33 files changed, 268 insertions, 124 deletions

diff --git a/tools/perf/Documentation/perf-record.txt b/tools/perf/Documentation/perf-record.txt
index e297b74471b8..ca0d3d9f4bac 100644
--- a/tools/perf/Documentation/perf-record.txt
+++ b/tools/perf/Documentation/perf-record.txt
@@ -90,8 +90,20 @@ OPTIONS
         Number of mmap data pages. Must be a power of two.
 
 -g::
+        Enables call-graph (stack chain/backtrace) recording.
+
 --call-graph::
-        Do call-graph (stack chain/backtrace) recording.
+        Setup and enable call-graph (stack chain/backtrace) recording,
+        implies -g.
+
+        Allows specifying "fp" (frame pointer) or "dwarf"
+        (DWARF's CFI - Call Frame Information) as the method to collect
+        the information used to show the call graphs.
+
+        In some systems, where binaries are build with gcc
+        --fomit-frame-pointer, using the "fp" method will produce bogus
+        call graphs, using "dwarf", if available (perf tools linked to
+        the libunwind library) should be used instead.
 
 -q::
 --quiet::
diff --git a/tools/perf/Documentation/perf-top.txt b/tools/perf/Documentation/perf-top.txt
index 58d6598a9686..6a118e71d003 100644
--- a/tools/perf/Documentation/perf-top.txt
+++ b/tools/perf/Documentation/perf-top.txt
@@ -140,20 +140,12 @@ Default is to monitor all CPUS.
 --asm-raw::
         Show raw instruction encoding of assembly instructions.
 
--G [type,min,order]::
+-G::
+        Enables call-graph (stack chain/backtrace) recording.
+
 --call-graph::
-        Display call chains using type, min percent threshold and order.
-        type can be either:
-        - flat: single column, linear exposure of call chains.
-        - graph: use a graph tree, displaying absolute overhead rates.
-        - fractal: like graph, but displays relative rates. Each branch of
-                 the tree is considered as a new profiled object.
-
-        order can be either:
-        - callee: callee based call graph.
-        - caller: inverted caller based call graph.
-
-        Default: fractal,0.5,callee.
+        Setup and enable call-graph (stack chain/backtrace) recording,
+        implies -G.
 
 --ignore-callees=<regex>::
         Ignore callees of the function(s) matching the given regex.
diff --git a/tools/perf/Makefile b/tools/perf/Makefile
index 3a0ff7fb71b6..64c043b7a438 100644
--- a/tools/perf/Makefile
+++ b/tools/perf/Makefile
@@ -770,6 +770,7 @@ check: $(OUTPUT)common-cmds.h
 install-bin: all
         $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(bindir_SQ)'
         $(INSTALL) $(OUTPUT)perf '$(DESTDIR_SQ)$(bindir_SQ)'
+        $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
         $(INSTALL) $(OUTPUT)perf-archive -t '$(DESTDIR_SQ)$(perfexec_instdir_SQ)'
 ifndef NO_LIBPERL
         $(INSTALL) -d -m 755 '$(DESTDIR_SQ)$(perfexec_instdir_SQ)/scripts/perl/Perf-Trace-Util/lib/Perf/Trace'
diff --git a/tools/perf/builtin-kvm.c b/tools/perf/builtin-kvm.c
index 935d52216c89..fbc2888d6495 100644
--- a/tools/perf/builtin-kvm.c
+++ b/tools/perf/builtin-kvm.c
@@ -888,11 +888,18 @@ static s64 perf_kvm__mmap_read_idx(struct perf_kvm_stat *kvm, int idx,
         while ((event = perf_evlist__mmap_read(kvm->evlist, idx)) != NULL) {
                 err = perf_evlist__parse_sample(kvm->evlist, event, &sample);
                 if (err) {
+                        perf_evlist__mmap_consume(kvm->evlist, idx);
                         pr_err("Failed to parse sample\n");
                         return -1;
                 }
 
                 err = perf_session_queue_event(kvm->session, event, &sample, 0);
+                /*
+                 * 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);
+
                 if (err) {
                         pr_err("Failed to enqueue sample: %d\n", err);
                         return -1;
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index a41ac41546c9..d04651484640 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -712,21 +712,12 @@ static int get_stack_size(char *str, unsigned long *_size)
 }
 #endif /* LIBUNWIND_SUPPORT */
 
-int record_parse_callchain_opt(const struct option *opt,
-                               const char *arg, int unset)
+int record_parse_callchain(const char *arg, struct perf_record_opts *opts)
 {
-        struct perf_record_opts *opts = opt->value;
         char *tok, *name, *saveptr = NULL;
         char *buf;
         int ret = -1;
 
-        /* --no-call-graph */
-        if (unset)
-                return 0;
-
-        /* We specified default option if none is provided. */
-        BUG_ON(!arg);
-
         /* We need buffer that we know we can write to. */
         buf = malloc(strlen(arg) + 1);
         if (!buf)
@@ -764,13 +755,9 @@ int record_parse_callchain_opt(const struct option *opt,
                                 ret = get_stack_size(tok, &size);
                                 opts->stack_dump_size = size;
                         }
-
-                        if (!ret)
-                                pr_debug("callchain: stack dump size %d\n",
-                                         opts->stack_dump_size);
 #endif /* LIBUNWIND_SUPPORT */
                 } else {
-                        pr_err("callchain: Unknown -g option "
+                        pr_err("callchain: Unknown --call-graph option "
                                "value: %s\n", arg);
                         break;
                 }
@@ -778,13 +765,52 @@ int record_parse_callchain_opt(const struct option *opt,
         } while (0);
 
         free(buf);
+        return ret;
+}
+
+static void callchain_debug(struct perf_record_opts *opts)
+{
+        pr_debug("callchain: type %d\n", opts->call_graph);
 
