perf callchain: Create real callchain entries for inlined frames

The inline_node structs are maintained by the new dso->inlines tree.
This in turn keeps ownership of the fake symbols and srcline string
representing an inline frame.

This tree is sorted by address to allow quick lookups. All other entries
of the symbol beside the function name are unused for inline frames. The
advantage of this approach is that all existing users of the callchain
API can now transparently display inlined frames without having to patch
their code.

Signed-off-by: Milian Wolff <milian.wolff@kdab.com>
Reviewed-by: Jiri Olsa <jolsa@redhat.com>
Reviewed-by: Namhyung Kim <namhyung@kernel.org>
Cc: David Ahern <dsahern@gmail.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Yao Jin <yao.jin@linux.intel.com>
Link: http://lkml.kernel.org/r/20171009203310.17362-6-milian.wolff@kdab.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/util/dso.c

@@ -10,6 +10,7 @@
 #include "compress.h"
 #include "path.h"
 #include "symbol.h"
+#include "srcline.h"
 #include "dso.h"
 #include "machine.h"
 #include "auxtrace.h"
@@ -1201,6 +1202,7 @@ struct dso *dso__new(const char *name)
 		for (i = 0; i < MAP__NR_TYPES; ++i)
 			dso->symbols[i] = dso->symbol_names[i] = RB_ROOT;
 		dso->data.cache = RB_ROOT;
+		dso->inlined_nodes = RB_ROOT;
 		dso->data.fd = -1;
 		dso->data.status = DSO_DATA_STATUS_UNKNOWN;
 		dso->symtab_type = DSO_BINARY_TYPE__NOT_FOUND;
@@ -1232,6 +1234,9 @@ void dso__delete(struct dso *dso)
 	if (!RB_EMPTY_NODE(&dso->rb_node))
 		pr_err("DSO %s is still in rbtree when being deleted!\n",
 		       dso->long_name);
+
+	/* free inlines first, as they reference symbols */
+	inlines__tree_delete(&dso->inlined_nodes);
 	for (i = 0; i < MAP__NR_TYPES; ++i)
 		symbols__delete(&dso->symbols[i]);
 

tools/perf/util/dso.h

@@ -141,6 +141,7 @@ struct dso {
 	struct rb_root	 *root;		/* root of rbtree that rb_node is in */
 	struct rb_root	 symbols[MAP__NR_TYPES];
 	struct rb_root	 symbol_names[MAP__NR_TYPES];
+	struct rb_root	 inlined_nodes;
 	struct {
 		u64		addr;
 		struct symbol	*symbol;

tools/perf/util/machine.c

@@ -2109,6 +2109,40 @@ static int thread__resolve_callchain_sample(struct thread *thread,
 	return 0;
 }
 
+static int append_inlines(struct callchain_cursor *cursor,
+			  struct map *map, struct symbol *sym, u64 ip)
+{
+	struct inline_node *inline_node;
+	struct inline_list *ilist;
+	u64 addr;
+
+	if (!symbol_conf.inline_name || !map || !sym)
+		return 1;
+
+	addr = map__rip_2objdump(map, ip);
+
+	inline_node = inlines__tree_find(&map->dso->inlined_nodes, addr);
+	if (!inline_node) {
+		inline_node = dso__parse_addr_inlines(map->dso, addr, sym);
+		if (!inline_node)
+			return 1;
+
+		inlines__tree_insert(&map->dso->inlined_nodes, inline_node);
+	}
+
+	list_for_each_entry(ilist, &inline_node->val, list) {
+		int ret = callchain_cursor_append(cursor, ip, map,
+						  ilist->symbol, false,
+						  NULL, 0, 0, 0,
+						  ilist->srcline);
+
+		if (ret != 0)
+			return ret;
+	}
+
+	return 0;
+}
+
 static int unwind_entry(struct unwind_entry *entry, void *arg)
 {
 	struct callchain_cursor *cursor = arg;
@@ -2117,6 +2151,9 @@ static int unwind_entry(struct unwind_entry *entry, void *arg)
 	if (symbol_conf.hide_unresolved && entry->sym == NULL)
 		return 0;
 
+	if (append_inlines(cursor, entry->map, entry->sym, entry->ip) == 0)
+		return 0;
+
 	srcline = callchain_srcline(entry->map, entry->sym, entry->ip);
 	return callchain_cursor_append(cursor, entry->ip,
 				       entry->map, entry->sym,

tools/perf/util/srcline.c

@@ -583,3 +583,54 @@ void inline_node__delete(struct inline_node *node)
 
 	free(node);
 }
+
+void inlines__tree_insert(struct rb_root *tree, struct inline_node *inlines)
+{
+	struct rb_node **p = &tree->rb_node;
+	struct rb_node *parent = NULL;
+	const u64 addr = inlines->addr;
+	struct inline_node *i;
+
+	while (*p != NULL) {
+		parent = *p;
+		i = rb_entry(parent, struct inline_node, rb_node);
+		if (addr < i->addr)
+			p = &(*p)->rb_left;
+		else
+			p = &(*p)->rb_right;
+	}
+	rb_link_node(&inlines->rb_node, parent, p);
+	rb_insert_color(&inlines->rb_node, tree);
+}
+
+struct inline_node *inlines__tree_find(struct rb_root *tree, u64 addr)
+{
+	struct rb_node *n = tree->rb_node;
+
+	while (n) {
+		struct inline_node *i = rb_entry(n, struct inline_node,
+						 rb_node);
+
+		if (addr < i->addr)
+			n = n->rb_left;
+		else if (addr > i->addr)
+			n = n->rb_right;
+		else
+			return i;
+	}
+
+	return NULL;
+}
+
+void inlines__tree_delete(struct rb_root *tree)
+{
+	struct inline_node *pos;
+	struct rb_node *next = rb_first(tree);
+
+	while (next) {
+		pos = rb_entry(next, struct inline_node, rb_node);
+		next = rb_next(&pos->rb_node);
+		rb_erase(&pos->rb_node, tree);
+		inline_node__delete(pos);
+	}
+}

tools/perf/util/srcline.h

@@ -2,6 +2,7 @@
 #define PERF_SRCLINE_H
 
 #include <linux/list.h>
+#include <linux/rbtree.h>
 #include <linux/types.h>
 
 struct dso;
@@ -25,6 +26,7 @@ struct inline_list {
 struct inline_node {
 	u64			addr;
 	struct list_head	val;
+	struct rb_node		rb_node;
 };
 
 /* parse inlined frames for the given address */
@@ -33,4 +35,11 @@ struct inline_node *dso__parse_addr_inlines(struct dso *dso, u64 addr,
 /* free resources associated to the inline node list */
 void inline_node__delete(struct inline_node *node);
 
+/* insert the inline node list into the DSO, which will take ownership */
+void inlines__tree_insert(struct rb_root *tree, struct inline_node *inlines);
+/* find previously inserted inline node list */
+struct inline_node *inlines__tree_find(struct rb_root *tree, u64 addr);
+/* delete all nodes within the tree of inline_node s */
+void inlines__tree_delete(struct rb_root *tree);
+
 #endif /* PERF_SRCLINE_H */