1 files changed, 339 insertions, 190 deletions

diff --git a/tools/perf/util/dsos.c b/tools/perf/util/dsos.c
index cf80aa42dd07..ab3d0c01dd63 100644
--- a/tools/perf/util/dsos.c
+++ b/tools/perf/util/dsos.c
@@ -12,115 +12,140 @@
 #include <symbol.h> // filename__read_build_id
 #include <unistd.h>
 
-static int __dso_id__cmp(struct dso_id *a, struct dso_id *b)
+void dsos__init(struct dsos *dsos)
 {
-	if (a->maj > b->maj) return -1;
-	if (a->maj < b->maj) return 1;
+	init_rwsem(&dsos->lock);
 
-	if (a->min > b->min) return -1;
-	if (a->min < b->min) return 1;
+	dsos->cnt = 0;
+	dsos->allocated = 0;
+	dsos->dsos = NULL;
+	dsos->sorted = true;
+}
 
-	if (a->ino > b->ino) return -1;
-	if (a->ino < b->ino) return 1;
+static void dsos__purge(struct dsos *dsos)
+{
+	down_write(&dsos->lock);
 
-	/*
-	 * Synthesized MMAP events have zero ino_generation, avoid comparing
-	 * them with MMAP events with actual ino_generation.
-	 *
-	 * I found it harmful because the mismatch resulted in a new
-	 * dso that did not have a build ID whereas the original dso did have a
-	 * build ID. The build ID was essential because the object was not found
-	 * otherwise. - Adrian
-	 */
-	if (a->ino_generation && b->ino_generation) {
-		if (a->ino_generation > b->ino_generation) return -1;
-		if (a->ino_generation < b->ino_generation) return 1;
-	}
+	for (unsigned int i = 0; i < dsos->cnt; i++) {
+		struct dso *dso = dsos->dsos[i];
 
-	return 0;
-}
+		dso__set_dsos(dso, NULL);
+		dso__put(dso);
+	}
 
-static bool dso_id__empty(struct dso_id *id)
-{
-	if (!id)
-		return true;
+	zfree(&dsos->dsos);
+	dsos->cnt = 0;
+	dsos->allocated = 0;
+	dsos->sorted = true;
 
-	return !id->maj && !id->min && !id->ino && !id->ino_generation;
+	up_write(&dsos->lock);
 }
 
-static void dso__inject_id(struct dso *dso, struct dso_id *id)
+void dsos__exit(struct dsos *dsos)
 {
-	dso->id.maj = id->maj;
-	dso->id.min = id->min;
-	dso->id.ino = id->ino;
-	dso->id.ino_generation = id->ino_generation;
+	dsos__purge(dsos);
+	exit_rwsem(&dsos->lock);
 }
 
-static int dso_id__cmp(struct dso_id *a, struct dso_id *b)
+
+static int __dsos__for_each_dso(struct dsos *dsos,
+				int (*cb)(struct dso *dso, void *data),
+				void *data)
 {
-	/*
-	 * The second is always dso->id, so zeroes if not set, assume passing
-	 * NULL for a means a zeroed id
-	 */
-	if (dso_id__empty(a) || dso_id__empty(b))
-		return 0;
+	for (unsigned int i = 0; i < dsos->cnt; i++) {
+		struct dso *dso = dsos->dsos[i];
+		int err;
 
-	return __dso_id__cmp(a, b);
+		err = cb(dso, data);
+		if (err)
+			return err;
+	}
+	return 0;
 }
 
-int dso__cmp_id(struct dso *a, struct dso *b)
-{
-	return __dso_id__cmp(&a->id, &b->id);
-}
+struct dsos__read_build_ids_cb_args {
+	bool with_hits;
+	bool have_build_id;
+};
 
-bool __dsos__read_build_ids(struct list_head *head, bool with_hits)
+static int dsos__read_build_ids_cb(struct dso *dso, void *data)
 {
-	bool have_build_id = false;
-	struct dso *pos;
+	struct dsos__read_build_ids_cb_args *args = data;
 	struct nscookie nsc;
 
