Merge branch 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto updates from Herbert Xu:
 "Here is the crypto update for 4.8:

  API:
   - first part of skcipher low-level conversions
   - add KPP (Key-agreement Protocol Primitives) interface.

  Algorithms:
   - fix IPsec/cryptd reordering issues that affects aesni
   - RSA no longer does explicit leading zero removal
   - add SHA3
   - add DH
   - add ECDH
   - improve DRBG performance by not doing CTR by hand

  Drivers:
   - add x86 AVX2 multibuffer SHA256/512
   - add POWER8 optimised crc32c
   - add xts support to vmx
   - add DH support to qat
   - add RSA support to caam
   - add Layerscape support to caam
   - add SEC1 AEAD support to talitos
   - improve performance by chaining requests in marvell/cesa
   - add support for Araneus Alea I USB RNG
   - add support for Broadcom BCM5301 RNG
   - add support for Amlogic Meson RNG
   - add support Broadcom NSP SoC RNG"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (180 commits)
  crypto: vmx - Fix aes_p8_xts_decrypt build failure
  crypto: vmx - Ignore generated files
  crypto: vmx - Adding support for XTS
  crypto: vmx - Adding asm subroutines for XTS
  crypto: skcipher - add comment for skcipher_alg->base
  crypto: testmgr - Print akcipher algorithm name
  crypto: marvell - Fix wrong flag used for GFP in mv_cesa_dma_add_iv_op
  crypto: nx - off by one bug in nx_of_update_msc()
  crypto: rsa-pkcs1pad - fix rsa-pkcs1pad request struct
  crypto: scatterwalk - Inline start/map/done
  crypto: scatterwalk - Remove unnecessary BUG in scatterwalk_start
  crypto: scatterwalk - Remove unnecessary advance in scatterwalk_pagedone
  crypto: scatterwalk - Fix test in scatterwalk_done
  crypto: api - Optimise away crypto_yield when hard preemption is on
  crypto: scatterwalk - add no-copy support to copychunks
  crypto: scatterwalk - Remove scatterwalk_bytes_sglen
  crypto: omap - Stop using crypto scatterwalk_bytes_sglen
  crypto: skcipher - Remove top-level givcipher interface
  crypto: user - Remove crypto_lookup_skcipher call
  crypto: cts - Convert to skcipher
  ...

47 files changed, 7582 insertions, 291 deletions

diff --git a/arch/arm/boot/dts/bcm-nsp.dtsi b/arch/arm/boot/dts/bcm-nsp.dtsi
index def9e783b5c6..1ed829e699d4 100644
--- a/arch/arm/boot/dts/bcm-nsp.dtsi
+++ b/arch/arm/boot/dts/bcm-nsp.dtsi
@@ -206,6 +206,11 @@
 			brcm,nand-has-wp;
 		};
 
+		rng: rng@33000 {
+			compatible = "brcm,bcm-nsp-rng";
+			reg = <0x33000 0x14>;
+		};
+
 		ccbtimer0: timer@34000 {
 			compatible = "arm,sp804";
 			reg = <0x34000 0x1000>;
diff --git a/arch/arm/crypto/ghash-ce-glue.c b/arch/arm/crypto/ghash-ce-glue.c
index 03a39fe29246..1568cb5cd870 100644
--- a/arch/arm/crypto/ghash-ce-glue.c
+++ b/arch/arm/crypto/ghash-ce-glue.c
@@ -154,30 +154,23 @@ static int ghash_async_init(struct ahash_request *req)
 	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
+	struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
+	struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
 
