aarch64: Avoid duplicating bti j insns for jump tables [PR99988]

This patch fixes PR99988 which shows us generating large (> 250)
sequences of back-to-back bti j instructions.

The fix is simply to avoid inserting bti j instructions at the target of
a jump table if we've already inserted one for a given label.

gcc/ChangeLog:

	PR target/99988
	* config/aarch64/aarch64-bti-insert.c (aarch64_bti_j_insn_p): New.
	(rest_of_insert_bti): Avoid inserting duplicate bti j insns for
	jump table targets.

gcc/testsuite/ChangeLog:

	PR target/99988
	* gcc.target/aarch64/pr99988.c: New test.

2 files changed, 81 insertions, 0 deletions

diff --git a/gcc/config/aarch64/aarch64-bti-insert.c b/gcc/config/aarch64/aarch64-bti-insert.c
index 9366497..5d6bc16 100644
--- a/gcc/config/aarch64/aarch64-bti-insert.c
+++ b/gcc/config/aarch64/aarch64-bti-insert.c
@@ -120,6 +120,17 @@ aarch64_pac_insn_p (rtx x)
   return false;
 }
 
+/* Check if INSN is a BTI J insn.  */
+static bool
+aarch64_bti_j_insn_p (rtx_insn *insn)
+{
+  if (!insn || !INSN_P (insn))
+    return false;
+
+  rtx pat = PATTERN (insn);
+  return GET_CODE (pat) == UNSPEC_VOLATILE && XINT (pat, 1) == UNSPECV_BTI_J;
+}
+
 /* Insert the BTI instruction.  */
 /* This is implemented as a late RTL pass that runs before branch
    shortening and does the following.  */
@@ -165,6 +176,10 @@ rest_of_insert_bti (void)
 		  for (j = GET_NUM_ELEM (vec) - 1; j >= 0; --j)
 		    {
 		      label = as_a <rtx_insn *> (XEXP (RTVEC_ELT (vec, j), 0));
+		      rtx_insn *next = next_nonnote_nondebug_insn (label);
+		      if (aarch64_bti_j_insn_p (next))
+			continue;
+
 		      bti_insn = gen_bti_j ();
 		      emit_insn_after (bti_insn, label);
 		    }
diff --git a/gcc/testsuite/gcc.target/aarch64/pr99988.c b/gcc/testsuite/gcc.target/aarch64/pr99988.c
new file mode 100644
index 0000000..2d87f41
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/pr99988.c
@@ -0,0 +1,66 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -mbranch-protection=standard" } */
+/* { dg-final { scan-assembler-times {bti j} 13 } } */
+int a;
+int c();
+int d();
+int e();
+int f();
+int g();
+void h() {
+  switch (a) {
+  case 0:
+  case 56:
+  case 57:
+    break;
+  case 58:
+  case 59:
+  case 61:
+  case 62:
+    c();
+  case 64:
+  case 63:
+    d();
+  case 66:
+  case 65:
+    d();
+  case 68:
+  case 67:
+    d();
+  case 69:
+  case 70:
+    d();
+  case 71:
+  case 72:
+  case 88:
+  case 87:
+    d();
+  case 90:
+  case 89:
+    d();
+  case 92:
+  case 1:
+    d();
+  case 93:
+  case 73:
+  case 4:
+    e();
+  case 76:
+  case 5:
+    f();
+  case 7:
+  case 8:
+  case 84:
+  case 85:
+    break;
+  case 6:
+  case 299:
+  case 9:
+  case 80:
+  case 2:
+  case 3:
+    e();
+  default:
+    g();
+  }
+}