crypto: crc32c-pclmul - Shrink K_table to 32-bit words

There's no need for the K_table to be made of 64-bit words.  For some
reason, the original authors didn't fully reduce the values modulo the
CRC32C polynomial, and so had some 33-bit values in there.  They can
all be reduced to 32 bits.

Doing that cuts the table size in half.  Since the code depends on both
pclmulq and crc32, SSE 4.1 is obviously present, so we can use pmovzxdq
to fetch it in the correct format.

This adds (measured on Ivy Bridge) 1 cycle per main loop iteration
(CRC of up to 3K bytes), less than 0.2%.  The hope is that the reduced
D-cache footprint will make up the loss in other code.

Two other related fixes:
* K_table is read-only, so belongs in .rodata, and
* There's no need for more than 8-byte alignment
Acked-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: George Spelvin <linux@horizon.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

arch/x86/crypto/crc32c-pcl-intel-asm_64.S

@@ -72,6 +72,7 @@
 
 # unsigned int crc_pcl(u8 *buffer, int len, unsigned int crc_init);
 
+.text
 ENTRY(crc_pcl)
 #define    bufp		%rdi
 #define    bufp_dw	%edi
@@ -216,15 +217,11 @@ LABEL crc_ %i
 	## 4) Combine three results:
 	################################################################
 
-	lea	(K_table-16)(%rip), bufp	# first entry is for idx 1
+	lea	(K_table-8)(%rip), bufp		# first entry is for idx 1
 	shlq    $3, %rax			# rax *= 8
-	subq    %rax, tmp			# tmp -= rax*8
-	shlq    $1, %rax
-	subq    %rax, tmp			# tmp -= rax*16
-						# (total tmp -= rax*24)
-	addq    %rax, bufp
-
-	movdqa  (bufp), %xmm0			# 2 consts: K1:K2
+	pmovzxdq (bufp,%rax), %xmm0		# 2 consts: K1:K2
+	leal	(%eax,%eax,2), %eax		# rax *= 3 (total *24)
+	subq    %rax, tmp			# tmp -= rax*24
 
 	movq    crc_init, %xmm1			# CRC for block 1
 	PCLMULQDQ 0x00,%xmm0,%xmm1		# Multiply by K2
@@ -238,9 +235,9 @@ LABEL crc_ %i
 	mov     crc2, crc_init
 	crc32   %rax, crc_init
 
-################################################################
-## 5) Check for end:
-################################################################
+	################################################################
+	## 5) Check for end:
+	################################################################
 
 LABEL crc_ 0
 	mov     tmp, len
@@ -331,136 +328,136 @@ ENDPROC(crc_pcl)
 
