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

Pull crypto updates from Herbert Xu:
 "API:

   - crypto_destroy_tfm now ignores errors as well as NULL pointers

  Algorithms:

   - Add explicit curve IDs in ECDH algorithm names

   - Add NIST P384 curve parameters

   - Add ECDSA

  Drivers:

   - Add support for Green Sardine in ccp

   - Add ecdh/curve25519 to hisilicon/hpre

   - Add support for AM64 in sa2ul"

* 'linus' of git://git.kernel.org/pub/scm/linux/kernel/git/herbert/crypto-2.6: (184 commits)
  fsverity: relax build time dependency on CRYPTO_SHA256
  fscrypt: relax Kconfig dependencies for crypto API algorithms
  crypto: camellia - drop duplicate "depends on CRYPTO"
  crypto: s5p-sss - consistently use local 'dev' variable in probe()
  crypto: s5p-sss - remove unneeded local variable initialization
  crypto: s5p-sss - simplify getting of_device_id match data
  ccp: ccp - add support for Green Sardine
  crypto: ccp - Make ccp_dev_suspend and ccp_dev_resume void functions
  crypto: octeontx2 - add support for OcteonTX2 98xx CPT block.
  crypto: chelsio/chcr - Remove useless MODULE_VERSION
  crypto: ux500/cryp - Remove duplicate argument
  crypto: chelsio - remove unused function
  crypto: sa2ul - Add support for AM64
  crypto: sa2ul - Support for per channel coherency
  dt-bindings: crypto: ti,sa2ul: Add new compatible for AM64
  crypto: hisilicon - enable new error types for QM
  crypto: hisilicon - add new error type for SEC
  crypto: hisilicon - support new error types for ZIP
  crypto: hisilicon - dynamic configuration 'err_info'
  crypto: doc - fix kernel-doc notation in chacha.c and af_alg.c
  ...

1 files changed, 205 insertions, 86 deletions

diff --git a/crypto/ecc.c b/crypto/ecc.c
index c80aa25994a0..afc6cefdc1d9 100644
--- a/crypto/ecc.c
+++ b/crypto/ecc.c
@@ -24,6 +24,7 @@
  * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
  */
 
+#include <crypto/ecc_curve.h>
 #include <linux/module.h>
 #include <linux/random.h>
 #include <linux/slab.h>
@@ -42,7 +43,14 @@ typedef struct {
 	u64 m_high;
 } uint128_t;
 
-static inline const struct ecc_curve *ecc_get_curve(unsigned int curve_id)
+/* Returns curv25519 curve param */
+const struct ecc_curve *ecc_get_curve25519(void)
+{
+	return &ecc_25519;
+}
+EXPORT_SYMBOL(ecc_get_curve25519);
+
+const struct ecc_curve *ecc_get_curve(unsigned int curve_id)
 {
 	switch (curve_id) {
 	/* In FIPS mode only allow P256 and higher */
@@ -50,10 +58,13 @@ static inline const struct ecc_curve *ecc_get_curve(unsigned int curve_id)
 		return fips_enabled ? NULL : &nist_p192;
 	case ECC_CURVE_NIST_P256:
 		return &nist_p256;
+	case ECC_CURVE_NIST_P384:
+		return &nist_p384;
 	default:
 		return NULL;
 	}
 }
+EXPORT_SYMBOL(ecc_get_curve);
 
 static u64 *ecc_alloc_digits_space(unsigned int ndigits)
 {
@@ -128,7 +139,7 @@ bool vli_is_zero(const u64 *vli, unsigned int ndigits)
 }
 EXPORT_SYMBOL(vli_is_zero);
 
-/* Returns nonzero if bit bit of vli is set. */
+/* Returns nonzero if bit of vli is set. */
 static u64 vli_test_bit(const u64 *vli, unsigned int bit)
 {
 	return (vli[bit / 64] & ((u64)1 << (bit % 64)));
@@ -775,18 +786,133 @@ static void vli_mmod_fast_256(u64 *result, const u64 *product,
 	}
 }
 
+#define SL32OR32(x32, y32) (((u64)x32 << 32) | y32)
+#define AND64H(x64)  (x64 & 0xffFFffFF00000000ull)
+#define AND64L(x64)  (x64 & 0x00000000ffFFffFFull)
+
+/* Computes result = product % curve_prime
+ * from "Mathematical routines for the NIST prime elliptic curves"
+ */
+static void vli_mmod_fast_384(u64 *result, const u64 *product,
+				const u64 *curve_prime, u64 *tmp)
+{
+	int carry;
+	const unsigned int ndigits = 6;
+
+	/* t */
+	vli_set(result, product, ndigits);
+
+	/* s1 */
+	tmp[0] = 0;		// 0 || 0
+	tmp[1] = 0;		// 0 || 0
+	tmp[2] = SL32OR32(product[11], (product[10]>>32));	//a22||a21
+	tmp[3] = product[11]>>32;	// 0 ||a23
+	tmp[4] = 0;		// 0 || 0
+	tmp[5] = 0;		// 0 || 0
+	carry = vli_lshift(tmp, tmp, 1, ndigits);
+	carry += vli_add(result, result, tmp, ndigits);
+
+	/* s2 */
+	tmp[0] = product[6];	//a13||a12
+	tmp[1] = product[7];	//a15||a14
+	tmp[2] = product[8];	//a17||a16
+	tmp[3] = product[9];	//a19||a18
+	tmp[4] = product[10];	//a21||a20
+	tmp[5] = product[11];	//a23||a22
+	carry += vli_add(result, result, tmp, ndigits);
+
+	/* s3 */
+	tmp[0] = SL32OR32(product[11], (product[10]>>32));	//a22||a21
+	tmp[1] = SL32OR32(product[6], (product[11]>>32));	//a12||a23
+	tmp[2] = SL32OR32(product[7], (product[6])>>32);	//a14||a13
+	tmp[3] = SL32OR32(product[8], (product[7]>>32));	//a16||a15
+	tmp[4] = SL32OR32(product[9], (product[8]>>32));	//a18||a17
+	tmp[5] = SL32OR32(product[10], (product[9]>>32));	//a20||a19
+	carry += vli_add(result, result, tmp, ndigits);
+
+	/* s4 */
+	tmp[0] = AND64H(product[11]);	//a23|| 0
+	tmp[1] = (product[10]<<32);	//a20|| 0
+	tmp[2] = product[6];	//a13||a12
+	tmp[3] = product[7];	//a15||a14
+	tmp[4] = product[8];	//a17||a16
+	tmp[5] = product[9];	//a19||a18
+	carry += vli_add(result, result, tmp, ndigits);
+
+	/* s5 */
+	tmp[0] = 0;		//  0|| 0
+	tmp[1] = 0;		//  0|| 0
+	tmp[2] = product[10];	//a21||a20
+	tmp[3] = product[11];	//a23||a22
+	tmp[4] = 0;		//  0|| 0
+	tmp[5] = 0;		//  0|| 0
+	carry += vli_add(result, result, tmp, ndigits);
+
+	/* s6 */
+	tmp[0] = AND64L(product[10]);	// 0 ||a20
+	tmp[1] = AND64H(product[10]);	//a21|| 0
+	tmp[2] = product[11];	//a23||a22
+	tmp[3] = 0;		// 0 || 0
+	tmp[4] = 0;		// 0 || 0
+	tmp[5] = 0;		// 0 || 0
+	carry += vli_add(result, result, tmp, ndigits);
+
+	/* d1 */
+	tmp[0] = SL32OR32(product[6], (product[11]>>32));	//a12||a23
+	tmp[1] = SL32OR32(product[7], (product[6]>>32));	//a14||a13
+	tmp[2] = SL32OR32(product[8], (product[7]>>32));	//a16||a15
+	tmp[3] = SL32OR32(product[9], (product[8]>>32));	//a18||a17
+	tmp[4] = SL32OR32(product[10], (product[9]>>32));	//a20||a19
+	tmp[5] = SL32OR32(product[11], (product[10]>>32));	//a22||a21
+	carry -= vli_sub(result, result, tmp, ndigits);
+
+	/* d2 */
+	tmp[0] = (product[10]<<32);	//a20|| 0
+	tmp[1] = SL32OR32(product[11], (product[10]>>32));	//a22||a21
+	tmp[2] = (product[11]>>32);	// 0 ||a23
+	tmp[3] = 0;		// 0 || 0
+	tmp[4] = 0;		// 0 || 0
+	tmp[5] = 0;		// 0 || 0
+	carry -= vli_sub(result, result, tmp, ndigits);
+
+	/* d3 */
+	tmp[0] = 0;		// 0 || 0
+	tmp[1] = AND64H(product[11]);	//a23|| 0
+	tmp[2] = product[11]>>32;	// 0 ||a23
+	tmp[3] = 0;		// 0 || 0
+	tmp[4] = 0;		// 0 || 0
+	tmp[5] = 0;		// 0 || 0
+	carry -= vli_sub(result, result, tmp, ndigits);
+
+	if (carry < 0) {
+		do {
+			carry += vli_add(result, result, curve_prime, ndigits);
+		} while (carry < 0);
+	} else {
+		while (carry || vli_cmp(curve_prime, result, ndigits) != 1)
+			carry -= vli_sub(result, result, curve_prime, ndigits);
+	}
+
+}
+
+#undef SL32OR32
+#undef AND64H
+#undef AND64L
+
 /* Computes result = product % curve_prime for different curve_primes.
  *
  * Note that curve_primes are distinguished just by heuristic check and
  * not by complete conformance check.
  */
 static bool vli_mmod_fast(u64 *result, u64 *product,
-			  const u64 *curve_prime, unsigned int ndigits)
+			  const struct ecc_curve *curve)
 {
 	u64 tmp[2 * ECC_MAX_DIGITS];
+	const u64 *curve_prime = curve->p;
+	const unsigned int ndigits = curve->g.ndigits;
 
