1 files changed, 121 insertions, 30 deletions

diff --git a/pack-revindex.c b/pack-revindex.c
index 77a0465be6..5c8376e978 100644
--- a/pack-revindex.c
+++ b/pack-revindex.c
@@ -16,11 +16,6 @@
  * get the object sha1 from the main index.
  */
 
-struct pack_revindex {
-	struct packed_git *p;
-	struct revindex_entry *revindex;
-};
-
 static struct pack_revindex *pack_revindex;
 static int pack_revindex_hashsz;
 
@@ -50,7 +45,7 @@ static void init_pack_revindex(void)
 	if (!num)
 		return;
 	pack_revindex_hashsz = num * 11;
-	pack_revindex = xcalloc(sizeof(*pack_revindex), pack_revindex_hashsz);
+	pack_revindex = xcalloc(pack_revindex_hashsz, sizeof(*pack_revindex));
 	for (p = packed_git; p; p = p->next) {
 		num = pack_revindex_ix(p);
 		num = - 1 - num;
@@ -59,11 +54,101 @@ static void init_pack_revindex(void)
 	/* revindex elements are lazily initialized */
 }
 
-static int cmp_offset(const void *a_, const void *b_)
+/*
+ * This is a least-significant-digit radix sort.
+ *
+ * It sorts each of the "n" items in "entries" by its offset field. The "max"
+ * parameter must be at least as large as the largest offset in the array,
+ * and lets us quit the sort early.
+ */
+static void sort_revindex(struct revindex_entry *entries, unsigned n, off_t max)
 {
-	const struct revindex_entry *a = a_;
-	const struct revindex_entry *b = b_;
-	return (a->offset < b->offset) ? -1 : (a->offset > b->offset) ? 1 : 0;
+	/*
+	 * We use a "digit" size of 16 bits. That keeps our memory
+	 * usage reasonable, and we can generally (for a 4G or smaller
+	 * packfile) quit after two rounds of radix-sorting.
+	 */
+#define DIGIT_SIZE (16)
+#define BUCKETS (1 << DIGIT_SIZE)
+	/*
+	 * We want to know the bucket that a[i] will go into when we are using
+	 * the digit that is N bits from the (least significant) end.
+	 */
+#define BUCKET_FOR(a, i, bits) (((a)[(i)].offset >> (bits)) & (BUCKETS-1))
+
+	/*
+	 * We need O(n) temporary storage. Rather than do an extra copy of the
+	 * partial results into "entries", we sort back and forth between the
+	 * real array and temporary storage. In each iteration of the loop, we
+	 * keep track of them with alias pointers, always sorting from "from"
+	 * to "to".
+	 */
+	struct revindex_entry *tmp = xmalloc(n * sizeof(*tmp));
+	struct revindex_entry *from = entries, *to = tmp;
+	int bits;
+	unsigned *pos = xmalloc(BUCKETS * sizeof(*pos));
+
+	/*
+	 * If (max >> bits) is zero, then we know that the radix digit we are
+	 * on (and any higher) will be zero for all entries, and our loop will
+	 * be a no-op, as everybody lands in the same zero-th bucket.
+	 */
+	for (bits = 0; max >> bits; bits += DIGIT_SIZE) {
+		struct revindex_entry *swap;
+		unsigned i;
+
+		memset(pos, 0, BUCKETS * sizeof(*pos));
+
+		/*
+		 * We want pos[i] to store the index of the last element that
+		 * will go in bucket "i" (actually one past the last element).
+		 * To do this, we first count the items that will go in each
+		 * bucket, which gives us a relative offset from the last
+		 * bucket. We can then cumulatively add the index from the
+		 * previous bucket to get the true index.
+		 */
+		for (i = 0; i < n; i++)
+			pos[BUCKET_FOR(from, i, bits)]++;
+		for (i = 1; i < BUCKETS; i++)
+			pos[i] += pos[i-1];
+
+		/*
+		 * Now we can drop the elements into their correct buckets (in
+		 * our temporary array).  We iterate the pos counter backwards
+		 * to avoid using an extra index to count up. And since we are
+		 * going backwards there, we must also go backwards through the
+		 * array itself, to keep the sort stable.
+		 *
+		 * Note that we use an unsigned iterator to make sure we can
+		 * handle 2^32-1 objects, even on a 32-bit system. But this
+		 * means we cannot use the more obvious "i >= 0" loop condition
+		 * for counting backwards, and must instead check for
+		 * wrap-around with UINT_MAX.
+		 */
+		for (i = n - 1; i != UINT_MAX; i--)
+			to[--pos[BUCKET_FOR(from, i, bits)]] = from[i];
+
+		/*
+		 * Now "to" contains the most sorted list, so we swap "from" and
+		 * "to" for the next iteration.
+		 */
+		swap = from;
+		from = to;
+		to = swap;
+	}
+
+	/*
+	 * If we ended with our data in the original array, great. If not,
+	 * we have to move it back from the temporary storage.
+	 */
+	if (from != entries)
+		memcpy(entries, tmp, n * sizeof(*entries));
+	free(tmp);
+	free(pos);
+
+#undef BUCKET_FOR
+#undef BUCKETS
+#undef DIGIT_SIZE
 }
 
