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

* git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (31 commits)
  crypto: aes_generic - Fix checkpatch errors
  crypto: fcrypt - Fix checkpatch errors
  crypto: ecb - Fix checkpatch errors
  crypto: des_generic - Fix checkpatch errors
  crypto: deflate - Fix checkpatch errors
  crypto: crypto_null - Fix checkpatch errors
  crypto: cipher - Fix checkpatch errors
  crypto: crc32 - Fix checkpatch errors
  crypto: compress - Fix checkpatch errors
  crypto: cast6 - Fix checkpatch errors
  crypto: cast5 - Fix checkpatch errors
  crypto: camellia - Fix checkpatch errors
  crypto: authenc - Fix checkpatch errors
  crypto: api - Fix checkpatch errors
  crypto: anubis - Fix checkpatch errors
  crypto: algapi - Fix checkpatch errors
  crypto: blowfish - Fix checkpatch errors
  crypto: aead - Fix checkpatch errors
  crypto: ablkcipher - Fix checkpatch errors
  crypto: pcrypt - call the complete function on error
  ...

arch/arm/mach-nomadik/cpu-8815.c

@@ -86,11 +86,19 @@ static struct amba_device cpu8815_amba_gpio[] = {
 	},
 };
 
+static struct amba_device cpu8815_amba_rng = {
+	.dev = {
+		.init_name = "rng",
+	},
+	__MEM_4K_RESOURCE(NOMADIK_RNG_BASE),
+};
+
 static struct amba_device *amba_devs[] __initdata = {
 	cpu8815_amba_gpio + 0,
 	cpu8815_amba_gpio + 1,
 	cpu8815_amba_gpio + 2,
 	cpu8815_amba_gpio + 3,
+	&cpu8815_amba_rng
 };
 
 static int __init cpu8815_init(void)

arch/s390/crypto/aes_s390.c

@@ -78,14 +78,14 @@ static int setkey_fallback_cip(struct crypto_tfm *tfm, const u8 *in_key,
 	struct s390_aes_ctx *sctx = crypto_tfm_ctx(tfm);
 	int ret;
 
-	sctx->fallback.blk->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
-	sctx->fallback.blk->base.crt_flags |= (tfm->crt_flags &
+	sctx->fallback.cip->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
+	sctx->fallback.cip->base.crt_flags |= (tfm->crt_flags &
 			CRYPTO_TFM_REQ_MASK);
 
 	ret = crypto_cipher_setkey(sctx->fallback.cip, in_key, key_len);
 	if (ret) {
 		tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
-		tfm->crt_flags |= (sctx->fallback.blk->base.crt_flags &
+		tfm->crt_flags |= (sctx->fallback.cip->base.crt_flags &
 				CRYPTO_TFM_RES_MASK);
 	}
 	return ret;

crypto/Kconfig

@@ -114,6 +114,16 @@ config CRYPTO_NULL
 	help
 	  These are 'Null' algorithms, used by IPsec, which do nothing.
 
+config CRYPTO_PCRYPT
+	tristate "Parallel crypto engine (EXPERIMENTAL)"
+	depends on SMP && EXPERIMENTAL
+	select PADATA
+	select CRYPTO_MANAGER
+	select CRYPTO_AEAD
+	help
+	  This converts an arbitrary crypto algorithm into a parallel
+	  algorithm that executes in kernel threads.
+
 config CRYPTO_WORKQUEUE
        tristate
 

crypto/Makefile

@@ -56,6 +56,7 @@ obj-$(CONFIG_CRYPTO_XTS) += xts.o
 obj-$(CONFIG_CRYPTO_CTR) += ctr.o
 obj-$(CONFIG_CRYPTO_GCM) += gcm.o
 obj-$(CONFIG_CRYPTO_CCM) += ccm.o
+obj-$(CONFIG_CRYPTO_PCRYPT) += pcrypt.o
 obj-$(CONFIG_CRYPTO_CRYPTD) += cryptd.o
 obj-$(CONFIG_CRYPTO_DES) += des_generic.o
 obj-$(CONFIG_CRYPTO_FCRYPT) += fcrypt.o

crypto/aes_generic.c

@@ -1127,7 +1127,7 @@ EXPORT_SYMBOL_GPL(crypto_il_tab);
 
 #define star_x(x) (((x) & 0x7f7f7f7f) << 1) ^ ((((x) & 0x80808080) >> 7) * 0x1b)
 
-#define imix_col(y,x)	do {		\
+#define imix_col(y, x)	do {		\
 	u	= star_x(x);		\
 	v	= star_x(u);		\
 	w	= star_x(v);		\

crypto/anubis.c

@@ -469,14 +469,13 @@ static int anubis_setkey(struct crypto_tfm *tfm, const u8 *in_key,
 	u32 kappa[ANUBIS_MAX_N];
 	u32 inter[ANUBIS_MAX_N];
 
-	switch (key_len)
-	{
+	switch (key_len) {
 		case 16: case 20: case 24: case 28:
 		case 32: case 36: case 40:
 			break;
 		default:
 			*flags |= CRYPTO_TFM_RES_BAD_KEY_LEN;
-			return - EINVAL;
+			return -EINVAL;
 	}
 
 	ctx->key_len = key_len * 8;
@@ -530,24 +529,25 @@ static int anubis_setkey(struct crypto_tfm *tfm, const u8 *in_key,
 		/*
 		 * compute kappa^{r+1} from kappa^r:
 		 */
-		if (r == R) {
+		if (r == R)
 			break;
-		}
 		for (i = 0; i < N; i++) {
 			int j = i;
 			inter[i]  = T0[(kappa[j--] >> 24)       ];
-			if (j < 0) j = N - 1;
+			if (j < 0)
+				j = N - 1;
 			inter[i] ^= T1[(kappa[j--] >> 16) & 0xff];
-			if (j < 0) j = N - 1;
+			if (j < 0)
+				j = N - 1;
 			inter[i] ^= T2[(kappa[j--] >>  8) & 0xff];
-			if (j < 0) j = N - 1;
+			if (j < 0)
+				j = N - 1;
 			inter[i] ^= T3[(kappa[j  ]      ) & 0xff];
 		}
 		kappa[0] = inter[0] ^ rc[r];
-		for (i = 1; i < N; i++) {
+		for (i = 1; i < N; i++)
 			kappa[i] = inter[i];
 	}
-	}
 
 	/*
 	 * generate inverse key schedule: K'^0 = K^R, K'^R =

crypto/api.c

@@ -318,7 +318,6 @@ static void crypto_exit_ops(struct crypto_tfm *tfm)
 
 	default:
 		BUG();
-		
 	}
 }
 

crypto/authenc.c

@@ -194,7 +194,7 @@ static void authenc_verify_ahash_update_done(struct crypto_async_request *areq,
 	scatterwalk_map_and_copy(ihash, areq_ctx->sg, areq_ctx->cryptlen,
 				 authsize, 0);
 
-	err = memcmp(ihash, ahreq->result, authsize) ? -EBADMSG: 0;
+	err = memcmp(ihash, ahreq->result, authsize) ? -EBADMSG : 0;
 	if (err)
 		goto out;
 
@@ -231,7 +231,7 @@ static void authenc_verify_ahash_done(struct crypto_async_request *areq,
 	scatterwalk_map_and_copy(ihash, areq_ctx->sg, areq_ctx->cryptlen,
 				 authsize, 0);
 
-	err = memcmp(ihash, ahreq->result, authsize) ? -EBADMSG: 0;
+	err = memcmp(ihash, ahreq->result, authsize) ? -EBADMSG : 0;
 	if (err)
 		goto out;
 
@@ -464,7 +464,7 @@ static int crypto_authenc_verify(struct aead_request *req,
 	ihash = ohash + authsize;
 	scatterwalk_map_and_copy(ihash, areq_ctx->sg, areq_ctx->cryptlen,
 				 authsize, 0);
-	return memcmp(ihash, ohash, authsize) ? -EBADMSG: 0;
+	return memcmp(ihash, ohash, authsize) ? -EBADMSG : 0;
 }
 
 static int crypto_authenc_iverify(struct aead_request *req, u8 *iv,

crypto/blowfish.c

@@ -417,10 +417,10 @@ static int bf_setkey(struct crypto_tfm *tfm, const u8 *key, unsigned int keylen)
 
 	/* Actual subkey generation */
 	for (j = 0, i = 0; i < 16 + 2; i++) {
-		temp = (((u32 )key[j] << 24) |
-			((u32 )key[(j + 1) % keylen] << 16) |
-			((u32 )key[(j + 2) % keylen] << 8) |
-			((u32 )key[(j + 3) % keylen]));
+		temp = (((u32)key[j] << 24) |
+			((u32)key[(j + 1) % keylen] << 16) |
+			((u32)key[(j + 2) % keylen] << 8) |
+			((u32)key[(j + 3) % keylen]));
 
 		P[i] = P[i] ^ temp;
 		j = (j + 4) % keylen;

crypto/cast5.c

@@ -569,12 +569,12 @@ static const u32 sb8[256] = {
 	0xeaee6801, 0x8db2a283, 0xea8bf59e
 };
 
-#define F1(D,m,r)  (  (I = ((m) + (D))), (I=rol32(I,(r))),   \
-    (((s1[I >> 24] ^ s2[(I>>16)&0xff]) - s3[(I>>8)&0xff]) + s4[I&0xff]) )
-#define F2(D,m,r)  (  (I = ((m) ^ (D))), (I=rol32(I,(r))),   \
-    (((s1[I >> 24] - s2[(I>>16)&0xff]) + s3[(I>>8)&0xff]) ^ s4[I&0xff]) )
-#define F3(D,m,r)  (  (I = ((m) - (D))), (I=rol32(I,(r))),   \
-    (((s1[I >> 24] + s2[(I>>16)&0xff]) ^ s3[(I>>8)&0xff]) - s4[I&0xff]) )
+#define F1(D, m, r)  ((I = ((m) + (D))), (I = rol32(I, (r))),   \
+    (((s1[I >> 24] ^ s2[(I>>16)&0xff]) - s3[(I>>8)&0xff]) + s4[I&0xff]))
+#define F2(D, m, r)  ((I = ((m) ^ (D))), (I = rol32(I, (r))),   \
+    (((s1[I >> 24] - s2[(I>>16)&0xff]) + s3[(I>>8)&0xff]) ^ s4[I&0xff]))
+#define F3(D, m, r)  ((I = ((m) - (D))), (I = rol32(I, (r))),   \
+    (((s1[I >> 24] + s2[(I>>16)&0xff]) ^ s3[(I>>8)&0xff]) - s4[I&0xff]))
 
 
 static void cast5_encrypt(struct crypto_tfm *tfm, u8 *outbuf, const u8 *inbuf)
@@ -694,7 +694,7 @@ static void cast5_decrypt(struct crypto_tfm *tfm, u8 *outbuf, const u8 *inbuf)
 	dst[1] = cpu_to_be32(l);
 }
 
-static void key_schedule(u32 * x, u32 * z, u32 * k)
+static void key_schedule(u32 *x, u32 *z, u32 *k)
 {
 
 #define xi(i)   ((x[(i)/4] >> (8*(3-((i)%4)))) & 0xff)

crypto/cast6.c

@@ -35,12 +35,12 @@ struct cast6_ctx {
 	u8 Kr[12][4];
 };
 
