reftable: prevent 'update_index' changes after adding records

The function `reftable_writer_set_limits()` allows updating the
'min_update_index' and 'max_update_index' of a reftable writer. These
values are written to both the writer's header and footer.

Since the header is written during the first block write, any subsequent
changes to the update index would create a mismatch between the header
and footer values. The footer would contain the newer values while the
header retained the original ones.

To fix this bug, prevent callers from updating these values after any
record is written. To do this, modify the function to return an error
whenever the limits are modified after any record adds. Check for record
adds within `reftable_writer_set_limits()` by checking the `last_key`
variable, which is set whenever a new record is added.

Modify all callers of the function to anticipate a return type and
handle it accordingly.

Helped-by: Patrick Steinhardt <ps@pks.im>
Signed-off-by: Karthik Nayak <karthik.188@gmail.com>
Signed-off-by: Junio C Hamano <gitster@pobox.com>

Author: KarthikNayak

Diff for: refs/reftable-backend.c

@@ -1444,7 +1444,9 @@ static int write_transaction_table(struct reftable_writer *writer, void *cb_data
 	 * multiple entries. Each entry will contain a different update_index,
 	 * so set the limits accordingly.
 	 */
-	reftable_writer_set_limits(writer, ts, ts + arg->max_index);
+	ret = reftable_writer_set_limits(writer, ts, ts + arg->max_index);
+	if (ret < 0)
+		goto done;
 
 	for (i = 0; i < arg->updates_nr; i++) {
 		struct reftable_transaction_update *tx_update = &arg->updates[i];
@@ -1769,7 +1771,9 @@ static int write_copy_table(struct reftable_writer *writer, void *cb_data)
 	deletion_ts = creation_ts = reftable_stack_next_update_index(arg->be->stack);
 	if (arg->delete_old)
 		creation_ts++;
-	reftable_writer_set_limits(writer, deletion_ts, creation_ts);
+	ret = reftable_writer_set_limits(writer, deletion_ts, creation_ts);
+	if (ret < 0)
+		goto done;
 
 	/*
 	 * Add the new reference. If this is a rename then we also delete the
@@ -2301,7 +2305,9 @@ static int write_reflog_existence_table(struct reftable_writer *writer,
 	if (ret <= 0)
 		goto done;
 
-	reftable_writer_set_limits(writer, ts, ts);
+	ret = reftable_writer_set_limits(writer, ts, ts);
+	if (ret < 0)
+		goto done;
 
 	/*
 	 * The existence entry has both old and new object ID set to the
@@ -2360,7 +2366,9 @@ static int write_reflog_delete_table(struct reftable_writer *writer, void *cb_da
 	uint64_t ts = reftable_stack_next_update_index(arg->stack);
 	int ret;
 
-	reftable_writer_set_limits(writer, ts, ts);
+	ret = reftable_writer_set_limits(writer, ts, ts);
+	if (ret < 0)
+		goto out;
 
 	ret = reftable_stack_init_log_iterator(arg->stack, &it);
 	if (ret < 0)
@@ -2437,7 +2445,9 @@ static int write_reflog_expiry_table(struct reftable_writer *writer, void *cb_da
 		if (arg->records[i].value_type == REFTABLE_LOG_UPDATE)
 			live_records++;
 
-	reftable_writer_set_limits(writer, ts, ts);
+	ret = reftable_writer_set_limits(writer, ts, ts);
+	if (ret < 0)
+		return ret;
 
 	if (!is_null_oid(&arg->update_oid)) {
 		struct reftable_ref_record ref = {0};

Diff for: reftable/reftable-error.h

@@ -30,6 +30,7 @@ enum reftable_error {
 
 	/* Misuse of the API:
 	 *  - on writing a record with NULL refname.
+	 *  - on writing a record before setting the writer limits.
 	 *  - on writing a reftable_ref_record outside the table limits
 	 *  - on writing a ref or log record before the stack's
 	 * next_update_inde*x

