From: Richard Sandiford <richard.sandiford@arm.com>
To: gcc-patches@gcc.gnu.org
Cc: Richard Sandiford <richard.sandiford@arm.com>
Subject: [PATCH 01/19] aarch64: Use local frame vars in shrink-wrapping code
Date: Tue, 12 Sep 2023 16:25:11 +0100 [thread overview]
Message-ID: <20230912152529.3322336-2-richard.sandiford@arm.com> (raw)
In-Reply-To: <20230912152529.3322336-1-richard.sandiford@arm.com>
aarch64_layout_frame uses a shorthand for referring to
cfun->machine->frame:
aarch64_frame &frame = cfun->machine->frame;
This patch does the same for some other heavy users of the structure.
No functional change intended.
gcc/
* config/aarch64/aarch64.cc (aarch64_save_callee_saves): Use
a local shorthand for cfun->machine->frame.
(aarch64_restore_callee_saves, aarch64_get_separate_components):
(aarch64_process_components): Likewise.
(aarch64_allocate_and_probe_stack_space): Likewise.
(aarch64_expand_prologue, aarch64_expand_epilogue): Likewise.
(aarch64_layout_frame): Use existing shorthand for one more case.
---
gcc/config/aarch64/aarch64.cc | 123 ++++++++++++++++++----------------
1 file changed, 64 insertions(+), 59 deletions(-)
diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc
index 37d414021ca..b91f77d7b1f 100644
--- a/gcc/config/aarch64/aarch64.cc
+++ b/gcc/config/aarch64/aarch64.cc
@@ -8651,7 +8651,7 @@ aarch64_layout_frame (void)
frame.is_scs_enabled
= (!crtl->calls_eh_return
&& sanitize_flags_p (SANITIZE_SHADOW_CALL_STACK)
- && known_ge (cfun->machine->frame.reg_offset[LR_REGNUM], 0));
+ && known_ge (frame.reg_offset[LR_REGNUM], 0));
/* When shadow call stack is enabled, the scs_pop in the epilogue will
restore x30, and we don't need to pop x30 again in the traditional
@@ -9117,6 +9117,7 @@ aarch64_save_callee_saves (poly_int64 start_offset,
unsigned start, unsigned limit, bool skip_wb,
bool hard_fp_valid_p)
{
+ aarch64_frame &frame = cfun->machine->frame;
rtx_insn *insn;
unsigned regno;
unsigned regno2;
@@ -9131,8 +9132,8 @@ aarch64_save_callee_saves (poly_int64 start_offset,
bool frame_related_p = aarch64_emit_cfi_for_reg_p (regno);
if (skip_wb
- && (regno == cfun->machine->frame.wb_push_candidate1
- || regno == cfun->machine->frame.wb_push_candidate2))
+ && (regno == frame.wb_push_candidate1
+ || regno == frame.wb_push_candidate2))
continue;
if (cfun->machine->reg_is_wrapped_separately[regno])
@@ -9140,7 +9141,7 @@ aarch64_save_callee_saves (poly_int64 start_offset,
machine_mode mode = aarch64_reg_save_mode (regno);
reg = gen_rtx_REG (mode, regno);
- offset = start_offset + cfun->machine->frame.reg_offset[regno];
+ offset = start_offset + frame.reg_offset[regno];
rtx base_rtx = stack_pointer_rtx;
poly_int64 sp_offset = offset;
@@ -9153,7 +9154,7 @@ aarch64_save_callee_saves (poly_int64 start_offset,
{
gcc_assert (known_eq (start_offset, 0));
poly_int64 fp_offset
- = cfun->machine->frame.below_hard_fp_saved_regs_size;
+ = frame.below_hard_fp_saved_regs_size;
if (hard_fp_valid_p)
base_rtx = hard_frame_pointer_rtx;
else
@@ -9175,8 +9176,7 @@ aarch64_save_callee_saves (poly_int64 start_offset,
&& (regno2 = aarch64_next_callee_save (regno + 1, limit)) <= limit
&& !cfun->machine->reg_is_wrapped_separately[regno2]
&& known_eq (GET_MODE_SIZE (mode),
- cfun->machine->frame.reg_offset[regno2]
- - cfun->machine->frame.reg_offset[regno]))
+ frame.reg_offset[regno2] - frame.reg_offset[regno]))
{
rtx reg2 = gen_rtx_REG (mode, regno2);
rtx mem2;
@@ -9226,6 +9226,7 @@ static void
