Merge tag 'perf-urgent-for-mingo-4.20-20181031' of git://git.kernel.org/pub/scm/linux/kernel/git/acme/linux into perf/urgent

Pull perf/urgent improvements and fixes from Arnaldo Carvalho de Melo:

- Fixes dealing with the removal of the fallback to looking up samples
  marked as userspace in the kernel maps, done recently:

  - For intel-pt, that was setting the synthesized header misc field
    as PERF_RECORD_MISC_USER, depending thus on the fallback to take
    place, now it sets as USER or KERNEL according to x86 specific
    knowledge. Also now it inserts the PERF_CONTEXT_{USER,KERNEL} into
    the PERF_SAMPLE_CALLCHAINs it synthesizes from hw traces (Adrian Hunter)

  - Similar fixes for the cs-etm ARM HW trace code, that used the Intel PT
    model as a starting point (Leo Yan)

  - For the "caller" callchain order, where the callchain returned by the
    kernel was simply reversed without taking into account the
    PERF_CONTEXT_{USER,KERNEL,etc} markers from where to define if an entry
    was for kernel or userspace, working just because the map lookup fallback
    was in place (David S. Miller)

- Allow for selecting if 'overwrite' mode should be used in 'perf top' and
  make the default for it not to be used. This is due to problems with the
  current implementation where the pausing used ends up making 'perf top'
  miss PERF_RECORD_{MMAP,FORK,EXEC,etc} events, which with short lifetime
  threads workloads leads quickly to many "unknown" maps (and thus symbols)
  to appear in the UI. Workloads with long thread lifetimes and with few
  metadata events can still use --overwrite to take advantage of the
  overwrite mode (Arnaldo Carvalho de Melo)

- Start 'perf top''s display thread earlier, so that the screen doesn't
  remain blank for too long at tool start (David S. Miller)

- Don't clone maps from parent when synthesizing forks, to avoid the inevitable
  flurry of overlapping maps as we process the synthesized MMAP2 events that get
  delivered shortly thereafter. (David S. Miller)

- Take pgoff into account when reporting elf to libdwfl, now the unwinding
  results are the same with elfutils's libdwfl and libunwind (Milian Wolff)

- Update lotsa kernel ABI headers (Arnaldo Carvalho de Melo)

- 'perf trace' syscall arg beautification improvements to allow for
  handling args such as mount's 'flags', where maks have to be ignored
  before considering what is left, that, if only zeroes, is suppressed
  like other args without such masks (Arnaldo Carvalho de Melo)

- Beautify mount's 'source' and 'flags' args (Arnaldo Carvalho de Melo)

- Generate mmap's flags bit constants from linux/mman.h and all the
  arch specific mman.h files, so that no changes in the main 'perf trace'
  source files is required when new flags get added (Arnaldo Carvalho de Melo)

- Consider syscall aliases, so that 'perf trace -e umount' works and we don't
  have to use 'umount2' (that works as well, just not required) (Arnaldo Carvalho de Melo)

Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>

55 files changed, 408 insertions, 135 deletions

diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 114fda12aa49..808b664343c9 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -242,6 +242,16 @@ Default is to monitor all CPUS.
 --hierarchy::
         Enable hierarchy output.
 
+--overwrite::
+        Enable this to use just the most recent records, which helps in high core count
+        machines such as Knights Landing/Mill, but right now is disabled by default as
+        the pausing used in this technique is leading to loss of metadata events such
+        as PERF_RECORD_MMAP which makes 'perf top' unable to resolve samples, leading
+        to lots of unknown samples appearing on the UI. Enable this if you are in such
+        machines and profiling a workload that doesn't creates short lived threads and/or
+        doesn't uses many executable mmap operations. Work is being planed to solve
+        this situation, till then, this will remain disabled by default.
+
 --force::
         Don't do ownership validation.
 
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 2f3bf025e305..3ccb4f0bf088 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -1,4 +1,5 @@
 include ../scripts/Makefile.include
+include ../scripts/Makefile.arch
 
 # The default target of this Makefile is...
 all:
@@ -385,6 +386,8 @@ export INSTALL SHELL_PATH
 SHELL = $(SHELL_PATH)
 
 linux_uapi_dir := $(srctree)/tools/include/uapi/linux
+asm_generic_uapi_dir := $(srctree)/tools/include/uapi/asm-generic
+arch_asm_uapi_dir := $(srctree)/tools/arch/$(ARCH)/include/uapi/asm/
 
 beauty_outdir := $(OUTPUT)trace/beauty/generated
 beauty_ioctl_outdir := $(beauty_outdir)/ioctl
@@ -460,6 +463,18 @@ madvise_behavior_tbl := $(srctree)/tools/perf/trace/beauty/madvise_behavior.sh
 $(madvise_behavior_array): $(madvise_hdr_dir)/mman-common.h $(madvise_behavior_tbl)
         $(Q)$(SHELL) '$(madvise_behavior_tbl)' $(madvise_hdr_dir) > $@
 
+mmap_flags_array := $(beauty_outdir)/mmap_flags_array.c
+mmap_flags_tbl := $(srctree)/tools/perf/trace/beauty/mmap_flags.sh
+
+$(mmap_flags_array): $(asm_generic_uapi_dir)/mman.h $(asm_generic_uapi_dir)/mman-common.h $(arch_asm_uapi_dir)/mman.h $(mmap_flags_tbl)
+        $(Q)$(SHELL) '$(mmap_flags_tbl)' $(asm_generic_uapi_dir) $(arch_asm_uapi_dir) > $@
+
+mount_flags_array := $(beauty_outdir)/mount_flags_array.c
+mount_flags_tbl := $(srctree)/tools/perf/trace/beauty/mount_flags.sh
+
+$(mount_flags_array): $(linux_uapi_dir)/fs.h $(mount_flags_tbl)
+        $(Q)$(SHELL) '$(mount_flags_tbl)' $(linux_uapi_dir) > $@
+
 prctl_option_array := $(beauty_outdir)/prctl_option_array.c
 prctl_hdr_dir := $(srctree)/tools/include/uapi/linux/
 prctl_option_tbl := $(srctree)/tools/perf/trace/beauty/prctl_option.sh
@@ -577,6 +592,8 @@ prepare: $(OUTPUT)PERF-VERSION-FILE $(OUTPUT)common-cmds.h archheaders $(drm_ioc
         $(socket_ipproto_array) \
         $(vhost_virtio_ioctl_array) \
         $(madvise_behavior_array) \
+        $(mmap_flags_array) \
+        $(mount_flags_array) \
         $(perf_ioctl_array) \
         $(prctl_option_array) \
         $(arch_errno_name_array)
@@ -863,6 +880,8 @@ clean:: $(LIBTRACEEVENT)-clean $(LIBAPI)-clean $(LIBBPF)-clean $(LIBSUBCMD)-clea
                 $(OUTPUT)tests/llvm-src-{base,kbuild,prologue,relocation}.c \
                 $(OUTPUT)pmu-events/pmu-events.c \
                 $(OUTPUT)$(madvise_behavior_array) \
+                $(OUTPUT)$(mmap_flags_array) \
+                $(OUTPUT)$(mount_flags_array) \
                 $(OUTPUT)$(drm_ioctl_array) \
                 $(OUTPUT)$(pkey_alloc_access_rights_array) \
                 $(OUTPUT)$(sndrv_ctl_ioctl_array) \
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index d21d8751e749..b2838de13de0 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -1134,11 +1134,6 @@ static int __cmd_top(struct perf_top *top)
         if (!target__none(&opts->target))
                 perf_evlist__enable(top->evlist);
 
