summaryrefslogtreecommitdiffstats
path: root/crypto/openssl/crypto/bn/bn_exp.c
diff options
context:
space:
mode:
Diffstat (limited to 'crypto/openssl/crypto/bn/bn_exp.c')
-rw-r--r--crypto/openssl/crypto/bn/bn_exp.c103
1 files changed, 71 insertions, 32 deletions
diff --git a/crypto/openssl/crypto/bn/bn_exp.c b/crypto/openssl/crypto/bn/bn_exp.c
index 6d30d1e..1670f01 100644
--- a/crypto/openssl/crypto/bn/bn_exp.c
+++ b/crypto/openssl/crypto/bn/bn_exp.c
@@ -110,6 +110,7 @@
*/
#include "cryptlib.h"
+#include "constant_time_locl.h"
#include "bn_lcl.h"
#include <stdlib.h>
@@ -606,15 +607,17 @@ static BN_ULONG bn_get_bits(const BIGNUM *a, int bitpos)
static int MOD_EXP_CTIME_COPY_TO_PREBUF(const BIGNUM *b, int top,
unsigned char *buf, int idx,
- int width)
+ int window)
{
- size_t i, j;
+ int i, j;
+ int width = 1 << window;
+ BN_ULONG *table = (BN_ULONG *)buf;
if (top > b->top)
top = b->top; /* this works because 'buf' is explicitly
* zeroed */
- for (i = 0, j = idx; i < top * sizeof b->d[0]; i++, j += width) {
- buf[j] = ((unsigned char *)b->d)[i];
+ for (i = 0, j = idx; i < top; i++, j += width) {
+ table[j] = b->d[i];
}
return 1;
@@ -622,15 +625,51 @@ static int MOD_EXP_CTIME_COPY_TO_PREBUF(const BIGNUM *b, int top,
static int MOD_EXP_CTIME_COPY_FROM_PREBUF(BIGNUM *b, int top,
unsigned char *buf, int idx,
- int width)
+ int window)
{
- size_t i, j;
+ int i, j;
+ int width = 1 << window;
+ volatile BN_ULONG *table = (volatile BN_ULONG *)buf;
if (bn_wexpand(b, top) == NULL)
return 0;
- for (i = 0, j = idx; i < top * sizeof b->d[0]; i++, j += width) {
- ((unsigned char *)b->d)[i] = buf[j];
+ if (window <= 3) {
+ for (i = 0; i < top; i++, table += width) {
+ BN_ULONG acc = 0;
+
+ for (j = 0; j < width; j++) {
+ acc |= table[j] &
+ ((BN_ULONG)0 - (constant_time_eq_int(j,idx)&1));
+ }
+
+ b->d[i] = acc;
+ }
+ } else {
+ int xstride = 1 << (window - 2);
+ BN_ULONG y0, y1, y2, y3;
+
+ i = idx >> (window - 2); /* equivalent of idx / xstride */
+ idx &= xstride - 1; /* equivalent of idx % xstride */
+
+ y0 = (BN_ULONG)0 - (constant_time_eq_int(i,0)&1);
+ y1 = (BN_ULONG)0 - (constant_time_eq_int(i,1)&1);
+ y2 = (BN_ULONG)0 - (constant_time_eq_int(i,2)&1);
+ y3 = (BN_ULONG)0 - (constant_time_eq_int(i,3)&1);
+
+ for (i = 0; i < top; i++, table += width) {
+ BN_ULONG acc = 0;
+
+ for (j = 0; j < xstride; j++) {
+ acc |= ( (table[j + 0 * xstride] & y0) |
+ (table[j + 1 * xstride] & y1) |
+ (table[j + 2 * xstride] & y2) |