-	if (!may_use_simd()) {
-		memcpy(cryptd_req, req, sizeof(*req));
-		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
-		return crypto_ahash_init(cryptd_req);
-	} else {
-		struct shash_desc *desc = cryptd_shash_desc(cryptd_req);
-		struct crypto_shash *child = cryptd_ahash_child(cryptd_tfm);
-
-		desc->tfm = child;
-		desc->flags = req->base.flags;
-		return crypto_shash_init(desc);
-	}
+	desc->tfm = child;
+	desc->flags = req->base.flags;
+	return crypto_shash_init(desc);
 }
 
 static int ghash_async_update(struct ahash_request *req)
 {
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!may_use_simd()) {
-		struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-		struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-		struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
+	if (!may_use_simd() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
 		return crypto_ahash_update(cryptd_req);
@@ -190,12 +183,12 @@ static int ghash_async_update(struct ahash_request *req)
 static int ghash_async_final(struct ahash_request *req)
 {
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
+	struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
+	struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
+	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!may_use_simd()) {
-		struct crypto_ahash *tfm = crypto_ahash_reqtfm(req);
-		struct ghash_async_ctx *ctx = crypto_ahash_ctx(tfm);
-		struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
-
+	if (!may_use_simd() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
 		return crypto_ahash_final(cryptd_req);
@@ -212,7 +205,8 @@ static int ghash_async_digest(struct ahash_request *req)
 	struct ahash_request *cryptd_req = ahash_request_ctx(req);
 	struct cryptd_ahash *cryptd_tfm = ctx->cryptd_tfm;
 
-	if (!may_use_simd()) {
+	if (!may_use_simd() ||
+	    (in_atomic() && cryptd_ahash_queued(cryptd_tfm))) {
 		memcpy(cryptd_req, req, sizeof(*req));
 		ahash_request_set_tfm(cryptd_req, &cryptd_tfm->base);
 		return crypto_ahash_digest(cryptd_req);
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts b/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts
index f895fc02ab06..40846319be69 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a-rdb.dts
@@ -49,6 +49,10 @@
 
 / {
 	model = "LS1043A RDB Board";
+
+	aliases {
+		crypto = &crypto;
+	};
 };
 
 &i2c0 {
diff --git a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
index de0323b48b1e..6bd46c133010 100644
--- a/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
+++ b/arch/arm64/boot/dts/freescale/fsl-ls1043a.dtsi
@@ -159,6 +159,49 @@
 			big-endian;
 		};
 
+		crypto: crypto@1700000 {
+			compatible = "fsl,sec-v5.4", "fsl,sec-v5.0",
+				     "fsl,sec-v4.0";
+			fsl,sec-era = <3>;
+			#address-cells = <1>;
+			#size-cells = <1>;
+			ranges = <0x0 0x00 0x1700000 0x100000>;
+			reg = <0x00 0x1700000 0x0 0x100000>;
+			interrupts = <0 75 0x4>;
+
+			sec_jr0: jr@10000 {
+				compatible = "fsl,sec-v5.4-job-ring",
+					     "fsl,sec-v5.0-job-ring",
+					     "fsl,sec-v4.0-job-ring";
+				reg	   = <0x10000 0x10000>;
+				interrupts = <0 71 0x4>;
+			};
+
+			sec_jr1: jr@20000 {
+				compatible = "fsl,sec-v5.4-job-ring",
+					     "fsl,sec-v5.0-job-ring",
+					     "fsl,sec-v4.0-job-ring";
+				reg	   = <0x20000 0x10000>;
+				interrupts = <0 72 0x4>;
+			};
+
+			sec_jr2: jr@30000 {
+				compatible = "fsl,sec-v5.4-job-ring",
+					     "fsl,sec-v5.0-job-ring",
+					     "fsl,sec-v4.0-job-ring";
+				reg	   = <0x30000 0x10000>;
+				interrupts = <0 73 0x4>;
+			};
+
+			sec_jr3: jr@40000 {
+				compatible = "fsl,sec-v5.4-job-ring",
+					     "fsl,sec-v5.0-job-ring",
+					     "fsl,sec-v4.0-job-ring";
+				reg	   = <0x40000 0x10000>;
+				interrupts = <0 74 0x4>;
+			};
+		};
+
 		dcfg: dcfg@1ee0000 {
 			compatible = "fsl,ls1043a-dcfg", "syscon";
 			reg = <0x0 0x1ee0000 0x0 0x10000>;
diff --git a/arch/arm64/include/asm/io.h b/arch/arm64/include/asm/io.h
index 44be1e03ed65..9b6e408cfa51 100644
--- a/arch/arm64/include/asm/io.h
+++ b/arch/arm64/include/asm/io.h
@@ -174,13 +174,15 @@ extern void __iomem *ioremap_cache(phys_addr_t phys_addr, size_t size);
 #define iounmap				__iounmap
 
