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

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

This is used in linker scripts.

Differential revision: http://reviews.llvm.org/D17290

llvm-svn: 261726

3 files changed, 84 insertions, 17 deletions

diff --git a/lld/ELF/LinkerScript.cpp b/lld/ELF/LinkerScript.cpp
index 8028f30a983..af9704a4d39 100644
--- a/lld/ELF/LinkerScript.cpp
+++ b/lld/ELF/LinkerScript.cpp
@@ -66,8 +66,9 @@ int LinkerScript::compareSections(StringRef A, StringRef B) {
   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())
@@ -82,7 +83,7 @@ static bool matchStr(StringRef S, StringRef T) {
           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);
diff --git a/lld/test/ELF/linkerscript-sections.s b/lld/test/ELF/linkerscript-sections.s
index 9471ccde682..ea9ae2b2726 100644
--- a/lld/test/ELF/linkerscript-sections.s
+++ b/lld/test/ELF/linkerscript-sections.s
@@ -38,20 +38,6 @@
 # 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
diff --git a/lld/test/ELF/wildcards.s b/lld/test/ELF/wildcards.s
new file mode 100644
index 00000000000..fe75c95a21e
--- /dev/null
+++ b/lld/test/ELF/wildcards.s
@@ -0,0 +1,80 @@
+# 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: