[AArch64] Add support for Transactional Memory Extension (TME)

momchil-velikov · momchil-velikov · commit a36d31478c18 · 2019-07-31T12:52:17.000Z
Re-commit r366322 after some fixes TME is a future architecture technology, documented in https://developer.arm.com/architectures/cpu-architecture/a-profile/exploration-tools https://developer.arm.com/docs/ddi0601/a More about the future architectures: https://community.arm.com/developer/ip-products/processors/b/processors-ip-blog/posts/new-technologies-for-the-arm-a-profile-architecture This patch adds support for the TME instructions TSTART, TTEST, TCOMMIT, and TCANCEL and the target feature/arch extension "tme". It also implements TME builtin functions, defined in ACLE Q2 2019 (https://developer.arm.com/docs/101028/latest) Differential Revision: https://reviews.llvm.org/D64416 Patch by Javed Absar and Momchil Velikov llvm-svn: 367428
diff --git a/clang/include/clang/Basic/BuiltinsAArch64.def b/clang/include/clang/Basic/BuiltinsAArch64.def
@@ -91,6 +91,12 @@ LANGBUILTIN(__sevl,  "v", "",   ALL_MS_LANGUAGES)
 // Misc
 BUILTIN(__builtin_sponentry, "v*", "c")
 
+// Transactional Memory Extension
+BUILTIN(__builtin_arm_tstart, "WUi", "nj")
+BUILTIN(__builtin_arm_tcommit, "v", "n")
+BUILTIN(__builtin_arm_tcancel, "vWUIi", "n")
+BUILTIN(__builtin_arm_ttest, "WUi", "nc")
+
 TARGET_HEADER_BUILTIN(_BitScanForward, "UcUNi*UNi", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
 TARGET_HEADER_BUILTIN(_BitScanReverse, "UcUNi*UNi", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
 TARGET_HEADER_BUILTIN(_BitScanForward64, "UcUNi*ULLi", "nh", "intrin.h", ALL_MS_LANGUAGES, "")
diff --git a/clang/lib/Basic/Targets/AArch64.cpp b/clang/lib/Basic/Targets/AArch64.cpp
@@ -216,6 +216,9 @@ void AArch64TargetInfo::getTargetDefines(const LangOptions &Opts,
   if (HasMTE)
     Builder.defineMacro("__ARM_FEATURE_MEMORY_TAGGING", "1");
 
+  if (HasTME)
+    Builder.defineMacro("__ARM_FEATURE_TME", "1");
+
   if ((FPU & NeonMode) && HasFP16FML)
     Builder.defineMacro("__ARM_FEATURE_FP16FML", "1");
 
@@ -267,6 +270,7 @@ bool AArch64TargetInfo::handleTargetFeatures(std::vector<std::string> &Features,
   HasDotProd = false;
   HasFP16FML = false;
   HasMTE = false;
+  HasTME = false;
   ArchKind = llvm::AArch64::ArchKind::ARMV8A;
 
   for (const auto &Feature : Features) {
@@ -298,6 +302,8 @@ bool AArch64TargetInfo::handleTargetFeatures(std::vector<std::string> &Features,
       HasFP16FML = true;
     if (Feature == "+mte")
       HasMTE = true;
+    if (Feature == "+tme")
+      HasTME = true;
   }
 
   setDataLayout();
diff --git a/clang/lib/Basic/Targets/AArch64.h b/clang/lib/Basic/Targets/AArch64.h
@@ -35,6 +35,7 @@ class LLVM_LIBRARY_VISIBILITY AArch64TargetInfo : public TargetInfo {
   bool HasDotProd;
   bool HasFP16FML;
   bool HasMTE;
+  bool HasTME;
 
   llvm::AArch64::ArchKind ArchKind;
 
diff --git a/clang/lib/Headers/arm_acle.h b/clang/lib/Headers/arm_acle.h
@@ -613,7 +613,7 @@ __jcvt(double __a) {
 #define __arm_wsr64(sysreg, v) __builtin_arm_wsr64(sysreg, v)
 #define __arm_wsrp(sysreg, v) __builtin_arm_wsrp(sysreg, v)
 
