Merge git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6

Pull crypto update from Herbert Xu:
 "Here is the crypto update for 3.12:

   - Added MODULE_SOFTDEP to allow pre-loading of modules.
   - Reinstated crct10dif driver using the module softdep feature.
   - Allow via rng driver to be auto-loaded.

   - Split large input data when necessary in nx.
   - Handle zero length messages correctly for GCM/XCBC in nx.
   - Handle SHA-2 chunks bigger than block size properly in nx.

   - Handle unaligned lengths in omap-aes.
   - Added SHA384/SHA512 to omap-sham.
   - Added OMAP5/AM43XX SHAM support.
   - Added OMAP4 TRNG support.

   - Misc fixes"

* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (66 commits)
  Reinstate "crypto: crct10dif - Wrap crc_t10dif function all to use crypto transform framework"
  hwrng: via - Add MODULE_DEVICE_TABLE
  crypto: fcrypt - Fix bitoperation for compilation with clang
  crypto: nx - fix SHA-2 for chunks bigger than block size
  crypto: nx - fix GCM for zero length messages
  crypto: nx - fix XCBC for zero length messages
  crypto: nx - fix limits to sg lists for AES-CCM
  crypto: nx - fix limits to sg lists for AES-XCBC
  crypto: nx - fix limits to sg lists for AES-GCM
  crypto: nx - fix limits to sg lists for AES-CTR
  crypto: nx - fix limits to sg lists for AES-CBC
  crypto: nx - fix limits to sg lists for AES-ECB
  crypto: nx - add offset to nx_build_sg_lists()
  padata - Register hotcpu notifier after initialization
  padata - share code between CPU_ONLINE and CPU_DOWN_FAILED, same to CPU_DOWN_PREPARE and CPU_UP_CANCELED
  hwrng: omap - reorder OMAP TRNG driver code
  crypto: omap-sham - correct dma burst size
  crypto: omap-sham - Enable Polling mode if DMA fails
  crypto: tegra-aes - bitwise vs logical and
  crypto: sahara - checking the wrong variable
  ...

11 files changed, 305 insertions, 34 deletions

diff --git a/crypto/Kconfig b/crypto/Kconfig
index aca01164f00..69ce573f122 100644
--- a/crypto/Kconfig
+++ b/crypto/Kconfig
@@ -376,6 +376,25 @@ config CRYPTO_CRC32_PCLMUL
 	  which will enable any routine to use the CRC-32-IEEE 802.3 checksum
 	  and gain better performance as compared with the table implementation.
 
+config CRYPTO_CRCT10DIF
+	tristate "CRCT10DIF algorithm"
+	select CRYPTO_HASH
+	help
+	  CRC T10 Data Integrity Field computation is being cast as
+	  a crypto transform.  This allows for faster crc t10 diff
+	  transforms to be used if they are available.
+
+config CRYPTO_CRCT10DIF_PCLMUL
+	tristate "CRCT10DIF PCLMULQDQ hardware acceleration"
+	depends on X86 && 64BIT && CRC_T10DIF
+	select CRYPTO_HASH
+	help
+	  For x86_64 processors with SSE4.2 and PCLMULQDQ supported,
+	  CRC T10 DIF PCLMULQDQ computation can be hardware
+	  accelerated PCLMULQDQ instruction. This option will create
+	  'crct10dif-plcmul' module, which is faster when computing the
+	  crct10dif checksum as compared with the generic table implementation.
+
 config CRYPTO_GHASH
 	tristate "GHASH digest algorithm"
 	select CRYPTO_GF128MUL
diff --git a/crypto/Makefile b/crypto/Makefile
index 2ba0df2f908..2d5ed08a239 100644
--- a/crypto/Makefile
+++ b/crypto/Makefile
@@ -83,6 +83,7 @@ obj-$(CONFIG_CRYPTO_ZLIB) += zlib.o
 obj-$(CONFIG_CRYPTO_MICHAEL_MIC) += michael_mic.o
 obj-$(CONFIG_CRYPTO_CRC32C) += crc32c.o
 obj-$(CONFIG_CRYPTO_CRC32) += crc32.o
+obj-$(CONFIG_CRYPTO_CRCT10DIF) += crct10dif.o
 obj-$(CONFIG_CRYPTO_AUTHENC) += authenc.o authencesn.o
 obj-$(CONFIG_CRYPTO_LZO) += lzo.o
 obj-$(CONFIG_CRYPTO_LZ4) += lz4.o
diff --git a/crypto/aes_generic.c b/crypto/aes_generic.c
index 47f2e5c7175..fd0d6b45497 100644
--- a/crypto/aes_generic.c
+++ b/crypto/aes_generic.c
@@ -62,7 +62,7 @@ static inline u8 byte(const u32 x, const unsigned n)
 
