[lld][ARM] Fix assertion when mixing ARM and Thumb objects (#101985)

Previously, we selected the Thumb2 PLT sequences if any input object is
marked as not supporting the ARM ISA, which then causes assertion
failures when calls from ARM code in other objects are seen. I think the
intention here was to only use Thumb PLTs when the target does not have
the ARM ISA available, signalled by no objects being marked as having it
available. To do that we need to track which ISAs we have seen as we
parse the build attributes, and defer the decision about PLTs until all
input objects have been parsed.

This bug was triggered by real code in picolibc, which have some
versions of string.h functions built with Thumb2-only build attributes,
so that they are compatible with v7-A, v7-R and v7-M.

Fixes #99008.

lld/ELF/Arch/ARM.cpp

@@ -228,10 +228,16 @@ static void writePltHeaderLong(uint8_t *buf) {
   write32(buf + 16, gotPlt - l1 - 8);
 }
 
+// True if we should use Thumb PLTs, which currently require Thumb2, and are
+// only used if the target does not have the ARM ISA.
+static bool useThumbPLTs() {
+  return config->armHasThumb2ISA && !config->armHasArmISA;
+}
+
 // The default PLT header requires the .got.plt to be within 128 Mb of the
 // .plt in the positive direction.
 void ARM::writePltHeader(uint8_t *buf) const {
-  if (config->armThumbPLTs) {
+  if (useThumbPLTs()) {
     // The instruction sequence for thumb:
     //
     // 0: b500          push    {lr}
@@ -289,7 +295,7 @@ void ARM::writePltHeader(uint8_t *buf) const {
 }
 
 void ARM::addPltHeaderSymbols(InputSection &isec) const {
-  if (config->armThumbPLTs) {
+  if (useThumbPLTs()) {
     addSyntheticLocal("$t", STT_NOTYPE, 0, 0, isec);
     addSyntheticLocal("$d", STT_NOTYPE, 12, 0, isec);
   } else {
@@ -315,7 +321,7 @@ static void writePltLong(uint8_t *buf, uint64_t gotPltEntryAddr,
 void ARM::writePlt(uint8_t *buf, const Symbol &sym,
                    uint64_t pltEntryAddr) const {
 
-  if (!config->armThumbPLTs) {
+  if (!useThumbPLTs()) {
     uint64_t offset = sym.getGotPltVA() - pltEntryAddr - 8;
 
     // The PLT entry is similar to the example given in Appendix A of ELF for
@@ -367,7 +373,7 @@ void ARM::writePlt(uint8_t *buf, const Symbol &sym,
 }
 
 void ARM::addPltSymbols(InputSection &isec, uint64_t off) const {
-  if (config->armThumbPLTs) {
+  if (useThumbPLTs()) {
     addSyntheticLocal("$t", STT_NOTYPE, off, 0, isec);
   } else {
     addSyntheticLocal("$a", STT_NOTYPE, off, 0, isec);
@@ -393,7 +399,7 @@ bool ARM::needsThunk(RelExpr expr, RelType type, const InputFile *file,
   case R_ARM_JUMP24:
     // Source is ARM, all PLT entries are ARM so no interworking required.
     // Otherwise we need to interwork if STT_FUNC Symbol has bit 0 set (Thumb).
-    assert(!config->armThumbPLTs &&
+    assert(!useThumbPLTs() &&
            "If the source is ARM, we should not need Thumb PLTs");
     if (s.isFunc() && expr == R_PC && (s.getVA() & 1))
       return true;
@@ -407,7 +413,8 @@ bool ARM::needsThunk(RelExpr expr, RelType type, const InputFile *file,
   case R_ARM_THM_JUMP24:
     // Source is Thumb, when all PLT entries are ARM interworking is required.
     // Otherwise we need to interwork if STT_FUNC Symbol has bit 0 clear (ARM).
-    if ((expr == R_PLT_PC && !config->armThumbPLTs) || (s.isFunc() && (s.getVA() & 1) == 0))
+    if ((expr == R_PLT_PC && !useThumbPLTs()) ||
+        (s.isFunc() && (s.getVA() & 1) == 0))
       return true;
     [[fallthrough]];
   case R_ARM_THM_CALL: {
@@ -675,7 +682,7 @@ void ARM::relocate(uint8_t *loc, const Relocation &rel, uint64_t val) const {
     // PLT entries are always ARM state so we know we need to interwork.
     assert(rel.sym); // R_ARM_THM_CALL is always reached via relocate().
     bool bit0Thumb = val & 1;
-    bool useThumb = bit0Thumb || config->armThumbPLTs;
+    bool useThumb = bit0Thumb || useThumbPLTs();
     bool isBlx = (read16(loc + 2) & 0x1000) == 0;
     // lld 10.0 and before always used bit0Thumb when deciding to write a BLX
     // even when type not STT_FUNC.