+ (table[j + 3 * xstride] & y3) )
+ & ((BN_ULONG)0 - (constant_time_eq_int(j,idx)&1));
+ }
+
+ b->d[i] = acc;
+ }
}
b->top = top;
@@ -749,8 +788,8 @@ int BN_mod_exp_mont_consttime(BIGNUM *rr, const BIGNUM *a, const BIGNUM *p,
if (window >= 5) {
window = 5; /* ~5% improvement for RSA2048 sign, and even
* for RSA4096 */
- if ((top & 7) == 0)
- powerbufLen += 2 * top * sizeof(m->d[0]);
+ /* reserve space for mont->N.d[] copy */
+ powerbufLen += top * sizeof(mont->N.d[0]);
}
#endif
(void)0;
@@ -971,7 +1010,7 @@ int BN_mod_exp_mont_consttime(BIGNUM *rr, const BIGNUM *a, const BIGNUM *p,
const BN_ULONG *not_used, const BN_ULONG *np,
const BN_ULONG *n0, int num);
- BN_ULONG *np = mont->N.d, *n0 = mont->n0, *np2;
+ BN_ULONG *n0 = mont->n0, *np;
/*
* BN_to_montgomery can contaminate words above .top [in
@@ -982,11 +1021,11 @@ int BN_mod_exp_mont_consttime(BIGNUM *rr, const BIGNUM *a, const BIGNUM *p,
for (i = tmp.top; i < top; i++)
tmp.d[i] = 0;
- if (top & 7)
- np2 = np;
- else
- for (np2 = am.d + top, i = 0; i < top; i++)
- np2[2 * i] = np[i];
+ /*
+ * copy mont->N.d[] to improve cache locality
+ */
+ for (np = am.d + top, i = 0; i < top; i++)
+ np[i] = mont->N.d[i];
bn_scatter5(tmp.d, top, powerbuf, 0);
bn_scatter5(am.d, am.top, powerbuf, 1);
@@ -996,7 +1035,7 @@ int BN_mod_exp_mont_consttime(BIGNUM *rr, const BIGNUM *a, const BIGNUM *p,
# if 0
for (i = 3; i < 32; i++) {
/* Calculate a^i = a^(i-1) * a */
- bn_mul_mont_gather5(tmp.d, am.d, powerbuf, np2, n0, top, i - 1);
+ bn_mul_mont_gather5(tmp.d, am.d, powerbuf, np, n0, top, i - 1);
bn_scatter5(tmp.d, top, powerbuf, i);
}
# else
@@ -1007,7 +1046,7 @@ int BN_mod_exp_mont_consttime(BIGNUM *rr, const BIGNUM *a, const BIGNUM *p,
}
for (i = 3; i < 8; i += 2) {
int j;
- bn_mul_mont_gather5(tmp.d, am.d, powerbuf, np2, n0, top, i - 1);
+ bn_mul_mont_gather5(tmp.d, am.d, powerbuf, np, n0, top, i - 1);
bn_scatter5(tmp.d, top, powerbuf, i);
for (j = 2 * i; j < 32; j *= 2) {
bn_mul_mont(tmp.d, tmp.d, tmp.d, np, n0, top);
@@ -1015,13 +1054,13 @@ int BN_mod_exp_mont_consttime(BIGNUM *rr, const BIGNUM *a, const BIGNUM *p,
}
}
for (; i < 16; i += 2) {
- bn_mul_mont_gather5(tmp.d, am.d, powerbuf, np2, n0, top, i - 1);
+ bn_mul_mont_gather5(tmp.d, am.d, powerbuf, np, n0, top, i - 1);
bn_scatter5(tmp.d, top, powerbuf, i);
bn_mul_mont(tmp.d, tmp.d, tmp.d, np, n0, top);
bn_scatter5(tmp.d, top, powerbuf, 2 * i);
}
for (; i < 32; i += 2) {
- bn_mul_mont_gather5(tmp.d, am.d, powerbuf, np2, n0, top, i - 1);
