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

Pull crypto update from Herbert Xu:
 - Do not idle omap device between crypto operations in one session.
 - Added sha224/sha384 shims for SSSE3.
 - More optimisations for camellia-aesni-avx2.
 - Removed defunct blowfish/twofish AVX2 implementations.
 - Added unaligned buffer self-tests.
 - Added PCLMULQDQ optimisation for CRCT10DIF.
 - Added support for Freescale's DCP co-processor
 - Misc fixes.

* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (44 commits)
  crypto: testmgr - test hash implementations with unaligned buffers
  crypto: testmgr - test AEADs with unaligned buffers
  crypto: testmgr - test skciphers with unaligned buffers
  crypto: testmgr - check that entries in alg_test_descs are in correct order
  Revert "crypto: twofish - add AVX2/x86_64 assembler implementation of twofish cipher"
  Revert "crypto: blowfish - add AVX2/x86_64 implementation of blowfish cipher"
  crypto: camellia-aesni-avx2 - tune assembly code for more performance
  hwrng: bcm2835 - fix MODULE_LICENSE tag
  hwrng: nomadik - use clk_prepare_enable()
  crypto: picoxcell - replace strict_strtoul() with kstrtoul()
  crypto: dcp - Staticize local symbols
  crypto: dcp - Use NULL instead of 0
  crypto: dcp - Use devm_* APIs
  crypto: dcp - Remove redundant platform_set_drvdata()
  hwrng: use platform_{get,set}_drvdata()
  crypto: omap-aes - Don't idle/start AES device between Encrypt operations
  crypto: crct10dif - Use PTR_RET
  crypto: ux500 - Cocci spatch "resource_size.spatch"
  crypto: sha256_ssse3 - add sha224 support
  crypto: sha512_ssse3 - add sha384 support
  ...

15 files changed, 1099 insertions, 36 deletions

diff --git a/drivers/crypto/Kconfig b/drivers/crypto/Kconfig
index dffb8552536..8ff7c230d82 100644
--- a/drivers/crypto/Kconfig
+++ b/drivers/crypto/Kconfig
@@ -278,7 +278,7 @@ config CRYPTO_DEV_PICOXCELL
 
 config CRYPTO_DEV_SAHARA
 	tristate "Support for SAHARA crypto accelerator"
-	depends on ARCH_MXC && EXPERIMENTAL && OF
+	depends on ARCH_MXC && OF
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_AES
 	select CRYPTO_ECB
@@ -286,6 +286,16 @@ config CRYPTO_DEV_SAHARA
 	  This option enables support for the SAHARA HW crypto accelerator
 	  found in some Freescale i.MX chips.
 
+config CRYPTO_DEV_DCP
+	tristate "Support for the DCP engine"
+	depends on ARCH_MXS && OF
+	select CRYPTO_BLKCIPHER
+	select CRYPTO_AES
+	select CRYPTO_CBC
+	help
+	  This options enables support for the hardware crypto-acceleration
+	  capabilities of the DCP co-processor
+
 config CRYPTO_DEV_S5P
 	tristate "Support for Samsung S5PV210 crypto accelerator"
 	depends on ARCH_S5PV210
diff --git a/drivers/crypto/Makefile b/drivers/crypto/Makefile
index 38ce13d3b79..b4946ddd255 100644
--- a/drivers/crypto/Makefile
+++ b/drivers/crypto/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_CRYPTO_DEV_OMAP_SHAM) += omap-sham.o
 obj-$(CONFIG_CRYPTO_DEV_OMAP_AES) += omap-aes.o
 obj-$(CONFIG_CRYPTO_DEV_PICOXCELL) += picoxcell_crypto.o
 obj-$(CONFIG_CRYPTO_DEV_SAHARA) += sahara.o
+obj-$(CONFIG_CRYPTO_DEV_DCP) += dcp.o
 obj-$(CONFIG_CRYPTO_DEV_S5P) += s5p-sss.o
 obj-$(CONFIG_CRYPTO_DEV_TEGRA_AES) += tegra-aes.o
 obj-$(CONFIG_CRYPTO_DEV_UX500) += ux500/
diff --git a/drivers/crypto/caam/ctrl.c b/drivers/crypto/caam/ctrl.c
index 6e94bcd9467..f5d6deced1c 100644
--- a/drivers/crypto/caam/ctrl.c
+++ b/drivers/crypto/caam/ctrl.c
@@ -202,6 +202,7 @@ static int caam_probe(struct platform_device *pdev)
 #ifdef CONFIG_DEBUG_FS
 	struct caam_perfmon *perfmon;
 #endif
+	u64 cha_vid;
 
