Merge branch 'linus' into x86/pti to pick up upstream changes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

283 files changed, 14144 insertions, 2672 deletions

diff --git a/tools/arch/powerpc/include/uapi/asm/kvm.h b/tools/arch/powerpc/include/uapi/asm/kvm.h
index 637b7263cb86..833ed9a16adf 100644
--- a/tools/arch/powerpc/include/uapi/asm/kvm.h
+++ b/tools/arch/powerpc/include/uapi/asm/kvm.h
@@ -632,6 +632,8 @@ struct kvm_ppc_cpu_char {
 #define KVM_REG_PPC_TIDR        (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbc)
 #define KVM_REG_PPC_PSSCR       (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbd)
 
+#define KVM_REG_PPC_DEC_EXPIRY  (KVM_REG_PPC | KVM_REG_SIZE_U64 | 0xbe)
+
 /* Transactional Memory checkpointed state:
  * This is all GPRs, all VSX regs and a subset of SPRs
  */
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/arch/s390/include/uapi/asm/unistd.h b/tools/arch/s390/include/uapi/asm/unistd.h
deleted file mode 100644
index 725120939051..000000000000
--- a/tools/arch/s390/include/uapi/asm/unistd.h
+++ /dev/null
@@ -1,412 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
-/*
- *  S390 version
- *
- *  Derived from "include/asm-i386/unistd.h"
- */
-
-#ifndef _UAPI_ASM_S390_UNISTD_H_
-#define _UAPI_ASM_S390_UNISTD_H_
-
-/*
- * This file contains the system call numbers.
- */
-
-#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_restart_syscall      7
-#define __NR_creat                8
-#define __NR_link                 9
-#define __NR_unlink              10
-#define __NR_execve              11
-#define __NR_chdir               12
-#define __NR_mknod               14
-#define __NR_chmod               15
-#define __NR_lseek               19
-#define __NR_getpid              20
-#define __NR_mount               21
-#define __NR_umount              22
-#define __NR_ptrace              26
-#define __NR_alarm               27
-#define __NR_pause               29
-#define __NR_utime               30
-#define __NR_access              33
-#define __NR_nice                34
-#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_brk                 45
-#define __NR_signal              48
-#define __NR_acct                51
-#define __NR_umount2             52
-#define __NR_ioctl               54
-#define __NR_fcntl               55
-#define __NR_setpgid             57
-#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_sigsuspend          72
-#define __NR_sigpending          73
-#define __NR_sethostname         74
-#define __NR_setrlimit           75
-#define __NR_getrusage           77
-#define __NR_gettimeofday        78
-#define __NR_settimeofday        79
-#define __NR_symlink             83
-#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_getpriority         96
-#define __NR_setpriority         97
-#define __NR_statfs              99
-#define __NR_fstatfs            100
-#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_lookup_dcookie     110
-#define __NR_vhangup            111
-#define __NR_idle               112
-#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_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_getdents           141
-#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_query_module       167
-#define __NR_poll               168
-#define __NR_nfsservctl         169
-#define __NR_prctl              172
-#define __NR_rt_sigreturn       173
-#define __NR_rt_sigaction       174
-#define __NR_rt_sigprocmask     175
-#define __NR_rt_sigpending      176
-#define __NR_rt_sigtimedwait    177
-#define __NR_rt_sigqueueinfo    178
-#define __NR_rt_sigsuspend      179
-#define __NR_pread64            180
-#define __NR_pwrite64           181
-#define __NR_getcwd             183
-#define __NR_capget             184
-#define __NR_capset             185
-#define __NR_sigaltstack        186
-#define __NR_sendfile           187
-#define __NR_getpmsg            188
-#define __NR_putpmsg            189
-#define __NR_vfork              190
-#define __NR_pivot_root         217
-#define __NR_mincore            218
-#define __NR_madvise            219
-#define __NR_getdents64         220
-#define __NR_readahead          222
-#define __NR_setxattr           224
-#define __NR_lsetxattr          225
-#define __NR_fsetxattr          226
-#define __NR_getxattr           227
-#define __NR_lgetxattr          228
-#define __NR_fgetxattr          229
-#define __NR_listxattr          230
-#define __NR_llistxattr         231
-#define __NR_flistxattr         232
-#define __NR_removexattr        233
-#define __NR_lremovexattr       234
-#define __NR_fremovexattr       235
-#define __NR_gettid             236
-#define __NR_tkill              237
-#define __NR_futex              238
-#define __NR_sched_setaffinity  239
-#define __NR_sched_getaffinity  240
-#define __NR_tgkill             241
-/* Number 242 is reserved for tux */
-#define __NR_io_setup           243
-#define __NR_io_destroy         244
-#define __NR_io_getevents       245
-#define __NR_io_submit          246
-#define __NR_io_cancel          247
-#define __NR_exit_group         248
-#define __NR_epoll_create       249
-#define __NR_epoll_ctl          250
-#define __NR_epoll_wait         251
-#define __NR_set_tid_address    252
-#define __NR_fadvise64          253
-#define __NR_timer_create       254
-#define __NR_timer_settime      255
-#define __NR_timer_gettime      256
-#define __NR_timer_getoverrun   257
-#define __NR_timer_delete       258
-#define __NR_clock_settime      259
-#define __NR_clock_gettime      260
-#define __NR_clock_getres       261
-#define __NR_clock_nanosleep    262
-/* Number 263 is reserved for vserver */
-#define __NR_statfs64           265
-#define __NR_fstatfs64          266
-#define __NR_remap_file_pages   267
-#define __NR_mbind              268
-#define __NR_get_mempolicy      269
-#define __NR_set_mempolicy      270
-#define __NR_mq_open            271
-#define __NR_mq_unlink          272
-#define __NR_mq_timedsend       273
-#define __NR_mq_timedreceive    274
-#define __NR_mq_notify          275
-#define __NR_mq_getsetattr      276
-#define __NR_kexec_load         277
-#define __NR_add_key            278
-#define __NR_request_key        279
-#define __NR_keyctl             280
-#define __NR_waitid             281
-#define __NR_ioprio_set         282
-#define __NR_ioprio_get         283
-#define __NR_inotify_init       284
-#define __NR_inotify_add_watch  285
-#define __NR_inotify_rm_watch   286
-#define __NR_migrate_pages      287
-#define __NR_openat             288
-#define __NR_mkdirat            289
-#define __NR_mknodat            290
-#define __NR_fchownat           291
-#define __NR_futimesat          292
-#define __NR_unlinkat           294
-#define __NR_renameat           295
-#define __NR_linkat             296
-#define __NR_symlinkat          297
-#define __NR_readlinkat         298
-#define __NR_fchmodat           299
-#define __NR_faccessat          300
-#define __NR_pselect6           301
-#define __NR_ppoll              302
-#define __NR_unshare            303
-#define __NR_set_robust_list    304
-#define __NR_get_robust_list    305
-#define __NR_splice             306
-#define __NR_sync_file_range    307
-#define __NR_tee                308
-#define __NR_vmsplice           309
-#define __NR_move_pages         310
-#define __NR_getcpu             311
-#define __NR_epoll_pwait        312
-#define __NR_utimes             313
-#define __NR_fallocate          314
-#define __NR_utimensat          315
-#define __NR_signalfd           316
-#define __NR_timerfd            317
-#define __NR_eventfd            318
-#define __NR_timerfd_create     319
-#define __NR_timerfd_settime    320
-#define __NR_timerfd_gettime    321
-#define __NR_signalfd4          322
-#define __NR_eventfd2           323
-#define __NR_inotify_init1      324
-#define __NR_pipe2              325
-#define __NR_dup3               326
-#define __NR_epoll_create1      327
-#define __NR_preadv             328
-#define __NR_pwritev            329
-#define __NR_rt_tgsigqueueinfo  330
-#define __NR_perf_event_open    331
-#define __NR_fanotify_init      332
-#define __NR_fanotify_mark      333
-#define __NR_prlimit64          334
-#define __NR_name_to_handle_at  335
-#define __NR_open_by_handle_at  336
-#define __NR_clock_adjtime      337
-#define __NR_syncfs             338
-#define __NR_setns              339
-#define __NR_process_vm_readv   340
-#define __NR_process_vm_writev  341
-#define __NR_s390_runtime_instr 342
-#define __NR_kcmp               343
-#define __NR_finit_module       344
-#define __NR_sched_setattr      345
-#define __NR_sched_getattr      346
-#define __NR_renameat2          347
-#define __NR_seccomp            348
-#define __NR_getrandom          349
-#define __NR_memfd_create       350
-#define __NR_bpf                351
-#define __NR_s390_pci_mmio_write        352
-#define __NR_s390_pci_mmio_read         353
-#define __NR_execveat           354
-#define __NR_userfaultfd        355
-#define __NR_membarrier         356
-#define __NR_recvmmsg           357
-#define __NR_sendmmsg           358
-#define __NR_socket             359
-#define __NR_socketpair         360
-#define __NR_bind               361
-#define __NR_connect            362
-#define __NR_listen             363
-#define __NR_accept4            364
-#define __NR_getsockopt         365
-#define __NR_setsockopt         366
-#define __NR_getsockname        367
-#define __NR_getpeername        368
-#define __NR_sendto             369
-#define __NR_sendmsg            370
-#define __NR_recvfrom           371
-#define __NR_recvmsg            372
-#define __NR_shutdown           373
-#define __NR_mlock2             374
-#define __NR_copy_file_range    375
-#define __NR_preadv2            376
-#define __NR_pwritev2           377
-#define __NR_s390_guarded_storage       378
-#define __NR_statx              379
-#define __NR_s390_sthyi         380
-#define NR_syscalls 381
-
-/* 
- * There are some system calls that are not present on 64 bit, some
- * have a different name although they do the same (e.g. __NR_chown32
- * is __NR_chown on 64 bit).
- */
-#ifndef __s390x__
-
-#define __NR_time                13
-#define __NR_lchown              16
-#define __NR_setuid              23
-#define __NR_getuid              24
-#define __NR_stime               25
-#define __NR_setgid              46
-#define __NR_getgid              47
-#define __NR_geteuid             49
-#define __NR_getegid             50
-#define __NR_setreuid            70
-#define __NR_setregid            71
-#define __NR_getrlimit           76
-#define __NR_getgroups           80
-#define __NR_setgroups           81
-#define __NR_fchown              95
-#define __NR_ioperm             101
-#define __NR_setfsuid           138
-#define __NR_setfsgid           139
-#define __NR__llseek            140
-#define __NR__newselect         142
-#define __NR_setresuid          164
-#define __NR_getresuid          165
-#define __NR_setresgid          170
-#define __NR_getresgid          171
-#define __NR_chown              182
-#define __NR_ugetrlimit         191     /* SuS compliant getrlimit */
-#define __NR_mmap2              192
-#define __NR_truncate64         193
-#define __NR_ftruncate64        194
-#define __NR_stat64             195
-#define __NR_lstat64            196
-#define __NR_fstat64            197
-#define __NR_lchown32           198
-#define __NR_getuid32           199
-#define __NR_getgid32           200
-#define __NR_geteuid32          201
-#define __NR_getegid32          202
-#define __NR_setreuid32         203
-#define __NR_setregid32         204
-#define __NR_getgroups32        205
-#define __NR_setgroups32        206
-#define __NR_fchown32           207
-#define __NR_setresuid32        208
-#define __NR_getresuid32        209
-#define __NR_setresgid32        210
-#define __NR_getresgid32        211
-#define __NR_chown32            212
-#define __NR_setuid32           213
-#define __NR_setgid32           214
-#define __NR_setfsuid32         215
-#define __NR_setfsgid32         216
-#define __NR_fcntl64            221
-#define __NR_sendfile64         223
-#define __NR_fadvise64_64       264
-#define __NR_fstatat64          293
-
-#else
-
-#define __NR_select             142
-#define __NR_getrlimit          191     /* SuS compliant getrlimit */
-#define __NR_lchown             198
-#define __NR_getuid             199
-#define __NR_getgid             200
-#define __NR_geteuid            201
-#define __NR_getegid            202
-#define __NR_setreuid           203
-#define __NR_setregid           204
-#define __NR_getgroups          205
-#define __NR_setgroups          206
-#define __NR_fchown             207
-#define __NR_setresuid          208
-#define __NR_getresuid          209
-#define __NR_setresgid          210
-#define __NR_getresgid          211
-#define __NR_chown              212
-#define __NR_setuid             213
-#define __NR_setgid             214
-#define __NR_setfsuid           215
-#define __NR_setfsgid           216
-#define __NR_newfstatat         293
-
-#endif
-
-#endif /* _UAPI_ASM_S390_UNISTD_H_ */
diff --git a/tools/arch/x86/include/asm/cpufeatures.h b/tools/arch/x86/include/asm/cpufeatures.h
index 1d9199e1c2ad..f41079da38c5 100644
--- a/tools/arch/x86/include/asm/cpufeatures.h
+++ b/tools/arch/x86/include/asm/cpufeatures.h
@@ -210,8 +210,10 @@
 
 #define X86_FEATURE_MBA                 ( 7*32+18) /* Memory Bandwidth Allocation */
 #define X86_FEATURE_RSB_CTXSW           ( 7*32+19) /* "" Fill RSB on context switches */
+#define X86_FEATURE_SEV                 ( 7*32+20) /* AMD Secure Encrypted Virtualization */
 
 #define X86_FEATURE_USE_IBPB            ( 7*32+21) /* "" Indirect Branch Prediction Barrier enabled */
+#define X86_FEATURE_USE_IBRS_FW         ( 7*32+22) /* "" Use IBRS during runtime firmware calls */
 
 /* Virtualization flags: Linux defined, word 8 */
 #define X86_FEATURE_TPR_SHADOW          ( 8*32+ 0) /* Intel TPR Shadow */
diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
index 0b482c0070e0..465995281dcd 100644
--- a/tools/bpf/bpftool/common.c
+++ b/tools/bpf/bpftool/common.c
@@ -55,6 +55,10 @@
 
 #include "main.h"
 
+#ifndef BPF_FS_MAGIC
+#define BPF_FS_MAGIC            0xcafe4a11
+#endif
+
 void p_err(const char *fmt, ...)
 {
         va_list ap;
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index 3a0396d87c42..185acfa229b5 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -244,7 +244,7 @@ static int do_batch(int argc, char **argv)
         }
 
         if (errno && errno != ENOENT) {
-                perror("reading batch file failed");
+                p_err("reading batch file failed: %s", strerror(errno));
                 err = -1;
         } else {
                 p_info("processed %d lines", lines);
diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index f95fa67bb498..f509c86faede 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -428,7 +428,7 @@ static int show_map_close_json(int fd, struct bpf_map_info *info)
                 jsonw_string_field(json_wtr, "name", info->name);
 
         jsonw_name(json_wtr, "flags");
-        jsonw_printf(json_wtr, "%#x", info->map_flags);
+        jsonw_printf(json_wtr, "%d", info->map_flags);
 
         print_dev_json(info->ifindex, info->netns_dev, info->netns_ino);
 
diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
index e8e2baaf93c2..e549e329be82 100644
--- a/tools/bpf/bpftool/prog.c
+++ b/tools/bpf/bpftool/prog.c
@@ -774,6 +774,9 @@ static int do_dump(int argc, char **argv)
                               n < 0 ? strerror(errno) : "short write");
                         goto err_free;
                 }
+
+                if (json_output)
+                        jsonw_null(json_wtr);
         } else {
                 if (member_len == &info.jited_prog_len) {
                         const char *name = NULL;
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/cgroup/Makefile b/tools/cgroup/Makefile
index 860fa151640a..ffca068e4a76 100644
--- a/tools/cgroup/Makefile
+++ b/tools/cgroup/Makefile
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for cgroup tools
 
-CC = $(CROSS_COMPILE)gcc
 CFLAGS = -Wall -Wextra
 
 all: cgroup_event_listener
diff --git a/tools/gpio/Makefile b/tools/gpio/Makefile
index 805a2c0cf4cd..240eda014b37 100644
--- a/tools/gpio/Makefile
+++ b/tools/gpio/Makefile
@@ -12,8 +12,6 @@ endif
 # (this improves performance and avoids hard-to-debug behaviour);
 MAKEFLAGS += -r
 
-CC = $(CROSS_COMPILE)gcc
-LD = $(CROSS_COMPILE)ld
 CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include
 
 ALL_TARGETS := lsgpio gpio-hammer gpio-event-mon
diff --git a/tools/hv/Makefile b/tools/hv/Makefile
index 1139d71fa0cf..5db5e62cebda 100644
--- a/tools/hv/Makefile
+++ b/tools/hv/Makefile
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for Hyper-V tools
 
-CC = $(CROSS_COMPILE)gcc
 WARNINGS = -Wall -Wextra
 CFLAGS = $(WARNINGS) -g $(shell getconf LFS_CFLAGS)
 
diff --git a/tools/iio/Makefile b/tools/iio/Makefile
index a08e7a47d6a3..332ed2f6c2c2 100644
--- a/tools/iio/Makefile
+++ b/tools/iio/Makefile
@@ -12,8 +12,6 @@ endif
 # (this improves performance and avoids hard-to-debug behaviour);
 MAKEFLAGS += -r
 
-CC = $(CROSS_COMPILE)gcc
-LD = $(CROSS_COMPILE)ld
 CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include
 
 ALL_TARGETS := iio_event_monitor lsiio iio_generic_buffer
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/drm/i915_drm.h b/tools/include/uapi/drm/i915_drm.h
index ac3c6503ca27..536ee4febd74 100644
--- a/tools/include/uapi/drm/i915_drm.h
+++ b/tools/include/uapi/drm/i915_drm.h
@@ -86,6 +86,62 @@ enum i915_mocs_table_index {
         I915_MOCS_CACHED,
 };
 
+/*
+ * Different engines serve different roles, and there may be more than one
+ * engine serving each role. enum drm_i915_gem_engine_class provides a
+ * classification of the role of the engine, which may be used when requesting
+ * operations to be performed on a certain subset of engines, or for providing
+ * information about that group.
+ */
+enum drm_i915_gem_engine_class {
+        I915_ENGINE_CLASS_RENDER        = 0,
+        I915_ENGINE_CLASS_COPY          = 1,
+        I915_ENGINE_CLASS_VIDEO         = 2,
+        I915_ENGINE_CLASS_VIDEO_ENHANCE = 3,
+
+        I915_ENGINE_CLASS_INVALID       = -1
+};
+
+/**
+ * DOC: perf_events exposed by i915 through /sys/bus/event_sources/drivers/i915
+ *
+ */
+
+enum drm_i915_pmu_engine_sample {
+        I915_SAMPLE_BUSY = 0,
+        I915_SAMPLE_WAIT = 1,
+        I915_SAMPLE_SEMA = 2
+};
+
+#define I915_PMU_SAMPLE_BITS (4)
+#define I915_PMU_SAMPLE_MASK (0xf)
+#define I915_PMU_SAMPLE_INSTANCE_BITS (8)
+#define I915_PMU_CLASS_SHIFT \
+        (I915_PMU_SAMPLE_BITS + I915_PMU_SAMPLE_INSTANCE_BITS)
+
+#define __I915_PMU_ENGINE(class, instance, sample) \
+        ((class) << I915_PMU_CLASS_SHIFT | \
+        (instance) << I915_PMU_SAMPLE_BITS | \
+        (sample))
+
+#define I915_PMU_ENGINE_BUSY(class, instance) \
+        __I915_PMU_ENGINE(class, instance, I915_SAMPLE_BUSY)
+
+#define I915_PMU_ENGINE_WAIT(class, instance) \
+        __I915_PMU_ENGINE(class, instance, I915_SAMPLE_WAIT)
+
+#define I915_PMU_ENGINE_SEMA(class, instance) \
+        __I915_PMU_ENGINE(class, instance, I915_SAMPLE_SEMA)
+
+#define __I915_PMU_OTHER(x) (__I915_PMU_ENGINE(0xff, 0xff, 0xf) + 1 + (x))
+
+#define I915_PMU_ACTUAL_FREQUENCY       __I915_PMU_OTHER(0)
+#define I915_PMU_REQUESTED_FREQUENCY    __I915_PMU_OTHER(1)
+#define I915_PMU_INTERRUPTS             __I915_PMU_OTHER(2)
+#define I915_PMU_RC6_RESIDENCY          __I915_PMU_OTHER(3)
+
+#define I915_PMU_LAST I915_PMU_RC6_RESIDENCY
+
 /* Each region is a minimum of 16k, and there are at most 255 of them.
  */
 #define I915_NR_TEX_REGIONS 255 /* table size 2k - maximum due to use
@@ -450,6 +506,27 @@ typedef struct drm_i915_irq_wait {
  */
 #define I915_PARAM_HAS_EXEC_FENCE_ARRAY  49
 
+/*
+ * Query whether every context (both per-file default and user created) is
+ * isolated (insofar as HW supports). If this parameter is not true, then
+ * freshly created contexts may inherit values from an existing context,
+ * rather than default HW values. If true, it also ensures (insofar as HW
+ * supports) that all state set by this context will not leak to any other
+ * context.
+ *
+ * As not every engine across every gen support contexts, the returned
+ * value reports the support of context isolation for individual engines by
+ * returning a bitmask of each engine class set to true if that class supports
+ * isolation.
+ */
+#define I915_PARAM_HAS_CONTEXT_ISOLATION 50
+
+/* Frequency of the command streamer timestamps given by the *_TIMESTAMP
+ * registers. This used to be fixed per platform but from CNL onwards, this
+ * might vary depending on the parts.
+ */
+#define I915_PARAM_CS_TIMESTAMP_FREQUENCY 51
+
 typedef struct drm_i915_getparam {
         __s32 param;
         /*
diff --git a/tools/include/uapi/linux/if_link.h b/tools/include/uapi/linux/if_link.h
index 8616131e2c61..6d9447700e18 100644
--- a/tools/include/uapi/linux/if_link.h
+++ b/tools/include/uapi/linux/if_link.h
@@ -163,6 +163,7 @@ enum {
         IFLA_IF_NETNSID,
         IFLA_CARRIER_UP_COUNT,
         IFLA_CARRIER_DOWN_COUNT,
+        IFLA_NEW_IFINDEX,
         __IFLA_MAX
 };
 
diff --git a/tools/include/uapi/linux/kvm.h b/tools/include/uapi/linux/kvm.h
index 8fb90a0819c3..7b26d4b0b052 100644
--- a/tools/include/uapi/linux/kvm.h
+++ b/tools/include/uapi/linux/kvm.h
@@ -761,6 +761,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_TRACE_PAUSE           __KVM_DEPRECATED_MAIN_0x07
 #define KVM_TRACE_DISABLE         __KVM_DEPRECATED_MAIN_0x08
 #define KVM_GET_EMULATED_CPUID    _IOWR(KVMIO, 0x09, struct kvm_cpuid2)
+#define KVM_GET_MSR_FEATURE_INDEX_LIST    _IOWR(KVMIO, 0x0a, struct kvm_msr_list)
 
 /*
  * Extension capability list.
@@ -934,6 +935,7 @@ struct kvm_ppc_resize_hpt {
 #define KVM_CAP_S390_AIS_MIGRATION 150
 #define KVM_CAP_PPC_GET_CPU_CHAR 151
 #define KVM_CAP_S390_BPB 152
+#define KVM_CAP_GET_MSR_FEATURES 153
 
 #ifdef KVM_CAP_IRQ_ROUTING
 
@@ -1362,6 +1364,96 @@ struct kvm_s390_ucas_mapping {
 /* Available with KVM_CAP_S390_CMMA_MIGRATION */
 #define KVM_S390_GET_CMMA_BITS      _IOWR(KVMIO, 0xb8, struct kvm_s390_cmma_log)
 #define KVM_S390_SET_CMMA_BITS      _IOW(KVMIO, 0xb9, struct kvm_s390_cmma_log)
+/* Memory Encryption Commands */
+#define KVM_MEMORY_ENCRYPT_OP      _IOWR(KVMIO, 0xba, unsigned long)
+
+struct kvm_enc_region {
+        __u64 addr;
+        __u64 size;
+};
+
+#define KVM_MEMORY_ENCRYPT_REG_REGION    _IOR(KVMIO, 0xbb, struct kvm_enc_region)
+#define KVM_MEMORY_ENCRYPT_UNREG_REGION  _IOR(KVMIO, 0xbc, struct kvm_enc_region)
+
+/* Secure Encrypted Virtualization command */
+enum sev_cmd_id {
+        /* Guest initialization commands */
+        KVM_SEV_INIT = 0,
+        KVM_SEV_ES_INIT,
+        /* Guest launch commands */
+        KVM_SEV_LAUNCH_START,
+        KVM_SEV_LAUNCH_UPDATE_DATA,
+        KVM_SEV_LAUNCH_UPDATE_VMSA,
+        KVM_SEV_LAUNCH_SECRET,
+        KVM_SEV_LAUNCH_MEASURE,
+        KVM_SEV_LAUNCH_FINISH,
+        /* Guest migration commands (outgoing) */
+        KVM_SEV_SEND_START,
+        KVM_SEV_SEND_UPDATE_DATA,
+        KVM_SEV_SEND_UPDATE_VMSA,
+        KVM_SEV_SEND_FINISH,
+        /* Guest migration commands (incoming) */
+        KVM_SEV_RECEIVE_START,
+        KVM_SEV_RECEIVE_UPDATE_DATA,
+        KVM_SEV_RECEIVE_UPDATE_VMSA,
+        KVM_SEV_RECEIVE_FINISH,
+        /* Guest status and debug commands */
+        KVM_SEV_GUEST_STATUS,
+        KVM_SEV_DBG_DECRYPT,
+        KVM_SEV_DBG_ENCRYPT,
+        /* Guest certificates commands */
+        KVM_SEV_CERT_EXPORT,
+
+        KVM_SEV_NR_MAX,
+};
+
+struct kvm_sev_cmd {
+        __u32 id;
+        __u64 data;
+        __u32 error;
+        __u32 sev_fd;
+};
+
+struct kvm_sev_launch_start {
+        __u32 handle;
+        __u32 policy;
+        __u64 dh_uaddr;
+        __u32 dh_len;
+        __u64 session_uaddr;
+        __u32 session_len;
+};
+
+struct kvm_sev_launch_update_data {
+        __u64 uaddr;
+        __u32 len;
+};
+
+
+struct kvm_sev_launch_secret {
+        __u64 hdr_uaddr;
+        __u32 hdr_len;
+        __u64 guest_uaddr;
+        __u32 guest_len;
+        __u64 trans_uaddr;
+        __u32 trans_len;
+};
+
+struct kvm_sev_launch_measure {
+        __u64 uaddr;
+        __u32 len;
+};
+
+struct kvm_sev_guest_status {
+        __u32 handle;
+        __u32 policy;
+        __u32 state;
+};
+
+struct kvm_sev_dbg {
+        __u64 src_uaddr;
+        __u64 dst_uaddr;
+        __u32 len;
+};
 
 #define KVM_DEV_ASSIGN_ENABLE_IOMMU     (1 << 0)
 #define KVM_DEV_ASSIGN_PCI_2_3          (1 << 1)
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/kvm/kvm_stat/kvm_stat b/tools/kvm/kvm_stat/kvm_stat
index a5684d0968b4..5898c22ba310 100755
--- a/tools/kvm/kvm_stat/kvm_stat
+++ b/tools/kvm/kvm_stat/kvm_stat
@@ -33,7 +33,7 @@ import resource
 import struct
 import re
 import subprocess
-from collections import defaultdict
+from collections import defaultdict, namedtuple
 
 VMX_EXIT_REASONS = {
     'EXCEPTION_NMI':        0,
@@ -228,6 +228,7 @@ IOCTL_NUMBERS = {
 }
 
 ENCODING = locale.getpreferredencoding(False)
+TRACE_FILTER = re.compile(r'^[^\(]*$')
 
 
 class Arch(object):
@@ -260,6 +261,11 @@ class Arch(object):
                     return ArchX86(SVM_EXIT_REASONS)
                 return
 
+    def tracepoint_is_child(self, field):
+        if (TRACE_FILTER.match(field)):
+            return None
+        return field.split('(', 1)[0]
+
 
 class ArchX86(Arch):
     def __init__(self, exit_reasons):
@@ -267,6 +273,10 @@ class ArchX86(Arch):
         self.ioctl_numbers = IOCTL_NUMBERS
         self.exit_reasons = exit_reasons
 
+    def debugfs_is_child(self, field):
+        """ Returns name of parent if 'field' is a child, None otherwise """
+        return None
+
 
 class ArchPPC(Arch):
     def __init__(self):
@@ -282,6 +292,10 @@ class ArchPPC(Arch):
         self.ioctl_numbers['SET_FILTER'] = 0x80002406 | char_ptr_size << 16
         self.exit_reasons = {}
 
+    def debugfs_is_child(self, field):
+        """ Returns name of parent if 'field' is a child, None otherwise """
+        return None
+
 
 class ArchA64(Arch):
     def __init__(self):
@@ -289,6 +303,10 @@ class ArchA64(Arch):
         self.ioctl_numbers = IOCTL_NUMBERS
         self.exit_reasons = AARCH64_EXIT_REASONS
 
+    def debugfs_is_child(self, field):
+        """ Returns name of parent if 'field' is a child, None otherwise """
+        return None
+
 
 class ArchS390(Arch):
     def __init__(self):
@@ -296,6 +314,12 @@ class ArchS390(Arch):
         self.ioctl_numbers = IOCTL_NUMBERS
         self.exit_reasons = None
 
+    def debugfs_is_child(self, field):
+        """ Returns name of parent if 'field' is a child, None otherwise """
+        if field.startswith('instruction_'):
+            return 'exit_instruction'
+
+
 ARCH = Arch.get_arch()
 
 
@@ -331,9 +355,6 @@ class perf_event_attr(ctypes.Structure):
 PERF_TYPE_TRACEPOINT = 2
 PERF_FORMAT_GROUP = 1 << 3
 
-PATH_DEBUGFS_TRACING = '/sys/kernel/debug/tracing'
-PATH_DEBUGFS_KVM = '/sys/kernel/debug/kvm'
-
 
 class Group(object):
     """Represents a perf event group."""
@@ -376,8 +397,8 @@ class Event(object):
         self.syscall = self.libc.syscall
         self.name = name
         self.fd = None
-        self.setup_event(group, trace_cpu, trace_pid, trace_point,
-                         trace_filter, trace_set)
+        self._setup_event(group, trace_cpu, trace_pid, trace_point,
+                          trace_filter, trace_set)
 
     def __del__(self):
         """Closes the event's file descriptor.
@@ -390,7 +411,7 @@ class Event(object):
         if self.fd:
             os.close(self.fd)
 
-    def perf_event_open(self, attr, pid, cpu, group_fd, flags):
+    def _perf_event_open(self, attr, pid, cpu, group_fd, flags):
         """Wrapper for the sys_perf_evt_open() syscall.
 
         Used to set up performance events, returns a file descriptor or -1
@@ -409,7 +430,7 @@ class Event(object):
                             ctypes.c_int(pid), ctypes.c_int(cpu),
                             ctypes.c_int(group_fd), ctypes.c_long(flags))
 
-    def setup_event_attribute(self, trace_set, trace_point):
+    def _setup_event_attribute(self, trace_set, trace_point):
         """Returns an initialized ctype perf_event_attr struct."""
 
         id_path = os.path.join(PATH_DEBUGFS_TRACING, 'events', trace_set,
@@ -419,8 +440,8 @@ class Event(object):
         event_attr.config = int(open(id_path).read())
         return event_attr
 
-    def setup_event(self, group, trace_cpu, trace_pid, trace_point,
-                    trace_filter, trace_set):
+    def _setup_event(self, group, trace_cpu, trace_pid, trace_point,
+                     trace_filter, trace_set):
         """Sets up the perf event in Linux.
 
         Issues the syscall to register the event in the kernel and
@@ -428,7 +449,7 @@ class Event(object):
 
         """
 
-        event_attr = self.setup_event_attribute(trace_set, trace_point)
+        event_attr = self._setup_event_attribute(trace_set, trace_point)
 
         # First event will be group leader.
         group_leader = -1
@@ -437,8 +458,8 @@ class Event(object):
         if group.events:
             group_leader = group.events[0].fd
 
-        fd = self.perf_event_open(event_attr, trace_pid,
-                                  trace_cpu, group_leader, 0)
+        fd = self._perf_event_open(event_attr, trace_pid,
+                                   trace_cpu, group_leader, 0)
         if fd == -1:
             err = ctypes.get_errno()
             raise OSError(err, os.strerror(err),
@@ -475,6 +496,10 @@ class Event(object):
 
 class Provider(object):
     """Encapsulates functionalities used by all providers."""
+    def __init__(self, pid):
+        self.child_events = False
+        self.pid = pid
+
     @staticmethod
     def is_field_wanted(fields_filter, field):
         """Indicate whether field is valid according to fields_filter."""
@@ -500,12 +525,12 @@ class TracepointProvider(Provider):
     """
     def __init__(self, pid, fields_filter):
         self.group_leaders = []
-        self.filters = self.get_filters()
+        self.filters = self._get_filters()
         self.update_fields(fields_filter)
-        self.pid = pid
+        super(TracepointProvider, self).__init__(pid)
 
     @staticmethod
-    def get_filters():
+    def _get_filters():
         """Returns a dict of trace events, their filter ids and
         the values that can be filtered.
 
@@ -521,8 +546,8 @@ class TracepointProvider(Provider):
             filters['kvm_exit'] = ('exit_reason', ARCH.exit_reasons)
         return filters
 
-    def get_available_fields(self):
-        """Returns a list of available event's of format 'event name(filter
+    def _get_available_fields(self):
+        """Returns a list of available events of format 'event name(filter
         name)'.
 
         All available events have directories under
@@ -549,11 +574,12 @@ class TracepointProvider(Provider):
 
     def update_fields(self, fields_filter):
         """Refresh fields, applying fields_filter"""
-        self.fields = [field for field in self.get_available_fields()
-                       if self.is_field_wanted(fields_filter, field)]
+        self.fields = [field for field in self._get_available_fields()
+                       if self.is_field_wanted(fields_filter, field) or
+                       ARCH.tracepoint_is_child(field)]
 
     @staticmethod
-    def get_online_cpus():
+    def _get_online_cpus():
         """Returns a list of cpu id integers."""
         def parse_int_list(list_string):
             """Returns an int list from a string of comma separated integers and
@@ -575,17 +601,17 @@ class TracepointProvider(Provider):
             cpu_string = cpu_list.readline()
             return parse_int_list(cpu_string)
 
-    def setup_traces(self):
+    def _setup_traces(self):
         """Creates all event and group objects needed to be able to retrieve
         data."""
-        fields = self.get_available_fields()
+        fields = self._get_available_fields()
         if self._pid > 0:
             # Fetch list of all threads of the monitored pid, as qemu
             # starts a thread for each vcpu.
             path = os.path.join('/proc', str(self._pid), 'task')
             groupids = self.walkdir(path)[1]
         else:
-            groupids = self.get_online_cpus()
+            groupids = self._get_online_cpus()
 
         # The constant is needed as a buffer for python libs, std
         # streams and other files that the script opens.
@@ -663,7 +689,7 @@ class TracepointProvider(Provider):
         # The garbage collector will get rid of all Event/Group
         # objects and open files after removing the references.
         self.group_leaders = []
-        self.setup_traces()
+        self._setup_traces()
         self.fields = self._fields
 
     def read(self, by_guest=0):
@@ -671,8 +697,12 @@ class TracepointProvider(Provider):
         ret = defaultdict(int)
         for group in self.group_leaders:
             for name, val in group.read().items():
-                if name in self._fields:
-                    ret[name] += val
+                if name not in self._fields:
+                    continue
+                parent = ARCH.tracepoint_is_child(name)
+                if parent:
+                    name += ' ' + parent
+                ret[name] += val
         return ret
 
     def reset(self):
@@ -690,11 +720,11 @@ class DebugfsProvider(Provider):
         self._baseline = {}
         self.do_read = True
         self.paths = []
-        self.pid = pid
+        super(DebugfsProvider, self).__init__(pid)
         if include_past:
-            self.restore()
+            self._restore()
 
-    def get_available_fields(self):
+    def _get_available_fields(self):
         """"Returns a list of available fields.
 
         The fields are all available KVM debugfs files
@@ -704,8 +734,9 @@ class DebugfsProvider(Provider):
 
     def update_fields(self, fields_filter):
         """Refresh fields, applying fields_filter"""
-        self._fields = [field for field in self.get_available_fields()
-                        if self.is_field_wanted(fields_filter, field)]
+        self._fields = [field for field in self._get_available_fields()
+                        if self.is_field_wanted(fields_filter, field) or
+                        ARCH.debugfs_is_child(field)]
 
     @property
     def fields(self):
@@ -758,7 +789,7 @@ class DebugfsProvider(Provider):
                     paths.append(dir)
         for path in paths:
             for field in self._fields:
-                value = self.read_field(field, path)
+                value = self._read_field(field, path)
                 key = path + field
                 if reset == 1:
                     self._baseline[key] = value
@@ -766,20 +797,21 @@ class DebugfsProvider(Provider):
                     self._baseline[key] = 0
                 if self._baseline.get(key, -1) == -1:
                     self._baseline[key] = value
-                increment = (results.get(field, 0) + value -
-                             self._baseline.get(key, 0))
-                if by_guest:
-                    pid = key.split('-')[0]
-                    if pid in results:
-                        results[pid] += increment
-                    else:
-                        results[pid] = increment
+                parent = ARCH.debugfs_is_child(field)
+                if parent:
+                    field = field + ' ' + parent
+                else:
+                    if by_guest:
+                        field = key.split('-')[0]    # set 'field' to 'pid'
+                increment = value - self._baseline.get(key, 0)
+                if field in results:
+                    results[field] += increment
                 else:
                     results[field] = increment
 
         return results
 
-    def read_field(self, field, path):
+    def _read_field(self, field, path):
         """Returns the value of a single field from a specific VM."""
         try:
             return int(open(os.path.join(PATH_DEBUGFS_KVM,
@@ -794,12 +826,15 @@ class DebugfsProvider(Provider):
         self._baseline = {}
         self.read(1)
 
-    def restore(self):
+    def _restore(self):
         """Reset field counters"""
         self._baseline = {}
         self.read(2)
 
 
+EventStat = namedtuple('EventStat', ['value', 'delta'])
+
+
 class Stats(object):
     """Manages the data providers and the data they provide.
 