 /*
- * io{read,write}{16,32}be() macros
+ * io{read,write}{16,32,64}be() macros
  */
 #define ioread16be(p)		({ __u16 __v = be16_to_cpu((__force __be16)__raw_readw(p)); __iormb(); __v; })
 #define ioread32be(p)		({ __u32 __v = be32_to_cpu((__force __be32)__raw_readl(p)); __iormb(); __v; })
+#define ioread64be(p)		({ __u64 __v = be64_to_cpu((__force __be64)__raw_readq(p)); __iormb(); __v; })
 
 #define iowrite16be(v,p)	({ __iowmb(); __raw_writew((__force __u16)cpu_to_be16(v), p); })
 #define iowrite32be(v,p)	({ __iowmb(); __raw_writel((__force __u32)cpu_to_be32(v), p); })
+#define iowrite64be(v,p)	({ __iowmb(); __raw_writeq((__force __u64)cpu_to_be64(v), p); })
 
 /*
  * Convert a physical pointer to a virtual kernel pointer for /dev/mem
diff --git a/arch/powerpc/crypto/Makefile b/arch/powerpc/crypto/Makefile
index 9c221b69c181..7998c177f0a2 100644
--- a/arch/powerpc/crypto/Makefile
+++ b/arch/powerpc/crypto/Makefile
@@ -9,9 +9,11 @@ obj-$(CONFIG_CRYPTO_MD5_PPC) += md5-ppc.o
 obj-$(CONFIG_CRYPTO_SHA1_PPC) += sha1-powerpc.o
 obj-$(CONFIG_CRYPTO_SHA1_PPC_SPE) += sha1-ppc-spe.o
 obj-$(CONFIG_CRYPTO_SHA256_PPC_SPE) += sha256-ppc-spe.o
+obj-$(CONFIG_CRYPT_CRC32C_VPMSUM) += crc32c-vpmsum.o
 
