[RISCV][MC] Reject bare symbols for the simm12 operand type

[asb]

Summary

addi a0, a0, foo and lw a0, foo(a0) and similar are now rejected. An explicit %lo and %pcrel_lo modifier is required. This matches gas behaviour.

[apazos]

LGTM, verified this patch with the fuzzer tool

[asb]

Closed by rL342487

lib/Target/RISCV/AsmParser/RISCVAsmParser.cpp

bool isSImm12() const {
     bool IsValid;
     if (!isImm())
       return false;
     bool IsConstantImm = evaluateConstantImm(Imm, VK);
     if (!IsConstantImm)
       IsValid = RISCVAsmParser::classifySymbolRef(getImm(), VK, Imm);
     else
       IsValid = isInt<12>(Imm);
-    return IsValid && (VK == RISCVMCExpr::VK_RISCV_None ||
+    return IsValid && ((IsConstantImm && VK == RISCVMCExpr::VK_RISCV_None) ||
                        VK == RISCVMCExpr::VK_RISCV_LO ||
                        VK == RISCVMCExpr::VK_RISCV_PCREL_LO);
   }
 
   bool isSImm12Lsb0() const { return isBareSimmNLsb0<12>(); }
 
   bool isUImm12() const {
     int64_t Imm;
case Match_InvalidUImm10Lsb00NonZero:
     return generateImmOutOfRangeError(
         Operands, ErrorInfo, 4, (1 << 10) - 4,
         "immediate must be a multiple of 4 bytes in the range");
   case Match_InvalidSImm10Lsb0000NonZero:
     return generateImmOutOfRangeError(
         Operands, ErrorInfo, -(1 << 9), (1 << 9) - 16,
         "immediate must be a multiple of 16 bytes and non-zero in the range");
   case Match_InvalidSImm12:
-    return generateImmOutOfRangeError(Operands, ErrorInfo, -(1 << 11),
-                                      (1 << 11) - 1);
+    return generateImmOutOfRangeError(
+        Operands, ErrorInfo, -(1 << 11), (1 << 11) - 1,
+        "operand must be a symbol with %lo/%pcrel_lo modifier or an integer in "
+        "the range");
   case Match_InvalidSImm12Lsb0:
     return generateImmOutOfRangeError(
         Operands, ErrorInfo, -(1 << 11), (1 << 11) - 2,
         "immediate must be a multiple of 2 bytes in the range");
   case Match_InvalidUImm12:
     return generateImmOutOfRangeError(Operands, ErrorInfo, 0, (1 << 12) - 1);
   case Match_InvalidSImm13Lsb0:
     return generateImmOutOfRangeError(

test/MC/RISCV/rv32d-invalid.s

 # RUN: not llvm-mc -triple riscv32 -mattr=+d < %s 2>&1 | FileCheck %s
 
 # Out of range immediates
 ## simm12
-fld ft1, -2049(a0) # CHECK: :[[@LINE]]:10: error: immediate must be an integer in the range [-2048, 2047]
-fsd ft2, 2048(a1) # CHECK: :[[@LINE]]:10: error: immediate must be an integer in the range [-2048, 2047]
+fld ft1, -2049(a0) # CHECK: :[[@LINE]]:10: error: operand must be a symbol with %lo/%pcrel_lo modifier or an integer in the range [-2048, 2047]
+fsd ft2, 2048(a1) # CHECK: :[[@LINE]]:10: error: operand must be a symbol with %lo/%pcrel_lo modifier or an integer in the range [-2048, 2047]
 
 # Memory operand not formatted correctly
-fld ft1, a0, -200 # CHECK: :[[@LINE]]:10: error: immediate must be an integer in the range [-2048, 2047]
-fsd ft2, a1, 100 # CHECK: :[[@LINE]]:10: error: immediate must be an integer in the range [-2048, 2047]
+fld ft1, a0, -200 # CHECK: :[[@LINE]]:10: error: operand must be a symbol with %lo/%pcrel_lo modifier or an integer in the range [-2048, 2047]
+fsd ft2, a1, 100 # CHECK: :[[@LINE]]:10: error: operand must be a symbol with %lo/%pcrel_lo modifier or an integer in the range [-2048, 2047]
 