-	list_for_each_entry(pos, head, node) {
-		if (with_hits && !pos->hit && !dso__is_vdso(pos))
-			continue;
-		if (pos->has_build_id) {
-			have_build_id = true;
-			continue;
-		}
-		nsinfo__mountns_enter(pos->nsinfo, &nsc);
-		if (filename__read_build_id(pos->long_name, &pos->bid) > 0) {
-			have_build_id	  = true;
-			pos->has_build_id = true;
-		} else if (errno == ENOENT && pos->nsinfo) {
-			char *new_name = dso__filename_with_chroot(pos, pos->long_name);
-
-			if (new_name && filename__read_build_id(new_name,
-								&pos->bid) > 0) {
-				have_build_id = true;
-				pos->has_build_id = true;
-			}
-			free(new_name);
+	if (args->with_hits && !dso__hit(dso) && !dso__is_vdso(dso))
+		return 0;
+	if (dso__has_build_id(dso)) {
+		args->have_build_id = true;
+		return 0;
+	}
+	nsinfo__mountns_enter(dso__nsinfo(dso), &nsc);
+	if (filename__read_build_id(dso__long_name(dso), dso__bid(dso)) > 0) {
+		args->have_build_id = true;
+		dso__set_has_build_id(dso);
+	} else if (errno == ENOENT && dso__nsinfo(dso)) {
+		char *new_name = dso__filename_with_chroot(dso, dso__long_name(dso));
+
+		if (new_name && filename__read_build_id(new_name, dso__bid(dso)) > 0) {
+			args->have_build_id = true;
+			dso__set_has_build_id(dso);
 		}
-		nsinfo__mountns_exit(&nsc);
+		free(new_name);
 	}
+	nsinfo__mountns_exit(&nsc);
+	return 0;
+}
 
-	return have_build_id;
+bool dsos__read_build_ids(struct dsos *dsos, bool with_hits)
+{
+	struct dsos__read_build_ids_cb_args args = {
+		.with_hits = with_hits,
+		.have_build_id = false,
+	};
+
+	dsos__for_each_dso(dsos, dsos__read_build_ids_cb, &args);
+	return args.have_build_id;
 }
 
-static int __dso__cmp_long_name(const char *long_name, struct dso_id *id, struct dso *b)
+static int __dso__cmp_long_name(const char *long_name, const struct dso_id *id,
+				const struct dso *b)
 {
-	int rc = strcmp(long_name, b->long_name);
-	return rc ?: dso_id__cmp(id, &b->id);
+	int rc = strcmp(long_name, dso__long_name(b));
+	return rc ?: dso_id__cmp(id, dso__id_const(b));
 }
 
-static int __dso__cmp_short_name(const char *short_name, struct dso_id *id, struct dso *b)
+static int __dso__cmp_short_name(const char *short_name, const struct dso_id *id,
+				 const struct dso *b)
 {
-	int rc = strcmp(short_name, b->short_name);
-	return rc ?: dso_id__cmp(id, &b->id);
+	int rc = strcmp(short_name, dso__short_name(b));
+	return rc ?: dso_id__cmp(id, dso__id_const(b));
 }
 
-static int dso__cmp_short_name(struct dso *a, struct dso *b)
+static int dsos__cmp_long_name_id_short_name(const void *va, const void *vb)
 {
-	return __dso__cmp_short_name(a->short_name, &a->id, b);
+	const struct dso *a = *((const struct dso **)va);
+	const struct dso *b = *((const struct dso **)vb);
+	int rc = strcmp(dso__long_name(a), dso__long_name(b));
+
+	if (!rc) {
+		rc = dso_id__cmp(dso__id_const(a), dso__id_const(b));
+		if (!rc)
+			rc = strcmp(dso__short_name(a), dso__short_name(b));
+	}
+	return rc;
+}
+
+struct dsos__key {
+	const char *long_name;
+	const struct dso_id *id;
+};
+
+static int dsos__cmp_key_long_name_id(const void *vkey, const void *vdso)
+{
+	const struct dsos__key *key = vkey;
+	const struct dso *dso = *((const struct dso **)vdso);
+
+	return __dso__cmp_long_name(key->long_name, key->id, dso);
 }
 
