midx repack: avoid integer overflow on 32 bit systems

On a 32 bit system "git multi-pack-index --repack --batch-size=120M"
failed with

    fatal: size_t overflow: 6038786 * 1289

The calculation to estimated size of the objects in the pack referenced
by the multi-pack-index uses st_mult() to multiply the pack size by the
number of referenced objects before dividing by the total number of
objects in the pack. As size_t is 32 bits on 32 bit systems this
calculation easily overflows. Fix this by using 64bit arithmetic instead.

Also fix a potential overflow when caluculating the total size of the
objects referenced by the multipack index with a batch size larger
than SIZE_MAX / 2. In that case

    total_size += estimated_size

can overflow as both total_size and estimated_size can be greater that
SIZE_MAX / 2. This is addressed by using saturating arithmetic for the
addition. Although estimated_size is of type uint64_t by the time we
reach this sum it is bounded by the batch size which is of type size_t
and so casting estimated_size to size_t does not truncate the value.

Signed-off-by: Phillip Wood <phillip.wood@dunelm.org.uk>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

diff --git a/git-compat-util.h b/git-compat-util.h
index 36b9577c8d4b3b39b02f4c9bfbea0f193026c39c..4678e21c4cb80bbf90d6ca8afcbb4206b509ee62 100644 (file)
--- a/git-compat-util.h
+++ b/git-compat-util.h
@@ -668,6 +668,22 @@ static inline int cast_size_t_to_int(size_t a)
        return (int)a;
 }
 
+static inline uint64_t u64_mult(uint64_t a, uint64_t b)
+{
+       if (unsigned_mult_overflows(a, b))
+               die("uint64_t overflow: %"PRIuMAX" * %"PRIuMAX,
+                   (uintmax_t)a, (uintmax_t)b);
+       return a * b;
+}
+
+static inline uint64_t u64_add(uint64_t a, uint64_t b)
+{
+       if (unsigned_add_overflows(a, b))
+               die("uint64_t overflow: %"PRIuMAX" + %"PRIuMAX,
+                   (uintmax_t)a, (uintmax_t)b);
+       return a + b;
+}
+
 /*
  * Limit size of IO chunks, because huge chunks only cause pain.  OS X
  * 64-bit is buggy, returning EINVAL if len >= INT_MAX; and even in

diff --git a/midx-write.c b/midx-write.c
index dd3b3070e55dfcea80e04bd969a4928f21df33a3..105014a2792266193e82b759a997f1a81de6dcb4 100644 (file)
--- a/midx-write.c
+++ b/midx-write.c
@@ -1699,19 +1699,23 @@ static void fill_included_packs_batch(struct repository *r,
        for (i = 0; total_size < batch_size && i < m->num_packs; i++) {
                int pack_int_id = pack_info[i].pack_int_id;
                struct packed_git *p = m->packs[pack_int_id];
-               size_t expected_size;
+               uint64_t expected_size;
 
                if (!want_included_pack(r, m, pack_kept_objects, pack_int_id))
                        continue;
 
-               expected_size = st_mult(p->pack_size,
-                                       pack_info[i].referenced_objects);
+               expected_size = uint64_mult(p->pack_size,
+                                           pack_info[i].referenced_objects);
                expected_size /= p->num_objects;
 
                if (expected_size >= batch_size)
                        continue;
 
-               total_size += expected_size;
+               if (unsigned_add_overflows(total_size, (size_t)expected_size))
+                       total_size = SIZE_MAX;
+               else
+                       total_size += expected_size;
+
                include_pack[pack_int_id] = 1;
        }