+        if (opts->call_graph == CALLCHAIN_DWARF)
+                pr_debug("callchain: stack dump size %d\n",
+                         opts->stack_dump_size);
+}
+
+int record_parse_callchain_opt(const struct option *opt,
+                               const char *arg,
+                               int unset)
+{
+        struct perf_record_opts *opts = opt->value;
+        int ret;
+
+        /* --no-call-graph */
+        if (unset) {
+                opts->call_graph = CALLCHAIN_NONE;
+                pr_debug("callchain: disabled\n");
+                return 0;
+        }
+
+        ret = record_parse_callchain(arg, opts);
         if (!ret)
-                pr_debug("callchain: type %d\n", opts->call_graph);
+                callchain_debug(opts);
 
         return ret;
 }
 
+int record_callchain_opt(const struct option *opt,
+                         const char *arg __maybe_unused,
+                         int unset __maybe_unused)
+{
+        struct perf_record_opts *opts = opt->value;
+
+        if (opts->call_graph == CALLCHAIN_NONE)
+                opts->call_graph = CALLCHAIN_FP;
+
+        callchain_debug(opts);
+        return 0;
+}
+
 static const char * const record_usage[] = {
         "perf record [<options>] [<command>]",
         "perf record [<options>] -- <command> [<options>]",
@@ -813,12 +839,12 @@ static struct perf_record record = {
         },
 };
 
-#define CALLCHAIN_HELP "do call-graph (stack chain/backtrace) recording: "
+#define CALLCHAIN_HELP "setup and enables call-graph (stack chain/backtrace) recording: "
 
 #ifdef LIBUNWIND_SUPPORT
-const char record_callchain_help[] = CALLCHAIN_HELP "[fp] dwarf";
+const char record_callchain_help[] = CALLCHAIN_HELP "fp dwarf";
 #else
-const char record_callchain_help[] = CALLCHAIN_HELP "[fp]";
+const char record_callchain_help[] = CALLCHAIN_HELP "fp";
 #endif
 
 /*
@@ -858,9 +884,12 @@ const struct option record_options[] = {
                      "number of mmap data pages"),
         OPT_BOOLEAN(0, "group", &record.opts.group,
                     "put the counters into a counter group"),
-        OPT_CALLBACK_DEFAULT('g', "call-graph", &record.opts,
-                             "mode[,dump_size]", record_callchain_help,
-                             &record_parse_callchain_opt, "fp"),
+        OPT_CALLBACK_NOOPT('g', NULL, &record.opts,
+                           NULL, "enables call-graph recording" ,
+                           &record_callchain_opt),
+        OPT_CALLBACK(0, "call-graph", &record.opts,
+                     "mode[,dump_size]", record_callchain_help,
+                     &record_parse_callchain_opt),
         OPT_INCR('v', "verbose", &verbose,
                     "be more verbose (show counter open errors, etc)"),
         OPT_BOOLEAN('q', "quiet", &quiet, "don't print any message"),
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index f686d5ff594e..5098f144b92d 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -457,6 +457,7 @@ static int __run_perf_stat(int argc, const char **argv)
                         perror("failed to prepare workload");
                         return -1;
                 }
+                child_pid = evsel_list->workload.pid;
         }
 
         if (group)
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 212214162bb2..5a11f13e56f9 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -810,7 +810,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
                 ret = perf_evlist__parse_sample(top->evlist, event, &sample);
                 if (ret) {
                         pr_err("Can't parse sample, err = %d\n", ret);
-                        continue;
+                        goto next_event;
                 }
 
                 evsel = perf_evlist__id2evsel(session->evlist, sample.id);
@@ -825,13 +825,13 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
                 case PERF_RECORD_MISC_USER:
                         ++top->us_samples;
                         if (top->hide_user_symbols)
-                                continue;
+                                goto next_event;
                         machine = &session->machines.host;
                         break;
                 case PERF_RECORD_MISC_KERNEL:
                         ++top->kernel_samples;
                         if (top->hide_kernel_symbols)
-                                continue;
+                                goto next_event;
                         machine = &session->machines.host;
                         break;
                 case PERF_RECORD_MISC_GUEST_KERNEL:
@@ -847,7 +847,7 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
                          */
                         /* Fall thru */
                 default:
-                        continue;
+                        goto next_event;
                 }
 
 
@@ -859,6 +859,8 @@ static void perf_top__mmap_read_idx(struct perf_top *top, int idx)
                         machine__process_event(machine, event);
                 } else
                         ++session->stats.nr_unknown_events;
+next_event:
+                perf_evlist__mmap_consume(top->evlist, idx);
         }
 }
 
@@ -1016,16 +1018,16 @@ out_delete:
 }
 
 static int
-parse_callchain_opt(const struct option *opt, const char *arg, int unset)
+callchain_opt(const struct option *opt, const char *arg, int unset)
 {
-        /*
-         * --no-call-graph
-         */
-        if (unset)
-                return 0;
-
         symbol_conf.use_callchain = true;
+        return record_callchain_opt(opt, arg, unset);
+}
 