aarch64_restore_callee_saves (poly_int64 start_offset, unsigned start,
unsigned limit, bool skip_wb, rtx *cfi_ops)
{
+ aarch64_frame &frame = cfun->machine->frame;
unsigned regno;
unsigned regno2;
poly_int64 offset;
@@ -9242,13 +9243,13 @@ aarch64_restore_callee_saves (poly_int64 start_offset, unsigned start,
rtx reg, mem;
if (skip_wb
- && (regno == cfun->machine->frame.wb_pop_candidate1
- || regno == cfun->machine->frame.wb_pop_candidate2))
+ && (regno == frame.wb_pop_candidate1
+ || regno == frame.wb_pop_candidate2))
continue;
machine_mode mode = aarch64_reg_save_mode (regno);
reg = gen_rtx_REG (mode, regno);
- offset = start_offset + cfun->machine->frame.reg_offset[regno];
+ offset = start_offset + frame.reg_offset[regno];
rtx base_rtx = stack_pointer_rtx;
if (mode == VNx2DImode && BYTES_BIG_ENDIAN)
aarch64_adjust_sve_callee_save_base (mode, base_rtx, anchor_reg,
@@ -9259,8 +9260,7 @@ aarch64_restore_callee_saves (poly_int64 start_offset, unsigned start,
&& (regno2 = aarch64_next_callee_save (regno + 1, limit)) <= limit
&& !cfun->machine->reg_is_wrapped_separately[regno2]
&& known_eq (GET_MODE_SIZE (mode),
- cfun->machine->frame.reg_offset[regno2]
- - cfun->machine->frame.reg_offset[regno]))
+ frame.reg_offset[regno2] - frame.reg_offset[regno]))
{
rtx reg2 = gen_rtx_REG (mode, regno2);
rtx mem2;
@@ -9365,6 +9365,7 @@ offset_12bit_unsigned_scaled_p (machine_mode mode, poly_int64 offset)
static sbitmap
aarch64_get_separate_components (void)
{
+ aarch64_frame &frame = cfun->machine->frame;
sbitmap components = sbitmap_alloc (LAST_SAVED_REGNUM + 1);
bitmap_clear (components);
@@ -9381,18 +9382,18 @@ aarch64_get_separate_components (void)
if (mode == VNx2DImode && BYTES_BIG_ENDIAN)
continue;
- poly_int64 offset = cfun->machine->frame.reg_offset[regno];
+ poly_int64 offset = frame.reg_offset[regno];
/* If the register is saved in the first SVE save slot, we use
it as a stack probe for -fstack-clash-protection. */
if (flag_stack_clash_protection
- && maybe_ne (cfun->machine->frame.below_hard_fp_saved_regs_size, 0)
+ && maybe_ne (frame.below_hard_fp_saved_regs_size, 0)
&& known_eq (offset, 0))
continue;
/* Get the offset relative to the register we'll use. */
if (frame_pointer_needed)
- offset -= cfun->machine->frame.below_hard_fp_saved_regs_size;
+ offset -= frame.below_hard_fp_saved_regs_size;
else
offset += crtl->outgoing_args_size;
@@ -9411,11 +9412,11 @@ aarch64_get_separate_components (void)
/* If the spare predicate register used by big-endian SVE code
is call-preserved, it must be saved in the main prologue
before any saves that use it. */
- if (cfun->machine->frame.spare_pred_reg != INVALID_REGNUM)
- bitmap_clear_bit (components, cfun->machine->frame.spare_pred_reg);
+ if (frame.spare_pred_reg != INVALID_REGNUM)
+ bitmap_clear_bit (components, frame.spare_pred_reg);
- unsigned reg1 = cfun->machine->frame.wb_push_candidate1;
- unsigned reg2 = cfun->machine->frame.wb_push_candidate2;
+ unsigned reg1 = frame.wb_push_candidate1;
+ unsigned reg2 = frame.wb_push_candidate2;
/* If registers have been chosen to be stored/restored with
writeback don't interfere with them to avoid having to output explicit
stack adjustment instructions. */
@@ -9524,6 +9525,7 @@ aarch64_get_next_set_bit (sbitmap bmp, unsigned int start)
static void
aarch64_process_components (sbitmap components, bool prologue_p)
{
+ aarch64_frame &frame = cfun->machine->frame;
rtx ptr_reg = gen_rtx_REG (Pmode, frame_pointer_needed
