[llvm-branch-commits] [llvm] a87fccb - [AArch64] Lower calls with rv_marker attribute .
Florian Hahn via llvm-branch-commits
llvm-branch-commits at lists.llvm.org
Fri Dec 11 11:50:07 PST 2020
Author: Florian Hahn
Date: 2020-12-11T19:45:44Z
New Revision: a87fccb3ff9c11986d3110d9f77fb0ccea0daf79
URL: https://github.com/llvm/llvm-project/commit/a87fccb3ff9c11986d3110d9f77fb0ccea0daf79
DIFF: https://github.com/llvm/llvm-project/commit/a87fccb3ff9c11986d3110d9f77fb0ccea0daf79.diff
LOG: [AArch64] Lower calls with rv_marker attribute .
This patch adds support for lowering function calls with the
rv_marker attribute. The goal is to expand such calls to the
following sequence of instructions:
BL @fn
mov x29, x29
This sequence of instructions triggers Objective-C runtime optimizations,
hence we want to ensure no instructions get moved in between them.
This patch achieves that by adding a new CALL_RVMARKER ISD node,
which gets turned into the BLR_RVMARKER pseudo, which eventually gets
expanded into the sequence mentioned above. The sequence is then marked
as instruction bundle, to avoid anything being moved in between.
@ahatanak is working on using this attribute in the front- & middle-end.
Together with the front- & middle-end changes, this should address
PR31925 for AArch64.
Reviewed By: t.p.northover
Differential Revision: https://reviews.llvm.org/D92569
Added:
llvm/test/CodeGen/AArch64/call-rv-marker.ll
llvm/test/CodeGen/AArch64/expand-blr-rvmarker-pseudo.mir
Modified:
llvm/lib/Target/AArch64/AArch64ExpandPseudoInsts.cpp
llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
llvm/lib/Target/AArch64/AArch64ISelLowering.h
llvm/lib/Target/AArch64/AArch64InstrInfo.td
Removed:
################################################################################
diff --git a/llvm/lib/Target/AArch64/AArch64ExpandPseudoInsts.cpp b/llvm/lib/Target/AArch64/AArch64ExpandPseudoInsts.cpp
index 9e65ad2e18f9..ce34a9283e17 100644
--- a/llvm/lib/Target/AArch64/AArch64ExpandPseudoInsts.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ExpandPseudoInsts.cpp
@@ -83,6 +83,8 @@ class AArch64ExpandPseudo : public MachineFunctionPass {
bool expandSVESpillFill(MachineBasicBlock &MBB,
MachineBasicBlock::iterator MBBI, unsigned Opc,
unsigned N);
+ bool expandCALL_RVMARKER(MachineBasicBlock &MBB,
+ MachineBasicBlock::iterator MBBI);
};
} // end anonymous namespace
@@ -627,6 +629,46 @@ bool AArch64ExpandPseudo::expandSVESpillFill(MachineBasicBlock &MBB,
return true;
}
+bool AArch64ExpandPseudo::expandCALL_RVMARKER(
+ MachineBasicBlock &MBB, MachineBasicBlock::iterator MBBI) {
+ // Expand CALL_RVMARKER pseudo to a branch, followed by the special `mov x29,
+ // x29` marker. Mark the sequence as bundle, to avoid passes moving other code
+ // in between.
+ MachineInstr &MI = *MBBI;
+
+ MachineInstr *OriginalCall;
+ MachineOperand &CallTarget = MI.getOperand(0);
+ assert((CallTarget.isGlobal() || CallTarget.isReg()) &&
+ "invalid operand for regular call");
+ unsigned Opc = CallTarget.isGlobal() ? AArch64::BL : AArch64::BLR;
+ OriginalCall = BuildMI(MBB, MBBI, MI.getDebugLoc(), TII->get(Opc)).getInstr();
+ OriginalCall->addOperand(CallTarget);
+
+ unsigned RegMaskStartIdx = 1;
+ // Skip register arguments. Those are added during ISel, but are not
+ // needed for the concrete branch.
