diff --git a/llvm/lib/Transforms/IPO/Inliner.cpp b/llvm/lib/Transforms/IPO/Inliner.cpp
--- a/llvm/lib/Transforms/IPO/Inliner.cpp
+++ b/llvm/lib/Transforms/IPO/Inliner.cpp
@@ -35,6 +35,7 @@
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/Transforms/Utils/Local.h"
+#include "llvm/Transforms/Utils/CallPromotionUtils.h"
 #include "llvm/IR/Attributes.h"
 #include "llvm/IR/BasicBlock.h"
 #include "llvm/IR/CallSite.h"
@@ -1096,10 +1097,20 @@
       if (!IFI.InlinedCallSites.empty()) {
         int NewHistoryID = InlineHistory.size();
         InlineHistory.push_back({&Callee, InlineHistoryID});
-        for (CallSite &CS : reverse(IFI.InlinedCallSites))
-          if (Function *NewCallee = CS.getCalledFunction())
+        for (CallSite &CS : reverse(IFI.InlinedCallSites)) {
+          Function *NewCallee = CS.getCalledFunction();
+          if (!NewCallee) {
+            // Try to promote an indirect (virtual) call without waiting for the
+            // post-inline cleanup and the next DevirtSCCRepeatedPass iteration
+            // because the next iteration may not happen and we may miss
+            // inlining it.
+            if (tryPromoteCall(CS))
+              NewCallee = CS.getCalledFunction();
+          }
+          if (NewCallee)
             if (!NewCallee->isDeclaration())
               Calls.push_back({CS, NewHistoryID});
+        }
       }
 
       if (InlinerFunctionImportStats != InlinerFunctionImportStatsOpts::No)
diff --git a/llvm/test/Transforms/Inline/devirtualize-4.ll b/llvm/test/Transforms/Inline/devirtualize-4.ll
new file mode 100644
--- /dev/null
+++ b/llvm/test/Transforms/Inline/devirtualize-4.ll
@@ -0,0 +1,109 @@
+; RUN: opt < %s -passes='cgscc(devirt<4>(inline))' -S | FileCheck %s
+; RUN: opt < %s -passes='default<O3>' -S | FileCheck %s
+
+; Check that DoNotOptimize is inlined into Test.
+; CHECK: @_Z4Testv()
+; CHECK-NOT: ret void
+; CHECK: call void asm
+; CHECK: ret void
+
+;template <class T>
+;void DoNotOptimize(const T& var) {
+;  asm volatile("" : "+m"(const_cast<T&>(var)));
+;}
+;
+;class Interface {
+; public:
+;  virtual void Run() = 0;
+;};
+;
+;class Impl : public Interface {
+; public:
+;  Impl() : f(3) {}
+;  void Run() { DoNotOptimize(this); }
+;
+; private:
+;  int f;
+;};
+;
+;static void IndirectRun(Interface& o) { o.Run(); }
+;
+;void Test() {
+;  Impl o;
+;  IndirectRun(o);
+;}
+
+%class.Impl = type <{ %class.Interface, i32, [4 x i8] }>
+%class.Interface = type { i32 (...)** }
+
+@_ZTV4Impl = linkonce_odr dso_local unnamed_addr constant { [3 x i8*] } { [3 x i8*] [i8* null, i8* bitcast ({ i8*, i8*, i8* }* @_ZTI4Impl to i8*), i8* bitcast (void (%class.Impl*)* @_ZN4Impl3RunEv to i8*)] }, align 8
+@_ZTVN10__cxxabiv120__si_class_type_infoE = external dso_local global i8*
+@_ZTS4Impl = linkonce_odr dso_local constant [6 x i8] c"4Impl\00", align 1
+@_ZTVN10__cxxabiv117__class_type_infoE = external dso_local global i8*
+@_ZTS9Interface = linkonce_odr dso_local constant [11 x i8] c"9Interface\00", align 1
+@_ZTI9Interface = linkonce_odr dso_local constant { i8*, i8* } { i8* bitcast (i8** getelementptr inbounds (i8*, i8** @_ZTVN10__cxxabiv117__class_type_infoE, i64 2) to i8*), i8* getelementptr inbounds ([11 x i8], [11 x i8]* @_ZTS9Interface, i32 0, i32 0) }, align 8
