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 4.15:

  API:

   - Disambiguate EBUSY when queueing crypto request by adding ENOSPC.
     This change touches code outside the crypto API.
   - Reset settings when empty string is written to rng_current.

  Algorithms:

   - Add OSCCA SM3 secure hash.

  Drivers:

   - Remove old mv_cesa driver (replaced by marvell/cesa).
   - Enable rfc3686/ecb/cfb/ofb AES in crypto4xx.
   - Add ccm/gcm AES in crypto4xx.
   - Add support for BCM7278 in iproc-rng200.
   - Add hash support on Exynos in s5p-sss.
   - Fix fallback-induced error in vmx.
   - Fix output IV in atmel-aes.
   - Fix empty GCM hash in mediatek.

  Others:

   - Fix DoS potential in lib/mpi.
   - Fix potential out-of-order issues with padata"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (162 commits)
  lib/mpi: call cond_resched() from mpi_powm() loop
  crypto: stm32/hash - Fix return issue on update
  crypto: dh - Remove pointless checks for NULL 'p' and 'g'
  crypto: qat - Clean up error handling in qat_dh_set_secret()
  crypto: dh - Don't permit 'key' or 'g' size longer than 'p'
  crypto: dh - Don't permit 'p' to be 0
  crypto: dh - Fix double free of ctx->p
  hwrng: iproc-rng200 - Add support for BCM7278
  dt-bindings: rng: Document BCM7278 RNG200 compatible
  crypto: chcr - Replace _manual_ swap with swap macro
  crypto: marvell - Add a NULL entry at the end of mv_cesa_plat_id_table[]
  hwrng: virtio - Virtio RNG devices need to be re-registered after suspend/resume
  crypto: atmel - remove empty functions
  crypto: ecdh - remove empty exit()
  MAINTAINERS: update maintainer for qat
  crypto: caam - remove unused param of ctx_map_to_sec4_sg()
  crypto: caam - remove unneeded edesc zeroization
  crypto: atmel-aes - Reset the controller before each use
  crypto: atmel-aes - properly set IV after {en,de}crypt
  hwrng: core - Reset user selected rng by writing "" to rng_current
  ...

11 files changed, 230 insertions, 31 deletions

diff --git a/include/crypto/dh.h b/include/crypto/dh.h
index f638998fb6d0ef..71e1bb24d79f03 100644
--- a/include/crypto/dh.h
+++ b/include/crypto/dh.h
@@ -53,7 +53,7 @@ struct dh {
  *
  * Return: size of the key in bytes
  */
-int crypto_dh_key_len(const struct dh *params);
+unsigned int crypto_dh_key_len(const struct dh *params);
 
 /**
  * crypto_dh_encode_key() - encode the private key
diff --git a/include/crypto/drbg.h b/include/crypto/drbg.h
index 22f884c97387e9..8f941102af3633 100644
--- a/include/crypto/drbg.h
+++ b/include/crypto/drbg.h
@@ -126,8 +126,7 @@ struct drbg_state {
 	__u8 *ctr_null_value;			/* CTR mode aligned zero buf */
 	__u8 *outscratchpadbuf;			/* CTR mode output scratchpad */
         __u8 *outscratchpad;			/* CTR mode aligned outbuf */
-	struct completion ctr_completion;	/* CTR mode async handler */
-	int ctr_async_err;			/* CTR mode async error */
+	struct crypto_wait ctr_wait;		/* CTR mode async wait obj */
 
 	bool seeded;		/* DRBG fully seeded? */
 	bool pr;		/* Prediction resistance enabled? */
diff --git a/include/crypto/ecdh.h b/include/crypto/ecdh.h
index 1aff2a8a3a6892..d696317c43a8c4 100644
--- a/include/crypto/ecdh.h
+++ b/include/crypto/ecdh.h
@@ -54,7 +54,7 @@ struct ecdh {
  *
  * Return: size of the key in bytes
  */
-int crypto_ecdh_key_len(const struct ecdh *params);
+unsigned int crypto_ecdh_key_len(const struct ecdh *params);
 
