powerpc: Call CPU ->restore callback earlier on secondary CPUs

We do it before we loop on the PACA start flag. This way, we get a
chance to set critical SPRs on all CPUs before Linux tries to start
them up, which avoids problems when changing some bits such as LPCR
bits that need to be identical on all threads of a core or similar
things like that. Ideally, some of that should also be done before
the MMU is enabled, but that's a separate issue which would require
moving some of the SMP startup code earlier, let's not get there
for now, it works with that change alone.
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

arch/powerpc/kernel/head_64.S

@@ -236,17 +236,6 @@ generic_secondary_common_init:
 
 	/* From now on, r24 is expected to be logical cpuid */
 	mr	r24,r5
-3:	HMT_LOW
-	lbz	r23,PACAPROCSTART(r13)	/* Test if this processor should */
-					/* start.			 */
-
-#ifndef CONFIG_SMP
-	b	3b			/* Never go on non-SMP		 */
-#else
-	cmpwi	0,r23,0
-	beq	3b			/* Loop until told to go	 */
-
-	sync				/* order paca.run and cur_cpu_spec */
 
 	/* See if we need to call a cpu state restore handler */
 	LOAD_REG_ADDR(r23, cur_cpu_spec)
@@ -258,6 +247,17 @@ generic_secondary_common_init:
 	mtctr	r23
 	bctrl
 
+3:	HMT_LOW
+	lbz	r23,PACAPROCSTART(r13)	/* Test if this processor should */
+					/* start.			 */
+#ifndef CONFIG_SMP
+	b	3b			/* Never go on non-SMP		 */
+#else
+	cmpwi	0,r23,0
+	beq	3b			/* Loop until told to go	 */
+
+	sync				/* order paca.run and cur_cpu_spec */
+
 4:	/* Create a temp kernel stack for use before relocation is on.	*/
 	ld	r1,PACAEMERGSP(r13)
 	subi	r1,r1,STACK_FRAME_OVERHEAD