diff --git a/llvm/include/llvm/CodeGen/TargetLowering.h b/llvm/include/llvm/CodeGen/TargetLowering.h
--- a/llvm/include/llvm/CodeGen/TargetLowering.h
+++ b/llvm/include/llvm/CodeGen/TargetLowering.h
@@ -4471,6 +4471,12 @@
     return nullptr;
   }
 
+  /// Returns a 0 terminated array of rounding control registers that can be
+  /// attached into strict FP call.
+  virtual const MCPhysReg *getRoundingControlRegisters() const {
+    return nullptr;
+  }
+
   /// This callback is used to prepare for a volatile or atomic load.
   /// It takes a chain node as input and returns the chain for the load itself.
   ///
diff --git a/llvm/lib/CodeGen/SelectionDAG/InstrEmitter.cpp b/llvm/lib/CodeGen/SelectionDAG/InstrEmitter.cpp
--- a/llvm/lib/CodeGen/SelectionDAG/InstrEmitter.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/InstrEmitter.cpp
@@ -1125,6 +1125,14 @@
     }
   }
 
+  // Add rounding control registers as implicit def for function call.
+  if (II.isCall() && MF->getFunction().hasFnAttribute(Attribute::StrictFP)) {
+    const MCPhysReg *RCRegs = TLI->getRoundingControlRegisters();
+    if (RCRegs)
+      for (; *RCRegs; ++RCRegs)
+        UsedRegs.push_back(*RCRegs);
+  }
+
   // Finally mark unused registers as dead.
   if (!UsedRegs.empty() || II.getImplicitDefs() || II.hasOptionalDef())
     MIB->setPhysRegsDeadExcept(UsedRegs, *TRI);
diff --git a/llvm/lib/Target/X86/X86ISelLowering.h b/llvm/lib/Target/X86/X86ISelLowering.h
--- a/llvm/lib/Target/X86/X86ISelLowering.h
+++ b/llvm/lib/Target/X86/X86ISelLowering.h
@@ -1677,6 +1677,7 @@
                         LLVMContext &Context) const override;
 
     const MCPhysReg *getScratchRegisters(CallingConv::ID CC) const override;
+    const MCPhysReg *getRoundingControlRegisters() const override;
 
     TargetLoweringBase::AtomicExpansionKind
     shouldExpandAtomicLoadInIR(LoadInst *LI) const override;
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -3053,6 +3053,13 @@
   return ScratchRegs;
 }
 
+const MCPhysReg *X86TargetLowering::getRoundingControlRegisters() const {
+  // FIXME: We should def X86::FPCW for x87 as well. But it affects a lot of lit
+  // tests at the moment, which is not what we expected.
+  static const MCPhysReg RCRegs[] = { X86::MXCSR, 0 };
+  return RCRegs;
+}
+
 /// Lowers masks values (v*i1) to the local register values
 /// \returns DAG node after lowering to register type
 static SDValue lowerMasksToReg(const SDValue &ValArg, const EVT &ValLoc,
diff --git a/llvm/test/CodeGen/X86/fp-strict-scalar-inttofp-fp16.ll b/llvm/test/CodeGen/X86/fp-strict-scalar-inttofp-fp16.ll
--- a/llvm/test/CodeGen/X86/fp-strict-scalar-inttofp-fp16.ll
+++ b/llvm/test/CodeGen/X86/fp-strict-scalar-inttofp-fp16.ll
@@ -380,10 +380,12 @@
 ; SSE2-NEXT:    orq %rax, %rcx
 ; SSE2-NEXT:    testq %rdi, %rdi
 ; SSE2-NEXT:    cmovnsq %rdi, %rcx
-; SSE2-NEXT:    cvtsi2ss %rcx, %xmm0
-; SSE2-NEXT:    jns .LBB9_2
+; SSE2-NEXT:    cvtsi2ss %rcx, %xmm1
+; SSE2-NEXT:    movaps %xmm1, %xmm0
+; SSE2-NEXT:    addss %xmm1, %xmm0
+; SSE2-NEXT:    js .LBB9_2
 ; SSE2-NEXT:  # %bb.1:
-; SSE2-NEXT:    addss %xmm0, %xmm0
+; SSE2-NEXT:    movaps %xmm1, %xmm0
 ; SSE2-NEXT:  .LBB9_2:
 ; SSE2-NEXT:    pushq %rax
 ; SSE2-NEXT:    callq __truncsfhf2@PLT
diff --git a/llvm/test/CodeGen/X86/pr59305.ll b/llvm/test/CodeGen/X86/pr59305.ll
--- a/llvm/test/CodeGen/X86/pr59305.ll
+++ b/llvm/test/CodeGen/X86/pr59305.ll
@@ -4,23 +4,28 @@
 define double @foo(double %0) #0 {
 ; CHECK-LABEL: foo:
 ; CHECK:       # %bb.0:
-; CHECK-NEXT:    pushq %rax
+; CHECK-NEXT:    subq $24, %rsp
 ; CHECK-NEXT:    movsd %xmm0, (%rsp) # 8-byte Spill
 ; CHECK-NEXT:    movl $1024, %edi # imm = 0x400
 ; CHECK-NEXT:    callq fesetround@PLT
-; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
-; CHECK-NEXT:    divsd (%rsp), %xmm0 # 8-byte Folded Reload
-; CHECK-NEXT:    movsd %xmm0, (%rsp) # 8-byte Spill
+; CHECK-NEXT:    movsd {{.*#+}} xmm1 = mem[0],zero
+; CHECK-NEXT:    divsd (%rsp), %xmm1 # 8-byte Folded Reload
+; CHECK-NEXT:    movsd %xmm1, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
 ; CHECK-NEXT:    movl $1024, %edi # imm = 0x400
 ; CHECK-NEXT:    callq fesetround@PLT
+; CHECK-NEXT:    movsd {{.*#+}} xmm0 = mem[0],zero
+; CHECK-NEXT:    divsd (%rsp), %xmm0 # 8-byte Folded Reload
+; CHECK-NEXT:    movsd %xmm0, {{[-0-9]+}}(%r{{[sb]}}p) # 8-byte Spill
 ; CHECK-NEXT:    movl $1024, %edi # imm = 0x400
 ; CHECK-NEXT:    callq fesetround@PLT
-; CHECK-NEXT:    movsd (%rsp), %xmm0 # 8-byte Reload
+; CHECK-NEXT:    movsd {{.*#+}} xmm2 = mem[0],zero
+; CHECK-NEXT:    divsd (%rsp), %xmm2 # 8-byte Folded Reload
+; CHECK-NEXT:    movsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm0 # 8-byte Reload
 ; CHECK-NEXT:    # xmm0 = mem[0],zero
-; CHECK-NEXT:    movaps %xmm0, %xmm1
-; CHECK-NEXT:    movaps %xmm0, %xmm2
+; CHECK-NEXT:    movsd {{[-0-9]+}}(%r{{[sb]}}p), %xmm1 # 8-byte Reload
+; CHECK-NEXT:    # xmm1 = mem[0],zero
 ; CHECK-NEXT:    callq fma@PLT
-; CHECK-NEXT:    popq %rax
+; CHECK-NEXT:    addq $24, %rsp
 ; CHECK-NEXT:    retq
     %2 = call i32 @fesetround(i32 noundef 1024)
     %3 = call double @llvm.experimental.constrained.fdiv.f64(double 1.000000e+00, double %0, metadata !"round.dynamic", metadata !"fpexcept.ignore") #0