scripts/sortextable: Handle relative entries, and other cleanups

x86 is now using relative rather than absolute addresses in its
exception table, so we add a sorter for these.  If there are
relocations on the __ex_table section, they are redundant and probably
incorrect after the sort, so they are zeroed out leaving them valid
and consistent.

Also use the unaligned safe accessors from tools/{be,le}_byteshift.h

Signed-off-by: David Daney <david.daney@cavium.com>
Link: http://lkml.kernel.org/r/1335291795-26693-2-git-send-email-ddaney.cavm@gmail.com
Signed-off-by: H. Peter Anvin <hpa@zytor.com>

3 files changed, 164 insertions, 88 deletions

diff --git a/scripts/Makefile b/scripts/Makefile
index 43e19b9fc641..9eace52c64df 100644
--- a/scripts/Makefile
+++ b/scripts/Makefile
@@ -15,6 +15,8 @@ hostprogs-$(CONFIG_IKCONFIG)     += bin2c
 hostprogs-$(BUILD_C_RECORDMCOUNT) += recordmcount
 hostprogs-$(CONFIG_BUILDTIME_EXTABLE_SORT) += sortextable
 
+HOSTCFLAGS_sortextable.o = -I$(srctree)/tools/include
+
 always          := $(hostprogs-y) $(hostprogs-m)
 
 # The following hostprogs-y programs are only build on demand
diff --git a/scripts/sortextable.c b/scripts/sortextable.c
index f51f1d43da63..1ca9ceb95eb6 100644
--- a/scripts/sortextable.c
+++ b/scripts/sortextable.c
@@ -1,7 +1,7 @@
 /*
  * sortextable.c: Sort the kernel's exception table
  *
- * Copyright 2011 Cavium, Inc.
+ * Copyright 2011 - 2012 Cavium, Inc.
  *
  * Based on code taken from recortmcount.c which is:
  *
@@ -28,6 +28,9 @@
 #include <string.h>
 #include <unistd.h>
 
+#include <tools/be_byteshift.h>
+#include <tools/le_byteshift.h>
+
 static int fd_map;      /* File descriptor for file being modified. */
 static int mmap_failed; /* Boolean flag. */
 static void *ehdr_curr; /* current ElfXX_Ehdr *  for resource cleanup */
@@ -94,109 +97,157 @@ static void *mmap_file(char const *fname)
         return addr;
 }
 
-/* w8rev, w8nat, ...: Handle endianness. */
-
-static uint64_t w8rev(uint64_t const x)
+static uint64_t r8be(const uint64_t *x)
 {
-        return   ((0xff & (x >> (0 * 8))) << (7 * 8))
-               | ((0xff & (x >> (1 * 8))) << (6 * 8))
-               | ((0xff & (x >> (2 * 8))) << (5 * 8))
-               | ((0xff & (x >> (3 * 8))) << (4 * 8))
-               | ((0xff & (x >> (4 * 8))) << (3 * 8))
-               | ((0xff & (x >> (5 * 8))) << (2 * 8))
-               | ((0xff & (x >> (6 * 8))) << (1 * 8))
-               | ((0xff & (x >> (7 * 8))) << (0 * 8));
+        return get_unaligned_be64(x);
 }
-
-static uint32_t w4rev(uint32_t const x)
+static uint32_t rbe(const uint32_t *x)
 {
-        return   ((0xff & (x >> (0 * 8))) << (3 * 8))
-               | ((0xff & (x >> (1 * 8))) << (2 * 8))
-               | ((0xff & (x >> (2 * 8))) << (1 * 8))
-               | ((0xff & (x >> (3 * 8))) << (0 * 8));
+        return get_unaligned_be32(x);
 }
-
-static uint32_t w2rev(uint16_t const x)
+static uint16_t r2be(const uint16_t *x)
 {
-        return   ((0xff & (x >> (0 * 8))) << (1 * 8))
-               | ((0xff & (x >> (1 * 8))) << (0 * 8));
+        return get_unaligned_be16(x);
 }
-
-static uint64_t w8nat(uint64_t const x)
+static uint64_t r8le(const uint64_t *x)
 {
-        return x;
+        return get_unaligned_le64(x);
 }
-
-static uint32_t w4nat(uint32_t const x)
+static uint32_t rle(const uint32_t *x)
+{
+        return get_unaligned_le32(x);
+}
+static uint16_t r2le(const uint16_t *x)
 {
-        return x;
+        return get_unaligned_le16(x);
 }
 
-static uint32_t w2nat(uint16_t const x)
+static void w8be(uint64_t val, uint64_t *x)
+{
+        put_unaligned_be64(val, x);
+}
+static void wbe(uint32_t val, uint32_t *x)
+{
+        put_unaligned_be32(val, x);
+}
+static void w2be(uint16_t val, uint16_t *x)
+{
+        put_unaligned_be16(val, x);
+}
+static void w8le(uint64_t val, uint64_t *x)
+{
+        put_unaligned_le64(val, x);
+}
+static void wle(uint32_t val, uint32_t *x)
+{
+        put_unaligned_le32(val, x);
+}
+static void w2le(uint16_t val, uint16_t *x)
 {
-        return x;
+        put_unaligned_le16(val, x);
 }
 
-static uint64_t (*w8)(uint64_t);
-static uint32_t (*w)(uint32_t);
-static uint32_t (*w2)(uint16_t);
+static uint64_t (*r8)(const uint64_t *);
+static uint32_t (*r)(const uint32_t *);
+static uint16_t (*r2)(const uint16_t *);
+static void (*w8)(uint64_t, uint64_t *);
+static void (*w)(uint32_t, uint32_t *);
+static void (*w2)(uint16_t, uint16_t *);
 
+typedef void (*table_sort_t)(char *, int);
 
 /* 32 bit and 64 bit are very similar */
 #include "sortextable.h"
 #define SORTEXTABLE_64
 #include "sortextable.h"
 
+static int compare_x86_table(const void *a, const void *b)
+{
+        int32_t av = (int32_t)r(a);
+        int32_t bv = (int32_t)r(b);
+
+        if (av < bv)
+                return -1;
+        if (av > bv)
+                return 1;
+        return 0;
+}
+
+static void sort_x86_table(char *extab_image, int image_size)
+{
+        int i;
+
+        /*
+         * Do the same thing the runtime sort does, first normalize to
+         * being relative to the start of the section.
+         */
+        i = 0;
+        while (i < image_size) {
+                uint32_t *loc = (uint32_t *)(extab_image + i);
+                w(r(loc) + i, loc);
+                i += 4;
+        }
+
+        qsort(extab_image, image_size / 8, 8, compare_x86_table);
+
+        /* Now denormalize. */
+        i = 0;
+        while (i < image_size) {
+                uint32_t *loc = (uint32_t *)(extab_image + i);
+                w(r(loc) - i, loc);
+                i += 4;
+        }
+}
 
 static void
 do_file(char const *const fname)
 {
-        Elf32_Ehdr *const ehdr = mmap_file(fname);
+        table_sort_t custom_sort;
+        Elf32_Ehdr *ehdr = mmap_file(fname);
 
         ehdr_curr = ehdr;
-        w = w4nat;
-        w2 = w2nat;
-        w8 = w8nat;
         switch (ehdr->e_ident[EI_DATA]) {
-                static unsigned int const endian = 1;