kallsyms: new /proc/kallmodsyms with builtin modules and symbol sizes

@@ -49,6 +49,7 @@
 *.zst
 Module.symvers
 modules.order
+modules_thick.builtin
 
 #
 # Top-level generic files

@@ -183,6 +183,7 @@ modules.builtin
 modules.builtin.modinfo
 modules.nsdeps
 modules.order
+modules_thick.builtin
 modversions.h*
 nconf
 nconf-cfg

@@ -1195,7 +1195,7 @@ cmd_link-vmlinux =                                                 \
 	$(CONFIG_SHELL) $< "$(LD)" "$(KBUILD_LDFLAGS)" "$(LDFLAGS_vmlinux)";    \
 	$(if $(ARCH_POSTLINK), $(MAKE) -f $(ARCH_POSTLINK) $@, true)
 
-vmlinux: scripts/link-vmlinux.sh autoksyms_recursive $(vmlinux-deps) FORCE
+vmlinux: scripts/link-vmlinux.sh autoksyms_recursive $(vmlinux-deps) modules_thick.builtin FORCE
 	+$(call if_changed_dep,link-vmlinux)
 
 targets := vmlinux

@@ -1496,6 +1496,23 @@ __modinst_pre:
 
 endif # CONFIG_MODULES
 
+# modules_thick.builtin maps from kernel modules (or rather the object file
+# names they would have had had they not been built in) to their constituent
+# object files: we can use this to determine which modules any given object
+# file is part of.  (We cannot eliminate the slight redundancy here without
+# double-expansion.)
+
+modthickbuiltin-files := $(addsuffix /modules_thick.builtin, $(build-dirs))
+
+modules_thick.builtin: $(modthickbuiltin-files)
+	$(Q)$(AWK) '!x[$$0]++' $(addsuffix /$@, $(build-dirs)) > $@
+
+# tristate.conf is not included from this Makefile. Add it as a prerequisite
+# here to make it self-healing in case somebody accidentally removes it.
+$(modthickbuiltin-files): include/config/tristate.conf
+	$(Q)$(MAKE) $(modbuiltin)=$(patsubst %/modules_thick.builtin,%,$@) builtin-file=modules_thick.builtin
+
+
 ###
 # Cleaning is done on three levels.
 # make clean     Delete most generated files

@@ -1865,7 +1882,7 @@ clean: $(clean-dirs)
 		-o -name '*.lex.c' -o -name '*.tab.[ch]' \
 		-o -name '*.asn1.[ch]' \
 		-o -name '*.symtypes' -o -name 'modules.order' \
-		-o -name '.tmp_*.o.*' \
+		-o -name '.tmp_*.o.*' -o -name modules_thick.builtin \
 		-o -name '*.c.[012]*.*' \
 		-o -name '*.ll' \
 		-o -name '*.gcno' \

@@ -579,7 +579,8 @@ struct module *find_module(const char *name);
 /* Returns 0 and fills in value, defined and namebuf, or -ERANGE if
    symnum out of range. */
 int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
-			char *name, char *module_name, int *exported);
+		       char *name, char *module_name, unsigned long *size,
+		       int *exported);
 
 /* Look for this name: can be of form module:name. */
 unsigned long module_kallsyms_lookup_name(const char *name);

@@ -756,8 +757,8 @@ static inline int lookup_module_symbol_attrs(unsigned long addr, unsigned long *
 }
 
 static inline int module_get_kallsym(unsigned int symnum, unsigned long *value,
-					char *type, char *name,
-					char *module_name, int *exported)
+				     char *type, char *name, char *module_name,
+				     unsigned long *size, int *exported)
 {
 	return -ERANGE;
 }

@@ -1495,6 +1495,14 @@ config POSIX_TIMERS
 
 	  If unsure say y.
 
+config KALLMODSYMS
+	default y
+	bool "Enable support for /proc/kallmodsyms" if EXPERT
+	depends on KALLSYMS
+	help
+	  This option enables the /proc/kallmodsyms file, which maps symbols
+	  to addresses and their associated modules.
+
 config PRINTK
 	default y
 	bool "Enable support for printk" if EXPERT

@@ -33,6 +33,7 @@
  */
 extern const unsigned long kallsyms_addresses[] __weak;
 extern const int kallsyms_offsets[] __weak;
+extern const unsigned long kallsyms_sizes[] __weak;
 extern const u8 kallsyms_names[] __weak;
 
 /*

@@ -45,8 +46,18 @@ __section(".rodata") __attribute__((weak));
 extern const unsigned long kallsyms_relative_base
 __section(".rodata") __attribute__((weak));
 
+extern const unsigned long kallsyms_num_modules
+__section(".rodata") __attribute__((weak));
+
+extern const unsigned long kallsyms_module_names_len
+__section(".rodata") __attribute__((weak));
+
 extern const char kallsyms_token_table[] __weak;
 extern const u16 kallsyms_token_index[] __weak;
+extern const unsigned long kallsyms_module_addresses[] __weak;
+extern const int kallsyms_module_offsets[] __weak;
+extern const u32 kallsyms_modules[] __weak;
+extern const char kallsyms_module_names[] __weak;
 
 extern const unsigned int kallsyms_markers[] __weak;
 

@@ -182,6 +193,25 @@ static inline bool cleanup_symbol_name(char *s)
 static inline bool cleanup_symbol_name(char *s) { return false; }
 #endif
 
+#ifdef CONFIG_KALLMODSYMS
+static unsigned long kallsyms_builtin_module_address(int idx)
+{
+	if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE))
+		return kallsyms_module_addresses[idx];
+
+	/* values are unsigned offsets if --absolute-percpu is not in effect */
+	if (!IS_ENABLED(CONFIG_KALLSYMS_ABSOLUTE_PERCPU))
+		return kallsyms_relative_base + (u32)kallsyms_module_offsets[idx];
+
+	/* ...otherwise, positive offsets are absolute values */
+	if (kallsyms_module_offsets[idx] >= 0)
+		return kallsyms_module_offsets[idx];
+
+	/* ...and negative offsets are relative to kallsyms_relative_base - 1 */
+	return kallsyms_relative_base - 1 - kallsyms_module_offsets[idx];
+}
+#endif
+
 /* Lookup the address for this symbol. Returns 0 if not found. */
 unsigned long kallsyms_lookup_name(const char *name)
 {

@@ -225,12 +255,24 @@ int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
 }
 #endif /* CONFIG_LIVEPATCH */
 
+/*
+ * The caller passes in an address, and we return an index to the symbol --
+ * potentially also size and offset information.
+ * But an address might map to multiple symbols because:
+ *   - some symbols might have zero size
+ *   - some symbols might be aliases of one another
+ *   - some symbols might span (encompass) others
+ * The symbols should already be ordered so that, for a particular address,
+ * we first have the zero-size ones, then the biggest, then the smallest.
+ * So we find the index by:
+ *   - finding the last symbol with the target address
+ *   - backing the index up so long as both the address and size are unchanged
+ */
 static unsigned long get_symbol_pos(unsigned long addr,
 				    unsigned long *symbolsize,
 				    unsigned long *offset)
 {
-	unsigned long symbol_start = 0, symbol_end = 0;
-	unsigned long i, low, high, mid;
+	unsigned long low, high, mid;
 
 	/* This kernel should never had been booted. */
 	if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE))

@@ -251,40 +293,69 @@ static unsigned long get_symbol_pos(unsigned long addr,
 	}
 
 	/*
-	 * Search for the first aliased symbol. Aliased
-	 * symbols are symbols with the same address.
+	 * Search for the first aliased symbol.
 	 */
-	while (low && kallsyms_sym_address(low-1) == kallsyms_sym_address(low))
+	while (low
+	    && kallsyms_sym_address(low-1) == kallsyms_sym_address(low)
+	    && kallsyms_sizes[low-1] == kallsyms_sizes[low])
 		--low;
 