 /*
@@ -128,110 +153,121 @@ static int dso__cmp_short_name(struct dso *a, struct dso *b)
  * Either one of the dso or name parameter must be non-NULL or the
  * function will not work.
  */
-struct dso *__dsos__findnew_link_by_longname_id(struct rb_root *root, struct dso *dso,
-						const char *name, struct dso_id *id)
+static struct dso *__dsos__find_by_longname_id(struct dsos *dsos,
+					       const char *name,
+					       struct dso_id *id,
+					       bool write_locked)
 {
-	struct rb_node **p = &root->rb_node;
-	struct rb_node  *parent = NULL;
-
-	if (!name)
-		name = dso->long_name;
-	/*
-	 * Find node with the matching name
-	 */
-	while (*p) {
-		struct dso *this = rb_entry(*p, struct dso, rb_node);
-		int rc = __dso__cmp_long_name(name, id, this);
-
-		parent = *p;
-		if (rc == 0) {
-			/*
-			 * In case the new DSO is a duplicate of an existing
-			 * one, print a one-time warning & put the new entry
-			 * at the end of the list of duplicates.
-			 */
-			if (!dso || (dso == this))
-				return this;	/* Find matching dso */
-			/*
-			 * The core kernel DSOs may have duplicated long name.
-			 * In this case, the short name should be different.
-			 * Comparing the short names to differentiate the DSOs.
-			 */
-			rc = dso__cmp_short_name(dso, this);
-			if (rc == 0) {
-				pr_err("Duplicated dso name: %s\n", name);
-				return NULL;
-			}
+	struct dsos__key key = {
+		.long_name = name,
+		.id = id,
+	};
+	struct dso **res;
+
+	if (!dsos->sorted) {
+		if (!write_locked) {
+			struct dso *dso;
+
+			up_read(&dsos->lock);
+			down_write(&dsos->lock);
+			dso = __dsos__find_by_longname_id(dsos, name, id,
+							  /*write_locked=*/true);
+			up_write(&dsos->lock);
+			down_read(&dsos->lock);
+			return dso;
 		}
-		if (rc < 0)
-			p = &parent->rb_left;
-		else
-			p = &parent->rb_right;
+		qsort(dsos->dsos, dsos->cnt, sizeof(struct dso *),
+		      dsos__cmp_long_name_id_short_name);
+		dsos->sorted = true;
 	}
-	if (dso) {
-		/* Add new node and rebalance tree */
-		rb_link_node(&dso->rb_node, parent, p);
-		rb_insert_color(&dso->rb_node, root);
-		dso->root = root;
-	}
-	return NULL;
+
+	res = bsearch(&key, dsos->dsos, dsos->cnt, sizeof(struct dso *),
+		      dsos__cmp_key_long_name_id);
+	if (!res)
+		return NULL;
+
+	return dso__get(*res);
 }
 
-void __dsos__add(struct dsos *dsos, struct dso *dso)
+int __dsos__add(struct dsos *dsos, struct dso *dso)
 {
-	list_add_tail(&dso->node, &dsos->head);
-	__dsos__findnew_link_by_longname_id(&dsos->root, dso, NULL, &dso->id);
-	/*
-	 * 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);
+	if (dsos->cnt == dsos->allocated) {
+		unsigned int to_allocate = 2;
+		struct dso **temp;
+
+		if (dsos->allocated > 0)
+			to_allocate = dsos->allocated * 2;
+		temp = realloc(dsos->dsos, sizeof(struct dso *) * to_allocate);
+		if (!temp)
+			return -ENOMEM;
+		dsos->dsos = temp;
+		dsos->allocated = to_allocate;
+	}
+	dsos->dsos[dsos->cnt++] = dso__get(dso);
+	if (dsos->cnt >= 2 && dsos->sorted) {
+		dsos->sorted = dsos__cmp_long_name_id_short_name(&dsos->dsos[dsos->cnt - 2],
+								 &dsos->dsos[dsos->cnt - 1])
+			<= 0;
+	}
+	dso__set_dsos(dso, dsos);
+	return 0;
 }
 
-void dsos__add(struct dsos *dsos, struct dso *dso)
+int dsos__add(struct dsos *dsos, struct dso *dso)
 {
+	int ret;
+
 	down_write(&dsos->lock);
-	__dsos__add(dsos, dso);
+	ret = __dsos__add(dsos, dso);
 	up_write(&dsos->lock);
+	return ret;
 }
 
-static struct dso *__dsos__findnew_by_longname_id(struct rb_root *root, const char *name, struct dso_id *id)
+struct dsos__find_id_cb_args {
+	const char *name;
+	struct dso_id *id;
+	struct dso *res;
+};
+
+static int dsos__find_id_cb(struct dso *dso, void *data)
 {
-	return __dsos__findnew_link_by_longname_id(root, NULL, name, id);
+	struct dsos__find_id_cb_args *args = data;
+
+	if (__dso__cmp_short_name(args->name, args->id, dso) == 0) {
+		args->res = dso__get(dso);
+		return 1;
+	}
+	return 0;
+
 }
 
-static struct dso *__dsos__find_id(struct dsos *dsos, const char *name, struct dso_id *id, bool cmp_short)
+static struct dso *__dsos__find_id(struct dsos *dsos, const char *name, struct dso_id *id,
+				   bool cmp_short, bool write_locked)
 {
-	struct dso *pos;
+	struct dso *res;
 
 	if (cmp_short) {
-		list_for_each_entry(pos, &dsos->head, node)
-			if (__dso__cmp_short_name(name, id, pos) == 0)
-				return pos;
-		return NULL;
+		struct dsos__find_id_cb_args args = {
+			.name = name,
+			.id = id,
+			.res = NULL,
+		};
+
+		__dsos__for_each_dso(dsos, dsos__find_id_cb, &args);
+		return args.res;
 	}
-	return __dsos__findnew_by_longname_id(&dsos->root, name, id);
+	res = __dsos__find_by_longname_id(dsos, name, id, write_locked);
+	return res;
 }
 
