From e536db08ac81c41f614ed1c5502d3abd023df376 Mon Sep 17 00:00:00 2001
From: Dehao Chen <dehao@google.com>
Date: Tue, 19 Sep 2017 21:18:14 +0000
Subject: [PATCH] Import all inlined indirect call targets for SamplePGO.

Summary: In the ThinLTO compilation, if a function is inlined in the profiling binary, we need to inline it before annotation. If the callee is not available in the primary module, a first step is needed to import that callee function. For the current implementation, if the call is an indirect call, which has been promoted to >1 targets and inlined, SamplePGO will only import one target with the largest sample count. This patch fixed the bug to import all targets instead.

Reviewers: tejohnson, davidxl

Reviewed By: tejohnson

Subscribers: sanjoy, llvm-commits, mehdi_amini

Differential Revision: https://reviews.llvm.org/D36637

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@313678 91177308-0d34-0410-b5e6-96231b3b80d8
---
 lib/Transforms/IPO/SampleProfile.cpp             |  8 +++++---
 test/Transforms/SampleProfile/Inputs/import.prof |  6 +++++-
 test/Transforms/SampleProfile/import.ll          | 16 +++++++++++-----
 3 files changed, 21 insertions(+), 9 deletions(-)

diff --git a/lib/Transforms/IPO/SampleProfile.cpp b/lib/Transforms/IPO/SampleProfile.cpp
index 039fed0360f..5258746dbb9 100644
--- a/lib/Transforms/IPO/SampleProfile.cpp
+++ b/lib/Transforms/IPO/SampleProfile.cpp
@@ -756,9 +756,11 @@ bool SampleProfileLoader::inlineHotFunctions(
           continue;
       }
       if (!CalledFunction || !CalledFunction->getSubprogram()) {
-        findCalleeFunctionSamples(*I)->findImportedFunctions(
-            ImportGUIDs, F.getParent(),
-            Samples->getTotalSamples() * SampleProfileHotThreshold / 100);
+        // Handles functions that are imported from other modules.
+        for (const FunctionSamples *FS : findIndirectCallFunctionSamples(*I))
+          FS->findImportedFunctions(
+              ImportGUIDs, F.getParent(),
+              Samples->getTotalSamples() * SampleProfileHotThreshold / 100);
         continue;
       }
       assert(isa<CallInst>(DI) || isa<InvokeInst>(DI));
diff --git a/test/Transforms/SampleProfile/Inputs/import.prof b/test/Transforms/SampleProfile/Inputs/import.prof
index efadc0c5c9c..aae072ac191 100644
--- a/test/Transforms/SampleProfile/Inputs/import.prof
+++ b/test/Transforms/SampleProfile/Inputs/import.prof
@@ -1,4 +1,8 @@
-main:10000:0
+test:10000:0
  3: foo:1000
   3: bar:200
    4: baz:10
+ 4: foo1:1000
+  1: 1000
+ 4: foo2:1000
+  1: 1000
diff --git a/test/Transforms/SampleProfile/import.ll b/test/Transforms/SampleProfile/import.ll
index 1ee45fb4fd3..ad9c2d55aa9 100644
--- a/test/Transforms/SampleProfile/import.ll
+++ b/test/Transforms/SampleProfile/import.ll
@@ -5,14 +5,19 @@
 
 declare void @foo()
 
-define void @main() !dbg !7 {
+define void @test(void ()*) !dbg !7 {
+  %2 = alloca void ()*
+  store void ()* %0, void ()** %2
+  %3 = load void ()*, void ()** %2
+  ; CHECK: call {{.*}}, !prof ![[PROF:[0-9]+]]
   call void @foo(), !dbg !18
+  call void %3(), !dbg !19
   ret void
 }
 
-; GUIDs of foo and bar should be included in the metadata to make sure hot
-; inline stacks are imported.
-; CHECK: !{!"function_entry_count", i64 1, i64 6699318081062747564, i64 -2012135647395072713}
+; GUIDs of foo, bar, foo1 and foo2 should be included in the metadata to make
+; sure hot inline stacks are imported.
+; CHECK: !{!"function_entry_count", i64 1, i64 2494702099028631698, i64 6699318081062747564, i64 7682762345278052905, i64 -2012135647395072713}
 
 !llvm.dbg.cu = !{!0}
 !llvm.module.flags = !{!8, !9}
@@ -22,10 +27,11 @@ define void @main() !dbg !7 {
 !1 = !DIFile(filename: "calls.cc", directory: ".")
 !2 = !{}
 !6 = !DISubroutineType(types: !2)
-!7 = distinct !DISubprogram(name: "main", line: 7, isLocal: false, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: false, unit: !0, scopeLine: 7, file: !1, scope: !1, type: !6, variables: !2)
+!7 = distinct !DISubprogram(name: "test", line: 7, isLocal: false, isDefinition: true, virtualIndex: 6, flags: DIFlagPrototyped, isOptimized: false, unit: !0, scopeLine: 7, file: !1, scope: !1, type: !6, variables: !2)
 !8 = !{i32 2, !"Dwarf Version", i32 4}
 !9 = !{i32 1, !"Debug Info Version", i32 3}
 !10 = !{!"clang version 3.5 "}
 !15 = !DILexicalBlockFile(discriminator: 1, file: !1, scope: !7)
 !17 = distinct !DILexicalBlock(line: 10, column: 0, file: !1, scope: !7)
 !18 = !DILocation(line: 10, scope: !17)
+!19 = !DILocation(line: 11, scope: !17)