-	symbol_start = kallsyms_sym_address(low);
-
-	/* Search for next non-aliased symbol. */
-	for (i = low + 1; i < kallsyms_num_syms; i++) {
-		if (kallsyms_sym_address(i) > symbol_start) {
-			symbol_end = kallsyms_sym_address(i);
-			break;
-		}
-	}
-
-	/* If we found no next symbol, we use the end of the section. */
-	if (!symbol_end) {
-		if (is_kernel_inittext(addr))
-			symbol_end = (unsigned long)_einittext;
-		else if (IS_ENABLED(CONFIG_KALLSYMS_ALL))
-			symbol_end = (unsigned long)_end;
-		else
-			symbol_end = (unsigned long)_etext;
-	}
-
 	if (symbolsize)
-		*symbolsize = symbol_end - symbol_start;
+		*symbolsize = kallsyms_sizes[low];
 	if (offset)
-		*offset = addr - symbol_start;
+		*offset = addr - kallsyms_sym_address(low);
 
 	return low;
 }
 
+/*
+ * The caller passes in an address, and we return an index to the corresponding
+ * builtin module index in .kallsyms_modules, or (unsigned long) -1 if none
+ * match.
+ *
+ * The hint_idx, if set, is a hint as to the possible return value, to handle
+ * the common case in which consecutive runs of addresses relate to the same
+ * index.
+ */
+#ifdef CONFIG_KALLMODSYMS
+static unsigned long get_builtin_module_idx(unsigned long addr, unsigned long hint_idx)
+{
+	unsigned long low, high, mid;
+
+	if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE))
+		BUG_ON(!kallsyms_module_addresses);
+	else
+		BUG_ON(!kallsyms_module_offsets);
+
+	/*
+	 * Do a binary search on the sorted kallsyms_modules array.  The last
+	 * entry in this array indicates the end of the text section, not an
+	 * object file.
+	 */
+	low = 0;
+	high = kallsyms_num_modules - 1;
+
+	if (hint_idx > low && hint_idx < (high - 1) &&
+	    addr >= kallsyms_builtin_module_address(hint_idx) &&
+	    addr < kallsyms_builtin_module_address(hint_idx + 1))
+		return hint_idx;
+
+	if (addr >= kallsyms_builtin_module_address(low)
+	    && addr < kallsyms_builtin_module_address(high)) {
+		while (high - low > 1) {
+			mid = low + (high - low) / 2;
+			if (kallsyms_builtin_module_address(mid) <= addr)
+				low = mid;
+			else
+				high = mid;
+		}
+		return low;
+	}
+
+	return (unsigned long) -1;
+}
+#endif
+
 /*
  * Lookup an address but don't bother to find any names.
  */

@@ -300,6 +371,7 @@ int kallsyms_lookup_size_offset(unsigned long addr, unsigned long *symbolsize,
 	return !!module_address_lookup(addr, symbolsize, offset, NULL, namebuf) ||
 	       !!__bpf_address_lookup(addr, symbolsize, offset, namebuf);
 }
+EXPORT_SYMBOL_GPL(kallsyms_lookup_size_offset);
 
 /*
  * Lookup an address

@@ -492,9 +564,12 @@ struct kallsym_iter {
 	loff_t pos_bpf_end;
 	unsigned long value;
 	unsigned int nameoff; /* If iterating in core kernel symbols. */
+	unsigned long size;
 	char type;
 	char name[KSYM_NAME_LEN];
 	char module_name[MODULE_NAME_LEN];
+	const char *builtin_module_names;
+	unsigned long hint_builtin_module_idx;
 	int exported;
 	int show_value;
 };

@@ -524,7 +599,9 @@ static int get_ksymbol_mod(struct kallsym_iter *iter)
 	int ret = module_get_kallsym(iter->pos - iter->pos_arch_end,
 				     &iter->value, &iter->type,
 				     iter->name, iter->module_name,
-				     &iter->exported);
+				     &iter->size, &iter->exported);
+	iter->builtin_module_names = NULL;
+
 	if (ret < 0) {
 		iter->pos_mod_end = iter->pos;
 		return 0;

@@ -544,6 +621,8 @@ static int get_ksymbol_ftrace_mod(struct kallsym_iter *iter)
 					 &iter->value, &iter->type,
 					 iter->name, iter->module_name,
 					 &iter->exported);
+	iter->builtin_module_names = NULL;
+
 	if (ret < 0) {
 		iter->pos_ftrace_mod_end = iter->pos;
 		return 0;

@@ -558,6 +637,7 @@ static int get_ksymbol_bpf(struct kallsym_iter *iter)
 
 	strlcpy(iter->module_name, "bpf", MODULE_NAME_LEN);
 	iter->exported = 0;
+	iter->builtin_module_names = NULL;
 	ret = bpf_get_kallsym(iter->pos - iter->pos_ftrace_mod_end,
 			      &iter->value, &iter->type,
 			      iter->name);

@@ -578,23 +658,53 @@ static int get_ksymbol_kprobe(struct kallsym_iter *iter)
 {
 	strlcpy(iter->module_name, "__builtin__kprobes", MODULE_NAME_LEN);
 	iter->exported = 0;
+	iter->builtin_module_names = NULL;
 	return kprobe_get_kallsym(iter->pos - iter->pos_bpf_end,
 				  &iter->value, &iter->type,
 				  iter->name) < 0 ? 0 : 1;
 }
 
 /* Returns space to next name. */
-static unsigned long get_ksymbol_core(struct kallsym_iter *iter)
+static unsigned long get_ksymbol_core(struct kallsym_iter *iter, int kallmodsyms)
 {
 	unsigned off = iter->nameoff;
+	unsigned long mod_idx;
 
-	iter->module_name[0] = '\0';
+	iter->exported = 0;
 	iter->value = kallsyms_sym_address(iter->pos);
 
+	iter->size = kallsyms_sizes[iter->pos];
 	iter->type = kallsyms_get_symbol_type(off);
 
+	iter->module_name[0] = '\0';
+	iter->builtin_module_names = NULL;
+
 	off = kallsyms_expand_symbol(off, iter->name, ARRAY_SIZE(iter->name));
+#ifdef CONFIG_KALLMODSYMS
+	if (kallmodsyms) {
+		if (kallsyms_module_offsets)
+			mod_idx =
+			  get_builtin_module_idx(iter->value,
+						 iter->hint_builtin_module_idx);
 
+		/*
+		 * This is a built-in module iff the tables of built-in modules
+		 * (address->module name mappings) and module names are known,
+		 * and if the address was found there, and if the corresponding
+		 * module index is nonzero.  All other cases mean off the end of
+		 * the binary or in a non-modular range in between one or more
+		 * modules.  (Also guard against a corrupt kallsyms_objfiles
+		 * array pointing off the end of kallsyms_modules.)
+		 */
+		if (kallsyms_modules != NULL && kallsyms_module_names != NULL &&
+		    mod_idx != (unsigned long) -1 &&
+		    kallsyms_modules[mod_idx] != 0 &&
+		    kallsyms_modules[mod_idx] < kallsyms_module_names_len)
+			iter->builtin_module_names =
+			  &kallsyms_module_names[kallsyms_modules[mod_idx]];
+		iter->hint_builtin_module_idx = mod_idx;
+	}
+#endif
 	return off - iter->nameoff;
 }
 

@@ -640,7 +750,7 @@ static int update_iter_mod(struct kallsym_iter *iter, loff_t pos)
 }
 
 /* Returns false if pos at or past end of file. */
-static int update_iter(struct kallsym_iter *iter, loff_t pos)
+int update_iter(struct kallsym_iter *iter, loff_t pos, int kallmodsyms)
 {
 	/* Module symbols can be accessed randomly. */
 	if (pos >= kallsyms_num_syms)

@@ -650,7 +760,7 @@ static int update_iter(struct kallsym_iter *iter, loff_t pos)
 	if (pos != iter->pos)
 		reset_iter(iter, pos);
 
-	iter->nameoff += get_ksymbol_core(iter);
+	iter->nameoff += get_ksymbol_core(iter, kallmodsyms);
 	iter->pos++;
 
 	return 1;

@@ -660,14 +770,14 @@ static void *s_next(struct seq_file *m, void *p, loff_t *pos)
 {
 	(*pos)++;
 
-	if (!update_iter(m->private, *pos))
+	if (!update_iter(m->private, *pos, 0))
 		return NULL;
 	return p;
 }
 
 static void *s_start(struct seq_file *m, loff_t *pos)
 {
-	if (!update_iter(m->private, *pos))
+	if (!update_iter(m->private, *pos, 0))
 		return NULL;
 	return m->private;
 }

@@ -676,34 +786,86 @@ static void s_stop(struct seq_file *m, void *p)
 {
 }
 
-static int s_show(struct seq_file *m, void *p)
+static int s_show_internal(struct seq_file *m, void *p, int kallmodsyms)
 {
 	void *value;
 	struct kallsym_iter *iter = m->private;
+	unsigned long size;
 
