[ARM64][Windows] Share unwind codes between epilogues
There are cases where we have multiple epilogues that have the exact same unwind
code sequence. In that case, the epilogues can share the same unwind codes in
the .xdata section. This should get us past the assert "SEH unwind data
splitting not yet implemented" in many cases.
We still need to add support for generating multiple .pdata/.xdata sections for
those functions that need to be split into fragments.
Differential Revision: https://reviews.llvm.org/D56813
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@351421 91177308-0d34-0410-b5e6-96231b3b80d8
diff --git a/lib/MC/MCWin64EH.cpp b/lib/MC/MCWin64EH.cpp
index 0724b10..2e4eea3 100644
--- a/lib/MC/MCWin64EH.cpp
+++ b/lib/MC/MCWin64EH.cpp
@@ -453,6 +453,38 @@
}
}
+// Returns the epilog symbol of an epilog with the exact same unwind code
+// sequence, if it exists. Otherwise, returns nulltpr.
+// EpilogInstrs - Unwind codes for the current epilog.
+// Epilogs - Epilogs that potentialy match the current epilog.
+static MCSymbol*
+FindMatchingEpilog(const std::vector<WinEH::Instruction>& EpilogInstrs,
+ const std::vector<MCSymbol *>& Epilogs,
+ const WinEH::FrameInfo *info) {
+ for (auto *EpilogStart : Epilogs) {
+ auto InstrsIter = info->EpilogMap.find(EpilogStart);
+ assert(InstrsIter != info->EpilogMap.end() &&
+ "Epilog not found in EpilogMap");
+ const auto &Instrs = InstrsIter->second;
+
+ if (Instrs.size() != EpilogInstrs.size())
+ continue;
+
+ bool Match = true;
+ for (unsigned i = 0; i < Instrs.size(); ++i)
+ if (Instrs[i].Operation != EpilogInstrs[i].Operation ||
+ Instrs[i].Offset != EpilogInstrs[i].Offset ||
+ Instrs[i].Register != EpilogInstrs[i].Register) {
+ Match = false;
+ break;
+ }
+
+ if (Match)
+ return EpilogStart;
+ }
+ return nullptr;
+}
+
// Populate the .xdata section. The format of .xdata on ARM64 is documented at
// https://docs.microsoft.com/en-us/cpp/build/arm64-exception-handling
static void ARM64EmitUnwindInfo(MCStreamer &streamer, WinEH::FrameInfo *info) {
@@ -477,12 +509,29 @@
// Process epilogs.
MapVector<MCSymbol *, uint32_t> EpilogInfo;
+ // Epilogs processed so far.
+ std::vector<MCSymbol *> AddedEpilogs;
+
for (auto &I : info->EpilogMap) {
MCSymbol *EpilogStart = I.first;
auto &EpilogInstrs = I.second;
uint32_t CodeBytes = ARM64CountOfUnwindCodes(EpilogInstrs);
- EpilogInfo[EpilogStart] = TotalCodeBytes;
- TotalCodeBytes += CodeBytes;
+
+ uint32_t NumUnwindCodes = EpilogInstrs.size();
+ MCSymbol* MatchingEpilog =
+ FindMatchingEpilog(EpilogInstrs, AddedEpilogs, info);
+ if (MatchingEpilog) {
+ assert(EpilogInfo.find(MatchingEpilog) != EpilogInfo.end() &&
+ "Duplicate epilog not found");
+ EpilogInfo[EpilogStart] = EpilogInfo[MatchingEpilog];
+ // Clear the unwind codes in the EpilogMap, so that they don't get output
+ // in the logic below.