? HARD_FRAME_POINTER_REGNUM
: STACK_POINTER_REGNUM);
@@ -9538,9 +9540,9 @@ aarch64_process_components (sbitmap components, bool prologue_p)
machine_mode mode = aarch64_reg_save_mode (regno);
rtx reg = gen_rtx_REG (mode, regno);
- poly_int64 offset = cfun->machine->frame.reg_offset[regno];
+ poly_int64 offset = frame.reg_offset[regno];
if (frame_pointer_needed)
- offset -= cfun->machine->frame.below_hard_fp_saved_regs_size;
+ offset -= frame.below_hard_fp_saved_regs_size;
else
offset += crtl->outgoing_args_size;
@@ -9565,14 +9567,14 @@ aarch64_process_components (sbitmap components, bool prologue_p)
break;
}
- poly_int64 offset2 = cfun->machine->frame.reg_offset[regno2];
+ poly_int64 offset2 = frame.reg_offset[regno2];
/* The next register is not of the same class or its offset is not
mergeable with the current one into a pair. */
if (aarch64_sve_mode_p (mode)
|| !satisfies_constraint_Ump (mem)
|| GP_REGNUM_P (regno) != GP_REGNUM_P (regno2)
|| (crtl->abi->id () == ARM_PCS_SIMD && FP_REGNUM_P (regno))
- || maybe_ne ((offset2 - cfun->machine->frame.reg_offset[regno]),
+ || maybe_ne ((offset2 - frame.reg_offset[regno]),
GET_MODE_SIZE (mode)))
{
insn = emit_insn (set);
@@ -9594,7 +9596,7 @@ aarch64_process_components (sbitmap components, bool prologue_p)
/* REGNO2 can be saved/restored in a pair with REGNO. */
rtx reg2 = gen_rtx_REG (mode, regno2);
if (frame_pointer_needed)
- offset2 -= cfun->machine->frame.below_hard_fp_saved_regs_size;
+ offset2 -= frame.below_hard_fp_saved_regs_size;
else
offset2 += crtl->outgoing_args_size;
rtx addr2 = plus_constant (Pmode, ptr_reg, offset2);
@@ -9699,6 +9701,7 @@ aarch64_allocate_and_probe_stack_space (rtx temp1, rtx temp2,
bool frame_related_p,
bool final_adjustment_p)
{
+ aarch64_frame &frame = cfun->machine->frame;
HOST_WIDE_INT guard_size
= 1 << param_stack_clash_protection_guard_size;
HOST_WIDE_INT guard_used_by_caller = STACK_CLASH_CALLER_GUARD;
@@ -9719,25 +9722,25 @@ aarch64_allocate_and_probe_stack_space (rtx temp1, rtx temp2,
register as a probe. We can't assume that LR was saved at position 0
though, so treat any space below it as unprobed. */
if (final_adjustment_p
- && known_eq (cfun->machine->frame.below_hard_fp_saved_regs_size, 0))
+ && known_eq (frame.below_hard_fp_saved_regs_size, 0))
{
- poly_int64 lr_offset = cfun->machine->frame.reg_offset[LR_REGNUM];
+ poly_int64 lr_offset = frame.reg_offset[LR_REGNUM];
if (known_ge (lr_offset, 0))
min_probe_threshold -= lr_offset.to_constant ();
else
gcc_assert (!flag_stack_clash_protection || known_eq (poly_size, 0));
}
- poly_int64 frame_size = cfun->machine->frame.frame_size;
+ poly_int64 frame_size = frame.frame_size;
/* We should always have a positive probe threshold. */
gcc_assert (min_probe_threshold > 0);
if (flag_stack_clash_protection && !final_adjustment_p)
{
- poly_int64 initial_adjust = cfun->machine->frame.initial_adjust;
- poly_int64 sve_callee_adjust = cfun->machine->frame.sve_callee_adjust;
- poly_int64 final_adjust = cfun->machine->frame.final_adjust;
+ poly_int64 initial_adjust = frame.initial_adjust;
+ poly_int64 sve_callee_adjust = frame.sve_callee_adjust;
+ poly_int64 final_adjust = frame.final_adjust;
if (known_eq (frame_size, 0))
{
@@ -10026,17 +10029,18 @@ aarch64_epilogue_uses (int regno)
void
aarch64_expand_prologue (void)
{
- poly_int64 frame_size = cfun->machine->frame.frame_size;
- poly_int64 initial_adjust = cfun->machine->frame.initial_adjust;
