diff options
Diffstat (limited to '0119-aarch64-Simplif-yprobe-of-final-frame-allocation.patch')
| -rw-r--r-- | 0119-aarch64-Simplif-yprobe-of-final-frame-allocation.patch | 98 |
1 files changed, 98 insertions, 0 deletions
diff --git a/0119-aarch64-Simplif-yprobe-of-final-frame-allocation.patch b/0119-aarch64-Simplif-yprobe-of-final-frame-allocation.patch new file mode 100644 index 0000000..e59baf2 --- /dev/null +++ b/0119-aarch64-Simplif-yprobe-of-final-frame-allocation.patch @@ -0,0 +1,98 @@ +From c940aadecb4f623a39abe16b6c62b307e2b10638 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] 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 | 4 ++-- + 3 files changed, 7 insertions(+), 11 deletions(-) + +diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c +index 3d73c5f352f..37c6219b07a 100644 +--- a/gcc/config/aarch64/aarch64.c ++++ b/gcc/config/aarch64/aarch64.c +@@ -8153,16 +8153,12 @@ 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) +@@ -8173,8 +8169,8 @@ 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 0d8a25d73a2..f0ec1389771 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 b646f040b54..71d33ba34e9 100644 +--- a/gcc/testsuite/gcc.target/aarch64/stack-check-prologue-18.c ++++ b/gcc/testsuite/gcc.target/aarch64/stack-check-prologue-18.c +@@ -10,7 +10,7 @@ void g(); + ** str x30, \[sp\] + ** ... + ** sub sp, sp, #4064 +-** str xzr, \[sp\] ++** str xzr, \[sp, #?1024\] + ** cbnz w0, .* + ** bl g + ** ... +@@ -52,7 +52,7 @@ int test1(int z) { + ** str x30, \[sp\] + ** ... + ** sub sp, sp, #1040 +-** str xzr, \[sp\] ++** str xzr, \[sp, #?1024\] + ** cbnz w0, .* + ** bl g + ** ... +-- +2.39.3 |