+static int
+parse_callchain_opt(const struct option *opt, const char *arg, int unset)
+{
+        symbol_conf.use_callchain = true;
         return record_parse_callchain_opt(opt, arg, unset);
 }
 
@@ -1106,9 +1108,12 @@ int cmd_top(int argc, const char **argv, const char *prefix __maybe_unused)
                    "sort by key(s): pid, comm, dso, symbol, parent, weight, local_weight"),
         OPT_BOOLEAN('n', "show-nr-samples", &symbol_conf.show_nr_samples,
                     "Show a column with the number of samples"),
-        OPT_CALLBACK_DEFAULT('G', "call-graph", &top.record_opts,
-                             "mode[,dump_size]", record_callchain_help,
-                             &parse_callchain_opt, "fp"),
+        OPT_CALLBACK_NOOPT('G', NULL, &top.record_opts,
+                           NULL, "enables call-graph recording",
+                           &callchain_opt),
+        OPT_CALLBACK(0, "call-graph", &top.record_opts,
+                     "mode[,dump_size]", record_callchain_help,
+                     &parse_callchain_opt),
         OPT_CALLBACK(0, "ignore-callees", NULL, "regex",
                    "ignore callees of these functions in call graphs",
                    report_parse_ignore_callees_opt),
diff --git a/tools/perf/builtin-trace.c b/tools/perf/builtin-trace.c
index 71aa3e35406b..99c8d9ad6729 100644
--- a/tools/perf/builtin-trace.c
+++ b/tools/perf/builtin-trace.c
@@ -987,7 +987,7 @@ again:
                         err = perf_evlist__parse_sample(evlist, event, &sample);
                         if (err) {
                                 fprintf(trace->output, "Can't parse sample, err = %d, skipping...\n", err);
-                                continue;
+                                goto next_event;
                         }
 
                         if (trace->base_time == 0)
@@ -1001,18 +1001,20 @@ again:
                         evsel = perf_evlist__id2evsel(evlist, sample.id);
                         if (evsel == NULL) {
                                 fprintf(trace->output, "Unknown tp ID %" PRIu64 ", skipping...\n", sample.id);
-                                continue;
+                                goto next_event;
                         }
 
                         if (sample.raw_data == NULL) {
                                 fprintf(trace->output, "%s sample with no payload for tid: %d, cpu %d, raw_size=%d, skipping...\n",
                                        perf_evsel__name(evsel), sample.tid,
                                        sample.cpu, sample.raw_size);
-                                continue;
+                                goto next_event;
                         }
 
                         handler = evsel->handler.func;
                         handler(trace, evsel, &sample);
+next_event:
+                        perf_evlist__mmap_consume(evlist, i);
 
                         if (done)
                                 goto out_unmap_evlist;
diff --git a/tools/perf/config/feature-tests.mak b/tools/perf/config/feature-tests.mak
index d5a8dd44945f..f79305739ecc 100644
--- a/tools/perf/config/feature-tests.mak
+++ b/tools/perf/config/feature-tests.mak
@@ -219,7 +219,7 @@ define SOURCE_LIBAUDIT
 
 int main(void)
 {
-        printf(\"error message: %s\n\", audit_errno_to_name(0));
+        printf(\"error message: %s\", audit_errno_to_name(0));
         return audit_open();
 }
 endef
diff --git a/tools/perf/tests/code-reading.c b/tools/perf/tests/code-reading.c
index 6fb781d5586c..e3fedfa2906e 100644
--- a/tools/perf/tests/code-reading.c
+++ b/tools/perf/tests/code-reading.c
@@ -290,6 +290,7 @@ static int process_events(struct machine *machine, struct perf_evlist *evlist,
         for (i = 0; i < evlist->nr_mmaps; i++) {
                 while ((event = perf_evlist__mmap_read(evlist, i)) != NULL) {
                         ret = process_event(machine, evlist, event, state);
+                        perf_evlist__mmap_consume(evlist, i);
                         if (ret < 0)
                                 return ret;
                 }
diff --git a/tools/perf/tests/keep-tracking.c b/tools/perf/tests/keep-tracking.c
index d444ea2c47d9..376c35608534 100644
--- a/tools/perf/tests/keep-tracking.c
+++ b/tools/perf/tests/keep-tracking.c
@@ -36,6 +36,7 @@ static int find_comm(struct perf_evlist *evlist, const char *comm)
                             (pid_t)event->comm.tid == getpid() &&
                             strcmp(event->comm.comm, comm) == 0)
                                 found += 1;
+                        perf_evlist__mmap_consume(evlist, i);
                 }
         }
         return found;
diff --git a/tools/perf/tests/mmap-basic.c b/tools/perf/tests/mmap-basic.c
index c4185b9aeb80..a7232c204eb9 100644
--- a/tools/perf/tests/mmap-basic.c
+++ b/tools/perf/tests/mmap-basic.c
@@ -122,6 +122,7 @@ int test__basic_mmap(void)
                         goto out_munmap;
                 }
                 nr_events[evsel->idx]++;
+                perf_evlist__mmap_consume(evlist, 0);
         }
 
         err = 0;
diff --git a/tools/perf/tests/open-syscall-tp-fields.c b/tools/perf/tests/open-syscall-tp-fields.c
index fc5b9fca8b47..524b221b829b 100644
--- a/tools/perf/tests/open-syscall-tp-fields.c
+++ b/tools/perf/tests/open-syscall-tp-fields.c
@@ -77,8 +77,10 @@ int test__syscall_open_tp_fields(void)
 