 	ctrlpriv = kzalloc(sizeof(struct caam_drv_private), GFP_KERNEL);
 	if (!ctrlpriv)
@@ -293,11 +294,14 @@ static int caam_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
+	cha_vid = rd_reg64(&topregs->ctrl.perfmon.cha_id);
+
 	/*
-	 * RNG4 based SECs (v5+) need special initialization prior
-	 * to executing any descriptors
+	 * If SEC has RNG version >= 4 and RNG state handle has not been
+	 * already instantiated ,do RNG instantiation
 	 */
-	if (of_device_is_compatible(nprop, "fsl,sec-v5.0")) {
+	if ((cha_vid & CHA_ID_RNG_MASK) >> CHA_ID_RNG_SHIFT >= 4 &&
+	    !(rd_reg32(&topregs->ctrl.r4tst[0].rdsta) & RDSTA_IF0)) {
 		kick_trng(pdev);
 		ret = instantiate_rng(ctrlpriv->jrdev[0]);
 		if (ret) {
diff --git a/drivers/crypto/caam/desc.h b/drivers/crypto/caam/desc.h
index f7f833be8c6..53b296f78b0 100644
--- a/drivers/crypto/caam/desc.h
+++ b/drivers/crypto/caam/desc.h
@@ -231,7 +231,12 @@ struct sec4_sg_entry {
 #define LDST_SRCDST_WORD_PKHA_B_SZ	(0x11 << LDST_SRCDST_SHIFT)
 #define LDST_SRCDST_WORD_PKHA_N_SZ	(0x12 << LDST_SRCDST_SHIFT)
 #define LDST_SRCDST_WORD_PKHA_E_SZ	(0x13 << LDST_SRCDST_SHIFT)
+#define LDST_SRCDST_WORD_CLASS_CTX	(0x20 << LDST_SRCDST_SHIFT)
 #define LDST_SRCDST_WORD_DESCBUF	(0x40 << LDST_SRCDST_SHIFT)
+#define LDST_SRCDST_WORD_DESCBUF_JOB	(0x41 << LDST_SRCDST_SHIFT)
+#define LDST_SRCDST_WORD_DESCBUF_SHARED	(0x42 << LDST_SRCDST_SHIFT)
+#define LDST_SRCDST_WORD_DESCBUF_JOB_WE	(0x45 << LDST_SRCDST_SHIFT)
+#define LDST_SRCDST_WORD_DESCBUF_SHARED_WE (0x46 << LDST_SRCDST_SHIFT)
 #define LDST_SRCDST_WORD_INFO_FIFO	(0x7a << LDST_SRCDST_SHIFT)
 
 /* Offset in source/destination */
@@ -366,6 +371,7 @@ struct sec4_sg_entry {
 #define FIFOLD_TYPE_LAST2FLUSH1 (0x05 << FIFOLD_TYPE_SHIFT)
 #define FIFOLD_TYPE_LASTBOTH	(0x06 << FIFOLD_TYPE_SHIFT)
 #define FIFOLD_TYPE_LASTBOTHFL	(0x07 << FIFOLD_TYPE_SHIFT)
+#define FIFOLD_TYPE_NOINFOFIFO	(0x0F << FIFOLD_TYPE_SHIFT)
 
 #define FIFOLDST_LEN_MASK	0xffff
 #define FIFOLDST_EXT_LEN_MASK	0xffffffff
@@ -1294,10 +1300,10 @@ struct sec4_sg_entry {
 #define SQOUT_SGF	0x01000000
 
 /* Appends to a previous pointer */
-#define SQOUT_PRE	0x00800000
+#define SQOUT_PRE	SQIN_PRE
 
 /* Restore sequence with pointer/length */
-#define SQOUT_RTO	0x00200000
+#define SQOUT_RTO	 SQIN_RTO
 
 /* Use extended length following pointer */
 #define SQOUT_EXT	0x00400000
@@ -1359,6 +1365,7 @@ struct sec4_sg_entry {
 #define MOVE_DEST_MATH3		(0x07 << MOVE_DEST_SHIFT)
 #define MOVE_DEST_CLASS1INFIFO	(0x08 << MOVE_DEST_SHIFT)
 #define MOVE_DEST_CLASS2INFIFO	(0x09 << MOVE_DEST_SHIFT)
+#define MOVE_DEST_INFIFO_NOINFO (0x0a << MOVE_DEST_SHIFT)
 #define MOVE_DEST_PK_A		(0x0c << MOVE_DEST_SHIFT)
 #define MOVE_DEST_CLASS1KEY	(0x0d << MOVE_DEST_SHIFT)
 #define MOVE_DEST_CLASS2KEY	(0x0e << MOVE_DEST_SHIFT)
@@ -1411,6 +1418,7 @@ struct sec4_sg_entry {
 #define MATH_SRC0_REG2		(0x02 << MATH_SRC0_SHIFT)
 #define MATH_SRC0_REG3		(0x03 << MATH_SRC0_SHIFT)
 #define MATH_SRC0_IMM		(0x04 << MATH_SRC0_SHIFT)
+#define MATH_SRC0_DPOVRD	(0x07 << MATH_SRC0_SHIFT)
 #define MATH_SRC0_SEQINLEN	(0x08 << MATH_SRC0_SHIFT)
 #define MATH_SRC0_SEQOUTLEN	(0x09 << MATH_SRC0_SHIFT)
 #define MATH_SRC0_VARSEQINLEN	(0x0a << MATH_SRC0_SHIFT)
@@ -1425,6 +1433,7 @@ struct sec4_sg_entry {
 #define MATH_SRC1_REG2		(0x02 << MATH_SRC1_SHIFT)
 #define MATH_SRC1_REG3		(0x03 << MATH_SRC1_SHIFT)
 #define MATH_SRC1_IMM		(0x04 << MATH_SRC1_SHIFT)
+#define MATH_SRC1_DPOVRD	(0x07 << MATH_SRC0_SHIFT)
 #define MATH_SRC1_INFIFO	(0x0a << MATH_SRC1_SHIFT)
 #define MATH_SRC1_OUTFIFO	(0x0b << MATH_SRC1_SHIFT)
 #define MATH_SRC1_ONE		(0x0c << MATH_SRC1_SHIFT)
@@ -1600,4 +1609,13 @@ struct sec4_sg_entry {
 #define NFIFOENTRY_PLEN_SHIFT	0
 #define NFIFOENTRY_PLEN_MASK	(0xFF << NFIFOENTRY_PLEN_SHIFT)
 
