[ELF] - Teach input section wildcard patterns to recognize '?' meta character.

[grimar]

Summary

`?' - matches any single character
https://sourceware.org/binutils/docs/ld/Input-Section-Wildcards.html

This is used in few linker scripts I saw. Ex:

.init_array     :
  {
    KEEP (*(SORT_BY_INIT_PRIORITY(.init_array.*) SORT_BY_INIT_PRIORITY(.ctors.*)))
    KEEP (*(.init_array EXCLUDE_FILE (*crtbegin.o *crtbegin?.o *crtend.o *crtend?.o ) .ctors))
  }

[• rafael]

Testcase?

[grimar]

• Added testcase

[grimar]

• Fixed comment in testcase

[• rafael]

ELF/LinkerScript.cpp

66 ↗

(On Diff #48320)

Why rename S to W in the same commit?

[ruiu]

ELF/LinkerScript.cpp

58–63 ↗

(On Diff #48320)

I don't think we need examples because this pattern matching is familiar.

// Returns true if S matches T. S can contain DOS-style wildcard characters.
// The asterisk ('*') matches one or more characacters, and the question
// mark ('?') matches one character.

test/ELF/wildcards.s

1 ↗

(On Diff #48320)

If you create a new file, please move the existing test for '*' in linkerscript-sections.s to this file.

[grimar]

• Addressed review comments.

ELF/LinkerScript.cpp

66 ↗

(On Diff #48320)

We often rename the variables during common patches. See nothing ubnormal here. But reverted it back, if you think it is better to do separatelly.

test/ELF/wildcards.s

1 ↗

(On Diff #48320)

I can't do that. Those test uses those file source code.
I removed test from linkerscript-sections.s and added one additional for * here.

[• rafael]

ELF/LinkerScript.cpp

58 ↗

(On Diff #48477)

glob is probably a better known term than DOS-style wildcard.

[grimar]

ELF/LinkerScript.cpp

58 ↗

(On Diff #48477)

https://sourceware.org/binutils/docs/ld/Input-Section-Wildcards.html
In specs it just called "the wildcard patterns characters" I think.
At least there is a mention that "The wildcard patterns are like those used by the Unix shell." and below each special symbol named as character.

[• rafael]

ELF/LinkerScript.cpp

58 ↗

(On Diff #48477)

"those used by the Unix shell" == glob.

Please don't use DOS-style.

[ruiu]

ELF/LinkerScript.cpp

58 ↗

(On Diff #48477)

glob sounds fine.

[grimar]

• s/DOS-style wildcard characters/glob meta-characters

[• rafael]

LGTM with a nit. This patch is not changing what '*' does and should not change its description to say it doesn't match 0 characters.

ELF/LinkerScript.cpp

70 ↗

(On Diff #48786)

'*' can't really mach 0 characters?

[ruiu]

LGTM

ELF/LinkerScript.cpp

70 ↗

(On Diff #48786)

That's a good question, and I found that either the code or this comment is wrong. If my understanding is correct, '*' in this function matches zero-or-more. We need to fix either one.

lld/trunk/ELF/LinkerScript.cpp

int LinkerScript::compareSections(StringRef A, StringRef B) {
   auto E = SectionOrder.end();
   auto I = std::find(SectionOrder.begin(), E, A);
   auto J = std::find(SectionOrder.begin(), E, B);
   if (I == E || J == E)
     return 0;
   return I < J ? -1 : 1;
 }
 
-// Returns true if S matches T. S may contain a meta character '*'
-// which matches zero or more occurrences of any character.
+// Returns true if S matches T. S can contain glob meta-characters.
+// The asterisk ('*') matches zero or more characacters, and the question
+// mark ('?') matches one character.
 static bool matchStr(StringRef S, StringRef T) {
   for (;;) {
     if (S.empty())
       return T.empty();
     if (S[0] == '*') {
       S = S.substr(1);
       if (S.empty())
         // Fast path. If a pattern is '*', it matches anything.
         return true;
       for (size_t I = 0, E = T.size(); I < E; ++I)
         if (matchStr(S, T.substr(I)))
           return true;
       return false;
     }
-    if (T.empty() || S[0] != T[0])
+    if (T.empty() || (S[0] != T[0] && S[0] != '?'))
       return false;
     S = S.substr(1);
     T = T.substr(1);
   }
 }
 
 template <class ELFT> bool SectionRule::match(InputSectionBase<ELFT> *S) {
   return matchStr(SectionPattern, S->getSectionName());

lld/trunk/test/ELF/linkerscript-sections.s

 # RUN:          .symtab : { *(.symtab) } \
 # RUN:          .strtab : { *(.strtab) } \
 # RUN:          .data : { *(.data) } \
 # RUN:          .text : { *(.text) } }" > %t.script
 # RUN: ld.lld -o %t3 --script %t.script %t
 # RUN: llvm-objdump -section-headers %t3 | \
 # RUN:   FileCheck -check-prefix=SEC-ORDER %s
 