 static const u32 rco_tab[10] = { 1, 2, 4, 8, 16, 32, 64, 128, 27, 54 };
 
-const u32 crypto_ft_tab[4][256] = {
+__visible const u32 crypto_ft_tab[4][256] = {
 	{
 		0xa56363c6, 0x847c7cf8, 0x997777ee, 0x8d7b7bf6,
 		0x0df2f2ff, 0xbd6b6bd6, 0xb16f6fde, 0x54c5c591,
@@ -326,7 +326,7 @@ const u32 crypto_ft_tab[4][256] = {
 	}
 };
 
-const u32 crypto_fl_tab[4][256] = {
+__visible const u32 crypto_fl_tab[4][256] = {
 	{
 		0x00000063, 0x0000007c, 0x00000077, 0x0000007b,
 		0x000000f2, 0x0000006b, 0x0000006f, 0x000000c5,
@@ -590,7 +590,7 @@ const u32 crypto_fl_tab[4][256] = {
 	}
 };
 
-const u32 crypto_it_tab[4][256] = {
+__visible const u32 crypto_it_tab[4][256] = {
 	{
 		0x50a7f451, 0x5365417e, 0xc3a4171a, 0x965e273a,
 		0xcb6bab3b, 0xf1459d1f, 0xab58faac, 0x9303e34b,
@@ -854,7 +854,7 @@ const u32 crypto_it_tab[4][256] = {
 	}
 };
 