                                 ++nr_events;
 
-                                if (type != PERF_RECORD_SAMPLE)
+                                if (type != PERF_RECORD_SAMPLE) {
+                                        perf_evlist__mmap_consume(evlist, i);
                                         continue;
+                                }
 
                                 err = perf_evsel__parse_sample(evsel, event, &sample);
                                 if (err) {
diff --git a/tools/perf/tests/perf-record.c b/tools/perf/tests/perf-record.c
index b8a7056519ac..7923b06ffc91 100644
--- a/tools/perf/tests/perf-record.c
+++ b/tools/perf/tests/perf-record.c
@@ -263,6 +263,8 @@ int test__PERF_RECORD(void)
                                                  type);
                                         ++errs;
                                 }
+
+                                perf_evlist__mmap_consume(evlist, i);
                         }
                 }
 
diff --git a/tools/perf/tests/perf-time-to-tsc.c b/tools/perf/tests/perf-time-to-tsc.c
index 0ab61b1f408e..4ca1b938f6a6 100644
--- a/tools/perf/tests/perf-time-to-tsc.c
+++ b/tools/perf/tests/perf-time-to-tsc.c
@@ -122,7 +122,7 @@ int test__perf_time_to_tsc(void)
                         if (event->header.type != PERF_RECORD_COMM ||
                             (pid_t)event->comm.pid != getpid() ||
                             (pid_t)event->comm.tid != getpid())
-                                continue;
+                                goto next_event;
 
                         if (strcmp(event->comm.comm, comm1) == 0) {
                                 CHECK__(perf_evsel__parse_sample(evsel, event,
@@ -134,6 +134,8 @@ int test__perf_time_to_tsc(void)
                                                                  &sample));
                                 comm2_time = sample.time;
                         }
+next_event:
+                        perf_evlist__mmap_consume(evlist, i);
                 }
         }
 
diff --git a/tools/perf/tests/sw-clock.c b/tools/perf/tests/sw-clock.c
index 2e41e2d32ccc..6e2b44ec0749 100644
--- a/tools/perf/tests/sw-clock.c
+++ b/tools/perf/tests/sw-clock.c
@@ -78,7 +78,7 @@ static int __test__sw_clock_freq(enum perf_sw_ids clock_id)
                 struct perf_sample sample;
 
                 if (event->header.type != PERF_RECORD_SAMPLE)
-                        continue;
+                        goto next_event;
 
                 err = perf_evlist__parse_sample(evlist, event, &sample);
                 if (err < 0) {
@@ -88,6 +88,8 @@ 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);
         }
 
         if ((u64) nr_samples == total_periods) {
diff --git a/tools/perf/tests/task-exit.c b/tools/perf/tests/task-exit.c
index 28fe5894b061..a3e64876e940 100644
--- a/tools/perf/tests/task-exit.c
+++ b/tools/perf/tests/task-exit.c
@@ -96,10 +96,10 @@ int test__task_exit(void)
 
 retry:
         while ((event = perf_evlist__mmap_read(evlist, 0)) != NULL) {
-                if (event->header.type != PERF_RECORD_EXIT)
-                        continue;
+                if (event->header.type == PERF_RECORD_EXIT)
+                        nr_exit++;
 
-                nr_exit++;
+                perf_evlist__mmap_consume(evlist, 0);
         }
 
         if (!exited || !nr_exit) {
diff --git a/tools/perf/ui/stdio/hist.c b/tools/perf/ui/stdio/hist.c
index 194e2f42ff5d..6c152686e837 100644
--- a/tools/perf/ui/stdio/hist.c
+++ b/tools/perf/ui/stdio/hist.c
@@ -315,8 +315,7 @@ static inline void advance_hpp(struct perf_hpp *hpp, int inc)
 }
 
 static int hist_entry__period_snprintf(struct perf_hpp *hpp,
-                                       struct hist_entry *he,
-                                       bool color)
+                                       struct hist_entry *he)
 {
         const char *sep = symbol_conf.field_sep;
         struct perf_hpp_fmt *fmt;
@@ -338,7 +337,7 @@ static int hist_entry__period_snprintf(struct perf_hpp *hpp,
                 } else
                         first = false;
 
-                if (color && fmt->color)
+                if (perf_hpp__use_color() && fmt->color)
                         ret = fmt->color(fmt, hpp, he);
                 else
                         ret = fmt->entry(fmt, hpp, he);
@@ -358,12 +357,11 @@ static int hist_entry__fprintf(struct hist_entry *he, size_t size,
                 .buf            = bf,
                 .size           = size,
         };
-        bool color = !symbol_conf.field_sep;
 
         if (size == 0 || size > bfsz)
                 size = hpp.size = bfsz;
 