@@ -808,13 +843,13 @@ class Stats(object):
 
     """
     def __init__(self, options):
-        self.providers = self.get_providers(options)
+        self.providers = self._get_providers(options)
         self._pid_filter = options.pid
         self._fields_filter = options.fields
         self.values = {}
+        self._child_events = False
 
-    @staticmethod
-    def get_providers(options):
+    def _get_providers(self, options):
         """Returns a list of data providers depending on the passed options."""
         providers = []
 
@@ -826,7 +861,7 @@ class Stats(object):
 
         return providers
 
-    def update_provider_filters(self):
+    def _update_provider_filters(self):
         """Propagates fields filters to providers."""
         # As we reset the counters when updating the fields we can
         # also clear the cache of old values.
@@ -847,7 +882,7 @@ class Stats(object):
     def fields_filter(self, fields_filter):
         if fields_filter != self._fields_filter:
             self._fields_filter = fields_filter
-            self.update_provider_filters()
+            self._update_provider_filters()
 
     @property
     def pid_filter(self):
@@ -861,16 +896,33 @@ class Stats(object):
             for provider in self.providers:
                 provider.pid = self._pid_filter
 
+    @property
+    def child_events(self):
+        return self._child_events
+
+    @child_events.setter
+    def child_events(self, val):
+        self._child_events = val
+        for provider in self.providers:
+            provider.child_events = val
+
     def get(self, by_guest=0):
         """Returns a dict with field -> (value, delta to last value) of all
-        provider data."""
+        provider data.
+        Key formats:
+          * plain: 'key' is event name
+          * child-parent: 'key' is in format '<child> <parent>'
+          * pid: 'key' is the pid of the guest, and the record contains the
+               aggregated event data
+        These formats are generated by the providers, and handled in class TUI.
+        """
         for provider in self.providers:
             new = provider.read(by_guest=by_guest)
-            for key in new if by_guest else provider.fields:
-                oldval = self.values.get(key, (0, 0))[0]
+            for key in new:
+                oldval = self.values.get(key, EventStat(0, 0)).value
                 newval = new.get(key, 0)
                 newdelta = newval - oldval
-                self.values[key] = (newval, newdelta)
+                self.values[key] = EventStat(newval, newdelta)
         return self.values
 
     def toggle_display_guests(self, to_pid):
@@ -899,10 +951,10 @@ class Stats(object):
         self.get(to_pid)
         return 0
 
+
 DELAY_DEFAULT = 3.0
 MAX_GUEST_NAME_LEN = 48
 MAX_REGEX_LEN = 44
-DEFAULT_REGEX = r'^[^\(]*$'
 SORT_DEFAULT = 0
 
 
@@ -969,7 +1021,7 @@ class Tui(object):
 
         return res
 
-    def print_all_gnames(self, row):
+    def _print_all_gnames(self, row):
         """Print a list of all running guests along with their pids."""
         self.screen.addstr(row, 2, '%8s  %-60s' %
                            ('Pid', 'Guest Name (fuzzy list, might be '
@@ -1032,19 +1084,13 @@ class Tui(object):
 
         return name
 
-    def update_drilldown(self):
-        """Sets or removes a filter that only allows fields without braces."""
-        if not self.stats.fields_filter:
-            self.stats.fields_filter = DEFAULT_REGEX
-
-        elif self.stats.fields_filter == DEFAULT_REGEX:
-            self.stats.fields_filter = None
-
-    def update_pid(self, pid):
+    def _update_pid(self, pid):
         """Propagates pid selection to stats object."""
+        self.screen.addstr(4, 1, 'Updating pid filter...')
+        self.screen.refresh()
         self.stats.pid_filter = pid
 
-    def refresh_header(self, pid=None):
+    def _refresh_header(self, pid=None):
         """Refreshes the header."""
         if pid is None:
             pid = self.stats.pid_filter
@@ -1059,8 +1105,7 @@ class Tui(object):
                                .format(pid, gname), curses.A_BOLD)
         else:
             self.screen.addstr(0, 0, 'kvm statistics - summary', curses.A_BOLD)
-        if self.stats.fields_filter and self.stats.fields_filter \
-           != DEFAULT_REGEX:
+        if self.stats.fields_filter:
             regex = self.stats.fields_filter
             if len(regex) > MAX_REGEX_LEN:
                 regex = regex[:MAX_REGEX_LEN] + '...'
@@ -1075,56 +1120,99 @@ class Tui(object):
         self.screen.addstr(4, 1, 'Collecting data...')
         self.screen.refresh()
 
-    def refresh_body(self, sleeptime):
+    def _refresh_body(self, sleeptime):
+        def is_child_field(field):
+            return field.find('(') != -1
+
+        def insert_child(sorted_items, child, values, parent):
+            num = len(sorted_items)
+            for i in range(0, num):
+                # only add child if parent is present
+                if parent.startswith(sorted_items[i][0]):
+                    sorted_items.insert(i + 1, ('  ' + child, values))
+
+        def get_sorted_events(self, stats):
+            """ separate parent and child events """
+            if self._sorting == SORT_DEFAULT:
+                def sortkey((_k, v)):
+                    # sort by (delta value, overall value)
+                    return (v.delta, v.value)
+            else:
+                def sortkey((_k, v)):
+                    # sort by overall value
+                    return v.value
+
+            childs = []
+            sorted_items = []
+            # we can't rule out child events to appear prior to parents even
+            # when sorted - separate out all children first, and add in later
+            for key, values in sorted(stats.items(), key=sortkey,
+                                      reverse=True):
+                if values == (0, 0):
+                    continue
+                if key.find(' ') != -1:
+                    if not self.stats.child_events:
+                        continue
+                    childs.insert(0, (key, values))
+                else:
+                    sorted_items.append((key, values))
+            if self.stats.child_events:
+                for key, values in childs:
+                    (child, parent) = key.split(' ')
+                    insert_child(sorted_items, child, values, parent)
+
+            return sorted_items
+
         row = 3
         self.screen.move(row, 0)
         self.screen.clrtobot()
         stats = self.stats.get(self._display_guests)
-
-        def sortCurAvg(x):
-            # sort by current events if available
-            if stats[x][1]:
-                return (-stats[x][1], -stats[x][0])
+        total = 0.
+        ctotal = 0.
+        for key, values in stats.items():
+            if self._display_guests:
+                if self.get_gname_from_pid(key):
+                    total += values.value
+                continue
+            if not key.find(' ') != -1:
+                total += values.value
             else:
-                return (0, -stats[x][0])
+                ctotal += values.value
+        if total == 0.:
+            # we don't have any fields, or all non-child events are filtered
+            total = ctotal
 
-        def sortTotal(x):
-            # sort by totals
-            return (0, -stats[x][0])
-        total = 0.
-        for key in stats.keys():
-            if key.find('(') is -1:
-                total += stats[key][0]
-        if self._sorting == SORT_DEFAULT:
-            sortkey = sortCurAvg
-        else:
-            sortkey = sortTotal
+        # print events
         tavg = 0
-        for key in sorted(stats.keys(), key=sortkey):
-            if row >= self.screen.getmaxyx()[0] - 1:
-                break
-            values = stats[key]
-            if not values[0] and not values[1]:
+        tcur = 0
+        for key, values in get_sorted_events(self, stats):
+            if row >= self.screen.getmaxyx()[0] - 1 or values == (0, 0):
                 break
-            if values[0] is not None:
-                cur = int(round(values[1] / sleeptime)) if values[1] else ''
-                if self._display_guests:
-                    key = self.get_gname_from_pid(key)
-                self.screen.addstr(row, 1, '%-40s %10d%7.1f %8s' %
-                                   (key, values[0], values[0] * 100 / total,
-                                    cur))
-                if cur is not '' and key.find('(') is -1:
-                    tavg += cur
+            if self._display_guests:
+                key = self.get_gname_from_pid(key)
+                if not key:
+                    continue
+            cur = int(round(values.delta / sleeptime)) if values.delta else ''
+            if key[0] != ' ':
+                if values.delta:
+                    tcur += values.delta
+                ptotal = values.value
+                ltotal = total
+            else:
+                ltotal = ptotal
+            self.screen.addstr(row, 1, '%-40s %10d%7.1f %8s' % (key,
+                               values.value,
+                               values.value * 100 / float(ltotal), cur))
             row += 1
         if row == 3:
             self.screen.addstr(4, 1, 'No matching events reported yet')
-        else:
+        if row > 4:
+            tavg = int(round(tcur / sleeptime)) if tcur > 0 else ''
             self.screen.addstr(row, 1, '%-40s %10d        %8s' %
-                               ('Total', total, tavg if tavg else ''),
-                               curses.A_BOLD)
+                               ('Total', total, tavg), curses.A_BOLD)
         self.screen.refresh()
 
-    def show_msg(self, text):
+    def _show_msg(self, text):
         """Display message centered text and exit on key press"""
         hint = 'Press any key to continue'
         curses.cbreak()
@@ -1139,16 +1227,16 @@ class Tui(object):
                            curses.A_STANDOUT)
         self.screen.getkey()
 
-    def show_help_interactive(self):
+    def _show_help_interactive(self):
         """Display help with list of interactive commands"""
         msg = ('   b     toggle events by guests (debugfs only, honors'
                ' filters)',
                '   c     clear filter',
                '   f     filter by regular expression',
-               '   g     filter by guest name',
+               '   g     filter by guest name/PID',
                '   h     display interactive commands reference',
                '   o     toggle sorting order (Total vs CurAvg/s)',
-               '   p     filter by PID',
+               '   p     filter by guest name/PID',
                '   q     quit',
                '   r     reset stats',
                '   s     set update interval',
@@ -1165,14 +1253,15 @@ class Tui(object):
             self.screen.addstr(row, 0, line)
             row += 1
         self.screen.getkey()
-        self.refresh_header()
+        self._refresh_header()
 
-    def show_filter_selection(self):
+    def _show_filter_selection(self):
         """Draws filter selection mask.
 
         Asks for a valid regex and sets the fields filter accordingly.
 
         """
+        msg = ''
         while True:
             self.screen.erase()
             self.screen.addstr(0, 0,
@@ -1181,61 +1270,25 @@ class Tui(object):
             self.screen.addstr(2, 0,
                                "Current regex: {0}"
                                .format(self.stats.fields_filter))
+            self.screen.addstr(5, 0, msg)
             self.screen.addstr(3, 0, "New regex: ")
             curses.echo()
             regex = self.screen.getstr().decode(ENCODING)
             curses.noecho()
             if len(regex) == 0:
-                self.stats.fields_filter = DEFAULT_REGEX
-                self.refresh_header()
+                self.stats.fields_filter = ''
+                self._refresh_header()
                 return
             try:
                 re.compile(regex)
                 self.stats.fields_filter = regex
-                self.refresh_header()
+                self._refresh_header()
                 return
             except re.error:
+                msg = '"' + regex + '": Not a valid regular expression'
                 continue
 
-    def show_vm_selection_by_pid(self):
-        """Draws PID selection mask.
-
-        Asks for a pid until a valid pid or 0 has been entered.
-
-        """
-        msg = ''
-        while True:
-            self.screen.erase()
-            self.screen.addstr(0, 0,
-                               'Show statistics for specific pid.',
-                               curses.A_BOLD)
-            self.screen.addstr(1, 0,
-                               'This might limit the shown data to the trace '
-                               'statistics.')
-            self.screen.addstr(5, 0, msg)
-            self.print_all_gnames(7)
-
-            curses.echo()
-            self.screen.addstr(3, 0, "Pid [0 or pid]: ")
-            pid = self.screen.getstr().decode(ENCODING)
-            curses.noecho()
-
-            try:
-                if len(pid) > 0:
-                    pid = int(pid)
-                    if pid != 0 and not os.path.isdir(os.path.join('/proc/',
-                                                                   str(pid))):
-                        msg = '"' + str(pid) + '": Not a running process'
-                        continue
-                else:
-                    pid = 0
-                self.refresh_header(pid)
-                self.update_pid(pid)
-                break
-            except ValueError:
-                msg = '"' + str(pid) + '": Not a valid pid'
-
-    def show_set_update_interval(self):
+    def _show_set_update_interval(self):
         """Draws update interval selection mask."""
         msg = ''
         while True:
@@ -1265,60 +1318,67 @@ class Tui(object):
 
             except ValueError:
                 msg = '"' + str(val) + '": Invalid value'
-        self.refresh_header()
+        self._refresh_header()
 
-    def show_vm_selection_by_guest_name(self):
+    def _show_vm_selection_by_guest(self):
         """Draws guest selection mask.
 
-        Asks for a guest name until a valid guest name or '' is entered.
+        Asks for a guest name or pid until a valid guest name or '' is entered.
 
         """
         msg = ''
         while True:
             self.screen.erase()
             self.screen.addstr(0, 0,
-                               'Show statistics for specific guest.',
+                               'Show statistics for specific guest or pid.',
                                curses.A_BOLD)
             self.screen.addstr(1, 0,
                                'This might limit the shown data to the trace '
                                'statistics.')
             self.screen.addstr(5, 0, msg)
-            self.print_all_gnames(7)
+            self._print_all_gnames(7)
             curses.echo()
-            self.screen.addstr(3, 0, "Guest [ENTER or guest]: ")
-            gname = self.screen.getstr().decode(ENCODING)
+            curses.curs_set(1)
+            self.screen.addstr(3, 0, "Guest or pid [ENTER exits]: ")
+            guest = self.screen.getstr().decode(ENCODING)
             curses.noecho()
 
-            if not gname:
-                self.refresh_header(0)
-                self.update_pid(0)
+            pid = 0
+            if not guest or guest == '0':
                 break
-            else:
-                pids = []
-                try:
-                    pids = self.get_pid_from_gname(gname)
-                except:
-                    msg = '"' + gname + '": Internal error while searching, ' \
-                          'use pid filter instead'
-                    continue
-                if len(pids) == 0:
-                    msg = '"' + gname + '": Not an active guest'
+            if guest.isdigit():
+                if not os.path.isdir(os.path.join('/proc/', guest)):
+                    msg = '"' + guest + '": Not a running process'
                     continue
-                if len(pids) > 1:
-                    msg = '"' + gname + '": Multiple matches found, use pid ' \
-                          'filter instead'
-                    continue
-                self.refresh_header(pids[0])
-                self.update_pid(pids[0])
+                pid = int(guest)
                 break
+            pids = []
+            try:
+                pids = self.get_pid_from_gname(guest)
+            except:
+                msg = '"' + guest + '": Internal error while searching, ' \
+                      'use pid filter instead'
+                continue
+            if len(pids) == 0:
+                msg = '"' + guest + '": Not an active guest'
+                continue
+            if len(pids) > 1:
+                msg = '"' + guest + '": Multiple matches found, use pid ' \
+                      'filter instead'
+                continue
+            pid = pids[0]
+            break
+        curses.curs_set(0)
+        self._refresh_header(pid)
+        self._update_pid(pid)
 
     def show_stats(self):
         """Refreshes the screen and processes user input."""
         sleeptime = self._delay_initial
-        self.refresh_header()
+        self._refresh_header()
         start = 0.0  # result based on init value never appears on screen
         while True:
-            self.refresh_body(time.time() - start)
+            self._refresh_body(time.time() - start)
             curses.halfdelay(int(sleeptime * 10))
             start = time.time()
             sleeptime = self._delay_regular
@@ -1327,47 +1387,39 @@ class Tui(object):
                 if char == 'b':
                     self._display_guests = not self._display_guests
                     if self.stats.toggle_display_guests(self._display_guests):
-                        self.show_msg(['Command not available with tracepoints'
-                                       ' enabled', 'Restart with debugfs only '
-                                       '(see option \'-d\') and try again!'])
+                        self._show_msg(['Command not available with '
+                                        'tracepoints enabled', 'Restart with '
+                                        'debugfs only (see option \'-d\') and '
+                                        'try again!'])
                         self._display_guests = not self._display_guests
-                    self.refresh_header()
+                    self._refresh_header()
                 if char == 'c':
-                    self.stats.fields_filter = DEFAULT_REGEX
-                    self.refresh_header(0)
-                    self.update_pid(0)
+                    self.stats.fields_filter = ''
+                    self._refresh_header(0)
+                    self._update_pid(0)
                 if char == 'f':
                     curses.curs_set(1)
-                    self.show_filter_selection()
+                    self._show_filter_selection()
                     curses.curs_set(0)
                     sleeptime = self._delay_initial
-                if char == 'g':
-                    curses.curs_set(1)
-                    self.show_vm_selection_by_guest_name()
-                    curses.curs_set(0)
+                if char == 'g' or char == 'p':
+                    self._show_vm_selection_by_guest()
                     sleeptime = self._delay_initial
                 if char == 'h':
-                    self.show_help_interactive()
+                    self._show_help_interactive()
                 if char == 'o':
                     self._sorting = not self._sorting
-                if char == 'p':
-                    curses.curs_set(1)
-                    self.show_vm_selection_by_pid()
-                    curses.curs_set(0)
-                    sleeptime = self._delay_initial
                 if char == 'q':
                     break
                 if char == 'r':
                     self.stats.reset()
                 if char == 's':
                     curses.curs_set(1)
-                    self.show_set_update_interval()
+                    self._show_set_update_interval()
                     curses.curs_set(0)
                     sleeptime = self._delay_initial
                 if char == 'x':
-                    self.update_drilldown()
-                    # prevents display of current values on next refresh
-                    self.stats.get(self._display_guests)
+                    self.stats.child_events = not self.stats.child_events
             except KeyboardInterrupt:
                 break
             except curses.error:
@@ -1380,9 +1432,9 @@ def batch(stats):
         s = stats.get()
         time.sleep(1)
         s = stats.get()
-        for key in sorted(s.keys()):
-            values = s[key]
-            print('%-42s%10d%10d' % (key, values[0], values[1]))
+        for key, values in sorted(s.items()):
+            print('%-42s%10d%10d' % (key.split(' ')[0], values.value,
+                  values.delta))
     except KeyboardInterrupt:
         pass
 
@@ -1392,14 +1444,14 @@ def log(stats):
     keys = sorted(stats.get().keys())
 
     def banner():
-        for k in keys:
-            print(k, end=' ')
+        for key in keys:
+            print(key.split(' ')[0], end=' ')
         print()
 
     def statline():
         s = stats.get()
-        for k in keys:
-            print(' %9d' % s[k][1], end=' ')
+        for key in keys:
+            print(' %9d' % s[key].delta, end=' ')
         print()
     line = 0
     banner_repeat = 20
@@ -1504,7 +1556,7 @@ Press any other key to refresh statistics immediately.
                          )
     optparser.add_option('-f', '--fields',
                          action='store',
-                         default=DEFAULT_REGEX,
+                         default='',
                          dest='fields',
                          help='''fields to display (regex)
                                  "-f help" for a list of available events''',
@@ -1539,17 +1591,6 @@ Press any other key to refresh statistics immediately.
 
 def check_access(options):
     """Exits if the current user can't access all needed directories."""
-    if not os.path.exists('/sys/kernel/debug'):
-        sys.stderr.write('Please enable CONFIG_DEBUG_FS in your kernel.')
-        sys.exit(1)
-
-    if not os.path.exists(PATH_DEBUGFS_KVM):
-        sys.stderr.write("Please make sure, that debugfs is mounted and "
-                         "readable by the current user:\n"
-                         "('mount -t debugfs debugfs /sys/kernel/debug')\n"
-                         "Also ensure, that the kvm modules are loaded.\n")
-        sys.exit(1)
-
     if not os.path.exists(PATH_DEBUGFS_TRACING) and (options.tracepoints or
                                                      not options.debugfs):
         sys.stderr.write("Please enable CONFIG_TRACING in your kernel "
@@ -1567,7 +1608,33 @@ def check_access(options):
     return options
 
 
+def assign_globals():
+    global PATH_DEBUGFS_KVM
+    global PATH_DEBUGFS_TRACING
+
+    debugfs = ''
+    for line in file('/proc/mounts'):
+        if line.split(' ')[0] == 'debugfs':
+            debugfs = line.split(' ')[1]
+            break
+    if debugfs == '':
+        sys.stderr.write("Please make sure that CONFIG_DEBUG_FS is enabled in "
+                         "your kernel, mounted and\nreadable by the current "
+                         "user:\n"
+                         "('mount -t debugfs debugfs /sys/kernel/debug')\n")
+        sys.exit(1)
+
+    PATH_DEBUGFS_KVM = os.path.join(debugfs, 'kvm')
+    PATH_DEBUGFS_TRACING = os.path.join(debugfs, 'tracing')
+
+    if not os.path.exists(PATH_DEBUGFS_KVM):
+        sys.stderr.write("Please make sure that CONFIG_KVM is enabled in "
+                         "your kernel and that the modules are loaded.\n")
+        sys.exit(1)
+
+
 def main():
+    assign_globals()
     options = get_options()
     options = check_access(options)
 
diff --git a/tools/kvm/kvm_stat/kvm_stat.txt b/tools/kvm/kvm_stat/kvm_stat.txt
index b5b3810c9e94..0811d860fe75 100644
--- a/tools/kvm/kvm_stat/kvm_stat.txt
+++ b/tools/kvm/kvm_stat/kvm_stat.txt
@@ -35,13 +35,13 @@ INTERACTIVE COMMANDS
 
 *f*::   filter by regular expression
 
-*g*::   filter by guest name
+*g*::   filter by guest name/PID
 
 *h*::   display interactive commands reference
 
 *o*::   toggle sorting order (Total vs CurAvg/s)
 
-*p*::   filter by PID
+*p*::   filter by guest name/PID
 
 *q*::   quit
 
diff --git a/tools/laptop/freefall/Makefile b/tools/laptop/freefall/Makefile
index 5f758c489a20..b572d94255f6 100644
--- a/tools/laptop/freefall/Makefile
+++ b/tools/laptop/freefall/Makefile
@@ -2,7 +2,6 @@
 PREFIX ?= /usr
 SBINDIR ?= sbin
 INSTALL ?= install
-CC = $(CROSS_COMPILE)gcc
 
 TARGET = freefall
 
diff --git a/tools/leds/Makefile b/tools/leds/Makefile
index c379af003807..7b6bed13daaa 100644
--- a/tools/leds/Makefile
+++ b/tools/leds/Makefile
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for LEDs tools
 
-CC = $(CROSS_COMPILE)gcc
 CFLAGS = -Wall -Wextra -g -I../../include/uapi
 
 all: uledmon led_hw_brightness_mon
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/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 97073d649c1a..5bbbf285af74 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -1060,11 +1060,12 @@ bpf_program__reloc_text(struct bpf_program *prog, struct bpf_object *obj,
                 prog->insns = new_insn;
                 prog->main_prog_cnt = prog->insns_cnt;
                 prog->insns_cnt = new_cnt;
+                pr_debug("added %zd insn from %s to prog %s\n",
+                         text->insns_cnt, text->section_name,
+                         prog->section_name);
         }
         insn = &prog->insns[relo->insn_idx];
         insn->imm += prog->main_prog_cnt - relo->insn_idx;
-        pr_debug("added %zd insn from %s to prog %s\n",
-                 text->insns_cnt, text->section_name, prog->section_name);
         return 0;
 }
 
