objtool: Fix x86 orc generation on big endian cross-compiles

Correct objtool orc generation endianness problems to enable fully
functional x86 cross-compiles on big endian hardware.

Introduce bswap_if_needed() macro, which does a byte swap if target
endianness doesn't match the host, i.e. cross-compilation for little
endian on big endian and vice versa. The macro is used for conversion
of multi-byte values which are read from / about to be written to a
target native endianness ELF file.

Signed-off-by: Vasily Gorbik <[e-mail]>
Acked-by: Peter Zijlstra (Intel) <[e-mail]>
Acked-by: Masami Hiramatsu <[e-mail]>
Signed-off-by: Josh Poimboeuf <[e-mail]>

arch/x86/include/asm/orc_types.h

···
 #define ORC_REG_MAX			15
 
 #ifndef __ASSEMBLY__
+#include <asm/byteorder.h>
+
 /*
  * This struct is more or less a vastly simplified version of the DWARF Call
  * Frame Information standard.  It contains only the necessary parts of DWARF
···
 struct orc_entry {
 	s16		sp_offset;
 	s16		bp_offset;
+#if defined(__LITTLE_ENDIAN_BITFIELD)
 	unsigned	sp_reg:4;
 	unsigned	bp_reg:4;
 	unsigned	type:2;
 	unsigned	end:1;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+	unsigned	bp_reg:4;
+	unsigned	sp_reg:4;
+	unsigned	unused:5;
+	unsigned	end:1;
+	unsigned	type:2;
+#endif
 } __packed;
 
 #endif /* __ASSEMBLY__ */

tools/arch/x86/include/asm/orc_types.h

···
 #define ORC_REG_MAX			15
 
 #ifndef __ASSEMBLY__
+#include <asm/byteorder.h>
+
 /*
  * This struct is more or less a vastly simplified version of the DWARF Call
  * Frame Information standard.  It contains only the necessary parts of DWARF
···
 struct orc_entry {
 	s16		sp_offset;
 	s16		bp_offset;
+#if defined(__LITTLE_ENDIAN_BITFIELD)
 	unsigned	sp_reg:4;
 	unsigned	bp_reg:4;
 	unsigned	type:2;
 	unsigned	end:1;
+#elif defined(__BIG_ENDIAN_BITFIELD)
+	unsigned	bp_reg:4;
+	unsigned	sp_reg:4;
+	unsigned	unused:5;
+	unsigned	end:1;
+	unsigned	type:2;
+#endif
 } __packed;
 
 #endif /* __ASSEMBLY__ */

tools/objtool/arch/x86/include/arch_endianness.h

···
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _ARCH_ENDIANNESS_H
+#define _ARCH_ENDIANNESS_H
+
+#include <endian.h>
+
+#define __TARGET_BYTE_ORDER __LITTLE_ENDIAN
+
+#endif /* _ARCH_ENDIANNESS_H */

tools/objtool/check.c

···
 #include "special.h"
 #include "warn.h"
 #include "arch_elf.h"
+#include "endianness.h"
 
 #include <linux/objtool.h>
 #include <linux/hashtable.h>
···
 		cfa = &insn->cfi.cfa;
 
 		if (hint->type == UNWIND_HINT_TYPE_RET_OFFSET) {
-			insn->ret_offset = hint->sp_offset;
+			insn->ret_offset = bswap_if_needed(hint->sp_offset);
 			continue;
 		}
 
···
 			return -1;
 		}
 
-		cfa->offset = hint->sp_offset;
+		cfa->offset = bswap_if_needed(hint->sp_offset);
 		insn->cfi.type = hint->type;
 		insn->cfi.end = hint->end;
 	}

tools/objtool/endianness.h

···
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _OBJTOOL_ENDIANNESS_H
+#define _OBJTOOL_ENDIANNESS_H
+
+#include <linux/kernel.h>
+#include <endian.h>
+#include "arch_endianness.h"
+
+#ifndef __TARGET_BYTE_ORDER
+#error undefined arch __TARGET_BYTE_ORDER
+#endif
+
+#if __BYTE_ORDER != __TARGET_BYTE_ORDER
+#define __NEED_BSWAP 1
+#else
+#define __NEED_BSWAP 0
+#endif
+
+/*
+ * Does a byte swap if target endianness doesn't match the host, i.e. cross
+ * compilation for little endian on big endian and vice versa.
+ * To be used for multi-byte values conversion, which are read from / about
+ * to be written to a target native endianness ELF file.
+ */
+#define bswap_if_needed(val)						\
+({									\
+	__typeof__(val) __ret;						\
+	switch (sizeof(val)) {						\
+	case 8: __ret = __NEED_BSWAP ? bswap_64(val) : (val); break;	\
+	case 4: __ret = __NEED_BSWAP ? bswap_32(val) : (val); break;	\
+	case 2: __ret = __NEED_BSWAP ? bswap_16(val) : (val); break;	\
+	default:							\
+		BUILD_BUG(); break;					\
+	}								\
+	__ret;								\
+})
+
+#endif /* _OBJTOOL_ENDIANNESS_H */

tools/objtool/orc_dump.c

···
 #include <asm/orc_types.h>
 #include "objtool.h"
 #include "warn.h"
+#include "endianness.h"
 
 static const char *reg_name(unsigned int reg)
 {
···
 
 		printf(" sp:");
 
-		print_reg(orc[i].sp_reg, orc[i].sp_offset);
+		print_reg(orc[i].sp_reg, bswap_if_needed(orc[i].sp_offset));
 
 		printf(" bp:");
 
-		print_reg(orc[i].bp_reg, orc[i].bp_offset);
+		print_reg(orc[i].bp_reg, bswap_if_needed(orc[i].bp_offset));
 
 		printf(" type:%s end:%d\n",
 		       orc_type_name(orc[i].type), orc[i].end);

tools/objtool/orc_gen.c

···
 
 #include "check.h"
 #include "warn.h"
+#include "endianness.h"
 
 int create_orc(struct objtool_file *file)
 {
···
 	/* populate ORC data */
 	orc = (struct orc_entry *)u_sec->data->d_buf + idx;
 	memcpy(orc, o, sizeof(*orc));
+	orc->sp_offset = bswap_if_needed(orc->sp_offset);
+	orc->bp_offset = bswap_if_needed(orc->bp_offset);
 
 	/* populate reloc for ip */
 	reloc = malloc(sizeof(*reloc));

tools/objtool/special.c

···
 #include "special.h"
 #include "warn.h"
 #include "arch_special.h"
+#include "endianness.h"
 
 struct special_entry {
 	const char *sec;
···
 	if (entry->feature) {
 		unsigned short feature;
 
-		feature = *(unsigned short *)(sec->data->d_buf + offset +
-					      entry->feature);
+		feature = bswap_if_needed(*(unsigned short *)(sec->data->d_buf +
+							      offset +
+							      entry->feature));
 		arch_handle_alternative(feature, alt);
 	}