 /**
  * crypto_ecdh_encode_key() - encode the private key
diff --git a/include/crypto/gcm.h b/include/crypto/gcm.h
new file mode 100644
index 00000000000000..c50e057ea17e30
--- /dev/null
+++ b/include/crypto/gcm.h
@@ -0,0 +1,8 @@
+#ifndef _CRYPTO_GCM_H
+#define _CRYPTO_GCM_H
+
+#define GCM_AES_IV_SIZE 12
+#define GCM_RFC4106_IV_SIZE 8
+#define GCM_RFC4543_IV_SIZE 8
+
+#endif
diff --git a/include/crypto/gf128mul.h b/include/crypto/gf128mul.h
index 0977fb18ff68c6..fa0a63d298dc48 100644
--- a/include/crypto/gf128mul.h
+++ b/include/crypto/gf128mul.h
@@ -227,7 +227,7 @@ struct gf128mul_4k *gf128mul_init_4k_lle(const be128 *g);
 struct gf128mul_4k *gf128mul_init_4k_bbe(const be128 *g);
 void gf128mul_4k_lle(be128 *a, const struct gf128mul_4k *t);
 void gf128mul_4k_bbe(be128 *a, const struct gf128mul_4k *t);
-
+void gf128mul_x8_ble(le128 *r, const le128 *x);
 static inline void gf128mul_free_4k(struct gf128mul_4k *t)
 {
 	kzfree(t);
diff --git a/include/crypto/hash.h b/include/crypto/hash.h
index b5727bcd233626..0ed31fd80242cf 100644
--- a/include/crypto/hash.h
+++ b/include/crypto/hash.h
@@ -75,6 +75,7 @@ struct ahash_request {
  *	  state of the HASH transformation at the beginning. This shall fill in
  *	  the internal structures used during the entire duration of the whole
  *	  transformation. No data processing happens at this point.
+ *	  Note: mandatory.
  * @update: Push a chunk of data into the driver for transformation. This
  *	   function actually pushes blocks of data from upper layers into the
  *	   driver, which then passes those to the hardware as seen fit. This
@@ -84,16 +85,20 @@ struct ahash_request {
  *	   context, as this function may be called in parallel with the same
  *	   transformation object. Data processing can happen synchronously
  *	   [SHASH] or asynchronously [AHASH] at this point.
+ *	   Note: mandatory.
  * @final: Retrieve result from the driver. This function finalizes the
  *	   transformation and retrieves the resulting hash from the driver and
  *	   pushes it back to upper layers. No data processing happens at this
- *	   point.
+ *	   point unless hardware requires it to finish the transformation
+ *	   (then the data buffered by the device driver is processed).
+ *	   Note: mandatory.
  * @finup: Combination of @update and @final. This function is effectively a
  *	   combination of @update and @final calls issued in sequence. As some
  *	   hardware cannot do @update and @final separately, this callback was
  *	   added to allow such hardware to be used at least by IPsec. Data
  *	   processing can happen synchronously [SHASH] or asynchronously [AHASH]
  *	   at this point.
+ *	   Note: optional.
  * @digest: Combination of @init and @update and @final. This function
  *	    effectively behaves as the entire chain of operations, @init,
  *	    @update and @final issued in sequence. Just like @finup, this was
@@ -416,11 +421,10 @@ static inline bool crypto_ahash_has_setkey(struct crypto_ahash *tfm)
  *	 needed to perform the cipher operation
  *
  * This function is a "short-hand" for the function calls of
- * crypto_ahash_update and crypto_shash_final. The parameters have the same
+ * crypto_ahash_update and crypto_ahash_final. The parameters have the same
  * meaning as discussed for those separate functions.
  *
- * Return: 0 if the message digest creation was successful; < 0 if an error
- *	   occurred
+ * Return: see crypto_ahash_final()
  */
 int crypto_ahash_finup(struct ahash_request *req);
 