 aes-ppc-spe-y := aes-spe-core.o aes-spe-keys.o aes-tab-4k.o aes-spe-modes.o aes-spe-glue.o
 md5-ppc-y := md5-asm.o md5-glue.o
 sha1-powerpc-y := sha1-powerpc-asm.o sha1.o
 sha1-ppc-spe-y := sha1-spe-asm.o sha1-spe-glue.o
 sha256-ppc-spe-y := sha256-spe-asm.o sha256-spe-glue.o
+crc32c-vpmsum-y := crc32c-vpmsum_asm.o crc32c-vpmsum_glue.o
diff --git a/arch/powerpc/crypto/aes-spe-regs.h b/arch/powerpc/crypto/aes-spe-regs.h
index 30d217b399c3..2cc3a2caadae 100644
--- a/arch/powerpc/crypto/aes-spe-regs.h
+++ b/arch/powerpc/crypto/aes-spe-regs.h
@@ -18,7 +18,7 @@
 #define rLN r7	/* length of data to be processed			*/
 #define rIP r8	/* potiner to IV (CBC/CTR/XTS modes)			*/
 #define rKT r9	/* pointer to tweak key (XTS mode)			*/
-#define rT0 r11	/* pointers to en-/decrpytion tables			*/
+#define rT0 r11	/* pointers to en-/decryption tables			*/
 #define rT1 r10
 #define rD0 r9	/* data 						*/
 #define rD1 r14
diff --git a/arch/powerpc/crypto/crc32c-vpmsum_asm.S b/arch/powerpc/crypto/crc32c-vpmsum_asm.S
new file mode 100644
index 000000000000..dc640b212299
--- /dev/null
+++ b/arch/powerpc/crypto/crc32c-vpmsum_asm.S
@@ -0,0 +1,1553 @@
+/*
+ * Calculate the checksum of data that is 16 byte aligned and a multiple of
+ * 16 bytes.
+ *
+ * The first step is to reduce it to 1024 bits. We do this in 8 parallel
+ * chunks in order to mask the latency of the vpmsum instructions. If we
+ * have more than 32 kB of data to checksum we repeat this step multiple
+ * times, passing in the previous 1024 bits.
+ *
+ * The next step is to reduce the 1024 bits to 64 bits. This step adds
+ * 32 bits of 0s to the end - this matches what a CRC does. We just
+ * calculate constants that land the data in this 32 bits.
+ *
+ * We then use fixed point Barrett reduction to compute a mod n over GF(2)
+ * for n = CRC using POWER8 instructions. We use x = 32.
+ *
+ * http://en.wikipedia.org/wiki/Barrett_reduction
+ *
+ * Copyright (C) 2015 Anton Blanchard <anton@au.ibm.com>, IBM
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+#include <asm/ppc_asm.h>
+#include <asm/ppc-opcode.h>
+
+	.section	.rodata
+.balign 16
+
+.byteswap_constant:
+	/* byte reverse permute constant */
+	.octa 0x0F0E0D0C0B0A09080706050403020100
+
+#define MAX_SIZE	32768
+.constants:
+
+	/* Reduce 262144 kbits to 1024 bits */
+	/* x^261120 mod p(x)` << 1, x^261184 mod p(x)` << 1 */
+	.octa 0x00000000b6ca9e20000000009c37c408
+
+	/* x^260096 mod p(x)` << 1, x^260160 mod p(x)` << 1 */
+	.octa 0x00000000350249a800000001b51df26c
+
+	/* x^259072 mod p(x)` << 1, x^259136 mod p(x)` << 1 */
+	.octa 0x00000001862dac54000000000724b9d0
+
+	/* x^258048 mod p(x)` << 1, x^258112 mod p(x)` << 1 */
+	.octa 0x00000001d87fb48c00000001c00532fe
+