+ EpilogInstrs.clear();
+ } else {
+ EpilogInfo[EpilogStart] = TotalCodeBytes;
+ TotalCodeBytes += CodeBytes;
+ AddedEpilogs.push_back(EpilogStart);
+ }
}
// Code Words, Epilog count, E, X, Vers, Function Length
diff --git a/test/CodeGen/AArch64/wineh4.mir b/test/CodeGen/AArch64/wineh4.mir
index 4d4cc89..3a32432 100644
--- a/test/CodeGen/AArch64/wineh4.mir
+++ b/test/CodeGen/AArch64/wineh4.mir
@@ -1,7 +1,7 @@
# RUN: llc -o - %s -mtriple=aarch64-windows -start-after=prologepilog \
# RUN: -disable-branch-fold -filetype=obj \
# RUN: | llvm-readobj -unwind | FileCheck %s
-# Check that multiple epilgoues are correctly placed in .xdata.
+# Check that identical multiple epilgoues are correctly shared in .xdata.
# CHECK: ExceptionData {
# CHECK-NEXT: FunctionLength: 164
@@ -9,7 +9,7 @@
# CHECK-NEXT: ExceptionData: No
# CHECK-NEXT: EpiloguePacked: No
# CHECK-NEXT: EpilogueScopes: 2
-# CHECK-NEXT: ByteCodeLength: 48
+# CHECK-NEXT: ByteCodeLength: 32
# CHECK-NEXT: Prologue [
# CHECK-NEXT: 0xc80c ; stp x19, x20, [sp, #96]
# CHECK-NEXT: 0xc88a ; stp x21, x22, [sp, #80]
@@ -37,7 +37,7 @@
# CHECK-NEXT: }
# CHECK-NEXT: EpilogueScope {
# CHECK-NEXT: StartOffset: 33
-# CHECK-NEXT: EpilogueStartIndex: 30
+# CHECK-NEXT: EpilogueStartIndex: 15
# CHECK-NEXT: Opcodes [
# CHECK-NEXT: 0xc80c ; ldp x19, x20, [sp, #96]
# CHECK-NEXT: 0xc88a ; ldp x21, x22, [sp, #80]
diff --git a/test/CodeGen/AArch64/wineh8.mir b/test/CodeGen/AArch64/wineh8.mir
new file mode 100644
index 0000000..606bc14
--- /dev/null
+++ b/test/CodeGen/AArch64/wineh8.mir
@@ -0,0 +1,225 @@
+# RUN: llc -o - %s -mtriple=aarch64-windows -start-after=prologepilog \
+# RUN: -disable-branch-fold -filetype=obj \
+# RUN: | llvm-readobj -unwind | FileCheck %s
+# Check that non-identical multiple epilgoues are correctly shared in .xdata.
+
+# CHECK: ExceptionData {
+# CHECK-NEXT: FunctionLength: 160
+# CHECK-NEXT: Version: 0
+# CHECK-NEXT: ExceptionData: No
+# CHECK-NEXT: EpiloguePacked: No
+# CHECK-NEXT: EpilogueScopes: 2
+# CHECK-NEXT: ByteCodeLength: 44
+# CHECK-NEXT: Prologue [
+# CHECK-NEXT: 0xc80c ; stp x19, x20, [sp, #96]
+# CHECK-NEXT: 0xc88a ; stp x21, x22, [sp, #80]
+# CHECK-NEXT: 0xc908 ; stp x23, x24, [sp, #64]
+# CHECK-NEXT: 0xc986 ; stp x25, x26, [sp, #48]
+# CHECK-NEXT: 0xca04 ; stp x27, x28, [sp, #32]
+# CHECK-NEXT: 0xd802 ; stp d8, d9, [sp, #16]
+# CHECK-NEXT: 0xda8d ; stp d10, d11, [sp, #-112]!