@@ -433,8 +437,11 @@ int crypto_ahash_finup(struct ahash_request *req);
  * based on all data added to the cipher handle. The message digest is placed
  * into the output buffer registered with the ahash_request handle.
  *
- * Return: 0 if the message digest creation was successful; < 0 if an error
- *	   occurred
+ * Return:
+ * 0		if the message digest was successfully calculated;
+ * -EINPROGRESS	if data is feeded into hardware (DMA) or queued for later;
+ * -EBUSY	if queue is full and request should be resubmitted later;
+ * other < 0	if an error occurred
  */
 int crypto_ahash_final(struct ahash_request *req);
 
@@ -447,8 +454,7 @@ int crypto_ahash_final(struct ahash_request *req);
  * crypto_ahash_update and crypto_ahash_final. The parameters have the same
  * meaning as discussed for those separate three functions.
  *
- * Return: 0 if the message digest creation was successful; < 0 if an error
- *	   occurred
+ * Return: see crypto_ahash_final()
  */
 int crypto_ahash_digest(struct ahash_request *req);
 
@@ -493,8 +499,7 @@ static inline int crypto_ahash_import(struct ahash_request *req, const void *in)
  * handle. Any potentially existing state created by previous operations is
  * discarded.
  *
- * Return: 0 if the message digest initialization was successful; < 0 if an
- *	   error occurred
+ * Return: see crypto_ahash_final()
  */
 static inline int crypto_ahash_init(struct ahash_request *req)
 {
@@ -510,8 +515,7 @@ static inline int crypto_ahash_init(struct ahash_request *req)
  * is pointed to by the scatter/gather list registered in the &ahash_request
  * handle
  *
- * Return: 0 if the message digest update was successful; < 0 if an error
- *	   occurred
+ * Return: see crypto_ahash_final()
  */
 static inline int crypto_ahash_update(struct ahash_request *req)
 {
diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h
index 75ec9c662268bc..6abf0a3604dc39 100644
--- a/include/crypto/if_alg.h
+++ b/include/crypto/if_alg.h
@@ -40,11 +40,6 @@ struct alg_sock {
 	void *private;
 };
 
-struct af_alg_completion {
-	struct completion completion;
-	int err;
-};
-
 struct af_alg_control {
 	struct af_alg_iv *iv;
 	int op;
@@ -152,7 +147,7 @@ struct af_alg_ctx {
 	void *iv;
 	size_t aead_assoclen;
 
-	struct af_alg_completion completion;
+	struct crypto_wait wait;
 
 	size_t used;
 	size_t rcvused;
@@ -177,19 +172,11 @@ void af_alg_link_sg(struct af_alg_sgl *sgl_prev, struct af_alg_sgl *sgl_new);
 
 int af_alg_cmsg_send(struct msghdr *msg, struct af_alg_control *con);
 
-int af_alg_wait_for_completion(int err, struct af_alg_completion *completion);
-void af_alg_complete(struct crypto_async_request *req, int err);
-
 static inline struct alg_sock *alg_sk(struct sock *sk)
 {
 	return (struct alg_sock *)sk;
 }
 
