diff --git a/src/buffer.c b/src/buffer.c
index 3c7f6ccb4..b083768e3 100644
--- a/src/buffer.c
+++ b/src/buffer.c
@@ -136,30 +136,39 @@ int buffer_insert_line2(struct buffer *b, char *pos, const char *str, int len)
 	return delta;
 }
 
-/* This function realigns input data in a possibly wrapping buffer so that it
- * becomes contiguous and starts at the beginning of the buffer area. The
- * function may only be used when the buffer's output is empty.
+/* This function realigns a possibly wrapping buffer so that the input part is
+ * contiguous and starts at the beginning of the buffer and the output part
+ * ends at the end of the buffer. This provides the best conditions since it
+ * allows the largest inputs to be processed at once and ensures that once the
+ * output data leaves, the whole buffer is available at once.
  */
 void buffer_slow_realign(struct buffer *buf)
 {
-	/* two possible cases :
-	 *   - the buffer is in one contiguous block, we move it in-place
-	 *   - the buffer is in two blocks, we move it via the swap_buffer
-	 */
-	if (buf->i) {
-		int block1 = buf->i;
-		int block2 = 0;
-		if (buf->p + buf->i > buf->data + buf->size) {
-			/* non-contiguous block */
-			block1 = buf->data + buf->size - buf->p;
-			block2 = buf->p + buf->i - (buf->data + buf->size);
-		}
-		if (block2)
-			memcpy(swap_buffer, buf->data, block2);
-		memmove(buf->data, buf->p, block1);
-		if (block2)
-			memcpy(buf->data + block1, swap_buffer, block2);
+	int block1 = buf->o;
+	int block2 = 0;
+
+	/* process output data in two steps to cover wrapping */
+	if (block1 > buf->p - buf->data) {
+		block2 = buf->p - buf->data;
+		block1 -= block2;
 	}
+	memcpy(swap_buffer + buf->size - buf->o, bo_ptr(buf), block1);
+	memcpy(swap_buffer + buf->size - block2, buf->data, block2);
+
+	/* process input data in two steps to cover wrapping */
+	block1 = buf->i;
+	block2 = 0;
+
+	if (block1 > buf->data + buf->size - buf->p) {
+		block1 = buf->data + buf->size - buf->p;
+		block2 = buf->i - block1;
+	}
+	memcpy(swap_buffer, bi_ptr(buf), block1);
+	memcpy(swap_buffer + block1, buf->data, block2);
+
+	/* reinject changes into the buffer */
+	memcpy(buf->data, swap_buffer, buf->i);
+	memcpy(buf->data + buf->size - buf->o, swap_buffer + buf->size - buf->o, buf->o);
 
 	buf->p = buf->data;
 }