-        /* Wait for a minimal set of events before starting the snapshot */
-        perf_evlist__poll(top->evlist, 100);
-
-        perf_top__mmap_read(top);
-
         ret = -1;
         if (pthread_create(&thread, NULL, (use_browser > 0 ? display_thread_tui :
                                                             display_thread), top)) {
@@ -1156,6 +1151,11 @@ static int __cmd_top(struct perf_top *top)
                 }
         }
 
+        /* Wait for a minimal set of events before starting the snapshot */
+        perf_evlist__poll(top->evlist, 100);
+
+        perf_top__mmap_read(top);
+
         while (!done) {
                 u64 hits = top->samples;
 
@@ -1257,7 +1257,14 @@ int cmd_top(int argc, const char **argv)
                                 .uses_mmap   = true,
                         },
                         .proc_map_timeout    = 500,
-                        .overwrite      = 1,
+                        /*
+                         * FIXME: This will lose PERF_RECORD_MMAP and other metadata
+                         * when we pause, fix that and reenable. Probably using a
+                         * separate evlist with a dummy event, i.e. a non-overwrite
+                         * ring buffer just for metadata events, while PERF_RECORD_SAMPLE
+                         * stays in overwrite mode. -acme
+                         * */
+                        .overwrite      = 0,
                 },
                 .max_stack           = sysctl__max_stack(),
                 .annotation_opts     = annotation__default_options,
@@ -1372,6 +1379,8 @@ int cmd_top(int argc, const char **argv)
                     "Show raw trace event output (do not use print fmt or plugins)"),
         OPT_BOOLEAN(0, "hierarchy", &symbol_conf.report_hierarchy,
                     "Show entries in a hierarchy"),
+        OPT_BOOLEAN(0, "overwrite", &top.record_opts.overwrite,
+                    "Use a backward ring buffer, default: no"),
         OPT_BOOLEAN(0, "force", &symbol_conf.force, "don't complain, do it"),
         OPT_UINTEGER(0, "num-thread-synthesize", &top.nr_threads_synthesize,
                         "number of thread to run event synthesize"),
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 7081d7ea12e5..dc8a6c4986ce 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -614,6 +614,7 @@ static size_t syscall_arg__scnprintf_getrandom_flags(char *bf, size_t size,
 
 struct syscall_arg_fmt {
         size_t     (*scnprintf)(char *bf, size_t size, struct syscall_arg *arg);
+        unsigned long (*mask_val)(struct syscall_arg *arg, unsigned long val);
         void       *parm;
         const char *name;
         bool       show_zero;
@@ -725,6 +726,10 @@ static struct syscall_fmt {
           .arg = { [0] = { .scnprintf = SCA_HEX,        /* addr */ },
                    [2] = { .scnprintf = SCA_MMAP_PROT,  /* prot */ },
                    [3] = { .scnprintf = SCA_MMAP_FLAGS, /* flags */ }, }, },
+        { .name     = "mount",
+          .arg = { [0] = { .scnprintf = SCA_FILENAME, /* dev_name */ },
+                   [3] = { .scnprintf = SCA_MOUNT_FLAGS, /* flags */
+                           .mask_val  = SCAMV_MOUNT_FLAGS, /* flags */ }, }, },
         { .name     = "mprotect",
           .arg = { [0] = { .scnprintf = SCA_HEX,        /* start */ },
                    [2] = { .scnprintf = SCA_MMAP_PROT,  /* prot */ }, }, },
@@ -834,7 +839,8 @@ static struct syscall_fmt {
           .arg = { [2] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
         { .name     = "tkill",
           .arg = { [1] = { .scnprintf = SCA_SIGNUM, /* sig */ }, }, },
-        { .name     = "umount2", .alias = "umount", },
+        { .name     = "umount2", .alias = "umount",
+          .arg = { [0] = { .scnprintf = SCA_FILENAME, /* name */ }, }, },
         { .name     = "uname", .alias = "newuname", },
         { .name     = "unlinkat",
           .arg = { [0] = { .scnprintf = SCA_FDAT, /* dfd */ }, }, },
@@ -858,6 +864,18 @@ static struct syscall_fmt *syscall_fmt__find(const char *name)
         return bsearch(name, syscall_fmts, nmemb, sizeof(struct syscall_fmt), syscall_fmt__cmp);
 }
 
+static struct syscall_fmt *syscall_fmt__find_by_alias(const char *alias)
+{
+        int i, nmemb = ARRAY_SIZE(syscall_fmts);
+
+        for (i = 0; i < nmemb; ++i) {
+                if (syscall_fmts[i].alias && strcmp(syscall_fmts[i].alias, alias) == 0)
+                        return &syscall_fmts[i];
+        }
+
+        return NULL;
+}
+
 /*
  * is_exit: is this "exit" or "exit_group"?
  * is_open: is this "open" or "openat"? To associate the fd returned in sys_exit with the pathname in sys_enter.
@@ -1487,6 +1505,19 @@ static size_t syscall__scnprintf_name(struct syscall *sc, char *bf, size_t size,
         return scnprintf(bf, size, "arg%d: ", arg->idx);
 }
 
+/*
+ * Check if the value is in fact zero, i.e. mask whatever needs masking, such
+ * as mount 'flags' argument that needs ignoring some magic flag, see comment
+ * in tools/perf/trace/beauty/mount_flags.c
+ */
+static unsigned long syscall__mask_val(struct syscall *sc, struct syscall_arg *arg, unsigned long val)
+{
+        if (sc->arg_fmt && sc->arg_fmt[arg->idx].mask_val)
+                return sc->arg_fmt[arg->idx].mask_val(arg, val);
+
+        return val;
+}
+
 static size_t syscall__scnprintf_val(struct syscall *sc, char *bf, size_t size,
                                      struct syscall_arg *arg, unsigned long val)
 {
@@ -1535,6 +1566,11 @@ static size_t syscall__scnprintf_args(struct syscall *sc, char *bf, size_t size,
                                 continue;
 
                         val = syscall_arg__val(&arg, arg.idx);
+                        /*
+                         * Some syscall args need some mask, most don't and
+                         * return val untouched.
+                         */
+                        val = syscall__mask_val(sc, &arg, val);
 