 # Invalid register names
 fld ft15, 100(a0) # CHECK: :[[@LINE]]:5: error: invalid operand for instruction
 fld ft1, 100(a10) # CHECK: :[[@LINE]]:14: error: expected register
 fsgnjn.d fa100, fa2, fa3 # CHECK: :[[@LINE]]:10: error: invalid operand for instruction
 
 # Integer registers where FP regs are expected
 fadd.d a2, a1, a0 # CHECK: :[[@LINE]]:8: error: invalid operand for instruction
 
 # FP registers where integer regs are expected
 fcvt.wu.d ft2, a1 # CHECK: :[[@LINE]]:11: error: invalid operand for instruction

test/MC/RISCV/rv32f-invalid.s

 # RUN: not llvm-mc -triple riscv32 -mattr=+f < %s 2>&1 | FileCheck %s
 
 # Out of range immediates
 ## simm12
-flw ft1, -2049(a0) # CHECK: :[[@LINE]]:10: error: immediate must be an integer in the range [-2048, 2047]
-fsw ft2, 2048(a1) # CHECK: :[[@LINE]]:10: error: immediate must be an integer in the range [-2048, 2047]
+flw ft1, -2049(a0) # CHECK: :[[@LINE]]:10: error: operand must be a symbol with %lo/%pcrel_lo modifier or an integer in the range [-2048, 2047]
+fsw ft2, 2048(a1) # CHECK: :[[@LINE]]:10: error: operand must be a symbol with %lo/%pcrel_lo modifier or an integer in the range [-2048, 2047]
 
 # Memory operand not formatted correctly
-flw ft1, a0, -200 # CHECK: :[[@LINE]]:10: error: immediate must be an integer in the range [-2048, 2047]
-fsw ft2, a1, 100 # CHECK: :[[@LINE]]:10: error: immediate must be an integer in the range [-2048, 2047]
+flw ft1, a0, -200 # CHECK: :[[@LINE]]:10: error: operand must be a symbol with %lo/%pcrel_lo modifier or an integer in the range [-2048, 2047]
+fsw ft2, a1, 100 # CHECK: :[[@LINE]]:10: error: operand must be a symbol with %lo/%pcrel_lo modifier or an integer in the range [-2048, 2047]
 
 # Invalid register names
 flw ft15, 100(a0) # CHECK: :[[@LINE]]:5: error: invalid operand for instruction
 flw ft1, 100(a10) # CHECK: :[[@LINE]]:14: error: expected register
 fsgnjn.s fa100, fa2, fa3 # CHECK: :[[@LINE]]:10: error: invalid operand for instruction
 
 # Integer registers where FP regs are expected
 fmv.x.w fs7, a2 # CHECK: :[[@LINE]]:9: error: invalid operand for instruction

test/MC/RISCV/rv32i-invalid.s

 slli a0, a0, 32 # CHECK: :[[@LINE]]:14: error: immediate must be an integer in the range [0, 31]
 srli a0, a0, -1 # CHECK: :[[@LINE]]:14: error: immediate must be an integer in the range [0, 31]
 srai a0, a0, -19 # CHECK: :[[@LINE]]:14: error: immediate must be an integer in the range [0, 31]
 csrrwi a1, 0x1, -1 # CHECK: :[[@LINE]]:17: error: immediate must be an integer in the range [0, 31]
 csrrsi t1, 999, 32 # CHECK: :[[@LINE]]:17: error: immediate must be an integer in the range [0, 31]
 csrrci x0, 43, -90 # CHECK: :[[@LINE]]:16: error: immediate must be an integer in the range [0, 31]
 
 ## simm12
-ori a0, a1, -2049 # CHECK: :[[@LINE]]:13: error: immediate must be an integer in the range [-2048, 2047]
-andi ra, sp, 2048 # CHECK: :[[@LINE]]:14: error: immediate must be an integer in the range [-2048, 2047]
+ori a0, a1, -2049 # CHECK: :[[@LINE]]:13: error: operand must be a symbol with %lo/%pcrel_lo modifier or an integer in the range [-2048, 2047]
+andi ra, sp, 2048 # CHECK: :[[@LINE]]:14: error: operand must be a symbol with %lo/%pcrel_lo modifier or an integer in the range [-2048, 2047]
 
 ## uimm12
 csrrw a0, -1, a0 # CHECK: :[[@LINE]]:11: error: immediate must be an integer in the range [0, 4095]
 csrrs a0, 4096, a0 # CHECK: :[[@LINE]]:11: error: immediate must be an integer in the range [0, 4095]
 csrrs a0, -0xf, a0 # CHECK: :[[@LINE]]:11: error: immediate must be an integer in the range [0, 4095]
 csrrc a0, 0x1000, a0 # CHECK: :[[@LINE]]:11: error: immediate must be an integer in the range [0, 4095]
 csrrwi a0, -50, 0 # CHECK: :[[@LINE]]:12: error: immediate must be an integer in the range [0, 4095]
 csrrsi a0, 4097, a0 # CHECK: :[[@LINE]]:12: error: immediate must be an integer in the range [0, 4095]

 srai a0, a0, %hi(2) # CHECK: :[[@LINE]]:14: error: immediate must be an integer in the range [0, 31]
 csrrwi a1, 0x1, %hi(b) # CHECK: :[[@LINE]]:17: error: immediate must be an integer in the range [0, 31]
 csrrsi t1, 999, %pcrel_hi(3) # CHECK: :[[@LINE]]:17: error: immediate must be an integer in the range [0, 31]
 csrrci x0, 43, %pcrel_hi(c) # CHECK: :[[@LINE]]:16: error: immediate must be an integer in the range [0, 31]
 csrrsi t1, 999, %pcrel_lo(4) # CHECK: :[[@LINE]]:17: error: immediate must be an integer in the range [0, 31]
 csrrci x0, 43, %pcrel_lo(d) # CHECK: :[[@LINE]]:16: error: immediate must be an integer in the range [0, 31]
 
 ## simm12
-ori a0, a1, %hi(foo) # CHECK: :[[@LINE]]:13: error: immediate must be an integer in the range [-2048, 2047]
-andi ra, sp, %pcrel_hi(123) # CHECK: :[[@LINE]]:14: error: immediate must be an integer in the range [-2048, 2047]
-xori a2, a3, %hi(345) # CHECK: :[[@LINE]]:14: error: immediate must be an integer in the range [-2048, 2047]
-add a1, a2, (a3) # CHECK: :[[@LINE]]:13: error: immediate must be an integer in the range [-2048, 2047]
+ori a0, a1, %hi(foo) # CHECK: :[[@LINE]]:13: error: operand must be a symbol with %lo/%pcrel_lo modifier or an integer in the range [-2048, 2047]
+andi ra, sp, %pcrel_hi(123) # CHECK: :[[@LINE]]:14: error: operand must be a symbol with %lo/%pcrel_lo modifier or an integer in the range [-2048, 2047]
+xori a2, a3, %hi(345) # CHECK: :[[@LINE]]:14: error: operand must be a symbol with %lo/%pcrel_lo modifier or an integer in the range [-2048, 2047]
+add a1, a2, (a3) # CHECK: :[[@LINE]]:13: error: operand must be a symbol with %lo/%pcrel_lo modifier or an integer in the range [-2048, 2047]
+add a1, a2, foo # CHECK: :[[@LINE]]:13: error: operand must be a symbol with %lo/%pcrel_lo modifier or an integer in the range [-2048, 2047]
 
