From 9e07fbf6411110b0f3e9b814a2e2bcac74c9eb88 Mon Sep 17 00:00:00 2001
From: Fangrui Song <i@maskray.me>
Date: Mon, 10 Feb 2025 09:21:31 -0800
Subject: [PATCH] [ELF] --package-metadata: support %[0-9a-fA-F][0-9a-fA-F]

(This application-specific option is probably not appropriate as a
linker option (.o file offers more flexibility and decouples JSON
verification from linkers). However, the option has gained some traction
in Linux distributions, with support in GNU ld, gold, and mold.)

GNU ld has supported percent-encoded bytes and extensions like
`%[comma]` since November 2024.  mold supports just percent-encoded
bytes.  To prepare for potential adoption by Ubuntu, let's support
percent-encoded bytes.

Link: https://sourceware.org/bugzilla/show_bug.cgi?id=32003
Link: https://bugs.launchpad.net/ubuntu/+source/dpkg/+bug/2071468

Pull Request: https://github.com/llvm/llvm-project/pull/126396

(cherry picked from commit 0a470a926481d370251731cb2dd897531756335f)
---
 lld/ELF/Config.h                |  2 +-
 lld/ELF/Driver.cpp              | 23 ++++++++++++++++++++++-
 lld/ELF/Options.td              |  2 +-
 lld/docs/ld.lld.1               |  4 ++++
 lld/test/ELF/package-metadata.s | 20 +++++++++++++++-----
 5 files changed, 43 insertions(+), 8 deletions(-)

diff --git a/lld/ELF/Config.h b/lld/ELF/Config.h
index c2aadb2cef520..98e52b52ea46a 100644
--- a/lld/ELF/Config.h
+++ b/lld/ELF/Config.h
@@ -407,7 +407,7 @@ struct Config {
   StringRef thinLTOJobs;
   unsigned timeTraceGranularity;
   int32_t splitStackAdjustSize;
-  StringRef packageMetadata;
+  SmallVector<uint8_t, 0> packageMetadata;
 
   // The following config options do not directly correspond to any
   // particular command line options.
diff --git a/lld/ELF/Driver.cpp b/lld/ELF/Driver.cpp
index 9d0c992c1e851..2d8a5ade2fece 100644
--- a/lld/ELF/Driver.cpp
+++ b/lld/ELF/Driver.cpp
@@ -822,6 +822,26 @@ static ICFLevel getICF(opt::InputArgList &args) {
   return ICFLevel::All;
 }
 
+static void parsePackageMetadata(Ctx &ctx, const opt::Arg &arg) {
+  unsigned c0, c1;
+  SmallVector<uint8_t, 0> decoded;
+  StringRef s = arg.getValue();
+  for (size_t i = 0, e = s.size(); i != e; ++i) {
+    if (s[i] != '%') {
+      decoded.push_back(s[i]);
+    } else if (i + 2 < e && (c1 = hexDigitValue(s[i + 1])) != -1u &&
+               (c0 = hexDigitValue(s[i + 2])) != -1u) {
+      decoded.push_back(uint8_t(c1 * 16 + c0));
+      i += 2;
+    } else {
+      ErrAlways(ctx) << arg.getSpelling() << ": invalid % escape at byte " << i
+                     << "; supports only %[0-9a-fA-F][0-9a-fA-F]";
+      return;
+    }
+  }
+  ctx.arg.packageMetadata = std::move(decoded);
+}
+
 static StripPolicy getStrip(Ctx &ctx, opt::InputArgList &args) {
   if (args.hasArg(OPT_relocatable))
     return StripPolicy::None;
@@ -1383,7 +1403,8 @@ static void readConfigs(Ctx &ctx, opt::InputArgList &args) {
   ctx.arg.optimize = args::getInteger(args, OPT_O, 1);
   ctx.arg.orphanHandling = getOrphanHandling(ctx, args);
   ctx.arg.outputFile = args.getLastArgValue(OPT_o);
-  ctx.arg.packageMetadata = args.getLastArgValue(OPT_package_metadata);
+  if (auto *arg = args.getLastArg(OPT_package_metadata))
+    parsePackageMetadata(ctx, *arg);
   ctx.arg.pie = args.hasFlag(OPT_pie, OPT_no_pie, false);
   ctx.arg.printIcfSections =
       args.hasFlag(OPT_print_icf_sections, OPT_no_print_icf_sections, false);
diff --git a/lld/ELF/Options.td b/lld/ELF/Options.td
index c31875305952f..d9998176d0dd4 100644
--- a/lld/ELF/Options.td
+++ b/lld/ELF/Options.td
@@ -565,7 +565,7 @@ def z: JoinedOrSeparate<["-"], "z">, MetaVarName<"<option>">,
 def visual_studio_diagnostics_format : FF<"vs-diagnostics">,
 HelpText<"Format diagnostics for Visual Studio compatibility">;
 
