Merge tag 'perf-core-for-mingo-5.1-20190311' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/core improvements and fixes from Arnaldo:

kernel:

  Stephane Eranian :

  - Restore mmap record type correctly when handling PERF_RECORD_MMAP2
    events, as the same template is used for all the threads interested
    in mmap events, some may want just PERF_RECORD_MMAP, while some
    may want the extra info in MMAP2 records.

perf probe:

  Adrian Hunter:

  - Fix getting the kernel map, because since changes related to x86 PTI
    entry trampolines handling, there are more than one kernel map.

perf script:

  Andi Kleen:

  - Support insn output for normal samples, i.e.:

    perf script -F ip,sym,insn --xed

    Will fetch the sample IP from the thread address space and feed it
    to Intel's XED disassembler, producing lines such as:

      ffffffffa4068804 native_write_msr            wrmsr
      ffffffffa415b95e __hrtimer_next_event_base   movq  0x18(%rax), %rdx

    That match 'perf annotate's output.

  - Make the --cpu filter apply to  PERF_RECORD_COMM/FORK/... events, in
    addition to PERF_RECORD_SAMPLE.

perf report:

  - Add a new --samples option to save a small random number of samples
    per hist entry, using a reservoir technique to select a representative
    number of samples.

    Then allow browsing the samples using 'perf script' as part of the hist
    entry context menu. This automatically adds the right filters, so only
    the thread or CPU of the sample is displayed. Then we use less' search
    functionality to directly jump to the time stamp of the selected sample.

    It uses different menus for assembler and source display.  Assembler
    needs xed installed and source needs debuginfo.

  - Fix the UI browser scripts pop up menu when there are many scripts
    available.

perf report:

  Andi Kleen:

  - Add 'time' sort option. E.g.:

    % perf report --sort time,overhead,symbol --time-quantum 1ms --stdio
    ...
         0.67%  277061.87300  [.] _dl_start
         0.50%  277061.87300  [.] f1
         0.50%  277061.87300  [.] f2
         0.33%  277061.87300  [.] main
         0.29%  277061.87300  [.] _dl_lookup_symbol_x
         0.29%  277061.87300  [.] dl_main
         0.29%  277061.87300  [.] do_lookup_x
         0.17%  277061.87300  [.] _dl_debug_initialize
         0.17%  277061.87300  [.] _dl_init_paths
         0.08%  277061.87300  [.] check_match
         0.04%  277061.87300  [.] _dl_count_modids
         1.33%  277061.87400  [.] f1
         1.33%  277061.87400  [.] f2
         1.33%  277061.87400  [.] main
         1.17%  277061.87500  [.] main
         1.08%  277061.87500  [.] f1
         1.08%  277061.87500  [.] f2
         1.00%  277061.87600  [.] main
         0.83%  277061.87600  [.] f1
         0.83%  277061.87600  [.] f2
         1.00%  277061.87700  [.] main

tools headers:

  Arnaldo Carvalho de Melo:

  - Update x86's syscall_64.tbl, no change in tools/perf behaviour.

  -  Sync copies asm-generic/unistd.h and linux/in with the kernel sources.

perf data:

  Jiri Olsa:

  - Prep work to support having perf.data stored as a directory, with one
    file per CPU, that ultimately will allow having one ring buffer reading
    thread per CPU.

Vendor events:

  Martin Liška:

  - perf PMU events for AMD Family 17h.

perf script python:

  Tony Jones:

  - Add python3 support for the remaining Intel PT related scripts, with
    these we should have a clean build of perf with python3 while still
    supporting the build with python2.

libbpf:

  Arnaldo Carvalho de Melo:

  - Fix the build on uCLibc, adding the missing stdarg.h since we use
    va_list in one typedef.