-#define F1(D,r,m)  (  (I = ((m) + (D))), (I=rol32(I,(r))),   \
-    (((s1[I >> 24] ^ s2[(I>>16)&0xff]) - s3[(I>>8)&0xff]) + s4[I&0xff]) )
-#define F2(D,r,m)  (  (I = ((m) ^ (D))), (I=rol32(I,(r))),   \
-    (((s1[I >> 24] - s2[(I>>16)&0xff]) + s3[(I>>8)&0xff]) ^ s4[I&0xff]) )
-#define F3(D,r,m)  (  (I = ((m) - (D))), (I=rol32(I,(r))),   \
-    (((s1[I >> 24] + s2[(I>>16)&0xff]) ^ s3[(I>>8)&0xff]) - s4[I&0xff]) )
+#define F1(D, r, m)  ((I = ((m) + (D))), (I = rol32(I, (r))),   \
+    (((s1[I >> 24] ^ s2[(I>>16)&0xff]) - s3[(I>>8)&0xff]) + s4[I&0xff]))
+#define F2(D, r, m)  ((I = ((m) ^ (D))), (I = rol32(I, (r))),   \
+    (((s1[I >> 24] - s2[(I>>16)&0xff]) + s3[(I>>8)&0xff]) ^ s4[I&0xff]))
+#define F3(D, r, m)  ((I = ((m) - (D))), (I = rol32(I, (r))),   \
+    (((s1[I >> 24] + s2[(I>>16)&0xff]) ^ s3[(I>>8)&0xff]) - s4[I&0xff]))
 
 static const u32 s1[256] = {
 	0x30fb40d4, 0x9fa0ff0b, 0x6beccd2f, 0x3f258c7a, 0x1e213f2f,
@@ -369,7 +369,8 @@ static const u8 Tr[4][8] = {
 };
 
 /* forward octave */
-static void W(u32 *key, unsigned int i) {
+static void W(u32 *key, unsigned int i)
+{
 	u32 I;
 	key[6] ^= F1(key[7], Tr[i % 4][0], Tm[i][0]);
 	key[5] ^= F2(key[6], Tr[i % 4][1], Tm[i][1]);
@@ -395,8 +396,8 @@ static int cast6_setkey(struct crypto_tfm *tfm, const u8 *in_key,
 		return -EINVAL;
 	}
 
-	memset (p_key, 0, 32);
-	memcpy (p_key, in_key, key_len);
+	memset(p_key, 0, 32);
+	memcpy(p_key, in_key, key_len);
 
 	key[0] = be32_to_cpu(p_key[0]);		/* A */
 	key[1] = be32_to_cpu(p_key[1]);		/* B */
@@ -407,11 +408,9 @@ static int cast6_setkey(struct crypto_tfm *tfm, const u8 *in_key,
 	key[6] = be32_to_cpu(p_key[6]);		/* G */
 	key[7] = be32_to_cpu(p_key[7]);		/* H */
 
-
-
 	for (i = 0; i < 12; i++) {
-		W (key, 2 * i);
-		W (key, 2 * i + 1);
+		W(key, 2 * i);
+		W(key, 2 * i + 1);
 
 		c->Kr[i][0] = key[0] & 0x1f;
 		c->Kr[i][1] = key[2] & 0x1f;
@@ -428,7 +427,8 @@ static int cast6_setkey(struct crypto_tfm *tfm, const u8 *in_key,
 }
 
 /*forward quad round*/
-static void Q (u32 * block, u8 * Kr, u32 * Km) {
+static void Q(u32 *block, u8 *Kr, u32 *Km)
+{
 	u32 I;
 	block[2] ^= F1(block[3], Kr[0], Km[0]);
 	block[1] ^= F2(block[2], Kr[1], Km[1]);
@@ -437,7 +437,8 @@ static void Q (u32 * block, u8 * Kr, u32 * Km) {
 }
 
 /*reverse quad round*/
-static void QBAR (u32 * block, u8 * Kr, u32 * Km) {
+static void QBAR(u32 *block, u8 *Kr, u32 *Km)
+{
 	u32 I;
 	block[3] ^= F1(block[0], Kr[3], Km[3]);
 	block[0] ^= F3(block[1], Kr[2], Km[2]);
@@ -451,26 +452,26 @@ static void cast6_encrypt(struct crypto_tfm *tfm, u8 *outbuf, const u8 *inbuf)
 	const __be32 *src = (const __be32 *)inbuf;
 	__be32 *dst = (__be32 *)outbuf;
 	u32 block[4];
-	u32 * Km; 
-	u8 * Kr;
+	u32 *Km;
+	u8 *Kr;
 
 	block[0] = be32_to_cpu(src[0]);
 	block[1] = be32_to_cpu(src[1]);
 	block[2] = be32_to_cpu(src[2]);
 	block[3] = be32_to_cpu(src[3]);
 
-	Km = c->Km[0]; Kr = c->Kr[0]; Q (block, Kr, Km);
-	Km = c->Km[1]; Kr = c->Kr[1]; Q (block, Kr, Km);
-	Km = c->Km[2]; Kr = c->Kr[2]; Q (block, Kr, Km);
-	Km = c->Km[3]; Kr = c->Kr[3]; Q (block, Kr, Km);
-	Km = c->Km[4]; Kr = c->Kr[4]; Q (block, Kr, Km);
-	Km = c->Km[5]; Kr = c->Kr[5]; Q (block, Kr, Km);
-	Km = c->Km[6]; Kr = c->Kr[6]; QBAR (block, Kr, Km);
-	Km = c->Km[7]; Kr = c->Kr[7]; QBAR (block, Kr, Km);
-	Km = c->Km[8]; Kr = c->Kr[8]; QBAR (block, Kr, Km);
-	Km = c->Km[9]; Kr = c->Kr[9]; QBAR (block, Kr, Km);
-	Km = c->Km[10]; Kr = c->Kr[10]; QBAR (block, Kr, Km);
-	Km = c->Km[11]; Kr = c->Kr[11]; QBAR (block, Kr, Km);
+	Km = c->Km[0]; Kr = c->Kr[0]; Q(block, Kr, Km);
+	Km = c->Km[1]; Kr = c->Kr[1]; Q(block, Kr, Km);
+	Km = c->Km[2]; Kr = c->Kr[2]; Q(block, Kr, Km);
+	Km = c->Km[3]; Kr = c->Kr[3]; Q(block, Kr, Km);
+	Km = c->Km[4]; Kr = c->Kr[4]; Q(block, Kr, Km);
+	Km = c->Km[5]; Kr = c->Kr[5]; Q(block, Kr, Km);
+	Km = c->Km[6]; Kr = c->Kr[6]; QBAR(block, Kr, Km);
+	Km = c->Km[7]; Kr = c->Kr[7]; QBAR(block, Kr, Km);
+	Km = c->Km[8]; Kr = c->Kr[8]; QBAR(block, Kr, Km);
+	Km = c->Km[9]; Kr = c->Kr[9]; QBAR(block, Kr, Km);
+	Km = c->Km[10]; Kr = c->Kr[10]; QBAR(block, Kr, Km);
+	Km = c->Km[11]; Kr = c->Kr[11]; QBAR(block, Kr, Km);
 
 	dst[0] = cpu_to_be32(block[0]);
 	dst[1] = cpu_to_be32(block[1]);
@@ -478,31 +479,32 @@ static void cast6_encrypt(struct crypto_tfm *tfm, u8 *outbuf, const u8 *inbuf)
 	dst[3] = cpu_to_be32(block[3]);
 }
 
-static void cast6_decrypt(struct crypto_tfm *tfm, u8 *outbuf, const u8 *inbuf) {
-	struct cast6_ctx * c = crypto_tfm_ctx(tfm);
+static void cast6_decrypt(struct crypto_tfm *tfm, u8 *outbuf, const u8 *inbuf)
+{
+	struct cast6_ctx *c = crypto_tfm_ctx(tfm);
 	const __be32 *src = (const __be32 *)inbuf;
 	__be32 *dst = (__be32 *)outbuf;
 	u32 block[4];
-	u32 * Km; 
-	u8 * Kr;
+	u32 *Km;
+	u8 *Kr;
 
 	block[0] = be32_to_cpu(src[0]);
 	block[1] = be32_to_cpu(src[1]);
 	block[2] = be32_to_cpu(src[2]);
 	block[3] = be32_to_cpu(src[3]);
 
-	Km = c->Km[11]; Kr = c->Kr[11]; Q (block, Kr, Km);
-	Km = c->Km[10]; Kr = c->Kr[10]; Q (block, Kr, Km);
-	Km = c->Km[9]; Kr = c->Kr[9]; Q (block, Kr, Km);
-	Km = c->Km[8]; Kr = c->Kr[8]; Q (block, Kr, Km);
-	Km = c->Km[7]; Kr = c->Kr[7]; Q (block, Kr, Km);
-	Km = c->Km[6]; Kr = c->Kr[6]; Q (block, Kr, Km);
-	Km = c->Km[5]; Kr = c->Kr[5]; QBAR (block, Kr, Km);
-	Km = c->Km[4]; Kr = c->Kr[4]; QBAR (block, Kr, Km);
-	Km = c->Km[3]; Kr = c->Kr[3]; QBAR (block, Kr, Km);
-	Km = c->Km[2]; Kr = c->Kr[2]; QBAR (block, Kr, Km);
-	Km = c->Km[1]; Kr = c->Kr[1]; QBAR (block, Kr, Km);
-	Km = c->Km[0]; Kr = c->Kr[0]; QBAR (block, Kr, Km);
+	Km = c->Km[11]; Kr = c->Kr[11]; Q(block, Kr, Km);
+	Km = c->Km[10]; Kr = c->Kr[10]; Q(block, Kr, Km);
+	Km = c->Km[9]; Kr = c->Kr[9]; Q(block, Kr, Km);
+	Km = c->Km[8]; Kr = c->Kr[8]; Q(block, Kr, Km);
+	Km = c->Km[7]; Kr = c->Kr[7]; Q(block, Kr, Km);
+	Km = c->Km[6]; Kr = c->Kr[6]; Q(block, Kr, Km);
+	Km = c->Km[5]; Kr = c->Kr[5]; QBAR(block, Kr, Km);
+	Km = c->Km[4]; Kr = c->Kr[4]; QBAR(block, Kr, Km);
+	Km = c->Km[3]; Kr = c->Kr[3]; QBAR(block, Kr, Km);
+	Km = c->Km[2]; Kr = c->Kr[2]; QBAR(block, Kr, Km);
+	Km = c->Km[1]; Kr = c->Kr[1]; QBAR(block, Kr, Km);
+	Km = c->Km[0]; Kr = c->Kr[0]; QBAR(block, Kr, Km);
 
 	dst[0] = cpu_to_be32(block[0]);
 	dst[1] = cpu_to_be32(block[1]);

crypto/deflate.c

@@ -49,7 +49,7 @@ static int deflate_comp_init(struct deflate_ctx *ctx)
 	struct z_stream_s *stream = &ctx->comp_stream;
 
 	stream->workspace = vmalloc(zlib_deflate_workspacesize());
-	if (!stream->workspace ) {
+	if (!stream->workspace) {
 		ret = -ENOMEM;
 		goto out;
 	}
@@ -74,7 +74,7 @@ static int deflate_decomp_init(struct deflate_ctx *ctx)
 	struct z_stream_s *stream = &ctx->decomp_stream;
 
 	stream->workspace = kzalloc(zlib_inflate_workspacesize(), GFP_KERNEL);
-	if (!stream->workspace ) {
+	if (!stream->workspace) {
 		ret = -ENOMEM;
 		goto out;
 	}

crypto/des_generic.c

@@ -869,8 +869,7 @@ static int des3_ede_setkey(struct crypto_tfm *tfm, const u8 *key,
 
 	if (unlikely(!((K[0] ^ K[2]) | (K[1] ^ K[3])) ||
 		     !((K[2] ^ K[4]) | (K[3] ^ K[5]))) &&
-		     (*flags & CRYPTO_TFM_REQ_WEAK_KEY))
-	{
+		     (*flags & CRYPTO_TFM_REQ_WEAK_KEY)) {
 		*flags |= CRYPTO_TFM_RES_WEAK_KEY;
 		return -EINVAL;
 	}

crypto/fcrypt.c

@@ -60,13 +60,13 @@ do {								\
 	u32 t = lo & ((1 << n) - 1);				\
 	lo = (lo >> n) | ((hi & ((1 << n) - 1)) << (32 - n));	\
 	hi = (hi >> n) | (t << (24-n));				\
-} while(0)
+} while (0)
 
