[SPARC64]: store-init needs trailing membar.

The manual says that it is required and we actually have crash reports
where loads see stale data due to not having membars here.

In one case the networking does:

	memset(skb, 0, offsetof(struct sk_buff, truesize));

and then some code later checks skb->nohdr for zero, but it's still
the value that was there before the memset().

Note that arch/sparc64/lib/xor.S already got this right.

Signed-off-by: David S. Miller <davem@davemloft.net>

arch/sparc64/kernel/tsb.S

@@ -546,6 +546,7 @@ NGtsb_init:
 	subcc		%o1, 0x100, %o1
 	bne,pt		%xcc, 1b
 	 add		%o0, 0x100, %o0
+	membar		#Sync
 	retl
 	 wr		%g2, 0x0, %asi
 	.size		NGtsb_init, .-NGtsb_init

arch/sparc64/lib/NGbzero.S

@@ -88,6 +88,7 @@ NGbzero_loop:
 	bne,pt		%xcc, NGbzero_loop
 	 add		%o0, 64, %o0
 
+	membar		#Sync
 	wr		%o4, 0x0, %asi
 	brz,pn		%o1, NGbzero_done
 NGbzero_medium:

arch/sparc64/lib/NGmemcpy.S

@@ -247,6 +247,8 @@ FUNC_NAME:	/* %o0=dst, %o1=src, %o2=len */
 	/* fall through */
 
 60:	
+	membar		#Sync
+
 	/* %o2 contains any final bytes still needed to be copied
 	 * over. If anything is left, we copy it one byte at a time.
 	 */

arch/sparc64/lib/NGpage.S

@@ -41,6 +41,7 @@ NGcopy_user_page:	/* %o0=dest, %o1=src, %o2=vaddr */
 	subcc		%g7, 64, %g7
 	bne,pt		%xcc, 1b
 	 add		%o0, 32, %o0
+	membar		#Sync
 	retl
 	 nop
 
@@ -63,6 +64,7 @@ NGclear_user_page:	/* %o0=dest, %o1=vaddr */
 	subcc		%g7, 64, %g7
 	bne,pt		%xcc, 1b
 	 add		%o0, 32, %o0
+	membar		#Sync
 	retl
 	 nop