[llvm] 917574d - [MachineLICM][WinEH] Don't hoist register reloads out of funclets
Martin Storsjö via llvm-commits
llvm-commits at lists.llvm.org
Sun Aug 13 14:04:33 PDT 2023
Author: Karl-Johan Johnsson
Date: 2023-08-13T23:58:16+03:00
New Revision: 917574d5d8beacbefab4d0e6469dac5b50117832
URL: https://github.com/llvm/llvm-project/commit/917574d5d8beacbefab4d0e6469dac5b50117832
DIFF: https://github.com/llvm/llvm-project/commit/917574d5d8beacbefab4d0e6469dac5b50117832.diff
LOG: [MachineLICM][WinEH] Don't hoist register reloads out of funclets
This fixes https://github.com/llvm/llvm-project/issues/60766
With MSVC style exception-handling (funclets), no registers are
alive when entering the funclet so they must be reloaded from the
stack. MachineLICM can sometimes hoist such reloads out of the
funclet which is not correct, the register will have been clobbered
when entering the funclet. This can happen in any loop that
contains a try-catch.
This has been tested on x86_64-pc-window-msvc. I'm not sure if
funclets work the same on the other windows archs.
Reviewed By: rnk, arsenm
Differential Revision: https://reviews.llvm.org/D153337
Added:
llvm/test/CodeGen/X86/machine-licm-vs-wineh.mir
Modified:
llvm/lib/CodeGen/MachineLICM.cpp
Removed:
################################################################################
diff --git a/llvm/lib/CodeGen/MachineLICM.cpp b/llvm/lib/CodeGen/MachineLICM.cpp
index 4ca487e183d60e..fa7aa4a7a44ad0 100644
--- a/llvm/lib/CodeGen/MachineLICM.cpp
+++ b/llvm/lib/CodeGen/MachineLICM.cpp
@@ -538,6 +538,10 @@ void MachineLICMBase::HoistRegionPostRA() {
PhysRegDefs.set(*AI);
}
+ // Funclet entry blocks will clobber all registers
+ if (const uint32_t *Mask = BB->getBeginClobberMask(TRI))
+ PhysRegClobbers.setBitsNotInMask(Mask);
+
SpeculationState = SpeculateUnknown;
for (MachineInstr &MI : *BB)
ProcessMI(&MI, PhysRegDefs, PhysRegClobbers, StoredFIs, Candidates);
diff --git a/llvm/test/CodeGen/X86/machine-licm-vs-wineh.mir b/llvm/test/CodeGen/X86/machine-licm-vs-wineh.mir
new file mode 100644
index 00000000000000..4bfd749fb77235
--- /dev/null
+++ b/llvm/test/CodeGen/X86/machine-licm-vs-wineh.mir
@@ -0,0 +1,141 @@
+# RUN: llc -o - %s -mtriple=x86_64-pc-windows-msvc -run-pass=machinelicm | FileCheck %s
+#
+# This test checks that MachineLICM doesn't hoist loads out of funclets.
+# Manually modified from the IR of the following C++ function by running
+# llc -stop-after=machine-cp.
+#
+# void may_throw();
+# void use(int);
+#
+# void test(int n, int arg)
+# {
+# for (int i = 0 ; i < n ; i++)
+# try {
+# may_throw();
+# }
+# catch (...) {
+# // Two uses to get 'arg' allocated to a register
+# use(arg);
+# use(arg);
+# }
+# }
+
+--- |
+ target triple = "x86_64-pc-windows-msvc"
+
+ define void @test(i32 %n, i32 %arg) personality ptr @__CxxFrameHandler3 {
+ entry:
+ %cmp3 = icmp sgt i32 %n, 0
+ br i1 %cmp3, label %for.body.preheader, label %for.cond.cleanup
+
+ for.body.preheader: ; preds = %entry
+ br label %for.body
+
+ for.cond.cleanup: ; preds = %for.inc, %entry
+ ret void
+
+ for.body: ; preds = %for.body.preheader, %for.inc
+ %lsr.iv = phi i32 [ %n, %for.body.preheader ], [ %lsr.iv.next, %for.inc ]
+ invoke void @may_throw()
+ to label %for.inc unwind label %catch.dispatch
+
+ catch.dispatch: ; preds = %for.body
+ %0 = catchswitch within none [label %catch] unwind to caller
+
+ catch: ; preds = %catch.dispatch
+ %1 = catchpad within %0 [ptr null, i32 64, ptr null]
+ call void @use(i32 %arg) [ "funclet"(token %1) ]
+ call void @use(i32 %arg) [ "funclet"(token %1) ]
+ catchret from %1 to label %for.inc
+
+ for.inc: ; preds = %catch, %for.body
+ %lsr.iv.next = add i32 %lsr.iv, -1
+ %exitcond.not = icmp eq i32 %lsr.iv.next, 0
+ br i1 %exitcond.not, label %for.cond.cleanup, label %for.body
+ }
+
+ declare i32 @__CxxFrameHandler3(...)
