X-Git-Url: http://www.pilppa.org/gitweb/gitweb.cgi?a=blobdiff_plain;f=arch%2Farm%2Flib%2Fmemzero.S;h=b8f79d80ee9bf703d7554c15d2a22ceb1fe9ef1e;hb=f91a8dcc25398c5d708056de081d6cebf3f2023e;hp=abf2508e8221a65113b63cd14b87c3c129d8a5f2;hpb=2239aff6ab2b95af1f628eee7a809f21c41605b3;p=linux-2.6-omap-h63xx.git

diff --git a/arch/arm/lib/memzero.S b/arch/arm/lib/memzero.S
index abf2508e822..b8f79d80ee9 100644
--- a/arch/arm/lib/memzero.S
+++ b/arch/arm/lib/memzero.S
@@ -39,6 +39,9 @@ ENTRY(__memzero)
  */
 	cmp	r1, #16			@ 1 we can skip this chunk if we
 	blt	4f			@ 1 have < 16 bytes
+
+#if ! CALGN(1)+0
+
 /*
  * We need an extra register for this loop - save the return address and
  * use the LR
@@ -64,6 +67,47 @@ ENTRY(__memzero)
 	stmneia	r0!, {r2, r3, ip, lr}	@ 4
 	ldr	lr, [sp], #4		@ 1
 
+#else
+
+/*
+ * This version aligns the destination pointer in order to write
+ * whole cache lines at once.
+ */
+
+	stmfd	sp!, {r4-r7, lr}
+	mov	r4, r2
+	mov	r5, r2
+	mov	r6, r2
+	mov	r7, r2
+	mov	ip, r2
+	mov	lr, r2
+
+	cmp	r1, #96
+	andgts	ip, r0, #31
+	ble	3f
+
+	rsb	ip, ip, #32
+	sub	r1, r1, ip
+	movs	ip, ip, lsl #(32 - 4)
+	stmcsia	r0!, {r4, r5, r6, r7}
+	stmmiia	r0!, {r4, r5}
+	movs	ip, ip, lsl #2
+	strcs	r2, [r0], #4
+
+3:	subs	r1, r1, #64
+	stmgeia	r0!, {r2-r7, ip, lr}
+	stmgeia	r0!, {r2-r7, ip, lr}
+	bgt	3b
+	ldmeqfd	sp!, {r4-r7, pc}
+
+	tst	r1, #32
+	stmneia	r0!, {r2-r7, ip, lr}
+	tst	r1, #16
+	stmneia	r0!, {r4-r7}
+	ldmfd	sp!, {r4-r7, lr}
+
+#endif
+
 4:	tst	r1, #8			@ 1 8 bytes or more?
 	stmneia	r0!, {r2, r3}		@ 2
 	tst	r1, #4			@ 1 4 bytes or more?