Index: lib/Transforms/Scalar/MemCpyOptimizer.cpp
===================================================================
--- lib/Transforms/Scalar/MemCpyOptimizer.cpp
+++ lib/Transforms/Scalar/MemCpyOptimizer.cpp
@@ -1391,10 +1391,19 @@
 bool MemCpyOptPass::iterateOnFunction(Function &F) {
   bool MadeChange = false;
 
+  DominatorTree &DT = LookupDomTree();
+
   // Walk all instruction in the function.
   for (BasicBlock &BB : F) {
+    // Skip unreachable blocks. For example processStore assumes that an
+    // instruction in a BB can't be dominated by a later instruction in the
+    // same BB (which is a scenario that can happen for an unreachable BB that
+    // has itself as a predecessor).
+    if (!DT.isReachableFromEntry(&BB))
+      continue;
+
     for (BasicBlock::iterator BI = BB.begin(), BE = BB.end(); BI != BE;) {
-      // Avoid invalidating the iterator.
+        // Avoid invalidating the iterator.
       Instruction *I = &*BI++;
 
       bool RepeatInstruction = false;
Index: test/Transforms/MemCpyOpt/process_store.ll
===================================================================
--- /dev/null
+++ test/Transforms/MemCpyOpt/process_store.ll
@@ -0,0 +1,39 @@
+; RUN: opt < %s -memcpyopt -disable-output
+
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+@b = common dso_local local_unnamed_addr global i32 0, align 4
+@a = common dso_local local_unnamed_addr global i32 0, align 4
+
+declare dso_local i32 @f1()
+
+; Do not crash due to store first in BB.
+define dso_local void @f2() {
+for.end:
+  %0 = load i32, i32* @b, align 4
+  ret void
+
+for.body:
+  store i32 %1, i32* @a, align 4
+  %call = call i32 @f1()
+  %cmp = icmp sge i32 %call, 0
+  %1 = load i32, i32* @b, align 4
+  br label %for.body
+}
+
+; Do not crash due to call not before store in BB.
+define dso_local void @f3() {
+for.end:
+  %0 = load i32, i32* @b, align 4
+  ret void
+
+for.body:
+  %t = add i32 %t2, 1
+  store i32 %1, i32* @a, align 4
+  %call = call i32 @f1()
+  %cmp = icmp sge i32 %call, 0
+  %1 = load i32, i32* @b, align 4
+  %t2 = xor i32 %t, 5
+  br label %for.body
+}