-        ret = hist_entry__period_snprintf(&hpp, he, color);
+        ret = hist_entry__period_snprintf(&hpp, he);
         hist_entry__sort_snprintf(he, bf + ret, size - ret, hists);
 
         ret = fprintf(fp, "%s\n", bf);
@@ -482,6 +480,7 @@ size_t hists__fprintf(struct hists *hists, bool show_header, int max_rows,
 
 print_entries:
         linesz = hists__sort_list_width(hists) + 3 + 1;
+        linesz += perf_hpp__color_overhead();
         line = malloc(linesz);
         if (line == NULL) {
                 ret = -1;
diff --git a/tools/perf/util/callchain.h b/tools/perf/util/callchain.h
index 2b585bc308cf..9e99060408ae 100644
--- a/tools/perf/util/callchain.h
+++ b/tools/perf/util/callchain.h
@@ -147,6 +147,9 @@ static inline void callchain_cursor_advance(struct callchain_cursor *cursor)
 
 struct option;
 
+int record_parse_callchain(const char *arg, struct perf_record_opts *opts);
 int record_parse_callchain_opt(const struct option *opt, const char *arg, int unset);
+int record_callchain_opt(const struct option *opt, const char *arg, int unset);
+
 extern const char record_callchain_help[];
 #endif  /* __PERF_CALLCHAIN_H */
diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
index e23bde19d590..7defd77105d0 100644
--- a/tools/perf/util/dwarf-aux.c
+++ b/tools/perf/util/dwarf-aux.c
@@ -426,7 +426,7 @@ static int __die_search_func_cb(Dwarf_Die *fn_die, void *data)
  * @die_mem: a buffer for result DIE
  *
  * Search a non-inlined function DIE which includes @addr. Stores the
- * DIE to @die_mem and returns it if found. Returns NULl if failed.
+ * DIE to @die_mem and returns it if found. Returns NULL if failed.
  */
 Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
                                     Dwarf_Die *die_mem)
@@ -454,15 +454,32 @@ static int __die_find_inline_cb(Dwarf_Die *die_mem, void *data)
 }
 
 /**
+ * die_find_top_inlinefunc - Search the top inlined function at given address
+ * @sp_die: a subprogram DIE which including @addr
+ * @addr: target address
+ * @die_mem: a buffer for result DIE
+ *
+ * Search an inlined function DIE which includes @addr. Stores the
+ * DIE to @die_mem and returns it if found. Returns NULL if failed.
+ * Even if several inlined functions are expanded recursively, this
+ * doesn't trace it down, and returns the topmost one.
+ */
+Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
+                                   Dwarf_Die *die_mem)
+{
+        return die_find_child(sp_die, __die_find_inline_cb, &addr, die_mem);
+}
+
+/**
  * die_find_inlinefunc - Search an inlined function at given address
- * @cu_die: a CU DIE which including @addr
+ * @sp_die: a subprogram DIE which including @addr
  * @addr: target address
  * @die_mem: a buffer for result DIE
  *
  * Search an inlined function DIE which includes @addr. Stores the
- * DIE to @die_mem and returns it if found. Returns NULl if failed.
+ * DIE to @die_mem and returns it if found. Returns NULL if failed.
  * If several inlined functions are expanded recursively, this trace
- * it and returns deepest one.
+ * it down and returns deepest one.
  */
 Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
                                Dwarf_Die *die_mem)
diff --git a/tools/perf/util/dwarf-aux.h b/tools/perf/util/dwarf-aux.h
index 8658d41697d2..b4fe90c6cb2d 100644
--- a/tools/perf/util/dwarf-aux.h
+++ b/tools/perf/util/dwarf-aux.h
@@ -79,7 +79,11 @@ extern Dwarf_Die *die_find_child(Dwarf_Die *rt_die,
 extern Dwarf_Die *die_find_realfunc(Dwarf_Die *cu_die, Dwarf_Addr addr,
                                     Dwarf_Die *die_mem);
 
-/* Search an inlined function including given address */
+/* Search the top inlined function including given address */
+extern Dwarf_Die *die_find_top_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
+                                          Dwarf_Die *die_mem);
+
+/* Search the deepest inlined function including given address */
 extern Dwarf_Die *die_find_inlinefunc(Dwarf_Die *sp_die, Dwarf_Addr addr,
                                       Dwarf_Die *die_mem);
 
diff --git a/tools/perf/util/event.c b/tools/perf/util/event.c
index 9b393e7dca6f..49096ea58a15 100644
--- a/tools/perf/util/event.c
+++ b/tools/perf/util/event.c
@@ -187,7 +187,7 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
                 return -1;
         }
 
-        event->header.type = PERF_RECORD_MMAP2;
+        event->header.type = PERF_RECORD_MMAP;
         /*
          * Just like the kernel, see __perf_event_mmap in kernel/perf_event.c
          */
@@ -198,7 +198,6 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
                 char prot[5];
                 char execname[PATH_MAX];
                 char anonstr[] = "//anon";
-                unsigned int ino;
                 size_t size;
                 ssize_t n;
 
@@ -209,15 +208,12 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
                 strcpy(execname, "");
 
                 /* 00400000-0040c000 r-xp 00000000 fd:01 41038  /bin/cat */
-                n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %x:%x %u %s\n",
-                       &event->mmap2.start, &event->mmap2.len, prot,
-                       &event->mmap2.pgoff, &event->mmap2.maj,
-                       &event->mmap2.min,
-                       &ino, execname);
-
-                event->mmap2.ino = (u64)ino;
+                n = sscanf(bf, "%"PRIx64"-%"PRIx64" %s %"PRIx64" %*x:%*x %*u %s\n",
+                       &event->mmap.start, &event->mmap.len, prot,
+                       &event->mmap.pgoff,
+                       execname);
 
