pack-bitmap: implement BLOB_NONE filtering

We can easily support BLOB_NONE filters with bitmaps. Since we know the
types of all of the objects, we just need to clear the result bits of
any blobs.

Note two subtleties in the implementation (which I also called out in
comments):

  - we have to include any blobs that were specifically asked for (and
    not reached through graph traversal) to match the non-bitmap version

  - we have to handle in-pack and "ext_index" objects separately.
    Arguably prepare_bitmap_walk() could be adding these ext_index
    objects to the type bitmaps. But it doesn't for now, so let's match
    the rest of the bitmap code here (it probably wouldn't be an
    efficiency improvement to do so since the cost of extending those
    bitmaps is about the same as our loop here, but it might make the
    code a bit simpler).

Here are perf results for the new test on git.git:

  Test                                    HEAD^             HEAD
  --------------------------------------------------------------------------------
  5310.9: rev-list count with blob:none   1.67(1.62+0.05)   0.22(0.21+0.02) -86.8%

Signed-off-by: Jeff King <peff@peff.net>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

1 files changed, 74 insertions, 0 deletions

diff --git a/pack-bitmap.c b/pack-bitmap.c
index 48c8694..dcf8a9a 100644
--- a/pack-bitmap.c
+++ b/pack-bitmap.c
@@ -712,6 +712,73 @@ static int in_bitmapped_pack(struct bitmap_index *bitmap_git,
 	return 0;
 }
 
+static struct bitmap *find_tip_blobs(struct bitmap_index *bitmap_git,
+				     struct object_list *tip_objects)
+{
+	struct bitmap *result = bitmap_new();
+	struct object_list *p;
+
+	for (p = tip_objects; p; p = p->next) {
+		int pos;
+
+		if (p->item->type != OBJ_BLOB)
+			continue;
+
+		pos = bitmap_position(bitmap_git, &p->item->oid);
+		if (pos < 0)
+			continue;
+
+		bitmap_set(result, pos);
+	}
+
+	return result;
+}
+
+static void filter_bitmap_blob_none(struct bitmap_index *bitmap_git,
+				    struct object_list *tip_objects,
+				    struct bitmap *to_filter)
+{
+	struct eindex *eindex = &bitmap_git->ext_index;
+	struct bitmap *tips;
+	struct ewah_iterator it;
+	eword_t mask;
+	uint32_t i;
+
+	/*
+	 * The non-bitmap version of this filter never removes
+	 * blobs which the other side specifically asked for,
+	 * so we must match that behavior.
+	 */
+	tips = find_tip_blobs(bitmap_git, tip_objects);
+
+	/*
+	 * We can use the blob type-bitmap to work in whole words
+	 * for the objects that are actually in the bitmapped packfile.
+	 */
+	for (i = 0, init_type_iterator(&it, bitmap_git, OBJ_BLOB);
+	     i < to_filter->word_alloc && ewah_iterator_next(&mask, &it);
+	     i++) {
+		if (i < tips->word_alloc)
+			mask &= ~tips->words[i];
+		to_filter->words[i] &= ~mask;
+	}
+
+	/*
+	 * Clear any blobs that weren't in the packfile (and so would not have
+	 * been caught by the loop above. We'll have to check them
+	 * individually.
+	 */
+	for (i = 0; i < eindex->count; i++) {
+		uint32_t pos = i + bitmap_git->pack->num_objects;
+		if (eindex->objects[i]->type == OBJ_BLOB &&
+		    bitmap_get(to_filter, pos) &&
+		    !bitmap_get(tips, pos))
+			bitmap_unset(to_filter, pos);
+	}
+
+	bitmap_free(tips);
+}
+
 static int filter_bitmap(struct bitmap_index *bitmap_git,
 			 struct object_list *tip_objects,
 			 struct bitmap *to_filter,
@@ -720,6 +787,13 @@ static int filter_bitmap(struct bitmap_index *bitmap_git,
 	if (!filter || filter->choice == LOFC_DISABLED)
 		return 0;
 
+	if (filter->choice == LOFC_BLOB_NONE) {
+		if (bitmap_git)
+			filter_bitmap_blob_none(bitmap_git, tip_objects,
+						to_filter);
+		return 0;
+	}
+
 	/* filter choice not handled */
 	return -1;
 }