+	/* x^257024 mod p(x)` << 1, x^257088 mod p(x)` << 1 */
+	.octa 0x00000001f39b699e00000000f05a9362
+
+	/* x^256000 mod p(x)` << 1, x^256064 mod p(x)` << 1 */
+	.octa 0x0000000101da11b400000001e1007970
+
+	/* x^254976 mod p(x)` << 1, x^255040 mod p(x)` << 1 */
+	.octa 0x00000001cab571e000000000a57366ee
+
+	/* x^253952 mod p(x)` << 1, x^254016 mod p(x)` << 1 */
+	.octa 0x00000000c7020cfe0000000192011284
+
+	/* x^252928 mod p(x)` << 1, x^252992 mod p(x)` << 1 */
+	.octa 0x00000000cdaed1ae0000000162716d9a
+
+	/* x^251904 mod p(x)` << 1, x^251968 mod p(x)` << 1 */
+	.octa 0x00000001e804effc00000000cd97ecde
+
+	/* x^250880 mod p(x)` << 1, x^250944 mod p(x)` << 1 */
+	.octa 0x0000000077c3ea3a0000000058812bc0
+
+	/* x^249856 mod p(x)` << 1, x^249920 mod p(x)` << 1 */
+	.octa 0x0000000068df31b40000000088b8c12e
+
+	/* x^248832 mod p(x)` << 1, x^248896 mod p(x)` << 1 */
+	.octa 0x00000000b059b6c200000001230b234c
+
+	/* x^247808 mod p(x)` << 1, x^247872 mod p(x)` << 1 */
+	.octa 0x0000000145fb8ed800000001120b416e
+
+	/* x^246784 mod p(x)` << 1, x^246848 mod p(x)` << 1 */
+	.octa 0x00000000cbc0916800000001974aecb0
+
+	/* x^245760 mod p(x)` << 1, x^245824 mod p(x)` << 1 */
+	.octa 0x000000005ceeedc2000000008ee3f226
+
+	/* x^244736 mod p(x)` << 1, x^244800 mod p(x)` << 1 */
+	.octa 0x0000000047d74e8600000001089aba9a
+
+	/* x^243712 mod p(x)` << 1, x^243776 mod p(x)` << 1 */
+	.octa 0x00000001407e9e220000000065113872
+
+	/* x^242688 mod p(x)` << 1, x^242752 mod p(x)` << 1 */
+	.octa 0x00000001da967bda000000005c07ec10
+
+	/* x^241664 mod p(x)` << 1, x^241728 mod p(x)` << 1 */
+	.octa 0x000000006c8983680000000187590924
+
+	/* x^240640 mod p(x)` << 1, x^240704 mod p(x)` << 1 */
+	.octa 0x00000000f2d14c9800000000e35da7c6
+
+	/* x^239616 mod p(x)` << 1, x^239680 mod p(x)` << 1 */
+	.octa 0x00000001993c6ad4000000000415855a
+
+	/* x^238592 mod p(x)` << 1, x^238656 mod p(x)` << 1 */
+	.octa 0x000000014683d1ac0000000073617758
+
+	/* x^237568 mod p(x)` << 1, x^237632 mod p(x)` << 1 */
+	.octa 0x00000001a7c93e6c0000000176021d28
+
+	/* x^236544 mod p(x)` << 1, x^236608 mod p(x)` << 1 */
+	.octa 0x000000010211e90a00000001c358fd0a
+
+	/* x^235520 mod p(x)` << 1, x^235584 mod p(x)` << 1 */
+	.octa 0x000000001119403e00000001ff7a2c18
+
+	/* x^234496 mod p(x)` << 1, x^234560 mod p(x)` << 1 */
+	.octa 0x000000001c3261aa00000000f2d9f7e4
+
+	/* x^233472 mod p(x)` << 1, x^233536 mod p(x)` << 1 */
+	.octa 0x000000014e37a634000000016cf1f9c8
+
+	/* x^232448 mod p(x)` << 1, x^232512 mod p(x)` << 1 */
+	.octa 0x0000000073786c0c000000010af9279a
+
+	/* x^231424 mod p(x)` << 1, x^231488 mod p(x)` << 1 */
+	.octa 0x000000011dc037f80000000004f101e8
+
+	/* x^230400 mod p(x)` << 1, x^230464 mod p(x)` << 1 */
+	.octa 0x0000000031433dfc0000000070bcf184
