powerpc/kexec: Fix memory corruption from unallocated slaves

Commit 1fc711f7ffb01089efc58042cfdbac8573d1b59a (powerpc/kexec: Fix race
in kexec shutdown) moved the write to signal the cpu had exited the kernel
from before the transition to real mode in kexec_smp_wait to kexec_wait.

Unfornately it missed that kexec_wait is used both by cpus leaving the
kernel and by secondary slave cpus that were not allocated a paca for
what ever reason -- they could be beyond nr_cpus or not described in
the current device tree for whatever reason (for example, kexec-load
was not refreshed after a cpu hotplug operation).  Cpus coming through
that path they will write to paca[NR_CPUS] which is beyond the space
allocated for the paca data and overwrite memory not allocated to pacas
but very likely still real mode accessable).

Move the write back to kexec_smp_wait, which is used only by cpus that
found their paca, but after the transition to real mode.

Signed-off-by: Milton Miller <miltonm@bga.com>
Cc: <stable@kernel.org> # (1fc711f was backported to 2.6.32)
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
diff --git a/arch/powerpc/kernel/misc_64.S b/arch/powerpc/kernel/misc_64.S
index 206a321..e89df59 100644
--- a/arch/powerpc/kernel/misc_64.S
+++ b/arch/powerpc/kernel/misc_64.S
@@ -462,7 +462,8 @@
  * wait for the flag to change, indicating this kernel is going away but
  * the slave code for the next one is at addresses 0 to 100.
  *
- * This is used by all slaves.
+ * This is used by all slaves, even those that did not find a matching
+ * paca in the secondary startup code.
  *
  * Physical (hardware) cpu id should be in r3.
  */
@@ -471,10 +472,6 @@
 1:	mflr	r5
 	addi	r5,r5,kexec_flag-1b
 
-	li	r4,KEXEC_STATE_REAL_MODE
-	stb	r4,PACAKEXECSTATE(r13)
-	SYNC
-
 99:	HMT_LOW
 #ifdef CONFIG_KEXEC		/* use no memory without kexec */
 	lwz	r4,0(r5)
@@ -499,11 +496,17 @@
  *
  * get phys id from paca
  * switch to real mode
+ * mark the paca as no longer used
  * join other cpus in kexec_wait(phys_id)
  */
 _GLOBAL(kexec_smp_wait)
 	lhz	r3,PACAHWCPUID(r13)
 	bl	real_mode
+
+	li	r4,KEXEC_STATE_REAL_MODE
+	stb	r4,PACAKEXECSTATE(r13)
+	SYNC
+
 	b	.kexec_wait
 
 /*