Index: lib/CodeGen/MachineBlockPlacement.cpp
===================================================================
--- lib/CodeGen/MachineBlockPlacement.cpp
+++ lib/CodeGen/MachineBlockPlacement.cpp
@@ -74,6 +74,12 @@
              "post dominator, out of line."),
     cl::init(false), cl::Hidden);
 
+static cl::opt<unsigned> OutlineOptionalThreshold(
+    "outline-optional-threshold",
+    cl::desc("Don't outline optional branches that are a single block with an "
+             "instruction count below this threshold"),
+    cl::init(4), cl::Hidden);
+
 namespace {
 class BlockChain;
 /// \brief Type for our function-wide basic block -> block chain mapping.
@@ -377,8 +383,19 @@
     // dominates all terminators of the MachineFunction. If it does, other
     // successors must be optional. Don't do this for cold branches.
     if (OutlineOptionalBranches && SuccProb > HotProb.getCompl() &&
-        UnavoidableBlocks.count(Succ) > 0)
+        UnavoidableBlocks.count(Succ) > 0) {
+      for (MachineBasicBlock *Pred : Succ->predecessors()) {
+        if (Pred == Succ || (BlockFilter && !BlockFilter->count(Pred)) ||
+            BlockToChain[Pred] == &Chain)
+          continue;
+        for (MachineBasicBlock *PredPred : Pred->predecessors()) {
+          if (BlockToChain[PredPred] == &Chain &&
+              Pred->size() < OutlineOptionalThreshold)
+            return Pred;
+        }
+      }
       return Succ;
+    }
 
     // Only consider successors which are either "hot", or wouldn't violate
     // any CFG constraints.
Index: test/CodeGen/X86/code_placement_outline_optional_branches.ll
===================================================================
--- test/CodeGen/X86/code_placement_outline_optional_branches.ll
+++ test/CodeGen/X86/code_placement_outline_optional_branches.ll
@@ -1,20 +1,30 @@
 ; RUN: llc -mcpu=corei7 -mtriple=x86_64-linux < %s | FileCheck %s -check-prefix=CHECK
 ; RUN: llc -mcpu=corei7 -mtriple=x86_64-linux -outline-optional-branches < %s | FileCheck %s -check-prefix=CHECK-OUTLINE
 
-define void @foo(i32 %t1, i32 %t2) {
+define void @foo(i32 %t1, i32 %t2, i32 %t3) {
 ; Test that we lift the call to 'c' up to immediately follow the call to 'b'
 ; when we disable the cfg conflict check.
 ;
 ; CHECK-LABEL: foo:
 ; CHECK: callq a
+; CHECK: callq a
+; CHECK: callq a
+; CHECK: callq a
 ; CHECK: callq b
 ; CHECK: callq c
 ; CHECK: callq d
+; CHECK: callq e
+; CHECK: callq f
 ;
 ; CHECK-OUTLINE-LABEL: foo:
 ; CHECK-OUTLINE: callq b
 ; CHECK-OUTLINE: callq c
 ; CHECK-OUTLINE: callq d
+; CHECK-OUTLINE: callq e
+; CHECK-OUTLINE: callq f
+; CHECK-OUTLINE: callq a
+; CHECK-OUTLINE: callq a
+; CHECK-OUTLINE: callq a
 ; CHECK-OUTLINE: callq a
 
 entry:
@@ -23,6 +33,9 @@
 
 if.then:
   call void @a()
+  call void @a()
+  call void @a()
+  call void @a()
   br label %if.end
 
 if.end:
@@ -39,6 +52,18 @@
 
 if.end2:
   call void @d()
+  br label %shortbranch
+
+shortbranch:
+  %cmp3 = icmp eq i32 %t3, 0
+  br i1 %cmp3, label %if.then3, label %if.end3
+
+if.then3:
+  call void @e()
+  br label %if.end3
+
+if.end3:
+  call void @f()
   ret void
 }
 
@@ -46,5 +71,7 @@
 declare void @b()
 declare void @c()
 declare void @d()
+declare void @e()
+declare void @f()
 
 !1 = !{!"branch_weights", i32 64, i32 4}