Diff for: reftable/reftable-writer.h

@@ -124,17 +124,21 @@ int reftable_writer_new(struct reftable_writer **out,
 			int (*flush_func)(void *),
 			void *writer_arg, const struct reftable_write_options *opts);
 
-/* Set the range of update indices for the records we will add. When writing a
-   table into a stack, the min should be at least
-   reftable_stack_next_update_index(), or REFTABLE_API_ERROR is returned.
-
-   For transactional updates to a stack, typically min==max, and the
-   update_index can be obtained by inspeciting the stack. When converting an
-   existing ref database into a single reftable, this would be a range of
-   update-index timestamps.
+/*
+ * Set the range of update indices for the records we will add. When writing a
+ * table into a stack, the min should be at least
+ * reftable_stack_next_update_index(), or REFTABLE_API_ERROR is returned.
+ *
+ * For transactional updates to a stack, typically min==max, and the
+ * update_index can be obtained by inspeciting the stack. When converting an
+ * existing ref database into a single reftable, this would be a range of
+ * update-index timestamps.
+ *
+ * The function should be called before adding any records to the writer. If not
+ * it will fail with REFTABLE_API_ERROR.
  */
-void reftable_writer_set_limits(struct reftable_writer *w, uint64_t min,
-				uint64_t max);
+int reftable_writer_set_limits(struct reftable_writer *w, uint64_t min,
+			       uint64_t max);
 
 /*
   Add a reftable_ref_record. The record should have names that come after

Diff for: reftable/stack.c

@@ -1058,8 +1058,10 @@ static int stack_write_compact(struct reftable_stack *st,
 
 	for (size_t i = first; i <= last; i++)
 		st->stats.bytes += st->readers[i]->size;
-	reftable_writer_set_limits(wr, st->readers[first]->min_update_index,
-				   st->readers[last]->max_update_index);
+	err = reftable_writer_set_limits(wr, st->readers[first]->min_update_index,
+					 st->readers[last]->max_update_index);
+	if (err < 0)
+		goto done;
 
 	err = reftable_merged_table_new(&mt, st->readers + first, subtabs_len,
 					st->opts.hash_id);

Diff for: reftable/writer.c

@@ -179,11 +179,20 @@ int reftable_writer_new(struct reftable_writer **out,
 	return 0;
 }
 
-void reftable_writer_set_limits(struct reftable_writer *w, uint64_t min,
-				uint64_t max)
+int reftable_writer_set_limits(struct reftable_writer *w, uint64_t min,
+			       uint64_t max)
 {
+	/*
+	 * The limits should be set before any records are added to the writer.
+	 * Check if any records were added by checking if `last_key` was set.
+	 */
+	if (w->last_key.len)
+		return REFTABLE_API_ERROR;
+
 	w->min_update_index = min;
 	w->max_update_index = max;
+
+	return 0;
 }
 
 static void writer_release(struct reftable_writer *w)

Diff for: t/unit-tests/t-reftable-stack.c

@@ -103,7 +103,8 @@ static void t_read_file(void)
 static int write_test_ref(struct reftable_writer *wr, void *arg)
 {
 	struct reftable_ref_record *ref = arg;
-	reftable_writer_set_limits(wr, ref->update_index, ref->update_index);
+	check(!reftable_writer_set_limits(wr, ref->update_index,
+					  ref->update_index));
 	return reftable_writer_add_ref(wr, ref);
 }
 
@@ -143,7 +144,8 @@ static int write_test_log(struct reftable_writer *wr, void *arg)
 {
 	struct write_log_arg *wla = arg;
 
-	reftable_writer_set_limits(wr, wla->update_index, wla->update_index);
+	check(!reftable_writer_set_limits(wr, wla->update_index,
+					  wla->update_index));
 	return reftable_writer_add_log(wr, wla->log);
 }
 
@@ -961,7 +963,7 @@ static void t_reflog_expire(void)
 
 static int write_nothing(struct reftable_writer *wr, void *arg UNUSED)
 {
-	reftable_writer_set_limits(wr, 1, 1);
+	check(!reftable_writer_set_limits(wr, 1, 1));
 	return 0;
 }