[PATCH v6 09/18] gendwarfksyms: Limit structure expansion

[Sami Tolvanen <samitolvanen@google.com>]

Expand each structure type only once per exported symbol. This
is necessary to support self-referential structures, which would
otherwise result in infinite recursion, and it's sufficient for
catching ABI changes.

Types defined in .c files are opaque to external users and thus
cannot affect the ABI. Consider type definitions in .c files to
be declarations to prevent opaque types from changing symbol
versions.

Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
---
 scripts/gendwarfksyms/Makefile        |   1 +
 scripts/gendwarfksyms/cache.c         |  51 +++++++++++
 scripts/gendwarfksyms/dwarf.c         | 125 ++++++++++++++++++++++++--
 scripts/gendwarfksyms/gendwarfksyms.h |  46 ++++++++++
 4 files changed, 215 insertions(+), 8 deletions(-)
 create mode 100644 scripts/gendwarfksyms/cache.c

diff --git a/scripts/gendwarfksyms/Makefile b/scripts/gendwarfksyms/Makefile
index c0d4ce50fc27..c06145d84df8 100644
--- a/scripts/gendwarfksyms/Makefile
+++ b/scripts/gendwarfksyms/Makefile
@@ -2,6 +2,7 @@
 hostprogs-always-y += gendwarfksyms
 
 gendwarfksyms-objs += gendwarfksyms.o
+gendwarfksyms-objs += cache.o
 gendwarfksyms-objs += die.o
 gendwarfksyms-objs += dwarf.o
 gendwarfksyms-objs += symbols.o
diff --git a/scripts/gendwarfksyms/cache.c b/scripts/gendwarfksyms/cache.c
new file mode 100644
index 000000000000..c9c19b86a686
--- /dev/null
+++ b/scripts/gendwarfksyms/cache.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Google LLC
+ */
+
+#include "gendwarfksyms.h"
+
+struct cache_item {
+	unsigned long key;
+	int value;
+	struct hlist_node hash;
+};
+
+void cache_set(struct cache *cache, unsigned long key, int value)
+{
+	struct cache_item *ci;
+
+	ci = xmalloc(sizeof(struct cache_item));
+	ci->key = key;
+	ci->value = value;
+	hash_add(cache->cache, &ci->hash, hash_32(key));
+}
+
+int cache_get(struct cache *cache, unsigned long key)
+{
+	struct cache_item *ci;
+
+	hash_for_each_possible(cache->cache, ci, hash, hash_32(key)) {
+		if (ci->key == key)
+			return ci->value;
+	}
+
+	return -1;
+}
+
+void cache_init(struct cache *cache)
+{
+	hash_init(cache->cache);
+}
+
+void cache_free(struct cache *cache)
+{
+	struct hlist_node *tmp;
+	struct cache_item *ci;
+
+	hash_for_each_safe(cache->cache, ci, tmp, hash) {
+		free(ci);
+	}
+
+	hash_init(cache->cache);
+}
diff --git a/scripts/gendwarfksyms/dwarf.c b/scripts/gendwarfksyms/dwarf.c
index 98191ca7cef0..3ea7583e6c3f 100644
--- a/scripts/gendwarfksyms/dwarf.c
+++ b/scripts/gendwarfksyms/dwarf.c
@@ -26,6 +26,7 @@ static void process_linebreak(struct die *cache, int n)
 		       !dwarf_form##attr(&da, value);                  \
 	}
 
+DEFINE_GET_ATTR(flag, bool)
 DEFINE_GET_ATTR(udata, Dwarf_Word)
 
 static bool get_ref_die_attr(Dwarf_Die *die, unsigned int id, Dwarf_Die *value)
@@ -79,6 +80,55 @@ static bool match_export_symbol(struct state *state, Dwarf_Die *die)
 	return !!state->sym;
 }
 
