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>

1 files changed, 33 insertions, 9 deletions

diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 5c5987f10819..fafd1a3ef0da 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -38,6 +38,7 @@
  * during the second link stage.
  */
 extern const unsigned long kallsyms_addresses[] __weak;
+extern const int kallsyms_offsets[] __weak;
 extern const u8 kallsyms_names[] __weak;
 
 /*
@@ -47,6 +48,9 @@ extern const u8 kallsyms_names[] __weak;
 extern const unsigned long kallsyms_num_syms
 __attribute__((weak, section(".rodata")));
 
+extern const unsigned long kallsyms_relative_base
+__attribute__((weak, section(".rodata")));
+
 extern const u8 kallsyms_token_table[] __weak;
 extern const u16 kallsyms_token_index[] __weak;
 
@@ -176,6 +180,23 @@ static unsigned int get_symbol_offset(unsigned long pos)
         return name - kallsyms_names;
 }
 
+static unsigned long kallsyms_sym_address(int idx)
+{
+        if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE))
+                return kallsyms_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_offsets[idx];
+
+        /* ...otherwise, positive offsets are absolute values */
+        if (kallsyms_offsets[idx] >= 0)
+                return kallsyms_offsets[idx];
+
+        /* ...and negative offsets are relative to kallsyms_relative_base - 1 */
+        return kallsyms_relative_base - 1 - kallsyms_offsets[idx];
+}
+
 /* Lookup the address for this symbol. Returns 0 if not found. */
 unsigned long kallsyms_lookup_name(const char *name)
 {
@@ -187,7 +208,7 @@ unsigned long kallsyms_lookup_name(const char *name)
                 off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
 
                 if (strcmp(namebuf, name) == 0)
-                        return kallsyms_addresses[i];
+                        return kallsyms_sym_address(i);
         }
         return module_kallsyms_lookup_name(name);
 }
@@ -204,7 +225,7 @@ int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
 
         for (i = 0, off = 0; i < kallsyms_num_syms; i++) {
                 off = kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
-                ret = fn(data, namebuf, NULL, kallsyms_addresses[i]);
+                ret = fn(data, namebuf, NULL, kallsyms_sym_address(i));
                 if (ret != 0)
                         return ret;
         }
@@ -220,7 +241,10 @@ static unsigned long get_symbol_pos(unsigned long addr,
         unsigned long i, low, high, mid;
 
         /* This kernel should never had been booted. */
-        BUG_ON(!kallsyms_addresses);
+        if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE))
+                BUG_ON(!kallsyms_addresses);
+        else
+                BUG_ON(!kallsyms_offsets);
 
         /* Do a binary search on the sorted kallsyms_addresses array. */
         low = 0;
@@ -228,7 +252,7 @@ static unsigned long get_symbol_pos(unsigned long addr,
 
         while (high - low > 1) {
                 mid = low + (high - low) / 2;
-                if (kallsyms_addresses[mid] <= addr)
+                if (kallsyms_sym_address(mid) <= addr)
                         low = mid;
                 else
                         high = mid;
@@ -238,15 +262,15 @@ static unsigned long get_symbol_pos(unsigned long addr,
          * Search for the first aliased symbol. Aliased
          * symbols are symbols with the same address.
          */
-        while (low && kallsyms_addresses[low-1] == kallsyms_addresses[low])
+        while (low && kallsyms_sym_address(low-1) == kallsyms_sym_address(low))
                 --low;
 
-        symbol_start = kallsyms_addresses[low];
+        symbol_start = kallsyms_sym_address(low);
 
         /* Search for next non-aliased symbol. */
         for (i = low + 1; i < kallsyms_num_syms; i++) {
-                if (kallsyms_addresses[i] > symbol_start) {
-                        symbol_end = kallsyms_addresses[i];
+                if (kallsyms_sym_address(i) > symbol_start) {
+                        symbol_end = kallsyms_sym_address(i);
                         break;
                 }
         }
@@ -470,7 +494,7 @@ static unsigned long get_ksymbol_core(struct kallsym_iter *iter)
         unsigned off = iter->nameoff;
 
         iter->module_name[0] = '\0';
-        iter->value = kallsyms_addresses[iter->pos];
+        iter->value = kallsyms_sym_address(iter->pos);
 
         iter->type = kallsyms_get_symbol_type(off);