17 files changed, 77 insertions, 33 deletions

diff --git a/tools/perf/MANIFEST b/tools/perf/MANIFEST
index 09dc0aabb515..d01a0aad5a01 100644
--- a/tools/perf/MANIFEST
+++ b/tools/perf/MANIFEST
@@ -18,6 +18,7 @@ tools/arch/x86/include/asm/atomic.h
 tools/arch/x86/include/asm/rmwcc.h
 tools/lib/traceevent
 tools/lib/api
+tools/lib/hweight.c
 tools/lib/rbtree.c
 tools/lib/symbol/kallsyms.c
 tools/lib/symbol/kallsyms.h
@@ -57,7 +58,6 @@ include/linux/perf_event.h
 include/linux/list.h
 include/linux/hash.h
 include/linux/stringify.h
-lib/hweight.c
 include/linux/swab.h
 arch/*/include/asm/unistd*.h
 arch/*/include/uapi/asm/unistd*.h
diff --git a/tools/perf/Makefile.perf b/tools/perf/Makefile.perf
index 7a4b549214e3..bba34636b733 100644
--- a/tools/perf/Makefile.perf
+++ b/tools/perf/Makefile.perf
@@ -109,9 +109,22 @@ $(OUTPUT)PERF-VERSION-FILE: ../../.git/HEAD
         $(Q)$(SHELL_PATH) util/PERF-VERSION-GEN $(OUTPUT)
         $(Q)touch $(OUTPUT)PERF-VERSION-FILE
 
-CC = $(CROSS_COMPILE)gcc
-LD ?= $(CROSS_COMPILE)ld
-AR = $(CROSS_COMPILE)ar
+# Makefiles suck: This macro sets a default value of $(2) for the
+# variable named by $(1), unless the variable has been set by
+# environment or command line. This is necessary for CC and AR
+# because make sets default values, so the simpler ?= approach
+# won't work as expected.
+define allow-override
+  $(if $(or $(findstring environment,$(origin $(1))),\
+            $(findstring command line,$(origin $(1)))),,\
+    $(eval $(1) = $(2)))
+endef
+
+# Allow setting CC and AR and LD, or setting CROSS_COMPILE as a prefix.
+$(call allow-override,CC,$(CROSS_COMPILE)gcc)
+$(call allow-override,AR,$(CROSS_COMPILE)ar)
+$(call allow-override,LD,$(CROSS_COMPILE)ld)
+
 PKG_CONFIG = $(CROSS_COMPILE)pkg-config
 
 RM      = rm -f
diff --git a/tools/perf/builtin-record.c b/tools/perf/builtin-record.c
index de165a1b9240..20b56eb987f8 100644
--- a/tools/perf/builtin-record.c
+++ b/tools/perf/builtin-record.c
@@ -521,6 +521,15 @@ static int __cmd_record(struct record *rec, int argc, const char **argv)
                 goto out_child;
         }
 
+        /*
+         * Normally perf_session__new would do this, but it doesn't have the
+         * evlist.
+         */
+        if (rec->tool.ordered_events && !perf_evlist__sample_id_all(rec->evlist)) {
+                pr_warning("WARNING: No sample_id_all support, falling back to unordered processing\n");
+                rec->tool.ordered_events = false;
+        }
+
         if (!rec->evlist->nr_groups)
                 perf_header__clear_feat(&session->header, HEADER_GROUP_DESC);
 
@@ -965,9 +974,11 @@ static struct record record = {
         .tool = {
                 .sample         = process_sample_event,
                 .fork           = perf_event__process_fork,
+                .exit           = perf_event__process_exit,
                 .comm           = perf_event__process_comm,
                 .mmap           = perf_event__process_mmap,
                 .mmap2          = perf_event__process_mmap2,
+                .ordered_events = true,
         },
 };
 
diff --git a/tools/perf/builtin-stat.c b/tools/perf/builtin-stat.c
index 37e301a32f43..d99d850e1444 100644
--- a/tools/perf/builtin-stat.c
+++ b/tools/perf/builtin-stat.c
@@ -343,7 +343,7 @@ static int read_counter(struct perf_evsel *counter)
         return 0;
 }
 