+# CHECK-NEXT: 0xe4 ; end
+# CHECK-NEXT: ]
+# CHECK-NEXT: EpilogueScopes [
+# CHECK-NEXT: EpilogueScope {
+# CHECK-NEXT: StartOffset: 16
+# CHECK-NEXT: EpilogueStartIndex: 15
+# CHECK-NEXT: Opcodes [
+# CHECK-NEXT: 0xc80c ; ldp x19, x20, [sp, #96]
+# CHECK-NEXT: 0xc88a ; ldp x21, x22, [sp, #80]
+# CHECK-NEXT: 0xc908 ; ldp x23, x24, [sp, #64]
+# CHECK-NEXT: 0xc986 ; ldp x25, x26, [sp, #48]
+# CHECK-NEXT: 0xd802 ; ldp d8, d9, [sp, #16]
+# CHECK-NEXT: 0xda8d ; ldp d10, d11, [sp], #112
+# CHECK-NEXT: 0xe4 ; end
+# CHECK-NEXT: ]
+# CHECK-NEXT: }
+# CHECK-NEXT: EpilogueScope {
+# CHECK-NEXT: StartOffset: 32
+# CHECK-NEXT: EpilogueStartIndex: 28
+# CHECK-NEXT: Opcodes [
+# CHECK-NEXT: 0xc80c ; ldp x19, x20, [sp, #96]
+# CHECK-NEXT: 0xc88a ; ldp x21, x22, [sp, #80]
+# CHECK-NEXT: 0xc908 ; ldp x23, x24, [sp, #64]
+# CHECK-NEXT: 0xc986 ; ldp x25, x26, [sp, #48]
+# CHECK-NEXT: 0xca04 ; ldp x27, x28, [sp, #32]
+# CHECK-NEXT: 0xd802 ; ldp d8, d9, [sp, #16]
+# CHECK-NEXT: 0xda8d ; ldp d10, d11, [sp], #112
+# CHECK-NEXT: 0xe4 ; end
+# CHECK-NEXT: ]
+# CHECK-NEXT: }
+# CHECK-NEXT: ]
+# CHECK-NEXT: }
+...
+---
+name: test
+alignment: 2
+exposesReturnsTwice: false
+legalized: false
+regBankSelected: false
+selected: false
+failedISel: false
+tracksRegLiveness: true
+hasWinCFI: true
+registers:
+liveins:
+ - { reg: '$w0', virtual-reg: '' }
+frameInfo:
+ isFrameAddressTaken: false
+ isReturnAddressTaken: false
+ hasStackMap: false
+ hasPatchPoint: false
+ stackSize: 112
+ offsetAdjustment: 0
+ maxAlignment: 8
+ adjustsStack: false
+ hasCalls: false
+ stackProtector: ''
+ maxCallFrameSize: 0
+ hasOpaqueSPAdjustment: true
+ hasVAStart: false
+ hasMustTailInVarArgFunc: false
+ localFrameSize: 0
+ savePoint: ''
+ restorePoint: ''
+fixedStack:
+stack:
+ - { id: 0, name: '', type: spill-slot, offset: -8, size: 8, alignment: 8,
+ stack-id: 0, callee-saved-register: '$x19', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 1, name: '', type: spill-slot, offset: -16, size: 8, alignment: 8,
+ stack-id: 0, callee-saved-register: '$x20', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 2, name: '', type: spill-slot, offset: -24, size: 8, alignment: 8,
+ stack-id: 0, callee-saved-register: '$x21', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 3, name: '', type: spill-slot, offset: -32, size: 8, alignment: 8,
+ stack-id: 0, callee-saved-register: '$x22', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 4, name: '', type: spill-slot, offset: -40, size: 8, alignment: 8,
+ stack-id: 0, callee-saved-register: '$x23', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 5, name: '', type: spill-slot, offset: -48, size: 8, alignment: 8,
+ stack-id: 0, callee-saved-register: '$x24', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 6, name: '', type: spill-slot, offset: -56, size: 8, alignment: 8,