                         /*
                          * Suppress this argument if its value is zero and
@@ -3173,6 +3209,7 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
         int len = strlen(str) + 1, err = -1, list, idx;
         char *strace_groups_dir = system_path(STRACE_GROUPS_DIR);
         char group_name[PATH_MAX];
+        struct syscall_fmt *fmt;
 
         if (strace_groups_dir == NULL)
                 return -1;
@@ -3190,12 +3227,19 @@ static int trace__parse_events_option(const struct option *opt, const char *str,
                 if (syscalltbl__id(trace->sctbl, s) >= 0 ||
                     syscalltbl__strglobmatch_first(trace->sctbl, s, &idx) >= 0) {
                         list = 1;
+                        goto do_concat;
+                }
+
+                fmt = syscall_fmt__find_by_alias(s);
+                if (fmt != NULL) {
+                        list = 1;
+                        s = fmt->name;
                 } else {
                         path__join(group_name, sizeof(group_name), strace_groups_dir, s);
                         if (access(group_name, R_OK) == 0)
                                 list = 1;
                 }
-
+do_concat:
                 if (lists[list]) {
                         sprintf(lists[list] + strlen(lists[list]), ",%s", s);
                 } else {
diff --git a/tools/perf/check-headers.sh b/tools/perf/check-headers.sh
index c72cc73a6b09..9531f7bd7d9b 100755
--- a/tools/perf/check-headers.sh
+++ b/tools/perf/check-headers.sh
@@ -5,6 +5,7 @@ HEADERS='
 include/uapi/drm/drm.h
 include/uapi/drm/i915_drm.h
 include/uapi/linux/fcntl.h
+include/uapi/linux/fs.h
 include/uapi/linux/kcmp.h
 include/uapi/linux/kvm.h
 include/uapi/linux/in.h
diff --git a/tools/perf/trace/beauty/Build b/tools/perf/trace/beauty/Build
index c3b0afd67760..304313073242 100644
--- a/tools/perf/trace/beauty/Build
+++ b/tools/perf/trace/beauty/Build
@@ -5,6 +5,7 @@ ifeq ($(SRCARCH),$(filter $(SRCARCH),x86))
 libperf-y += ioctl.o
 endif
 libperf-y += kcmp.o
+libperf-y += mount_flags.o
 libperf-y += pkey_alloc.o
 libperf-y += prctl.o
 libperf-y += sockaddr.o
diff --git a/tools/perf/trace/beauty/beauty.h b/tools/perf/trace/beauty/beauty.h
index 2570152d3909..039c29039b2c 100644
--- a/tools/perf/trace/beauty/beauty.h
+++ b/tools/perf/trace/beauty/beauty.h
@@ -24,6 +24,7 @@ struct strarray {
 }
 
 size_t strarray__scnprintf(struct strarray *sa, char *bf, size_t size, const char *intfmt, int val);
+size_t strarray__scnprintf_flags(struct strarray *sa, char *bf, size_t size, unsigned long flags);
 
 struct trace;
 struct thread;
@@ -122,6 +123,12 @@ size_t syscall_arg__scnprintf_kcmp_type(char *bf, size_t size, struct syscall_ar
 size_t syscall_arg__scnprintf_kcmp_idx(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_KCMP_IDX syscall_arg__scnprintf_kcmp_idx
 
+unsigned long syscall_arg__mask_val_mount_flags(struct syscall_arg *arg, unsigned long flags);
+#define SCAMV_MOUNT_FLAGS syscall_arg__mask_val_mount_flags
+
+size_t syscall_arg__scnprintf_mount_flags(char *bf, size_t size, struct syscall_arg *arg);
+#define SCA_MOUNT_FLAGS syscall_arg__scnprintf_mount_flags
+
 size_t syscall_arg__scnprintf_pkey_alloc_access_rights(char *bf, size_t size, struct syscall_arg *arg);
 #define SCA_PKEY_ALLOC_ACCESS_RIGHTS syscall_arg__scnprintf_pkey_alloc_access_rights
 
diff --git a/tools/perf/trace/beauty/clone.c b/tools/perf/trace/beauty/clone.c
index d64d049ab991..010406500c30 100644
--- a/tools/perf/trace/beauty/clone.c
+++ b/tools/perf/trace/beauty/clone.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/cone.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/drm_ioctl.sh b/tools/perf/trace/beauty/drm_ioctl.sh
index 9d3816815e60..9aa94fd523a9 100755
--- a/tools/perf/trace/beauty/drm_ioctl.sh
+++ b/tools/perf/trace/beauty/drm_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/drm/
 
diff --git a/tools/perf/trace/beauty/eventfd.c b/tools/perf/trace/beauty/eventfd.c
index 5d6a477a6400..db5b9b492113 100644
--- a/tools/perf/trace/beauty/eventfd.c
+++ b/tools/perf/trace/beauty/eventfd.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #ifndef EFD_SEMAPHORE
 #define EFD_SEMAPHORE           1
 #endif
diff --git a/tools/perf/trace/beauty/fcntl.c b/tools/perf/trace/beauty/fcntl.c
index 9e8900c13cb1..e6de31674e24 100644
--- a/tools/perf/trace/beauty/fcntl.c
+++ b/tools/perf/trace/beauty/fcntl.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/fcntl.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/flock.c b/tools/perf/trace/beauty/flock.c
index c4ff6ad30b06..cf02ae5f0ba6 100644
--- a/tools/perf/trace/beauty/flock.c
+++ b/tools/perf/trace/beauty/flock.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 
 #include "trace/beauty/beauty.h"
 #include <linux/kernel.h>
diff --git a/tools/perf/trace/beauty/futex_op.c b/tools/perf/trace/beauty/futex_op.c
index 61850fbc85ff..1136bde56406 100644
--- a/tools/perf/trace/beauty/futex_op.c
+++ b/tools/perf/trace/beauty/futex_op.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <linux/futex.h>
 
 #ifndef FUTEX_WAIT_BITSET
diff --git a/tools/perf/trace/beauty/futex_val3.c b/tools/perf/trace/beauty/futex_val3.c
index 26f6b3253511..138b7d588a70 100644
--- a/tools/perf/trace/beauty/futex_val3.c
+++ b/tools/perf/trace/beauty/futex_val3.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <linux/futex.h>
 
 #ifndef FUTEX_BITSET_MATCH_ANY
diff --git a/tools/perf/trace/beauty/ioctl.c b/tools/perf/trace/beauty/ioctl.c
index 1be3b4cf0827..5d2a7fd8d407 100644
--- a/tools/perf/trace/beauty/ioctl.c
+++ b/tools/perf/trace/beauty/ioctl.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/ioctl.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/kcmp.c b/tools/perf/trace/beauty/kcmp.c
index f62040eb9d5c..b276a274f203 100644
--- a/tools/perf/trace/beauty/kcmp.c
+++ b/tools/perf/trace/beauty/kcmp.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/kcmp.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/kcmp_type.sh b/tools/perf/trace/beauty/kcmp_type.sh
index a3c304caa336..df8b17486d57 100755
--- a/tools/perf/trace/beauty/kcmp_type.sh
+++ b/tools/perf/trace/beauty/kcmp_type.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/kvm_ioctl.sh b/tools/perf/trace/beauty/kvm_ioctl.sh
index c4699fd46bb6..4ce54f5bf756 100755
--- a/tools/perf/trace/beauty/kvm_ioctl.sh
+++ b/tools/perf/trace/beauty/kvm_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/madvise_behavior.sh b/tools/perf/trace/beauty/madvise_behavior.sh
index 431639eb4d29..4527d290cdfc 100755
--- a/tools/perf/trace/beauty/madvise_behavior.sh
+++ b/tools/perf/trace/beauty/madvise_behavior.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
diff --git a/tools/perf/trace/beauty/mmap.c b/tools/perf/trace/beauty/mmap.c
index 9f68077b241b..c534bd96ef5c 100644
--- a/tools/perf/trace/beauty/mmap.c
+++ b/tools/perf/trace/beauty/mmap.c
@@ -1,5 +1,6 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <uapi/linux/mman.h>
+#include <linux/log2.h>
 
 static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
                                                struct syscall_arg *arg)
@@ -30,50 +31,23 @@ static size_t syscall_arg__scnprintf_mmap_prot(char *bf, size_t size,
 
