Index: lib/Target/X86/X86ISelDAGToDAG.cpp
===================================================================
--- lib/Target/X86/X86ISelDAGToDAG.cpp
+++ lib/Target/X86/X86ISelDAGToDAG.cpp
@@ -2946,25 +2946,36 @@
 
   SDLoc DL(Node);
 
+  // If we do *NOT* have BMI2, let's find out if the if the 'X' is *logically*
+  // shifted (potentially with trunc inbetween), and if so look past truncation.
+  MVT XVT = NVT;
+  if (!Subtarget->hasBMI2() && X.getOpcode() == ISD::TRUNCATE &&
+      X.getOperand(0).getOpcode() == ISD::SRL) {
+    assert(NVT == MVT::i32 && "Expected target valuetype to be i32");
+    X = X.getOperand(0);
+    XVT = X.getSimpleValueType();
+    assert(XVT == MVT::i64 && "Expected truncation from i64");
+  }
+
   SDValue OrigNBits = NBits;
-  if (NBits.getValueType() != NVT) {
+  if (NBits.getValueType() != XVT) {
     // Truncate the shift amount.
     NBits = CurDAG->getNode(ISD::TRUNCATE, DL, MVT::i8, NBits);
     insertDAGNode(*CurDAG, OrigNBits, NBits);
 
-    // Insert 8-bit NBits into lowest 8 bits of NVT-sized (32 or 64-bit)
+    // Insert 8-bit NBits into lowest 8 bits of XVT-sized (32 or 64-bit)
     // register. All the other bits are undefined, we do not care about them.
     SDValue ImplDef =
-        SDValue(CurDAG->getMachineNode(TargetOpcode::IMPLICIT_DEF, DL, NVT), 0);
+        SDValue(CurDAG->getMachineNode(TargetOpcode::IMPLICIT_DEF, DL, XVT), 0);
     insertDAGNode(*CurDAG, OrigNBits, ImplDef);
     NBits =
-        CurDAG->getTargetInsertSubreg(X86::sub_8bit, DL, NVT, ImplDef, NBits);
+        CurDAG->getTargetInsertSubreg(X86::sub_8bit, DL, XVT, ImplDef, NBits);
     insertDAGNode(*CurDAG, OrigNBits, NBits);
   }
 
   if (Subtarget->hasBMI2()) {
     // Great, just emit the the BZHI..
-    SDValue Extract = CurDAG->getNode(X86ISD::BZHI, DL, NVT, X, NBits);
+    SDValue Extract = CurDAG->getNode(X86ISD::BZHI, DL, XVT, X, NBits);
     ReplaceNode(Node, Extract.getNode());
     SelectCode(Extract.getNode());
     return true;
@@ -2979,7 +2990,7 @@
   // Shift NBits left by 8 bits, thus producing 'control'.
   // This makes the low 8 bits to be zero.
   SDValue C8 = CurDAG->getConstant(8, DL, MVT::i8);
-  SDValue Control = CurDAG->getNode(ISD::SHL, DL, NVT, NBits, C8);
+  SDValue Control = CurDAG->getNode(ISD::SHL, DL, XVT, NBits, C8);
   insertDAGNode(*CurDAG, OrigNBits, Control);
 
   // If the 'X' is *logically* shifted, we can fold that shift into 'control'.
@@ -2992,16 +3003,23 @@
 
     // Now, *zero*-extend the shift amount. The bits 8...15 *must* be zero!
     SDValue OrigShiftAmt = ShiftAmt;
-    ShiftAmt = CurDAG->getNode(ISD::ZERO_EXTEND, DL, NVT, ShiftAmt);
+    ShiftAmt = CurDAG->getNode(ISD::ZERO_EXTEND, DL, XVT, ShiftAmt);
     insertDAGNode(*CurDAG, OrigShiftAmt, ShiftAmt);
 
     // And now 'or' these low 8 bits of shift amount into the 'control'.
-    Control = CurDAG->getNode(ISD::OR, DL, NVT, Control, ShiftAmt);
+    Control = CurDAG->getNode(ISD::OR, DL, XVT, Control, ShiftAmt);
     insertDAGNode(*CurDAG, OrigNBits, Control);
   }
 