-// Memory Tagging Extensions (MTE) Intrinsics
+/* Memory Tagging Extensions (MTE) Intrinsics */
 #if __ARM_FEATURE_MEMORY_TAGGING
 #define __arm_mte_create_random_tag(__ptr, __mask)  __builtin_arm_irg(__ptr, __mask)
 #define __arm_mte_increment_tag(__ptr, __tag_offset)  __builtin_arm_addg(__ptr, __tag_offset)
@@ -623,6 +623,28 @@ __jcvt(double __a) {
 #define __arm_mte_ptrdiff(__ptra, __ptrb) __builtin_arm_subp(__ptra, __ptrb)
 #endif
 
+/* Transactional Memory Extension (TME) Intrinsics */
+#if __ARM_FEATURE_TME
+
+#define _TMFAILURE_REASON  0x00007fffu
+#define _TMFAILURE_RTRY    0x00008000u
+#define _TMFAILURE_CNCL    0x00010000u
+#define _TMFAILURE_MEM     0x00020000u
+#define _TMFAILURE_IMP     0x00040000u
+#define _TMFAILURE_ERR     0x00080000u
+#define _TMFAILURE_SIZE    0x00100000u
+#define _TMFAILURE_NEST    0x00200000u
+#define _TMFAILURE_DBG     0x00400000u
+#define _TMFAILURE_INT     0x00800000u
+#define _TMFAILURE_TRIVIAL 0x01000000u
+
+#define __tstart()        __builtin_arm_tstart()
+#define __tcommit()       __builtin_arm_tcommit()
+#define __tcancel(__arg)  __builtin_arm_tcancel(__arg)
+#define __ttest()         __builtin_arm_ttest()
+
+#endif /* __ARM_FEATURE_TME */
+
 #if defined(__cplusplus)
 }
 #endif
diff --git a/clang/lib/Sema/SemaChecking.cpp b/clang/lib/Sema/SemaChecking.cpp
@@ -1932,6 +1932,7 @@ bool Sema::CheckAArch64BuiltinFunctionCall(unsigned BuiltinID,
   case AArch64::BI__builtin_arm_dmb:
   case AArch64::BI__builtin_arm_dsb:
   case AArch64::BI__builtin_arm_isb: l = 0; u = 15; break;
+  case AArch64::BI__builtin_arm_tcancel: l = 0; u = 65535; break;
   }
 