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

46 files changed, 1931 insertions, 287 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1032a16bd186..72d06e302e99 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7189,6 +7189,7 @@ static void perf_event_mmap_output(struct perf_event *event,
 	struct perf_output_handle handle;
 	struct perf_sample_data sample;
 	int size = mmap_event->event_id.header.size;
+	u32 type = mmap_event->event_id.header.type;
 	int ret;
 
 	if (!perf_event_mmap_match(event, data))
@@ -7232,6 +7233,7 @@ static void perf_event_mmap_output(struct perf_event *event,
 	perf_output_end(&handle);
 out:
 	mmap_event->event_id.header.size = size;
+	mmap_event->event_id.header.type = type;
 }
 
 static void perf_event_mmap_event(struct perf_mmap_event *mmap_event)
diff --git a/tools/arch/arm64/include/uapi/asm/unistd.h b/tools/arch/arm64/include/uapi/asm/unistd.h
index dae1584cf017..4703d218663a 100644
--- a/tools/arch/arm64/include/uapi/asm/unistd.h
+++ b/tools/arch/arm64/include/uapi/asm/unistd.h
@@ -17,5 +17,7 @@
 
 #define __ARCH_WANT_RENAMEAT
 #define __ARCH_WANT_NEW_STAT
+#define __ARCH_WANT_SET_GET_RLIMIT
+#define __ARCH_WANT_TIME32_SYSCALLS
 
 #include <asm-generic/unistd.h>
diff --git a/tools/include/uapi/asm-generic/unistd.h b/tools/include/uapi/asm-generic/unistd.h
index d90127298f12..12cdf611d217 100644
--- a/tools/include/uapi/asm-generic/unistd.h
+++ b/tools/include/uapi/asm-generic/unistd.h
@@ -38,8 +38,10 @@ __SYSCALL(__NR_io_destroy, sys_io_destroy)
 __SC_COMP(__NR_io_submit, sys_io_submit, compat_sys_io_submit)
 #define __NR_io_cancel 3
 __SYSCALL(__NR_io_cancel, sys_io_cancel)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_io_getevents 4
-__SC_COMP(__NR_io_getevents, sys_io_getevents, compat_sys_io_getevents)
+__SC_3264(__NR_io_getevents, sys_io_getevents_time32, sys_io_getevents)
+#endif
 
 /* fs/xattr.c */
 #define __NR_setxattr 5
@@ -179,7 +181,7 @@ __SYSCALL(__NR_fchownat, sys_fchownat)
 #define __NR_fchown 55
 __SYSCALL(__NR_fchown, sys_fchown)
 #define __NR_openat 56
-__SC_COMP(__NR_openat, sys_openat, compat_sys_openat)
+__SYSCALL(__NR_openat, sys_openat)
 #define __NR_close 57
 __SYSCALL(__NR_close, sys_close)
 #define __NR_vhangup 58
@@ -222,10 +224,12 @@ __SC_COMP(__NR_pwritev, sys_pwritev, compat_sys_pwritev)
 __SYSCALL(__NR3264_sendfile, sys_sendfile64)
 
 /* fs/select.c */
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_pselect6 72
-__SC_COMP(__NR_pselect6, sys_pselect6, compat_sys_pselect6)
+__SC_COMP_3264(__NR_pselect6, sys_pselect6_time32, sys_pselect6, compat_sys_pselect6_time32)
 #define __NR_ppoll 73
-__SC_COMP(__NR_ppoll, sys_ppoll, compat_sys_ppoll)
+__SC_COMP_3264(__NR_ppoll, sys_ppoll_time32, sys_ppoll, compat_sys_ppoll_time32)
+#endif
 
 /* fs/signalfd.c */
 #define __NR_signalfd4 74
@@ -269,16 +273,20 @@ __SC_COMP(__NR_sync_file_range, sys_sync_file_range, \
 /* fs/timerfd.c */
 #define __NR_timerfd_create 85
 __SYSCALL(__NR_timerfd_create, sys_timerfd_create)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_timerfd_settime 86
-__SC_COMP(__NR_timerfd_settime, sys_timerfd_settime, \
-	  compat_sys_timerfd_settime)
+__SC_3264(__NR_timerfd_settime, sys_timerfd_settime32, \
+	  sys_timerfd_settime)
 #define __NR_timerfd_gettime 87
-__SC_COMP(__NR_timerfd_gettime, sys_timerfd_gettime, \
-	  compat_sys_timerfd_gettime)
+__SC_3264(__NR_timerfd_gettime, sys_timerfd_gettime32, \
+	  sys_timerfd_gettime)
+#endif
 
