Resguardo inicial

linux-7.2.3/scripts/gendwarfksyms/.gitignore

@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+/gendwarfksyms

linux-7.2.3/scripts/gendwarfksyms/Makefile

@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0
+hostprogs-always-y += gendwarfksyms
+
+gendwarfksyms-objs += gendwarfksyms.o
+gendwarfksyms-objs += cache.o
+gendwarfksyms-objs += die.o
+gendwarfksyms-objs += dwarf.o
+gendwarfksyms-objs += kabi.o
+gendwarfksyms-objs += symbols.o
+gendwarfksyms-objs += types.o
+
+HOSTLDLIBS_gendwarfksyms := -ldw -lelf -lz

linux-7.2.3/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(*ci));
+	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);
+}

linux-7.2.3/scripts/gendwarfksyms/die.c

@@ -0,0 +1,166 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Google LLC
+ */
+
+#include <string.h>
+#include "gendwarfksyms.h"
+
+#define DIE_HASH_BITS 16
+
+/* {die->addr, state} -> struct die * */
+static HASHTABLE_DEFINE(die_map, 1 << DIE_HASH_BITS);
+
+static unsigned int map_hits;
+static unsigned int map_misses;
+
+static inline unsigned int die_hash(uintptr_t addr, enum die_state state)
+{
+	return hash_32(addr_hash(addr) ^ (unsigned int)state);
+}
+
+static void init_die(struct die *cd)
+{
+	cd->state = DIE_INCOMPLETE;
+	cd->mapped = false;
+	cd->fqn = NULL;
+	cd->tag = -1;
+	cd->addr = 0;
+	INIT_LIST_HEAD(&cd->fragments);
+}
+
+static struct die *create_die(Dwarf_Die *die, enum die_state state)
+{
+	struct die *cd;
+
+	cd = xmalloc(sizeof(*cd));
+	init_die(cd);
+	cd->addr = (uintptr_t)die->addr;
+
+	hash_add(die_map, &cd->hash, die_hash(cd->addr, state));
+	return cd;
+}
+
+int __die_map_get(uintptr_t addr, enum die_state state, struct die **res)
+{
+	struct die *cd;
+
+	hash_for_each_possible(die_map, cd, hash, die_hash(addr, state)) {
+		if (cd->addr == addr && cd->state == state) {
+			*res = cd;
+			return 0;
+		}
+	}
+
+	return -1;
+}
+
+struct die *die_map_get(Dwarf_Die *die, enum die_state state)
+{
+	struct die *cd;
+
+	if (__die_map_get((uintptr_t)die->addr, state, &cd) == 0) {
+		map_hits++;
+		return cd;
+	}
+
+	map_misses++;
+	return create_die(die, state);
+}
+
+static void reset_die(struct die *cd)
+{
+	struct die_fragment *tmp;
+	struct die_fragment *df;
+
+	list_for_each_entry_safe(df, tmp, &cd->fragments, list) {
+		if (df->type == FRAGMENT_STRING)
+			free(df->data.str);
+		free(df);
+	}
+
+	if (cd->fqn && *cd->fqn)
+		free(cd->fqn);
+	init_die(cd);
+}
+
+void die_map_for_each(die_map_callback_t func, void *arg)
+{
+	struct hlist_node *tmp;
+	struct die *cd;
+
+	hash_for_each_safe(die_map, cd, tmp, hash) {
+		func(cd, arg);
+	}
+}
+
+void die_map_free(void)
+{
+	struct hlist_node *tmp;
+	unsigned int stats[DIE_LAST + 1];
+	struct die *cd;
+	int i;
+
+	memset(stats, 0, sizeof(stats));
+
+	hash_for_each_safe(die_map, cd, tmp, hash) {
+		stats[cd->state]++;
+		reset_die(cd);
+		free(cd);
+	}
+	hash_init(die_map);
+
+	if (map_hits + map_misses > 0)
+		debug("hits %u, misses %u (hit rate %.02f%%)", map_hits,
+		      map_misses,
+		      (100.0f * map_hits) / (map_hits + map_misses));
+
+	for (i = 0; i <= DIE_LAST; i++)
+		debug("%s: %u entries", die_state_name(i), stats[i]);
+}
+
+static struct die_fragment *append_item(struct die *cd)
+{
+	struct die_fragment *df;
+
+	df = xmalloc(sizeof(*df));
+	df->type = FRAGMENT_EMPTY;
+	list_add_tail(&df->list, &cd->fragments);
+	return df;
+}
+
+void die_map_add_string(struct die *cd, const char *str)
+{
+	struct die_fragment *df;
+
+	if (!cd)
+		return;
+
+	df = append_item(cd);
+	df->data.str = xstrdup(str);
+	df->type = FRAGMENT_STRING;
+}
+
+void die_map_add_linebreak(struct die *cd, int linebreak)
+{
+	struct die_fragment *df;
+
+	if (!cd)
+		return;
+
+	df = append_item(cd);
+	df->data.linebreak = linebreak;
+	df->type = FRAGMENT_LINEBREAK;
+}
+
+void die_map_add_die(struct die *cd, struct die *child)
+{
+	struct die_fragment *df;
+
+	if (!cd)
+		return;
+
+	df = append_item(cd);
+	df->data.addr = child->addr;
+	df->type = FRAGMENT_DIE;
+}

linux-7.2.3/scripts/gendwarfksyms/examples/kabi.h

@@ -0,0 +1,174 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2024 Google LLC
+ *
+ * Example macros for maintaining kABI stability.
+ *
+ * This file is based on android_kabi.h, which has the following notice:
+ *
+ * Heavily influenced by rh_kabi.h which came from the RHEL/CENTOS kernel
+ * and was:
+ *	Copyright (c) 2014 Don Zickus
+ *	Copyright (c) 2015-2018 Jiri Benc
+ *	Copyright (c) 2015 Sabrina Dubroca, Hannes Frederic Sowa
+ *	Copyright (c) 2016-2018 Prarit Bhargava
+ *	Copyright (c) 2017 Paolo Abeni, Larry Woodman
+ */
+
+#ifndef __KABI_H__
+#define __KABI_H__
+
+/* Kernel macros for userspace testing. */
+#ifndef __aligned
+#define __aligned(x) __attribute__((__aligned__(x)))
+#endif
+#ifndef __used
+#define __used __attribute__((__used__))
+#endif
+#ifndef __section
+#define __section(section) __attribute__((__section__(section)))
+#endif
+#ifndef __PASTE
+#define ___PASTE(a, b) a##b
+#define __PASTE(a, b) ___PASTE(a, b)
+#endif
+#ifndef __stringify
+#define __stringify_1(x...) #x
+#define __stringify(x...) __stringify_1(x)
+#endif
+
+#define ___KABI_RULE(hint, target, value)                            \
+	static const char __PASTE(__gendwarfksyms_rule_,             \
+				  __COUNTER__)[] __used __aligned(1) \
+		__section(".discard.gendwarfksyms.kabi_rules") =     \
+			"1\0" #hint "\0" target "\0" value
+
+#define __KABI_RULE(hint, target, value) \
+	___KABI_RULE(hint, #target, #value)
+
+#define __KABI_NORMAL_SIZE_ALIGN(_orig, _new)                                             \
+	union {                                                                           \
+		_Static_assert(                                                           \
+			sizeof(struct { _new; }) <= sizeof(struct { _orig; }),            \
+			__FILE__ ":" __stringify(__LINE__) ": " __stringify(              \
+				_new) " is larger than " __stringify(_orig));             \
+		_Static_assert(                                                           \
+			__alignof__(struct { _new; }) <=                                  \
+				__alignof__(struct { _orig; }),                           \
+			__FILE__ ":" __stringify(__LINE__) ": " __stringify(              \
+				_orig) " is not aligned the same as " __stringify(_new)); \
+	}
+
+#define __KABI_REPLACE(_orig, _new)                    \
+	union {                                        \
+		_new;                                  \
+		struct {                               \
+			_orig;                         \
+		};                                     \
+		__KABI_NORMAL_SIZE_ALIGN(_orig, _new); \
+	}
+
+/*
+ * KABI_DECLONLY(fqn)
+ *   Treat the struct/union/enum fqn as a declaration, i.e. even if
+ *   a definition is available, don't expand the contents.
+ */
+#define KABI_DECLONLY(fqn) __KABI_RULE(declonly, fqn, )
+
+/*
+ * KABI_ENUMERATOR_IGNORE(fqn, field)
+ *   When expanding enum fqn, skip the provided field. This makes it
+ *   possible to hide added enum fields from versioning.
+ */
+#define KABI_ENUMERATOR_IGNORE(fqn, field) \
+	__KABI_RULE(enumerator_ignore, fqn field, )
+
+/*
+ * KABI_ENUMERATOR_VALUE(fqn, field, value)
+ *   When expanding enum fqn, use the provided value for the
+ *   specified field. This makes it possible to override enumerator
+ *   values when calculating versions.
+ */
+#define KABI_ENUMERATOR_VALUE(fqn, field, value) \
+	__KABI_RULE(enumerator_value, fqn field, value)
+
+/*
+ * KABI_BYTE_SIZE(fqn, value)
+ *   Set the byte_size attribute for the struct/union/enum fqn to
+ *   value bytes.
+ */
+#define KABI_BYTE_SIZE(fqn, value) __KABI_RULE(byte_size, fqn, value)
+
+/*
+ * KABI_TYPE_STRING(type, str)
+ *   For the given type, override the type string used in symtypes
+ *   output and version calculation with str.
+ */
+#define KABI_TYPE_STRING(type, str) ___KABI_RULE(type_string, type, str)
+
+/*
+ * KABI_RESERVE
+ *   Reserve some "padding" in a structure for use by LTS backports.
+ *   This is normally placed at the end of a structure.
+ *   number: the "number" of the padding variable in the structure.  Start with
+ *   1 and go up.
+ */
+#define KABI_RESERVE(n) unsigned long __kabi_reserved##n
+
+/*
+ * KABI_RESERVE_ARRAY
+ *   Same as _BACKPORT_RESERVE but allocates an array with the specified
+ *   size in bytes.
+ */
+#define KABI_RESERVE_ARRAY(n, s) \
+	unsigned char __aligned(8) __kabi_reserved##n[s]
+
+/*
+ * KABI_IGNORE
+ *   Add a new field that's ignored in versioning.
+ */
+#define KABI_IGNORE(n, _new)                     \
+	union {                                  \
+		_new;                            \
+		unsigned char __kabi_ignored##n; \
+	}
+
+/*
+ * KABI_REPLACE
+ *   Replace a field with a compatible new field.
+ */
+#define KABI_REPLACE(_oldtype, _oldname, _new) \
+	__KABI_REPLACE(_oldtype __kabi_renamed##_oldname, struct { _new; })
+
+/*
+ * KABI_USE(number, _new)
+ *   Use a previous padding entry that was defined with KABI_RESERVE
+ *   number: the previous "number" of the padding variable
+ *   _new: the variable to use now instead of the padding variable
+ */
+#define KABI_USE(number, _new) __KABI_REPLACE(KABI_RESERVE(number), _new)
+
+/*
+ * KABI_USE2(number, _new1, _new2)
+ *   Use a previous padding entry that was defined with KABI_RESERVE for
+ *   two new variables that fit into 64 bits.  This is good for when you do not
+ *   want to "burn" a 64bit padding variable for a smaller variable size if not
+ *   needed.
+ */
+#define KABI_USE2(number, _new1, _new2)        \
+	__KABI_REPLACE(                        \
+		KABI_RESERVE(number), struct { \
+			_new1;                 \
+			_new2;                 \
+		})
+/*
+ * KABI_USE_ARRAY(number, bytes, _new)
+ *   Use a previous padding entry that was defined with KABI_RESERVE_ARRAY
+ *   number: the previous "number" of the padding variable
+ *   bytes: the size in bytes reserved for the array
+ *   _new: the variable to use now instead of the padding variable
+ */
+#define KABI_USE_ARRAY(number, bytes, _new) \
+	__KABI_REPLACE(KABI_RESERVE_ARRAY(number, bytes), _new)
+
+#endif /* __KABI_H__ */

