aes-x86.s

Fast and transparent file system and swap encryption package for linux. No source code changes to li

	ksc8(1)
	ksc8(2)
	ksc8(3)
	ksc8(4)
	ksc8(5)
	ksc8(6)
	jmp	aes_37
aes_35:	ksc6(0)
	ksc6(1)
	ksc6(2)
	ksc6(3)
	ksc6(4)
	ksc6(5)
	ksc6(6)
	ksc6(7)
	jmp	aes_37
aes_36:	ksc4(0)
	ksc4(1)
	ksc4(2)
	ksc4(3)
	ksc4(4)
	ksc4(5)
	ksc4(6)
	ksc4(7)
	ksc4(8)
	ksc4(9)
aes_37:	pop	%ebp
	mov	aes_cx(%ebp),%edx	// edx -> AES context
	cmpl	$0,ed_flg(%ebp)
	jne	aes_39

// compile decryption key schedule from encryption schedule - reverse
// order and do mix_column operation on round keys except first and last

	mov	nrnd(%edx),%eax		// kt = cx->d_key + nc * cx->Nrnd
	shl	$2,%eax
	lea	dkey(%edx,%eax,4),%edi
	lea	ekey(%edx),%esi		// kf = cx->e_key

	movsl				// copy first round key (unmodified)
	movsl
	movsl
	movsl
	sub	$32,%edi
	movl	$1,cnt(%ebp)
aes_38:					// do mix column on each column of
	lodsl				// each round key
	mov	%eax,%ebx
	mix_col(aes_im_tab)
	stosl
	lodsl
	mov	%eax,%ebx
	mix_col(aes_im_tab)
	stosl
	lodsl
	mov	%eax,%ebx
	mix_col(aes_im_tab)
	stosl
	lodsl
	mov	%eax,%ebx
	mix_col(aes_im_tab)
	stosl
	sub	$32,%edi

	incl	cnt(%ebp)
	mov	cnt(%ebp),%eax
	cmp	nrnd(%edx),%eax
	jb	aes_38

	movsl				// copy last round key (unmodified)
	movsl
	movsl
	movsl
aes_39:	pop	%edi
	pop	%esi
	pop	%ebx
	mov	%ebp,%esp
	pop	%ebp
	popfl
	ret


// finite field multiplies by {02}, {04} and {08}

#define f2(x)	((x<<1)^(((x>>7)&1)*0x11b))
#define f4(x)	((x<<2)^(((x>>6)&1)*0x11b)^(((x>>6)&2)*0x11b))
#define f8(x)	((x<<3)^(((x>>5)&1)*0x11b)^(((x>>5)&2)*0x11b)^(((x>>5)&4)*0x11b))

// finite field multiplies required in table generation

#define f3(x)	(f2(x) ^ x)
#define f9(x)	(f8(x) ^ x)
#define fb(x)	(f8(x) ^ f2(x) ^ x)
#define fd(x)	(f8(x) ^ f4(x) ^ x)
#define fe(x)	(f8(x) ^ f4(x) ^ f2(x))

// These defines generate the forward table entries

#define u0(x)	((f3(x) << 24) | (x << 16) | (x << 8) | f2(x))
#define u1(x)	((x << 24) | (x << 16) | (f2(x) << 8) | f3(x))
#define u2(x)	((x << 24) | (f2(x) << 16) | (f3(x) << 8) | x)
#define u3(x)	((f2(x) << 24) | (f3(x) << 16) | (x << 8) | x)

// These defines generate the inverse table entries

#define v0(x)	((fb(x) << 24) | (fd(x) << 16) | (f9(x) << 8) | fe(x))
#define v1(x)	((fd(x) << 24) | (f9(x) << 16) | (fe(x) << 8) | fb(x))
#define v2(x)	((f9(x) << 24) | (fe(x) << 16) | (fb(x) << 8) | fd(x))
#define v3(x)	((fe(x) << 24) | (fb(x) << 16) | (fd(x) << 8) | f9(x))

// These defines generate entries for the last round tables

#define w0(x)	(x)
#define w1(x)	(x <<  8)
#define w2(x)	(x << 16)
#define w3(x)	(x << 24)

// macro to generate inverse mix column tables (needed for the key schedule)