 /*
@@ -72,8 +157,8 @@ static int cmp_offset(const void *a_, const void *b_)
 static void create_pack_revindex(struct pack_revindex *rix)
 {
 	struct packed_git *p = rix->p;
-	int num_ent = p->num_objects;
-	int i;
+	unsigned num_ent = p->num_objects;
+	unsigned i;
 	const char *index = p->index_data;
 
 	rix->revindex = xmalloc(sizeof(*rix->revindex) * (num_ent + 1));
@@ -108,18 +193,17 @@ static void create_pack_revindex(struct pack_revindex *rix)
 	 */
 	rix->revindex[num_ent].offset = p->pack_size - 20;
 	rix->revindex[num_ent].nr = -1;
-	qsort(rix->revindex, num_ent, sizeof(*rix->revindex), cmp_offset);
+	sort_revindex(rix->revindex, num_ent, p->pack_size);
 }
 
-struct revindex_entry *find_pack_revindex(struct packed_git *p, off_t ofs)
+struct pack_revindex *revindex_for_pack(struct packed_git *p)
 {
 	int num;
-	int lo, hi;
 	struct pack_revindex *rix;
-	struct revindex_entry *revindex;
 
 	if (!pack_revindex_hashsz)
 		init_pack_revindex();
+
 	num = pack_revindex_ix(p);
 	if (num < 0)
 		die("internal error: pack revindex fubar");
@@ -127,30 +211,37 @@ struct revindex_entry *find_pack_revindex(struct packed_git *p, off_t ofs)
 	rix = &pack_revindex[num];
 	if (!rix->revindex)
 		create_pack_revindex(rix);
-	revindex = rix->revindex;
 
-	lo = 0;
-	hi = p->num_objects + 1;
+	return rix;
+}
+
+int find_revindex_position(struct pack_revindex *pridx, off_t ofs)
+{
+	int lo = 0;
+	int hi = pridx->p->num_objects + 1;
+	struct revindex_entry *revindex = pridx->revindex;
+
 	do {
-		int mi = (lo + hi) / 2;
+		unsigned mi = lo + (hi - lo) / 2;
 		if (revindex[mi].offset == ofs) {
-			return revindex + mi;
+			return mi;
 		} else if (ofs < revindex[mi].offset)
 			hi = mi;
 		else
 			lo = mi + 1;
 	} while (lo < hi);
+
 	error("bad offset for revindex");
-	return NULL;
+	return -1;
 }
 
-void discard_revindex(void)
+struct revindex_entry *find_pack_revindex(struct packed_git *p, off_t ofs)
 {
-	if (pack_revindex_hashsz) {
-		int i;
-		for (i = 0; i < pack_revindex_hashsz; i++)
-			free(pack_revindex[i].revindex);
-		free(pack_revindex);
-		pack_revindex_hashsz = 0;
-	}
+	struct pack_revindex *pridx = revindex_for_pack(p);
+	int pos = find_revindex_position(pridx, ofs);
+
+	if (pos < 0)
+		return NULL;
+
+	return pridx->revindex + pos;
 }