code review 7891047: cmd/ld: emit TLS relocations during external linking

src/cmd/dist/buildruntime.c

 // Copyright 2012 The Go Authors.  All rights reserved.
 // Use of this source code is governed by a BSD-style
 // license that can be found in the LICENSE file.
 
 #include "a.h"
 
 /*
  * Helpers for building pkg/runtime.
  */
 
@@ skipping 115 matching lines @@
                 "// register and then use -8(%reg) and -4(%reg).  This kind\n"
                 "// of addressing is correct even when not running Xen.\n"
                 "//\n"
                 "// 8l can rewrite MOVL 0(GS), CX into the appropriate pair\n"
                 "// of mov instructions, using CX as the intermediate register\n"
                 "// (safe because CX is about to be written to anyway).\n"
                 "// But 8l cannot handle other instructions, like storing into 0(GS),\n"
                 "// which is where these macros come into play.\n"
                 "// get_tls sets up the temporary and then g and r use it.\n"
                 "//\n"
-                "// The final wrinkle is that get_tls needs to read from %gs:0,\n"
+                "// Another wrinkle is that get_tls needs to read from %gs:0,\n"
                 "// but in 8l input it's called 8(GS), because 8l is going to\n"
                 "// subtract 8 from all the offsets, as described above.\n"
+                "//\n"
+                "// The final wrinkle is that when generating an ELF .o file for\n"
+                "// external linking mode, we need to be able to relocate the\n"
+                "// -8(r) and -4(r) instructions. Tag them with an extra (GS*1)\n"
+                "// that is ignored by the linker except for that identification.\n"
                 "#define        get_tls(r)      MOVL 8(GS), r\n"
-                "#define        g(r)    -8(r)\n"
-                "#define        m(r)    -4(r)\n"
+                "#define        g(r)    -8(r)(GS*1)\n"
+                "#define        m(r)    -4(r)(GS*1)\n"
         },
         {"386", "",
                 "#define        get_tls(r)\n"
                 "#define        g(r)    0(GS)\n"
                 "#define        m(r)    4(GS)\n"
         },
 ········
         {"amd64", "windows",
                 "#define        get_tls(r) MOVQ 0x28(GS), r\n"
                 "#define        g(r) 0(r)\n"
@@ skipping 221 matching lines @@
 
         bfree(&in);
         bfree(&b);
         bfree(&b1);
         bfree(&out);
         vfree(&argv);
         vfree(&lines);
         vfree(&fields);
         vfree(&seen);
 }