+
+	/* x^229376 mod p(x)` << 1, x^229440 mod p(x)` << 1 */
+	.octa 0x000000009cde8348000000000a8de642
+
+	/* x^228352 mod p(x)` << 1, x^228416 mod p(x)` << 1 */
+	.octa 0x0000000038d3c2a60000000062ea130c
+
+	/* x^227328 mod p(x)` << 1, x^227392 mod p(x)` << 1 */
+	.octa 0x000000011b25f26000000001eb31cbb2
+
+	/* x^226304 mod p(x)` << 1, x^226368 mod p(x)` << 1 */
+	.octa 0x000000001629e6f00000000170783448
+
+	/* x^225280 mod p(x)` << 1, x^225344 mod p(x)` << 1 */
+	.octa 0x0000000160838b4c00000001a684b4c6
+
+	/* x^224256 mod p(x)` << 1, x^224320 mod p(x)` << 1 */
+	.octa 0x000000007a44011c00000000253ca5b4
+
+	/* x^223232 mod p(x)` << 1, x^223296 mod p(x)` << 1 */
+	.octa 0x00000000226f417a0000000057b4b1e2
+
+	/* x^222208 mod p(x)` << 1, x^222272 mod p(x)` << 1 */
+	.octa 0x0000000045eb2eb400000000b6bd084c
+
+	/* x^221184 mod p(x)` << 1, x^221248 mod p(x)` << 1 */
+	.octa 0x000000014459d70c0000000123c2d592
+
+	/* x^220160 mod p(x)` << 1, x^220224 mod p(x)` << 1 */
+	.octa 0x00000001d406ed8200000000159dafce
+
+	/* x^219136 mod p(x)` << 1, x^219200 mod p(x)` << 1 */
+	.octa 0x0000000160c8e1a80000000127e1a64e
+
+	/* x^218112 mod p(x)` << 1, x^218176 mod p(x)` << 1 */
+	.octa 0x0000000027ba80980000000056860754
+
+	/* x^217088 mod p(x)` << 1, x^217152 mod p(x)` << 1 */
+	.octa 0x000000006d92d01800000001e661aae8
+
+	/* x^216064 mod p(x)` << 1, x^216128 mod p(x)` << 1 */
+	.octa 0x000000012ed7e3f200000000f82c6166
+
+	/* x^215040 mod p(x)` << 1, x^215104 mod p(x)` << 1 */
+	.octa 0x000000002dc8778800000000c4f9c7ae
+
+	/* x^214016 mod p(x)` << 1, x^214080 mod p(x)` << 1 */
+	.octa 0x0000000018240bb80000000074203d20
+
+	/* x^212992 mod p(x)` << 1, x^213056 mod p(x)` << 1 */
+	.octa 0x000000001ad381580000000198173052
+
+	/* x^211968 mod p(x)` << 1, x^212032 mod p(x)` << 1 */
+	.octa 0x00000001396b78f200000001ce8aba54
+
+	/* x^210944 mod p(x)` << 1, x^211008 mod p(x)` << 1 */
+	.octa 0x000000011a68133400000001850d5d94
+
+	/* x^209920 mod p(x)` << 1, x^209984 mod p(x)` << 1 */
+	.octa 0x000000012104732e00000001d609239c
+
+	/* x^208896 mod p(x)` << 1, x^208960 mod p(x)` << 1 */
+	.octa 0x00000000a140d90c000000001595f048
+
+	/* x^207872 mod p(x)` << 1, x^207936 mod p(x)` << 1 */
+	.octa 0x00000001b7215eda0000000042ccee08
+
+	/* x^206848 mod p(x)` << 1, x^206912 mod p(x)` << 1 */
+	.octa 0x00000001aaf1df3c000000010a389d74
+
+	/* x^205824 mod p(x)` << 1, x^205888 mod p(x)` << 1 */
+	.octa 0x0000000029d15b8a000000012a840da6
+
+	/* x^204800 mod p(x)` << 1, x^204864 mod p(x)` << 1 */
+	.octa 0x00000000f1a96922000000001d181c0c
+
+	/* x^203776 mod p(x)` << 1, x^203840 mod p(x)` << 1 */
+	.octa 0x00000001ac80d03c0000000068b7d1f6
+
+	/* x^202752 mod p(x)` << 1, x^202816 mod p(x)` << 1 */
