1 files changed, 99 insertions, 3 deletions

diff --git a/builtin/backfill.c b/builtin/backfill.c
index 58d0866c0f..0eca175a7f 100644
--- a/builtin/backfill.c
+++ b/builtin/backfill.c
@@ -1,16 +1,112 @@
 #include "builtin.h"
+#include "git-compat-util.h"
 #include "config.h"
 #include "parse-options.h"
 #include "repository.h"
+#include "commit.h"
+#include "hex.h"
+#include "tree.h"
+#include "tree-walk.h"
 #include "object.h"
+#include "object-store-ll.h"
+#include "oid-array.h"
+#include "oidset.h"
+#include "promisor-remote.h"
+#include "strmap.h"
+#include "string-list.h"
+#include "revision.h"
+#include "trace2.h"
+#include "progress.h"
+#include "packfile.h"
+#include "path-walk.h"
 
 static const char * const builtin_backfill_usage[] = {
 	N_("git backfill [<options>]"),
 	NULL
 };
 
+struct backfill_context {
+	struct repository *repo;
+	struct oid_array current_batch;
+	size_t min_batch_size;
+};
+
+static void backfill_context_clear(struct backfill_context *ctx)
+{
+	oid_array_clear(&ctx->current_batch);
+}
+
+static void download_batch(struct backfill_context *ctx)
+{
+	promisor_remote_get_direct(ctx->repo,
+				   ctx->current_batch.oid,
+				   ctx->current_batch.nr);
+	oid_array_clear(&ctx->current_batch);
+
+	/*
+	 * We likely have a new packfile. Add it to the packed list to
+	 * avoid possible duplicate downloads of the same objects.
+	 */
+	reprepare_packed_git(ctx->repo);
+}
+
+static int fill_missing_blobs(const char *path UNUSED,
+			      struct oid_array *list,
+			      enum object_type type,
+			      void *data)
+{
+	struct backfill_context *ctx = data;
+
+	if (type != OBJ_BLOB)
+		return 0;
+
+	for (size_t i = 0; i < list->nr; i++) {
+		if (!has_object(ctx->repo, &list->oid[i],
+				OBJECT_INFO_FOR_PREFETCH))
+			oid_array_append(&ctx->current_batch, &list->oid[i]);
+	}
+
+	if (ctx->current_batch.nr >= ctx->min_batch_size)
+		download_batch(ctx);
+
+	return 0;
+}
+
+static int do_backfill(struct backfill_context *ctx)
+{
+	struct rev_info revs;
+	struct path_walk_info info = PATH_WALK_INFO_INIT;
+	int ret;
+
+	repo_init_revisions(ctx->repo, &revs, "");
+	handle_revision_arg("HEAD", &revs, 0, 0);
+
+	info.blobs = 1;
+	info.tags = info.commits = info.trees = 0;
+
+	info.revs = &revs;
+	info.path_fn = fill_missing_blobs;
+	info.path_fn_data = ctx;
+
+	ret = walk_objects_by_path(&info);
+
+	/* Download the objects that did not fill a batch. */
+	if (!ret)
+		download_batch(ctx);
+
+	path_walk_info_clear(&info);
+	release_revisions(&revs);
+	return ret;
+}
+
 int cmd_backfill(int argc, const char **argv, const char *prefix, struct repository *repo)
 {
+	int result;
+	struct backfill_context ctx = {
+		.repo = repo,
+		.current_batch = OID_ARRAY_INIT,
+		.min_batch_size = 50000,
+	};
 	struct option options[] = {
 		OPT_END(),
 	};
@@ -22,7 +118,7 @@ int cmd_backfill(int argc, const char **argv, const char *prefix, struct reposit
 
 	repo_config(repo, git_default_config, NULL);
 
-	die(_("not implemented"));
-
-	return 0;
+	result = do_backfill(&ctx);
+	backfill_context_clear(&ctx);
+	return result;
 }