-	/* Currently, both NIST primes have -1 in lowest qword. */
-	if (curve_prime[0] != -1ull) {
+	/* All NIST curves have name prefix 'nist_' */
+	if (strncmp(curve->name, "nist_", 5) != 0) {
 		/* Try to handle Pseudo-Marsenne primes. */
 		if (curve_prime[ndigits - 1] == -1ull) {
 			vli_mmod_special(result, product, curve_prime,
@@ -809,6 +935,9 @@ static bool vli_mmod_fast(u64 *result, u64 *product,
 	case 4:
 		vli_mmod_fast_256(result, product, curve_prime, tmp);
 		break;
+	case 6:
+		vli_mmod_fast_384(result, product, curve_prime, tmp);
+		break;
 	default:
 		pr_err_ratelimited("ecc: unsupported digits size!\n");
 		return false;
@@ -832,22 +961,22 @@ EXPORT_SYMBOL(vli_mod_mult_slow);
 
 /* Computes result = (left * right) % curve_prime. */
 static void vli_mod_mult_fast(u64 *result, const u64 *left, const u64 *right,
-			      const u64 *curve_prime, unsigned int ndigits)
+			      const struct ecc_curve *curve)
 {
 	u64 product[2 * ECC_MAX_DIGITS];
 
-	vli_mult(product, left, right, ndigits);
-	vli_mmod_fast(result, product, curve_prime, ndigits);
+	vli_mult(product, left, right, curve->g.ndigits);
+	vli_mmod_fast(result, product, curve);
 }
 
 /* Computes result = left^2 % curve_prime. */
 static void vli_mod_square_fast(u64 *result, const u64 *left,
-				const u64 *curve_prime, unsigned int ndigits)
+				const struct ecc_curve *curve)
 {
 	u64 product[2 * ECC_MAX_DIGITS];
 
-	vli_square(product, left, ndigits);
-	vli_mmod_fast(result, product, curve_prime, ndigits);
+	vli_square(product, left, curve->g.ndigits);
+	vli_mmod_fast(result, product, curve);
 }
 
 #define EVEN(vli) (!(vli[0] & 1))
@@ -945,25 +1074,27 @@ static bool ecc_point_is_zero(const struct ecc_point *point)
 
