Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Ingo Molnar:
 "A kernel crash fix plus three tooling fixes"

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/core: Fix crash in perf_event_read()
  perf callchain: Reference count maps
  perf diff: Fix -o/--order option behavior (again)
  perf diff: Fix segfault on 'perf diff -o N' option

kernel/events/core.c

@@ -3487,14 +3487,15 @@ struct perf_read_data {
 	int ret;
 };
 
-static int find_cpu_to_read(struct perf_event *event, int local_cpu)
+static int __perf_event_read_cpu(struct perf_event *event, int event_cpu)
 {
-	int event_cpu = event->oncpu;
 	u16 local_pkg, event_pkg;
 
 	if (event->group_caps & PERF_EV_CAP_READ_ACTIVE_PKG) {
-		event_pkg =  topology_physical_package_id(event_cpu);
-		local_pkg =  topology_physical_package_id(local_cpu);
+		int local_cpu = smp_processor_id();
+
+		event_pkg = topology_physical_package_id(event_cpu);
+		local_pkg = topology_physical_package_id(local_cpu);
 
 		if (event_pkg == local_pkg)
 			return local_cpu;
@@ -3624,7 +3625,7 @@ u64 perf_event_read_local(struct perf_event *event)
 
 static int perf_event_read(struct perf_event *event, bool group)
 {
-	int ret = 0, cpu_to_read, local_cpu;
+	int event_cpu, ret = 0;
 
 	/*
 	 * If event is enabled and currently active on a CPU, update the
@@ -3637,21 +3638,25 @@ static int perf_event_read(struct perf_event *event, bool group)
 			.ret = 0,
 		};
 
-		local_cpu = get_cpu();
-		cpu_to_read = find_cpu_to_read(event, local_cpu);
-		put_cpu();
+		event_cpu = READ_ONCE(event->oncpu);
+		if ((unsigned)event_cpu >= nr_cpu_ids)
+			return 0;
+
+		preempt_disable();
+		event_cpu = __perf_event_read_cpu(event, event_cpu);
 
 		/*
 		 * Purposely ignore the smp_call_function_single() return
 		 * value.
 		 *
-		 * If event->oncpu isn't a valid CPU it means the event got
+		 * If event_cpu isn't a valid CPU it means the event got
 		 * scheduled out and that will have updated the event count.
 		 *
 		 * Therefore, either way, we'll have an up-to-date event count
 		 * after this.
 		 */
-		(void)smp_call_function_single(cpu_to_read, __perf_event_read, &data, 1);
+		(void)smp_call_function_single(event_cpu, __perf_event_read, &data, 1);
+		preempt_enable();
 		ret = data.ret;
 	} else if (event->state == PERF_EVENT_STATE_INACTIVE) {
 		struct perf_event_context *ctx = event->ctx;

tools/perf/builtin-diff.c

@@ -1199,7 +1199,7 @@ static int ui_init(void)
 		BUG_ON(1);
 	}
 
-	perf_hpp__register_sort_field(fmt);
+	perf_hpp__prepend_sort_field(fmt);
 	return 0;
 }
 

tools/perf/ui/hist.c

@@ -521,6 +521,12 @@ void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
 	list_add_tail(&format->sort_list, &list->sorts);
 }
 
+void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
+				       struct perf_hpp_fmt *format)
+{
+	list_add(&format->sort_list, &list->sorts);
+}
+
 void perf_hpp__column_unregister(struct perf_hpp_fmt *format)
 {
 	list_del(&format->list);
@@ -560,6 +566,10 @@ void perf_hpp__setup_output_field(struct perf_hpp_list *list)
 	perf_hpp_list__for_each_sort_list(list, fmt) {
 		struct perf_hpp_fmt *pos;
 
+		/* skip sort-only fields ("sort_compute" in perf diff) */
+		if (!fmt->entry && !fmt->color)
+			continue;
+
 		perf_hpp_list__for_each_format(list, pos) {
 			if (fmt_equal(fmt, pos))
 				goto next;

tools/perf/util/callchain.c

@@ -437,7 +437,7 @@ fill_node(struct callchain_node *node, struct callchain_cursor *cursor)
 		}
 		call->ip = cursor_node->ip;
 		call->ms.sym = cursor_node->sym;
-		call->ms.map = cursor_node->map;
+		call->ms.map = map__get(cursor_node->map);
 
 		if (cursor_node->branch) {
 			call->branch_count = 1;
@@ -477,6 +477,7 @@ add_child(struct callchain_node *parent,
 
 		list_for_each_entry_safe(call, tmp, &new->val, list) {
 			list_del(&call->list);
+			map__zput(call->ms.map);
 			free(call);
 		}
 		free(new);
@@ -761,6 +762,7 @@ merge_chain_branch(struct callchain_cursor *cursor,
 					list->ms.map, list->ms.sym,
 					false, NULL, 0, 0);
 		list_del(&list->list);
+		map__zput(list->ms.map);
 		free(list);
 	}
 