+
+ declare void @may_throw()
+
+ declare void @use(i32)
+
+...
+---
+name: test
+alignment: 16
+tracksRegLiveness: true
+hasEHCatchret: true
+hasEHScopes: true
+hasEHFunclets: true
+debugInstrRef: true
+tracksDebugUserValues: true
+liveins:
+ - { reg: '$ecx' }
+ - { reg: '$edx' }
+frameInfo:
+ maxAlignment: 8
+ hasCalls: true
+ hasOpaqueSPAdjustment: true
+stack:
+ - { id: 0, type: spill-slot, size: 4, alignment: 4 }
+ - { id: 1, type: spill-slot, size: 4, alignment: 4 }
+machineFunctionInfo: {}
+body: |
+ bb.0.entry:
+ successors: %bb.1, %bb.2
+ liveins: $ecx, $edx
+
+ MOV32mr %stack.1, 1, $noreg, 0, $noreg, $edx :: (store (s32) into %stack.1)
+ TEST32rr renamable $ecx, renamable $ecx, implicit-def $eflags
+ JCC_1 %bb.2, 14, implicit killed $eflags
+
+ bb.1:
+ liveins: $ecx
+
+ JMP_1 %bb.3
+
+ bb.2.for.cond.cleanup:
+ RET 0
+
+ bb.3.for.body:
+ successors: %bb.5, %bb.4
+ liveins: $ecx
+
+ EH_LABEL <mcsymbol .Leh1>
+ MOV32mr %stack.0, 1, $noreg, 0, $noreg, killed renamable $ecx :: (store (s32) into %stack.0)
+ ADJCALLSTACKDOWN64 32, 0, 0, implicit-def dead $rsp, implicit-def dead $eflags, implicit-def dead $ssp, implicit $rsp, implicit $ssp
+ CALL64pcrel32 @may_throw, csr_win64, implicit $rsp, implicit $ssp, implicit-def $rsp, implicit-def $ssp
+ ADJCALLSTACKUP64 32, 0, implicit-def dead $rsp, implicit-def dead $eflags, implicit-def dead $ssp, implicit $rsp, implicit $ssp
+ EH_LABEL <mcsymbol .Leh2>
+ JMP_1 %bb.5
+
+ bb.4.catch (landing-pad, ehfunclet-entry):
+ successors: %bb.5
+
+ ADJCALLSTACKDOWN64 32, 0, 0, implicit-def dead $rsp, implicit-def dead $eflags, implicit-def dead $ssp, implicit $rsp, implicit $ssp
+ renamable $esi = MOV32rm %stack.1, 1, $noreg, 0, $noreg :: (load (s32) from %stack.1)
+ $ecx = COPY renamable $esi
+ CALL64pcrel32 @use, csr_win64, implicit $rsp, implicit $ssp, implicit $ecx, implicit-def $rsp, implicit-def $ssp
+ ADJCALLSTACKUP64 32, 0, implicit-def dead $rsp, implicit-def dead $eflags, implicit-def dead $ssp, implicit $rsp, implicit $ssp
+ ADJCALLSTACKDOWN64 32, 0, 0, implicit-def dead $rsp, implicit-def dead $eflags, implicit-def dead $ssp, implicit $rsp, implicit $ssp
+ $ecx = COPY killed renamable $esi
+ CALL64pcrel32 @use, csr_win64, implicit $rsp, implicit $ssp, implicit $ecx, implicit-def $rsp, implicit-def $ssp
+ ADJCALLSTACKUP64 32, 0, implicit-def dead $rsp, implicit-def dead $eflags, implicit-def dead $ssp, implicit $rsp, implicit $ssp
+ CATCHRET %bb.5, %bb.0
+
+ bb.5.for.inc:
+ successors: %bb.2, %bb.3
+
+ renamable $ecx = MOV32rm %stack.0, 1, $noreg, 0, $noreg :: (load (s32) from %stack.0)
+ renamable $ecx = DEC32r killed renamable $ecx, implicit-def $eflags
+ JCC_1 %bb.2, 4, implicit killed $eflags
+ JMP_1 %bb.3
+
+...
+#
+# CHECK: bb.4.catch
+# CHECK: ADJCALLSTACKDOWN64
+# CHECK-NEXT: renamable [[REG:\$[a-z0-9]+]] = MOV32rm %stack.1
+# CHECK-NEXT: $ecx = COPY renamable [[REG]]
+# CHECK-NEXT: CALL64pcrel32 @use
More information about the llvm-commits
mailing list