lld/ELF/Config.h

@@ -221,7 +221,8 @@ struct Config {
   bool allowMultipleDefinition;
   bool fatLTOObjects;
   bool androidPackDynRelocs = false;
-  bool armThumbPLTs = false;
+  bool armHasArmISA = false;
+  bool armHasThumb2ISA = false;
   bool armHasBlx = false;
   bool armHasMovtMovw = false;
   bool armJ1J2BranchEncoding = false;

lld/ELF/InputFiles.cpp

@@ -200,10 +200,8 @@ static void updateSupportedARMFeatures(const ARMAttributeParser &attributes) {
       attributes.getAttributeValue(ARMBuildAttrs::ARM_ISA_use);
   std::optional<unsigned> thumb =
       attributes.getAttributeValue(ARMBuildAttrs::THUMB_ISA_use);
-  bool noArmISA = !armISA || *armISA == ARMBuildAttrs::Not_Allowed;
-  bool hasThumb2 = thumb && *thumb >= ARMBuildAttrs::AllowThumb32;
-  if (noArmISA && hasThumb2)
-    config->armThumbPLTs = true;
+  config->armHasArmISA |= armISA && *armISA >= ARMBuildAttrs::Allowed;
+  config->armHasThumb2ISA |= thumb && *thumb >= ARMBuildAttrs::AllowThumb32;
 }
 
 InputFile::InputFile(Kind k, MemoryBufferRef m)

lld/test/ELF/arm-mixed-plts.s

@@ -0,0 +1,44 @@
+# REQUIRES: arm
+
+# RUN: rm -rf %t && split-file %s %t
+# RUN: llvm-mc -filetype=obj -arm-add-build-attributes -triple=armv7a-none-linux-gnueabi %t/a.s -o %t1.o
+# RUN: llvm-mc -filetype=obj -arm-add-build-attributes -triple=armv7a-none-linux-gnueabi %t/b.s -o %t2.o
+# RUN: ld.lld -shared %t1.o %t2.o -o %t.so
+# RUN: llvm-objdump -d %t.so | FileCheck %s
+
+## Check that, when the input is a mixture of objects which can and cannot use
+## the ARM ISA, we use the default ARM PLT sequences.
+
+# CHECK:      <.plt>:
+# CHECK-NEXT: e52de004      str     lr, [sp, #-0x4]!
+# CHECK-NEXT: e28fe600      add     lr, pc, #0, #12
+# CHECK-NEXT: e28eea20      add     lr, lr, #32, #20
+# CHECK-NEXT: e5bef084      ldr     pc, [lr, #0x84]!
+# CHECK-NEXT: d4 d4 d4 d4   .word   0xd4d4d4d4
+# CHECK-NEXT: d4 d4 d4 d4   .word   0xd4d4d4d4
+# CHECK-NEXT: d4 d4 d4 d4   .word   0xd4d4d4d4
+# CHECK-NEXT: d4 d4 d4 d4   .word   0xd4d4d4d4
+# CHECK-NEXT: e28fc600      add     r12, pc, #0, #12
+# CHECK-NEXT: e28cca20      add     r12, r12, #32, #20
+# CHECK-NEXT: e5bcf06c      ldr     pc, [r12, #0x6c]!
+# CHECK-NEXT: d4 d4 d4 d4   .word   0xd4d4d4d4
+
+#--- a.s
+  .globl foo
+  .type foo, %function
+  .globl bar
+  .type bar, %function
+
+  .thumb
+foo:
+  bl bar
+  bx lr
+
+#--- b.s
+  .eabi_attribute Tag_ARM_ISA_use, 0
+
+  .arm
+  .globl bar
+  .type bar, %function
+bar:
+  bx lr