[PATCH] Don't prefetch beyond end of patch to avoid bringing in cache-lines needlessly.

arch/ia64/lib/copy_page.S

@@ -30,6 +30,7 @@
 #define tgt2		r23
 #define srcf		r24
 #define tgtf		r25
+#define tgt_last	r26
 
 #define Nrot		((8*PIPE_DEPTH+7)&~7)
 
@@ -55,18 +56,21 @@ GLOBAL_ENTRY(copy_page)
 
 	mov src1=in1
 	adds src2=8,in1
+	mov tgt_last = PAGE_SIZE
 	;;
 	adds tgt2=8,in0
 	add srcf=512,in1
 	mov ar.lc=lcount
 	mov tgt1=in0
 	add tgtf=512,in0
+	add tgt_last = tgt_last, in0
 	;;
 1:
 (p[0])	ld8 t1[0]=[src1],16
 (EPI)	st8 [tgt1]=t1[PIPE_DEPTH-1],16
 (p[0])	ld8 t2[0]=[src2],16
 (EPI)	st8 [tgt2]=t2[PIPE_DEPTH-1],16
+	cmp.ltu p6,p0 = tgtf, tgt_last
 	;;
 (p[0])	ld8 t3[0]=[src1],16
 (EPI)	st8 [tgt1]=t3[PIPE_DEPTH-1],16
@@ -83,8 +87,8 @@ GLOBAL_ENTRY(copy_page)
 (p[0])	ld8 t8[0]=[src2],16
 (EPI)	st8 [tgt2]=t8[PIPE_DEPTH-1],16
 
-	lfetch [srcf], 64
-	lfetch [tgtf], 64
+(p6)	lfetch [srcf], 64
+(p6)	lfetch [tgtf], 64
 	br.ctop.sptk.few 1b
 	;;
 	mov pr=saved_pr,0xffffffffffff0000	// restore predicates