 /* fs/utimes.c */
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_utimensat 88
-__SC_COMP(__NR_utimensat, sys_utimensat, compat_sys_utimensat)
+__SC_3264(__NR_utimensat, sys_utimensat_time32, sys_utimensat)
+#endif
 
 /* kernel/acct.c */
 #define __NR_acct 89
@@ -309,8 +317,10 @@ __SYSCALL(__NR_set_tid_address, sys_set_tid_address)
 __SYSCALL(__NR_unshare, sys_unshare)
 
 /* kernel/futex.c */
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_futex 98
-__SC_COMP(__NR_futex, sys_futex, compat_sys_futex)
+__SC_3264(__NR_futex, sys_futex_time32, sys_futex)
+#endif
 #define __NR_set_robust_list 99
 __SC_COMP(__NR_set_robust_list, sys_set_robust_list, \
 	  compat_sys_set_robust_list)
@@ -319,8 +329,10 @@ __SC_COMP(__NR_get_robust_list, sys_get_robust_list, \
 	  compat_sys_get_robust_list)
 
 /* kernel/hrtimer.c */
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_nanosleep 101
-__SC_COMP(__NR_nanosleep, sys_nanosleep, compat_sys_nanosleep)
+__SC_3264(__NR_nanosleep, sys_nanosleep_time32, sys_nanosleep)
+#endif
 
 /* kernel/itimer.c */
 #define __NR_getitimer 102
@@ -341,23 +353,29 @@ __SYSCALL(__NR_delete_module, sys_delete_module)
 /* kernel/posix-timers.c */
 #define __NR_timer_create 107
 __SC_COMP(__NR_timer_create, sys_timer_create, compat_sys_timer_create)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_timer_gettime 108
-__SC_COMP(__NR_timer_gettime, sys_timer_gettime, compat_sys_timer_gettime)
+__SC_3264(__NR_timer_gettime, sys_timer_gettime32, sys_timer_gettime)
+#endif
 #define __NR_timer_getoverrun 109
 __SYSCALL(__NR_timer_getoverrun, sys_timer_getoverrun)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_timer_settime 110
-__SC_COMP(__NR_timer_settime, sys_timer_settime, compat_sys_timer_settime)
+__SC_3264(__NR_timer_settime, sys_timer_settime32, sys_timer_settime)
+#endif
 #define __NR_timer_delete 111
 __SYSCALL(__NR_timer_delete, sys_timer_delete)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_clock_settime 112
-__SC_COMP(__NR_clock_settime, sys_clock_settime, compat_sys_clock_settime)
+__SC_3264(__NR_clock_settime, sys_clock_settime32, sys_clock_settime)
 #define __NR_clock_gettime 113
-__SC_COMP(__NR_clock_gettime, sys_clock_gettime, compat_sys_clock_gettime)
+__SC_3264(__NR_clock_gettime, sys_clock_gettime32, sys_clock_gettime)
 #define __NR_clock_getres 114
-__SC_COMP(__NR_clock_getres, sys_clock_getres, compat_sys_clock_getres)
+__SC_3264(__NR_clock_getres, sys_clock_getres_time32, sys_clock_getres)
 #define __NR_clock_nanosleep 115
-__SC_COMP(__NR_clock_nanosleep, sys_clock_nanosleep, \
-	  compat_sys_clock_nanosleep)
+__SC_3264(__NR_clock_nanosleep, sys_clock_nanosleep_time32, \
+	  sys_clock_nanosleep)
+#endif
 