+/* Append Load Immediate Command */
+#define FD_CMD_APPEND_LOAD_IMMEDIATE			0x80000000
+
+/* Set SEQ LIODN equal to the Non-SEQ LIODN for the job */
+#define FD_CMD_SET_SEQ_LIODN_EQUAL_NONSEQ_LIODN		0x40000000
+
+/* Frame Descriptor Command for Replacement Job Descriptor */
+#define FD_CMD_REPLACE_JOB_DESC				0x20000000
+
 #endif /* DESC_H */
diff --git a/drivers/crypto/caam/desc_constr.h b/drivers/crypto/caam/desc_constr.h
index c85c1f05840..fe3bfd1b08c 100644
--- a/drivers/crypto/caam/desc_constr.h
+++ b/drivers/crypto/caam/desc_constr.h
@@ -110,6 +110,26 @@ static inline void append_cmd(u32 *desc, u32 command)
 	(*desc)++;
 }
 
+#define append_u32 append_cmd
+
+static inline void append_u64(u32 *desc, u64 data)
+{
+	u32 *offset = desc_end(desc);
+
+	*offset = upper_32_bits(data);
+	*(++offset) = lower_32_bits(data);
+
+	(*desc) += 2;
+}
+
+/* Write command without affecting header, and return pointer to next word */
+static inline u32 *write_cmd(u32 *desc, u32 command)
+{
+	*desc = command;
+
+	return desc + 1;
+}
+
 static inline void append_cmd_ptr(u32 *desc, dma_addr_t ptr, int len,
 				  u32 command)
 {
@@ -122,7 +142,8 @@ static inline void append_cmd_ptr_extlen(u32 *desc, dma_addr_t ptr,
 					 unsigned int len, u32 command)
 {
 	append_cmd(desc, command);
-	append_ptr(desc, ptr);
+	if (!(command & (SQIN_RTO | SQIN_PRE)))
+		append_ptr(desc, ptr);
 	append_cmd(desc, len);
 }
 
@@ -176,17 +197,36 @@ static inline void append_##cmd(u32 *desc, dma_addr_t ptr, unsigned int len, \
 }
 APPEND_CMD_PTR(key, KEY)
 APPEND_CMD_PTR(load, LOAD)
-APPEND_CMD_PTR(store, STORE)
 APPEND_CMD_PTR(fifo_load, FIFO_LOAD)
 APPEND_CMD_PTR(fifo_store, FIFO_STORE)
 
+static inline void append_store(u32 *desc, dma_addr_t ptr, unsigned int len,
+				u32 options)
+{
+	u32 cmd_src;
+
+	cmd_src = options & LDST_SRCDST_MASK;
+
+	append_cmd(desc, CMD_STORE | options | len);
+
+	/* The following options do not require pointer */
+	if (!(cmd_src == LDST_SRCDST_WORD_DESCBUF_SHARED ||
+	      cmd_src == LDST_SRCDST_WORD_DESCBUF_JOB    ||
+	      cmd_src == LDST_SRCDST_WORD_DESCBUF_JOB_WE ||
+	      cmd_src == LDST_SRCDST_WORD_DESCBUF_SHARED_WE))
+		append_ptr(desc, ptr);
+}
+
 #define APPEND_SEQ_PTR_INTLEN(cmd, op) \
 static inline void append_seq_##cmd##_ptr_intlen(u32 *desc, dma_addr_t ptr, \
 						 unsigned int len, \
 						 u32 options) \
 { \
 	PRINT_POS; \
-	append_cmd_ptr(desc, ptr, len, CMD_SEQ_##op##_PTR | options); \
+	if (options & (SQIN_RTO | SQIN_PRE)) \
+		append_cmd(desc, CMD_SEQ_##op##_PTR | len | options); \
+	else \
+		append_cmd_ptr(desc, ptr, len, CMD_SEQ_##op##_PTR | options); \
 }
 APPEND_SEQ_PTR_INTLEN(in, IN)
 APPEND_SEQ_PTR_INTLEN(out, OUT)
@@ -259,7 +299,7 @@ APPEND_CMD_RAW_IMM(load, LOAD, u32);
  */
 #define APPEND_MATH(op, desc, dest, src_0, src_1, len) \
 append_cmd(desc, CMD_MATH | MATH_FUN_##op | MATH_DEST_##dest | \
-	   MATH_SRC0_##src_0 | MATH_SRC1_##src_1 | (u32) (len & MATH_LEN_MASK));
+	MATH_SRC0_##src_0 | MATH_SRC1_##src_1 | (u32)len);
 
 #define append_math_add(desc, dest, src0, src1, len) \
 	APPEND_MATH(ADD, desc, dest, src0, src1, len)
@@ -279,6 +319,8 @@ append_cmd(desc, CMD_MATH | MATH_FUN_##op | MATH_DEST_##dest | \
 	APPEND_MATH(LSHIFT, desc, dest, src0, src1, len)
 #define append_math_rshift(desc, dest, src0, src1, len) \
 	APPEND_MATH(RSHIFT, desc, dest, src0, src1, len)
+#define append_math_ldshift(desc, dest, src0, src1, len) \
+	APPEND_MATH(SHLD, desc, dest, src0, src1, len)
 
