using a maximum frequency rate of %'d Hz\n", freq);
+	} else {
+		freq = atoi(str);
+	}
+
+	opts->user_freq = freq;
+	return 0;
+}
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index ea070883c593..10dd5fce082b 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -49,7 +49,37 @@
 #include "print_binary.h"
 #include "stat.h"
 
+#if PY_MAJOR_VERSION < 3
+#define _PyUnicode_FromString(arg) \
+  PyString_FromString(arg)
+#define _PyUnicode_FromStringAndSize(arg1, arg2) \
+  PyString_FromStringAndSize((arg1), (arg2))
+#define _PyBytes_FromStringAndSize(arg1, arg2) \
+  PyString_FromStringAndSize((arg1), (arg2))
+#define _PyLong_FromLong(arg) \
+  PyInt_FromLong(arg)
+#define _PyLong_AsLong(arg) \
+  PyInt_AsLong(arg)
+#define _PyCapsule_New(arg1, arg2, arg3) \
+  PyCObject_FromVoidPtr((arg1), (arg2))
+
 PyMODINIT_FUNC initperf_trace_context(void);
+#else
+#define _PyUnicode_FromString(arg) \
+  PyUnicode_FromString(arg)
+#define _PyUnicode_FromStringAndSize(arg1, arg2) \
+  PyUnicode_FromStringAndSize((arg1), (arg2))
+#define _PyBytes_FromStringAndSize(arg1, arg2) \
+  PyBytes_FromStringAndSize((arg1), (arg2))
+#define _PyLong_FromLong(arg) \
+  PyLong_FromLong(arg)
+#define _PyLong_AsLong(arg) \
+  PyLong_AsLong(arg)
+#define _PyCapsule_New(arg1, arg2, arg3) \
+  PyCapsule_New((arg1), (arg2), (arg3))
+
+PyMODINIT_FUNC PyInit_perf_trace_context(void);
+#endif
 
 #define TRACE_EVENT_TYPE_MAX				\
 	((1 << (sizeof(unsigned short) * 8)) - 1)
@@ -135,7 +165,7 @@ static int get_argument_count(PyObject *handler)
 		PyObject *arg_count_obj = PyObject_GetAttrString(code_obj,
 			"co_argcount");
 		if (arg_count_obj) {
-			arg_count = (int) PyInt_AsLong(arg_count_obj);
+			arg_count = (int) _PyLong_AsLong(arg_count_obj);
 			Py_DECREF(arg_count_obj);
 		}
 		Py_DECREF(code_obj);
@@ -182,10 +212,10 @@ static void define_value(enum print_arg_type field_type,
 
 	value = eval_flag(field_value);
 
-	PyTuple_SetItem(t, n++, PyString_FromString(ev_name));
-	PyTuple_SetItem(t, n++, PyString_FromString(field_name));
-	PyTuple_SetItem(t, n++, PyInt_FromLong(value));
-	PyTuple_SetItem(t, n++, PyString_FromString(field_str));
+	PyTuple_SetItem(t, n++, _PyUnicode_FromString(ev_name));
+	PyTuple_SetItem(t, n++, _PyUnicode_FromString(field_name));
+	PyTuple_SetItem(t, n++, _PyLong_FromLong(value));
+	PyTuple_SetItem(t, n++, _PyUnicode_FromString(field_str));
 
 	try_call_object(handler_name, t);
 
@@ -223,10 +253,10 @@ static void define_field(enum print_arg_type field_type,
 	if (!t)
 		Py_FatalError("couldn't create Python tuple");
 
-	PyTuple_SetItem(t, n++, PyString_FromString(ev_name));
-	PyTuple_SetItem(t, n++, PyString_FromString(field_name));
+	PyTuple_SetItem(t, n++, _PyUnicode_FromString(ev_name));
+	PyTuple_SetItem(t, n++, _PyUnicode_FromString(field_name));
 	if (field_type == PRINT_FLAGS)
-		PyTuple_SetItem(t, n++, PyString_FromString(delim));
+		PyTuple_SetItem(t, n++, _PyUnicode_FromString(delim));
 
 	try_call_object(handler_name, t);
 