linux-7.2.3/scripts/gendwarfksyms/examples/kabi_ex.c

@@ -0,0 +1,37 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * kabi_ex.c
+ *
+ * Copyright (C) 2024 Google LLC
+ *
+ * Examples for kABI stability features with --stable. See kabi_ex.h
+ * for details.
+ */
+
+#include "kabi_ex.h"
+
+struct s e0;
+enum e e1;
+
+struct ex0a ex0a;
+struct ex0b ex0b;
+struct ex0c ex0c;
+
+struct ex1a ex1a;
+struct ex1b ex1b;
+struct ex1c ex1c;
+
+struct ex2a ex2a;
+struct ex2b ex2b;
+struct ex2c ex2c;
+
+struct ex3a ex3a;
+struct ex3b ex3b;
+struct ex3c ex3c;
+
+struct ex4a ex4a;
+
+struct ex5a ex5a;
+struct ex5b ex5b;
+
+int ex6a;

linux-7.2.3/scripts/gendwarfksyms/examples/kabi_ex.h

@@ -0,0 +1,360 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * kabi_ex.h
+ *
+ * Copyright (C) 2024 Google LLC
+ *
+ * Examples for kABI stability features with --stable.
+ */
+
+/*
+ * The comments below each example contain the expected gendwarfksyms
+ * output, which can be verified using LLVM's FileCheck tool:
+ *
+ * https://llvm.org/docs/CommandGuide/FileCheck.html
+ *
+ * Usage:
+ *
+ * $ gcc -g -c examples/kabi_ex.c -o examples/kabi_ex.o
+ *
+ * $ nm examples/kabi_ex.o | awk '{ print $NF }' | \
+ * 	./gendwarfksyms --stable --dump-dies \
+ * 		examples/kabi_ex.o 2>&1 >/dev/null | \
+ * 	FileCheck examples/kabi_ex.h --check-prefix=STABLE
+
+ * $ nm examples/kabi_ex.o | awk '{ print $NF }' | \
+ * 	./gendwarfksyms --stable --dump-versions \
+ * 		examples/kabi_ex.o 2>&1 >/dev/null | \
+ * 	sort | \
+ * 	FileCheck examples/kabi_ex.h --check-prefix=VERSIONS
+ */
+
+#ifndef __KABI_EX_H__
+#define __KABI_EX_H__
+
+#include "kabi.h"
+
+/*
+ * Example: kABI rules
+ */
+
+struct s {
+	int a;
+};
+
+KABI_DECLONLY(s);
+
+/*
+ * STABLE:      variable structure_type s {
+ * STABLE-NEXT: }
+ */
+
+enum e {
+	A,
+	B,
+	C,
+	D,
+};
+
+KABI_ENUMERATOR_IGNORE(e, B);
+KABI_ENUMERATOR_IGNORE(e, C);
+KABI_ENUMERATOR_VALUE(e, D, 123456789);
+
+/*
+ * STABLE:      variable enumeration_type e {
+ * STABLE-NEXT:   enumerator A = 0 ,
+ * STABLE-NEXT:   enumerator D = 123456789
+ * STABLE-NEXT: } byte_size(4)
+*/
+
+/*
+ * Example: Reserved fields
+ */
+struct ex0a {
+	int a;
+	KABI_RESERVE(0);
+	KABI_RESERVE(1);
+};
+
+/*
+ * STABLE:      variable structure_type ex0a {
+ * STABLE-NEXT:   member base_type int byte_size(4) encoding(5) a data_member_location(0) ,
+ * STABLE-NEXT:   member base_type [[ULONG:long unsigned int|unsigned long]] byte_size(8) encoding(7) data_member_location(8) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(16)
+ * STABLE-NEXT: } byte_size(24)
+ */
+
+struct ex0b {
+	int a;
+	KABI_RESERVE(0);
+	KABI_USE2(1, int b, int c);
+};
+
+/*
+ * STABLE:      variable structure_type ex0b {
+ * STABLE-NEXT:   member base_type int byte_size(4) encoding(5) a data_member_location(0) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(8) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(16)
+ * STABLE-NEXT: } byte_size(24)
+ */
+
+struct ex0c {
+	int a;
+	KABI_USE(0, void *p);
+	KABI_USE2(1, int b, int c);
+};
+
+/*
+ * STABLE:      variable structure_type ex0c {
+ * STABLE-NEXT:   member base_type int byte_size(4) encoding(5) a data_member_location(0) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(8) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) data_member_location(16)
+ * STABLE-NEXT: } byte_size(24)
+ */
+
+/*
+ * Example: A reserved array
+ */
+
+struct ex1a {
+	unsigned int a;
+	KABI_RESERVE_ARRAY(0, 64);
+};
+
+/*
+ * STABLE:      variable structure_type ex1a {
+ * STABLE-NEXT:   member base_type unsigned int byte_size(4) encoding(7) a data_member_location(0) ,
+ * STABLE-NEXT:   member array_type[64] {
+ * STABLE-NEXT:     base_type unsigned char byte_size(1) encoding(8)
+ * STABLE-NEXT:   } data_member_location(8)
+ * STABLE-NEXT: } byte_size(72)
+ */
+
+struct ex1b {
+	unsigned int a;
+	KABI_USE_ARRAY(
+		0, 64, struct {
+			void *p;
+			KABI_RESERVE_ARRAY(1, 56);
+		});
+};
+
+/*
+ * STABLE:      variable structure_type ex1b {
+ * STABLE-NEXT:   member base_type unsigned int byte_size(4) encoding(7) a data_member_location(0) ,
+ * STABLE-NEXT:   member array_type[64] {
+ * STABLE-NEXT:     base_type unsigned char byte_size(1) encoding(8)
+ * STABLE-NEXT:   } data_member_location(8)
+ * STABLE-NEXT: } byte_size(72)
+ */
+
+struct ex1c {
+	unsigned int a;
+	KABI_USE_ARRAY(0, 64, void *p[8]);
+};
+
+/*
+ * STABLE:      variable structure_type ex1c {
+ * STABLE-NEXT:   member base_type unsigned int byte_size(4) encoding(7) a data_member_location(0) ,
+ * STABLE-NEXT:   member array_type[64] {
+ * STABLE-NEXT:     base_type unsigned char byte_size(1) encoding(8)
+ * STABLE-NEXT:   } data_member_location(8)
+ * STABLE-NEXT: } byte_size(72)
+ */
+
+/*
+ * Example: An ignored field added to an alignment hole
+ */
+
+struct ex2a {
+	int a;
+	unsigned long b;
+	int c;
+	unsigned long d;
+};
+
+/*
+ * STABLE:      variable structure_type ex2a {
+ * STABLE-NEXT:   member base_type int byte_size(4) encoding(5) a data_member_location(0) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) b data_member_location(8)
+ * STABLE-NEXT:   member base_type int byte_size(4) encoding(5) c data_member_location(16) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) d data_member_location(24)
+ * STABLE-NEXT: } byte_size(32)
+ */
+
+struct ex2b {
+	int a;
+	KABI_IGNORE(0, unsigned int n);
+	unsigned long b;
+	int c;
+	unsigned long d;
+};
+
+_Static_assert(sizeof(struct ex2a) == sizeof(struct ex2b), "ex2a size doesn't match ex2b");
+
+/*
+ * STABLE:      variable structure_type ex2b {
+ * STABLE-NEXT:   member base_type int byte_size(4) encoding(5) a data_member_location(0) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) b data_member_location(8)
+ * STABLE-NEXT:   member base_type int byte_size(4) encoding(5) c data_member_location(16) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) d data_member_location(24)
+ * STABLE-NEXT: } byte_size(32)
+ */
+
+struct ex2c {
+	int a;
+	KABI_IGNORE(0, unsigned int n);
+	unsigned long b;
+	int c;
+	KABI_IGNORE(1, unsigned int m);
+	unsigned long d;
+};
+
+_Static_assert(sizeof(struct ex2a) == sizeof(struct ex2c), "ex2a size doesn't match ex2c");
+
+/*
+ * STABLE:      variable structure_type ex2c {
+ * STABLE-NEXT:   member base_type int byte_size(4) encoding(5) a data_member_location(0) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) b data_member_location(8)
+ * STABLE-NEXT:   member base_type int byte_size(4) encoding(5) c data_member_location(16) ,
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) d data_member_location(24)
+ * STABLE-NEXT: } byte_size(32)
+ */
+
+
+/*
+ * Example: A replaced field
+ */
+
+struct ex3a {
+	unsigned long a;
+	unsigned long unused;
+};
+
+/*
+ * STABLE:      variable structure_type ex3a {
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) a data_member_location(0)
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) unused data_member_location(8)
+ * STABLE-NEXT: } byte_size(16)
+ */
+
+struct ex3b {
+	unsigned long a;
+	KABI_REPLACE(unsigned long, unused, unsigned long renamed);
+};
+
+_Static_assert(sizeof(struct ex3a) == sizeof(struct ex3b), "ex3a size doesn't match ex3b");
+
+/*
+ * STABLE:      variable structure_type ex3b {
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) a data_member_location(0)
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) unused data_member_location(8)
+ * STABLE-NEXT: } byte_size(16)
+ */
+
+struct ex3c {
+	unsigned long a;
+	KABI_REPLACE(unsigned long, unused, long replaced);
+};
+
+_Static_assert(sizeof(struct ex3a) == sizeof(struct ex3c), "ex3a size doesn't match ex3c");
+
+/*
+ * STABLE:      variable structure_type ex3c {
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) a data_member_location(0)
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) unused data_member_location(8)
+ * STABLE-NEXT: } byte_size(16)
+ */
+
+/*
+ * Example: An ignored field added to an end of a partially opaque struct,
+ * while keeping the byte_size attribute unchanged.
+ */
+
+struct ex4a {
+	unsigned long a;
+	KABI_IGNORE(0, unsigned long b);
+};
+
+/*
+ * This may be safe if the structure allocation is managed by the core kernel
+ * and the layout remains unchanged except for appended new members.
+ */
+KABI_BYTE_SIZE(ex4a, 8);
+
+/*
+ * STABLE:      variable structure_type ex4a {
+ * STABLE-NEXT:   member base_type [[ULONG]] byte_size(8) encoding(7) a data_member_location(0)
+ * STABLE-NEXT: } byte_size(8)
+ */
+
+/*
+ * Example: A type string override.
+ */
+
+struct ex5a {
+	unsigned long a;
+};
+
+/*
+ * This may be safe if the structure is fully opaque to modules, even though
+ * its definition has inadvertently become part of the ABI.
+ */
+KABI_TYPE_STRING(
+	"s#ex5a",
+	"structure_type ex5a { member pointer_type { s#ex4a } byte_size(8) p data_member_location(0) } byte_size(8)");
+
+/*
+ * Make sure the fully expanded type string includes ex4a.
+ *
+ * VERSIONS:      ex5a variable structure_type ex5a {
+ * VERSIONS-SAME:   member pointer_type {
+ * VERSIONS-SAME:     structure_type ex4a {
+ * VERSIONS-SAME:       member base_type [[ULONG:long unsigned int|unsigned long]] byte_size(8) encoding(7) a data_member_location(0)
+ * VERSIONS-SAME:     } byte_size(8)
+ * VERSIONS-SAME:   } byte_size(8) p data_member_location(0)
+ * VERSIONS-SAME: } byte_size(8)
+ */
+
+/*
+ * Example: A type string definition for a non-existent type.
+ */
+
+struct ex5b {
+	unsigned long a;
+};
+
+/* Replace the type string for struct ex5b */
+KABI_TYPE_STRING(
+	"s#ex5b",
+	"structure_type ex5b { member pointer_type { s#ex5c } byte_size(8) p data_member_location(0) } byte_size(8)");
+
+/* Define a type string for a non-existent struct ex5c */
+KABI_TYPE_STRING(
+	"s#ex5c",
+	"structure_type ex5c { member base_type int byte_size(4) encoding(5) n data_member_location(0) } byte_size(8)");
+
+/*
+ * Make sure the fully expanded type string includes the definition for ex5c.
+ *
+ * VERSIONS:      ex5b variable structure_type ex5b {
+ * VERSIONS-SAME:   member pointer_type {
+ * VERSIONS-SAME:     structure_type ex5c {
+ * VERSIONS-SAME:       member base_type int byte_size(4) encoding(5) n data_member_location(0)
+ * VERSIONS-SAME:     } byte_size(8)
+ * VERSIONS-SAME:   } byte_size(8) p data_member_location(0)
+ * VERSIONS-SAME: } byte_size(8)
+ */
+
+/*
+ * Example: A type string override for a symbol.
+ */
+
+KABI_TYPE_STRING("ex6a", "variable s#ex5c");
+
+/*
+ * VERSIONS:      ex6a variable structure_type ex5c {
+ * VERSIONS-SAME:   member base_type int byte_size(4) encoding(5) n data_member_location(0)
+ * VERSIONS-SAME: } byte_size(8)
+ */
+#endif /* __KABI_EX_H__ */