   return SemaBuiltinConstantArgRange(TheCall, i, l, u + l);
diff --git a/clang/test/CodeGen/aarch64-tme.cpp b/clang/test/CodeGen/aarch64-tme.cpp
@@ -0,0 +1,42 @@
+// RUN: %clang_cc1             -triple aarch64-eabi -target-feature +tme -S -emit-llvm %s -o - | FileCheck %s
+// RUN: %clang_cc1 -DUSE_ACLE  -triple aarch64-eabi -target-feature +tme -S -emit-llvm %s -o - | FileCheck %s
+
+#define A -1
+constexpr int f() { return 65536; }
+
+#ifdef USE_ACLE
+#include "arm_acle.h"
+void test_tme_funcs() {
+  __tstart();
+  (void)__ttest();
+  __tcommit();
+  __tcancel(0x789a);
+	__tcancel(f() + A);
+}
+#else
+void test_tme_funcs() {
+  __builtin_arm_tstart();
+  (void)__builtin_arm_ttest();
+  __builtin_arm_tcommit();
+  __builtin_arm_tcancel(0x789a);
+	__builtin_arm_tcancel(f() + A);
+}
+#endif
+// CHECK: call i64 @llvm.aarch64.tstart()
+// CHECK: call i64 @llvm.aarch64.ttest()
+// CHECK: call void @llvm.aarch64.tcommit()
+// CHECK: call void @llvm.aarch64.tcancel(i64 30874)
+// CHECK: call void @llvm.aarch64.tcancel(i64 65535)
+
+// CHECK: declare i64 @llvm.aarch64.tstart() #1
+// CHECK: declare i64 @llvm.aarch64.ttest() #1
+// CHECK: declare void @llvm.aarch64.tcommit() #1
+// CHECK: declare void @llvm.aarch64.tcancel(i64 immarg) #1
+
+#ifdef __ARM_FEATURE_TME
+extern "C" void arm_feature_tme_defined() {}
+#endif
+// CHECK: define void @arm_feature_tme_defined()
+
+// CHECK: attributes #1 = { nounwind }
+
diff --git a/clang/test/Sema/aarch64-tme-errors.c b/clang/test/Sema/aarch64-tme-errors.c
@@ -0,0 +1,8 @@
+// RUN: %clang_cc1 -triple aarch64-eabi -verify %s
+
+#include "arm_acle.h"
+
+void test_no_tme_funcs() {
+  __tstart();         // expected-warning{{implicit declaration of function '__tstart'}}
+  __builtin_tstart(); // expected-error{{use of unknown builtin '__builtin_tstart'}}
+}
diff --git a/clang/test/Sema/aarch64-tme-tcancel-errors.c b/clang/test/Sema/aarch64-tme-tcancel-errors.c
@@ -0,0 +1,9 @@
+// RUN: %clang_cc1 -triple aarch64-eabi -target-feature +tme -verify %s
+void t_cancel_const(unsigned short u) {
+  __builtin_arm_tcancel(u); // expected-error{{argument to '__builtin_arm_tcancel' must be a constant integer}}
+}
+
+// RUN: %clang_cc1 -triple aarch64-eabi -target-feature +tme -verify %s
+void t_cancel_range() {
+  __builtin_arm_tcancel(0x12345u); // expected-error{{argument value 74565 is outside the valid range [0, 65535]}}
+}
diff --git a/llvm/include/llvm/IR/IntrinsicsAArch64.td b/llvm/include/llvm/IR/IntrinsicsAArch64.td
@@ -733,3 +733,18 @@ def int_aarch64_settag_zero  : Intrinsic<[], [llvm_ptr_ty, llvm_i64_ty],
 def int_aarch64_stgp  : Intrinsic<[], [llvm_ptr_ty, llvm_i64_ty, llvm_i64_ty],
     [IntrWriteMem, IntrArgMemOnly, NoCapture<0>, WriteOnly<0>]>;
 }
+
+// Transactional Memory Extension (TME) Intrinsics
+let TargetPrefix = "aarch64" in {
+def int_aarch64_tstart  : GCCBuiltin<"__builtin_arm_tstart">,
+                         Intrinsic<[llvm_i64_ty]>;
+
+def int_aarch64_tcommit : GCCBuiltin<"__builtin_arm_tcommit">, Intrinsic<[]>;
+
+def int_aarch64_tcancel : GCCBuiltin<"__builtin_arm_tcancel">,
+                          Intrinsic<[], [llvm_i64_ty], [ImmArg<0>]>;
+
+def int_aarch64_ttest   : GCCBuiltin<"__builtin_arm_ttest">,
+                          Intrinsic<[llvm_i64_ty], [],
+                                    [IntrNoMem, IntrHasSideEffects]>;
+}
diff --git a/llvm/include/llvm/Support/AArch64TargetParser.def b/llvm/include/llvm/Support/AArch64TargetParser.def
@@ -79,6 +79,7 @@ AARCH64_ARCH_EXT_NAME("memtag",       AArch64::AEK_MTE,         "+mte",   "-mte"
 AARCH64_ARCH_EXT_NAME("ssbs",         AArch64::AEK_SSBS,        "+ssbs",  "-ssbs")
 AARCH64_ARCH_EXT_NAME("sb",           AArch64::AEK_SB,          "+sb",    "-sb")
 AARCH64_ARCH_EXT_NAME("predres",      AArch64::AEK_PREDRES,     "+predres", "-predres")
+AARCH64_ARCH_EXT_NAME("tme",          AArch64::AEK_TME,         "+tme",   "-tme")
 #undef AARCH64_ARCH_EXT_NAME
 
 #ifndef AARCH64_CPU_NAME
diff --git a/llvm/include/llvm/Support/AArch64TargetParser.h b/llvm/include/llvm/Support/AArch64TargetParser.h
@@ -54,6 +54,7 @@ enum ArchExtKind : unsigned {
   AEK_SVE2SM4 =     1 << 25,
   AEK_SVE2SHA3 =    1 << 26,
   AEK_SVE2BITPERM = 1 << 27,
+  AEK_TME =         1 << 28,
 };
 
 enum class ArchKind {
diff --git a/llvm/lib/Target/AArch64/AArch64.td b/llvm/lib/Target/AArch64/AArch64.td
@@ -352,6 +352,9 @@ def FeatureETE : SubtargetFeature<"ete", "HasETE",
     "true", "Enable Embedded Trace Extension",
     [FeatureTRBE]>;
 
