From f22315d5c19e8310e4dc880fd509678fd291fca8 Mon Sep 17 00:00:00 2001
From: Richard Sandiford <richard.sandiford@arm.com>
Date: Tue, 12 Sep 2023 16:08:54 +0100
Subject: [PATCH 23/28] aarch64: Tweak stack clash boundary condition

The AArch64 ABI says that, when stack clash protection is used,
there can be a maximum of 1KiB of unprobed space at sp on entry
to a function.  Therefore, we need to probe when allocating
>= guard_size - 1KiB of data (>= rather than >).  This is what
GCC does.

If an allocation is exactly guard_size bytes, it is enough to allocate
those bytes and probe once at offset 1024.  It isn't possible to use a
single probe at any other offset: higher would conmplicate later code,
by leaving more unprobed space than usual, while lower would risk
leaving an entire page unprobed.  For simplicity, the code probes all
allocations at offset 1024.

Some register saves also act as probes.  If we need to allocate
more space below the last such register save probe, we need to
probe the allocation if it is > 1KiB.  Again, this allocation is
then sometimes (but not always) probed at offset 1024.  This sort of
allocation is currently only used for outgoing arguments, which are
rarely this big.

However, the code also probed if this final outgoing-arguments
allocation was == 1KiB, rather than just > 1KiB.  This isn't
necessary, since the register save then probes at offset 1024
as required.  Continuing to probe allocations of exactly 1KiB
would complicate later patches.

gcc/
	* config/aarch64/aarch64.cc (aarch64_allocate_and_probe_stack_space):
	Don't probe final allocations that are exactly 1KiB in size (after
	unprobed space above the final allocation has been deducted).

gcc/testsuite/
	* gcc.target/aarch64/stack-check-prologue-17.c: New test.
---
 gcc/config/aarch64/aarch64.cc                 |  4 +-
 .../aarch64/stack-check-prologue-17.c         | 55 +++++++++++++++++++
 2 files changed, 58 insertions(+), 1 deletion(-)
 create mode 100644 gcc/testsuite/gcc.target/aarch64/stack-check-prologue-17.c

diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index 4d9fcf3d1623..34c1d8614cd9 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -9333,9 +9333,11 @@ aarch64_allocate_and_probe_stack_space (rtx temp1, rtx temp2,
   HOST_WIDE_INT guard_size
     = 1 << param_stack_clash_protection_guard_size;
   HOST_WIDE_INT guard_used_by_caller = STACK_CLASH_CALLER_GUARD;
+  HOST_WIDE_INT byte_sp_alignment = STACK_BOUNDARY / BITS_PER_UNIT;
+  gcc_assert (multiple_p (poly_size, byte_sp_alignment));
   HOST_WIDE_INT min_probe_threshold
     = (final_adjustment_p
-       ? guard_used_by_caller
+       ? guard_used_by_caller + byte_sp_alignment
        : guard_size - guard_used_by_caller);
   /* When doing the final adjustment for the outgoing arguments, take into
      account any unprobed space there is above the current SP.  There are
diff --git a/gcc/testsuite/gcc.target/aarch64/stack-check-prologue-17.c b/gcc/testsuite/gcc.target/aarch64/stack-check-prologue-17.c
new file mode 100644
index 000000000000..0d8a25d73a24
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/stack-check-prologue-17.c
@@ -0,0 +1,55 @@
+/* { dg-options "-O2 -fstack-clash-protection -fomit-frame-pointer --param stack-clash-protection-guard-size=12" } */
+/* { dg-final { check-function-bodies "**" "" } } */
+
+void f(int, ...);
+void g();
+
+/*
+** test1:
+**	...
+**	str	x30, \[sp\]
+**	sub	sp, sp, #1024
+**	cbnz	w0, .*
+**	bl	g
+**	...
+*/
+int test1(int z) {
+  __uint128_t x = 0;
+  int y[0x400];
+  if (z)
+    {
+      f(0, 0, 0, 0, 0, 0, 0, &y,
+	x, x, x, x, x, x, x, x, x, x, x, x, x, x, x, x,
+	x, x, x, x, x, x, x, x, x, x, x, x, x, x, x, x,
+	x, x, x, x, x, x, x, x, x, x, x, x, x, x, x, x,
+	x, x, x, x, x, x, x, x, x, x, x, x, x, x, x, x);
+    }
+  g();
+  return 1;
+}
+
+/*
+** test2:
+**	...
+**	str	x30, \[sp\]
+**	sub	sp, sp, #1040
+**	str	xzr, \[sp\]
+**	cbnz	w0, .*
+**	bl	g
+**	...
+*/
+int test2(int z) {
+  __uint128_t x = 0;
+  int y[0x400];
+  if (z)
+    {
+      f(0, 0, 0, 0, 0, 0, 0, &y,
+	x, x, x, x, x, x, x, x, x, x, x, x, x, x, x, x,
+	x, x, x, x, x, x, x, x, x, x, x, x, x, x, x, x,
+	x, x, x, x, x, x, x, x, x, x, x, x, x, x, x, x,
+	x, x, x, x, x, x, x, x, x, x, x, x, x, x, x, x,
+	x);
+    }
+  g();
+  return 1;
+}
-- 
2.42.0