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/memory-model/Documentation/cheatsheet.txt b/tools/memory-model/Documentation/cheatsheet.txt
new file mode 100644
index 000000000000..956b1ae4aafb
--- /dev/null
+++ b/tools/memory-model/Documentation/cheatsheet.txt
@@ -0,0 +1,29 @@
+                                  Prior Operation     Subsequent Operation
+                                  ---------------  ---------------------------
+                               C  Self  R  W  RWM  Self  R  W  DR  DW  RMW  SV
+                              --  ----  -  -  ---  ----  -  -  --  --  ---  --
+
+Store, e.g., WRITE_ONCE()            Y                                       Y
+Load, e.g., READ_ONCE()              Y                          Y   Y        Y
+Unsuccessful RMW operation           Y                          Y   Y        Y
+rcu_dereference()                    Y                          Y   Y        Y
+Successful *_acquire()               R                   Y  Y   Y   Y    Y   Y
+Successful *_release()         C        Y  Y    Y     W                      Y
+smp_rmb()                               Y       R        Y      Y        R
+smp_wmb()                                  Y    W           Y       Y    W
+smp_mb() & synchronize_rcu()  CP        Y  Y    Y        Y  Y   Y   Y    Y
+Successful full non-void RMW  CP     Y  Y  Y    Y     Y  Y  Y   Y   Y    Y   Y
+smp_mb__before_atomic()       CP        Y  Y    Y        a  a   a   a    Y
+smp_mb__after_atomic()        CP        a  a    Y        Y  Y   Y   Y
+
+
+Key:    C:      Ordering is cumulative
+        P:      Ordering propagates
+        R:      Read, for example, READ_ONCE(), or read portion of RMW
+        W:      Write, for example, WRITE_ONCE(), or write portion of RMW
+        Y:      Provides ordering
+        a:      Provides ordering given intervening RMW atomic operation
+        DR:     Dependent read (address dependency)
+        DW:     Dependent write (address, data, or control dependency)
+        RMW:    Atomic read-modify-write operation
+        SV      Same-variable access
diff --git a/tools/memory-model/Documentation/explanation.txt b/tools/memory-model/Documentation/explanation.txt
new file mode 100644
index 000000000000..a727c82bd434
--- /dev/null
+++ b/tools/memory-model/Documentation/explanation.txt
@@ -0,0 +1,1845 @@
+Explanation of the Linux-Kernel Memory Consistency Model
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+:Author: Alan Stern <stern@rowland.harvard.edu>
+:Created: October 2017
+
+.. Contents
+
+  1. INTRODUCTION
+  2. BACKGROUND
+  3. A SIMPLE EXAMPLE
+  4. A SELECTION OF MEMORY MODELS
+  5. ORDERING AND CYCLES
+  6. EVENTS
+  7. THE PROGRAM ORDER RELATION: po AND po-loc
+  8. A WARNING
+  9. DEPENDENCY RELATIONS: data, addr, and ctrl
+  10. THE READS-FROM RELATION: rf, rfi, and rfe
+  11. CACHE COHERENCE AND THE COHERENCE ORDER RELATION: co, coi, and coe
+  12. THE FROM-READS RELATION: fr, fri, and fre
+  13. AN OPERATIONAL MODEL
+  14. PROPAGATION ORDER RELATION: cumul-fence
+  15. DERIVATION OF THE LKMM FROM THE OPERATIONAL MODEL
+  16. SEQUENTIAL CONSISTENCY PER VARIABLE
+  17. ATOMIC UPDATES: rmw
+  18. THE PRESERVED PROGRAM ORDER RELATION: ppo
+  19. AND THEN THERE WAS ALPHA
+  20. THE HAPPENS-BEFORE RELATION: hb
+  21. THE PROPAGATES-BEFORE RELATION: pb
+  22. RCU RELATIONS: link, gp-link, rscs-link, and rcu-path
+  23. ODDS AND ENDS
+
+
+
+INTRODUCTION
+------------
+
+The Linux-kernel memory consistency model (LKMM) is rather complex and
+obscure.  This is particularly evident if you read through the
+linux-kernel.bell and linux-kernel.cat files that make up the formal
+version of the model; they are extremely terse and their meanings are
+far from clear.
+
+This document describes the ideas underlying the LKMM.  It is meant
+for people who want to understand how the model was designed.  It does
+not go into the details of the code in the .bell and .cat files;
+rather, it explains in English what the code expresses symbolically.
+
+Sections 2 (BACKGROUND) through 5 (ORDERING AND CYCLES) are aimed
+toward beginners; they explain what memory consistency models are and
+the basic notions shared by all such models.  People already familiar
+with these concepts can skim or skip over them.  Sections 6 (EVENTS)
+through 12 (THE FROM_READS RELATION) describe the fundamental
+relations used in many models.  Starting in Section 13 (AN OPERATIONAL
+MODEL), the workings of the LKMM itself are covered.
+
+Warning: The code examples in this document are not written in the
+proper format for litmus tests.  They don't include a header line, the
+initializations are not enclosed in braces, the global variables are
+not passed by pointers, and they don't have an "exists" clause at the
+end.  Converting them to the right format is left as an exercise for
+the reader.
+
+
+BACKGROUND
+----------
+
+A memory consistency model (or just memory model, for short) is
+something which predicts, given a piece of computer code running on a
+particular kind of system, what values may be obtained by the code's
+load instructions.  The LKMM makes these predictions for code running
+as part of the Linux kernel.
+
+In practice, people tend to use memory models the other way around.
+That is, given a piece of code and a collection of values specified
+for the loads, the model will predict whether it is possible for the
+code to run in such a way that the loads will indeed obtain the
+specified values.  Of course, this is just another way of expressing
+the same idea.
+
+For code running on a uniprocessor system, the predictions are easy:
+Each load instruction must obtain the value written by the most recent
+store instruction accessing the same location (we ignore complicating
+factors such as DMA and mixed-size accesses.)  But on multiprocessor
+systems, with multiple CPUs making concurrent accesses to shared
+memory locations, things aren't so simple.
+
+Different architectures have differing memory models, and the Linux
+kernel supports a variety of architectures.  The LKMM has to be fairly
+permissive, in the sense that any behavior allowed by one of these
+architectures also has to be allowed by the LKMM.
+
+
+A SIMPLE EXAMPLE
+----------------
+
+Here is a simple example to illustrate the basic concepts.  Consider
+some code running as part of a device driver for an input device.  The
+driver might contain an interrupt handler which collects data from the
+device, stores it in a buffer, and sets a flag to indicate the buffer
+is full.  Running concurrently on a different CPU might be a part of
+the driver code being executed by a process in the midst of a read(2)
+system call.  This code tests the flag to see whether the buffer is
+ready, and if it is, copies the data back to userspace.  The buffer
+and the flag are memory locations shared between the two CPUs.
+
+We can abstract out the important pieces of the driver code as follows
+(the reason for using WRITE_ONCE() and READ_ONCE() instead of simple
+assignment statements is discussed later):
+
+        int buf = 0, flag = 0;
+
+        P0()
+        {
+                WRITE_ONCE(buf, 1);
+                WRITE_ONCE(flag, 1);
+        }
+
+        P1()
+        {
+                int r1;
+                int r2 = 0;
+
+                r1 = READ_ONCE(flag);
+                if (r1)
+                        r2 = READ_ONCE(buf);
+        }
+
+Here the P0() function represents the interrupt handler running on one
+CPU and P1() represents the read() routine running on another.  The
+value 1 stored in buf represents input data collected from the device.
+Thus, P0 stores the data in buf and then sets flag.  Meanwhile, P1
+reads flag into the private variable r1, and if it is set, reads the
+data from buf into a second private variable r2 for copying to
+userspace.  (Presumably if flag is not set then the driver will wait a
+while and try again.)
+
+This pattern of memory accesses, where one CPU stores values to two
+shared memory locations and another CPU loads from those locations in
+the opposite order, is widely known as the "Message Passing" or MP
+pattern.  It is typical of memory access patterns in the kernel.
+
+Please note that this example code is a simplified abstraction.  Real
+buffers are usually larger than a single integer, real device drivers
+usually use sleep and wakeup mechanisms rather than polling for I/O
+completion, and real code generally doesn't bother to copy values into
+private variables before using them.  All that is beside the point;
+the idea here is simply to illustrate the overall pattern of memory
+accesses by the CPUs.
+
+A memory model will predict what values P1 might obtain for its loads
+from flag and buf, or equivalently, what values r1 and r2 might end up
+with after the code has finished running.
+
+Some predictions are trivial.  For instance, no sane memory model would
+predict that r1 = 42 or r2 = -7, because neither of those values ever
+gets stored in flag or buf.
+
+Some nontrivial predictions are nonetheless quite simple.  For
+instance, P1 might run entirely before P0 begins, in which case r1 and
+r2 will both be 0 at the end.  Or P0 might run entirely before P1
+begins, in which case r1 and r2 will both be 1.
+
+The interesting predictions concern what might happen when the two
+routines run concurrently.  One possibility is that P1 runs after P0's
+store to buf but before the store to flag.  In this case, r1 and r2
+will again both be 0.  (If P1 had been designed to read buf
+unconditionally then we would instead have r1 = 0 and r2 = 1.)
+
+However, the most interesting possibility is where r1 = 1 and r2 = 0.
+If this were to occur it would mean the driver contains a bug, because
+incorrect data would get sent to the user: 0 instead of 1.  As it
+happens, the LKMM does predict this outcome can occur, and the example
+driver code shown above is indeed buggy.
+
+
+A SELECTION OF MEMORY MODELS
+----------------------------
+
+The first widely cited memory model, and the simplest to understand,
+is Sequential Consistency.  According to this model, systems behave as
+if each CPU executed its instructions in order but with unspecified
+timing.  In other words, the instructions from the various CPUs get
+interleaved in a nondeterministic way, always according to some single
+global order that agrees with the order of the instructions in the
+program source for each CPU.  The model says that the value obtained
+by each load is simply the value written by the most recently executed
+store to the same memory location, from any CPU.
+
+For the MP example code shown above, Sequential Consistency predicts
+that the undesired result r1 = 1, r2 = 0 cannot occur.  The reasoning
+goes like this:
+
+        Since r1 = 1, P0 must store 1 to flag before P1 loads 1 from
+        it, as loads can obtain values only from earlier stores.
+
+        P1 loads from flag before loading from buf, since CPUs execute
+        their instructions in order.
+
+        P1 must load 0 from buf before P0 stores 1 to it; otherwise r2
+        would be 1 since a load obtains its value from the most recent
+        store to the same address.
+
+        P0 stores 1 to buf before storing 1 to flag, since it executes
+        its instructions in order.
+
+        Since an instruction (in this case, P1's store to flag) cannot
+        execute before itself, the specified outcome is impossible.
+
+However, real computer hardware almost never follows the Sequential
+Consistency memory model; doing so would rule out too many valuable
+performance optimizations.  On ARM and PowerPC architectures, for
+instance, the MP example code really does sometimes yield r1 = 1 and
+r2 = 0.
+
+x86 and SPARC follow yet a different memory model: TSO (Total Store
+Ordering).  This model predicts that the undesired outcome for the MP
+pattern cannot occur, but in other respects it differs from Sequential
+Consistency.  One example is the Store Buffer (SB) pattern, in which
+each CPU stores to its own shared location and then loads from the
+other CPU's location:
+
+        int x = 0, y = 0;
+
+        P0()
+        {
+                int r0;
+
+                WRITE_ONCE(x, 1);
+                r0 = READ_ONCE(y);
+        }
+
+        P1()
+        {
+                int r1;
+
+                WRITE_ONCE(y, 1);
+                r1 = READ_ONCE(x);
+        }
+
+Sequential Consistency predicts that the outcome r0 = 0, r1 = 0 is
+impossible.  (Exercise: Figure out the reasoning.)  But TSO allows
+this outcome to occur, and in fact it does sometimes occur on x86 and
+SPARC systems.
+
+The LKMM was inspired by the memory models followed by PowerPC, ARM,
+x86, Alpha, and other architectures.  However, it is different in
+detail from each of them.
+
+
+ORDERING AND CYCLES
+-------------------
+
+Memory models are all about ordering.  Often this is temporal ordering
+(i.e., the order in which certain events occur) but it doesn't have to
+be; consider for example the order of instructions in a program's
+source code.  We saw above that Sequential Consistency makes an
+important assumption that CPUs execute instructions in the same order
+as those instructions occur in the code, and there are many other
+instances of ordering playing central roles in memory models.
+
+The counterpart to ordering is a cycle.  Ordering rules out cycles:
+It's not possible to have X ordered before Y, Y ordered before Z, and
+Z ordered before X, because this would mean that X is ordered before
+itself.  The analysis of the MP example under Sequential Consistency
+involved just such an impossible cycle:
+
+        W: P0 stores 1 to flag   executes before
+        X: P1 loads 1 from flag  executes before
+        Y: P1 loads 0 from buf   executes before
+        Z: P0 stores 1 to buf    executes before
+        W: P0 stores 1 to flag.
+
+In short, if a memory model requires certain accesses to be ordered,
+and a certain outcome for the loads in a piece of code can happen only
+if those accesses would form a cycle, then the memory model predicts
+that outcome cannot occur.
+
+The LKMM is defined largely in terms of cycles, as we will see.
+
+
+EVENTS
+------
+
+The LKMM does not work directly with the C statements that make up
+kernel source code.  Instead it considers the effects of those
+statements in a more abstract form, namely, events.  The model
+includes three types of events:
+
+        Read events correspond to loads from shared memory, such as
+        calls to READ_ONCE(), smp_load_acquire(), or
+        rcu_dereference().
+
+        Write events correspond to stores to shared memory, such as
+        calls to WRITE_ONCE(), smp_store_release(), or atomic_set().
+
+        Fence events correspond to memory barriers (also known as
+        fences), such as calls to smp_rmb() or rcu_read_lock().
+
+These categories are not exclusive; a read or write event can also be
+a fence.  This happens with functions like smp_load_acquire() or
+spin_lock().  However, no single event can be both a read and a write.
+Atomic read-modify-write accesses, such as atomic_inc() or xchg(),
+correspond to a pair of events: a read followed by a write.  (The
+write event is omitted for executions where it doesn't occur, such as
+a cmpxchg() where the comparison fails.)
+
+Other parts of the code, those which do not involve interaction with
+shared memory, do not give rise to events.  Thus, arithmetic and
+logical computations, control-flow instructions, or accesses to
+private memory or CPU registers are not of central interest to the
+memory model.  They only affect the model's predictions indirectly.
+For example, an arithmetic computation might determine the value that
+gets stored to a shared memory location (or in the case of an array
+index, the address where the value gets stored), but the memory model
+is concerned only with the store itself -- its value and its address
+-- not the computation leading up to it.
+
+Events in the LKMM can be linked by various relations, which we will
+describe in the following sections.  The memory model requires certain
+of these relations to be orderings, that is, it requires them not to
+have any cycles.
+
+
+THE PROGRAM ORDER RELATION: po AND po-loc
+-----------------------------------------
+
+The most important relation between events is program order (po).  You
+can think of it as the order in which statements occur in the source
+code after branches are taken into account and loops have been
+unrolled.  A better description might be the order in which
+instructions are presented to a CPU's execution unit.  Thus, we say
+that X is po-before Y (written as "X ->po Y" in formulas) if X occurs
+before Y in the instruction stream.
+
+This is inherently a single-CPU relation; two instructions executing
+on different CPUs are never linked by po.  Also, it is by definition
+an ordering so it cannot have any cycles.
+
+po-loc is a sub-relation of po.  It links two memory accesses when the
+first comes before the second in program order and they access the
+same memory location (the "-loc" suffix).
+
+Although this may seem straightforward, there is one subtle aspect to
+program order we need to explain.  The LKMM was inspired by low-level
+architectural memory models which describe the behavior of machine
+code, and it retains their outlook to a considerable extent.  The
+read, write, and fence events used by the model are close in spirit to
+individual machine instructions.  Nevertheless, the LKMM describes
+kernel code written in C, and the mapping from C to machine code can
+be extremely complex.
+
+Optimizing compilers have great freedom in the way they translate
+source code to object code.  They are allowed to apply transformations
+that add memory accesses, eliminate accesses, combine them, split them
+into pieces, or move them around.  Faced with all these possibilities,
+the LKMM basically gives up.  It insists that the code it analyzes
+must contain no ordinary accesses to shared memory; all accesses must
+be performed using READ_ONCE(), WRITE_ONCE(), or one of the other
+atomic or synchronization primitives.  These primitives prevent a
+large number of compiler optimizations.  In particular, it is
+guaranteed that the compiler will not remove such accesses from the
+generated code (unless it can prove the accesses will never be
+executed), it will not change the order in which they occur in the
+code (within limits imposed by the C standard), and it will not
+introduce extraneous accesses.
+
+This explains why the MP and SB examples above used READ_ONCE() and
+WRITE_ONCE() rather than ordinary memory accesses.  Thanks to this
+usage, we can be certain that in the MP example, P0's write event to
+buf really is po-before its write event to flag, and similarly for the
+other shared memory accesses in the examples.
+
+Private variables are not subject to this restriction.  Since they are
+not shared between CPUs, they can be accessed normally without
+READ_ONCE() or WRITE_ONCE(), and there will be no ill effects.  In
+fact, they need not even be stored in normal memory at all -- in
+principle a private variable could be stored in a CPU register (hence
+the convention that these variables have names starting with the
+letter 'r').
+
+
+A WARNING
+---------
+
+The protections provided by READ_ONCE(), WRITE_ONCE(), and others are
+not perfect; and under some circumstances it is possible for the
+compiler to undermine the memory model.  Here is an example.  Suppose
+both branches of an "if" statement store the same value to the same
+location:
+
+        r1 = READ_ONCE(x);
+        if (r1) {
+                WRITE_ONCE(y, 2);
+                ...  /* do something */
+        } else {
+                WRITE_ONCE(y, 2);
+                ...  /* do something else */
+        }
+
+For this code, the LKMM predicts that the load from x will always be
+executed before either of the stores to y.  However, a compiler could
+lift the stores out of the conditional, transforming the code into
+something resembling:
+
+        r1 = READ_ONCE(x);
+        WRITE_ONCE(y, 2);
+        if (r1) {
+                ...  /* do something */
+        } else {
+                ...  /* do something else */
+        }
+
+Given this version of the code, the LKMM would predict that the load
+from x could be executed after the store to y.  Thus, the memory
+model's original prediction could be invalidated by the compiler.
+
+Another issue arises from the fact that in C, arguments to many
+operators and function calls can be evaluated in any order.  For
+example:
+
+        r1 = f(5) + g(6);
+
+The object code might call f(5) either before or after g(6); the
+memory model cannot assume there is a fixed program order relation
+between them.  (In fact, if the functions are inlined then the
+compiler might even interleave their object code.)
+
+
+DEPENDENCY RELATIONS: data, addr, and ctrl
+------------------------------------------
+
+We say that two events are linked by a dependency relation when the
+execution of the second event depends in some way on a value obtained
+from memory by the first.  The first event must be a read, and the
+value it obtains must somehow affect what the second event does.
+There are three kinds of dependencies: data, address (addr), and
+control (ctrl).
+
+A read and a write event are linked by a data dependency if the value
+obtained by the read affects the value stored by the write.  As a very
+simple example:
+
+        int x, y;
+
+        r1 = READ_ONCE(x);
+        WRITE_ONCE(y, r1 + 5);
+
+The value stored by the WRITE_ONCE obviously depends on the value
+loaded by the READ_ONCE.  Such dependencies can wind through
+arbitrarily complicated computations, and a write can depend on the
+values of multiple reads.
+
+A read event and another memory access event are linked by an address
+dependency if the value obtained by the read affects the location
+accessed by the other event.  The second event can be either a read or
+a write.  Here's another simple example:
+
+        int a[20];
+        int i;
+
+        r1 = READ_ONCE(i);
+        r2 = READ_ONCE(a[r1]);
+
+Here the location accessed by the second READ_ONCE() depends on the
+index value loaded by the first.  Pointer indirection also gives rise
+to address dependencies, since the address of a location accessed
+through a pointer will depend on the value read earlier from that
+pointer.
+
+Finally, a read event and another memory access event are linked by a
+control dependency if the value obtained by the read affects whether
+the second event is executed at all.  Simple example:
+
+        int x, y;
+
+        r1 = READ_ONCE(x);
+        if (r1)
+                WRITE_ONCE(y, 1984);
+
+Execution of the WRITE_ONCE() is controlled by a conditional expression
+which depends on the value obtained by the READ_ONCE(); hence there is
+a control dependency from the load to the store.
+
+It should be pretty obvious that events can only depend on reads that
+come earlier in program order.  Symbolically, if we have R ->data X,
+R ->addr X, or R ->ctrl X (where R is a read event), then we must also
+have R ->po X.  It wouldn't make sense for a computation to depend
+somehow on a value that doesn't get loaded from shared memory until
+later in the code!
+
+
+THE READS-FROM RELATION: rf, rfi, and rfe
+-----------------------------------------
+
+The reads-from relation (rf) links a write event to a read event when
+the value loaded by the read is the value that was stored by the
+write.  In colloquial terms, the load "reads from" the store.  We
+write W ->rf R to indicate that the load R reads from the store W.  We
+further distinguish the cases where the load and the store occur on
+the same CPU (internal reads-from, or rfi) and where they occur on
+different CPUs (external reads-from, or rfe).
+
+For our purposes, a memory location's initial value is treated as
+though it had been written there by an imaginary initial store that
+executes on a separate CPU before the program runs.
+
+Usage of the rf relation implicitly assumes that loads will always
+read from a single store.  It doesn't apply properly in the presence
+of load-tearing, where a load obtains some of its bits from one store
+and some of them from another store.  Fortunately, use of READ_ONCE()
+and WRITE_ONCE() will prevent load-tearing; it's not possible to have:
+
+        int x = 0;
+
+        P0()
+        {
+                WRITE_ONCE(x, 0x1234);
+        }
+
+        P1()
+        {
+                int r1;
+
+                r1 = READ_ONCE(x);
+        }
+
+and end up with r1 = 0x1200 (partly from x's initial value and partly
+from the value stored by P0).
+
+On the other hand, load-tearing is unavoidable when mixed-size
+accesses are used.  Consider this example:
+
+        union {
+                u32     w;
+                u16     h[2];
+        } x;
+
+        P0()
+        {
+                WRITE_ONCE(x.h[0], 0x1234);
+                WRITE_ONCE(x.h[1], 0x5678);
+        }
+
+        P1()
+        {
+                int r1;
+
+                r1 = READ_ONCE(x.w);
+        }
+
+If r1 = 0x56781234 (little-endian!) at the end, then P1 must have read
+from both of P0's stores.  It is possible to handle mixed-size and
+unaligned accesses in a memory model, but the LKMM currently does not
+attempt to do so.  It requires all accesses to be properly aligned and
+of the location's actual size.
+
+
+CACHE COHERENCE AND THE COHERENCE ORDER RELATION: co, coi, and coe
+------------------------------------------------------------------
+
+Cache coherence is a general principle requiring that in a
+multi-processor system, the CPUs must share a consistent view of the
+memory contents.  Specifically, it requires that for each location in
+shared memory, the stores to that location must form a single global
+ordering which all the CPUs agree on (the coherence order), and this
+ordering must be consistent with the program order for accesses to
+that location.
+
+To put it another way, for any variable x, the coherence order (co) of
+the stores to x is simply the order in which the stores overwrite one
+another.  The imaginary store which establishes x's initial value
+comes first in the coherence order; the store which directly
+overwrites the initial value comes second; the store which overwrites
+that value comes third, and so on.
+
+You can think of the coherence order as being the order in which the
+stores reach x's location in memory (or if you prefer a more
+hardware-centric view, the order in which the stores get written to
+x's cache line).  We write W ->co W' if W comes before W' in the
+coherence order, that is, if the value stored by W gets overwritten,
+directly or indirectly, by the value stored by W'.
+
+Coherence order is required to be consistent with program order.  This
+requirement takes the form of four coherency rules:
+
+        Write-write coherence: If W ->po-loc W' (i.e., W comes before
+        W' in program order and they access the same location), where W
+        and W' are two stores, then W ->co W'.
+
+        Write-read coherence: If W ->po-loc R, where W is a store and R
+        is a load, then R must read from W or from some other store
+        which comes after W in the coherence order.
+
+        Read-write coherence: If R ->po-loc W, where R is a load and W
+        is a store, then the store which R reads from must come before
+        W in the coherence order.
+
+        Read-read coherence: If R ->po-loc R', where R and R' are two
+        loads, then either they read from the same store or else the
+        store read by R comes before the store read by R' in the
+        coherence order.
+
+This is sometimes referred to as sequential consistency per variable,
+because it means that the accesses to any single memory location obey
+the rules of the Sequential Consistency memory model.  (According to
+Wikipedia, sequential consistency per variable and cache coherence
+mean the same thing except that cache coherence includes an extra
+requirement that every store eventually becomes visible to every CPU.)
+
+Any reasonable memory model will include cache coherence.  Indeed, our
+expectation of cache coherence is so deeply ingrained that violations
+of its requirements look more like hardware bugs than programming
+errors:
+
+        int x;
+
+        P0()
+        {
+                WRITE_ONCE(x, 17);
+                WRITE_ONCE(x, 23);
+        }
+
+If the final value stored in x after this code ran was 17, you would
+think your computer was broken.  It would be a violation of the
+write-write coherence rule: Since the store of 23 comes later in
+program order, it must also come later in x's coherence order and
+thus must overwrite the store of 17.
+
+        int x = 0;
+
+        P0()
+        {
+                int r1;
+
+                r1 = READ_ONCE(x);
+                WRITE_ONCE(x, 666);
+        }
+
+If r1 = 666 at the end, this would violate the read-write coherence
+rule: The READ_ONCE() load comes before the WRITE_ONCE() store in
+program order, so it must not read from that store but rather from one
+coming earlier in the coherence order (in this case, x's initial
+value).
+
+        int x = 0;
+
+        P0()
+        {
+                WRITE_ONCE(x, 5);
+        }
+
+        P1()
+        {
+                int r1, r2;
+
+                r1 = READ_ONCE(x);
+                r2 = READ_ONCE(x);
+        }
+
+If r1 = 5 (reading from P0's store) and r2 = 0 (reading from the
+imaginary store which establishes x's initial value) at the end, this
+would violate the read-read coherence rule: The r1 load comes before
+the r2 load in program order, so it must not read from a store that
+comes later in the coherence order.
+
+(As a minor curiosity, if this code had used normal loads instead of
+READ_ONCE() in P1, on Itanium it sometimes could end up with r1 = 5
+and r2 = 0!  This results from parallel execution of the operations
+encoded in Itanium's Very-Long-Instruction-Word format, and it is yet
+another motivation for using READ_ONCE() when accessing shared memory
+locations.)
+
+Just like the po relation, co is inherently an ordering -- it is not
+possible for a store to directly or indirectly overwrite itself!  And
+just like with the rf relation, we distinguish between stores that
+occur on the same CPU (internal coherence order, or coi) and stores
+that occur on different CPUs (external coherence order, or coe).
+
+On the other hand, stores to different memory locations are never
+related by co, just as instructions on different CPUs are never
+related by po.  Coherence order is strictly per-location, or if you
+prefer, each location has its own independent coherence order.
+
+
+THE FROM-READS RELATION: fr, fri, and fre
+-----------------------------------------
+
+The from-reads relation (fr) can be a little difficult for people to
+grok.  It describes the situation where a load reads a value that gets
+overwritten by a store.  In other words, we have R ->fr W when the
+value that R reads is overwritten (directly or indirectly) by W, or
+equivalently, when R reads from a store which comes earlier than W in
+the coherence order.
+
+For example:
+
+        int x = 0;
+
+        P0()
+        {
+                int r1;
+
+                r1 = READ_ONCE(x);
+                WRITE_ONCE(x, 2);
+        }
+
+The value loaded from x will be 0 (assuming cache coherence!), and it
+gets overwritten by the value 2.  Thus there is an fr link from the
+READ_ONCE() to the WRITE_ONCE().  If the code contained any later
+stores to x, there would also be fr links from the READ_ONCE() to
+them.
+
+As with rf, rfi, and rfe, we subdivide the fr relation into fri (when
+the load and the store are on the same CPU) and fre (when they are on
+different CPUs).
+
+Note that the fr relation is determined entirely by the rf and co
+relations; it is not independent.  Given a read event R and a write
+event W for the same location, we will have R ->fr W if and only if
+the write which R reads from is co-before W.  In symbols,
+
+        (R ->fr W) := (there exists W' with W' ->rf R and W' ->co W).
+
+
+AN OPERATIONAL MODEL
+--------------------
+
+The LKMM is based on various operational memory models, meaning that
+the models arise from an abstract view of how a computer system
+operates.  Here are the main ideas, as incorporated into the LKMM.
+
+The system as a whole is divided into the CPUs and a memory subsystem.
+The CPUs are responsible for executing instructions (not necessarily
+in program order), and they communicate with the memory subsystem.
+For the most part, executing an instruction requires a CPU to perform
+only internal operations.  However, loads, stores, and fences involve
+more.
+
+When CPU C executes a store instruction, it tells the memory subsystem
+to store a certain value at a certain location.  The memory subsystem
+propagates the store to all the other CPUs as well as to RAM.  (As a
+special case, we say that the store propagates to its own CPU at the
+time it is executed.)  The memory subsystem also determines where the
+store falls in the location's coherence order.  In particular, it must
+arrange for the store to be co-later than (i.e., to overwrite) any
+other store to the same location which has already propagated to CPU C.
+
+When a CPU executes a load instruction R, it first checks to see
+whether there are any as-yet unexecuted store instructions, for the
+same location, that come before R in program order.  If there are, it
+uses the value of the po-latest such store as the value obtained by R,
+and we say that the store's value is forwarded to R.  Otherwise, the
+CPU asks the memory subsystem for the value to load and we say that R
+is satisfied from memory.  The memory subsystem hands back the value
+of the co-latest store to the location in question which has already
+propagated to that CPU.
+
+(In fact, the picture needs to be a little more complicated than this.
+CPUs have local caches, and propagating a store to a CPU really means
+propagating it to the CPU's local cache.  A local cache can take some
+time to process the stores that it receives, and a store can't be used
+to satisfy one of the CPU's loads until it has been processed.  On
+most architectures, the local caches process stores in
+First-In-First-Out order, and consequently the processing delay
+doesn't matter for the memory model.  But on Alpha, the local caches
+have a partitioned design that results in non-FIFO behavior.  We will
+discuss this in more detail later.)
+
+Note that load instructions may be executed speculatively and may be
+restarted under certain circumstances.  The memory model ignores these
+premature executions; we simply say that the load executes at the
+final time it is forwarded or satisfied.
+
+Executing a fence (or memory barrier) instruction doesn't require a
+CPU to do anything special other than informing the memory subsystem
+about the fence.  However, fences do constrain the way CPUs and the
+memory subsystem handle other instructions, in two respects.
+
+First, a fence forces the CPU to execute various instructions in
+program order.  Exactly which instructions are ordered depends on the
+type of fence:
+
+        Strong fences, including smp_mb() and synchronize_rcu(), force
+        the CPU to execute all po-earlier instructions before any
+        po-later instructions;
+
+        smp_rmb() forces the CPU to execute all po-earlier loads
+        before any po-later loads;
+
+        smp_wmb() forces the CPU to execute all po-earlier stores
+        before any po-later stores;
+
+        Acquire fences, such as smp_load_acquire(), force the CPU to
+        execute the load associated with the fence (e.g., the load
+        part of an smp_load_acquire()) before any po-later
+        instructions;
+
+        Release fences, such as smp_store_release(), force the CPU to
+        execute all po-earlier instructions before the store
+        associated with the fence (e.g., the store part of an
+        smp_store_release()).
+
+Second, some types of fence affect the way the memory subsystem
+propagates stores.  When a fence instruction is executed on CPU C:
+
+        For each other CPU C', smb_wmb() forces all po-earlier stores
+        on C to propagate to C' before any po-later stores do.
+
+        For each other CPU C', any store which propagates to C before
+        a release fence is executed (including all po-earlier
+        stores executed on C) is forced to propagate to C' before the
+        store associated with the release fence does.
+
+        Any store which propagates to C before a strong fence is
+        executed (including all po-earlier stores on C) is forced to
+        propagate to all other CPUs before any instructions po-after
+        the strong fence are executed on C.
+
+The propagation ordering enforced by release fences and strong fences
+affects stores from other CPUs that propagate to CPU C before the
+fence is executed, as well as stores that are executed on C before the
+fence.  We describe this property by saying that release fences and
+strong fences are A-cumulative.  By contrast, smp_wmb() fences are not
+A-cumulative; they only affect the propagation of stores that are
+executed on C before the fence (i.e., those which precede the fence in
+program order).
+
+rcu_read_lock(), rcu_read_unlock(), and synchronize_rcu() fences have
+other properties which we discuss later.
+
+
+PROPAGATION ORDER RELATION: cumul-fence
+---------------------------------------
+
+The fences which affect propagation order (i.e., strong, release, and
+smp_wmb() fences) are collectively referred to as cumul-fences, even
+though smp_wmb() isn't A-cumulative.  The cumul-fence relation is
+defined to link memory access events E and F whenever:
+
+        E and F are both stores on the same CPU and an smp_wmb() fence
+        event occurs between them in program order; or
+
+        F is a release fence and some X comes before F in program order,
+        where either X = E or else E ->rf X; or
+
+        A strong fence event occurs between some X and F in program
+        order, where either X = E or else E ->rf X.
+
+The operational model requires that whenever W and W' are both stores
+and W ->cumul-fence W', then W must propagate to any given CPU
+before W' does.  However, for different CPUs C and C', it does not
+require W to propagate to C before W' propagates to C'.
+
+
+DERIVATION OF THE LKMM FROM THE OPERATIONAL MODEL
+-------------------------------------------------
+
+The LKMM is derived from the restrictions imposed by the design
+outlined above.  These restrictions involve the necessity of
+maintaining cache coherence and the fact that a CPU can't operate on a
+value before it knows what that value is, among other things.
+
+The formal version of the LKMM is defined by five requirements, or
+axioms:
+
+        Sequential consistency per variable: This requires that the
+        system obey the four coherency rules.
+
+        Atomicity: This requires that atomic read-modify-write
+        operations really are atomic, that is, no other stores can
+        sneak into the middle of such an update.
+
+        Happens-before: This requires that certain instructions are
+        executed in a specific order.
+
+        Propagation: This requires that certain stores propagate to
+        CPUs and to RAM in a specific order.
+
+        Rcu: This requires that RCU read-side critical sections and
+        grace periods obey the rules of RCU, in particular, the
+        Grace-Period Guarantee.
+
+The first and second are quite common; they can be found in many
+memory models (such as those for C11/C++11).  The "happens-before" and
+"propagation" axioms have analogs in other memory models as well.  The
+"rcu" axiom is specific to the LKMM.
+
+Each of these axioms is discussed below.
+
+
+SEQUENTIAL CONSISTENCY PER VARIABLE
+-----------------------------------
+
+According to the principle of cache coherence, the stores to any fixed
+shared location in memory form a global ordering.  We can imagine
+inserting the loads from that location into this ordering, by placing
+each load between the store that it reads from and the following
+store.  This leaves the relative positions of loads that read from the
+same store unspecified; let's say they are inserted in program order,
+first for CPU 0, then CPU 1, etc.
+
+You can check that the four coherency rules imply that the rf, co, fr,
+and po-loc relations agree with this global ordering; in other words,
+whenever we have X ->rf Y or X ->co Y or X ->fr Y or X ->po-loc Y, the
+X event comes before the Y event in the global ordering.  The LKMM's
+"coherence" axiom expresses this by requiring the union of these
+relations not to have any cycles.  This means it must not be possible
+to find events
+
+        X0 -> X1 -> X2 -> ... -> Xn -> X0,
+
+where each of the links is either rf, co, fr, or po-loc.  This has to
+hold if the accesses to the fixed memory location can be ordered as
+cache coherence demands.
+
+Although it is not obvious, it can be shown that the converse is also
+true: This LKMM axiom implies that the four coherency rules are
+obeyed.
+
+
+ATOMIC UPDATES: rmw
+-------------------
+
+What does it mean to say that a read-modify-write (rmw) update, such
+as atomic_inc(&x), is atomic?  It means that the memory location (x in
+this case) does not get altered between the read and the write events
+making up the atomic operation.  In particular, if two CPUs perform
+atomic_inc(&x) concurrently, it must be guaranteed that the final
+value of x will be the initial value plus two.  We should never have
+the following sequence of events:
+
+        CPU 0 loads x obtaining 13;
+                                        CPU 1 loads x obtaining 13;
+        CPU 0 stores 14 to x;
+                                        CPU 1 stores 14 to x;
+
+where the final value of x is wrong (14 rather than 15).
+
+In this example, CPU 0's increment effectively gets lost because it
+occurs in between CPU 1's load and store.  To put it another way, the
+problem is that the position of CPU 0's store in x's coherence order
+is between the store that CPU 1 reads from and the store that CPU 1
+performs.
+
+The same analysis applies to all atomic update operations.  Therefore,
+to enforce atomicity the LKMM requires that atomic updates follow this
+rule: Whenever R and W are the read and write events composing an
+atomic read-modify-write and W' is the write event which R reads from,
+there must not be any stores coming between W' and W in the coherence
+order.  Equivalently,
+
+        (R ->rmw W) implies (there is no X with R ->fr X and X ->co W),
+
+where the rmw relation links the read and write events making up each
+atomic update.  This is what the LKMM's "atomic" axiom says.
+
+
+THE PRESERVED PROGRAM ORDER RELATION: ppo
+-----------------------------------------
+
+There are many situations where a CPU is obligated to execute two
+instructions in program order.  We amalgamate them into the ppo (for
+"preserved program order") relation, which links the po-earlier
+instruction to the po-later instruction and is thus a sub-relation of
+po.
+
+The operational model already includes a description of one such
+situation: Fences are a source of ppo links.  Suppose X and Y are
+memory accesses with X ->po Y; then the CPU must execute X before Y if
+any of the following hold:
+
+        A strong (smp_mb() or synchronize_rcu()) fence occurs between
+        X and Y;
+
+        X and Y are both stores and an smp_wmb() fence occurs between
+        them;
+
+        X and Y are both loads and an smp_rmb() fence occurs between
+        them;
+
+        X is also an acquire fence, such as smp_load_acquire();
+
+        Y is also a release fence, such as smp_store_release().
+
+Another possibility, not mentioned earlier but discussed in the next
+section, is:
+
+        X and Y are both loads, X ->addr Y (i.e., there is an address
+        dependency from X to Y), and X is a READ_ONCE() or an atomic
+        access.
+
+Dependencies can also cause instructions to be executed in program
+order.  This is uncontroversial when the second instruction is a
+store; either a data, address, or control dependency from a load R to
+a store W will force the CPU to execute R before W.  This is very
+simply because the CPU cannot tell the memory subsystem about W's
+store before it knows what value should be stored (in the case of a
+data dependency), what location it should be stored into (in the case
+of an address dependency), or whether the store should actually take
+place (in the case of a control dependency).
+
+Dependencies to load instructions are more problematic.  To begin with,
+there is no such thing as a data dependency to a load.  Next, a CPU
+has no reason to respect a control dependency to a load, because it
+can always satisfy the second load speculatively before the first, and
+then ignore the result if it turns out that the second load shouldn't
+be executed after all.  And lastly, the real difficulties begin when
+we consider address dependencies to loads.
+
+To be fair about it, all Linux-supported architectures do execute
+loads in program order if there is an address dependency between them.
+After all, a CPU cannot ask the memory subsystem to load a value from
+a particular location before it knows what that location is.  However,
+the split-cache design used by Alpha can cause it to behave in a way
+that looks as if the loads were executed out of order (see the next
+section for more details).  The kernel includes a workaround for this
+problem when the loads come from READ_ONCE(), and therefore the LKMM
+includes address dependencies to loads in the ppo relation.
+
+On the other hand, dependencies can indirectly affect the ordering of
+two loads.  This happens when there is a dependency from a load to a
+store and a second, po-later load reads from that store:
+
+        R ->dep W ->rfi R',
+
+where the dep link can be either an address or a data dependency.  In
+this situation we know it is possible for the CPU to execute R' before
+W, because it can forward the value that W will store to R'.  But it
+cannot execute R' before R, because it cannot forward the value before
+it knows what that value is, or that W and R' do access the same
+location.  However, if there is merely a control dependency between R
+and W then the CPU can speculatively forward W to R' before executing
+R; if the speculation turns out to be wrong then the CPU merely has to
+restart or abandon R'.
+
+(In theory, a CPU might forward a store to a load when it runs across
+an address dependency like this:
+
+        r1 = READ_ONCE(ptr);
+        WRITE_ONCE(*r1, 17);
+        r2 = READ_ONCE(*r1);
+
+because it could tell that the store and the second load access the
+same location even before it knows what the location's address is.
+However, none of the architectures supported by the Linux kernel do
+this.)
+
+Two memory accesses of the same location must always be executed in
+program order if the second access is a store.  Thus, if we have
+
+        R ->po-loc W
+
+(the po-loc link says that R comes before W in program order and they
+access the same location), the CPU is obliged to execute W after R.
+If it executed W first then the memory subsystem would respond to R's
+read request with the value stored by W (or an even later store), in
+violation of the read-write coherence rule.  Similarly, if we had
+
+        W ->po-loc W'
+
+and the CPU executed W' before W, then the memory subsystem would put
+W' before W in the coherence order.  It would effectively cause W to
+overwrite W', in violation of the write-write coherence rule.
+(Interestingly, an early ARMv8 memory model, now obsolete, proposed
+allowing out-of-order writes like this to occur.  The model avoided
+violating the write-write coherence rule by requiring the CPU not to
+send the W write to the memory subsystem at all!)
+
+There is one last example of preserved program order in the LKMM: when
+a load-acquire reads from an earlier store-release.  For example:
+
+        smp_store_release(&x, 123);
+        r1 = smp_load_acquire(&x);
+
+If the smp_load_acquire() ends up obtaining the 123 value that was
+stored by the smp_store_release(), the LKMM says that the load must be
+executed after the store; the store cannot be forwarded to the load.
+This requirement does not arise from the operational model, but it
+yields correct predictions on all architectures supported by the Linux
+kernel, although for differing reasons.
+
+On some architectures, including x86 and ARMv8, it is true that the
+store cannot be forwarded to the load.  On others, including PowerPC
+and ARMv7, smp_store_release() generates object code that starts with
+a fence and smp_load_acquire() generates object code that ends with a
+fence.  The upshot is that even though the store may be forwarded to
+the load, it is still true that any instruction preceding the store
+will be executed before the load or any following instructions, and
+the store will be executed before any instruction following the load.
+
+
+AND THEN THERE WAS ALPHA
+------------------------
+
+As mentioned above, the Alpha architecture is unique in that it does
+not appear to respect address dependencies to loads.  This means that
+code such as the following:
+
+        int x = 0;
+        int y = -1;
+        int *ptr = &y;
+
+        P0()
+        {
+                WRITE_ONCE(x, 1);
+                smp_wmb();
+                WRITE_ONCE(ptr, &x);
+        }
+
+        P1()
+        {
+                int *r1;
+                int r2;
+
+                r1 = ptr;
+                r2 = READ_ONCE(*r1);
+        }
+
+can malfunction on Alpha systems (notice that P1 uses an ordinary load
+to read ptr instead of READ_ONCE()).  It is quite possible that r1 = &x
+and r2 = 0 at the end, in spite of the address dependency.
+
+At first glance this doesn't seem to make sense.  We know that the
+smp_wmb() forces P0's store to x to propagate to P1 before the store
+to ptr does.  And since P1 can't execute its second load
+until it knows what location to load from, i.e., after executing its
+first load, the value x = 1 must have propagated to P1 before the
+second load executed.  So why doesn't r2 end up equal to 1?
+
+The answer lies in the Alpha's split local caches.  Although the two
+stores do reach P1's local cache in the proper order, it can happen
+that the first store is processed by a busy part of the cache while
+the second store is processed by an idle part.  As a result, the x = 1
+value may not become available for P1's CPU to read until after the
+ptr = &x value does, leading to the undesirable result above.  The
+final effect is that even though the two loads really are executed in
+program order, it appears that they aren't.
+
+This could not have happened if the local cache had processed the
+incoming stores in FIFO order.  By contrast, other architectures
+maintain at least the appearance of FIFO order.
+
+In practice, this difficulty is solved by inserting a special fence
+between P1's two loads when the kernel is compiled for the Alpha
+architecture.  In fact, as of version 4.15, the kernel automatically
+adds this fence (called smp_read_barrier_depends() and defined as
+nothing at all on non-Alpha builds) after every READ_ONCE() and atomic
+load.  The effect of the fence is to cause the CPU not to execute any
+po-later instructions until after the local cache has finished
+processing all the stores it has already received.  Thus, if the code
+was changed to:
+
+        P1()
+        {
+                int *r1;
+                int r2;
+
+                r1 = READ_ONCE(ptr);
+                r2 = READ_ONCE(*r1);
+        }
+
+then we would never get r1 = &x and r2 = 0.  By the time P1 executed
+its second load, the x = 1 store would already be fully processed by
+the local cache and available for satisfying the read request.  Thus
+we have yet another reason why shared data should always be read with
+READ_ONCE() or another synchronization primitive rather than accessed
+directly.
+
+The LKMM requires that smp_rmb(), acquire fences, and strong fences
+share this property with smp_read_barrier_depends(): They do not allow
+the CPU to execute any po-later instructions (or po-later loads in the
+case of smp_rmb()) until all outstanding stores have been processed by
+the local cache.  In the case of a strong fence, the CPU first has to
+wait for all of its po-earlier stores to propagate to every other CPU
+in the system; then it has to wait for the local cache to process all
+the stores received as of that time -- not just the stores received
+when the strong fence began.
+
+And of course, none of this matters for any architecture other than
+Alpha.
+
+
+THE HAPPENS-BEFORE RELATION: hb
+-------------------------------
+
+The happens-before relation (hb) links memory accesses that have to
+execute in a certain order.  hb includes the ppo relation and two
+others, one of which is rfe.
+
+W ->rfe R implies that W and R are on different CPUs.  It also means
+that W's store must have propagated to R's CPU before R executed;
+otherwise R could not have read the value stored by W.  Therefore W
+must have executed before R, and so we have W ->hb R.
+
+The equivalent fact need not hold if W ->rfi R (i.e., W and R are on
+the same CPU).  As we have already seen, the operational model allows
+W's value to be forwarded to R in such cases, meaning that R may well
+execute before W does.
+
+It's important to understand that neither coe nor fre is included in
+hb, despite their similarities to rfe.  For example, suppose we have
+W ->coe W'.  This means that W and W' are stores to the same location,
+they execute on different CPUs, and W comes before W' in the coherence