+def FeatureTME : SubtargetFeature<"tme", "HasTME",
+    "true", "Enable Transactional Memory Extension" >;
+
 //===----------------------------------------------------------------------===//
 // Architectures.
 //
diff --git a/llvm/lib/Target/AArch64/AArch64InstrFormats.td b/llvm/lib/Target/AArch64/AArch64InstrFormats.td
@@ -678,12 +678,15 @@ def logical_imm64_not : Operand<i64> {
   let ParserMatchClass = LogicalImm64NotOperand;
 }
 
-// imm0_65535 predicate - True if the immediate is in the range [0,65535].
-def imm0_65535 : Operand<i32>, ImmLeaf<i32, [{
+// iXX_imm0_65535 predicates - True if the immediate is in the range [0,65535].
+let ParserMatchClass = AsmImmRange<0, 65535>, PrintMethod = "printImmHex" in {
+def i32_imm0_65535 : Operand<i32>, ImmLeaf<i32, [{
   return ((uint32_t)Imm) < 65536;
-}]> {
-  let ParserMatchClass = AsmImmRange<0, 65535>;
-  let PrintMethod = "printImmHex";
+}]>;
+
+def i64_imm0_65535 : Operand<i64>, ImmLeaf<i64, [{
+  return ((uint64_t)Imm) < 65536;
+}]>;
 }
 
 // imm0_255 predicate - True if the immediate is in the range [0,255].
@@ -1046,6 +1049,45 @@ class RtSystemI<bit L, dag oops, dag iops, string asm, string operands>
   let Inst{4-0} = Rt;
 }
 
+// System instructions for transactional memory extension
+class TMBaseSystemI<bit L, bits<4> CRm, bits<3> op2, dag oops, dag iops,
+                    string asm, string operands, list<dag> pattern>
+    : BaseSystemI<L, oops, iops, asm, operands, pattern>,
+      Sched<[WriteSys]> {
+  let Inst{20-12} = 0b000110011;
+  let Inst{11-8} = CRm;
+  let Inst{7-5} = op2;
+  let DecoderMethod = "";
+
+  let mayLoad = 1;
+  let mayStore = 1;
+}
+
+// System instructions for transactional memory - single input operand
+class TMSystemI<bits<4> CRm, string asm, list<dag> pattern>
+    : TMBaseSystemI<0b1, CRm, 0b011,
+                    (outs GPR64:$Rt), (ins), asm, "\t$Rt", pattern> {
+  bits<5> Rt;
+  let Inst{4-0} = Rt;
+}
+
+// System instructions for transactional memory - no operand
+class TMSystemINoOperand<bits<4> CRm, string asm, list<dag> pattern>
+    : TMBaseSystemI<0b0, CRm, 0b011, (outs), (ins), asm, "", pattern> {
+  let Inst{4-0} = 0b11111;
+}
+
+// System instructions for exit from transactions
+class TMSystemException<bits<3> op1, string asm, list<dag> pattern>
+    : I<(outs), (ins i64_imm0_65535:$imm), asm, "\t$imm", "", pattern>,
+      Sched<[WriteSys]> {
+  bits<16> imm;
+  let Inst{31-24} = 0b11010100;
+  let Inst{23-21} = op1;
+  let Inst{20-5}  = imm;
+  let Inst{4-0}   = 0b00000;
+}
+
 // Hint instructions that take both a CRm and a 3-bit immediate.
 // NOTE: ideally, this would have mayStore = 0, mayLoad = 0, but we cannot
 // model patterns with sufficiently fine granularity
@@ -4050,7 +4092,7 @@ multiclass MemTagStore<bits<2> opc1, string insn> {
 