 /* Double in place */
 static void ecc_point_double_jacobian(u64 *x1, u64 *y1, u64 *z1,
-				      u64 *curve_prime, unsigned int ndigits)
+					const struct ecc_curve *curve)
 {
 	/* t1 = x, t2 = y, t3 = z */
 	u64 t4[ECC_MAX_DIGITS];
 	u64 t5[ECC_MAX_DIGITS];
+	const u64 *curve_prime = curve->p;
+	const unsigned int ndigits = curve->g.ndigits;
 
 	if (vli_is_zero(z1, ndigits))
 		return;
 
 	/* t4 = y1^2 */
-	vli_mod_square_fast(t4, y1, curve_prime, ndigits);
+	vli_mod_square_fast(t4, y1, curve);
 	/* t5 = x1*y1^2 = A */
-	vli_mod_mult_fast(t5, x1, t4, curve_prime, ndigits);
+	vli_mod_mult_fast(t5, x1, t4, curve);
 	/* t4 = y1^4 */
-	vli_mod_square_fast(t4, t4, curve_prime, ndigits);
+	vli_mod_square_fast(t4, t4, curve);
 	/* t2 = y1*z1 = z3 */
-	vli_mod_mult_fast(y1, y1, z1, curve_prime, ndigits);
+	vli_mod_mult_fast(y1, y1, z1, curve);
 	/* t3 = z1^2 */
-	vli_mod_square_fast(z1, z1, curve_prime, ndigits);
+	vli_mod_square_fast(z1, z1, curve);
 
 	/* t1 = x1 + z1^2 */
 	vli_mod_add(x1, x1, z1, curve_prime, ndigits);
@@ -972,7 +1103,7 @@ static void ecc_point_double_jacobian(u64 *x1, u64 *y1, u64 *z1,
 	/* t3 = x1 - z1^2 */
 	vli_mod_sub(z1, x1, z1, curve_prime, ndigits);
 	/* t1 = x1^2 - z1^4 */
-	vli_mod_mult_fast(x1, x1, z1, curve_prime, ndigits);
+	vli_mod_mult_fast(x1, x1, z1, curve);
 
 	/* t3 = 2*(x1^2 - z1^4) */
 	vli_mod_add(z1, x1, x1, curve_prime, ndigits);
@@ -989,7 +1120,7 @@ static void ecc_point_double_jacobian(u64 *x1, u64 *y1, u64 *z1,
 	/* t1 = 3/2*(x1^2 - z1^4) = B */
 
 	/* t3 = B^2 */
-	vli_mod_square_fast(z1, x1, curve_prime, ndigits);
+	vli_mod_square_fast(z1, x1, curve);
 	/* t3 = B^2 - A */
 	vli_mod_sub(z1, z1, t5, curve_prime, ndigits);
 	/* t3 = B^2 - 2A = x3 */
@@ -997,7 +1128,7 @@ static void ecc_point_double_jacobian(u64 *x1, u64 *y1, u64 *z1,
 	/* t5 = A - x3 */
 	vli_mod_sub(t5, t5, z1, curve_prime, ndigits);
 	/* t1 = B * (A - x3) */
-	vli_mod_mult_fast(x1, x1, t5, curve_prime, ndigits);
+	vli_mod_mult_fast(x1, x1, t5, curve);
 	/* t4 = B * (A - x3) - y1^4 = y3 */
 	vli_mod_sub(t4, x1, t4, curve_prime, ndigits);
 
@@ -1007,23 +1138,22 @@ static void ecc_point_double_jacobian(u64 *x1, u64 *y1, u64 *z1,
 }
 
 /* Modify (x1, y1) => (x1 * z^2, y1 * z^3) */
-static void apply_z(u64 *x1, u64 *y1, u64 *z, u64 *curve_prime,
-		    unsigned int ndigits)
+static void apply_z(u64 *x1, u64 *y1, u64 *z, const struct ecc_curve *curve)
 {
 	u64 t1[ECC_MAX_DIGITS];
 
