[AArch64] Allow label arithmetic with add/sub/cmp

Allow instructions such as 'cmp w0, #(end - start)' by folding the
expression into a constant. For ELF, we fold only if the symbols are in
the same section. For MachO, we fold if the expression contains only
symbols that are not linker visible.

Fixes https://llvm.org/bugs/show_bug.cgi?id=18920

Differential Revision: https://reviews.llvm.org/D23834

llvm-svn: 283862

llvm/lib/Target/AArch64/AsmParser/AArch64AsmParser.cpp

@@ -729,9 +729,13 @@ public:
           || ELFRefKind == AArch64MCExpr::VK_TLSDESC_LO12;
     }
 
-    // Otherwise it should be a real immediate in range:
+    // If it's a constant, it should be a real immediate in range:
-    const MCConstantExpr *CE = cast<MCConstantExpr>(Expr);
+    if (auto *CE = dyn_cast<MCConstantExpr>(Expr))
       return CE->getValue() >= 0 && CE->getValue() <= 0xfff;
+
+    // If it's an expression, we hope for the best and let the fixup/relocation
+    // code deal with it.
+    return true;
   }
   bool isAddSubImmNeg() const {
     if (!isShiftedImm() && !isImm())
@@ -3568,9 +3572,7 @@ bool AArch64AsmParser::validateInstruction(MCInst &Inst,
       AArch64MCExpr::VariantKind ELFRefKind;
       MCSymbolRefExpr::VariantKind DarwinRefKind;
       int64_t Addend;
-      if (!classifySymbolRef(Expr, ELFRefKind, DarwinRefKind, Addend)) {
+      if (classifySymbolRef(Expr, ELFRefKind, DarwinRefKind, Addend)) {
-        return Error(Loc[2], "invalid immediate expression");
-      }
 
         // Only allow these with ADDXri.
         if ((DarwinRefKind == MCSymbolRefExpr::VK_PAGEOFF ||
@@ -3591,8 +3593,13 @@ bool AArch64AsmParser::validateInstruction(MCInst &Inst,
              Inst.getOpcode() == AArch64::ADDWri))
           return false;
 
-      // Don't allow expressions in the immediate field otherwise
+        // Don't allow symbol refs in the immediate field otherwise
-      return Error(Loc[2], "invalid immediate expression");
+        // Note: Loc.back() may be Loc[1] or Loc[2] depending on the number of
+        // operands of the original instruction (i.e. 'add w0, w1, borked' vs
+        // 'cmp w0, 'borked')
+        return Error(Loc.back(), "invalid immediate expression");
+      }
+      // We don't validate more complex expressions here
     }
     return false;
   }

llvm/lib/Target/AArch64/MCTargetDesc/AArch64AsmBackend.cpp

@@ -521,6 +521,17 @@ public:
 
     return CompactUnwindEncoding;
   }
+
+  void processFixupValue(const MCAssembler &Asm, const MCAsmLayout &Layout,
+                         const MCFixup &Fixup, const MCFragment *DF,
+                         const MCValue &Target, uint64_t &Value,
+                         bool &IsResolved) override {
+    // Try to get the encoded value for the fixup as-if we're mapping it into
+    // the instruction. This allows adjustFixupValue() to issue a diagnostic
+    // if the value is invalid.
+    if (IsResolved)
+      (void)adjustFixupValue(Fixup, Value, &Asm.getContext());
+  }
 };
 
 } // end anonymous namespace

llvm/lib/Target/AArch64/MCTargetDesc/AArch64MachObjectWriter.cpp

@@ -75,7 +75,7 @@ bool AArch64MachObjectWriter::getAArch64FixupKindMachOInfo(
     Log2Size = llvm::Log2_32(4);
     switch (Sym->getKind()) {
     default:
-      llvm_unreachable("Unexpected symbol reference variant kind!");
+      return false;
     case MCSymbolRefExpr::VK_PAGEOFF:
       RelocType = unsigned(MachO::ARM64_RELOC_PAGEOFF12);
       return true;

llvm/test/MC/AArch64/basic-a64-diagnostics.s

@@ -172,9 +172,14 @@
 
         // A relocation should be provided for symbols
         add x3, x9, #variable
+        add x3, x9, #variable-16
 // CHECK-ERROR: error: expected compatible register, symbol or integer in range [0, 4095]
 // CHECK-ERROR-NEXT:         add x3, x9, #variable
 // CHECK-ERROR-NEXT:                      ^
+// CHECK-ERROR-NEXT: error: expected compatible register, symbol or integer in range [0, 4095]
+// CHECK-ERROR-NEXT:         add x3, x9, #variable-16
+// CHECK-ERROR-NEXT:                 ^
+
 