- HOST_WIDE_INT callee_adjust = cfun->machine->frame.callee_adjust;
- poly_int64 final_adjust = cfun->machine->frame.final_adjust;
- poly_int64 callee_offset = cfun->machine->frame.callee_offset;
- poly_int64 sve_callee_adjust = cfun->machine->frame.sve_callee_adjust;
+ aarch64_frame &frame = cfun->machine->frame;
+ poly_int64 frame_size = frame.frame_size;
+ poly_int64 initial_adjust = frame.initial_adjust;
+ HOST_WIDE_INT callee_adjust = frame.callee_adjust;
+ poly_int64 final_adjust = frame.final_adjust;
+ poly_int64 callee_offset = frame.callee_offset;
+ poly_int64 sve_callee_adjust = frame.sve_callee_adjust;
poly_int64 below_hard_fp_saved_regs_size
- = cfun->machine->frame.below_hard_fp_saved_regs_size;
- unsigned reg1 = cfun->machine->frame.wb_push_candidate1;
- unsigned reg2 = cfun->machine->frame.wb_push_candidate2;
- bool emit_frame_chain = cfun->machine->frame.emit_frame_chain;
+ = frame.below_hard_fp_saved_regs_size;
+ unsigned reg1 = frame.wb_push_candidate1;
+ unsigned reg2 = frame.wb_push_candidate2;
+ bool emit_frame_chain = frame.emit_frame_chain;
rtx_insn *insn;
if (flag_stack_clash_protection && known_eq (callee_adjust, 0))
@@ -10067,7 +10071,7 @@ aarch64_expand_prologue (void)
}
/* Push return address to shadow call stack. */
- if (cfun->machine->frame.is_scs_enabled)
+ if (frame.is_scs_enabled)
emit_insn (gen_scs_push ());
if (flag_stack_usage_info)
@@ -10106,7 +10110,7 @@ aarch64_expand_prologue (void)
/* The offset of the frame chain record (if any) from the current SP. */
poly_int64 chain_offset = (initial_adjust + callee_adjust
- - cfun->machine->frame.hard_fp_offset);
+ - frame.hard_fp_offset);
gcc_assert (known_ge (chain_offset, 0));
/* The offset of the bottom of the save area from the current SP. */
@@ -10209,16 +10213,17 @@ aarch64_use_return_insn_p (void)
void
aarch64_expand_epilogue (bool for_sibcall)
{
- poly_int64 initial_adjust = cfun->machine->frame.initial_adjust;
- HOST_WIDE_INT callee_adjust = cfun->machine->frame.callee_adjust;
- poly_int64 final_adjust = cfun->machine->frame.final_adjust;
- poly_int64 callee_offset = cfun->machine->frame.callee_offset;
- poly_int64 sve_callee_adjust = cfun->machine->frame.sve_callee_adjust;
+ aarch64_frame &frame = cfun->machine->frame;
+ poly_int64 initial_adjust = frame.initial_adjust;
+ HOST_WIDE_INT callee_adjust = frame.callee_adjust;
+ poly_int64 final_adjust = frame.final_adjust;
+ poly_int64 callee_offset = frame.callee_offset;
+ poly_int64 sve_callee_adjust = frame.sve_callee_adjust;
poly_int64 below_hard_fp_saved_regs_size
- = cfun->machine->frame.below_hard_fp_saved_regs_size;
- unsigned reg1 = cfun->machine->frame.wb_pop_candidate1;
- unsigned reg2 = cfun->machine->frame.wb_pop_candidate2;
- unsigned int last_gpr = (cfun->machine->frame.is_scs_enabled
+ = frame.below_hard_fp_saved_regs_size;
+ unsigned reg1 = frame.wb_pop_candidate1;
+ unsigned reg2 = frame.wb_pop_candidate2;
+ unsigned int last_gpr = (frame.is_scs_enabled
? R29_REGNUM : R30_REGNUM);
rtx cfi_ops = NULL;
rtx_insn *insn;
@@ -10252,7 +10257,7 @@ aarch64_expand_epilogue (bool for_sibcall)
/* We need to add memory barrier to prevent read from deallocated stack. */
bool need_barrier_p
= maybe_ne (get_frame_size ()
- + cfun->machine->frame.saved_varargs_size, 0);
+ + frame.saved_varargs_size, 0);
/* Emit a barrier to prevent loads from a deallocated stack. */
if (maybe_gt (final_adjust, crtl->outgoing_args_size)
@@ -10333,7 +10338,7 @@ aarch64_expand_epilogue (bool for_sibcall)