-const u32 crypto_il_tab[4][256] = {
+__visible const u32 crypto_il_tab[4][256] = {
 	{
 		0x00000052, 0x00000009, 0x0000006a, 0x000000d5,
 		0x00000030, 0x00000036, 0x000000a5, 0x00000038,
diff --git a/crypto/camellia_generic.c b/crypto/camellia_generic.c
index 75efa205230..26bcd7a2d6b 100644
--- a/crypto/camellia_generic.c
+++ b/crypto/camellia_generic.c
@@ -388,8 +388,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 	/* round 6 */
 	subL[7] ^= subL[1]; subR[7] ^= subR[1];
 	subL[1] ^= subR[1] & ~subR[9];
-	dw = subL[1] & subL[9],
-		subR[1] ^= rol32(dw, 1); /* modified for FLinv(kl2) */
+	dw = subL[1] & subL[9];
+	subR[1] ^= rol32(dw, 1); /* modified for FLinv(kl2) */
 	/* round 8 */
 	subL[11] ^= subL[1]; subR[11] ^= subR[1];
 	/* round 10 */
@@ -397,8 +397,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 	/* round 12 */
 	subL[15] ^= subL[1]; subR[15] ^= subR[1];
 	subL[1] ^= subR[1] & ~subR[17];
-	dw = subL[1] & subL[17],
-		subR[1] ^= rol32(dw, 1); /* modified for FLinv(kl4) */
+	dw = subL[1] & subL[17];
+	subR[1] ^= rol32(dw, 1); /* modified for FLinv(kl4) */
 	/* round 14 */
 	subL[19] ^= subL[1]; subR[19] ^= subR[1];
 	/* round 16 */
@@ -413,8 +413,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 		kw4l = subL[25]; kw4r = subR[25];
 	} else {
 		subL[1] ^= subR[1] & ~subR[25];
-		dw = subL[1] & subL[25],
-			subR[1] ^= rol32(dw, 1); /* modified for FLinv(kl6) */
+		dw = subL[1] & subL[25];
+		subR[1] ^= rol32(dw, 1); /* modified for FLinv(kl6) */
 		/* round 20 */
 		subL[27] ^= subL[1]; subR[27] ^= subR[1];
 		/* round 22 */
@@ -433,8 +433,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 		/* round 19 */
 		subL[26] ^= kw4l; subR[26] ^= kw4r;
 		kw4l ^= kw4r & ~subR[24];
-		dw = kw4l & subL[24],
-			kw4r ^= rol32(dw, 1); /* modified for FL(kl5) */
+		dw = kw4l & subL[24];
+		kw4r ^= rol32(dw, 1); /* modified for FL(kl5) */
 	}
 	/* round 17 */
 	subL[22] ^= kw4l; subR[22] ^= kw4r;
@@ -443,8 +443,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 	/* round 13 */
 	subL[18] ^= kw4l; subR[18] ^= kw4r;
 	kw4l ^= kw4r & ~subR[16];
-	dw = kw4l & subL[16],
-		kw4r ^= rol32(dw, 1); /* modified for FL(kl3) */
+	dw = kw4l & subL[16];
+	kw4r ^= rol32(dw, 1); /* modified for FL(kl3) */
 	/* round 11 */
 	subL[14] ^= kw4l; subR[14] ^= kw4r;
 	/* round 9 */
@@ -452,8 +452,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 	/* round 7 */
 	subL[10] ^= kw4l; subR[10] ^= kw4r;
 	kw4l ^= kw4r & ~subR[8];
-	dw = kw4l & subL[8],
-		kw4r ^= rol32(dw, 1); /* modified for FL(kl1) */
+	dw = kw4l & subL[8];
+	kw4r ^= rol32(dw, 1); /* modified for FL(kl1) */
 	/* round 5 */
 	subL[6] ^= kw4l; subR[6] ^= kw4r;
 	/* round 3 */
@@ -477,8 +477,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 	SUBKEY_L(6) = subL[5] ^ subL[7]; /* round 5 */
 	SUBKEY_R(6) = subR[5] ^ subR[7];
 	tl = subL[10] ^ (subR[10] & ~subR[8]);
-	dw = tl & subL[8],  /* FL(kl1) */
-		tr = subR[10] ^ rol32(dw, 1);
+	dw = tl & subL[8];  /* FL(kl1) */
+	tr = subR[10] ^ rol32(dw, 1);
 	SUBKEY_L(7) = subL[6] ^ tl; /* round 6 */
 	SUBKEY_R(7) = subR[6] ^ tr;
 	SUBKEY_L(8) = subL[8];       /* FL(kl1) */
@@ -486,8 +486,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 	SUBKEY_L(9) = subL[9];       /* FLinv(kl2) */
 	SUBKEY_R(9) = subR[9];
 	tl = subL[7] ^ (subR[7] & ~subR[9]);
-	dw = tl & subL[9],  /* FLinv(kl2) */
-		tr = subR[7] ^ rol32(dw, 1);
+	dw = tl & subL[9];  /* FLinv(kl2) */
+	tr = subR[7] ^ rol32(dw, 1);
 	SUBKEY_L(10) = tl ^ subL[11]; /* round 7 */
 	SUBKEY_R(10) = tr ^ subR[11];
 	SUBKEY_L(11) = subL[10] ^ subL[12]; /* round 8 */
@@ -499,8 +499,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 	SUBKEY_L(14) = subL[13] ^ subL[15]; /* round 11 */
 	SUBKEY_R(14) = subR[13] ^ subR[15];
 	tl = subL[18] ^ (subR[18] & ~subR[16]);
-	dw = tl & subL[16], /* FL(kl3) */
-		tr = subR[18] ^ rol32(dw, 1);
+	dw = tl & subL[16]; /* FL(kl3) */
+	tr = subR[18] ^ rol32(dw, 1);
 	SUBKEY_L(15) = subL[14] ^ tl; /* round 12 */
 	SUBKEY_R(15) = subR[14] ^ tr;
 	SUBKEY_L(16) = subL[16];     /* FL(kl3) */
@@ -508,8 +508,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 	SUBKEY_L(17) = subL[17];     /* FLinv(kl4) */
 	SUBKEY_R(17) = subR[17];
 	tl = subL[15] ^ (subR[15] & ~subR[17]);
-	dw = tl & subL[17], /* FLinv(kl4) */
-		tr = subR[15] ^ rol32(dw, 1);
+	dw = tl & subL[17]; /* FLinv(kl4) */
+	tr = subR[15] ^ rol32(dw, 1);
 	SUBKEY_L(18) = tl ^ subL[19]; /* round 13 */
 	SUBKEY_R(18) = tr ^ subR[19];
 	SUBKEY_L(19) = subL[18] ^ subL[20]; /* round 14 */
@@ -527,8 +527,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 		SUBKEY_R(24) = subR[24] ^ subR[23];
 	} else {
 		tl = subL[26] ^ (subR[26] & ~subR[24]);
-		dw = tl & subL[24], /* FL(kl5) */
-			tr = subR[26] ^ rol32(dw, 1);
+		dw = tl & subL[24]; /* FL(kl5) */
+		tr = subR[26] ^ rol32(dw, 1);
 		SUBKEY_L(23) = subL[22] ^ tl; /* round 18 */
 		SUBKEY_R(23) = subR[22] ^ tr;
 		SUBKEY_L(24) = subL[24];     /* FL(kl5) */
@@ -536,8 +536,8 @@ static void camellia_setup_tail(u32 *subkey, u32 *subL, u32 *subR, int max)
 		SUBKEY_L(25) = subL[25];     /* FLinv(kl6) */
 		SUBKEY_R(25) = subR[25];
 		tl = subL[23] ^ (subR[23] & ~subR[25]);
-		dw = tl & subL[25], /* FLinv(kl6) */
-			tr = subR[23] ^ rol32(dw, 1);
+		dw = tl & subL[25]; /* FLinv(kl6) */
+		tr = subR[23] ^ rol32(dw, 1);
 		SUBKEY_L(26) = tl ^ subL[27]; /* round 19 */
 		SUBKEY_R(26) = tr ^ subR[27];
 		SUBKEY_L(27) = subL[26] ^ subL[28]; /* round 20 */
diff --git a/crypto/cast_common.c b/crypto/cast_common.c
index a15f523d5f5..117dd8250f2 100644
--- a/crypto/cast_common.c
+++ b/crypto/cast_common.c
@@ -15,7 +15,7 @@
 #include <linux/module.h>
 #include <crypto/cast_common.h>
 
-const u32 cast_s1[256] = {
+__visible const u32 cast_s1[256] = {
 	0x30fb40d4, 0x9fa0ff0b, 0x6beccd2f, 0x3f258c7a, 0x1e213f2f,
 	0x9c004dd3, 0x6003e540, 0xcf9fc949,
 	0xbfd4af27, 0x88bbbdb5, 0xe2034090, 0x98d09675, 0x6e63a0e0,
@@ -83,7 +83,7 @@ const u32 cast_s1[256] = {
 };
 EXPORT_SYMBOL_GPL(cast_s1);
 
-const u32 cast_s2[256] = {
+__visible const u32 cast_s2[256] = {
 	0x1f201094, 0xef0ba75b, 0x69e3cf7e, 0x393f4380, 0xfe61cf7a,
 	0xeec5207a, 0x55889c94, 0x72fc0651,
 	0xada7ef79, 0x4e1d7235, 0xd55a63ce, 0xde0436ba, 0x99c430ef,
@@ -151,7 +151,7 @@ const u32 cast_s2[256] = {
 };
 EXPORT_SYMBOL_GPL(cast_s2);
 
-const u32 cast_s3[256] = {
+__visible const u32 cast_s3[256] = {
 	0x8defc240, 0x25fa5d9f, 0xeb903dbf, 0xe810c907, 0x47607fff,
 	0x369fe44b, 0x8c1fc644, 0xaececa90,
 	0xbeb1f9bf, 0xeefbcaea, 0xe8cf1950, 0x51df07ae, 0x920e8806,
@@ -219,7 +219,7 @@ const u32 cast_s3[256] = {
 };
 EXPORT_SYMBOL_GPL(cast_s3);
 