@@ -325,12 +355,12 @@ static PyObject *get_field_numeric_entry(struct event_format *event,
 		if (field->flags & FIELD_IS_SIGNED) {
 			if ((long long)val >= LONG_MIN &&
 					(long long)val <= LONG_MAX)
-				obj = PyInt_FromLong(val);
+				obj = _PyLong_FromLong(val);
 			else
 				obj = PyLong_FromLongLong(val);
 		} else {
 			if (val <= LONG_MAX)
-				obj = PyInt_FromLong(val);
+				obj = _PyLong_FromLong(val);
 			else
 				obj = PyLong_FromUnsignedLongLong(val);
 		}
@@ -389,9 +419,9 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
 			pydict_set_item_string_decref(pysym, "end",
 					PyLong_FromUnsignedLongLong(node->sym->end));
 			pydict_set_item_string_decref(pysym, "binding",
-					PyInt_FromLong(node->sym->binding));
+					_PyLong_FromLong(node->sym->binding));
 			pydict_set_item_string_decref(pysym, "name",
-					PyString_FromStringAndSize(node->sym->name,
+					_PyUnicode_FromStringAndSize(node->sym->name,
 							node->sym->namelen));
 			pydict_set_item_string_decref(pyelem, "sym", pysym);
 		}
@@ -406,7 +436,7 @@ static PyObject *python_process_callchain(struct perf_sample *sample,
 					dsoname = map->dso->name;
 			}
 			pydict_set_item_string_decref(pyelem, "dso",
-					PyString_FromString(dsoname));
+					_PyUnicode_FromString(dsoname));
 		}
 
 		callchain_cursor_advance(&callchain_cursor);
@@ -483,16 +513,16 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
 	if (!dict_sample)
 		Py_FatalError("couldn't create Python dictionary");
 
-	pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
-	pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize(
+	pydict_set_item_string_decref(dict, "ev_name", _PyUnicode_FromString(perf_evsel__name(evsel)));
+	pydict_set_item_string_decref(dict, "attr", _PyUnicode_FromStringAndSize(
 			(const char *)&evsel->attr, sizeof(evsel->attr)));
 
 	pydict_set_item_string_decref(dict_sample, "pid",
-			PyInt_FromLong(sample->pid));
+			_PyLong_FromLong(sample->pid));
 	pydict_set_item_string_decref(dict_sample, "tid",
-			PyInt_FromLong(sample->tid));
+			_PyLong_FromLong(sample->tid));
 	pydict_set_item_string_decref(dict_sample, "cpu",
-			PyInt_FromLong(sample->cpu));
+			_PyLong_FromLong(sample->cpu));
 	pydict_set_item_string_decref(dict_sample, "ip",
 			PyLong_FromUnsignedLongLong(sample->ip));
 	pydict_set_item_string_decref(dict_sample, "time",
@@ -504,17 +534,17 @@ static PyObject *get_perf_sample_dict(struct perf_sample *sample,
 	set_sample_read_in_dict(dict_sample, sample, evsel);
 	pydict_set_item_string_decref(dict, "sample", dict_sample);
 
-	pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize(
+	pydict_set_item_string_decref(dict, "raw_buf", _PyBytes_FromStringAndSize(
 			(const char *)sample->raw_data, sample->raw_size));
 	pydict_set_item_string_decref(dict, "comm",
-			PyString_FromString(thread__comm_str(al->thread)));
+			_PyUnicode_FromString(thread__comm_str(al->thread)));
 	if (al->map) {
 		pydict_set_item_string_decref(dict, "dso",
-			PyString_FromString(al->map->dso->name));
+			_PyUnicode_FromString(al->map->dso->name));
 	}
 	if (al->sym) {
 		pydict_set_item_string_decref(dict, "symbol",
-			PyString_FromString(al->sym->name));
+			_PyUnicode_FromString(al->sym->name));
 	}
 
 	pydict_set_item_string_decref(dict, "callchain", callchain);
@@ -574,9 +604,9 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	scripting_context->event_data = data;
 	scripting_context->pevent = evsel->tp_format->pevent;
 
