powerpc: Endian safe trampoline

Create a trampoline that works in either endian and flips to
the expected endian. Use it for primary and secondary thread
entry as well as RTAS and OF call return.

Credit for finding the magic instruction goes to Paul Mackerras
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

arch/powerpc/include/asm/ppc_asm.h

@@ -845,6 +845,35 @@ END_FTR_SECTION_NESTED(CPU_FTR_HAS_PPR,CPU_FTR_HAS_PPR,946)
 #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 */

arch/powerpc/kernel/entry_64.S

@@ -1017,7 +1017,7 @@ _GLOBAL(enter_rtas)
 	
         li      r9,1
         rldicr  r9,r9,MSR_SF_LG,(63-MSR_SF_LG)
-	ori	r9,r9,MSR_IR|MSR_DR|MSR_FE0|MSR_FE1|MSR_FP|MSR_RI
+	ori	r9,r9,MSR_IR|MSR_DR|MSR_FE0|MSR_FE1|MSR_FP|MSR_RI|MSR_LE
 	andc	r6,r0,r9
 	sync				/* disable interrupts so SRR0/1 */
 	mtmsrd	r0			/* don't get trashed */
@@ -1032,6 +1032,8 @@ _GLOBAL(enter_rtas)
 	b	.	/* prevent speculative execution */
 
 _STATIC(rtas_return_loc)
+	FIXUP_ENDIAN
+
 	/* relocation is off at this point */
 	GET_PACA(r4)
 	clrldi	r4,r4,2			/* convert to realmode address */
@@ -1103,28 +1105,30 @@ _GLOBAL(enter_prom)
 	std	r10,_CCR(r1)
 	std	r11,_MSR(r1)
 
-	/* Get the PROM entrypoint */
+	/* Put PROM address in SRR0 */
+	mtsrr0	r4
+
+	/* Setup our trampoline return addr in LR */
+	bcl	20,31,$+4
+0:	mflr	r4
+	addi	r4,r4,(1f - 0b)
        	mtlr	r4
 
-	/* Switch MSR to 32 bits mode
+	/* Prepare a 32-bit mode big endian MSR
 	 */
 #ifdef CONFIG_PPC_BOOK3E
 	rlwinm	r11,r11,0,1,31
-	mtmsr	r11
+	mtsrr1	r11
+	rfi
 #else /* CONFIG_PPC_BOOK3E */
-        mfmsr   r11
-        li      r12,1
-        rldicr  r12,r12,MSR_SF_LG,(63-MSR_SF_LG)
+	LOAD_REG_IMMEDIATE(r12, MSR_SF | MSR_ISF | MSR_LE)
 	andc	r11,r11,r12
-        li      r12,1
-        rldicr  r12,r12,MSR_ISF_LG,(63-MSR_ISF_LG)
-        andc    r11,r11,r12
-        mtmsrd  r11
+	mtsrr1	r11
+	rfid
 #endif /* CONFIG_PPC_BOOK3E */
-        isync
 
-	/* Enter PROM here... */
-	blrl
+1:	/* Return from OF */
+	FIXUP_ENDIAN
 
 	/* Just make sure that r1 top 32 bits didn't get
 	 * corrupt by OF

arch/powerpc/kernel/head_64.S

@@ -68,6 +68,7 @@ _stext:
 _GLOBAL(__start)
 	/* NOP this out unconditionally */
 BEGIN_FTR_SECTION
+	FIXUP_ENDIAN
 	b	.__start_initialization_multiplatform
 END_FTR_SECTION(0, 1)
 
@@ -115,6 +116,7 @@ __run_at_load:
  */
 	.globl	__secondary_hold
 __secondary_hold:
+	FIXUP_ENDIAN
 #ifndef CONFIG_PPC_BOOK3E
 	mfmsr	r24
 	ori	r24,r24,MSR_RI
@@ -205,6 +207,7 @@ _GLOBAL(generic_secondary_thread_init)
  * as SCOM before entry).
  */
 _GLOBAL(generic_secondary_smp_init)
+	FIXUP_ENDIAN
 	mr	r24,r3
 	mr	r25,r4