-const u32 cast_s4[256] = {
+__visible const u32 cast_s4[256] = {
 	0x9db30420, 0x1fb6e9de, 0xa7be7bef, 0xd273a298, 0x4a4f7bdb,
 	0x64ad8c57, 0x85510443, 0xfa020ed1,
 	0x7e287aff, 0xe60fb663, 0x095f35a1, 0x79ebf120, 0xfd059d43,
diff --git a/crypto/crct10dif.c b/crypto/crct10dif.c
new file mode 100644
index 00000000000..92aca96d6b9
--- /dev/null
+++ b/crypto/crct10dif.c
@@ -0,0 +1,178 @@
+/*
+ * Cryptographic API.
+ *
+ * T10 Data Integrity Field CRC16 Crypto Transform
+ *
+ * Copyright (c) 2007 Oracle Corporation.  All rights reserved.
+ * Written by Martin K. Petersen <martin.petersen@oracle.com>
+ * Copyright (C) 2013 Intel Corporation
+ * Author: Tim Chen <tim.c.chen@linux.intel.com>
+ *
+ * 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.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+ * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+ * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+ * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+ * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+ * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+ * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ *
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/crc-t10dif.h>
+#include <crypto/internal/hash.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+
+struct chksum_desc_ctx {
+	__u16 crc;
+};
+
+/* Table generated using the following polynomium:
+ * x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x + 1
+ * gt: 0x8bb7
+ */
+static const __u16 t10_dif_crc_table[256] = {
+	0x0000, 0x8BB7, 0x9CD9, 0x176E, 0xB205, 0x39B2, 0x2EDC, 0xA56B,
+	0xEFBD, 0x640A, 0x7364, 0xF8D3, 0x5DB8, 0xD60F, 0xC161, 0x4AD6,
+	0x54CD, 0xDF7A, 0xC814, 0x43A3, 0xE6C8, 0x6D7F, 0x7A11, 0xF1A6,
+	0xBB70, 0x30C7, 0x27A9, 0xAC1E, 0x0975, 0x82C2, 0x95AC, 0x1E1B,
+	0xA99A, 0x222D, 0x3543, 0xBEF4, 0x1B9F, 0x9028, 0x8746, 0x0CF1,
+	0x4627, 0xCD90, 0xDAFE, 0x5149, 0xF422, 0x7F95, 0x68FB, 0xE34C,
+	0xFD57, 0x76E0, 0x618E, 0xEA39, 0x4F52, 0xC4E5, 0xD38B, 0x583C,
+	0x12EA, 0x995D, 0x8E33, 0x0584, 0xA0EF, 0x2B58, 0x3C36, 0xB781,
+	0xD883, 0x5334, 0x445A, 0xCFED, 0x6A86, 0xE131, 0xF65F, 0x7DE8,
+	0x373E, 0xBC89, 0xABE7, 0x2050, 0x853B, 0x0E8C, 0x19E2, 0x9255,
+	0x8C4E, 0x07F9, 0x1097, 0x9B20, 0x3E4B, 0xB5FC, 0xA292, 0x2925,
+	0x63F3, 0xE844, 0xFF2A, 0x749D, 0xD1F6, 0x5A41, 0x4D2F, 0xC698,
+	0x7119, 0xFAAE, 0xEDC0, 0x6677, 0xC31C, 0x48AB, 0x5FC5, 0xD472,
+	0x9EA4, 0x1513, 0x027D, 0x89CA, 0x2CA1, 0xA716, 0xB078, 0x3BCF,
+	0x25D4, 0xAE63, 0xB90D, 0x32BA, 0x97D1, 0x1C66, 0x0B08, 0x80BF,
+	0xCA69, 0x41DE, 0x56B0, 0xDD07, 0x786C, 0xF3DB, 0xE4B5, 0x6F02,
+	0x3AB1, 0xB106, 0xA668, 0x2DDF, 0x88B4, 0x0303, 0x146D, 0x9FDA,
+	0xD50C, 0x5EBB, 0x49D5, 0xC262, 0x6709, 0xECBE, 0xFBD0, 0x7067,
+	0x6E7C, 0xE5CB, 0xF2A5, 0x7912, 0xDC79, 0x57CE, 0x40A0, 0xCB17,
+	0x81C1, 0x0A76, 0x1D18, 0x96AF, 0x33C4, 0xB873, 0xAF1D, 0x24AA,
+	0x932B, 0x189C, 0x0FF2, 0x8445, 0x212E, 0xAA99, 0xBDF7, 0x3640,
+	0x7C96, 0xF721, 0xE04F, 0x6BF8, 0xCE93, 0x4524, 0x524A, 0xD9FD,
+	0xC7E6, 0x4C51, 0x5B3F, 0xD088, 0x75E3, 0xFE54, 0xE93A, 0x628D,
