[PATCH RFC] symbols: check table sizes don't change between linking passes 2 and 3

[Jan Beulich <jbeulich@suse.com>]

While sizes (and possibly positions) of the symbol table related symbols
(and as a result other ones) are expected to change from linking pass 1
to pass 2, no such change should happen anymore from pass 2 to pass 3, or
else the internally recorded symbol table wouldn't represent the ELF or
PE/COFF ones.

For comparing to be actually useful, i.e. most notably also covering the
last of the arrays emitted, symbol sizes need establishing. Make use of
the xen/linkage.h machinery to achieve that.

Suggested-by: Roger Pau Monné <roger.pau@citrix.com>
Signed-off-by: Jan Beulich <jbeulich@suse.com>
---
Likely other ports also want to add such checking. Really it would be nice
if we could properly abstract out shared parts of the linking steps.

RFC: Aiui this can't go in as is right now, or we would break building Xen
     with lld. Further changes are first needed to help the situation
     there.

RFC: I'm all ears towards improvement suggestions in the temporary helper
     file handling of compare-symbol-tables. Or ideally some approach to
     avoid the use of a helper file altogether.

--- a/xen/arch/x86/Makefile
+++ b/xen/arch/x86/Makefile
@@ -146,6 +146,7 @@ $(TARGET)-syms: $(objtree)/prelink.o $(o
 		| $(objtree)/tools/symbols $(all_symbols) --sysv --sort $(syms-warn-dup-y) \
 		> $(dot-target).1.S
 	$(MAKE) $(build)=$(@D) $(dot-target).1.o
+	$(call compare-symbol-tables, $(dot-target).0.o, $(dot-target).1.o)
 	$(LD) $(XEN_LDFLAGS) -T $(obj)/xen.lds $< $(build_id_linker) \
 	    $(orphan-handling-y) $(dot-target).1.o -o $@
 	$(NM) -pa --format=sysv $@ \
@@ -226,6 +227,8 @@ endif
 		| $(objtree)/tools/symbols $(all_symbols) --sysv --sort \
 		> $(dot-target).1s.S
 	$(MAKE) $(build)=$(@D) .$(@F).1r.o .$(@F).1s.o
+	$(call compare-symbol-tables, $(dot-target).0r.o, $(dot-target).1r.o)
+	$(call compare-symbol-tables, $(dot-target).0s.o, $(dot-target).1s.o)
 	$(LD) $(call EFI_LDFLAGS,$(VIRT_BASE)) -T $(obj)/efi.lds $< \
 	      $(dot-target).1r.o $(dot-target).1s.o $(orphan-handling-y) \
 	      $(note_file_option) -o $@
--- a/xen/scripts/Kbuild.include
+++ b/xen/scripts/Kbuild.include
@@ -56,6 +56,19 @@ define filechk
 	fi
 endef
 
+###
+# Compare the symbol tables of two object files.  As diff's -I option isn't
+# standardized, the name difference of the two object files needs abstracting
+# out.
+define compare-symbol-tables
+    ln -f $(1) $(@D)/.cst.$$$$; \
+    $(OBJDUMP) -t $(@D)/.cst.$$$$ > $(1).sym; \
+    ln -f $(1) $(@D)/.cst.$$$$; \
+    $(OBJDUMP) -t $(@D)/.cst.$$$$ > $(2).sym; \
+    rm -f $(@D)/.cst.$$$$
+    diff -u $(1).sym $(2).sym
+endef
+
 # as-insn: Check whether assembler supports an instruction.
 # Usage: cflags-y += $(call as-insn,CC FLAGS,"insn",option-yes,option-no)
 as-insn = $(if $(shell echo 'void _(void) { asm volatile ( $(2) ); }' \
--- a/xen/tools/symbols.c
+++ b/xen/tools/symbols.c
@@ -253,17 +253,26 @@ static void read_map(FILE *in)
 	}
 }
 
-static void output_label(char *label)
+static void output_label(const char *label, bool keep)
 {
-	if (symbol_prefix_char)
-		printf(".globl %c%s\n", symbol_prefix_char, label);
-	else
-		printf(".globl %s\n", label);
-	printf("\tALGN\n");
-	if (symbol_prefix_char)
-		printf("%c%s:\n", symbol_prefix_char, label);
-	else
-		printf("%s:\n", label);
+	static bool pending;
+
+	if (pending && !keep) {
+		printf("END(CURRENT)\n");
+		printf("#undef CURRENT\n\n");
+	}
+
+	pending = label;
+	if (!label)
+		return;
+
+	if (symbol_prefix_char) {
+		printf("DATA(%c%s, ALGN)\n", symbol_prefix_char, label);
+		printf("#define CURRENT %c%s\n", symbol_prefix_char, label);
+	} else {
+		printf("DATA(%s, ALGN)\n", label);
+		printf("#define CURRENT %s\n", label);
+	}
 }
 
