[Inliner] Report inlining decision before deleting Callee contents (#153616)

Call `recordInliningWithCalleeDeleted` before dropping the contents of
the Callee. Otherwise the handlers don't have access to e.g. the
DebugLoc, so the Callee DebugLoc was missing in inlining remarks for
functions with internal linkage.

The test is the same as `optimization-remarks-passed-yaml.ll` except
that the function `foo` has internal linkage instead of external linkage.

Author: tobias-stadler

llvm/lib/Transforms/IPO/Inliner.cpp

@@ -459,6 +459,9 @@ PreservedAnalyses InlinerPass::run(LazyCallGraph::SCC &InitialC,
                              }),
               Calls.end());
 
+          // Report inlining decision BEFORE deleting function contents, so we
+          // can still access e.g. the DebugLoc
+          Advice->recordInliningWithCalleeDeleted();
           // Clear the body and queue the function itself for call graph
           // updating when we finish inlining.
           makeFunctionBodyUnreachable(Callee);
@@ -470,9 +473,7 @@ PreservedAnalyses InlinerPass::run(LazyCallGraph::SCC &InitialC,
           DeadFunctionsInComdats.push_back(&Callee);
         }
       }
-      if (CalleeWasDeleted)
-        Advice->recordInliningWithCalleeDeleted();
-      else
+      if (!CalleeWasDeleted)
         Advice->recordInlining();
     }
 

llvm/lib/Transforms/IPO/ModuleInliner.cpp

@@ -284,6 +284,10 @@ PreservedAnalyses ModuleInlinerPass::run(Module &M,
         Calls->erase_if([&](const std::pair<CallBase *, int> &Call) {
           return Call.first->getCaller() == &Callee;
         });
+
+        // Report inlining decision BEFORE deleting function contents, so we
+        // can still access e.g. the DebugLoc
+        Advice->recordInliningWithCalleeDeleted();
         // Clear the body and queue the function itself for deletion when we
         // finish inlining.
         // Note that after this point, it is an error to do anything other
@@ -295,9 +299,7 @@ PreservedAnalyses ModuleInlinerPass::run(Module &M,
         CalleeWasDeleted = true;
       }
     }
-    if (CalleeWasDeleted)
-      Advice->recordInliningWithCalleeDeleted();
-    else
+    if (!CalleeWasDeleted)
       Advice->recordInlining();
   }
 