-static void read_counters(bool close)
+static void read_counters(bool close_counters)
 {
         struct perf_evsel *counter;
 
@@ -354,7 +354,7 @@ static void read_counters(bool close)
                 if (process_counter(counter))
                         pr_warning("failed to process counter %s\n", counter->name);
 
-                if (close) {
+                if (close_counters) {
                         perf_evsel__close_fd(counter, perf_evsel__nr_cpus(counter),
                                              thread_map__nr(evsel_list->threads));
                 }
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index ecf319728f25..6135cc07213c 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -601,8 +601,8 @@ static void display_sig(int sig __maybe_unused)
 
 static void display_setup_sig(void)
 {
-        signal(SIGSEGV, display_sig);
-        signal(SIGFPE,  display_sig);
+        signal(SIGSEGV, sighandler_dump_stack);
+        signal(SIGFPE, sighandler_dump_stack);
         signal(SIGINT,  display_sig);
         signal(SIGQUIT, display_sig);
         signal(SIGTERM, display_sig);
diff --git a/tools/perf/config/Makefile b/tools/perf/config/Makefile
index 094ddaee104c..d31fac19c30b 100644
--- a/tools/perf/config/Makefile
+++ b/tools/perf/config/Makefile
@@ -638,7 +638,7 @@ ifndef DESTDIR
 prefix ?= $(HOME)
 endif
 bindir_relative = bin
-bindir = $(prefix)/$(bindir_relative)
+bindir = $(abspath $(prefix)/$(bindir_relative))
 mandir = share/man
 infodir = share/info
 perfexecdir = libexec/perf-core
diff --git a/tools/perf/ui/browsers/hists.c b/tools/perf/ui/browsers/hists.c
index 7629bef2fd79..fa67613976a8 100644
--- a/tools/perf/ui/browsers/hists.c
+++ b/tools/perf/ui/browsers/hists.c
@@ -48,7 +48,7 @@ static struct rb_node *hists__filter_entries(struct rb_node *nd,
 
 static bool hist_browser__has_filter(struct hist_browser *hb)
 {
-        return hists__has_filter(hb->hists) || hb->min_pcnt;
+        return hists__has_filter(hb->hists) || hb->min_pcnt || symbol_conf.has_filter;
 }
 
 static int hist_browser__get_folding(struct hist_browser *browser)
diff --git a/tools/perf/util/Build b/tools/perf/util/Build
index 601d11440596..d2d318c59b37 100644
--- a/tools/perf/util/Build
+++ b/tools/perf/util/Build
@@ -143,6 +143,6 @@ $(OUTPUT)util/rbtree.o: ../lib/rbtree.c FORCE
         $(call rule_mkdir)
         $(call if_changed_dep,cc_o_c)
 
-$(OUTPUT)util/hweight.o: ../../lib/hweight.c FORCE
+$(OUTPUT)util/hweight.o: ../lib/hweight.c FORCE
         $(call rule_mkdir)
         $(call if_changed_dep,cc_o_c)
diff --git a/tools/perf/util/auxtrace.c b/tools/perf/util/auxtrace.c
index 7e7405c9b936..83d9dd96fe08 100644
--- a/tools/perf/util/auxtrace.c
+++ b/tools/perf/util/auxtrace.c
@@ -53,11 +53,6 @@ int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
 {
         struct perf_event_mmap_page *pc = userpg;
 
-#if BITS_PER_LONG != 64 && !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
-        pr_err("Cannot use AUX area tracing mmaps\n");
-        return -1;
-#endif
-
         WARN_ONCE(mm->base, "Uninitialized auxtrace_mmap\n");
 
         mm->userpg = userpg;
@@ -73,6 +68,11 @@ int auxtrace_mmap__mmap(struct auxtrace_mmap *mm,
                 return 0;
         }
 