+	0x285B, 0xA3EC, 0xB482, 0x3F35, 0x9A5E, 0x11E9, 0x0687, 0x8D30,
+	0xE232, 0x6985, 0x7EEB, 0xF55C, 0x5037, 0xDB80, 0xCCEE, 0x4759,
+	0x0D8F, 0x8638, 0x9156, 0x1AE1, 0xBF8A, 0x343D, 0x2353, 0xA8E4,
+	0xB6FF, 0x3D48, 0x2A26, 0xA191, 0x04FA, 0x8F4D, 0x9823, 0x1394,
+	0x5942, 0xD2F5, 0xC59B, 0x4E2C, 0xEB47, 0x60F0, 0x779E, 0xFC29,
+	0x4BA8, 0xC01F, 0xD771, 0x5CC6, 0xF9AD, 0x721A, 0x6574, 0xEEC3,
+	0xA415, 0x2FA2, 0x38CC, 0xB37B, 0x1610, 0x9DA7, 0x8AC9, 0x017E,
+	0x1F65, 0x94D2, 0x83BC, 0x080B, 0xAD60, 0x26D7, 0x31B9, 0xBA0E,
+	0xF0D8, 0x7B6F, 0x6C01, 0xE7B6, 0x42DD, 0xC96A, 0xDE04, 0x55B3
+};
+
+__u16 crc_t10dif_generic(__u16 crc, const unsigned char *buffer, size_t len)
+{
+	unsigned int i;
+
+	for (i = 0 ; i < len ; i++)
+		crc = (crc << 8) ^ t10_dif_crc_table[((crc >> 8) ^ buffer[i]) & 0xff];
+
+	return crc;
+}
+EXPORT_SYMBOL(crc_t10dif_generic);
+
+/*
+ * Steps through buffer one byte at at time, calculates reflected
+ * crc using table.
+ */
+
+static int chksum_init(struct shash_desc *desc)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	ctx->crc = 0;
+
+	return 0;
+}
+
+static int chksum_update(struct shash_desc *desc, const u8 *data,
+			 unsigned int length)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	ctx->crc = crc_t10dif_generic(ctx->crc, data, length);
+	return 0;
+}
+
+static int chksum_final(struct shash_desc *desc, u8 *out)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	*(__u16 *)out = ctx->crc;
+	return 0;
+}
+
+static int __chksum_finup(__u16 *crcp, const u8 *data, unsigned int len,
+			u8 *out)
+{
+	*(__u16 *)out = crc_t10dif_generic(*crcp, data, len);
+	return 0;
+}
+
+static int chksum_finup(struct shash_desc *desc, const u8 *data,
+			unsigned int len, u8 *out)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	return __chksum_finup(&ctx->crc, data, len, out);
+}
+
+static int chksum_digest(struct shash_desc *desc, const u8 *data,
+			 unsigned int length, u8 *out)
+{
+	struct chksum_desc_ctx *ctx = shash_desc_ctx(desc);
+
+	return __chksum_finup(&ctx->crc, data, length, out);
+}
+
+static struct shash_alg alg = {
+	.digestsize		=	CRC_T10DIF_DIGEST_SIZE,
+	.init		=	chksum_init,
+	.update		=	chksum_update,
+	.final		=	chksum_final,
+	.finup		=	chksum_finup,
+	.digest		=	chksum_digest,
+	.descsize		=	sizeof(struct chksum_desc_ctx),
+	.base			=	{
+		.cra_name		=	"crct10dif",
+		.cra_driver_name	=	"crct10dif-generic",
+		.cra_priority		=	100,
+		.cra_blocksize		=	CRC_T10DIF_BLOCK_SIZE,
+		.cra_module		=	THIS_MODULE,
+	}
+};
+
+static int __init crct10dif_mod_init(void)
+{
+	int ret;
+
+	ret = crypto_register_shash(&alg);
+	return ret;
+}
+
+static void __exit crct10dif_mod_fini(void)
+{
+	crypto_unregister_shash(&alg);
+}
+
+module_init(crct10dif_mod_init);
+module_exit(crct10dif_mod_fini);
+
+MODULE_AUTHOR("Tim Chen <tim.c.chen@linux.intel.com>");
+MODULE_DESCRIPTION("T10 DIF CRC calculation.");
+MODULE_LICENSE("GPL");
diff --git a/crypto/fcrypt.c b/crypto/fcrypt.c
index 3b2cf569c68..021d7fec6bc 100644
--- a/crypto/fcrypt.c
+++ b/crypto/fcrypt.c
@@ -110,7 +110,7 @@ static const __be32 sbox0[256] = {
 };
 