 /* kernel/printk.c */
 #define __NR_syslog 116
@@ -388,9 +406,11 @@ __SYSCALL(__NR_sched_yield, sys_sched_yield)
 __SYSCALL(__NR_sched_get_priority_max, sys_sched_get_priority_max)
 #define __NR_sched_get_priority_min 126
 __SYSCALL(__NR_sched_get_priority_min, sys_sched_get_priority_min)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_sched_rr_get_interval 127
-__SC_COMP(__NR_sched_rr_get_interval, sys_sched_rr_get_interval, \
-	  compat_sys_sched_rr_get_interval)
+__SC_3264(__NR_sched_rr_get_interval, sys_sched_rr_get_interval_time32, \
+	  sys_sched_rr_get_interval)
+#endif
 
 /* kernel/signal.c */
 #define __NR_restart_syscall 128
@@ -411,9 +431,11 @@ __SC_COMP(__NR_rt_sigaction, sys_rt_sigaction, compat_sys_rt_sigaction)
 __SC_COMP(__NR_rt_sigprocmask, sys_rt_sigprocmask, compat_sys_rt_sigprocmask)
 #define __NR_rt_sigpending 136
 __SC_COMP(__NR_rt_sigpending, sys_rt_sigpending, compat_sys_rt_sigpending)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_rt_sigtimedwait 137
-__SC_COMP(__NR_rt_sigtimedwait, sys_rt_sigtimedwait, \
-	  compat_sys_rt_sigtimedwait)
+__SC_COMP_3264(__NR_rt_sigtimedwait, sys_rt_sigtimedwait_time32, \
+	  sys_rt_sigtimedwait, compat_sys_rt_sigtimedwait_time32)
+#endif
 #define __NR_rt_sigqueueinfo 138
 __SC_COMP(__NR_rt_sigqueueinfo, sys_rt_sigqueueinfo, \
 	  compat_sys_rt_sigqueueinfo)
@@ -467,10 +489,15 @@ __SYSCALL(__NR_uname, sys_newuname)
 __SYSCALL(__NR_sethostname, sys_sethostname)
 #define __NR_setdomainname 162
 __SYSCALL(__NR_setdomainname, sys_setdomainname)
+
+#ifdef __ARCH_WANT_SET_GET_RLIMIT
+/* getrlimit and setrlimit are superseded with prlimit64 */
 #define __NR_getrlimit 163
 __SC_COMP(__NR_getrlimit, sys_getrlimit, compat_sys_getrlimit)
 #define __NR_setrlimit 164
 __SC_COMP(__NR_setrlimit, sys_setrlimit, compat_sys_setrlimit)
+#endif
+
 #define __NR_getrusage 165
 __SC_COMP(__NR_getrusage, sys_getrusage, compat_sys_getrusage)
 #define __NR_umask 166
@@ -481,12 +508,14 @@ __SYSCALL(__NR_prctl, sys_prctl)
 __SYSCALL(__NR_getcpu, sys_getcpu)
 
 /* kernel/time.c */
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_gettimeofday 169
 __SC_COMP(__NR_gettimeofday, sys_gettimeofday, compat_sys_gettimeofday)
 #define __NR_settimeofday 170
 __SC_COMP(__NR_settimeofday, sys_settimeofday, compat_sys_settimeofday)
 #define __NR_adjtimex 171
-__SC_COMP(__NR_adjtimex, sys_adjtimex, compat_sys_adjtimex)
+__SC_3264(__NR_adjtimex, sys_adjtimex_time32, sys_adjtimex)
+#endif
 