+#if BITS_PER_LONG != 64 && !defined(HAVE_SYNC_COMPARE_AND_SWAP_SUPPORT)
+        pr_err("Cannot use AUX area tracing mmaps\n");
+        return -1;
+#endif
+
         pc->aux_offset = mp->offset;
         pc->aux_size = mp->len;
 
diff --git a/tools/perf/util/machine.c b/tools/perf/util/machine.c
index 7ff682770fdb..f1a4c833121e 100644
--- a/tools/perf/util/machine.c
+++ b/tools/perf/util/machine.c
@@ -1387,6 +1387,24 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
                                                         event->fork.ptid);
         int err = 0;
 
+        if (dump_trace)
+                perf_event__fprintf_task(event, stdout);
+
+        /*
+         * There may be an existing thread that is not actually the parent,
+         * either because we are processing events out of order, or because the
+         * (fork) event that would have removed the thread was lost. Assume the
+         * latter case and continue on as best we can.
+         */
+        if (parent->pid_ != (pid_t)event->fork.ppid) {
+                dump_printf("removing erroneous parent thread %d/%d\n",
+                            parent->pid_, parent->tid);
+                machine__remove_thread(machine, parent);
+                thread__put(parent);
+                parent = machine__findnew_thread(machine, event->fork.ppid,
+                                                 event->fork.ptid);
+        }
+
         /* if a thread currently exists for the thread id remove it */
         if (thread != NULL) {
                 machine__remove_thread(machine, thread);
@@ -1395,8 +1413,6 @@ int machine__process_fork_event(struct machine *machine, union perf_event *event
 
         thread = machine__findnew_thread(machine, event->fork.pid,
                                          event->fork.tid);
-        if (dump_trace)
-                perf_event__fprintf_task(event, stdout);
 
         if (thread == NULL || parent == NULL ||
             thread__fork(thread, parent, sample->time) < 0) {
diff --git a/tools/perf/util/python-ext-sources b/tools/perf/util/python-ext-sources
index e23ded40c79e..0766d98c5da5 100644
--- a/tools/perf/util/python-ext-sources
+++ b/tools/perf/util/python-ext-sources
@@ -10,7 +10,7 @@ util/ctype.c
 util/evlist.c
 util/evsel.c
 util/cpumap.c
-../../lib/hweight.c
+../lib/hweight.c
 util/thread_map.c
 util/util.c
 util/xyarray.c
@@ -19,5 +19,5 @@ util/rblist.c
 util/stat.c
 util/strlist.c
 util/trace-event.c
-../../lib/rbtree.c
+../lib/rbtree.c
 util/string.c
diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
index 53e8bb7bc852..2a5d8d7698ae 100644
--- a/tools/perf/util/stat-shadow.c
+++ b/tools/perf/util/stat-shadow.c
@@ -85,7 +85,7 @@ void perf_stat__update_shadow_stats(struct perf_evsel *counter, u64 *count,
         else if (perf_evsel__match(counter, HARDWARE, HW_CPU_CYCLES))
                 update_stats(&runtime_cycles_stats[ctx][cpu], count[0]);
         else if (perf_stat_evsel__is(counter, CYCLES_IN_TX))
-                update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
+                update_stats(&runtime_cycles_in_tx_stats[ctx][cpu], count[0]);
         else if (perf_stat_evsel__is(counter, TRANSACTION_START))
                 update_stats(&runtime_transaction_stats[ctx][cpu], count[0]);
         else if (perf_stat_evsel__is(counter, ELISION_START))
@@ -398,20 +398,18 @@ void perf_stat__print_shadow_stats(FILE *out, struct perf_evsel *evsel,
                                 " #   %5.2f%% aborted cycles         ",
                                 100.0 * ((total2-avg) / total));
         } else if (perf_stat_evsel__is(evsel, TRANSACTION_START) &&
-                   avg > 0 &&
                    runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
                 total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
-                if (total)
+                if (avg)
                         ratio = total / avg;
 
                 fprintf(out, " # %8.0f cycles / transaction   ", ratio);
         } else if (perf_stat_evsel__is(evsel, ELISION_START) &&
-                   avg > 0 &&
                    runtime_cycles_in_tx_stats[ctx][cpu].n != 0) {
                 total = avg_stats(&runtime_cycles_in_tx_stats[ctx][cpu]);
 