-	vli_mod_square_fast(t1, z, curve_prime, ndigits);    /* z^2 */
-	vli_mod_mult_fast(x1, x1, t1, curve_prime, ndigits); /* x1 * z^2 */
-	vli_mod_mult_fast(t1, t1, z, curve_prime, ndigits);  /* z^3 */
-	vli_mod_mult_fast(y1, y1, t1, curve_prime, ndigits); /* y1 * z^3 */
+	vli_mod_square_fast(t1, z, curve);		/* z^2 */
+	vli_mod_mult_fast(x1, x1, t1, curve);	/* x1 * z^2 */
+	vli_mod_mult_fast(t1, t1, z, curve);	/* z^3 */
+	vli_mod_mult_fast(y1, y1, t1, curve);	/* y1 * z^3 */
 }
 
 /* P = (x1, y1) => 2P, (x2, y2) => P' */
 static void xycz_initial_double(u64 *x1, u64 *y1, u64 *x2, u64 *y2,
-				u64 *p_initial_z, u64 *curve_prime,
-				unsigned int ndigits)
+				u64 *p_initial_z, const struct ecc_curve *curve)
 {
 	u64 z[ECC_MAX_DIGITS];
+	const unsigned int ndigits = curve->g.ndigits;
 
 	vli_set(x2, x1, ndigits);
 	vli_set(y2, y1, ndigits);
@@ -1034,35 +1164,37 @@ static void xycz_initial_double(u64 *x1, u64 *y1, u64 *x2, u64 *y2,
 	if (p_initial_z)
 		vli_set(z, p_initial_z, ndigits);
 
-	apply_z(x1, y1, z, curve_prime, ndigits);
+	apply_z(x1, y1, z, curve);
 
-	ecc_point_double_jacobian(x1, y1, z, curve_prime, ndigits);
+	ecc_point_double_jacobian(x1, y1, z, curve);
 
-	apply_z(x2, y2, z, curve_prime, ndigits);
+	apply_z(x2, y2, z, curve);
 }
 
 /* Input P = (x1, y1, Z), Q = (x2, y2, Z)
  * Output P' = (x1', y1', Z3), P + Q = (x3, y3, Z3)
  * or P => P', Q => P + Q
  */
-static void xycz_add(u64 *x1, u64 *y1, u64 *x2, u64 *y2, u64 *curve_prime,
-		     unsigned int ndigits)
+static void xycz_add(u64 *x1, u64 *y1, u64 *x2, u64 *y2,
+			const struct ecc_curve *curve)
 {
 	/* t1 = X1, t2 = Y1, t3 = X2, t4 = Y2 */
 	u64 t5[ECC_MAX_DIGITS];
+	const u64 *curve_prime = curve->p;
+	const unsigned int ndigits = curve->g.ndigits;
 
 	/* t5 = x2 - x1 */
 	vli_mod_sub(t5, x2, x1, curve_prime, ndigits);
 	/* t5 = (x2 - x1)^2 = A */
-	vli_mod_square_fast(t5, t5, curve_prime, ndigits);
+	vli_mod_square_fast(t5, t5, curve);
 	/* t1 = x1*A = B */
-	vli_mod_mult_fast(x1, x1, t5, curve_prime, ndigits);
+	vli_mod_mult_fast(x1, x1, t5, curve);
 	/* t3 = x2*A = C */
-	vli_mod_mult_fast(x2, x2, t5, curve_prime, ndigits);
+	vli_mod_mult_fast(x2, x2, t5, curve);
 	/* t4 = y2 - y1 */
 	vli_mod_sub(y2, y2, y1, curve_prime, ndigits);
 	/* t5 = (y2 - y1)^2 = D */
-	vli_mod_square_fast(t5, y2, curve_prime, ndigits);
+	vli_mod_square_fast(t5, y2, curve);
 
