Recommit r281721 "[ELF] - Linkerscript: implement EXCLUDE_FILE in the middle of a input section description."

With fix for 2 bots. Details about the fix performed is on a review page.

Initial commit message:
This is PR30387:

From PR description:
We fail to parse

SECTIONS
{
  foo :
  {
    *(sec0 EXCLUDE_FILE (zed1.o) sec1  EXCLUDE_FILE (zed2.o) sec2 )
  }
}
The semantics according to bfd are:

Include sec1 from every file but zed1.o
Include sec2 from every file but zed2.o
Include sec0 from every file

Patch implements the support.

Differential revision: https://reviews.llvm.org/D24650

llvm-svn: 281754

5 files changed, 100 insertions, 26 deletions

diff --git a/lld/ELF/LinkerScript.cpp b/lld/ELF/LinkerScript.cpp
index 175ec5f668c..d676d38c4c1 100644
--- a/lld/ELF/LinkerScript.cpp
+++ b/lld/ELF/LinkerScript.cpp
@@ -109,10 +109,10 @@ bool LinkerScript<ELFT>::shouldKeep(InputSectionBase<ELFT> *S) {
   return false;
 }
 
-static bool fileMatches(const InputSectionDescription *Desc,
-                        StringRef Filename) {
-  return const_cast<Regex &>(Desc->FileRe).match(Filename) &&
-         !const_cast<Regex &>(Desc->ExcludedFileRe).match(Filename);
+static bool fileMatches(const llvm::Regex &FileRe,
+                        const llvm::Regex &ExcludedFileRe, StringRef Filename) {
+  return const_cast<Regex &>(FileRe).match(Filename) &&
+         !const_cast<Regex &>(ExcludedFileRe).match(Filename);
 }
 
 static bool comparePriority(InputSectionData *A, InputSectionData *B) {
@@ -161,16 +161,19 @@ static bool matchConstraints(ArrayRef<InputSectionData *> Sections,
 template <class ELFT>
 void LinkerScript<ELFT>::computeInputSections(InputSectionDescription *I,
                                               ConstraintKind Constraint) {
-  const Regex &Re = I->SectionRe;
-  for (ObjectFile<ELFT> *F : Symtab<ELFT>::X->getObjectFiles())
-    if (fileMatches(I, sys::path::filename(F->getName())))
-      for (InputSectionBase<ELFT> *S : F->getSections())
-        if (!isDiscarded(S) && !S->OutSec &&
-            const_cast<Regex &>(Re).match(S->Name))
-          I->Sections.push_back(S);
-
-  if (const_cast<Regex &>(Re).match("COMMON"))
-    I->Sections.push_back(CommonInputSection<ELFT>::X);
+  for (const std::pair<llvm::Regex, llvm::Regex> &V : I->SectionsVec) {
+    for (ObjectFile<ELFT> *F : Symtab<ELFT>::X->getObjectFiles()) {
+      if (fileMatches(I->FileRe, V.first, sys::path::filename(F->getName()))) {
+        Regex &Re = const_cast<Regex &>(V.second);
+        for (InputSectionBase<ELFT> *S : F->getSections())
+          if (!isDiscarded(S) && !S->OutSec && Re.match(S->Name))
+            I->Sections.push_back(S);
+
+        if (Re.match("COMMON"))
+          I->Sections.push_back(CommonInputSection<ELFT>::X);
+      }
+    }
+  }
 
   if (!matchConstraints<ELFT>(I->Sections, Constraint)) {
     I->Sections.clear();
@@ -698,6 +701,7 @@ private:
   std::vector<StringRef> readOutputSectionPhdrs();
   InputSectionDescription *readInputSectionDescription(StringRef Tok);
   Regex readFilePatterns();
+  void readSectionExcludes(InputSectionDescription *Cmd);
   InputSectionDescription *readInputSectionRules(StringRef FilePattern);
   unsigned readPhdrType();
   SortKind readSortKind();
@@ -991,17 +995,41 @@ SortKind ScriptParser::readSortKind() {
   return SortNone;
 }
 
+// Method reads a list of sequence of excluded files and section globs given in
+// a following form: ((EXCLUDE_FILE(file_pattern+))? section_pattern+)+
+// Example: *(.foo.1 EXCLUDE_FILE (*a.o) .foo.2 EXCLUDE_FILE (*b.o) .foo.3)
+void ScriptParser::readSectionExcludes(InputSectionDescription *Cmd) {
+  llvm::Regex ExcludeFileRe;
+  std::vector<StringRef> V;
+
+  while (!Error) {
+    if (skip(")")) {
+      Cmd->SectionsVec.push_back(
+          {std::move(ExcludeFileRe), compileGlobPatterns(V)});
+      return;
+    }
+
+    if (skip("EXCLUDE_FILE")) {
+      if (!V.empty()) {
+        Cmd->SectionsVec.push_back(
+            {std::move(ExcludeFileRe), compileGlobPatterns(V)});
+        V.clear();
+      }
+
+      expect("(");
+      ExcludeFileRe = readFilePatterns();
+      continue;
+    }
+
+    V.push_back(next());
+  }
+}
+
 InputSectionDescription *
 ScriptParser::readInputSectionRules(StringRef FilePattern) {
   auto *Cmd = new InputSectionDescription(FilePattern);
   expect("(");
 