 /* kernel/timer.c */
 #define __NR_getpid 172
@@ -511,11 +540,13 @@ __SC_COMP(__NR_sysinfo, sys_sysinfo, compat_sys_sysinfo)
 __SC_COMP(__NR_mq_open, sys_mq_open, compat_sys_mq_open)
 #define __NR_mq_unlink 181
 __SYSCALL(__NR_mq_unlink, sys_mq_unlink)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_mq_timedsend 182
-__SC_COMP(__NR_mq_timedsend, sys_mq_timedsend, compat_sys_mq_timedsend)
+__SC_3264(__NR_mq_timedsend, sys_mq_timedsend_time32, sys_mq_timedsend)
 #define __NR_mq_timedreceive 183
-__SC_COMP(__NR_mq_timedreceive, sys_mq_timedreceive, \
-	  compat_sys_mq_timedreceive)
+__SC_3264(__NR_mq_timedreceive, sys_mq_timedreceive_time32, \
+	  sys_mq_timedreceive)
+#endif
 #define __NR_mq_notify 184
 __SC_COMP(__NR_mq_notify, sys_mq_notify, compat_sys_mq_notify)
 #define __NR_mq_getsetattr 185
@@ -536,8 +567,10 @@ __SC_COMP(__NR_msgsnd, sys_msgsnd, compat_sys_msgsnd)
 __SYSCALL(__NR_semget, sys_semget)
 #define __NR_semctl 191
 __SC_COMP(__NR_semctl, sys_semctl, compat_sys_semctl)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_semtimedop 192
-__SC_COMP(__NR_semtimedop, sys_semtimedop, compat_sys_semtimedop)
+__SC_COMP(__NR_semtimedop, sys_semtimedop, sys_semtimedop_time32)
+#endif
 #define __NR_semop 193
 __SYSCALL(__NR_semop, sys_semop)
 
@@ -658,8 +691,10 @@ __SC_COMP(__NR_rt_tgsigqueueinfo, sys_rt_tgsigqueueinfo, \
 __SYSCALL(__NR_perf_event_open, sys_perf_event_open)
 #define __NR_accept4 242
 __SYSCALL(__NR_accept4, sys_accept4)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_recvmmsg 243
-__SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg)
+__SC_COMP_3264(__NR_recvmmsg, sys_recvmmsg_time32, sys_recvmmsg, compat_sys_recvmmsg_time32)
+#endif
 
 /*
  * Architectures may provide up to 16 syscalls of their own
@@ -667,8 +702,10 @@ __SC_COMP(__NR_recvmmsg, sys_recvmmsg, compat_sys_recvmmsg)
  */
 #define __NR_arch_specific_syscall 244
 