 	/* t5 = D - B */
 	vli_mod_sub(t5, t5, x1, curve_prime, ndigits);
@@ -1071,11 +1203,11 @@ static void xycz_add(u64 *x1, u64 *y1, u64 *x2, u64 *y2, u64 *curve_prime,
 	/* t3 = C - B */
 	vli_mod_sub(x2, x2, x1, curve_prime, ndigits);
 	/* t2 = y1*(C - B) */
-	vli_mod_mult_fast(y1, y1, x2, curve_prime, ndigits);
+	vli_mod_mult_fast(y1, y1, x2, curve);
 	/* t3 = B - x3 */
 	vli_mod_sub(x2, x1, t5, curve_prime, ndigits);
 	/* t4 = (y2 - y1)*(B - x3) */
-	vli_mod_mult_fast(y2, y2, x2, curve_prime, ndigits);
+	vli_mod_mult_fast(y2, y2, x2, curve);
 	/* t4 = y3 */
 	vli_mod_sub(y2, y2, y1, curve_prime, ndigits);
 
@@ -1086,22 +1218,24 @@ static void xycz_add(u64 *x1, u64 *y1, u64 *x2, u64 *y2, u64 *curve_prime,
  * Output P + Q = (x3, y3, Z3), P - Q = (x3', y3', Z3)
  * or P => P - Q, Q => P + Q
  */
-static void xycz_add_c(u64 *x1, u64 *y1, u64 *x2, u64 *y2, u64 *curve_prime,
-		       unsigned int ndigits)
+static void xycz_add_c(u64 *x1, u64 *y1, u64 *x2, u64 *y2,
+			const struct ecc_curve *curve)
 {
 	/* t1 = X1, t2 = Y1, t3 = X2, t4 = Y2 */
 	u64 t5[ECC_MAX_DIGITS];
 	u64 t6[ECC_MAX_DIGITS];
 	u64 t7[ECC_MAX_DIGITS];
+	const u64 *curve_prime = curve->p;
+	const unsigned int ndigits = curve->g.ndigits;
 
 	/* t5 = x2 - x1 */
 	vli_mod_sub(t5, x2, x1, curve_prime, ndigits);
 	/* t5 = (x2 - x1)^2 = A */
-	vli_mod_square_fast(t5, t5, curve_prime, ndigits);
+	vli_mod_square_fast(t5, t5, curve);
 	/* t1 = x1*A = B */
-	vli_mod_mult_fast(x1, x1, t5, curve_prime, ndigits);
+	vli_mod_mult_fast(x1, x1, t5, curve);
 	/* t3 = x2*A = C */
-	vli_mod_mult_fast(x2, x2, t5, curve_prime, ndigits);
+	vli_mod_mult_fast(x2, x2, t5, curve);
 	/* t4 = y2 + y1 */
 	vli_mod_add(t5, y2, y1, curve_prime, ndigits);
 	/* t4 = y2 - y1 */
@@ -1110,29 +1244,29 @@ static void xycz_add_c(u64 *x1, u64 *y1, u64 *x2, u64 *y2, u64 *curve_prime,
 	/* t6 = C - B */
 	vli_mod_sub(t6, x2, x1, curve_prime, ndigits);
 	/* t2 = y1 * (C - B) */
-	vli_mod_mult_fast(y1, y1, t6, curve_prime, ndigits);
+	vli_mod_mult_fast(y1, y1, t6, curve);
 	/* t6 = B + C */
 	vli_mod_add(t6, x1, x2, curve_prime, ndigits);
 	/* t3 = (y2 - y1)^2 */
-	vli_mod_square_fast(x2, y2, curve_prime, ndigits);
+	vli_mod_square_fast(x2, y2, curve);
 	/* t3 = x3 */
 	vli_mod_sub(x2, x2, t6, curve_prime, ndigits);
 
 	/* t7 = B - x3 */
 	vli_mod_sub(t7, x1, x2, curve_prime, ndigits);
 	/* t4 = (y2 - y1)*(B - x3) */
-	vli_mod_mult_fast(y2, y2, t7, curve_prime, ndigits);
+	vli_mod_mult_fast(y2, y2, t7, curve);
 	/* t4 = y3 */
 	vli_mod_sub(y2, y2, y1, curve_prime, ndigits);
 
