sparc64: Fix corrupted thread fault code.

Every path that ends up at do_sparc64_fault() must install a valid
FAULT_CODE_* bitmask in the per-thread fault code byte.

Two paths leading to the label winfix_trampoline (which expects the
FAULT_CODE_* mask in register %g4) were not doing so:

1) For pre-hypervisor TLB protection violation traps, if we took
   the 'winfix_trampoline' path we wouldn't have %g4 initialized
   with the FAULT_CODE_* value yet.  Resulting in using the
   TLB_TAG_ACCESS register address value instead.

2) In the TSB miss path, when we notice that we are going to use a
   hugepage mapping, but we haven't allocated the hugepage TSB yet, we
   still have to take the window fixup case into consideration and
   in that particular path we leave %g4 not setup properly.

Errors on this sort were largely invisible previously, but after
commit 4ccb927289 ("sparc64: sun4v TLB
error power off events") we now have a fault_code mask bit
(FAULT_CODE_BAD_RA) that triggers due to this bug.

FAULT_CODE_BAD_RA triggers because this bit is set in TLB_TAG_ACCESS
(see #1 above) and thus we get seemingly random bus errors triggered
for user processes.

Fixes: 4ccb927289 ("sparc64: sun4v TLB error power off events")
Reported-by: Meelis Roos <mroos@linux.ee>
Signed-off-by: David S. Miller <davem@davemloft.net>

arch/sparc/kernel/dtlb_prot.S

@@ -24,11 +24,11 @@
 	mov		TLB_TAG_ACCESS, %g4		! For reload of vaddr
 
 /* PROT ** ICACHE line 2: More real fault processing */
+	ldxa		[%g4] ASI_DMMU, %g5		! Put tagaccess in %g5
 	bgu,pn		%xcc, winfix_trampoline		! Yes, perform winfixup
-	 ldxa		[%g4] ASI_DMMU, %g5		! Put tagaccess in %g5
-	ba,pt		%xcc, sparc64_realfault_common	! Nope, normal fault
 	 mov		FAULT_CODE_DTLB | FAULT_CODE_WRITE, %g4
-	nop
+	ba,pt		%xcc, sparc64_realfault_common	! Nope, normal fault
+	 nop
 	nop
 	nop
 	nop

arch/sparc/kernel/tsb.S

@@ -162,10 +162,10 @@ tsb_miss_page_table_walk_sun4v_fastpath:
 	nop
 	.previous
 
-	rdpr	%tl, %g3
-	cmp	%g3, 1
+	rdpr	%tl, %g7
+	cmp	%g7, 1
 	bne,pn	%xcc, winfix_trampoline
-	 nop
+	 mov	%g3, %g4
 	ba,pt	%xcc, etrap
 	 rd	%pc, %g7
 	call	hugetlb_setup