Merging r354672:

------------------------------------------------------------------------
r354672 | petarj | 2019-02-22 06:53:58 -0800 (Fri, 22 Feb 2019) | 13 lines

[mips][micromips] fix filling delay slots for PseudoIndirectBranch_MM

Filling a delay slot in 32bit jump instructions with a 16bit instruction
can cause issues. According to the documentation such an operation is
unpredictable.
This patch adds opcode Mips::PseudoIndirectBranch_MM alongside
Mips::PseudoIndirectBranch and other instructions that are expanded to jr
instruction and do not allow a 16bit instruction in their delay slots.

Patch by Mirko Brkusanin.

Differential Revision: https://reviews.llvm.org/D58507

------------------------------------------------------------------------

llvm-svn: 358920

Author: tstellar

llvm/lib/Target/Mips/MipsDelaySlotFiller.cpp

@@ -726,6 +726,7 @@ bool MipsDelaySlotFiller::searchRange(MachineBasicBlock &MBB, IterTy Begin,
     // but we don't have enough information to make that decision.
      if (InMicroMipsMode && TII->getInstSizeInBytes(*CurrI) == 2 &&
         (Opcode == Mips::JR || Opcode == Mips::PseudoIndirectBranch ||
+         Opcode == Mips::PseudoIndirectBranch_MM ||
          Opcode == Mips::PseudoReturn || Opcode == Mips::TAILCALL))
       continue;
      // Instructions LWP/SWP and MOVEP should not be in a delay slot as that

llvm/test/CodeGen/Mips/pseudo-jump-fill.ll

@@ -0,0 +1,68 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -mtriple=mipsel-linux-gnu -mattr=+micromips -relocation-model=pic < %s | FileCheck %s
+
+; Test that the delay slot filler correctly handles indirect branches for
+; microMIPS in regard to incorrectly using 16bit instructions in delay slots of
+; 32bit instructions.
+
+define i32 @test(i32 signext %x, i32 signext %c) {
+; CHECK-LABEL: test:
+; CHECK:       # %bb.0: # %entry
+; CHECK-NEXT:    lui $2, %hi(_gp_disp)
+; CHECK-NEXT:    addiu $2, $2, %lo(_gp_disp)
+; CHECK-NEXT:    addiur2 $5, $5, -1
+; CHECK-NEXT:    sltiu $1, $5, 4
+; CHECK-NEXT:    beqz $1, $BB0_3
+; CHECK-NEXT:    addu $3, $2, $25
+; CHECK-NEXT:  $BB0_1: # %entry
+; CHECK-NEXT:    li16 $2, 0
+; CHECK-NEXT:    sll16 $5, $5, 2
+; CHECK-NEXT:    lw $6, %got($JTI0_0)($3)
+; CHECK-NEXT:    addu16 $5, $5, $6
+; CHECK-NEXT:    lw $5, %lo($JTI0_0)($5)
+; CHECK-NEXT:    addu16 $3, $5, $3
+; CHECK-NEXT:    jr $3
+; CHECK-NEXT:    nop
+; CHECK-NEXT:  $BB0_2: # %sw.bb2
+; CHECK-NEXT:    addiur2 $2, $4, 1
+; CHECK-NEXT:    jrc $ra
+; CHECK-NEXT:  $BB0_3:
+; CHECK-NEXT:    move $2, $4
+; CHECK-NEXT:    jrc $ra
+; CHECK-NEXT:  $BB0_4: # %sw.bb3
+; CHECK-NEXT:    addius5 $4, 2
+; CHECK-NEXT:    move $2, $4
+; CHECK-NEXT:    jrc $ra
+; CHECK-NEXT:  $BB0_5: # %sw.bb5
+; CHECK-NEXT:    addius5 $4, 3
+; CHECK-NEXT:    move $2, $4
+; CHECK-NEXT:  $BB0_6: # %for.cond.cleanup
+; CHECK-NEXT:    jrc $ra
+entry:
+  switch i32 %c, label %sw.epilog [
+    i32 4, label %sw.bb5
+    i32 1, label %for.cond.cleanup
+    i32 2, label %sw.bb2
+    i32 3, label %sw.bb3
+  ]
+
+sw.bb2:
+  %add = add nsw i32 %x, 1
+  br label %sw.epilog
+
+sw.bb3:
+  %add4 = add nsw i32 %x, 2
+  br label %sw.epilog
+
+sw.bb5:
+  %add6 = add nsw i32 %x, 3
+  br label %sw.epilog
+
+sw.epilog:
+  %a.0 = phi i32 [ %add6, %sw.bb5 ], [ %add4, %sw.bb3 ], [ %add, %sw.bb2 ], [ %x, %entry ]
+  br label %for.cond.cleanup
+
+for.cond.cleanup:
+  %a.028 = phi i32 [ %a.0, %sw.epilog ], [ 0, %entry ]
+  ret i32 %a.028
+}