RISCV: adjust relocation emission

Simplify and make the pair-wise relocation more precise.  If either of
the symbol references are textual, the relocation must be delayed.  If
the difference is across sections, delay it as well which partially
matches the behaviour of gas.  We unfortunately do not handle the case
where the difference references a symbol that is not yet defined.  In
such a case, we simply fail to resolve the difference, which should
hopefully not be too onerous (particularly since no other target
supports cross-section references and it is not clear if this was
intentional on the part of RISCV).

Differential Revision: https://reviews.llvm.org/D132262
Reviewed By: @MaskRay

llvm/lib/Target/RISCV/MCTargetDesc/RISCVELFStreamer.cpp

@@ -209,14 +209,6 @@ class RISCVELFStreamer : public MCELFStreamer {
 
   static bool requiresFixups(MCContext &C, const MCExpr *Value,
                              const MCExpr *&LHS, const MCExpr *&RHS) {
-    auto IsMetadataOrEHFrameSection = [](const MCSection &S) -> bool {
-      // Additionally check .apple_names/.apple_types. They are fixed-size and
-      // do not need fixups. llvm-dwarfdump --apple-names does not process
-      // R_RISCV_{ADD,SUB}32 in them.
-      return S.getKind().isMetadata() || S.getName() == ".eh_frame" ||
-             S.getName() == ".apple_names" || S.getName() == ".apple_types";
-    };
-
     const auto *MBE = dyn_cast<MCBinaryExpr>(Value);
     if (MBE == nullptr)
       return false;
@@ -235,15 +227,21 @@ class RISCVELFStreamer : public MCELFStreamer {
                              MCConstantExpr::create(E.getConstant(), C), C);
     RHS = E.getSymB();
 
-    // TODO: when available, R_RISCV_n_PCREL should be preferred.
-
-    // Avoid pairwise relocations for symbolic difference in debug and .eh_frame
-    if (A.isInSection())
-      return !IsMetadataOrEHFrameSection(A.getSection());
-    if (B.isInSection())
-      return !IsMetadataOrEHFrameSection(B.getSection());
-    // as well as for absolute symbols.
-    return !A.getName().empty() || !B.getName().empty();
+    // If either symbol is in a text section, we need to delay the relocation
+    // evaluation as relaxation may alter the size of the symbol.
+    //
+    // Unfortunately, we cannot identify if the symbol was built with relaxation
+    // as we do not track the state per symbol or section.  However, BFD will
+    // always emit the relocation and so we follow suit which avoids the need to
+    // track that information.
+    if (A.isInSection() && A.getSection().getKind().isText())
+      return true;
+    if (B.isInSection() && B.getSection().getKind().isText())
+      return true;
+
+    // Support cross-section symbolic differences ...
+    return A.isInSection() && B.isInSection() &&
+           A.getSection().getName() != B.getSection().getName();
   }
 
   void reset() override {

llvm/test/MC/RISCV/riscv64-64b-pcrel.s

@@ -1,5 +1,7 @@
 # RUN: llvm-mc -triple riscv64-unknown-linux-gnu -filetype obj -o - %s \
 # RUN:   | llvm-readobj -r - | FileCheck %s
+# RUN: not llvm-mc -triple riscv64-unknown-linux-gnu -filetype obj --defsym ERR=1 -o /dev/null %s 2>&1 \
+# RUN:   | FileCheck %s --check-prefix CHECK-ERROR
 
 # CHECK: Relocations [
 # CHECK:  .relasx {
@@ -10,10 +12,6 @@
 # CHECK-NEXT:    0x0 R_RISCV_ADD64 x 0x0
 # CHECK-NEXT:    0x0 R_RISCV_SUB64 y 0x0
 # CHECK:  }
-# CHECK:  .relasz {
-# CHECK-NEXT:    0x0 R_RISCV_ADD64 z 0x0
-# CHECK-NEXT:    0x0 R_RISCV_SUB64 a 0x0
-# CHECK:  }
 # CHECK:  .relasa {
 # CHECK-NEXT:    0x0 R_RISCV_ADD64 a 0x0
 # CHECK-NEXT:    0x0 R_RISCV_SUB64 z 0x0
@@ -30,8 +28,16 @@ y:
 
 	.section	sz
 z:
+.ifdef ERR
 	.quad z-a
 
+# CHECK-ERROR: Cannot represent a difference across sections
+# CHECK-ERROR: 	.quad z-a
+# CHECK-ERROR:        ^
+.else
+	.quad 0
+.endif
+
 	.section	sa
 a:
 	.quad a-z