 
 //------------------------------------------------------------------------------

llvm/test/MC/AArch64/label-arithmetic-darwin.s

@@ -0,0 +1,61 @@
+// RUN: llvm-mc -triple aarch64-darwin -filetype=obj %s -o - | llvm-objdump -r -d - | FileCheck %s
+// RUN: llvm-mc -triple aarch64-ios -filetype=obj %s -o - | llvm-objdump -r -d - | FileCheck %s
+
+visible:
+  .space 8
+Lstart:
+  .space 8
+Lend:
+  adds w0, w1, #(Lend - Lstart)
+  adds x0, x1, #(Lend - Lstart)
+  add w0, w1, #(Lend - Lstart)
+  add x0, x1, #(Lend - Lstart)
+  cmp w0, #(Lend - Lstart)
+  cmp x0, #(Lend - Lstart)
+  sub w0, w1, #(Lend - Lstart)
+  sub x0, x1, #(Lend - Lstart)
+  // CHECK: adds w0, w1, #8
+  // CHECK: adds x0, x1, #8
+  // CHECK: add w0, w1, #8
+  // CHECK: add x0, x1, #8
+  // CHECK: cmp w0, #8
+  // CHECK: cmp x0, #8
+  // CHECK: sub w0, w1, #8
+  // CHECK: sub x0, x1, #8
+
+  add w0, w1, #(Lend - Lstart), lsl #12
+  cmp w0, #(Lend - Lstart), lsl #12
+  // CHECK: add w0, w1, #8, lsl #12
+  // CHECK: cmp w0, #8, lsl #12
+
+  add w0, w1, #((Lend - Lstart) >> 2)
+  cmp w0, #((Lend - Lstart) >> 2)
+  // CHECK: add w0, w1, #2
+  // CHECK: cmp w0, #2
+
+  add w0, w1, #(Lend - Lstart + 12)
+  cmp w0, #(Lend - Lstart + 12)
+  // CHECK: add w0, w1, #20
+  // CHECK: cmp w0, #20
+
+  add w0, w1, #(Lforward - Lend)
+  cmp w0, #(Lforward - Lend)
+  // CHECK: add w0, w1, #320
+  // CHECK: cmp w0, #320
+
+  add w0, w1, #(Lstart - visible)
+  cmp w0, #(Lstart - visible)
+  // CHECK: add w0, w1, #8
+  // CHECK: cmp w0, #8
+
+// Add some filler so we don't have to modify #(Lforward - Lend) if we add more
+// instructions above
+Lfiller:
+  .space 320 - (Lfiller - Lend)
+
+Lforward:
+  .space 4
+  add w0, w1, #(. - Lforward)
+  cmp w0, #(. - Lforward)
+  // CHECK: add w0, w1, #4
+  // CHECK: cmp w0, #8

llvm/test/MC/AArch64/label-arithmetic-diags-darwin.s

@@ -0,0 +1,68 @@
+// RUN: not llvm-mc -triple aarch64-darwin -filetype=obj %s -o /dev/null 2>&1 | FileCheck %s
+// RUN: not llvm-mc -triple aarch64-ios -filetype=obj %s -o /dev/null 2>&1 | FileCheck %s
+
+Lstart:
+  .space 8
+Lend:
+  add w0, w1, #(Lend - external)
+  cmp w0, #(Lend - external)
+  // CHECK: error: unknown AArch64 fixup kind!
+  // CHECK-NEXT: add w0, w1, #(Lend - external)
+  // CHECK-NEXT: ^
+  // CHECK: error: unknown AArch64 fixup kind!
+  // CHECK-NEXT: cmp w0, #(Lend - external)
+  // CHECK-NEXT: ^
+
+  add w0, w1, #(Lend - var@TLVPPAGEOFF)
+  cmp w0, #(Lend - var@TLVPPAGEOFF)
+  // CHECK: error: unknown AArch64 fixup kind!
+  // CHECK-NEXT: add w0, w1, #(Lend - var@TLVPPAGEOFF)
+  // CHECK-NEXT: ^
+  // CHECK: error: unknown AArch64 fixup kind!
+  // CHECK-NEXT: cmp w0, #(Lend - var@TLVPPAGEOFF)
+  // CHECK-NEXT: ^
+
+  add w0, w1, #(Lstart - Lend)
+  cmp w0, #(Lstart - Lend)
+  // CHECK: error: fixup value out of range
+  // CHECK-NEXT: add w0, w1, #(Lstart - Lend)
+  // CHECK-NEXT: ^
+  // CHECK: error: fixup value out of range
+  // CHECK-NEXT: cmp w0, #(Lstart - Lend)
+  // CHECK-NEXT: ^
+
+  .space 5000
+Lfar:
+  add w0, w1, #(Lfar - Lend)
+  cmp w0, #(Lfar - Lend)
+  // CHECK: error: fixup value out of range
+  // CHECK-NEXT: add w0, w1, #(Lfar - Lend)
+  // CHECK-NEXT: ^
+  // CHECK: error: fixup value out of range
+  // CHECK-NEXT: cmp w0, #(Lfar - Lend)
+  // CHECK-NEXT: ^
+
+Lprivate1:
+  .space 8
+notprivate:
+  .space 8
+Lprivate2:
+  add w0, w1, #(Lprivate2 - Lprivate1)
+  cmp w0, #(Lprivate2 - Lprivate1)
+  // CHECK: error: unknown AArch64 fixup kind!
+  // CHECK-NEXT: add w0, w1, #(Lprivate2 - Lprivate1)
+  // CHECK-NEXT: ^
+  // CHECK: error: unknown AArch64 fixup kind!
+  // CHECK-NEXT: cmp w0, #(Lprivate2 - Lprivate1)
+  // CHECK-NEXT: ^
+
+  .section __TEXT, sec_y, regular, pure_instructions
+Lend_across_sec:
+  add w0, w1, #(Lend_across_sec - Lprivate2)
+  cmp w0, #(Lend_across_sec - Lprivate2)
+  // CHECK: error: unknown AArch64 fixup kind!
+  // CHECK-NEXT: add w0, w1, #(Lend_across_sec - Lprivate2)
+  // CHECK-NEXT: ^
+  // CHECK: error: unknown AArch64 fixup kind!
+  // CHECK-NEXT: cmp w0, #(Lend_across_sec - Lprivate2)
+  // CHECK-NEXT: ^

llvm/test/MC/AArch64/label-arithmetic-diags-elf.s

@@ -0,0 +1,71 @@
+// RUN: not llvm-mc -triple aarch64-elf -filetype=obj %s -o /dev/null 2>&1 | FileCheck %s
+
+  .section sec_x
+start:
+  .space 5000
+end:
+  add w0, w1, #(end - start)
+  cmp w0, #(end - start)
+  // CHECK: error: fixup value out of range
+  // CHECK-NEXT: add w0, w1, #(end - start)
+  // CHECK-NEXT: ^
+  // CHECK: error: fixup value out of range
+  // CHECK-NEXT: cmp w0, #(end - start)
+  // CHECK-NEXT: ^
+
+negative:
+  add w0, w1, #(end - negative)
+  cmp w0, #(end - negative)
+  // CHECK: error: fixup value out of range
+  // CHECK-NEXT: add w0, w1, #(end - negative)
+  // CHECK-NEXT: ^
+  // CHECK: error: fixup value out of range
+  // CHECK-NEXT: cmp w0, #(end - negative)
+  // CHECK-NEXT: ^
+
+  add w0, w1, #(end - external)
+  cmp w0, #(end - external)
+  // CHECK: error: symbol 'external' can not be undefined in a subtraction expression
+  // CHECK-NEXT: add w0, w1, #(end - external)
+  // CHECK-NEXT: ^
+  // CHECK: error: symbol 'external' can not be undefined in a subtraction expression
+  // CHECK-NEXT: cmp w0, #(end - external)
+  // CHECK-NEXT: ^
+
+  add w0, w1, #:lo12:external - end
+  cmp w0, #:lo12:external - end
+  // CHECK: error: Unsupported pc-relative fixup kind
+  // CHECK-NEXT: add w0, w1, #:lo12:external - end
+  // CHECK-NEXT: ^
+  // CHECK: error: Unsupported pc-relative fixup kind
+  // CHECK-NEXT: cmp w0, #:lo12:external - end
+  // CHECK-NEXT: ^
+
+  add w0, w1, #:got_lo12:external - end
+  cmp w0, #:got_lo12:external - end
+  // CHECK: error: Unsupported pc-relative fixup kind
+  // CHECK-NEXT: add w0, w1, #:got_lo12:external - end
+  // CHECK-NEXT: ^
+  // CHECK: error: Unsupported pc-relative fixup kind
+  // CHECK-NEXT: cmp w0, #:got_lo12:external - end
+  // CHECK-NEXT: ^
+
+  .section sec_y
+end_across_sec:
+  add w0, w1, #(end_across_sec - start)
+  cmp w0, #(end_across_sec - start)
+  // CHECK: error: Cannot represent a difference across sections
+  // CHECK-NEXT: add w0, w1, #(end_across_sec - start)
+  // CHECK-NEXT: ^
+  // CHECK: error: Cannot represent a difference across sections
+  // CHECK-NEXT: cmp w0, #(end_across_sec - start)
+  // CHECK-NEXT: ^
+
+  add w0, w1, #(sec_y - sec_x)
+  cmp w0, #(sec_y - sec_x)
+  // CHECK: error: symbol 'sec_x' can not be undefined in a subtraction expression
+  // CHECK-NEXT: add w0, w1, #(sec_y - sec_x)
+  // CHECK-NEXT: ^
+  // CHECK: error: symbol 'sec_x' can not be undefined in a subtraction expression
+  // CHECK-NEXT: cmp w0, #(sec_y - sec_x)
+  // CHECK-NEXT: ^