 	/* Some debugging symbols have no name.  Ignore them. */
 	if (!iter->name[0])
 		return 0;
 
 	value = iter->show_value ? (void *)iter->value : NULL;
+	size = iter->show_value ? iter->size : 0;
 
-	if (iter->module_name[0]) {
+	/*
+	 * Real module, or built-in module and /proc/kallsyms being shown.
+	 */
+	if (iter->module_name[0] != '\0' ||
+	    (iter->builtin_module_names != NULL && kallmodsyms != 0)) {
 		char type;
 
 		/*
-		 * Label it "global" if it is exported,
-		 * "local" if not exported.
+		 * Label it "global" if it is exported, "local" if not exported.
 		 */
 		type = iter->exported ? toupper(iter->type) :
 					tolower(iter->type);
-		seq_printf(m, "%px %c %s\t[%s]\n", value,
-			   type, iter->name, iter->module_name);
-	} else
+#ifdef CONFIG_KALLMODSYMS
+		if (kallmodsyms) {
+			/*
+			 * /proc/kallmodsyms, built as a module.
+			 */
+			if (iter->builtin_module_names == NULL)
+				seq_printf(m, "%px %lx %c %s\t[%s]\n", value,
+					   size, type, iter->name,
+					   iter->module_name);
+			/*
+			 * /proc/kallmodsyms, single-module symbol.
+			 */
+			else if (*iter->builtin_module_names != '\0')
+				seq_printf(m, "%px %lx %c %s\t[%s]\n", value,
+					   size, type, iter->name,
+					   iter->builtin_module_names);
+			/*
+			 * /proc/kallmodsyms, multimodule symbol.  Formatted
+			 * as \0MODULE_COUNTmodule-1\0module-2\0, where
+			 * MODULE_COUNT is a single byte, 2 or higher.
+			 */
+			else {
+				size_t i = *(char *)(iter->builtin_module_names + 1);
+				const char *walk = iter->builtin_module_names + 2;
+
+				seq_printf(m, "%px %lx %c %s\t[%s]", value,
+					   size, type, iter->name, walk);
+
+                                while (--i > 0) {
+					walk += strlen(walk) + 1;
+					seq_printf (m, " [%s]", walk);
+				}
+				seq_printf(m, "\n");
+			}
+		} else				/* !kallmodsyms */
+#endif /* CONFIG_KALLMODSYMS */
+			seq_printf(m, "%px %c %s\t[%s]\n", value,
+				   type, iter->name, iter->module_name);
+	/*
+	 * Non-modular, /proc/kallmodsyms -> print size.
+	 */
+	} else if (kallmodsyms)
+		seq_printf(m, "%px %lx %c %s\n", value, size,
+			   iter->type, iter->name);
+	else
 		seq_printf(m, "%px %c %s\n", value,
 			   iter->type, iter->name);
 	return 0;
 }
 
+static int s_show(struct seq_file *m, void *p)
+{
+	return s_show_internal(m, p, 0);
+}
+
 static const struct seq_operations kallsyms_op = {
 	.start = s_start,
 	.next = s_next,

@@ -711,6 +873,35 @@ static const struct seq_operations kallsyms_op = {
 	.show = s_show
 };
 
+#ifdef CONFIG_KALLMODSYMS
+static int s_mod_show(struct seq_file *m, void *p)
+{
+	return s_show_internal(m, p, 1);
+}
+static void *s_mod_next(struct seq_file *m, void *p, loff_t *pos)
+{
+	(*pos)++;
+
+	if (!update_iter(m->private, *pos, 1))
+		return NULL;
+	return p;
+}
+
+static void *s_mod_start(struct seq_file *m, loff_t *pos)
+{
+	if (!update_iter(m->private, *pos, 1))
+		return NULL;
+	return m->private;
+}
+
+static const struct seq_operations kallmodsyms_op = {
+	.start = s_mod_start,
+	.next = s_mod_next,
+	.stop = s_stop,
+	.show = s_mod_show
+};
+#endif
+
 static inline int kallsyms_for_perf(void)
 {
 #ifdef CONFIG_PERF_EVENTS

@@ -746,7 +937,8 @@ bool kallsyms_show_value(const struct cred *cred)
 	}
 }
 
-static int kallsyms_open(struct inode *inode, struct file *file)
+static int kallsyms_open_internal(struct inode *inode, struct file *file,
+	const struct seq_operations *ops)
 {
 	/*
 	 * We keep iterator in m->private, since normal case is to

@@ -754,7 +946,7 @@ static int kallsyms_open(struct inode *inode, struct file *file)
 	 * using get_symbol_offset for every symbol.
 	 */
 	struct kallsym_iter *iter;
-	iter = __seq_open_private(file, &kallsyms_op, sizeof(*iter));
+	iter = __seq_open_private(file, ops, sizeof(*iter));
 	if (!iter)
 		return -ENOMEM;
 	reset_iter(iter, 0);

@@ -767,6 +959,18 @@ static int kallsyms_open(struct inode *inode, struct file *file)
 	return 0;
 }
 
+static int kallsyms_open(struct inode *inode, struct file *file)
+{
+	return kallsyms_open_internal(inode, file, &kallsyms_op);
+}
+
+#ifdef CONFIG_KALLMODSYMS
+static int kallmodsyms_open(struct inode *inode, struct file *file)
+{
+	return kallsyms_open_internal(inode, file, &kallmodsyms_op);
+}
+#endif
+
 #ifdef	CONFIG_KGDB_KDB
 const char *kdb_walk_kallsyms(loff_t *pos)
 {

@@ -777,7 +981,7 @@ const char *kdb_walk_kallsyms(loff_t *pos)
 		reset_iter(&kdb_walk_kallsyms_iter, 0);
 	}
 	while (1) {
-		if (!update_iter(&kdb_walk_kallsyms_iter, *pos))
+		if (!update_iter(&kdb_walk_kallsyms_iter, *pos, 0))
 			return NULL;
 		++*pos;
 		/* Some debugging symbols have no name.  Ignore them. */

@@ -794,9 +998,21 @@ static const struct proc_ops kallsyms_proc_ops = {
 	.proc_release	= seq_release_private,
 };
 
+#ifdef CONFIG_KALLMODSYMS
+static const struct proc_ops kallmodsyms_proc_ops = {
+	.proc_open	= kallmodsyms_open,
+	.proc_read	= seq_read,
+	.proc_lseek	= seq_lseek,
+	.proc_release	= seq_release_private,
+};
+#endif
+
 static int __init kallsyms_init(void)
 {
 	proc_create("kallsyms", 0444, NULL, &kallsyms_proc_ops);
+#ifdef CONFIG_KALLMODSYMS
+	proc_create("kallmodsyms", 0444, NULL, &kallmodsyms_proc_ops);
+#endif
 	return 0;
 }
 device_initcall(kallsyms_init);

@@ -4332,7 +4332,8 @@ int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size,
 }
 
 int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
-			char *name, char *module_name, int *exported)
+		       char *name, char *module_name, unsigned long *size,
+		       int *exported)
 {
 	struct module *mod;
 

@@ -4351,6 +4352,7 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
 			strlcpy(name, kallsyms_symbol_name(kallsyms, symnum), KSYM_NAME_LEN);
 			strlcpy(module_name, mod->name, MODULE_NAME_LEN);
 			*exported = is_exported(name, *value, mod);
+			*size = kallsyms->symtab[symnum].st_size;
 			preempt_enable();
 			return 0;
 		}

@@ -73,6 +73,12 @@ endef
 # $(Q)$(MAKE) $(build)=dir
 build := -f $(srctree)/scripts/Makefile.build obj
 
+###
+# Shorthand for $(Q)$(MAKE) -f scripts/Makefile.modbuiltin obj=
+# Usage:
+# $(Q)$(MAKE) $(modbuiltin)=dir
+modbuiltin := -f $(srctree)/scripts/Makefile.modbuiltin obj
+
 ###
 # Shorthand for $(Q)$(MAKE) -f scripts/Makefile.dtbinst obj=
 # Usage:

@@ -32,6 +32,12 @@ HOSTCFLAGS_sorttable.o += -DUNWINDER_ORC_ENABLED
 HOSTLDLIBS_sorttable = -lpthread
 endif
 
+kallsyms-objs  := kallsyms.o
+
+ifdef CONFIG_KALLMODSYMS
+kallsyms-objs += modules_thick.o
+endif
+
 # The following programs are only built on demand
 hostprogs += unifdef
 

