[RISCV] Fix assertion failure when using -fstack-clash-protection

We can't assume MBBI is still pointing at MBB if we've already expanded
a probe. We need to re-query the MBB from MBBI. Fixes #135206

Co-authored-by: Craig Topper <[email protected]>

Author: ilovepi

llvm/lib/Target/RISCV/RISCVFrameLowering.cpp

@@ -2270,11 +2270,13 @@ TargetStackID::Value RISCVFrameLowering::getStackIDForScalableVectors() const {
 }
 
 // Synthesize the probe loop.
-static void emitStackProbeInline(MachineFunction &MF, MachineBasicBlock &MBB,
-                                 MachineBasicBlock::iterator MBBI, DebugLoc DL,
+static void emitStackProbeInline(MachineBasicBlock::iterator MBBI, DebugLoc DL,
                                  Register TargetReg, bool IsRVV) {
   assert(TargetReg != RISCV::X2 && "New top of stack cannot already be in SP");
 
+  MachineBasicBlock &MBB = *MBBI->getParent();
+  MachineFunction &MF = *MBB.getParent();
+
   auto &Subtarget = MF.getSubtarget<RISCVSubtarget>();
   const RISCVInstrInfo *TII = Subtarget.getInstrInfo();
   bool IsRV64 = Subtarget.is64Bit();
@@ -2363,7 +2365,7 @@ void RISCVFrameLowering::inlineStackProbe(MachineFunction &MF,
       MachineBasicBlock::iterator MBBI = MI->getIterator();
       DebugLoc DL = MBB.findDebugLoc(MBBI);
       Register TargetReg = MI->getOperand(1).getReg();
-      emitStackProbeInline(MF, MBB, MBBI, DL, TargetReg,
+      emitStackProbeInline(MBBI, DL, TargetReg,
                            (MI->getOpcode() == RISCV::PROBED_STACKALLOC_RVV));
       MBBI->eraseFromParent();
     }