#define im_data0(p1) \
	.long	p1(0x00),p1(0x01),p1(0x02),p1(0x03),p1(0x04),p1(0x05),p1(0x06),p1(0x07) ;\
	.long	p1(0x08),p1(0x09),p1(0x0a),p1(0x0b),p1(0x0c),p1(0x0d),p1(0x0e),p1(0x0f) ;\
	.long	p1(0x10),p1(0x11),p1(0x12),p1(0x13),p1(0x14),p1(0x15),p1(0x16),p1(0x17) ;\
	.long	p1(0x18),p1(0x19),p1(0x1a),p1(0x1b),p1(0x1c),p1(0x1d),p1(0x1e),p1(0x1f)
#define im_data1(p1) \
	.long	p1(0x20),p1(0x21),p1(0x22),p1(0x23),p1(0x24),p1(0x25),p1(0x26),p1(0x27) ;\
	.long	p1(0x28),p1(0x29),p1(0x2a),p1(0x2b),p1(0x2c),p1(0x2d),p1(0x2e),p1(0x2f) ;\
	.long	p1(0x30),p1(0x31),p1(0x32),p1(0x33),p1(0x34),p1(0x35),p1(0x36),p1(0x37) ;\
	.long	p1(0x38),p1(0x39),p1(0x3a),p1(0x3b),p1(0x3c),p1(0x3d),p1(0x3e),p1(0x3f)
#define im_data2(p1) \
	.long	p1(0x40),p1(0x41),p1(0x42),p1(0x43),p1(0x44),p1(0x45),p1(0x46),p1(0x47) ;\
	.long	p1(0x48),p1(0x49),p1(0x4a),p1(0x4b),p1(0x4c),p1(0x4d),p1(0x4e),p1(0x4f) ;\
	.long	p1(0x50),p1(0x51),p1(0x52),p1(0x53),p1(0x54),p1(0x55),p1(0x56),p1(0x57) ;\
	.long	p1(0x58),p1(0x59),p1(0x5a),p1(0x5b),p1(0x5c),p1(0x5d),p1(0x5e),p1(0x5f)
#define im_data3(p1) \
	.long	p1(0x60),p1(0x61),p1(0x62),p1(0x63),p1(0x64),p1(0x65),p1(0x66),p1(0x67) ;\
	.long	p1(0x68),p1(0x69),p1(0x6a),p1(0x6b),p1(0x6c),p1(0x6d),p1(0x6e),p1(0x6f) ;\
	.long	p1(0x70),p1(0x71),p1(0x72),p1(0x73),p1(0x74),p1(0x75),p1(0x76),p1(0x77) ;\
	.long	p1(0x78),p1(0x79),p1(0x7a),p1(0x7b),p1(0x7c),p1(0x7d),p1(0x7e),p1(0x7f)
#define im_data4(p1) \
	.long	p1(0x80),p1(0x81),p1(0x82),p1(0x83),p1(0x84),p1(0x85),p1(0x86),p1(0x87) ;\
	.long	p1(0x88),p1(0x89),p1(0x8a),p1(0x8b),p1(0x8c),p1(0x8d),p1(0x8e),p1(0x8f) ;\
	.long	p1(0x90),p1(0x91),p1(0x92),p1(0x93),p1(0x94),p1(0x95),p1(0x96),p1(0x97) ;\
	.long	p1(0x98),p1(0x99),p1(0x9a),p1(0x9b),p1(0x9c),p1(0x9d),p1(0x9e),p1(0x9f)
#define im_data5(p1) \
	.long	p1(0xa0),p1(0xa1),p1(0xa2),p1(0xa3),p1(0xa4),p1(0xa5),p1(0xa6),p1(0xa7) ;\
	.long	p1(0xa8),p1(0xa9),p1(0xaa),p1(0xab),p1(0xac),p1(0xad),p1(0xae),p1(0xaf) ;\
	.long	p1(0xb0),p1(0xb1),p1(0xb2),p1(0xb3),p1(0xb4),p1(0xb5),p1(0xb6),p1(0xb7) ;\
	.long	p1(0xb8),p1(0xb9),p1(0xba),p1(0xbb),p1(0xbc),p1(0xbd),p1(0xbe),p1(0xbf)
#define im_data6(p1) \
	.long	p1(0xc0),p1(0xc1),p1(0xc2),p1(0xc3),p1(0xc4),p1(0xc5),p1(0xc6),p1(0xc7) ;\
	.long	p1(0xc8),p1(0xc9),p1(0xca),p1(0xcb),p1(0xcc),p1(0xcd),p1(0xce),p1(0xcf) ;\
	.long	p1(0xd0),p1(0xd1),p1(0xd2),p1(0xd3),p1(0xd4),p1(0xd5),p1(0xd6),p1(0xd7) ;\
	.long	p1(0xd8),p1(0xd9),p1(0xda),p1(0xdb),p1(0xdc),p1(0xdd),p1(0xde),p1(0xdf)
#define im_data7(p1) \
	.long	p1(0xe0),p1(0xe1),p1(0xe2),p1(0xe3),p1(0xe4),p1(0xe5),p1(0xe6),p1(0xe7) ;\
	.long	p1(0xe8),p1(0xe9),p1(0xea),p1(0xeb),p1(0xec),p1(0xed),p1(0xee),p1(0xef) ;\
	.long	p1(0xf0),p1(0xf1),p1(0xf2),p1(0xf3),p1(0xf4),p1(0xf5),p1(0xf6),p1(0xf7) ;\
	.long	p1(0xf8),p1(0xf9),p1(0xfa),p1(0xfb),p1(0xfc),p1(0xfd),p1(0xfe),p1(0xff)