 /* uncompress a compressed symbol. When this function is called, the best table
@@ -331,22 +340,22 @@ static void write_src(void)
 
 		return;
 	}
-	printf("#include <xen/config.h>\n");
+	printf("#include <xen/linkage.h>\n");
 	printf("#if BITS_PER_LONG == 64 && !defined(SYMBOLS_ORIGIN)\n");
 	printf("#define PTR .quad\n");
-	printf("#define ALGN .balign 8\n");
+	printf("#define ALGN 8\n");
 	printf("#else\n");
 	printf("#define PTR .long\n");
-	printf("#define ALGN .balign 4\n");
+	printf("#define ALGN 4\n");
 	printf("#endif\n");
 
 	printf("\t.section .rodata, \"a\"\n");
 
 	printf("#ifndef SYMBOLS_ORIGIN\n");
 	printf("#define SYMBOLS_ORIGIN 0\n");
-	output_label("symbols_addresses");
+	output_label("symbols_addresses", false);
 	printf("#else\n");
-	output_label("symbols_offsets");
+	output_label("symbols_offsets", true);
 	printf("#endif\n");
 	for (i = 0, ends = 0; i < table_cnt; i++) {
 		printf("\tPTR\t%#llx - SYMBOLS_ORIGIN\n", table[i].addr);
@@ -370,17 +379,15 @@ static void write_src(void)
 		printf("\tPTR\t%#llx - SYMBOLS_ORIGIN\n",
 		       table[i].addr + table[i].size);
 	}
-	printf("\n");
 
-	output_label("symbols_num_addrs");
+	output_label("symbols_num_addrs", false);
 	printf("\t.long\t%d\n", table_cnt + ends);
-	printf("\n");
 
 	/* table of offset markers, that give the offset in the compressed stream
 	 * every 256 symbols */
 	markers = malloc(sizeof(*markers) * ((table_cnt + ends + 255) >> 8));
 
-	output_label("symbols_names");
+	output_label("symbols_names", false);
 	for (i = 0, off = 0, ends = 0; i < table_cnt; i++) {
 		if (((i + ends) & 0xFF) == 0)
 			markers[(i + ends) >> 8] = off;
@@ -404,15 +411,12 @@ static void write_src(void)
 		printf("\t.byte 0\n");
 		++off;
 	}
-	printf("\n");
 
-	output_label("symbols_markers");
+	output_label("symbols_markers", false);
 	for (i = 0; i < ((table_cnt + ends + 255) >> 8); i++)
 		printf("\t.long\t%d\n", markers[i]);
-	printf("\n");
 
-
-	output_label("symbols_token_table");
+	output_label("symbols_token_table", false);
 	off = 0;
 	for (i = 0; i < 256; i++) {
 		best_idx[i] = off;
@@ -420,34 +424,27 @@ static void write_src(void)
 		printf("\t.asciz\t\"%s\"\n", buf);
 		off += strlen(buf) + 1;
 	}
-	printf("\n");
 
-	output_label("symbols_token_index");
+	output_label("symbols_token_index", false);
 	for (i = 0; i < 256; i++)
 		printf("\t.short\t%d\n", best_idx[i]);
-	printf("\n");
 
-	if (!sort_by_name) {
-		free(markers);
-		return;
-	}
-
-	output_label("symbols_num_names");
-	printf("\t.long\t%d\n", table_cnt);
-	printf("\n");
-
-	/* Sorted by original symbol names and type. */
-	qsort(table, table_cnt, sizeof(*table), compare_name_orig);
-
-	output_label("symbols_sorted_offsets");
-	/* A fixed sized array with two entries: offset in the
-	 * compressed stream (for symbol name), and offset in
-	 * symbols_addresses (or symbols_offset). */
-	for (i = 0; i < table_cnt; i++) {
-		printf("\t.long %u, %u\n", table[i].stream_offset, table[i].addr_idx);
+	if (sort_by_name) {
+		output_label("symbols_num_names", false);
+		printf("\t.long\t%d\n", table_cnt);
+
+		/* Sorted by original symbol names and type. */
+		qsort(table, table_cnt, sizeof(*table), compare_name_orig);
+
+		/* A fixed sized array with two entries: offset in the
+		 * compressed stream (for symbol name), and offset in
+		 * symbols_addresses (or symbols_offset). */
+		output_label("symbols_sorted_offsets", false);
+		for (i = 0; i < table_cnt; i++)
+			printf("\t.long %u, %u\n", table[i].stream_offset, table[i].addr_idx);
 	}
-	printf("\n");
 
+	output_label(NULL, false);
 	free(markers);
 }