@@ -0,0 +1,56 @@
+# SPDX-License-Identifier: GPL-2.0
+# ==========================================================================
+# Generating modules_thick.builtin
+# ==========================================================================
+
+src := $(obj)
+
+PHONY := __modbuiltin
+__modbuiltin:
+
+include include/config/auto.conf
+# tristate.conf sets tristate variables to uppercase 'Y' or 'M'
+# That way, we get the list of built-in modules in obj-Y
+include include/config/tristate.conf
+
+include scripts/Kbuild.include
+
+ifdef building_out_of_srctree
+# Create output directory if not already present
+_dummy := $(shell [ -d $(obj) ] || mkdir -p $(obj))
+endif
+
+# The filename Kbuild has precedence over Makefile
+kbuild-dir := $(if $(filter /%,$(src)),$(src),$(srctree)/$(src))
+kbuild-file := $(if $(wildcard $(kbuild-dir)/Kbuild),$(kbuild-dir)/Kbuild,$(kbuild-dir)/Makefile)
+include $(kbuild-file)
+
+include scripts/Makefile.lib
+
+modthickbuiltin-subdirs := $(patsubst %,%/modules_thick.builtin, $(subdir-ym))
+modthickbuiltin-target  := $(obj)/modules_thick.builtin
+
+__modbuiltin: $(obj)/$(builtin-file) $(subdir-ym)
+	@:
+
+$(modthickbuiltin-target): $(subdir-ym) FORCE
+	$(Q) rm -f $@
+	$(Q) $(foreach mod-o, $(filter %.o,$(obj-Y)),\
+		printf "%s:" $(addprefix $(obj)/,$(mod-o)) >> $@; \
+		printf " %s" $(sort $(strip $(addprefix $(obj)/,$($(mod-o:.o=-objs)) \
+			$($(mod-o:.o=-y)) $($(mod-o:.o=-Y))))) >> $@; \
+		printf "\n" >> $@; ) \
+	cat /dev/null $(modthickbuiltin-subdirs) >> $@;
+
+PHONY += FORCE
+
+FORCE:
+
+# Descending
+# ---------------------------------------------------------------------------
+
+PHONY += $(subdir-ym)
+$(subdir-ym):
+	$(Q)$(MAKE) $(modbuiltin)=$@ builtin-file=$(builtin-file)
+
+.PHONY: $(PHONY)

@@ -5,7 +5,10 @@
  * This software may be used and distributed according to the terms
  * of the GNU General Public License, incorporated herein by reference.
  *
- * Usage: nm -n vmlinux | scripts/kallsyms [--all-symbols] > symbols.S
+ * Usage: nm -n -S vmlinux
+ *        | scripts/kallsyms [--all-symbols] [--absolute-percpu]
+ *             [--base-relative] [--builtin=modules_thick.builtin]
+ *        > symbols.S
  *
  *      Table compression uses all the unused char codes on the symbols and
  *  maps these to the most used substrings (tokens). For instance, it might

@@ -18,19 +21,31 @@
  *
  */
 
+#define _GNU_SOURCE 1
 #include <stdbool.h>
 #include <stdio.h>
 #include <stdlib.h>
 #include <string.h>
 #include <ctype.h>
 #include <limits.h>
+#include <assert.h>
+#include "modules_thick.h"
 
+#include "../include/generated/autoconf.h"
+
+#ifdef CONFIG_KALLMODSYMS
+#include <errno.h>
+#endif
+
+#ifndef ARRAY_SIZE
 #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0]))
+#endif
 
 #define KSYM_NAME_LEN		128
 
 struct sym_entry {
 	unsigned long long addr;
+	unsigned long long size;
 	unsigned int len;
 	unsigned int start_pos;
 	unsigned int percpu_absolute;

@@ -67,11 +82,304 @@ static int token_profit[0x10000];
 static unsigned char best_table[256][2];
 static unsigned char best_table_len[256];
 