// S-box data - 256 entries

#define sb_data0(p1) \
	.long	p1(0x63),p1(0x7c),p1(0x77),p1(0x7b),p1(0xf2),p1(0x6b),p1(0x6f),p1(0xc5) ;\
	.long	p1(0x30),p1(0x01),p1(0x67),p1(0x2b),p1(0xfe),p1(0xd7),p1(0xab),p1(0x76) ;\
	.long	p1(0xca),p1(0x82),p1(0xc9),p1(0x7d),p1(0xfa),p1(0x59),p1(0x47),p1(0xf0) ;\
	.long	p1(0xad),p1(0xd4),p1(0xa2),p1(0xaf),p1(0x9c),p1(0xa4),p1(0x72),p1(0xc0)
#define sb_data1(p1) \
	.long	p1(0xb7),p1(0xfd),p1(0x93),p1(0x26),p1(0x36),p1(0x3f),p1(0xf7),p1(0xcc) ;\
	.long	p1(0x34),p1(0xa5),p1(0xe5),p1(0xf1),p1(0x71),p1(0xd8),p1(0x31),p1(0x15) ;\
	.long	p1(0x04),p1(0xc7),p1(0x23),p1(0xc3),p1(0x18),p1(0x96),p1(0x05),p1(0x9a) ;\
	.long	p1(0x07),p1(0x12),p1(0x80),p1(0xe2),p1(0xeb),p1(0x27),p1(0xb2),p1(0x75)
#define sb_data2(p1) \
	.long	p1(0x09),p1(0x83),p1(0x2c),p1(0x1a),p1(0x1b),p1(0x6e),p1(0x5a),p1(0xa0) ;\
	.long	p1(0x52),p1(0x3b),p1(0xd6),p1(0xb3),p1(0x29),p1(0xe3),p1(0x2f),p1(0x84) ;\
	.long	p1(0x53),p1(0xd1),p1(0x00),p1(0xed),p1(0x20),p1(0xfc),p1(0xb1),p1(0x5b) ;\
	.long	p1(0x6a),p1(0xcb),p1(0xbe),p1(0x39),p1(0x4a),p1(0x4c),p1(0x58),p1(0xcf)
#define sb_data3(p1) \
	.long	p1(0xd0),p1(0xef),p1(0xaa),p1(0xfb),p1(0x43),p1(0x4d),p1(0x33),p1(0x85) ;\
	.long	p1(0x45),p1(0xf9),p1(0x02),p1(0x7f),p1(0x50),p1(0x3c),p1(0x9f),p1(0xa8) ;\
	.long	p1(0x51),p1(0xa3),p1(0x40),p1(0x8f),p1(0x92),p1(0x9d),p1(0x38),p1(0xf5) ;\
	.long	p1(0xbc),p1(0xb6),p1(0xda),p1(0x21),p1(0x10),p1(0xff),p1(0xf3),p1(0xd2)
#define sb_data4(p1) \
	.long	p1(0xcd),p1(0x0c),p1(0x13),p1(0xec),p1(0x5f),p1(0x97),p1(0x44),p1(0x17) ;\
	.long	p1(0xc4),p1(0xa7),p1(0x7e),p1(0x3d),p1(0x64),p1(0x5d),p1(0x19),p1(0x73) ;\
	.long	p1(0x60),p1(0x81),p1(0x4f),p1(0xdc),p1(0x22),p1(0x2a),p1(0x90),p1(0x88) ;\
	.long	p1(0x46),p1(0xee),p1(0xb8),p1(0x14),p1(0xde),p1(0x5e),p1(0x0b),p1(0xdb)
#define sb_data5(p1) \
	.long	p1(0xe0),p1(0x32),p1(0x3a),p1(0x0a),p1(0x49),p1(0x06),p1(0x24),p1(0x5c) ;\
	.long	p1(0xc2),p1(0xd3),p1(0xac),p1(0x62),p1(0x91),p1(0x95),p1(0xe4),p1(0x79) ;\
	.long	p1(0xe7),p1(0xc8),p1(0x37),p1(0x6d),p1(0x8d),p1(0xd5),p1(0x4e),p1(0xa9) ;\
	.long	p1(0x6c),p1(0x56),p1(0xf4),p1(0xea),p1(0x65),p1(0x7a),p1(0xae),p1(0x08)
#define sb_data6(p1) \
	.long	p1(0xba),p1(0x78),p1(0x25),p1(0x2e),p1(0x1c),p1(0xa6),p1(0xb4),p1(0xc6) ;\
	.long	p1(0xe8),p1(0xdd),p1(0x74),p1(0x1f),p1(0x4b),p1(0xbd),p1(0x8b),p1(0x8a) ;\
	.long	p1(0x70),p1(0x3e),p1(0xb5),p1(0x66),p1(0x48),p1(0x03),p1(0xf6),p1(0x0e) ;\
	.long	p1(0x61),p1(0x35),p1(0x57),p1(0xb9),p1(0x86),p1(0xc1),p1(0x1d),p1(0x9e)
#define sb_data7(p1) \
	.long	p1(0xe1),p1(0xf8),p1(0x98),p1(0x11),p1(0x69),p1(0xd9),p1(0x8e),p1(0x94) ;\
	.long	p1(0x9b),p1(0x1e),p1(0x87),p1(0xe9),p1(0xce),p1(0x55),p1(0x28),p1(0xdf) ;\
	.long	p1(0x8c),p1(0xa1),p1(0x89),p1(0x0d),p1(0xbf),p1(0xe6),p1(0x42),p1(0x68) ;\
	.long	p1(0x41),p1(0x99),p1(0x2d),p1(0x0f),p1(0xb0),p1(0x54),p1(0xbb),p1(0x16)