+/* DW_AT_decl_file -> struct srcfile */
+static struct cache srcfile_cache;
+
+static bool is_definition_private(Dwarf_Die *die)
+{
+	Dwarf_Word filenum;
+	Dwarf_Files *files;
+	Dwarf_Die cudie;
+	const char *s;
+	int res;
+
+	/*
+	 * Definitions in .c files cannot change the public ABI,
+	 * so consider them private.
+	 */
+	if (!get_udata_attr(die, DW_AT_decl_file, &filenum))
+		return false;
+
+	res = cache_get(&srcfile_cache, filenum);
+	if (res >= 0)
+		return !!res;
+
+	if (!dwarf_cu_die(die->cu, &cudie, NULL, NULL, NULL, NULL, NULL, NULL))
+		error("dwarf_cu_die failed: '%s'", dwarf_errmsg(-1));
+
+	if (dwarf_getsrcfiles(&cudie, &files, NULL))
+		error("dwarf_getsrcfiles failed: '%s'", dwarf_errmsg(-1));
+
+	s = dwarf_filesrc(files, filenum, NULL, NULL);
+	if (!s)
+		error("dwarf_filesrc failed: '%s'", dwarf_errmsg(-1));
+
+	s = strrchr(s, '.');
+	res = s && !strcmp(s, ".c");
+	cache_set(&srcfile_cache, filenum, res);
+
+	return !!res;
+}
+
+static bool is_declaration(Dwarf_Die *die)
+{
+	bool value;
+
+	if (get_flag_attr(die, DW_AT_declaration, &value) && value)
+		return true;
+
+	return is_definition_private(die);
+}
+
 /*
  * Type string processing
  */
@@ -455,19 +505,27 @@ static void __process_structure_type(struct state *state, struct die *cache,
 				     die_callback_t process_func,
 				     die_match_callback_t match_func)
 {
+	bool is_decl;
+
 	process(cache, type);
 	process_fqn(cache, die);
 	process(cache, " {");
 	process_linebreak(cache, 1);
 
-	check(process_die_container(state, cache, die, process_func,
-				    match_func));
+	is_decl = is_declaration(die);
+
+	if (!is_decl && state->expand.expand) {
+		check(process_die_container(state, cache, die, process_func,
+					    match_func));
+	}
 
 	process_linebreak(cache, -1);
 	process(cache, "}");
 
-	process_byte_size_attr(cache, die);
-	process_alignment_attr(cache, die);
+	if (!is_decl && state->expand.expand) {
+		process_byte_size_attr(cache, die);
+		process_alignment_attr(cache, die);
+	}
 }
 
 #define DEFINE_PROCESS_STRUCTURE_TYPE(structure)                        \
@@ -552,6 +610,30 @@ static void process_cached(struct state *state, struct die *cache,
 	}
 }
 
+static void state_init(struct state *state)
+{
+	state->expand.expand = true;
+	cache_init(&state->expansion_cache);
+}
+
+static void expansion_state_restore(struct expansion_state *state,
+				    struct expansion_state *saved)
+{
+	state->expand = saved->expand;
+}
+
+static void expansion_state_save(struct expansion_state *state,
+				 struct expansion_state *saved)
+{
+	expansion_state_restore(saved, state);
+}
+
+static bool is_expanded_type(int tag)
+{
+	return tag == DW_TAG_class_type || tag == DW_TAG_structure_type ||
+	       tag == DW_TAG_union_type || tag == DW_TAG_enumeration_type;
+}
+
 #define PROCESS_TYPE(type)                                \
 	case DW_TAG_##type##_type:                        \
 		process_##type##_type(state, cache, die); \
@@ -559,18 +641,39 @@ static void process_cached(struct state *state, struct die *cache,
 
 static int process_type(struct state *state, struct die *parent, Dwarf_Die *die)
 {
+	enum die_state want_state = DIE_COMPLETE;
 	struct die *cache;
+	struct expansion_state saved;
 	int tag = dwarf_tag(die);
 
+	expansion_state_save(&state->expand, &saved);
+
 	/*
-	 * If we have the DIE already cached, use it instead of walking
+	 * Structures and enumeration types are expanded only once per
+	 * exported symbol. This is sufficient for detecting ABI changes
+	 * within the structure.
+	 */
+	if (is_expanded_type(tag)) {
+		if (cache_was_expanded(&state->expansion_cache, die->addr))
+			state->expand.expand = false;
+
+		if (state->expand.expand)
+			cache_mark_expanded(&state->expansion_cache, die->addr);
+		else
+			want_state = DIE_UNEXPANDED;
+	}
+
+	/*
+	 * If we have want_state already cached, use it instead of walking
 	 * through DWARF.
 	 */
-	cache = die_map_get(die, DIE_COMPLETE);
+	cache = die_map_get(die, want_state);
 