 	/* t7 = (y2 + y1)^2 = F */
-	vli_mod_square_fast(t7, t5, curve_prime, ndigits);
+	vli_mod_square_fast(t7, t5, curve);
 	/* t7 = x3' */
 	vli_mod_sub(t7, t7, t6, curve_prime, ndigits);
 	/* t6 = x3' - B */
 	vli_mod_sub(t6, t7, x1, curve_prime, ndigits);
 	/* t6 = (y2 + y1)*(x3' - B) */
-	vli_mod_mult_fast(t6, t6, t5, curve_prime, ndigits);
+	vli_mod_mult_fast(t6, t6, t5, curve);
 	/* t2 = y3' */
 	vli_mod_sub(y1, t6, y1, curve_prime, ndigits);
 
@@ -1162,41 +1296,37 @@ static void ecc_point_mult(struct ecc_point *result,
 	vli_set(rx[1], point->x, ndigits);
 	vli_set(ry[1], point->y, ndigits);
 
-	xycz_initial_double(rx[1], ry[1], rx[0], ry[0], initial_z, curve_prime,
-			    ndigits);
+	xycz_initial_double(rx[1], ry[1], rx[0], ry[0], initial_z, curve);
 
 	for (i = num_bits - 2; i > 0; i--) {
 		nb = !vli_test_bit(scalar, i);
-		xycz_add_c(rx[1 - nb], ry[1 - nb], rx[nb], ry[nb], curve_prime,
-			   ndigits);
-		xycz_add(rx[nb], ry[nb], rx[1 - nb], ry[1 - nb], curve_prime,
-			 ndigits);
+		xycz_add_c(rx[1 - nb], ry[1 - nb], rx[nb], ry[nb], curve);
+		xycz_add(rx[nb], ry[nb], rx[1 - nb], ry[1 - nb], curve);
 	}
 
 	nb = !vli_test_bit(scalar, 0);
-	xycz_add_c(rx[1 - nb], ry[1 - nb], rx[nb], ry[nb], curve_prime,
-		   ndigits);
+	xycz_add_c(rx[1 - nb], ry[1 - nb], rx[nb], ry[nb], curve);
 
 	/* Find final 1/Z value. */
 	/* X1 - X0 */
 	vli_mod_sub(z, rx[1], rx[0], curve_prime, ndigits);
 	/* Yb * (X1 - X0) */
-	vli_mod_mult_fast(z, z, ry[1 - nb], curve_prime, ndigits);
+	vli_mod_mult_fast(z, z, ry[1 - nb], curve);
 	/* xP * Yb * (X1 - X0) */
-	vli_mod_mult_fast(z, z, point->x, curve_prime, ndigits);
+	vli_mod_mult_fast(z, z, point->x, curve);
 
 	/* 1 / (xP * Yb * (X1 - X0)) */
 	vli_mod_inv(z, z, curve_prime, point->ndigits);
 
 	/* yP / (xP * Yb * (X1 - X0)) */
-	vli_mod_mult_fast(z, z, point->y, curve_prime, ndigits);
+	vli_mod_mult_fast(z, z, point->y, curve);
 	/* Xb * yP / (xP * Yb * (X1 - X0)) */
-	vli_mod_mult_fast(z, z, rx[1 - nb], curve_prime, ndigits);
+	vli_mod_mult_fast(z, z, rx[1 - nb], curve);
 	/* End 1/Z calculation */
 
-	xycz_add(rx[nb], ry[nb], rx[1 - nb], ry[1 - nb], curve_prime, ndigits);
+	xycz_add(rx[nb], ry[nb], rx[1 - nb], ry[1 - nb], curve);
 
-	apply_z(rx[0], ry[0], z, curve_prime, ndigits);
+	apply_z(rx[0], ry[0], z, curve);
 
 	vli_set(result->x, rx[0], ndigits);
 	vli_set(result->y, ry[0], ndigits);
@@ -1217,9 +1347,9 @@ static void ecc_point_add(const struct ecc_point *result,
 	vli_mod_sub(z, result->x, p->x, curve->p, ndigits);
 	vli_set(px, p->x, ndigits);
 	vli_set(py, p->y, ndigits);
-	xycz_add(px, py, result->x, result->y, curve->p, ndigits);
+	xycz_add(px, py, result->x, result->y, curve);
 	vli_mod_inv(z, z, curve->p, ndigits);
-	apply_z(result->x, result->y, z, curve->p, ndigits);
+	apply_z(result->x, result->y, z, curve);
 }
 