 /* Exactly one source is IMM. Data is passed in as u32 value */
 #define APPEND_MATH_IMM_u32(op, desc, dest, src_0, src_1, data) \
@@ -305,3 +347,34 @@ do { \
 	APPEND_MATH_IMM_u32(LSHIFT, desc, dest, src0, src1, data)
 #define append_math_rshift_imm_u32(desc, dest, src0, src1, data) \
 	APPEND_MATH_IMM_u32(RSHIFT, desc, dest, src0, src1, data)
+
+/* Exactly one source is IMM. Data is passed in as u64 value */
+#define APPEND_MATH_IMM_u64(op, desc, dest, src_0, src_1, data) \
+do { \
+	u32 upper = (data >> 16) >> 16; \
+	APPEND_MATH(op, desc, dest, src_0, src_1, CAAM_CMD_SZ * 2 | \
+		    (upper ? 0 : MATH_IFB)); \
+	if (upper) \
+		append_u64(desc, data); \
+	else \
+		append_u32(desc, data); \
+} while (0)
+
+#define append_math_add_imm_u64(desc, dest, src0, src1, data) \
+	APPEND_MATH_IMM_u64(ADD, desc, dest, src0, src1, data)
+#define append_math_sub_imm_u64(desc, dest, src0, src1, data) \
+	APPEND_MATH_IMM_u64(SUB, desc, dest, src0, src1, data)
+#define append_math_add_c_imm_u64(desc, dest, src0, src1, data) \
+	APPEND_MATH_IMM_u64(ADDC, desc, dest, src0, src1, data)
+#define append_math_sub_b_imm_u64(desc, dest, src0, src1, data) \
+	APPEND_MATH_IMM_u64(SUBB, desc, dest, src0, src1, data)
+#define append_math_and_imm_u64(desc, dest, src0, src1, data) \
+	APPEND_MATH_IMM_u64(AND, desc, dest, src0, src1, data)
+#define append_math_or_imm_u64(desc, dest, src0, src1, data) \
+	APPEND_MATH_IMM_u64(OR, desc, dest, src0, src1, data)
+#define append_math_xor_imm_u64(desc, dest, src0, src1, data) \
+	APPEND_MATH_IMM_u64(XOR, desc, dest, src0, src1, data)
+#define append_math_lshift_imm_u64(desc, dest, src0, src1, data) \
+	APPEND_MATH_IMM_u64(LSHIFT, desc, dest, src0, src1, data)
+#define append_math_rshift_imm_u64(desc, dest, src0, src1, data) \
+	APPEND_MATH_IMM_u64(RSHIFT, desc, dest, src0, src1, data)
diff --git a/drivers/crypto/caam/pdb.h b/drivers/crypto/caam/pdb.h
index 62950d22ac1..3a87c0cf879 100644
--- a/drivers/crypto/caam/pdb.h
+++ b/drivers/crypto/caam/pdb.h
@@ -44,6 +44,7 @@
 #define PDBOPTS_ESP_IPHDRSRC	0x08 /* IP header comes from PDB (encap) */
 #define PDBOPTS_ESP_INCIPHDR	0x04 /* Prepend IP header to output frame */
 #define PDBOPTS_ESP_IPVSN	0x02 /* process IPv6 header */
+#define PDBOPTS_ESP_AOFL	0x04 /* adjust out frame len (decap, SEC>=5.3)*/
 #define PDBOPTS_ESP_TUNNEL	0x01 /* tunnel mode next-header byte */
 #define PDBOPTS_ESP_IPV6	0x02 /* ip header version is V6 */
 #define PDBOPTS_ESP_DIFFSERV	0x40 /* copy TOS/TC from inner iphdr */
diff --git a/drivers/crypto/caam/regs.h b/drivers/crypto/caam/regs.h
index cd6fedad993..c09142fc13e 100644
--- a/drivers/crypto/caam/regs.h
+++ b/drivers/crypto/caam/regs.h
@@ -117,6 +117,43 @@ struct jr_outentry {
 #define CHA_NUM_DECONUM_SHIFT	56
 #define CHA_NUM_DECONUM_MASK	(0xfull << CHA_NUM_DECONUM_SHIFT)
 
+/* CHA Version IDs */
+#define CHA_ID_AES_SHIFT	0
+#define CHA_ID_AES_MASK		(0xfull << CHA_ID_AES_SHIFT)
+
+#define CHA_ID_DES_SHIFT	4
+#define CHA_ID_DES_MASK		(0xfull << CHA_ID_DES_SHIFT)
+
+#define CHA_ID_ARC4_SHIFT	8
+#define CHA_ID_ARC4_MASK	(0xfull << CHA_ID_ARC4_SHIFT)
+
+#define CHA_ID_MD_SHIFT		12
+#define CHA_ID_MD_MASK		(0xfull << CHA_ID_MD_SHIFT)
+
+#define CHA_ID_RNG_SHIFT	16
+#define CHA_ID_RNG_MASK		(0xfull << CHA_ID_RNG_SHIFT)
+
+#define CHA_ID_SNW8_SHIFT	20
+#define CHA_ID_SNW8_MASK	(0xfull << CHA_ID_SNW8_SHIFT)
+
+#define CHA_ID_KAS_SHIFT	24
+#define CHA_ID_KAS_MASK		(0xfull << CHA_ID_KAS_SHIFT)
+
+#define CHA_ID_PK_SHIFT		28
+#define CHA_ID_PK_MASK		(0xfull << CHA_ID_PK_SHIFT)
+
+#define CHA_ID_CRC_SHIFT	32
+#define CHA_ID_CRC_MASK		(0xfull << CHA_ID_CRC_SHIFT)
+
+#define CHA_ID_SNW9_SHIFT	36
+#define CHA_ID_SNW9_MASK	(0xfull << CHA_ID_SNW9_SHIFT)
+
+#define CHA_ID_DECO_SHIFT	56
+#define CHA_ID_DECO_MASK	(0xfull << CHA_ID_DECO_SHIFT)
+
+#define CHA_ID_JR_SHIFT		60
+#define CHA_ID_JR_MASK		(0xfull << CHA_ID_JR_SHIFT)
+
 struct sec_vid {
 	u16 ip_id;
 	u8 maj_rev;
@@ -228,7 +265,10 @@ struct rng4tst {
 		u32 rtfrqmax;	/* PRGM=1: freq. count max. limit register */
 		u32 rtfrqcnt;	/* PRGM=0: freq. count register */
 	};
-	u32 rsvd1[56];
+	u32 rsvd1[40];
+#define RDSTA_IF0 0x00000001
+	u32 rdsta;
+	u32 rsvd2[15];
 };
 