-def package_metadata: JJ<"package-metadata=">, HelpText<"Emit package metadata note">;
+def package_metadata: JJ<"package-metadata=">, HelpText<"Emit a percent-encoded string to the .note.package section">;
 
 // Aliases
 def: Separate<["-"], "dT">, Alias<default_script>, HelpText<"Alias for --default-script">;
diff --git a/lld/docs/ld.lld.1 b/lld/docs/ld.lld.1
index b28c6082f68b0..b5c1816ce6e5f 100644
--- a/lld/docs/ld.lld.1
+++ b/lld/docs/ld.lld.1
@@ -493,6 +493,10 @@ If
 .Fl -use-android-relr-tags
 is specified, use SHT_ANDROID_RELR instead of SHT_RELR.
 .Pp
+.It Fl -package-metadata
+Emit a percent-encoded string to the
+.Cm .note.package
+section. For example, %25 decodes to a single %.
 .It Fl -pic-veneer
 Always generate position independent thunks.
 .It Fl -pie , Fl -pic-executable
diff --git a/lld/test/ELF/package-metadata.s b/lld/test/ELF/package-metadata.s
index 29df499d7e98d..a70a8940d7c68 100644
--- a/lld/test/ELF/package-metadata.s
+++ b/lld/test/ELF/package-metadata.s
@@ -1,12 +1,15 @@
 # REQUIRES: x86
+# RUN: rm -rf %t && split-file %s %t && cd %t
+# RUN: llvm-mc -filetype=obj -triple=x86_64 a.s -o a.o
 
-# RUN: llvm-mc -filetype=obj -triple=x86_64 %s -o %t.o
+# RUN: ld.lld a.o --package-metadata='{}'
+# RUN: llvm-readelf -n a.out | FileCheck %s --check-prefixes=NOTE,FIRST
 
-# RUN: ld.lld %t.o -o %t --package-metadata='{}'
-# RUN: llvm-readelf -n %t | FileCheck %s --check-prefixes=NOTE,FIRST
+# RUN: ld.lld a.o --package-metadata='{"abc":123}'
+# RUN: llvm-readelf -n a.out | FileCheck %s --check-prefixes=NOTE,SECOND
 
-# RUN: ld.lld %t.o -o %t --package-metadata='{"abc":123}'
-# RUN: llvm-readelf -n %t | FileCheck %s --check-prefixes=NOTE,SECOND
+# RUN: ld.lld a.o --package-metadata='%7b%22abc%22:123%7D'
+# RUN: llvm-readelf -n a.out | FileCheck %s --check-prefixes=NOTE,SECOND
 
 # NOTE: .note.package
 # NOTE-NEXT: Owner
@@ -14,6 +17,13 @@
 # FIRST-NEXT: description data: 7b 7d 00
 # SECOND-NEXT: description data: 7b 22 61 62 63 22 3a 31 32 33 7d 00
 
+# RUN: not ld.lld a.o --package-metadata='%7b%' 2>&1 | FileCheck %s --check-prefix=ERR
+# RUN: not ld.lld a.o --package-metadata='%7b%7' 2>&1 | FileCheck %s --check-prefix=ERR
+# RUN: not ld.lld a.o --package-metadata='%7b%7g' 2>&1 | FileCheck %s --check-prefix=ERR
+
+# ERR: error: --package-metadata=: invalid % escape at byte 3; supports only %[0-9a-fA-F][0-9a-fA-F]
+
+#--- a.s
 .globl _start
 _start:
   ret