kallsyms: add support for relative offsets in kallsyms address table

Similar to how relative extables are implemented, it is possible to emit
the kallsyms table in such a way that it contains offsets relative to
some anchor point in the kernel image rather than absolute addresses.

On 64-bit architectures, it cuts the size of the kallsyms address table
in half, since offsets between kernel symbols can typically be expressed
in 32 bits.  This saves several hundreds of kilobytes of permanent
.rodata on average.  In addition, the kallsyms address table is no
longer subject to dynamic relocation when CONFIG_RELOCATABLE is in
effect, so the relocation work done after decompression now doesn't have
to do relocation updates for all these values.  This saves up to 24
bytes (i.e., the size of a ELF64 RELA relocation table entry) per value,
which easily adds up to a couple of megabytes of uncompressed __init
data on ppc64 or arm64.  Even if these relocation entries typically
compress well, the combined size reduction of 2.8 MB uncompressed for a
ppc64_defconfig build (of which 2.4 MB is __init data) results in a ~500
KB space saving in the compressed image.

Since it is useful for some architectures (like x86) to retain the
ability to emit absolute values as well, this patch also adds support
for capturing both absolute and relative values when
KALLSYMS_ABSOLUTE_PERCPU is in effect, by emitting absolute per-cpu
addresses as positive 32-bit values, and addresses relative to the
lowest encountered relative symbol as negative values, which are
subtracted from the runtime address of this base symbol to produce the
actual address.

Support for the above is enabled by default for all architectures except
IA-64 and Tile-GX, whose symbols are too far apart to capture in this
manner.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Tested-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Kees Cook <keescook@chromium.org>
Tested-by: Kees Cook <keescook@chromium.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Michal Marek <mmarek@suse.cz>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

3 files changed, 75 insertions, 10 deletions

diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
index d39a1eeb080e..638b143ee60f 100644
--- a/scripts/kallsyms.c
+++ b/scripts/kallsyms.c
@@ -22,6 +22,7 @@
 #include <stdlib.h>
 #include <string.h>
 #include <ctype.h>
+#include <limits.h>
 
 #ifndef ARRAY_SIZE
 #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof(arr[0]))
@@ -43,6 +44,7 @@ struct addr_range {
 };
 
 static unsigned long long _text;
+static unsigned long long relative_base;
 static struct addr_range text_ranges[] = {
 	{ "_stext",     "_etext"     },
 	{ "_sinittext", "_einittext" },
@@ -62,6 +64,7 @@ static int all_symbols = 0;
 static int absolute_percpu = 0;
 static char symbol_prefix_char = '\0';
 static unsigned long long kernel_start_addr = 0;
+static int base_relative = 0;
 
 int token_profit[0x10000];
 
@@ -75,7 +78,7 @@ static void usage(void)
 	fprintf(stderr, "Usage: kallsyms [--all-symbols] "
 			"[--symbol-prefix=<prefix char>] "
 			"[--page-offset=<CONFIG_PAGE_OFFSET>] "
-			"< in.map > out.S\n");
+			"[--base-relative] < in.map > out.S\n");
 	exit(1);
 }
 
@@ -205,6 +208,8 @@ static int symbol_valid(struct sym_entry *s)
 	 */
 	static char *special_symbols[] = {
 		"kallsyms_addresses",
+		"kallsyms_offsets",
+		"kallsyms_relative_base",
 		"kallsyms_num_syms",
 		"kallsyms_names",
 		"kallsyms_markers",
@@ -349,16 +354,48 @@ static void write_src(void)
 
 	printf("\t.section .rodata, \"a\"\n");
 