-struct dso *__dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
+struct dso *dsos__find(struct dsos *dsos, const char *name, bool cmp_short)
 {
-	return __dsos__find_id(dsos, name, NULL, cmp_short);
+	struct dso *res;
+
+	down_read(&dsos->lock);
+	res = __dsos__find_id(dsos, name, NULL, cmp_short, /*write_locked=*/false);
+	up_read(&dsos->lock);
+	return res;
 }
 
 static void dso__set_basename(struct dso *dso)
@@ -239,7 +275,7 @@ static void dso__set_basename(struct dso *dso)
 	char *base, *lname;
 	int tid;
 
-	if (sscanf(dso->long_name, "/tmp/perf-%d.map", &tid) == 1) {
+	if (sscanf(dso__long_name(dso), "/tmp/perf-%d.map", &tid) == 1) {
 		if (asprintf(&base, "[JIT] tid %d", tid) < 0)
 			return;
 	} else {
@@ -247,7 +283,7 @@ static void dso__set_basename(struct dso *dso)
 	       * basename() may modify path buffer, so we must pass
                * a copy.
                */
-		lname = strdup(dso->long_name);
+		lname = strdup(dso__long_name(dso));
 		if (!lname)
 			return;
 
@@ -271,25 +307,23 @@ static struct dso *__dsos__addnew_id(struct dsos *dsos, const char *name, struct
 	struct dso *dso = dso__new_id(name, id);
 
 	if (dso != NULL) {
-		__dsos__add(dsos, dso);
+		/*
+		 * The dsos lock is held on entry, so rename the dso before
+		 * adding it to avoid needing to take the dsos lock again to say
+		 * the array isn't sorted.
+		 */
 		dso__set_basename(dso);
-		/* Put dso here because __dsos_add already got it */
-		dso__put(dso);
+		__dsos__add(dsos, dso);
 	}
 	return dso;
 }
 
-struct dso *__dsos__addnew(struct dsos *dsos, const char *name)
-{
-	return __dsos__addnew_id(dsos, name, NULL);
-}
-
 static struct dso *__dsos__findnew_id(struct dsos *dsos, const char *name, struct dso_id *id)
 {
-	struct dso *dso = __dsos__find_id(dsos, name, id, false);
+	struct dso *dso = __dsos__find_id(dsos, name, id, false, /*write_locked=*/true);
 
-	if (dso && dso_id__empty(&dso->id) && !dso_id__empty(id))
-		dso__inject_id(dso, id);
+	if (dso && dso_id__empty(dso__id(dso)) && !dso_id__empty(id))
+		__dso__inject_id(dso, id);
 
 	return dso ? dso : __dsos__addnew_id(dsos, name, id);
 }
@@ -298,36 +332,151 @@ struct dso *dsos__findnew_id(struct dsos *dsos, const char *name, struct dso_id
 {
 	struct dso *dso;
 	down_write(&dsos->lock);
-	dso = dso__get(__dsos__findnew_id(dsos, name, id));
+	dso = __dsos__findnew_id(dsos, name, id);
 	up_write(&dsos->lock);
 	return dso;
 }
 
-size_t __dsos__fprintf_buildid(struct list_head *head, FILE *fp,
-			       bool (skip)(struct dso *dso, int parm), int parm)
+struct dsos__fprintf_buildid_cb_args {
+	FILE *fp;
+	bool (*skip)(struct dso *dso, int parm);
+	int parm;
+	size_t ret;
+};
+
+static int dsos__fprintf_buildid_cb(struct dso *dso, void *data)
 {
-	struct dso *pos;
-	size_t ret = 0;
+	struct dsos__fprintf_buildid_cb_args *args = data;
+	char sbuild_id[SBUILD_ID_SIZE];
 
-	list_for_each_entry(pos, head, node) {
-		char sbuild_id[SBUILD_ID_SIZE];
+	if (args->skip && args->skip(dso, args->parm))
+		return 0;
+	build_id__sprintf(dso__bid(dso), sbuild_id);
+	args->ret += fprintf(args->fp, "%-40s %s\n", sbuild_id, dso__long_name(dso));
+	return 0;
+}
 
