Implement a micro-optimization which has been on our TODO list for ages:

remove "or ebp,-1" when not needed

src/p_tmt.cpp

@@ -87,6 +87,8 @@ void PackTmt::buildLoader(const Filter *ft)
     // prepare loader
     initLoader(stub_i386_dos32_tmt, sizeof(stub_i386_dos32_tmt));
     addLoader("IDENTSTR,TMTMAIN1",
+              ph.first_offset_found == 1 ? "TMTMAIN1A" : "",
+              "TMTMAIN1B",
               ft->id ? "TMTCALT1" : "",
               "TMTMAIN2,UPX1HEAD,TMTCUTPO",
               NULL);