 /* Rotate right one 64 bit number as a 56 bit number */
 #define ror56_64(k, n)						\
 do {								\
 	k = (k >> n) | ((k & ((1 << n) - 1)) << (56 - n));	\
-} while(0)
+} while (0)
 
 /*
  * Sboxes for Feistel network derived from
@@ -228,7 +228,7 @@ do {									\
 	union lc4 { __be32 l; u8 c[4]; } u;				\
 	u.l = sched ^ R;						\
 	L ^= sbox0[u.c[0]] ^ sbox1[u.c[1]] ^ sbox2[u.c[2]] ^ sbox3[u.c[3]]; \
-} while(0)
+} while (0)
 
 /*
  * encryptor

crypto/gcm.c

@@ -37,6 +37,19 @@ struct crypto_rfc4106_ctx {
 	u8 nonce[4];
 };
 
+struct crypto_rfc4543_ctx {
+	struct crypto_aead *child;
+	u8 nonce[4];
+};
+
+struct crypto_rfc4543_req_ctx {
+	u8 auth_tag[16];
+	struct scatterlist cipher[1];
+	struct scatterlist payload[2];
+	struct scatterlist assoc[2];
+	struct aead_request subreq;
+};
+
 struct crypto_gcm_ghash_ctx {
 	unsigned int cryptlen;
 	struct scatterlist *src;
@@ -1047,6 +1060,272 @@ static struct crypto_template crypto_rfc4106_tmpl = {
 	.module = THIS_MODULE,
 };
 
+static inline struct crypto_rfc4543_req_ctx *crypto_rfc4543_reqctx(
+	struct aead_request *req)
+{
+	unsigned long align = crypto_aead_alignmask(crypto_aead_reqtfm(req));
+
+	return (void *)PTR_ALIGN((u8 *)aead_request_ctx(req), align + 1);
+}
+
+static int crypto_rfc4543_setkey(struct crypto_aead *parent, const u8 *key,
+				 unsigned int keylen)
+{
+	struct crypto_rfc4543_ctx *ctx = crypto_aead_ctx(parent);
+	struct crypto_aead *child = ctx->child;
+	int err;
+
+	if (keylen < 4)
+		return -EINVAL;
+
+	keylen -= 4;
+	memcpy(ctx->nonce, key + keylen, 4);
+
+	crypto_aead_clear_flags(child, CRYPTO_TFM_REQ_MASK);
+	crypto_aead_set_flags(child, crypto_aead_get_flags(parent) &
+				     CRYPTO_TFM_REQ_MASK);
+	err = crypto_aead_setkey(child, key, keylen);
+	crypto_aead_set_flags(parent, crypto_aead_get_flags(child) &
+				      CRYPTO_TFM_RES_MASK);
+
+	return err;
+}
+
+static int crypto_rfc4543_setauthsize(struct crypto_aead *parent,
+				      unsigned int authsize)
+{
+	struct crypto_rfc4543_ctx *ctx = crypto_aead_ctx(parent);
+
+	if (authsize != 16)
+		return -EINVAL;
+
+	return crypto_aead_setauthsize(ctx->child, authsize);
+}
+
+/* this is the same as crypto_authenc_chain */
+static void crypto_rfc4543_chain(struct scatterlist *head,
+				 struct scatterlist *sg, int chain)
+{
+	if (chain) {
+		head->length += sg->length;
+		sg = scatterwalk_sg_next(sg);
+	}
+
+	if (sg)
+		scatterwalk_sg_chain(head, 2, sg);
+	else
+		sg_mark_end(head);
+}
+
+static struct aead_request *crypto_rfc4543_crypt(struct aead_request *req,
+						 int enc)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct crypto_rfc4543_ctx *ctx = crypto_aead_ctx(aead);
+	struct crypto_rfc4543_req_ctx *rctx = crypto_rfc4543_reqctx(req);
+	struct aead_request *subreq = &rctx->subreq;
+	struct scatterlist *dst = req->dst;
+	struct scatterlist *cipher = rctx->cipher;
+	struct scatterlist *payload = rctx->payload;
+	struct scatterlist *assoc = rctx->assoc;
+	unsigned int authsize = crypto_aead_authsize(aead);
+	unsigned int assoclen = req->assoclen;
+	struct page *dstp;
+	u8 *vdst;
+	u8 *iv = PTR_ALIGN((u8 *)(rctx + 1) + crypto_aead_reqsize(ctx->child),
+			   crypto_aead_alignmask(ctx->child) + 1);
+
+	memcpy(iv, ctx->nonce, 4);
+	memcpy(iv + 4, req->iv, 8);
+
+	/* construct cipher/plaintext */
+	if (enc)
+		memset(rctx->auth_tag, 0, authsize);
+	else
+		scatterwalk_map_and_copy(rctx->auth_tag, dst,
+					 req->cryptlen - authsize,
+					 authsize, 0);
+
+	sg_init_one(cipher, rctx->auth_tag, authsize);
+
+	/* construct the aad */
+	dstp = sg_page(dst);
+	vdst = PageHighMem(dstp) ? NULL : page_address(dstp) + dst->offset;
+
+	sg_init_table(payload, 2);
+	sg_set_buf(payload, req->iv, 8);
+	crypto_rfc4543_chain(payload, dst, vdst == req->iv + 8);
+	assoclen += 8 + req->cryptlen - (enc ? 0 : authsize);
+
+	sg_init_table(assoc, 2);
+	sg_set_page(assoc, sg_page(req->assoc), req->assoc->length,
+		    req->assoc->offset);
+	crypto_rfc4543_chain(assoc, payload, 0);
+
+	aead_request_set_tfm(subreq, ctx->child);
+	aead_request_set_callback(subreq, req->base.flags, req->base.complete,
+				  req->base.data);
+	aead_request_set_crypt(subreq, cipher, cipher, enc ? 0 : authsize, iv);
+	aead_request_set_assoc(subreq, assoc, assoclen);
+
+	return subreq;
+}
+
+static int crypto_rfc4543_encrypt(struct aead_request *req)
+{
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct crypto_rfc4543_req_ctx *rctx = crypto_rfc4543_reqctx(req);
+	struct aead_request *subreq;
+	int err;
+
+	subreq = crypto_rfc4543_crypt(req, 1);
+	err = crypto_aead_encrypt(subreq);
+	if (err)
+		return err;
+
+	scatterwalk_map_and_copy(rctx->auth_tag, req->dst, req->cryptlen,
+				 crypto_aead_authsize(aead), 1);
+
+	return 0;
+}
+
+static int crypto_rfc4543_decrypt(struct aead_request *req)
+{
+	req = crypto_rfc4543_crypt(req, 0);
+
+	return crypto_aead_decrypt(req);
+}
+
+static int crypto_rfc4543_init_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_instance *inst = (void *)tfm->__crt_alg;
+	struct crypto_aead_spawn *spawn = crypto_instance_ctx(inst);
+	struct crypto_rfc4543_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_aead *aead;
+	unsigned long align;
+
+	aead = crypto_spawn_aead(spawn);
+	if (IS_ERR(aead))
+		return PTR_ERR(aead);
+
+	ctx->child = aead;
+
+	align = crypto_aead_alignmask(aead);
+	align &= ~(crypto_tfm_ctx_alignment() - 1);
+	tfm->crt_aead.reqsize = sizeof(struct crypto_rfc4543_req_ctx) +
+				ALIGN(crypto_aead_reqsize(aead),
+				      crypto_tfm_ctx_alignment()) +
+				align + 16;
+
+	return 0;
+}
+
+static void crypto_rfc4543_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct crypto_rfc4543_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_aead(ctx->child);
+}
+
+static struct crypto_instance *crypto_rfc4543_alloc(struct rtattr **tb)
+{
+	struct crypto_attr_type *algt;
+	struct crypto_instance *inst;
+	struct crypto_aead_spawn *spawn;
+	struct crypto_alg *alg;
+	const char *ccm_name;
+	int err;
+
+	algt = crypto_get_attr_type(tb);
+	err = PTR_ERR(algt);
+	if (IS_ERR(algt))
+		return ERR_PTR(err);
+
+	if ((algt->type ^ CRYPTO_ALG_TYPE_AEAD) & algt->mask)
+		return ERR_PTR(-EINVAL);
+
+	ccm_name = crypto_attr_alg_name(tb[1]);
+	err = PTR_ERR(ccm_name);
+	if (IS_ERR(ccm_name))
+		return ERR_PTR(err);
+
+	inst = kzalloc(sizeof(*inst) + sizeof(*spawn), GFP_KERNEL);
+	if (!inst)
+		return ERR_PTR(-ENOMEM);
+
+	spawn = crypto_instance_ctx(inst);
+	crypto_set_aead_spawn(spawn, inst);
+	err = crypto_grab_aead(spawn, ccm_name, 0,
+			       crypto_requires_sync(algt->type, algt->mask));
+	if (err)
+		goto out_free_inst;
+
+	alg = crypto_aead_spawn_alg(spawn);
+
+	err = -EINVAL;
+
+	/* We only support 16-byte blocks. */
+	if (alg->cra_aead.ivsize != 16)
+		goto out_drop_alg;
+
+	/* Not a stream cipher? */
+	if (alg->cra_blocksize != 1)
+		goto out_drop_alg;
+
+	err = -ENAMETOOLONG;
+	if (snprintf(inst->alg.cra_name, CRYPTO_MAX_ALG_NAME,
+		     "rfc4543(%s)", alg->cra_name) >= CRYPTO_MAX_ALG_NAME ||
+	    snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+		     "rfc4543(%s)", alg->cra_driver_name) >=
+	    CRYPTO_MAX_ALG_NAME)
+		goto out_drop_alg;
+
+	inst->alg.cra_flags = CRYPTO_ALG_TYPE_AEAD;
+	inst->alg.cra_flags |= alg->cra_flags & CRYPTO_ALG_ASYNC;
+	inst->alg.cra_priority = alg->cra_priority;
+	inst->alg.cra_blocksize = 1;
+	inst->alg.cra_alignmask = alg->cra_alignmask;
+	inst->alg.cra_type = &crypto_nivaead_type;
+
+	inst->alg.cra_aead.ivsize = 8;
+	inst->alg.cra_aead.maxauthsize = 16;
+
+	inst->alg.cra_ctxsize = sizeof(struct crypto_rfc4543_ctx);
+
+	inst->alg.cra_init = crypto_rfc4543_init_tfm;
+	inst->alg.cra_exit = crypto_rfc4543_exit_tfm;
+
+	inst->alg.cra_aead.setkey = crypto_rfc4543_setkey;
+	inst->alg.cra_aead.setauthsize = crypto_rfc4543_setauthsize;
+	inst->alg.cra_aead.encrypt = crypto_rfc4543_encrypt;
+	inst->alg.cra_aead.decrypt = crypto_rfc4543_decrypt;
+
+	inst->alg.cra_aead.geniv = "seqiv";
+
+out:
+	return inst;
+
+out_drop_alg:
+	crypto_drop_aead(spawn);
+out_free_inst:
+	kfree(inst);
+	inst = ERR_PTR(err);
+	goto out;
+}
+
+static void crypto_rfc4543_free(struct crypto_instance *inst)
+{
+	crypto_drop_spawn(crypto_instance_ctx(inst));
+	kfree(inst);
+}
+
+static struct crypto_template crypto_rfc4543_tmpl = {
+	.name = "rfc4543",
+	.alloc = crypto_rfc4543_alloc,
+	.free = crypto_rfc4543_free,
+	.module = THIS_MODULE,
+};
+
 static int __init crypto_gcm_module_init(void)
 {
 	int err;
@@ -1067,8 +1346,14 @@ static int __init crypto_gcm_module_init(void)
 	if (err)
 		goto out_undo_gcm;
 
