From 74188ea645ff546e35873235cb67e4dd32dbe017 Mon Sep 17 00:00:00 2001
From: Lewis Revill <lewis.revill@embecosm.com>
Date: Wed, 19 Jun 2019 10:11:13 +0000
Subject: [PATCH] [RISCV] Fix failure to parse parenthesized immediates

Since the parser attempts to parse an operand as a register with
parentheses before parsing it as an immediate, immediates in
parentheses should not be parsed by parseRegister. However in the case
where the immediate does not start with an identifier, the LParen is not
unlexed and so the RParen causes an unexpected token error.

This patch adds the missing UnLex, and modifies the existing UnLex to
not use a buffered token, as it should always be unlexing an LParen.

Differential Revision: https://reviews.llvm.org/D57319


git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@363782 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/Target/RISCV/AsmParser/RISCVAsmParser.cpp | 11 ++++++++---
 test/MC/RISCV/rv32i-valid.s                   | 24 ++++++++++++++++++++++++
 2 files changed, 32 insertions(+), 3 deletions(-)

diff --git a/lib/Target/RISCV/AsmParser/RISCVAsmParser.cpp b/lib/Target/RISCV/AsmParser/RISCVAsmParser.cpp
index bac43187ca7..083d4b77ccc 100644
--- a/lib/Target/RISCV/AsmParser/RISCVAsmParser.cpp
+++ b/lib/Target/RISCV/AsmParser/RISCVAsmParser.cpp
@@ -997,19 +997,24 @@ OperandMatchResultTy RISCVAsmParser::parseRegister(OperandVector &Operands,
                                                    bool AllowParens) {
   SMLoc FirstS = getLoc();
   bool HadParens = false;
-  AsmToken Buf[2];
+  AsmToken LParen;
 
-  // If this a parenthesised register name is allowed, parse it atomically
+  // If this is an LParen and a parenthesised register name is allowed, parse it
+  // atomically.
   if (AllowParens && getLexer().is(AsmToken::LParen)) {
+    AsmToken Buf[2];
     size_t ReadCount = getLexer().peekTokens(Buf);
     if (ReadCount == 2 && Buf[1].getKind() == AsmToken::RParen) {
       HadParens = true;
+      LParen = getParser().getTok();
       getParser().Lex(); // Eat '('
     }
   }
 
   switch (getLexer().getKind()) {
   default:
+    if (HadParens)
+      getLexer().UnLex(LParen);
     return MatchOperand_NoMatch;
   case AsmToken::Identifier:
     StringRef Name = getLexer().getTok().getIdentifier();
@@ -1018,7 +1023,7 @@ OperandMatchResultTy RISCVAsmParser::parseRegister(OperandVector &Operands,
 
     if (RegNo == 0) {
       if (HadParens)
-        getLexer().UnLex(Buf[0]);
+        getLexer().UnLex(LParen);
       return MatchOperand_NoMatch;
     }
     if (HadParens)
diff --git a/test/MC/RISCV/rv32i-valid.s b/test/MC/RISCV/rv32i-valid.s
index 01b46b58dd6..7b711a32231 100644
--- a/test/MC/RISCV/rv32i-valid.s
+++ b/test/MC/RISCV/rv32i-valid.s
@@ -84,6 +84,12 @@ jal a0, a0
 # CHECK-ASM-AND-OBJ: jal a0, 30
 # CHECK-ASM: encoding: [0x6f,0x05,0xe0,0x01]
 jal a0, CONST
+# CHECK-ASM-AND-OBJ: jal s0, 0
+# CHECK-ASM: encoding: [0x6f,0x04,0x00,0x00]
+jal s0, (0)
+# CHECK-ASM-AND-OBJ: jal s0, 156
+# CHECK-ASM: encoding: [0x6f,0x04,0xc0,0x09]
+jal s0, (0xff-99)
 
 # CHECK-ASM-AND-OBJ: jalr a0, a1, -2048
 # CHECK-ASM: encoding: [0x67,0x85,0x05,0x80]
@@ -154,6 +160,12 @@ lhu t3, %pcrel_lo(foo)(t3)
 # CHECK-ASM-AND-OBJ: lb t0, 30(t1)
 # CHECK-ASM: encoding: [0x83,0x02,0xe3,0x01]
 lb t0, CONST(t1)
+# CHECK-ASM-AND-OBJ: lb s0, 0(s1)
+# CHECK-ASM: encoding: [0x03,0x84,0x04,0x00]
+lb s0, (0)(s1)
+# CHECK-ASM-AND-OBJ: lb s0, 156(s1)
+# CHECK-ASM: encoding: [0x03,0x84,0xc4,0x09]
+lb s0, (0xff-99)(s1)
 
 # CHECK-ASM-AND-OBJ: sb a0, 2047(a2)
 # CHECK-ASM: encoding: [0xa3,0x0f,0xa6,0x7e]
@@ -170,6 +182,12 @@ sw ra, 999(zero)
 # CHECK-ASM-AND-OBJ: sw a0, 30(t0)
 # CHECK-ASM: encoding: [0x23,0xaf,0xa2,0x00]
 sw a0, CONST(t0)
+# CHECK-ASM-AND-OBJ: sw s0, 0(s1)
+# CHECK-ASM: encoding: [0x23,0xa0,0x84,0x00]
+sw s0, (0)(s1)
+# CHECK-ASM-AND-OBJ: sw s0, 156(s1)
+# CHECK-ASM: encoding: [0x23,0xae,0x84,0x08]
+sw s0, (0xff-99)(s1)
 
 # CHECK-ASM-AND-OBJ: addi ra, sp, 2
 # CHECK-ASM: encoding: [0x93,0x00,0x21,0x00]
@@ -182,6 +200,12 @@ addi ra, sp, %lo(foo)
 # CHECK-ASM-AND-OBJ: addi ra, sp, 30
 # CHECK-ASM: encoding: [0x93,0x00,0xe1,0x01]
 addi ra, sp, CONST
+# CHECK-ASM-AND-OBJ: addi ra, sp, 0
+# CHECK-ASM: encoding: [0x93,0x00,0x01,0x00]
+addi ra, sp, (0)
+# CHECK-ASM-AND-OBJ: addi ra, sp, 156
+# CHECK-ASM: encoding: [0x93,0x00,0xc1,0x09]
+addi ra, sp, (0xff-99)
 # CHECK-ASM-AND-OBJ: slti a0, a2, -20
 # CHECK-ASM: encoding: [0x13,0x25,0xc6,0xfe]
 slti a0, a2, -20
-- 
2.11.0