+#ifdef CONFIG_KALLMODSYMS
+static unsigned int strhash(const char *s)
+{
+	/* fnv32 hash */
+	unsigned int hash = 2166136261U;
+
+	for (; *s; s++)
+		hash = (hash ^ *s) * 0x01000193;
+	return hash;
+}
+
+static unsigned int memhash(char *s, size_t len)
+{
+	/* fnv32 hash */
+	unsigned int hash = 2166136261U;
+	size_t i;
+
+	for (i = 0; i < len; i++)
+		hash = (hash ^ *(s + i)) * 0x01000193;
+	return hash;
+}
+
+#define OBJ2MOD_BITS 10
+#define OBJ2MOD_N (1 << OBJ2MOD_BITS)
+#define OBJ2MOD_MASK (OBJ2MOD_N - 1)
+struct obj2mod_elem {
+	char *obj;
+	char *mods;			/* sorted module name strtab */
+	size_t nmods;			/* number of modules in "mods" */
+	size_t mods_size;		/* size of all mods together */
+	int mod_offset;			/* offset in .kallsyms_module_names */
+	/*
+	 * If set at emission time, this points at another obj2mod entry that
+	 * contains the module name we need (possibly at a slightly later
+	 * offset, if the entry is for an objfile that appears in many modules).
+	 */
+	struct obj2mod_elem *xref;
+	struct obj2mod_elem *obj2mod_next;
+	struct obj2mod_elem *mod2obj_next;
+};
+
+/*
+ * Map from object files to obj2mod entries (a unique mapping), and vice versa
+ * (not unique, but entries for objfiles in more than one module in this hash
+ * are ignored).
+ */
+
+static struct obj2mod_elem *obj2mod[OBJ2MOD_N];
+static struct obj2mod_elem *mod2obj[OBJ2MOD_N];
+static size_t num_objfiles;
+
+/*
+ * An ordered list of address ranges and the objfile that occupies that range.
+ */
+struct addrmap_entry {
+	unsigned long long addr;
+	struct obj2mod_elem *objfile;
+};
+static struct addrmap_entry *addrmap;
+static int addrmap_num, addrmap_alloced;
+
+static void obj2mod_init(void)
+{
+	memset(obj2mod, 0, sizeof(obj2mod));
+}
+
+static struct obj2mod_elem *obj2mod_get(const char *obj)
+{
+	int i = strhash(obj) & OBJ2MOD_MASK;
+	struct obj2mod_elem *elem;
+
+	for (elem = obj2mod[i]; elem; elem = elem->obj2mod_next) {
+		if (strcmp(elem->obj, obj) == 0)
+			return elem;
+	}
+	return NULL;
+}
+
+/*
+ * Note that a given object file is found in some module, interning it in the
+ * obj2mod hash.  Should not be called more than once for any given (module,
+ * object) pair.
+ */
+static void obj2mod_add(char *obj, char *mod)
+{
+	int i = strhash(obj) & OBJ2MOD_MASK;
+	struct obj2mod_elem *elem;
+
+	elem = obj2mod_get(obj);
+	if (!elem) {
+		int j = strhash(mod) & OBJ2MOD_MASK;
+
+		elem = malloc(sizeof(struct obj2mod_elem));
+		if (!elem)
+			goto oom;
+		memset(elem, 0, sizeof(struct obj2mod_elem));
+		elem->obj = strdup(obj);
+		if (!elem->obj)
+			goto oom;
+		elem->mods = strdup(mod);
+		if (!elem->mods)
+			goto oom;
+
+		elem->obj2mod_next = obj2mod[i];
+		obj2mod[i] = elem;
+		elem->mod2obj_next = mod2obj[j];
+		mod2obj[j] = elem;
+		num_objfiles++;
+	} else {
+		/*
+		 * TU appears in multiple modules.  mod2obj for this entry will
+		 * be ignored from now on, except insofar as it is needed to
+		 * maintain the hash chain.
+		 */
+		elem->mods = realloc(elem->mods, elem->mods_size +
+				     strlen(mod) + 1);
+		if (!elem->mods)
+			goto oom;
+		strcpy(elem->mods + elem->mods_size, mod);
+	}
+
+	elem->mods_size += strlen(mod) + 1;
+	elem->nmods++;
+	if (elem->nmods > 255) {
+		fprintf(stderr, "kallsyms: %s: too many modules associated with this object file\n",
+			obj);
+		exit(EXIT_FAILURE);
+	}
+	return;
+oom:
+	fprintf(stderr, "kallsyms: out of memory\n");
+	exit(1);
+}
+
+/*
+ * Used inside optimize_obj2mod to identify duplicate module entries.
+ */
+struct obj2mod_modhash_elem {
+	struct obj2mod_elem *elem;
+	unsigned int modhash;		/* hash value of this entry */
+};
+
+static int qstrcmp(const void *a, const void *b)
+{
+	return strcmp((const char *) a, (const char *) b);
+}
+
+static int qmodhash(const void *a, const void *b)
+{
+	const struct obj2mod_modhash_elem *el_a = a;
+	const struct obj2mod_modhash_elem *el_b = b;
+	if (el_a->modhash < el_b->modhash)
+		return -1;
+	else if (el_a->modhash > el_b->modhash)
+		return 1;
+	return 0;
+}
+
+/*
+ * Associate all TUs in obj2mod which refer to the same module with a single
+ * obj2mod entry for emission, preferring to point into the module list in a
+ * multi-module objfile.
+ */
+static void optimize_obj2mod(void)
+{
+	size_t i;
+	size_t n = 0;
+	struct obj2mod_elem *elem;
+	struct obj2mod_elem *dedup;
+	/* An array of all obj2mod_elems, later sorted by hashval.  */
+	struct obj2mod_modhash_elem *uniq;
+	struct obj2mod_modhash_elem *last;
+
+	/*
+	 * Canonicalize all module lists by sorting them, then compute their
+	 * hash values.
+	 */
+	uniq = malloc(sizeof(struct obj2mod_modhash_elem) * num_objfiles);
+	if (uniq == NULL)
+		goto oom;
+
+	for (i = 0; i < OBJ2MOD_N; i++) {
+		for (elem = obj2mod[i]; elem; elem = elem->obj2mod_next) {
+			if (elem->nmods >= 2) {
+				char **sorter;
+				char *walk;
+				char *tmp_mods;
+				size_t j;
+
+				tmp_mods = malloc(elem->mods_size);
+				sorter = malloc(sizeof(char *) * elem->nmods);
+				if (sorter == NULL || tmp_mods == NULL)
+					goto oom;
+				memcpy(tmp_mods, elem->mods, elem->mods_size);
+
+				for (j = 0, walk = tmp_mods; j < elem->nmods;
+				     j++) {
+					sorter[j] = walk;
+					walk += strlen(walk) + 1;
+				}
+				qsort(sorter, elem->nmods, sizeof (char *),
+				      qstrcmp);
+				for (j = 0, walk = elem->mods; j < elem->nmods;
+				     j++) {
+					strcpy(walk, sorter[j]);
+					walk += strlen(walk) + 1;
+				}
+				free(tmp_mods);
+				free(sorter);
+			}
+
+			uniq[n].elem = elem;
+			uniq[n].modhash = memhash(elem->mods, elem->mods_size);
+			n++;
+		}
+	}
+
+	qsort (uniq, num_objfiles, sizeof (struct obj2mod_modhash_elem),
+	       qmodhash);
+
+	/*
+	 * Work over multimodule entries.  These must be emitted into
+	 * .kallsyms_module_names as a unit, but we can still optimize by
+	 * reusing some other identical entry.  Single-file modules are amenable
+	 * to the same optimization, but we avoid doing it for now so that we
+	 * can prefer to point them directly inside a multimodule entry.
+	 */
+	for (i = 0, last = NULL; i < num_objfiles; i++) {
+		const char *onemod;
+		size_t j;
+
+		if (uniq[i].elem->nmods < 2)
+			continue;
+
+		/* Duplicate multimodule.  Reuse the first we saw.  */
+		if (last != NULL && last->modhash == uniq[i].modhash) {
+			uniq[i].elem->xref = last->elem;
+			continue;
+		}
+
+		/*
+		 * Single-module entries relating to modules also emitted as
+		 * part of this multimodule entry can refer to it: later, we
+		 * will hunt down the right specific module name within this
+		 * multimodule entry and point directly to it.
+		 */
+		onemod = uniq[i].elem->mods;
+		for (j = uniq[i].elem->nmods; j > 0; j--) {
+			int h = strhash(onemod) & OBJ2MOD_MASK;
+
+			for (dedup = mod2obj[h]; dedup;
+			     dedup = dedup->mod2obj_next) {
+				if (dedup->nmods > 1)
+					continue;
+
+				if (strcmp(dedup->mods, onemod) != 0)
+					continue;
+				dedup->xref = uniq[i].elem;
+				assert (uniq[i].elem->xref == NULL);
+			}
+			onemod += strlen(onemod) + 1;
+		}
+
+		last = &uniq[i];
+	}
+
+	/*
+	 * Now traverse all single-module entries, xreffing every one that
+	 * relates to a given module to the first one we saw that refers to that
+	 * module.
+	 */
+	for (i = 0, last = NULL; i < num_objfiles; i++) {
+		if (uniq[i].elem->nmods > 1)
+			continue;
+
+		if (uniq[i].elem->xref != NULL)
+			continue;
+
+		/* Duplicate module name.  Reuse the first we saw.  */
+		if (last != NULL && last->modhash == uniq[i].modhash) {
+			uniq[i].elem->xref = last->elem;
+			assert (last->elem->xref == NULL);
+			continue;
+		}
+		last = &uniq[i];
+	}
+	return;
+oom:
+	fprintf(stderr, "kallsyms: out of memory optimizing module list\n");
+	exit(EXIT_FAILURE);
+}
+#endif
 
 static void usage(void)
 {
-	fprintf(stderr, "Usage: kallsyms [--all-symbols] "
-			"[--base-relative] < in.map > out.S\n");
+	fprintf(stderr, "Usage: kallsyms [--all-symbols] [--absolute-percpu] "
+			"[--base-relative] [--builtin=modules_thick.builtin] "
+			"< nm_vmlinux.out > symbols.S\n");
 	exit(1);
 }
 

@@ -94,11 +402,18 @@ static bool is_ignored_symbol(const char *name, char type)
 		"kallsyms_addresses",
 		"kallsyms_offsets",
 		"kallsyms_relative_base",
+		"kallsyms_sizes",
 		"kallsyms_num_syms",
+		"kallsyms_num_modules",
 		"kallsyms_names",
 		"kallsyms_markers",
 		"kallsyms_token_table",
 		"kallsyms_token_index",
+		"kallsyms_module_offsets",
+		"kallsyms_module_addresses",
+		"kallsyms_modules",
+		"kallsyms_module_names",
+		"kallsyms_module_names_len",
 		/* Exclude linker generated symbols which vary between passes */
 		"_SDA_BASE_",		/* ppc */
 		"_SDA2_BASE_",		/* ppc */

@@ -201,10 +516,11 @@ static struct sym_entry *read_symbol(FILE *in)
 	unsigned long long addr;
 	unsigned int len;
 	struct sym_entry *sym;
-	int rc;
+	int rc = 0;
+	unsigned long long size;
 
-	rc = fscanf(in, "%llx %c %499s\n", &addr, &type, name);
-	if (rc != 3) {
+	rc = fscanf(in, "%llx %llx %c %499s\n", &addr, &size, &type, name);
+	if (rc != 4) {
 		if (rc != EOF && fgets(name, 500, in) == NULL)
 			fprintf(stderr, "Read error or end of file.\n");
 		return NULL;

@@ -242,12 +558,13 @@ static struct sym_entry *read_symbol(FILE *in)
 	sym->sym[0] = type;
 	strcpy(sym_name(sym), name);
 	sym->percpu_absolute = 0;
+	sym->size = size;
 
 	return sym;
 }
 
-static int symbol_in_range(const struct sym_entry *s,
-			   const struct addr_range *ranges, int entries)
+static int addr_in_range(unsigned long long addr,
+			 const struct addr_range *ranges, int entries)
 {
 	size_t i;
 	const struct addr_range *ar;

@@ -255,7 +572,7 @@ static int symbol_in_range(const struct sym_entry *s,
 	for (i = 0; i < entries; ++i) {
 		ar = &ranges[i];
 
-		if (s->addr >= ar->start && s->addr <= ar->end)
+		if (addr >= ar->start && addr <= ar->end)
 			return 1;
 	}
 