 #define SCA_MMAP_PROT syscall_arg__scnprintf_mmap_prot
 
+static size_t mmap__scnprintf_flags(unsigned long flags, char *bf, size_t size)
+{
+#include "trace/beauty/generated/mmap_flags_array.c"
+       static DEFINE_STRARRAY(mmap_flags);
+
+       return strarray__scnprintf_flags(&strarray__mmap_flags, bf, size, flags);
+}
+
 static size_t syscall_arg__scnprintf_mmap_flags(char *bf, size_t size,
                                                 struct syscall_arg *arg)
 {
-        int printed = 0, flags = arg->val;
+        unsigned long flags = arg->val;
 
         if (flags & MAP_ANONYMOUS)
                 arg->mask |= (1 << 4) | (1 << 5); /* Mask 4th ('fd') and 5th ('offset') args, ignored */
 
-#define P_MMAP_FLAG(n) \
-        if (flags & MAP_##n) { \
-                printed += scnprintf(bf + printed, size - printed, "%s%s", printed ? "|" : "", #n); \
-                flags &= ~MAP_##n; \
-        }
-
-        P_MMAP_FLAG(SHARED);
-        P_MMAP_FLAG(PRIVATE);
-#ifdef MAP_32BIT
-        P_MMAP_FLAG(32BIT);
-#endif
-        P_MMAP_FLAG(ANONYMOUS);
-        P_MMAP_FLAG(DENYWRITE);
-        P_MMAP_FLAG(EXECUTABLE);
-        P_MMAP_FLAG(FILE);
-        P_MMAP_FLAG(FIXED);
-#ifdef MAP_FIXED_NOREPLACE
-        P_MMAP_FLAG(FIXED_NOREPLACE);
-#endif
-        P_MMAP_FLAG(GROWSDOWN);
-        P_MMAP_FLAG(HUGETLB);
-        P_MMAP_FLAG(LOCKED);
-        P_MMAP_FLAG(NONBLOCK);
-        P_MMAP_FLAG(NORESERVE);
-        P_MMAP_FLAG(POPULATE);
-        P_MMAP_FLAG(STACK);
-        P_MMAP_FLAG(UNINITIALIZED);
-#ifdef MAP_SYNC
-        P_MMAP_FLAG(SYNC);
-#endif
-#undef P_MMAP_FLAG
-
-        if (flags)
-                printed += scnprintf(bf + printed, size - printed, "%s%#x", printed ? "|" : "", flags);
-
-        return printed;
+        return mmap__scnprintf_flags(flags, bf, size);
 }
 
 #define SCA_MMAP_FLAGS syscall_arg__scnprintf_mmap_flags
diff --git a/tools/perf/trace/beauty/mmap_flags.sh b/tools/perf/trace/beauty/mmap_flags.sh
new file mode 100755
index 000000000000..22c3fdca8975
--- /dev/null
+++ b/tools/perf/trace/beauty/mmap_flags.sh
@@ -0,0 +1,32 @@
+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+
+if [ $# -ne 2 ] ; then
+        [ $# -eq 1 ] && hostarch=$1 || hostarch=`uname -m | sed -e s/i.86/x86/ -e s/x86_64/x86/`
+        header_dir=tools/include/uapi/asm-generic
+        arch_header_dir=tools/arch/${hostarch}/include/uapi/asm
+else
+        header_dir=$1
+        arch_header_dir=$2
+fi
+
+arch_mman=${arch_header_dir}/mman.h
+
+# those in egrep -vw are flags, we want just the bits
+
+printf "static const char *mmap_flags[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MAP_([[:alnum:]_]+)[[:space:]]+(0x[[:xdigit:]]+)[[:space:]]*.*'
+egrep -q $regex ${arch_mman} && \
+(egrep $regex ${arch_mman} | \
+        sed -r "s/$regex/\2 \1/g"       | \
+        xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
+egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.*' ${arch_mman} &&
+(egrep $regex ${header_dir}/mman-common.h | \
+        egrep -vw 'MAP_(UNINITIALIZED|TYPE|SHARED_VALIDATE)' | \
+        sed -r "s/$regex/\2 \1/g"       | \
+        xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
+egrep -q '#[[:space:]]*include[[:space:]]+<uapi/asm-generic/mman.h>.*' ${arch_mman} &&
+(egrep $regex ${header_dir}/mman.h | \
+        sed -r "s/$regex/\2 \1/g"       | \
+        xargs printf "\t[ilog2(%s) + 1] = \"%s\",\n")
+printf "};\n"
diff --git a/tools/perf/trace/beauty/mode_t.c b/tools/perf/trace/beauty/mode_t.c
index d929ad7dd97b..6879d36d3004 100644
--- a/tools/perf/trace/beauty/mode_t.c
+++ b/tools/perf/trace/beauty/mode_t.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <unistd.h>
diff --git a/tools/perf/trace/beauty/mount_flags.c b/tools/perf/trace/beauty/mount_flags.c
new file mode 100644
index 000000000000..712935c6620a
--- /dev/null
+++ b/tools/perf/trace/beauty/mount_flags.c
@@ -0,0 +1,43 @@
+// SPDX-License-Identifier: LGPL-2.1
+/*
+ * trace/beauty/mount_flags.c
+ *
+ *  Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
+ */
+
+#include "trace/beauty/beauty.h"
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/log2.h>
+#include <sys/mount.h>
+
+static size_t mount__scnprintf_flags(unsigned long flags, char *bf, size_t size)
+{
+#include "trace/beauty/generated/mount_flags_array.c"
+        static DEFINE_STRARRAY(mount_flags);
+
+        return strarray__scnprintf_flags(&strarray__mount_flags, bf, size, flags);
+}
+
+unsigned long syscall_arg__mask_val_mount_flags(struct syscall_arg *arg __maybe_unused, unsigned long flags)
+{
+        // do_mount in fs/namespace.c:
+        /*
+         * Pre-0.97 versions of mount() didn't have a flags word.  When the
+         * flags word was introduced its top half was required to have the
+         * magic value 0xC0ED, and this remained so until 2.4.0-test9.
+         * Therefore, if this magic number is present, it carries no
+         * information and must be discarded.
+         */
+        if ((flags & MS_MGC_MSK) == MS_MGC_VAL)
+                flags &= ~MS_MGC_MSK;
+
+        return flags;
+}
+
+size_t syscall_arg__scnprintf_mount_flags(char *bf, size_t size, struct syscall_arg *arg)
+{
+        unsigned long flags = arg->val;
+
+        return mount__scnprintf_flags(flags, bf, size);
+}
diff --git a/tools/perf/trace/beauty/mount_flags.sh b/tools/perf/trace/beauty/mount_flags.sh
new file mode 100755
index 000000000000..45547573a1db
--- /dev/null
+++ b/tools/perf/trace/beauty/mount_flags.sh
@@ -0,0 +1,15 @@
+#!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
+
+[ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
+
+printf "static const char *mount_flags[] = {\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MS_([[:alnum:]_]+)[[:space:]]+([[:digit:]]+)[[:space:]]*.*'
+egrep $regex ${header_dir}/fs.h | egrep -v '(MSK|VERBOSE|MGC_VAL)\>' | \
+        sed -r "s/$regex/\2 \2 \1/g" | sort -n | \
+        xargs printf "\t[%s ? (ilog2(%s) + 1) : 0] = \"%s\",\n"
+regex='^[[:space:]]*#[[:space:]]*define[[:space:]]+MS_([[:alnum:]_]+)[[:space:]]+\(1<<([[:digit:]]+)\)[[:space:]]*.*'
+egrep $regex ${header_dir}/fs.h | \
+        sed -r "s/$regex/\2 \1/g" | \
+        xargs printf "\t[%s + 1] = \"%s\",\n"
+printf "};\n"
diff --git a/tools/perf/trace/beauty/msg_flags.c b/tools/perf/trace/beauty/msg_flags.c
index c064d6aae659..1b9d6306d274 100644
--- a/tools/perf/trace/beauty/msg_flags.c
+++ b/tools/perf/trace/beauty/msg_flags.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sys/types.h>
 #include <sys/socket.h>
 