 	################################################################
 	## PCLMULQDQ tables
-	## Table is 128 entries x 2 quad words each
+	## Table is 128 entries x 2 words (8 bytes) each
 	################################################################
-.data
-.align 64
+.section	.rotata, "a", %progbits
+.align 8
 K_table:
-        .quad 0x14cd00bd6,0x105ec76f0
-        .quad 0x0ba4fc28e,0x14cd00bd6
-        .quad 0x1d82c63da,0x0f20c0dfe
-        .quad 0x09e4addf8,0x0ba4fc28e
-        .quad 0x039d3b296,0x1384aa63a
-        .quad 0x102f9b8a2,0x1d82c63da
-        .quad 0x14237f5e6,0x01c291d04
-        .quad 0x00d3b6092,0x09e4addf8
-        .quad 0x0c96cfdc0,0x0740eef02
-        .quad 0x18266e456,0x039d3b296
-        .quad 0x0daece73e,0x0083a6eec
-        .quad 0x0ab7aff2a,0x102f9b8a2
-        .quad 0x1248ea574,0x1c1733996
-        .quad 0x083348832,0x14237f5e6
-        .quad 0x12c743124,0x02ad91c30
-        .quad 0x0b9e02b86,0x00d3b6092
-        .quad 0x018b33a4e,0x06992cea2
-        .quad 0x1b331e26a,0x0c96cfdc0
-        .quad 0x17d35ba46,0x07e908048
-        .quad 0x1bf2e8b8a,0x18266e456
-        .quad 0x1a3e0968a,0x11ed1f9d8
-        .quad 0x0ce7f39f4,0x0daece73e
-        .quad 0x061d82e56,0x0f1d0f55e
-        .quad 0x0d270f1a2,0x0ab7aff2a
-        .quad 0x1c3f5f66c,0x0a87ab8a8
-        .quad 0x12ed0daac,0x1248ea574
-        .quad 0x065863b64,0x08462d800
-        .quad 0x11eef4f8e,0x083348832
-        .quad 0x1ee54f54c,0x071d111a8
-        .quad 0x0b3e32c28,0x12c743124
-        .quad 0x0064f7f26,0x0ffd852c6
-        .quad 0x0dd7e3b0c,0x0b9e02b86
-        .quad 0x0f285651c,0x0dcb17aa4
-        .quad 0x010746f3c,0x018b33a4e
-        .quad 0x1c24afea4,0x0f37c5aee
-        .quad 0x0271d9844,0x1b331e26a
-        .quad 0x08e766a0c,0x06051d5a2
-        .quad 0x093a5f730,0x17d35ba46
-        .quad 0x06cb08e5c,0x11d5ca20e
-        .quad 0x06b749fb2,0x1bf2e8b8a
-        .quad 0x1167f94f2,0x021f3d99c
-        .quad 0x0cec3662e,0x1a3e0968a
-        .quad 0x19329634a,0x08f158014
-        .quad 0x0e6fc4e6a,0x0ce7f39f4
-        .quad 0x08227bb8a,0x1a5e82106
-        .quad 0x0b0cd4768,0x061d82e56
-        .quad 0x13c2b89c4,0x188815ab2
-        .quad 0x0d7a4825c,0x0d270f1a2
-        .quad 0x10f5ff2ba,0x105405f3e
-        .quad 0x00167d312,0x1c3f5f66c
-        .quad 0x0f6076544,0x0e9adf796
-        .quad 0x026f6a60a,0x12ed0daac
-        .quad 0x1a2adb74e,0x096638b34
-        .quad 0x19d34af3a,0x065863b64
-        .quad 0x049c3cc9c,0x1e50585a0
-        .quad 0x068bce87a,0x11eef4f8e
-        .quad 0x1524fa6c6,0x19f1c69dc
-        .quad 0x16cba8aca,0x1ee54f54c
-        .quad 0x042d98888,0x12913343e
-        .quad 0x1329d9f7e,0x0b3e32c28
-        .quad 0x1b1c69528,0x088f25a3a
-        .quad 0x02178513a,0x0064f7f26
-        .quad 0x0e0ac139e,0x04e36f0b0
-        .quad 0x0170076fa,0x0dd7e3b0c
-        .quad 0x141a1a2e2,0x0bd6f81f8
-        .quad 0x16ad828b4,0x0f285651c
-        .quad 0x041d17b64,0x19425cbba
-        .quad 0x1fae1cc66,0x010746f3c
-        .quad 0x1a75b4b00,0x18db37e8a
-        .quad 0x0f872e54c,0x1c24afea4
-        .quad 0x01e41e9fc,0x04c144932