@@ -269,8 +586,8 @@ static int symbol_valid(const struct sym_entry *s)
 	/* if --all-symbols is not specified, then symbols outside the text
 	 * and inittext sections are discarded */
 	if (!all_symbols) {
-		if (symbol_in_range(s, text_ranges,
-				    ARRAY_SIZE(text_ranges)) == 0)
+		if (addr_in_range(s->addr, text_ranges,
+				  ARRAY_SIZE(text_ranges)) == 0)
 			return 0;
 		/* Corner case.  Discard any symbols with the same value as
 		 * _etext _einittext; they can move between pass 1 and 2 when

@@ -352,6 +669,181 @@ static void output_address(unsigned long long addr)
 		printf("\tPTR\t_text - %#llx\n", _text - addr);
 }
 
+#ifdef CONFIG_KALLMODSYMS
+/* Output the .kallmodsyms_modules symbol content. */
+static void output_kallmodsyms_modules(void)
+{
+	struct obj2mod_elem *elem;
+	size_t offset = 1;
+	size_t i;
+
+	/*
+	 * Traverse and emit, chasing xref and updating mod_offset accordingly.
+	 * Emit a single \0 at the start, to encode non-modular objfiles.
+	 */
+	output_label("kallsyms_module_names");
+	printf("\t.byte\t0\n");
+	for (i = 0; i < OBJ2MOD_N; i++) {
+		for (elem = obj2mod[i]; elem;
+		     elem = elem->obj2mod_next) {
+			const char *onemod;
+			size_t i;
+			struct obj2mod_elem *out_elem = elem;
+
+			if (elem->xref)
+				out_elem = elem->xref;
+			if (out_elem->mod_offset != 0)
+				continue;	/* Already emitted.  */
+
+			out_elem->mod_offset = offset;
+			onemod = out_elem->mods;
+
+			/*
+			 * Technically this is a waste of space: we could just
+			 * as well implement multimodule entries by pointing one
+			 * byte further back, to the trailing \0 of the previous
+			 * entry, but doing it this way makes it more obvious
+			 * when an entry is a multimodule entry.
+			 */
+			if (out_elem->nmods != 1) {
+				printf("\t.byte\t0\n");
+				printf("\t.byte\t%zi\n", out_elem->nmods);
+				offset += 2;
+			}
+
+			for (i = out_elem->nmods; i > 0; i--) {
+				printf("\t.asciz\t\"%s\"\n", onemod);
+				offset += strlen(onemod) + 1;
+				onemod += strlen(onemod) + 1;
+			}
+		}
+	}
+	printf("\n");
+	output_label("kallsyms_module_names_len");
+	printf("\t.long\t%zi\n", offset);
+}
+
+static void output_kallmodsyms_objfiles(void)
+{
+	size_t i = 0;
+	size_t emitted_offsets = 0;
+	size_t emitted_objfiles = 0;
+
+	if (base_relative)
+		output_label("kallsyms_module_offsets");
+	else
+		output_label("kallsyms_module_addresses");
+
+	for (i = 0; i < addrmap_num; i++) {
+		long long offset;
+		int overflow;
+
+                /*
+                 * Fuse consecutive address ranges citing the same object file
+                 * into one.
+                 */
+                if (i > 0 && addrmap[i-1].objfile == addrmap[i].objfile)
+                        continue;
+
+		if (base_relative) {
+			if (!absolute_percpu) {
+				offset = addrmap[i].addr - relative_base;
+				overflow = (offset < 0 || offset > UINT_MAX);
+			} else {
+				offset = relative_base - addrmap[i].addr - 1;
+				overflow = (offset < INT_MIN || offset >= 0);
+			}
+			if (overflow) {
+				fprintf(stderr, "kallsyms failure: "
+					"objfile %s at address %#llx out of range in relative mode\n",
+					addrmap[i].objfile ? addrmap[i].objfile->obj :
+					"in always-built-in object", table[i]->addr);
+				exit(EXIT_FAILURE);
+			}
+			printf("\t.long\t0x%x\n", (int)offset);
+		} else
+			printf("\tPTR\t%#llx\n", addrmap[i].addr);
+		emitted_offsets++;
+	}
+
+	output_label("kallsyms_modules");
+
+	for (i = 0; i < addrmap_num; i++) {
+		struct obj2mod_elem *elem = addrmap[i].objfile;
+		int orig_nmods;
+		const char *orig_modname;
+		int mod_offset;
+
+		if (i > 0 && addrmap[i-1].objfile == addrmap[i].objfile)
+			continue;
+
+		/*
+		 * Address range cites no object file: point at 0, the built-in
+		 * module.
+		 */
+		if (addrmap[i].objfile == NULL) {
+			printf("\t.long\t0x0\n");
+			emitted_objfiles++;
+			continue;
+		}
+
+		orig_nmods = elem->nmods;
+		orig_modname = elem->mods;
+
+		/*
+		 * Chase down xrefs, if need be.  There can only be one layer of
+		 * these: from single-module entry to other single-module entry,
+		 * or from single- or multi-module entry to another multi-module
+		 * entry.  Single -> single and multi -> multi always points at
+		 * the start of the xref target, so its offset can be used as is.
+		 */ 
+		if (elem->xref)
+			elem = elem->xref;
+
+		if (elem->nmods == 1 || orig_nmods > 1)
+			mod_offset = elem->mod_offset;
+		else {
+			/*
+			 * If this is a reference from a single-module entry to
+			 * a multi-module entry, hunt down the offset to this
+			 * specific module's name (which is guaranteed to be
+			 * present: see optimize_obj2mod).
+			 */
+
+			size_t j = elem->nmods;
+			const char *onemod = elem->mods;
+			mod_offset = elem->mod_offset;
+
+			for (; j > 0; j--) {
+				if (strcmp(orig_modname, onemod) == 0)
+					break;
+				onemod += strlen(onemod) + 1;
+			}
+			assert (j > 0);
+			/*
+			 * +2 to skip the null byte and count at the start of
+			 * the multimodule entry.
+			 */
+			mod_offset += onemod - elem->mods + 2;
+		}
+
+		/*
+		 * Zero offset is the initial \0, there to catch uninitialized
+		 * obj2mod entries, and is forbidden.
+		 */
+		assert (mod_offset != 0);
+
+		printf("\t.long\t0x%x\n", mod_offset);
+		emitted_objfiles++;
+	}
+
+	assert (emitted_offsets == emitted_objfiles);
+	output_label("kallsyms_num_modules");
+	printf("\t.long\t%zi\n", emitted_objfiles);
+	printf("\n");
+}
+#endif /* CONFIG_KALLMODSYMS */
+
 /* uncompress a compressed symbol. When this function is called, the best table
  * might still be compressed itself, so the function needs to be recursive */
 static int expand_symbol(const unsigned char *data, int len, char *result)

@@ -451,6 +943,16 @@ static void write_src(void)
 		printf("\n");
 	}
 
+	output_label("kallsyms_sizes");
+	for (i = 0; i < table_cnt; i++)
+		printf("\tPTR\t%#llx\n", table[i]->size);
+	printf("\n");
+
+#ifdef CONFIG_KALLMODSYMS
+	output_kallmodsyms_modules();
+	output_kallmodsyms_objfiles();
+#endif
+
 	output_label("kallsyms_num_syms");
 	printf("\t.long\t%u\n", table_cnt);
 	printf("\n");

@@ -502,7 +1004,6 @@ static void write_src(void)
 	printf("\n");
 }
 
-
 /* table lookup compression functions */
 
 /* count all the possible tokens in a symbol */

@@ -703,6 +1204,18 @@ static int compare_symbols(const void *a, const void *b)
 	if (sa->addr < sb->addr)
 		return -1;
 
+	/* zero-size markers before nonzero-size symbols */
+	if (sa->size > 0 && sb->size == 0)
+		return 1;
+	if (sa->size == 0 && sb->size > 0)
+		return -1;
+
+	/* sort by size (large size preceding symbols it encompasses) */
+	if (sa->size < sb->size)
+		return 1;
+	if (sa->size > sb->size)
+		return -1;
+
 	/* sort by "weakness" type */
 	wa = (sa->sym[0] == 'w') || (sa->sym[0] == 'W');
 	wb = (sb->sym[0] == 'w') || (sb->sym[0] == 'W');

@@ -735,7 +1248,7 @@ static void make_percpus_absolute(void)
 	unsigned int i;
 
 	for (i = 0; i < table_cnt; i++)
-		if (symbol_in_range(table[i], &percpu_range, 1)) {
+		if (addr_in_range(table[i]->addr, &percpu_range, 1)) {
 			/*
 			 * Keep the 'A' override for percpu symbols to
 			 * ensure consistent behavior compared to older