diff --git a/tools/perf/trace/beauty/open_flags.c b/tools/perf/trace/beauty/open_flags.c
index 6aec6178a99d..cc673fec9184 100644
--- a/tools/perf/trace/beauty/open_flags.c
+++ b/tools/perf/trace/beauty/open_flags.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sys/types.h>
 #include <sys/stat.h>
 #include <fcntl.h>
diff --git a/tools/perf/trace/beauty/perf_event_open.c b/tools/perf/trace/beauty/perf_event_open.c
index 2bafd7c995ff..981185c1974b 100644
--- a/tools/perf/trace/beauty/perf_event_open.c
+++ b/tools/perf/trace/beauty/perf_event_open.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #ifndef PERF_FLAG_FD_NO_GROUP
 # define PERF_FLAG_FD_NO_GROUP          (1UL << 0)
 #endif
diff --git a/tools/perf/trace/beauty/perf_ioctl.sh b/tools/perf/trace/beauty/perf_ioctl.sh
index 6492c74df928..9aabd9743ef6 100755
--- a/tools/perf/trace/beauty/perf_ioctl.sh
+++ b/tools/perf/trace/beauty/perf_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/pid.c b/tools/perf/trace/beauty/pid.c
index 0313df342830..1a6acc46807b 100644
--- a/tools/perf/trace/beauty/pid.c
+++ b/tools/perf/trace/beauty/pid.c
@@ -1,4 +1,5 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
+
 size_t syscall_arg__scnprintf_pid(char *bf, size_t size, struct syscall_arg *arg)
 {
         int pid = arg->val;
diff --git a/tools/perf/trace/beauty/pkey_alloc.c b/tools/perf/trace/beauty/pkey_alloc.c
index 2ba784a3734a..1b8ed4cac815 100644
--- a/tools/perf/trace/beauty/pkey_alloc.c
+++ b/tools/perf/trace/beauty/pkey_alloc.c
@@ -1,40 +1,36 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/pkey_alloc.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
 #include <linux/kernel.h>
 #include <linux/log2.h>
 
-static size_t pkey_alloc__scnprintf_access_rights(int access_rights, char *bf, size_t size)
+size_t strarray__scnprintf_flags(struct strarray *sa, char *bf, size_t size, unsigned long flags)
 {
         int i, printed = 0;
 
-#include "trace/beauty/generated/pkey_alloc_access_rights_array.c"
-        static DEFINE_STRARRAY(pkey_alloc_access_rights);
-
-        if (access_rights == 0) {
-                const char *s = strarray__pkey_alloc_access_rights.entries[0];
+        if (flags == 0) {
+                const char *s = sa->entries[0];
                 if (s)
                         return scnprintf(bf, size, "%s", s);
                 return scnprintf(bf, size, "%d", 0);
         }
 
-        for (i = 1; i < strarray__pkey_alloc_access_rights.nr_entries; ++i) {
-                int bit = 1 << (i - 1);
+        for (i = 1; i < sa->nr_entries; ++i) {
+                unsigned long bit = 1UL << (i - 1);
 
-                if (!(access_rights & bit))
+                if (!(flags & bit))
                         continue;
 
                 if (printed != 0)
                         printed += scnprintf(bf + printed, size - printed, "|");
 
-                if (strarray__pkey_alloc_access_rights.entries[i] != NULL)
-                        printed += scnprintf(bf + printed, size - printed, "%s", strarray__pkey_alloc_access_rights.entries[i]);
+                if (sa->entries[i] != NULL)
+                        printed += scnprintf(bf + printed, size - printed, "%s", sa->entries[i]);
                 else
                         printed += scnprintf(bf + printed, size - printed, "0x%#", bit);
         }
@@ -42,6 +38,14 @@ static size_t pkey_alloc__scnprintf_access_rights(int access_rights, char *bf, s
         return printed;
 }
 
+static size_t pkey_alloc__scnprintf_access_rights(int access_rights, char *bf, size_t size)
+{
+#include "trace/beauty/generated/pkey_alloc_access_rights_array.c"
+        static DEFINE_STRARRAY(pkey_alloc_access_rights);
+
+        return strarray__scnprintf_flags(&strarray__pkey_alloc_access_rights, bf, size, access_rights);
+}
+
 size_t syscall_arg__scnprintf_pkey_alloc_access_rights(char *bf, size_t size, struct syscall_arg *arg)
 {
         unsigned long cmd = arg->val;
diff --git a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
index e0a51aeb20b2..f8f1b560cf8a 100755
--- a/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
+++ b/tools/perf/trace/beauty/pkey_alloc_access_rights.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/asm-generic/
 
diff --git a/tools/perf/trace/beauty/prctl.c b/tools/perf/trace/beauty/prctl.c
index 246130dad6c4..be7a5d395975 100644
--- a/tools/perf/trace/beauty/prctl.c
+++ b/tools/perf/trace/beauty/prctl.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/prctl.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/prctl_option.sh b/tools/perf/trace/beauty/prctl_option.sh
index f24722146ebe..d32f8f1124af 100755
--- a/tools/perf/trace/beauty/prctl_option.sh
+++ b/tools/perf/trace/beauty/prctl_option.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/sched_policy.c b/tools/perf/trace/beauty/sched_policy.c
index ba5096ae76b6..48f2b5c9aa3e 100644
--- a/tools/perf/trace/beauty/sched_policy.c
+++ b/tools/perf/trace/beauty/sched_policy.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sched.h>
 
