Index: llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp
===================================================================
--- llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp
+++ llvm/trunk/lib/Target/ARM/ARMISelLowering.cpp
@@ -2282,6 +2282,13 @@
 
   assert(Subtarget->supportsTailCall());
 
+  // Tail calls to function pointers cannot be optimized for Thumb1 if the args
+  // to the call take up r0-r3. The reason is that there are no legal registers
+  // left to hold the pointer to the function to be called.
+  if (Subtarget->isThumb1Only() && Outs.size() >= 4 &&
+      !isa<GlobalAddressSDNode>(Callee.getNode()))
+      return false;
+
   // Look for obvious safe cases to perform tail call optimization that do not
   // require ABI changes. This is what gcc calls sibcall.
 
Index: llvm/trunk/test/CodeGen/ARM/v8m-tail-call.ll
===================================================================
--- llvm/trunk/test/CodeGen/ARM/v8m-tail-call.ll
+++ llvm/trunk/test/CodeGen/ARM/v8m-tail-call.ll
@@ -45,3 +45,61 @@
 ; CHECK-NEXT: add     sp, #4
 ; CHECK-NEXT: b       h2
 }
+
+; Make sure that tail calls to function pointers that require r0-r3 for argument
+; passing do not break the compiler.
+@fnptr = global i32 (i32, i32, i32, i32)* null
+define i32 @test3() {
+; CHECK-LABEL: test3:
+; CHECK: blx {{r[0-9]+}}
+  %1 = load i32 (i32, i32, i32, i32)*, i32 (i32, i32, i32, i32)** @fnptr
+  %2 = tail call i32 %1(i32 1, i32 2, i32 3, i32 4)
+  ret i32 %2
+}
+
+@fnptr2 = global i32 (i32, i32, i64)* null
+define i32 @test4() {
+; CHECK-LABEL: test4:
+; CHECK: blx {{r[0-9]+}}
+  %1 = load i32 (i32, i32, i64)*, i32 (i32, i32, i64)** @fnptr2
+  %2 = tail call i32 %1(i32 1, i32 2, i64 3)
+  ret i32 %2
+}
+
+; Check that tail calls to function pointers where not all of r0-r3 are used for
+; parameter passing are tail-call optimized.
+; test5: params in r0, r1. r2 & r3 are free.
+@fnptr3 = global i32 (i32, i32)* null
+define i32 @test5() {
+; CHECK-LABEL: test5:
+; CHECK: ldr [[REG:r[0-9]+]]
+; CHECK: bx [[REG]]
+; CHECK-NOT: blx [[REG]]
+  %1 = load i32 (i32, i32)*, i32 (i32, i32)** @fnptr3
+  %2 = tail call i32 %1(i32 1, i32 2)
+  ret i32 %2
+}
+
+; test6: params in r0 and r2-r3. r1 is free.
+@fnptr4 = global i32 (i32, i64)* null
+define i32 @test6() {
+; CHECK-LABEL: test6:
+; CHECK: ldr [[REG:r[0-9]+]]
+; CHECK: bx [[REG]]
+; CHECK-NOT: blx [[REG]]
+  %1 = load i32 (i32, i64)*, i32 (i32, i64)** @fnptr4
+  %2 = tail call i32 %1(i32 1, i64 2)
+  ret i32 %2
+}
+
+; Check that tail calls to functions other than function pointers are
+; tail-call optimized.
+define i32 @test7() {
+; CHECK-LABEL: test7:
+; CHECK: b bar
+; CHECK-NOT: bl bar
+  %tail = tail call i32 @bar(i32 1, i32 2, i32 3, i32 4)
+  ret i32 %tail
+}
+
+declare i32 @bar(i32, i32, i32, i32)