llvm/test/CodeGen/RISCV/pr135206.ll

@@ -0,0 +1,105 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
+; RUN: llc -mtriple riscv64 < %s -o - | FileCheck %s
+
+%"buff" = type { [4096 x i64] }
+
+declare void @llvm.memset.p0.i64(ptr, i8, i64, i1)
+declare void @bar()
+
+define i1 @foo() #0 {
+; CHECK-LABEL: foo:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    addi sp, sp, -2032
+; CHECK-NEXT:    .cfi_def_cfa_offset 2032
+; CHECK-NEXT:    sd ra, 2024(sp) # 8-byte Folded Spill
+; CHECK-NEXT:    sd s0, 2016(sp) # 8-byte Folded Spill
+; CHECK-NEXT:    sd s1, 2008(sp) # 8-byte Folded Spill
+; CHECK-NEXT:    sd s2, 2000(sp) # 8-byte Folded Spill
+; CHECK-NEXT:    sd s3, 1992(sp) # 8-byte Folded Spill
+; CHECK-NEXT:    .cfi_offset ra, -8
+; CHECK-NEXT:    .cfi_offset s0, -16
+; CHECK-NEXT:    .cfi_offset s1, -24
+; CHECK-NEXT:    .cfi_offset s2, -32
+; CHECK-NEXT:    .cfi_offset s3, -40
+; CHECK-NEXT:    lui a0, 7
+; CHECK-NEXT:    sub t1, sp, a0
+; CHECK-NEXT:    .cfi_def_cfa t1, 28672
+; CHECK-NEXT:    lui t2, 1
+; CHECK-NEXT:  .LBB0_1: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    sub sp, sp, t2
+; CHECK-NEXT:    sd zero, 0(sp)
+; CHECK-NEXT:    bne sp, t1, .LBB0_1
+; CHECK-NEXT:  # %bb.2:
+; CHECK-NEXT:    .cfi_def_cfa_register sp
+; CHECK-NEXT:    addi sp, sp, -2048
+; CHECK-NEXT:    addi sp, sp, -96
+; CHECK-NEXT:    .cfi_def_cfa_offset 30816
+; CHECK-NEXT:    csrr t1, vlenb
+; CHECK-NEXT:    .cfi_def_cfa t1, -8
+; CHECK-NEXT:    lui t2, 1
+; CHECK-NEXT:  .LBB0_3: # =>This Inner Loop Header: Depth=1
+; CHECK-NEXT:    sub sp, sp, t2
+; CHECK-NEXT:    sd zero, 0(sp)
+; CHECK-NEXT:    sub t1, t1, t2
+; CHECK-NEXT:    bge t1, t2, .LBB0_3
+; CHECK-NEXT:  # %bb.4:
+; CHECK-NEXT:    .cfi_def_cfa_register sp
+; CHECK-NEXT:    sub sp, sp, t1
+; CHECK-NEXT:    .cfi_escape 0x0f, 0x0f, 0x72, 0x00, 0x11, 0xd0, 0x80, 0x02, 0x22, 0x11, 0x01, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 32848 + 1 * vlenb
+; CHECK-NEXT:    li a0, 86
+; CHECK-NEXT:    addi s0, sp, 48
+; CHECK-NEXT:    addi s1, sp, 32
+; CHECK-NEXT:    addi s2, sp, 16
+; CHECK-NEXT:    lui a1, 353637
+; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
+; CHECK-NEXT:    vmv.v.x v8, a0
+; CHECK-NEXT:    lui a0, 8
+; CHECK-NEXT:    addiw a0, a0, 32
+; CHECK-NEXT:    add a0, sp, a0
+; CHECK-NEXT:    vs1r.v v8, (a0) # vscale x 8-byte Folded Spill
+; CHECK-NEXT:    addiw a0, a1, 1622
+; CHECK-NEXT:    vse8.v v8, (s0)
+; CHECK-NEXT:    vse8.v v8, (s1)
+; CHECK-NEXT:    vse8.v v8, (s2)
+; CHECK-NEXT:    slli a1, a0, 32
+; CHECK-NEXT:    add s3, a0, a1
+; CHECK-NEXT:    sd s3, 64(sp)
+; CHECK-NEXT:    call bar
+; CHECK-NEXT:    lui a0, 8
+; CHECK-NEXT:    addiw a0, a0, 32
+; CHECK-NEXT:    add a0, sp, a0
+; CHECK-NEXT:    vl1r.v v8, (a0) # vscale x 8-byte Folded Reload
+; CHECK-NEXT:    vsetivli zero, 16, e8, m1, ta, ma
+; CHECK-NEXT:    vse8.v v8, (s2)
+; CHECK-NEXT:    vse8.v v8, (s1)
+; CHECK-NEXT:    vse8.v v8, (s0)
+; CHECK-NEXT:    sd s3, 64(sp)
+; CHECK-NEXT:    li a0, 0
+; CHECK-NEXT:    csrr a1, vlenb
+; CHECK-NEXT:    add sp, sp, a1
+; CHECK-NEXT:    .cfi_def_cfa sp, 2032
+; CHECK-NEXT:    lui a1, 8
+; CHECK-NEXT:    addiw a1, a1, -1952
+; CHECK-NEXT:    add sp, sp, a1
+; CHECK-NEXT:    .cfi_def_cfa_offset 2032
+; CHECK-NEXT:    ld ra, 2024(sp) # 8-byte Folded Reload
+; CHECK-NEXT:    ld s0, 2016(sp) # 8-byte Folded Reload
+; CHECK-NEXT:    ld s1, 2008(sp) # 8-byte Folded Reload
+; CHECK-NEXT:    ld s2, 2000(sp) # 8-byte Folded Reload
+; CHECK-NEXT:    ld s3, 1992(sp) # 8-byte Folded Reload
+; CHECK-NEXT:    .cfi_restore ra
+; CHECK-NEXT:    .cfi_restore s0
+; CHECK-NEXT:    .cfi_restore s1
+; CHECK-NEXT:    .cfi_restore s2
+; CHECK-NEXT:    .cfi_restore s3
+; CHECK-NEXT:    addi sp, sp, 2032
+; CHECK-NEXT:    .cfi_def_cfa_offset 0
+; CHECK-NEXT:    ret
+  %1 = alloca %"buff", align 8
+  call void @llvm.memset.p0.i64(ptr %1, i8 86, i64 56, i1 false)
+  call void @bar()
+  call void @llvm.memset.p0.i64(ptr %1, i8 86, i64 56, i1 false)
+  ret i1 false
+}
+
+attributes #0 = { "probe-stack"="inline-asm" "target-features"="+v" }