 #undef Z
-#define Z(x) cpu_to_be32((x << 27) | (x >> 5))
+#define Z(x) cpu_to_be32(((x & 0x1f) << 27) | (x >> 5))
 static const __be32 sbox1[256] = {
 	Z(0x77), Z(0x14), Z(0xa6), Z(0xfe), Z(0xb2), Z(0x5e), Z(0x8c), Z(0x3e),
 	Z(0x67), Z(0x6c), Z(0xa1), Z(0x0d), Z(0xc2), Z(0xa2), Z(0xc1), Z(0x85),
diff --git a/crypto/scatterwalk.c b/crypto/scatterwalk.c
index 7281b8a93ad..79ca2278c2a 100644
--- a/crypto/scatterwalk.c
+++ b/crypto/scatterwalk.c
@@ -124,3 +124,25 @@ void scatterwalk_map_and_copy(void *buf, struct scatterlist *sg,
 	scatterwalk_done(&walk, out, 0);
 }
 EXPORT_SYMBOL_GPL(scatterwalk_map_and_copy);
+
+int scatterwalk_bytes_sglen(struct scatterlist *sg, int num_bytes)
+{
+	int offset = 0, n = 0;
+
+	/* num_bytes is too small */
+	if (num_bytes < sg->length)
+		return -1;
+
+	do {
+		offset += sg->length;
+		n++;
+		sg = scatterwalk_sg_next(sg);
+
+		/* num_bytes is too large */
+		if (unlikely(!sg && (num_bytes < offset)))
+			return -1;
+	} while (sg && (num_bytes > offset));
+
+	return n;
+}
+EXPORT_SYMBOL_GPL(scatterwalk_bytes_sglen);
diff --git a/crypto/tcrypt.c b/crypto/tcrypt.c
index 66d254ce0d1..25a5934f0e5 100644
--- a/crypto/tcrypt.c
+++ b/crypto/tcrypt.c
@@ -1174,6 +1174,10 @@ static int do_test(int m)
 		ret += tcrypt_test("ghash");
 		break;
 
+	case 47:
+		ret += tcrypt_test("crct10dif");
+		break;
+
 	case 100:
 		ret += tcrypt_test("hmac(md5)");
 		break;
@@ -1498,6 +1502,10 @@ static int do_test(int m)
 		test_hash_speed("crc32c", sec, generic_hash_speed_template);
 		if (mode > 300 && mode < 400) break;
 
+	case 320:
+		test_hash_speed("crct10dif", sec, generic_hash_speed_template);
+		if (mode > 300 && mode < 400) break;
+
 	case 399:
 		break;
 
diff --git a/crypto/testmgr.c b/crypto/testmgr.c
index ecddf921a9d..e091ef6e179 100644
--- a/crypto/testmgr.c
+++ b/crypto/testmgr.c
@@ -2046,6 +2046,16 @@ static const struct alg_test_desc alg_test_descs[] = {
 			}
 		}
 	}, {
+		.alg = "crct10dif",
+		.test = alg_test_hash,
+		.fips_allowed = 1,
+		.suite = {
+			.hash = {
+				.vecs = crct10dif_tv_template,
+				.count = CRCT10DIF_TEST_VECTORS
+			}
+		}
+	}, {
 		.alg = "cryptd(__driver-cbc-aes-aesni)",
 		.test = alg_test_null,
 		.fips_allowed = 1,
@@ -3224,7 +3234,7 @@ int alg_test(const char *driver, const char *alg, u32 type, u32 mask)
 	if (i >= 0)
 		rc |= alg_test_descs[i].test(alg_test_descs + i, driver,
 					     type, mask);
-	if (j >= 0)
+	if (j >= 0 && j != i)
 		rc |= alg_test_descs[j].test(alg_test_descs + j, driver,
 					     type, mask);
 
diff --git a/crypto/testmgr.h b/crypto/testmgr.h
index 1e701bc075b..7d44aa3d6b4 100644
--- a/crypto/testmgr.h
+++ b/crypto/testmgr.h
@@ -450,6 +450,39 @@ static struct hash_testvec rmd320_tv_template[] = {
 	}
 };
 
+#define CRCT10DIF_TEST_VECTORS	3
+static struct hash_testvec crct10dif_tv_template[] = {
+	{
+		.plaintext = "abc",
+		.psize  = 3,
+#ifdef __LITTLE_ENDIAN
+		.digest = "\x3b\x44",
+#else
+		.digest = "\x44\x3b",
+#endif
+	}, {
+		.plaintext = "1234567890123456789012345678901234567890"
+			     "123456789012345678901234567890123456789",
+		.psize	= 79,
+#ifdef __LITTLE_ENDIAN
+		.digest	= "\x70\x4b",
+#else
+		.digest	= "\x4b\x70",
+#endif
+	}, {
+		.plaintext =
+		"abcddddddddddddddddddddddddddddddddddddddddddddddddddddd",
+		.psize  = 56,
+#ifdef __LITTLE_ENDIAN
+		.digest = "\xe3\x9c",
+#else
+		.digest = "\x9c\xe3",
+#endif
+		.np     = 2,
+		.tap    = { 28, 28 }
+	}
+};
+
 /*
  * SHA1 test vectors  from from FIPS PUB 180-1
  * Long vector from CAVS 5.0