[BranchFolding] Avoid moving blocks to fall through to an indirect target (#152916)

Depend on #152591 to fix
#149023.
Similar to an EH pad, there is no real advantage in "falling through" to
an indirect target of an INLINEASM_BR. And multiple indirect targets of
inline asm at the end of a function may be rotated infinitely.
Therefore, this patch avoids such optimization on indirect target of
inline asm as fall through.

Author: XChy

llvm/lib/CodeGen/BranchFolding.cpp

@@ -1787,10 +1787,18 @@ bool BranchFolder::OptimizeBlock(MachineBasicBlock *MBB) {
       // below were performed for EH "FallThrough" blocks.  Therefore, even if
       // that appears not to be happening anymore, we should assume that it is
       // possible and not remove the "!FallThrough()->isEHPad" condition below.
+      //
+      // Similarly, the analyzeBranch call does not consider callbr, which also
+      // introduces the possibility of infinite rotation, as there may be
+      // multiple successors of PrevBB. Thus we check such case by
+      // FallThrough->isInlineAsmBrIndirectTarget().
+      // NOTE: Checking if PrevBB contains callbr is more precise, but much
+      // more expensive.
       MachineBasicBlock *PrevTBB = nullptr, *PrevFBB = nullptr;
       SmallVector<MachineOperand, 4> PrevCond;
-      if (FallThrough != MF.end() &&
-          !FallThrough->isEHPad() &&
+
+      if (FallThrough != MF.end() && !FallThrough->isEHPad() &&
+          !FallThrough->isInlineAsmBrIndirectTarget() &&
           !TII->analyzeBranch(PrevBB, PrevTBB, PrevFBB, PrevCond, true) &&
           PrevBB.isSuccessor(&*FallThrough)) {
         MBB->moveAfter(&MF.back());

llvm/test/CodeGen/X86/callbr-asm-loop.ll

@@ -1,35 +1,28 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
 
-; RUN: llc -O0 -mtriple=i686-- < %s | FileCheck %s
+; RUN: llc -O1 -mtriple=i686-- < %s | FileCheck %s
 
 ; Test that causes multiple defs of %eax.
-; FIXME: The testcase hangs with -O1/2/3 enabled.
 define i32 @loop1() nounwind {
 ; CHECK-LABEL: loop1:
 ; CHECK:       # %bb.0: # %entry
-; CHECK-NEXT:    pushl %esi
-; CHECK-NEXT:    jmp .LBB0_1
+; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB0_1: # %tailrecurse
 ; CHECK-NEXT:    # =>This Inner Loop Header: Depth=1
 ; CHECK-NEXT:    xorl %eax, %eax
 ; CHECK-NEXT:    movl $1, %edx
 ; CHECK-NEXT:    #APP
 ; CHECK-NEXT:    #NO_APP
-; CHECK-NEXT:    movl %eax, %ecx
-; CHECK-NEXT:    movl %edx, %esi
-; CHECK-NEXT:    jmp .LBB0_3
+; CHECK-NEXT:    jmp .LBB0_1
 ; CHECK-NEXT:  .LBB0_2: # Inline asm indirect target
-; CHECK-NEXT:    # %tailrecurse.tailrecurse.backedge_crit_edge
+; CHECK-NEXT:    # %tailrecurse.tailrecurse_crit_edge
 ; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
 ; CHECK-NEXT:    # Label of block must be emitted
-; CHECK-NEXT:  .LBB0_3: # %tailrecurse.backedge
-; CHECK-NEXT:    # in Loop: Header=BB0_1 Depth=1
 ; CHECK-NEXT:    jmp .LBB0_1
-; CHECK-NEXT:  .LBB0_4: # Inline asm indirect target
+; CHECK-NEXT:  .LBB0_3: # Inline asm indirect target
 ; CHECK-NEXT:    # %lab2.split
 ; CHECK-NEXT:    # Label of block must be emitted
 ; CHECK-NEXT:    movl %edx, %eax
-; CHECK-NEXT:    popl %esi
 ; CHECK-NEXT:    retl
 entry:
   br label %tailrecurse