 /*
diff --git a/tools/perf/trace/beauty/seccomp.c b/tools/perf/trace/beauty/seccomp.c
index b7097fd5fed9..e36156b19c70 100644
--- a/tools/perf/trace/beauty/seccomp.c
+++ b/tools/perf/trace/beauty/seccomp.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #ifndef SECCOMP_SET_MODE_STRICT
 #define SECCOMP_SET_MODE_STRICT 0
 #endif
diff --git a/tools/perf/trace/beauty/signum.c b/tools/perf/trace/beauty/signum.c
index bde18a53f090..587fec545b8a 100644
--- a/tools/perf/trace/beauty/signum.c
+++ b/tools/perf/trace/beauty/signum.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <signal.h>
 
 static size_t syscall_arg__scnprintf_signum(char *bf, size_t size, struct syscall_arg *arg)
diff --git a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
index eb511bb5fbd3..e0803b957593 100755
--- a/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_ctl_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
diff --git a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
index 6818392968b2..7a464a7bf913 100755
--- a/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
+++ b/tools/perf/trace/beauty/sndrv_pcm_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/sound/
 
diff --git a/tools/perf/trace/beauty/sockaddr.c b/tools/perf/trace/beauty/sockaddr.c
index 71a79f72d9d9..9410ad230f10 100644
--- a/tools/perf/trace/beauty/sockaddr.c
+++ b/tools/perf/trace/beauty/sockaddr.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 // Copyright (C) 2018, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/socket.c b/tools/perf/trace/beauty/socket.c
index 65227269384b..d971a2596417 100644
--- a/tools/perf/trace/beauty/socket.c
+++ b/tools/perf/trace/beauty/socket.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/socket.c
  *
diff --git a/tools/perf/trace/beauty/socket_ipproto.sh b/tools/perf/trace/beauty/socket_ipproto.sh
index a3cc24633bec..de0f2f29017f 100755
--- a/tools/perf/trace/beauty/socket_ipproto.sh
+++ b/tools/perf/trace/beauty/socket_ipproto.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/socket_type.c b/tools/perf/trace/beauty/socket_type.c
index bca26aef4a77..a63a9a332aa0 100644
--- a/tools/perf/trace/beauty/socket_type.c
+++ b/tools/perf/trace/beauty/socket_type.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sys/types.h>
 #include <sys/socket.h>
 
diff --git a/tools/perf/trace/beauty/statx.c b/tools/perf/trace/beauty/statx.c
index 5643b692af4c..630f2760dd66 100644
--- a/tools/perf/trace/beauty/statx.c
+++ b/tools/perf/trace/beauty/statx.c
@@ -1,9 +1,8 @@
+// SPDX-License-Identifier: LGPL-2.1
 /*
  * trace/beauty/statx.c
  *
  *  Copyright (C) 2017, Red Hat Inc, Arnaldo Carvalho de Melo <acme@redhat.com>
- *
- * Released under the GPL v2. (and only v2, not any later version)
  */
 
 #include "trace/beauty/beauty.h"
diff --git a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
index 0f6a5197d0be..439773daaf77 100755
--- a/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
+++ b/tools/perf/trace/beauty/vhost_virtio_ioctl.sh
@@ -1,4 +1,5 @@
 #!/bin/sh
+# SPDX-License-Identifier: LGPL-2.1
 
 [ $# -eq 1 ] && header_dir=$1 || header_dir=tools/include/uapi/linux/
 
diff --git a/tools/perf/trace/beauty/waitid_options.c b/tools/perf/trace/beauty/waitid_options.c
index 8465281a093d..42ff58ad613b 100644
--- a/tools/perf/trace/beauty/waitid_options.c
+++ b/tools/perf/trace/beauty/waitid_options.c
@@ -1,4 +1,4 @@
-// SPDX-License-Identifier: GPL-2.0
+// SPDX-License-Identifier: LGPL-2.1
 #include <sys/types.h>
 #include <sys/wait.h>
 
diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
index 3b37d66dc533..73430b73570d 100644
--- a/tools/perf/util/cs-etm.c
+++ b/tools/perf/util/cs-etm.c
@@ -244,6 +244,27 @@ static void cs_etm__free(struct perf_session *session)
         zfree(&aux);
 }
 
+static u8 cs_etm__cpu_mode(struct cs_etm_queue *etmq, u64 address)
+{
+        struct machine *machine;
+
+        machine = etmq->etm->machine;
+
+        if (address >= etmq->etm->kernel_start) {
+                if (machine__is_host(machine))
+                        return PERF_RECORD_MISC_KERNEL;
+                else
+                        return PERF_RECORD_MISC_GUEST_KERNEL;
+        } else {
+                if (machine__is_host(machine))
+                        return PERF_RECORD_MISC_USER;
+                else if (perf_guest)
+                        return PERF_RECORD_MISC_GUEST_USER;
+                else
+                        return PERF_RECORD_MISC_HYPERVISOR;
+        }
+}
+
 static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
                               size_t size, u8 *buffer)
 {
@@ -258,10 +279,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u64 address,
                 return -1;
 
         machine = etmq->etm->machine;
-        if (address >= etmq->etm->kernel_start)
-                cpumode = PERF_RECORD_MISC_KERNEL;
-        else
-                cpumode = PERF_RECORD_MISC_USER;
+        cpumode = cs_etm__cpu_mode(etmq, address);
 
         thread = etmq->thread;
         if (!thread) {
@@ -653,7 +671,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
         struct perf_sample sample = {.ip = 0,};
 
         event->sample.header.type = PERF_RECORD_SAMPLE;
-        event->sample.header.misc = PERF_RECORD_MISC_USER;
+        event->sample.header.misc = cs_etm__cpu_mode(etmq, addr);
         event->sample.header.size = sizeof(struct perf_event_header);
 
         sample.ip = addr;
@@ -665,7 +683,7 @@ static int cs_etm__synth_instruction_sample(struct cs_etm_queue *etmq,
         sample.cpu = etmq->packet->cpu;
         sample.flags = 0;
         sample.insn_len = 1;
-        sample.cpumode = event->header.misc;
+        sample.cpumode = event->sample.header.misc;
 
         if (etm->synth_opts.last_branch) {
                 cs_etm__copy_last_branch_rb(etmq);
@@ -706,12 +724,15 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
                 u64                     nr;
                 struct branch_entry     entries;
         } dummy_bs;
+        u64 ip;
+
+        ip = cs_etm__last_executed_instr(etmq->prev_packet);
 
         event->sample.header.type = PERF_RECORD_SAMPLE;
-        event->sample.header.misc = PERF_RECORD_MISC_USER;
+        event->sample.header.misc = cs_etm__cpu_mode(etmq, ip);
         event->sample.header.size = sizeof(struct perf_event_header);
 
-        sample.ip = cs_etm__last_executed_instr(etmq->prev_packet);
+        sample.ip = ip;
         sample.pid = etmq->pid;
         sample.tid = etmq->tid;
         sample.addr = cs_etm__first_executed_instr(etmq->packet);
@@ -720,7 +741,7 @@ static int cs_etm__synth_branch_sample(struct cs_etm_queue *etmq)
         sample.period = 1;
         sample.cpu = etmq->packet->cpu;
         sample.flags = 0;
-        sample.cpumode = PERF_RECORD_MISC_USER;
+        sample.cpumode = event->sample.header.misc;
 
         /*
          * perf report cannot handle events without a branch stack
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index bc646185f8d9..e9c108a6b1c3 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -308,6 +308,7 @@ static int perf_event__synthesize_fork(struct perf_tool *tool,
         event->fork.pid  = tgid;
         event->fork.tid  = pid;
         event->fork.header.type = PERF_RECORD_FORK;
+        event->fork.header.misc = PERF_RECORD_MISC_FORK_EXEC;
 
         event->fork.header.size = (sizeof(event->fork) + machine->id_hdr_size);
 
diff --git a/tools/perf/util/intel-bts.c b/tools/perf/util/intel-bts.c
index 3b3a3d55dca1..7b27d77306c2 100644
--- a/tools/perf/util/intel-bts.c
+++ b/tools/perf/util/intel-bts.c
@@ -269,6 +269,13 @@ static int intel_bts_do_fix_overlap(struct auxtrace_queue *queue,
         return 0;
 }
 