+@_ZTI4Impl = linkonce_odr dso_local constant { i8*, i8*, i8* } { i8* bitcast (i8** getelementptr inbounds (i8*, i8** @_ZTVN10__cxxabiv120__si_class_type_infoE, i64 2) to i8*), i8* getelementptr inbounds ([6 x i8], [6 x i8]* @_ZTS4Impl, i32 0, i32 0), i8* bitcast ({ i8*, i8* }* @_ZTI9Interface to i8*) }, align 8
+@_ZTV9Interface = linkonce_odr dso_local unnamed_addr constant { [3 x i8*] } { [3 x i8*] [i8* null, i8* bitcast ({ i8*, i8* }* @_ZTI9Interface to i8*), i8* bitcast (void ()* @__cxa_pure_virtual to i8*)] }, align 8
+
+define dso_local void @_Z4Testv() local_unnamed_addr {
+entry:
+  %o = alloca %class.Impl, align 8
+  %0 = bitcast %class.Impl* %o to i8*
+  call void @llvm.lifetime.start.p0i8(i64 16, i8* nonnull %0)
+  call void @_ZN4ImplC2Ev(%class.Impl* nonnull %o)
+  %1 = getelementptr inbounds %class.Impl, %class.Impl* %o, i64 0, i32 0
+  call fastcc void @_ZL11IndirectRunR9Interface(%class.Interface* nonnull dereferenceable(8) %1)
+  call void @llvm.lifetime.end.p0i8(i64 16, i8* nonnull %0)
+  ret void
+}
+
+declare void @llvm.lifetime.start.p0i8(i64 immarg, i8* nocapture)
+
+define linkonce_odr dso_local void @_ZN4ImplC2Ev(%class.Impl* %this) unnamed_addr align 2 {
+entry:
+  %0 = getelementptr %class.Impl, %class.Impl* %this, i64 0, i32 0
+  call void @_ZN9InterfaceC2Ev(%class.Interface* %0)
+  %1 = getelementptr %class.Impl, %class.Impl* %this, i64 0, i32 0, i32 0
+  store i32 (...)** bitcast (i8** getelementptr inbounds ({ [3 x i8*] }, { [3 x i8*] }* @_ZTV4Impl, i64 0, inrange i32 0, i64 2) to i32 (...)**), i32 (...)*** %1, align 8
+  %f = getelementptr inbounds %class.Impl, %class.Impl* %this, i64 0, i32 1
+  store i32 3, i32* %f, align 8
+  ret void
+}
+
+define internal fastcc void @_ZL11IndirectRunR9Interface(%class.Interface* dereferenceable(8) %o) unnamed_addr {
+entry:
+  %0 = bitcast %class.Interface* %o to void (%class.Interface*)***
+  %vtable = load void (%class.Interface*)**, void (%class.Interface*)*** %0, align 8
+  %1 = load void (%class.Interface*)*, void (%class.Interface*)** %vtable, align 8
+  call void %1(%class.Interface* nonnull %o)
+  ret void
+}
+
+declare void @llvm.lifetime.end.p0i8(i64 immarg, i8* nocapture)
+
+define linkonce_odr dso_local void @_ZN9InterfaceC2Ev(%class.Interface* %this) unnamed_addr align 2 {
+entry:
+  %0 = getelementptr %class.Interface, %class.Interface* %this, i64 0, i32 0
+  store i32 (...)** bitcast (i8** getelementptr inbounds ({ [3 x i8*] }, { [3 x i8*] }* @_ZTV9Interface, i64 0, inrange i32 0, i64 2) to i32 (...)**), i32 (...)*** %0, align 8
+  ret void
+}
+
+define linkonce_odr dso_local void @_ZN4Impl3RunEv(%class.Impl* %this) unnamed_addr align 2 {
+entry:
+  %ref.tmp = alloca %class.Impl*, align 8
+  %0 = bitcast %class.Impl** %ref.tmp to i8*
+  call void @llvm.lifetime.start.p0i8(i64 8, i8* nonnull %0)
+  store %class.Impl* %this, %class.Impl** %ref.tmp, align 8
+  call void @_Z13DoNotOptimizeIP4ImplEvRKT_(%class.Impl** nonnull dereferenceable(8) %ref.tmp)
+  call void @llvm.lifetime.end.p0i8(i64 8, i8* nonnull %0)
+  ret void
+}
+
+declare dso_local void @__cxa_pure_virtual() unnamed_addr
+
+define linkonce_odr dso_local void @_Z13DoNotOptimizeIP4ImplEvRKT_(%class.Impl** dereferenceable(8) %var) local_unnamed_addr {
+entry:
+  call void asm sideeffect "", "=*m,*m,~{dirflag},~{fpsr},~{flags}"(%class.Impl** nonnull %var, %class.Impl** nonnull %var)
+  ret void
+}
+