-	/* Provide proper symbols relocatability by their '_text'
-	 * relativeness.  The symbol names cannot be used to construct
-	 * normal symbol references as the list of symbols contains
-	 * symbols that are declared static and are private to their
-	 * .o files.  This prevents .tmp_kallsyms.o or any other
-	 * object from referencing them.
+	/* Provide proper symbols relocatability by their relativeness
+	 * to a fixed anchor point in the runtime image, either '_text'
+	 * for absolute address tables, in which case the linker will
+	 * emit the final addresses at build time. Otherwise, use the
+	 * offset relative to the lowest value encountered of all relative
+	 * symbols, and emit non-relocatable fixed offsets that will be fixed
+	 * up at runtime.
+	 *
+	 * The symbol names cannot be used to construct normal symbol
+	 * references as the list of symbols contains symbols that are
+	 * declared static and are private to their .o files.  This prevents
+	 * .tmp_kallsyms.o or any other object from referencing them.
 	 */
-	output_label("kallsyms_addresses");
+	if (!base_relative)
+		output_label("kallsyms_addresses");
+	else
+		output_label("kallsyms_offsets");
+
 	for (i = 0; i < table_cnt; i++) {
-		if (!symbol_absolute(&table[i])) {
+		if (base_relative) {
+			long long offset;
+			int overflow;
+
+			if (!absolute_percpu) {
+				offset = table[i].addr - relative_base;
+				overflow = (offset < 0 || offset > UINT_MAX);
+			} else if (symbol_absolute(&table[i])) {
+				offset = table[i].addr;
+				overflow = (offset < 0 || offset > INT_MAX);
+			} else {
+				offset = relative_base - table[i].addr - 1;
+				overflow = (offset < INT_MIN || offset >= 0);
+			}
+			if (overflow) {
+				fprintf(stderr, "kallsyms failure: "
+					"%s symbol value %#llx out of range in relative mode\n",
+					symbol_absolute(&table[i]) ? "absolute" : "relative",
+					table[i].addr);
+				exit(EXIT_FAILURE);
+			}
+			printf("\t.long\t%#x\n", (int)offset);
+		} else if (!symbol_absolute(&table[i])) {
 			if (_text <= table[i].addr)
 				printf("\tPTR\t_text + %#llx\n",
 					table[i].addr - _text);
@@ -371,6 +408,12 @@ static void write_src(void)
 	}
 	printf("\n");
 
+	if (base_relative) {
+		output_label("kallsyms_relative_base");
+		printf("\tPTR\t_text - %#llx\n", _text - relative_base);
+		printf("\n");
+	}
+
 	output_label("kallsyms_num_syms");
 	printf("\tPTR\t%d\n", table_cnt);
 	printf("\n");
@@ -695,6 +738,18 @@ static void make_percpus_absolute(void)
 		}
 }
 
+/* find the minimum non-absolute symbol address */
+static void record_relative_base(void)
+{
+	unsigned int i;
+
+	relative_base = -1ULL;
+	for (i = 0; i < table_cnt; i++)
+		if (!symbol_absolute(&table[i]) &&
+		    table[i].addr < relative_base)
+			relative_base = table[i].addr;
+}
+
 int main(int argc, char **argv)
 {
 	if (argc >= 2) {
@@ -713,7 +768,9 @@ int main(int argc, char **argv)
 			} else if (strncmp(argv[i], "--page-offset=", 14) == 0) {
 				const char *p = &argv[i][14];
 				kernel_start_addr = strtoull(p, NULL, 16);
-			} else
+			} else if (strcmp(argv[i], "--base-relative") == 0)
+				base_relative = 1;
+			else
 				usage();
 		}
 	} else if (argc != 1)
@@ -722,6 +779,8 @@ int main(int argc, char **argv)
 	read_map(stdin);
 	if (absolute_percpu)
 		make_percpus_absolute();
+	if (base_relative)
+		record_relative_base();
 	sort_symbols();
 	optimize_token_table();
 	write_src();
diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
index 7a08bf9a9576..453ede9d2f3d 100755
--- a/scripts/link-vmlinux.sh
+++ b/scripts/link-vmlinux.sh
@@ -90,6 +90,10 @@ kallsyms()
 		kallsymopt="${kallsymopt} --absolute-percpu"
 	fi
 
+	if [ -n "${CONFIG_KALLSYMS_BASE_RELATIVE}" ]; then
+		kallsymopt="${kallsymopt} --base-relative"
+	fi
+
 	local aflags="${KBUILD_AFLAGS} ${KBUILD_AFLAGS_KERNEL}               \
 		      ${NOSTDINC_FLAGS} ${LINUXINCLUDE} ${KBUILD_CPPFLAGS}"
 
diff --git a/scripts/namespace.pl b/scripts/namespace.pl
index a71be6b7cdec..9f3c9d47a4a5 100755
--- a/scripts/namespace.pl
+++ b/scripts/namespace.pl
@@ -117,6 +117,8 @@ my %nameexception = (
     'kallsyms_names'	=> 1,
     'kallsyms_num_syms'	=> 1,
     'kallsyms_addresses'=> 1,
+    'kallsyms_offsets'	=> 1,
+    'kallsyms_relative_base'=> 1,
     '__this_module'	=> 1,
     '_etext'		=> 1,
     '_edata'		=> 1,