+order (i.e., W' overwrites W).  Nevertheless, it is possible for W' to
+execute before W, because the decision as to which store overwrites
+the other is made later by the memory subsystem.  When the stores are
+nearly simultaneous, either one can come out on top.  Similarly,
+R ->fre W means that W overwrites the value which R reads, but it
+doesn't mean that W has to execute after R.  All that's necessary is
+for the memory subsystem not to propagate W to R's CPU until after R
+has executed, which is possible if W executes shortly before R.
+
+The third relation included in hb is like ppo, in that it only links
+events that are on the same CPU.  However it is more difficult to
+explain, because it arises only indirectly from the requirement of
+cache coherence.  The relation is called prop, and it links two events
+on CPU C in situations where a store from some other CPU comes after
+the first event in the coherence order and propagates to C before the
+second event executes.
+
+This is best explained with some examples.  The simplest case looks
+like this:
+
+        int x;
+
+        P0()
+        {
+                int r1;
+
+                WRITE_ONCE(x, 1);
+                r1 = READ_ONCE(x);
+        }
+
+        P1()
+        {
+                WRITE_ONCE(x, 8);
+        }
+
+If r1 = 8 at the end then P0's accesses must have executed in program
+order.  We can deduce this from the operational model; if P0's load
+had executed before its store then the value of the store would have
+been forwarded to the load, so r1 would have ended up equal to 1, not
+8.  In this case there is a prop link from P0's write event to its read
+event, because P1's store came after P0's store in x's coherence
+order, and P1's store propagated to P0 before P0's load executed.
+
+An equally simple case involves two loads of the same location that
+read from different stores:
+
+        int x = 0;
+
+        P0()
+        {
+                int r1, r2;
+
+                r1 = READ_ONCE(x);
+                r2 = READ_ONCE(x);
+        }
+
+        P1()
+        {
+                WRITE_ONCE(x, 9);
+        }
+
+If r1 = 0 and r2 = 9 at the end then P0's accesses must have executed
+in program order.  If the second load had executed before the first
+then the x = 9 store must have been propagated to P0 before the first
+load executed, and so r1 would have been 9 rather than 0.  In this
+case there is a prop link from P0's first read event to its second,
+because P1's store overwrote the value read by P0's first load, and
+P1's store propagated to P0 before P0's second load executed.
+
+Less trivial examples of prop all involve fences.  Unlike the simple
+examples above, they can require that some instructions are executed
+out of program order.  This next one should look familiar:
+
+        int buf = 0, flag = 0;
+
+        P0()
+        {
+                WRITE_ONCE(buf, 1);
+                smp_wmb();
+                WRITE_ONCE(flag, 1);
+        }
+
+        P1()
+        {
+                int r1;
+                int r2;
+
+                r1 = READ_ONCE(flag);
+                r2 = READ_ONCE(buf);
+        }
+
+This is the MP pattern again, with an smp_wmb() fence between the two
+stores.  If r1 = 1 and r2 = 0 at the end then there is a prop link
+from P1's second load to its first (backwards!).  The reason is
+similar to the previous examples: The value P1 loads from buf gets
+overwritten by P0's store to buf, the fence guarantees that the store
+to buf will propagate to P1 before the store to flag does, and the
+store to flag propagates to P1 before P1 reads flag.
+
+The prop link says that in order to obtain the r1 = 1, r2 = 0 result,
+P1 must execute its second load before the first.  Indeed, if the load
+from flag were executed first, then the buf = 1 store would already
+have propagated to P1 by the time P1's load from buf executed, so r2
+would have been 1 at the end, not 0.  (The reasoning holds even for
+Alpha, although the details are more complicated and we will not go
+into them.)
+
+But what if we put an smp_rmb() fence between P1's loads?  The fence
+would force the two loads to be executed in program order, and it
+would generate a cycle in the hb relation: The fence would create a ppo
+link (hence an hb link) from the first load to the second, and the
+prop relation would give an hb link from the second load to the first.
+Since an instruction can't execute before itself, we are forced to
+conclude that if an smp_rmb() fence is added, the r1 = 1, r2 = 0
+outcome is impossible -- as it should be.
+
+The formal definition of the prop relation involves a coe or fre link,
+followed by an arbitrary number of cumul-fence links, ending with an
+rfe link.  You can concoct more exotic examples, containing more than
+one fence, although this quickly leads to diminishing returns in terms
+of complexity.  For instance, here's an example containing a coe link
+followed by two fences and an rfe link, utilizing the fact that
+release fences are A-cumulative:
+
+        int x, y, z;
+
+        P0()
+        {
+                int r0;
+
+                WRITE_ONCE(x, 1);
+                r0 = READ_ONCE(z);
+        }
+
+        P1()
+        {
+                WRITE_ONCE(x, 2);
+                smp_wmb();
+                WRITE_ONCE(y, 1);
+        }
+
+        P2()
+        {
+                int r2;
+
+                r2 = READ_ONCE(y);
+                smp_store_release(&z, 1);
+        }
+
+If x = 2, r0 = 1, and r2 = 1 after this code runs then there is a prop
+link from P0's store to its load.  This is because P0's store gets
+overwritten by P1's store since x = 2 at the end (a coe link), the
+smp_wmb() ensures that P1's store to x propagates to P2 before the
+store to y does (the first fence), the store to y propagates to P2
+before P2's load and store execute, P2's smp_store_release()
+guarantees that the stores to x and y both propagate to P0 before the
+store to z does (the second fence), and P0's load executes after the
+store to z has propagated to P0 (an rfe link).
+
+In summary, the fact that the hb relation links memory access events
+in the order they execute means that it must not have cycles.  This
+requirement is the content of the LKMM's "happens-before" axiom.
+
+The LKMM defines yet another relation connected to times of
+instruction execution, but it is not included in hb.  It relies on the
+particular properties of strong fences, which we cover in the next
+section.
+
+
+THE PROPAGATES-BEFORE RELATION: pb
+----------------------------------
+
+The propagates-before (pb) relation capitalizes on the special
+features of strong fences.  It links two events E and F whenever some
+store is coherence-later than E and propagates to every CPU and to RAM
+before F executes.  The formal definition requires that E be linked to
+F via a coe or fre link, an arbitrary number of cumul-fences, an
+optional rfe link, a strong fence, and an arbitrary number of hb
+links.  Let's see how this definition works out.
+
+Consider first the case where E is a store (implying that the sequence
+of links begins with coe).  Then there are events W, X, Y, and Z such
+that:
+
+        E ->coe W ->cumul-fence* X ->rfe? Y ->strong-fence Z ->hb* F,
+
+where the * suffix indicates an arbitrary number of links of the
+specified type, and the ? suffix indicates the link is optional (Y may
+be equal to X).  Because of the cumul-fence links, we know that W will
+propagate to Y's CPU before X does, hence before Y executes and hence
+before the strong fence executes.  Because this fence is strong, we
+know that W will propagate to every CPU and to RAM before Z executes.
+And because of the hb links, we know that Z will execute before F.
+Thus W, which comes later than E in the coherence order, will
+propagate to every CPU and to RAM before F executes.
+
+The case where E is a load is exactly the same, except that the first
+link in the sequence is fre instead of coe.
+
+The existence of a pb link from E to F implies that E must execute
+before F.  To see why, suppose that F executed first.  Then W would
+have propagated to E's CPU before E executed.  If E was a store, the
+memory subsystem would then be forced to make E come after W in the
+coherence order, contradicting the fact that E ->coe W.  If E was a
+load, the memory subsystem would then be forced to satisfy E's read
+request with the value stored by W or an even later store,
+contradicting the fact that E ->fre W.
+
+A good example illustrating how pb works is the SB pattern with strong
+fences:
+
+        int x = 0, y = 0;
+
+        P0()
+        {
+                int r0;
+
+                WRITE_ONCE(x, 1);
+                smp_mb();
+                r0 = READ_ONCE(y);
+        }
+
+        P1()
+        {
+                int r1;
+
+                WRITE_ONCE(y, 1);
+                smp_mb();
+                r1 = READ_ONCE(x);
+        }
+
+If r0 = 0 at the end then there is a pb link from P0's load to P1's
+load: an fre link from P0's load to P1's store (which overwrites the
+value read by P0), and a strong fence between P1's store and its load.
+In this example, the sequences of cumul-fence and hb links are empty.
+Note that this pb link is not included in hb as an instance of prop,
+because it does not start and end on the same CPU.
+
+Similarly, if r1 = 0 at the end then there is a pb link from P1's load
+to P0's.  This means that if both r1 and r2 were 0 there would be a
+cycle in pb, which is not possible since an instruction cannot execute
+before itself.  Thus, adding smp_mb() fences to the SB pattern
+prevents the r0 = 0, r1 = 0 outcome.
+
+In summary, the fact that the pb relation links events in the order
+they execute means that it cannot have cycles.  This requirement is
+the content of the LKMM's "propagation" axiom.
+
+
+RCU RELATIONS: link, gp-link, rscs-link, and rcu-path
+-----------------------------------------------------
+
+RCU (Read-Copy-Update) is a powerful synchronization mechanism.  It
+rests on two concepts: grace periods and read-side critical sections.
+
+A grace period is the span of time occupied by a call to
+synchronize_rcu().  A read-side critical section (or just critical
+section, for short) is a region of code delimited by rcu_read_lock()
+at the start and rcu_read_unlock() at the end.  Critical sections can
+be nested, although we won't make use of this fact.
+
+As far as memory models are concerned, RCU's main feature is its
+Grace-Period Guarantee, which states that a critical section can never
+span a full grace period.  In more detail, the Guarantee says:
+
+        If a critical section starts before a grace period then it
+        must end before the grace period does.  In addition, every
+        store that propagates to the critical section's CPU before the
+        end of the critical section must propagate to every CPU before
+        the end of the grace period.
+
+        If a critical section ends after a grace period ends then it
+        must start after the grace period does.  In addition, every
+        store that propagates to the grace period's CPU before the
+        start of the grace period must propagate to every CPU before
+        the start of the critical section.
+
+Here is a simple example of RCU in action:
+
+        int x, y;
+
+        P0()
+        {
+                rcu_read_lock();
+                WRITE_ONCE(x, 1);
+                WRITE_ONCE(y, 1);
+                rcu_read_unlock();
+        }
+
+        P1()
+        {
+                int r1, r2;
+
+                r1 = READ_ONCE(x);
+                synchronize_rcu();
+                r2 = READ_ONCE(y);
+        }
+
+The Grace Period Guarantee tells us that when this code runs, it will
+never end with r1 = 1 and r2 = 0.  The reasoning is as follows.  r1 = 1
+means that P0's store to x propagated to P1 before P1 called
+synchronize_rcu(), so P0's critical section must have started before
+P1's grace period.  On the other hand, r2 = 0 means that P0's store to
+y, which occurs before the end of the critical section, did not
+propagate to P1 before the end of the grace period, violating the
+Guarantee.
+
+In the kernel's implementations of RCU, the business about stores
+propagating to every CPU is realized by placing strong fences at
+suitable places in the RCU-related code.  Thus, if a critical section
+starts before a grace period does then the critical section's CPU will
+execute an smp_mb() fence after the end of the critical section and
+some time before the grace period's synchronize_rcu() call returns.
+And if a critical section ends after a grace period does then the
+synchronize_rcu() routine will execute an smp_mb() fence at its start
+and some time before the critical section's opening rcu_read_lock()
+executes.
+
+What exactly do we mean by saying that a critical section "starts
+before" or "ends after" a grace period?  Some aspects of the meaning
+are pretty obvious, as in the example above, but the details aren't
+entirely clear.  The LKMM formalizes this notion by means of a
+relation with the unfortunately generic name "link".  It is a very
+general relation; among other things, X ->link Z includes cases where
+X happens-before or is equal to some event Y which is equal to or
+comes before Z in the coherence order.  Taking Y = Z, this says that
+X ->rfe Z implies X ->link Z, and taking Y = X, it says that X ->fr Z
+and X ->co Z each imply X ->link Z.
+
+The formal definition of the link relation is more than a little
+obscure, and we won't give it here.  It is closely related to the pb
+relation, and the details don't matter unless you want to comb through
+a somewhat lengthy formal proof.  Pretty much all you need to know
+about link is the information in the preceding paragraph.
+
+The LKMM goes on to define the gp-link and rscs-link relations.  They
+bring grace periods and read-side critical sections into the picture,
+in the following way:
+
+        E ->gp-link F means there is a synchronize_rcu() fence event S
+        and an event X such that E ->po S, either S ->po X or S = X,
+        and X ->link F.  In other words, E and F are connected by a
+        grace period followed by an instance of link.
+
+        E ->rscs-link F means there is a critical section delimited by
+        an rcu_read_lock() fence L and an rcu_read_unlock() fence U,
+        and an event X such that E ->po U, either L ->po X or L = X,
+        and X ->link F.  Roughly speaking, this says that some event
+        in the same critical section as E is connected by link to F.
+
+If we think of the link relation as standing for an extended "before",
+then E ->gp-link F says that E executes before a grace period which
+ends before F executes.  (In fact it says more than this, because it
+includes cases where E executes before a grace period and some store
+propagates to F's CPU before F executes and doesn't propagate to some
+other CPU until after the grace period ends.)  Similarly,
+E ->rscs-link F says that E is part of (or before the start of) a
+critical section which starts before F executes.
+
+Putting this all together, the LKMM expresses the Grace Period
+Guarantee by requiring that there are no cycles consisting of gp-link
+and rscs-link connections in which the number of gp-link instances is
+>= the number of rscs-link instances.  It does this by defining the
+rcu-path relation to link events E and F whenever it is possible to
+pass from E to F by a sequence of gp-link and rscs-link connections
+with at least as many of the former as the latter.  The LKMM's "rcu"
+axiom then says that there are no events E such that E ->rcu-path E.
+
+Justifying this axiom takes some intellectual effort, but it is in
+fact a valid formalization of the Grace Period Guarantee.  We won't
+attempt to go through the detailed argument, but the following
+analysis gives a taste of what is involved.  Suppose we have a
+violation of the first part of the Guarantee: A critical section
+starts before a grace period, and some store propagates to the
+critical section's CPU before the end of the critical section but
+doesn't propagate to some other CPU until after the end of the grace
+period.
+
+Putting symbols to these ideas, let L and U be the rcu_read_lock() and
+rcu_read_unlock() fence events delimiting the critical section in
+question, and let S be the synchronize_rcu() fence event for the grace
+period.  Saying that the critical section starts before S means there
+are events E and F where E is po-after L (which marks the start of the
+critical section), E is "before" F in the sense of the link relation,
+and F is po-before the grace period S:
+
+        L ->po E ->link F ->po S.
+
+Let W be the store mentioned above, let Z come before the end of the
+critical section and witness that W propagates to the critical
+section's CPU by reading from W, and let Y on some arbitrary CPU be a
+witness that W has not propagated to that CPU, where Y happens after
+some event X which is po-after S.  Symbolically, this amounts to:
+
+        S ->po X ->hb* Y ->fr W ->rf Z ->po U.
+
+The fr link from Y to W indicates that W has not propagated to Y's CPU
+at the time that Y executes.  From this, it can be shown (see the
+discussion of the link relation earlier) that X and Z are connected by
+link, yielding:
+
+        S ->po X ->link Z ->po U.
+
+These formulas say that S is po-between F and X, hence F ->gp-link Z
+via X.  They also say that Z comes before the end of the critical
+section and E comes after its start, hence Z ->rscs-link F via E.  But
+now we have a forbidden cycle: F ->gp-link Z ->rscs-link F.  Thus the
+"rcu" axiom rules out this violation of the Grace Period Guarantee.
+
+For something a little more down-to-earth, let's see how the axiom
+works out in practice.  Consider the RCU code example from above, this
+time with statement labels added to the memory access instructions:
+
+        int x, y;
+
+        P0()
+        {
+                rcu_read_lock();
+                W: WRITE_ONCE(x, 1);
+                X: WRITE_ONCE(y, 1);
+                rcu_read_unlock();
+        }
+
+        P1()
+        {
+                int r1, r2;
+
+                Y: r1 = READ_ONCE(x);
+                synchronize_rcu();
+                Z: r2 = READ_ONCE(y);
+        }
+
+
+If r2 = 0 at the end then P0's store at X overwrites the value
+that P1's load at Z reads from, so we have Z ->fre X and thus
+Z ->link X.  In addition, there is a synchronize_rcu() between Y and
+Z, so therefore we have Y ->gp-link X.
+
+If r1 = 1 at the end then P1's load at Y reads from P0's store at W,
+so we have W ->link Y.  In addition, W and X are in the same critical
+section, so therefore we have X ->rscs-link Y.
+
+This gives us a cycle, Y ->gp-link X ->rscs-link Y, with one gp-link
+and one rscs-link, violating the "rcu" axiom.  Hence the outcome is
+not allowed by the LKMM, as we would expect.
+
+For contrast, let's see what can happen in a more complicated example:
+
+        int x, y, z;
+
+        P0()
+        {
+                int r0;
+
+                rcu_read_lock();
+                W: r0 = READ_ONCE(x);
+                X: WRITE_ONCE(y, 1);
+                rcu_read_unlock();
+        }
+
+        P1()
+        {
+                int r1;
+
+                Y: r1 = READ_ONCE(y);
+                synchronize_rcu();
+                Z: WRITE_ONCE(z, 1);
+        }
+
+        P2()
+        {
+                int r2;
+
+                rcu_read_lock();
+                U: r2 = READ_ONCE(z);
+                V: WRITE_ONCE(x, 1);
+                rcu_read_unlock();
+        }
+
+If r0 = r1 = r2 = 1 at the end, then similar reasoning to before shows
+that W ->rscs-link Y via X, Y ->gp-link U via Z, and U ->rscs-link W
+via V.  And just as before, this gives a cycle:
+
+        W ->rscs-link Y ->gp-link U ->rscs-link W.
+
+However, this cycle has fewer gp-link instances than rscs-link
+instances, and consequently the outcome is not forbidden by the LKMM.
+The following instruction timing diagram shows how it might actually
+occur:
+
+P0                      P1                      P2
+--------------------    --------------------    --------------------
+rcu_read_lock()
+X: WRITE_ONCE(y, 1)
+                        Y: r1 = READ_ONCE(y)
+                        synchronize_rcu() starts
+                        .                       rcu_read_lock()
+                        .                       V: WRITE_ONCE(x, 1)
+W: r0 = READ_ONCE(x)    .
+rcu_read_unlock()       .
+                        synchronize_rcu() ends
+                        Z: WRITE_ONCE(z, 1)
+                                                U: r2 = READ_ONCE(z)
+                                                rcu_read_unlock()
+
+This requires P0 and P2 to execute their loads and stores out of
+program order, but of course they are allowed to do so.  And as you
+can see, the Grace Period Guarantee is not violated: The critical
+section in P0 both starts before P1's grace period does and ends
+before it does, and the critical section in P2 both starts after P1's
+grace period does and ends after it does.
+
+
+ODDS AND ENDS
+-------------
+
+This section covers material that didn't quite fit anywhere in the
+earlier sections.
+
+The descriptions in this document don't always match the formal
+version of the LKMM exactly.  For example, the actual formal
+definition of the prop relation makes the initial coe or fre part
+optional, and it doesn't require the events linked by the relation to
+be on the same CPU.  These differences are very unimportant; indeed,
+instances where the coe/fre part of prop is missing are of no interest
+because all the other parts (fences and rfe) are already included in
+hb anyway, and where the formal model adds prop into hb, it includes
+an explicit requirement that the events being linked are on the same
+CPU.
+
+Another minor difference has to do with events that are both memory
+accesses and fences, such as those corresponding to smp_load_acquire()
+calls.  In the formal model, these events aren't actually both reads
+and fences; rather, they are read events with an annotation marking
+them as acquires.  (Or write events annotated as releases, in the case
+smp_store_release().)  The final effect is the same.
+
+Although we didn't mention it above, the instruction execution
+ordering provided by the smp_rmb() fence doesn't apply to read events
+that are part of a non-value-returning atomic update.  For instance,
+given:
+
+        atomic_inc(&x);
+        smp_rmb();
+        r1 = READ_ONCE(y);
+
+it is not guaranteed that the load from y will execute after the
+update to x.  This is because the ARMv8 architecture allows
+non-value-returning atomic operations effectively to be executed off
+the CPU.  Basically, the CPU tells the memory subsystem to increment
+x, and then the increment is carried out by the memory hardware with
+no further involvement from the CPU.  Since the CPU doesn't ever read
+the value of x, there is nothing for the smp_rmb() fence to act on.
+
+The LKMM defines a few extra synchronization operations in terms of
+things we have already covered.  In particular, rcu_dereference() is
+treated as READ_ONCE() and rcu_assign_pointer() is treated as
+smp_store_release() -- which is basically how the Linux kernel treats
+them.
+
+There are a few oddball fences which need special treatment:
+smp_mb__before_atomic(), smp_mb__after_atomic(), and
+smp_mb__after_spinlock().  The LKMM uses fence events with special
+annotations for them; they act as strong fences just like smp_mb()
+except for the sets of events that they order.  Instead of ordering
+all po-earlier events against all po-later events, as smp_mb() does,
+they behave as follows:
+
+        smp_mb__before_atomic() orders all po-earlier events against
+        po-later atomic updates and the events following them;
+
+        smp_mb__after_atomic() orders po-earlier atomic updates and
+        the events preceding them against all po-later events;
+
+        smp_mb_after_spinlock() orders po-earlier lock acquisition
+        events and the events preceding them against all po-later
+        events.
+
+The LKMM includes locking.  In fact, there is special code for locking
+in the formal model, added in order to make tools run faster.
+However, this special code is intended to be exactly equivalent to
+concepts we have already covered.  A spinlock_t variable is treated
+the same as an int, and spin_lock(&s) is treated the same as:
+
+        while (cmpxchg_acquire(&s, 0, 1) != 0)
+                cpu_relax();
+
+which waits until s is equal to 0 and then atomically sets it to 1,
+and where the read part of the atomic update is also an acquire fence.
+An alternate way to express the same thing would be:
+
+        r = xchg_acquire(&s, 1);
+
+along with a requirement that at the end, r = 0.  spin_unlock(&s) is
+treated the same as:
+
+        smp_store_release(&s, 0);
+
+Interestingly, RCU and locking each introduce the possibility of
+deadlock.  When faced with code sequences such as:
+
+        spin_lock(&s);
+        spin_lock(&s);
+        spin_unlock(&s);
+        spin_unlock(&s);
+
+or:
+
+        rcu_read_lock();
+        synchronize_rcu();
+        rcu_read_unlock();
+
+what does the LKMM have to say?  Answer: It says there are no allowed
+executions at all, which makes sense.  But this can also lead to
+misleading results, because if a piece of code has multiple possible
+executions, some of which deadlock, the model will report only on the
+non-deadlocking executions.  For example:
+
+        int x, y;
+
+        P0()
+        {
+                int r0;
+
+                WRITE_ONCE(x, 1);
+                r0 = READ_ONCE(y);
+        }
+
+        P1()
+        {
+                rcu_read_lock();
+                if (READ_ONCE(x) > 0) {
+                        WRITE_ONCE(y, 36);
+                        synchronize_rcu();
+                }
+                rcu_read_unlock();
+        }
+
+Is it possible to end up with r0 = 36 at the end?  The LKMM will tell
+you it is not, but the model won't mention that this is because P1
+will self-deadlock in the executions where it stores 36 in y.
diff --git a/tools/memory-model/Documentation/recipes.txt b/tools/memory-model/Documentation/recipes.txt
new file mode 100644
index 000000000000..ee4309a87fc4
--- /dev/null
+++ b/tools/memory-model/Documentation/recipes.txt
@@ -0,0 +1,570 @@
+This document provides "recipes", that is, litmus tests for commonly
+occurring situations, as well as a few that illustrate subtly broken but
+attractive nuisances.  Many of these recipes include example code from
+v4.13 of the Linux kernel.
+
+The first section covers simple special cases, the second section
+takes off the training wheels to cover more involved examples,
+and the third section provides a few rules of thumb.
+
+
+Simple special cases
+====================
+
+This section presents two simple special cases, the first being where
+there is only one CPU or only one memory location is accessed, and the
+second being use of that old concurrency workhorse, locking.
+
+
+Single CPU or single memory location
+------------------------------------
+
+If there is only one CPU on the one hand or only one variable
+on the other, the code will execute in order.  There are (as
+usual) some things to be careful of:
+
+1.      Some aspects of the C language are unordered.  For example,
+        in the expression "f(x) + g(y)", the order in which f and g are
+        called is not defined; the object code is allowed to use either
+        order or even to interleave the computations.
+
+2.      Compilers are permitted to use the "as-if" rule.  That is, a
+        compiler can emit whatever code it likes for normal accesses,
+        as long as the results of a single-threaded execution appear
+        just as if the compiler had followed all the relevant rules.
+        To see this, compile with a high level of optimization and run
+        the debugger on the resulting binary.
+
+3.      If there is only one variable but multiple CPUs, that variable
+        must be properly aligned and all accesses to that variable must
+        be full sized.  Variables that straddle cachelines or pages void
+        your full-ordering warranty, as do undersized accesses that load
+        from or store to only part of the variable.
+
+4.      If there are multiple CPUs, accesses to shared variables should
+        use READ_ONCE() and WRITE_ONCE() or stronger to prevent load/store
+        tearing, load/store fusing, and invented loads and stores.
+        There are exceptions to this rule, including:
+
+        i.      When there is no possibility of a given shared variable
+                being updated by some other CPU, for example, while
+                holding the update-side lock, reads from that variable
+                need not use READ_ONCE().
+
+        ii.     When there is no possibility of a given shared variable
+                being either read or updated by other CPUs, for example,
+                when running during early boot, reads from that variable
+                need not use READ_ONCE() and writes to that variable
+                need not use WRITE_ONCE().
+
+
+Locking
+-------
+
+Locking is well-known and straightforward, at least if you don't think
+about it too hard.  And the basic rule is indeed quite simple: Any CPU that
+has acquired a given lock sees any changes previously seen or made by any
+CPU before it released that same lock.  Note that this statement is a bit
+stronger than "Any CPU holding a given lock sees all changes made by any
+CPU during the time that CPU was holding this same lock".  For example,
+consider the following pair of code fragments:
+
+        /* See MP+polocks.litmus. */
+        void CPU0(void)
+        {
+                WRITE_ONCE(x, 1);
+                spin_lock(&mylock);
+                WRITE_ONCE(y, 1);
+                spin_unlock(&mylock);
+        }
+
+        void CPU1(void)
+        {
+                spin_lock(&mylock);
+                r0 = READ_ONCE(y);
+                spin_unlock(&mylock);
+                r1 = READ_ONCE(x);
+        }
+
+The basic rule guarantees that if CPU0() acquires mylock before CPU1(),
+then both r0 and r1 must be set to the value 1.  This also has the
+consequence that if the final value of r0 is equal to 1, then the final
+value of r1 must also be equal to 1.  In contrast, the weaker rule would
+say nothing about the final value of r1.
+
+The converse to the basic rule also holds, as illustrated by the
+following litmus test:
+
+        /* See MP+porevlocks.litmus. */
+        void CPU0(void)
+        {
+                r0 = READ_ONCE(y);
+                spin_lock(&mylock);
+                r1 = READ_ONCE(x);
+                spin_unlock(&mylock);
+        }
+
+        void CPU1(void)
+        {
+                spin_lock(&mylock);
+                WRITE_ONCE(x, 1);
+                spin_unlock(&mylock);
+                WRITE_ONCE(y, 1);
+        }
+
+This converse to the basic rule guarantees that if CPU0() acquires
+mylock before CPU1(), then both r0 and r1 must be set to the value 0.
+This also has the consequence that if the final value of r1 is equal
+to 0, then the final value of r0 must also be equal to 0.  In contrast,
+the weaker rule would say nothing about the final value of r0.
+
+These examples show only a single pair of CPUs, but the effects of the
+locking basic rule extend across multiple acquisitions of a given lock
+across multiple CPUs.
+
+However, it is not necessarily the case that accesses ordered by
+locking will be seen as ordered by CPUs not holding that lock.
+Consider this example:
+
+        /* See Z6.0+pooncelock+pooncelock+pombonce.litmus. */
+        void CPU0(void)
+        {
+                spin_lock(&mylock);
+                WRITE_ONCE(x, 1);
+                WRITE_ONCE(y, 1);
+                spin_unlock(&mylock);
+        }
+
+        void CPU1(void)
+        {
+                spin_lock(&mylock);
+                r0 = READ_ONCE(y);
+                WRITE_ONCE(z, 1);
+                spin_unlock(&mylock);
+        }
+
+        void CPU2(void)
+        {
+                WRITE_ONCE(z, 2);
+                smp_mb();
+                r1 = READ_ONCE(x);
+        }
+
+Counter-intuitive though it might be, it is quite possible to have
+the final value of r0 be 1, the final value of z be 2, and the final
+value of r1 be 0.  The reason for this surprising outcome is that
+CPU2() never acquired the lock, and thus did not benefit from the
+lock's ordering properties.
+
+Ordering can be extended to CPUs not holding the lock by careful use
+of smp_mb__after_spinlock():
+
+        /* See Z6.0+pooncelock+poonceLock+pombonce.litmus. */
+        void CPU0(void)
+        {
+                spin_lock(&mylock);
+                WRITE_ONCE(x, 1);
+                WRITE_ONCE(y, 1);
+                spin_unlock(&mylock);
+        }
+
+        void CPU1(void)
+        {
+                spin_lock(&mylock);
+                smp_mb__after_spinlock();
+                r0 = READ_ONCE(y);
+                WRITE_ONCE(z, 1);
+                spin_unlock(&mylock);
+        }
+
+        void CPU2(void)
+        {
+                WRITE_ONCE(z, 2);
+                smp_mb();
+                r1 = READ_ONCE(x);
+        }
+
+This addition of smp_mb__after_spinlock() strengthens the lock acquisition
+sufficiently to rule out the counter-intuitive outcome.
+
+
+Taking off the training wheels
+==============================
+
+This section looks at more complex examples, including message passing,
+load buffering, release-acquire chains, store buffering.
+Many classes of litmus tests have abbreviated names, which may be found
+here: https://www.cl.cam.ac.uk/~pes20/ppc-supplemental/test6.pdf
+
+
+Message passing (MP)
+--------------------
+
+The MP pattern has one CPU execute a pair of stores to a pair of variables
+and another CPU execute a pair of loads from this same pair of variables,
+but in the opposite order.  The goal is to avoid the counter-intuitive
+outcome in which the first load sees the value written by the second store
+but the second load does not see the value written by the first store.
+In the absence of any ordering, this goal may not be met, as can be seen
+in the MP+poonceonces.litmus litmus test.  This section therefore looks at
+a number of ways of meeting this goal.
+
+
+Release and acquire
+~~~~~~~~~~~~~~~~~~~
+
+Use of smp_store_release() and smp_load_acquire() is one way to force
+the desired MP ordering.  The general approach is shown below:
+
+        /* See MP+pooncerelease+poacquireonce.litmus. */
+        void CPU0(void)
+        {
+                WRITE_ONCE(x, 1);
+                smp_store_release(&y, 1);
+        }
+
+        void CPU1(void)
+        {
+                r0 = smp_load_acquire(&y);
+                r1 = READ_ONCE(x);
+        }
+
+The smp_store_release() macro orders any prior accesses against the
+store, while the smp_load_acquire macro orders the load against any
+subsequent accesses.  Therefore, if the final value of r0 is the value 1,
+the final value of r1 must also be the value 1.
+
+The init_stack_slab() function in lib/stackdepot.c uses release-acquire
+in this way to safely initialize of a slab of the stack.  Working out
+the mutual-exclusion design is left as an exercise for the reader.
+
+
+Assign and dereference
+~~~~~~~~~~~~~~~~~~~~~~
+
+Use of rcu_assign_pointer() and rcu_dereference() is quite similar to the
+use of smp_store_release() and smp_load_acquire(), except that both
+rcu_assign_pointer() and rcu_dereference() operate on RCU-protected
+pointers.  The general approach is shown below:
+
+        /* See MP+onceassign+derefonce.litmus. */
+        int z;
+        int *y = &z;
+        int x;
+
+        void CPU0(void)
+        {
+                WRITE_ONCE(x, 1);
+                rcu_assign_pointer(y, &x);
+        }
+
+        void CPU1(void)
+        {
+                rcu_read_lock();
+                r0 = rcu_dereference(y);
+                r1 = READ_ONCE(*r0);
+                rcu_read_unlock();
+        }
+
+In this example, if the final value of r0 is &x then the final value of
+r1 must be 1.
+
+The rcu_assign_pointer() macro has the same ordering properties as does
+smp_store_release(), but the rcu_dereference() macro orders the load only
+against later accesses that depend on the value loaded.  A dependency
+is present if the value loaded determines the address of a later access
+(address dependency, as shown above), the value written by a later store
+(data dependency), or whether or not a later store is executed in the
+first place (control dependency).  Note that the term "data dependency"
+is sometimes casually used to cover both address and data dependencies.
+
+In lib/prime_numbers.c, the expand_to_next_prime() function invokes
+rcu_assign_pointer(), and the next_prime_number() function invokes
+rcu_dereference().  This combination mediates access to a bit vector
+that is expanded as additional primes are needed.
+
+
+Write and read memory barriers
+~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+
+It is usually better to use smp_store_release() instead of smp_wmb()
+and to use smp_load_acquire() instead of smp_rmb().  However, the older
+smp_wmb() and smp_rmb() APIs are still heavily used, so it is important
+to understand their use cases.  The general approach is shown below:
+
+        /* See MP+wmbonceonce+rmbonceonce.litmus. */
+        void CPU0(void)
+        {
+                WRITE_ONCE(x, 1);
+                smp_wmb();
+                WRITE_ONCE(y, 1);
+        }
+
+        void CPU1(void)
+        {
+                r0 = READ_ONCE(y);
+                smp_rmb();
+                r1 = READ_ONCE(x);
+        }
+
+The smp_wmb() macro orders prior stores against later stores, and the
+smp_rmb() macro orders prior loads against later loads.  Therefore, if
+the final value of r0 is 1, the final value of r1 must also be 1.
+
+The the xlog_state_switch_iclogs() function in fs/xfs/xfs_log.c contains
+the following write-side code fragment:
+
+        log->l_curr_block -= log->l_logBBsize;
+        ASSERT(log->l_curr_block >= 0);
+        smp_wmb();
+        log->l_curr_cycle++;
+
+And the xlog_valid_lsn() function in fs/xfs/xfs_log_priv.h contains
+the corresponding read-side code fragment:
+
+        cur_cycle = ACCESS_ONCE(log->l_curr_cycle);
+        smp_rmb();
+        cur_block = ACCESS_ONCE(log->l_curr_block);
+
+Alternatively, consider the following comment in function
+perf_output_put_handle() in kernel/events/ring_buffer.c:
+
+         *   kernel                             user
+         *
+         *   if (LOAD ->data_tail) {            LOAD ->data_head
+         *                      (A)             smp_rmb()       (C)
+         *      STORE $data                     LOAD $data
+         *      smp_wmb()       (B)             smp_mb()        (D)
+         *      STORE ->data_head               STORE ->data_tail
+         *   }
+
+The B/C pairing is an example of the MP pattern using smp_wmb() on the
+write side and smp_rmb() on the read side.
+
+Of course, given that smp_mb() is strictly stronger than either smp_wmb()
+or smp_rmb(), any code fragment that would work with smp_rmb() and
+smp_wmb() would also work with smp_mb() replacing either or both of the
+weaker barriers.
+
+
+Load buffering (LB)
+-------------------
+
+The LB pattern has one CPU load from one variable and then store to a
+second, while another CPU loads from the second variable and then stores
+to the first.  The goal is to avoid the counter-intuitive situation where
+each load reads the value written by the other CPU's store.  In the
+absence of any ordering it is quite possible that this may happen, as
+can be seen in the LB+poonceonces.litmus litmus test.
+
+One way of avoiding the counter-intuitive outcome is through the use of a
+control dependency paired with a full memory barrier:
+
+        /* See LB+ctrlonceonce+mbonceonce.litmus. */
+        void CPU0(void)
+        {
+                r0 = READ_ONCE(x);
+                if (r0)
+                        WRITE_ONCE(y, 1);
+        }
+
+        void CPU1(void)
+        {
+                r1 = READ_ONCE(y);
+                smp_mb();
+                WRITE_ONCE(x, 1);
+        }
+
+This pairing of a control dependency in CPU0() with a full memory
+barrier in CPU1() prevents r0 and r1 from both ending up equal to 1.
+
+The A/D pairing from the ring-buffer use case shown earlier also
+illustrates LB.  Here is a repeat of the comment in
+perf_output_put_handle() in kernel/events/ring_buffer.c, showing a
+control dependency on the kernel side and a full memory barrier on
+the user side:
+
+         *   kernel                             user
+         *
+         *   if (LOAD ->data_tail) {            LOAD ->data_head
+         *                      (A)             smp_rmb()       (C)
+         *      STORE $data                     LOAD $data
+         *      smp_wmb()       (B)             smp_mb()        (D)
+         *      STORE ->data_head               STORE ->data_tail
+         *   }
+         *
+         * Where A pairs with D, and B pairs with C.
+
+The kernel's control dependency between the load from ->data_tail
+and the store to data combined with the user's full memory barrier
+between the load from data and the store to ->data_tail prevents
+the counter-intuitive outcome where the kernel overwrites the data
+before the user gets done loading it.
+
+
+Release-acquire chains
+----------------------
+
+Release-acquire chains are a low-overhead, flexible, and easy-to-use
+method of maintaining order.  However, they do have some limitations that
+need to be fully understood.  Here is an example that maintains order:
+
+        /* See ISA2+pooncerelease+poacquirerelease+poacquireonce.litmus. */
+        void CPU0(void)
+        {
+                WRITE_ONCE(x, 1);
+                smp_store_release(&y, 1);
+        }
+
+        void CPU1(void)
+        {
+                r0 = smp_load_acquire(y);
+                smp_store_release(&z, 1);
+        }
+
+        void CPU2(void)
+        {
+                r1 = smp_load_acquire(z);
+                r2 = READ_ONCE(x);
+        }
+
+In this case, if r0 and r1 both have final values of 1, then r2 must
+also have a final value of 1.
+
+The ordering in this example is stronger than it needs to be.  For
+example, ordering would still be preserved if CPU1()'s smp_load_acquire()
+invocation was replaced with READ_ONCE().
+
+It is tempting to assume that CPU0()'s store to x is globally ordered
+before CPU1()'s store to z, but this is not the case:
+
+        /* See Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus. */
+        void CPU0(void)
+        {
+                WRITE_ONCE(x, 1);
+                smp_store_release(&y, 1);
+        }
+
+        void CPU1(void)
+        {
+                r0 = smp_load_acquire(y);
+                smp_store_release(&z, 1);
+        }
+
+        void CPU2(void)
+        {
+                WRITE_ONCE(z, 2);
+                smp_mb();
+                r1 = READ_ONCE(x);
+        }
+
+One might hope that if the final value of r0 is 1 and the final value
+of z is 2, then the final value of r1 must also be 1, but it really is
+possible for r1 to have the final value of 0.  The reason, of course,
+is that in this version, CPU2() is not part of the release-acquire chain.
+This situation is accounted for in the rules of thumb below.
+
+Despite this limitation, release-acquire chains are low-overhead as
+well as simple and powerful, at least as memory-ordering mechanisms go.
+
+
+Store buffering
+---------------
+
+Store buffering can be thought of as upside-down load buffering, so
+that one CPU first stores to one variable and then loads from a second,
+while another CPU stores to the second variable and then loads from the
+first.  Preserving order requires nothing less than full barriers:
+
+        /* See SB+mbonceonces.litmus. */
+        void CPU0(void)
+        {
+                WRITE_ONCE(x, 1);
+                smp_mb();
+                r0 = READ_ONCE(y);
+        }
+
+        void CPU1(void)
+        {
+                WRITE_ONCE(y, 1);
+                smp_mb();
+                r1 = READ_ONCE(x);
+        }
+
+Omitting either smp_mb() will allow both r0 and r1 to have final
+values of 0, but providing both full barriers as shown above prevents
+this counter-intuitive outcome.
+
+This pattern most famously appears as part of Dekker's locking
+algorithm, but it has a much more practical use within the Linux kernel
+of ordering wakeups.  The following comment taken from waitqueue_active()
+in include/linux/wait.h shows the canonical pattern:
+
+ *      CPU0 - waker                    CPU1 - waiter
+ *
+ *                                      for (;;) {
+ *      @cond = true;                     prepare_to_wait(&wq_head, &wait, state);
+ *      smp_mb();                         // smp_mb() from set_current_state()
+ *      if (waitqueue_active(wq_head))         if (@cond)
+ *        wake_up(wq_head);                      break;
+ *                                        schedule();
+ *                                      }
+ *                                      finish_wait(&wq_head, &wait);
+
+On CPU0, the store is to @cond and the load is in waitqueue_active().
+On CPU1, prepare_to_wait() contains both a store to wq_head and a call
+to set_current_state(), which contains an smp_mb() barrier; the load is
+"if (@cond)".  The full barriers prevent the undesirable outcome where
+CPU1 puts the waiting task to sleep and CPU0 fails to wake it up.
+
+Note that use of locking can greatly simplify this pattern.
+
+
+Rules of thumb
+==============
+
+There might seem to be no pattern governing what ordering primitives are
+needed in which situations, but this is not the case.  There is a pattern
+based on the relation between the accesses linking successive CPUs in a
+given litmus test.  There are three types of linkage:
+
+1.      Write-to-read, where the next CPU reads the value that the
+        previous CPU wrote.  The LB litmus-test patterns contain only
+        this type of relation.  In formal memory-modeling texts, this
+        relation is called "reads-from" and is usually abbreviated "rf".
+
+2.      Read-to-write, where the next CPU overwrites the value that the
+        previous CPU read.  The SB litmus test contains only this type
+        of relation.  In formal memory-modeling texts, this relation is
+        often called "from-reads" and is sometimes abbreviated "fr".
+
+3.      Write-to-write, where the next CPU overwrites the value written
+        by the previous CPU.  The Z6.0 litmus test pattern contains a
+        write-to-write relation between the last access of CPU1() and
+        the first access of CPU2().  In formal memory-modeling texts,
+        this relation is often called "coherence order" and is sometimes
+        abbreviated "co".  In the C++ standard, it is instead called
+        "modification order" and often abbreviated "mo".
+
+The strength of memory ordering required for a given litmus test to
+avoid a counter-intuitive outcome depends on the types of relations
+linking the memory accesses for the outcome in question:
+
+o       If all links are write-to-read links, then the weakest
+        possible ordering within each CPU suffices.  For example, in
+        the LB litmus test, a control dependency was enough to do the
+        job.
+
+o       If all but one of the links are write-to-read links, then a
+        release-acquire chain suffices.  Both the MP and the ISA2
+        litmus tests illustrate this case.
+
+o       If more than one of the links are something other than
+        write-to-read links, then a full memory barrier is required
+        between each successive pair of non-write-to-read links.  This
+        case is illustrated by the Z6.0 litmus tests, both in the
+        locking and in the release-acquire sections.
+
+However, if you find yourself having to stretch these rules of thumb
+to fit your situation, you should consider creating a litmus test and
+running it on the model.
diff --git a/tools/memory-model/Documentation/references.txt b/tools/memory-model/Documentation/references.txt
new file mode 100644
index 000000000000..ba2e34c2ec3f
--- /dev/null
+++ b/tools/memory-model/Documentation/references.txt
@@ -0,0 +1,107 @@
+This document provides background reading for memory models and related
+tools.  These documents are aimed at kernel hackers who are interested
+in memory models.
+
+
+Hardware manuals and models
+===========================
+
+o       SPARC International Inc. (Ed.). 1994. "The SPARC Architecture
+        Reference Manual Version 9". SPARC International Inc.
+
+o       Compaq Computer Corporation (Ed.). 2002. "Alpha Architecture
+        Reference Manual".  Compaq Computer Corporation.
+
+o       Intel Corporation (Ed.). 2002. "A Formal Specification of Intel
+        Itanium Processor Family Memory Ordering". Intel Corporation.
+
+o       Intel Corporation (Ed.). 2002. "Intel 64 and IA-32 Architectures
+        Software Developer’s Manual". Intel Corporation.
+
+o       Peter Sewell, Susmit Sarkar, Scott Owens, Francesco Zappa Nardelli,
+        and Magnus O. Myreen. 2010. "x86-TSO: A Rigorous and Usable
+        Programmer's Model for x86 Multiprocessors". Commun. ACM 53, 7
+        (July, 2010), 89-97. http://doi.acm.org/10.1145/1785414.1785443
+
+o       IBM Corporation (Ed.). 2009. "Power ISA Version 2.06". IBM
+        Corporation.
+
+o       ARM Ltd. (Ed.). 2009. "ARM Barrier Litmus Tests and Cookbook".
+        ARM Ltd.
+
+o       Susmit Sarkar, Peter Sewell, Jade Alglave, Luc Maranget, and
+        Derek Williams.  2011. "Understanding POWER Multiprocessors". In
+        Proceedings of the 32Nd ACM SIGPLAN Conference on Programming
+        Language Design and Implementation (PLDI ’11). ACM, New York,
+        NY, USA, 175–186.
+
+o       Susmit Sarkar, Kayvan Memarian, Scott Owens, Mark Batty,
+        Peter Sewell, Luc Maranget, Jade Alglave, and Derek Williams.
+        2012. "Synchronising C/C++ and POWER". In Proceedings of the 33rd
+        ACM SIGPLAN Conference on Programming Language Design and
+        Implementation (PLDI '12). ACM, New York, NY, USA, 311-322.
+
+o       ARM Ltd. (Ed.). 2014. "ARM Architecture Reference Manual (ARMv8,
+        for ARMv8-A architecture profile)". ARM Ltd.
+
+o       Imagination Technologies, LTD. 2015. "MIPS(R) Architecture
+        For Programmers, Volume II-A: The MIPS64(R) Instruction,
+        Set Reference Manual". Imagination Technologies,
+        LTD. https://imgtec.com/?do-download=4302.
+
+o       Shaked Flur, Kathryn E. Gray, Christopher Pulte, Susmit
+        Sarkar, Ali Sezgin, Luc Maranget, Will Deacon, and Peter
+        Sewell. 2016. "Modelling the ARMv8 Architecture, Operationally:
+        Concurrency and ISA". In Proceedings of the 43rd Annual ACM
+        SIGPLAN-SIGACT Symposium on Principles of Programming Languages
+        (POPL ’16). ACM, New York, NY, USA, 608–621.
+
+o       Shaked Flur, Susmit Sarkar, Christopher Pulte, Kyndylan Nienhuis,
+        Luc Maranget, Kathryn E. Gray, Ali Sezgin, Mark Batty, and Peter
+        Sewell. 2017. "Mixed-size Concurrency: ARM, POWER, C/C++11,
+        and SC". In Proceedings of the 44th ACM SIGPLAN Symposium on
+        Principles of Programming Languages (POPL 2017). ACM, New York,
+        NY, USA, 429–442.
+
+
+Linux-kernel memory model
+=========================
+
+o       Andrea Parri, Alan Stern, Luc Maranget, Paul E. McKenney,
+        and Jade Alglave.  2017. "A formal model of
+        Linux-kernel memory ordering - companion webpage".
+        http://moscova.inria.fr/∼maranget/cats7/linux/. (2017). [Online;
+        accessed 30-January-2017].
+
+o       Jade Alglave, Luc Maranget, Paul E. McKenney, Andrea Parri, and
+        Alan Stern.  2017.  "A formal kernel memory-ordering model (part 1)"
+        Linux Weekly News.  https://lwn.net/Articles/718628/
+
+o       Jade Alglave, Luc Maranget, Paul E. McKenney, Andrea Parri, and
+        Alan Stern.  2017.  "A formal kernel memory-ordering model (part 2)"
+        Linux Weekly News.  https://lwn.net/Articles/720550/
+
+
+Memory-model tooling
+====================
+
+o       Daniel Jackson. 2002. "Alloy: A Lightweight Object Modelling
+        Notation". ACM Trans. Softw. Eng. Methodol. 11, 2 (April 2002),
+        256–290. http://doi.acm.org/10.1145/505145.505149
+
+o       Jade Alglave, Luc Maranget, and Michael Tautschnig. 2014. "Herding
+        Cats: Modelling, Simulation, Testing, and Data Mining for Weak
+        Memory". ACM Trans. Program. Lang. Syst. 36, 2, Article 7 (July
+        2014), 7:1–7:74 pages.
+
+o       Jade Alglave, Patrick Cousot, and Luc Maranget. 2016. "Syntax and
+        semantics of the weak consistency model specification language
+        cat". CoRR abs/1608.07531 (2016). http://arxiv.org/abs/1608.07531
+
+
+Memory-model comparisons
+========================
+
+o       Paul E. McKenney, Ulrich Weigand, Andrea Parri, and Boqun
+        Feng. 2016. "Linux-Kernel Memory Model". (6 June 2016).
+        http://open-std.org/JTC1/SC22/WG21/docs/papers/2016/p0124r2.html.
diff --git a/tools/memory-model/README b/tools/memory-model/README
new file mode 100644
index 000000000000..0b3a5f3c9ccd
--- /dev/null
+++ b/tools/memory-model/README
@@ -0,0 +1,206 @@
+                =====================================
+                LINUX KERNEL MEMORY CONSISTENCY MODEL
+                =====================================
+
+============
+INTRODUCTION
+============
+
+This directory contains the memory consistency model (memory model, for
+short) of the Linux kernel, written in the "cat" language and executable
+by the externally provided "herd7" simulator, which exhaustively explores