+ while (!MI.getOperand(RegMaskStartIdx).isRegMask()) {
+ assert(MI.getOperand(RegMaskStartIdx).isReg() &&
+ "should only skip register operands");
+ RegMaskStartIdx++;
+ }
+ for (; RegMaskStartIdx < MI.getNumOperands(); ++RegMaskStartIdx)
+ OriginalCall->addOperand(MI.getOperand(RegMaskStartIdx));
+
+ auto *Marker = BuildMI(MBB, MBBI, MI.getDebugLoc(), TII->get(AArch64::ORRXrs))
+ .addReg(AArch64::FP)
+ .addReg(AArch64::XZR)
+ .addReg(AArch64::FP)
+ .addImm(0)
+ .getInstr();
+ if (MI.shouldUpdateCallSiteInfo())
+ MBB.getParent()->moveCallSiteInfo(&MI, Marker);
+ MI.eraseFromParent();
+ finalizeBundle(MBB, OriginalCall->getIterator(),
+ std::next(Marker->getIterator()));
+ return true;
+}
+
/// If MBBI references a pseudo instruction that should be expanded here,
/// do the expansion and return true. Otherwise return false.
bool AArch64ExpandPseudo::expandMI(MachineBasicBlock &MBB,
@@ -1014,6 +1056,8 @@ bool AArch64ExpandPseudo::expandMI(MachineBasicBlock &MBB,
return expandSVESpillFill(MBB, MBBI, AArch64::LDR_ZXI, 3);
case AArch64::LDR_ZZXI:
return expandSVESpillFill(MBB, MBBI, AArch64::LDR_ZXI, 2);
+ case AArch64::BLR_RVMARKER:
+ return expandCALL_RVMARKER(MBB, MBBI);
}
return false;
}
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index 01301abf10e3..4e7dba09d5b0 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -1934,6 +1934,7 @@ const char *AArch64TargetLowering::getTargetNodeName(unsigned Opcode) const {
MAKE_CASE(AArch64ISD::INDEX_VECTOR)
MAKE_CASE(AArch64ISD::UABD)
MAKE_CASE(AArch64ISD::SABD)
+ MAKE_CASE(AArch64ISD::CALL_RVMARKER)
}
#undef MAKE_CASE
return nullptr;
@@ -5539,8 +5540,17 @@ AArch64TargetLowering::LowerCall(CallLoweringInfo &CLI,
return Ret;
}
+ unsigned CallOpc = AArch64ISD::CALL;
+ // Calls marked with "rv_marker" are special. They should be expanded to the
+ // call, directly followed by a special marker sequence. Use the CALL_RVMARKER
+ // to do that.
+ if (CLI.CB && CLI.CB->hasRetAttr("rv_marker")) {
+ assert(!IsTailCall && "tail calls cannot be marked with rv_marker");
+ CallOpc = AArch64ISD::CALL_RVMARKER;
+ }
+
// Returns a chain and a flag for retval copy to use.
- Chain = DAG.getNode(AArch64ISD::CALL, DL, NodeTys, Ops);
+ Chain = DAG.getNode(CallOpc, DL, NodeTys, Ops);
DAG.addNoMergeSiteInfo(Chain.getNode(), CLI.NoMerge);
InFlag = Chain.getValue(1);
DAG.addCallSiteInfo(Chain.getNode(), std::move(CSInfo));
diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.h b/llvm/lib/Target/AArch64/AArch64ISelLowering.h
index 334517ad992b..f7baa1910c09 100644
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.h
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.h
@@ -417,7 +417,11 @@ enum NodeType : unsigned {
LDP,
STP,
- STNP
+ STNP,
+
+ // Pseudo for a OBJC call that gets emitted together with a special `mov
+ // x29, x29` marker instruction.
+ CALL_RVMARKER
};
} // end namespace AArch64ISD
diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.td b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
index 564f5fdce6f1..28ab67599c48 100644
--- a/llvm/lib/Target/AArch64/AArch64InstrInfo.td
+++ b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
@@ -399,6 +399,12 @@ def AArch64call : SDNode<"AArch64ISD::CALL",
SDTypeProfile<0, -1, [SDTCisPtrTy<0>]>,
[SDNPHasChain, SDNPOptInGlue, SDNPOutGlue,
SDNPVariadic]>;
+