+ stack-id: 0, callee-saved-register: '$x25', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 7, name: '', type: spill-slot, offset: -64, size: 8, alignment: 8,
+ stack-id: 0, callee-saved-register: '$x26', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 8, name: '', type: spill-slot, offset: -72, size: 8, alignment: 8,
+ stack-id: 0, callee-saved-register: '$x27', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 9, name: '', type: spill-slot, offset: -80, size: 8, alignment: 8,
+ stack-id: 0, callee-saved-register: '$x28', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 10, name: '', type: spill-slot, offset: -88, size: 8, alignment: 8,
+ stack-id: 0, callee-saved-register: '$d8', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 11, name: '', type: spill-slot, offset: -96, size: 8, alignment: 8,
+ stack-id: 0, callee-saved-register: '$d9', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 12, name: '', type: spill-slot, offset: -104, size: 8, alignment: 8,
+ stack-id: 0, callee-saved-register: '$d10', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+ - { id: 13, name: '', type: spill-slot, offset: -112, size: 8, alignment: 8,
+ stack-id: 0, callee-saved-register: '$d11', callee-saved-restored: true,
+ debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
+constants:
+body: |
+ bb.0.entry:
+ successors: %bb.2(0x40000000), %bb.1(0x40000000)
+ liveins: $x0, $x1, $d0, $d1, $d10, $d11, $d8, $d9, $x27, $x28, $x25, $x26, $x23, $x24, $x21, $x22, $x19, $x20
+
+ early-clobber $sp = frame-setup STPDpre killed $d10, killed $d11, $sp, -14 :: (store 8 into %stack.12), (store 8 into %stack.13)
+ frame-setup SEH_SaveFRegP_X 10, 11, -112
+ frame-setup STPDi killed $d8, killed $d9, $sp, 2 :: (store 8 into %stack.10), (store 8 into %stack.11)
+ frame-setup SEH_SaveFRegP 8, 9, 16
+ frame-setup STPXi killed $x27, killed $x28, $sp, 4 :: (store 8 into %stack.8), (store 8 into %stack.9)
+ frame-setup SEH_SaveRegP 27, 28, 32
+ frame-setup STPXi killed $x25, killed $x26, $sp, 6 :: (store 8 into %stack.6), (store 8 into %stack.7)
+ frame-setup SEH_SaveRegP 25, 26, 48
+ frame-setup STPXi killed $x23, killed $x24, $sp, 8 :: (store 8 into %stack.4), (store 8 into %stack.5)
+ frame-setup SEH_SaveRegP 23, 24, 64
+ frame-setup STPXi killed $x21, killed $x22, $sp, 10 :: (store 8 into %stack.2), (store 8 into %stack.3)
+ frame-setup SEH_SaveRegP 21, 22, 80
+ frame-setup STPXi killed $x19, killed $x20, $sp, 12 :: (store 8 into %stack.0), (store 8 into %stack.1)
+ frame-setup SEH_SaveRegP 19, 20, 96
+ frame-setup SEH_PrologEnd
+ frame-setup CFI_INSTRUCTION def_cfa_offset 112
+ frame-setup CFI_INSTRUCTION offset $w19, -8
+ frame-setup CFI_INSTRUCTION offset $w20, -16
+ frame-setup CFI_INSTRUCTION offset $w21, -24
+ frame-setup CFI_INSTRUCTION offset $w22, -32
+ frame-setup CFI_INSTRUCTION offset $w23, -40
+ frame-setup CFI_INSTRUCTION offset $w24, -48
+ frame-setup CFI_INSTRUCTION offset $w25, -56
+ frame-setup CFI_INSTRUCTION offset $w26, -64