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_wait4 260
 __SC_COMP(__NR_wait4, sys_wait4, compat_sys_wait4)
+#endif
 #define __NR_prlimit64 261
 __SYSCALL(__NR_prlimit64, sys_prlimit64)
 #define __NR_fanotify_init 262
@@ -678,10 +715,11 @@ __SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
 #define __NR_name_to_handle_at         264
 __SYSCALL(__NR_name_to_handle_at, sys_name_to_handle_at)
 #define __NR_open_by_handle_at         265
-__SC_COMP(__NR_open_by_handle_at, sys_open_by_handle_at, \
-	  compat_sys_open_by_handle_at)
+__SYSCALL(__NR_open_by_handle_at, sys_open_by_handle_at)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_clock_adjtime 266
-__SC_COMP(__NR_clock_adjtime, sys_clock_adjtime, compat_sys_clock_adjtime)
+__SC_3264(__NR_clock_adjtime, sys_clock_adjtime32, sys_clock_adjtime)
+#endif
 #define __NR_syncfs 267
 __SYSCALL(__NR_syncfs, sys_syncfs)
 #define __NR_setns 268
@@ -734,15 +772,60 @@ __SYSCALL(__NR_pkey_alloc,    sys_pkey_alloc)
 __SYSCALL(__NR_pkey_free,     sys_pkey_free)
 #define __NR_statx 291
 __SYSCALL(__NR_statx,     sys_statx)
+#if defined(__ARCH_WANT_TIME32_SYSCALLS) || __BITS_PER_LONG != 32
 #define __NR_io_pgetevents 292
-__SC_COMP(__NR_io_pgetevents, sys_io_pgetevents, compat_sys_io_pgetevents)
+__SC_COMP_3264(__NR_io_pgetevents, sys_io_pgetevents_time32, sys_io_pgetevents, compat_sys_io_pgetevents)
+#endif
 #define __NR_rseq 293
 __SYSCALL(__NR_rseq, sys_rseq)
 #define __NR_kexec_file_load 294
 __SYSCALL(__NR_kexec_file_load,     sys_kexec_file_load)
+/* 295 through 402 are unassigned to sync up with generic numbers, don't use */
+#if __BITS_PER_LONG == 32
+#define __NR_clock_gettime64 403
+__SYSCALL(__NR_clock_gettime64, sys_clock_gettime)
+#define __NR_clock_settime64 404
+__SYSCALL(__NR_clock_settime64, sys_clock_settime)
+#define __NR_clock_adjtime64 405
+__SYSCALL(__NR_clock_adjtime64, sys_clock_adjtime)
+#define __NR_clock_getres_time64 406
+__SYSCALL(__NR_clock_getres_time64, sys_clock_getres)
+#define __NR_clock_nanosleep_time64 407
+__SYSCALL(__NR_clock_nanosleep_time64, sys_clock_nanosleep)
+#define __NR_timer_gettime64 408
+__SYSCALL(__NR_timer_gettime64, sys_timer_gettime)
+#define __NR_timer_settime64 409
+__SYSCALL(__NR_timer_settime64, sys_timer_settime)
+#define __NR_timerfd_gettime64 410
+__SYSCALL(__NR_timerfd_gettime64, sys_timerfd_gettime)
+#define __NR_timerfd_settime64 411
+__SYSCALL(__NR_timerfd_settime64, sys_timerfd_settime)
+#define __NR_utimensat_time64 412
+__SYSCALL(__NR_utimensat_time64, sys_utimensat)
+#define __NR_pselect6_time64 413
+__SC_COMP(__NR_pselect6_time64, sys_pselect6, compat_sys_pselect6_time64)
+#define __NR_ppoll_time64 414
+__SC_COMP(__NR_ppoll_time64, sys_ppoll, compat_sys_ppoll_time64)
+#define __NR_io_pgetevents_time64 416
+__SYSCALL(__NR_io_pgetevents_time64, sys_io_pgetevents)
+#define __NR_recvmmsg_time64 417
+__SC_COMP(__NR_recvmmsg_time64, sys_recvmmsg, compat_sys_recvmmsg_time64)
+#define __NR_mq_timedsend_time64 418
+__SYSCALL(__NR_mq_timedsend_time64, sys_mq_timedsend)
+#define __NR_mq_timedreceive_time64 419
+__SYSCALL(__NR_mq_timedreceive_time64, sys_mq_timedreceive)
+#define __NR_semtimedop_time64 420
+__SYSCALL(__NR_semtimedop_time64, sys_semtimedop)
+#define __NR_rt_sigtimedwait_time64 421
+__SC_COMP(__NR_rt_sigtimedwait_time64, sys_rt_sigtimedwait, compat_sys_rt_sigtimedwait_time64)
+#define __NR_futex_time64 422
+__SYSCALL(__NR_futex_time64, sys_futex)
+#define __NR_sched_rr_get_interval_time64 423
+__SYSCALL(__NR_sched_rr_get_interval_time64, sys_sched_rr_get_interval)
+#endif
 
 #undef __NR_syscalls
-#define __NR_syscalls 295
+#define __NR_syscalls 424
 
 /*
  * 32 bit systems traditionally used different
diff --git a/tools/include/uapi/linux/in.h b/tools/include/uapi/linux/in.h
index a55cb8b10165..e7ad9d350a28 100644
--- a/tools/include/uapi/linux/in.h
+++ b/tools/include/uapi/linux/in.h
@@ -292,10 +292,11 @@ struct sockaddr_in {
 #define	IN_LOOPBACK(a)		((((long int) (a)) & 0xff000000) == 0x7f000000)
 