+	err = crypto_register_template(&crypto_rfc4543_tmpl);
+	if (err)
+		goto out_undo_rfc4106;
+
 	return 0;
 
+out_undo_rfc4106:
+	crypto_unregister_template(&crypto_rfc4106_tmpl);
 out_undo_gcm:
 	crypto_unregister_template(&crypto_gcm_tmpl);
 out_undo_base:
@@ -1081,6 +1366,7 @@ static int __init crypto_gcm_module_init(void)
 static void __exit crypto_gcm_module_exit(void)
 {
 	kfree(gcm_zeroes);
+	crypto_unregister_template(&crypto_rfc4543_tmpl);
 	crypto_unregister_template(&crypto_rfc4106_tmpl);
 	crypto_unregister_template(&crypto_gcm_tmpl);
 	crypto_unregister_template(&crypto_gcm_base_tmpl);
@@ -1094,3 +1380,4 @@ MODULE_DESCRIPTION("Galois/Counter Mode");
 MODULE_AUTHOR("Mikko Herranen <mh1@iki.fi>");
 MODULE_ALIAS("gcm_base");
 MODULE_ALIAS("rfc4106");
+MODULE_ALIAS("rfc4543");

crypto/md5.c

@@ -16,17 +16,13 @@
  *
  */
 #include <crypto/internal/hash.h>
+#include <crypto/md5.h>
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/string.h>
 #include <linux/types.h>
 #include <asm/byteorder.h>
 
-#define MD5_DIGEST_SIZE		16
-#define MD5_HMAC_BLOCK_SIZE	64
-#define MD5_BLOCK_WORDS		16
-#define MD5_HASH_WORDS		4
-
 #define F1(x, y, z)	(z ^ (x & (y ^ z)))
 #define F2(x, y, z)	F1(z, x, y)
 #define F3(x, y, z)	(x ^ y ^ z)
@@ -35,12 +31,6 @@
 #define MD5STEP(f, w, x, y, z, in, s) \
 	(w += f(x, y, z) + in, w = (w<<s | w>>(32-s)) + x)
 
-struct md5_ctx {
-	u32 hash[MD5_HASH_WORDS];
-	u32 block[MD5_BLOCK_WORDS];
-	u64 byte_count;
-};
-
 static void md5_transform(u32 *hash, u32 const *in)
 {
 	u32 a, b, c, d;
@@ -141,7 +131,7 @@ static inline void cpu_to_le32_array(u32 *buf, unsigned int words)
 	}
 }
 
-static inline void md5_transform_helper(struct md5_ctx *ctx)
+static inline void md5_transform_helper(struct md5_state *ctx)
 {
 	le32_to_cpu_array(ctx->block, sizeof(ctx->block) / sizeof(u32));
 	md5_transform(ctx->hash, ctx->block);
@@ -149,7 +139,7 @@ static inline void md5_transform_helper(struct md5_ctx *ctx)
 
 static int md5_init(struct shash_desc *desc)
 {
-	struct md5_ctx *mctx = shash_desc_ctx(desc);
+	struct md5_state *mctx = shash_desc_ctx(desc);
 
 	mctx->hash[0] = 0x67452301;
 	mctx->hash[1] = 0xefcdab89;
@@ -162,7 +152,7 @@ static int md5_init(struct shash_desc *desc)
 
 static int md5_update(struct shash_desc *desc, const u8 *data, unsigned int len)
 {
-	struct md5_ctx *mctx = shash_desc_ctx(desc);
+	struct md5_state *mctx = shash_desc_ctx(desc);
 	const u32 avail = sizeof(mctx->block) - (mctx->byte_count & 0x3f);
 
 	mctx->byte_count += len;
@@ -194,7 +184,7 @@ static int md5_update(struct shash_desc *desc, const u8 *data, unsigned int len)
 
 static int md5_final(struct shash_desc *desc, u8 *out)
 {
-	struct md5_ctx *mctx = shash_desc_ctx(desc);
+	struct md5_state *mctx = shash_desc_ctx(desc);
 	const unsigned int offset = mctx->byte_count & 0x3f;
 	char *p = (char *)mctx->block + offset;
 	int padding = 56 - (offset + 1);
@@ -220,12 +210,30 @@ static int md5_final(struct shash_desc *desc, u8 *out)
 	return 0;
 }
 
+static int md5_export(struct shash_desc *desc, void *out)
+{
+	struct md5_state *ctx = shash_desc_ctx(desc);
+
+	memcpy(out, ctx, sizeof(*ctx));
+	return 0;
+}
+
+static int md5_import(struct shash_desc *desc, const void *in)
+{
+	struct md5_state *ctx = shash_desc_ctx(desc);
+
+	memcpy(ctx, in, sizeof(*ctx));
+	return 0;
+}
+
 static struct shash_alg alg = {
 	.digestsize	=	MD5_DIGEST_SIZE,
 	.init		=	md5_init,
 	.update		=	md5_update,
 	.final		=	md5_final,
-	.descsize	=	sizeof(struct md5_ctx),
+	.export		=	md5_export,
+	.import		=	md5_import,
+	.descsize	=	sizeof(struct md5_state),
 	.base		=	{
 		.cra_name	=	"md5",
 		.cra_flags	=	CRYPTO_ALG_TYPE_SHASH,

