/* $OpenBSD: bcopy.S,v 1.5 2015/08/31 02:53:56 guenther Exp $ */ /*- * Copyright (c) 1991, 1993 * The Regents of the University of California. All rights reserved. * * This code is derived from software contributed to Berkeley by * Ralph Campbell. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of the University nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * THIS SOFTWARE IS PROVIDED BY THE REGENTS AND CONTRIBUTORS ``AS IS'' AND * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF * SUCH DAMAGE. */ #include "SYS.h" /* bcopy(s1, s2, n) */ LEAF(bcopy, 0) .set noreorder daddu t0, a0, a2 # t0 = end of s1 region sltu t1, a1, t0 sltu t2, a0, a1 and t1, t1, t2 # t1 = true if from < to < (from+len) beq t1, zero, forward # non overlapping, do forward copy slt t2, a2, 12 # check for small copy ble a2, zero, 2f daddu t1, a1, a2 # t1 = end of to region 1: lb v0, -1(t0) # copy bytes backwards, dsubu t0, t0, 1 # does not happen often so do slow way dsubu t1, t1, 1 bne t0, a0, 1b sb v0, 0(t1) 2: j ra nop forward: bne t2, zero, smallcpy # do a small bcopy xor v0, a0, a1 # compare low two bits of addresses and v0, v0, 3 dsubu a3, zero, a1 # compute # bytes to word align address beq v0, zero, aligned # addresses can be word aligned and a3, a3, 3 beq a3, zero, 1f dsubu a2, a2, a3 # subtract from remaining count LWHI v0, 0(a0) # get next 4 bytes (unaligned) LWLO v0, 3(a0) daddu a0, a0, a3 SWHI v0, 0(a1) # store 1, 2, or 3 bytes to align a1 daddu a1, a1, a3 1: and v0, a2, 3 # compute number of words left dsubu a3, a2, v0 move a2, v0 daddu a3, a3, a0 # compute ending address 2: LWHI v0, 0(a0) # copy words a0 unaligned, a1 aligned LWLO v0, 3(a0) daddu a0, a0, 4 daddu a1, a1, 4 bne a0, a3, 2b sw v0, -4(a1) b smallcpy nop aligned: beq a3, zero, 1f dsubu a2, a2, a3 # subtract from remaining count LWHI v0, 0(a0) # copy 1, 2, or 3 bytes to align daddu a0, a0, a3 SWHI v0, 0(a1) daddu a1, a1, a3 1: and v0, a2, 3 # compute number of whole words left dsubu a3, a2, v0 move a2, v0 daddu a3, a3, a0 # compute ending address 2: lw v0, 0(a0) # copy words daddu a0, a0, 4 daddu a1, a1, 4 bne a0, a3, 2b sw v0, -4(a1) smallcpy: ble a2, zero, 2f daddu a3, a2, a0 # compute ending address 1: lbu v0, 0(a0) # copy bytes daddu a0, a0, 1 daddu a1, a1, 1 bne a0, a3, 1b sb v0, -1(a1) 2: j ra nop .set reorder END_WEAK(bcopy)