// Inverse S-box data - 256 entries

#define ib_data0(p1) \
	.long	p1(0x52),p1(0x09),p1(0x6a),p1(0xd5),p1(0x30),p1(0x36),p1(0xa5),p1(0x38) ;\
	.long	p1(0xbf),p1(0x40),p1(0xa3),p1(0x9e),p1(0x81),p1(0xf3),p1(0xd7),p1(0xfb) ;\
	.long	p1(0x7c),p1(0xe3),p1(0x39),p1(0x82),p1(0x9b),p1(0x2f),p1(0xff),p1(0x87) ;\
	.long	p1(0x34),p1(0x8e),p1(0x43),p1(0x44),p1(0xc4),p1(0xde),p1(0xe9),p1(0xcb)
#define ib_data1(p1) \
	.long	p1(0x54),p1(0x7b),p1(0x94),p1(0x32),p1(0xa6),p1(0xc2),p1(0x23),p1(0x3d) ;\
	.long	p1(0xee),p1(0x4c),p1(0x95),p1(0x0b),p1(0x42),p1(0xfa),p1(0xc3),p1(0x4e) ;\
	.long	p1(0x08),p1(0x2e),p1(0xa1),p1(0x66),p1(0x28),p1(0xd9),p1(0x24),p1(0xb2) ;\
	.long	p1(0x76),p1(0x5b),p1(0xa2),p1(0x49),p1(0x6d),p1(0x8b),p1(0xd1),p1(0x25)
#define ib_data2(p1) \
	.long	p1(0x72),p1(0xf8),p1(0xf6),p1(0x64),p1(0x86),p1(0x68),p1(0x98),p1(0x16) ;\
	.long	p1(0xd4),p1(0xa4),p1(0x5c),p1(0xcc),p1(0x5d),p1(0x65),p1(0xb6),p1(0x92) ;\
	.long	p1(0x6c),p1(0x70),p1(0x48),p1(0x50),p1(0xfd),p1(0xed),p1(0xb9),p1(0xda) ;\
	.long	p1(0x5e),p1(0x15),p1(0x46),p1(0x57),p1(0xa7),p1(0x8d),p1(0x9d),p1(0x84)
#define ib_data3(p1) \
	.long	p1(0x90),p1(0xd8),p1(0xab),p1(0x00),p1(0x8c),p1(0xbc),p1(0xd3),p1(0x0a) ;\
	.long	p1(0xf7),p1(0xe4),p1(0x58),p1(0x05),p1(0xb8),p1(0xb3),p1(0x45),p1(0x06) ;\
	.long	p1(0xd0),p1(0x2c),p1(0x1e),p1(0x8f),p1(0xca),p1(0x3f),p1(0x0f),p1(0x02) ;\
	.long	p1(0xc1),p1(0xaf),p1(0xbd),p1(0x03),p1(0x01),p1(0x13),p1(0x8a),p1(0x6b)
#define ib_data4(p1) \
	.long	p1(0x3a),p1(0x91),p1(0x11),p1(0x41),p1(0x4f),p1(0x67),p1(0xdc),p1(0xea) ;\
	.long	p1(0x97),p1(0xf2),p1(0xcf),p1(0xce),p1(0xf0),p1(0xb4),p1(0xe6),p1(0x73) ;\
