Initial commit from HTC m7ul-3.4.10-jb-crc-ddcfb8c
diff --git a/arch/arm/lib/memzero.S b/arch/arm/lib/memzero.S
new file mode 100644
index 0000000..3fbdef5
--- /dev/null
+++ b/arch/arm/lib/memzero.S
@@ -0,0 +1,125 @@
+/*
+ * linux/arch/arm/lib/memzero.S
+ *
+ * Copyright (C) 1995-2000 Russell King
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+ .text
+ .align 5
+ .word 0
+/*
+ * Align the pointer in r0. r3 contains the number of bytes that we are
+ * mis-aligned by, and r1 is the number of bytes. If r1 < 4, then we
+ * don't bother; we use byte stores instead.
+ */
+1: subs r1, r1, #4 @ 1 do we have enough
+ blt 5f @ 1 bytes to align with?
+ cmp r3, #2 @ 1
+ strltb r2, [r0], #1 @ 1
+ strleb r2, [r0], #1 @ 1
+ strb r2, [r0], #1 @ 1
+ add r1, r1, r3 @ 1 (r1 = r1 - (4 - r3))
+/*
+ * The pointer is now aligned and the length is adjusted. Try doing the
+ * memzero again.
+ */
+
+ENTRY(__memzero)
+ mov r2, #0 @ 1
+ ands r3, r0, #3 @ 1 unaligned?
+ bne 1b @ 1
+/*
+ * r3 = 0, and we know that the pointer in r0 is aligned to a word boundary.
+ */
+ 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
+ */
+ str lr, [sp, #-4]! @ 1
+ mov ip, r2 @ 1
+ mov lr, r2 @ 1
+
+3: subs r1, r1, #64 @ 1 write 32 bytes out per loop
+ stmgeia r0!, {r2, r3, ip, lr} @ 4
+ stmgeia r0!, {r2, r3, ip, lr} @ 4
+ stmgeia r0!, {r2, r3, ip, lr} @ 4
+ stmgeia r0!, {r2, r3, ip, lr} @ 4
+ bgt 3b @ 1
+ ldmeqfd sp!, {pc} @ 1/2 quick exit
+/*
+ * No need to correct the count; we're only testing bits from now on
+ */
+ tst r1, #32 @ 1
+ stmneia r0!, {r2, r3, ip, lr} @ 4
+ stmneia r0!, {r2, r3, ip, lr} @ 4
+ tst r1, #16 @ 1 16 bytes or more?
+ 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?
+ strne r2, [r0], #4 @ 1
+/*
+ * When we get here, we've got less than 4 bytes to zero. We
+ * may have an unaligned pointer as well.
+ */
+5: tst r1, #2 @ 1 2 bytes or more?
+ strneb r2, [r0], #1 @ 1
+ strneb r2, [r0], #1 @ 1
+ tst r1, #1 @ 1 a byte left over
+ strneb r2, [r0], #1 @ 1
+ mov pc, lr @ 1
+ENDPROC(__memzero)