crypto/pcrypt.c

+/*
+ * pcrypt - Parallel crypto wrapper.
+ *
+ * Copyright (C) 2009 secunet Security Networks AG
+ * Copyright (C) 2009 Steffen Klassert <steffen.klassert@secunet.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/internal/aead.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <crypto/pcrypt.h>
+
+static struct padata_instance *pcrypt_enc_padata;
+static struct padata_instance *pcrypt_dec_padata;
+static struct workqueue_struct *encwq;
+static struct workqueue_struct *decwq;
+
+struct pcrypt_instance_ctx {
+	struct crypto_spawn spawn;
+	unsigned int tfm_count;
+};
+
+struct pcrypt_aead_ctx {
+	struct crypto_aead *child;
+	unsigned int cb_cpu;
+};
+
+static int pcrypt_do_parallel(struct padata_priv *padata, unsigned int *cb_cpu,
+			      struct padata_instance *pinst)
+{
+	unsigned int cpu_index, cpu, i;
+
+	cpu = *cb_cpu;
+
+	if (cpumask_test_cpu(cpu, cpu_active_mask))
+			goto out;
+
+	cpu_index = cpu % cpumask_weight(cpu_active_mask);
+
+	cpu = cpumask_first(cpu_active_mask);
+	for (i = 0; i < cpu_index; i++)
+		cpu = cpumask_next(cpu, cpu_active_mask);
+
+	*cb_cpu = cpu;
+
+out:
+	return padata_do_parallel(pinst, padata, cpu);
+}
+
+static int pcrypt_aead_setkey(struct crypto_aead *parent,
+			      const u8 *key, unsigned int keylen)
+{
+	struct pcrypt_aead_ctx *ctx = crypto_aead_ctx(parent);
+
+	return crypto_aead_setkey(ctx->child, key, keylen);
+}
+
+static int pcrypt_aead_setauthsize(struct crypto_aead *parent,
+				   unsigned int authsize)
+{
+	struct pcrypt_aead_ctx *ctx = crypto_aead_ctx(parent);
+
+	return crypto_aead_setauthsize(ctx->child, authsize);
+}
+
+static void pcrypt_aead_serial(struct padata_priv *padata)
+{
+	struct pcrypt_request *preq = pcrypt_padata_request(padata);
+	struct aead_request *req = pcrypt_request_ctx(preq);
+
+	aead_request_complete(req->base.data, padata->info);
+}
+
+static void pcrypt_aead_giv_serial(struct padata_priv *padata)
+{
+	struct pcrypt_request *preq = pcrypt_padata_request(padata);
+	struct aead_givcrypt_request *req = pcrypt_request_ctx(preq);
+
+	aead_request_complete(req->areq.base.data, padata->info);
+}
+
+static void pcrypt_aead_done(struct crypto_async_request *areq, int err)
+{
+	struct aead_request *req = areq->data;
+	struct pcrypt_request *preq = aead_request_ctx(req);
+	struct padata_priv *padata = pcrypt_request_padata(preq);
+
+	padata->info = err;
+	req->base.flags &= ~CRYPTO_TFM_REQ_MAY_SLEEP;
+
+	padata_do_serial(padata);
+}
+
+static void pcrypt_aead_enc(struct padata_priv *padata)
+{
+	struct pcrypt_request *preq = pcrypt_padata_request(padata);
+	struct aead_request *req = pcrypt_request_ctx(preq);
+
+	padata->info = crypto_aead_encrypt(req);
+
+	if (padata->info == -EINPROGRESS)
+		return;
+
+	padata_do_serial(padata);
+}
+
+static int pcrypt_aead_encrypt(struct aead_request *req)
+{
+	int err;
+	struct pcrypt_request *preq = aead_request_ctx(req);
+	struct aead_request *creq = pcrypt_request_ctx(preq);
+	struct padata_priv *padata = pcrypt_request_padata(preq);
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct pcrypt_aead_ctx *ctx = crypto_aead_ctx(aead);
+	u32 flags = aead_request_flags(req);
+
+	memset(padata, 0, sizeof(struct padata_priv));
+
+	padata->parallel = pcrypt_aead_enc;
+	padata->serial = pcrypt_aead_serial;
+
+	aead_request_set_tfm(creq, ctx->child);
+	aead_request_set_callback(creq, flags & ~CRYPTO_TFM_REQ_MAY_SLEEP,
+				  pcrypt_aead_done, req);
+	aead_request_set_crypt(creq, req->src, req->dst,
+			       req->cryptlen, req->iv);
+	aead_request_set_assoc(creq, req->assoc, req->assoclen);
+
+	err = pcrypt_do_parallel(padata, &ctx->cb_cpu, pcrypt_enc_padata);
+	if (err)
+		return err;
+	else
+		err = crypto_aead_encrypt(creq);
+
+	return err;
+}
+
+static void pcrypt_aead_dec(struct padata_priv *padata)
+{
+	struct pcrypt_request *preq = pcrypt_padata_request(padata);
+	struct aead_request *req = pcrypt_request_ctx(preq);
+
+	padata->info = crypto_aead_decrypt(req);
+
+	if (padata->info == -EINPROGRESS)
+		return;
+
+	padata_do_serial(padata);
+}
+
+static int pcrypt_aead_decrypt(struct aead_request *req)
+{
+	int err;
+	struct pcrypt_request *preq = aead_request_ctx(req);
+	struct aead_request *creq = pcrypt_request_ctx(preq);
+	struct padata_priv *padata = pcrypt_request_padata(preq);
+	struct crypto_aead *aead = crypto_aead_reqtfm(req);
+	struct pcrypt_aead_ctx *ctx = crypto_aead_ctx(aead);
+	u32 flags = aead_request_flags(req);
+
+	memset(padata, 0, sizeof(struct padata_priv));
+
+	padata->parallel = pcrypt_aead_dec;
+	padata->serial = pcrypt_aead_serial;
+
+	aead_request_set_tfm(creq, ctx->child);
+	aead_request_set_callback(creq, flags & ~CRYPTO_TFM_REQ_MAY_SLEEP,
+				  pcrypt_aead_done, req);
+	aead_request_set_crypt(creq, req->src, req->dst,
+			       req->cryptlen, req->iv);
+	aead_request_set_assoc(creq, req->assoc, req->assoclen);
+
+	err = pcrypt_do_parallel(padata, &ctx->cb_cpu, pcrypt_dec_padata);
+	if (err)
+		return err;
+	else
+		err = crypto_aead_decrypt(creq);
+
+	return err;
+}
+
+static void pcrypt_aead_givenc(struct padata_priv *padata)
+{
+	struct pcrypt_request *preq = pcrypt_padata_request(padata);
+	struct aead_givcrypt_request *req = pcrypt_request_ctx(preq);
+
+	padata->info = crypto_aead_givencrypt(req);
+
+	if (padata->info == -EINPROGRESS)
+		return;
+
+	padata_do_serial(padata);
+}
+
+static int pcrypt_aead_givencrypt(struct aead_givcrypt_request *req)
+{
+	int err;
+	struct aead_request *areq = &req->areq;
+	struct pcrypt_request *preq = aead_request_ctx(areq);
+	struct aead_givcrypt_request *creq = pcrypt_request_ctx(preq);
+	struct padata_priv *padata = pcrypt_request_padata(preq);
+	struct crypto_aead *aead = aead_givcrypt_reqtfm(req);
+	struct pcrypt_aead_ctx *ctx = crypto_aead_ctx(aead);
+	u32 flags = aead_request_flags(areq);
+
+	memset(padata, 0, sizeof(struct padata_priv));
+
+	padata->parallel = pcrypt_aead_givenc;
+	padata->serial = pcrypt_aead_giv_serial;
+
+	aead_givcrypt_set_tfm(creq, ctx->child);
+	aead_givcrypt_set_callback(creq, flags & ~CRYPTO_TFM_REQ_MAY_SLEEP,
+				   pcrypt_aead_done, areq);
+	aead_givcrypt_set_crypt(creq, areq->src, areq->dst,
+				areq->cryptlen, areq->iv);
+	aead_givcrypt_set_assoc(creq, areq->assoc, areq->assoclen);
+	aead_givcrypt_set_giv(creq, req->giv, req->seq);
+
+	err = pcrypt_do_parallel(padata, &ctx->cb_cpu, pcrypt_enc_padata);
+	if (err)
+		return err;
+	else
+		err = crypto_aead_givencrypt(creq);
+
+	return err;
+}
+
+static int pcrypt_aead_init_tfm(struct crypto_tfm *tfm)
+{
+	int cpu, cpu_index;
+	struct crypto_instance *inst = crypto_tfm_alg_instance(tfm);
+	struct pcrypt_instance_ctx *ictx = crypto_instance_ctx(inst);
+	struct pcrypt_aead_ctx *ctx = crypto_tfm_ctx(tfm);
+	struct crypto_aead *cipher;
+
+	ictx->tfm_count++;
+
+	cpu_index = ictx->tfm_count % cpumask_weight(cpu_active_mask);
+
+	ctx->cb_cpu = cpumask_first(cpu_active_mask);
+	for (cpu = 0; cpu < cpu_index; cpu++)
+		ctx->cb_cpu = cpumask_next(ctx->cb_cpu, cpu_active_mask);
+
+	cipher = crypto_spawn_aead(crypto_instance_ctx(inst));
+
+	if (IS_ERR(cipher))
+		return PTR_ERR(cipher);
+
+	ctx->child = cipher;
+	tfm->crt_aead.reqsize = sizeof(struct pcrypt_request)
+		+ sizeof(struct aead_givcrypt_request)
+		+ crypto_aead_reqsize(cipher);
+
+	return 0;
+}
+
+static void pcrypt_aead_exit_tfm(struct crypto_tfm *tfm)
+{
+	struct pcrypt_aead_ctx *ctx = crypto_tfm_ctx(tfm);
+
+	crypto_free_aead(ctx->child);
+}
+
+static struct crypto_instance *pcrypt_alloc_instance(struct crypto_alg *alg)
+{
+	struct crypto_instance *inst;
+	struct pcrypt_instance_ctx *ctx;
+	int err;
+
+	inst = kzalloc(sizeof(*inst) + sizeof(*ctx), GFP_KERNEL);
+	if (!inst) {
+		inst = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	err = -ENAMETOOLONG;
+	if (snprintf(inst->alg.cra_driver_name, CRYPTO_MAX_ALG_NAME,
+		     "pcrypt(%s)", alg->cra_driver_name) >= CRYPTO_MAX_ALG_NAME)
+		goto out_free_inst;
+
+	memcpy(inst->alg.cra_name, alg->cra_name, CRYPTO_MAX_ALG_NAME);
+
+	ctx = crypto_instance_ctx(inst);
+	err = crypto_init_spawn(&ctx->spawn, alg, inst,
+				CRYPTO_ALG_TYPE_MASK);
+	if (err)
+		goto out_free_inst;
+
+	inst->alg.cra_priority = alg->cra_priority + 100;
+	inst->alg.cra_blocksize = alg->cra_blocksize;
+	inst->alg.cra_alignmask = alg->cra_alignmask;
+
+out:
+	return inst;
+
+out_free_inst:
+	kfree(inst);
+	inst = ERR_PTR(err);
+	goto out;
+}
+
+static struct crypto_instance *pcrypt_alloc_aead(struct rtattr **tb)
+{
+	struct crypto_instance *inst;
+	struct crypto_alg *alg;
+	struct crypto_attr_type *algt;
+
+	algt = crypto_get_attr_type(tb);
+
+	alg = crypto_get_attr_alg(tb, algt->type,
+				  (algt->mask & CRYPTO_ALG_TYPE_MASK));
+	if (IS_ERR(alg))
+		return ERR_CAST(alg);
+
+	inst = pcrypt_alloc_instance(alg);
+	if (IS_ERR(inst))
+		goto out_put_alg;
+
+	inst->alg.cra_flags = CRYPTO_ALG_TYPE_AEAD | CRYPTO_ALG_ASYNC;
+	inst->alg.cra_type = &crypto_aead_type;
+
+	inst->alg.cra_aead.ivsize = alg->cra_aead.ivsize;
+	inst->alg.cra_aead.geniv = alg->cra_aead.geniv;
+	inst->alg.cra_aead.maxauthsize = alg->cra_aead.maxauthsize;
+
+	inst->alg.cra_ctxsize = sizeof(struct pcrypt_aead_ctx);
+
+	inst->alg.cra_init = pcrypt_aead_init_tfm;
+	inst->alg.cra_exit = pcrypt_aead_exit_tfm;
+
+	inst->alg.cra_aead.setkey = pcrypt_aead_setkey;
+	inst->alg.cra_aead.setauthsize = pcrypt_aead_setauthsize;
+	inst->alg.cra_aead.encrypt = pcrypt_aead_encrypt;
+	inst->alg.cra_aead.decrypt = pcrypt_aead_decrypt;
+	inst->alg.cra_aead.givencrypt = pcrypt_aead_givencrypt;
+
+out_put_alg:
+	crypto_mod_put(alg);
+	return inst;
+}
+
+static struct crypto_instance *pcrypt_alloc(struct rtattr **tb)
+{
+	struct crypto_attr_type *algt;
+
+	algt = crypto_get_attr_type(tb);
+	if (IS_ERR(algt))
+		return ERR_CAST(algt);
+
+	switch (algt->type & algt->mask & CRYPTO_ALG_TYPE_MASK) {
+	case CRYPTO_ALG_TYPE_AEAD:
+		return pcrypt_alloc_aead(tb);
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static void pcrypt_free(struct crypto_instance *inst)
+{
+	struct pcrypt_instance_ctx *ctx = crypto_instance_ctx(inst);
+
+	crypto_drop_spawn(&ctx->spawn);
+	kfree(inst);
+}
+
+static struct crypto_template pcrypt_tmpl = {
+	.name = "pcrypt",
+	.alloc = pcrypt_alloc,
+	.free = pcrypt_free,
+	.module = THIS_MODULE,
+};
+
+static int __init pcrypt_init(void)
+{
+	encwq = create_workqueue("pencrypt");
+	if (!encwq)
+		goto err;
+
+	decwq = create_workqueue("pdecrypt");
+	if (!decwq)
+		goto err_destroy_encwq;
+
+
+	pcrypt_enc_padata = padata_alloc(cpu_possible_mask, encwq);
+	if (!pcrypt_enc_padata)
+		goto err_destroy_decwq;
+
+	pcrypt_dec_padata = padata_alloc(cpu_possible_mask, decwq);
+	if (!pcrypt_dec_padata)
+		goto err_free_padata;
+
+	padata_start(pcrypt_enc_padata);
+	padata_start(pcrypt_dec_padata);
+
+	return crypto_register_template(&pcrypt_tmpl);
+
+err_free_padata:
+	padata_free(pcrypt_enc_padata);
+
+err_destroy_decwq:
+	destroy_workqueue(decwq);
+
+err_destroy_encwq:
+	destroy_workqueue(encwq);
+
+err:
+	return -ENOMEM;
+}
+
+static void __exit pcrypt_exit(void)
+{
+	padata_stop(pcrypt_enc_padata);
+	padata_stop(pcrypt_dec_padata);
+
+	destroy_workqueue(encwq);
+	destroy_workqueue(decwq);
+
+	padata_free(pcrypt_enc_padata);
+	padata_free(pcrypt_dec_padata);
+
+	crypto_unregister_template(&pcrypt_tmpl);
+}
+
+module_init(pcrypt_init);
+module_exit(pcrypt_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Steffen Klassert <steffen.klassert@secunet.com>");
+MODULE_DESCRIPTION("Parallel crypto wrapper");

crypto/testmgr.c

@@ -1477,9 +1477,54 @@ static int alg_test_cprng(const struct alg_test_desc *desc, const char *driver,
 	return err;
 }
 
+static int alg_test_null(const struct alg_test_desc *desc,
+			     const char *driver, u32 type, u32 mask)
+{
+	return 0;
+}
+
 /* Please keep this list sorted by algorithm name. */
 static const struct alg_test_desc alg_test_descs[] = {
 	{
+		.alg = "__driver-cbc-aes-aesni",
+		.test = alg_test_null,
+		.suite = {
+			.cipher = {
+				.enc = {
+					.vecs = NULL,
+					.count = 0
+				},
+				.dec = {
+					.vecs = NULL,
+					.count = 0
+				}
+			}
+		}
+	}, {
+		.alg = "__driver-ecb-aes-aesni",
+		.test = alg_test_null,
+		.suite = {
+			.cipher = {
+				.enc = {
+					.vecs = NULL,
+					.count = 0
+				},
+				.dec = {
+					.vecs = NULL,
+					.count = 0
+				}
+			}
+		}
+	}, {
+		.alg = "__ghash-pclmulqdqni",
+		.test = alg_test_null,
+		.suite = {
+			.hash = {
+				.vecs = NULL,
+				.count = 0
+			}
+		}
+	}, {
 		.alg = "ansi_cprng",
 		.test = alg_test_cprng,
 		.fips_allowed = 1,
@@ -1622,6 +1667,30 @@ static const struct alg_test_desc alg_test_descs[] = {
 				.count = CRC32C_TEST_VECTORS
 			}
 		}
+	}, {
+		.alg = "cryptd(__driver-ecb-aes-aesni)",
+		.test = alg_test_null,
+		.suite = {
+			.cipher = {
+				.enc = {
+					.vecs = NULL,
+					.count = 0
+				},
+				.dec = {
+					.vecs = NULL,
+					.count = 0
+				}
+			}
+		}
+	}, {
+		.alg = "cryptd(__ghash-pclmulqdqni)",
+		.test = alg_test_null,
+		.suite = {
+			.hash = {
+				.vecs = NULL,
+				.count = 0
+			}
+		}
 	}, {
 		.alg = "ctr(aes)",
 		.test = alg_test_skcipher,
@@ -1668,6 +1737,21 @@ static const struct alg_test_desc alg_test_descs[] = {
 				}
 			}
 		}
+	}, {
+		.alg = "ecb(__aes-aesni)",
+		.test = alg_test_null,
+		.suite = {
+			.cipher = {
+				.enc = {
+					.vecs = NULL,
+					.count = 0
+				},
+				.dec = {
+					.vecs = NULL,
+					.count = 0
+				}
+			}
+		}
 	}, {
 		.alg = "ecb(aes)",
 		.test = alg_test_skcipher,

drivers/char/hw_random/Kconfig

@@ -186,3 +186,15 @@ config HW_RANDOM_MXC_RNGA
 	  module will be called mxc-rnga.
 
 	  If unsure, say Y.
+
+config HW_RANDOM_NOMADIK
+	tristate "ST-Ericsson Nomadik Random Number Generator support"
+	depends on HW_RANDOM && PLAT_NOMADIK
+	---help---
+	  This driver provides kernel-side support for the Random Number
+	  Generator hardware found on ST-Ericsson SoCs (8815 and 8500).
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called nomadik-rng.
+
+	  If unsure, say Y.

drivers/char/hw_random/Makefile

@@ -18,3 +18,4 @@ obj-$(CONFIG_HW_RANDOM_VIRTIO) += virtio-rng.o
 obj-$(CONFIG_HW_RANDOM_TX4939) += tx4939-rng.o
 obj-$(CONFIG_HW_RANDOM_MXC_RNGA) += mxc-rnga.o
 obj-$(CONFIG_HW_RANDOM_OCTEON) += octeon-rng.o
+obj-$(CONFIG_HW_RANDOM_NOMADIK) += nomadik-rng.o

drivers/char/hw_random/nomadik-rng.c

+/*
+ * Nomadik RNG support
+ *  Copyright 2009 Alessandro Rubini
+ *
+ *  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 <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/device.h>
+#include <linux/amba/bus.h>
+#include <linux/hw_random.h>
+#include <linux/io.h>
+
+static int nmk_rng_read(struct hwrng *rng, void *data, size_t max, bool wait)
+{
+	void __iomem *base = (void __iomem *)rng->priv;
+
+	/*
+	 * The register is 32 bits and gives 16 random bits (low half).
+	 * A subsequent read will delay the core for 400ns, so we just read
+	 * once and accept the very unlikely very small delay, even if wait==0.
+	 */
+	*(u16 *)data = __raw_readl(base + 8) & 0xffff;
+	return 2;
+}
+
+/* we have at most one RNG per machine, granted */
+static struct hwrng nmk_rng = {
+	.name		= "nomadik",
+	.read		= nmk_rng_read,
+};
+
+static int nmk_rng_probe(struct amba_device *dev, struct amba_id *id)
+{
+	void __iomem *base;
+	int ret;
+
+	ret = amba_request_regions(dev, dev->dev.init_name);
+	if (ret)
+		return ret;
+	ret = -ENOMEM;
+	base = ioremap(dev->res.start, resource_size(&dev->res));
+	if (!base)
+		goto out_release;
+	nmk_rng.priv = (unsigned long)base;
+	ret = hwrng_register(&nmk_rng);
+	if (ret)
+		goto out_unmap;
+	return 0;
+
+out_unmap:
+	iounmap(base);
+out_release:
+	amba_release_regions(dev);
+	return ret;
+}
+
+static int nmk_rng_remove(struct amba_device *dev)
+{
+	void __iomem *base = (void __iomem *)nmk_rng.priv;
+	hwrng_unregister(&nmk_rng);
+	iounmap(base);
+	amba_release_regions(dev);
+	return 0;
+}
+
+static struct amba_id nmk_rng_ids[] = {
+	{
+		.id	= 0x000805e1,
+		.mask	= 0x000fffff, /* top bits are rev and cfg: accept all */
+	},
+	{0, 0},
+};
+
+static struct amba_driver nmk_rng_driver = {
+	.drv = {
+		.owner = THIS_MODULE,
+		.name = "rng",
+		},
+	.probe = nmk_rng_probe,
+	.remove = nmk_rng_remove,
+	.id_table = nmk_rng_ids,
+};
+
+static int __init nmk_rng_init(void)
+{
+	return amba_driver_register(&nmk_rng_driver);
+}
+
+static void __devexit nmk_rng_exit(void)
+{
+	amba_driver_unregister(&nmk_rng_driver);
+}
+
+module_init(nmk_rng_init);
+module_exit(nmk_rng_exit);
+
+MODULE_LICENSE("GPL");

drivers/crypto/amcc/crypto4xx_core.c

@@ -1274,7 +1274,7 @@ static int __exit crypto4xx_remove(struct of_device *ofdev)
 	return 0;
 }
 
-static struct of_device_id crypto4xx_match[] = {
+static const struct of_device_id crypto4xx_match[] = {
 	{ .compatible      = "amcc,ppc4xx-crypto",},
 	{ },
 };

drivers/crypto/geode-aes.c

@@ -135,13 +135,13 @@ static int geode_setkey_cip(struct crypto_tfm *tfm, const u8 *key,
 	/*
 	 * The requested key size is not supported by HW, do a fallback
 	 */
-	op->fallback.blk->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
-	op->fallback.blk->base.crt_flags |= (tfm->crt_flags & CRYPTO_TFM_REQ_MASK);
+	op->fallback.cip->base.crt_flags &= ~CRYPTO_TFM_REQ_MASK;
+	op->fallback.cip->base.crt_flags |= (tfm->crt_flags & CRYPTO_TFM_REQ_MASK);
 
 	ret = crypto_cipher_setkey(op->fallback.cip, key, len);
 	if (ret) {
 		tfm->crt_flags &= ~CRYPTO_TFM_RES_MASK;
-		tfm->crt_flags |= (op->fallback.blk->base.crt_flags & CRYPTO_TFM_RES_MASK);
+		tfm->crt_flags |= (op->fallback.cip->base.crt_flags & CRYPTO_TFM_RES_MASK);
 	}
 	return ret;
 }
@@ -263,7 +263,7 @@ static int fallback_init_cip(struct crypto_tfm *tfm)
 
 	if (IS_ERR(op->fallback.cip)) {
 		printk(KERN_ERR "Error allocating fallback algo %s\n", name);
-		return PTR_ERR(op->fallback.blk);
+		return PTR_ERR(op->fallback.cip);
 	}
 
 	return 0;

drivers/crypto/talitos.c

@@ -1958,7 +1958,7 @@ static int talitos_probe(struct of_device *ofdev,
 	return err;
 }
 
-static struct of_device_id talitos_match[] = {
+static const struct of_device_id talitos_match[] = {
 	{
 		.compatible = "fsl,sec2.0",
 	},

include/crypto/md5.h

+#ifndef _CRYPTO_MD5_H
+#define _CRYPTO_MD5_H
+
+#include <linux/types.h>
+
+#define MD5_DIGEST_SIZE		16
+#define MD5_HMAC_BLOCK_SIZE	64
+#define MD5_BLOCK_WORDS		16
+#define MD5_HASH_WORDS		4
+
+struct md5_state {
+	u32 hash[MD5_HASH_WORDS];
+	u32 block[MD5_BLOCK_WORDS];
+	u64 byte_count;
+};
+
+#endif

include/crypto/pcrypt.h

+/*
+ * pcrypt - Parallel crypto engine.
+ *
+ * Copyright (C) 2009 secunet Security Networks AG
+ * Copyright (C) 2009 Steffen Klassert <steffen.klassert@secunet.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#ifndef _CRYPTO_PCRYPT_H
+#define _CRYPTO_PCRYPT_H
+
+#include <linux/crypto.h>
+#include <linux/kernel.h>
+#include <linux/padata.h>
+
+struct pcrypt_request {
+	struct padata_priv	padata;
+	void			*data;
+	void			*__ctx[] CRYPTO_MINALIGN_ATTR;
+};
+
+static inline void *pcrypt_request_ctx(struct pcrypt_request *req)
+{
+	return req->__ctx;
+}
+
+static inline
+struct padata_priv *pcrypt_request_padata(struct pcrypt_request *req)
+{
+	return &req->padata;
+}
+
+static inline
+struct pcrypt_request *pcrypt_padata_request(struct padata_priv *padata)
+{
+	return container_of(padata, struct pcrypt_request, padata);
+}
+
+#endif

include/linux/padata.h

+/*
+ * padata.h - header for the padata parallelization interface
+ *
+ * Copyright (C) 2008, 2009 secunet Security Networks AG
+ * Copyright (C) 2008, 2009 Steffen Klassert <steffen.klassert@secunet.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#ifndef PADATA_H
+#define PADATA_H
+
+#include <linux/workqueue.h>
+#include <linux/spinlock.h>
+#include <linux/list.h>
+
+struct padata_priv {
+	struct list_head	list;
+	struct parallel_data	*pd;
+	int			cb_cpu;
+	int			seq_nr;
+	int			info;
+	void                    (*parallel)(struct padata_priv *padata);
+	void                    (*serial)(struct padata_priv *padata);
+};
+
+struct padata_list {
+	struct list_head        list;
+	spinlock_t              lock;
+};
+
+struct padata_queue {
+	struct padata_list	parallel;
+	struct padata_list	reorder;
+	struct padata_list	serial;
+	struct work_struct	pwork;
+	struct work_struct	swork;
+	struct parallel_data    *pd;
+	atomic_t		num_obj;
+	int			cpu_index;
+};
+
+struct parallel_data {
+	struct padata_instance	*pinst;
+	struct padata_queue	*queue;
+	atomic_t		seq_nr;
+	atomic_t		reorder_objects;
+	atomic_t                refcnt;
+	unsigned int		max_seq_nr;
+	cpumask_var_t		cpumask;
+	spinlock_t              lock;
+};
+
+struct padata_instance {
+	struct notifier_block   cpu_notifier;
+	struct workqueue_struct *wq;
+	struct parallel_data	*pd;
+	cpumask_var_t           cpumask;
+	struct mutex		lock;
+	u8			flags;
+#define	PADATA_INIT		1
+#define	PADATA_RESET		2
+};
+
+extern struct padata_instance *padata_alloc(const struct cpumask *cpumask,
+					    struct workqueue_struct *wq);
+extern void padata_free(struct padata_instance *pinst);
+extern int padata_do_parallel(struct padata_instance *pinst,
+			      struct padata_priv *padata, int cb_cpu);
+extern void padata_do_serial(struct padata_priv *padata);
+extern int padata_set_cpumask(struct padata_instance *pinst,
+			      cpumask_var_t cpumask);
+extern int padata_add_cpu(struct padata_instance *pinst, int cpu);
+extern int padata_remove_cpu(struct padata_instance *pinst, int cpu);
+extern void padata_start(struct padata_instance *pinst);
+extern void padata_stop(struct padata_instance *pinst);
+#endif

