Improves bsdiff performance by preventing excessive iterations when processing similar data blocks (#2693)

* Port bsdiff optimizations for diffing large blocks that only differ by less than 8 bytes

* Retrigger CI

* Bump the minor version for major 2, 3, and 4

* Comments for ChromiumOS ported commits

Author: wfairclough

Autoupdate/SUBinaryDeltaCommon.m

@@ -113,11 +113,11 @@ uint16_t latestMinorVersionForMajorVersion(SUBinaryDeltaMajorVersion majorVersio
         case SUBinaryDeltaMajorVersion1:
             return 2;
         case SUBinaryDeltaMajorVersion2:
-            return 4;
+            return 5;
         case SUBinaryDeltaMajorVersion3:
-            return 1;
+            return 2;
         case SUBinaryDeltaMajorVersion4:
-            return 0;
+            return 1;
     }
     return 0;
 }

Vendor/bsdiff/bsdiff.c

@@ -84,7 +84,9 @@ static off_t search(off_t *I, u_char *old, off_t oldsize,
     }
 
     x = st + (en - st)/2;
-    if (memcmp(old + I[x], new, (size_t)(MIN(oldsize - I[x], newsize))) < 0) {
+    /* Modification ported from ChromiumOS project:
+     * https://chromium.googlesource.com/chromiumos/third_party/bsdiff/+/58146f74abd6b1b69693943195f37f4ac6a6acef%5E%21/#F0 */
+    if (memcmp(old + I[x], new, (size_t)(MIN(oldsize - I[x], newsize))) <= 0) {
         return search(I, old, oldsize, new, newsize, x, en, pos);
     } else {
         return search(I, old, oldsize, new, newsize, st, x, pos);
@@ -212,8 +214,18 @@ int bsdiff(int argc, char *argv[])
     lastoffset = 0;
     while (scan < newsize) {
         oldscore = 0;
-
+        /* Modification ported from ChromiumOS project:
+         * https://chromium.googlesource.com/chromiumos/third_party/bsdiff/+/a055996c743add7a9558839276fd1e4994d16bd3%5E%21/#F0 */
+        /* If we come across a large block of data that only differs
+         * by less than 8 bytes, this loop will take a long time to
+         * go past that block of data. We need to track the number of
+         * times we're stuck in the block and break out of it. */
+        int num_less_than_eight = 0;
+        off_t prev_len, prev_oldscore, prev_pos;
         for (scsc = scan += len; scan < newsize; scan++) {
+            prev_len = len;
+            prev_oldscore = oldscore;
+            prev_pos = pos;
             /* 'oldscore' is the number of characters that match between the
              * substrings 'old[lastoffset + scan:lastoffset + scsc]' and
              * 'new[scan:scsc]'. */
@@ -240,6 +252,19 @@ int bsdiff(int argc, char *argv[])
             if ((scan + lastoffset < oldsize) &&
                 (old[scan + lastoffset] == new[scan]))
                 oldscore--;
+
+            /* Modification ported from ChromiumOS project:
+             * https://chromium.googlesource.com/chromiumos/third_party/bsdiff/+/426e4aa1cbeb3c8a73002047d7a796ca8e5e17d4%5E%21/#F0 */
+            const off_t fuzz = 8;
+            if (prev_len - fuzz <= len && len <= prev_len &&
+                prev_oldscore - fuzz <= oldscore &&
+                oldscore <= prev_oldscore &&
+                prev_pos <= pos && pos <= prev_pos + fuzz &&
+                oldscore <= len && len <= oldscore + fuzz)
+                ++num_less_than_eight;
+            else
+                num_less_than_eight=0;
+            if (num_less_than_eight > 100) break;
         }
 
         /* Skip this section if we found an exact match that would be