 /*
diff --git a/drivers/crypto/dcp.c b/drivers/crypto/dcp.c
new file mode 100644
index 00000000000..a8a7dd4b0d2
--- /dev/null
+++ b/drivers/crypto/dcp.c
@@ -0,0 +1,912 @@
+/*
+ * Cryptographic API.
+ *
+ * Support for DCP cryptographic accelerator.
+ *
+ * Copyright (c) 2013
+ * Author: Tobias Rauter <tobias.rauter@gmail.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ *
+ * Based on tegra-aes.c, dcp.c (from freescale SDK) and sahara.c
+ */
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/platform_device.h>
+#include <linux/dma-mapping.h>
+#include <linux/io.h>
+#include <linux/mutex.h>
+#include <linux/interrupt.h>
+#include <linux/completion.h>
+#include <linux/workqueue.h>
+#include <linux/delay.h>
+#include <linux/crypto.h>
+#include <linux/miscdevice.h>
+
+#include <crypto/scatterwalk.h>
+#include <crypto/aes.h>
+
+
+/* IOCTL for DCP OTP Key AES - taken from Freescale's SDK*/
+#define DBS_IOCTL_BASE   'd'
+#define DBS_ENC	_IOW(DBS_IOCTL_BASE, 0x00, uint8_t[16])
+#define DBS_DEC _IOW(DBS_IOCTL_BASE, 0x01, uint8_t[16])
+
+/* DCP channel used for AES */
+#define USED_CHANNEL 1
+/* Ring Buffers' maximum size */
+#define DCP_MAX_PKG 20
+
+/* Control Register */
+#define DCP_REG_CTRL 0x000
+#define DCP_CTRL_SFRST (1<<31)
+#define DCP_CTRL_CLKGATE (1<<30)
+#define DCP_CTRL_CRYPTO_PRESENT (1<<29)
+#define DCP_CTRL_SHA_PRESENT (1<<28)
+#define DCP_CTRL_GATHER_RES_WRITE (1<<23)
+#define DCP_CTRL_ENABLE_CONTEXT_CACHE (1<<22)
+#define DCP_CTRL_ENABLE_CONTEXT_SWITCH (1<<21)
+#define DCP_CTRL_CH_IRQ_E_0 0x01
+#define DCP_CTRL_CH_IRQ_E_1 0x02
+#define DCP_CTRL_CH_IRQ_E_2 0x04
+#define DCP_CTRL_CH_IRQ_E_3 0x08
+
+/* Status register */
+#define DCP_REG_STAT 0x010
+#define DCP_STAT_OTP_KEY_READY (1<<28)
+#define DCP_STAT_CUR_CHANNEL(stat) ((stat>>24)&0x0F)
+#define DCP_STAT_READY_CHANNEL(stat) ((stat>>16)&0x0F)
+#define DCP_STAT_IRQ(stat) (stat&0x0F)
+#define DCP_STAT_CHAN_0 (0x01)
+#define DCP_STAT_CHAN_1 (0x02)
+#define DCP_STAT_CHAN_2 (0x04)
+#define DCP_STAT_CHAN_3 (0x08)
+
+/* Channel Control Register */
+#define DCP_REG_CHAN_CTRL 0x020
+#define DCP_CHAN_CTRL_CH0_IRQ_MERGED (1<<16)
+#define DCP_CHAN_CTRL_HIGH_PRIO_0 (0x0100)
+#define DCP_CHAN_CTRL_HIGH_PRIO_1 (0x0200)
+#define DCP_CHAN_CTRL_HIGH_PRIO_2 (0x0400)
+#define DCP_CHAN_CTRL_HIGH_PRIO_3 (0x0800)
+#define DCP_CHAN_CTRL_ENABLE_0 (0x01)
+#define DCP_CHAN_CTRL_ENABLE_1 (0x02)
+#define DCP_CHAN_CTRL_ENABLE_2 (0x04)
+#define DCP_CHAN_CTRL_ENABLE_3 (0x08)
+
+/*
+ * Channel Registers:
+ * The DCP has 4 channels. Each of this channels
+ * has 4 registers (command pointer, semaphore, status and options).
+ * The address of register REG of channel CHAN is obtained by
+ * dcp_chan_reg(REG, CHAN)
+ */
+#define DCP_REG_CHAN_PTR	0x00000100
+#define DCP_REG_CHAN_SEMA	0x00000110
+#define DCP_REG_CHAN_STAT	0x00000120
+#define DCP_REG_CHAN_OPT	0x00000130
+
+#define DCP_CHAN_STAT_NEXT_CHAIN_IS_0	0x010000
+#define DCP_CHAN_STAT_NO_CHAIN		0x020000
+#define DCP_CHAN_STAT_CONTEXT_ERROR	0x030000
+#define DCP_CHAN_STAT_PAYLOAD_ERROR	0x040000
+#define DCP_CHAN_STAT_INVALID_MODE	0x050000
+#define DCP_CHAN_STAT_PAGEFAULT		0x40
+#define DCP_CHAN_STAT_DST		0x20
+#define DCP_CHAN_STAT_SRC		0x10
+#define DCP_CHAN_STAT_PACKET		0x08
+#define DCP_CHAN_STAT_SETUP		0x04
+#define DCP_CHAN_STAT_MISMATCH		0x02
+
+/* hw packet control*/
+
+#define DCP_PKT_PAYLOAD_KEY	(1<<11)
+#define DCP_PKT_OTP_KEY		(1<<10)
+#define DCP_PKT_CIPHER_INIT	(1<<9)
+#define DCP_PKG_CIPHER_ENCRYPT	(1<<8)
+#define DCP_PKT_CIPHER_ENABLE	(1<<5)
+#define DCP_PKT_DECR_SEM	(1<<1)
+#define DCP_PKT_CHAIN		(1<<2)
+#define DCP_PKT_IRQ		1
+
+#define DCP_PKT_MODE_CBC	(1<<4)