 let mayLoad = 0, mayStore = 0, hasSideEffects = 1 in
 class ExceptionGeneration<bits<3> op1, bits<2> ll, string asm>
-    : I<(outs), (ins imm0_65535:$imm), asm, "\t$imm", "", []>,
+    : I<(outs), (ins i32_imm0_65535:$imm), asm, "\t$imm", "", []>,
       Sched<[WriteSys]> {
   bits<16> imm;
   let Inst{31-24} = 0b11010100;
diff --git a/llvm/lib/Target/AArch64/AArch64InstrInfo.td b/llvm/lib/Target/AArch64/AArch64InstrInfo.td
@@ -133,6 +133,8 @@ def HasBTI           : Predicate<"Subtarget->hasBTI()">,
                        AssemblerPredicate<"FeatureBranchTargetId", "bti">;
 def HasMTE           : Predicate<"Subtarget->hasMTE()">,
                        AssemblerPredicate<"FeatureMTE", "mte">;
+def HasTME           : Predicate<"Subtarget->hasTME()">,
+                       AssemblerPredicate<"FeatureTME", "tme">;
 def HasETE           : Predicate<"Subtarget->hasETE()">,
                        AssemblerPredicate<"FeatureETE", "ete">;
 def HasTRBE          : Predicate<"Subtarget->hasTRBE()">,
@@ -808,6 +810,23 @@ def : InstAlias<"sys $op1, $Cn, $Cm, $op2",
                 (SYSxt imm0_7:$op1, sys_cr_op:$Cn,
                  sys_cr_op:$Cm, imm0_7:$op2, XZR)>;
 
+
+let Predicates = [HasTME] in {
+
+def TSTART : TMSystemI<0b0000, "tstart",
+                      [(set GPR64:$Rt, (int_aarch64_tstart))]>;
+
+def TCOMMIT : TMSystemINoOperand<0b0000, "tcommit", [(int_aarch64_tcommit)]>;
+
+def TCANCEL : TMSystemException<0b011, "tcancel",
+                                [(int_aarch64_tcancel i64_imm0_65535:$imm)]>;
+
+def TTEST : TMSystemI<0b0001, "ttest", [(set GPR64:$Rt, (int_aarch64_ttest))]> {
+  let mayLoad = 0;
+  let mayStore = 0;
+}
+} // HasTME
+
 //===----------------------------------------------------------------------===//
 // Move immediate instructions.
 //===----------------------------------------------------------------------===//
@@ -819,12 +838,12 @@ let PostEncoderMethod = "fixMOVZ" in
 defm MOVZ : MoveImmediate<0b10, "movz">;
 
 // First group of aliases covers an implicit "lsl #0".
-def : InstAlias<"movk $dst, $imm", (MOVKWi GPR32:$dst, imm0_65535:$imm, 0), 0>;
-def : InstAlias<"movk $dst, $imm", (MOVKXi GPR64:$dst, imm0_65535:$imm, 0), 0>;
-def : InstAlias<"movn $dst, $imm", (MOVNWi GPR32:$dst, imm0_65535:$imm, 0)>;
-def : InstAlias<"movn $dst, $imm", (MOVNXi GPR64:$dst, imm0_65535:$imm, 0)>;
-def : InstAlias<"movz $dst, $imm", (MOVZWi GPR32:$dst, imm0_65535:$imm, 0)>;
-def : InstAlias<"movz $dst, $imm", (MOVZXi GPR64:$dst, imm0_65535:$imm, 0)>;
+def : InstAlias<"movk $dst, $imm", (MOVKWi GPR32:$dst, i32_imm0_65535:$imm, 0), 0>;
+def : InstAlias<"movk $dst, $imm", (MOVKXi GPR64:$dst, i32_imm0_65535:$imm, 0), 0>;
+def : InstAlias<"movn $dst, $imm", (MOVNWi GPR32:$dst, i32_imm0_65535:$imm, 0)>;
+def : InstAlias<"movn $dst, $imm", (MOVNXi GPR64:$dst, i32_imm0_65535:$imm, 0)>;
+def : InstAlias<"movz $dst, $imm", (MOVZWi GPR32:$dst, i32_imm0_65535:$imm, 0)>;
+def : InstAlias<"movz $dst, $imm", (MOVZXi GPR64:$dst, i32_imm0_65535:$imm, 0)>;
 