+def AArch64call_rvmarker: SDNode<"AArch64ISD::CALL_RVMARKER",
+ SDTypeProfile<0, -1, [SDTCisPtrTy<0>]>,
+ [SDNPHasChain, SDNPOptInGlue, SDNPOutGlue,
+ SDNPVariadic]>;
+
def AArch64brcond : SDNode<"AArch64ISD::BRCOND", SDT_AArch64Brcond,
[SDNPHasChain]>;
def AArch64cbz : SDNode<"AArch64ISD::CBZ", SDT_AArch64cbz,
@@ -2089,6 +2095,8 @@ let isCall = 1, Defs = [LR], Uses = [SP] in {
def BLRNoIP : Pseudo<(outs), (ins GPR64noip:$Rn), []>,
Sched<[WriteBrReg]>,
PseudoInstExpansion<(BLR GPR64:$Rn)>;
+ def BLR_RVMARKER : Pseudo<(outs), (ins variable_ops), []>,
+ Sched<[WriteBrReg]>;
} // isCall
def : Pat<(AArch64call GPR64:$Rn),
@@ -2098,6 +2106,10 @@ def : Pat<(AArch64call GPR64noip:$Rn),
(BLRNoIP GPR64noip:$Rn)>,
Requires<[SLSBLRMitigation]>;
+def : Pat<(AArch64call_rvmarker GPR64:$Rn),
+ (BLR_RVMARKER GPR64:$Rn)>,
+ Requires<[NoSLSBLRMitigation]>;
+
let isBranch = 1, isTerminator = 1, isBarrier = 1, isIndirectBranch = 1 in {
def BR : BranchReg<0b0000, "br", [(brind GPR64:$Rn)]>;
} // isBranch, isTerminator, isBarrier, isIndirectBranch
diff --git a/llvm/test/CodeGen/AArch64/call-rv-marker.ll b/llvm/test/CodeGen/AArch64/call-rv-marker.ll
new file mode 100644
index 000000000000..d3820b825c3f
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/call-rv-marker.ll
@@ -0,0 +1,149 @@
+; RUN: llc -o - %s | FileCheck --check-prefix=SELDAG --check-prefix=CHECK %s
+; RUN: llc -global-isel -o - %s | FileCheck --check-prefix=GISEL --check-prefix=CHECK %s
+
+; TODO: support marker generation with GlobalISel
+target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
+target triple = "arm64-apple-iphoneos"
+
+declare i8* @foo0(i32)
+declare i8* @foo1()
+
+declare void @llvm.objc.release(i8*)
+declare void @objc_object(i8*)
+
+declare void @foo2(i8*)
+
+declare void @llvm.lifetime.start.p0i8(i64 immarg, i8* nocapture)
+
+declare %struct.S* @_ZN1SD1Ev(%struct.S* nonnull dereferenceable(1))
+
+declare void @llvm.lifetime.end.p0i8(i64 immarg, i8* nocapture)
+
+
+%struct.S = type { i8 }
+
+ at g = global i8* null, align 8
+ at fptr = global i8* ()* null, align 8
+
+define i8* @rv_marker_1() {
+; CHECK-LABEL: rv_marker_1:
+; CHECK: .cfi_offset w30, -16
+; CHECK-NEXT: bl foo1
+; SELDAG-NEXT: mov x29, x29
+; GISEL-NOT: mov x29, x29
+;
+entry:
+ %call = call "rv_marker" i8* @foo1()
+ ret i8* %call
+}
+
+define void @rv_marker_2_select(i32 %c) {
+; CHECK-LABEL: rv_marker_2_select:
+; SELDAG: cinc w0, w8, eq
+; GISEL: csinc w0, w8, wzr, eq
+; CHECK-NEXT: bl foo0
+; SELDAG-NEXT: mov x29, x29
+; CHECK-NEXT: ldr x30, [sp], #16
+; CHECK-NEXT: b foo2
+;
+entry:
+ %tobool.not = icmp eq i32 %c, 0
+ %.sink = select i1 %tobool.not, i32 2, i32 1
+ %call1 = call "rv_marker" i8* @foo0(i32 %.sink)
+ tail call void @foo2(i8* %call1)
+ ret void
+}
+
+define void @rv_marker_3() personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
+; CHECK-LABEL: rv_marker_3
+; CHECK: .cfi_offset w30, -32
+; CHECK-NEXT: bl foo1
+; SELDAG-NEXT: mov x29, x29
+;
+entry:
+ %call = call "rv_marker" i8* @foo1()
+ invoke void @objc_object(i8* %call) #5
+ to label %invoke.cont unwind label %lpad
+
+invoke.cont: ; preds = %entry
+ tail call void @llvm.objc.release(i8* %call)
+ ret void
+
+lpad: ; preds = %entry
+ %0 = landingpad { i8*, i32 }
+ cleanup
+ tail call void @llvm.objc.release(i8* %call)
+ resume { i8*, i32 } %0
+}
+