   // And finally, form the BEXTR itself.
-  SDValue Extract = CurDAG->getNode(X86ISD::BEXTR, DL, NVT, X, Control);
+  SDValue Extract = CurDAG->getNode(X86ISD::BEXTR, DL, XVT, X, Control);
+
+  // The 'X' was originally truncated. Do that now.
+  if (XVT != NVT) {
+    insertDAGNode(*CurDAG, OrigNBits, Extract);
+    Extract = CurDAG->getNode(ISD::TRUNCATE, DL, NVT, Extract);
+  }
+
   ReplaceNode(Node, Extract.getNode());
   SelectCode(Extract.getNode());
 
Index: test/CodeGen/X86/extract-bits.ll
===================================================================
--- test/CodeGen/X86/extract-bits.ll
+++ test/CodeGen/X86/extract-bits.ll
@@ -1828,11 +1828,12 @@
 ;
 ; X64-BMI1NOTBM-LABEL: bextr64_32_a1:
 ; X64-BMI1NOTBM:       # %bb.0:
-; X64-BMI1NOTBM-NEXT:    movq %rsi, %rcx
-; X64-BMI1NOTBM-NEXT:    # kill: def $cl killed $cl killed $rcx
-; X64-BMI1NOTBM-NEXT:    shrq %cl, %rdi
-; X64-BMI1NOTBM-NEXT:    shll $8, %edx
-; X64-BMI1NOTBM-NEXT:    bextrl %edx, %edi, %eax
+; X64-BMI1NOTBM-NEXT:    # kill: def $edx killed $edx def $rdx
+; X64-BMI1NOTBM-NEXT:    shlq $8, %rdx
+; X64-BMI1NOTBM-NEXT:    movzbl %sil, %eax
+; X64-BMI1NOTBM-NEXT:    orq %rdx, %rax
+; X64-BMI1NOTBM-NEXT:    bextrq %rax, %rdi, %rax
+; X64-BMI1NOTBM-NEXT:    # kill: def $eax killed $eax killed $rax
 ; X64-BMI1NOTBM-NEXT:    retq
 ;
 ; X64-BMI1BMI2-LABEL: bextr64_32_a1:
@@ -1953,21 +1954,24 @@
 ;
 ; X64-BMI1NOTBM-LABEL: bextr64_32_a1_trunc_extrause:
 ; X64-BMI1NOTBM:       # %bb.0:
-; X64-BMI1NOTBM-NEXT:    pushq %rbp
+; X64-BMI1NOTBM-NEXT:    pushq %r15
+; X64-BMI1NOTBM-NEXT:    pushq %r14
 ; X64-BMI1NOTBM-NEXT:    pushq %rbx
-; X64-BMI1NOTBM-NEXT:    pushq %rax
-; X64-BMI1NOTBM-NEXT:    movl %edx, %ebp
-; X64-BMI1NOTBM-NEXT:    movq %rsi, %rcx
-; X64-BMI1NOTBM-NEXT:    movq %rdi, %rbx
-; X64-BMI1NOTBM-NEXT:    # kill: def $cl killed $cl killed $rcx
-; X64-BMI1NOTBM-NEXT:    shrq %cl, %rbx
-; X64-BMI1NOTBM-NEXT:    movl %ebx, %edi
+; X64-BMI1NOTBM-NEXT:    movl %edx, %ebx
+; X64-BMI1NOTBM-NEXT:    movq %rsi, %r14
+; X64-BMI1NOTBM-NEXT:    movq %rdi, %r15
+; X64-BMI1NOTBM-NEXT:    movl %r14d, %ecx
+; X64-BMI1NOTBM-NEXT:    shrq %cl, %rdi
+; X64-BMI1NOTBM-NEXT:    # kill: def $edi killed $edi killed $rdi
 ; X64-BMI1NOTBM-NEXT:    callq use32
-; X64-BMI1NOTBM-NEXT:    shll $8, %ebp
-; X64-BMI1NOTBM-NEXT:    bextrl %ebp, %ebx, %eax
-; X64-BMI1NOTBM-NEXT:    addq $8, %rsp