+#define DCP_PKT_KEYSELECT_OTP	(0xFF<<8)
+
+/* cipher flags */
+#define DCP_ENC		0x0001
+#define DCP_DEC		0x0002
+#define DCP_ECB		0x0004
+#define DCP_CBC		0x0008
+#define DCP_CBC_INIT	0x0010
+#define DCP_NEW_KEY	0x0040
+#define DCP_OTP_KEY	0x0080
+#define DCP_AES		0x1000
+
+/* DCP Flags */
+#define DCP_FLAG_BUSY	0x01
+#define DCP_FLAG_PRODUCING	0x02
+
+/* clock defines */
+#define CLOCK_ON	1
+#define CLOCK_OFF	0
+
+struct dcp_dev_req_ctx {
+	int mode;
+};
+
+struct dcp_op {
+	unsigned int		flags;
+	u8			key[AES_KEYSIZE_128];
+	int			keylen;
+
+	struct ablkcipher_request	*req;
+	struct crypto_ablkcipher	*fallback;
+
+	uint32_t stat;
+	uint32_t pkt1;
+	uint32_t pkt2;
+	struct ablkcipher_walk walk;
+};
+
+struct dcp_dev {
+	struct device *dev;
+	void __iomem *dcp_regs_base;
+
+	int dcp_vmi_irq;
+	int dcp_irq;
+
+	spinlock_t queue_lock;
+	struct crypto_queue queue;
+
+	uint32_t pkt_produced;
+	uint32_t pkt_consumed;
+
+	struct dcp_hw_packet *hw_pkg[DCP_MAX_PKG];
+	dma_addr_t hw_phys_pkg;
+
+	/* [KEY][IV] Both with 16 Bytes */
+	u8 *payload_base;
+	dma_addr_t payload_base_dma;
+
+
+	struct tasklet_struct	done_task;
+	struct tasklet_struct	queue_task;
+	struct timer_list	watchdog;
+
+	unsigned long		flags;
+
+	struct dcp_op *ctx;
+
+	struct miscdevice dcp_bootstream_misc;
+};
+
+struct dcp_hw_packet {
+	uint32_t next;
+	uint32_t pkt1;
+	uint32_t pkt2;
+	uint32_t src;
+	uint32_t dst;
+	uint32_t size;
+	uint32_t payload;
+	uint32_t stat;
+};
+
+static struct dcp_dev *global_dev;
+
+static inline u32 dcp_chan_reg(u32 reg, int chan)
+{
+	return reg + (chan) * 0x40;
+}
+
+static inline void dcp_write(struct dcp_dev *dev, u32 data, u32 reg)
+{
+	writel(data, dev->dcp_regs_base + reg);
+}
+
+static inline void dcp_set(struct dcp_dev *dev, u32 data, u32 reg)
+{
+	writel(data, dev->dcp_regs_base + (reg | 0x04));
+}
+
+static inline void dcp_clear(struct dcp_dev *dev, u32 data, u32 reg)
+{
+	writel(data, dev->dcp_regs_base + (reg | 0x08));
+}
+
+static inline void dcp_toggle(struct dcp_dev *dev, u32 data, u32 reg)
+{
+	writel(data, dev->dcp_regs_base + (reg | 0x0C));
+}
+
+static inline unsigned int dcp_read(struct dcp_dev *dev, u32 reg)
+{
+	return readl(dev->dcp_regs_base + reg);
+}
+
+static void dcp_dma_unmap(struct dcp_dev *dev, struct dcp_hw_packet *pkt)
+{
+	dma_unmap_page(dev->dev, pkt->src, pkt->size, DMA_TO_DEVICE);
+	dma_unmap_page(dev->dev, pkt->dst, pkt->size, DMA_FROM_DEVICE);
+	dev_dbg(dev->dev, "unmap packet %x", (unsigned int) pkt);
+}
+
+static int dcp_dma_map(struct dcp_dev *dev,
+	struct ablkcipher_walk *walk, struct dcp_hw_packet *pkt)
+{
+	dev_dbg(dev->dev, "map packet %x", (unsigned int) pkt);
+	/* align to length = 16 */
+	pkt->size = walk->nbytes - (walk->nbytes % 16);
+
+	pkt->src = dma_map_page(dev->dev, walk->src.page, walk->src.offset,
+		pkt->size, DMA_TO_DEVICE);
+
+	if (pkt->src == 0) {
+		dev_err(dev->dev, "Unable to map src");
+		return -ENOMEM;
+	}
+
+	pkt->dst = dma_map_page(dev->dev, walk->dst.page, walk->dst.offset,
+		pkt->size, DMA_FROM_DEVICE);
+
+	if (pkt->dst == 0) {
+		dev_err(dev->dev, "Unable to map dst");
+		dma_unmap_page(dev->dev, pkt->src, pkt->size, DMA_TO_DEVICE);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void dcp_op_one(struct dcp_dev *dev, struct dcp_hw_packet *pkt,
+			uint8_t last)
+{
+	struct dcp_op *ctx = dev->ctx;
+	pkt->pkt1 = ctx->pkt1;
+	pkt->pkt2 = ctx->pkt2;
+
+	pkt->payload = (u32) dev->payload_base_dma;
+	pkt->stat = 0;
+
+	if (ctx->flags & DCP_CBC_INIT) {
+		pkt->pkt1 |= DCP_PKT_CIPHER_INIT;
+		ctx->flags &= ~DCP_CBC_INIT;
+	}
+
+	mod_timer(&dev->watchdog, jiffies + msecs_to_jiffies(500));
+	pkt->pkt1 |= DCP_PKT_IRQ;