linux-7.2.3/scripts/gendwarfksyms/examples/symbolptr.c

@@ -0,0 +1,33 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Google LLC
+ *
+ * Example for symbol pointers. When compiled with Clang, gendwarfkyms
+ * uses a symbol pointer for `f`.
+ *
+ * $ clang -g -c examples/symbolptr.c -o examples/symbolptr.o
+ * $ echo -e "f\ng\np" | ./gendwarfksyms -d examples/symbolptr.o
+ */
+
+/* Kernel macros for userspace testing. */
+#ifndef __used
+#define __used __attribute__((__used__))
+#endif
+#ifndef __section
+#define __section(section) __attribute__((__section__(section)))
+#endif
+
+#define __GENDWARFKSYMS_EXPORT(sym)				\
+	static typeof(sym) *__gendwarfksyms_ptr_##sym __used	\
+		__section(".discard.gendwarfksyms") = &sym;
+
+extern void f(unsigned int arg);
+void g(int *arg);
+void g(int *arg) {}
+
+struct s;
+extern struct s *p;
+
+__GENDWARFKSYMS_EXPORT(f);
+__GENDWARFKSYMS_EXPORT(g);
+__GENDWARFKSYMS_EXPORT(p);

linux-7.2.3/scripts/gendwarfksyms/gendwarfksyms.c

@@ -0,0 +1,188 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Google LLC
+ */
+
+#include <fcntl.h>
+#include <getopt.h>
+#include <errno.h>
+#include <stdarg.h>
+#include <string.h>
+#include <unistd.h>
+#include "gendwarfksyms.h"
+
+/*
+ * Options
+ */
+
+/* Print debugging information to stderr */
+int debug;
+/* Dump DIE contents */
+int dump_dies;
+/* Print debugging information about die_map changes */
+int dump_die_map;
+/* Print out type strings (i.e. type_map) */
+int dump_types;
+/* Print out expanded type strings used for symbol versions */
+int dump_versions;
+/* Support kABI stability features */
+int stable;
+/* Write a symtypes file */
+int symtypes;
+static const char *symtypes_file;
+
+static void usage(void)
+{
+	fputs("Usage: gendwarfksyms [options] elf-object-file ... < symbol-list\n\n"
+	      "Options:\n"
+	      "  -d, --debug          Print debugging information\n"
+	      "      --dump-dies      Dump DWARF DIE contents\n"
+	      "      --dump-die-map   Print debugging information about die_map changes\n"
+	      "      --dump-types     Dump type strings\n"
+	      "      --dump-versions  Dump expanded type strings used for symbol versions\n"
+	      "  -s, --stable         Support kABI stability features\n"
+	      "  -T, --symtypes file  Write a symtypes file\n"
+	      "  -h, --help           Print this message\n"
+	      "\n",
+	      stderr);
+}
+
+static int process_module(Dwfl_Module *mod, void **userdata, const char *name,
+			  Dwarf_Addr base, void *arg)
+{
+	Dwarf_Addr dwbias;
+	Dwarf_Die cudie;
+	Dwarf_CU *cu = NULL;
+	Dwarf *dbg;
+	FILE *symfile = arg;
+	int res;
+
+	debug("%s", name);
+	dbg = dwfl_module_getdwarf(mod, &dwbias);
+
+	/*
+	 * Look for exported symbols in each CU, follow the DIE tree, and add
+	 * the entries to die_map.
+	 */
+	do {
+		res = dwarf_get_units(dbg, cu, &cu, NULL, NULL, &cudie, NULL);
+		if (res < 0)
+			error("dwarf_get_units failed: no debugging information?");
+		if (res == 1)
+			break; /* No more units */
+
+		process_cu(&cudie);
+	} while (cu);
+
+	/*
+	 * Use die_map to expand type strings, write them to `symfile`, and
+	 * calculate symbol versions.
+	 */
+	generate_symtypes_and_versions(symfile);
+	die_map_free();
+
+	return DWARF_CB_OK;
+}
+
+static const Dwfl_Callbacks callbacks = {
+	.section_address = dwfl_offline_section_address,
+	.find_debuginfo = dwfl_standard_find_debuginfo,
+};
+
+int main(int argc, char **argv)
+{
+	FILE *symfile = NULL;
+	unsigned int n;
+	int opt;
+
+	static const struct option opts[] = {
+		{ "debug", 0, NULL, 'd' },
+		{ "dump-dies", 0, &dump_dies, 1 },
+		{ "dump-die-map", 0, &dump_die_map, 1 },
+		{ "dump-types", 0, &dump_types, 1 },
+		{ "dump-versions", 0, &dump_versions, 1 },
+		{ "stable", 0, NULL, 's' },
+		{ "symtypes", 1, NULL, 'T' },
+		{ "help", 0, NULL, 'h' },
+		{ 0, 0, NULL, 0 }
+	};
+
+	while ((opt = getopt_long(argc, argv, "dsT:h", opts, NULL)) != EOF) {
+		switch (opt) {
+		case 0:
+			break;
+		case 'd':
+			debug = 1;
+			break;
+		case 's':
+			stable = 1;
+			break;
+		case 'T':
+			symtypes = 1;
+			symtypes_file = optarg;
+			break;
+		case 'h':
+			usage();
+			return 0;
+		default:
+			usage();
+			return 1;
+		}
+	}
+
+	if (dump_die_map)
+		dump_dies = 1;
+
+	if (optind >= argc) {
+		usage();
+		error("no input files?");
+	}
+
+	if (!symbol_read_exports(stdin))
+		return 0;
+
+	if (symtypes_file) {
+		symfile = fopen(symtypes_file, "w");
+		if (!symfile)
+			error("fopen failed for '%s': %s", symtypes_file,
+			      strerror(errno));
+	}
+
+	for (n = optind; n < argc; n++) {
+		Dwfl *dwfl;
+		int fd;
+
+		fd = open(argv[n], O_RDONLY);
+		if (fd == -1)
+			error("open failed for '%s': %s", argv[n],
+			      strerror(errno));
+
+		symbol_read_symtab(fd);
+		kabi_read_rules(fd);
+
+		dwfl = dwfl_begin(&callbacks);
+		if (!dwfl)
+			error("dwfl_begin failed for '%s': %s", argv[n],
+			      dwarf_errmsg(-1));
+
+		if (!dwfl_report_offline(dwfl, argv[n], argv[n], fd))
+			error("dwfl_report_offline failed for '%s': %s",
+			      argv[n], dwarf_errmsg(-1));
+
+		dwfl_report_end(dwfl, NULL, NULL);
+
+		if (dwfl_getmodules(dwfl, &process_module, symfile, 0))
+			error("dwfl_getmodules failed for '%s'", argv[n]);
+
+		dwfl_end(dwfl);
+		kabi_free();
+	}
+
+	if (symfile)
+		check(fclose(symfile));
+
+	symbol_print_versions();
+	symbol_free();
+
+	return 0;
+}

