[BOLT] Keep multi-entry functions simple in aggregation mode (llvm#128253)

BOLT used to mark multi-entry functions non-simple in non-relocation
mode with the reasoning that we can't move them due to potentially
undetected references. However, in aggregation mode it doesn't apply as
BOLT doesn't perform optimizations.

Relax this constraint in case of an aggregation job.

Test Plan: added entry-point-fallthru.s

Author: aaupov

bolt/lib/Core/BinaryFunction.cpp

@@ -15,6 +15,7 @@
 #include "bolt/Core/DynoStats.h"
 #include "bolt/Core/HashUtilities.h"
 #include "bolt/Core/MCPlusBuilder.h"
+#include "bolt/Utils/CommandLineOpts.h"
 #include "bolt/Utils/NameResolver.h"
 #include "bolt/Utils/NameShortener.h"
 #include "bolt/Utils/Utils.h"
@@ -1753,8 +1754,8 @@ void BinaryFunction::postProcessEntryPoints() {
     // In non-relocation mode there's potentially an external undetectable
     // reference to the entry point and hence we cannot move this entry
     // point. Optimizing without moving could be difficult.
-    // In BAT mode, register any known entry points for CFG construction.
-    if (!BC.HasRelocations && !BC.HasBATSection)
+    // In aggregation, register any known entry points for CFG construction.
+    if (!BC.HasRelocations && !opts::AggregateOnly)
       setSimple(false);
 
     const uint32_t Offset = KV.first;

bolt/test/X86/entry-point-fallthru.s

@@ -0,0 +1,24 @@
+## Checks that fallthroughs spanning entry points are accepted in aggregation
+## mode.
+
+# RUN: llvm-mc -filetype=obj -triple x86_64-unknown-unknown %s -o %t.o
+# RUN: ld.lld %t.o -o %t
+# RUN: link_fdata %s %t %t.preagg PREAGG
+# RUN: perf2bolt %t -p %t.preagg --pa -o %t.fdata | FileCheck %s
+# CHECK: traces mismatching disassembled function contents: 0
+
+	.globl main
+main:
+	.cfi_startproc
+	vmovaps %zmm31,%zmm3
+
+next:
+	add    $0x4,%r9
+	add    $0x40,%r10
+	dec    %r14
+Ljmp:
+	jne    main
+# PREAGG: T #Ljmp# #main# #Ljmp# 1
+	ret
+	.cfi_endproc
+.size main,.-main