+	if (!last)
+		pkt->pkt1 |= DCP_PKT_CHAIN;
+
+	dev->pkt_produced++;
+
+	dcp_write(dev, 1,
+		dcp_chan_reg(DCP_REG_CHAN_SEMA, USED_CHANNEL));
+}
+
+static void dcp_op_proceed(struct dcp_dev *dev)
+{
+	struct dcp_op *ctx = dev->ctx;
+	struct dcp_hw_packet *pkt;
+
+	while (ctx->walk.nbytes) {
+		int err = 0;
+
+		pkt = dev->hw_pkg[dev->pkt_produced % DCP_MAX_PKG];
+		err = dcp_dma_map(dev, &ctx->walk, pkt);
+		if (err) {
+			dev->ctx->stat |= err;
+			/* start timer to wait for already set up calls */
+			mod_timer(&dev->watchdog,
+				jiffies + msecs_to_jiffies(500));
+			break;
+		}
+
+
+		err = ctx->walk.nbytes - pkt->size;
+		ablkcipher_walk_done(dev->ctx->req, &dev->ctx->walk, err);
+
+		dcp_op_one(dev, pkt, ctx->walk.nbytes == 0);
+		/* we have to wait if no space is left in buffer */
+		if (dev->pkt_produced - dev->pkt_consumed == DCP_MAX_PKG)
+			break;
+	}
+	clear_bit(DCP_FLAG_PRODUCING, &dev->flags);
+}
+
+static void dcp_op_start(struct dcp_dev *dev, uint8_t use_walk)
+{
+	struct dcp_op *ctx = dev->ctx;
+
+	if (ctx->flags & DCP_NEW_KEY) {
+		memcpy(dev->payload_base, ctx->key, ctx->keylen);
+		ctx->flags &= ~DCP_NEW_KEY;
+	}
+
+	ctx->pkt1 = 0;
+	ctx->pkt1 |= DCP_PKT_CIPHER_ENABLE;
+	ctx->pkt1 |= DCP_PKT_DECR_SEM;
+
+	if (ctx->flags & DCP_OTP_KEY)
+		ctx->pkt1 |= DCP_PKT_OTP_KEY;
+	else
+		ctx->pkt1 |= DCP_PKT_PAYLOAD_KEY;
+
+	if (ctx->flags & DCP_ENC)
+		ctx->pkt1 |= DCP_PKG_CIPHER_ENCRYPT;
+
+	ctx->pkt2 = 0;
+	if (ctx->flags & DCP_CBC)
+		ctx->pkt2 |= DCP_PKT_MODE_CBC;
+
+	dev->pkt_produced = 0;
+	dev->pkt_consumed = 0;
+
+	ctx->stat = 0;
+	dcp_clear(dev, -1, dcp_chan_reg(DCP_REG_CHAN_STAT, USED_CHANNEL));
+	dcp_write(dev, (u32) dev->hw_phys_pkg,
+		dcp_chan_reg(DCP_REG_CHAN_PTR, USED_CHANNEL));
+
+	set_bit(DCP_FLAG_PRODUCING, &dev->flags);
+
+	if (use_walk) {
+		ablkcipher_walk_init(&ctx->walk, ctx->req->dst,
+				ctx->req->src, ctx->req->nbytes);
+		ablkcipher_walk_phys(ctx->req, &ctx->walk);
+		dcp_op_proceed(dev);
+	} else {
+		dcp_op_one(dev, dev->hw_pkg[0], 1);
+		clear_bit(DCP_FLAG_PRODUCING, &dev->flags);
+	}
+}
+
+static void dcp_done_task(unsigned long data)
+{
+	struct dcp_dev *dev = (struct dcp_dev *)data;
+	struct dcp_hw_packet *last_packet;
+	int fin;
+	fin = 0;
+
+	for (last_packet = dev->hw_pkg[(dev->pkt_consumed) % DCP_MAX_PKG];
+		last_packet->stat == 1;
+		last_packet =
+			dev->hw_pkg[++(dev->pkt_consumed) % DCP_MAX_PKG]) {
+
+		dcp_dma_unmap(dev, last_packet);
+		last_packet->stat = 0;
+		fin++;
+	}
+	/* the last call of this function already consumed this IRQ's packet */
+	if (fin == 0)
+		return;
+
+	dev_dbg(dev->dev,
+		"Packet(s) done with status %x; finished: %d, produced:%d, complete consumed: %d",
+		dev->ctx->stat, fin, dev->pkt_produced, dev->pkt_consumed);
+
+	last_packet = dev->hw_pkg[(dev->pkt_consumed - 1) % DCP_MAX_PKG];
+	if (!dev->ctx->stat && last_packet->pkt1 & DCP_PKT_CHAIN) {
+		if (!test_and_set_bit(DCP_FLAG_PRODUCING, &dev->flags))
+			dcp_op_proceed(dev);
+		return;
+	}
+
+	while (unlikely(dev->pkt_consumed < dev->pkt_produced)) {
+		dcp_dma_unmap(dev,
+			dev->hw_pkg[dev->pkt_consumed++ % DCP_MAX_PKG]);
+	}
+
+	if (dev->ctx->flags & DCP_OTP_KEY) {
+		/* we used the miscdevice, no walk to finish */
+		clear_bit(DCP_FLAG_BUSY, &dev->flags);
+		return;
+	}
+
+	ablkcipher_walk_complete(&dev->ctx->walk);
+	dev->ctx->req->base.complete(&dev->ctx->req->base,
+			dev->ctx->stat);
+	dev->ctx->req = NULL;
+	/* in case there are other requests in the queue */
+	tasklet_schedule(&dev->queue_task);
+}
+
+static void dcp_watchdog(unsigned long data)
+{
+	struct dcp_dev *dev = (struct dcp_dev *)data;
+	dev->ctx->stat |= dcp_read(dev,