	.long	p1(0x96),p1(0xac),p1(0x74),p1(0x22),p1(0xe7),p1(0xad),p1(0x35),p1(0x85) ;\
	.long	p1(0xe2),p1(0xf9),p1(0x37),p1(0xe8),p1(0x1c),p1(0x75),p1(0xdf),p1(0x6e)
#define ib_data5(p1) \
	.long	p1(0x47),p1(0xf1),p1(0x1a),p1(0x71),p1(0x1d),p1(0x29),p1(0xc5),p1(0x89) ;\
	.long	p1(0x6f),p1(0xb7),p1(0x62),p1(0x0e),p1(0xaa),p1(0x18),p1(0xbe),p1(0x1b) ;\
	.long	p1(0xfc),p1(0x56),p1(0x3e),p1(0x4b),p1(0xc6),p1(0xd2),p1(0x79),p1(0x20) ;\
	.long	p1(0x9a),p1(0xdb),p1(0xc0),p1(0xfe),p1(0x78),p1(0xcd),p1(0x5a),p1(0xf4)
#define ib_data6(p1) \
	.long	p1(0x1f),p1(0xdd),p1(0xa8),p1(0x33),p1(0x88),p1(0x07),p1(0xc7),p1(0x31) ;\
	.long	p1(0xb1),p1(0x12),p1(0x10),p1(0x59),p1(0x27),p1(0x80),p1(0xec),p1(0x5f) ;\
	.long	p1(0x60),p1(0x51),p1(0x7f),p1(0xa9),p1(0x19),p1(0xb5),p1(0x4a),p1(0x0d) ;\
	.long	p1(0x2d),p1(0xe5),p1(0x7a),p1(0x9f),p1(0x93),p1(0xc9),p1(0x9c),p1(0xef)
#define ib_data7(p1) \
	.long	p1(0xa0),p1(0xe0),p1(0x3b),p1(0x4d),p1(0xae),p1(0x2a),p1(0xf5),p1(0xb0) ;\
	.long	p1(0xc8),p1(0xeb),p1(0xbb),p1(0x3c),p1(0x83),p1(0x53),p1(0x99),p1(0x61) ;\
	.long	p1(0x17),p1(0x2b),p1(0x04),p1(0x7e),p1(0xba),p1(0x77),p1(0xd6),p1(0x26) ;\
	.long	p1(0xe1),p1(0x69),p1(0x14),p1(0x63),p1(0x55),p1(0x21),p1(0x0c),p1(0x7d)

// The rcon_table (needed for the key schedule)
//
// Here is original Dr Brian Gladman's source code:
//	_rcon_tab:
//	%assign x   1
//	%rep 29
//	    dd  x
//	%assign x f2(x)
//	%endrep
//
// Here is precomputed output (it's more portable this way):

	.section .rodata
	.align	ALIGN32BYTES
aes_rcon_tab:
	.long	0x01,0x02,0x04,0x08,0x10,0x20,0x40,0x80
	.long	0x1b,0x36,0x6c,0xd8,0xab,0x4d,0x9a,0x2f
	.long	0x5e,0xbc,0x63,0xc6,0x97,0x35,0x6a,0xd4
	.long	0xb3,0x7d,0xfa,0xef,0xc5