-	context = PyCObject_FromVoidPtr(scripting_context, NULL);
+	context = _PyCapsule_New(scripting_context, NULL, NULL);
 
-	PyTuple_SetItem(t, n++, PyString_FromString(handler_name));
+	PyTuple_SetItem(t, n++, _PyUnicode_FromString(handler_name));
 	PyTuple_SetItem(t, n++, context);
 
 	/* ip unwinding */
@@ -585,18 +615,18 @@ static void python_process_tracepoint(struct perf_sample *sample,
 	Py_INCREF(callchain);
 
 	if (!dict) {
-		PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
-		PyTuple_SetItem(t, n++, PyInt_FromLong(s));
-		PyTuple_SetItem(t, n++, PyInt_FromLong(ns));
-		PyTuple_SetItem(t, n++, PyInt_FromLong(pid));
-		PyTuple_SetItem(t, n++, PyString_FromString(comm));
+		PyTuple_SetItem(t, n++, _PyLong_FromLong(cpu));
+		PyTuple_SetItem(t, n++, _PyLong_FromLong(s));
+		PyTuple_SetItem(t, n++, _PyLong_FromLong(ns));
+		PyTuple_SetItem(t, n++, _PyLong_FromLong(pid));
+		PyTuple_SetItem(t, n++, _PyUnicode_FromString(comm));
 		PyTuple_SetItem(t, n++, callchain);
 	} else {
-		pydict_set_item_string_decref(dict, "common_cpu", PyInt_FromLong(cpu));
-		pydict_set_item_string_decref(dict, "common_s", PyInt_FromLong(s));
-		pydict_set_item_string_decref(dict, "common_ns", PyInt_FromLong(ns));
-		pydict_set_item_string_decref(dict, "common_pid", PyInt_FromLong(pid));
-		pydict_set_item_string_decref(dict, "common_comm", PyString_FromString(comm));
+		pydict_set_item_string_decref(dict, "common_cpu", _PyLong_FromLong(cpu));
+		pydict_set_item_string_decref(dict, "common_s", _PyLong_FromLong(s));
+		pydict_set_item_string_decref(dict, "common_ns", _PyLong_FromLong(ns));
+		pydict_set_item_string_decref(dict, "common_pid", _PyLong_FromLong(pid));
+		pydict_set_item_string_decref(dict, "common_comm", _PyUnicode_FromString(comm));
 		pydict_set_item_string_decref(dict, "common_callchain", callchain);
 	}
 	for (field = event->format.fields; field; field = field->next) {
@@ -615,7 +645,7 @@ static void python_process_tracepoint(struct perf_sample *sample,
 			}
 			if (field->flags & FIELD_IS_STRING &&
 			    is_printable_array(data + offset, len)) {
-				obj = PyString_FromString((char *) data + offset);
+				obj = _PyUnicode_FromString((char *) data + offset);
 			} else {
 				obj = PyByteArray_FromStringAndSize((const char *) data + offset, len);
 				field->flags &= ~FIELD_IS_STRING;
@@ -668,7 +698,7 @@ static PyObject *tuple_new(unsigned int sz)
 static int tuple_set_u64(PyObject *t, unsigned int pos, u64 val)
 {
 #if BITS_PER_LONG == 64
-	return PyTuple_SetItem(t, pos, PyInt_FromLong(val));
+	return PyTuple_SetItem(t, pos, _PyLong_FromLong(val));
 #endif
 #if BITS_PER_LONG == 32
 	return PyTuple_SetItem(t, pos, PyLong_FromLongLong(val));
@@ -677,12 +707,12 @@ static int tuple_set_u64(PyObject *t, unsigned int pos, u64 val)
 
