#define REST_16VRS(n,b,base) REST_8VRS(n,b,base); REST_8VRS(n+8,b,base)
#define REST_32VRS(n,b,base) REST_16VRS(n,b,base); REST_16VRS(n+16,b,base)
+#ifdef __BIG_ENDIAN__
+#define STXVD2X_ROT(n,b,base) STXVD2X(n,b,base)
+#define LXVD2X_ROT(n,b,base) LXVD2X(n,b,base)
+#else
+#define STXVD2X_ROT(n,b,base) XXSWAPD(n,n); \
+ STXVD2X(n,b,base); \
+ XXSWAPD(n,n)
+
+#define LXVD2X_ROT(n,b,base) LXVD2X(n,b,base); \
+ XXSWAPD(n,n)
+#endif
/* Save the lower 32 VSRs in the thread VSR region */
-#define SAVE_VSR(n,b,base) li b,16*(n); STXVD2X(n,R##base,R##b)
+#define SAVE_VSR(n,b,base) li b,16*(n); STXVD2X_ROT(n,R##base,R##b)
#define SAVE_2VSRS(n,b,base) SAVE_VSR(n,b,base); SAVE_VSR(n+1,b,base)
#define SAVE_4VSRS(n,b,base) SAVE_2VSRS(n,b,base); SAVE_2VSRS(n+2,b,base)
#define SAVE_8VSRS(n,b,base) SAVE_4VSRS(n,b,base); SAVE_4VSRS(n+4,b,base)
#define SAVE_16VSRS(n,b,base) SAVE_8VSRS(n,b,base); SAVE_8VSRS(n+8,b,base)
#define SAVE_32VSRS(n,b,base) SAVE_16VSRS(n,b,base); SAVE_16VSRS(n+16,b,base)
-#define REST_VSR(n,b,base) li b,16*(n); LXVD2X(n,R##base,R##b)
+#define REST_VSR(n,b,base) li b,16*(n); LXVD2X_ROT(n,R##base,R##b)
#define REST_2VSRS(n,b,base) REST_VSR(n,b,base); REST_VSR(n+1,b,base)
#define REST_4VSRS(n,b,base) REST_2VSRS(n,b,base); REST_2VSRS(n+2,b,base)
#define REST_8VSRS(n,b,base) REST_4VSRS(n,b,base); REST_4VSRS(n+4,b,base)
#define N_SLINE 68
#define N_SO 100
-#endif /* __ASSEMBLY__ */
+/*
+ * Create an endian fixup trampoline
+ *
+ * This starts with a "tdi 0,0,0x48" instruction which is
+ * essentially a "trap never", and thus akin to a nop.
+ *
+ * The opcode for this instruction read with the wrong endian
+ * however results in a b . + 8
+ *
+ * So essentially we use that trick to execute the following
+ * trampoline in "reverse endian" if we are running with the
+ * MSR_LE bit set the "wrong" way for whatever endianness the
+ * kernel is built for.
+ */
+#ifdef CONFIG_PPC_BOOK3E
+#define FIXUP_ENDIAN
+#else
+#define FIXUP_ENDIAN \
+ tdi 0,0,0x48; /* Reverse endian of b . + 8 */ \
+ b $+36; /* Skip trampoline if endian is good */ \
+ .long 0x05009f42; /* bcl 20,31,$+4 */ \
+ .long 0xa602487d; /* mflr r10 */ \
+ .long 0x1c004a39; /* addi r10,r10,28 */ \
+ .long 0xa600607d; /* mfmsr r11 */ \
+ .long 0x01006b69; /* xori r11,r11,1 */ \
+ .long 0xa6035a7d; /* mtsrr0 r10 */ \
+ .long 0xa6037b7d; /* mtsrr1 r11 */ \
+ .long 0x2400004c /* rfid */
+#endif /* !CONFIG_PPC_BOOK3E */
+#endif /* __ASSEMBLY__ */
#endif /* _ASM_POWERPC_PPC_ASM_H */