-# The same test as above but with wildcard patterns.
-# RUN: echo "SECTIONS { \
-# RUN:          .bss : { *(.bss) } \
-# RUN:          other : { *(o*er) } \
-# RUN:          .shstrtab : { *(.shstrt*) } \
-# RUN:          .symtab : { *(.symtab) } \
-# RUN:          .strtab : { *(.strtab) } \
-# RUN:          .data : { *(*data) } \
-# RUN:          .text : { *(.text) } }" > %t.script
-# RUN: cp %t %t.abc
-# RUN: ld.lld -o %t3 --script %t.script %t.abc
-# RUN: llvm-objdump -section-headers %t3 | \
-# RUN:   FileCheck -check-prefix=SEC-ORDER %s
-
 #           Idx Name          Size
 # SEC-ORDER: 1 .bss          00000002 {{[0-9a-f]*}} BSS
 # SEC-ORDER: 2 other         00000003 {{[0-9a-f]*}} DATA
 # SEC-ORDER: 3 .shstrtab     00000002 {{[0-9a-f]*}}
 # SEC-ORDER: 4 .shstrtab     00000032 {{[0-9a-f]*}}
 # SEC-ORDER: 5 .symtab       00000030 {{[0-9a-f]*}}
 # SEC-ORDER: 6 .strtab       00000008 {{[0-9a-f]*}}
 # SEC-ORDER: 7 .data         00000020 {{[0-9a-f]*}} DATA

lld/trunk/test/ELF/wildcards.s

+# REQUIRES: x86
+# RUN: llvm-mc -filetype=obj -triple=x86_64-unknown-linux %s -o %t
+
+## Default case: abc and abx included in text.
+# RUN: echo "SECTIONS { \
+# RUN:      .text : { *(.abc .abx) } }" > %t.script
+# RUN: ld.lld -o %t.out --script %t.script %t
+# RUN: llvm-objdump -section-headers %t.out | \
+# RUN:   FileCheck -check-prefix=SEC-DEFAULT %s
+# SEC-DEFAULT:      Sections:
+# SEC-DEFAULT-NEXT: Idx Name          Size      Address          Type
+# SEC-DEFAULT-NEXT:   0               00000000 0000000000000000
+# SEC-DEFAULT-NEXT:   1 .text         00000008 0000000000011000 TEXT DATA
+# SEC-DEFAULT-NEXT:   2 .abcd         00000004 0000000000011008 TEXT DATA
+# SEC-DEFAULT-NEXT:   3 .ad           00000004 000000000001100c TEXT DATA 
+# SEC-DEFAULT-NEXT:   4 .ag           00000004 0000000000011010 TEXT DATA 
+# SEC-DEFAULT-NEXT:   5 .symtab       00000030 0000000000000000 
+# SEC-DEFAULT-NEXT:   6 .shstrtab     0000002f 0000000000000000 
+# SEC-DEFAULT-NEXT:   7 .strtab       00000008 0000000000000000 
+
+## Now replace the symbol with '?' and check that results are the same.
+# RUN: echo "SECTIONS { \
+# RUN:      .text : { *(.abc .ab?) } }" > %t.script
+# RUN: ld.lld -o %t.out --script %t.script %t
+# RUN: llvm-objdump -section-headers %t.out | \
+# RUN:   FileCheck -check-prefix=SEC-DEFAULT %s
+
+## Now see how replacing '?' with '*' will consume whole abcd.
+# RUN: echo "SECTIONS { \
+# RUN:      .text : { *(.abc .ab*) } }" > %t.script
+# RUN: ld.lld -o %t.out --script %t.script %t
+# RUN: llvm-objdump -section-headers %t.out | \
+# RUN:   FileCheck -check-prefix=SEC-ALL %s
+# SEC-ALL:      Sections:
+# SEC-ALL-NEXT: Idx Name          Size      Address          Type
+# SEC-ALL-NEXT:   0               00000000 0000000000000000
+# SEC-ALL-NEXT:   1 .text         0000000c 0000000000011000 TEXT DATA
+# SEC-ALL-NEXT:   2 .ad           00000004 000000000001100c TEXT DATA 
+# SEC-ALL-NEXT:   3 .ag           00000004 0000000000011010 TEXT DATA 
+# SEC-ALL-NEXT:   4 .symtab       00000030 0000000000000000 
+# SEC-ALL-NEXT:   5 .shstrtab     00000029 0000000000000000 
+# SEC-ALL-NEXT:   6 .strtab       00000008 0000000000000000 
+
+## All sections started with .a are merged.
+# RUN: echo "SECTIONS { \
+# RUN:      .text : { *(.a*) } }" > %t.script
+# RUN: ld.lld -o %t.out --script %t.script %t
+# RUN: llvm-objdump -section-headers %t.out | \
+# RUN:   FileCheck -check-prefix=SEC-NO %s
+# SEC-NO: Sections:
+# SEC-NO-NEXT: Idx Name          Size      Address          Type
+# SEC-NO-NEXT:   0               00000000 0000000000000000 
+# SEC-NO-NEXT:   1 .text         00000014 0000000000011000 TEXT DATA 
+# SEC-NO-NEXT:   2 .symtab       00000030 0000000000000000 
+# SEC-NO-NEXT:   3 .shstrtab     00000021 0000000000000000 
+# SEC-NO-NEXT:   4 .strtab       00000008 0000000000000000 
+
+.text
+.section .abc,"ax",@progbits
+.long 0
+
+.text
+.section .abx,"ax",@progbits
+.long 0
+
+.text
+.section .abcd,"ax",@progbits
+.long 0
+
+.text
+.section .ad,"ax",@progbits
+.long 0
+
+.text
+.section .ag,"ax",@progbits
+.long 0
+
+
+.globl _start
+_start: