Import all inlined indirect call targets for SamplePGO.

[danielcdh]

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.

[tejohnson]

lib/Transforms/IPO/SampleProfile.cpp

734

I'm not really following the flow of what is supposed to happen here. I see that the earlier code already does an iteration over findIndirectCallFunctionSamples - can/should this be combined with that?

test/Transforms/SampleProfile/import.ll

18

Update comment (foo1 and foo2 also)

[danielcdh]

update

[danielcdh]

lib/Transforms/IPO/SampleProfile.cpp

734

I'm planning to do that in a separate patch, in which I'll also move the InlineFunction call inside the loop too.

[tejohnson]

LGTM

lib/Transforms/IPO/SampleProfile.cpp

for (auto I : CIS) {
           } else {
             DEBUG(dbgs() << "\nFailed to promote indirect call to "
                          << CalleeFunctionName << " because " << Reason
                          << "\n");
             continue;
           }
         }
       if (!CalledFunction || !CalledFunction->getSubprogram()) {
-        findCalleeFunctionSamples(*I)->findImportedFunctions(
+        for (const FunctionSamples *FS : findIndirectCallFunctionSamples(*I))
+          FS->findImportedFunctions(
               ImportGUIDs, F.getParent(),
               Samples->getTotalSamples() * SampleProfileHotThreshold / 100);
         continue;
       }
       DebugLoc DLoc = I->getDebugLoc();
       if (InlineFunction(CallSite(DI), IFI)) {
         LocalChanged = true;
         emitOptimizationRemark(Ctx, DEBUG_TYPE, F, DLoc,
                                Twine("inlined hot callee '") +
                                    CalledFunction->getName() + "' into '" +

test/Transforms/SampleProfile/Inputs/import.prof

-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

test/Transforms/SampleProfile/import.ll

 ; RUN: opt < %s -sample-profile -sample-profile-file=%S/Inputs/import.prof -S | FileCheck %s
 
 ; Tests whether the functions in the inline stack are added to the
 ; function_entry_count metadata.
 
 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}
+; CHECK: !{!"function_entry_count", i64 1, i64 2494702099028631698, i64 6699318081062747564, i64 7682762345278052905, i64 -2012135647395072713}
 
 !llvm.dbg.cu = !{!0}
 !llvm.module.flags = !{!8, !9}
 !llvm.ident = !{!10}
 
 !0 = distinct !DICompileUnit(language: DW_LANG_C_plus_plus, producer: "clang version 3.5 ", isOptimized: false, emissionKind: NoDebug, file: !1, enums: !2, retainedTypes: !2, globals: !2, imports: !2)
 !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)