+ bn_mul_mont_gather5(tmp.d, am.d, powerbuf, np, n0, top, i - 1);
bn_scatter5(tmp.d, top, powerbuf, i);
}
# endif
@@ -1050,11 +1089,11 @@ int BN_mod_exp_mont_consttime(BIGNUM *rr, const BIGNUM *a, const BIGNUM *p,
while (bits >= 0) {
wvalue = bn_get_bits5(p->d, bits - 4);
bits -= 5;
- bn_power5(tmp.d, tmp.d, powerbuf, np2, n0, top, wvalue);
+ bn_power5(tmp.d, tmp.d, powerbuf, np, n0, top, wvalue);
}
}
- ret = bn_from_montgomery(tmp.d, tmp.d, NULL, np2, n0, top);
+ ret = bn_from_montgomery(tmp.d, tmp.d, NULL, np, n0, top);
tmp.top = top;
bn_correct_top(&tmp);
if (ret) {
@@ -1065,9 +1104,9 @@ int BN_mod_exp_mont_consttime(BIGNUM *rr, const BIGNUM *a, const BIGNUM *p,
} else
#endif
{
- if (!MOD_EXP_CTIME_COPY_TO_PREBUF(&tmp, top, powerbuf, 0, numPowers))
+ if (!MOD_EXP_CTIME_COPY_TO_PREBUF(&tmp, top, powerbuf, 0, window))
goto err;
- if (!MOD_EXP_CTIME_COPY_TO_PREBUF(&am, top, powerbuf, 1, numPowers))
+ if (!MOD_EXP_CTIME_COPY_TO_PREBUF(&am, top, powerbuf, 1, window))
goto err;
/*
@@ -1079,15 +1118,15 @@ int BN_mod_exp_mont_consttime(BIGNUM *rr, const BIGNUM *a, const BIGNUM *p,
if (window > 1) {
if (!BN_mod_mul_montgomery(&tmp, &am, &am, mont, ctx))
goto err;
- if (!MOD_EXP_CTIME_COPY_TO_PREBUF
- (&tmp, top, powerbuf, 2, numPowers))
+ if (!MOD_EXP_CTIME_COPY_TO_PREBUF(&tmp, top, powerbuf, 2,
+ window))
goto err;
for (i = 3; i < numPowers; i++) {
/* Calculate a^i = a^(i-1) * a */
if (!BN_mod_mul_montgomery(&tmp, &am, &tmp, mont, ctx))
goto err;
- if (!MOD_EXP_CTIME_COPY_TO_PREBUF
- (&tmp, top, powerbuf, i, numPowers))
+ if (!MOD_EXP_CTIME_COPY_TO_PREBUF(&tmp, top, powerbuf, i,
+ window))
goto err;
}
}
@@ -1095,8 +1134,8 @@ int BN_mod_exp_mont_consttime(BIGNUM *rr, const BIGNUM *a, const BIGNUM *p,
bits--;
for (wvalue = 0, i = bits % window; i >= 0; i--, bits--)
wvalue = (wvalue << 1) + BN_is_bit_set(p, bits);
- if (!MOD_EXP_CTIME_COPY_FROM_PREBUF
- (&tmp, top, powerbuf, wvalue, numPowers))
+ if (!MOD_EXP_CTIME_COPY_FROM_PREBUF(&tmp, top, powerbuf, wvalue,
+ window))
goto err;
/*
@@ -1116,8 +1155,8 @@ int BN_mod_exp_mont_consttime(BIGNUM *rr, const BIGNUM *a, const BIGNUM *p,
/*
* Fetch the appropriate pre-computed value from the pre-buf
*/
- if (!MOD_EXP_CTIME_COPY_FROM_PREBUF
- (&am, top, powerbuf, wvalue, numPowers))
+ if (!MOD_EXP_CTIME_COPY_FROM_PREBUF(&am, top, powerbuf, wvalue,
+ window))
goto err;
/* Multiply the result into the intermediate result */
OpenPOWER on IntegriCloud