 /* Defines for Multicast INADDR */
-#define INADDR_UNSPEC_GROUP   	0xe0000000U	/* 224.0.0.0   */
-#define INADDR_ALLHOSTS_GROUP 	0xe0000001U	/* 224.0.0.1   */
-#define INADDR_ALLRTRS_GROUP    0xe0000002U	/* 224.0.0.2 */
-#define INADDR_MAX_LOCAL_GROUP  0xe00000ffU	/* 224.0.0.255 */
+#define INADDR_UNSPEC_GROUP		0xe0000000U	/* 224.0.0.0   */
+#define INADDR_ALLHOSTS_GROUP		0xe0000001U	/* 224.0.0.1   */
+#define INADDR_ALLRTRS_GROUP		0xe0000002U	/* 224.0.0.2 */
+#define INADDR_ALLSNOOPERS_GROUP	0xe000006aU	/* 224.0.0.106 */
+#define INADDR_MAX_LOCAL_GROUP		0xe00000ffU	/* 224.0.0.255 */
 #endif
 
 /* <asm/byteorder.h> contains the htonl type stuff.. */
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index b4652aa1a58a..aa1521a51687 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -10,6 +10,7 @@
 #ifndef __LIBBPF_LIBBPF_H
 #define __LIBBPF_LIBBPF_H
 
+#include <stdarg.h>
 #include <stdio.h>
 #include <stdint.h>
 #include <stdbool.h>
diff --git a/tools/perf/Documentation/perf-config.txt b/tools/perf/Documentation/perf-config.txt
index 86f3dcc15f83..95054a8176a2 100644
--- a/tools/perf/Documentation/perf-config.txt
+++ b/tools/perf/Documentation/perf-config.txt
@@ -584,6 +584,20 @@ llvm.*::
 	llvm.opts::
 		Options passed to llc.
 
+samples.*::
+
+	samples.context::
+		Define how many ns worth of time to show
+		around samples in perf report sample context browser.
+
+scripts.*::
+
+	Any option defines a script that is added to the scripts menu
+	in the interactive perf browser and whose output is displayed.
+	The name of the option is the name, the value is a script command line.
+	The script gets the same options passed as a full perf script,
+	in particular -i perfdata file, --cpu, --tid
+
 SEE ALSO
 --------
 linkperf:perf[1]
diff --git a/tools/perf/Documentation/perf-report.txt b/tools/perf/Documentation/perf-report.txt
index 1a27bfe05039..f441baa794ce 100644
--- a/tools/perf/Documentation/perf-report.txt
+++ b/tools/perf/Documentation/perf-report.txt
@@ -105,6 +105,8 @@ OPTIONS
 	guest machine
 	- sample: Number of sample
 	- period: Raw number of event count of sample
+	- time: Separate the samples by time stamp with the resolution specified by
+	--time-quantum (default 100ms). Specify with overhead and before it.
 
 	By default, comm, dso and symbol keys are used.
 	(i.e. --sort comm,dso,symbol)
@@ -459,6 +461,10 @@ include::itrace.txt[]
 --socket-filter::
 	Only report the samples on the processor socket that match with this filter
 
+--samples=N::
+	Save N individual samples for each histogram entry to show context in perf
+	report tui browser.
+
 --raw-trace::
 	When displaying traceevent output, do not use print fmt or plugins.
 
@@ -477,6 +483,9 @@ include::itrace.txt[]
 	Please note that not all mmaps are stored, options affecting which ones
 	are include 'perf record --data', for instance.
 
+--ns::
+	Show time stamps in nanoseconds.
+
 --stats::
 	Display overall events statistics without any further processing.
 	(like the one at the end of the perf report -D command)
@@ -494,6 +503,10 @@ include::itrace.txt[]
 	The period/hits keywords set the base the percentage is computed
 	on - the samples period or the number of samples (hits).
 