}
/* Pop return address from shadow call stack. */
- if (cfun->machine->frame.is_scs_enabled)
+ if (frame.is_scs_enabled)
{
machine_mode mode = aarch64_reg_save_mode (R30_REGNUM);
rtx reg = gen_rtx_REG (mode, R30_REGNUM);
@@ -12840,24 +12845,24 @@ aarch64_can_eliminate (const int from ATTRIBUTE_UNUSED, const int to)
poly_int64
aarch64_initial_elimination_offset (unsigned from, unsigned to)
{
+ aarch64_frame &frame = cfun->machine->frame;
+
if (to == HARD_FRAME_POINTER_REGNUM)
{
if (from == ARG_POINTER_REGNUM)
- return cfun->machine->frame.hard_fp_offset;
+ return frame.hard_fp_offset;
if (from == FRAME_POINTER_REGNUM)
- return cfun->machine->frame.hard_fp_offset
- - cfun->machine->frame.locals_offset;
+ return frame.hard_fp_offset - frame.locals_offset;
}
if (to == STACK_POINTER_REGNUM)
{
if (from == FRAME_POINTER_REGNUM)
- return cfun->machine->frame.frame_size
- - cfun->machine->frame.locals_offset;
+ return frame.frame_size - frame.locals_offset;
}
- return cfun->machine->frame.frame_size;
+ return frame.frame_size;
}
--
2.25.1
next prev parent reply other threads:[~2023-09-12 15:25 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-09-12 15:25 [PATCH 00/19] aarch64: Fix -fstack-protector issue Richard Sandiford
2023-09-12 15:25 ` Richard Sandiford [this message]
2023-09-12 15:25 ` [PATCH 02/19] aarch64: Avoid a use of callee_offset Richard Sandiford
2023-09-12 15:25 ` [PATCH 03/19] aarch64: Explicitly handle frames with no saved registers Richard Sandiford
2023-09-12 15:25 ` [PATCH 04/19] aarch64: Add bytes_below_saved_regs to frame info Richard Sandiford
2023-09-12 15:25 ` [PATCH 05/19] aarch64: Add bytes_below_hard_fp " Richard Sandiford
2023-09-12 15:25 ` [PATCH 06/19] aarch64: Tweak aarch64_save/restore_callee_saves Richard Sandiford
2023-09-12 15:25 ` [PATCH 07/19] aarch64: Only calculate chain_offset if there is a chain Richard Sandiford
2023-09-12 15:25 ` [PATCH 08/19] aarch64: Rename locals_offset to bytes_above_locals Richard Sandiford
2023-09-12 15:25 ` [PATCH 09/19] aarch64: Rename hard_fp_offset to bytes_above_hard_fp Richard Sandiford
2023-09-12 15:25 ` [PATCH 10/19] aarch64: Tweak frame_size comment Richard Sandiford
2023-09-12 15:25 ` [PATCH 11/19] aarch64: Measure reg_offset from the bottom of the frame Richard Sandiford
2023-09-12 15:25 ` [PATCH 12/19] aarch64: Simplify top of frame allocation Richard Sandiford
2023-09-12 15:25 ` [PATCH 13/19] aarch64: Minor initial adjustment tweak Richard Sandiford
2023-09-12 15:25 ` [PATCH 14/19] aarch64: Tweak stack clash boundary condition Richard Sandiford
2023-09-12 15:25 ` [PATCH 15/19] aarch64: Put LR save probe in first 16 bytes Richard Sandiford
2023-09-12 15:25 ` [PATCH 16/19] aarch64: Simplify probe of final frame allocation Richard Sandiford
2023-09-12 15:25 ` [PATCH 17/19] aarch64: Explicitly record probe registers in frame info Richard Sandiford
2023-09-12 15:25 ` [PATCH 18/19] aarch64: Remove below_hard_fp_saved_regs_size Richard Sandiford
2023-09-12 15:25 ` [PATCH 19/19] aarch64: Make stack smash canary protect saved registers Richard Sandiford
2023-09-12 16:45 ` [PATCH 00/19] aarch64: Fix -fstack-protector issue Siddhesh Poyarekar
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20230912152529.3322336-2-richard.sandiford@arm.com \
--to=richard.sandiford@arm.com \
--cc=gcc-patches@gcc.gnu.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for read-only IMAP folder(s) and NNTP newsgroup(s).