bn/bn_exp.c: constant-time MOD_EXP_CTIME_COPY_FROM_PREBUF.

Performance penalty varies from platform to platform, and even
key length. For rsa2048 sign it was observed to reach almost 10%.

CVE-2016-0702

Reviewed-by: Richard Levitte <levitte@openssl.org>
Reviewed-by: Rich Salz <rsalz@openssl.org>
(cherry picked from master)

Resolved conflicts:
	crypto/bn/bn_exp.c

diff --git a/crypto/bn/bn_exp.c b/crypto/bn/bn_exp.c
index 6d30d1e0fff56e4e90238feb2ecc75328a7357db..c3d575fe77a788d7d2dba44106c1222664745c90 100644 (file)
--- a/crypto/bn/bn_exp.c
+++ b/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;
@@ -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 */