+--time-quantum::
+	Configure time quantum for time sort key. Default 100ms.
+	Accepts s, us, ms, ns units.
+
 include::callchain-overhead-calculation.txt[]
 
 SEE ALSO
diff --git a/tools/perf/Documentation/tips.txt b/tools/perf/Documentation/tips.txt
index 849599f39c5e..869965d629ce 100644
--- a/tools/perf/Documentation/tips.txt
+++ b/tools/perf/Documentation/tips.txt
@@ -15,6 +15,7 @@ To see callchains in a more compact form: perf report -g folded
 Show individual samples with: perf script
 Limit to show entries above 5% only: perf report --percent-limit 5
 Profiling branch (mis)predictions with: perf record -b / perf report
+To show assembler sample contexts use perf record -b / perf script -F +brstackinsn --xed
 Treat branches as callchains: perf report --branch-history
 To count events in every 1000 msec: perf stat -I 1000
 Print event counts in CSV format with: perf stat -x,
@@ -34,3 +35,9 @@ Show current config key-value pairs: perf config --list
 Show user configuration overrides: perf config --user --list
 To add Node.js USDT(User-Level Statically Defined Tracing): perf buildid-cache --add `which node`
 To report cacheline events from previous recording: perf c2c report
+To browse sample contexts use perf report --sample 10 and select in context menu
+To separate samples by time use perf report --sort time,overhead,sym
+To set sample time separation other than 100ms with --sort time use --time-quantum
+Add -I to perf report to sample register values visible in perf report context.
+To show IPC for sampling periods use perf record -e '{cycles,instructions}:S' and then browse context
+To show context switches in perf report sample context add --switch-events to perf record.
diff --git a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
index f0b1709a5ffb..2ae92fddb6d5 100644
--- a/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/tools/perf/arch/x86/entry/syscalls/syscall_64.tbl
@@ -343,6 +343,8 @@
 332	common	statx			__x64_sys_statx
 333	common	io_pgetevents		__x64_sys_io_pgetevents
 334	common	rseq			__x64_sys_rseq
+# don't use numbers 387 through 423, add new calls after the last
+# 'common' entry
 
 #
 # x32-specific system call numbers start at 512 to avoid cache impact
@@ -361,7 +363,7 @@
 520	x32	execve			__x32_compat_sys_execve/ptregs
 521	x32	ptrace			__x32_compat_sys_ptrace
 522	x32	rt_sigpending		__x32_compat_sys_rt_sigpending
-523	x32	rt_sigtimedwait		__x32_compat_sys_rt_sigtimedwait
+523	x32	rt_sigtimedwait		__x32_compat_sys_rt_sigtimedwait_time64
 524	x32	rt_sigqueueinfo		__x32_compat_sys_rt_sigqueueinfo
 525	x32	sigaltstack		__x32_compat_sys_sigaltstack
 526	x32	timer_create		__x32_compat_sys_timer_create
@@ -375,7 +377,7 @@
 534	x32	preadv			__x32_compat_sys_preadv64
 535	x32	pwritev			__x32_compat_sys_pwritev64
 536	x32	rt_tgsigqueueinfo	__x32_compat_sys_rt_tgsigqueueinfo
-537	x32	recvmmsg		__x32_compat_sys_recvmmsg
+537	x32	recvmmsg		__x32_compat_sys_recvmmsg_time64
 538	x32	sendmmsg		__x32_compat_sys_sendmmsg
 539	x32	process_vm_readv	__x32_compat_sys_process_vm_readv
 540	x32	process_vm_writev	__x32_compat_sys_process_vm_writev
diff --git a/tools/perf/arch/x86/util/Build b/tools/perf/arch/x86/util/Build
index 7aab0be5fc5f..47f9c56e744f 100644
--- a/tools/perf/arch/x86/util/Build
+++ b/tools/perf/arch/x86/util/Build
@@ -14,5 +14,6 @@ perf-$(CONFIG_LOCAL_LIBUNWIND)    += unwind-libunwind.o
 perf-$(CONFIG_LIBDW_DWARF_UNWIND) += unwind-libdw.o
 
 perf-$(CONFIG_AUXTRACE) += auxtrac