+the state space of small litmus tests.
+
+In addition, the "klitmus7" tool (also externally provided) may be used
+to convert a litmus test to a Linux kernel module, which in turn allows
+that litmus test to be exercised within the Linux kernel.
+
+
+============
+REQUIREMENTS
+============
+
+Version 7.48 of the "herd7" and "klitmus7" tools must be downloaded
+separately:
+
+  https://github.com/herd/herdtools7
+
+See "herdtools7/INSTALL.md" for installation instructions.
+
+
+==================
+BASIC USAGE: HERD7
+==================
+
+The memory model is used, in conjunction with "herd7", to exhaustively
+explore the state space of small litmus tests.
+
+For example, to run SB+mbonceonces.litmus against the memory model:
+
+  $ herd7 -conf linux-kernel.cfg litmus-tests/SB+mbonceonces.litmus
+
+Here is the corresponding output:
+
+  Test SB+mbonceonces Allowed
+  States 3
+  0:r0=0; 1:r0=1;
+  0:r0=1; 1:r0=0;
+  0:r0=1; 1:r0=1;
+  No
+  Witnesses
+  Positive: 0 Negative: 3
+  Condition exists (0:r0=0 /\ 1:r0=0)
+  Observation SB+mbonceonces Never 0 3
+  Time SB+mbonceonces 0.01
+  Hash=d66d99523e2cac6b06e66f4c995ebb48
+
+The "Positive: 0 Negative: 3" and the "Never 0 3" each indicate that
+this litmus test's "exists" clause can not be satisfied.
+
+See "herd7 -help" or "herdtools7/doc/" for more information.
+
+
+=====================
+BASIC USAGE: KLITMUS7
+=====================
+
+The "klitmus7" tool converts a litmus test into a Linux kernel module,
+which may then be loaded and run.
+
+For example, to run SB+mbonceonces.litmus against hardware:
+
+  $ mkdir mymodules
+  $ klitmus7 -o mymodules litmus-tests/SB+mbonceonces.litmus
+  $ cd mymodules ; make
+  $ sudo sh run.sh
+
+The corresponding output includes:
+
+  Test SB+mbonceonces Allowed
+  Histogram (3 states)
+  644580  :>0:r0=1; 1:r0=0;
+  644328  :>0:r0=0; 1:r0=1;
+  711092  :>0:r0=1; 1:r0=1;
+  No
+  Witnesses
+  Positive: 0, Negative: 2000000
+  Condition exists (0:r0=0 /\ 1:r0=0) is NOT validated
+  Hash=d66d99523e2cac6b06e66f4c995ebb48
+  Observation SB+mbonceonces Never 0 2000000
+  Time SB+mbonceonces 0.16
+
+The "Positive: 0 Negative: 2000000" and the "Never 0 2000000" indicate
+that during two million trials, the state specified in this litmus
+test's "exists" clause was not reached.
+
+And, as with "herd7", please see "klitmus7 -help" or "herdtools7/doc/"
+for more information.
+
+
+====================
+DESCRIPTION OF FILES
+====================
+
+Documentation/cheatsheet.txt
+        Quick-reference guide to the Linux-kernel memory model.
+
+Documentation/explanation.txt
+        Describes the memory model in detail.
+
+Documentation/recipes.txt
+        Lists common memory-ordering patterns.
+
+Documentation/references.txt
+        Provides background reading.
+
+linux-kernel.bell
+        Categorizes the relevant instructions, including memory
+        references, memory barriers, atomic read-modify-write operations,
+        lock acquisition/release, and RCU operations.
+
+        More formally, this file (1) lists the subtypes of the various
+        event types used by the memory model and (2) performs RCU
+        read-side critical section nesting analysis.
+
+linux-kernel.cat
+        Specifies what reorderings are forbidden by memory references,
+        memory barriers, atomic read-modify-write operations, and RCU.
+
+        More formally, this file specifies what executions are forbidden
+        by the memory model.  Allowed executions are those which
+        satisfy the model's "coherence", "atomic", "happens-before",
+        "propagation", and "rcu" axioms, which are defined in the file.
+
+linux-kernel.cfg
+        Convenience file that gathers the common-case herd7 command-line
+        arguments.
+
+linux-kernel.def
+        Maps from C-like syntax to herd7's internal litmus-test
+        instruction-set architecture.
+
+litmus-tests
+        Directory containing a few representative litmus tests, which
+        are listed in litmus-tests/README.  A great deal more litmus
+        tests are available at https://github.com/paulmckrcu/litmus.
+
+lock.cat
+        Provides a front-end analysis of lock acquisition and release,
+        for example, associating a lock acquisition with the preceding
+        and following releases and checking for self-deadlock.
+
+        More formally, this file defines a performance-enhanced scheme
+        for generation of the possible reads-from and coherence order
+        relations on the locking primitives.
+
+README
+        This file.
+
+
+===========
+LIMITATIONS
+===========
+
+The Linux-kernel memory model has the following limitations:
+
+1.      Compiler optimizations are not modeled.  Of course, the use
+        of READ_ONCE() and WRITE_ONCE() limits the compiler's ability
+        to optimize, but there is Linux-kernel code that uses bare C
+        memory accesses.  Handling this code is on the to-do list.
+        For more information, see Documentation/explanation.txt (in
+        particular, the "THE PROGRAM ORDER RELATION: po AND po-loc"
+        and "A WARNING" sections).
+
+2.      Multiple access sizes for a single variable are not supported,
+        and neither are misaligned or partially overlapping accesses.
+
+3.      Exceptions and interrupts are not modeled.  In some cases,
+        this limitation can be overcome by modeling the interrupt or
+        exception with an additional process.
+
+4.      I/O such as MMIO or DMA is not supported.
+
+5.      Self-modifying code (such as that found in the kernel's
+        alternatives mechanism, function tracer, Berkeley Packet Filter
+        JIT compiler, and module loader) is not supported.
+
+6.      Complete modeling of all variants of atomic read-modify-write
+        operations, locking primitives, and RCU is not provided.
+        For example, call_rcu() and rcu_barrier() are not supported.
+        However, a substantial amount of support is provided for these
+        operations, as shown in the linux-kernel.def file.
+
+The "herd7" tool has some additional limitations of its own, apart from
+the memory model:
+
+1.      Non-trivial data structures such as arrays or structures are
+        not supported.  However, pointers are supported, allowing trivial
+        linked lists to be constructed.
+
+2.      Dynamic memory allocation is not supported, although this can
+        be worked around in some cases by supplying multiple statically
+        allocated variables.
+
+Some of these limitations may be overcome in the future, but others are
+more likely to be addressed by incorporating the Linux-kernel memory model
+into other tools.
diff --git a/tools/memory-model/linux-kernel.bell b/tools/memory-model/linux-kernel.bell
new file mode 100644
index 000000000000..432c7cf71b23
--- /dev/null
+++ b/tools/memory-model/linux-kernel.bell
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0+
+(*
+ * Copyright (C) 2015 Jade Alglave <j.alglave@ucl.ac.uk>,
+ * Copyright (C) 2016 Luc Maranget <luc.maranget@inria.fr> for Inria
+ * Copyright (C) 2017 Alan Stern <stern@rowland.harvard.edu>,
+ *                    Andrea Parri <parri.andrea@gmail.com>
+ *
+ * An earlier version of this file appears in the companion webpage for
+ * "Frightening small children and disconcerting grown-ups: Concurrency
+ * in the Linux kernel" by Alglave, Maranget, McKenney, Parri, and Stern,
+ * which is to appear in ASPLOS 2018.
+ *)
+
+"Linux-kernel memory consistency model"
+
+enum Accesses = 'once (*READ_ONCE,WRITE_ONCE,ACCESS_ONCE*) ||
+                'release (*smp_store_release*) ||
+                'acquire (*smp_load_acquire*) ||
+                'noreturn (* R of non-return RMW *)
+instructions R[{'once,'acquire,'noreturn}]
+instructions W[{'once,'release}]
+instructions RMW[{'once,'acquire,'release}]
+
+enum Barriers = 'wmb (*smp_wmb*) ||
+                'rmb (*smp_rmb*) ||
+                'mb (*smp_mb*) ||
+                'rcu-lock (*rcu_read_lock*)  ||
+                'rcu-unlock (*rcu_read_unlock*) ||
+                'sync-rcu (*synchronize_rcu*) ||
+                'before-atomic (*smp_mb__before_atomic*) ||
+                'after-atomic (*smp_mb__after_atomic*) ||
+                'after-spinlock (*smp_mb__after_spinlock*)
+instructions F[Barriers]
+
+(* Compute matching pairs of nested Rcu-lock and Rcu-unlock *)
+let matched = let rec
+            unmatched-locks = Rcu-lock \ domain(matched)
+        and unmatched-unlocks = Rcu-unlock \ range(matched)
+        and unmatched = unmatched-locks | unmatched-unlocks
+        and unmatched-po = [unmatched] ; po ; [unmatched]
+        and unmatched-locks-to-unlocks =
+                [unmatched-locks] ; po ; [unmatched-unlocks]
+        and matched = matched | (unmatched-locks-to-unlocks \
+                (unmatched-po ; unmatched-po))
+        in matched
+
+(* Validate nesting *)
+flag ~empty Rcu-lock \ domain(matched) as unbalanced-rcu-locking
+flag ~empty Rcu-unlock \ range(matched) as unbalanced-rcu-locking
+
+(* Outermost level of nesting only *)
+let crit = matched \ (po^-1 ; matched ; po^-1)
diff --git a/tools/memory-model/linux-kernel.cat b/tools/memory-model/linux-kernel.cat
new file mode 100644
index 000000000000..df97db03b6c2
--- /dev/null
+++ b/tools/memory-model/linux-kernel.cat
@@ -0,0 +1,121 @@
+// SPDX-License-Identifier: GPL-2.0+
+(*
+ * Copyright (C) 2015 Jade Alglave <j.alglave@ucl.ac.uk>,
+ * Copyright (C) 2016 Luc Maranget <luc.maranget@inria.fr> for Inria
+ * Copyright (C) 2017 Alan Stern <stern@rowland.harvard.edu>,
+ *                    Andrea Parri <parri.andrea@gmail.com>
+ *
+ * An earlier version of this file appears in the companion webpage for
+ * "Frightening small children and disconcerting grown-ups: Concurrency
+ * in the Linux kernel" by Alglave, Maranget, McKenney, Parri, and Stern,
+ * which is to appear in ASPLOS 2018.
+ *)
+
+"Linux-kernel memory consistency model"
+
+(*
+ * File "lock.cat" handles locks and is experimental.
+ * It can be replaced by include "cos.cat" for tests that do not use locks.
+ *)
+
+include "lock.cat"
+
+(*******************)
+(* Basic relations *)
+(*******************)
+
+(* Fences *)
+let rmb = [R \ Noreturn] ; fencerel(Rmb) ; [R \ Noreturn]
+let wmb = [W] ; fencerel(Wmb) ; [W]
+let mb = ([M] ; fencerel(Mb) ; [M]) |
+        ([M] ; fencerel(Before-atomic) ; [RMW] ; po? ; [M]) |
+        ([M] ; po? ; [RMW] ; fencerel(After-atomic) ; [M]) |
+        ([M] ; po? ; [LKW] ; fencerel(After-spinlock) ; [M])
+let gp = po ; [Sync-rcu] ; po?
+
+let strong-fence = mb | gp
+
+(* Release Acquire *)
+let acq-po = [Acquire] ; po ; [M]
+let po-rel = [M] ; po ; [Release]
+let rfi-rel-acq = [Release] ; rfi ; [Acquire]
+
+(**********************************)
+(* Fundamental coherence ordering *)
+(**********************************)
+
+(* Sequential Consistency Per Variable *)
+let com = rf | co | fr
+acyclic po-loc | com as coherence
+
+(* Atomic Read-Modify-Write *)
+empty rmw & (fre ; coe) as atomic
+
+(**********************************)
+(* Instruction execution ordering *)
+(**********************************)
+
+(* Preserved Program Order *)
+let dep = addr | data
+let rwdep = (dep | ctrl) ; [W]
+let overwrite = co | fr
+let to-w = rwdep | (overwrite & int)
+let to-r = addr | (dep ; rfi) | rfi-rel-acq
+let fence = strong-fence | wmb | po-rel | rmb | acq-po
+let ppo = to-r | to-w | fence
+
+(* Propagation: Ordering from release operations and strong fences. *)
+let A-cumul(r) = rfe? ; r
+let cumul-fence = A-cumul(strong-fence | po-rel) | wmb
+let prop = (overwrite & ext)? ; cumul-fence* ; rfe?
+
+(*
+ * Happens Before: Ordering from the passage of time.
+ * No fences needed here for prop because relation confined to one process.
+ *)
+let hb = ppo | rfe | ((prop \ id) & int)
+acyclic hb as happens-before
+
+(****************************************)
+(* Write and fence propagation ordering *)
+(****************************************)
+
+(* Propagation: Each non-rf link needs a strong fence. *)
+let pb = prop ; strong-fence ; hb*
+acyclic pb as propagation
+
+(*******)
+(* RCU *)
+(*******)
+
+(*
+ * Effect of read-side critical section proceeds from the rcu_read_lock()
+ * onward on the one hand and from the rcu_read_unlock() backwards on the
+ * other hand.
+ *)
+let rscs = po ; crit^-1 ; po?
+
+(*
+ * The synchronize_rcu() strong fence is special in that it can order not
+ * one but two non-rf relations, but only in conjunction with an RCU
+ * read-side critical section.
+ *)
+let link = hb* ; pb* ; prop
+
+(* Chains that affect the RCU grace-period guarantee *)
+let gp-link = gp ; link
+let rscs-link = rscs ; link
+
+(*
+ * A cycle containing at least as many grace periods as RCU read-side
+ * critical sections is forbidden.
+ *)
+let rec rcu-path =
+        gp-link |
+        (gp-link ; rscs-link) |
+        (rscs-link ; gp-link) |
+        (rcu-path ; rcu-path) |
+        (gp-link ; rcu-path ; rscs-link) |
+        (rscs-link ; rcu-path ; gp-link)
+
+irreflexive rcu-path as rcu
diff --git a/tools/memory-model/linux-kernel.cfg b/tools/memory-model/linux-kernel.cfg
new file mode 100644
index 000000000000..3c8098e99f41
--- /dev/null
+++ b/tools/memory-model/linux-kernel.cfg
@@ -0,0 +1,21 @@
+macros linux-kernel.def
+bell linux-kernel.bell
+model linux-kernel.cat
+graph columns
+squished true
+showevents noregs
+movelabel true
+fontsize 8
+xscale 2.0
+yscale 1.5
+arrowsize 0.8
+showinitrf false
+showfinalrf false
+showinitwrites false
+splines spline
+pad 0.1
+edgeattr hb,color,indigo
+edgeattr co,color,blue
+edgeattr mb,color,darkgreen
+edgeattr wmb,color,darkgreen
+edgeattr rmb,color,darkgreen
diff --git a/tools/memory-model/linux-kernel.def b/tools/memory-model/linux-kernel.def
new file mode 100644
index 000000000000..397e4e67e8c8
--- /dev/null
+++ b/tools/memory-model/linux-kernel.def
@@ -0,0 +1,106 @@
+// SPDX-License-Identifier: GPL-2.0+
+//
+// An earlier version of this file appears in the companion webpage for
+// "Frightening small children and disconcerting grown-ups: Concurrency
+// in the Linux kernel" by Alglave, Maranget, McKenney, Parri, and Stern,
+// which is to appear in ASPLOS 2018.
+
+// ONCE
+READ_ONCE(X) __load{once}(X)
+WRITE_ONCE(X,V) { __store{once}(X,V); }
+
+// Release Acquire and friends
+smp_store_release(X,V) { __store{release}(*X,V); }
+smp_load_acquire(X) __load{acquire}(*X)
+rcu_assign_pointer(X,V) { __store{release}(X,V); }
+rcu_dereference(X) __load{once}(X)
+
+// Fences
+smp_mb() { __fence{mb} ; }
+smp_rmb() { __fence{rmb} ; }
+smp_wmb() { __fence{wmb} ; }
+smp_mb__before_atomic() { __fence{before-atomic} ; }
+smp_mb__after_atomic() { __fence{after-atomic} ; }
+smp_mb__after_spinlock() { __fence{after-spinlock} ; }
+
+// Exchange
+xchg(X,V)  __xchg{mb}(X,V)
+xchg_relaxed(X,V) __xchg{once}(X,V)
+xchg_release(X,V) __xchg{release}(X,V)
+xchg_acquire(X,V) __xchg{acquire}(X,V)
+cmpxchg(X,V,W) __cmpxchg{mb}(X,V,W)
+cmpxchg_relaxed(X,V,W) __cmpxchg{once}(X,V,W)
+cmpxchg_acquire(X,V,W) __cmpxchg{acquire}(X,V,W)
+cmpxchg_release(X,V,W) __cmpxchg{release}(X,V,W)
+
+// Spinlocks
+spin_lock(X) { __lock(X) ; }
+spin_unlock(X) { __unlock(X) ; }
+spin_trylock(X) __trylock(X)
+
+// RCU
+rcu_read_lock() { __fence{rcu-lock}; }
+rcu_read_unlock() { __fence{rcu-unlock};}
+synchronize_rcu() { __fence{sync-rcu}; }
+synchronize_rcu_expedited() { __fence{sync-rcu}; }
+
+// Atomic
+atomic_read(X) READ_ONCE(*X)
+atomic_set(X,V) { WRITE_ONCE(*X,V) ; }
+atomic_read_acquire(X) smp_load_acquire(X)
+atomic_set_release(X,V) { smp_store_release(X,V); }
+
+atomic_add(V,X) { __atomic_op(X,+,V) ; }
+atomic_sub(V,X) { __atomic_op(X,-,V) ; }
+atomic_inc(X)   { __atomic_op(X,+,1) ; }
+atomic_dec(X)   { __atomic_op(X,-,1) ; }
+
+atomic_add_return(V,X) __atomic_op_return{mb}(X,+,V)
+atomic_add_return_relaxed(V,X) __atomic_op_return{once}(X,+,V)
+atomic_add_return_acquire(V,X) __atomic_op_return{acquire}(X,+,V)
+atomic_add_return_release(V,X) __atomic_op_return{release}(X,+,V)
+atomic_fetch_add(V,X) __atomic_fetch_op{mb}(X,+,V)
+atomic_fetch_add_relaxed(V,X) __atomic_fetch_op{once}(X,+,V)
+atomic_fetch_add_acquire(V,X) __atomic_fetch_op{acquire}(X,+,V)
+atomic_fetch_add_release(V,X) __atomic_fetch_op{release}(X,+,V)
+
+atomic_inc_return(X) __atomic_op_return{mb}(X,+,1)
+atomic_inc_return_relaxed(X) __atomic_op_return{once}(X,+,1)
+atomic_inc_return_acquire(X) __atomic_op_return{acquire}(X,+,1)
+atomic_inc_return_release(X) __atomic_op_return{release}(X,+,1)
+atomic_fetch_inc(X) __atomic_fetch_op{mb}(X,+,1)
+atomic_fetch_inc_relaxed(X) __atomic_fetch_op{once}(X,+,1)
+atomic_fetch_inc_acquire(X) __atomic_fetch_op{acquire}(X,+,1)
+atomic_fetch_inc_release(X) __atomic_fetch_op{release}(X,+,1)
+
+atomic_sub_return(V,X) __atomic_op_return{mb}(X,-,V)
+atomic_sub_return_relaxed(V,X) __atomic_op_return{once}(X,-,V)
+atomic_sub_return_acquire(V,X) __atomic_op_return{acquire}(X,-,V)
+atomic_sub_return_release(V,X) __atomic_op_return{release}(X,-,V)
+atomic_fetch_sub(V,X) __atomic_fetch_op{mb}(X,-,V)
+atomic_fetch_sub_relaxed(V,X) __atomic_fetch_op{once}(X,-,V)
+atomic_fetch_sub_acquire(V,X) __atomic_fetch_op{acquire}(X,-,V)
+atomic_fetch_sub_release(V,X) __atomic_fetch_op{release}(X,-,V)
+
+atomic_dec_return(X) __atomic_op_return{mb}(X,-,1)
+atomic_dec_return_relaxed(X) __atomic_op_return{once}(X,-,1)
+atomic_dec_return_acquire(X) __atomic_op_return{acquire}(X,-,1)
+atomic_dec_return_release(X) __atomic_op_return{release}(X,-,1)
+atomic_fetch_dec(X) __atomic_fetch_op{mb}(X,-,1)
+atomic_fetch_dec_relaxed(X) __atomic_fetch_op{once}(X,-,1)
+atomic_fetch_dec_acquire(X) __atomic_fetch_op{acquire}(X,-,1)
+atomic_fetch_dec_release(X) __atomic_fetch_op{release}(X,-,1)
+
+atomic_xchg(X,V) __xchg{mb}(X,V)
+atomic_xchg_relaxed(X,V) __xchg{once}(X,V)
+atomic_xchg_release(X,V) __xchg{release}(X,V)
+atomic_xchg_acquire(X,V) __xchg{acquire}(X,V)
+atomic_cmpxchg(X,V,W) __cmpxchg{mb}(X,V,W)
+atomic_cmpxchg_relaxed(X,V,W) __cmpxchg{once}(X,V,W)
+atomic_cmpxchg_acquire(X,V,W) __cmpxchg{acquire}(X,V,W)
+atomic_cmpxchg_release(X,V,W) __cmpxchg{release}(X,V,W)
+
+atomic_sub_and_test(V,X) __atomic_op_return{mb}(X,-,V) == 0
+atomic_dec_and_test(X)  __atomic_op_return{mb}(X,-,1) == 0
+atomic_inc_and_test(X)  __atomic_op_return{mb}(X,+,1) == 0
+atomic_add_negative(V,X) __atomic_op_return{mb}(X,+,V) < 0
diff --git a/tools/memory-model/litmus-tests/CoRR+poonceonce+Once.litmus b/tools/memory-model/litmus-tests/CoRR+poonceonce+Once.litmus
new file mode 100644
index 000000000000..967f9f2a6226
--- /dev/null
+++ b/tools/memory-model/litmus-tests/CoRR+poonceonce+Once.litmus
@@ -0,0 +1,26 @@
+C CoRR+poonceonce+Once
+
+(*
+ * Result: Never
+ *
+ * Test of read-read coherence, that is, whether or not two successive
+ * reads from the same variable are ordered.
+ *)
+
+{}
+
+P0(int *x)
+{
+        WRITE_ONCE(*x, 1);
+}
+
+P1(int *x)
+{
+        int r0;
+        int r1;
+
+        r0 = READ_ONCE(*x);
+        r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ 1:r1=0)
diff --git a/tools/memory-model/litmus-tests/CoRW+poonceonce+Once.litmus b/tools/memory-model/litmus-tests/CoRW+poonceonce+Once.litmus
new file mode 100644
index 000000000000..4635739f3974
--- /dev/null
+++ b/tools/memory-model/litmus-tests/CoRW+poonceonce+Once.litmus
@@ -0,0 +1,25 @@
+C CoRW+poonceonce+Once
+
+(*
+ * Result: Never
+ *
+ * Test of read-write coherence, that is, whether or not a read from
+ * a given variable and a later write to that same variable are ordered.
+ *)
+
+{}
+
+P0(int *x)
+{
+        int r0;
+
+        r0 = READ_ONCE(*x);
+        WRITE_ONCE(*x, 1);
+}
+
+P1(int *x)
+{
+        WRITE_ONCE(*x, 2);
+}
+
+exists (x=2 /\ 0:r0=2)
diff --git a/tools/memory-model/litmus-tests/CoWR+poonceonce+Once.litmus b/tools/memory-model/litmus-tests/CoWR+poonceonce+Once.litmus
new file mode 100644
index 000000000000..bb068c92d8da
--- /dev/null
+++ b/tools/memory-model/litmus-tests/CoWR+poonceonce+Once.litmus
@@ -0,0 +1,25 @@
+C CoWR+poonceonce+Once
+
+(*
+ * Result: Never
+ *
+ * Test of write-read coherence, that is, whether or not a write to a
+ * given variable and a later read from that same variable are ordered.
+ *)
+
+{}
+
+P0(int *x)
+{
+        int r0;
+
+        WRITE_ONCE(*x, 1);
+        r0 = READ_ONCE(*x);
+}
+
+P1(int *x)
+{
+        WRITE_ONCE(*x, 2);
+}
+
+exists (x=1 /\ 0:r0=2)
diff --git a/tools/memory-model/litmus-tests/CoWW+poonceonce.litmus b/tools/memory-model/litmus-tests/CoWW+poonceonce.litmus
new file mode 100644
index 000000000000..0d9f0a958799
--- /dev/null
+++ b/tools/memory-model/litmus-tests/CoWW+poonceonce.litmus
@@ -0,0 +1,18 @@
+C CoWW+poonceonce
+
+(*
+ * Result: Never
+ *
+ * Test of write-write coherence, that is, whether or not two successive
+ * writes to the same variable are ordered.
+ *)
+
+{}
+
+P0(int *x)
+{
+        WRITE_ONCE(*x, 1);
+        WRITE_ONCE(*x, 2);
+}
+
+exists (x=1)
diff --git a/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus b/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus
new file mode 100644
index 000000000000..50d5db9ea983
--- /dev/null
+++ b/tools/memory-model/litmus-tests/IRIW+mbonceonces+OnceOnce.litmus
@@ -0,0 +1,45 @@
+C IRIW+mbonceonces+OnceOnce
+
+(*
+ * Result: Never
+ *
+ * Test of independent reads from independent writes with smp_mb()
+ * between each pairs of reads.  In other words, is smp_mb() sufficient to
+ * cause two different reading processes to agree on the order of a pair
+ * of writes, where each write is to a different variable by a different
+ * process?
+ *)
+
+{}
+
+P0(int *x)
+{
+        WRITE_ONCE(*x, 1);
+}
+
+P1(int *x, int *y)
+{
+        int r0;
+        int r1;
+
+        r0 = READ_ONCE(*x);
+        smp_mb();
+        r1 = READ_ONCE(*y);
+}
+
+P2(int *y)
+{
+        WRITE_ONCE(*y, 1);
+}
+
+P3(int *x, int *y)
+{
+        int r0;
+        int r1;
+
+        r0 = READ_ONCE(*y);
+        smp_mb();
+        r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ 1:r1=0 /\ 3:r0=1 /\ 3:r1=0)
diff --git a/tools/memory-model/litmus-tests/IRIW+poonceonces+OnceOnce.litmus b/tools/memory-model/litmus-tests/IRIW+poonceonces+OnceOnce.litmus
new file mode 100644
index 000000000000..4b54dd6a6cd9
--- /dev/null
+++ b/tools/memory-model/litmus-tests/IRIW+poonceonces+OnceOnce.litmus
@@ -0,0 +1,43 @@
+C IRIW+poonceonces+OnceOnce
+
+(*
+ * Result: Sometimes
+ *
+ * Test of independent reads from independent writes with nothing
+ * between each pairs of reads.  In other words, is anything at all
+ * needed to cause two different reading processes to agree on the order
+ * of a pair of writes, where each write is to a different variable by a
+ * different process?
+ *)
+
+{}
+
+P0(int *x)
+{
+        WRITE_ONCE(*x, 1);
+}
+
+P1(int *x, int *y)
+{
+        int r0;
+        int r1;
+
+        r0 = READ_ONCE(*x);
+        r1 = READ_ONCE(*y);
+}
+
+P2(int *y)
+{
+        WRITE_ONCE(*y, 1);
+}
+
+P3(int *x, int *y)
+{
+        int r0;
+        int r1;
+
+        r0 = READ_ONCE(*y);
+        r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ 1:r1=0 /\ 3:r0=1 /\ 3:r1=0)
diff --git a/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus b/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
new file mode 100644
index 000000000000..7a39a0aaa976
--- /dev/null
+++ b/tools/memory-model/litmus-tests/ISA2+pooncelock+pooncelock+pombonce.litmus
@@ -0,0 +1,41 @@
+C ISA2+pooncelock+pooncelock+pombonce.litmus
+
+(*
+ * Result: Sometimes
+ *
+ * This test shows that the ordering provided by a lock-protected S
+ * litmus test (P0() and P1()) are not visible to external process P2().
+ * This is likely to change soon.
+ *)
+
+{}
+
+P0(int *x, int *y, spinlock_t *mylock)
+{
+        spin_lock(mylock);
+        WRITE_ONCE(*x, 1);
+        WRITE_ONCE(*y, 1);
+        spin_unlock(mylock);
+}
+
+P1(int *y, int *z, spinlock_t *mylock)
+{
+        int r0;
+
+        spin_lock(mylock);
+        r0 = READ_ONCE(*y);
+        WRITE_ONCE(*z, 1);
+        spin_unlock(mylock);
+}
+
+P2(int *x, int *z)
+{
+        int r1;
+        int r2;
+
+        r2 = READ_ONCE(*z);
+        smp_mb();
+        r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ 2:r2=1 /\ 2:r1=0)
diff --git a/tools/memory-model/litmus-tests/ISA2+poonceonces.litmus b/tools/memory-model/litmus-tests/ISA2+poonceonces.litmus
new file mode 100644
index 000000000000..b321aa6f4ea5
--- /dev/null
+++ b/tools/memory-model/litmus-tests/ISA2+poonceonces.litmus
@@ -0,0 +1,37 @@
+C ISA2+poonceonces
+
+(*
+ * Result: Sometimes
+ *
+ * Given a release-acquire chain ordering the first process's store
+ * against the last process's load, is ordering preserved if all of the
+ * smp_store_release() invocations are replaced by WRITE_ONCE() and all
+ * of the smp_load_acquire() invocations are replaced by READ_ONCE()?
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+        WRITE_ONCE(*x, 1);
+        WRITE_ONCE(*y, 1);
+}
+
+P1(int *y, int *z)
+{
+        int r0;
+
+        r0 = READ_ONCE(*y);
+        WRITE_ONCE(*z, 1);
+}
+
+P2(int *x, int *z)
+{
+        int r0;
+        int r1;
+
+        r0 = READ_ONCE(*z);
+        r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ 2:r0=1 /\ 2:r1=0)
diff --git a/tools/memory-model/litmus-tests/ISA2+pooncerelease+poacquirerelease+poacquireonce.litmus b/tools/memory-model/litmus-tests/ISA2+pooncerelease+poacquirerelease+poacquireonce.litmus
new file mode 100644
index 000000000000..025b0462ec9b
--- /dev/null
+++ b/tools/memory-model/litmus-tests/ISA2+pooncerelease+poacquirerelease+poacquireonce.litmus
@@ -0,0 +1,39 @@
+C ISA2+pooncerelease+poacquirerelease+poacquireonce
+
+(*
+ * Result: Never
+ *
+ * This litmus test demonstrates that a release-acquire chain suffices
+ * to order P0()'s initial write against P2()'s final read.  The reason
+ * that the release-acquire chain suffices is because in all but one
+ * case (P2() to P0()), each process reads from the preceding process's
+ * write.  In memory-model-speak, there is only one non-reads-from
+ * (AKA non-rf) link, so release-acquire is all that is needed.
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+        WRITE_ONCE(*x, 1);
+        smp_store_release(y, 1);
+}
+
+P1(int *y, int *z)
+{
+        int r0;
+
+        r0 = smp_load_acquire(y);
+        smp_store_release(z, 1);
+}
+
+P2(int *x, int *z)
+{
+        int r0;
+        int r1;
+
+        r0 = smp_load_acquire(z);
+        r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ 2:r0=1 /\ 2:r1=0)
diff --git a/tools/memory-model/litmus-tests/LB+ctrlonceonce+mbonceonce.litmus b/tools/memory-model/litmus-tests/LB+ctrlonceonce+mbonceonce.litmus
new file mode 100644
index 000000000000..de6708229dd1
--- /dev/null
+++ b/tools/memory-model/litmus-tests/LB+ctrlonceonce+mbonceonce.litmus
@@ -0,0 +1,34 @@
+C LB+ctrlonceonce+mbonceonce
+
+(*
+ * Result: Never
+ *
+ * This litmus test demonstrates that lightweight ordering suffices for
+ * the load-buffering pattern, in other words, preventing all processes
+ * reading from the preceding process's write.  In this example, the
+ * combination of a control dependency and a full memory barrier are enough
+ * to do the trick.  (But the full memory barrier could be replaced with
+ * another control dependency and order would still be maintained.)
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+        int r0;
+
+        r0 = READ_ONCE(*x);
+        if (r0)
+                WRITE_ONCE(*y, 1);
+}
+
+P1(int *x, int *y)
+{
+        int r0;
+
+        r0 = READ_ONCE(*y);
+        smp_mb();
+        WRITE_ONCE(*x, 1);
+}
+
+exists (0:r0=1 /\ 1:r0=1)
diff --git a/tools/memory-model/litmus-tests/LB+poacquireonce+pooncerelease.litmus b/tools/memory-model/litmus-tests/LB+poacquireonce+pooncerelease.litmus
new file mode 100644
index 000000000000..07b9904b0e49
--- /dev/null
+++ b/tools/memory-model/litmus-tests/LB+poacquireonce+pooncerelease.litmus
@@ -0,0 +1,29 @@
+C LB+poacquireonce+pooncerelease
+
+(*
+ * Result: Never
+ *
+ * Does a release-acquire pair suffice for the load-buffering litmus
+ * test, where each process reads from one of two variables then writes
+ * to the other?
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+        int r0;
+
+        r0 = READ_ONCE(*x);
+        smp_store_release(y, 1);
+}
+
+P1(int *x, int *y)
+{
+        int r0;
+
+        r0 = smp_load_acquire(y);
+        WRITE_ONCE(*x, 1);
+}
+
+exists (0:r0=1 /\ 1:r0=1)
diff --git a/tools/memory-model/litmus-tests/LB+poonceonces.litmus b/tools/memory-model/litmus-tests/LB+poonceonces.litmus
new file mode 100644
index 000000000000..74c49cb3c37b
--- /dev/null
+++ b/tools/memory-model/litmus-tests/LB+poonceonces.litmus
@@ -0,0 +1,28 @@
+C LB+poonceonces
+
+(*
+ * Result: Sometimes
+ *
+ * Can the counter-intuitive outcome for the load-buffering pattern
+ * be prevented even with no explicit ordering?
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+        int r0;
+
+        r0 = READ_ONCE(*x);
+        WRITE_ONCE(*y, 1);
+}
+
+P1(int *x, int *y)
+{
+        int r0;
+
+        r0 = READ_ONCE(*y);
+        WRITE_ONCE(*x, 1);
+}
+
+exists (0:r0=1 /\ 1:r0=1)
diff --git a/tools/memory-model/litmus-tests/MP+onceassign+derefonce.litmus b/tools/memory-model/litmus-tests/MP+onceassign+derefonce.litmus
new file mode 100644
index 000000000000..97731b4bbdd8
--- /dev/null
+++ b/tools/memory-model/litmus-tests/MP+onceassign+derefonce.litmus
@@ -0,0 +1,34 @@
+C MP+onceassign+derefonce
+
+(*
+ * Result: Never
+ *
+ * This litmus test demonstrates that rcu_assign_pointer() and
+ * rcu_dereference() suffice to ensure that an RCU reader will not see
+ * pre-initialization garbage when it traverses an RCU-protected data
+ * structure containing a newly inserted element.
+ *)
+
+{
+y=z;
+z=0;
+}
+
+P0(int *x, int **y)
+{
+        WRITE_ONCE(*x, 1);
+        rcu_assign_pointer(*y, x);
+}
+
+P1(int *x, int **y)
+{
+        int *r0;
+        int r1;
+
+        rcu_read_lock();
+        r0 = rcu_dereference(*y);
+        r1 = READ_ONCE(*r0);
+        rcu_read_unlock();
+}
+
+exists (1:r0=x /\ 1:r1=0)
diff --git a/tools/memory-model/litmus-tests/MP+polocks.litmus b/tools/memory-model/litmus-tests/MP+polocks.litmus
new file mode 100644
index 000000000000..712a4fcdf6ce
--- /dev/null
+++ b/tools/memory-model/litmus-tests/MP+polocks.litmus
@@ -0,0 +1,35 @@
+C MP+polocks
+
+(*
+ * Result: Never
+ *
+ * This litmus test demonstrates how lock acquisitions and releases can
+ * stand in for smp_load_acquire() and smp_store_release(), respectively.
+ * In other words, when holding a given lock (or indeed after releasing a
+ * given lock), a CPU is not only guaranteed to see the accesses that other
+ * CPUs made while previously holding that lock, it is also guaranteed
+ * to see all prior accesses by those other CPUs.
+ *)
+
+{}
+
+P0(int *x, int *y, spinlock_t *mylock)
+{
+        WRITE_ONCE(*x, 1);
+        spin_lock(mylock);
+        WRITE_ONCE(*y, 1);
+        spin_unlock(mylock);
+}
+
+P1(int *x, int *y, spinlock_t *mylock)
+{
+        int r0;
+        int r1;
+
+        spin_lock(mylock);
+        r0 = READ_ONCE(*y);
+        spin_unlock(mylock);
+        r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ 1:r1=0)
diff --git a/tools/memory-model/litmus-tests/MP+poonceonces.litmus b/tools/memory-model/litmus-tests/MP+poonceonces.litmus
new file mode 100644
index 000000000000..b2b60b84fb9d
--- /dev/null
+++ b/tools/memory-model/litmus-tests/MP+poonceonces.litmus
@@ -0,0 +1,27 @@
+C MP+poonceonces
+
+(*
+ * Result: Maybe
+ *
+ * Can the counter-intuitive message-passing outcome be prevented with
+ * no ordering at all?
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+        WRITE_ONCE(*x, 1);
+        WRITE_ONCE(*y, 1);
+}
+
+P1(int *x, int *y)
+{
+        int r0;
+        int r1;
+
+        r0 = READ_ONCE(*y);
+        r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ 1:r1=0)
diff --git a/tools/memory-model/litmus-tests/MP+pooncerelease+poacquireonce.litmus b/tools/memory-model/litmus-tests/MP+pooncerelease+poacquireonce.litmus
new file mode 100644
index 000000000000..d52c68429722
--- /dev/null
+++ b/tools/memory-model/litmus-tests/MP+pooncerelease+poacquireonce.litmus
@@ -0,0 +1,28 @@
+C MP+pooncerelease+poacquireonce
+
+(*
+ * Result: Never
+ *
+ * This litmus test demonstrates that smp_store_release() and
+ * smp_load_acquire() provide sufficient ordering for the message-passing
+ * pattern.
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+        WRITE_ONCE(*x, 1);
+        smp_store_release(y, 1);
+}
+
+P1(int *x, int *y)
+{
+        int r0;
+        int r1;
+
+        r0 = smp_load_acquire(y);
+        r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ 1:r1=0)
diff --git a/tools/memory-model/litmus-tests/MP+porevlocks.litmus b/tools/memory-model/litmus-tests/MP+porevlocks.litmus
new file mode 100644
index 000000000000..72c9276b363e
--- /dev/null
+++ b/tools/memory-model/litmus-tests/MP+porevlocks.litmus
@@ -0,0 +1,35 @@
+C MP+porevlocks
+
+(*
+ * Result: Never
+ *
+ * This litmus test demonstrates how lock acquisitions and releases can
+ * stand in for smp_load_acquire() and smp_store_release(), respectively.
+ * In other words, when holding a given lock (or indeed after releasing a
+ * given lock), a CPU is not only guaranteed to see the accesses that other
+ * CPUs made while previously holding that lock, it is also guaranteed to
+ * see all prior accesses by those other CPUs.
+ *)
+
+{}
+
+P0(int *x, int *y, spinlock_t *mylock)
+{
+        int r0;
+        int r1;
+
+        r0 = READ_ONCE(*y);
+        spin_lock(mylock);
+        r1 = READ_ONCE(*x);
+        spin_unlock(mylock);
+}
+
+P1(int *x, int *y, spinlock_t *mylock)
+{
+        spin_lock(mylock);
+        WRITE_ONCE(*x, 1);
+        spin_unlock(mylock);
+        WRITE_ONCE(*y, 1);
+}
+
+exists (0:r0=1 /\ 0:r1=0)
diff --git a/tools/memory-model/litmus-tests/MP+wmbonceonce+rmbonceonce.litmus b/tools/memory-model/litmus-tests/MP+wmbonceonce+rmbonceonce.litmus
new file mode 100644
index 000000000000..c078f38ff27a
--- /dev/null
+++ b/tools/memory-model/litmus-tests/MP+wmbonceonce+rmbonceonce.litmus
@@ -0,0 +1,30 @@
+C MP+wmbonceonce+rmbonceonce
+
+(*
+ * Result: Never
+ *
+ * This litmus test demonstrates that smp_wmb() and smp_rmb() provide
+ * sufficient ordering for the message-passing pattern.  However, it
+ * is usually better to use smp_store_release() and smp_load_acquire().
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+        WRITE_ONCE(*x, 1);
+        smp_wmb();
+        WRITE_ONCE(*y, 1);
+}
+
+P1(int *x, int *y)
+{
+        int r0;
+        int r1;
+
+        r0 = READ_ONCE(*y);
+        smp_rmb();
+        r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ 1:r1=0)
diff --git a/tools/memory-model/litmus-tests/R+mbonceonces.litmus b/tools/memory-model/litmus-tests/R+mbonceonces.litmus
new file mode 100644
index 000000000000..a0e884ad2132
--- /dev/null
+++ b/tools/memory-model/litmus-tests/R+mbonceonces.litmus
@@ -0,0 +1,30 @@
+C R+mbonceonces
+
+(*
+ * Result: Never
+ *
+ * This is the fully ordered (via smp_mb()) version of one of the classic
+ * counterintuitive litmus tests that illustrates the effects of store
+ * propagation delays.  Note that weakening either of the barriers would
+ * cause the resulting test to be allowed.
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+        WRITE_ONCE(*x, 1);
+        smp_mb();
+        WRITE_ONCE(*y, 1);
+}
+
+P1(int *x, int *y)
+{
+        int r0;
+
+        WRITE_ONCE(*y, 2);
+        smp_mb();
+        r0 = READ_ONCE(*x);
+}
+
+exists (y=2 /\ 1:r0=0)
diff --git a/tools/memory-model/litmus-tests/R+poonceonces.litmus b/tools/memory-model/litmus-tests/R+poonceonces.litmus
new file mode 100644
index 000000000000..5386f128a131
--- /dev/null
+++ b/tools/memory-model/litmus-tests/R+poonceonces.litmus
@@ -0,0 +1,27 @@
+C R+poonceonces
+
+(*
+ * Result: Sometimes
+ *
+ * This is the unordered (thus lacking smp_mb()) version of one of the
+ * classic counterintuitive litmus tests that illustrates the effects of
+ * store propagation delays.
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+        WRITE_ONCE(*x, 1);
+        WRITE_ONCE(*y, 1);
+}
+
+P1(int *x, int *y)
+{
+        int r0;
+
+        WRITE_ONCE(*y, 2);
+        r0 = READ_ONCE(*x);
+}
+
+exists (y=2 /\ 1:r0=0)
diff --git a/tools/memory-model/litmus-tests/README b/tools/memory-model/litmus-tests/README
new file mode 100644
index 000000000000..04096fb8b8d9
--- /dev/null
+++ b/tools/memory-model/litmus-tests/README
@@ -0,0 +1,131 @@
+This directory contains the following litmus tests:
+
+CoRR+poonceonce+Once.litmus
+        Test of read-read coherence, that is, whether or not two
+        successive reads from the same variable are ordered.
+
+CoRW+poonceonce+Once.litmus
+        Test of read-write coherence, that is, whether or not a read
+        from a given variable followed by a write to that same variable
+        are ordered.
+
+CoWR+poonceonce+Once.litmus
+        Test of write-read coherence, that is, whether or not a write
+        to a given variable followed by a read from that same variable
+        are ordered.
+
+CoWW+poonceonce.litmus
+        Test of write-write coherence, that is, whether or not two
+        successive writes to the same variable are ordered.
+
+IRIW+mbonceonces+OnceOnce.litmus
+        Test of independent reads from independent writes with smp_mb()
+        between each pairs of reads.  In other words, is smp_mb()
+        sufficient to cause two different reading processes to agree on
+        the order of a pair of writes, where each write is to a different
+        variable by a different process?
+
+IRIW+poonceonces+OnceOnce.litmus
+        Test of independent reads from independent writes with nothing
+        between each pairs of reads.  In other words, is anything at all
+        needed to cause two different reading processes to agree on the
+        order of a pair of writes, where each write is to a different
+        variable by a different process?
+
+ISA2+pooncelock+pooncelock+pombonce.litmus
+        Tests whether the ordering provided by a lock-protected S
+        litmus test is visible to an external process whose accesses are
+        separated by smp_mb().  This addition of an external process to
+        S is otherwise known as ISA2.
+
+ISA2+poonceonces.litmus
+        As below, but with store-release replaced with WRITE_ONCE()
+        and load-acquire replaced with READ_ONCE().
+
+ISA2+pooncerelease+poacquirerelease+poacquireonce.litmus
+        Can a release-acquire chain order a prior store against
+        a later load?
+
+LB+ctrlonceonce+mbonceonce.litmus
+        Does a control dependency and an smp_mb() suffice for the
+        load-buffering litmus test, where each process reads from one
+        of two variables then writes to the other?
+
+LB+poacquireonce+pooncerelease.litmus
+        Does a release-acquire pair suffice for the load-buffering
+        litmus test, where each process reads from one of two variables then
+        writes to the other?
+
+LB+poonceonces.litmus
+        As above, but with store-release replaced with WRITE_ONCE()
+        and load-acquire replaced with READ_ONCE().
+
+MP+onceassign+derefonce.litmus
+        As below, but with rcu_assign_pointer() and an rcu_dereference().
+
+MP+polocks.litmus
+        As below, but with the second access of the writer process
+        and the first access of reader process protected by a lock.
+
+MP+poonceonces.litmus
+        As below, but without the smp_rmb() and smp_wmb().
+
+MP+pooncerelease+poacquireonce.litmus
+        As below, but with a release-acquire chain.
+
+MP+porevlocks.litmus
+        As below, but with the first access of the writer process
+        and the second access of reader process protected by a lock.
+
+MP+wmbonceonce+rmbonceonce.litmus
+        Does a smp_wmb() (between the stores) and an smp_rmb() (between
+        the loads) suffice for the message-passing litmus test, where one
+        process writes data and then a flag, and the other process reads
+        the flag and then the data.  (This is similar to the ISA2 tests,
+        but with two processes instead of three.)
+
+R+mbonceonces.litmus
+        This is the fully ordered (via smp_mb()) version of one of
+        the classic counterintuitive litmus tests that illustrates the
+        effects of store propagation delays.
+
+R+poonceonces.litmus
+        As above, but without the smp_mb() invocations.
+
+SB+mbonceonces.litmus
+        This is the fully ordered (again, via smp_mb() version of store
+        buffering, which forms the core of Dekker's mutual-exclusion
+        algorithm.
+
+SB+poonceonces.litmus
+        As above, but without the smp_mb() invocations.
+
+S+poonceonces.litmus
+        As below, but without the smp_wmb() and acquire load.
+
+S+wmbonceonce+poacquireonce.litmus
+        Can a smp_wmb(), instead of a release, and an acquire order
+        a prior store against a subsequent store?
+
+WRC+poonceonces+Once.litmus
+WRC+pooncerelease+rmbonceonce+Once.litmus
+        These two are members of an extension of the MP litmus-test class
+        in which the first write is moved to a separate process.
+
+Z6.0+pooncelock+pooncelock+pombonce.litmus
+        Is the ordering provided by a spin_unlock() and a subsequent
+        spin_lock() sufficient to make ordering apparent to accesses
+        by a process not holding the lock?
+
+Z6.0+pooncelock+poonceLock+pombonce.litmus
+        As above, but with smp_mb__after_spinlock() immediately
+        following the spin_lock().
+
+Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus
+        Is the ordering provided by a release-acquire chain sufficient
+        to make ordering apparent to accesses by a process that does
+        not participate in that release-acquire chain?
+
+A great many more litmus tests are available here:
+
+        https://github.com/paulmckrcu/litmus
diff --git a/tools/memory-model/litmus-tests/S+poonceonces.litmus b/tools/memory-model/litmus-tests/S+poonceonces.litmus
new file mode 100644
index 000000000000..8c9c2f81a580
--- /dev/null
+++ b/tools/memory-model/litmus-tests/S+poonceonces.litmus
@@ -0,0 +1,28 @@
+C S+poonceonces
+
+(*
+ * Result: Sometimes
+ *
+ * Starting with a two-process release-acquire chain ordering P0()'s
+ * first store against P1()'s final load, if the smp_store_release()
+ * is replaced by WRITE_ONCE() and the smp_load_acquire() replaced by
+ * READ_ONCE(), is ordering preserved?
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+        WRITE_ONCE(*x, 2);
+        WRITE_ONCE(*y, 1);
+}
+
+P1(int *x, int *y)
+{
+        int r0;
+
+        r0 = READ_ONCE(*y);
+        WRITE_ONCE(*x, 1);
+}
+
+exists (x=2 /\ 1:r0=1)
diff --git a/tools/memory-model/litmus-tests/S+wmbonceonce+poacquireonce.litmus b/tools/memory-model/litmus-tests/S+wmbonceonce+poacquireonce.litmus
new file mode 100644
index 000000000000..c53350205d28
--- /dev/null
+++ b/tools/memory-model/litmus-tests/S+wmbonceonce+poacquireonce.litmus
@@ -0,0 +1,27 @@
+C S+wmbonceonce+poacquireonce
+
+(*
+ * Result: Never
+ *
+ * Can a smp_wmb(), instead of a release, and an acquire order a prior
+ * store against a subsequent store?
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+        WRITE_ONCE(*x, 2);
+        smp_wmb();
+        WRITE_ONCE(*y, 1);
+}
+
+P1(int *x, int *y)
+{
+        int r0;
+
+        r0 = smp_load_acquire(y);
+        WRITE_ONCE(*x, 1);
+}
+
+exists (x=2 /\ 1:r0=1)
diff --git a/tools/memory-model/litmus-tests/SB+mbonceonces.litmus b/tools/memory-model/litmus-tests/SB+mbonceonces.litmus
new file mode 100644
index 000000000000..74b874ffa8da
--- /dev/null
+++ b/tools/memory-model/litmus-tests/SB+mbonceonces.litmus
@@ -0,0 +1,32 @@
+C SB+mbonceonces
+
+(*
+ * Result: Never
+ *
+ * This litmus test demonstrates that full memory barriers suffice to
+ * order the store-buffering pattern, where each process writes to the
+ * variable that the preceding process reads.  (Locking and RCU can also
+ * suffice, but not much else.)
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+        int r0;
+
+        WRITE_ONCE(*x, 1);
+        smp_mb();
+        r0 = READ_ONCE(*y);
+}
+
+P1(int *x, int *y)
+{
+        int r0;
+
+        WRITE_ONCE(*y, 1);
+        smp_mb();
+        r0 = READ_ONCE(*x);
+}
+
+exists (0:r0=0 /\ 1:r0=0)
diff --git a/tools/memory-model/litmus-tests/SB+poonceonces.litmus b/tools/memory-model/litmus-tests/SB+poonceonces.litmus
new file mode 100644
index 000000000000..10d550730b25
--- /dev/null
+++ b/tools/memory-model/litmus-tests/SB+poonceonces.litmus
@@ -0,0 +1,29 @@
+C SB+poonceonces
+
+(*
+ * Result: Sometimes
+ *
+ * This litmus test demonstrates that at least some ordering is required
+ * to order the store-buffering pattern, where each process writes to the
+ * variable that the preceding process reads.
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+        int r0;
+
+        WRITE_ONCE(*x, 1);
+        r0 = READ_ONCE(*y);
+}
+
+P1(int *x, int *y)
+{
+        int r0;
+
+        WRITE_ONCE(*y, 1);
+        r0 = READ_ONCE(*x);
+}
+
+exists (0:r0=0 /\ 1:r0=0)
diff --git a/tools/memory-model/litmus-tests/WRC+poonceonces+Once.litmus b/tools/memory-model/litmus-tests/WRC+poonceonces+Once.litmus
new file mode 100644
index 000000000000..6a2bc12a1af1
--- /dev/null
+++ b/tools/memory-model/litmus-tests/WRC+poonceonces+Once.litmus
@@ -0,0 +1,35 @@
+C WRC+poonceonces+Once
+
+(*
+ * Result: Sometimes
+ *
+ * This litmus test is an extension of the message-passing pattern,
+ * where the first write is moved to a separate process.  Note that this
+ * test has no ordering at all.
+ *)
+
+{}
+
+P0(int *x)
+{
+        WRITE_ONCE(*x, 1);
+}
+
+P1(int *x, int *y)
+{
+        int r0;
+
+        r0 = READ_ONCE(*x);
+        WRITE_ONCE(*y, 1);
+}
+
+P2(int *x, int *y)
+{
+        int r0;
+        int r1;
+
+        r0 = READ_ONCE(*y);
+        r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ 2:r0=1 /\ 2:r1=0)
diff --git a/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus b/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus
new file mode 100644
index 000000000000..97fcbffde9a0
--- /dev/null
+++ b/tools/memory-model/litmus-tests/WRC+pooncerelease+rmbonceonce+Once.litmus
@@ -0,0 +1,36 @@
+C WRC+pooncerelease+rmbonceonce+Once
+
+(*
+ * Result: Never
+ *
+ * This litmus test is an extension of the message-passing pattern, where
+ * the first write is moved to a separate process.  Because it features
+ * a release and a read memory barrier, it should be forbidden.
+ *)
+
+{}
+
+P0(int *x)
+{
+        WRITE_ONCE(*x, 1);
+}
+
+P1(int *x, int *y)
+{
+        int r0;
+
+        r0 = READ_ONCE(*x);
+        smp_store_release(y, 1);
+}
+
+P2(int *x, int *y)
+{
+        int r0;
+        int r1;
+
+        r0 = READ_ONCE(*y);
+        smp_rmb();
+        r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ 2:r0=1 /\ 2:r1=0)
diff --git a/tools/memory-model/litmus-tests/Z6.0+pooncelock+poonceLock+pombonce.litmus b/tools/memory-model/litmus-tests/Z6.0+pooncelock+poonceLock+pombonce.litmus
new file mode 100644
index 000000000000..415248fb6699
--- /dev/null
+++ b/tools/memory-model/litmus-tests/Z6.0+pooncelock+poonceLock+pombonce.litmus
@@ -0,0 +1,42 @@
+C Z6.0+pooncelock+poonceLock+pombonce
+
+(*
+ * Result: Never
+ *
+ * This litmus test demonstrates how smp_mb__after_spinlock() may be
+ * used to ensure that accesses in different critical sections for a
+ * given lock running on different CPUs are nevertheless seen in order
+ * by CPUs not holding that lock.
+ *)
+
+{}
+
+P0(int *x, int *y, spinlock_t *mylock)
+{
+        spin_lock(mylock);
+        WRITE_ONCE(*x, 1);
+        WRITE_ONCE(*y, 1);
+        spin_unlock(mylock);
+}
+
+P1(int *y, int *z, spinlock_t *mylock)
+{
+        int r0;
+
+        spin_lock(mylock);
+        smp_mb__after_spinlock();
+        r0 = READ_ONCE(*y);
+        WRITE_ONCE(*z, 1);
+        spin_unlock(mylock);
+}
+
+P2(int *x, int *z)
+{
+        int r1;
+
+        WRITE_ONCE(*z, 2);
+        smp_mb();
+        r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ z=2 /\ 2:r1=0)
diff --git a/tools/memory-model/litmus-tests/Z6.0+pooncelock+pooncelock+pombonce.litmus b/tools/memory-model/litmus-tests/Z6.0+pooncelock+pooncelock+pombonce.litmus
new file mode 100644
index 000000000000..10a2aa04cd07
--- /dev/null
+++ b/tools/memory-model/litmus-tests/Z6.0+pooncelock+pooncelock+pombonce.litmus
@@ -0,0 +1,40 @@
+C Z6.0+pooncelock+pooncelock+pombonce
+
+(*
+ * Result: Sometimes
+ *
+ * This example demonstrates that a pair of accesses made by different
+ * processes each while holding a given lock will not necessarily be
+ * seen as ordered by a third process not holding that lock.
+ *)
+
+{}
+
+P0(int *x, int *y, spinlock_t *mylock)
+{
+        spin_lock(mylock);
+        WRITE_ONCE(*x, 1);
+        WRITE_ONCE(*y, 1);
+        spin_unlock(mylock);
+}
+
+P1(int *y, int *z, spinlock_t *mylock)
+{
+        int r0;
+
+        spin_lock(mylock);
+        r0 = READ_ONCE(*y);
+        WRITE_ONCE(*z, 1);
+        spin_unlock(mylock);
+}
+
+P2(int *x, int *z)
+{
+        int r1;
+
+        WRITE_ONCE(*z, 2);
+        smp_mb();
+        r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ z=2 /\ 2:r1=0)
diff --git a/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus b/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus
new file mode 100644
index 000000000000..a20fc3fafb53
--- /dev/null
+++ b/tools/memory-model/litmus-tests/Z6.0+pooncerelease+poacquirerelease+mbonceonce.litmus
@@ -0,0 +1,42 @@
+C Z6.0+pooncerelease+poacquirerelease+mbonceonce
+
+(*
+ * Result: Sometimes
+ *
+ * This litmus test shows that a release-acquire chain, while sufficient
+ * when there is but one non-reads-from (AKA non-rf) link, does not suffice
+ * if there is more than one.  Of the three processes, only P1() reads from
+ * P0's write, which means that there are two non-rf links: P1() to P2()
+ * is a write-to-write link (AKA a "coherence" or just "co" link) and P2()
+ * to P0() is a read-to-write link (AKA a "from-reads" or just "fr" link).
+ * When there are two or more non-rf links, you typically will need one
+ * full barrier for each non-rf link.  (Exceptions include some cases
+ * involving locking.)
+ *)
+
+{}
+
+P0(int *x, int *y)
+{
+        WRITE_ONCE(*x, 1);
+        smp_store_release(y, 1);
+}
+
+P1(int *y, int *z)
+{
+        int r0;
+
+        r0 = smp_load_acquire(y);
+        smp_store_release(z, 1);
+}
+
+P2(int *x, int *z)
+{
+        int r1;
+
+        WRITE_ONCE(*z, 2);
+        smp_mb();
+        r1 = READ_ONCE(*x);
+}
+
+exists (1:r0=1 /\ z=2 /\ 2:r1=0)
diff --git a/tools/memory-model/lock.cat b/tools/memory-model/lock.cat
new file mode 100644
index 000000000000..ba4a4ec6d313
--- /dev/null
+++ b/tools/memory-model/lock.cat
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0+
+(*
+ * Copyright (C) 2016 Luc Maranget <luc.maranget@inria.fr> for Inria
+ * Copyright (C) 2017 Alan Stern <stern@rowland.harvard.edu>
+ *)
+
+(* Generate coherence orders and handle lock operations *)
+
+include "cross.cat"
+
+(* From lock reads to their partner lock writes *)
+let lk-rmw = ([LKR] ; po-loc ; [LKW]) \ (po ; po)
+let rmw = rmw | lk-rmw
+
+(*
+ * A paired LKR must always see an unlocked value; spin_lock() calls nested
+ * inside a critical section (for the same lock) always deadlock.
+ *)
+empty ([LKW] ; po-loc ; [domain(lk-rmw)]) \ (po-loc ; [UL] ; po-loc)
+        as lock-nest
+
+(* The litmus test is invalid if an LKW event is not part of an RMW pair *)
+flag ~empty LKW \ range(lk-rmw) as unpaired-LKW
+
+(* This will be allowed if we implement spin_is_locked() *)
+flag ~empty LKR \ domain(lk-rmw) as unpaired-LKR
+
+(* There should be no R or W accesses to spinlocks *)
+let ALL-LOCKS = LKR | LKW | UL | LF
+flag ~empty [M \ IW] ; loc ; [ALL-LOCKS] as mixed-lock-accesses
+
+(* The final value of a spinlock should not be tested *)
+flag ~empty [FW] ; loc ; [ALL-LOCKS] as lock-final
+
+
+(*
+ * Put lock operations in their appropriate classes, but leave UL out of W
+ * until after the co relation has been generated.
+ *)
+let R = R | LKR | LF
+let W = W | LKW
+
+let Release = Release | UL
+let Acquire = Acquire | LKR
+
+
+(* Match LKW events to their corresponding UL events *)
+let critical = ([LKW] ; po-loc ; [UL]) \ (po-loc ; [LKW | UL] ; po-loc)
+
+flag ~empty UL \ range(critical) as unmatched-unlock
+
+(* Allow up to one unmatched LKW per location; more must deadlock *)
+let UNMATCHED-LKW = LKW \ domain(critical)
+empty ([UNMATCHED-LKW] ; loc ; [UNMATCHED-LKW]) \ id as unmatched-locks
+
+
+(* rfi for LF events: link each LKW to the LF events in its critical section *)
+let rfi-lf = ([LKW] ; po-loc ; [LF]) \ ([LKW] ; po-loc ; [UL] ; po-loc)
+
+(* rfe for LF events *)
+let all-possible-rfe-lf =
+  (*
+   * Given an LF event r, compute the possible rfe edges for that event
+   * (all those starting from LKW events in other threads),
+   * and then convert that relation to a set of single-edge relations.
+   *)
+  let possible-rfe-lf r =
+    let pair-to-relation p = p ++ 0
+    in map pair-to-relation ((LKW * {r}) & loc & ext)
+  (* Do this for each LF event r that isn't in rfi-lf *)
+  in map possible-rfe-lf (LF \ range(rfi-lf))
+
+(* Generate all rf relations for LF events *)
+with rfe-lf from cross(all-possible-rfe-lf)
+let rf = rf | rfi-lf | rfe-lf
+
+
+(* Generate all co relations, including LKW events but not UL *)
+let co0 = co0 | ([IW] ; loc ; [LKW]) |
+        (([LKW] ; loc ; [UNMATCHED-LKW]) \ [UNMATCHED-LKW])
+include "cos-opt.cat"
+let W = W | UL
+let M = R | W
+
+(* Merge UL events into co *)
+let co = (co | critical | (critical^-1 ; co))+
+let coe = co & ext
+let coi = co & int
+
+(* Merge LKR events into rf *)
+let rf = rf | ([IW | UL] ; singlestep(co) ; lk-rmw^-1)
+let rfe = rf & ext
+let rfi = rf & int
+
+let fr = rf^-1 ; co
+let fre = fr & ext
+let fri = fr & int
+
+show co,rf,fr
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 f0796a47dfa3..c87180764829 100644
--- a/tools/perf/Documentation/perf-data.txt
+++ b/tools/perf/Documentation/perf-data.txt
@@ -1,5 +1,5 @@
 perf-data(1)
-==============
+============
 
