[PATCH] [PowerPC] Indicate that PPC32PICGOT clobbers LR (#154654)

This pseudo-instruction emits a local `bl` writing LR, so that must be
saved and restored for the function to return to the right place. If
not, we'll return to the inline `.long` that the `bl` stepped over.

This fixes the `SIGILL` seen in rayon-rs/rayon#1268.

Gbp-Pq: Name powerpc-fix-SIGILL.diff

diff --git a/llvm/lib/Target/PowerPC/PPCInstrInfo.td b/llvm/lib/Target/PowerPC/PPCInstrInfo.td
index 69f8ddc0ea7010401f293f00dcd49522477df681..151df8800aa9d5b3fb6d1d4ee5dee76ff6cfa6fe 100644 (file)
--- a/llvm/lib/Target/PowerPC/PPCInstrInfo.td
+++ b/llvm/lib/Target/PowerPC/PPCInstrInfo.td
@@ -3224,7 +3224,8 @@ def PPC32GOT: PPCEmitTimePseudo<(outs gprc:$rD), (ins), "#PPC32GOT",
 
 // Get the _GLOBAL_OFFSET_TABLE_ in PIC mode.
 // This uses two output registers, the first as the real output, the second as a
-// temporary register, used internally in code generation.
+// temporary register, used internally in code generation. A "bl" also clobbers LR.
+let Defs = [LR] in
 def PPC32PICGOT: PPCEmitTimePseudo<(outs gprc:$rD, gprc:$rT), (ins), "#PPC32PICGOT",
                 []>, NoEncode<"$rT">;
 

diff --git a/llvm/test/CodeGen/PowerPC/tls-picgot.ll b/llvm/test/CodeGen/PowerPC/tls-picgot.ll
new file mode 100644 (file)
index 0000000..6562d86
--- /dev/null
+++ b/llvm/test/CodeGen/PowerPC/tls-picgot.ll
@@ -0,0 +1,31 @@
+; RUN: llc -verify-machineinstrs -relocation-model=pic < %s | FileCheck %s
+
+target triple = "powerpc-unknown-linux-gnu"
+
+; Test that LR is preserved when PPC32PICGOT clobbers it with a local "bl".
+
+@TLS = external thread_local global i8
+
+; CHECK-LABEL: tls_addr:
+; CHECK:        mflr [[SAVED_REG:[0-9]+]]
+
+; CHECK:        bl [[JUMP:\.L[[:alnum:]_]+]]
+; CHECK-NEXT:   [[OFFSET:\.L[[:alnum:]_]+]]:
+; CHECK-NEXT:   .long _GLOBAL_OFFSET_TABLE_-[[OFFSET]]
+; CHECK-NEXT:   [[JUMP]]
+; CHECK-NEXT:   mflr {{[0-9]+}}
+
+; CHECK:        mtlr [[SAVED_REG]]
+; CHECK-NEXT:   blr
+
+define ptr @tls_addr() unnamed_addr {
+  %1 = call ptr @llvm.threadlocal.address.p0(ptr @TLS)
+  ret ptr %1
+}
+
+declare nonnull ptr @llvm.threadlocal.address.p0(ptr nonnull)
+
+!llvm.module.flags = !{!0, !1}
+
+!0 = !{i32 8, !"PIC Level", i32 2}
+!1 = !{i32 7, !"PIE Level", i32 2}