+static inline u8 intel_bts_cpumode(struct intel_bts *bts, uint64_t ip)
+{
+        return machine__kernel_ip(bts->machine, ip) ?
+               PERF_RECORD_MISC_KERNEL :
+               PERF_RECORD_MISC_USER;
+}
+
 static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
                                          struct branch *branch)
 {
@@ -281,12 +288,8 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
             bts->num_events++ <= bts->synth_opts.initial_skip)
                 return 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.cpumode = PERF_RECORD_MISC_USER;
         sample.ip = le64_to_cpu(branch->from);
+        sample.cpumode = intel_bts_cpumode(bts, sample.ip);
         sample.pid = btsq->pid;
         sample.tid = btsq->tid;
         sample.addr = le64_to_cpu(branch->to);
@@ -298,6 +301,10 @@ static int intel_bts_synth_branch_sample(struct intel_bts_queue *btsq,
         sample.insn_len = btsq->intel_pt_insn.length;
         memcpy(sample.insn, btsq->intel_pt_insn.buf, INTEL_PT_INSN_BUF_SZ);
 
+        event.sample.header.type = PERF_RECORD_SAMPLE;
+        event.sample.header.misc = sample.cpumode;
+        event.sample.header.size = sizeof(struct perf_event_header);
+
         if (bts->synth_opts.inject) {
                 event.sample.header.size = bts->branches_event_size;
                 ret = perf_event__synthesize_sample(&event,
diff --git a/tools/perf/util/intel-pt.c b/tools/perf/util/intel-pt.c
index ffa385a029b3..86cc9a64e982 100644
--- a/tools/perf/util/intel-pt.c
+++ b/tools/perf/util/intel-pt.c
@@ -407,6 +407,13 @@ intel_pt_cache_lookup(struct dso *dso, struct machine *machine, u64 offset)
         return auxtrace_cache__lookup(dso->auxtrace_cache, offset);
 }
 
+static inline u8 intel_pt_cpumode(struct intel_pt *pt, uint64_t ip)
+{
+        return ip >= pt->kernel_start ?
+               PERF_RECORD_MISC_KERNEL :
+               PERF_RECORD_MISC_USER;
+}
+
 static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
                                    uint64_t *insn_cnt_ptr, uint64_t *ip,
                                    uint64_t to_ip, uint64_t max_insn_cnt,
@@ -429,10 +436,7 @@ static int intel_pt_walk_next_insn(struct intel_pt_insn *intel_pt_insn,
         if (to_ip && *ip == to_ip)
                 goto out_no_cache;
 
-        if (*ip >= ptq->pt->kernel_start)
-                cpumode = PERF_RECORD_MISC_KERNEL;
-        else
-                cpumode = PERF_RECORD_MISC_USER;
+        cpumode = intel_pt_cpumode(ptq->pt, *ip);
 
         thread = ptq->thread;
         if (!thread) {
@@ -759,7 +763,8 @@ static struct intel_pt_queue *intel_pt_alloc_queue(struct intel_pt *pt,
         if (pt->synth_opts.callchain) {
                 size_t sz = sizeof(struct ip_callchain);
 
-                sz += pt->synth_opts.callchain_sz * sizeof(u64);
+                /* Add 1 to callchain_sz for callchain context */
+                sz += (pt->synth_opts.callchain_sz + 1) * sizeof(u64);
                 ptq->chain = zalloc(sz);
                 if (!ptq->chain)
                         goto out_free;
@@ -1058,15 +1063,11 @@ static void intel_pt_prep_b_sample(struct intel_pt *pt,
                                    union perf_event *event,
                                    struct perf_sample *sample)
 {
-        event->sample.header.type = PERF_RECORD_SAMPLE;
-        event->sample.header.misc = PERF_RECORD_MISC_USER;
-        event->sample.header.size = sizeof(struct perf_event_header);
-
         if (!pt->timeless_decoding)
                 sample->time = tsc_to_perf_time(ptq->timestamp, &pt->tc);
 
-        sample->cpumode = PERF_RECORD_MISC_USER;
         sample->ip = ptq->state->from_ip;
+        sample->cpumode = intel_pt_cpumode(pt, sample->ip);
         sample->pid = ptq->pid;
         sample->tid = ptq->tid;
         sample->addr = ptq->state->to_ip;
@@ -1075,6 +1076,10 @@ static void intel_pt_prep_b_sample(struct intel_pt *pt,
         sample->flags = ptq->flags;
         sample->insn_len = ptq->insn_len;
         memcpy(sample->insn, ptq->insn, INTEL_PT_INSN_BUF_SZ);
+
+        event->sample.header.type = PERF_RECORD_SAMPLE;
+        event->sample.header.misc = sample->cpumode;
+        event->sample.header.size = sizeof(struct perf_event_header);
 }
 
 static int intel_pt_inject_event(union perf_event *event,
@@ -1160,7 +1165,8 @@ static void intel_pt_prep_sample(struct intel_pt *pt,
 
         if (pt->synth_opts.callchain) {
                 thread_stack__sample(ptq->thread, ptq->chain,
-                                     pt->synth_opts.callchain_sz, sample->ip);
+                                     pt->synth_opts.callchain_sz + 1,
+                                     sample->ip, pt->kernel_start);
                 sample->callchain = ptq->chain;
         }
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 111ae858cbcb..8f36ce813bc5 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1708,6 +1708,7 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
         struct thread *parent = machine__findnew_thread(machine,
                                                         event->fork.ppid,
                                                         event->fork.ptid);
+        bool do_maps_clone = true;
         int err = 0;
 
         if (dump_trace)
@@ -1736,9 +1737,25 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 
         thread = machine__findnew_thread(machine, event->fork.pid,
                                          event->fork.tid);
+        /*
+         * When synthesizing FORK events, we are trying to create thread
+         * objects for the already running tasks on the machine.
+         *
+         * Normally, for a kernel FORK event, we want to clone the parent's
+         * maps because that is what the kernel just did.
+         *
+         * But when synthesizing, this should not be done.  If we do, we end up
+         * with overlapping maps as we process the sythesized MMAP2 events that
+         * get delivered shortly thereafter.
+         *
+         * Use the FORK event misc flags in an internal way to signal this
+         * situation, so we can elide the map clone when appropriate.
+         */
+        if (event->fork.header.misc & PERF_RECORD_MISC_FORK_EXEC)
+                do_maps_clone = false;
 
         if (thread == NULL || parent == NULL ||
-            thread__fork(thread, parent, sample->time) < 0) {
+            thread__fork(thread, parent, sample->time, do_maps_clone) < 0) {
                 dump_printf("problem processing PERF_RECORD_FORK, skipping event.\n");
                 err = -1;
         }
@@ -2140,6 +2157,27 @@ static int resolve_lbr_callchain_sample(struct thread *thread,
         return 0;
 }
 