 static int tuple_set_s32(PyObject *t, unsigned int pos, s32 val)
 {
-	return PyTuple_SetItem(t, pos, PyInt_FromLong(val));
+	return PyTuple_SetItem(t, pos, _PyLong_FromLong(val));
 }
 
 static int tuple_set_string(PyObject *t, unsigned int pos, const char *s)
 {
-	return PyTuple_SetItem(t, pos, PyString_FromString(s));
+	return PyTuple_SetItem(t, pos, _PyUnicode_FromString(s));
 }
 
 static int python_export_evsel(struct db_export *dbe, struct perf_evsel *evsel)
@@ -1029,8 +1059,8 @@ process_stat(struct perf_evsel *counter, int cpu, int thread, u64 tstamp,
 		return;
 	}
 
-	PyTuple_SetItem(t, n++, PyInt_FromLong(cpu));
-	PyTuple_SetItem(t, n++, PyInt_FromLong(thread));
+	PyTuple_SetItem(t, n++, _PyLong_FromLong(cpu));
+	PyTuple_SetItem(t, n++, _PyLong_FromLong(thread));
 
 	tuple_set_u64(t, n++, tstamp);
 	tuple_set_u64(t, n++, count->val);
@@ -1212,27 +1242,58 @@ static void set_table_handlers(struct tables *tables)
 	SET_TABLE_HANDLER(call_return);
 }
 
+#if PY_MAJOR_VERSION < 3
+static void _free_command_line(const char **command_line, int num)
+{
+	free(command_line);
+}
+#else
+static void _free_command_line(wchar_t **command_line, int num)
+{
+	int i;
+	for (i = 0; i < num; i++)
+		PyMem_RawFree(command_line[i]);
+	free(command_line);
+}
+#endif
+
+
 /*
  * Start trace script
  */
 static int python_start_script(const char *script, int argc, const char **argv)
 {
 	struct tables *tables = &tables_global;
+#if PY_MAJOR_VERSION < 3
 	const char **command_line;
+#else
+	wchar_t **command_line;
+#endif
 	char buf[PATH_MAX];
 	int i, err = 0;
 	FILE *fp;
 
+#if PY_MAJOR_VERSION < 3
 	command_line = malloc((argc + 1) * sizeof(const char *));
 	command_line[0] = script;
 	for (i = 1; i < argc + 1; i++)
 		command_line[i] = argv[i - 1];
+#else
+	command_line = malloc((argc + 1) * sizeof(wchar_t *));
+	command_line[0] = Py_DecodeLocale(script, NULL);
+	for (i = 1; i < argc + 1; i++)
+		command_line[i] = Py_DecodeLocale(argv[i - 1], NULL);
+#endif
 
 	Py_Initialize();
 
+#if PY_MAJOR_VERSION < 3
 	initperf_trace_context();
-
 	PySys_SetArgv(argc + 1, (char **)command_line);
+#else
+	PyInit_perf_trace_context();
+	PySys_SetArgv(argc + 1, command_line);
+#endif
 
 	fp = fopen(script, "r");
 	if (!fp) {
@@ -1262,12 +1323,12 @@ static int python_start_script(const char *script, int argc, const char **argv)
 			goto error;
 	}
 