+			dcp_chan_reg(DCP_REG_CHAN_STAT, USED_CHANNEL));
+
+	dev_err(dev->dev, "Timeout, Channel status: %x", dev->ctx->stat);
+
+	if (!dev->ctx->stat)
+		dev->ctx->stat = -ETIMEDOUT;
+
+	dcp_done_task(data);
+}
+
+
+static irqreturn_t dcp_common_irq(int irq, void *context)
+{
+	u32 msk;
+	struct dcp_dev *dev = (struct dcp_dev *) context;
+
+	del_timer(&dev->watchdog);
+
+	msk = DCP_STAT_IRQ(dcp_read(dev, DCP_REG_STAT));
+	dcp_clear(dev, msk, DCP_REG_STAT);
+	if (msk == 0)
+		return IRQ_NONE;
+
+	dev->ctx->stat |= dcp_read(dev,
+			dcp_chan_reg(DCP_REG_CHAN_STAT, USED_CHANNEL));
+
+	if (msk & DCP_STAT_CHAN_1)
+		tasklet_schedule(&dev->done_task);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t dcp_vmi_irq(int irq, void *context)
+{
+	return dcp_common_irq(irq, context);
+}
+
+static irqreturn_t dcp_irq(int irq, void *context)
+{
+	return dcp_common_irq(irq, context);
+}
+
+static void dcp_crypt(struct dcp_dev *dev, struct dcp_op *ctx)
+{
+	dev->ctx = ctx;
+
+	if ((ctx->flags & DCP_CBC) && ctx->req->info) {
+		ctx->flags |= DCP_CBC_INIT;
+		memcpy(dev->payload_base + AES_KEYSIZE_128,
+			ctx->req->info, AES_KEYSIZE_128);
+	}
+
+	dcp_op_start(dev, 1);
+}
+
+static void dcp_queue_task(unsigned long data)
+{
+	struct dcp_dev *dev = (struct dcp_dev *) data;
+	struct crypto_async_request *async_req, *backlog;
+	struct crypto_ablkcipher *tfm;
+	struct dcp_op *ctx;
+	struct dcp_dev_req_ctx *rctx;
+	struct ablkcipher_request *req;
+	unsigned long flags;
+
+	spin_lock_irqsave(&dev->queue_lock, flags);
+
+	backlog = crypto_get_backlog(&dev->queue);
+	async_req = crypto_dequeue_request(&dev->queue);
+
+	spin_unlock_irqrestore(&dev->queue_lock, flags);
+
+	if (!async_req)
+		goto ret_nothing_done;
+
+	if (backlog)
+		backlog->complete(backlog, -EINPROGRESS);
+
+	req = ablkcipher_request_cast(async_req);
+	tfm = crypto_ablkcipher_reqtfm(req);
+	rctx = ablkcipher_request_ctx(req);
+	ctx = crypto_ablkcipher_ctx(tfm);
+
+	if (!req->src || !req->dst)
+		goto ret_nothing_done;
+
+	ctx->flags |= rctx->mode;
+	ctx->req = req;
+
+	dcp_crypt(dev, ctx);
+
+	return;
+
+ret_nothing_done:
+	clear_bit(DCP_FLAG_BUSY, &dev->flags);
+}
+
+
+static int dcp_cra_init(struct crypto_tfm *tfm)
+{
+	const char *name = tfm->__crt_alg->cra_name;
+	struct dcp_op *ctx = crypto_tfm_ctx(tfm);
+
+	tfm->crt_ablkcipher.reqsize = sizeof(struct dcp_dev_req_ctx);
+
+	ctx->fallback = crypto_alloc_ablkcipher(name, 0,
+				CRYPTO_ALG_ASYNC | CRYPTO_ALG_NEED_FALLBACK);
+
+	if (IS_ERR(ctx->fallback)) {
+		dev_err(global_dev->dev, "Error allocating fallback algo %s\n",
+			name);
+		return PTR_ERR(ctx->fallback);
+	}
+
+	return 0;
+}
+
+static void dcp_cra_exit(struct crypto_tfm *tfm)
+{
+	struct dcp_op *ctx = crypto_tfm_ctx(tfm);
+
+	if (ctx->fallback)
+		crypto_free_ablkcipher(ctx->fallback);
+
+	ctx->fallback = NULL;
+}
+
+/* async interface */
+static int dcp_aes_setkey(struct crypto_ablkcipher *tfm, const u8 *key,
+		unsigned int len)
+{
+	struct dcp_op *ctx = crypto_ablkcipher_ctx(tfm);
+	unsigned int ret = 0;
+	ctx->keylen = len;
+	ctx->flags = 0;
+	if (len == AES_KEYSIZE_128) {
+		if (memcmp(ctx->key, key, AES_KEYSIZE_128)) {
+			memcpy(ctx->key, key, len);
+			ctx->flags |= DCP_NEW_KEY;
+		}
+		return 0;
+	}
+
+	ctx->fallback->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
+	ctx->fallback->base.crt_flags |=
+		(tfm->base.crt_flags & CRYPTO_TFM_REQ_MASK);
+
+	ret = crypto_ablkcipher_setkey(ctx->fallback, key, len);
+	if (ret) {
+		struct crypto_tfm *tfm_aux = crypto_ablkcipher_tfm(tfm);
+
+		tfm_aux->crt_flags &= ~CRYPTO_TFM_RES_MASK;
+		tfm_aux->crt_flags |=
+			(ctx->fallback->base.crt_flags & CRYPTO_TFM_RES_MASK);