-        .quad 0x086d8e4d2,0x0271d9844
-        .quad 0x160f7af7a,0x052148f02
-        .quad 0x05bb8f1bc,0x08e766a0c
-        .quad 0x0a90fd27a,0x0a3c6f37a
-        .quad 0x0b3af077a,0x093a5f730
-        .quad 0x04984d782,0x1d22c238e
-        .quad 0x0ca6ef3ac,0x06cb08e5c
-        .quad 0x0234e0b26,0x063ded06a
-        .quad 0x1d88abd4a,0x06b749fb2
-        .quad 0x04597456a,0x04d56973c
-        .quad 0x0e9e28eb4,0x1167f94f2
-        .quad 0x07b3ff57a,0x19385bf2e
-        .quad 0x0c9c8b782,0x0cec3662e
-        .quad 0x13a9cba9e,0x0e417f38a
-        .quad 0x093e106a4,0x19329634a
-        .quad 0x167001a9c,0x14e727980
-        .quad 0x1ddffc5d4,0x0e6fc4e6a
-        .quad 0x00df04680,0x0d104b8fc
-        .quad 0x02342001e,0x08227bb8a
-        .quad 0x00a2a8d7e,0x05b397730
-        .quad 0x168763fa6,0x0b0cd4768
-        .quad 0x1ed5a407a,0x0e78eb416
-        .quad 0x0d2c3ed1a,0x13c2b89c4
-        .quad 0x0995a5724,0x1641378f0
-        .quad 0x19b1afbc4,0x0d7a4825c
-        .quad 0x109ffedc0,0x08d96551c
-        .quad 0x0f2271e60,0x10f5ff2ba
-        .quad 0x00b0bf8ca,0x00bf80dd2
-        .quad 0x123888b7a,0x00167d312
-        .quad 0x1e888f7dc,0x18dcddd1c
-        .quad 0x002ee03b2,0x0f6076544
-        .quad 0x183e8d8fe,0x06a45d2b2
-        .quad 0x133d7a042,0x026f6a60a
-        .quad 0x116b0f50c,0x1dd3e10e8
-        .quad 0x05fabe670,0x1a2adb74e
-        .quad 0x130004488,0x0de87806c
-        .quad 0x000bcf5f6,0x19d34af3a
-        .quad 0x18f0c7078,0x014338754
-        .quad 0x017f27698,0x049c3cc9c
-        .quad 0x058ca5f00,0x15e3e77ee
-        .quad 0x1af900c24,0x068bce87a
-        .quad 0x0b5cfca28,0x0dd07448e
-        .quad 0x0ded288f8,0x1524fa6c6
-        .quad 0x059f229bc,0x1d8048348
-        .quad 0x06d390dec,0x16cba8aca
-        .quad 0x037170390,0x0a3e3e02c
-        .quad 0x06353c1cc,0x042d98888
-        .quad 0x0c4584f5c,0x0d73c7bea
-        .quad 0x1f16a3418,0x1329d9f7e
-        .quad 0x0531377e2,0x185137662
-        .quad 0x1d8d9ca7c,0x1b1c69528
-        .quad 0x0b25b29f2,0x18a08b5bc
-        .quad 0x19fb2a8b0,0x02178513a
-        .quad 0x1a08fe6ac,0x1da758ae0
-        .quad 0x045cddf4e,0x0e0ac139e
-        .quad 0x1a91647f2,0x169cf9eb0
-        .quad 0x1a0f717c4,0x0170076fa
+	.long 0x493c7d27, 0x00000001
+	.long 0xba4fc28e, 0x493c7d27
+	.long 0xddc0152b, 0xf20c0dfe
+	.long 0x9e4addf8, 0xba4fc28e
+	.long 0x39d3b296, 0x3da6d0cb
+	.long 0x0715ce53, 0xddc0152b
+	.long 0x47db8317, 0x1c291d04
+	.long 0x0d3b6092, 0x9e4addf8
+	.long 0xc96cfdc0, 0x740eef02
+	.long 0x878a92a7, 0x39d3b296
+	.long 0xdaece73e, 0x083a6eec
+	.long 0xab7aff2a, 0x0715ce53
+	.long 0x2162d385, 0xc49f4f67
+	.long 0x83348832, 0x47db8317
+	.long 0x299847d5, 0x2ad91c30
+	.long 0xb9e02b86, 0x0d3b6092
+	.long 0x18b33a4e, 0x6992cea2
+	.long 0xb6dd949b, 0xc96cfdc0
+	.long 0x78d9ccb7, 0x7e908048
+	.long 0xbac2fd7b, 0x878a92a7
+	.long 0xa60ce07b, 0x1b3d8f29
+	.long 0xce7f39f4, 0xdaece73e
+	.long 0x61d82e56, 0xf1d0f55e
+	.long 0xd270f1a2, 0xab7aff2a
+	.long 0xc619809d, 0xa87ab8a8
+	.long 0x2b3cac5d, 0x2162d385
+	.long 0x65863b64, 0x8462d800
+	.long 0x1b03397f, 0x83348832
