diff options
Diffstat (limited to 'crypto/gf128mul.c')
| -rw-r--r-- | crypto/gf128mul.c | 171 |
1 files changed, 136 insertions, 35 deletions
diff --git a/crypto/gf128mul.c b/crypto/gf128mul.c index 5276607c72d0..f3d9f6da0767 100644 --- a/crypto/gf128mul.c +++ b/crypto/gf128mul.c @@ -44,7 +44,7 @@ --------------------------------------------------------------------------- Issue 31/01/2006 - This file provides fast multiplication in GF(128) as required by several + This file provides fast multiplication in GF(2^128) as required by several cryptographic authentication modes */ @@ -88,37 +88,52 @@ q(0xf8), q(0xf9), q(0xfa), q(0xfb), q(0xfc), q(0xfd), q(0xfe), q(0xff) \ } -/* Given the value i in 0..255 as the byte overflow when a field element - in GHASH is multiplied by x^8, this function will return the values that - are generated in the lo 16-bit word of the field value by applying the - modular polynomial. The values lo_byte and hi_byte are returned via the - macro xp_fun(lo_byte, hi_byte) so that the values can be assembled into - memory as required by a suitable definition of this macro operating on - the table above -*/ - -#define xx(p, q) 0x##p##q +/* + * Given a value i in 0..255 as the byte overflow when a field element + * in GF(2^128) is multiplied by x^8, the following macro returns the + * 16-bit value that must be XOR-ed into the low-degree end of the + * product to reduce it modulo the irreducible polynomial x^128 + x^7 + + * x^2 + x + 1. + * + * There are two versions of the macro, and hence two tables: one for + * the "be" convention where the highest-order bit is the coefficient of + * the highest-degree polynomial term, and one for the "le" convention + * where the highest-order bit is the coefficient of the lowest-degree + * polynomial term. In both cases the values are stored in CPU byte + * endianness such that the coefficients are ordered consistently across + * bytes, i.e. in the "be" table bits 15..0 of the stored value + * correspond to the coefficients of x^15..x^0, and in the "le" table + * bits 15..0 correspond to the coefficients of x^0..x^15. + * + * Therefore, provided that the appropriate byte endianness conversions + * are done by the multiplication functions (and these must be in place + * anyway to support both little endian and big endian CPUs), the "be" + * table can be used for multiplications of both "bbe" and "ble" + * elements, and the "le" table can be used for multiplications of both + * "lle" and "lbe" elements. + */ -#define xda_bbe(i) ( \ - (i & 0x80 ? xx(43, 80) : 0) ^ (i & 0x40 ? xx(21, c0) : 0) ^ \ - (i & 0x20 ? xx(10, e0) : 0) ^ (i & 0x10 ? xx(08, 70) : 0) ^ \ - (i & 0x08 ? xx(04, 38) : 0) ^ (i & 0x04 ? xx(02, 1c) : 0) ^ \ - (i & 0x02 ? xx(01, 0e) : 0) ^ (i & 0x01 ? xx(00, 87) : 0) \ +#define xda_be(i) ( \ + (i & 0x80 ? 0x4380 : 0) ^ (i & 0x40 ? 0x21c0 : 0) ^ \ + (i & 0x20 ? 0x10e0 : 0) ^ (i & 0x10 ? 0x0870 : 0) ^ \ + (i & 0x08 ? 0x0438 : 0) ^ (i & 0x04 ? 