[SVE] Fix crashes with inline assembly

All the crashes found compiling inline assembly are fixed in this
patch by changing AArch64TargetLowering::getRegForInlineAsmConstraint
to be more resilient to mismatched value and register types. For
example, it makes no sense to request a predicate register for
a nxv2i64 type and so on.

Tests have been added here:

  test/CodeGen/AArch64/inline-asm-constraints-bad-sve.ll

Differential Revision: https://reviews.llvm.org/D92554

diff --git a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
index cca31a7..700c281 100644 (file)
--- a/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
+++ b/llvm/lib/Target/AArch64/AArch64ISelLowering.cpp
@@ -7511,23 +7511,30 @@ AArch64TargetLowering::getRegForInlineAsmConstraint(
   if (Constraint.size() == 1) {
     switch (Constraint[0]) {
     case 'r':
-      if (VT.getSizeInBits() == 64)
+      if (VT.isScalableVector())
+        return std::make_pair(0U, nullptr);
+      if (VT.getFixedSizeInBits() == 64)
         return std::make_pair(0U, &AArch64::GPR64commonRegClass);
       return std::make_pair(0U, &AArch64::GPR32commonRegClass);
-    case 'w':
+    case 'w': {
       if (!Subtarget->hasFPARMv8())
         break;
-      if (VT.isScalableVector())
-        return std::make_pair(0U, &AArch64::ZPRRegClass);
-      if (VT.getSizeInBits() == 16)
+      if (VT.isScalableVector()) {
+        if (VT.getVectorElementType() != MVT::i1)
+          return std::make_pair(0U, &AArch64::ZPRRegClass);
+        return std::make_pair(0U, nullptr);
+      }
+      uint64_t VTSize = VT.getFixedSizeInBits();
+      if (VTSize == 16)
         return std::make_pair(0U, &AArch64::FPR16RegClass);
-      if (VT.getSizeInBits() == 32)
+      if (VTSize == 32)
         return std::make_pair(0U, &AArch64::FPR32RegClass);
-      if (VT.getSizeInBits() == 64)
+      if (VTSize == 64)
         return std::make_pair(0U, &AArch64::FPR64RegClass);
-      if (VT.getSizeInBits() == 128)
+      if (VTSize == 128)
         return std::make_pair(0U, &AArch64::FPR128RegClass);
       break;
+    }
     // The instructions that this constraint is designed for can
     // only take 128-bit registers so just use that regclass.
     case 'x':
@@ -7548,10 +7555,11 @@ AArch64TargetLowering::getRegForInlineAsmConstraint(
   } else {
     PredicateConstraint PC = parsePredicateConstraint(Constraint);
     if (PC != PredicateConstraint::Invalid) {
-      assert(VT.isScalableVector());
+      if (!VT.isScalableVector() || VT.getVectorElementType() != MVT::i1)
+        return std::make_pair(0U, nullptr);
       bool restricted = (PC == PredicateConstraint::Upl);
       return restricted ? std::make_pair(0U, &AArch64::PPR_3bRegClass)
-                          : std::make_pair(0U, &AArch64::PPRRegClass);
+                        : std::make_pair(0U, &AArch64::PPRRegClass);
     }
   }
   if (StringRef("{cc}").equals_lower(Constraint))

diff --git a/llvm/test/CodeGen/AArch64/inline-asm-constraints-bad-sve.ll b/llvm/test/CodeGen/AArch64/inline-asm-constraints-bad-sve.ll
new file mode 100644 (file)
index 0000000..5a2f474
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/inline-asm-constraints-bad-sve.ll
@@ -0,0 +1,29 @@
+; RUN: not llc -mtriple=aarch64-none-linux-gnu -mattr=+sve -o - %s 2>&1 | FileCheck %s
+
+target datalayout = "e-m:e-i8:8:32-i16:16:32-i64:64-i128:128-n32:64-S128"
+target triple = "aarch64-unknown-linux-gnu"
+
+; CHECK: error: couldn't allocate input reg for constraint 'Upa'
+; CHECK: error: couldn't allocate input reg for constraint 'r'
+; CHECK: error: couldn't allocate output register for constraint 'w'
+
+define <vscale x 16 x i1> @foo1(i32 *%in) {
+entry:
+  %0 = load i32, i32* %in, align 4
+  %1 = call <vscale x 16 x i1> asm sideeffect "mov $0.b, $1.b \0A", "=@3Upa,@3Upa"(i32 %0)
+  ret <vscale x 16 x i1> %1
+}
+
+define <vscale x 4 x float> @foo2(<vscale x 4 x i32> *%in) {
+entry:
+  %0 = load <vscale x 4 x i32>, <vscale x 4 x i32>* %in, align 16
+  %1 = call <vscale x 4 x float> asm sideeffect "ptrue p0.s, #1 \0Afabs $0.s, p0/m, $1.s \0A", "=w,r"(<vscale x 4 x i32> %0)
+  ret <vscale x 4 x float> %1
+}
+
+define <vscale x 16 x i1> @foo3(<vscale x 16 x i1> *%in) {
+entry:
+  %0 = load <vscale x 16 x i1>, <vscale x 16 x i1>* %in, align 2
+  %1 = call <vscale x 16 x i1> asm sideeffect "mov $0.b, $1.b \0A", "=&w,w"(<vscale x 16 x i1> %0)
+  ret <vscale x 16 x i1> %1
+}