@@ -762,17 +1275,125 @@ static void record_relative_base(void)
 		}
 }
 
+#ifdef CONFIG_KALLMODSYMS
+/*
+ * Read the linker map.
+ */
+static void read_linker_map(void)
+{
+	unsigned long long addr, size;
+	char obj[PATH_MAX+1];
+	FILE *f = fopen(".tmp_vmlinux.ranges", "r");
+
+	if (!f) {
+		fprintf(stderr, "Cannot open '.tmp_vmlinux.ranges'.\n");
+		exit(1);
+	}
+
+	addrmap_num = 0;
+	addrmap_alloced = 4096;
+	addrmap = malloc(sizeof(*addrmap) * addrmap_alloced);
+	if (!addrmap)
+		goto oom;
+
+	/*
+	 * For each address range, add to addrmap the address and the objfile
+	 * entry to which the range maps.  Only add entries relating to text
+	 * ranges.  (We assume that the text ranges are tightly packed, because
+	 * in any reasonable object file format they will be, so we can ignore
+	 * the size.)
+	 *
+	 * Ranges that do not correspond to a built-in module, but to an
+	 * always-built-in object file, have no obj2mod_elem and point at NULL
+	 * instead.
+	 */
+
+	while (fscanf(f, "%llx %llx %s\n", &addr, &size, obj) == 3) {
+		struct obj2mod_elem *elem = obj2mod_get(obj);
+
+		if (addr == 0 || size == 0 ||
+		    !addr_in_range(addr, text_ranges, ARRAY_SIZE(text_ranges)))
+			continue;
+
+		if (addrmap_num >= addrmap_alloced) {
+			addrmap_alloced *= 2;
+			addrmap = realloc(addrmap,
+			    sizeof(*addrmap) * addrmap_alloced);
+			if (!addrmap)
+				goto oom;
+		}
+
+                addrmap[addrmap_num].addr = addr;
+                addrmap[addrmap_num].objfile = elem;
+		addrmap_num++;
+	}
+	fclose(f);
+	return;
+
+oom:
+	fprintf(stderr, "kallsyms: out of memory\n");
+	exit(1);
+}
+
+/*
+ * Read "modules_thick.builtin" (the list of built-in modules).  Construct the
+ * obj2mod hash to track objfile -> module mappings.  Read ".tmp_vmlinux.ranges"
+ * (the linker map) and build addrmap[], which maps address ranges to built-in
+ * module names (using obj2mod).
+ */
+static void read_modules(const char *modules_builtin)
+{
+	struct modules_thick_iter *i;
+	char *module_name = NULL;
+	char **module_paths;
+
+	obj2mod_init();
+	/*
+	 * Iterate over all modules in modules_thick.builtin and add each.
+	 */
+	i = modules_thick_iter_new(modules_builtin);
+	if (i == NULL) {
+		fprintf(stderr, "Cannot iterate over builtin modules.\n");
+		exit(1);
+	}
+
+	while ((module_paths = modules_thick_iter_next(i, &module_name))) {
+		char **walk = module_paths;
+		while (*walk) {
+			obj2mod_add(*walk, module_name);
+			walk++;
+		}
+		free(module_paths);
+	}
+
+	free(module_name);
+	modules_thick_iter_free(i);
+	optimize_obj2mod();
+
+	/*
+	 * Read linker map.
+	 */
+	read_linker_map();
+}
+#else
+static void read_modules(const char *unused) {}
+#endif /* CONFIG_KALLMODSYMS */
+
 int main(int argc, char **argv)
 {
+	const char *modules_builtin = "modules_thick.builtin";
+
 	if (argc >= 2) {
 		int i;
 		for (i = 1; i < argc; i++) {
-			if(strcmp(argv[i], "--all-symbols") == 0)
+			if (strcmp(argv[i], "--all-symbols") == 0)
 				all_symbols = 1;
 			else if (strcmp(argv[i], "--absolute-percpu") == 0)
 				absolute_percpu = 1;
 			else if (strcmp(argv[i], "--base-relative") == 0)
 				base_relative = 1;
+			else if (strncmp(argv[i], "--builtin=", 10) == 0)
+				modules_builtin = &argv[i][10];
 			else
 				usage();
 		}

@@ -780,6 +1401,7 @@ int main(int argc, char **argv)
 		usage();
 
 	read_map(stdin);
+	read_modules(modules_builtin);
 	shrink_table();
 	if (absolute_percpu)
 		make_percpus_absolute();

@@ -725,6 +725,25 @@ static struct conf_printer header_printer_cb =
 	.print_comment = header_print_comment,
 };
 
+/*
+ * Tristate printer
+ *
+ * This printer is used when generating the `include/config/tristate.conf' file.
+ */
+static void
+tristate_print_symbol(FILE *fp, struct symbol *sym, const char *value, void *arg)
+{
+
+       if (sym->type == S_TRISTATE && *value != 'n')
+	       fprintf(fp, "%s%s=%c\n", CONFIG_, sym->name, (char)toupper(*value));
+}
+
+static struct conf_printer tristate_printer_cb =
+{
+       .print_symbol = tristate_print_symbol,
+       .print_comment = kconfig_print_comment,
+};
+
 static void conf_write_symbol(FILE *fp, struct symbol *sym,
 			      struct conf_printer *printer, void *printer_arg)
 {

@@ -1058,7 +1077,7 @@ int conf_write_autoconf(int overwrite)
 	struct symbol *sym;
 	const char *name;
 	const char *autoconf_name = conf_get_autoconfig_name();
-	FILE *out, *out_h;
+	FILE *out, *tristate, *out_h;
 	int i;
 
 	if (!overwrite && is_present(autoconf_name))

@@ -1073,6 +1092,13 @@ int conf_write_autoconf(int overwrite)
 	if (!out)
 		return 1;
 
+	tristate = fopen(".tmpconfig_tristate", "w");
+	if (!tristate) {
+		fclose(out);
+		fclose(tristate);
+		return 1;
+	}
+
 	out_h = fopen(".tmpconfig.h", "w");
 	if (!out_h) {
 		fclose(out);

@@ -1080,6 +1106,7 @@ int conf_write_autoconf(int overwrite)
 	}
 
 	conf_write_heading(out, &kconfig_printer_cb, NULL);
+	conf_write_heading(tristate, &tristate_printer_cb, NULL);
 	conf_write_heading(out_h, &header_printer_cb, NULL);
 
 	for_all_symbols(i, sym) {

@@ -1087,11 +1114,13 @@ int conf_write_autoconf(int overwrite)
 		if (!(sym->flags & SYMBOL_WRITE) || !sym->name)
 			continue;
 
-		/* write symbols to auto.conf and autoconf.h */
+		/* write symbols to auto.conf, tristate and autoconf.h */
 		conf_write_symbol(out, sym, &kconfig_printer_cb, (void *)1);
+		conf_write_symbol(tristate, sym, &tristate_printer_cb, (void *)1);
 		conf_write_symbol(out_h, sym, &header_printer_cb, NULL);
 	}
 	fclose(out);
+	fclose(tristate);
 	fclose(out_h);
 
 	name = getenv("KCONFIG_AUTOHEADER");

@@ -1102,6 +1131,14 @@ int conf_write_autoconf(int overwrite)
 	if (rename(".tmpconfig.h", name))
 		return 1;
 
+	name = getenv("KCONFIG_TRISTATE");
+	if (!name)
+		name = "include/config/tristate.conf";
+	if (make_parent_dir(name))
+		return 1;
+	if (rename(".tmpconfig_tristate", name))
+		return 1;
+	
 	if (make_parent_dir(autoconf_name))
 		return 1;
 	/*

@@ -178,6 +178,7 @@ vmlinux_link()
 			objects="--whole-archive		\
 				vmlinux.o 			\
 				--no-whole-archive		\
+				-Map=.tmp_vmlinux.map		\
 				${@}"
 		else
 			objects="--whole-archive		\

@@ -186,6 +187,7 @@ vmlinux_link()
 				--start-group			\
 				${KBUILD_VMLINUX_LIBS}		\
 				--end-group			\
+				-Map=.tmp_vmlinux.map		\
 				${@}"
 		fi
 

@@ -201,6 +203,7 @@ vmlinux_link()
 			-Wl,--start-group			\
 			${KBUILD_VMLINUX_LIBS}			\
 			-Wl,--end-group				\
+			-Wl,-Map=.tmp_vmlinux.map		\
 			${@}"
 