include/linux/pfkeyv2.h

@@ -315,6 +315,7 @@ struct sadb_x_kmaddress {
 #define SADB_X_EALG_AES_GCM_ICV12	19
 #define SADB_X_EALG_AES_GCM_ICV16	20
 #define SADB_X_EALG_CAMELLIACBC		22
+#define SADB_X_EALG_NULL_AES_GMAC	23
 #define SADB_EALG_MAX                   253 /* last EALG */
 /* private allocations should use 249-255 (RFC2407) */
 #define SADB_X_EALG_SERPENTCBC  252     /* draft-ietf-ipsec-ciph-aes-cbc-00 */

init/Kconfig

@@ -1262,4 +1262,8 @@ source "block/Kconfig"
 config PREEMPT_NOTIFIERS
 	bool
 
+config PADATA
+	depends on SMP
+	bool
+
 source "kernel/Kconfig.locks"

kernel/Makefile

@@ -100,6 +100,7 @@ obj-$(CONFIG_SLOW_WORK_DEBUG) += slow-work-debugfs.o
 obj-$(CONFIG_PERF_EVENTS) += perf_event.o
 obj-$(CONFIG_HAVE_HW_BREAKPOINT) += hw_breakpoint.o
 obj-$(CONFIG_USER_RETURN_NOTIFIER) += user-return-notifier.o
+obj-$(CONFIG_PADATA) += padata.o
 