-	free(command_line);
+	_free_command_line(command_line, argc + 1);
 
 	return err;
 error:
 	Py_Finalize();
-	free(command_line);
+	_free_command_line(command_line, argc + 1);
 
 	return err;
 }
diff --git a/tools/perf/util/setup.py b/tools/perf/util/setup.py
index af415febbc46..001be4f9d3b9 100644
--- a/tools/perf/util/setup.py
+++ b/tools/perf/util/setup.py
@@ -1,4 +1,4 @@
-#!/usr/bin/python2
+#!/usr/bin/python
 
 from os import getenv
 
@@ -28,6 +28,8 @@ class install_lib(_install_lib):
 cflags = getenv('CFLAGS', '').split()
 # switch off several checks (need to be at the end of cflags list)
 cflags += ['-fno-strict-aliasing', '-Wno-write-strings', '-Wno-unused-parameter' ]
+if cc != "clang":
+    cflags += ['-Wno-cast-function-type' ]
 
 src_perf  = getenv('srctree') + '/tools/perf'
 build_lib = getenv('PYTHON_EXTBUILD_LIB')
@@ -35,11 +37,11 @@ build_tmp = getenv('PYTHON_EXTBUILD_TMP')
 libtraceevent = getenv('LIBTRACEEVENT')
 libapikfs = getenv('LIBAPI')
 
-ext_sources = [f.strip() for f in file('util/python-ext-sources')
+ext_sources = [f.strip() for f in open('util/python-ext-sources')
 				if len(f.strip()) > 0 and f[0] != '#']
 
 # use full paths with source files
-ext_sources = map(lambda x: '%s/%s' % (src_perf, x) , ext_sources)
+ext_sources = list(map(lambda x: '%s/%s' % (src_perf, x) , ext_sources))
 
 perf = Extension('perf',
 		  sources = ext_sources,
diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
index 2da4d0456a03..e8514f651865 100644
--- a/tools/perf/util/sort.c
+++ b/tools/perf/util/sort.c
@@ -111,17 +111,20 @@ struct sort_entry sort_thread = {
 
 /* --sort comm */
 
+/*
+ * We can't use pointer comparison in functions below,
+ * because it gives different results based on pointer
+ * values, which could break some sorting assumptions.
+ */
 static int64_t
 sort__comm_cmp(struct hist_entry *left, struct hist_entry *right)
 {
-	/* Compare the addr that should be unique among comm */
 	return strcmp(comm__str(right->comm), comm__str(left->comm));
 }
 
 static int64_t
 sort__comm_collapse(struct hist_entry *left, struct hist_entry *right)
 {
-	/* Compare the addr that should be unique among comm */
 	return strcmp(comm__str(right->comm), comm__str(left->comm));
 }
 
diff --git a/tools/perf/util/stat.c b/tools/perf/util/stat.c
index 32235657c1ac..a0061e0b0fad 100644
--- a/tools/perf/util/stat.c
+++ b/tools/perf/util/stat.c
@@ -92,7 +92,7 @@ static const char *id_str[PERF_STAT_EVSEL_ID__MAX] = {
 };
 #undef ID
 
-void perf_stat_evsel_id_init(struct perf_evsel *evsel)
+static void perf_stat_evsel_id_init(struct perf_evsel *evsel)
 {
 	struct perf_stat_evsel *ps = evsel->stats;
 	int i;
diff --git a/tools/perf/util/stat.h b/tools/perf/util/stat.h
index dbc6f7134f61..8f56ba4fd258 100644
--- a/tools/perf/util/stat.h
+++ b/tools/perf/util/stat.h
@@ -90,6 +90,8 @@ struct perf_stat_config {
 	bool		scale;
 	FILE		*output;
 	unsigned int	interval;
+	unsigned int	timeout;
+	int		times;
 	struct runtime_stat *stats;
 	int		stats_num;
 };
@@ -126,8 +128,6 @@ bool __perf_evsel_stat__is(struct perf_evsel *evsel,
 #define perf_stat_evsel__is(evsel, id) \
 	__perf_evsel_stat__is(evsel, PERF_STAT_EVSEL_ID__ ## id)
 
-void perf_stat_evsel_id_init(struct perf_evsel *evsel);
-
 extern struct runtime_stat rt_stat;
 extern struct stats walltime_nsecs_stats;
 
