[llvm] r212568 - Add support for BSD format Archive map symbols (aka the table of contents

[Kevin Enderby]

Author: enderby
Date: Tue Jul  8 17:10:02 2014
New Revision: 212568

URL: http://llvm.org/viewvc/llvm-project?rev=212568&view=rev
Log:
Add support for BSD format Archive map symbols (aka the table of contents
from a __.SYMDEF or "__.SYMDEF SORTED" archive member).

Modified:
    llvm/trunk/lib/Object/Archive.cpp
    llvm/trunk/test/Object/archive-symtab.test

Modified: llvm/trunk/lib/Object/Archive.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Object/Archive.cpp?rev=212568&r1=212567&r2=212568&view=diff
==============================================================================
--- llvm/trunk/lib/Object/Archive.cpp (original)
+++ llvm/trunk/lib/Object/Archive.cpp Tue Jul  8 17:10:02 2014
@@ -339,7 +339,14 @@ ErrorOr<Archive::child_iterator> Archive
     Offset = *(reinterpret_cast<const support::ubig32_t*>(Offsets)
                + SymbolIndex);
   } else if (Parent->kind() == K_BSD) {
-    llvm_unreachable("BSD format is not supported");
+    // The SymbolIndex is an index into the ranlib structs that start at
+    // Offsets (the first uint32_t is the number of bytes of the ranlib
+    // structs).  The ranlib structs are a pair of uint32_t's the first
+    // being a string table offset and the second being the offset into
+    // the archive of the member that defines the symbol.  Which is what
+    // is needed here.
+    Offset = *(reinterpret_cast<const support::ulittle32_t *>(Offsets) +
+               (SymbolIndex * 2) + 1);
   } else {
     uint32_t MemberCount = *reinterpret_cast<const support::ulittle32_t*>(Buf);
     
@@ -377,9 +384,43 @@ ErrorOr<Archive::child_iterator> Archive
 
 Archive::Symbol Archive::Symbol::getNext() const {
   Symbol t(*this);
-  // Go to one past next null.
-  t.StringIndex =
-      Parent->SymbolTable->getBuffer().find('\0', t.StringIndex) + 1;
+  if (Parent->kind() == K_BSD) {
+    // t.StringIndex is an offset from the start of the __.SYMDEF or
+    // "__.SYMDEF SORTED" member into the string table for the ranlib
+    // struct indexed by t.SymbolIndex .  To change t.StringIndex to the
+    // offset in the string table for t.SymbolIndex+1 we subtract the
+    // its offset from the start of the string table for t.SymbolIndex
+    // and add the offset of the string table for t.SymbolIndex+1.
+
+    // The __.SYMDEF or "__.SYMDEF SORTED" member starts with a uint32_t
+    // which is the number of bytes of ranlib structs that follow.  The ranlib
+    // structs are a pair of uint32_t's the first being a string table offset
+    // and the second being the offset into the archive of the member that
+    // define the symbol. After that the next uint32_t is the byte count of
+    // the string table followed by the string table.
+    const char *Buf = Parent->SymbolTable->getBuffer().begin();
+    uint32_t RanlibCount = 0;
+    RanlibCount = (*reinterpret_cast<const support::ulittle32_t *>(Buf)) /
+                  (sizeof(uint32_t) * 2);
+    // If t.SymbolIndex + 1 will be past the count of symbols (the RanlibCount)
+    // don't change the t.StringIndex as we don't want to reference a ranlib
+    // past RanlibCount.
+    if (t.SymbolIndex + 1 < RanlibCount) {
+      const char *Ranlibs = Buf + 4;
+      uint32_t CurRanStrx = 0;
+      uint32_t NextRanStrx = 0;
+      CurRanStrx = *(reinterpret_cast<const support::ulittle32_t *>(Ranlibs) +
+                     (t.SymbolIndex * 2));
+      NextRanStrx = *(reinterpret_cast<const support::ulittle32_t *>(Ranlibs) +
+                      ((t.SymbolIndex + 1) * 2));
+      t.StringIndex -= CurRanStrx;
+      t.StringIndex += NextRanStrx;
+    }
+  } else {
+    // Go to one past next null.
+    t.StringIndex =
+        Parent->SymbolTable->getBuffer().find('\0', t.StringIndex) + 1;
+  }
   ++t.SymbolIndex;
   return t;
 }
@@ -394,7 +435,22 @@ Archive::symbol_iterator Archive::symbol
     symbol_count = *reinterpret_cast<const support::ubig32_t*>(buf);
     buf += sizeof(uint32_t) + (symbol_count * (sizeof(uint32_t)));
   } else if (kind() == K_BSD) {
-    llvm_unreachable("BSD archive format is not supported");
+    // The __.SYMDEF or "__.SYMDEF SORTED" member starts with a uint32_t
+    // which is the number of bytes of ranlib structs that follow.  The ranlib
+    // structs are a pair of uint32_t's the first being a string table offset
+    // and the second being the offset into the archive of the member that
+    // define the symbol. After that the next uint32_t is the byte count of
+    // the string table followed by the string table.
+    uint32_t ranlib_count = 0;
+    ranlib_count = (*reinterpret_cast<const support::ulittle32_t *>(buf)) /
+                   (sizeof(uint32_t) * 2);
+    const char *ranlibs = buf + 4;
+    uint32_t ran_strx = 0;
+    ran_strx = *(reinterpret_cast<const support::ulittle32_t *>(ranlibs));
+    buf += sizeof(uint32_t) + (ranlib_count * (2 * (sizeof(uint32_t))));
+    // Skip the byte count of the string table.
+    buf += sizeof(uint32_t);
+    buf += ran_strx;
   } else {
     uint32_t member_count = 0;
     uint32_t symbol_count = 0;
@@ -416,7 +472,8 @@ Archive::symbol_iterator Archive::symbol
   if (kind() == K_GNU) {
     symbol_count = *reinterpret_cast<const support::ubig32_t*>(buf);
   } else if (kind() == K_BSD) {
-    llvm_unreachable("BSD archive format is not supported");
+    symbol_count = (*reinterpret_cast<const support::ulittle32_t *>(buf)) /
+                   (sizeof(uint32_t) * 2);
   } else {
     uint32_t member_count = 0;
     member_count = *reinterpret_cast<const support::ulittle32_t*>(buf);

Modified: llvm/trunk/test/Object/archive-symtab.test
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Object/archive-symtab.test?rev=212568&r1=212567&r2=212568&view=diff
==============================================================================
--- llvm/trunk/test/Object/archive-symtab.test (original)
+++ llvm/trunk/test/Object/archive-symtab.test Tue Jul  8 17:10:02 2014
@@ -59,3 +59,9 @@ RUN: llvm-nm -s %t.a | FileCheck %s --ch
 
 RUN: llvm-ranlib %t.a
 RUN: llvm-nm -s %t.a | FileCheck %s
+
+RUN: llvm-nm -s %p/Inputs/macho-archive-x86_64.a | FileCheck %s --check-prefix=BSD-MachO
+
+BSD-MachO: Archive map
+BSD-MachO: _bar in bar.o
+BSD-MachO: _foo in foo.o