Index: lib/Transforms/InstCombine/InstCombineCompares.cpp
===================================================================
--- lib/Transforms/InstCombine/InstCombineCompares.cpp
+++ lib/Transforms/InstCombine/InstCombineCompares.cpp
@@ -4498,8 +4498,14 @@
     if (SelectInst *SI = dyn_cast<SelectInst>(I.user_back())) {
       Value *A, *B;
       SelectPatternResult SPR = matchSelectPattern(SI, A, B);
-      if (SPR.Flavor != SPF_UNKNOWN)
+      if (SPR.Flavor != SPF_UNKNOWN) {
+        // This may be expensive in compile-time, and transforms based on known
+        // bits can make further analysis more difficult, so we use it as the
+        // last resort if we cannot do anything better.
+        if (Instruction *Res = foldICmpUsingKnownBits(I))
+          return Res;
         return nullptr;
+      }
     }
 
   // Do this after checking for min/max to prevent infinite looping.
Index: test/Transforms/InstCombine/max_known_bits.ll
===================================================================
--- test/Transforms/InstCombine/max_known_bits.ll
+++ test/Transforms/InstCombine/max_known_bits.ll
@@ -1,17 +1,12 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
 ; RUN: opt -S -instcombine < %s | FileCheck %s
-; TODO: The entire thing should be folded to and i16 %0, 255.
+; The entire thing should be folded to and i16 %0, 255.
 
 define i16 @foo(i16 )  {
 ; CHECK-LABEL: @foo(
 ; CHECK-NEXT:  entry:
 ; CHECK-NEXT:    [[TMP1:%.*]] = and i16 [[TMP0:%.*]], 255
-; CHECK-NEXT:    [[TMP2:%.*]] = zext i16 [[TMP1]] to i32
-; CHECK-NEXT:    [[TMP3:%.*]] = icmp ult i32 [[TMP2]], 255
-; CHECK-NEXT:    [[TMP4:%.*]] = select i1 [[TMP3]], i32 [[TMP2]], i32 255
-; CHECK-NEXT:    [[TMP5:%.*]] = trunc i32 [[TMP4]] to i16
-; CHECK-NEXT:    [[TMP6:%.*]] = and i16 [[TMP5]], 255
-; CHECK-NEXT:    ret i16 [[TMP6]]
+; CHECK-NEXT:    ret i16 [[TMP1]]
 ;
 entry:
   %1 = and i16 %0, 255