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index cc065d4bfafc..62b2dd2253eb 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1582,7 +1582,7 @@ int dso__load(struct dso *dso, struct map *map)
 		bool next_slot = false;
 		bool is_reg;
 		bool nsexit;
-		int sirc;
+		int sirc = -1;
 
 		enum dso_binary_type symtab_type = binary_type_symtab[i];
 
@@ -1600,16 +1600,14 @@ int dso__load(struct dso *dso, struct map *map)
 			nsinfo__mountns_exit(&nsc);
 
 		is_reg = is_regular_file(name);
-		sirc = symsrc__init(ss, dso, name, symtab_type);
+		if (is_reg)
+			sirc = symsrc__init(ss, dso, name, symtab_type);
 
 		if (nsexit)
 			nsinfo__mountns_enter(dso->nsinfo, &nsc);
 
-		if (!is_reg || sirc < 0) {
-			if (sirc >= 0)
-				symsrc__destroy(ss);
+		if (!is_reg || sirc < 0)
 			continue;
-		}
 
 		if (!syms_ss && symsrc__has_symtab(ss)) {
 			syms_ss = ss;
@@ -1960,8 +1958,7 @@ static int dso__load_guest_kernel_sym(struct dso *dso, struct map *map)
 		pr_debug("Using %s for symbols\n", kallsyms_filename);
 	if (err > 0 && !dso__is_kcore(dso)) {
 		dso->binary_type = DSO_BINARY_TYPE__GUEST_KALLSYMS;
-		machine__mmap_name(machine, path, sizeof(path));
-		dso__set_long_name(dso, strdup(path), true);
+		dso__set_long_name(dso, machine->mmap_name, false);
 		map__fixup_start(map);
 		map__fixup_end(map);
 	}
@@ -2224,3 +2221,25 @@ int symbol__config_symfs(const struct option *opt __maybe_unused,
 	free(bf);
 	return 0;
 }
+
+struct mem_info *mem_info__get(struct mem_info *mi)
+{
+	if (mi)
+		refcount_inc(&mi->refcnt);
+	return mi;
+}
+
+void mem_info__put(struct mem_info *mi)
+{
+	if (mi && refcount_dec_and_test(&mi->refcnt))
+		free(mi);
+}
+
+struct mem_info *mem_info__new(void)
+{
+	struct mem_info *mi = zalloc(sizeof(*mi));
+
+	if (mi)
+		refcount_set(&mi->refcnt, 1);
+	return mi;
+}
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index 0563f33c1eb3..70c16741f50a 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -200,9 +200,10 @@ struct branch_info {
 };
 
 struct mem_info {
-	struct addr_map_symbol iaddr;
-	struct addr_map_symbol daddr;
-	union perf_mem_data_src data_src;
+	struct addr_map_symbol	iaddr;
+	struct addr_map_symbol	daddr;
+	union perf_mem_data_src	data_src;
+	refcount_t		refcnt;
 };
 
 struct addr_location {
@@ -389,4 +390,16 @@ int sdt_notes__get_count(struct list_head *start);
 #define SDT_NOTE_NAME "stapsdt"
 #define NR_ADDR 3
 
+struct mem_info *mem_info__new(void);
+struct mem_info *mem_info__get(struct mem_info *mi);
+void   mem_info__put(struct mem_info *mi);
+
+static inline void __mem_info__zput(struct mem_info **mi)
+{
+	mem_info__put(*mi);
+	*mi = NULL;
+}
+
+#define mem_info__zput(mi) __mem_info__zput(&mi)
+
 #endif /* __PERF_SYMBOL */
diff --git a/tools/perf/util/syscalltbl.c b/tools/perf/util/syscalltbl.c
index 303bdb84ab5a..895122d638dd 100644
--- a/tools/perf/util/syscalltbl.c
+++ b/tools/perf/util/syscalltbl.c
@@ -30,6 +30,14 @@ static const char **syscalltbl_native = syscalltbl_x86_64;
 #include <asm/syscalls_64.c>
 const int syscalltbl_native_max_id = SYSCALLTBL_S390_64_MAX_ID;
 static const char **syscalltbl_native = syscalltbl_s390_64;
+#elif defined(__powerpc64__)
+#include <asm/syscalls_64.c>
+const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_64_MAX_ID;
+static const char **syscalltbl_native = syscalltbl_powerpc_64;
+#elif defined(__powerpc__)
+#include <asm/syscalls_32.c>
+const int syscalltbl_native_max_id = SYSCALLTBL_POWERPC_32_MAX_ID;
+static const char **syscalltbl_native = syscalltbl_powerpc_32;
 #endif
 
