From 74f99f1adc696f446115f36974a3f94f66294a53 Mon Sep 17 00:00:00 2001
From: Richard Sandiford <richard.sandiford@arm.com>
Date: Wed, 20 Sep 2023 11:13:20 +0100
Subject: [PATCH] aarch64: Fix loose ldpstp check [PR111411]

aarch64_operands_ok_for_ldpstp contained the code:

  /* One of the memory accesses must be a mempair operand.
     If it is not the first one, they need to be swapped by the
     peephole.  */
  if (!aarch64_mem_pair_operand (mem_1, GET_MODE (mem_1))
       && !aarch64_mem_pair_operand (mem_2, GET_MODE (mem_2)))
    return false;

But the requirement isn't just that one of the accesses must be a
valid mempair operand.  It's that the lower access must be, since
that's the access that will be used for the instruction operand.

gcc/
	PR target/111411
	* config/aarch64/aarch64.cc (aarch64_operands_ok_for_ldpstp): Require
	the lower memory access to a mem-pair operand.

gcc/testsuite/
	PR target/111411
	* gcc.dg/rtl/aarch64/pr111411.c: New test.

(cherry picked from commit 2d38f45bcca62ca0c7afef4b579f82c5c2a01610)
---
 gcc/config/aarch64/aarch64.cc               |  8 ++-
 gcc/testsuite/gcc.dg/rtl/aarch64/pr111411.c | 57 +++++++++++++++++++++
 2 files changed, 60 insertions(+), 5 deletions(-)
 create mode 100644 gcc/testsuite/gcc.dg/rtl/aarch64/pr111411.c

diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index 96c3f48fdc49..a979accd90a9 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -26031,11 +26031,9 @@ aarch64_operands_ok_for_ldpstp (rtx *operands, bool load,
   gcc_assert (known_eq (GET_MODE_SIZE (GET_MODE (mem_1)),
 			GET_MODE_SIZE (GET_MODE (mem_2))));
 
-  /* One of the memory accesses must be a mempair operand.
-     If it is not the first one, they need to be swapped by the
-     peephole.  */
-  if (!aarch64_mem_pair_operand (mem_1, GET_MODE (mem_1))
-       && !aarch64_mem_pair_operand (mem_2, GET_MODE (mem_2)))
+  /* The lower memory access must be a mem-pair operand.  */
+  rtx lower_mem = reversed ? mem_2 : mem_1;
+  if (!aarch64_mem_pair_operand (lower_mem, GET_MODE (lower_mem)))
     return false;
 
   if (REG_P (reg_1) && FP_REGNUM_P (REGNO (reg_1)))
diff --git a/gcc/testsuite/gcc.dg/rtl/aarch64/pr111411.c b/gcc/testsuite/gcc.dg/rtl/aarch64/pr111411.c
new file mode 100644
index 000000000000..ad07e9c6c893
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/rtl/aarch64/pr111411.c
@@ -0,0 +1,57 @@
+/* { dg-do compile { target aarch64*-*-* } } */
+/* { dg-require-effective-target lp64 } */
+/* { dg-options "-O -fdisable-rtl-postreload -fpeephole2 -fno-schedule-fusion" } */
+
+extern int data[];
+
+void __RTL (startwith ("ira")) foo (void *ptr)
+{
+  (function "foo"
+    (param "ptr"
+      (DECL_RTL (reg/v:DI <0> [ ptr ]))
+      (DECL_RTL_INCOMING (reg/v:DI x0 [ ptr ]))
+    ) ;; param "ptr"
+    (insn-chain
+      (block 2
+	(edge-from entry (flags "FALLTHRU"))
+	(cnote 3 [bb 2] NOTE_INSN_BASIC_BLOCK)
+	(insn 4 (set (reg:DI <0>) (reg:DI x0)))
+	(insn 5 (set (reg:DI <1>)
+		     (plus:DI (reg:DI <0>) (const_int 768))))
+	(insn 6 (set (mem:SI (plus:DI (reg:DI <0>)
+				      (const_int 508)) [1 &data+508 S4 A4])
+		     (const_int 0)))
+	(insn 7 (set (mem:SI (plus:DI (reg:DI <1>)
+				      (const_int -256)) [1 &data+512 S4 A4])
+		     (const_int 0)))
+	(edge-to exit (flags "FALLTHRU"))
+      ) ;; block 2
+    ) ;; insn-chain
+  ) ;; function
+}
+
+void __RTL (startwith ("ira")) bar (void *ptr)
+{
+  (function "bar"
+    (param "ptr"
+      (DECL_RTL (reg/v:DI <0> [ ptr ]))
+      (DECL_RTL_INCOMING (reg/v:DI x0 [ ptr ]))
+    ) ;; param "ptr"
+    (insn-chain
+      (block 2
+	(edge-from entry (flags "FALLTHRU"))
+	(cnote 3 [bb 2] NOTE_INSN_BASIC_BLOCK)
+	(insn 4 (set (reg:DI <0>) (reg:DI x0)))
+	(insn 5 (set (reg:DI <1>)
+		     (plus:DI (reg:DI <0>) (const_int 768))))
+	(insn 6 (set (mem:SI (plus:DI (reg:DI <1>)
+				      (const_int -256)) [1 &data+512 S4 A4])
+		     (const_int 0)))
+	(insn 7 (set (mem:SI (plus:DI (reg:DI <0>)
+				      (const_int 508)) [1 &data+508 S4 A4])
+		     (const_int 0)))
+	(edge-to exit (flags "FALLTHRU"))
+      ) ;; block 2
+    ) ;; insn-chain
+  ) ;; function
+}
-- 
2.43.5