[PATCH] modpost: support arbitrary symbol length in modversion

[Gary Guo <gary@garyguo.net>]

Currently modversion uses a fixed size array of size (64 - sizeof(long))
to store symbol names, thus placing a hard limit on length of symbols.
Rust symbols (which encodes crate and module names) can be quite a bit
longer. The length limit in kallsyms is increased to 512 for this reason.

It's a waste of space to simply expand the fixed array size to 512 in
modversion info entries. I therefore make it variably sized, with offset
to the next entry indicated by the initial "next" field.

In addition to supporting longer-than-56/60 byte symbols, this patch also
reduce the size for short symbols by getting rid of excessive 0 paddings.
There are still some zero paddings to ensure "next" and "crc" fields are
properly aligned.

This patch does have a tiny drawback that it makes ".mod.c" files generated
a bit less easy to read, as code like

	"\x08\x00\x00\x00\x78\x56\x34\x12"
	"symbol\0\0"

is generated as opposed to

	{ 0x12345678, "symbol" },

because the structure is now variable-length. But hopefully nobody reads
the generated file :)

Link: b8a94bfb3395 ("kallsyms: increase maximum kernel symbol length to 512")
Link: https://github.com/Rust-for-Linux/linux/pull/379

Signed-off-by: Gary Guo <gary@garyguo.net>
---
 arch/powerpc/kernel/module_64.c |  3 ++-
 include/linux/module.h          |  6 ++++--
 kernel/module/version.c         | 21 +++++++++------------
 scripts/export_report.pl        |  9 +++++----
 scripts/mod/modpost.c           | 33 +++++++++++++++++++++++----------
 5 files changed, 43 insertions(+), 29 deletions(-)

diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c
index ff045644f13f..eac23c11d579 100644
--- a/arch/powerpc/kernel/module_64.c
+++ b/arch/powerpc/kernel/module_64.c
@@ -236,10 +236,11 @@ static void dedotify_versions(struct modversion_info *vers,
 {
 	struct modversion_info *end;
 
-	for (end = (void *)vers + size; vers < end; vers++)
+	for (end = (void *)vers + size; vers < end; vers = (void *)vers + vers->next) {
 		if (vers->name[0] == '.') {
 			memmove(vers->name, vers->name+1, strlen(vers->name));
 		}
+	}
 }
 
 /*
diff --git a/include/linux/module.h b/include/linux/module.h
index 8c5909c0076c..37cb25af9099 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -34,8 +34,10 @@
 #define MODULE_NAME_LEN MAX_PARAM_PREFIX_LEN
 
 struct modversion_info {
-	unsigned long crc;
-	char name[MODULE_NAME_LEN];
+	/* Offset of the next modversion entry in relation to this one. */
+	u32 next;
+	u32 crc;
+	char name[0];
 };
 
 struct module;
diff --git a/kernel/module/version.c b/kernel/module/version.c
index 53f43ac5a73e..af7478dcc158 100644
--- a/kernel/module/version.c
+++ b/kernel/module/version.c
@@ -17,32 +17,29 @@ int check_version(const struct load_info *info,
 {
 	Elf_Shdr *sechdrs = info->sechdrs;
 	unsigned int versindex = info->index.vers;
-	unsigned int i, num_versions;
-	struct modversion_info *versions;
+	struct modversion_info *versions, *end;
+	u32 crcval;
 
 	/* Exporting module didn't supply crcs?  OK, we're already tainted. */
 	if (!crc)
 		return 1;
+	crcval = *crc;
 
 	/* No versions at all?  modprobe --force does this. */
 	if (versindex == 0)
 		return try_to_force_load(mod, symname) == 0;
 
 	versions = (void *)sechdrs[versindex].sh_addr;
-	num_versions = sechdrs[versindex].sh_size
-		/ sizeof(struct modversion_info);
+	end = (void *)versions + sechdrs[versindex].sh_size;
 
-	for (i = 0; i < num_versions; i++) {
-		u32 crcval;
-
-		if (strcmp(versions[i].name, symname) != 0)
+	for (; versions < end; versions = (void *)versions + versions->next) {
+		if (strcmp(versions->name, symname) != 0)
 			continue;
 