0x021c : 0) ^ \ + (i & 0x02 ? 0x010e : 0) ^ (i & 0x01 ? 0x0087 : 0) \ ) -#define xda_lle(i) ( \ - (i & 0x80 ? xx(e1, 00) : 0) ^ (i & 0x40 ? xx(70, 80) : 0) ^ \ - (i & 0x20 ? xx(38, 40) : 0) ^ (i & 0x10 ? xx(1c, 20) : 0) ^ \ - (i & 0x08 ? xx(0e, 10) : 0) ^ (i & 0x04 ? xx(07, 08) : 0) ^ \ - (i & 0x02 ? xx(03, 84) : 0) ^ (i & 0x01 ? xx(01, c2) : 0) \ +#define xda_le(i) ( \ + (i & 0x80 ? 0xe100 : 0) ^ (i & 0x40 ? 0x7080 : 0) ^ \ + (i & 0x20 ? 0x3840 : 0) ^ (i & 0x10 ? 0x1c20 : 0) ^ \ + (i & 0x08 ? 0x0e10 : 0) ^ (i & 0x04 ? 0x0708 : 0) ^ \ + (i & 0x02 ? 0x0384 : 0) ^ (i & 0x01 ? 0x01c2 : 0) \ ) -static const u16 gf128mul_table_lle[256] = gf128mul_dat(xda_lle); -static const u16 gf128mul_table_bbe[256] = gf128mul_dat(xda_bbe); +static const u16 gf128mul_table_le[256] = gf128mul_dat(xda_le); +static const u16 gf128mul_table_be[256] = gf128mul_dat(xda_be); -/* These functions multiply a field element by x, by x^4 and by x^8 - * in the polynomial field representation. It uses 32-bit word operations - * to gain speed but compensates for machine endianess and hence works +/* + * The following functions multiply a field element by x or by x^8 in + * the polynomial field representation. They use 64-bit word operations + * to gain speed but compensate for machine endianness and hence work * correctly on both styles of machine. */ @@ -126,7 +141,7 @@ static void gf128mul_x_lle(be128 *r, const be128 *x) { u64 a = be64_to_cpu(x->a); u64 b = be64_to_cpu(x->b); - u64 _tt = gf128mul_table_lle[(b << 7) & 0xff]; + u64 _tt = gf128mul_table_le[(b << 7) & 0xff]; r->b = cpu_to_be64((b >> 1) | (a << 63)); r->a = cpu_to_be64((a >> 1) ^ (_tt << 48)); @@ -136,7 +151,7 @@ static void gf128mul_x_bbe(be128 *r, const be128 *x) { u64 a = be64_to_cpu(x->a); u64 b = be64_to_cpu(x->b); - u64 _tt = gf128mul_table_bbe[a >> 63]; + u64 _tt = gf128mul_table_be[a >> 63]; r->a = cpu_to_be64((a << 1) | (b >> 63)); r->b = cpu_to_be64((b << 1) ^ _tt); @@ -146,7 +161,7 @@ void gf128mul_x_ble(be128 *r, const be128 *x) { u64 a = le64_to_cpu(x->a); u64 b = le64_to_cpu(x->b); - u64 _tt = gf128mul_table_bbe[b >> 63]; + u64 _tt = gf128mul_table_be[b >> 63]; r->a = cpu_to_le64((a << 1) ^ _tt); r->b = cpu_to_le64((b << 1) | (a >> 63)); @@ -157,7 +172,7 @@ static void gf128mul_x8_lle(be128 *x) { u64 a = be64_to_cpu(x->a); u64 b = be64_to_cpu(x->b); - u64 _tt = gf128mul_table_lle[b & 0xff]; + u64 _tt = gf128mul_table_le[b & 0xff]; x->b = cpu_to_be64((b >> 8) | (a << 56)); x->a = cpu_to_be64((a >> 8) ^ (_tt << 48)); @@ -167,12 +182,22 @@ static void gf128mul_x8_bbe(be128 *x) { u64 a = be64_to_cpu(x->a); u64 b = be64_to_cpu(x->b); - u64 _tt = gf128mul_table_bbe[a >> 56]; + u64 _tt = gf128mul_table_be[a >> 56]; x->a = cpu_to_be64((a << 8) | (b >> 56)); x->b = cpu_to_be64((b << 8) ^ _tt); } +static void gf128mul_x8_ble(be128 *x) +{ + u64 a = le64_to_cpu(x->b); + u64 b = le64_to_cpu(x->a); + u64 _tt = gf128mul_table_be[a >> 56]; + + x->b = cpu_to_le64((a << 8) | (b >> 56)); + x->a = cpu_to_le64((b << 8) ^ _tt); +} + void gf128mul_lle(be128 *r, const be128 *b) { be128 p[8]; @@ -249,9 +274,48 @@ void gf128mul_bbe(be128 *r, const be128 *b) } EXPORT_SYMBOL(gf128mul_bbe); +void gf128mul_ble(be128 *r, const be128 *b) +{ + be128 p[8]; + int i; + + p[0] = *r; + for (i = 0; i < 7; ++i) + gf128mul_x_ble((be128 *)&p[i + 1], (be128 *)&p[i]); + + memset(r, 0, sizeof(*r)); + for (i = 0;;) { + u8 ch = ((u8 *)b)[15 - i]; + + if (ch & 0x80) + be128_xor(r, r, &p[7]); + if (ch & 0x40) + be128_xor(r, r, &p[6]); + if (ch & 0x20) + be128_xor(r, r, &p[5]); + if (ch & 0x10) + be128_xor(r, r, &p[4]); + if (ch & 0x08) + be128_xor(r, r, &p[3]); + if (ch & 0x04) + be128_xor(r, r, &p[2]); + if (ch & 0x02) + be128_xor(r, r, &p[1]); + if (ch & 0x01) + be128_xor(r, r, &p[0]); + + if (++i >= 16) + break; + + gf128mul_x8_ble(r); + } +} +EXPORT_SYMBOL(gf128mul_ble); + + /* This version uses 64k bytes of table space. A 16 byte buffer has to be multiplied by a 16 byte key - value in GF(128). If we consider a GF(128) value in + value in GF(2^128). If we consider a GF(2^128) value in the buffer's lowest byte, we can construct a table of the 256 16 byte values that result from the 256 values of this byte. This requires 4096 bytes. But we also @@ -352,8 +416,8 @@ void gf128mul_free_64k(struct gf128mul_64k *t) int i; for (i = 0; i < 16; i++) - kfree(t->t[i]); - kfree(t); + kzfree(t->t[i]); + kzfree(t); } EXPORT_SYMBOL(gf128mul_free_64k); @@ -385,7 +449,7 @@ EXPORT_SYMBOL(gf128mul_64k_bbe); /* This version uses 4k bytes of table space. A 16 byte buffer has to be multiplied by a 16 byte key - value in GF(128). If we consider a GF(128) value in a + value in GF(2^128). If we consider a GF(2^128) value in a single byte, we can construct a table of the 256 16 byte values that result from the 256 values of this byte. This requires 4096 bytes. If we take the highest byte in @@ -443,6 +507,28 @@ out: } EXPORT_SYMBOL(gf128mul_init_4k_bbe); +struct gf128mul_4k *gf128mul_init_4k_ble(const be128 *g) +{ + struct gf128mul_4k *t; + int j, k; + + t = kzalloc(sizeof(*t), GFP_KERNEL); + if (!t) + goto out; + + t->t[1] = *g; + for (j = 1; j <= 64; j <<= 1) + gf128mul_x_ble(&t->t[j + j], &t->t[j]); + + for (j = 2; j < 256; j += j) + for (k = 1; k < j; ++k) + be128_xor(&t->t[j + k], &t->t[j], &t->t[k]); + +out: + return t; +} +EXPORT_SYMBOL(gf128mul_init_4k_ble); + void gf128mul_4k_lle(be128 *a, struct gf128mul_4k *t) { u8 *ap = (u8 *)a; @@ -473,5 +559,20 @@ void gf128mul_4k_bbe(be128 *a, struct gf128mul_4k *t) } EXPORT_SYMBOL(gf128mul_4k_bbe); +void gf128mul_4k_ble(be128 *a, struct gf128mul_4k *t) +{ + u8 *ap = (u8 *)a; + be128 r[1]; + int i = 15; + + *r = t->t[ap[15]]; + while (i--) { + gf128mul_x8_ble(r); + be128_xor(r, r, &t->t[ap[i]]); + } + *a = *r; +} +EXPORT_SYMBOL(gf128mul_4k_ble); + MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Functions for multiplying elements of GF(2^128)"); |