-	if (cache->state == DIE_COMPLETE) {
+	if (cache->state == want_state) {
 		process_cached(state, cache, die);
 		die_map_add_die(parent, cache);
+
+		expansion_state_restore(&state->expand, &saved);
 		return 0;
 	}
 
@@ -611,9 +714,10 @@ static int process_type(struct state *state, struct die *parent, Dwarf_Die *die)
 
 	/* Update cache state and append to the parent (if any) */
 	cache->tag = tag;
-	cache->state = DIE_COMPLETE;
+	cache->state = want_state;
 	die_map_add_die(parent, cache);
 
+	expansion_state_restore(&state->expand, &saved);
 	return 0;
 }
 
@@ -675,11 +779,14 @@ static int process_exported_symbols(struct state *unused, struct die *cache,
 		if (!match_export_symbol(&state, die))
 			return 0;
 
+		state_init(&state);
+
 		if (tag == DW_TAG_subprogram)
 			process_subprogram(&state, &state.die);
 		else
 			process_variable(&state, &state.die);
 
+		cache_free(&state.expansion_cache);
 		return 0;
 	}
 	default:
@@ -691,4 +798,6 @@ void process_cu(Dwarf_Die *cudie)
 {
 	check(process_die_container(NULL, NULL, cudie, process_exported_symbols,
 				    match_all));
+
+	cache_free(&srcfile_cache);
 }
diff --git a/scripts/gendwarfksyms/gendwarfksyms.h b/scripts/gendwarfksyms/gendwarfksyms.h
index 2646e11595ab..7b29d8f07aa0 100644
--- a/scripts/gendwarfksyms/gendwarfksyms.h
+++ b/scripts/gendwarfksyms/gendwarfksyms.h
@@ -107,6 +107,7 @@ void symbol_free(void);
 
 enum die_state {
 	DIE_INCOMPLETE,
+	DIE_UNEXPANDED,
 	DIE_COMPLETE,
 	DIE_LAST = DIE_COMPLETE
 };
@@ -136,6 +137,7 @@ static inline const char *die_state_name(enum die_state state)
 {
 	switch (state) {
 	CASE_CONST_TO_STR(DIE_INCOMPLETE)
+	CASE_CONST_TO_STR(DIE_UNEXPANDED)
 	CASE_CONST_TO_STR(DIE_COMPLETE)
 	}
 
@@ -158,16 +160,60 @@ void die_map_add_linebreak(struct die *pd, int linebreak);
 void die_map_add_die(struct die *pd, struct die *child);
 void die_map_free(void);
 
+/*
+ * cache.c
+ */
+
+#define CACHE_HASH_BITS 11
+
+/* A cache for addresses we've already seen. */
+struct cache {
+	HASHTABLE_DECLARE(cache, 1 << CACHE_HASH_BITS);
+};
+
+void cache_set(struct cache *cache, unsigned long key, int value);
+int cache_get(struct cache *cache, unsigned long key);
+void cache_init(struct cache *cache);
+void cache_free(struct cache *cache);
+
+static inline void __cache_mark_expanded(struct cache *cache, uintptr_t addr)
+{
+	cache_set(cache, addr, 1);
+}
+
+static inline bool __cache_was_expanded(struct cache *cache, uintptr_t addr)
+{
+	return cache_get(cache, addr) == 1;
+}
+
+static inline void cache_mark_expanded(struct cache *cache, void *addr)
+{
+	__cache_mark_expanded(cache, (uintptr_t)addr);
+}
+
+static inline bool cache_was_expanded(struct cache *cache, void *addr)
+{
+	return __cache_was_expanded(cache, (uintptr_t)addr);
+}
+
 /*
  * dwarf.c
  */
 
+struct expansion_state {
+	bool expand;
+};
+
 struct state {
 	struct symbol *sym;
 	Dwarf_Die die;
 
 	/* List expansion */
 	bool first_list_item;
+
+	/* Structure expansion */
+	struct expansion_state expand;
+	struct cache expansion_cache;
 };
 
 typedef int (*die_callback_t)(struct state *state, struct die *cache,
-- 
2.47.0.371.ga323438b13-goog