[gcc r12-3303] Fix target/101934: aarch64 memset code creates unaligned stores for -mstrict-align

[Andrew Pinski]

https://gcc.gnu.org/g:a45786e9a31f995087d8cb42bc3a4fe06911e588

commit r12-3303-ga45786e9a31f995087d8cb42bc3a4fe06911e588
Author: Andrew Pinski <apinski@marvell.com>
Date:   Tue Aug 31 04:41:14 2021 +0000

    Fix target/101934: aarch64 memset code creates unaligned stores for -mstrict-align
    
    The problem here is the aarch64_expand_setmem code did not check
    STRICT_ALIGNMENT if it is creating an overlapping store.
    This patch adds that check and the testcase works.
    
    gcc/ChangeLog:
    
            PR target/101934
            * config/aarch64/aarch64.c (aarch64_expand_setmem):
            Check STRICT_ALIGNMENT before creating an overlapping
            store.
    
    gcc/testsuite/ChangeLog:
    
            PR target/101934
            * gcc.target/aarch64/memset-strict-align-1.c: New test.

Diff:
---
 gcc/config/aarch64/aarch64.c                       |  4 ++--
 .../gcc.target/aarch64/memset-strict-align-1.c     | 28 ++++++++++++++++++++++
 2 files changed, 30 insertions(+), 2 deletions(-)

diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 3213585a588..26d59ba1e13 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -23566,8 +23566,8 @@ aarch64_expand_setmem (rtx *operands)
       /* Do certain trailing copies as overlapping if it's going to be
 	 cheaper.  i.e. less instructions to do so.  For instance doing a 15
 	 byte copy it's more efficient to do two overlapping 8 byte copies than
-	 8 + 4 + 2 + 1.  */
-      if (n > 0 && n < copy_limit / 2)
+	 8 + 4 + 2 + 1.  Only do this when -mstrict-align is not supplied.  */
+      if (n > 0 && n < copy_limit / 2 && !STRICT_ALIGNMENT)
 	{
 	  next_mode = smallest_mode_for_size (n, MODE_INT);
 	  int n_bits = GET_MODE_BITSIZE (next_mode).to_constant ();
diff --git a/gcc/testsuite/gcc.target/aarch64/memset-strict-align-1.c b/gcc/testsuite/gcc.target/aarch64/memset-strict-align-1.c
new file mode 100644
index 00000000000..5cdc8a44968
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/memset-strict-align-1.c
@@ -0,0 +1,28 @@
+/* { dg-do compile } */
+/* { dg-options "-Os -mstrict-align" } */
+
+struct s { char x[95]; };
+void foo (struct s *);
+void bar (void) { struct s s1 = {}; foo (&s1); }
+
+/* memset (s1 = {}, sizeof = 95) should be expanded out
+   such that there are no overlap stores when -mstrict-align
+   is in use.
+   so 2 pair 16 bytes stores (64 bytes).
+   1 16 byte stores
+   1 8 byte store
+   1 4 byte store
+   1 2 byte store
+   1 1 byte store
+   */
+
+/* { dg-final { scan-assembler-times "stp\tq" 2 } } */
+/* { dg-final { scan-assembler-times "str\tq" 1 } } */
+/* { dg-final { scan-assembler-times "str\txzr" 1 } } */
+/* { dg-final { scan-assembler-times "str\twzr" 1 } } */
+/* { dg-final { scan-assembler-times "strh\twzr" 1 } } */
+/* { dg-final { scan-assembler-times "strb\twzr" 1 } } */
+
+/* Also one store pair for the frame-pointer and the LR. */
+/* { dg-final { scan-assembler-times "stp\tx" 1 } } */
+