The inliner has traditionally not considered call sites

that appear due to inlining a callee as candidates for
futher inlining, but a recent patch made it do this if
those call sites were indirect and became direct.

Unfortunately, in bizarre cases (see testcase) doing this
can cause us to infinitely inline mutually recursive
functions into callers not in the cycle.  Fix this by
keeping track of the inline history from which callsite
inline candidates got inlined from.

This shouldn't affect any "real world" code, but is required
for a follow on patch that is coming up next.



git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@102822 91177308-0d34-0410-b5e6-96231b3b80d8

1 files changed, 43 insertions, 2 deletions

diff --git a/test/Transforms/Inline/noinline-recursive-fn.ll b/test/Transforms/Inline/noinline-recursive-fn.ll
index dcae024..1d5ebbb 100644
--- a/test/Transforms/Inline/noinline-recursive-fn.ll
+++ b/test/Transforms/Inline/noinline-recursive-fn.ll
@@ -2,7 +2,7 @@
 ; This effectively is just peeling off the first iteration of a loop, and the
 ; inliner heuristics are not set up for this.
 
-; RUN: opt -inline %s -S | grep "call void @foo(i32 42)"
+; RUN: opt -inline %s -S | FileCheck %s
 
 target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
 target triple = "x86_64-apple-darwin10.3"
@@ -11,7 +11,6 @@ target triple = "x86_64-apple-darwin10.3"
 
 define internal void @foo(i32 %x) nounwind ssp {
 entry:
-  %"alloca point" = bitcast i32 0 to i32          ; <i32> [#uses=0]
   %0 = icmp slt i32 %x, 0                         ; <i1> [#uses=1]
   br i1 %0, label %return, label %bb
 
@@ -25,8 +24,50 @@ return:                                           ; preds = %entry
   ret void
 }
 
+
+;; CHECK: @bonk
+;; CHECK: call void @foo(i32 42)
 define void @bonk() nounwind ssp {
 entry:
   call void @foo(i32 42) nounwind ssp
   ret void
 }
+
+
+
+;; Here is an indirect case that should not be infinitely inlined.
+
+define internal void @f1(i32 %x, i8* %Foo, i8* %Bar) nounwind ssp {
+entry:
+  %0 = bitcast i8* %Bar to void (i32, i8*, i8*)*
+  %1 = sub nsw i32 %x, 1
+  call void %0(i32 %1, i8* %Foo, i8* %Bar) nounwind
+  volatile store i32 42, i32* @g, align 4
+  ret void
+}
+
+define internal void @f2(i32 %x, i8* %Foo, i8* %Bar) nounwind ssp {
+entry:
+  %0 = icmp slt i32 %x, 0                         ; <i1> [#uses=1]
+  br i1 %0, label %return, label %bb
+
+bb:                                               ; preds = %entry
+  %1 = bitcast i8* %Foo to void (i32, i8*, i8*)*  ; <void (i32, i8*, i8*)*> [#uses=1]
+  call void %1(i32 %x, i8* %Foo, i8* %Bar) nounwind
+  volatile store i32 13, i32* @g, align 4
+  ret void
+
+return:                                           ; preds = %entry
+  ret void
+}
+
+
+; CHECK: @top_level
+; CHECK: call void @f2(i32 122
+; Here we inline one instance of the cycle, but we don't want to completely
+; unroll it.
+define void @top_level() nounwind ssp {
+entry:
+  call void @f2(i32 123, i8* bitcast (void (i32, i8*, i8*)* @f1 to i8*), i8* bitcast (void (i32, i8*, i8*)* @f2 to i8*)) nounwind ssp
+  ret void
+}