 NAME
 ----
@@ -30,6 +30,10 @@ OPTIONS for 'convert'
 -i::
         Specify input perf data file path.
 
+-f::
+--force::
+        Don't complain, do it.
+
 -v::
 --verbose::
         Be more verbose (show counter open errors, etc).
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 954ea9e21236..f3c620951f6e 100644
--- a/tools/perf/Documentation/perf-kallsyms.txt
+++ b/tools/perf/Documentation/perf-kallsyms.txt
@@ -1,5 +1,5 @@
 perf-kallsyms(1)
-==============
+================
 
 NAME
 ----
@@ -8,7 +8,7 @@ perf-kallsyms - Searches running kernel for symbols
 SYNOPSIS
 --------
 [verse]
-'perf kallsyms <options> symbol_name[,symbol_name...]'
+'perf kallsyms' [<options>] symbol_name[,symbol_name...]
 
 DESCRIPTION
 -----------
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 9b0351d3ce34..f7517e1b73f8 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -146,12 +146,6 @@ define allow-override
     $(eval $(1) = $(2)))
 endef
 
-# Allow setting CC and AR and LD, or setting CROSS_COMPILE as a prefix.
-$(call allow-override,CC,$(CROSS_COMPILE)gcc)
-$(call allow-override,AR,$(CROSS_COMPILE)ar)
-$(call allow-override,LD,$(CROSS_COMPILE)ld)
-$(call allow-override,CXX,$(CROSS_COMPILE)g++)
-
 LD += $(EXTRA_LDFLAGS)
 
 HOSTCC  ?= gcc
@@ -302,7 +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)
@@ -479,7 +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)$$(:)
@@ -714,15 +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/Makefile b/tools/perf/arch/s390/Makefile
index 48228de415d0..dfa6e3103437 100644
--- a/tools/perf/arch/s390/Makefile
+++ b/tools/perf/arch/s390/Makefile
@@ -10,15 +10,19 @@ PERF_HAVE_ARCH_REGS_QUERY_REGISTER_OFFSET := 1
 
 out    := $(OUTPUT)arch/s390/include/generated/asm
 header := $(out)/syscalls_64.c
-sysdef := $(srctree)/tools/arch/s390/include/uapi/asm/unistd.h
-sysprf := $(srctree)/tools/perf/arch/s390/entry/syscalls/
+syskrn := $(srctree)/arch/s390/kernel/syscalls/syscall.tbl
+sysprf := $(srctree)/tools/perf/arch/s390/entry/syscalls
+sysdef := $(sysprf)/syscall.tbl
 systbl := $(sysprf)/mksyscalltbl
 
 # Create output directory if not already present
 _dummy := $(shell [ -d '$(out)' ] || mkdir -p '$(out)')
 
 $(header): $(sysdef) $(systbl)
-        $(Q)$(SHELL) '$(systbl)' '$(CC)' $(sysdef) > $@
+        @(test -d ../../kernel -a -d ../../tools -a -d ../perf && ( \
+        (diff -B $(sysdef) $(syskrn) >/dev/null) \
+        || echo "Warning: Kernel ABI header at '$(sysdef)' differs from latest version at '$(syskrn)'" >&2 )) || true
+        $(Q)$(SHELL) '$(systbl)' $(sysdef) > $@
 
 clean::
         $(call QUIET_CLEAN, s390) $(RM) $(header)
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/entry/syscalls/mksyscalltbl b/tools/perf/arch/s390/entry/syscalls/mksyscalltbl
index 7fa0d0abd419..72ecbb676370 100755
--- a/tools/perf/arch/s390/entry/syscalls/mksyscalltbl
+++ b/tools/perf/arch/s390/entry/syscalls/mksyscalltbl
@@ -3,25 +3,23 @@
 #
 # Generate system call table for perf
 #
-#
-# Copyright IBM Corp. 2017
+# Copyright IBM Corp. 2017, 2018
 # Author(s):  Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
 #
 
-gcc=$1
-input=$2
+SYSCALL_TBL=$1
 
-if ! test -r $input; then
+if ! test -r $SYSCALL_TBL; then
         echo "Could not read input file" >&2
         exit 1
 fi
 
 create_table()
 {
-        local max_nr
+        local max_nr nr abi sc discard
 
         echo 'static const char *syscalltbl_s390_64[] = {'
-        while read sc nr; do
+        while read nr abi sc discard; do
                 printf '\t[%d] = "%s",\n' $nr $sc
                 max_nr=$nr
         done
@@ -29,8 +27,6 @@ create_table()
         echo "#define SYSCALLTBL_S390_64_MAX_ID $max_nr"
 }
 
-
-$gcc -m64 -E -dM -x c  $input          \
-        |sed -ne 's/^#define __NR_//p' \
-        |sort -t' ' -k2 -nu            \
+grep -E "^[[:digit:]]+[[:space:]]+(common|64)" $SYSCALL_TBL     \
+        |sort -k1 -n                                    \
         |create_table
diff --git a/tools/perf/arch/s390/entry/syscalls/syscall.tbl b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
new file mode 100644
index 000000000000..b38d48464368
--- /dev/null
+++ b/tools/perf/arch/s390/entry/syscalls/syscall.tbl
@@ -0,0 +1,390 @@
+# SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note
+#
+# System call table for s390
+#
+# Format:
+#
+# <nr> <abi> <syscall> <entry-64bit> <compat-entry>
+#
+# where <abi> can be common, 64, or 32
+
+1    common     exit                    sys_exit                        sys_exit
+2    common     fork                    sys_fork                        sys_fork
+3    common     read                    sys_read                        compat_sys_s390_read
+4    common     write                   sys_write                       compat_sys_s390_write
+5    common     open                    sys_open                        compat_sys_open
+6    common     close                   sys_close                       sys_close
+7    common     restart_syscall         sys_restart_syscall             sys_restart_syscall
+8    common     creat                   sys_creat                       compat_sys_creat
+9    common     link                    sys_link                        compat_sys_link
+10   common     unlink                  sys_unlink                      compat_sys_unlink
+11   common     execve                  sys_execve                      compat_sys_execve
+12   common     chdir                   sys_chdir                       compat_sys_chdir
+13   32         time                    -                               compat_sys_time
+14   common     mknod                   sys_mknod                       compat_sys_mknod
+15   common     chmod                   sys_chmod                       compat_sys_chmod
+16   32         lchown                  -                               compat_sys_s390_lchown16
+19   common     lseek                   sys_lseek                       compat_sys_lseek
+20   common     getpid                  sys_getpid                      sys_getpid
+21   common     mount                   sys_mount                       compat_sys_mount
+22   common     umount                  sys_oldumount                   compat_sys_oldumount
+23   32         setuid                  -                               compat_sys_s390_setuid16
+24   32         getuid                  -                               compat_sys_s390_getuid16
+25   32         stime                   -                               compat_sys_stime
+26   common     ptrace                  sys_ptrace                      compat_sys_ptrace
+27   common     alarm                   sys_alarm                       sys_alarm
+29   common     pause                   sys_pause                       sys_pause
+30   common     utime                   sys_utime                       compat_sys_utime
+33   common     access                  sys_access                      compat_sys_access
+34   common     nice                    sys_nice                        sys_nice
+36   common     sync                    sys_sync                        sys_sync
+37   common     kill                    sys_kill                        sys_kill
+38   common     rename                  sys_rename                      compat_sys_rename
+39   common     mkdir                   sys_mkdir                       compat_sys_mkdir
+40   common     rmdir                   sys_rmdir                       compat_sys_rmdir
+41   common     dup                     sys_dup                         sys_dup
+42   common     pipe                    sys_pipe                        compat_sys_pipe
+43   common     times                   sys_times                       compat_sys_times
+45   common     brk                     sys_brk                         compat_sys_brk
+46   32         setgid                  -                               compat_sys_s390_setgid16
+47   32         getgid                  -                               compat_sys_s390_getgid16
+48   common     signal                  sys_signal                      compat_sys_signal
+49   32         geteuid                 -                               compat_sys_s390_geteuid16
+50   32         getegid                 -                               compat_sys_s390_getegid16
+51   common     acct                    sys_acct                        compat_sys_acct
+52   common     umount2                 sys_umount                      compat_sys_umount
+54   common     ioctl                   sys_ioctl                       compat_sys_ioctl
+55   common     fcntl                   sys_fcntl                       compat_sys_fcntl
+57   common     setpgid                 sys_setpgid                     sys_setpgid
+60   common     umask                   sys_umask                       sys_umask
+61   common     chroot                  sys_chroot                      compat_sys_chroot
+62   common     ustat                   sys_ustat                       compat_sys_ustat
+63   common     dup2                    sys_dup2                        sys_dup2
+64   common     getppid                 sys_getppid                     sys_getppid
+65   common     getpgrp                 sys_getpgrp                     sys_getpgrp
+66   common     setsid                  sys_setsid                      sys_setsid
+67   common     sigaction               sys_sigaction                   compat_sys_sigaction
+70   32         setreuid                -                               compat_sys_s390_setreuid16
+71   32         setregid                -                               compat_sys_s390_setregid16
+72   common     sigsuspend              sys_sigsuspend                  compat_sys_sigsuspend
+73   common     sigpending              sys_sigpending                  compat_sys_sigpending
+74   common     sethostname             sys_sethostname                 compat_sys_sethostname
+75   common     setrlimit               sys_setrlimit                   compat_sys_setrlimit
+76   32         getrlimit               -                               compat_sys_old_getrlimit
+77   common     getrusage               sys_getrusage                   compat_sys_getrusage
+78   common     gettimeofday            sys_gettimeofday                compat_sys_gettimeofday
+79   common     settimeofday            sys_settimeofday                compat_sys_settimeofday
+80   32         getgroups               -                               compat_sys_s390_getgroups16
+81   32         setgroups               -                               compat_sys_s390_setgroups16
+83   common     symlink                 sys_symlink                     compat_sys_symlink
+85   common     readlink                sys_readlink                    compat_sys_readlink
+86   common     uselib                  sys_uselib                      compat_sys_uselib
+87   common     swapon                  sys_swapon                      compat_sys_swapon
+88   common     reboot                  sys_reboot                      compat_sys_reboot
+89   common     readdir                 -                               compat_sys_old_readdir
+90   common     mmap                    sys_old_mmap                    compat_sys_s390_old_mmap
+91   common     munmap                  sys_munmap                      compat_sys_munmap
+92   common     truncate                sys_truncate                    compat_sys_truncate
+93   common     ftruncate               sys_ftruncate                   compat_sys_ftruncate
+94   common     fchmod                  sys_fchmod                      sys_fchmod
+95   32         fchown                  -                               compat_sys_s390_fchown16
+96   common     getpriority             sys_getpriority                 sys_getpriority
+97   common     setpriority             sys_setpriority                 sys_setpriority
+99   common     statfs                  sys_statfs                      compat_sys_statfs
+100  common     fstatfs                 sys_fstatfs                     compat_sys_fstatfs
+101  32         ioperm                  -                               -
+102  common     socketcall              sys_socketcall                  compat_sys_socketcall
+103  common     syslog                  sys_syslog                      compat_sys_syslog
+104  common     setitimer               sys_setitimer                   compat_sys_setitimer
+105  common     getitimer               sys_getitimer                   compat_sys_getitimer
+106  common     stat                    sys_newstat                     compat_sys_newstat
+107  common     lstat                   sys_newlstat                    compat_sys_newlstat
+108  common     fstat                   sys_newfstat                    compat_sys_newfstat
+110  common     lookup_dcookie          sys_lookup_dcookie              compat_sys_lookup_dcookie
+111  common     vhangup                 sys_vhangup                     sys_vhangup
+112  common     idle                    -                               -
+114  common     wait4                   sys_wait4                       compat_sys_wait4
+115  common     swapoff                 sys_swapoff                     compat_sys_swapoff
+116  common     sysinfo                 sys_sysinfo                     compat_sys_sysinfo
+117  common     ipc                     sys_s390_ipc                    compat_sys_s390_ipc
+118  common     fsync                   sys_fsync                       sys_fsync
+119  common     sigreturn               sys_sigreturn                   compat_sys_sigreturn
+120  common     clone                   sys_clone                       compat_sys_clone
+121  common     setdomainname           sys_setdomainname               compat_sys_setdomainname
+122  common     uname                   sys_newuname                    compat_sys_newuname
+124  common     adjtimex                sys_adjtimex                    compat_sys_adjtimex
+125  common     mprotect                sys_mprotect                    compat_sys_mprotect
+126  common     sigprocmask             sys_sigprocmask                 compat_sys_sigprocmask
+127  common     create_module           -                               -
+128  common     init_module             sys_init_module                 compat_sys_init_module
+129  common     delete_module           sys_delete_module               compat_sys_delete_module
+130  common     get_kernel_syms         -                               -
+131  common     quotactl                sys_quotactl                    compat_sys_quotactl
+132  common     getpgid                 sys_getpgid                     sys_getpgid
+133  common     fchdir                  sys_fchdir                      sys_fchdir
+134  common     bdflush                 sys_bdflush                     compat_sys_bdflush
+135  common     sysfs                   sys_sysfs                       compat_sys_sysfs
+136  common     personality             sys_s390_personality            sys_s390_personality
+137  common     afs_syscall             -                               -
+138  32         setfsuid                -                               compat_sys_s390_setfsuid16
+139  32         setfsgid                -                               compat_sys_s390_setfsgid16
+140  32         _llseek                 -                               compat_sys_llseek
+141  common     getdents                sys_getdents                    compat_sys_getdents
+142  32         _newselect              -                               compat_sys_select
+142  64         select                  sys_select                      -
+143  common     flock                   sys_flock                       sys_flock
+144  common     msync                   sys_msync                       compat_sys_msync
+145  common     readv                   sys_readv                       compat_sys_readv
+146  common     writev                  sys_writev                      compat_sys_writev
+147  common     getsid                  sys_getsid                      sys_getsid
+148  common     fdatasync               sys_fdatasync                   sys_fdatasync
+149  common     _sysctl                 sys_sysctl                      compat_sys_sysctl
+150  common     mlock                   sys_mlock                       compat_sys_mlock
+151  common     munlock                 sys_munlock                     compat_sys_munlock
+152  common     mlockall                sys_mlockall                    sys_mlockall
+153  common     munlockall              sys_munlockall                  sys_munlockall
+154  common     sched_setparam          sys_sched_setparam              compat_sys_sched_setparam
+155  common     sched_getparam          sys_sched_getparam              compat_sys_sched_getparam
+156  common     sched_setscheduler      sys_sched_setscheduler          compat_sys_sched_setscheduler
+157  common     sched_getscheduler      sys_sched_getscheduler          sys_sched_getscheduler
+158  common     sched_yield             sys_sched_yield                 sys_sched_yield
+159  common     sched_get_priority_max  sys_sched_get_priority_max      sys_sched_get_priority_max
+160  common     sched_get_priority_min  sys_sched_get_priority_min      sys_sched_get_priority_min
+161  common     sched_rr_get_interval   sys_sched_rr_get_interval       compat_sys_sched_rr_get_interval
+162  common     nanosleep               sys_nanosleep                   compat_sys_nanosleep
+163  common     mremap                  sys_mremap                      compat_sys_mremap
+164  32         setresuid               -                               compat_sys_s390_setresuid16
+165  32         getresuid               -                               compat_sys_s390_getresuid16
+167  common     query_module            -                               -
+168  common     poll                    sys_poll                        compat_sys_poll
+169  common     nfsservctl              -                               -
+170  32         setresgid               -                               compat_sys_s390_setresgid16
+171  32         getresgid               -                               compat_sys_s390_getresgid16
+172  common     prctl                   sys_prctl                       compat_sys_prctl
+173  common     rt_sigreturn            sys_rt_sigreturn                compat_sys_rt_sigreturn
+174  common     rt_sigaction            sys_rt_sigaction                compat_sys_rt_sigaction
+175  common     rt_sigprocmask          sys_rt_sigprocmask              compat_sys_rt_sigprocmask
+176  common     rt_sigpending           sys_rt_sigpending               compat_sys_rt_sigpending
+177  common     rt_sigtimedwait         sys_rt_sigtimedwait             compat_sys_rt_sigtimedwait
+178  common     rt_sigqueueinfo         sys_rt_sigqueueinfo             compat_sys_rt_sigqueueinfo
+179  common     rt_sigsuspend           sys_rt_sigsuspend               compat_sys_rt_sigsuspend
+180  common     pread64                 sys_pread64                     compat_sys_s390_pread64
+181  common     pwrite64                sys_pwrite64                    compat_sys_s390_pwrite64
+182  32         chown                   -                               compat_sys_s390_chown16
+183  common     getcwd                  sys_getcwd                      compat_sys_getcwd
+184  common     capget                  sys_capget                      compat_sys_capget
+185  common     capset                  sys_capset                      compat_sys_capset
+186  common     sigaltstack             sys_sigaltstack                 compat_sys_sigaltstack
+187  common     sendfile                sys_sendfile64                  compat_sys_sendfile
+188  common     getpmsg                 -                               -
+189  common     putpmsg                 -                               -
+190  common     vfork                   sys_vfork                       sys_vfork
+191  32         ugetrlimit              -                               compat_sys_getrlimit
+191  64         getrlimit               sys_getrlimit                   -
+192  32         mmap2                   -                               compat_sys_s390_mmap2
+193  32         truncate64              -                               compat_sys_s390_truncate64
+194  32         ftruncate64             -                               compat_sys_s390_ftruncate64
+195  32         stat64                  -                               compat_sys_s390_stat64
+196  32         lstat64                 -                               compat_sys_s390_lstat64
+197  32         fstat64                 -                               compat_sys_s390_fstat64
+198  32         lchown32                -                               compat_sys_lchown
+198  64         lchown                  sys_lchown                      -
+199  32         getuid32                -                               sys_getuid
+199  64         getuid                  sys_getuid                      -
+200  32         getgid32                -                               sys_getgid
+200  64         getgid                  sys_getgid                      -
+201  32         geteuid32               -                               sys_geteuid
+201  64         geteuid                 sys_geteuid                     -
+202  32         getegid32               -                               sys_getegid
+202  64         getegid                 sys_getegid                     -
+203  32         setreuid32              -                               sys_setreuid
+203  64         setreuid                sys_setreuid                    -
+204  32         setregid32              -                               sys_setregid
+204  64         setregid                sys_setregid                    -
+205  32         getgroups32             -                               compat_sys_getgroups
+205  64         getgroups               sys_getgroups                   -
+206  32         setgroups32             -                               compat_sys_setgroups
+206  64         setgroups               sys_setgroups                   -
+207  32         fchown32                -                               sys_fchown
+207  64         fchown                  sys_fchown                      -
+208  32         setresuid32             -                               sys_setresuid
+208  64         setresuid               sys_setresuid                   -
+209  32         getresuid32             -                               compat_sys_getresuid
+209  64         getresuid               sys_getresuid                   -
+210  32         setresgid32             -                               sys_setresgid
+210  64         setresgid               sys_setresgid                   -
+211  32         getresgid32             -                               compat_sys_getresgid
+211  64         getresgid               sys_getresgid                   -
+212  32         chown32                 -                               compat_sys_chown
+212  64         chown                   sys_chown                       -
+213  32         setuid32                -                               sys_setuid
+213  64         setuid                  sys_setuid                      -
+214  32         setgid32                -                               sys_setgid
+214  64         setgid                  sys_setgid                      -
+215  32         setfsuid32              -                               sys_setfsuid
+215  64         setfsuid                sys_setfsuid                    -
+216  32         setfsgid32              -                               sys_setfsgid
+216  64         setfsgid                sys_setfsgid                    -
+217  common     pivot_root              sys_pivot_root                  compat_sys_pivot_root
+218  common     mincore                 sys_mincore                     compat_sys_mincore
+219  common     madvise                 sys_madvise                     compat_sys_madvise
+220  common     getdents64              sys_getdents64                  compat_sys_getdents64
+221  32         fcntl64                 -                               compat_sys_fcntl64
+222  common     readahead               sys_readahead                   compat_sys_s390_readahead
+223  32         sendfile64              -                               compat_sys_sendfile64
+224  common     setxattr                sys_setxattr                    compat_sys_setxattr
+225  common     lsetxattr               sys_lsetxattr                   compat_sys_lsetxattr
+226  common     fsetxattr               sys_fsetxattr                   compat_sys_fsetxattr
+227  common     getxattr                sys_getxattr                    compat_sys_getxattr
+228  common     lgetxattr               sys_lgetxattr                   compat_sys_lgetxattr
+229  common     fgetxattr               sys_fgetxattr                   compat_sys_fgetxattr
+230  common     listxattr               sys_listxattr                   compat_sys_listxattr
+231  common     llistxattr              sys_llistxattr                  compat_sys_llistxattr
+232  common     flistxattr              sys_flistxattr                  compat_sys_flistxattr
+233  common     removexattr             sys_removexattr                 compat_sys_removexattr
+234  common     lremovexattr            sys_lremovexattr                compat_sys_lremovexattr
+235  common     fremovexattr            sys_fremovexattr                compat_sys_fremovexattr
+236  common     gettid                  sys_gettid                      sys_gettid
+237  common     tkill                   sys_tkill                       sys_tkill
+238  common     futex                   sys_futex                       compat_sys_futex
+239  common     sched_setaffinity       sys_sched_setaffinity           compat_sys_sched_setaffinity
+240  common     sched_getaffinity       sys_sched_getaffinity           compat_sys_sched_getaffinity
+241  common     tgkill                  sys_tgkill                      sys_tgkill
+243  common     io_setup                sys_io_setup                    compat_sys_io_setup
+244  common     io_destroy              sys_io_destroy                  compat_sys_io_destroy
+245  common     io_getevents            sys_io_getevents                compat_sys_io_getevents
+246  common     io_submit               sys_io_submit                   compat_sys_io_submit
+247  common     io_cancel               sys_io_cancel                   compat_sys_io_cancel
+248  common     exit_group              sys_exit_group                  sys_exit_group
+249  common     epoll_create            sys_epoll_create                sys_epoll_create
+250  common     epoll_ctl               sys_epoll_ctl                   compat_sys_epoll_ctl
+251  common     epoll_wait              sys_epoll_wait                  compat_sys_epoll_wait
+252  common     set_tid_address         sys_set_tid_address             compat_sys_set_tid_address
+253  common     fadvise64               sys_fadvise64_64                compat_sys_s390_fadvise64
+254  common     timer_create            sys_timer_create                compat_sys_timer_create
+255  common     timer_settime           sys_timer_settime               compat_sys_timer_settime
+256  common     timer_gettime           sys_timer_gettime               compat_sys_timer_gettime
+257  common     timer_getoverrun        sys_timer_getoverrun            sys_timer_getoverrun
+258  common     timer_delete            sys_timer_delete                sys_timer_delete
+259  common     clock_settime           sys_clock_settime               compat_sys_clock_settime
+260  common     clock_gettime           sys_clock_gettime               compat_sys_clock_gettime
+261  common     clock_getres            sys_clock_getres                compat_sys_clock_getres
+262  common     clock_nanosleep         sys_clock_nanosleep             compat_sys_clock_nanosleep
+264  32         fadvise64_64            -                               compat_sys_s390_fadvise64_64
+265  common     statfs64                sys_statfs64                    compat_sys_statfs64
+266  common     fstatfs64               sys_fstatfs64                   compat_sys_fstatfs64
+267  common     remap_file_pages        sys_remap_file_pages            compat_sys_remap_file_pages
+268  common     mbind                   sys_mbind                       compat_sys_mbind
+269  common     get_mempolicy           sys_get_mempolicy               compat_sys_get_mempolicy
+270  common     set_mempolicy           sys_set_mempolicy               compat_sys_set_mempolicy
+271  common     mq_open                 sys_mq_open                     compat_sys_mq_open
+272  common     mq_unlink               sys_mq_unlink                   compat_sys_mq_unlink
+273  common     mq_timedsend            sys_mq_timedsend                compat_sys_mq_timedsend
+274  common     mq_timedreceive         sys_mq_timedreceive             compat_sys_mq_timedreceive
+275  common     mq_notify               sys_mq_notify                   compat_sys_mq_notify
+276  common     mq_getsetattr           sys_mq_getsetattr               compat_sys_mq_getsetattr
+277  common     kexec_load              sys_kexec_load                  compat_sys_kexec_load
+278  common     add_key                 sys_add_key                     compat_sys_add_key
+279  common     request_key             sys_request_key                 compat_sys_request_key
+280  common     keyctl                  sys_keyctl                      compat_sys_keyctl
+281  common     waitid                  sys_waitid                      compat_sys_waitid
+282  common     ioprio_set              sys_ioprio_set                  sys_ioprio_set
+283  common     ioprio_get              sys_ioprio_get                  sys_ioprio_get
+284  common     inotify_init            sys_inotify_init                sys_inotify_init
+285  common     inotify_add_watch       sys_inotify_add_watch           compat_sys_inotify_add_watch
+286  common     inotify_rm_watch        sys_inotify_rm_watch            sys_inotify_rm_watch
+287  common     migrate_pages           sys_migrate_pages               compat_sys_migrate_pages
+288  common     openat                  sys_openat                      compat_sys_openat
+289  common     mkdirat                 sys_mkdirat                     compat_sys_mkdirat
+290  common     mknodat                 sys_mknodat                     compat_sys_mknodat
+291  common     fchownat                sys_fchownat                    compat_sys_fchownat
+292  common     futimesat               sys_futimesat                   compat_sys_futimesat
+293  32         fstatat64               -                               compat_sys_s390_fstatat64
+293  64         newfstatat              sys_newfstatat                  -
+294  common     unlinkat                sys_unlinkat                    compat_sys_unlinkat
+295  common     renameat                sys_renameat                    compat_sys_renameat
+296  common     linkat                  sys_linkat                      compat_sys_linkat
+297  common     symlinkat               sys_symlinkat                   compat_sys_symlinkat
+298  common     readlinkat              sys_readlinkat                  compat_sys_readlinkat
+299  common     fchmodat                sys_fchmodat                    compat_sys_fchmodat
+300  common     faccessat               sys_faccessat                   compat_sys_faccessat
+301  common     pselect6                sys_pselect6                    compat_sys_pselect6
+302  common     ppoll                   sys_ppoll                       compat_sys_ppoll
+303  common     unshare                 sys_unshare                     compat_sys_unshare
+304  common     set_robust_list         sys_set_robust_list             compat_sys_set_robust_list
+305  common     get_robust_list         sys_get_robust_list             compat_sys_get_robust_list
+306  common     splice                  sys_splice                      compat_sys_splice
+307  common     sync_file_range         sys_sync_file_range             compat_sys_s390_sync_file_range
+308  common     tee                     sys_tee                         compat_sys_tee
+309  common     vmsplice                sys_vmsplice                    compat_sys_vmsplice
+310  common     move_pages              sys_move_pages                  compat_sys_move_pages
+311  common     getcpu                  sys_getcpu                      compat_sys_getcpu
+312  common     epoll_pwait             sys_epoll_pwait                 compat_sys_epoll_pwait
+313  common     utimes                  sys_utimes                      compat_sys_utimes
+314  common     fallocate               sys_fallocate                   compat_sys_s390_fallocate
+315  common     utimensat               sys_utimensat                   compat_sys_utimensat
+316  common     signalfd                sys_signalfd                    compat_sys_signalfd
+317  common     timerfd                 -                               -
+318  common     eventfd                 sys_eventfd                     sys_eventfd
+319  common     timerfd_create          sys_timerfd_create              sys_timerfd_create
+320  common     timerfd_settime         sys_timerfd_settime             compat_sys_timerfd_settime
+321  common     timerfd_gettime         sys_timerfd_gettime             compat_sys_timerfd_gettime
+322  common     signalfd4               sys_signalfd4                   compat_sys_signalfd4
+323  common     eventfd2                sys_eventfd2                    sys_eventfd2
+324  common     inotify_init1           sys_inotify_init1               sys_inotify_init1
+325  common     pipe2                   sys_pipe2                       compat_sys_pipe2
+326  common     dup3                    sys_dup3                        sys_dup3
+327  common     epoll_create1           sys_epoll_create1               sys_epoll_create1
+328  common     preadv                  sys_preadv                      compat_sys_preadv
+329  common     pwritev                 sys_pwritev                     compat_sys_pwritev
+330  common     rt_tgsigqueueinfo       sys_rt_tgsigqueueinfo           compat_sys_rt_tgsigqueueinfo
+331  common     perf_event_open         sys_perf_event_open             compat_sys_perf_event_open
+332  common     fanotify_init           sys_fanotify_init               sys_fanotify_init
+333  common     fanotify_mark           sys_fanotify_mark               compat_sys_fanotify_mark
+334  common     prlimit64               sys_prlimit64                   compat_sys_prlimit64
+335  common     name_to_handle_at       sys_name_to_handle_at           compat_sys_name_to_handle_at
+336  common     open_by_handle_at       sys_open_by_handle_at           compat_sys_open_by_handle_at
+337  common     clock_adjtime           sys_clock_adjtime               compat_sys_clock_adjtime
+338  common     syncfs                  sys_syncfs                      sys_syncfs
+339  common     setns                   sys_setns                       sys_setns
+340  common     process_vm_readv        sys_process_vm_readv            compat_sys_process_vm_readv
+341  common     process_vm_writev       sys_process_vm_writev           compat_sys_process_vm_writev
+342  common     s390_runtime_instr      sys_s390_runtime_instr          sys_s390_runtime_instr
+343  common     kcmp                    sys_kcmp                        compat_sys_kcmp
+344  common     finit_module            sys_finit_module                compat_sys_finit_module
+345  common     sched_setattr           sys_sched_setattr               compat_sys_sched_setattr
+346  common     sched_getattr           sys_sched_getattr               compat_sys_sched_getattr
+347  common     renameat2               sys_renameat2                   compat_sys_renameat2
+348  common     seccomp                 sys_seccomp                     compat_sys_seccomp
+349  common     getrandom               sys_getrandom                   compat_sys_getrandom
+350  common     memfd_create            sys_memfd_create                compat_sys_memfd_create
+351  common     bpf                     sys_bpf                         compat_sys_bpf
+352  common     s390_pci_mmio_write     sys_s390_pci_mmio_write         compat_sys_s390_pci_mmio_write
+353  common     s390_pci_mmio_read      sys_s390_pci_mmio_read          compat_sys_s390_pci_mmio_read
+354  common     execveat                sys_execveat                    compat_sys_execveat
+355  common     userfaultfd             sys_userfaultfd                 sys_userfaultfd
+356  common     membarrier              sys_membarrier                  sys_membarrier
+357  common     recvmmsg                sys_recvmmsg                    compat_sys_recvmmsg
+358  common     sendmmsg                sys_sendmmsg                    compat_sys_sendmmsg
+359  common     socket                  sys_socket                      sys_socket
+360  common     socketpair              sys_socketpair                  compat_sys_socketpair
+361  common     bind                    sys_bind                        compat_sys_bind
+362  common     connect                 sys_connect                     compat_sys_connect
+363  common     listen                  sys_listen                      sys_listen
+364  common     accept4                 sys_accept4                     compat_sys_accept4
+365  common     getsockopt              sys_getsockopt                  compat_sys_getsockopt
+366  common     setsockopt              sys_setsockopt                  compat_sys_setsockopt
+367  common     getsockname             sys_getsockname                 compat_sys_getsockname
+368  common     getpeername             sys_getpeername                 compat_sys_getpeername
+369  common     sendto                  sys_sendto                      compat_sys_sendto
+370  common     sendmsg                 sys_sendmsg                     compat_sys_sendmsg
+371  common     recvfrom                sys_recvfrom                    compat_sys_recvfrom
+372  common     recvmsg                 sys_recvmsg                     compat_sys_recvmsg
+373  common     shutdown                sys_shutdown                    sys_shutdown
+374  common     mlock2                  sys_mlock2                      compat_sys_mlock2
+375  common     copy_file_range         sys_copy_file_range             compat_sys_copy_file_range
+376  common     preadv2                 sys_preadv2                     compat_sys_preadv2
+377  common     pwritev2                sys_pwritev2                    compat_sys_pwritev2
+378  common     s390_guarded_storage    sys_s390_guarded_storage        compat_sys_s390_guarded_storage
+379  common     statx                   sys_statx                       compat_sys_statx
+380  common     s390_sthyi              sys_s390_sthyi                  compat_sys_s390_sthyi
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 c0815a37fdb5..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);
 
@@ -2245,7 +2368,7 @@ static int perf_c2c__browse_cacheline(struct hist_entry *he)
         c2c_browser__update_nr_entries(browser);
 
         while (1) {
-                key = hist_browser__run(browser, "? - help");
+                key = hist_browser__run(browser, "? - help", true);
 
                 switch (key) {
                 case 's':
@@ -2314,7 +2437,7 @@ static int perf_c2c__hists_browse(struct hists *hists)
         c2c_browser__update_nr_entries(browser);
 
         while (1) {
-                key = hist_browser__run(browser, "? - help");
+                key = hist_browser__run(browser, "? - help", true);
 
                 switch (key) {
                 case 'q':
@@ -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 bf4ca749d1ac..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);
@@ -881,6 +905,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
                 }
         }
 
+        /*
+         * If we have just single event and are sending data
+         * through pipe, we need to force the ids allocation,
+         * because we synthesize event name through the pipe
+         * and need the id for that.
+         */
+        if (data->is_pipe && rec->evlist->nr_entries == 1)
+                rec->opts.sample_id = true;
+
         if (record__open(rec) != 0) {
                 err = -1;
                 goto out_child;
@@ -926,8 +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;
@@ -955,6 +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;
 
@@ -1251,10 +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 {
@@ -1542,7 +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),
@@ -1651,6 +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);
@@ -1711,17 +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().
@@ -1730,7 +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;
 
@@ -1803,7 +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 42a52dcc41cd..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);
@@ -530,7 +572,8 @@ static int report__browse_hists(struct report *rep)
         case 1:
                 ret = perf_evlist__tui_browse_hists(evlist, help, NULL,
                                                     rep->min_percent,
-                                                    &session->header.env);
+                                                    &session->header.env,
+                                                    true);
                 /*
                  * Usually "ret" is the last pressed key, and we only
                  * care if the key notifies us to switch data file.
@@ -613,6 +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;
@@ -953,7 +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,
                 },
@@ -974,6 +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"),
@@ -1055,7 +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",
@@ -1172,6 +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;
 
@@ -1294,6 +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)
@@ -1331,6 +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 98bf9d32f222..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;
+                        }
                 }
         }
 
@@ -917,7 +943,7 @@ static void print_metric_csv(void *ctx,
         char buf[64], *vals, *ends;
 
         if (unit == NULL || fmt == NULL) {
-                fprintf(out, "%s%s%s%s", csv_sep, csv_sep, csv_sep, csv_sep);
+                fprintf(out, "%s%s", csv_sep, csv_sep);
                 return;
         }
         snprintf(buf, sizeof(buf), fmt, val);
@@ -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 c6ccda52117d..f39bd60d2708 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -283,8 +283,9 @@ static void perf_top__print_sym_table(struct perf_top *top)
 
         printf("%-*.*s\n", win_width, win_width, graph_dotted_line);
 
-        if (hists->stats.nr_lost_warned !=
-            hists->stats.nr_events[PERF_RECORD_LOST]) {
+        if (!top->record_opts.overwrite &&
+            (hists->stats.nr_lost_warned !=
+            hists->stats.nr_events[PERF_RECORD_LOST])) {
                 hists->stats.nr_lost_warned =
                               hists->stats.nr_events[PERF_RECORD_LOST];
                 color_fprintf(stdout, PERF_COLOR_RED,
@@ -611,7 +612,8 @@ static void *display_thread_tui(void *arg)
 
         perf_evlist__tui_browse_hists(top->evlist, help, &hbt,
                                       top->min_percent,
-                                      &top->session->header.env);
+                                      &top->session->header.env,
+                                      !top->record_opts.overwrite);
 
         done = 1;
         return NULL;
@@ -807,15 +809,22 @@ static void perf_event__process_sample(struct perf_tool *tool,
 
 static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
 {
+        struct record_opts *opts = &top->record_opts;
+        struct perf_evlist *evlist = top->evlist;
         struct perf_sample sample;
         struct perf_evsel *evsel;
+        struct perf_mmap *md;
         struct perf_session *session = top->session;
         union perf_event *event;
         struct machine *machine;
         int ret;
 
-        while ((event = perf_evlist__mmap_read(top->evlist, idx)) != NULL) {
-                ret = perf_evlist__parse_sample(top->evlist, event, &sample);
+        md = opts->overwrite ? &evlist->overwrite_mmap[idx] : &evlist->mmap[idx];
+        if (perf_mmap__read_init(md) < 0)
+                return;
+
+        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);
                         goto next_event;
@@ -869,16 +878,120 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
                 } else
                         ++session->evlist->stats.nr_unknown_events;
 next_event:
-                perf_evlist__mmap_consume(top->evlist, idx);
+                perf_mmap__consume(md);
         }
+
+        perf_mmap__read_done(md);
 }
 
 static void perf_top__mmap_read(struct perf_top *top)
 {
+        bool overwrite = top->record_opts.overwrite;
+        struct perf_evlist *evlist = top->evlist;
+        unsigned long long start, end;
         int i;
 
+        start = rdclock();
+        if (overwrite)
+                perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_DATA_PENDING);
+
         for (i = 0; i < top->evlist->nr_mmaps; i++)
                 perf_top__mmap_read_idx(top, i);
+
+        if (overwrite) {
+                perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_EMPTY);
+                perf_evlist__toggle_bkw_mmap(evlist, BKW_MMAP_RUNNING);
+        }
+        end = rdclock();
+
+        if ((end - start) > (unsigned long long)top->delay_secs * NSEC_PER_SEC)
+                ui__warning("Too slow to read ring buffer.\n"
+                            "Please try increasing the period (-c) or\n"
+                            "decreasing the freq (-F) or\n"
+                            "limiting the number of CPUs (-C)\n");
+}
+
+/*
+ * Check per-event overwrite term.
+ * perf top should support consistent term for all events.
+ * - All events don't have per-event term
+ *   E.g. "cpu/cpu-cycles/,cpu/instructions/"
+ *   Nothing change, return 0.
+ * - All events have same per-event term
+ *   E.g. "cpu/cpu-cycles,no-overwrite/,cpu/instructions,no-overwrite/
+ *   Using the per-event setting to replace the opts->overwrite if
+ *   they are different, then return 0.
+ * - Events have different per-event term
+ *   E.g. "cpu/cpu-cycles,overwrite/,cpu/instructions,no-overwrite/"
+ *   Return -1
+ * - Some of the event set per-event term, but some not.
+ *   E.g. "cpu/cpu-cycles/,cpu/instructions,no-overwrite/"
+ *   Return -1
+ */
+static int perf_top__overwrite_check(struct perf_top *top)
+{
+        struct record_opts *opts = &top->record_opts;
+        struct perf_evlist *evlist = top->evlist;
+        struct perf_evsel_config_term *term;
+        struct list_head *config_terms;
+        struct perf_evsel *evsel;
+        int set, overwrite = -1;
+
+        evlist__for_each_entry(evlist, evsel) {
+                set = -1;
+                config_terms = &evsel->config_terms;
+                list_for_each_entry(term, config_terms, list) {
+                        if (term->type == PERF_EVSEL__CONFIG_TERM_OVERWRITE)
+                                set = term->val.overwrite ? 1 : 0;
+                }
+
+                /* no term for current and previous event (likely) */
+                if ((overwrite < 0) && (set < 0))
+                        continue;
+
+                /* has term for both current and previous event, compare */
+                if ((overwrite >= 0) && (set >= 0) && (overwrite != set))
+                        return -1;
+
+                /* no term for current event but has term for previous one */
+                if ((overwrite >= 0) && (set < 0))
+                        return -1;
+
+                /* has term for current event */
+                if ((overwrite < 0) && (set >= 0)) {
+                        /* if it's first event, set overwrite */
+                        if (evsel == perf_evlist__first(evlist))
+                                overwrite = set;
+                        else
+                                return -1;
+                }
+        }
+
+        if ((overwrite >= 0) && (opts->overwrite != overwrite))
+                opts->overwrite = overwrite;
+
+        return 0;
+}
+
+static int perf_top_overwrite_fallback(struct perf_top *top,
+                                       struct perf_evsel *evsel)
+{
+        struct record_opts *opts = &top->record_opts;
+        struct perf_evlist *evlist = top->evlist;
+        struct perf_evsel *counter;
+
+        if (!opts->overwrite)
+                return 0;
+
+        /* only fall back when first event fails */
+        if (evsel != perf_evlist__first(evlist))
+                return 0;
+
+        evlist__for_each_entry(evlist, counter)
+                counter->attr.write_backward = false;
+        opts->overwrite = false;
+        pr_debug2("fall back to non-overwrite mode\n");
+        return 1;
 }
 
 static int perf_top__start_counters(struct perf_top *top)
@@ -888,12 +1001,33 @@ static int perf_top__start_counters(struct perf_top *top)
         struct perf_evlist *evlist = top->evlist;
         struct record_opts *opts = &top->record_opts;
 
+        if (perf_top__overwrite_check(top)) {
+                ui__error("perf top only support consistent per-event "
+                          "overwrite setting for all events\n");
+                goto out_err;
+        }
+
         perf_evlist__config(evlist, opts, &callchain_param);
 
         evlist__for_each_entry(evlist, counter) {
 try_again:
                 if (perf_evsel__open(counter, top->evlist->cpus,
                                      top->evlist->threads) < 0) {
+
+                        /*
+                         * Specially handle overwrite fall back.
+                         * Because perf top is the only tool which has
+                         * overwrite mode by default, support
+                         * both overwrite and non-overwrite mode, and
+                         * require consistent mode for all events.
+                         *
+                         * May move it to generic code with more tools
+                         * have similar attribute.
+                         */
+                        if (perf_missing_features.write_backward &&
+                            perf_top_overwrite_fallback(top, counter))
+                                goto try_again;
+
                         if (perf_evsel__fallback(counter, errno, msg, sizeof(msg))) {
                                 if (verbose > 0)
                                         ui__warning("%s\n", msg);
@@ -1033,7 +1167,7 @@ static int __cmd_top(struct perf_top *top)
 
                 perf_top__mmap_read(top);
 
-                if (hits == top->samples)
+                if (opts->overwrite || (hits == top->samples))
                         ret = perf_evlist__poll(top->evlist, 100);
 
                 if (resize) {
@@ -1089,8 +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;
@@ -1127,6 +1263,7 @@ int cmd_top(int argc, const char **argv)
                                 .uses_mmap   = true,
                         },
                         .proc_map_timeout    = 500,
+                        .overwrite      = 1,
                 },
                 .max_stack           = sysctl_perf_event_max_stack,
                 .sym_pcnt_filter     = 5,
@@ -1171,7 +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,
@@ -1354,6 +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 51abdb0a4047..9aff89bc7535 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -33,7 +33,6 @@ arch/s390/include/uapi/asm/kvm.h
 arch/s390/include/uapi/asm/kvm_perf.h
 arch/s390/include/uapi/asm/ptrace.h
 arch/s390/include/uapi/asm/sie.h
-arch/s390/include/uapi/asm/unistd.h
 arch/arm/include/uapi/asm/kvm.h
 arch/arm64/include/uapi/asm/kvm.h
 arch/alpha/include/uapi/asm/errno.h
@@ -43,6 +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
@@ -59,6 +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 cfe46236a5e5..8fec1abd0f1f 100644
--- a/tools/perf/perf.h
+++ b/tools/perf/perf.h
@@ -61,6 +61,8 @@ 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;
         unsigned int auxtrace_mmap_pages;
@@ -82,4 +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/arm/cortex-a53/branch.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/branch.json
new file mode 100644
index 000000000000..0b0e6b26605b
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/branch.json
@@ -0,0 +1,25 @@
+[
+  {
+    "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/arm/cortex-a53/memory.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/memory.json
new file mode 100644
index 000000000000..25ae642ba381
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/memory.json
@@ -0,0 +1,12 @@
+[
+  {
+    "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/arm/cortex-a53/pipeline.json b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/pipeline.json
new file mode 100644
index 000000000000..f45a6b5d0025
--- /dev/null
+++ b/tools/perf/pmu-events/arch/arm64/arm/cortex-a53/pipeline.json
@@ -0,0 +1,52 @@
+[
+  {
+    "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/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 219d6756134e..f03e26ecb658 100644
--- a/tools/perf/pmu-events/arch/arm64/mapfile.csv
+++ b/tools/perf/pmu-events/arch/arm64/mapfile.csv
@@ -12,4 +12,7 @@
 #
 #
 #Family-model,Version,Filename,EventType
-0x00000000420f5160,v1,cavium,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 4035d43523c3..6d598cc071ae 100644
--- a/tools/perf/tests/backward-ring-buffer.c
+++ b/tools/perf/tests/backward-ring-buffer.c
@@ -31,10 +31,11 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count,
         int i;
 
         for (i = 0; i < evlist->nr_mmaps; i++) {
+                struct perf_mmap *map = &evlist->overwrite_mmap[i];
                 union perf_event *event;
 
-                perf_mmap__read_catchup(&evlist->overwrite_mmap[i]);
-                while ((event = perf_mmap__read_backward(&evlist->overwrite_mmap[i])) != NULL) {
+                perf_mmap__read_init(map);
+                while ((event = perf_mmap__read_event(map)) != NULL) {
                         const u32 type = event->header.type;
 
                         switch (type) {
@@ -49,6 +50,7 @@ static int count_samples(struct perf_evlist *evlist, int *sample_count,
                                 return TEST_FAIL;
                         }
                 }
+                perf_mmap__read_done(map);
         }
         return TEST_OK;
 }
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 8b3da21a08f1..1ecc1f0ff84a 100755
--- a/tools/perf/tests/shell/trace+probe_libc_inet_pton.sh
+++ b/tools/perf/tests/shell/record+probe_libc_inet_pton.sh
@@ -15,17 +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[7]="getaddrinfo[[:space:]]\($libc\)$"
-        expected[8]=".*\(.*/bin/ping.*\)$"
-
-        perf trace --no-syscalls -e probe_libc:inet_pton/max-stack=3/ ping -6 -c 1 ::1 2>&1 | grep -v ^$ | while read line ; do
+        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[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[2]="getaddrinfo[[:space:]]\($libc\)$"
+                expected[3]=".*\(.*/bin/ping.*\)$"
+                ;;
+        esac
+
+        file=`mktemp -u /tmp/perf.data.XXX`
+
+        perf record -e probe_libc:inet_pton/$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
@@ -33,8 +44,13 @@ trace_libc_inet_pton_backtrace() {
                         exit 1
                 fi
                 let idx+=1
-                [ $idx -eq 9 ] && break
+                [ -z "${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 286427975112..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);
@@ -314,39 +144,65 @@ 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;
 
-        target = ab->offsets[cursor->ops.target.offset];
-
-        bcursor = browser_line(&cursor->al);
-        btarget = browser_line(target);
+        /*
+         * This first was seen with a gcc function, _cpp_lex_token, that
+         * has the usual jumps:
+         *
+         *  │1159e6c: ↓ jne    115aa32 <_cpp_lex_token@@Base+0xf92>
+         *
+         * I.e. jumps to a label inside that function (_cpp_lex_token), and
+         * those works, but also this kind:
+         *
+         *  │1159e8b: ↓ jne    c469be <cpp_named_operator2name@@Base+0xa72>
+         *
+         *  I.e. jumps to another function, outside _cpp_lex_token, which
+         *  are not being correctly handled generating as a side effect references
+         *  to ab->offset[] entries that are set to NULL, so to make this code
+         *  more robust, check that here.
+         *
+         *  A proper fix for will be put in place, looking at the function
+         *  name right after the '<' token and probably treating this like a
+         *  'call' instruction.
+         */
+        target = notes->offsets[cursor->ops.target.offset];
+        if (target == NULL) {
+                ui_helpline__printf("WARN: jump target inconsistency, press 'o', notes->offsets[%#x] = NULL\n",
+                                    cursor->ops.target.offset);
+                return;
+        }
 
-        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);
         }
@@ -354,11 +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);
@@ -400,6 +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);
@@ -409,7 +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;
@@ -423,16 +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;
+        struct annotation *notes = browser__annotation(&browser->b);
+        struct annotation_line * pos = rb_entry(nd, struct annotation_line, rb_node);
+        u32 idx = pos->idx;
 
-        pos = rb_entry(nd, struct annotation_line, rb_node);
-        bpos = browser_line(pos);
-
-        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;
 }
@@ -480,47 +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)
@@ -531,6 +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)
@@ -538,35 +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;
@@ -576,23 +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;
@@ -601,6 +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) {
@@ -617,14 +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;
@@ -656,14 +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;
@@ -739,19 +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)
@@ -759,6 +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;
@@ -833,6 +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;
@@ -842,8 +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;
@@ -853,15 +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)) {
@@ -887,7 +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:
@@ -903,22 +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:
@@ -940,12 +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);
 }
 
@@ -959,129 +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,
@@ -1097,26 +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));
@@ -1124,110 +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 68146f4620a5..8b4e82548f8e 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -608,7 +608,8 @@ static int hist_browser__title(struct hist_browser *browser, char *bf, size_t si
         return browser->title ? browser->title(browser, bf, size) : 0;
 }
 
-int hist_browser__run(struct hist_browser *browser, const char *help)
+int hist_browser__run(struct hist_browser *browser, const char *help,
+                      bool warn_lost_event)
 {
         int key;
         char title[160];
@@ -638,8 +639,9 @@ int hist_browser__run(struct hist_browser *browser, const char *help)
                         nr_entries = hist_browser__nr_entries(browser);
                         ui_browser__update_nr_entries(&browser->b, nr_entries);
 
-                        if (browser->hists->stats.nr_lost_warned !=
-                            browser->hists->stats.nr_events[PERF_RECORD_LOST]) {
+                        if (warn_lost_event &&
+                            (browser->hists->stats.nr_lost_warned !=
+                            browser->hists->stats.nr_events[PERF_RECORD_LOST])) {
                                 browser->hists->stats.nr_lost_warned =
                                         browser->hists->stats.nr_events[PERF_RECORD_LOST];
                                 ui_browser__warn_lost_events(&browser->b);
@@ -2221,7 +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;
@@ -2253,10 +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)
@@ -2763,7 +2770,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
                                     bool left_exits,
                                     struct hist_browser_timer *hbt,
                                     float min_pcnt,
-                                    struct perf_env *env)
+                                    struct perf_env *env,
+                                    bool warn_lost_event)
 {
         struct hists *hists = evsel__hists(evsel);
         struct hist_browser *browser = perf_evsel_browser__new(evsel, hbt, env);
@@ -2844,7 +2852,8 @@ static int perf_evsel__hists_browse(struct perf_evsel *evsel, int nr_events,
 
                 nr_options = 0;
 
-                key = hist_browser__run(browser, helpline);
+                key = hist_browser__run(browser, helpline,
+                                        warn_lost_event);
 
                 if (browser->he_selection != NULL) {
                         thread = hist_browser__selected_thread(browser);
@@ -3184,7 +3193,8 @@ static void perf_evsel_menu__write(struct ui_browser *browser,
 
 static int perf_evsel_menu__run(struct perf_evsel_menu *menu,
                                 int nr_events, const char *help,
-                                struct hist_browser_timer *hbt)
+                                struct hist_browser_timer *hbt,
+                                bool warn_lost_event)
 {
         struct perf_evlist *evlist = menu->b.priv;
         struct perf_evsel *pos;
@@ -3203,7 +3213,9 @@ static int perf_evsel_menu__run(struct perf_evsel_menu *menu,
                 case K_TIMER:
                         hbt->timer(hbt->arg);
 
-                        if (!menu->lost_events_warned && menu->lost_events) {
+                        if (!menu->lost_events_warned &&
+                            menu->lost_events &&
+                            warn_lost_event) {
                                 ui_browser__warn_lost_events(&menu->b);
                                 menu->lost_events_warned = true;
                         }
@@ -3224,7 +3236,8 @@ browse_hists:
                         key = perf_evsel__hists_browse(pos, nr_events, help,
                                                        true, hbt,
                                                        menu->min_pcnt,
-                                                       menu->env);
+                                                       menu->env,
+                                                       warn_lost_event);
                         ui_browser__show_title(&menu->b, title);
                         switch (key) {
                         case K_TAB:
@@ -3282,7 +3295,8 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
                                            int nr_entries, const char *help,
                                            struct hist_browser_timer *hbt,
                                            float min_pcnt,
-                                           struct perf_env *env)
+                                           struct perf_env *env,
+                                           bool warn_lost_event)
 {
         struct perf_evsel *pos;
         struct perf_evsel_menu menu = {
@@ -3309,13 +3323,15 @@ static int __perf_evlist__tui_browse_hists(struct perf_evlist *evlist,
                         menu.b.width = line_len;
         }
 
-        return perf_evsel_menu__run(&menu, nr_entries, help, hbt);
+        return perf_evsel_menu__run(&menu, nr_entries, help,
+                                    hbt, warn_lost_event);
 }
 
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
                                   struct hist_browser_timer *hbt,
                                   float min_pcnt,
-                                  struct perf_env *env)
+                                  struct perf_env *env,
+                                  bool warn_lost_event)
 {
         int nr_entries = evlist->nr_entries;
 
@@ -3325,7 +3341,7 @@ single_entry:
 
                 return perf_evsel__hists_browse(first, nr_entries, help,
                                                 false, hbt, min_pcnt,
-                                                env);
+                                                env, warn_lost_event);
         }
 
         if (symbol_conf.event_group) {
@@ -3342,5 +3358,6 @@ single_entry:
         }
 
         return __perf_evlist__tui_browse_hists(evlist, nr_entries, help,
-                                               hbt, min_pcnt, env);
+                                               hbt, min_pcnt, env,
+                                               warn_lost_event);
 }
diff --git a/tools/perf/ui/browsers/hists.h b/tools/perf/ui/browsers/hists.h
index ba431777f559..9428bee076f2 100644
--- a/tools/perf/ui/browsers/hists.h
+++ b/tools/perf/ui/browsers/hists.h
@@ -28,7 +28,8 @@ struct hist_browser {
 
 struct hist_browser *hist_browser__new(struct hists *hists);
 void hist_browser__delete(struct hist_browser *browser);
-int hist_browser__run(struct hist_browser *browser, const char *help);
+int hist_browser__run(struct hist_browser *browser, const char *help,
+                      bool warn_lost_event);
 void hist_browser__init(struct hist_browser *browser,
                         struct hists *hists);
 #endif /* _PERF_UI_BROWSER_HISTS_H_ */
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 9faf3b5367db..fb357a00dd86 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -60,6 +60,12 @@
 #include "sane_ctype.h"
 #include "symbol/kallsyms.h"
 
+static bool auxtrace__dont_decode(struct perf_session *session)
+{
+        return !session->itrace_synth_opts ||
+               session->itrace_synth_opts->dont_decode;
+}
+
 int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
                         struct auxtrace_mmap_params *mp,
                         void *userpg, int fd)
@@ -227,9 +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;
@@ -280,7 +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;
@@ -296,11 +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;
@@ -311,14 +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)
@@ -353,13 +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:
@@ -762,6 +775,9 @@ int auxtrace_queues__process_index(struct auxtrace_queues *queues,
         size_t i;
         int err;
 
+        if (auxtrace__dont_decode(session))
+                return 0;
+
         list_for_each_entry(auxtrace_index, &session->auxtrace_index, list) {
                 for (i = 0; i < auxtrace_index->nr; i++) {
                         ent = &auxtrace_index->entries[i];
@@ -892,12 +908,6 @@ out_free:
         return err;
 }
 
-static bool auxtrace__dont_decode(struct perf_session *session)
-{
-        return !session->itrace_synth_opts ||
-               session->itrace_synth_opts->dont_decode;
-}
-
 int perf_event__process_auxtrace_info(struct perf_tool *tool __maybe_unused,
                                       union perf_event *event,
                                       struct perf_session *session)
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 ac35cd214feb..a59281d64368 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -702,46 +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_backward(struct perf_evlist *evlist, int idx)
-{
-        struct perf_mmap *md = &evlist->mmap[idx];
-
-        /*
-         * No need to check messup for backward ring buffer:
-         * We can always read arbitrary long data from a backward
-         * ring buffer unless we forget to pause it before reading.
-         */
-        return perf_mmap__read_backward(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_read_catchup(struct perf_evlist *evlist, int idx)
-{
-        perf_mmap__read_catchup(&evlist->mmap[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;
@@ -762,7 +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;
@@ -776,9 +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.
                  *
@@ -819,7 +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;
@@ -1069,7 +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;
 
@@ -1103,11 +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 75f8e0ad5d76..6c41b2f78713 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -129,14 +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);
-union perf_event *perf_evlist__mmap_read_backward(struct perf_evlist *evlist,
-                                                  int idx);
-void perf_evlist__mmap_read_catchup(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 ff359c9ece2e..1ac8d9236efd 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -41,17 +41,7 @@
 
 #include "sane_ctype.h"
 
-static struct {
-        bool sample_id_all;
-        bool exclude_guest;
-        bool mmap2;
-        bool cloexec;
-        bool clockid;
-        bool clockid_wrong;
-        bool lbr_flags;
-        bool write_backward;
-        bool group_read;
-} perf_missing_features;
+struct perf_missing_features perf_missing_features;
 
 static clockid_t clockid;
 
@@ -254,6 +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)
@@ -631,22 +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;
 }
@@ -1243,7 +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);
@@ -1925,6 +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 846e41644525..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 {
@@ -149,6 +151,20 @@ union u64_swap {
         u32 val32[2];
 };
 
+struct perf_missing_features {
+        bool sample_id_all;
+        bool exclude_guest;
+        bool mmap2;
+        bool cloexec;
+        bool clockid;
+        bool clockid_wrong;
+        bool lbr_flags;
+        bool write_backward;
+        bool group_read;
+};
+
+extern struct perf_missing_features perf_missing_features;
+
 struct cpu_map;
 struct target;
 struct thread_map;
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 f6630cb95eff..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;
@@ -430,7 +429,8 @@ int hist_entry__tui_annotate(struct hist_entry *he, struct perf_evsel *evsel,
 int perf_evlist__tui_browse_hists(struct perf_evlist *evlist, const char *help,
                                   struct hist_browser_timer *hbt,
                                   float min_pcnt,
-                                  struct perf_env *env);
+                                  struct perf_env *env,
+                                  bool warn_lost_event);
 int script_browse(const char *script_opt);
 #else
 static inline
@@ -438,7 +438,8 @@ int perf_evlist__tui_browse_hists(struct perf_evlist *evlist __maybe_unused,
                                   const char *help __maybe_unused,
                                   struct hist_browser_timer *hbt __maybe_unused,
                                   float min_pcnt __maybe_unused,
-                                  struct perf_env *env __maybe_unused)
+                                  struct perf_env *env __maybe_unused,
+                                  bool warn_lost_event __maybe_unused)
 {
         return 0;
 }
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 05076e683938..fc832676a798 100644
--- a/tools/perf/util/mmap.c
+++ b/tools/perf/util/mmap.c
@@ -22,29 +22,27 @@ size_t perf_mmap__mmap_len(struct perf_mmap *map)
 
 /* When check_messup is true, 'end' must points to a good entry */
 static union perf_event *perf_mmap__read(struct perf_mmap *map,
-                                         u64 start, u64 end, u64 *prev)
+                                         u64 *startp, u64 end)
 {
         unsigned char *data = map->base + page_size;
         union perf_event *event = NULL;
-        int diff = end - start;
+        int diff = end - *startp;
 
         if (diff >= (int)sizeof(event->header)) {
                 size_t size;
 
-                event = (union perf_event *)&data[start & map->mask];
+                event = (union perf_event *)&data[*startp & map->mask];
                 size = event->header.size;
 
-                if (size < sizeof(event->header) || diff < (int)size) {
-                        event = NULL;
-                        goto broken_event;
-                }
+                if (size < sizeof(event->header) || diff < (int)size)
+                        return NULL;
 
                 /*
                  * Event straddles the mmap boundary -- header should always
                  * be inside due to u64 alignment of output.
                  */
-                if ((start & map->mask) + size != ((start + size) & map->mask)) {
-                        unsigned int offset = start;
+                if ((*startp & map->mask) + size != ((*startp + size) & map->mask)) {
+                        unsigned int offset = *startp;
                         unsigned int len = min(sizeof(*event), size), cpy;
                         void *dst = map->event_copy;
 
@@ -59,36 +57,27 @@ static union perf_event *perf_mmap__read(struct perf_mmap *map,
                         event = (union perf_event *)map->event_copy;
                 }
 
-                start += size;
+                *startp += size;
         }
 
-broken_event:
-        if (prev)
-                *prev = start;
-
         return event;
 }
 
-union perf_event *perf_mmap__read_forward(struct perf_mmap *map)
-{
-        u64 head;
-        u64 old = map->prev;
-
-        /*
-         * 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, old, head, &map->prev);
-}
-
-union perf_event *perf_mmap__read_backward(struct perf_mmap *map)
+/*
+ * Read event from ring buffer one by one.
+ * Return one event for each call.
+ *
+ * Usage:
+ * perf_mmap__read_init()
+ * while(event = perf_mmap__read_event()) {
+ *      //process the event
+ *      perf_mmap__consume()
+ * }
+ * perf_mmap__read_done()
+ */
+union perf_event *perf_mmap__read_event(struct perf_mmap *map)
 {
-        u64 head, end;
-        u64 start = map->prev;
+        union perf_event *event;
 
         /*
          * Check if event was unmapped due to a POLLHUP/POLLERR.
@@ -96,40 +85,16 @@ union perf_event *perf_mmap__read_backward(struct perf_mmap *map)
         if (!refcount_read(&map->refcnt))
                 return NULL;
 
-        head = perf_mmap__read_head(map);
-        if (!head)
-                return NULL;
-
-        /*
-         * 'head' pointer starts from 0. Kernel minus sizeof(record) form
-         * it each time when kernel writes to it, so in fact 'head' is
-         * negative. 'end' pointer is made manually by adding the size of
-         * the ring buffer to 'head' pointer, means the validate data can
-         * read is the whole ring buffer. If 'end' is positive, the ring
-         * buffer has not fully filled, so we must adjust 'end' to 0.
-         *
-         * However, since both 'head' and 'end' is unsigned, we can't
-         * simply compare 'end' against 0. Here we compare '-head' and
-         * the size of the ring buffer, where -head is the number of bytes
-         * kernel write to the ring buffer.
-         */
-        if (-head < (u64)(map->mask + 1))
-                end = 0;
-        else
-                end = head + map->mask + 1;
-
-        return perf_mmap__read(map, start, end, &map->prev);
-}
+        /* non-overwirte doesn't pause the ringbuffer */
+        if (!map->overwrite)
+                map->end = perf_mmap__read_head(map);
 
-void perf_mmap__read_catchup(struct perf_mmap *map)
-{
-        u64 head;
+        event = perf_mmap__read(map, &map->start, map->end);
 
-        if (!refcount_read(&map->refcnt))
-                return;
+        if (!map->overwrite)
+                map->prev = map->start;
 
-        head = perf_mmap__read_head(map);
-        map->prev = head;
+        return event;
 }
 
 static bool perf_mmap__empty(struct perf_mmap *map)
@@ -150,9 +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);
@@ -202,7 +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.
          *
@@ -234,19 +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;
@@ -267,45 +231,73 @@ static int overwrite_rb_find_range(void *buf, int mask, u64 head, u64 *start, u6
         return -1;
 }
 
-int perf_mmap__push(struct perf_mmap *md, bool overwrite,
-                    void *to, int push(void *to, void *buf, size_t size))
+/*
+ * Report the start and end of the available data in ringbuffer
+ */
+static int __perf_mmap__read_init(struct perf_mmap *md)
 {
         u64 head = perf_mmap__read_head(md);
         u64 old = md->prev;
-        u64 end = head, start = old;
         unsigned char *data = md->base + page_size;
         unsigned long size;
-        void *buf;
-        int rc = 0;
 
-        start = overwrite ? head : old;
-        end = overwrite ? old : head;
+        md->start = md->overwrite ? head : old;
+        md->end = md->overwrite ? old : head;
 
-        if (start == end)
-                return 0;
+        if (md->start == md->end)
+                return -EAGAIN;
 
-        size = end - start;
+        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);
-                        return 0;
+                        perf_mmap__consume(md);
+                        return -EAGAIN;
                 }
 
                 /*
                  * 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, &start, &end))
-                        return -1;
+                if (overwrite_rb_find_range(data, md->mask, &md->start, &md->end))
+                        return -EINVAL;
         }
 
-        if ((start & md->mask) + size != (end & md->mask)) {
-                buf = &data[start & md->mask];
-                size = md->mask + 1 - (start & md->mask);
-                start += size;
+        return 0;
+}
+
+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);
+        unsigned char *data = md->base + page_size;
+        unsigned long size;
+        void *buf;
+        int rc = 0;
+
+        rc = perf_mmap__read_init(md);
+        if (rc < 0)
+                return (rc == -EAGAIN) ? 0 : -1;
+
+        size = md->end - md->start;
+
+        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;
@@ -313,9 +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;
@@ -323,7 +315,24 @@ 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;
 }
+
+/*
+ * Mandatory for overwrite mode
+ * The direction of overwrite mode is backward.
+ * The last perf_mmap__read() will set tail to map->prev.
+ * Need to correct the map->prev to head which is the end of next read.
+ */
+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 e43d7b55a55f..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);
 };
@@ -63,9 +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__read_catchup(struct perf_mmap *md);
+void perf_mmap__consume(struct perf_mmap *map);
 
 static inline u64 perf_mmap__read_head(struct perf_mmap *mm)
 {
@@ -87,11 +88,14 @@ 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_backward(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));
+union perf_event *perf_mmap__read_event(struct perf_mmap *map);
+
+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);
+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 1e97937b03a9..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"
 
@@ -137,6 +138,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
         struct perf_evsel *evsel;
         bool use_sample_identifier = false;
         bool use_comm_exec;
+        bool sample_id = opts->sample_id;
 
         /*
          * Set the evsel leader links before we configure attributes,
@@ -163,8 +165,7 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
                  * match the id.
                  */
                 use_sample_identifier = perf_can_sample_identifier();
-                evlist__for_each_entry(evlist, evsel)
-                        perf_evsel__set_sample_id(evsel, use_sample_identifier);
+                sample_id = true;
         } else if (evlist->nr_entries > 1) {
                 struct perf_evsel *first = perf_evlist__first(evlist);
 
@@ -174,6 +175,10 @@ void perf_evlist__config(struct perf_evlist *evlist, struct record_opts *opts,
                         use_sample_identifier = perf_can_sample_identifier();
                         break;
                 }
+                sample_id = true;
+        }
+
+        if (sample_id) {
                 evlist__for_each_entry(evlist, evsel)
                         perf_evsel__set_sample_id(evsel, use_sample_identifier);
         }
@@ -215,11 +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;
+                }
         }
 
         /*
@@ -287,3 +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/trigger.h b/tools/perf/util/trigger.h
index 370138e7e35c..88223bc7c82b 100644
--- a/tools/perf/util/trigger.h
+++ b/tools/perf/util/trigger.h
@@ -12,7 +12,7 @@
  * States and transits:
  *
  *
- *  OFF--(on)--> READY --(hit)--> HIT
+ *  OFF--> ON --> READY --(hit)--> HIT
  *                 ^               |
  *                 |            (ready)
  *                 |               |
@@ -27,8 +27,9 @@ struct trigger {
         volatile enum {
                 TRIGGER_ERROR           = -2,
                 TRIGGER_OFF             = -1,
-                TRIGGER_READY           = 0,
-                TRIGGER_HIT             = 1,
+                TRIGGER_ON              = 0,
+                TRIGGER_READY           = 1,
+                TRIGGER_HIT             = 2,
         } state;
         const char *name;
 };
@@ -50,7 +51,7 @@ static inline bool trigger_is_error(struct trigger *t)
 static inline void trigger_on(struct trigger *t)
 {
         TRIGGER_WARN_ONCE(t, TRIGGER_OFF);
-        t->state = TRIGGER_READY;
+        t->state = TRIGGER_ON;
 }
 
 static inline void trigger_ready(struct trigger *t)
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);
diff --git a/tools/perf/util/util.c b/tools/perf/util/util.c
index 443892dabedb..1019bbc5dbd8 100644
--- a/tools/perf/util/util.c
+++ b/tools/perf/util/util.c
@@ -340,35 +340,15 @@ size_t hex_width(u64 v)
         return n;
 }
 
-static int hex(char ch)
-{
-        if ((ch >= '0') && (ch <= '9'))
-                return ch - '0';
-        if ((ch >= 'a') && (ch <= 'f'))
-                return ch - 'a' + 10;
-        if ((ch >= 'A') && (ch <= 'F'))
-                return ch - 'A' + 10;
-        return -1;
-}
-
 /*
  * While we find nice hex chars, build a long_val.
  * Return number of chars processed.
  */
 int hex2u64(const char *ptr, u64 *long_val)
 {
-        const char *p = ptr;
-        *long_val = 0;
-
-        while (*p) {
-                const int hex_val = hex(*p);
+        char *p;
 
-                if (hex_val < 0)
-                        break;
-
-                *long_val = (*long_val << 4) | hex_val;
-                p++;
-        }
+        *long_val = strtoull(ptr, &p, 16);
 
         return p - ptr;
 }
diff --git a/tools/power/acpi/Makefile.config b/tools/power/acpi/Makefile.config
index a1883bbb0144..2cccbba64418 100644
--- a/tools/power/acpi/Makefile.config
+++ b/tools/power/acpi/Makefile.config
@@ -56,9 +56,6 @@ INSTALL_SCRIPT = ${INSTALL_PROGRAM}
 # to compile vs uClibc, that can be done here as well.
 CROSS = #/usr/i386-linux-uclibc/usr/bin/i386-uclibc-
 CROSS_COMPILE ?= $(CROSS)
-CC = $(CROSS_COMPILE)gcc
-LD = $(CROSS_COMPILE)gcc
-STRIP = $(CROSS_COMPILE)strip
 HOSTCC = gcc
 
 # check if compiler option is supported
diff --git a/tools/scripts/Makefile.include b/tools/scripts/Makefile.include
index fcb3ed0be5f8..dd614463d4d6 100644
--- a/tools/scripts/Makefile.include
+++ b/tools/scripts/Makefile.include
@@ -42,6 +42,24 @@ EXTRA_WARNINGS += -Wformat
 
 CC_NO_CLANG := $(shell $(CC) -dM -E -x c /dev/null | grep -Fq "__clang__"; echo $$?)
 
+# Makefiles suck: This macro sets a default value of $(2) for the
+# variable named by $(1), unless the variable has been set by
+# environment or command line. This is necessary for CC and AR
+# because make sets default values, so the simpler ?= approach
+# won't work as expected.
+define allow-override
+  $(if $(or $(findstring environment,$(origin $(1))),\
+            $(findstring command line,$(origin $(1)))),,\
+    $(eval $(1) = $(2)))
+endef
+
+# Allow setting various cross-compile vars or setting CROSS_COMPILE as a prefix.
+$(call allow-override,CC,$(CROSS_COMPILE)gcc)
+$(call allow-override,AR,$(CROSS_COMPILE)ar)
+$(call allow-override,LD,$(CROSS_COMPILE)ld)
+$(call allow-override,CXX,$(CROSS_COMPILE)g++)
+$(call allow-override,STRIP,$(CROSS_COMPILE)strip)
+
 ifeq ($(CC_NO_CLANG), 1)
 EXTRA_WARNINGS += -Wstrict-aliasing=3
 endif
diff --git a/tools/spi/Makefile b/tools/spi/Makefile
index 90615e10c79a..815d15589177 100644
--- a/tools/spi/Makefile
+++ b/tools/spi/Makefile
@@ -11,8 +11,6 @@ endif
 # (this improves performance and avoids hard-to-debug behaviour);
 MAKEFLAGS += -r
 
-CC = $(CROSS_COMPILE)gcc
-LD = $(CROSS_COMPILE)ld
 CFLAGS += -O2 -Wall -g -D_GNU_SOURCE -I$(OUTPUT)include
 
 ALL_TARGETS := spidev_test spidev_fdx
diff --git a/tools/testing/radix-tree/idr-test.c b/tools/testing/radix-tree/idr-test.c
index 44ef9eba5a7a..6c645eb77d42 100644
--- a/tools/testing/radix-tree/idr-test.c
+++ b/tools/testing/radix-tree/idr-test.c
@@ -178,6 +178,55 @@ void idr_get_next_test(int base)
         idr_destroy(&idr);
 }
 
+int idr_u32_cb(int id, void *ptr, void *data)
+{
+        BUG_ON(id < 0);
+        BUG_ON(ptr != DUMMY_PTR);
+        return 0;
+}
+
+void idr_u32_test1(struct idr *idr, u32 handle)
+{
+        static bool warned = false;
+        u32 id = handle;
+        int sid = 0;
+        void *ptr;
+
+        BUG_ON(idr_alloc_u32(idr, DUMMY_PTR, &id, id, GFP_KERNEL));
+        BUG_ON(id != handle);
+        BUG_ON(idr_alloc_u32(idr, DUMMY_PTR, &id, id, GFP_KERNEL) != -ENOSPC);
+        BUG_ON(id != handle);
+        if (!warned && id > INT_MAX)
+                printk("vvv Ignore these warnings\n");
+        ptr = idr_get_next(idr, &sid);
+        if (id > INT_MAX) {
+                BUG_ON(ptr != NULL);
+                BUG_ON(sid != 0);
+        } else {
+                BUG_ON(ptr != DUMMY_PTR);
+                BUG_ON(sid != id);
+        }
+        idr_for_each(idr, idr_u32_cb, NULL);
+        if (!warned && id > INT_MAX) {
+                printk("^^^ Warnings over\n");
+                warned = true;
+        }
+        BUG_ON(idr_remove(idr, id) != DUMMY_PTR);
+        BUG_ON(!idr_is_empty(idr));
+}
+
+void idr_u32_test(int base)
+{
+        DEFINE_IDR(idr);
+        idr_init_base(&idr, base);
+        idr_u32_test1(&idr, 10);
+        idr_u32_test1(&idr, 0x7fffffff);
+        idr_u32_test1(&idr, 0x80000000);
+        idr_u32_test1(&idr, 0x80000001);
+        idr_u32_test1(&idr, 0xffe00000);
+        idr_u32_test1(&idr, 0xffffffff);
+}
+
 void idr_checks(void)
 {
         unsigned long i;
@@ -248,6 +297,9 @@ void idr_checks(void)
         idr_get_next_test(0);
         idr_get_next_test(1);
         idr_get_next_test(4);
+        idr_u32_test(4);
+        idr_u32_test(1);
+        idr_u32_test(0);
 }
 
 /*
diff --git a/tools/testing/radix-tree/linux.c b/tools/testing/radix-tree/linux.c
index 6903ccf35595..44a0d1ad4408 100644
--- a/tools/testing/radix-tree/linux.c
+++ b/tools/testing/radix-tree/linux.c
@@ -29,7 +29,7 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, int flags)
 {
         struct radix_tree_node *node;
 
-        if (flags & __GFP_NOWARN)
+        if (!(flags & __GFP_DIRECT_RECLAIM))
                 return NULL;
 
         pthread_mutex_lock(&cachep->lock);
@@ -73,10 +73,17 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp)
 
 void *kmalloc(size_t size, gfp_t gfp)
 {
-        void *ret = malloc(size);
+        void *ret;
+
+        if (!(gfp & __GFP_DIRECT_RECLAIM))
+                return NULL;
+
+        ret = malloc(size);
         uatomic_inc(&nr_allocated);
         if (kmalloc_verbose)
                 printf("Allocating %p from malloc\n", ret);
+        if (gfp & __GFP_ZERO)
+                memset(ret, 0, size);
         return ret;
 }
 
diff --git a/tools/testing/radix-tree/linux/compiler_types.h b/tools/testing/radix-tree/linux/compiler_types.h
new file mode 100644
index 000000000000..e69de29bb2d1
--- /dev/null
+++ b/tools/testing/radix-tree/linux/compiler_types.h
diff --git a/tools/testing/radix-tree/linux/gfp.h b/tools/testing/radix-tree/linux/gfp.h
index e9fff59dfd8a..e3201ccf54c3 100644
--- a/tools/testing/radix-tree/linux/gfp.h
+++ b/tools/testing/radix-tree/linux/gfp.h
@@ -11,6 +11,7 @@
 #define __GFP_IO                0x40u
 #define __GFP_FS                0x80u
 #define __GFP_NOWARN            0x200u
+#define __GFP_ZERO              0x8000u
 #define __GFP_ATOMIC            0x80000u
 #define __GFP_ACCOUNT           0x100000u
 #define __GFP_DIRECT_RECLAIM    0x400000u
diff --git a/tools/testing/radix-tree/linux/slab.h b/tools/testing/radix-tree/linux/slab.h
index 979baeec7e70..a037def0dec6 100644
--- a/tools/testing/radix-tree/linux/slab.h
+++ b/tools/testing/radix-tree/linux/slab.h
@@ -3,6 +3,7 @@
 #define SLAB_H
 
 #include <linux/types.h>
+#include <linux/gfp.h>
 
 #define SLAB_HWCACHE_ALIGN 1
 #define SLAB_PANIC 2
@@ -11,6 +12,11 @@
 void *kmalloc(size_t size, gfp_t);
 void kfree(void *);
 
+static inline void *kzalloc(size_t size, gfp_t gfp)
+{
+        return kmalloc(size, gfp | __GFP_ZERO);
+}
+
 void *kmem_cache_alloc(struct kmem_cache *cachep, int flags);
 void kmem_cache_free(struct kmem_cache *cachep, void *objp);
 
diff --git a/tools/testing/selftests/android/Makefile b/tools/testing/selftests/android/Makefile
index 1a7492268993..f6304d2be90c 100644
--- a/tools/testing/selftests/android/Makefile
+++ b/tools/testing/selftests/android/Makefile
@@ -11,11 +11,11 @@ all:
                 BUILD_TARGET=$(OUTPUT)/$$DIR;   \
                 mkdir $$BUILD_TARGET  -p;       \
                 make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
-                #SUBDIR test prog name should be in the form: SUBDIR_test.sh
+                #SUBDIR test prog name should be in the form: SUBDIR_test.sh \
                 TEST=$$DIR"_test.sh"; \
-                if [ -e $$DIR/$$TEST ]; then
-                        rsync -a $$DIR/$$TEST $$BUILD_TARGET/;
-                fi
+                if [ -e $$DIR/$$TEST ]; then \
+                        rsync -a $$DIR/$$TEST $$BUILD_TARGET/; \
+                fi \
         done
 
 override define RUN_TESTS
diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore
index cc15af2e54fe..9cf83f895d98 100644
--- a/tools/testing/selftests/bpf/.gitignore
+++ b/tools/testing/selftests/bpf/.gitignore
@@ -11,3 +11,4 @@ test_progs
 test_tcpbpf_user
 test_verifier_log
 feature
+test_libbpf_open
diff --git a/tools/testing/selftests/bpf/test_maps.c b/tools/testing/selftests/bpf/test_maps.c
index 436c4c72414f..9e03a4c356a4 100644
--- a/tools/testing/selftests/bpf/test_maps.c
+++ b/tools/testing/selftests/bpf/test_maps.c
@@ -126,6 +126,8 @@ static void test_hashmap_sizes(int task, void *data)
                         fd = bpf_create_map(BPF_MAP_TYPE_HASH, i, j,
                                             2, map_flags);
                         if (fd < 0) {
+                                if (errno == ENOMEM)
+                                        return;
                                 printf("Failed to create hashmap key=%d value=%d '%s'\n",
                                        i, j, strerror(errno));
                                 exit(1);
diff --git a/tools/testing/selftests/bpf/test_tcpbpf_kern.c b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
index 57119ad57a3f..3e645ee41ed5 100644
--- a/tools/testing/selftests/bpf/test_tcpbpf_kern.c
+++ b/tools/testing/selftests/bpf/test_tcpbpf_kern.c
@@ -5,7 +5,6 @@
 #include <linux/if_ether.h>
 #include <linux/if_packet.h>
 #include <linux/ip.h>
-#include <linux/in6.h>
 #include <linux/types.h>
 #include <linux/socket.h>
 #include <linux/tcp.h>
diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c
index c0f16e93f9bd..437c0b1c9d21 100644
--- a/tools/testing/selftests/bpf/test_verifier.c
+++ b/tools/testing/selftests/bpf/test_verifier.c
@@ -2587,6 +2587,32 @@ static struct bpf_test tests[] = {
                 .result = ACCEPT,
         },
         {
+                "runtime/jit: pass negative index to tail_call",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_3, -1),
+                        BPF_LD_MAP_FD(BPF_REG_2, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_tail_call),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_prog = { 1 },
+                .result = ACCEPT,
+        },
+        {
+                "runtime/jit: pass > 32bit index to tail_call",
+                .insns = {
+                        BPF_LD_IMM64(BPF_REG_3, 0x100000000ULL),
+                        BPF_LD_MAP_FD(BPF_REG_2, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_tail_call),
+                        BPF_MOV64_IMM(BPF_REG_0, 0),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_prog = { 2 },
+                .result = ACCEPT,
+        },
+        {
                 "stack pointer arithmetic",
                 .insns = {
                         BPF_MOV64_IMM(BPF_REG_1, 4),
@@ -11137,6 +11163,64 @@ static struct bpf_test tests[] = {
                 .result = REJECT,
                 .prog_type = BPF_PROG_TYPE_TRACEPOINT,
         },
+        {
+                "xadd/w check unaligned stack",
+                .insns = {
+                        BPF_MOV64_IMM(BPF_REG_0, 1),
+                        BPF_STX_MEM(BPF_DW, BPF_REG_10, BPF_REG_0, -8),
+                        BPF_STX_XADD(BPF_W, BPF_REG_10, BPF_REG_0, -7),
+                        BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_10, -8),
+                        BPF_EXIT_INSN(),
+                },
+                .result = REJECT,
+                .errstr = "misaligned stack access off",
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "xadd/w check unaligned map",
+                .insns = {
+                        BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0),
+                        BPF_MOV64_REG(BPF_REG_2, BPF_REG_10),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8),
+                        BPF_LD_MAP_FD(BPF_REG_1, 0),
+                        BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0,
+                                     BPF_FUNC_map_lookup_elem),
+                        BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 1),
+                        BPF_EXIT_INSN(),
+                        BPF_MOV64_IMM(BPF_REG_1, 1),
+                        BPF_STX_XADD(BPF_W, BPF_REG_0, BPF_REG_1, 3),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_0, 3),
+                        BPF_EXIT_INSN(),
+                },
+                .fixup_map1 = { 3 },
+                .result = REJECT,
+                .errstr = "misaligned value access off",
+                .prog_type = BPF_PROG_TYPE_SCHED_CLS,
+        },
+        {
+                "xadd/w check unaligned pkt",
+                .insns = {
+                        BPF_LDX_MEM(BPF_W, BPF_REG_2, BPF_REG_1,
+                                    offsetof(struct xdp_md, data)),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_1,
+                                    offsetof(struct xdp_md, data_end)),
+                        BPF_MOV64_REG(BPF_REG_1, BPF_REG_2),
+                        BPF_ALU64_IMM(BPF_ADD, BPF_REG_1, 8),
+                        BPF_JMP_REG(BPF_JLT, BPF_REG_1, BPF_REG_3, 2),
+                        BPF_MOV64_IMM(BPF_REG_0, 99),
+                        BPF_JMP_IMM(BPF_JA, 0, 0, 6),
+                        BPF_MOV64_IMM(BPF_REG_0, 1),
+                        BPF_ST_MEM(BPF_W, BPF_REG_2, 0, 0),
+                        BPF_ST_MEM(BPF_W, BPF_REG_2, 3, 0),
+                        BPF_STX_XADD(BPF_W, BPF_REG_2, BPF_REG_0, 1),
+                        BPF_STX_XADD(BPF_W, BPF_REG_2, BPF_REG_0, 2),
+                        BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_2, 1),
+                        BPF_EXIT_INSN(),
+                },
+                .result = REJECT,
+                .errstr = "BPF_XADD stores into R2 packet",
+                .prog_type = BPF_PROG_TYPE_XDP,
+        },
 };
 
 static int probe_filter_length(const struct bpf_insn *fp)
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc
new file mode 100644
index 000000000000..5ba73035e1d9
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc
@@ -0,0 +1,46 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Kprobe event string type argument
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+echo 0 > events/enable
+echo > kprobe_events
+
+case `uname -m` in
+x86_64)
+  ARG2=%si
+  OFFS=8
+;;
+i[3456]86)
+  ARG2=%cx
+  OFFS=4
+;;
+aarch64)
+  ARG2=%x1
+  OFFS=8
+;;
+arm*)
+  ARG2=%r1
+  OFFS=4
+;;
+*)
+  echo "Please implement other architecture here"
+  exit_untested
+esac
+
+: "Test get argument (1)"
+echo "p:testprobe create_trace_kprobe arg1=+0(+0(${ARG2})):string" > kprobe_events
+echo 1 > events/kprobes/testprobe/enable
+! echo test >> kprobe_events
+tail -n 1 trace | grep -qe "testprobe.* arg1=\"test\""
+
+echo 0 > events/kprobes/testprobe/enable
+: "Test get argument (2)"
+echo "p:testprobe create_trace_kprobe arg1=+0(+0(${ARG2})):string arg2=+0(+${OFFS}(${ARG2})):string" > kprobe_events
+echo 1 > events/kprobes/testprobe/enable
+! echo test1 test2 >> kprobe_events
+tail -n 1 trace | grep -qe "testprobe.* arg1=\"test1\" arg2=\"test2\""
+
+echo 0 > events/enable
+echo > kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc
new file mode 100644
index 000000000000..231bcd2c4eb5
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_syntax.tc
@@ -0,0 +1,97 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Kprobe event argument syntax
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+grep "x8/16/32/64" README > /dev/null || exit_unsupported # version issue
+
+echo 0 > events/enable
+echo > kprobe_events
+
+PROBEFUNC="vfs_read"
+GOODREG=
+BADREG=
+GOODSYM="_sdata"
+if ! grep -qw ${GOODSYM} /proc/kallsyms ; then
+  GOODSYM=$PROBEFUNC
+fi
+BADSYM="deaqswdefr"
+SYMADDR=0x`grep -w ${GOODSYM} /proc/kallsyms | cut -f 1 -d " "`
+GOODTYPE="x16"
+BADTYPE="y16"
+
+case `uname -m` in
+x86_64|i[3456]86)
+  GOODREG=%ax
+  BADREG=%ex
+;;
+aarch64)
+  GOODREG=%x0
+  BADREG=%ax
+;;
+arm*)
+  GOODREG=%r0
+  BADREG=%ax
+;;
+esac
+
+test_goodarg() # Good-args
+{
+  while [ "$1" ]; do
+    echo "p ${PROBEFUNC} $1" > kprobe_events
+    shift 1
+  done;
+}
+
+test_badarg() # Bad-args
+{
+  while [ "$1" ]; do
+    ! echo "p ${PROBEFUNC} $1" > kprobe_events
+    shift 1
+  done;
+}
+
+echo > kprobe_events
+
+: "Register access"
+test_goodarg ${GOODREG}
+test_badarg ${BADREG}
+
+: "Symbol access"
+test_goodarg "@${GOODSYM}" "@${SYMADDR}" "@${GOODSYM}+10" "@${GOODSYM}-10"
+test_badarg "@" "@${BADSYM}" "@${GOODSYM}*10" "@${GOODSYM}/10" \
+            "@${GOODSYM}%10" "@${GOODSYM}&10" "@${GOODSYM}|10"
+
+: "Stack access"
+test_goodarg "\$stack" "\$stack0" "\$stack1"
+test_badarg "\$stackp" "\$stack0+10" "\$stack1-10"
+
+: "Retval access"
+echo "r ${PROBEFUNC} \$retval" > kprobe_events
+! echo "p ${PROBEFUNC} \$retval" > kprobe_events
+
+: "Comm access"
+test_goodarg "\$comm"
+
+: "Indirect memory access"
+test_goodarg "+0(${GOODREG})" "-0(${GOODREG})" "+10(\$stack)" \
+        "+0(\$stack1)" "+10(@${GOODSYM}-10)" "+0(+10(+20(\$stack)))"
+test_badarg "+(${GOODREG})" "(${GOODREG}+10)" "-(${GOODREG})" "(${GOODREG})" \
+        "+10(\$comm)" "+0(${GOODREG})+10"
+
+: "Name assignment"
+test_goodarg "varname=${GOODREG}"
+test_badarg "varname=varname2=${GOODREG}"
+
+: "Type syntax"
+test_goodarg "${GOODREG}:${GOODTYPE}"
+test_badarg "${GOODREG}::${GOODTYPE}" "${GOODREG}:${BADTYPE}" \
+        "${GOODTYPE}:${GOODREG}"
+
+: "Combination check"
+
+test_goodarg "\$comm:string" "+0(\$stack):string"
+test_badarg "\$comm:x64" "\$stack:string" "${GOODREG}:string"
+
+echo > kprobe_events
diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc b/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc
new file mode 100644
index 000000000000..4fda01a08da4
--- /dev/null
+++ b/tools/testing/selftests/ftrace/test.d/kprobe/probepoint.tc
@@ -0,0 +1,43 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Kprobe events - probe points
+
+[ -f kprobe_events ] || exit_unsupported # this is configurable
+
+TARGET_FUNC=create_trace_kprobe
+
+dec_addr() { # hexaddr
+  printf "%d" "0x"`echo $1 | tail -c 8`
+}
+
+set_offs() { # prev target next
+  A1=`dec_addr $1`
+  A2=`dec_addr $2`
+  A3=`dec_addr $3`
+  TARGET="0x$2" # an address
+  PREV=`expr $A1 - $A2` # offset to previous symbol
+  NEXT=+`expr $A3 - $A2` # offset to next symbol
+  OVERFLOW=+`printf "0x%x" ${PREV}` # overflow offset to previous symbol
+}
+
+# We have to decode symbol addresses to get correct offsets.
+# If the offset is not an instruction boundary, it cause -EILSEQ.
+set_offs `grep -A1 -B1 ${TARGET_FUNC} /proc/kallsyms | cut -f 1 -d " " | xargs`
+
+UINT_TEST=no
+# printf "%x" -1 returns (unsigned long)-1.
+if [ `printf "%x" -1 | wc -c` != 9 ]; then
+  UINT_TEST=yes
+fi
+
+echo 0 > events/enable
+echo > kprobe_events
+echo "p:testprobe ${TARGET_FUNC}" > kprobe_events
+echo "p:testprobe ${TARGET}" > kprobe_events
+echo "p:testprobe ${TARGET_FUNC}${NEXT}" > kprobe_events
+! echo "p:testprobe ${TARGET_FUNC}${PREV}" > kprobe_events
+if [ "${UINT_TEST}" = yes ]; then
+! echo "p:testprobe ${TARGET_FUNC}${OVERFLOW}" > kprobe_events
+fi
+echo > kprobe_events
+clear_trace
diff --git a/tools/testing/selftests/futex/Makefile b/tools/testing/selftests/futex/Makefile
index cea4adcd42b8..a63e8453984d 100644
--- a/tools/testing/selftests/futex/Makefile
+++ b/tools/testing/selftests/futex/Makefile
@@ -12,9 +12,9 @@ all:
                 BUILD_TARGET=$(OUTPUT)/$$DIR;   \
                 mkdir $$BUILD_TARGET  -p;       \
                 make OUTPUT=$$BUILD_TARGET -C $$DIR $@;\
-                if [ -e $$DIR/$(TEST_PROGS) ]; then
-                        rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/;
-                fi
+                if [ -e $$DIR/$(TEST_PROGS) ]; then \
+                        rsync -a $$DIR/$(TEST_PROGS) $$BUILD_TARGET/; \
+                fi \
         done
 
 override define RUN_TESTS
diff --git a/tools/testing/selftests/memfd/Makefile b/tools/testing/selftests/memfd/Makefile
index a5276a91dfbf..0862e6f47a38 100644
--- a/tools/testing/selftests/memfd/Makefile
+++ b/tools/testing/selftests/memfd/Makefile
@@ -5,6 +5,7 @@ CFLAGS += -I../../../../include/
 CFLAGS += -I../../../../usr/include/
 
 TEST_PROGS := run_tests.sh
+TEST_FILES := run_fuse_test.sh
 TEST_GEN_FILES := memfd_test fuse_mnt fuse_test
 
 fuse_mnt.o: CFLAGS += $(shell pkg-config fuse --cflags)
diff --git a/tools/testing/selftests/memfd/config b/tools/testing/selftests/memfd/config
new file mode 100644
index 000000000000..835c7f4dadcd
--- /dev/null
+++ b/tools/testing/selftests/memfd/config
@@ -0,0 +1 @@
+CONFIG_FUSE_FS=m
diff --git a/tools/testing/selftests/memory-hotplug/Makefile b/tools/testing/selftests/memory-hotplug/Makefile
index 86636d207adf..686da510f989 100644
--- a/tools/testing/selftests/memory-hotplug/Makefile
+++ b/tools/testing/selftests/memory-hotplug/Makefile
@@ -4,8 +4,9 @@ all:
 include ../lib.mk
 
 TEST_PROGS := mem-on-off-test.sh
-override RUN_TESTS := ./mem-on-off-test.sh -r 2 && echo "selftests: memory-hotplug [PASS]" || echo "selftests: memory-hotplug [FAIL]"
-override EMIT_TESTS := echo "$(RUN_TESTS)"
+override RUN_TESTS := @./mem-on-off-test.sh -r 2 && echo "selftests: memory-hotplug [PASS]" || echo "selftests: memory-hotplug [FAIL]"
+
+override EMIT_TESTS := echo "$(subst @,,$(RUN_TESTS))"
 
 run_full_test:
         @/bin/bash ./mem-on-off-test.sh && echo "memory-hotplug selftests: [PASS]" || echo "memory-hotplug selftests: [FAIL]"
diff --git a/tools/testing/selftests/powerpc/mm/subpage_prot.c b/tools/testing/selftests/powerpc/mm/subpage_prot.c
index 35ade7406dcd..3ae77ba93208 100644
--- a/tools/testing/selftests/powerpc/mm/subpage_prot.c
+++ b/tools/testing/selftests/powerpc/mm/subpage_prot.c
@@ -135,6 +135,16 @@ static int run_test(void *addr, unsigned long size)
         return 0;
 }
 
+static int syscall_available(void)
+{
+        int rc;
+
+        errno = 0;
+        rc = syscall(__NR_subpage_prot, 0, 0, 0);
+
+        return rc == 0 || (errno != ENOENT && errno != ENOSYS);
+}
+
 int test_anon(void)
 {
         unsigned long align;
@@ -145,6 +155,8 @@ int test_anon(void)
         void *mallocblock;
         unsigned long mallocsize;
 
+        SKIP_IF(!syscall_available());
+
         if (getpagesize() != 0x10000) {
                 fprintf(stderr, "Kernel page size must be 64K!\n");
                 return 1;
@@ -180,6 +192,8 @@ int test_file(void)
         off_t filesize;
         int fd;
 
+        SKIP_IF(!syscall_available());
+
         fd = open(file_name, O_RDWR);
         if (fd == -1) {
                 perror("failed to open file");
diff --git a/tools/testing/selftests/powerpc/tm/Makefile b/tools/testing/selftests/powerpc/tm/Makefile
index a23453943ad2..5c72ff978f27 100644
--- a/tools/testing/selftests/powerpc/tm/Makefile
+++ b/tools/testing/selftests/powerpc/tm/Makefile
@@ -16,7 +16,7 @@ $(OUTPUT)/tm-syscall: tm-syscall-asm.S
 $(OUTPUT)/tm-syscall: CFLAGS += -I../../../../../usr/include
 $(OUTPUT)/tm-tmspr: CFLAGS += -pthread
 $(OUTPUT)/tm-vmx-unavail: CFLAGS += -pthread -m64
-$(OUTPUT)/tm-resched-dscr: ../pmu/lib.o
+$(OUTPUT)/tm-resched-dscr: ../pmu/lib.c
 $(OUTPUT)/tm-unavailable: CFLAGS += -O0 -pthread -m64 -Wno-error=uninitialized -mvsx
 $(OUTPUT)/tm-trap: CFLAGS += -O0 -pthread -m64
 
diff --git a/tools/testing/selftests/powerpc/tm/tm-trap.c b/tools/testing/selftests/powerpc/tm/tm-trap.c
index 5d92c23ee6cb..179d592f0073 100644
--- a/tools/testing/selftests/powerpc/tm/tm-trap.c
+++ b/tools/testing/selftests/powerpc/tm/tm-trap.c
@@ -255,6 +255,8 @@ int tm_trap_test(void)
 
         struct sigaction trap_sa;
 
+        SKIP_IF(!have_htm());
+
         trap_sa.sa_flags = SA_SIGINFO;
         trap_sa.sa_sigaction = trap_signal_handler;
         sigaction(SIGTRAP, &trap_sa, NULL);
diff --git a/tools/testing/selftests/pstore/config b/tools/testing/selftests/pstore/config
index 6a8e5a9bfc10..d148f9f89fb6 100644
--- a/tools/testing/selftests/pstore/config
+++ b/tools/testing/selftests/pstore/config
@@ -2,3 +2,4 @@ CONFIG_MISC_FILESYSTEMS=y
 CONFIG_PSTORE=y
 CONFIG_PSTORE_PMSG=y
 CONFIG_PSTORE_CONSOLE=y
+CONFIG_PSTORE_RAM=m
diff --git a/tools/testing/selftests/rcutorture/bin/functions.sh b/tools/testing/selftests/rcutorture/bin/functions.sh
index 07a13779eece..65f6655026f0 100644
--- a/tools/testing/selftests/rcutorture/bin/functions.sh
+++ b/tools/testing/selftests/rcutorture/bin/functions.sh
@@ -136,6 +136,9 @@ identify_boot_image () {
                 qemu-system-x86_64|qemu-system-i386)
                         echo arch/x86/boot/bzImage
                         ;;
+                qemu-system-aarch64)
+                        echo arch/arm64/boot/Image
+                        ;;
                 *)
                         echo vmlinux
                         ;;
@@ -158,6 +161,9 @@ identify_qemu () {
         elif echo $u | grep -q "Intel 80386"
         then
                 echo qemu-system-i386
+        elif echo $u | grep -q aarch64
+        then
+                echo qemu-system-aarch64
         elif uname -a | grep -q ppc64
         then
                 echo qemu-system-ppc64
@@ -176,16 +182,20 @@ identify_qemu () {
 # Output arguments for the qemu "-append" string based on CPU type
 # and the TORTURE_QEMU_INTERACTIVE environment variable.
 identify_qemu_append () {
+        local console=ttyS0
         case "$1" in
         qemu-system-x86_64|qemu-system-i386)
                 echo noapic selinux=0 initcall_debug debug
                 ;;
+        qemu-system-aarch64)
+                console=ttyAMA0
+                ;;
         esac
         if test -n "$TORTURE_QEMU_INTERACTIVE"
         then
                 echo root=/dev/sda
         else
-                echo console=ttyS0
+                echo console=$console
         fi
 }
 
@@ -197,6 +207,9 @@ identify_qemu_args () {
         case "$1" in
         qemu-system-x86_64|qemu-system-i386)
                 ;;
+        qemu-system-aarch64)
+                echo -machine virt,gic-version=host -cpu host
+                ;;
         qemu-system-ppc64)
                 echo -enable-kvm -M pseries -nodefaults
                 echo -device spapr-vscsi
@@ -254,7 +267,7 @@ specify_qemu_cpus () {
                 echo $2
         else
                 case "$1" in
-                qemu-system-x86_64|qemu-system-i386)
+                qemu-system-x86_64|qemu-system-i386|qemu-system-aarch64)
                         echo $2 -smp $3
                         ;;
                 qemu-system-ppc64)
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf-ftrace.sh b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf-ftrace.sh
index 963f71289d22..8948f7926b21 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf-ftrace.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-recheck-rcuperf-ftrace.sh
@@ -39,30 +39,31 @@ sed -e 's/us : / : /' |
 tr -d '\015' |
 awk '
 $8 == "start" {
-        if (starttask != "")
+        if (startseq != "")
                 nlost++;
         starttask = $1;
         starttime = $3;
         startseq = $7;
+        seqtask[startseq] = starttask;
 }
 
 $8 == "end" {
-        if (starttask == $1 && startseq == $7) {
+        if (startseq == $7) {
                 curgpdur = $3 - starttime;
                 gptimes[++n] = curgpdur;
                 gptaskcnt[starttask]++;
                 sum += curgpdur;
                 if (curgpdur > 1000)
                         print "Long GP " starttime "us to " $3 "us (" curgpdur "us)";
-                starttask = "";
+                startseq = "";
         } else {
                 # Lost a message or some such, reset.
-                starttask = "";
+                startseq = "";
                 nlost++;
         }
 }
 
-$8 == "done" {
+$8 == "done" && seqtask[$7] != $1 {
         piggybackcnt[$1]++;
 }
 
diff --git a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
index 1b78a12740e5..5f8fbb0d7c17 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm-test-1-run.sh
@@ -177,8 +177,8 @@ then
         exit 0
 fi
 echo "NOTE: $QEMU either did not run or was interactive" > $resdir/console.log
-echo $QEMU $qemu_args -m 512 -kernel $KERNEL -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd
-( $QEMU $qemu_args -m 512 -kernel $KERNEL -append "$qemu_append $boot_args"& echo $! > $resdir/qemu_pid; wait `cat  $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) &
+echo $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append \"$qemu_append $boot_args\" > $resdir/qemu-cmd
+( $QEMU $qemu_args -m $TORTURE_QEMU_MEM -kernel $KERNEL -append "$qemu_append $boot_args"& echo $! > $resdir/qemu_pid; wait `cat  $resdir/qemu_pid`; echo $? > $resdir/qemu-retval ) &
 commandcompleted=0
 sleep 10 # Give qemu's pid a chance to reach the file
 if test -s "$resdir/qemu_pid"
diff --git a/tools/testing/selftests/rcutorture/bin/kvm.sh b/tools/testing/selftests/rcutorture/bin/kvm.sh
index 7d1f607f0f76..56610dbbdf73 100755
--- a/tools/testing/selftests/rcutorture/bin/kvm.sh
+++ b/tools/testing/selftests/rcutorture/bin/kvm.sh
@@ -1,10 +1,8 @@
 #!/bin/bash
 #
-# Run a series of 14 tests under KVM.  These are not particularly
-# well-selected or well-tuned, but are the current set.
-#
-# Edit the definitions below to set the locations of the various directories,
-# as well as the test duration.
+# Run a series of tests under KVM.  By default, this series is specified
+# by the relevant CFLIST file, but can be overridden by the --configs
+# command-line argument.
 #
 # Usage: kvm.sh [ options ]
 #
@@ -44,6 +42,7 @@ TORTURE_BOOT_IMAGE=""
 TORTURE_INITRD="$KVM/initrd"; export TORTURE_INITRD
 TORTURE_KCONFIG_ARG=""
 TORTURE_KMAKE_ARG=""
+TORTURE_QEMU_MEM=512
 TORTURE_SHUTDOWN_GRACE=180
 TORTURE_SUITE=rcu
 resdir=""
@@ -70,6 +69,7 @@ usage () {
         echo "       --kconfig Kconfig-options"
         echo "       --kmake-arg kernel-make-arguments"
         echo "       --mac nn:nn:nn:nn:nn:nn"
+        echo "       --memory megabytes | nnnG"
         echo "       --no-initrd"
         echo "       --qemu-args qemu-arguments"
         echo "       --qemu-cmd qemu-system-..."
@@ -147,6 +147,11 @@ do
                 TORTURE_QEMU_MAC=$2
                 shift
                 ;;
+        --memory)
+                checkarg --memory "(memory size)" $# "$2" '^[0-9]\+[MG]\?$' error
+                TORTURE_QEMU_MEM=$2
+                shift
+                ;;
         --no-initrd)
                 TORTURE_INITRD=""; export TORTURE_INITRD
                 ;;
@@ -174,6 +179,12 @@ do
                 checkarg --torture "(suite name)" "$#" "$2" '^\(lock\|rcu\|rcuperf\)$' '^--'
                 TORTURE_SUITE=$2
                 shift
+                if test "$TORTURE_SUITE" = rcuperf
+                then
+                        # If you really want jitter for rcuperf, specify
+                        # it after specifying rcuperf.  (But why?)
+                        jitter=0
+                fi
                 ;;
         *)
                 echo Unknown argument $1
@@ -288,6 +299,7 @@ TORTURE_KMAKE_ARG="$TORTURE_KMAKE_ARG"; export TORTURE_KMAKE_ARG
 TORTURE_QEMU_CMD="$TORTURE_QEMU_CMD"; export TORTURE_QEMU_CMD
 TORTURE_QEMU_INTERACTIVE="$TORTURE_QEMU_INTERACTIVE"; export TORTURE_QEMU_INTERACTIVE
 TORTURE_QEMU_MAC="$TORTURE_QEMU_MAC"; export TORTURE_QEMU_MAC
+TORTURE_QEMU_MEM="$TORTURE_QEMU_MEM"; export TORTURE_QEMU_MEM
 TORTURE_SHUTDOWN_GRACE="$TORTURE_SHUTDOWN_GRACE"; export TORTURE_SHUTDOWN_GRACE
 TORTURE_SUITE="$TORTURE_SUITE"; export TORTURE_SUITE
 if ! test -e $resdir
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03 b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03
index c70c51d5ded1..28568b72a31b 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03
@@ -9,5 +9,4 @@ CONFIG_PREEMPT=y
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=y
-CONFIG_NO_HZ_FULL_ALL=y
 #CHECK#CONFIG_RCU_EXPERT=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03.boot b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03.boot
index cd2a188eeb6d..838297c58318 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TASKS03.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TASKS03.boot
@@ -1 +1 @@
-rcutorture.torture_type=tasks
+rcutorture.torture_type=tasks nohz_full=1
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04 b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
index 27d22695d64c..24c9f6012e35 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04
@@ -7,7 +7,6 @@ CONFIG_PREEMPT=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=y
-CONFIG_NO_HZ_FULL_ALL=y
 CONFIG_RCU_FAST_NO_HZ=y
 CONFIG_RCU_TRACE=y
 CONFIG_HOTPLUG_CPU=n
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot b/tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot
index e34c33430447..e6071bb96c7d 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE04.boot
@@ -1 +1 @@
-rcutorture.torture_type=rcu_bh rcutree.rcu_fanout_leaf=4
+rcutorture.torture_type=rcu_bh rcutree.rcu_fanout_leaf=4 nohz_full=1-7
diff --git a/tools/testing/selftests/rcutorture/configs/rcu/TREE07 b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
index 0f4759f4232e..d7afb271a586 100644
--- a/tools/testing/selftests/rcutorture/configs/rcu/TREE07
+++ b/tools/testing/selftests/rcutorture/configs/rcu/TREE07
@@ -7,7 +7,6 @@ CONFIG_PREEMPT=n
 CONFIG_HZ_PERIODIC=n
 CONFIG_NO_HZ_IDLE=n
 CONFIG_NO_HZ_FULL=y
-CONFIG_NO_HZ_FULL_ALL=n
 CONFIG_RCU_FAST_NO_HZ=n
 CONFIG_RCU_TRACE=y
 CONFIG_HOTPLUG_CPU=y
diff --git a/tools/testing/selftests/rcutorture/configs/rcuperf/ver_functions.sh b/tools/testing/selftests/rcutorture/configs/rcuperf/ver_functions.sh
index b9603115d7c7..d36b8fd6f0fc 100644
--- a/tools/testing/selftests/rcutorture/configs/rcuperf/ver_functions.sh
+++ b/tools/testing/selftests/rcutorture/configs/rcuperf/ver_functions.sh
@@ -20,32 +20,10 @@
 #
 # Authors: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
 
-# rcuperf_param_nreaders bootparam-string
-#
-# Adds nreaders rcuperf module parameter if not already specified.
-rcuperf_param_nreaders () {
-        if ! echo "$1" | grep -q "rcuperf.nreaders"
-        then
-                echo rcuperf.nreaders=-1
-        fi
-}
-
-# rcuperf_param_nwriters bootparam-string
-#
-# Adds nwriters rcuperf module parameter if not already specified.
-rcuperf_param_nwriters () {
-        if ! echo "$1" | grep -q "rcuperf.nwriters"
-        then
-                echo rcuperf.nwriters=-1
-        fi
-}
-
 # per_version_boot_params bootparam-string config-file seconds
 #
 # Adds per-version torture-module parameters to kernels supporting them.
 per_version_boot_params () {
-        echo $1 `rcuperf_param_nreaders "$1"` \
-                `rcuperf_param_nwriters "$1"` \
-                rcuperf.shutdown=1 \
+        echo $1 rcuperf.shutdown=1 \
                 rcuperf.verbose=1
 }
diff --git a/tools/testing/selftests/rcutorture/doc/rcu-test-image.txt b/tools/testing/selftests/rcutorture/doc/rcu-test-image.txt
index 66efb59a1bd1..449cf579d6f9 100644
--- a/tools/testing/selftests/rcutorture/doc/rcu-test-image.txt
+++ b/tools/testing/selftests/rcutorture/doc/rcu-test-image.txt
@@ -1,4 +1,4 @@
-This document describes one way to created the rcu-test-image file
+This document describes one way to create the rcu-test-image file
 that contains the filesystem used by the guest-OS kernel.  There are
 probably much better ways of doing this, and this filesystem could no
 doubt be smaller.  It is probably also possible to simply download
diff --git a/tools/testing/selftests/seccomp/seccomp_bpf.c b/tools/testing/selftests/seccomp/seccomp_bpf.c
index 0b457e8e0f0c..5df609950a66 100644
--- a/tools/testing/selftests/seccomp/seccomp_bpf.c
+++ b/tools/testing/selftests/seccomp/seccomp_bpf.c
@@ -141,6 +141,15 @@ struct seccomp_data {
 #define SECCOMP_FILTER_FLAG_LOG 2
 #endif
 
+#ifndef PTRACE_SECCOMP_GET_METADATA
+#define PTRACE_SECCOMP_GET_METADATA     0x420d
+
+struct seccomp_metadata {
+        __u64 filter_off;       /* Input: which filter */
+        __u64 flags;             /* Output: filter's flags */
+};
+#endif
+
 #ifndef seccomp
 int seccomp(unsigned int op, unsigned int flags, void *args)
 {
@@ -2845,6 +2854,58 @@ TEST(get_action_avail)
         EXPECT_EQ(errno, EOPNOTSUPP);
 }
 
+TEST(get_metadata)
+{
+        pid_t pid;
+        int pipefd[2];
+        char buf;
+        struct seccomp_metadata md;
+
+        ASSERT_EQ(0, pipe(pipefd));
+
+        pid = fork();
+        ASSERT_GE(pid, 0);
+        if (pid == 0) {
+                struct sock_filter filter[] = {
+                        BPF_STMT(BPF_RET|BPF_K, SECCOMP_RET_ALLOW),
+                };
+                struct sock_fprog prog = {
+                        .len = (unsigned short)ARRAY_SIZE(filter),
+                        .filter = filter,
+                };
+
+                /* one with log, one without */
+                ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER,
+                                     SECCOMP_FILTER_FLAG_LOG, &prog));
+                ASSERT_EQ(0, seccomp(SECCOMP_SET_MODE_FILTER, 0, &prog));
+
+                ASSERT_EQ(0, close(pipefd[0]));
+                ASSERT_EQ(1, write(pipefd[1], "1", 1));
+                ASSERT_EQ(0, close(pipefd[1]));
+
+                while (1)
+                        sleep(100);
+        }
+
+        ASSERT_EQ(0, close(pipefd[1]));
+        ASSERT_EQ(1, read(pipefd[0], &buf, 1));
+
+        ASSERT_EQ(0, ptrace(PTRACE_ATTACH, pid));
+        ASSERT_EQ(pid, waitpid(pid, NULL, 0));
+
+        md.filter_off = 0;
+        ASSERT_EQ(sizeof(md), ptrace(PTRACE_SECCOMP_GET_METADATA, pid, sizeof(md), &md));
+        EXPECT_EQ(md.flags, SECCOMP_FILTER_FLAG_LOG);
+        EXPECT_EQ(md.filter_off, 0);
+
+        md.filter_off = 1;
+        ASSERT_EQ(sizeof(md), ptrace(PTRACE_SECCOMP_GET_METADATA, pid, sizeof(md), &md));
+        EXPECT_EQ(md.flags, 0);
+        EXPECT_EQ(md.filter_off, 1);
+
+        ASSERT_EQ(0, kill(pid, SIGKILL));
+}
+
 /*
  * TODO:
  * - add microbenchmarks
diff --git a/tools/testing/selftests/sync/Makefile b/tools/testing/selftests/sync/Makefile
index b3c8ba3cb668..d0121a8a3523 100644
--- a/tools/testing/selftests/sync/Makefile
+++ b/tools/testing/selftests/sync/Makefile
@@ -30,7 +30,7 @@ $(TEST_CUSTOM_PROGS): $(TESTS) $(OBJS)
         $(CC) -o $(TEST_CUSTOM_PROGS) $(OBJS) $(TESTS) $(CFLAGS) $(LDFLAGS)
 
 $(OBJS): $(OUTPUT)/%.o: %.c
-        $(CC) -c $^ -o $@
+        $(CC) -c $^ -o $@ $(CFLAGS)
 
 $(TESTS): $(OUTPUT)/%.o: %.c
         $(CC) -c $^ -o $@
diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
index e34075059c26..90bba48c3f07 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/actions/skbmod.json
@@ -315,7 +315,7 @@
         "cmdUnderTest": "$TC actions ls action skbmod",
         "expExitCode": "0",
         "verifyCmd": "$TC actions get action skbmod index 4",
-        "matchPattern": "action order [0-9]*: skbmod pipe set etype 0x0031",
+        "matchPattern": "action order [0-9]*: skbmod pipe set etype 0x31",
         "matchCount": "1",
         "teardown": [
             "$TC actions flush action skbmod"
diff --git a/tools/testing/selftests/vDSO/Makefile b/tools/testing/selftests/vDSO/Makefile
index 3d5a62ff7d31..f5d7a7851e21 100644
--- a/tools/testing/selftests/vDSO/Makefile
+++ b/tools/testing/selftests/vDSO/Makefile
@@ -1,4 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
+include ../lib.mk
+
 ifndef CROSS_COMPILE
 CFLAGS := -std=gnu99
 CFLAGS_vdso_standalone_test_x86 := -nostdlib -fno-asynchronous-unwind-tables -fno-stack-protector
@@ -6,16 +8,14 @@ ifeq ($(CONFIG_X86_32),y)
 LDLIBS += -lgcc_s
 endif
 
-TEST_PROGS := vdso_test vdso_standalone_test_x86
+TEST_PROGS := $(OUTPUT)/vdso_test $(OUTPUT)/vdso_standalone_test_x86
 
 all: $(TEST_PROGS)
-vdso_test: parse_vdso.c vdso_test.c
-vdso_standalone_test_x86: vdso_standalone_test_x86.c parse_vdso.c
+$(OUTPUT)/vdso_test: parse_vdso.c vdso_test.c
+$(OUTPUT)/vdso_standalone_test_x86: vdso_standalone_test_x86.c parse_vdso.c
         $(CC) $(CFLAGS) $(CFLAGS_vdso_standalone_test_x86) \
                 vdso_standalone_test_x86.c parse_vdso.c \
-                -o vdso_standalone_test_x86
+                -o $@
 
-include ../lib.mk
-clean:
-        rm -fr $(TEST_PROGS)
+EXTRA_CLEAN := $(TEST_PROGS)
 endif
diff --git a/tools/testing/selftests/vm/.gitignore b/tools/testing/selftests/vm/.gitignore
index 63c94d776e89..342c7bc9dc8c 100644
--- a/tools/testing/selftests/vm/.gitignore
+++ b/tools/testing/selftests/vm/.gitignore
@@ -11,3 +11,4 @@ mlock-intersect-test
 mlock-random-test
 virtual_address_range
 gup_benchmark
+va_128TBswitch
diff --git a/tools/testing/selftests/vm/run_vmtests b/tools/testing/selftests/vm/run_vmtests
index d2561895a021..22d564673830 100755
--- a/tools/testing/selftests/vm/run_vmtests
+++ b/tools/testing/selftests/vm/run_vmtests
@@ -2,25 +2,33 @@
 # SPDX-License-Identifier: GPL-2.0
 #please run as root
 
-#we need 256M, below is the size in kB
-needmem=262144
 mnt=./huge
 exitcode=0
 
-#get pagesize and freepages from /proc/meminfo
+#get huge pagesize and freepages from /proc/meminfo
 while read name size unit; do
         if [ "$name" = "HugePages_Free:" ]; then
                 freepgs=$size
         fi
         if [ "$name" = "Hugepagesize:" ]; then
-                pgsize=$size
+                hpgsize_KB=$size
         fi
 done < /proc/meminfo
 
+# Simple hugetlbfs tests have a hardcoded minimum requirement of
+# huge pages totaling 256MB (262144KB) in size.  The userfaultfd
+# hugetlb test requires a minimum of 2 * nr_cpus huge pages.  Take
+# both of these requirements into account and attempt to increase
+# number of huge pages available.
+nr_cpus=$(nproc)
+hpgsize_MB=$((hpgsize_KB / 1024))
+half_ufd_size_MB=$((((nr_cpus * hpgsize_MB + 127) / 128) * 128))
+needmem_KB=$((half_ufd_size_MB * 2 * 1024))
+
 #set proper nr_hugepages
-if [ -n "$freepgs" ] && [ -n "$pgsize" ]; then
+if [ -n "$freepgs" ] && [ -n "$hpgsize_KB" ]; then
         nr_hugepgs=`cat /proc/sys/vm/nr_hugepages`
-        needpgs=`expr $needmem / $pgsize`
+        needpgs=$((needmem_KB / hpgsize_KB))
         tries=2
         while [ $tries -gt 0 ] && [ $freepgs -lt $needpgs ]; do
                 lackpgs=$(( $needpgs - $freepgs ))
@@ -107,8 +115,9 @@ fi
 echo "---------------------------"
 echo "running userfaultfd_hugetlb"
 echo "---------------------------"
-# 256MB total huge pages == 128MB src and 128MB dst
-./userfaultfd hugetlb 128 32 $mnt/ufd_test_file
+# Test requires source and destination huge pages.  Size of source
+# (half_ufd_size_MB) is passed as argument to test.
+./userfaultfd hugetlb $half_ufd_size_MB 32 $mnt/ufd_test_file
 if [ $? -ne 0 ]; then
         echo "[FAIL]"
         exitcode=1
diff --git a/tools/usb/Makefile b/tools/usb/Makefile
index 4e6506078494..01d758d73b6d 100644
--- a/tools/usb/Makefile
+++ b/tools/usb/Makefile
@@ -1,7 +1,6 @@
 # SPDX-License-Identifier: GPL-2.0
 # Makefile for USB tools
 
-CC = $(CROSS_COMPILE)gcc
 PTHREAD_LIBS = -lpthread
 WARNINGS = -Wall -Wextra
 CFLAGS = $(WARNINGS) -g -I../include
diff --git a/tools/vm/Makefile b/tools/vm/Makefile
index be320b905ea7..20f6cf04377f 100644
--- a/tools/vm/Makefile
+++ b/tools/vm/Makefile
@@ -6,7 +6,6 @@ TARGETS=page-types slabinfo page_owner_sort
 LIB_DIR = ../lib/api
 LIBS = $(LIB_DIR)/libapi.a
 
-CC = $(CROSS_COMPILE)gcc
 CFLAGS = -Wall -Wextra -I../lib/
 LDFLAGS = $(LIBS)
 
diff --git a/tools/wmi/Makefile b/tools/wmi/Makefile
index e664f1167388..e0e87239126b 100644
--- a/tools/wmi/Makefile
+++ b/tools/wmi/Makefile
@@ -2,7 +2,6 @@ PREFIX ?= /usr
 SBINDIR ?= sbin
 INSTALL ?= install
 CFLAGS += -D__EXPORTED_HEADERS__ -I../../include/uapi -I../../include
-CC = $(CROSS_COMPILE)gcc
 
 TARGET = dell-smbios-example