-                if (total)
+                if (avg)
                         ratio = total / avg;
 
                 fprintf(out, " # %8.0f cycles / elision       ", ratio);
diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
index 48b588c6951a..60f11414bb5c 100644
--- a/tools/perf/util/symbol.c
+++ b/tools/perf/util/symbol.c
@@ -1911,6 +1911,8 @@ int setup_list(struct strlist **list, const char *list_str,
                 pr_err("problems parsing %s list\n", list_name);
                 return -1;
         }
+
+        symbol_conf.has_filter = true;
         return 0;
 }
 
diff --git a/tools/perf/util/symbol.h b/tools/perf/util/symbol.h
index bef47ead1d9b..b98ce51af142 100644
--- a/tools/perf/util/symbol.h
+++ b/tools/perf/util/symbol.h
@@ -105,7 +105,8 @@ struct symbol_conf {
                         demangle_kernel,
                         filter_relative,
                         show_hist_headers,
-                        branch_callstack;
+                        branch_callstack,
+                        has_filter;
         const char      *vmlinux_name,
                         *kallsyms_name,
                         *source_prefix,
diff --git a/tools/perf/util/thread.c b/tools/perf/util/thread.c
index 28c4b746baa1..0a9ae8014729 100644
--- a/tools/perf/util/thread.c
+++ b/tools/perf/util/thread.c
@@ -191,6 +191,12 @@ static int thread__clone_map_groups(struct thread *thread,
         if (thread->pid_ == parent->pid_)
                 return 0;
 
+        if (thread->mg == parent->mg) {
+                pr_debug("broken map groups on thread %d/%d parent %d/%d\n",
+                         thread->pid_, thread->tid, parent->pid_, parent->tid);
+                return 0;
+        }
+
         /* But this one is new process, copy maps. */
         for (i = 0; i < MAP__NR_TYPES; ++i)
                 if (map_groups__clone(thread->mg, parent->mg, i) < 0)
diff --git a/tools/perf/util/thread_map.c b/tools/perf/util/thread_map.c
index da7646d767fe..292ae2c90e06 100644
--- a/tools/perf/util/thread_map.c
+++ b/tools/perf/util/thread_map.c
@@ -136,8 +136,7 @@ struct thread_map *thread_map__new_by_uid(uid_t uid)
                 if (grow) {
                         struct thread_map *tmp;
 
-                        tmp = realloc(threads, (sizeof(*threads) +
-                                                max_threads * sizeof(pid_t)));
+                        tmp = thread_map__realloc(threads, max_threads);
                         if (tmp == NULL)
                                 goto out_free_namelist;
 
diff --git a/tools/perf/util/vdso.c b/tools/perf/util/vdso.c
index 4b89118f158d..44d440da15dc 100644
--- a/tools/perf/util/vdso.c
+++ b/tools/perf/util/vdso.c
@@ -236,18 +236,16 @@ static struct dso *__machine__findnew_compat(struct machine *machine,
         const char *file_name;
         struct dso *dso;
 
-        pthread_rwlock_wrlock(&machine->dsos.lock);
         dso = __dsos__find(&machine->dsos, vdso_file->dso_name, true);
         if (dso)
-                goto out_unlock;
+                goto out;
 
         file_name = vdso__get_compat_file(vdso_file);
         if (!file_name)
-                goto out_unlock;
+                goto out;
 
         dso = __machine__addnew_vdso(machine, vdso_file->dso_name, file_name);
-out_unlock:
-        pthread_rwlock_unlock(&machine->dsos.lock);
+out:
         return dso;
 }