-static inline void af_alg_init_completion(struct af_alg_completion *completion)
-{
-	init_completion(&completion->completion);
-}
-
 /**
  * Size of available buffer for sending data from user space to kernel.
  *
diff --git a/include/crypto/sm3.h b/include/crypto/sm3.h
new file mode 100644
index 00000000000000..1438942dc77374
--- /dev/null
+++ b/include/crypto/sm3.h
@@ -0,0 +1,40 @@
+/*
+ * Common values for SM3 algorithm
+ */
+
+#ifndef _CRYPTO_SM3_H
+#define _CRYPTO_SM3_H
+
+#include <linux/types.h>
+
+#define SM3_DIGEST_SIZE	32
+#define SM3_BLOCK_SIZE	64
+
+#define SM3_T1		0x79CC4519
+#define SM3_T2		0x7A879D8A
+
+#define SM3_IVA		0x7380166f
+#define SM3_IVB		0x4914b2b9
+#define SM3_IVC		0x172442d7
+#define SM3_IVD		0xda8a0600
+#define SM3_IVE		0xa96f30bc
+#define SM3_IVF		0x163138aa
+#define SM3_IVG		0xe38dee4d
+#define SM3_IVH		0xb0fb0e4e
+
+extern const u8 sm3_zero_message_hash[SM3_DIGEST_SIZE];
+
+struct sm3_state {
+	u32 state[SM3_DIGEST_SIZE / 4];
+	u64 count;
+	u8 buffer[SM3_BLOCK_SIZE];
+};
+
+struct shash_desc;
+
+extern int crypto_sm3_update(struct shash_desc *desc, const u8 *data,
+			      unsigned int len);
+
+extern int crypto_sm3_finup(struct shash_desc *desc, const u8 *data,
+			     unsigned int len, u8 *hash);
+#endif
diff --git a/include/crypto/sm3_base.h b/include/crypto/sm3_base.h
new file mode 100644
index 00000000000000..256948e3929641
--- /dev/null
+++ b/include/crypto/sm3_base.h
@@ -0,0 +1,117 @@
+/*
+ * sm3_base.h - core logic for SM3 implementations
+ *
+ * Copyright (C) 2017 ARM Limited or its affiliates.
+ * Written by Gilad Ben-Yossef <gilad@benyossef.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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <crypto/internal/hash.h>
+#include <crypto/sm3.h>
+#include <linux/crypto.h>
+#include <linux/module.h>
+#include <asm/unaligned.h>
+
+typedef void (sm3_block_fn)(struct sm3_state *sst, u8 const *src, int blocks);
+
+static inline int sm3_base_init(struct shash_desc *desc)
+{
+	struct sm3_state *sctx = shash_desc_ctx(desc);
+
+	sctx->state[0] = SM3_IVA;
+	sctx->state[1] = SM3_IVB;
+	sctx->state[2] = SM3_IVC;
+	sctx->state[3] = SM3_IVD;
+	sctx->state[4] = SM3_IVE;
+	sctx->state[5] = SM3_IVF;
+	sctx->state[6] = SM3_IVG;
+	sctx->state[7] = SM3_IVH;
+	sctx->count = 0;
+
+	return 0;
+}
+
+static inline int sm3_base_do_update(struct shash_desc *desc,
+				      const u8 *data,
+				      unsigned int len,
+				      sm3_block_fn *block_fn)
+{
+	struct sm3_state *sctx = shash_desc_ctx(desc);
+	unsigned int partial = sctx->count % SM3_BLOCK_SIZE;
+
+	sctx->count += len;
+
+	if (unlikely((partial + len) >= SM3_BLOCK_SIZE)) {
+		int blocks;
+
+		if (partial) {
+			int p = SM3_BLOCK_SIZE - partial;
+
+			memcpy(sctx->buffer + partial, data, p);
+			data += p;
+			len -= p;
+
+			block_fn(sctx, sctx->buffer, 1);
+		}
+
+		blocks = len / SM3_BLOCK_SIZE;
+		len %= SM3_BLOCK_SIZE;
+
+		if (blocks) {
+			block_fn(sctx, data, blocks);
+			data += blocks * SM3_BLOCK_SIZE;
+		}
+		partial = 0;
+	}
+	if (len)
+		memcpy(sctx->buffer + partial, data, len);
+
+	return 0;
+}
+
+static inline int sm3_base_do_finalize(struct shash_desc *desc,
+					sm3_block_fn *block_fn)
+{
+	const int bit_offset = SM3_BLOCK_SIZE - sizeof(__be64);
+	struct sm3_state *sctx = shash_desc_ctx(desc);
+	__be64 *bits = (__be64 *)(sctx->buffer + bit_offset);
+	unsigned int partial = sctx->count % SM3_BLOCK_SIZE;
+
+	sctx->buffer[partial++] = 0x80;
+	if (partial > bit_offset) {
+		memset(sctx->buffer + partial, 0x0, SM3_BLOCK_SIZE - partial);
+		partial = 0;
+
+		block_fn(sctx, sctx->buffer, 1);
+	}
+
+	memset(sctx->buffer + partial, 0x0, bit_offset - partial);
+	*bits = cpu_to_be64(sctx->count << 3);
+	block_fn(sctx, sctx->buffer, 1);
+
+	return 0;
+}
+
+static inline int sm3_base_finish(struct shash_desc *desc, u8 *out)
+{
+	struct sm3_state *sctx = shash_desc_ctx(desc);
+	__be32 *digest = (__be32 *)out;
+	int i;
+
+	for (i = 0; i < SM3_DIGEST_SIZE / sizeof(__be32); i++)
+		put_unaligned_be32(sctx->state[i], digest++);
+
+	*sctx = (struct sm3_state){};
+	return 0;
+}
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index 84da9978e9516a..78508ca4b10857 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -24,6 +24,7 @@
 #include <linux/slab.h>
 #include <linux/string.h>
 #include <linux/uaccess.h>
+#include <linux/completion.h>
 