 		${CC} ${CFLAGS_vmlinux}				\

@@ -259,6 +262,19 @@ kallsyms()
 {
 	local kallsymopt;
 
+	# read the linker map to identify ranges of addresses:
+	#   - for each *.o file, report address, size, pathname
+	#       - most such lines will have four fields
+	#       - but sometimes there is a line break after the first field
+	#   - start reading at "Linker script and memory map"
+	#   - stop reading at ".brk"
+	${AWK} '
+	    /\.o$/ && start==1 { print $(NF-2), $(NF-1), $NF }
+	    /^Linker script and memory map/ { start = 1 }
+	    /^\.brk/ { exit(0) }
+	' .tmp_vmlinux.map | sort > .tmp_vmlinux.ranges
+
+	# get kallsyms options
 	if [ -n "${CONFIG_KALLSYMS_ALL}" ]; then
 		kallsymopt="${kallsymopt} --all-symbols"
 	fi

@@ -272,7 +288,12 @@ kallsyms()
 	fi
 
 	info KSYMS ${2}
-	${NM} -n ${1} | scripts/kallsyms ${kallsymopt} > ${2}
+	# "nm -S" does not print symbol size when size is 0
+	# Therefore use awk to regularize the data:
+	#   - when there are only three fields, add an explicit "0"
+	#   - when there are already four fields, pass through as is
+	${NM} -n -S ${1} | ${AWK} 'NF==3 {print $1, 0, $2, $3}; NF==4' | \
+	    scripts/kallsyms ${kallsymopt} > ${2}
 }
 
 # Perform one step in kallsyms generation, including temporary linking of

@@ -0,0 +1,200 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A simple modules_thick reader.
+ *
+ * (C) 2014, 2021 Oracle, Inc.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <errno.h>
+#include <stdio.h>
+#include <stdlib.h>
+#include <string.h>
+
+#include "modules_thick.h"
+
+/*
+ * Read a modules_thick.builtin file and translate it into a stream of
+ * name / module-name pairs.
+ */
+
+/*
+ * Construct a modules_thick.builtin iterator.
+ */
+struct modules_thick_iter *
+modules_thick_iter_new(const char *modules_thick_file)
+{
+	struct modules_thick_iter *i;
+
+	i = calloc(1, sizeof(struct modules_thick_iter));
+	if (i == NULL)
+		return NULL;
+
+	i->f = fopen(modules_thick_file, "r");
+
+	if (i->f == NULL) {
+		fprintf(stderr, "Cannot open builtin module file %s: %s\n",
+			modules_thick_file, strerror(errno));
+		return NULL;
+	}
+
+	return i;
+}
+
+/*
+ * Iterate, returning a new null-terminated array of object file names, and a
+ * new dynamically-allocated module name.  (The module name passed in is freed.)
+ *
+ * The array of object file names should be freed by the caller: the strings it
+ * points to are owned by the iterator, and should not be freed.
+ */
+
+char ** __attribute__((__nonnull__))
+modules_thick_iter_next(struct modules_thick_iter *i, char **module_name)
+{
+	size_t npaths = 1;
+	char **module_paths;
+	char *last_slash;
+	char *last_dot;
+	char *trailing_linefeed;
+	char *object_name = i->line;
+	char *dash;
+	int composite = 0;
+
+	/*
+	 * Read in all module entries, computing the suffixless, pathless name
+	 * of the module and building the next arrayful of object file names for
+	 * return.
+	 *
+	 * Modules can consist of multiple files: in this case, the portion
+	 * before the colon is the path to the module (as before): the portion
+	 * after the colon is a space-separated list of files that should be
+	 * considered part of this module.  In this case, the portion before the
+	 * name is an "object file" that does not actually exist: it is merged
+	 * into built-in.a without ever being written out.
+	 *
+	 * All module names have - translated to _, to match what is done to the
+	 * names of the same things when built as modules.
+	 */
+
+	/*
+	 * Reinvocation of exhausted iterator. Return NULL, once.
+	 */
+retry:
+	if (getline(&i->line, &i->line_size, i->f) < 0) {
+		if (ferror(i->f)) {
+			fprintf(stderr, "Error reading from modules_thick file:"
+				" %s\n", strerror(errno));
+			exit(1);
+		}
+		rewind(i->f);
+		return NULL;
+	}
+
+	if (i->line[0] == '\0')
+		goto retry;
+
+	/*
+	 * Slice the line in two at the colon, if any.  If there is anything
+	 * past the ': ', this is a composite module.  (We allow for no colon
+	 * for robustness, even though one should always be present.)
+	 */
+	if (strchr(i->line, ':') != NULL) {
+		char *name_start;
+
+		object_name = strchr(i->line, ':');
+		*object_name = '\0';
+		object_name++;
+		name_start = object_name + strspn(object_name, " \n");
+		if (*name_start != '\0') {
+			composite = 1;
+			object_name = name_start;
+		}
+	}
+
+	/*
+	 * Figure out the module name.
+	 */
+	last_slash = strrchr(i->line, '/');
+	last_slash = (!last_slash) ? i->line :
+		last_slash + 1;
+	free(*module_name);
+	*module_name = strdup(last_slash);
+	dash = *module_name;
+
+	while (dash != NULL) {
+		dash = strchr(dash, '-');
+		if (dash != NULL)
+			*dash = '_';
+	}
+
+	last_dot = strrchr(*module_name, '.');
+	if (last_dot != NULL)
+		*last_dot = '\0';
+
+	trailing_linefeed = strchr(object_name, '\n');
+	if (trailing_linefeed != NULL)
+		*trailing_linefeed = '\0';
+
+	/*
+	 * Multifile separator? Object file names explicitly stated:
+	 * slice them up and shuffle them in.
+	 *
+	 * The array size may be an overestimate if any object file
+	 * names start or end with spaces (very unlikely) but cannot be
+	 * an underestimate.  (Check for it anyway.)
+	 */
+	if (composite) {
+		char *one_object;
+
+		for (npaths = 0, one_object = object_name;
+		     one_object != NULL;
+		     npaths++, one_object = strchr(one_object + 1, ' '));
+	}
+
+	module_paths = malloc((npaths + 1) * sizeof(char *));
+	if (!module_paths) {
+		fprintf(stderr, "%s: out of memory on module %s\n", __func__,
+			*module_name);
+		exit(1);
+	}
+
+	if (composite) {
+		char *one_object;
+		size_t i = 0;
+
+		while ((one_object = strsep(&object_name, " ")) != NULL) {
+			if (i >= npaths) {
+				fprintf(stderr, "%s: num_objs overflow on module "
+					"%s: this is a bug.\n", __func__,
+					*module_name);
+				exit(1);
+			}
+
+			module_paths[i++] = one_object;
+		}
+	} else
+		module_paths[0] = i->line;	/* untransformed module name */
+
+	module_paths[npaths] = NULL;
+
+	return module_paths;
+}
+
+/*
+ * Free an iterator. Can be called while iteration is underway, so even
+ * state that is freed at the end of iteration must be freed here too.
+ */
+void
+modules_thick_iter_free(struct modules_thick_iter *i)
+{
+	if (i == NULL)
+		return;
+	fclose(i->f);
+	free(i->line);
+	free(i);
+}

@@ -0,0 +1,48 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * A simple modules_thick reader.
+ *
+ * (C) 2014, 2021 Oracle, Inc.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _LINUX_MODULES_THICK_H
+#define _LINUX_MODULES_THICK_H
+
+#include <stdio.h>
+#include <stddef.h>
+
+/*
+ * modules_thick.builtin iteration state.
+ */
+struct modules_thick_iter {
+	FILE *f;
+	char *line;
+	size_t line_size;
+};
+
+/*
+ * Construct a modules_thick.builtin iterator.
+ */
+struct modules_thick_iter *
+modules_thick_iter_new(const char *modules_thick_file);
+
+/*
+ * Iterate, returning a new null-terminated array of object file names, and a
+ * new dynamically-allocated module name.  (The module name passed in is freed.)
+ *
+ * The array of object file names should be freed by the caller: the strings it
+ * points to are owned by the iterator, and should not be freed.
+ */
+
+char ** __attribute__((__nonnull__))
+modules_thick_iter_next(struct modules_thick_iter *i, char **module_name);
+
+void
+modules_thick_iter_free(struct modules_thick_iter *i);
+
+#endif