 struct syscall {
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 40cfa36c022a..14d44c3235b8 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -26,7 +26,6 @@ struct thread {
 	pid_t			ppid;
 	int			cpu;
 	refcount_t		refcnt;
-	char			shortname[3];
 	bool			comm_set;
 	int			comm_len;
 	bool			dead; /* if set thread has exited */
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index 3e1038f6491c..5d467d8ae9ab 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -32,6 +32,7 @@ static void thread_map__reset(struct thread_map *map, int start, int nr)
 	size_t size = (nr - start) * sizeof(map->map[0]);
 
 	memset(&map->map[start], 0, size);
+	map->err_thread = -1;
 }
 
 static struct thread_map *thread_map__realloc(struct thread_map *map, int nr)
@@ -323,7 +324,7 @@ out_free_threads:
 }
 
 struct thread_map *thread_map__new_str(const char *pid, const char *tid,
-				       uid_t uid, bool per_thread)
+				       uid_t uid, bool all_threads)
 {
 	if (pid)
 		return thread_map__new_by_pid_str(pid);
@@ -331,7 +332,7 @@ struct thread_map *thread_map__new_str(const char *pid, const char *tid,
 	if (!tid && uid != UINT_MAX)
 		return thread_map__new_by_uid(uid);
 
-	if (per_thread)
+	if (all_threads)
 		return thread_map__new_all_cpus();
 
 	return thread_map__new_by_tid_str(tid);
diff --git a/tools/perf/util/thread_map.h b/tools/perf/util/thread_map.h
index 0a806b99e73c..2f689c90a8c6 100644
--- a/tools/perf/util/thread_map.h
+++ b/tools/perf/util/thread_map.h
@@ -14,6 +14,7 @@ struct thread_map_data {
 struct thread_map {
 	refcount_t refcnt;
 	int nr;
+	int err_thread;
 	struct thread_map_data map[];
 };
 
@@ -31,7 +32,7 @@ struct thread_map *thread_map__get(struct thread_map *map);
 void thread_map__put(struct thread_map *map);
 
 struct thread_map *thread_map__new_str(const char *pid,
-		const char *tid, uid_t uid, bool per_thread);
+		const char *tid, uid_t uid, bool all_threads);
 
 struct thread_map *thread_map__new_by_tid_str(const char *tid_str);
 
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 1e9c974faf67..7bdd239c795c 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -50,7 +50,7 @@ static int __report_module(struct addr_location *al, u64 ip,
 
 	if (!mod)
 		mod = dwfl_report_elf(ui->dwfl, dso->short_name,
-				      dso->long_name, -1, al->map->start,
+				      (dso->symsrc_filename ? dso->symsrc_filename : dso->long_name), -1, al->map->start,
 				      false);
 
 	return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1;
@@ -236,7 +236,8 @@ int unwind__get_entries(unwind_entry_cb_t cb, void *arg,
 	if (err)
 		goto out;
 
-	if (!dwfl_attach_state(ui->dwfl, EM_NONE, thread->tid, &callbacks, ui))
+	err = !dwfl_attach_state(ui->dwfl, EM_NONE, thread->tid, &callbacks, ui);
+	if (err)
 		goto out;
 
 	err = dwfl_getthread_frames(ui->dwfl, thread->tid, frame_callback, ui);