Add support for the Meta architecture

Meta cores are 32-bit, hardware multithreaded, general purpose, embedded
processors which also feature a DSP instruction set, and can be found in
many digital radios. They are capable of running different operating
systems on different hardware threads, for example a digital radio might
run RTOSes for DAB decoding and audio decoding on 3 hardware threads,
and run Linux on the 4th hardware thread to manage the user interface,
networking etc. HTPs are also capable of running SMP Linux on multiple
hardware threads.

Signed-off-by: Markos Chandras <markos.chandras@imgtec.com>
Signed-off-by: Bernhard Reutner-Fischer <rep.dot.nop@gmail.com>

1 files changed, 94 insertions, 0 deletions

diff --git a/libc/string/metag/strcpy.S b/libc/string/metag/strcpy.S
new file mode 100644
index 000000000..529ac9279
--- /dev/null
+++ b/libc/string/metag/strcpy.S
@@ -0,0 +1,94 @@
+!    Copyright (C) 2013 Imagination Technologies Ltd.
+
+!    Licensed under LGPL v2.1 or later, see the file COPYING.LIB in this tarball.
+
+
+	.text
+	.global	_strcpy
+	.type	_strcpy,function
+! D1Ar1 dst
+! D0Ar2 src
+
+_strcpy:
+	MOV	A1.2, D1Ar1
+
+	! test 4 byte alignment of src
+	ANDS	D0Ar4, D0Ar2, #3
+	BNZ	$Lbyteloop
+
+	! test 4 byte alignment of dest
+	ANDS	D1Ar5, D1Ar1, #3
+	BNZ	$Lbyteloop
+
+	! load mask values for aligned loops
+	MOVT	D1Ar3, #HI(0xfefefeff)
+	ADD	D1Ar3, D1Ar3, #LO(0xfefefeff)
+	MOVT	D0FrT, #HI(0x80808080)
+	ADD	D0FrT, D0FrT, #LO(0x80808080)
+
+	! test 8 byte alignment of src
+	ANDS	D0Ar4, D0Ar2, #7
+	BNZ	$Lwordloop
+
+	! test 8 byte alignment of dest
+	ANDS	D1Ar5, D1Ar1, #7
+	BNZ	$Lwordloop
+
+$L8byteloop:
+	GETL	D1Ar5, D0Ar6, [D0Ar2++]
+	MOV	D1Re0, D1Ar5
+	MOV	D0Re0, D1Ar5
+	ADD	D1Re0, D1Re0, D1Ar3
+	XOR	D0Re0, D0Re0, #-1
+	AND	D1Re0, D1Re0, D0Re0
+	ANDS	D1Re0, D1Re0, D0FrT
+	BNZ	$Lnullfound		! NULL in first word
+
+	MOV	D1Re0, D0Ar6
+	MOV	D0Re0, D0Ar6
+	ADD	D1Re0, D1Re0, D1Ar3
+	XOR	D0Re0, D0Re0, #-1
+	AND	D1Re0, D1Re0, D0Re0
+	ANDS	D1Re0, D1Re0, D0FrT
+	BNZ	$Lnullfound2		! NULL in the second word
+
+	SETL	[A1.2++], D1Ar5, D0Ar6
+	B	$L8byteloop
+
+$Lwordloop:
+	GETD	D0Ar6, [D0Ar2++]
+	MOV	D1Re0, D0Ar6
+	MOV	D0Re0, D0Ar6
+	ADD	D1Re0, D1Re0, D1Ar3
+	XOR	D0Re0, D0Re0, #-1
+	AND	D1Re0, D1Re0, D0Re0
+	ANDS	D1Re0, D1Re0, D0FrT
+	MOV	D1Ar5, D0Ar6
+	BNZ	$Lnullfound
+	SETD	[A1.2++], D0Ar6
+	B	$Lwordloop
+
+$Lnullfound2:
+	SETD	[A1.2++], D1Ar5
+	MOV	D1Ar5, D0Ar6
+
+$Lnullfound:
+	SETB	[A1.2++], D1Ar5
+	ANDS	D0Ar6, D1Ar5, #0xff
+	LSR	D1Ar5, D1Ar5, #8
+	BNZ	$Lnullfound
+	B	$Lend
+
+$Lbyteloop:
+	GETB	D0Ar6, [D0Ar2++]
+	SETB	[A1.2++], D0Ar6
+	CMP	D0Ar6, #0
+	BNZ	$Lbyteloop
+
+$Lend:
+	MOV	D0Re0, D1Ar1
+	MOV	PC, D1RtP
+
+	.size _strcpy,.-_strcpy
+
+libc_hidden_def(strcpy)