 /* Computes R = u1P + u2Q mod p using Shamir's trick.
@@ -1248,8 +1378,7 @@ void ecc_point_mult_shamir(const struct ecc_point *result,
 	points[2] = q;
 	points[3] = &sum;
 
-	num_bits = max(vli_num_bits(u1, ndigits),
-		       vli_num_bits(u2, ndigits));
+	num_bits = max(vli_num_bits(u1, ndigits), vli_num_bits(u2, ndigits));
 	i = num_bits - 1;
 	idx = (!!vli_test_bit(u1, i)) | ((!!vli_test_bit(u2, i)) << 1);
 	point = points[idx];
@@ -1260,7 +1389,7 @@ void ecc_point_mult_shamir(const struct ecc_point *result,
 	z[0] = 1;
 
 	for (--i; i >= 0; i--) {
-		ecc_point_double_jacobian(rx, ry, z, curve->p, ndigits);
+		ecc_point_double_jacobian(rx, ry, z, curve);
 		idx = (!!vli_test_bit(u1, i)) | ((!!vli_test_bit(u2, i)) << 1);
 		point = points[idx];
 		if (point) {
@@ -1270,27 +1399,17 @@ void ecc_point_mult_shamir(const struct ecc_point *result,
 
 			vli_set(tx, point->x, ndigits);
 			vli_set(ty, point->y, ndigits);
-			apply_z(tx, ty, z, curve->p, ndigits);
+			apply_z(tx, ty, z, curve);
 			vli_mod_sub(tz, rx, tx, curve->p, ndigits);
-			xycz_add(tx, ty, rx, ry, curve->p, ndigits);
-			vli_mod_mult_fast(z, z, tz, curve->p, ndigits);
+			xycz_add(tx, ty, rx, ry, curve);
+			vli_mod_mult_fast(z, z, tz, curve);
 		}
 	}
 	vli_mod_inv(z, z, curve->p, ndigits);
-	apply_z(rx, ry, z, curve->p, ndigits);
+	apply_z(rx, ry, z, curve);
 }
 EXPORT_SYMBOL(ecc_point_mult_shamir);
 
-static inline void ecc_swap_digits(const u64 *in, u64 *out,
-				   unsigned int ndigits)
-{
-	const __be64 *src = (__force __be64 *)in;
-	int i;
-
-	for (i = 0; i < ndigits; i++)
-		out[i] = be64_to_cpu(src[ndigits - 1 - i]);
-}
-
 static int __ecc_is_key_valid(const struct ecc_curve *curve,
 			      const u64 *private_key, unsigned int ndigits)
 {
@@ -1441,10 +1560,10 @@ int ecc_is_pubkey_valid_partial(const struct ecc_curve *curve,
 		return -EINVAL;
 
 	/* Check 3: Verify that y^2 == (x^3 + a·x + b) mod p */
-	vli_mod_square_fast(yy, pk->y, curve->p, pk->ndigits); /* y^2 */
-	vli_mod_square_fast(xxx, pk->x, curve->p, pk->ndigits); /* x^2 */
-	vli_mod_mult_fast(xxx, xxx, pk->x, curve->p, pk->ndigits); /* x^3 */
-	vli_mod_mult_fast(w, curve->a, pk->x, curve->p, pk->ndigits); /* a·x */
+	vli_mod_square_fast(yy, pk->y, curve); /* y^2 */
+	vli_mod_square_fast(xxx, pk->x, curve); /* x^2 */
+	vli_mod_mult_fast(xxx, xxx, pk->x, curve); /* x^3 */
+	vli_mod_mult_fast(w, curve->a, pk->x, curve); /* a·x */
 	vli_mod_add(w, w, curve->b, curve->p, pk->ndigits); /* a·x + b */
 	vli_mod_add(w, w, xxx, curve->p, pk->ndigits); /* x^3 + a·x + b */
 	if (vli_cmp(yy, w, pk->ndigits) != 0) /* Equation */