linux-7.2.3/scripts/gendwarfksyms/gendwarfksyms.h

@@ -0,0 +1,290 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2024 Google LLC
+ */
+
+#include <dwarf.h>
+#include <elfutils/libdw.h>
+#include <elfutils/libdwfl.h>
+#include <stdlib.h>
+#include <stdio.h>
+
+#include <hash.h>
+#include <hashtable.h>
+#include <xalloc.h>
+
+#ifndef __GENDWARFKSYMS_H
+#define __GENDWARFKSYMS_H
+
+/*
+ * Options -- in gendwarfksyms.c
+ */
+extern int debug;
+extern int dump_dies;
+extern int dump_die_map;
+extern int dump_types;
+extern int dump_versions;
+extern int stable;
+extern int symtypes;
+
+/*
+ * Output helpers
+ */
+#define __PREFIX "gendwarfksyms: "
+#define __println(prefix, format, ...)                                \
+	fprintf(stderr, prefix __PREFIX "%s: " format "\n", __func__, \
+		##__VA_ARGS__)
+
+#define debug(format, ...)                                    \
+	do {                                                  \
+		if (debug)                                    \
+			__println("", format, ##__VA_ARGS__); \
+	} while (0)
+
+#define warn(format, ...) __println("warning: ", format, ##__VA_ARGS__)
+#define error(format, ...)                                   \
+	do {                                                 \
+		__println("error: ", format, ##__VA_ARGS__); \
+		exit(1);                                     \
+	} while (0)
+
+#define __die_debug(color, format, ...)                                 \
+	do {                                                            \
+		if (dump_dies && dump_die_map)                          \
+			fprintf(stderr,                                 \
+				"\033[" #color "m<" format ">\033[39m", \
+				__VA_ARGS__);                           \
+	} while (0)
+
+#define die_debug_r(format, ...) __die_debug(91, format, __VA_ARGS__)
+#define die_debug_g(format, ...) __die_debug(92, format, __VA_ARGS__)
+#define die_debug_b(format, ...) __die_debug(94, format, __VA_ARGS__)
+
+/*
+ * Error handling helpers
+ */
+#define __check(expr, test)                                     \
+	({                                                      \
+		int __res = expr;                               \
+		if (test)                                       \
+			error("`%s` failed: %d", #expr, __res); \
+		__res;                                          \
+	})
+
+/* Error == non-zero values */
+#define check(expr) __check(expr, __res)
+/* Error == negative values */
+#define checkp(expr) __check(expr, __res < 0)
+
+/* Consistent aliases (DW_TAG_<type>_type) for DWARF tags */
+#define DW_TAG_enumerator_type DW_TAG_enumerator
+#define DW_TAG_formal_parameter_type DW_TAG_formal_parameter
+#define DW_TAG_member_type DW_TAG_member
+#define DW_TAG_template_type_parameter_type DW_TAG_template_type_parameter
+#define DW_TAG_typedef_type DW_TAG_typedef
+#define DW_TAG_variant_part_type DW_TAG_variant_part
+#define DW_TAG_variant_type DW_TAG_variant
+
+/*
+ * symbols.c
+ */
+
+/* See symbols.c:is_symbol_ptr */
+#define SYMBOL_PTR_PREFIX "__gendwarfksyms_ptr_"
+#define SYMBOL_PTR_PREFIX_LEN (sizeof(SYMBOL_PTR_PREFIX) - 1)
+
+static inline unsigned int addr_hash(uintptr_t addr)
+{
+	return hash_ptr((const void *)addr);
+}
+
+enum symbol_state {
+	SYMBOL_UNPROCESSED,
+	SYMBOL_MAPPED,
+	SYMBOL_PROCESSED
+};
+
+struct symbol_addr {
+	uint32_t section;
+	Elf64_Addr address;
+};
+
+struct symbol {
+	const char *name;
+	struct symbol_addr addr;
+	struct hlist_node addr_hash;
+	struct hlist_node name_hash;
+	enum symbol_state state;
+	uintptr_t die_addr;
+	uintptr_t ptr_die_addr;
+	unsigned long crc;
+};
+
+typedef void (*symbol_callback_t)(struct symbol *, void *arg);
+
+bool is_symbol_ptr(const char *name);
+int symbol_read_exports(FILE *file);
+void symbol_read_symtab(int fd);
+struct symbol *symbol_get(const char *name);
+void symbol_set_ptr(struct symbol *sym, Dwarf_Die *ptr);
+void symbol_set_die(struct symbol *sym, Dwarf_Die *die);
+void symbol_set_crc(struct symbol *sym, unsigned long crc);
+void symbol_for_each(symbol_callback_t func, void *arg);
+void symbol_print_versions(void);
+void symbol_free(void);
+
+/*
+ * die.c
+ */
+
+enum die_state {
+	DIE_INCOMPLETE,
+	DIE_FQN,
+	DIE_UNEXPANDED,
+	DIE_COMPLETE,
+	DIE_SYMBOL,
+	DIE_LAST = DIE_SYMBOL
+};
+
+enum die_fragment_type {
+	FRAGMENT_EMPTY,
+	FRAGMENT_STRING,
+	FRAGMENT_LINEBREAK,
+	FRAGMENT_DIE
+};
+
+struct die_fragment {
+	enum die_fragment_type type;
+	union {
+		char *str;
+		int linebreak;
+		uintptr_t addr;
+	} data;
+	struct list_head list;
+};
+
+#define CASE_CONST_TO_STR(name) \
+	case name:              \
+		return #name;
+
+static inline const char *die_state_name(enum die_state state)
+{
+	switch (state) {
+	CASE_CONST_TO_STR(DIE_INCOMPLETE)
+	CASE_CONST_TO_STR(DIE_FQN)
+	CASE_CONST_TO_STR(DIE_UNEXPANDED)
+	CASE_CONST_TO_STR(DIE_COMPLETE)
+	CASE_CONST_TO_STR(DIE_SYMBOL)
+	}
+
+	error("unexpected die_state: %d", state);
+}
+
+struct die {
+	enum die_state state;
+	bool mapped;
+	char *fqn;
+	int tag;
+	uintptr_t addr;
+	struct list_head fragments;
+	struct hlist_node hash;
+};
+
+typedef void (*die_map_callback_t)(struct die *, void *arg);
+
+int __die_map_get(uintptr_t addr, enum die_state state, struct die **res);
+struct die *die_map_get(Dwarf_Die *die, enum die_state state);
+void die_map_add_string(struct die *pd, const char *str);
+void die_map_add_linebreak(struct die *pd, int linebreak);
+void die_map_for_each(die_map_callback_t func, void *arg);
+void die_map_add_die(struct die *pd, struct die *child);
+void die_map_free(void);
+
+/*
+ * cache.c
+ */
+
+#define CACHE_HASH_BITS 10
+
+/* 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, void *addr)
+{
+	cache_set(cache, (unsigned long)addr, 1);
+}
+
+static inline bool cache_was_expanded(struct cache *cache, void *addr)
+{
+	return cache_get(cache, (unsigned long)addr) == 1;
+}
+
+/*
+ * dwarf.c
+ */
+
+struct expansion_state {
+	bool expand;
+	const char *current_fqn;
+};
+
+struct kabi_state {
+	int members;
+	Dwarf_Die placeholder;
+	const char *orig_name;
+};
+
+struct state {
+	struct symbol *sym;
+	Dwarf_Die die;
+
+	/* List expansion */
+	bool first_list_item;
+
+	/* Structure expansion */
+	struct expansion_state expand;
+	struct cache expansion_cache;
+
+	/* Reserved or ignored members */
+	struct kabi_state kabi;
+};
+
+typedef int (*die_callback_t)(struct state *state, struct die *cache,
+			      Dwarf_Die *die);
+typedef bool (*die_match_callback_t)(Dwarf_Die *die);
+bool match_all(Dwarf_Die *die);
+
+int process_die_container(struct state *state, struct die *cache,
+			  Dwarf_Die *die, die_callback_t func,
+			  die_match_callback_t match);
+
+void process_cu(Dwarf_Die *cudie);
+
+/*
+ * types.c
+ */
+
+void generate_symtypes_and_versions(FILE *file);
+
+/*
+ * kabi.c
+ */
+
+bool kabi_get_byte_size(const char *fqn, unsigned long *value);
+bool kabi_is_enumerator_ignored(const char *fqn, const char *field);
+bool kabi_get_enumerator_value(const char *fqn, const char *field,
+			       unsigned long *value);
+bool kabi_is_declonly(const char *fqn);
+bool kabi_get_type_string(const char *type, const char **str);
+
+void kabi_read_rules(int fd);
+void kabi_free(void);
+
+#endif /* __GENDWARFKSYMS_H */