 // Next, we have various ELF relocations with the ":XYZ_g0:sym" syntax.
 def : InstAlias<"movz $Rd, $sym", (MOVZXi GPR64:$Rd, movw_symbol_g3:$sym, 48)>;
diff --git a/llvm/lib/Target/AArch64/AArch64Subtarget.h b/llvm/lib/Target/AArch64/AArch64Subtarget.h
@@ -137,6 +137,7 @@ class AArch64Subtarget final : public AArch64GenSubtargetInfo {
   bool HasBTI = false;
   bool HasRandGen = false;
   bool HasMTE = false;
+  bool HasTME = false;
 
   // Arm SVE2 extensions
   bool HasSVE2AES = false;
@@ -387,6 +388,7 @@ class AArch64Subtarget final : public AArch64GenSubtargetInfo {
   bool hasBTI() const { return HasBTI; }
   bool hasRandGen() const { return HasRandGen; }
   bool hasMTE() const { return HasMTE; }
+  bool hasTME() const { return HasTME; }
   // Arm SVE2 extensions
   bool hasSVE2AES() const { return HasSVE2AES; }
   bool hasSVE2SM4() const { return HasSVE2SM4; }
diff --git a/llvm/test/CodeGen/AArch64/tme.ll b/llvm/test/CodeGen/AArch64/tme.ll
@@ -0,0 +1,44 @@
+; RUN: llc %s -verify-machineinstrs -o - | FileCheck %s
+
+target triple = "aarch64-unknown-unknown-eabi"
+
+define i64 @test_tstart() #0 {
+  %r = tail call i64 @llvm.aarch64.tstart()
+  ret i64 %r
+}
+declare i64 @llvm.aarch64.tstart() #1
+; CHECK-LABEL: test_tstart
+; CHECK: tstart x
+
+define i64 @test_ttest() #0 {
+  %r = tail call i64 @llvm.aarch64.ttest()
+  ret i64 %r
+}
+declare i64 @llvm.aarch64.ttest() #1
+; CHECK-LABEL: test_ttest
+; CHECK: ttest x
+
+define void @test_tcommit() #0 {
+  tail call void @llvm.aarch64.tcommit()
+  ret void
+}
+declare void @llvm.aarch64.tcommit() #1
+; CHECK-LABEL: test_tcommit
+; CHECK: tcommit
+
+define void @test_tcancel() #0 {
+  tail call void @llvm.aarch64.tcancel(i64 0) #1
+  tail call void @llvm.aarch64.tcancel(i64 1) #1
+  tail call void @llvm.aarch64.tcancel(i64 65534) #1
+  tail call void @llvm.aarch64.tcancel(i64 65535) #1
+  ret void
+}
+declare void @llvm.aarch64.tcancel(i64 immarg) #1
+; CHECK-LABEL: test_tcancel
+; CHECK: tcancel #0
+; CHECK: tcancel #0x1
+; CHECK: tcancel #0xfffe
+; CHECK: tcancel #0xffff
+
+attributes #0 = { "target-features"="+tme" }
+attributes #1 = { nounwind }
diff --git a/llvm/test/MC/AArch64/tme-error.s b/llvm/test/MC/AArch64/tme-error.s
diff --git a/llvm/test/MC/AArch64/tme.s b/llvm/test/MC/AArch64/tme.s
diff --git a/llvm/test/MC/Disassembler/AArch64/tme.txt b/llvm/test/MC/Disassembler/AArch64/tme.txt
diff --git a/llvm/unittests/Support/TargetParserTest.cpp b/llvm/unittests/Support/TargetParserTest.cpp

Original file line number	Diff line number	Diff line change
`@@ -1932,6 +1932,7 @@ bool Sema::CheckAArch64BuiltinFunctionCall(unsigned BuiltinID,`
`1932`	`1932`	`case AArch64::BI__builtin_arm_dmb:`
`1933`	`1933`	`case AArch64::BI__builtin_arm_dsb:`
`1934`	`1934`	`case AArch64::BI__builtin_arm_isb: l = 0; u = 15; break;`
	`1935`	`+ case AArch64::BI__builtin_arm_tcancel: l = 0; u = 65535; break;`
`1935`	`1936`	`}`
`1936`	`1937`
`1937`	`1938`	`return SemaBuiltinConstantArgRange(TheCall, i, l, u + l);`