-  // Read EXCLUDE_FILE().
-  if (skip("EXCLUDE_FILE")) {
-    expect("(");
-    Cmd->ExcludedFileRe = readFilePatterns();
-  }
-
   // Read SORT().
   if (SortKind K1 = readSortKind()) {
     Cmd->SortOuter = K1;
@@ -1009,16 +1037,16 @@ ScriptParser::readInputSectionRules(StringRef FilePattern) {
     if (SortKind K2 = readSortKind()) {
       Cmd->SortInner = K2;
       expect("(");
-      Cmd->SectionRe = readFilePatterns();
+      Cmd->SectionsVec.push_back({llvm::Regex(), readFilePatterns()});
       expect(")");
     } else {
-      Cmd->SectionRe = readFilePatterns();
+      Cmd->SectionsVec.push_back({llvm::Regex(), readFilePatterns()});
     }
     expect(")");
     return Cmd;
   }
 
-  Cmd->SectionRe = readFilePatterns();
+  readSectionExcludes(Cmd);
   return Cmd;
 }
 
@@ -1031,7 +1059,8 @@ ScriptParser::readInputSectionDescription(StringRef Tok) {
     StringRef FilePattern = next();
     InputSectionDescription *Cmd = readInputSectionRules(FilePattern);
     expect(")");
-    Opt.KeptSections.push_back(&Cmd->SectionRe);
+    for (std::pair<llvm::Regex, llvm::Regex> &Regex : Cmd->SectionsVec)
+      Opt.KeptSections.push_back(&Regex.second);
     return Cmd;
   }
   return readInputSectionRules(Tok);
diff --git a/lld/ELF/LinkerScript.h b/lld/ELF/LinkerScript.h
index d9fc1175fce..159cac3f9f0 100644
--- a/lld/ELF/LinkerScript.h
+++ b/lld/ELF/LinkerScript.h
@@ -20,6 +20,7 @@
 #include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Support/Regex.h"
 #include <functional>
+#include <list>
 
 namespace lld {
 namespace elf {
@@ -106,8 +107,8 @@ struct InputSectionDescription : BaseCommand {
   llvm::Regex FileRe;
   SortKind SortOuter = SortNone;
   SortKind SortInner = SortNone;
-  llvm::Regex ExcludedFileRe;
-  llvm::Regex SectionRe;
+  // Pairs of section regex and files excluded.
+  std::list<std::pair<llvm::Regex, llvm::Regex>> SectionsVec;
   std::vector<InputSectionData *> Sections;
 };
 
diff --git a/lld/test/ELF/linkerscript/Inputs/exclude-multiple1.s b/lld/test/ELF/linkerscript/Inputs/exclude-multiple1.s
new file mode 100644
index 00000000000..1e0f741df40
--- /dev/null
+++ b/lld/test/ELF/linkerscript/Inputs/exclude-multiple1.s
@@ -0,0 +1,8 @@
+.section .foo.1,"a"
+ .quad 4
+
+.section .foo.2,"a"
+ .quad 5
+
+.section .foo.3,"a"
+ .quad 6
diff --git a/lld/test/ELF/linkerscript/Inputs/exclude-multiple2.s b/lld/test/ELF/linkerscript/Inputs/exclude-multiple2.s
new file mode 100644
index 00000000000..60f790fa235
--- /dev/null
+++ b/lld/test/ELF/linkerscript/Inputs/exclude-multiple2.s
@@ -0,0 +1,8 @@
+.section .foo.1,"a"
+ .quad 7
+
+.section .foo.2,"a"
+ .quad 8
+
+.section .foo.3,"a"
+ .quad 9
diff --git a/lld/test/ELF/linkerscript/exclude-multiple.s b/lld/test/ELF/linkerscript/exclude-multiple.s
new file mode 100644
index 00000000000..24c7f2faeea
--- /dev/null
+++ b/lld/test/ELF/linkerscript/exclude-multiple.s
@@ -0,0 +1,28 @@
+# REQUIRES: x86
+# RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %s -o %tfile1.o
+# RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %p/Inputs/exclude-multiple1.s -o %tfile2.o
+# RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %p/Inputs/exclude-multiple2.s -o %tfile3.o
+# RUN: echo "SECTIONS { \
+# RUN:   .foo : { *(.foo.1 EXCLUDE_FILE (*file1.o) .foo.2 EXCLUDE_FILE (*file2.o) .foo.3) } \
+# RUN:  }" > %t1.script
+# RUN: ld.lld -script %t1.script %tfile1.o %tfile2.o %tfile3.o -o %t1.o
+# RUN: llvm-objdump -s %t1.o | FileCheck %s
+
+# CHECK:      Contents of section .foo:
+# CHECK-NEXT:  0120 01000000 00000000 04000000 00000000
+# CHECK-NEXT:  0130 07000000 00000000 05000000 00000000
+# CHECK-NEXT:  0140 08000000 00000000 03000000 00000000
+# CHECK-NEXT:  0150 09000000 00000000
+# CHECK-NEXT: Contents of section .foo.2:
+# CHECK-NEXT:  0158 02000000 00000000
+# CHECK-NEXT: Contents of section .foo.3:
+# CHECK-NEXT:  0160 06000000 00000000
+
+.section .foo.1,"a"
+ .quad 1
+
+.section .foo.2,"a"
+ .quad 2
+
+.section .foo.3,"a"
+ .quad 3