crosstool-ng/packages/gcc/9.5.0/0029-aarch64-Simplify-probe-of-final-frame-allocation.patch

112 lines
3.8 KiB
Diff

From f2684e63652bb251d22c79e40081c646df1f36b6 Mon Sep 17 00:00:00 2001
From: Richard Sandiford <richard.sandiford@arm.com>
Date: Tue, 8 Aug 2023 01:57:26 +0100
Subject: [PATCH 29/30] aarch64: Simplify probe of final frame allocation
Previous patches ensured that the final frame allocation only needs
a probe when the size is strictly greater than 1KiB. It's therefore
safe to use the normal 1024 probe offset in all cases.
The main motivation for doing this is to simplify the code and
remove the number of special cases.
gcc/
* config/aarch64/aarch64.c (aarch64_allocate_and_probe_stack_space):
Always probe the residual allocation at offset 1024, asserting
that that is in range.
gcc/testsuite/
* gcc.target/aarch64/stack-check-prologue-17.c: Expect the probe
to be at offset 1024 rather than offset 0.
* gcc.target/aarch64/stack-check-prologue-18.c: Likewise.
---
gcc/config/aarch64/aarch64.c | 12 ++++--------
.../gcc.target/aarch64/stack-check-prologue-17.c | 2 +-
.../gcc.target/aarch64/stack-check-prologue-18.c | 7 +++++--
3 files changed, 10 insertions(+), 11 deletions(-)
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index 1e8467fdd03f..705f719a2eaa 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -5695,16 +5695,12 @@ aarch64_allocate_and_probe_stack_space (rtx temp1, rtx temp2,
are still safe. */
if (residual)
{
- HOST_WIDE_INT residual_probe_offset = guard_used_by_caller;
+ gcc_assert (guard_used_by_caller + byte_sp_alignment <= size);
+
/* If we're doing final adjustments, and we've done any full page
allocations then any residual needs to be probed. */
if (final_adjustment_p && rounded_size != 0)
min_probe_threshold = 0;
- /* If doing a small final adjustment, we always probe at offset 0.
- This is done to avoid issues when the final adjustment is smaller
- than the probing offset. */
- else if (final_adjustment_p && rounded_size == 0)
- residual_probe_offset = 0;
aarch64_sub_sp (temp1, temp2, residual, frame_related_p);
if (residual >= min_probe_threshold)
@@ -5715,8 +5711,8 @@ aarch64_allocate_and_probe_stack_space (rtx temp1, rtx temp2,
HOST_WIDE_INT_PRINT_DEC " bytes, probing will be required."
"\n", residual);
- emit_stack_probe (plus_constant (Pmode, stack_pointer_rtx,
- residual_probe_offset));
+ emit_stack_probe (plus_constant (Pmode, stack_pointer_rtx,
+ guard_used_by_caller));
emit_insn (gen_blockage ());
}
}
diff --git a/gcc/testsuite/gcc.target/aarch64/stack-check-prologue-17.c b/gcc/testsuite/gcc.target/aarch64/stack-check-prologue-17.c
index 0d8a25d73a24..f0ec1389771d 100644
--- a/gcc/testsuite/gcc.target/aarch64/stack-check-prologue-17.c
+++ b/gcc/testsuite/gcc.target/aarch64/stack-check-prologue-17.c
@@ -33,7 +33,7 @@ int test1(int z) {
** ...
** str x30, \[sp\]
** sub sp, sp, #1040
-** str xzr, \[sp\]
+** str xzr, \[sp, #?1024\]
** cbnz w0, .*
** bl g
** ...
diff --git a/gcc/testsuite/gcc.target/aarch64/stack-check-prologue-18.c b/gcc/testsuite/gcc.target/aarch64/stack-check-prologue-18.c
index 82447d20fff5..71d33ba34e9e 100644
--- a/gcc/testsuite/gcc.target/aarch64/stack-check-prologue-18.c
+++ b/gcc/testsuite/gcc.target/aarch64/stack-check-prologue-18.c
@@ -8,8 +8,9 @@ void g();
** test1:
** ...
** str x30, \[sp\]
+** ...
** sub sp, sp, #4064
-** str xzr, \[sp\]
+** str xzr, \[sp, #?1024\]
** cbnz w0, .*
** bl g
** ...
@@ -49,8 +50,9 @@ int test1(int z) {
** test2:
** ...
** str x30, \[sp\]
+** ...
** sub sp, sp, #1040
-** str xzr, \[sp\]
+** str xzr, \[sp, #?1024\]
** cbnz w0, .*
** bl g
** ...
@@ -77,6 +79,7 @@ int test2(int z) {
** test3:
** ...
** str x30, \[sp\]
+** ...
** sub sp, sp, #1024
** cbnz w0, .*
** bl g
--
2.42.0