llvm/test/MC/AArch64/label-arithmetic-elf.s

@@ -0,0 +1,96 @@
+// RUN: llvm-mc -triple aarch64-elf -filetype=obj %s -o - | llvm-objdump -d - | FileCheck %s
+
+start:
+  .space 8
+end:
+  // CHECK-LABEL: end:
+
+  adds w0, w1, #(end - start)
+  adds x0, x1, #(end - start)
+  add w0, w1, #(end - start)
+  add x0, x1, #(end - start)
+  cmp w0, #(end - start)
+  cmp x0, #(end - start)
+  sub w0, w1, #(end - start)
+  sub x0, x1, #(end - start)
+  // CHECK: adds w0, w1, #8
+  // CHECK: adds x0, x1, #8
+  // CHECK: add w0, w1, #8
+  // CHECK: add x0, x1, #8
+  // CHECK: cmp w0, #8
+  // CHECK: cmp x0, #8
+  // CHECK: sub w0, w1, #8
+  // CHECK: sub x0, x1, #8
+
+  add w0, w1, #(end - start), lsl #12
+  cmp w0, #(end - start), lsl #12
+  // CHECK: add w0, w1, #8, lsl #12
+  // CHECK: cmp w0, #8, lsl #12
+
+  add w0, w1, #((end - start) >> 2)
+  cmp w0, #((end - start) >> 2)
+  // CHECK: add w0, w1, #2
+  // CHECK: cmp w0, #2
+
+  add w0, w1, #(end - start + 12)
+  cmp w0, #(end - start + 12)
+  // CHECK: add w0, w1, #20
+  // CHECK: cmp w0, #20
+
+  add w0, w1, #(forward - end)
+  cmp w0, #(forward - end)
+  // CHECK: add w0, w1, #320
+  // CHECK: cmp w0, #320
+
+// Add some filler so we don't have to modify #(forward - end) if we add more
+// instructions above
+.Lfiller:
+  .space 320 - (.Lfiller - end)
+
+forward:
+  .space 8
+
+.Lstart:
+  .space 8
+.Lend:
+  add w0, w1, #(.Lend - .Lstart)
+  cmp w0, #(.Lend - .Lstart)
+  // CHECK: add w0, w1, #8
+  // CHECK: cmp w0, #8
+
+.Lprivate1:
+  .space 8
+notprivate:
+  .space 8
+.Lprivate2:
+  add w0, w1, #(.Lprivate2 - .Lprivate1)
+  cmp w0, #(.Lprivate2 - .Lprivate1)
+  // CHECK: add w0, w1, #16
+  // CHECK: cmp w0, #16
+
+  .type foo, @function
+foo:
+  // CHECK-LABEL: foo:
+
+  add w0, w1, #(foo - .Lprivate2)
+  cmp w0, #(foo - .Lprivate2)
+  // CHECK: add w0, w1, #8
+  // CHECK: cmp w0, #8
+
+  ret
+
+  .type goo, @function
+goo:
+  // CHECK-LABEL: goo:
+
+  add w0, w1, #(goo - foo)
+  cmp w0, #(goo - foo)
+  // CHECK: add w0, w1, #12
+  // CHECK: cmp w0, #12
+
+  add w0, w1, #(. - goo)
+  cmp w0, #(. - goo)
+  // CHECK: add w0, w1, #8
+  // CHECK: cmp w0, #12
+
+  ret