-                if (n != 8)
+                if (n != 5)
                         continue;
 
                 if (prot[2] != 'x')
@@ -227,15 +223,15 @@ static int perf_event__synthesize_mmap_events(struct perf_tool *tool,
                         strcpy(execname, anonstr);
 
                 size = strlen(execname) + 1;
-                memcpy(event->mmap2.filename, execname, size);
+                memcpy(event->mmap.filename, execname, size);
                 size = PERF_ALIGN(size, sizeof(u64));
-                event->mmap2.len -= event->mmap.start;
-                event->mmap2.header.size = (sizeof(event->mmap2) -
-                                        (sizeof(event->mmap2.filename) - size));
-                memset(event->mmap2.filename + size, 0, machine->id_hdr_size);
-                event->mmap2.header.size += machine->id_hdr_size;
-                event->mmap2.pid = tgid;
-                event->mmap2.tid = pid;
+                event->mmap.len -= event->mmap.start;
+                event->mmap.header.size = (sizeof(event->mmap) -
+                                        (sizeof(event->mmap.filename) - size));
+                memset(event->mmap.filename + size, 0, machine->id_hdr_size);
+                event->mmap.header.size += machine->id_hdr_size;
+                event->mmap.pid = tgid;
+                event->mmap.tid = pid;
 
                 if (process(tool, event, &synth_sample, machine) != 0) {
                         rc = -1;
diff --git a/tools/perf/util/evlist.c b/tools/perf/util/evlist.c
index f9f77bee0b1b..e584cd30b0f2 100644
--- a/tools/perf/util/evlist.c
+++ b/tools/perf/util/evlist.c
@@ -545,12 +545,19 @@ union perf_event *perf_evlist__mmap_read(struct perf_evlist *evlist, int idx)
 
         md->prev = old;
 
-        if (!evlist->overwrite)
-                perf_mmap__write_tail(md, old);
-
         return event;
 }
 
+void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx)
+{
+        if (!evlist->overwrite) {
+                struct perf_mmap *md = &evlist->mmap[idx];
+                unsigned int old = md->prev;
+
+                perf_mmap__write_tail(md, old);
+        }
+}
+
 static void __perf_evlist__munmap(struct perf_evlist *evlist, int idx)
 {
         if (evlist->mmap[idx].base != NULL) {
diff --git a/tools/perf/util/evlist.h b/tools/perf/util/evlist.h
index 880d7139d2fb..206d09339306 100644
--- a/tools/perf/util/evlist.h
+++ b/tools/perf/util/evlist.h
@@ -89,6 +89,8 @@ struct perf_sample_id *perf_evlist__id2sid(struct perf_evlist *evlist, u64 id);
 
 union perf_event *perf_evlist__mmap_read(struct perf_evlist *self, int idx);
 
+void perf_evlist__mmap_consume(struct perf_evlist *evlist, int idx);
+
 int perf_evlist__open(struct perf_evlist *evlist);
 void perf_evlist__close(struct perf_evlist *evlist);
 
diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 0ce9febf1ba0..9f1ef9bee2d0 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -678,7 +678,6 @@ void perf_evsel__config(struct perf_evsel *evsel,
                 attr->sample_type       |= PERF_SAMPLE_WEIGHT;
 
         attr->mmap  = track;
-        attr->mmap2 = track && !perf_missing_features.mmap2;
         attr->comm  = track;
 
         /*
diff --git a/tools/perf/util/header.c b/tools/perf/util/header.c
index ce69901176d8..c3e5a3b817ab 100644
--- a/tools/perf/util/header.c
+++ b/tools/perf/util/header.c
@@ -2768,6 +2768,18 @@ int perf_session__read_header(struct perf_session *session)
         if (perf_file_header__read(&f_header, header, fd) < 0)
                 return -EINVAL;
 
+        /*
+         * Sanity check that perf.data was written cleanly; data size is
+         * initialized to 0 and updated only if the on_exit function is run.
+         * If data size is still 0 then the file contains only partial
+         * information.  Just warn user and process it as much as it can.
+         */
+        if (f_header.data.size == 0) {
+                pr_warning("WARNING: The %s file's data size field is 0 which is unexpected.\n"
+                           "Was the 'perf record' command properly terminated?\n",
+                           session->filename);
+        }
+
         nr_attrs = f_header.attrs.size / f_header.attr_size;
         lseek(fd, f_header.attrs.offset, SEEK_SET);
 
diff --git a/tools/perf/util/hist.h b/tools/perf/util/hist.h
index 1329b6b6ffe6..ce8dc61ce2c3 100644
--- a/tools/perf/util/hist.h
+++ b/tools/perf/util/hist.h
@@ -5,6 +5,7 @@
 #include <pthread.h>
 #include "callchain.h"
 #include "header.h"
+#include "color.h"
 
 extern struct callchain_param callchain_param;
 
@@ -175,6 +176,18 @@ void perf_hpp__init(void);
 void perf_hpp__column_register(struct perf_hpp_fmt *format);
 void perf_hpp__column_enable(unsigned col);
 
+static inline size_t perf_hpp__use_color(void)
+{
+        return !symbol_conf.field_sep;
+}
+
+static inline size_t perf_hpp__color_overhead(void)
+{
+        return perf_hpp__use_color() ?
+               (COLOR_MAXLEN + sizeof(PERF_COLOR_RESET)) * PERF_HPP__MAX_INDEX
+               : 0;
+}
+
 struct perf_evlist;
 
 struct hist_browser_timer {
diff --git a/tools/perf/util/probe-finder.c b/tools/perf/util/probe-finder.c
index 371476cb8ddc..f0692737ebf1 100644
--- a/tools/perf/util/probe-finder.c
+++ b/tools/perf/util/probe-finder.c
@@ -1327,8 +1327,8 @@ int debuginfo__find_probe_point(struct debuginfo *self, unsigned long addr,
                                 struct perf_probe_point *ppt)
 {
         Dwarf_Die cudie, spdie, indie;
-        Dwarf_Addr _addr, baseaddr;
-        const char *fname = NULL, *func = NULL, *tmp;
+        Dwarf_Addr _addr = 0, baseaddr = 0;
+        const char *fname = NULL, *func = NULL, *basefunc = NULL, *tmp;
         int baseline = 0, lineno = 0, ret = 0;
 
         /* Adjust address with bias */
@@ -1349,27 +1349,36 @@ int debuginfo__find_probe_point(struct debuginfo *self, unsigned long addr,
         /* Find a corresponding function (name, baseline and baseaddr) */
         if (die_find_realfunc(&cudie, (Dwarf_Addr)addr, &spdie)) {
                 /* Get function entry information */
-                tmp = dwarf_diename(&spdie);
-                if (!tmp ||
+                func = basefunc = dwarf_diename(&spdie);
+                if (!func ||
                     dwarf_entrypc(&spdie, &baseaddr) != 0 ||
-                    dwarf_decl_line(&spdie, &baseline) != 0)
+                    dwarf_decl_line(&spdie, &baseline) != 0) {
+                        lineno = 0;
                         goto post;
-                func = tmp;
+                }
 
-                if (addr == (unsigned long)baseaddr)
+                fname = dwarf_decl_file(&spdie);
+                if (addr == (unsigned long)baseaddr) {
                         /* Function entry - Relative line number is 0 */
                         lineno = baseline;
-                else if (die_find_inlinefunc(&spdie, (Dwarf_Addr)addr,
-                                             &indie)) {
+                        goto post;
+                }
+
+                /* Track down the inline functions step by step */
+                while (die_find_top_inlinefunc(&spdie, (Dwarf_Addr)addr,
+                                                &indie)) {
+                        /* There is an inline function */
                         if (dwarf_entrypc(&indie, &_addr) == 0 &&
-                            _addr == addr)
+                            _addr == addr) {
                                 /*
                                  * addr is at an inline function entry.
                                  * In this case, lineno should be the call-site
-                                 * line number.
+                                 * line number. (overwrite lineinfo)
                                  */
                                 lineno = die_get_call_lineno(&indie);
-                        else {
+                                fname = die_get_call_file(&indie);
+                                break;
+                        } else {
                                 /*
                                  * addr is in an inline function body.
                                  * Since lineno points one of the lines
@@ -1377,19 +1386,27 @@ int debuginfo__find_probe_point(struct debuginfo *self, unsigned long addr,
                                  * be the entry line of the inline function.
                                  */
                                 tmp = dwarf_diename(&indie);
-                                if (tmp &&
-                                    dwarf_decl_line(&spdie, &baseline) == 0)
-                                        func = tmp;
+                                if (!tmp ||
+                                    dwarf_decl_line(&indie, &baseline) != 0)
+                                        break;
+                                func = tmp;
+                                spdie = indie;
                         }
                 }
+                /* Verify the lineno and baseline are in a same file */
+                tmp = dwarf_decl_file(&spdie);
+                if (!tmp || strcmp(tmp, fname) != 0)
+                        lineno = 0;
         }
 
 post:
         /* Make a relative line number or an offset */
         if (lineno)
                 ppt->line = lineno - baseline;
-        else if (func)
+        else if (basefunc) {
                 ppt->offset = addr - (unsigned long)baseaddr;
+                func = basefunc;
+        }
 
         /* Duplicate strings */
         if (func) {
diff --git a/tools/perf/util/python.c b/tools/perf/util/python.c
index 71b5412bbbb9..2ac4bc92bb1f 100644
--- a/tools/perf/util/python.c
+++ b/tools/perf/util/python.c
@@ -822,6 +822,8 @@ static PyObject *pyrf_evlist__read_on_cpu(struct pyrf_evlist *pevlist,
                 PyObject *pyevent = pyrf_event__new(event);
                 struct pyrf_event *pevent = (struct pyrf_event *)pyevent;
 
+                perf_evlist__mmap_consume(evlist, cpu);
+
                 if (pyevent == NULL)
                         return PyErr_NoMemory();
 
diff --git a/tools/perf/util/scripting-engines/trace-event-perl.c b/tools/perf/util/scripting-engines/trace-event-perl.c
index a85e4ae5f3ac..c0c9795c4f02 100644
--- a/tools/perf/util/scripting-engines/trace-event-perl.c
+++ b/tools/perf/util/scripting-engines/trace-event-perl.c
@@ -282,7 +282,7 @@ static void perl_process_tracepoint(union perf_event *perf_event __maybe_unused,
 
         event = find_cache_event(evsel);
         if (!event)
-                die("ug! no event found for type %" PRIu64, evsel->attr.config);
+                die("ug! no event found for type %" PRIu64, (u64)evsel->attr.config);
 
         pid = raw_field_value(event, "common_pid", data);
 
diff --git a/tools/perf/util/scripting-engines/trace-event-python.c b/tools/perf/util/scripting-engines/trace-event-python.c
index cc75a3cef388..95d91a0b23af 100644
--- a/tools/perf/util/scripting-engines/trace-event-python.c
+++ b/tools/perf/util/scripting-engines/trace-event-python.c
@@ -56,6 +56,17 @@ static void handler_call_die(const char *handler_name)
         Py_FatalError("problem in Python trace event handler");
 }
 
+/*
+ * Insert val into into the dictionary and decrement the reference counter.
+ * This is necessary for dictionaries since PyDict_SetItemString() does not 
+ * steal a reference, as opposed to PyTuple_SetItem().
+ */
+static void pydict_set_item_string_decref(PyObject *dict, const char *key, PyObject *val)
+{
+        PyDict_SetItemString(dict, key, val);
+        Py_DECREF(val);
+}
+
 static void define_value(enum print_arg_type field_type,
                          const char *ev_name,
                          const char *field_name,
@@ -279,11 +290,11 @@ static void python_process_tracepoint(union perf_event *perf_event
                 PyTuple_SetItem(t, n++, PyInt_FromLong(pid));
                 PyTuple_SetItem(t, n++, PyString_FromString(comm));
         } else {
-                PyDict_SetItemString(dict, "common_cpu", PyInt_FromLong(cpu));
-                PyDict_SetItemString(dict, "common_s", PyInt_FromLong(s));
-                PyDict_SetItemString(dict, "common_ns", PyInt_FromLong(ns));
-                PyDict_SetItemString(dict, "common_pid", PyInt_FromLong(pid));
-                PyDict_SetItemString(dict, "common_comm", PyString_FromString(comm));
+                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));
         }
         for (field = event->format.fields; field; field = field->next) {
                 if (field->flags & FIELD_IS_STRING) {
@@ -313,7 +324,7 @@ static void python_process_tracepoint(union perf_event *perf_event
                 if (handler)
                         PyTuple_SetItem(t, n++, obj);
                 else
-                        PyDict_SetItemString(dict, field->name, obj);
+                        pydict_set_item_string_decref(dict, field->name, obj);
 
         }
         if (!handler)
@@ -370,21 +381,21 @@ static void python_process_general_event(union perf_event *perf_event
         if (!handler || !PyCallable_Check(handler))
                 goto exit;
 
-        PyDict_SetItemString(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
-        PyDict_SetItemString(dict, "attr", PyString_FromStringAndSize(
+        pydict_set_item_string_decref(dict, "ev_name", PyString_FromString(perf_evsel__name(evsel)));
+        pydict_set_item_string_decref(dict, "attr", PyString_FromStringAndSize(
                         (const char *)&evsel->attr, sizeof(evsel->attr)));
-        PyDict_SetItemString(dict, "sample", PyString_FromStringAndSize(
+        pydict_set_item_string_decref(dict, "sample", PyString_FromStringAndSize(
                         (const char *)sample, sizeof(*sample)));
-        PyDict_SetItemString(dict, "raw_buf", PyString_FromStringAndSize(
+        pydict_set_item_string_decref(dict, "raw_buf", PyString_FromStringAndSize(
                         (const char *)sample->raw_data, sample->raw_size));
-        PyDict_SetItemString(dict, "comm",
+        pydict_set_item_string_decref(dict, "comm",
                         PyString_FromString(thread->comm));
         if (al->map) {
-                PyDict_SetItemString(dict, "dso",
+                pydict_set_item_string_decref(dict, "dso",
                         PyString_FromString(al->map->dso->name));
         }
         if (al->sym) {
-                PyDict_SetItemString(dict, "symbol",
+                pydict_set_item_string_decref(dict, "symbol",
                         PyString_FromString(al->sym->name));
         }
 
diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
index 70ffa41518f3..568b750c01f6 100644
--- a/tools/perf/util/session.c
+++ b/tools/perf/util/session.c
@@ -256,6 +256,8 @@ void perf_tool__fill_defaults(struct perf_tool *tool)
                 tool->sample = process_event_sample_stub;
         if (tool->mmap == NULL)
                 tool->mmap = process_event_stub;
+        if (tool->mmap2 == NULL)
+                tool->mmap2 = process_event_stub;
         if (tool->comm == NULL)
                 tool->comm = process_event_stub;
         if (tool->fork == NULL)
@@ -1310,7 +1312,7 @@ int __perf_session__process_events(struct perf_session *session,
         file_offset = page_offset;
         head = data_offset - page_offset;
 
-        if (data_offset + data_size < file_size)
+        if (data_size && (data_offset + data_size < file_size))
                 file_size = data_offset + data_size;
 
         progress_next = file_size / 16;
diff --git a/tools/testing/selftests/timers/posix_timers.c b/tools/testing/selftests/timers/posix_timers.c
index 4fa655d68a81..41bd85559d4b 100644
--- a/tools/testing/selftests/timers/posix_timers.c
+++ b/tools/testing/selftests/timers/posix_timers.c
@@ -151,7 +151,7 @@ static int check_timer_create(int which)
         fflush(stdout);
 
         done = 0;
-        timer_create(which, NULL, &id);
+        err = timer_create(which, NULL, &id);
         if (err < 0) {
                 perror("Can't create timer\n");
                 return -1;