Index: llvm/lib/Transforms/IPO/ArgumentPromotion.cpp
===================================================================
--- llvm/lib/Transforms/IPO/ArgumentPromotion.cpp
+++ llvm/lib/Transforms/IPO/ArgumentPromotion.cpp
@@ -46,7 +46,10 @@
 #include "llvm/Analysis/CallGraphSCCPass.h"
 #include "llvm/Analysis/LazyCallGraph.h"
 #include "llvm/Analysis/Loads.h"
+#include "llvm/Analysis/LoopInfo.h"
 #include "llvm/Analysis/MemoryLocation.h"
+#include "llvm/Analysis/MustExecute.h"
+#include "llvm/Analysis/PostDominators.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
 #include "llvm/Analysis/TargetTransformInfo.h"
 #include "llvm/IR/Argument.h"
@@ -620,20 +623,33 @@
     return true;
   };
 
-  // First, iterate the entry block and mark loads of (geps of) arguments as
-  // safe.
+  // First, iterate all the basic blocks that must be executed upon entry
+  // and mark loads of (geps of) arguments as safe.
   BasicBlock &EntryBlock = Arg->getParent()->front();
+  GetterTy<LoopInfo> LIGetter = [&](const Function &F) {
+    DominatorTree *DT = new DominatorTree(const_cast<Function &>(F));
+    LoopInfo *LI = new LoopInfo(*DT);
+    return LI;
+  };
+  GetterTy<PostDominatorTree> PDTGetter = [&](const Function &F) {
+    PostDominatorTree *PDT = new PostDominatorTree(const_cast<Function &>(F));
+    return PDT;
+  };
+  MustBeExecutedContextExplorer Explorer(true, LIGetter, PDTGetter);
   // Declare this here so we can reuse it
   IndicesVector Indices;
-  for (Instruction &I : EntryBlock)
-    if (LoadInst *LI = dyn_cast<LoadInst>(&I)) {
-      Value *V = LI->getPointerOperand();
-      if (GetElementPtrInst *GEP = dyn_cast<GetElementPtrInst>(V)) {
+  for (
+    auto EIt = Explorer.begin(&EntryBlock.front()), EEnd = Explorer.end(&EntryBlock.front());
+    EIt != EEnd; ++EIt
+  )
+    if (const LoadInst *LI = dyn_cast<LoadInst>(EIt.getCurrentInst())) {
+      const Value *V = LI->getPointerOperand();
+      if (const GetElementPtrInst *GEP = dyn_cast<GetElementPtrInst>(V)) {
         V = GEP->getPointerOperand();
         if (V == Arg) {
           // This load actually loads (part of) Arg? Check the indices then.
           Indices.reserve(GEP->getNumIndices());
-          for (User::op_iterator II = GEP->idx_begin(), IE = GEP->idx_end();
+          for (User::const_op_iterator II = GEP->idx_begin(), IE = GEP->idx_end();
                II != IE; ++II)
             if (ConstantInt *CI = dyn_cast<ConstantInt>(*II))
               Indices.push_back(CI->getSExtValue());
Index: llvm/test/Transforms/ArgumentPromotion/control-flow3.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/ArgumentPromotion/control-flow3.ll
@@ -0,0 +1,81 @@
+; RUN: opt < %s -argpromotion -S | FileCheck %s
+; RUN: opt < %s -passes=argpromotion -S | FileCheck %s
+
+target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128"
+
+; CHECK-LABEL: define internal i32 @callee0(i32 %P.val)
+define internal i32 @callee0(i32* %P) {
+entry:
+  br label %bb1
+
+bb1:
+  br label %bb2
+
+bb2:
+  ; CHECK-NOT: load i32, i32* %P
+  %X = load i32, i32* %P
+  ret i32 %X
+}
+
+; CHECK-LABEL: define i32 @caller0() {
+define i32 @caller0() {
+  %A = alloca i32
+  store i32 17, i32* %A
+  ; CHECK: %A.val = load i32, i32* %A
+  ; CHECK: %X = call i32 @callee0(i32 %A.val)
+  %X = call i32 @callee0(i32* %A)
+  ret i32 %X
+}
+
+; CHECK-LABEL: define internal i32 @callee1(i1 %C, i32 %P.val)
+define internal i32 @callee1(i1 %C, i32* %P) {
+entry:
+  br label %bb1
+
+bb1:
+  br label %bb2
+
+bb2:
+  ; CHECK-NOT: load i32, i32* %P
+  %X = load i32, i32* %P
+  br i1 %C, label %bb2, label %exit
+
+exit:
+  ret i32 %X
+}
+
+; CHECK-LABEL: define i32 @caller1() {
+define i32 @caller1() {
+  %A = alloca i32
+  store i32 17, i32* %A
+  ; CHECK: %A.val = load i32, i32* %A
+  ; CHECK: %X = call i32 @callee1(i1 false, i32 %A.val)
+  %X = call i32 @callee1(i1 false, i32* %A)
+  ret i32 %X
+}
+
+; CHECK-LABEL: define internal i32 @callee2(i32* %P) {
+define internal i32 @callee2(i32* %P) {
+entry:
+  br label %bb1
+
+bb1:
+  %gep0 = getelementptr i32, i32* %P, i64 0
+  ; CHECK: %X = load i32, i32* %gep0
+  %X = load i32, i32* %gep0
+  br label %bb1
+
+bb2:
+  %gep1 = getelementptr i32, i32* %P, i64 1
+  ; CHECK: %Y = load i32, i32* %gep1
+  %Y = load i32, i32* %gep1
+  ret i32 %X
+}
+
+define i32 @caller2() {
+  %A = alloca i32
+  store i32 17, i32* %A
+  ; CHECK: %X = call i32 @callee2(i32* %A)
+  %X = call i32 @callee2(i32* %A)
+  ret i32 %X
+}