[MC] Fix undefined behavior in MCInstPrinter::formatHex

Passing INT64_MIN to MCInstPrinter::formatHex triggers undefined
behavior because the negation of -9223372036854775808 cannot be
represented in type 'int64_t' (aka 'long long'). This patch puts a
workaround in place to just print the hex value directly.

A possible alternative involves using a small helper functions that uses
(implementation) defined conversions to achieve the desirable value:

  static int64_t helper(int64_t V) {
    auto U = static_cast<uint64_t>(V);
    return V < 0 ? -U : U;
  }

The underlying problem is that MCInstPrinter::formatHex(int64_t) returns
a format_object<int64_t> and should really return a
format_object<uint64_t>. However, that's not possible because formatImm
needs to be able to print both as decimal (where a signed is required)
and hex (where we'd prefer to always have an unsigned).

  format_object<int64_t> formatImm(int64_t Value) const {
    return PrintImmHex ? formatHex(Value) : formatDec(Value);
  }

Differential revision: https://reviews.llvm.org/D67236

llvm-svn: 371159

1 files changed, 13 insertions, 12 deletions

diff --git a/llvm/lib/MC/MCInstPrinter.cpp b/llvm/lib/MC/MCInstPrinter.cpp
index c462dea3c8c..c5c06f323e6 100644
--- a/llvm/lib/MC/MCInstPrinter.cpp
+++ b/llvm/lib/MC/MCInstPrinter.cpp
@@ -83,24 +83,25 @@ format_object<int64_t> MCInstPrinter::formatDec(int64_t Value) const {
 }
 
 format_object<int64_t> MCInstPrinter::formatHex(int64_t Value) const {
-  switch(PrintHexStyle) {
+  switch (PrintHexStyle) {
   case HexStyle::C:
-    if (Value < 0)
+    if (Value < 0) {
+      if (Value == std::numeric_limits<int64_t>::min())
+        return format<int64_t>("-0x8000000000000000", Value);
       return format("-0x%" PRIx64, -Value);
-    else
-      return format("0x%" PRIx64, Value);
+    }
+    return format("0x%" PRIx64, Value);
   case HexStyle::Asm:
     if (Value < 0) {
-      if (needsLeadingZero((uint64_t)(-Value)))
+      if (Value == std::numeric_limits<int64_t>::min())
+        return format<int64_t>("-8000000000000000h", Value);
+      if (needsLeadingZero(-(uint64_t)(Value)))
         return format("-0%" PRIx64 "h", -Value);
-      else
-        return format("-%" PRIx64 "h", -Value);
-    } else {
-      if (needsLeadingZero((uint64_t)(Value)))
-        return format("0%" PRIx64 "h", Value);
-      else
-        return format("%" PRIx64 "h", Value);
+      return format("-%" PRIx64 "h", -Value);
     }
+    if (needsLeadingZero((uint64_t)(Value)))
+      return format("0%" PRIx64 "h", Value);
+    return format("%" PRIx64 "h", Value);
   }
   llvm_unreachable("unsupported print style");
 }