 /*
  * Autoloaded crypto modules should only use a prefixed name to avoid allowing
@@ -468,6 +469,45 @@ struct crypto_alg {
 } CRYPTO_MINALIGN_ATTR;
 
 /*
+ * A helper struct for waiting for completion of async crypto ops
+ */
+struct crypto_wait {
+	struct completion completion;
+	int err;
+};
+
+/*
+ * Macro for declaring a crypto op async wait object on stack
+ */
+#define DECLARE_CRYPTO_WAIT(_wait) \
+	struct crypto_wait _wait = { \
+		COMPLETION_INITIALIZER_ONSTACK((_wait).completion), 0 }
+
+/*
+ * Async ops completion helper functioons
+ */
+void crypto_req_done(struct crypto_async_request *req, int err);
+
+static inline int crypto_wait_req(int err, struct crypto_wait *wait)
+{
+	switch (err) {
+	case -EINPROGRESS:
+	case -EBUSY:
+		wait_for_completion(&wait->completion);
+		reinit_completion(&wait->completion);
+		err = wait->err;
+		break;
+	};
+
+	return err;
+}
+
+static inline void crypto_init_wait(struct crypto_wait *wait)
+{
+	init_completion(&wait->completion);
+}
+
+/*
  * Algorithm registration interface.
  */
 int crypto_register_alg(struct crypto_alg *alg);
diff --git a/include/linux/padata.h b/include/linux/padata.h
index 2f9c1f93b1ce4e..5d13d25da2c86b 100644
--- a/include/linux/padata.h
+++ b/include/linux/padata.h
@@ -37,6 +37,7 @@
  * @list: List entry, to attach to the padata lists.
  * @pd: Pointer to the internal control structure.
  * @cb_cpu: Callback cpu for serializatioon.
+ * @cpu: Cpu for parallelization.
  * @seq_nr: Sequence number of the parallelized data object.
  * @info: Used to pass information from the parallel to the serial function.
  * @parallel: Parallel execution function.
@@ -46,6 +47,7 @@ struct padata_priv {
 	struct list_head	list;
 	struct parallel_data	*pd;
 	int			cb_cpu;
+	int			cpu;
 	int			info;
 	void                    (*parallel)(struct padata_priv *padata);
 	void                    (*serial)(struct padata_priv *padata);
@@ -85,6 +87,7 @@ struct padata_serial_queue {
  * @swork: work struct for serialization.
  * @pd: Backpointer to the internal control structure.
  * @work: work struct for parallelization.
+ * @reorder_work: work struct for reordering.
  * @num_obj: Number of objects that are processed by this cpu.
  * @cpu_index: Index of the cpu.
  */
@@ -93,6 +96,7 @@ struct padata_parallel_queue {
        struct padata_list    reorder;
        struct parallel_data *pd;
        struct work_struct    work;
+       struct work_struct    reorder_work;
        atomic_t              num_obj;
        int                   cpu_index;
 };