-		if (skip && skip(pos, parm))
-			continue;
-		build_id__sprintf(&pos->bid, sbuild_id);
-		ret += fprintf(fp, "%-40s %s\n", sbuild_id, pos->long_name);
-	}
-	return ret;
+size_t dsos__fprintf_buildid(struct dsos *dsos, FILE *fp,
+			       bool (*skip)(struct dso *dso, int parm), int parm)
+{
+	struct dsos__fprintf_buildid_cb_args args = {
+		.fp = fp,
+		.skip = skip,
+		.parm = parm,
+		.ret = 0,
+	};
+
+	dsos__for_each_dso(dsos, dsos__fprintf_buildid_cb, &args);
+	return args.ret;
+}
+
+struct dsos__fprintf_cb_args {
+	FILE *fp;
+	size_t ret;
+};
+
+static int dsos__fprintf_cb(struct dso *dso, void *data)
+{
+	struct dsos__fprintf_cb_args *args = data;
+
+	args->ret += dso__fprintf(dso, args->fp);
+	return 0;
+}
+
+size_t dsos__fprintf(struct dsos *dsos, FILE *fp)
+{
+	struct dsos__fprintf_cb_args args = {
+		.fp = fp,
+		.ret = 0,
+	};
+
+	dsos__for_each_dso(dsos, dsos__fprintf_cb, &args);
+	return args.ret;
+}
+
+static int dsos__hit_all_cb(struct dso *dso, void *data __maybe_unused)
+{
+	dso__set_hit(dso);
+	return 0;
+}
+
+int dsos__hit_all(struct dsos *dsos)
+{
+	return dsos__for_each_dso(dsos, dsos__hit_all_cb, NULL);
 }
 
-size_t __dsos__fprintf(struct list_head *head, FILE *fp)
+struct dso *dsos__findnew_module_dso(struct dsos *dsos,
+				     struct machine *machine,
+				     struct kmod_path *m,
+				     const char *filename)
 {
-	struct dso *pos;
-	size_t ret = 0;
+	struct dso *dso;
+
+	down_write(&dsos->lock);
 
-	list_for_each_entry(pos, head, node) {
-		ret += dso__fprintf(pos, fp);
+	dso = __dsos__find_id(dsos, m->name, NULL, /*cmp_short=*/true, /*write_locked=*/true);
+	if (dso) {
+		up_write(&dsos->lock);
+		return dso;
 	}
+	/*
+	 * Failed to find the dso so create it. Change the name before adding it
+	 * to the array, to avoid unnecessary sorts and potential locking
+	 * issues.
+	 */
+	dso = dso__new_id(m->name, /*id=*/NULL);
+	if (!dso) {
+		up_write(&dsos->lock);
+		return NULL;
+	}
+	dso__set_basename(dso);
+	dso__set_module_info(dso, m, machine);
+	dso__set_long_name(dso,	strdup(filename), true);
+	dso__set_kernel(dso, DSO_SPACE__KERNEL);
+	__dsos__add(dsos, dso);
 
-	return ret;
+	up_write(&dsos->lock);
+	return dso;
+}
+
+static int dsos__find_kernel_dso_cb(struct dso *dso, void *data)
+{
+	struct dso **res = data;
+	/*
+	 * The cpumode passed to is_kernel_module is not the cpumode of *this*
+	 * event. If we insist on passing correct cpumode to is_kernel_module,
+	 * we should record the cpumode when we adding this dso to the linked
+	 * list.
+	 *
+	 * However we don't really need passing correct cpumode.  We know the
+	 * correct cpumode must be kernel mode (if not, we should not link it
+	 * onto kernel_dsos list).
+	 *
+	 * Therefore, we pass PERF_RECORD_MISC_CPUMODE_UNKNOWN.
+	 * is_kernel_module() treats it as a kernel cpumode.
+	 */
+	if (!dso__kernel(dso) ||
+	    is_kernel_module(dso__long_name(dso), PERF_RECORD_MISC_CPUMODE_UNKNOWN))
+		return 0;
+
+	*res = dso__get(dso);
+	return 1;
+}
+
+struct dso *dsos__find_kernel_dso(struct dsos *dsos)
+{
+	struct dso *res = NULL;
+
+	dsos__for_each_dso(dsos, dsos__find_kernel_dso_cb, &res);
+	return res;
+}
+
+int dsos__for_each_dso(struct dsos *dsos, int (*cb)(struct dso *dso, void *data), void *data)
+{
+	int err;
+
+	down_read(&dsos->lock);
+	err = __dsos__for_each_dso(dsos, cb, data);
+	up_read(&dsos->lock);
+	return err;
 }