 ## uimm12
 csrrw a0, %lo(1), a0 # CHECK: :[[@LINE]]:11: error: immediate must be an integer in the range [0, 4095]
 csrrs a0, %lo(a), a0 # CHECK: :[[@LINE]]:11: error: immediate must be an integer in the range [0, 4095]
 csrrs a0, %hi(2), a0 # CHECK: :[[@LINE]]:11: error: immediate must be an integer in the range [0, 4095]
 csrrc a0, %hi(b), a0 # CHECK: :[[@LINE]]:11: error: immediate must be an integer in the range [0, 4095]
 csrrwi a0, %pcrel_hi(3), 0 # CHECK: :[[@LINE]]:12: error: immediate must be an integer in the range [0, 4095]
 csrrsi a0, %pcrel_hi(c), a0 # CHECK: :[[@LINE]]:12: error: immediate must be an integer in the range [0, 4095]

 xori sp, 22, 220 # CHECK: :[[@LINE]]:10: error: invalid operand for instruction
 sub t0, t2, 1 # CHECK: :[[@LINE]]:13: error: invalid operand for instruction
 
 # Too many operands
 add ra, zero, zero, zero # CHECK: :[[@LINE]]:21: error: invalid operand for instruction
 sltiu s2, s3, 0x50, 0x60 # CHECK: :[[@LINE]]:21: error: invalid operand for instruction
 
 # Memory operand not formatted correctly
-lw a4, a5, 111 # CHECK: :[[@LINE]]:8: error: immediate must be an integer in the range [-2048, 2047]
+lw a4, a5, 111 # CHECK: :[[@LINE]]:8: error: operand must be a symbol with %lo/%pcrel_lo modifier or an integer in the range [-2048, 2047]
 
 # Too few operands
 ori a0, a1 # CHECK: :[[@LINE]]:1: error: too few operands for instruction
 xor s2, s2 # CHECK: :[[@LINE]]:1: error: too few operands for instruction
 # FIXME: Fix jal behavior to interpret a3 as a symbol rather than a register.
 jal a3     # CHECK: :[[@LINE]]:1: error: too few operands for instruction
 
 # Instruction not in the base ISA

test/MC/RISCV/rv32i-valid.s

 # CHECK-ASM: encoding: [0x03,0x13,0x00,0x80]
 lh t1, %lo(2048)(zero)
 # CHECK-ASM-AND-OBJ: lh sp, 2047(a0)
 # CHECK-ASM: encoding: [0x03,0x11,0xf5,0x7f]
 lh sp, 2047(a0)
 # CHECK-ASM-AND-OBJ: lw a0, 97(a2)
 # CHECK-ASM: encoding: [0x03,0x25,0x16,0x06]
 lw a0, 97(a2)
-# CHECK-ASM-AND-OBJ: lbu s5, 0(s6)
-# CHECK-ASM: encoding: [0x83,0x4a,0x0b,0x00]
-lbu s5, 0(s6)
-# CHECK-ASM-AND-OBJ: lhu t3, 255(t3)
-# CHECK-ASM: encoding: [0x03,0x5e,0xfe,0x0f]
-lhu t3, 255(t3)
+# CHECK-ASM: lbu s5, %lo(foo)(s6)
+# CHECK-ASM: encoding: [0x83,0x4a,0bAAAA1011,A]
+# CHECK-OBJ: lbu s5, 0(s6)
+# CHECK-OBJ: R_RISCV_LO12
+lbu s5, %lo(foo)(s6)
+# CHECK-ASM: lhu t3, %pcrel_lo(foo)(t3)
+# CHECK-ASM: encoding: [0x03,0x5e,0bAAAA1110,A]
+# CHECK-OBJ: lhu t3, 0(t3)
+# CHECK-OBJ: R_RISCV_PCREL_LO12
+lhu t3, %pcrel_lo(foo)(t3)
 
 # CHECK-ASM-AND-OBJ: sb a0, 2047(a2)
 # CHECK-ASM: encoding: [0xa3,0x0f,0xa6,0x7e]
 sb a0, 2047(a2)
 # CHECK-ASM-AND-OBJ: sh t3, -2048(t5)
 # CHECK-ASM: encoding: [0x23,0x10,0xcf,0x81]
 sh t3, -2048(t5)
 # CHECK-ASM-AND-OBJ: sh t3, -2048(t5)
 # CHECK-ASM: encoding: [0x23,0x10,0xcf,0x81]
 sh t3, %lo(2048)(t5)
 # CHECK-ASM-AND-OBJ: sw ra, 999(zero)
 # CHECK-ASM: encoding: [0xa3,0x23,0x10,0x3e]
 sw ra, 999(zero)
 
 # CHECK-ASM-AND-OBJ: addi ra, sp, 2
 # CHECK-ASM: encoding: [0x93,0x00,0x21,0x00]
 addi ra, sp, 2
+# CHECK-ASM: addi ra, sp, %lo(foo)
+# CHECK-ASM: encoding: [0x93,0x00,0bAAAA0001,A]
+# CHECK-OBJ: addi ra, sp, 0
+# CHECK-OBJ: R_RISCV_LO12
+addi ra, sp, %lo(foo)
 # CHECK-ASM-AND-OBJ: slti a0, a2, -20
 # CHECK-ASM: encoding: [0x13,0x25,0xc6,0xfe]
 slti a0, a2, -20
 # CHECK-ASM-AND-OBJ: sltiu s2, s3, 80
 # CHECK-ASM: encoding: [0x13,0xb9,0x09,0x05]
 sltiu s2, s3, 0x50
 # CHECK-ASM-AND-OBJ: xori tp, t1, -99
 # CHECK-ASM: encoding: [0x13,0x42,0xd3,0xf9]

test/MC/RISCV/rv64i-invalid.s

 # RUN: not llvm-mc -triple riscv64 < %s 2>&1 | FileCheck %s
 
 # Out of range immediates
 ## uimm5
 slliw a0, a0, 32 # CHECK: :[[@LINE]]:15: error: immediate must be an integer in the range [0, 31]
 srliw a0, a0, -1 # CHECK: :[[@LINE]]:15: error: immediate must be an integer in the range [0, 31]
 sraiw a0, a0, -19 # CHECK: :[[@LINE]]:15: error: immediate must be an integer in the range [0, 31]
 
 ## simm12
-addiw a0, a1, -2049 # CHECK: :[[@LINE]]:15: error: immediate must be an integer in the range [-2048, 2047]
-ld ra, 2048(sp) # CHECK: :[[@LINE]]:8: error: immediate must be an integer in the range [-2048, 2047]
+addiw a0, a1, -2049 # CHECK: :[[@LINE]]:15: error: operand must be a symbol with %lo/%pcrel_lo modifier or an integer in the range [-2048, 2047]
+ld ra, 2048(sp) # CHECK: :[[@LINE]]:8: error: operand must be a symbol with %lo/%pcrel_lo modifier or an integer in the range [-2048, 2047]
 
 # Illegal operand modifier
 ## uimm5
 slliw a0, a0, %lo(1) # CHECK: :[[@LINE]]:15: error: immediate must be an integer in the range [0, 31]
 srliw a0, a0, %lo(a) # CHECK: :[[@LINE]]:15: error: immediate must be an integer in the range [0, 31]
 sraiw a0, a0, %hi(2) # CHECK: :[[@LINE]]:15: error: immediate must be an integer in the range [0, 31]
 
 ## simm12
-addiw a0, a1, %hi(foo) # CHECK: :[[@LINE]]:15: error: immediate must be an integer in the range [-2048, 2047]
+addiw a0, a1, %hi(foo) # CHECK: :[[@LINE]]:15: error: operand must be a symbol with %lo/%pcrel_lo modifier or an integer in the range [-2048, 2047]