llvm/test/Transforms/Inline/optimization-remarks-passed-deleted-callee-yaml.ll

@@ -0,0 +1,97 @@
+; RUN: opt < %s -S -passes=inline -pass-remarks-output=%t -pass-remarks=inline \
+; RUN:    -pass-remarks-missed=inline -pass-remarks-analysis=inline \
+; RUN:    -pass-remarks-with-hotness 2>&1 | FileCheck %s
+; RUN: cat %t | FileCheck -check-prefixes=YAML,YAML-NO-ANNOTATE %s
+
+; RUN: opt < %s -S -passes=inline -pass-remarks-output=%t -pass-remarks=inline \
+; RUN:    -pass-remarks-missed=inline -pass-remarks-analysis=inline \
+; RUN:    -pass-remarks-with-hotness 2>&1 | FileCheck %s
+; RUN: cat %t | FileCheck -check-prefixes=YAML,YAML-NO-ANNOTATE %s
+
+; RUN: opt < %s -S -passes=inliner-wrapper -pass-remarks-output=%t -pass-remarks=inline \
+; RUN:    -pass-remarks-missed=inline -pass-remarks-analysis=inline \
+; RUN:    -annotate-inline-phase=false \
+; RUN:    -pass-remarks-with-hotness 2>&1 | FileCheck %s
+; RUN: cat %t | FileCheck -check-prefixes=YAML,YAML-NO-ANNOTATE %s
+
+; RUN: opt < %s -S -passes=inliner-wrapper -pass-remarks-output=%t -pass-remarks=inline \
+; RUN:    -pass-remarks-missed=inline -pass-remarks-analysis=inline \
+; RUN:    -annotate-inline-phase \
+; RUN:    -pass-remarks-with-hotness 2>&1 | FileCheck %s
+; RUN: cat %t | FileCheck -check-prefixes=YAML,YAML-ANNOTATE %s
+
+; Same as optimization-remarks-passed-yaml.ll, but here foo has internal linkage
+; instead of external linkage. This exercises a different hook for reporting the inlining decision,
+; because foo is deleted after it is inlined (due to internal linkage).
+; Make sure that the Remark correctly emits the DebugLoc for foo before it is deleted.
+
+; CHECK: remark: /tmp/s.c:4:10: 'foo' inlined into 'bar' with (cost={{[0-9\-]+}}, threshold={{[0-9]+}}) at callsite bar:1:10; (hotness: 30)
+
+; YAML:      --- !Passed
+; YAML-NO-ANNOTATE-NEXT: Pass:            inline
+; YAML-ANNOTATE-NEXT: Pass:            main-always-inline
+; YAML-NEXT: Name:            Inlined
+; YAML-NEXT: DebugLoc:        { File: '/tmp/s.c', Line: 4, Column: 10 }
+; YAML-NEXT: Function:        bar
+; YAML-NEXT: Hotness:         30
+; YAML-NEXT: Args:
+; YAML-NEXT:   - String: ''''
+; YAML-NEXT:   - Callee: foo
+; YAML-NEXT:     DebugLoc:        { File: '/tmp/s.c', Line: 1, Column: 0 }
+; YAML-NEXT:   - String: ''' inlined into '''
+; YAML-NEXT:   - Caller: bar
+; YAML-NEXT:     DebugLoc:        { File: '/tmp/s.c', Line: 3, Column: 0 }
+; YAML-NEXT:   - String: ''''
+; YAML-NEXT:   - String: ' with '
+; YAML-NEXT:   - String: '(cost='
+; YAML-NEXT:   - Cost: '{{[0-9\-]+}}'
+; YAML-NEXT:   - String: ', threshold='
+; YAML-NEXT:   - Threshold: '{{[0-9]+}}'
+; YAML-NEXT:   - String: ')'
+; YAML-NEXT:   - String:          ' at callsite '
+; YAML-NEXT:   - String:          bar
+; YAML-NEXT:   - String:          ':'
+; YAML-NEXT:   - Line:            '1'
+; YAML-NEXT:   - String:          ':'
+; YAML-NEXT:   - Column:          '10'
+; YAML-NEXT:   - String:          ';'
+; YAML-NEXT: ...
+
+; ModuleID = '/tmp/s.c'
+source_filename = "/tmp/s.c"
+target datalayout = "e-m:o-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.11.0"
+
+; Function Attrs: nounwind ssp uwtable
+define internal i32 @foo() #0 !dbg !7 {
+entry:
+  ret i32 1, !dbg !9
+}
+
+; Function Attrs: nounwind ssp uwtable
+define i32 @bar() #0 !dbg !10 !prof !13 {
+entry:
+  %call = call i32 @foo(), !dbg !11
+  ret i32 %call, !dbg !12
+}
+
+attributes #0 = { nounwind ssp uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "frame-pointer"="all" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="core2" "target-features"="+cx16,+fxsr,+mmx,+sse,+sse2,+sse3,+ssse3,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" }
+
+!llvm.dbg.cu = !{!0}
+!llvm.module.flags = !{!3, !4, !5}
+!llvm.ident = !{!6}
+
+!0 = distinct !DICompileUnit(language: DW_LANG_C99, file: !1, producer: "clang version 4.0.0 (trunk 282540) (llvm/trunk 282542)", isOptimized: true, runtimeVersion: 0, emissionKind: LineTablesOnly, enums: !2)
+!1 = !DIFile(filename: "/tmp/s.c", directory: "/tmp")
+!2 = !{}
+!3 = !{i32 2, !"Dwarf Version", i32 4}
+!4 = !{i32 2, !"Debug Info Version", i32 3}
+!5 = !{i32 1, !"PIC Level", i32 2}
+!6 = !{!"clang version 4.0.0 (trunk 282540) (llvm/trunk 282542)"}
+!7 = distinct !DISubprogram(name: "foo", scope: !1, file: !1, line: 1, type: !8, isLocal: false, isDefinition: true, scopeLine: 1, isOptimized: true, unit: !0, retainedNodes: !2)
+!8 = !DISubroutineType(types: !2)
+!9 = !DILocation(line: 1, column: 13, scope: !7)
+!10 = distinct !DISubprogram(name: "bar", scope: !1, file: !1, line: 3, type: !8, isLocal: false, isDefinition: true, scopeLine: 3, isOptimized: true, unit: !0, retainedNodes: !2)
+!11 = !DILocation(line: 4, column: 10, scope: !10)
+!12 = !DILocation(line: 4, column: 3, scope: !10)
+!13 = !{!"function_entry_count", i64 30}