+static int find_prev_cpumode(struct ip_callchain *chain, struct thread *thread,
+                             struct callchain_cursor *cursor,
+                             struct symbol **parent,
+                             struct addr_location *root_al,
+                             u8 *cpumode, int ent)
+{
+        int err = 0;
+
+        while (--ent >= 0) {
+                u64 ip = chain->ips[ent];
+
+                if (ip >= PERF_CONTEXT_MAX) {
+                        err = add_callchain_ip(thread, cursor, parent,
+                                               root_al, cpumode, ip,
+                                               false, NULL, NULL, 0);
+                        break;
+                }
+        }
+        return err;
+}
+
 static int thread__resolve_callchain_sample(struct thread *thread,
                                             struct callchain_cursor *cursor,
                                             struct perf_evsel *evsel,
@@ -2246,6 +2284,12 @@ static int thread__resolve_callchain_sample(struct thread *thread,
         }
 
 check_calls:
+        if (callchain_param.order != ORDER_CALLEE) {
+                err = find_prev_cpumode(chain, thread, cursor, parent, root_al,
+                                        &cpumode, chain->nr - first_call);
+                if (err)
+                        return (err < 0) ? err : 0;
+        }
         for (i = first_call, nr_entries = 0;
              i < chain_nr && nr_entries < max_stack; i++) {
                 u64 ip;
@@ -2260,9 +2304,15 @@ check_calls:
                         continue;
 #endif
                 ip = chain->ips[j];
-
                 if (ip < PERF_CONTEXT_MAX)
                        ++nr_entries;
+                else if (callchain_param.order != ORDER_CALLEE) {
+                        err = find_prev_cpumode(chain, thread, cursor, parent,
+                                                root_al, &cpumode, j);
+                        if (err)
+                                return (err < 0) ? err : 0;
+                        continue;
+                }
 
                 err = add_callchain_ip(thread, cursor, parent,
                                        root_al, &cpumode, ip,
diff --git a/tools/perf/util/thread-stack.c b/tools/perf/util/thread-stack.c
index c091635bf7dc..61a4286a74dc 100644
--- a/tools/perf/util/thread-stack.c
+++ b/tools/perf/util/thread-stack.c
@@ -310,20 +310,46 @@ void thread_stack__free(struct thread *thread)
         }
 }
 
+static inline u64 callchain_context(u64 ip, u64 kernel_start)
+{
+        return ip < kernel_start ? PERF_CONTEXT_USER : PERF_CONTEXT_KERNEL;
+}
+
 void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
-                          size_t sz, u64 ip)
+                          size_t sz, u64 ip, u64 kernel_start)
 {
-        size_t i;
+        u64 context = callchain_context(ip, kernel_start);
+        u64 last_context;
+        size_t i, j;
 
-        if (!thread || !thread->ts)
-                chain->nr = 1;
-        else
-                chain->nr = min(sz, thread->ts->cnt + 1);
+        if (sz < 2) {
+                chain->nr = 0;
+                return;
+        }
 
-        chain->ips[0] = ip;
+        chain->ips[0] = context;
+        chain->ips[1] = ip;
+
+        if (!thread || !thread->ts) {
+                chain->nr = 2;
+                return;
+        }
+
+        last_context = context;
+
+        for (i = 2, j = 1; i < sz && j <= thread->ts->cnt; i++, j++) {
+                ip = thread->ts->stack[thread->ts->cnt - j].ret_addr;
+                context = callchain_context(ip, kernel_start);
+                if (context != last_context) {
+                        if (i >= sz - 1)
+                                break;
+                        chain->ips[i++] = context;
+                        last_context = context;
+                }
+                chain->ips[i] = ip;
+        }
 
-        for (i = 1; i < chain->nr; i++)
-                chain->ips[i] = thread->ts->stack[thread->ts->cnt - i].ret_addr;
+        chain->nr = i;
 }
 
 struct call_return_processor *
diff --git a/tools/perf/util/thread-stack.h b/tools/perf/util/thread-stack.h
index b7e41c4ebfdd..f97c00a8c251 100644
--- a/tools/perf/util/thread-stack.h
+++ b/tools/perf/util/thread-stack.h
@@ -84,7 +84,7 @@ int thread_stack__event(struct thread *thread, u32 flags, u64 from_ip,
                         u64 to_ip, u16 insn_len, u64 trace_nr);
 void thread_stack__set_trace_nr(struct thread *thread, u64 trace_nr);
 void thread_stack__sample(struct thread *thread, struct ip_callchain *chain,
-                          size_t sz, u64 ip);
+                          size_t sz, u64 ip, u64 kernel_start);
 int thread_stack__flush(struct thread *thread);
 void thread_stack__free(struct thread *thread);
 size_t thread_stack__depth(struct thread *thread);
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 2048d393ece6..3d9ed7d0e281 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -330,7 +330,8 @@ static int thread__prepare_access(struct thread *thread)
 }
 
 static int thread__clone_map_groups(struct thread *thread,
-                                    struct thread *parent)
+                                    struct thread *parent,
+                                    bool do_maps_clone)
 {
         /* This is new thread, we share map groups for process. */
         if (thread->pid_ == parent->pid_)
@@ -341,15 +342,11 @@ static int thread__clone_map_groups(struct thread *thread,
                          thread->pid_, thread->tid, parent->pid_, parent->tid);
                 return 0;
         }
-
         /* But this one is new process, copy maps. */
-        if (map_groups__clone(thread, parent->mg) < 0)
-                return -ENOMEM;
-
-        return 0;
+        return do_maps_clone ? map_groups__clone(thread, parent->mg) : 0;
 }
 
-int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
+int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone)
 {
         if (parent->comm_set) {
                 const char *comm = thread__comm_str(parent);
@@ -362,7 +359,7 @@ int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp)
         }
 
         thread->ppid = parent->tid;
-        return thread__clone_map_groups(thread, parent);
+        return thread__clone_map_groups(thread, parent, do_maps_clone);
 }
 
 void thread__find_cpumode_addr_location(struct thread *thread, u64 addr,
diff --git a/tools/perf/util/thread.h b/tools/perf/util/thread.h
index 36c09a9904e6..30e2b4c165fe 100644
--- a/tools/perf/util/thread.h
+++ b/tools/perf/util/thread.h
@@ -89,7 +89,7 @@ struct comm *thread__comm(const struct thread *thread);
 struct comm *thread__exec_comm(const struct thread *thread);
 const char *thread__comm_str(const struct thread *thread);
 int thread__insert_map(struct thread *thread, struct map *map);
-int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp);
+int thread__fork(struct thread *thread, struct thread *parent, u64 timestamp, bool do_maps_clone);
 size_t thread__fprintf(struct thread *thread, FILE *fp);
 
 struct thread *thread__main_thread(struct machine *machine, struct thread *thread);
diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
index 6f318b15950e..5eff9bfc5758 100644
--- a/tools/perf/util/unwind-libdw.c
+++ b/tools/perf/util/unwind-libdw.c
@@ -45,13 +45,13 @@ static int __report_module(struct addr_location *al, u64 ip,
                 Dwarf_Addr s;
 
                 dwfl_module_info(mod, NULL, &s, NULL, NULL, NULL, NULL, NULL);
-                if (s != al->map->start)
+                if (s != al->map->start - al->map->pgoff)
                         mod = 0;
         }
 
         if (!mod)
                 mod = dwfl_report_elf(ui->dwfl, dso->short_name,
-                                      (dso->symsrc_filename ? dso->symsrc_filename : dso->long_name), -1, al->map->start,
+                                      (dso->symsrc_filename ? dso->symsrc_filename : dso->long_name), -1, al->map->start - al->map->pgoff,
                                       false);
 
         return mod && dwfl_addrmodule(ui->dwfl, ip) == mod ? 0 : -1;