+; X64-BMI1NOTBM-NEXT:    shlq $8, %rbx
+; X64-BMI1NOTBM-NEXT:    movzbl %r14b, %eax
+; X64-BMI1NOTBM-NEXT:    orq %rbx, %rax
+; X64-BMI1NOTBM-NEXT:    bextrq %rax, %r15, %rax
+; X64-BMI1NOTBM-NEXT:    # kill: def $eax killed $eax killed $rax
 ; X64-BMI1NOTBM-NEXT:    popq %rbx
-; X64-BMI1NOTBM-NEXT:    popq %rbp
+; X64-BMI1NOTBM-NEXT:    popq %r14
+; X64-BMI1NOTBM-NEXT:    popq %r15
 ; X64-BMI1NOTBM-NEXT:    retq
 ;
 ; X64-BMI1BMI2-LABEL: bextr64_32_a1_trunc_extrause:
@@ -2074,11 +2078,12 @@
 ;
 ; X64-BMI1NOTBM-LABEL: bextr64_32_a2:
 ; X64-BMI1NOTBM:       # %bb.0:
-; X64-BMI1NOTBM-NEXT:    movq %rsi, %rcx
-; X64-BMI1NOTBM-NEXT:    # kill: def $cl killed $cl killed $rcx
-; X64-BMI1NOTBM-NEXT:    shrq %cl, %rdi
-; X64-BMI1NOTBM-NEXT:    shll $8, %edx
-; X64-BMI1NOTBM-NEXT:    bextrl %edx, %edi, %eax
+; X64-BMI1NOTBM-NEXT:    # kill: def $edx killed $edx def $rdx
+; X64-BMI1NOTBM-NEXT:    shlq $8, %rdx
+; X64-BMI1NOTBM-NEXT:    movzbl %sil, %eax
+; X64-BMI1NOTBM-NEXT:    orq %rdx, %rax
+; X64-BMI1NOTBM-NEXT:    bextrq %rax, %rdi, %rax
+; X64-BMI1NOTBM-NEXT:    # kill: def $eax killed $eax killed $rax
 ; X64-BMI1NOTBM-NEXT:    retq
 ;
 ; X64-BMI1BMI2-LABEL: bextr64_32_a2:
@@ -3660,11 +3665,12 @@
 ;
 ; X64-BMI1NOTBM-LABEL: bextr64_32_b1:
 ; X64-BMI1NOTBM:       # %bb.0:
-; X64-BMI1NOTBM-NEXT:    movq %rsi, %rcx
-; X64-BMI1NOTBM-NEXT:    # kill: def $cl killed $cl killed $rcx
-; X64-BMI1NOTBM-NEXT:    shrq %cl, %rdi
-; X64-BMI1NOTBM-NEXT:    shll $8, %edx
-; X64-BMI1NOTBM-NEXT:    bextrl %edx, %edi, %eax
+; X64-BMI1NOTBM-NEXT:    # kill: def $edx killed $edx def $rdx
+; X64-BMI1NOTBM-NEXT:    shlq $8, %rdx
+; X64-BMI1NOTBM-NEXT:    movzbl %sil, %eax
+; X64-BMI1NOTBM-NEXT:    orq %rdx, %rax
+; X64-BMI1NOTBM-NEXT:    bextrq %rax, %rdi, %rax
+; X64-BMI1NOTBM-NEXT:    # kill: def $eax killed $eax killed $rax
 ; X64-BMI1NOTBM-NEXT:    retq
 ;
 ; X64-BMI1BMI2-LABEL: bextr64_32_b1:
@@ -3762,11 +3768,12 @@
 ;
 ; X64-BMI1NOTBM-LABEL: bextr64_32_b2:
 ; X64-BMI1NOTBM:       # %bb.0:
-; X64-BMI1NOTBM-NEXT:    movq %rsi, %rcx
-; X64-BMI1NOTBM-NEXT:    # kill: def $cl killed $cl killed $rcx
-; X64-BMI1NOTBM-NEXT:    shrq %cl, %rdi
-; X64-BMI1NOTBM-NEXT:    shll $8, %edx
-; X64-BMI1NOTBM-NEXT:    bextrl %edx, %edi, %eax
+; X64-BMI1NOTBM-NEXT:    # kill: def $edx killed $edx def $rdx
+; X64-BMI1NOTBM-NEXT:    shlq $8, %rdx
+; X64-BMI1NOTBM-NEXT:    movzbl %sil, %eax