+define void @rv_marker_4() personality i8* bitcast (i32 (...)* @__gxx_personality_v0 to i8*) {
+; CHECK-LABEL: rv_marker_4
+; CHECK: .Ltmp3:
+; CHECK-NEXT: bl foo1
+; SELDAG-NEXT: mov x29, x29
+; CHECK-NEXT: .Ltmp4:
+;
+entry:
+ %s = alloca %struct.S, align 1
+ %0 = getelementptr inbounds %struct.S, %struct.S* %s, i64 0, i32 0
+ call void @llvm.lifetime.start.p0i8(i64 1, i8* nonnull %0) #2
+ %call = invoke "rv_marker" i8* @foo1()
+ to label %invoke.cont unwind label %lpad
+
+invoke.cont: ; preds = %entry
+ invoke void @objc_object(i8* %call) #5
+ to label %invoke.cont2 unwind label %lpad1
+
+invoke.cont2: ; preds = %invoke.cont
+ tail call void @llvm.objc.release(i8* %call)
+ %call3 = call %struct.S* @_ZN1SD1Ev(%struct.S* nonnull dereferenceable(1) %s)
+ call void @llvm.lifetime.end.p0i8(i64 1, i8* nonnull %0)
+ ret void
+
+lpad: ; preds = %entry
+ %1 = landingpad { i8*, i32 }
+ cleanup
+ br label %ehcleanup
+
+lpad1: ; preds = %invoke.cont
+ %2 = landingpad { i8*, i32 }
+ cleanup
+ tail call void @llvm.objc.release(i8* %call)
+ br label %ehcleanup
+
+ehcleanup: ; preds = %lpad1, %lpad
+ %.pn = phi { i8*, i32 } [ %2, %lpad1 ], [ %1, %lpad ]
+ %call4 = call %struct.S* @_ZN1SD1Ev(%struct.S* nonnull dereferenceable(1) %s)
+ call void @llvm.lifetime.end.p0i8(i64 1, i8* nonnull %0)
+ resume { i8*, i32 } %.pn
+}
+
+define i8* @rv_marker_5_indirect_call() {
+; CHECK-LABEL: rv_marker_5_indirect_call
+; CHECK: ldr [[ADDR:x[0-9]+]], [
+; CHECK-NEXT: blr [[ADDR]]
+; SLEDAG-NEXT: mov x29, x29
+; GISEL-NOT: mov x29, x29
+;
+entry:
+ %0 = load i8* ()*, i8* ()** @fptr, align 8
+ %call = call "rv_marker" i8* %0()
+ tail call void @foo2(i8* %call)
+ ret i8* %call
+}
+
+declare void @foo(i64, i64, i64)
+
+define void @rv_marker_multiarg(i64 %a, i64 %b, i64 %c) {
+; CHECK-LABEL: rv_marker_multiarg
+; CHECK: mov [[TMP:x[0-9]+]], x0
+; CHECK-NEXT: mov x0, x2
+; CHECK-NEXT: mov x2, [[TMP]]
+; CHECK-NEXT: bl foo
+; SELDAG-NEXT: mov x29, x29
+; GISEL-NOT: mov x29, x29
+ call "rv_marker" void @foo(i64 %c, i64 %b, i64 %a)
+ ret void
+}
+
+declare i32 @__gxx_personality_v0(...)
diff --git a/llvm/test/CodeGen/AArch64/expand-blr-rvmarker-pseudo.mir b/llvm/test/CodeGen/AArch64/expand-blr-rvmarker-pseudo.mir
new file mode 100644
index 000000000000..84bc44bd17d4
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/expand-blr-rvmarker-pseudo.mir
@@ -0,0 +1,21 @@
+# RUN: llc -run-pass=aarch64-expand-pseudo -mtriple=arm64-apple-ios -o - -emit-call-site-info %s | FileCheck %s
+
+# CHECK-LABEL: test_1_callsite_info
+# CHECK: bb.0.entry:
+# CHECK-NEXT: BUNDLE implicit-def $lr, implicit-def $w30, implicit-def $sp, implicit-def $wsp, implicit-def dead $x0, implicit $x0, implicit $sp, implicit $fp, implicit $xzr {
+# CHECK-NEXT: BLR $x0, csr_aarch64_aapcs, implicit-def $lr, implicit $sp, implicit-def dead $lr, implicit $sp, implicit-def $sp, implicit-def dead $x0
+# CHECK-NEXT: ORRXrs $fp, $xzr, $fp, 0
+# CHECK-NEXT: }
+# CHECK-NEXT: RET undef $lr, implicit killed $w0
+---
+name: test_1_callsite_info
+callSites:
+ - {bb: 0, offset: 0, fwdArgRegs:
+ - { arg: 0, reg: '$x0' } }
+body: |
+ bb.0.entry:
+ liveins: $lr, $x0
+
+ BLR_RVMARKER $x0, csr_aarch64_aapcs, implicit-def dead $lr, implicit $sp, implicit-def $sp, implicit-def dead $x0
+ RET_ReallyLR implicit killed $w0
+...
More information about the llvm-branch-commits
mailing list