linux-7.2.3/scripts/gendwarfksyms/kabi.c

@@ -0,0 +1,373 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Google LLC
+ */
+
+#define _GNU_SOURCE
+#include <errno.h>
+#include <stdio.h>
+
+#include "gendwarfksyms.h"
+
+#define KABI_RULE_SECTION ".discard.gendwarfksyms.kabi_rules"
+#define KABI_RULE_VERSION "1"
+
+/*
+ * The rule section consists of four null-terminated strings per
+ * entry:
+ *
+ *   1. version
+ *      Entry format version. Must match KABI_RULE_VERSION.
+ *
+ *   2. type
+ *      Type of the kABI rule. Must be one of the tags defined below.
+ *
+ *   3. target
+ *      Rule-dependent target, typically the fully qualified name of
+ *      the target DIE.
+ *
+ *   4. value
+ *      Rule-dependent value.
+ */
+#define KABI_RULE_MIN_ENTRY_SIZE                                  \
+	(/* version\0 */ 2 + /* type\0 */ 2 + /* target\0" */ 1 + \
+	 /* value\0 */ 1)
+#define KABI_RULE_EMPTY_VALUE ""
+
+/*
+ * Rule: declonly
+ * - For the struct/enum/union in the target field, treat it as a
+ *   declaration only even if a definition is available.
+ */
+#define KABI_RULE_TAG_DECLONLY "declonly"
+
+/*
+ * Rule: enumerator_ignore
+ * - For the enum_field in the target field, ignore the enumerator.
+ */
+#define KABI_RULE_TAG_ENUMERATOR_IGNORE "enumerator_ignore"
+
+/*
+ * Rule: enumerator_value
+ * - For the fqn_field in the target field, set the value to the
+ *   unsigned integer in the value field.
+ */
+#define KABI_RULE_TAG_ENUMERATOR_VALUE "enumerator_value"
+
+/*
+ * Rule: byte_size
+ * - For the fqn_field in the target field, set the byte_size
+ *   attribute to the value in the value field.
+ */
+#define KABI_RULE_TAG_BYTE_SIZE "byte_size"
+
+/*
+ * Rule: type_string
+ * - For the type reference in the fqn field, use the type string
+ *   in the value field.
+ */
+#define KABI_RULE_TAG_TYPE_STRING "type_string"
+
+enum kabi_rule_type {
+	KABI_RULE_TYPE_UNKNOWN,
+	KABI_RULE_TYPE_DECLONLY,
+	KABI_RULE_TYPE_ENUMERATOR_IGNORE,
+	KABI_RULE_TYPE_ENUMERATOR_VALUE,
+	KABI_RULE_TYPE_BYTE_SIZE,
+	KABI_RULE_TYPE_TYPE_STRING,
+};
+
+#define RULE_HASH_BITS 7
+
+struct rule {
+	enum kabi_rule_type type;
+	const char *target;
+	const char *value;
+	struct hlist_node hash;
+};
+
+/* { type, target } -> struct rule */
+static HASHTABLE_DEFINE(rules, 1 << RULE_HASH_BITS);
+
+static inline unsigned int rule_values_hash(enum kabi_rule_type type,
+					    const char *target)
+{
+	return hash_32(type) ^ hash_str(target);
+}
+
+static inline unsigned int rule_hash(const struct rule *rule)
+{
+	return rule_values_hash(rule->type, rule->target);
+}
+
+static inline const char *get_rule_field(const char **pos, ssize_t *left)
+{
+	const char *start = *pos;
+	size_t len;
+
+	if (*left <= 0)
+		error("unexpected end of kABI rules");
+
+	len = strnlen(start, *left) + 1;
+	*pos += len;
+	*left -= len;
+
+	return start;
+}
+
+void kabi_read_rules(int fd)
+{
+	GElf_Shdr shdr_mem;
+	GElf_Shdr *shdr;
+	Elf_Data *rule_data = NULL;
+	Elf_Scn *scn;
+	Elf *elf;
+	size_t shstrndx;
+	const char *rule_str;
+	ssize_t left;
+	int i;
+
+	const struct {
+		enum kabi_rule_type type;
+		const char *tag;
+	} rule_types[] = {
+		{
+			.type = KABI_RULE_TYPE_DECLONLY,
+			.tag = KABI_RULE_TAG_DECLONLY,
+		},
+		{
+			.type = KABI_RULE_TYPE_ENUMERATOR_IGNORE,
+			.tag = KABI_RULE_TAG_ENUMERATOR_IGNORE,
+		},
+		{
+			.type = KABI_RULE_TYPE_ENUMERATOR_VALUE,
+			.tag = KABI_RULE_TAG_ENUMERATOR_VALUE,
+		},
+		{
+			.type = KABI_RULE_TYPE_BYTE_SIZE,
+			.tag = KABI_RULE_TAG_BYTE_SIZE,
+		},
+		{
+			.type = KABI_RULE_TYPE_TYPE_STRING,
+			.tag = KABI_RULE_TAG_TYPE_STRING,
+		},
+	};
+
+	if (!stable)
+		return;
+
+	if (elf_version(EV_CURRENT) != EV_CURRENT)
+		error("elf_version failed: %s", elf_errmsg(-1));
+
+	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
+	if (!elf)
+		error("elf_begin failed: %s", elf_errmsg(-1));
+
+	if (elf_getshdrstrndx(elf, &shstrndx) < 0)
+		error("elf_getshdrstrndx failed: %s", elf_errmsg(-1));
+
+	scn = elf_nextscn(elf, NULL);
+
+	while (scn) {
+		const char *sname;
+
+		shdr = gelf_getshdr(scn, &shdr_mem);
+		if (!shdr)
+			error("gelf_getshdr failed: %s", elf_errmsg(-1));
+
+		sname = elf_strptr(elf, shstrndx, shdr->sh_name);
+		if (!sname)
+			error("elf_strptr failed: %s", elf_errmsg(-1));
+
+		if (!strcmp(sname, KABI_RULE_SECTION)) {
+			rule_data = elf_getdata(scn, NULL);
+			if (!rule_data)
+				error("elf_getdata failed: %s", elf_errmsg(-1));
+			break;
+		}
+
+		scn = elf_nextscn(elf, scn);
+	}
+
+	if (!rule_data) {
+		debug("kABI rules not found");
+		check(elf_end(elf));
+		return;
+	}
+
+	rule_str = rule_data->d_buf;
+	left = shdr->sh_size;
+
+	if (left < KABI_RULE_MIN_ENTRY_SIZE)
+		error("kABI rule section too small: %zd bytes", left);
+
+	if (rule_str[left - 1] != '\0')
+		error("kABI rules are not null-terminated");
+
+	while (left > KABI_RULE_MIN_ENTRY_SIZE) {
+		enum kabi_rule_type type = KABI_RULE_TYPE_UNKNOWN;
+		const char *field;
+		struct rule *rule;
+
+		/* version */
+		field = get_rule_field(&rule_str, &left);
+
+		if (strcmp(field, KABI_RULE_VERSION))
+			error("unsupported kABI rule version: '%s'", field);
+
+		/* type */
+		field = get_rule_field(&rule_str, &left);
+
+		for (i = 0; i < ARRAY_SIZE(rule_types); i++) {
+			if (!strcmp(field, rule_types[i].tag)) {
+				type = rule_types[i].type;
+				break;
+			}
+		}
+
+		if (type == KABI_RULE_TYPE_UNKNOWN)
+			error("unsupported kABI rule type: '%s'", field);
+
+		rule = xmalloc(sizeof(*rule));
+
+		rule->type = type;
+		rule->target = xstrdup(get_rule_field(&rule_str, &left));
+		rule->value = xstrdup(get_rule_field(&rule_str, &left));
+
+		hash_add(rules, &rule->hash, rule_hash(rule));
+
+		debug("kABI rule: type: '%s', target: '%s', value: '%s'", field,
+		      rule->target, rule->value);
+	}
+
+	if (left > 0)
+		warn("unexpected data at the end of the kABI rules section");
+
+	check(elf_end(elf));
+}
+
+static char *get_enumerator_target(const char *fqn, const char *field)
+{
+	char *target = NULL;
+
+	if (asprintf(&target, "%s %s", fqn, field) < 0)
+		error("asprintf failed for '%s %s'", fqn, field);
+
+	return target;
+}
+
+static struct rule *find_rule(enum kabi_rule_type type, const char *target)
+{
+	struct rule *rule;
+
+	if (!stable)
+		return NULL;
+	if (!target || !*target)
+		return NULL;
+
+	hash_for_each_possible(rules, rule, hash,
+			       rule_values_hash(type, target)) {
+		if (rule->type == type && !strcmp(target, rule->target))
+			return rule;
+	}
+
+	return NULL;
+}
+
+static struct rule *find_enumerator_rule(enum kabi_rule_type type,
+					 const char *fqn, const char *field)
+{
+	struct rule *rule;
+	char *target;
+
+	if (!stable)
+		return NULL;
+	if (!fqn || !*fqn || !field || !*field)
+		return NULL;
+
+	target = get_enumerator_target(fqn, field);
+	rule = find_rule(type, target);
+
+	free(target);
+	return rule;
+}
+
+bool kabi_is_declonly(const char *fqn)
+{
+	return !!find_rule(KABI_RULE_TYPE_DECLONLY, fqn);
+}
+
+static unsigned long get_ulong_value(const char *value)
+{
+	unsigned long result = 0;
+	char *endptr = NULL;
+
+	errno = 0;
+	result = strtoul(value, &endptr, 10);
+
+	if (errno || *endptr)
+		error("invalid unsigned value '%s'", value);
+
+	return result;
+}
+
+bool kabi_is_enumerator_ignored(const char *fqn, const char *field)
+{
+	return !!find_enumerator_rule(KABI_RULE_TYPE_ENUMERATOR_IGNORE, fqn,
+				      field);
+}
+
+bool kabi_get_enumerator_value(const char *fqn, const char *field,
+			       unsigned long *value)
+{
+	struct rule *rule;
+
+	rule = find_enumerator_rule(KABI_RULE_TYPE_ENUMERATOR_VALUE, fqn,
+				    field);
+	if (rule) {
+		*value = get_ulong_value(rule->value);
+		return true;
+	}
+
+	return false;
+}
+
+bool kabi_get_byte_size(const char *fqn, unsigned long *value)
+{
+	struct rule *rule;
+
+	rule = find_rule(KABI_RULE_TYPE_BYTE_SIZE, fqn);
+	if (rule) {
+		*value = get_ulong_value(rule->value);
+		return true;
+	}
+
+	return false;
+}
+
+bool kabi_get_type_string(const char *type, const char **str)
+{
+	struct rule *rule;
+
+	rule = find_rule(KABI_RULE_TYPE_TYPE_STRING, type);
+	if (rule) {
+		*str = rule->value;
+		return true;
+	}
+
+	return false;
+}
+
+void kabi_free(void)
+{
+	struct hlist_node *tmp;
+	struct rule *rule;
+
+	hash_for_each_safe(rules, rule, tmp, hash) {
+		free((void *)rule->target);
+		free((void *)rule->value);
+		free(rule);
+	}
+
+	hash_init(rules);
+}

linux-7.2.3/scripts/gendwarfksyms/symbols.c

@@ -0,0 +1,344 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Google LLC
+ */
+
+#include <inttypes.h>
+#include "gendwarfksyms.h"
+
+#define SYMBOL_HASH_BITS 12
+
+/* struct symbol_addr -> struct symbol */
+static HASHTABLE_DEFINE(symbol_addrs, 1 << SYMBOL_HASH_BITS);
+/* name -> struct symbol */
+static HASHTABLE_DEFINE(symbol_names, 1 << SYMBOL_HASH_BITS);
+
+static inline unsigned int symbol_addr_hash(const struct symbol_addr *addr)
+{
+	return hash_32(addr->section ^ addr_hash(addr->address));
+}
+
+static unsigned int __for_each_addr(struct symbol *sym, symbol_callback_t func,
+				    void *data)
+{
+	struct hlist_node *tmp;
+	struct symbol *match = NULL;
+	unsigned int processed = 0;
+
+	hash_for_each_possible_safe(symbol_addrs, match, tmp, addr_hash,
+				    symbol_addr_hash(&sym->addr)) {
+		if (match == sym)
+			continue; /* Already processed */
+
+		if (match->addr.section == sym->addr.section &&
+		    match->addr.address == sym->addr.address) {
+			func(match, data);
+			++processed;
+		}
+	}
+
+	return processed;
+}
+
+/*
+ * For symbols without debugging information (e.g. symbols defined in other
+ * TUs), we also match __gendwarfksyms_ptr_<symbol_name> symbols, which the
+ * kernel uses to ensure type information is present in the TU that exports
+ * the symbol. A __gendwarfksyms_ptr pointer must have the same type as the
+ * exported symbol, e.g.:
+ *
+ *   typeof(symname) *__gendwarf_ptr_symname = &symname;
+ */
+bool is_symbol_ptr(const char *name)
+{
+	return name && !strncmp(name, SYMBOL_PTR_PREFIX, SYMBOL_PTR_PREFIX_LEN);
+}
+
+static unsigned int for_each(const char *name, symbol_callback_t func,
+			     void *data)
+{
+	struct hlist_node *tmp;
+	struct symbol *match;
+
+	if (!name || !*name)
+		return 0;
+	if (is_symbol_ptr(name))
+		name += SYMBOL_PTR_PREFIX_LEN;
+
+	hash_for_each_possible_safe(symbol_names, match, tmp, name_hash,
+				    hash_str(name)) {
+		if (strcmp(match->name, name))
+			continue;
+
+		/* Call func for the match, and all address matches */
+		if (func)
+			func(match, data);
+
+		if (match->addr.section != SHN_UNDEF)
+			return __for_each_addr(match, func, data) + 1;
+
+		return 1;
+	}
+
+	return 0;
+}
+
+static void set_crc(struct symbol *sym, void *data)
+{
+	unsigned long *crc = data;
+
+	if (sym->state == SYMBOL_PROCESSED && sym->crc != *crc)
+		warn("overriding version for symbol %s (crc %lx vs. %lx)",
+		     sym->name, sym->crc, *crc);
+
+	sym->state = SYMBOL_PROCESSED;
+	sym->crc = *crc;
+}
+
+void symbol_set_crc(struct symbol *sym, unsigned long crc)
+{
+	if (for_each(sym->name, set_crc, &crc) == 0)
+		error("no matching symbols: '%s'", sym->name);
+}
+
+static void set_ptr(struct symbol *sym, void *data)
+{
+	sym->ptr_die_addr = (uintptr_t)((Dwarf_Die *)data)->addr;
+}
+
+void symbol_set_ptr(struct symbol *sym, Dwarf_Die *ptr)
+{
+	if (for_each(sym->name, set_ptr, ptr) == 0)
+		error("no matching symbols: '%s'", sym->name);
+}
+
+static void set_die(struct symbol *sym, void *data)
+{
+	sym->die_addr = (uintptr_t)((Dwarf_Die *)data)->addr;
+	sym->state = SYMBOL_MAPPED;
+}
+
+void symbol_set_die(struct symbol *sym, Dwarf_Die *die)
+{
+	if (for_each(sym->name, set_die, die) == 0)
+		error("no matching symbols: '%s'", sym->name);
+}
+
+static bool is_exported(const char *name)
+{
+	return for_each(name, NULL, NULL) > 0;
+}
+
+int symbol_read_exports(FILE *file)
+{
+	struct symbol *sym;
+	char *line = NULL;
+	char *name = NULL;
+	size_t size = 0;
+	int nsym = 0;
+
+	while (getline(&line, &size, file) > 0) {
+		if (sscanf(line, "%ms\n", &name) != 1)
+			error("malformed input line: %s", line);
+
+		if (is_exported(name)) {
+			/* Ignore duplicates */
+			free(name);
+			continue;
+		}
+
+		sym = xcalloc(1, sizeof(*sym));
+		sym->name = name;
+		sym->addr.section = SHN_UNDEF;
+		sym->state = SYMBOL_UNPROCESSED;
+
+		hash_add(symbol_names, &sym->name_hash, hash_str(sym->name));
+		++nsym;
+
+		debug("%s", sym->name);
+	}
+
+	free(line);
+	debug("%d exported symbols", nsym);
+
+	return nsym;
+}
+
+static void get_symbol(struct symbol *sym, void *arg)
+{
+	struct symbol **res = arg;
+
+	if (sym->state == SYMBOL_UNPROCESSED)
+		*res = sym;
+}
+
+struct symbol *symbol_get(const char *name)
+{
+	struct symbol *sym = NULL;
+
+	for_each(name, get_symbol, &sym);
+	return sym;
+}
+
+void symbol_for_each(symbol_callback_t func, void *arg)
+{
+	struct hlist_node *tmp;
+	struct symbol *sym;
+
+	hash_for_each_safe(symbol_names, sym, tmp, name_hash) {
+		func(sym, arg);
+	}
+}
+
+typedef void (*elf_symbol_callback_t)(const char *name, GElf_Sym *sym,
+				      Elf32_Word xndx, void *arg);
+
+static void elf_for_each_global(int fd, elf_symbol_callback_t func, void *arg)
+{
+	size_t sym_size;
+	GElf_Shdr shdr_mem;
+	GElf_Shdr *shdr;
+	Elf_Data *xndx_data = NULL;
+	Elf_Scn *scn;
+	Elf *elf;
+
+	if (elf_version(EV_CURRENT) != EV_CURRENT)
+		error("elf_version failed: %s", elf_errmsg(-1));
+
+	elf = elf_begin(fd, ELF_C_READ_MMAP, NULL);
+	if (!elf)
+		error("elf_begin failed: %s", elf_errmsg(-1));
+
+	scn = elf_nextscn(elf, NULL);
+
+	while (scn) {
+		shdr = gelf_getshdr(scn, &shdr_mem);
+		if (!shdr)
+			error("gelf_getshdr failed: %s", elf_errmsg(-1));
+
+		if (shdr->sh_type == SHT_SYMTAB_SHNDX) {
+			xndx_data = elf_getdata(scn, NULL);
+			if (!xndx_data)
+				error("elf_getdata failed: %s", elf_errmsg(-1));
+			break;
+		}
+
+		scn = elf_nextscn(elf, scn);
+	}
+
+	sym_size = gelf_fsize(elf, ELF_T_SYM, 1, EV_CURRENT);
+	scn = elf_nextscn(elf, NULL);
+
+	while (scn) {
+		shdr = gelf_getshdr(scn, &shdr_mem);
+		if (!shdr)
+			error("gelf_getshdr failed: %s", elf_errmsg(-1));
+
+		if (shdr->sh_type == SHT_SYMTAB) {
+			unsigned int nsyms;
+			unsigned int n;
+			Elf_Data *data = elf_getdata(scn, NULL);
+
+			if (!data)
+				error("elf_getdata failed: %s", elf_errmsg(-1));
+
+			if (shdr->sh_entsize != sym_size)
+				error("expected sh_entsize (%" PRIu64 ") to be %zu",
+				      shdr->sh_entsize, sym_size);
+
+			nsyms = shdr->sh_size / shdr->sh_entsize;
+
+			for (n = 1; n < nsyms; ++n) {
+				const char *name = NULL;
+				Elf32_Word xndx = 0;
+				GElf_Sym sym_mem;
+				GElf_Sym *sym;
+
+				sym = gelf_getsymshndx(data, xndx_data, n,
+						       &sym_mem, &xndx);
+				if (!sym)
+					error("gelf_getsymshndx failed: %s",
+					      elf_errmsg(-1));
+
+				if (GELF_ST_BIND(sym->st_info) == STB_LOCAL)
+					continue;
+
+				if (sym->st_shndx != SHN_XINDEX)
+					xndx = sym->st_shndx;
+
+				name = elf_strptr(elf, shdr->sh_link,
+						  sym->st_name);
+				if (!name)
+					error("elf_strptr failed: %s",
+					      elf_errmsg(-1));
+
+				/* Skip empty symbol names */
+				if (*name)
+					func(name, sym, xndx, arg);
+			}
+		}
+
+		scn = elf_nextscn(elf, scn);
+	}
+
+	check(elf_end(elf));
+}
+
+static void set_symbol_addr(struct symbol *sym, void *arg)
+{
+	struct symbol_addr *addr = arg;
+
+	if (sym->addr.section == SHN_UNDEF) {
+		sym->addr = *addr;
+		hash_add(symbol_addrs, &sym->addr_hash,
+			 symbol_addr_hash(&sym->addr));
+
+		debug("%s -> { %u, %" PRIx64 " }", sym->name, sym->addr.section,
+		      sym->addr.address);
+	} else if (sym->addr.section != addr->section ||
+		   sym->addr.address != addr->address) {
+		warn("multiple addresses for symbol %s?", sym->name);
+	}
+}
+
+static void elf_set_symbol_addr(const char *name, GElf_Sym *sym,
+				Elf32_Word xndx, void *arg)
+{
+	struct symbol_addr addr = { .section = xndx, .address = sym->st_value };
+
+	/* Set addresses for exported symbols */
+	if (addr.section != SHN_UNDEF)
+		for_each(name, set_symbol_addr, &addr);
+}
+
+void symbol_read_symtab(int fd)
+{
+	elf_for_each_global(fd, elf_set_symbol_addr, NULL);
+}
+
+void symbol_print_versions(void)
+{
+	struct hlist_node *tmp;
+	struct symbol *sym;
+
+	hash_for_each_safe(symbol_names, sym, tmp, name_hash) {
+		if (sym->state != SYMBOL_PROCESSED)
+			warn("no information for symbol %s", sym->name);
+
+		printf("#SYMVER %s 0x%08lx\n", sym->name, sym->crc);
+	}
+}
+
+void symbol_free(void)
+{
+	struct hlist_node *tmp;
+	struct symbol *sym;
+
+	hash_for_each_safe(symbol_names, sym, tmp, name_hash) {
+		free((void *)sym->name);
+		free(sym);
+	}
+
+	hash_init(symbol_addrs);
+	hash_init(symbol_names);
+}