+; X64-BMI1NOTBM-NEXT:    orq %rdx, %rax
+; X64-BMI1NOTBM-NEXT:    bextrq %rax, %rdi, %rax
+; X64-BMI1NOTBM-NEXT:    # kill: def $eax killed $eax killed $rax
 ; X64-BMI1NOTBM-NEXT:    retq
 ;
 ; X64-BMI1BMI2-LABEL: bextr64_32_b2:
@@ -6131,11 +6138,12 @@
 ;
 ; X64-BMI1NOTBM-LABEL: bextr64_32_c1:
 ; X64-BMI1NOTBM:       # %bb.0:
-; X64-BMI1NOTBM-NEXT:    movq %rsi, %rcx
-; X64-BMI1NOTBM-NEXT:    # kill: def $cl killed $cl killed $rcx
-; X64-BMI1NOTBM-NEXT:    shrq %cl, %rdi
-; X64-BMI1NOTBM-NEXT:    shll $8, %edx
-; X64-BMI1NOTBM-NEXT:    bextrl %edx, %edi, %eax
+; X64-BMI1NOTBM-NEXT:    # kill: def $edx killed $edx def $rdx
+; X64-BMI1NOTBM-NEXT:    shlq $8, %rdx
+; X64-BMI1NOTBM-NEXT:    movzbl %sil, %eax
+; X64-BMI1NOTBM-NEXT:    orq %rdx, %rax
+; X64-BMI1NOTBM-NEXT:    bextrq %rax, %rdi, %rax
+; X64-BMI1NOTBM-NEXT:    # kill: def $eax killed $eax killed $rax
 ; X64-BMI1NOTBM-NEXT:    retq
 ;
 ; X64-BMI1BMI2-LABEL: bextr64_32_c1:
@@ -6230,11 +6238,12 @@
 ;
 ; X64-BMI1NOTBM-LABEL: bextr64_32_c2:
 ; X64-BMI1NOTBM:       # %bb.0:
-; X64-BMI1NOTBM-NEXT:    movq %rsi, %rcx
-; X64-BMI1NOTBM-NEXT:    # kill: def $cl killed $cl killed $rcx
-; X64-BMI1NOTBM-NEXT:    shrq %cl, %rdi
-; X64-BMI1NOTBM-NEXT:    shll $8, %edx
-; X64-BMI1NOTBM-NEXT:    bextrl %edx, %edi, %eax
+; X64-BMI1NOTBM-NEXT:    # kill: def $edx killed $edx def $rdx
+; X64-BMI1NOTBM-NEXT:    shlq $8, %rdx
+; X64-BMI1NOTBM-NEXT:    movzbl %sil, %eax
+; X64-BMI1NOTBM-NEXT:    orq %rdx, %rax
+; X64-BMI1NOTBM-NEXT:    bextrq %rax, %rdi, %rax
+; X64-BMI1NOTBM-NEXT:    # kill: def $eax killed $eax killed $rax
 ; X64-BMI1NOTBM-NEXT:    retq
 ;
 ; X64-BMI1BMI2-LABEL: bextr64_32_c2:
@@ -7756,11 +7765,12 @@
 ;
 ; X64-BMI1NOTBM-LABEL: bextr64_32_d1:
 ; X64-BMI1NOTBM:       # %bb.0:
-; X64-BMI1NOTBM-NEXT:    movq %rsi, %rcx
-; X64-BMI1NOTBM-NEXT:    # kill: def $cl killed $cl killed $rcx
-; X64-BMI1NOTBM-NEXT:    shrq %cl, %rdi
-; X64-BMI1NOTBM-NEXT:    shll $8, %edx
-; X64-BMI1NOTBM-NEXT:    bextrl %edx, %edi, %eax
+; X64-BMI1NOTBM-NEXT:    # kill: def $edx killed $edx def $rdx
+; X64-BMI1NOTBM-NEXT:    shlq $8, %rdx
+; X64-BMI1NOTBM-NEXT:    movzbl %sil, %eax
+; X64-BMI1NOTBM-NEXT:    orq %rdx, %rax
+; X64-BMI1NOTBM-NEXT:    bextrq %rax, %rdi, %rax
+; X64-BMI1NOTBM-NEXT:    # kill: def $eax killed $eax killed $rax
 ; X64-BMI1NOTBM-NEXT:    retq
 ;
 ; X64-BMI1BMI2-LABEL: bextr64_32_d1: