perf tools: Reference count struct dso

This has a different model than the 'thread' and 'map' struct lifetimes:
there is not a definitive "don't use this DSO anymore" event, i.e. we may
get many 'struct map' holding references to the '/usr/lib64/libc-2.20.so'
DSO but then at some point some DSO may have no references but we still
don't want to straight away release its resources, because "soon" we may
get a new 'struct map' that needs it and we want to reuse its symtab or
other resources.

So we need some way to garbage collect it when crossing some memory
usage threshold, which is left for anoter patch, for now it is
sufficient to release it when calling dsos__exit(), i.e. when deleting
the whole list as part of deleting the 'struct machine' containing it,
which will leave only referenced objects being used.

Cc: Adrian Hunter <adrian.hunter@intel.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: http://lkml.kernel.org/n/tip-majzgz07cm90t2tejrjy4clf@git.kernel.org
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>

tools/perf/tests/dso-data.c

@@ -166,7 +166,7 @@ int test__dso_data(void)
 		free(buf);
 	}
 
-	dso__delete(dso);
+	dso__put(dso);
 	unlink(file);
 	return 0;
 }
@@ -226,7 +226,7 @@ static void dsos__delete(int cnt)
 		struct dso *dso = dsos[i];
 
 		unlink(dso->name);
-		dso__delete(dso);
+		dso__put(dso);
 	}
 
 	free(dsos);

tools/perf/tests/hists_common.c

@@ -134,11 +134,15 @@ struct machine *setup_fake_machine(struct machines *machines)
 
 			sym = symbol__new(fsym->start, fsym->length,
 					  STB_GLOBAL, fsym->name);
-			if (sym == NULL)
+			if (sym == NULL) {
+				dso__put(dso);
 				goto out;
+			}
 
 			symbols__insert(&dso->symbols[MAP__FUNCTION], sym);
 		}
+
+		dso__put(dso);
 	}
 
 	return machine;

tools/perf/util/dso.c

@@ -1049,6 +1049,7 @@ struct dso *dso__new(const char *name)
 		INIT_LIST_HEAD(&dso->node);
 		INIT_LIST_HEAD(&dso->data.open_entry);
 		pthread_mutex_init(&dso->lock, NULL);
+		atomic_set(&dso->refcnt, 1);
 	}
 
 	return dso;
@@ -1083,6 +1084,19 @@ void dso__delete(struct dso *dso)
 	free(dso);
 }
 
+struct dso *dso__get(struct dso *dso)
+{
+	if (dso)
+		atomic_inc(&dso->refcnt);
+	return dso;
+}
+
+void dso__put(struct dso *dso)
+{
+	if (dso && atomic_dec_and_test(&dso->refcnt))
+		dso__delete(dso);
+}
+
 void dso__set_build_id(struct dso *dso, void *build_id)
 {
 	memcpy(dso->build_id, build_id, sizeof(dso->build_id));
@@ -1153,6 +1167,27 @@ void __dsos__add(struct dsos *dsos, struct dso *dso)
 {
 	list_add_tail(&dso->node, &dsos->head);
 	__dso__findlink_by_longname(&dsos->root, dso, NULL);
+	/*
+	 * It is now in the linked list, grab a reference, then garbage collect
+	 * this when needing memory, by looking at LRU dso instances in the
+	 * list with atomic_read(&dso->refcnt) == 1, i.e. no references
+	 * anywhere besides the one for the list, do, under a lock for the
+	 * list: remove it from the list, then a dso__put(), that probably will
+	 * be the last and will then call dso__delete(), end of life.
+	 *
+	 * That, or at the end of the 'struct machine' lifetime, when all
+	 * 'struct dso' instances will be removed from the list, in
+	 * dsos__exit(), if they have no other reference from some other data
+	 * structure.
+	 *
+	 * E.g.: after processing a 'perf.data' file and storing references
+	 * to objects instantiated while processing events, we will have
+	 * references to the 'thread', 'map', 'dso' structs all from 'struct
+	 * hist_entry' instances, but we may not need anything not referenced,
+	 * so we might as well call machines__exit()/machines__delete() and
+	 * garbage collect it.
+	 */
+	dso__get(dso);
 }
 
 void dsos__add(struct dsos *dsos, struct dso *dso)
@@ -1206,7 +1241,7 @@ struct dso *dsos__findnew(struct dsos *dsos, const char *name)
 {
 	struct dso *dso;
 	pthread_rwlock_wrlock(&dsos->lock);
-	dso = __dsos__findnew(dsos, name);
+	dso = dso__get(__dsos__findnew(dsos, name));
 	pthread_rwlock_unlock(&dsos->lock);
 	return dso;
 }

tools/perf/util/dso.h

@@ -1,6 +1,7 @@
 #ifndef __PERF_DSO
 #define __PERF_DSO
 
+#include <linux/atomic.h>
 #include <linux/types.h>
 #include <linux/rbtree.h>
 #include <stdbool.h>
@@ -179,7 +180,7 @@ struct dso {
 		void	 *priv;
 		u64	 db_id;
 	};
-
+	atomic_t	 refcnt;
 	char		 name[0];
 };
 
@@ -206,6 +207,17 @@ void dso__set_long_name(struct dso *dso, const char *name, bool name_allocated);
 
 int dso__name_len(const struct dso *dso);
 
+struct dso *dso__get(struct dso *dso);
+void dso__put(struct dso *dso);
+
+static inline void __dso__zput(struct dso **dso)
+{
+	dso__put(*dso);
+	*dso = NULL;
+}
+
+#define dso__zput(dso) __dso__zput(&dso)
+
 bool dso__loaded(const struct dso *dso, enum map_type type);
 
 bool dso__sorted_by_name(const struct dso *dso, enum map_type type);

tools/perf/util/header.c

@@ -1277,6 +1277,7 @@ static int __event_process_build_id(struct build_id_event *bev,
 				  sbuild_id);
 		pr_debug("build id event received for %s: %s\n",
 			 dso->long_name, sbuild_id);
+		dso__put(dso);
 	}
 
 	err = 0;

tools/perf/util/machine.c

@@ -82,7 +82,7 @@ out_delete:
 	return NULL;
 }
 
-static void dsos__exit(struct dsos *dsos)
+static void dsos__purge(struct dsos *dsos)
 {
 	struct dso *pos, *n;
 
@@ -90,12 +90,16 @@ static void dsos__exit(struct dsos *dsos)
 
 	list_for_each_entry_safe(pos, n, &dsos->head, node) {
 		RB_CLEAR_NODE(&pos->rb_node);
-		list_del(&pos->node);
-		dso__delete(pos);
+		list_del_init(&pos->node);
+		dso__put(pos);
 	}
 
 	pthread_rwlock_unlock(&dsos->lock);
+}
 
+static void dsos__exit(struct dsos *dsos)
+{
+	dsos__purge(dsos);
 	pthread_rwlock_destroy(&dsos->lock);
 }
 
@@ -524,6 +528,7 @@ static struct dso *machine__findnew_module_dso(struct machine *machine,
 		dso__set_long_name(dso, strdup(filename), true);
 	}
 
+	dso__get(dso);
 out_unlock:
 	pthread_rwlock_unlock(&machine->dsos.lock);
 	return dso;
@@ -1205,8 +1210,10 @@ static int machine__process_kernel_mmap_event(struct machine *machine,
 			goto out_problem;
 
 		kernel->kernel = kernel_type;
-		if (__machine__create_kernel_maps(machine, kernel) < 0)
+		if (__machine__create_kernel_maps(machine, kernel) < 0) {
+			dso__put(kernel);
 			goto out_problem;
+		}
 
 		if (strstr(kernel->long_name, "vmlinux"))
 			dso__set_short_name(kernel, "[kernel.vmlinux]", false);

tools/perf/util/map.c

@@ -132,7 +132,7 @@ void map__init(struct map *map, enum map_type type,
 	map->end      = end;
 	map->pgoff    = pgoff;
 	map->reloc    = 0;
-	map->dso      = dso;
+	map->dso      = dso__get(dso);
 	map->map_ip   = map__map_ip;
 	map->unmap_ip = map__unmap_ip;
 	RB_CLEAR_NODE(&map->rb_node);
@@ -198,6 +198,7 @@ struct map *map__new(struct machine *machine, u64 start, u64 len,
 			if (type != MAP__FUNCTION)
 				dso__set_loaded(dso, map->type);
 		}
+		dso__put(dso);
 	}
 	return map;
 out_delete:
@@ -224,9 +225,15 @@ struct map *map__new2(u64 start, struct dso *dso, enum map_type type)
 	return map;
 }
 
-void map__delete(struct map *map)
+static void map__exit(struct map *map)
 {
 	BUG_ON(!RB_EMPTY_NODE(&map->rb_node));
+	dso__zput(map->dso);
+}
+
+void map__delete(struct map *map)
+{
+	map__exit(map);
 	free(map);
 }
 

tools/perf/util/probe-finder.c

@@ -130,7 +130,7 @@ struct debuginfo *debuginfo__new(const char *path)
 			continue;
 		dinfo = __debuginfo__new(buf);
 	}
-	dso__delete(dso);
+	dso__put(dso);
 
 out:
 	/* if failed to open all distro debuginfo, open given binary */

tools/perf/util/symbol-elf.c

@@ -1016,7 +1016,7 @@ int dso__load_sym(struct dso *dso, struct map *map,
 				curr_map = map__new2(start, curr_dso,
 						     map->type);
 				if (curr_map == NULL) {
-					dso__delete(curr_dso);
+					dso__put(curr_dso);
 					goto out_elf_end;
 				}
 				if (adjust_kernel_syms) {

tools/perf/util/symbol.c

@@ -786,7 +786,7 @@ static int dso__split_kallsyms(struct dso *dso, struct map *map, u64 delta,
 
 			curr_map = map__new2(pos->start, ndso, map->type);
 			if (curr_map == NULL) {
-				dso__delete(ndso);
+				dso__put(ndso);
 				return -1;
 			}
 

tools/perf/util/vdso.c

@@ -314,6 +314,7 @@ struct dso *machine__findnew_vdso(struct machine *machine,
 	}
 
 out_unlock:
+	dso__get(dso);
 	pthread_rwlock_unlock(&machine->dsos.lock);
 	return dso;
 }