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is

kernel/padata.c

+/*
+ * padata.c - generic interface to process data streams in parallel
+ *
+ * Copyright (C) 2008, 2009 secunet Security Networks AG
+ * Copyright (C) 2008, 2009 Steffen Klassert <steffen.klassert@secunet.com>
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope 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, write to the Free Software Foundation, Inc.,
+ * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA.
+ */
+
+#include <linux/module.h>
+#include <linux/cpumask.h>
+#include <linux/err.h>
+#include <linux/cpu.h>
+#include <linux/padata.h>
+#include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/rcupdate.h>
+
+#define MAX_SEQ_NR INT_MAX - NR_CPUS
+#define MAX_OBJ_NUM 10000 * NR_CPUS
+
+static int padata_index_to_cpu(struct parallel_data *pd, int cpu_index)
+{
+	int cpu, target_cpu;
+
+	target_cpu = cpumask_first(pd->cpumask);
+	for (cpu = 0; cpu < cpu_index; cpu++)
+		target_cpu = cpumask_next(target_cpu, pd->cpumask);
+
+	return target_cpu;
+}
+
+static int padata_cpu_hash(struct padata_priv *padata)
+{
+	int cpu_index;
+	struct parallel_data *pd;
+
+	pd =  padata->pd;
+
+	/*
+	 * Hash the sequence numbers to the cpus by taking
+	 * seq_nr mod. number of cpus in use.
+	 */
+	cpu_index =  padata->seq_nr % cpumask_weight(pd->cpumask);
+
+	return padata_index_to_cpu(pd, cpu_index);
+}
+
+static void padata_parallel_worker(struct work_struct *work)
+{
+	struct padata_queue *queue;
+	struct parallel_data *pd;
+	struct padata_instance *pinst;
+	LIST_HEAD(local_list);
+
+	local_bh_disable();
+	queue = container_of(work, struct padata_queue, pwork);
+	pd = queue->pd;
+	pinst = pd->pinst;
+
+	spin_lock(&queue->parallel.lock);
+	list_replace_init(&queue->parallel.list, &local_list);
+	spin_unlock(&queue->parallel.lock);
+
+	while (!list_empty(&local_list)) {
+		struct padata_priv *padata;
+
+		padata = list_entry(local_list.next,
+				    struct padata_priv, list);
+
+		list_del_init(&padata->list);
+
+		padata->parallel(padata);
+	}
+
+	local_bh_enable();
+}
+
+/*
+ * padata_do_parallel - padata parallelization function
+ *
+ * @pinst: padata instance
+ * @padata: object to be parallelized
+ * @cb_cpu: cpu the serialization callback function will run on,
+ *          must be in the cpumask of padata.
+ *
+ * The parallelization callback function will run with BHs off.
+ * Note: Every object which is parallelized by padata_do_parallel
+ * must be seen by padata_do_serial.
+ */
+int padata_do_parallel(struct padata_instance *pinst,
+		       struct padata_priv *padata, int cb_cpu)
+{
+	int target_cpu, err;
+	struct padata_queue *queue;
+	struct parallel_data *pd;
+
+	rcu_read_lock_bh();
+
+	pd = rcu_dereference(pinst->pd);
+
+	err = 0;
+	if (!(pinst->flags & PADATA_INIT))
+		goto out;
+
+	err =  -EBUSY;
+	if ((pinst->flags & PADATA_RESET))
+		goto out;
+
+	if (atomic_read(&pd->refcnt) >= MAX_OBJ_NUM)
+		goto out;
+
+	err = -EINVAL;
+	if (!cpumask_test_cpu(cb_cpu, pd->cpumask))
+		goto out;
+
+	err = -EINPROGRESS;
+	atomic_inc(&pd->refcnt);
+	padata->pd = pd;
+	padata->cb_cpu = cb_cpu;
+
+	if (unlikely(atomic_read(&pd->seq_nr) == pd->max_seq_nr))
+		atomic_set(&pd->seq_nr, -1);
+
+	padata->seq_nr = atomic_inc_return(&pd->seq_nr);
+
+	target_cpu = padata_cpu_hash(padata);
+	queue = per_cpu_ptr(pd->queue, target_cpu);
+
+	spin_lock(&queue->parallel.lock);
+	list_add_tail(&padata->list, &queue->parallel.list);
+	spin_unlock(&queue->parallel.lock);
+
+	queue_work_on(target_cpu, pinst->wq, &queue->pwork);
+
+out:
+	rcu_read_unlock_bh();
+
+	return err;
+}
+EXPORT_SYMBOL(padata_do_parallel);
+
+static struct padata_priv *padata_get_next(struct parallel_data *pd)
+{
+	int cpu, num_cpus, empty, calc_seq_nr;
+	int seq_nr, next_nr, overrun, next_overrun;
+	struct padata_queue *queue, *next_queue;
+	struct padata_priv *padata;
+	struct padata_list *reorder;
+
+	empty = 0;
+	next_nr = -1;
+	next_overrun = 0;
+	next_queue = NULL;
+
+	num_cpus = cpumask_weight(pd->cpumask);
+
+	for_each_cpu(cpu, pd->cpumask) {
+		queue = per_cpu_ptr(pd->queue, cpu);
+		reorder = &queue->reorder;
+
+		/*
+		 * Calculate the seq_nr of the object that should be
+		 * next in this queue.
+		 */
+		overrun = 0;
+		calc_seq_nr = (atomic_read(&queue->num_obj) * num_cpus)
+			       + queue->cpu_index;
+
+		if (unlikely(calc_seq_nr > pd->max_seq_nr)) {
+			calc_seq_nr = calc_seq_nr - pd->max_seq_nr - 1;
+			overrun = 1;
+		}
+
+		if (!list_empty(&reorder->list)) {
+			padata = list_entry(reorder->list.next,
+					    struct padata_priv, list);
+
+			seq_nr  = padata->seq_nr;
+			BUG_ON(calc_seq_nr != seq_nr);
+		} else {
+			seq_nr = calc_seq_nr;
+			empty++;
+		}
+
+		if (next_nr < 0 || seq_nr < next_nr
+		    || (next_overrun && !overrun)) {
+			next_nr = seq_nr;
+			next_overrun = overrun;
+			next_queue = queue;
+		}
+	}
+
+	padata = NULL;
+
+	if (empty == num_cpus)
+		goto out;
+
+	reorder = &next_queue->reorder;
+
+	if (!list_empty(&reorder->list)) {
+		padata = list_entry(reorder->list.next,
+				    struct padata_priv, list);
+
+		if (unlikely(next_overrun)) {
+			for_each_cpu(cpu, pd->cpumask) {
+				queue = per_cpu_ptr(pd->queue, cpu);
+				atomic_set(&queue->num_obj, 0);
+			}
+		}
+
+		spin_lock(&reorder->lock);
+		list_del_init(&padata->list);
+		atomic_dec(&pd->reorder_objects);
+		spin_unlock(&reorder->lock);
+
+		atomic_inc(&next_queue->num_obj);
+
+		goto out;
+	}
+
+	if (next_nr % num_cpus == next_queue->cpu_index) {
+		padata = ERR_PTR(-ENODATA);
+		goto out;
+	}
+
+	padata = ERR_PTR(-EINPROGRESS);
+out:
+	return padata;
+}
+
+static void padata_reorder(struct parallel_data *pd)
+{
+	struct padata_priv *padata;
+	struct padata_queue *queue;
+	struct padata_instance *pinst = pd->pinst;
+
+try_again:
+	if (!spin_trylock_bh(&pd->lock))
+		goto out;
+
+	while (1) {
+		padata = padata_get_next(pd);
+
+		if (!padata || PTR_ERR(padata) == -EINPROGRESS)
+			break;
+
+		if (PTR_ERR(padata) == -ENODATA) {
+			spin_unlock_bh(&pd->lock);
+			goto out;
+		}
+
+		queue = per_cpu_ptr(pd->queue, padata->cb_cpu);
+
+		spin_lock(&queue->serial.lock);
+		list_add_tail(&padata->list, &queue->serial.list);
+		spin_unlock(&queue->serial.lock);
+
+		queue_work_on(padata->cb_cpu, pinst->wq, &queue->swork);
+	}
+
+	spin_unlock_bh(&pd->lock);
+
+	if (atomic_read(&pd->reorder_objects))
+		goto try_again;
+
+out:
+	return;
+}
+
+static void padata_serial_worker(struct work_struct *work)
+{
+	struct padata_queue *queue;
+	struct parallel_data *pd;
+	LIST_HEAD(local_list);
+
+	local_bh_disable();
+	queue = container_of(work, struct padata_queue, swork);
+	pd = queue->pd;
+
+	spin_lock(&queue->serial.lock);
+	list_replace_init(&queue->serial.list, &local_list);
+	spin_unlock(&queue->serial.lock);
+
+	while (!list_empty(&local_list)) {
+		struct padata_priv *padata;
+
+		padata = list_entry(local_list.next,
+				    struct padata_priv, list);
+
+		list_del_init(&padata->list);
+
+		padata->serial(padata);
+		atomic_dec(&pd->refcnt);
+	}
+	local_bh_enable();
+}
+
+/*
+ * padata_do_serial - padata serialization function
+ *
+ * @padata: object to be serialized.
+ *
+ * padata_do_serial must be called for every parallelized object.
+ * The serialization callback function will run with BHs off.
+ */
+void padata_do_serial(struct padata_priv *padata)
+{
+	int cpu;
+	struct padata_queue *queue;
+	struct parallel_data *pd;
+
+	pd = padata->pd;
+
+	cpu = get_cpu();
+	queue = per_cpu_ptr(pd->queue, cpu);
+
+	spin_lock(&queue->reorder.lock);
+	atomic_inc(&pd->reorder_objects);
+	list_add_tail(&padata->list, &queue->reorder.list);
+	spin_unlock(&queue->reorder.lock);
+
+	put_cpu();
+
+	padata_reorder(pd);
+}
+EXPORT_SYMBOL(padata_do_serial);
+
+static struct parallel_data *padata_alloc_pd(struct padata_instance *pinst,
+					     const struct cpumask *cpumask)
+{
+	int cpu, cpu_index, num_cpus;
+	struct padata_queue *queue;
+	struct parallel_data *pd;
+
+	cpu_index = 0;
+
+	pd = kzalloc(sizeof(struct parallel_data), GFP_KERNEL);
+	if (!pd)
+		goto err;
+
+	pd->queue = alloc_percpu(struct padata_queue);
+	if (!pd->queue)
+		goto err_free_pd;
+
+	if (!alloc_cpumask_var(&pd->cpumask, GFP_KERNEL))
+		goto err_free_queue;
+
+	for_each_possible_cpu(cpu) {
+		queue = per_cpu_ptr(pd->queue, cpu);
+
+		queue->pd = pd;
+
+		if (cpumask_test_cpu(cpu, cpumask)
+		    && cpumask_test_cpu(cpu, cpu_active_mask)) {
+			queue->cpu_index = cpu_index;
+			cpu_index++;
+		} else
+			queue->cpu_index = -1;
+
+		INIT_LIST_HEAD(&queue->reorder.list);
+		INIT_LIST_HEAD(&queue->parallel.list);
+		INIT_LIST_HEAD(&queue->serial.list);
+		spin_lock_init(&queue->reorder.lock);
+		spin_lock_init(&queue->parallel.lock);
+		spin_lock_init(&queue->serial.lock);
+
+		INIT_WORK(&queue->pwork, padata_parallel_worker);
+		INIT_WORK(&queue->swork, padata_serial_worker);
+		atomic_set(&queue->num_obj, 0);
+	}
+
+	cpumask_and(pd->cpumask, cpumask, cpu_active_mask);
+
+	num_cpus = cpumask_weight(pd->cpumask);
+	pd->max_seq_nr = (MAX_SEQ_NR / num_cpus) * num_cpus - 1;
+
+	atomic_set(&pd->seq_nr, -1);
+	atomic_set(&pd->reorder_objects, 0);
+	atomic_set(&pd->refcnt, 0);
+	pd->pinst = pinst;
+	spin_lock_init(&pd->lock);
+
+	return pd;
+
+err_free_queue:
+	free_percpu(pd->queue);
+err_free_pd:
+	kfree(pd);
+err:
+	return NULL;
+}
+
+static void padata_free_pd(struct parallel_data *pd)
+{
+	free_cpumask_var(pd->cpumask);
+	free_percpu(pd->queue);
+	kfree(pd);
+}
+
+static void padata_replace(struct padata_instance *pinst,
+			   struct parallel_data *pd_new)
+{
+	struct parallel_data *pd_old = pinst->pd;
+
+	pinst->flags |= PADATA_RESET;
+
+	rcu_assign_pointer(pinst->pd, pd_new);
+
+	synchronize_rcu();
+
+	while (atomic_read(&pd_old->refcnt) != 0)
+		yield();
+
+	flush_workqueue(pinst->wq);
+
+	padata_free_pd(pd_old);
+
+	pinst->flags &= ~PADATA_RESET;
+}
+
+/*
+ * padata_set_cpumask - set the cpumask that padata should use
+ *
+ * @pinst: padata instance
+ * @cpumask: the cpumask to use
+ */
+int padata_set_cpumask(struct padata_instance *pinst,
+			cpumask_var_t cpumask)
+{
+	struct parallel_data *pd;
+	int err = 0;
+
+	might_sleep();
+
+	mutex_lock(&pinst->lock);
+
+	pd = padata_alloc_pd(pinst, cpumask);
+	if (!pd) {
+		err = -ENOMEM;
+		goto out;
+	}
+
+	cpumask_copy(pinst->cpumask, cpumask);
+
+	padata_replace(pinst, pd);
+
+out:
+	mutex_unlock(&pinst->lock);
+
+	return err;
+}
+EXPORT_SYMBOL(padata_set_cpumask);
+
+static int __padata_add_cpu(struct padata_instance *pinst, int cpu)
+{
+	struct parallel_data *pd;
+
+	if (cpumask_test_cpu(cpu, cpu_active_mask)) {
+		pd = padata_alloc_pd(pinst, pinst->cpumask);
+		if (!pd)
+			return -ENOMEM;
+
+		padata_replace(pinst, pd);
+	}
+
+	return 0;
+}
+
+/*
+ * padata_add_cpu - add a cpu to the padata cpumask
+ *
+ * @pinst: padata instance
+ * @cpu: cpu to add
+ */
+int padata_add_cpu(struct padata_instance *pinst, int cpu)
+{
+	int err;
+
+	might_sleep();
+
+	mutex_lock(&pinst->lock);
+
+	cpumask_set_cpu(cpu, pinst->cpumask);
+	err = __padata_add_cpu(pinst, cpu);
+
+	mutex_unlock(&pinst->lock);
+
+	return err;
+}
+EXPORT_SYMBOL(padata_add_cpu);
+
+static int __padata_remove_cpu(struct padata_instance *pinst, int cpu)
+{
+	struct parallel_data *pd;
+
+	if (cpumask_test_cpu(cpu, cpu_online_mask)) {
+		pd = padata_alloc_pd(pinst, pinst->cpumask);
+		if (!pd)
+			return -ENOMEM;
+
+		padata_replace(pinst, pd);
+	}
+
+	return 0;
+}
+
+/*
+ * padata_remove_cpu - remove a cpu from the padata cpumask
+ *
+ * @pinst: padata instance
+ * @cpu: cpu to remove
+ */
+int padata_remove_cpu(struct padata_instance *pinst, int cpu)
+{
+	int err;
+
+	might_sleep();
+
+	mutex_lock(&pinst->lock);
+
+	cpumask_clear_cpu(cpu, pinst->cpumask);
+	err = __padata_remove_cpu(pinst, cpu);
+
+	mutex_unlock(&pinst->lock);
+
+	return err;
+}
+EXPORT_SYMBOL(padata_remove_cpu);
+
+/*
+ * padata_start - start the parallel processing
+ *
+ * @pinst: padata instance to start
+ */
+void padata_start(struct padata_instance *pinst)
+{
+	might_sleep();
+
+	mutex_lock(&pinst->lock);
+	pinst->flags |= PADATA_INIT;
+	mutex_unlock(&pinst->lock);
+}
+EXPORT_SYMBOL(padata_start);
+
+/*
+ * padata_stop - stop the parallel processing
+ *
+ * @pinst: padata instance to stop
+ */
+void padata_stop(struct padata_instance *pinst)
+{
+	might_sleep();
+
+	mutex_lock(&pinst->lock);
+	pinst->flags &= ~PADATA_INIT;
+	mutex_unlock(&pinst->lock);
+}
+EXPORT_SYMBOL(padata_stop);
+
+static int __cpuinit padata_cpu_callback(struct notifier_block *nfb,
+					 unsigned long action, void *hcpu)
+{
+	int err;
+	struct padata_instance *pinst;
+	int cpu = (unsigned long)hcpu;
+
+	pinst = container_of(nfb, struct padata_instance, cpu_notifier);
+
+	switch (action) {
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+		if (!cpumask_test_cpu(cpu, pinst->cpumask))
+			break;
+		mutex_lock(&pinst->lock);
+		err = __padata_add_cpu(pinst, cpu);
+		mutex_unlock(&pinst->lock);
+		if (err)
+			return NOTIFY_BAD;
+		break;
+
+	case CPU_DOWN_PREPARE:
+	case CPU_DOWN_PREPARE_FROZEN:
+		if (!cpumask_test_cpu(cpu, pinst->cpumask))
+			break;
+		mutex_lock(&pinst->lock);
+		err = __padata_remove_cpu(pinst, cpu);
+		mutex_unlock(&pinst->lock);
+		if (err)
+			return NOTIFY_BAD;
+		break;
+
+	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
+		if (!cpumask_test_cpu(cpu, pinst->cpumask))
+			break;
+		mutex_lock(&pinst->lock);
+		__padata_remove_cpu(pinst, cpu);
+		mutex_unlock(&pinst->lock);
+
+	case CPU_DOWN_FAILED:
+	case CPU_DOWN_FAILED_FROZEN:
+		if (!cpumask_test_cpu(cpu, pinst->cpumask))
+			break;
+		mutex_lock(&pinst->lock);
+		__padata_add_cpu(pinst, cpu);
+		mutex_unlock(&pinst->lock);
+	}
+
+	return NOTIFY_OK;
+}
+
+/*
+ * padata_alloc - allocate and initialize a padata instance
+ *
+ * @cpumask: cpumask that padata uses for parallelization
+ * @wq: workqueue to use for the allocated padata instance
+ */
+struct padata_instance *padata_alloc(const struct cpumask *cpumask,
+				     struct workqueue_struct *wq)
+{
+	int err;
+	struct padata_instance *pinst;
+	struct parallel_data *pd;
+
+	pinst = kzalloc(sizeof(struct padata_instance), GFP_KERNEL);
+	if (!pinst)
+		goto err;
+
+	pd = padata_alloc_pd(pinst, cpumask);
+	if (!pd)
+		goto err_free_inst;
+
+	rcu_assign_pointer(pinst->pd, pd);
+
+	pinst->wq = wq;
+
+	cpumask_copy(pinst->cpumask, cpumask);
+
+	pinst->flags = 0;
+
+	pinst->cpu_notifier.notifier_call = padata_cpu_callback;
+	pinst->cpu_notifier.priority = 0;
+	err = register_hotcpu_notifier(&pinst->cpu_notifier);
+	if (err)
+		goto err_free_pd;
+
+	mutex_init(&pinst->lock);
+
+	return pinst;
+
+err_free_pd:
+	padata_free_pd(pd);
+err_free_inst:
+	kfree(pinst);
+err:
+	return NULL;
+}
+EXPORT_SYMBOL(padata_alloc);
+
+/*
+ * padata_free - free a padata instance
+ *
+ * @ padata_inst: padata instance to free
+ */
+void padata_free(struct padata_instance *pinst)
+{
+	padata_stop(pinst);
+
+	synchronize_rcu();
+
+	while (atomic_read(&pinst->pd->refcnt) != 0)
+		yield();
+
+	unregister_hotcpu_notifier(&pinst->cpu_notifier);
+	padata_free_pd(pinst->pd);
+	kfree(pinst);
+}
+EXPORT_SYMBOL(padata_free);

net/xfrm/xfrm_algo.c

@@ -125,6 +125,22 @@ static struct xfrm_algo_desc aead_list[] = {
 		.sadb_alg_maxbits = 256
 	}
 },
+{
+	.name = "rfc4543(gcm(aes))",
+
+	.uinfo = {
+		.aead = {
+			.icv_truncbits = 128,
+		}
+	},
+
+	.desc = {
+		.sadb_alg_id = SADB_X_EALG_NULL_AES_GMAC,
+		.sadb_alg_ivlen = 8,
+		.sadb_alg_minbits = 128,
+		.sadb_alg_maxbits = 256
+	}
+},
 };
 
 static struct xfrm_algo_desc aalg_list[] = {