+	.octa 0x000000000f11d56a000000005b0f14fc
+
+	/* x^201728 mod p(x)` << 1, x^201792 mod p(x)` << 1 */
+	.octa 0x00000001f1c022a20000000179e9e730
+
+	/* x^200704 mod p(x)` << 1, x^200768 mod p(x)` << 1 */
+	.octa 0x0000000173d00ae200000001ce1368d6
+
+	/* x^199680 mod p(x)` << 1, x^199744 mod p(x)` << 1 */
+	.octa 0x00000001d4ffe4ac0000000112c3a84c
+
+	/* x^198656 mod p(x)` << 1, x^198720 mod p(x)` << 1 */
+	.octa 0x000000016edc5ae400000000de940fee
+
+	/* x^197632 mod p(x)` << 1, x^197696 mod p(x)` << 1 */
+	.octa 0x00000001f1a0214000000000fe896b7e
+
+	/* x^196608 mod p(x)` << 1, x^196672 mod p(x)` << 1 */
+	.octa 0x00000000ca0b28a000000001f797431c
+
+	/* x^195584 mod p(x)` << 1, x^195648 mod p(x)` << 1 */
+	.octa 0x00000001928e30a20000000053e989ba
+
+	/* x^194560 mod p(x)` << 1, x^194624 mod p(x)` << 1 */
+	.octa 0x0000000097b1b002000000003920cd16
+
+	/* x^193536 mod p(x)` << 1, x^193600 mod p(x)` << 1 */
+	.octa 0x00000000b15bf90600000001e6f579b8
+
+	/* x^192512 mod p(x)` << 1, x^192576 mod p(x)` << 1 */
+	.octa 0x00000000411c5d52000000007493cb0a
+
+	/* x^191488 mod p(x)` << 1, x^191552 mod p(x)` << 1 */
+	.octa 0x00000001c36f330000000001bdd376d8
+
+	/* x^190464 mod p(x)` << 1, x^190528 mod p(x)` << 1 */
+	.octa 0x00000001119227e0000000016badfee6
+
+	/* x^189440 mod p(x)` << 1, x^189504 mod p(x)` << 1 */
+	.octa 0x00000000114d47020000000071de5c58
+
+	/* x^188416 mod p(x)` << 1, x^188480 mod p(x)` << 1 */
+	.octa 0x00000000458b5b9800000000453f317c
+
+	/* x^187392 mod p(x)` << 1, x^187456 mod p(x)` << 1 */
+	.octa 0x000000012e31fb8e0000000121675cce
+
+	/* x^186368 mod p(x)` << 1, x^186432 mod p(x)` << 1 */
+	.octa 0x000000005cf619d800000001f409ee92
+
+	/* x^185344 mod p(x)` << 1, x^185408 mod p(x)` << 1 */
+	.octa 0x0000000063f4d8b200000000f36b9c88
+
+	/* x^184320 mod p(x)` << 1, x^184384 mod p(x)` << 1 */
+	.octa 0x000000004138dc8a0000000036b398f4
+
+	/* x^183296 mod p(x)` << 1, x^183360 mod p(x)` << 1 */
+	.octa 0x00000001d29ee8e000000001748f9adc
+
+	/* x^182272 mod p(x)` << 1, x^182336 mod p(x)` << 1 */
+	.octa 0x000000006a08ace800000001be94ec00
+
+	/* x^181248 mod p(x)` << 1, x^181312 mod p(x)` << 1 */
+	.octa 0x0000000127d4201000000000b74370d6
+
+	/* x^180224 mod p(x)` << 1, x^180288 mod p(x)` << 1 */
+	.octa 0x0000000019d76b6200000001174d0b98
+
+	/* x^179200 mod p(x)` << 1, x^179264 mod p(x)` << 1 */
+	.octa 0x00000001b1471f6e00000000befc06a4
+
+	/* x^178176 mod p(x)` << 1, x^178240 mod p(x)` << 1 */
+	.octa 0x00000001f64c19cc00000001ae125288
+
+	/* x^177152 mod p(x)` << 1, x^177216 mod p(x)` << 1 */
+	.octa 0x00000000003c0ea00000000095c19b34
+
+	/* x^176128 mod p(x)` << 1, x^176192 mod p(x)` << 1 */
+	.octa 0x000000014d73abf600000001a78496f2
+