-		crcval = *crc;
-		if (versions[i].crc == crcval)
+		if (versions->crc == crcval)
 			return 1;
-		pr_debug("Found checksum %X vs module %lX\n",
-			 crcval, versions[i].crc);
+		pr_debug("Found checksum %X vs module %X\n",
+			 crcval, versions->crc);
 		goto bad_version;
 	}
 
diff --git a/scripts/export_report.pl b/scripts/export_report.pl
index feb3d5542a62..1117646f3141 100755
--- a/scripts/export_report.pl
+++ b/scripts/export_report.pl
@@ -116,18 +116,19 @@ foreach my $thismod (@allcfiles) {
 	while ( <$module> ) {
 		chomp;
 		if ($state == 0) {
-			$state = 1 if ($_ =~ /static const struct modversion_info/);
+			$state = 1 if ($_ =~ /static const char ____versions/);
 			next;
 		}
 		if ($state == 1) {
-			$state = 2 if ($_ =~ /__attribute__\(\(section\("__versions"\)\)\)/);
+			$state = 2 if ($_ =~ /__used __section\("__versions"\)/);
 			next;
 		}
 		if ($state == 2) {
-			if ( $_ !~ /0x[0-9a-f]+,/ ) {
+			if ( $_ !~ /\\0"/ ) {
+				last if ($_ =~ /;/);
 				next;
 			}
-			my $sym = (split /([,"])/,)[4];
+			my $sym = (split /(["\\])/,)[2];
 			my ($module, $value, $symbol, $gpl) = @{$SYMBOL{$sym}};
 			$SYMBOL{ $sym } =  [ $module, $value+1, $symbol, $gpl];
 			push(@{$MODULE{$thismod}} , $sym);
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index efff8078e395..334d170de31f 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -2046,13 +2046,17 @@ static void add_exported_symbols(struct buffer *buf, struct module *mod)
 static void add_versions(struct buffer *b, struct module *mod)
 {
 	struct symbol *s;
+	unsigned int name_len;
+	unsigned int name_len_padded;
+	unsigned int tmp;
+	unsigned char *tmp_view = (unsigned char *)&tmp;
 
 	if (!modversions)
 		return;
 
 	buf_printf(b, "\n");
-	buf_printf(b, "static const struct modversion_info ____versions[]\n");
-	buf_printf(b, "__used __section(\"__versions\") = {\n");
+	buf_printf(b, "static const char ____versions[]\n");
+	buf_printf(b, "__used __section(\"__versions\") =\n");
 
 	list_for_each_entry(s, &mod->unresolved_symbols, list) {
 		if (!s->module)
@@ -2062,16 +2066,25 @@ static void add_versions(struct buffer *b, struct module *mod)
 				s->name, mod->name);
 			continue;
 		}
-		if (strlen(s->name) >= MODULE_NAME_LEN) {
-			error("too long symbol \"%s\" [%s.ko]\n",
-			      s->name, mod->name);
-			break;
-		}
-		buf_printf(b, "\t{ %#8x, \"%s\" },\n",
-			   s->crc, s->name);
+		name_len = strlen(s->name);
+		name_len_padded = (name_len + 1 + 3) & ~3;
+
+		/* Offset to next entry */
+		tmp = TO_NATIVE(8 + name_len_padded);
+		buf_printf(b, "\t\"\\x%02x\\x%02x\\x%02x\\x%02x",
+			   tmp_view[0], tmp_view[1], tmp_view[2], tmp_view[3]);
+
+		tmp = TO_NATIVE(s->crc);
+		buf_printf(b, "\\x%02x\\x%02x\\x%02x\\x%02x\"\n",
+			   tmp_view[0], tmp_view[1], tmp_view[2], tmp_view[3]);
+
+		buf_printf(b, "\t\"%s", s->name);
+		for (; name_len < name_len_padded; name_len++)
+			buf_printf(b, "\\0");
+		buf_printf(b, "\"\n");
 	}
 
-	buf_printf(b, "};\n");
+	buf_printf(b, ";\n");
 }
 
 static void add_depends(struct buffer *b, struct module *mod)
-- 
2.34.1