[BOLT] Fix impute-fall-throughs (#166305)

BOLT expects pre-aggregated profile entries to be unique, which holds
for externally aggregated traces (or branches+fall-through ranges).
Therefore, BOLT doesn't merge duplicate entries for faster processing.
However, such traces are not expressly prohibited and could come from
concatenated pre-aggregated profiles or otherwise.

Relax the assumption about no duplicate (branch-only) traces in fall-
through imputing.

Test Plan: updated callcont-fallthru.s

Author: aaupov

bolt/lib/Profile/DataAggregator.cpp

@@ -564,30 +564,30 @@ void DataAggregator::imputeFallThroughs() {
     // Skip fall-throughs in external code.
     if (Trace.From == Trace::EXTERNAL)
       continue;
-    std::pair CurrentBranch(Trace.Branch, Trace.From);
+    if (std::pair CurrentBranch(Trace.Branch, Trace.From);
+        CurrentBranch != PrevBranch) {
+      // New group: reset aggregates.
+      AggregateCount = AggregateFallthroughSize = 0;
+      PrevBranch = CurrentBranch;
+    }
     // BR_ONLY must be the last trace in the group
     if (Trace.To == Trace::BR_ONLY) {
       // If the group is not empty, use aggregate values, otherwise 0-length
       // for unconditional jumps (call/ret/uncond branch) or 1-length for others
       uint64_t InferredBytes =
-          PrevBranch == CurrentBranch
+          AggregateFallthroughSize
               ? AggregateFallthroughSize / AggregateCount
               : !checkUnconditionalControlTransfer(Trace.From);
       Trace.To = Trace.From + InferredBytes;
       LLVM_DEBUG(dbgs() << "imputed " << Trace << " (" << InferredBytes
                         << " bytes)\n");
       ++InferredTraces;
     } else {
-      // Trace with a valid fall-through
-      // New group: reset aggregates.
-      if (CurrentBranch != PrevBranch)
-        AggregateCount = AggregateFallthroughSize = 0;
       // Only use valid fall-through lengths
       if (Trace.To != Trace::EXTERNAL)
         AggregateFallthroughSize += (Trace.To - Trace.From) * Info.TakenCount;
       AggregateCount += Info.TakenCount;
     }
-    PrevBranch = CurrentBranch;
   }
   if (opts::Verbosity >= 1)
     outs() << "BOLT-INFO: imputed " << InferredTraces << " traces\n";

bolt/test/X86/callcont-fallthru.s

@@ -15,6 +15,8 @@
 # External return to a landing pad/entry point call continuation
 # RUN: link_fdata %s %t %t.pa-eret PREAGG-ERET
 # RUN-DISABLED: link_fdata %s %t %t.pa-plt PREAGG-PLT
+## Fall-through imputing test cases
+# RUN: link_fdata %s %t %t.pa-imp PREAGG-IMP
 
 # RUN: llvm-strip --strip-unneeded %t -o %t.strip
 # RUN: llvm-objcopy --remove-section=.eh_frame %t.strip %t.noeh
@@ -63,6 +65,11 @@
 # RUN-DISABLED:   --check-prefix=CHECK-PLT
 # CHECK-PLT: traces mismatching disassembled function contents: 0
 
+## Check --impute-trace-fall-throughs accepting duplicate branch-only traces
+# RUN: perf2bolt %t --pa -p %t.pa-imp -o %t.pa-imp.fdata --impute-trace-fall-through
+# RUN: FileCheck %s --check-prefix=CHECK-IMP --input-file %t.pa-imp.fdata
+# CHECK-IMP: 0 [unknown] 0 1 main {{.*}} 0 3
+
   .globl foo
   .type foo, %function
 foo:
@@ -102,6 +109,8 @@ Ltmp1:
 
 Ltmp4:
 	cmpl	$0x0, -0x14(%rbp)
+# PREAGG-IMP: B X:0 #Ltmp4_br# 1 0
+# PREAGG-IMP: B X:0 #Ltmp4_br# 2 0
 Ltmp4_br:
 	je	Ltmp0