+	/* x^175104 mod p(x)` << 1, x^175168 mod p(x)` << 1 */
+	.octa 0x00000001620eb84400000001ac5390a0
+
+	/* x^174080 mod p(x)` << 1, x^174144 mod p(x)` << 1 */
+	.octa 0x0000000147655048000000002a80ed6e
+
+	/* x^173056 mod p(x)` << 1, x^173120 mod p(x)` << 1 */
+	.octa 0x0000000067b5077e00000001fa9b0128
+
+	/* x^172032 mod p(x)` << 1, x^172096 mod p(x)` << 1 */
+	.octa 0x0000000010ffe20600000001ea94929e
+
+	/* x^171008 mod p(x)` << 1, x^171072 mod p(x)` << 1 */
+	.octa 0x000000000fee8f1e0000000125f4305c
+
+	/* x^169984 mod p(x)` << 1, x^170048 mod p(x)` << 1 */
+	.octa 0x00000001da26fbae00000001471e2002
+
+	/* x^168960 mod p(x)` << 1, x^169024 mod p(x)` << 1 */
+	.octa 0x00000001b3a8bd880000000132d2253a
+
+	/* x^167936 mod p(x)` << 1, x^168000 mod p(x)` << 1 */
+	.octa 0x00000000e8f3898e00000000f26b3592
+
+	/* x^166912 mod p(x)` << 1, x^166976 mod p(x)` << 1 */
+	.octa 0x00000000b0d0d28c00000000bc8b67b0
+
+	/* x^165888 mod p(x)` << 1, x^165952 mod p(x)` << 1 */
+	.octa 0x0000000030f2a798000000013a826ef2
+
+	/* x^164864 mod p(x)` << 1, x^164928 mod p(x)` << 1 */
+	.octa 0x000000000fba10020000000081482c84
+
+	/* x^163840 mod p(x)` << 1, x^163904 mod p(x)` << 1 */
+	.octa 0x00000000bdb9bd7200000000e77307c2
+
+	/* x^162816 mod p(x)` << 1, x^162880 mod p(x)` << 1 */
+	.octa 0x0000000075d3bf5a00000000d4a07ec8
+
+	/* x^161792 mod p(x)` << 1, x^161856 mod p(x)` << 1 */
+	.octa 0x00000000ef1f98a00000000017102100
+
+	/* x^160768 mod p(x)` << 1, x^160832 mod p(x)` << 1 */
+	.octa 0x00000000689c760200000000db406486
+
+	/* x^159744 mod p(x)` << 1, x^159808 mod p(x)` << 1 */
+	.octa 0x000000016d5fa5fe0000000192db7f88
+
+	/* x^158720 mod p(x)` << 1, x^158784 mod p(x)` << 1 */
+	.octa 0x00000001d0d2b9ca000000018bf67b1e
+
+	/* x^157696 mod p(x)` << 1, x^157760 mod p(x)` << 1 */
+	.octa 0x0000000041e7b470000000007c09163e
+
+	/* x^156672 mod p(x)` << 1, x^156736 mod p(x)` << 1 */
+	.octa 0x00000001cbb6495e000000000adac060
+
+	/* x^155648 mod p(x)` << 1, x^155712 mod p(x)` << 1 */
+	.octa 0x000000010052a0b000000000bd8316ae
+
+	/* x^154624 mod p(x)` << 1, x^154688 mod p(x)` << 1 */
+	.octa 0x00000001d8effb5c000000019f09ab54
+
+	/* x^153600 mod p(x)` << 1, x^153664 mod p(x)` << 1 */
+	.octa 0x00000001d969853c0000000125155542
+
+	/* x^152576 mod p(x)` << 1, x^152640 mod p(x)` << 1 */
+	.octa 0x00000000523ccce2000000018fdb5882
+
+	/* x^151552 mod p(x)` << 1, x^151616 mod p(x)` << 1 */
+	.octa 0x000000001e2436bc00000000e794b3f4
+
+	/* x^150528 mod p(x)` << 1, x^150592 mod p(x)` << 1 */
+	.octa 0x00000000ddd1c3a2000000016f9bb022
+
+	/* x^149504 mod p(x)` << 1, x^149568 mod p(x)` << 1 */
+	.octa 0x0000000019fcfe3800000000290c9978
+
+	/* x^148480 mod p(x)` << 1, x^148544 mod p(x)` << 1 */
+	.octa 0x00000001ce95db640000000083c0f350
+