Index: llvm/lib/Analysis/BasicAliasAnalysis.cpp
===================================================================
--- llvm/lib/Analysis/BasicAliasAnalysis.cpp
+++ llvm/lib/Analysis/BasicAliasAnalysis.cpp
@@ -801,14 +801,15 @@
 
   const Value *Object = GetUnderlyingObject(Loc.Ptr, DL);
 
-  // If this is a tail call and Loc.Ptr points to a stack location, we know that
-  // the tail call cannot access or modify the local stack.
-  // We cannot exclude byval arguments here; these belong to the caller of
-  // the current function not to the current function, and a tail callee
-  // may reference them.
+  // Calls marked 'tail' cannot read or write allocas from the current frame
+  // because the current frame might be destroyed by the time they run. However,
+  // a tail call may use an alloca with byval. Calling with byval copies the
+  // contents of the alloca into argument registers or stack slots, so there is
+  // no lifetime issue.
   if (isa<AllocaInst>(Object))
     if (const CallInst *CI = dyn_cast<CallInst>(CS.getInstruction()))
-      if (CI->isTailCall())
+      if (CI->isTailCall() &&
+          !CI->getAttributes().hasAttrSomewhere(Attribute::ByVal))
         return ModRefInfo::NoModRef;
 
   // If the pointer is to a locally allocated object that does not escape,
Index: llvm/test/Analysis/BasicAA/tail-byval.ll
===================================================================
--- /dev/null
+++ llvm/test/Analysis/BasicAA/tail-byval.ll
@@ -0,0 +1,15 @@
+; RUN: opt -basicaa -aa-eval -print-all-alias-modref-info -disable-output < %s 2>&1 | FileCheck %s
+
+declare void @takebyval(i32* byval %p)
+
+define i32 @tailbyval() {
+entry:
+  %p = alloca i32
+  store i32 42, i32* %p
+  tail call void @takebyval(i32* byval %p)
+  %rv = load i32, i32* %p
+  ret i32 %rv
+}
+; FIXME: This should be Just Ref.
+; CHECK-LABEL: Function: tailbyval: 1 pointers, 1 call sites
+; CHECK-NEXT:   Both ModRef:  Ptr: i32* %p       <->  tail call void @takebyval(i32* byval %p)
Index: llvm/test/Transforms/DeadStoreElimination/tail-byval.ll
===================================================================
--- /dev/null
+++ llvm/test/Transforms/DeadStoreElimination/tail-byval.ll
@@ -0,0 +1,23 @@
+; RUN: opt -dse -S < %s | FileCheck %s
+
+; Don't eliminate stores to allocas before tail calls to functions that use
+; byval. It's correct to mark calls like these as 'tail'. To implement this tail
+; call, the backend should copy the bytes from the alloca into the argument area
+; before clearing the stack.
+
+target datalayout = "e-m:e-p:32:32-f64:32:64-f80:32-n8:16:32-S128"
+target triple = "i386-unknown-linux-gnu"
+
+declare void @g(i32* byval %p)
+
+define void @f(i32* byval %x) {
+entry:
+  %p = alloca i32
+  %v = load i32, i32* %x
+  store i32 %v, i32* %p
+  tail call void @g(i32* byval %p)
+  ret void
+}
+; CHECK-LABEL: define void @f(i32* byval %x)
+; CHECK:   store i32 %v, i32* %p
+; CHECK:   tail call void @g(i32* byval %p)
Index: llvm/test/Transforms/InstCombine/load.ll
===================================================================
--- llvm/test/Transforms/InstCombine/load.ll
+++ llvm/test/Transforms/InstCombine/load.ll
@@ -1,5 +1,5 @@
 ; RUN: opt -instcombine -S < %s | FileCheck %s
-; RUN: opt -passes=instcombine -S < %s | FileCheck %s
+; RUN: opt -aa-pipeline=basic-aa -passes=instcombine -S < %s | FileCheck %s
 
 ; This test makes sure that these instructions are properly eliminated.