linux-7.2.3/scripts/gendwarfksyms/types.c

@@ -0,0 +1,589 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Google LLC
+ */
+
+#define _GNU_SOURCE
+#include <inttypes.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+#include <zlib.h>
+
+#include "gendwarfksyms.h"
+
+static struct cache expansion_cache;
+
+/*
+ * A simple linked list of shared or owned strings to avoid copying strings
+ * around when not necessary.
+ */
+struct type_list_entry {
+	const char *str;
+	void *owned;
+	struct list_head list;
+};
+
+static void type_list_free(struct list_head *list)
+{
+	struct type_list_entry *entry;
+	struct type_list_entry *tmp;
+
+	list_for_each_entry_safe(entry, tmp, list, list) {
+		if (entry->owned)
+			free(entry->owned);
+		free(entry);
+	}
+
+	INIT_LIST_HEAD(list);
+}
+
+static int type_list_append(struct list_head *list, const char *s, void *owned)
+{
+	struct type_list_entry *entry;
+
+	if (!s)
+		return 0;
+
+	entry = xmalloc(sizeof(*entry));
+	entry->str = s;
+	entry->owned = owned;
+	list_add_tail(&entry->list, list);
+
+	return strlen(entry->str);
+}
+
+static void type_list_write(struct list_head *list, FILE *file)
+{
+	struct type_list_entry *entry;
+
+	list_for_each_entry(entry, list, list) {
+		if (entry->str)
+			checkp(fputs(entry->str, file));
+	}
+}
+
+/*
+ * An expanded type string in symtypes format.
+ */
+struct type_expansion {
+	char *name;
+	size_t len;
+	struct list_head expanded;
+	struct hlist_node hash;
+};
+
+static void type_expansion_init(struct type_expansion *type)
+{
+	type->name = NULL;
+	type->len = 0;
+	INIT_LIST_HEAD(&type->expanded);
+}
+
+static inline void type_expansion_free(struct type_expansion *type)
+{
+	free(type->name);
+	type->name = NULL;
+	type->len = 0;
+	type_list_free(&type->expanded);
+}
+
+static void type_expansion_append(struct type_expansion *type, const char *s,
+				  void *owned)
+{
+	type->len += type_list_append(&type->expanded, s, owned);
+}
+
+/*
+ * type_map -- the longest expansions for each type.
+ *
+ * const char *name -> struct type_expansion *
+ */
+#define TYPE_HASH_BITS 12
+static HASHTABLE_DEFINE(type_map, 1 << TYPE_HASH_BITS);
+
+static int __type_map_get(const char *name, struct type_expansion **res)
+{
+	struct type_expansion *e;
+
+	hash_for_each_possible(type_map, e, hash, hash_str(name)) {
+		if (!strcmp(name, e->name)) {
+			*res = e;
+			return 0;
+		}
+	}
+
+	return -1;
+}
+
+static struct type_expansion *type_map_add(const char *name,
+					   struct type_expansion *type)
+{
+	struct type_expansion *e;
+
+	if (__type_map_get(name, &e)) {
+		e = xmalloc(sizeof(*e));
+		type_expansion_init(e);
+		e->name = xstrdup(name);
+
+		hash_add(type_map, &e->hash, hash_str(e->name));
+
+		if (dump_types)
+			debug("adding %s", e->name);
+	} else {
+		/* Use the longest available expansion */
+		if (type->len <= e->len)
+			return e;
+
+		type_list_free(&e->expanded);
+
+		if (dump_types)
+			debug("replacing %s", e->name);
+	}
+
+	/* Take ownership of type->expanded */
+	list_replace_init(&type->expanded, &e->expanded);
+	e->len = type->len;
+
+	if (dump_types) {
+		checkp(fputs(e->name, stderr));
+		checkp(fputs(" ", stderr));
+		type_list_write(&e->expanded, stderr);
+		checkp(fputs("\n", stderr));
+	}
+
+	return e;
+}
+
+static void type_parse(const char *name, const char *str,
+		       struct type_expansion *type);
+
+static int type_map_get(const char *name, struct type_expansion **res)
+{
+	struct type_expansion type;
+	const char *override;
+
+	if (!__type_map_get(name, res))
+		return 0;
+
+	/*
+	 * If die_map didn't contain a type, we might still have
+	 * a type_string kABI rule that defines it.
+	 */
+	if (stable && kabi_get_type_string(name, &override)) {
+		type_expansion_init(&type);
+		type_parse(name, override, &type);
+		*res = type_map_add(name, &type);
+		type_expansion_free(&type);
+		return 0;
+	}
+
+	return -1;
+}
+
+static int cmp_expansion_name(const void *p1, const void *p2)
+{
+	struct type_expansion *const *e1 = p1;
+	struct type_expansion *const *e2 = p2;
+
+	return strcmp((*e1)->name, (*e2)->name);
+}
+
+static void type_map_write(FILE *file)
+{
+	struct type_expansion *e;
+	struct hlist_node *tmp;
+	struct type_expansion **es;
+	size_t count = 0;
+	size_t i = 0;
+
+	if (!file)
+		return;
+
+	hash_for_each_safe(type_map, e, tmp, hash)
+		++count;
+	es = xmalloc(count * sizeof(*es));
+	hash_for_each_safe(type_map, e, tmp, hash)
+		es[i++] = e;
+
+	qsort(es, count, sizeof(*es), cmp_expansion_name);
+
+	for (i = 0; i < count; ++i) {
+		checkp(fputs(es[i]->name, file));
+		checkp(fputs(" ", file));
+		type_list_write(&es[i]->expanded, file);
+		checkp(fputs("\n", file));
+	}
+
+	free(es);
+}
+
+static void type_map_free(void)
+{
+	struct type_expansion *e;
+	struct hlist_node *tmp;
+
+	hash_for_each_safe(type_map, e, tmp, hash) {
+		type_expansion_free(e);
+		free(e);
+	}
+
+	hash_init(type_map);
+}
+
+/*
+ * CRC for a type, with an optional fully expanded type string for
+ * debugging.
+ */
+struct version {
+	struct type_expansion type;
+	unsigned long crc;
+};
+
+static void version_init(struct version *version)
+{
+	version->crc = crc32(0, NULL, 0);
+	type_expansion_init(&version->type);
+}
+
+static void version_free(struct version *version)
+{
+	type_expansion_free(&version->type);
+}
+
+static void version_add(struct version *version, const char *s)
+{
+	version->crc = crc32(version->crc, (void *)s, strlen(s));
+	if (dump_versions)
+		type_expansion_append(&version->type, s, NULL);
+}
+
+/*
+ * Type reference format: <prefix>#<name>, where prefix:
+ * 	s -> structure
+ * 	u -> union
+ * 	e -> enum
+ * 	t -> typedef
+ *
+ * Names with spaces are additionally wrapped in single quotes.
+ */
+static inline bool is_type_prefix(const char *s)
+{
+	return (s[0] == 's' || s[0] == 'u' || s[0] == 'e' || s[0] == 't') &&
+	       s[1] == '#';
+}
+
+static char get_type_prefix(int tag)
+{
+	switch (tag) {
+	case DW_TAG_class_type:
+	case DW_TAG_structure_type:
+		return 's';
+	case DW_TAG_union_type:
+		return 'u';
+	case DW_TAG_enumeration_type:
+		return 'e';
+	case DW_TAG_typedef_type:
+		return 't';
+	default:
+		return 0;
+	}
+}
+
+static char *get_type_name(struct die *cache)
+{
+	const char *quote;
+	char prefix;
+	char *name;
+
+	if (cache->state == DIE_INCOMPLETE) {
+		warn("found incomplete cache entry: %p", cache);
+		return NULL;
+	}
+	if (cache->state == DIE_SYMBOL || cache->state == DIE_FQN)
+		return NULL;
+	if (!cache->fqn || !*cache->fqn)
+		return NULL;
+
+	prefix = get_type_prefix(cache->tag);
+	if (!prefix)
+		return NULL;
+
+	/* Wrap names with spaces in single quotes */
+	quote = strstr(cache->fqn, " ") ? "'" : "";
+
+	/* <prefix>#<type_name>\0 */
+	if (asprintf(&name, "%c#%s%s%s", prefix, quote, cache->fqn, quote) < 0)
+		error("asprintf failed for '%s'", cache->fqn);
+
+	return name;
+}
+
+static void __calculate_version(struct version *version,
+				struct type_expansion *type)
+{
+	struct type_list_entry *entry;
+	struct type_expansion *e;
+
+	/* Calculate a CRC over an expanded type string */
+	list_for_each_entry(entry, &type->expanded, list) {
+		if (is_type_prefix(entry->str)) {
+			if (type_map_get(entry->str, &e))
+				error("unknown type reference to '%s' when expanding '%s'",
+				      entry->str, type->name);
+
+			/*
+			 * It's sufficient to expand each type reference just
+			 * once to detect changes.
+			 */
+			if (cache_was_expanded(&expansion_cache, e)) {
+				version_add(version, entry->str);
+			} else {
+				cache_mark_expanded(&expansion_cache, e);
+				__calculate_version(version, e);
+			}
+		} else {
+			version_add(version, entry->str);
+		}
+	}
+}
+
+static void calculate_version(struct version *version,
+			      struct type_expansion *type)
+{
+	version_init(version);
+	__calculate_version(version, type);
+	cache_free(&expansion_cache);
+}
+
+static void __type_expand(struct die *cache, struct type_expansion *type)
+{
+	struct die_fragment *df;
+	struct die *child;
+	char *name;
+
+	list_for_each_entry(df, &cache->fragments, list) {
+		switch (df->type) {
+		case FRAGMENT_STRING:
+			type_expansion_append(type, df->data.str, NULL);
+			break;
+		case FRAGMENT_DIE:
+			/* Use a complete die_map expansion if available */
+			if (__die_map_get(df->data.addr, DIE_COMPLETE,
+					  &child) &&
+			    __die_map_get(df->data.addr, DIE_UNEXPANDED,
+					  &child))
+				error("unknown child: %" PRIxPTR,
+				      df->data.addr);
+
+			name = get_type_name(child);
+			if (name)
+				type_expansion_append(type, name, name);
+			else
+				__type_expand(child, type);
+
+			break;
+		case FRAGMENT_LINEBREAK:
+			/*
+			 * Keep whitespace in the symtypes format, but avoid
+			 * repeated spaces.
+			 */
+			if (list_is_last(&df->list, &cache->fragments) ||
+			    list_next_entry(df, list)->type !=
+				    FRAGMENT_LINEBREAK)
+				type_expansion_append(type, " ", NULL);
+			break;
+		default:
+			error("empty die_fragment in %p", cache);
+		}
+	}
+}
+
+static void type_expand(const char *name, struct die *cache,
+			struct type_expansion *type)
+{
+	const char *override;
+
+	type_expansion_init(type);
+
+	if (stable && kabi_get_type_string(name, &override))
+		type_parse(name, override, type);
+	else
+		__type_expand(cache, type);
+}
+
+static void type_parse(const char *name, const char *str,
+		       struct type_expansion *type)
+{
+	char *fragment;
+	size_t start = 0;
+	size_t end;
+	size_t pos;
+
+	if (!*str)
+		error("empty type string override for '%s'", name);
+
+	for (pos = 0; str[pos]; ++pos) {
+		bool empty;
+		char marker = ' ';
+
+		if (!is_type_prefix(&str[pos]))
+			continue;
+
+		end = pos + 2;
+
+		/*
+		 * Find the end of the type reference. If the type name contains
+		 * spaces, it must be in single quotes.
+		 */
+		if (str[end] == '\'') {
+			marker = '\'';
+			++end;
+		}
+		while (str[end] && str[end] != marker)
+			++end;
+
+		/* Check that we have a non-empty type name */
+		if (marker == '\'') {
+			if (str[end] != marker)
+				error("incomplete %c# type reference for '%s' (string : '%s')",
+				      str[pos], name, str);
+			empty = end == pos + 3;
+			++end;
+		} else {
+			empty = end == pos + 2;
+		}
+		if (empty)
+			error("empty %c# type name for '%s' (string: '%s')",
+			      str[pos], name, str);
+
+		/* Append the part of the string before the type reference */
+		if (pos > start) {
+			fragment = xstrndup(&str[start], pos - start);
+			type_expansion_append(type, fragment, fragment);
+		}
+
+		/*
+		 * Append the type reference -- note that if the reference
+		 * is invalid, i.e. points to a non-existent type, we will
+		 * print out an error when calculating versions.
+		 */
+		fragment = xstrndup(&str[pos], end - pos);
+		type_expansion_append(type, fragment, fragment);
+
+		start = end;
+		pos = end - 1;
+	}
+
+	/* Append the rest of the type string, if there's any left */
+	if (str[start])
+		type_expansion_append(type, &str[start], NULL);
+}
+
+static void expand_type(struct die *cache, void *arg)
+{
+	struct type_expansion type;
+	char *name;
+
+	if (cache->mapped)
+		return;
+
+	cache->mapped = true;
+
+	/*
+	 * Skip unexpanded die_map entries if there's a complete
+	 * expansion available for this DIE.
+	 */
+	if (cache->state == DIE_UNEXPANDED &&
+	    !__die_map_get(cache->addr, DIE_COMPLETE, &cache)) {
+		if (cache->mapped)
+			return;
+
+		cache->mapped = true;
+	}
+
+	name = get_type_name(cache);
+	if (!name)
+		return;
+
+	debug("%s", name);
+
+	type_expand(name, cache, &type);
+	type_map_add(name, &type);
+	type_expansion_free(&type);
+	free(name);
+}
+
+static void expand_symbol(struct symbol *sym, void *arg)
+{
+	struct type_expansion type;
+	struct version version;
+	struct die *cache;
+
+	/*
+	 * No need to expand again unless we want a symtypes file entry
+	 * for the symbol. Note that this means `sym` has the same address
+	 * as another symbol that was already processed.
+	 */
+	if (!symtypes && sym->state == SYMBOL_PROCESSED)
+		return;
+
+	if (__die_map_get(sym->die_addr, DIE_SYMBOL, &cache))
+		return; /* We'll warn about missing CRCs later. */
+
+	type_expand(sym->name, cache, &type);
+
+	/* If the symbol already has a version, don't calculate it again. */
+	if (sym->state != SYMBOL_PROCESSED) {
+		calculate_version(&version, &type);
+		symbol_set_crc(sym, version.crc);
+		debug("%s = %lx", sym->name, version.crc);
+
+		if (dump_versions) {
+			checkp(fputs(sym->name, stderr));
+			checkp(fputs(" ", stderr));
+			type_list_write(&version.type.expanded, stderr);
+			checkp(fputs("\n", stderr));
+		}
+
+		version_free(&version);
+	}
+
+	/* These aren't needed in type_map unless we want a symtypes file. */
+	if (symtypes)
+		type_map_add(sym->name, &type);
+
+	type_expansion_free(&type);
+}
+
+void generate_symtypes_and_versions(FILE *file)
+{
+	cache_init(&expansion_cache);
+
+	/*
+	 * die_map processing:
+	 *
+	 *   1. die_map contains all types referenced in exported symbol
+	 *      signatures, but can contain duplicates just like the original
+	 *      DWARF, and some references may not be fully expanded depending
+	 *      on how far we processed the DIE tree for that specific symbol.
+	 *
+	 *      For each die_map entry, find the longest available expansion,
+	 *      and add it to type_map.
+	 */
+	die_map_for_each(expand_type, NULL);
+
+	/*
+	 *   2. For each exported symbol, expand the die_map type, and use
+	 *      type_map expansions to calculate a symbol version from the
+	 *      fully expanded type string.
+	 */
+	symbol_for_each(expand_symbol, NULL);
+
+	/*
+	 *   3. If a symtypes file is requested, write type_map contents to
+	 *      the file.
+	 */
+	type_map_write(file);
+	type_map_free();
+}