@@ -811,7 +813,8 @@ int callchain_cursor_append(struct callchain_cursor *cursor,
 	}
 
 	node->ip = ip;
-	node->map = map;
+	map__zput(node->map);
+	node->map = map__get(map);
 	node->sym = sym;
 	node->branch = branch;
 	node->nr_loop_iter = nr_loop_iter;
@@ -1142,11 +1145,13 @@ static void free_callchain_node(struct callchain_node *node)
 
 	list_for_each_entry_safe(list, tmp, &node->parent_val, list) {
 		list_del(&list->list);
+		map__zput(list->ms.map);
 		free(list);
 	}
 
 	list_for_each_entry_safe(list, tmp, &node->val, list) {
 		list_del(&list->list);
+		map__zput(list->ms.map);
 		free(list);
 	}
 
@@ -1210,6 +1215,7 @@ int callchain_node__make_parent_list(struct callchain_node *node)
 				goto out;
 			*new = *chain;
 			new->has_children = false;
+			map__get(new->ms.map);
 			list_add_tail(&new->list, &head);
 		}
 		parent = parent->parent;
@@ -1230,6 +1236,7 @@ int callchain_node__make_parent_list(struct callchain_node *node)
 out:
 	list_for_each_entry_safe(chain, new, &head, list) {
 		list_del(&chain->list);
+		map__zput(chain->ms.map);
 		free(chain);
 	}
 	return -ENOMEM;

tools/perf/util/callchain.h

@@ -5,6 +5,7 @@
 #include <linux/list.h>
 #include <linux/rbtree.h>
 #include "event.h"
+#include "map.h"
 #include "symbol.h"
 
 #define HELP_PAD "\t\t\t\t"
@@ -184,8 +185,13 @@ int callchain_merge(struct callchain_cursor *cursor,
  */
 static inline void callchain_cursor_reset(struct callchain_cursor *cursor)
 {
+	struct callchain_cursor_node *node;
+
 	cursor->nr = 0;
 	cursor->last = &cursor->first;
+
+	for (node = cursor->first; node != NULL; node = node->next)
+		map__zput(node->map);
 }
 
 int callchain_cursor_append(struct callchain_cursor *cursor, u64 ip,

tools/perf/util/hist.c

@@ -1,6 +1,7 @@
 #include "util.h"
 #include "build-id.h"
 #include "hist.h"
+#include "map.h"
 #include "session.h"
 #include "sort.h"
 #include "evlist.h"
@@ -1019,6 +1020,10 @@ int hist_entry_iter__add(struct hist_entry_iter *iter, struct addr_location *al,
 			 int max_stack_depth, void *arg)
 {
 	int err, err2;
+	struct map *alm = NULL;
+
+	if (al && al->map)
+		alm = map__get(al->map);
 
 	err = sample__resolve_callchain(iter->sample, &callchain_cursor, &iter->parent,
 					iter->evsel, al, max_stack_depth);
@@ -1058,6 +1063,8 @@ out:
 	if (!err)
 		err = err2;
 
+	map__put(alm);
+
 	return err;
 }
 

tools/perf/util/hist.h

@@ -283,6 +283,8 @@ void perf_hpp_list__column_register(struct perf_hpp_list *list,
 				    struct perf_hpp_fmt *format);
 void perf_hpp_list__register_sort_field(struct perf_hpp_list *list,
 					struct perf_hpp_fmt *format);
+void perf_hpp_list__prepend_sort_field(struct perf_hpp_list *list,
+				       struct perf_hpp_fmt *format);
 
 static inline void perf_hpp__column_register(struct perf_hpp_fmt *format)
 {
@@ -294,6 +296,11 @@ static inline void perf_hpp__register_sort_field(struct perf_hpp_fmt *format)
 	perf_hpp_list__register_sort_field(&perf_hpp_list, format);
 }
 
+static inline void perf_hpp__prepend_sort_field(struct perf_hpp_fmt *format)
+{
+	perf_hpp_list__prepend_sort_field(&perf_hpp_list, format);
+}
+
 #define perf_hpp_list__for_each_format(_list, format) \
 	list_for_each_entry(format, &(_list)->fields, list)