+	.long 0xebb883bd, 0x71d111a8
+	.long 0xb3e32c28, 0x299847d5
+	.long 0x064f7f26, 0xffd852c6
+	.long 0xdd7e3b0c, 0xb9e02b86
+	.long 0xf285651c, 0xdcb17aa4
+	.long 0x10746f3c, 0x18b33a4e
+	.long 0xc7a68855, 0xf37c5aee
+	.long 0x271d9844, 0xb6dd949b
+	.long 0x8e766a0c, 0x6051d5a2
+	.long 0x93a5f730, 0x78d9ccb7
+	.long 0x6cb08e5c, 0x18b0d4ff
+	.long 0x6b749fb2, 0xbac2fd7b
+	.long 0x1393e203, 0x21f3d99c
+	.long 0xcec3662e, 0xa60ce07b
+	.long 0x96c515bb, 0x8f158014
+	.long 0xe6fc4e6a, 0xce7f39f4
+	.long 0x8227bb8a, 0xa00457f7
+	.long 0xb0cd4768, 0x61d82e56
+	.long 0x39c7ff35, 0x8d6d2c43
+	.long 0xd7a4825c, 0xd270f1a2
+	.long 0x0ab3844b, 0x00ac29cf
+	.long 0x0167d312, 0xc619809d
+	.long 0xf6076544, 0xe9adf796
+	.long 0x26f6a60a, 0x2b3cac5d
+	.long 0xa741c1bf, 0x96638b34
+	.long 0x98d8d9cb, 0x65863b64
+	.long 0x49c3cc9c, 0xe0e9f351
+	.long 0x68bce87a, 0x1b03397f
+	.long 0x57a3d037, 0x9af01f2d
+	.long 0x6956fc3b, 0xebb883bd
+	.long 0x42d98888, 0x2cff42cf
+	.long 0x3771e98f, 0xb3e32c28
+	.long 0xb42ae3d9, 0x88f25a3a
+	.long 0x2178513a, 0x064f7f26
+	.long 0xe0ac139e, 0x4e36f0b0
+	.long 0x170076fa, 0xdd7e3b0c
+	.long 0x444dd413, 0xbd6f81f8
+	.long 0x6f345e45, 0xf285651c
+	.long 0x41d17b64, 0x91c9bd4b
+	.long 0xff0dba97, 0x10746f3c
+	.long 0xa2b73df1, 0x885f087b
+	.long 0xf872e54c, 0xc7a68855
+	.long 0x1e41e9fc, 0x4c144932
+	.long 0x86d8e4d2, 0x271d9844
+	.long 0x651bd98b, 0x52148f02
+	.long 0x5bb8f1bc, 0x8e766a0c
+	.long 0xa90fd27a, 0xa3c6f37a
+	.long 0xb3af077a, 0x93a5f730
+	.long 0x4984d782, 0xd7c0557f
+	.long 0xca6ef3ac, 0x6cb08e5c
+	.long 0x234e0b26, 0x63ded06a
+	.long 0xdd66cbbb, 0x6b749fb2
+	.long 0x4597456a, 0x4d56973c
+	.long 0xe9e28eb4, 0x1393e203
+	.long 0x7b3ff57a, 0x9669c9df
+	.long 0xc9c8b782, 0xcec3662e
+	.long 0x3f70cc6f, 0xe417f38a
+	.long 0x93e106a4, 0x96c515bb
+	.long 0x62ec6c6d, 0x4b9e0f71
+	.long 0xd813b325, 0xe6fc4e6a
+	.long 0x0df04680, 0xd104b8fc
+	.long 0x2342001e, 0x8227bb8a
+	.long 0x0a2a8d7e, 0x5b397730
+	.long 0x6d9a4957, 0xb0cd4768
+	.long 0xe8b6368b, 0xe78eb416
+	.long 0xd2c3ed1a, 0x39c7ff35
+	.long 0x995a5724, 0x61ff0e01
+	.long 0x9ef68d35, 0xd7a4825c
+	.long 0x0c139b31, 0x8d96551c
+	.long 0xf2271e60, 0x0ab3844b
+	.long 0x0b0bf8ca, 0x0bf80dd2
+	.long 0x2664fd8b, 0x0167d312
+	.long 0xed64812d, 0x8821abed
+	.long 0x02ee03b2, 0xf6076544
+	.long 0x8604ae0f, 0x6a45d2b2
+	.long 0x363bd6b3, 0x26f6a60a
+	.long 0x135c83fd, 0xd8d26619
+	.long 0x5fabe670, 0xa741c1bf
+	.long 0x35ec3279, 0xde87806c
+	.long 0x00bcf5f6, 0x98d8d9cb
+	.long 0x8ae00689, 0x14338754
+	.long 0x17f27698, 0x49c3cc9c
+	.long 0x58ca5f00, 0x5bd2011f
+	.long 0xaa7c7ad5, 0x68bce87a
+	.long 0xb5cfca28, 0xdd07448e
+	.long 0xded288f8, 0x57a3d037
+	.long 0x59f229bc, 0xdde8f5b9
+	.long 0x6d390dec, 0x6956fc3b
+	.long 0x37170390, 0xa3e3e02c
+	.long 0x6353c1cc, 0x42d98888
+	.long 0xc4584f5c, 0xd73c7bea
+	.long 0xf48642e9, 0x3771e98f
+	.long 0x531377e2, 0x80ff0093
+	.long 0xdd35bc8d, 0xb42ae3d9
+	.long 0xb25b29f2, 0x8fe4c34d
+	.long 0x9a5ede41, 0x2178513a
+	.long 0xa563905d, 0xdf99fc11
+	.long 0x45cddf4e, 0xe0ac139e
+	.long 0xacfa3103, 0x6c23e841
+	.long 0xa51b6135, 0x170076fa