+ frame-setup CFI_INSTRUCTION offset $w27, -72
+ frame-setup CFI_INSTRUCTION offset $w28, -80
+ frame-setup CFI_INSTRUCTION offset $b8, -88
+ frame-setup CFI_INSTRUCTION offset $b9, -96
+ frame-setup CFI_INSTRUCTION offset $b10, -104
+ frame-setup CFI_INSTRUCTION offset $b11, -112
+ $x19 = ADDXrr $x0, killed $x1
+ $d8 = FADDDrr killed $d0, $d1
+ $d9 = FADDDrr $d8, $d1
+ $d10 = FADDDrr $d9, $d8
+ $d11 = FADDDrr killed $d9, $d10
+ $x20 = SUBSXrr $x19, killed $x0, implicit-def $nzcv
+ Bcc 1, %bb.2, implicit killed $nzcv
+ B %bb.1
+
+ bb.1:
+ liveins: $x19, $x20
+
+ $x21 = ADDXrr $x20, killed $x19
+ $x22 = ADDXrr $x21, killed $x20
+ $x23 = ADDXrr $x22, killed $x21
+ $x24 = ADDXrr $x23, killed $x22
+ $x25 = ADDXrr $x24, killed $x23
+ $x26 = ADDXrr $x25, killed $x24
+ $x27 = ADDXrr $x26, killed $x25
+ $x28 = ADDXrr $x27, killed $x26
+ $x0 = COPY $x28
+ frame-destroy SEH_EpilogStart
+ $x19, $x20 = frame-destroy LDPXi $sp, 12 :: (load 8 from %stack.0), (load 8 from %stack.1)
+ frame-destroy SEH_SaveRegP 19, 20, 96
+ $x21, $x22 = frame-destroy LDPXi $sp, 10 :: (load 8 from %stack.2), (load 8 from %stack.3)
+ frame-destroy SEH_SaveRegP 21, 22, 80
+ $x23, $x24 = frame-destroy LDPXi $sp, 8 :: (load 8 from %stack.4), (load 8 from %stack.5)
+ frame-destroy SEH_SaveRegP 23, 24, 64
+ $x25, $x26 = frame-destroy LDPXi $sp, 6 :: (load 8 from %stack.6), (load 8 from %stack.7)
+ frame-destroy SEH_SaveRegP 25, 26, 48
+ $x27, $x28 = frame-destroy LDPXi $sp, 4 :: (load 8 from %stack.8), (load 8 from %stack.9)
+ frame-destroy SEH_SaveRegP 27, 28, 32
+ $d8, $d9 = frame-destroy LDPDi $sp, 2 :: (load 8 from %stack.10), (load 8 from %stack.11)
+ frame-destroy SEH_SaveFRegP 8, 9, 16
+ early-clobber $sp, $d10, $d11 = frame-destroy LDPDpost $sp, 14 :: (load 8 from %stack.12), (load 8 from %stack.13)
+ frame-destroy SEH_SaveFRegP_X 10, 11, -112
+ frame-destroy SEH_EpilogEnd
+ RET_ReallyLR implicit $x0
+
+ bb.2:
+ liveins: $x28, $d11
+
+ $x0 = COPY $d11
+ $x0 = ADDXrr $x0, killed $x28
+ frame-destroy SEH_EpilogStart
+ $x19, $x20 = frame-destroy LDPXi $sp, 12 :: (load 8 from %stack.0), (load 8 from %stack.1)
+ frame-destroy SEH_SaveRegP 19, 20, 96
+ $x21, $x22 = frame-destroy LDPXi $sp, 10 :: (load 8 from %stack.2), (load 8 from %stack.3)
+ frame-destroy SEH_SaveRegP 21, 22, 80
+ $x23, $x24 = frame-destroy LDPXi $sp, 8 :: (load 8 from %stack.4), (load 8 from %stack.5)
+ frame-destroy SEH_SaveRegP 23, 24, 64
+ $x25, $x26 = frame-destroy LDPXi $sp, 6 :: (load 8 from %stack.6), (load 8 from %stack.7)
+ frame-destroy SEH_SaveRegP 25, 26, 48
+ $d8, $d9 = frame-destroy LDPDi $sp, 2 :: (load 8 from %stack.10), (load 8 from %stack.11)
+ frame-destroy SEH_SaveFRegP 8, 9, 16
+ early-clobber $sp, $d10, $d11 = frame-destroy LDPDpost $sp, 14 :: (load 8 from %stack.12), (load 8 from %stack.13)
+ frame-destroy SEH_SaveFRegP_X 10, 11, -112
+ frame-destroy SEH_EpilogEnd
+ RET_ReallyLR implicit $x0
+
+...
