Index: arch/parisc/kernel/pacache.S
===================================================================
RCS file: /var/cvs/linux-2.6/arch/parisc/kernel/pacache.S,v
retrieving revision 1.13
diff -u -p -r1.13 pacache.S
--- arch/parisc/kernel/pacache.S	19 Dec 2004 04:50:35 -0000	1.13
+++ arch/parisc/kernel/pacache.S	29 Dec 2004 05:37:46 -0000
@@ -295,17 +295,72 @@ copy_user_page_asm:
 	.callinfo NO_CALLS
 	.entry
 
-	ldi		64, %r1
+#ifdef __LP64__
+	/* PA8x00 CPUs can consume 2 loads and 2 stores per cycle.
+	 * Unroll the loop by hand and arrange insn appropriately.
+	 * GCC probably can do this just as well.
+	 *
+	 * Prefetching and using more regs to increase the "distance"
+	 * between ldd and corresponding std are possible optimizations.
+	 */
+
+	ldi		32, %r1                 /* PAGE_SIZE/128 == 32 */
+
+1:	ldd		0(%r25), %r19		/* prolog == 1 bundle */
+	ldd		8(%r25), %r20
+
+	ldd		16(%r25), %r21		/* bundle 2 */
+	ldd		24(%r25), %r22
+	std		%r19, 0(%r26)
+	std		%r20, 8(%r26)
+
+	ldd		32(%r25), %r19		/* bundle 3 */
+	ldd		40(%r25), %r20
+	std		%r21, 16(%r26)
+	std		%r22, 24(%r26)
+
+	ldd		48(%r25), %r21		/* bundle 4 */
+	ldd		56(%r25), %r22
+	std		%r19, 32(%r26)
+	std		%r20, 40(%r26)
+
+	ldd		64(%r25), %r19		/* bundle 5 */
+	ldd		72(%r25), %r20
+	std		%r21, 48(%r26)
+	std		%r22, 56(%r26)
+
+	ldd		80(%r25), %r21		/* bundle 6 */
+	ldd		88(%r25), %r22
+	std		%r19, 64(%r26)
+	std		%r20, 72(%r26)
+
+	ldd		 96(%r25), %r19		/* bundle 7 */
+	ldd		104(%r25), %r20
+	std		%r21, 80(%r26)
+	std		%r22, 88(%r26)
+
+	ldd		112(%r25), %r21		/* bundle 8 */
+	ldd		120(%r25), %r22
+	std		%r19, 96(%r26)
+	std		%r20, 104(%r26)
+
+	ldo		128(%r25), %r25		/* epilog == 2 bundles */
+	std		%r21, 112(%r26)
+	std		%r22, 120(%r26)
+
+	ADDIB>		-1, %r1, 1b
+	ldo		128(%r26), %r26
+
+#else
 
 	/*
 	 * This loop is optimized for PCXL/PCXL2 ldw/ldw and stw/stw
-	 * bundles (very restricted rules for bundling). It probably
-	 * does OK on PCXU and better, but we could do better with
-	 * ldd/std instructions. Note that until (if) we start saving
+	 * bundles (very restricted rules for bundling).
+	 * Note that until (if) we start saving
 	 * the full 64 bit register values on interrupt, we can't
 	 * use ldd/std on a 32 bit kernel.
 	 */
-
+	ldi		64, %r1		/* PAGE_SIZE/64 == 64 */
 
 1:
 	ldw		0(%r25), %r19
@@ -343,7 +398,7 @@ copy_user_page_asm:
 	ldo		64(%r26), %r26
 	ADDIB>		-1, %r1, 1b
 	ldo		64(%r25), %r25
-
+#endif
 	bv		%r0(%r2)
 	nop
 	.exit