// The forward xor tables

	.align	ALIGN32BYTES
aes_ft_tab:
	sb_data0(u0)
	sb_data1(u0)
	sb_data2(u0)
	sb_data3(u0)
	sb_data4(u0)
	sb_data5(u0)
	sb_data6(u0)
	sb_data7(u0)

	sb_data0(u1)
	sb_data1(u1)
	sb_data2(u1)
	sb_data3(u1)
	sb_data4(u1)
	sb_data5(u1)
	sb_data6(u1)
	sb_data7(u1)

	sb_data0(u2)
	sb_data1(u2)
	sb_data2(u2)
	sb_data3(u2)
	sb_data4(u2)
	sb_data5(u2)
	sb_data6(u2)
	sb_data7(u2)

	sb_data0(u3)
	sb_data1(u3)
	sb_data2(u3)
	sb_data3(u3)
	sb_data4(u3)
	sb_data5(u3)
	sb_data6(u3)
	sb_data7(u3)

	.align	ALIGN32BYTES
aes_fl_tab:
	sb_data0(w0)
	sb_data1(w0)
	sb_data2(w0)
	sb_data3(w0)
	sb_data4(w0)
	sb_data5(w0)
	sb_data6(w0)
	sb_data7(w0)

	sb_data0(w1)
	sb_data1(w1)
	sb_data2(w1)
	sb_data3(w1)
	sb_data4(w1)
	sb_data5(w1)
	sb_data6(w1)
	sb_data7(w1)

	sb_data0(w2)
	sb_data1(w2)
	sb_data2(w2)
	sb_data3(w2)
	sb_data4(w2)
	sb_data5(w2)
	sb_data6(w2)
	sb_data7(w2)

	sb_data0(w3)
	sb_data1(w3)
	sb_data2(w3)
	sb_data3(w3)
	sb_data4(w3)
	sb_data5(w3)
	sb_data6(w3)
	sb_data7(w3)

// The inverse xor tables

	.align	ALIGN32BYTES
aes_it_tab:
	ib_data0(v0)
	ib_data1(v0)
	ib_data2(v0)
	ib_data3(v0)
	ib_data4(v0)
	ib_data5(v0)
	ib_data6(v0)
	ib_data7(v0)

	ib_data0(v1)
	ib_data1(v1)
	ib_data2(v1)
	ib_data3(v1)
	ib_data4(v1)
	ib_data5(v1)
	ib_data6(v1)
	ib_data7(v1)

	ib_data0(v2)
	ib_data1(v2)
	ib_data2(v2)
	ib_data3(v2)
	ib_data4(v2)
	ib_data5(v2)
	ib_data6(v2)
	ib_data7(v2)

	ib_data0(v3)
	ib_data1(v3)
	ib_data2(v3)
	ib_data3(v3)
	ib_data4(v3)
	ib_data5(v3)
	ib_data6(v3)
	ib_data7(v3)

	.align	ALIGN32BYTES
aes_il_tab:
	ib_data0(w0)
	ib_data1(w0)
	ib_data2(w0)
	ib_data3(w0)
	ib_data4(w0)
	ib_data5(w0)
	ib_data6(w0)
	ib_data7(w0)

	ib_data0(w1)
	ib_data1(w1)
	ib_data2(w1)
	ib_data3(w1)
	ib_data4(w1)
	ib_data5(w1)
	ib_data6(w1)
	ib_data7(w1)

	ib_data0(w2)
	ib_data1(w2)
	ib_data2(w2)
	ib_data3(w2)
	ib_data4(w2)
	ib_data5(w2)
	ib_data6(w2)
	ib_data7(w2)

	ib_data0(w3)
	ib_data1(w3)
	ib_data2(w3)
	ib_data3(w3)
	ib_data4(w3)
	ib_data5(w3)
	ib_data6(w3)
	ib_data7(w3)

// The inverse mix column tables

	.align	ALIGN32BYTES
aes_im_tab:
	im_data0(v0)
	im_data1(v0)
	im_data2(v0)
	im_data3(v0)
	im_data4(v0)
	im_data5(v0)
	im_data6(v0)
	im_data7(v0)

	im_data0(v1)
	im_data1(v1)
	im_data2(v1)
	im_data3(v1)
	im_data4(v1)
	im_data5(v1)
	im_data6(v1)
	im_data7(v1)

	im_data0(v2)
	im_data1(v2)
	im_data2(v2)
	im_data3(v2)
	im_data4(v2)
	im_data5(v2)
	im_data6(v2)
	im_data7(v2)

	im_data0(v3)
	im_data1(v3)
	im_data2(v3)
	im_data3(v3)
	im_data4(v3)
	im_data5(v3)
	im_data6(v3)
	im_data7(v3)