diff options
Diffstat (limited to '0183-Backport-SME-aarch64-Avoid-a-use-of-callee_offset.patch')
| -rw-r--r-- | 0183-Backport-SME-aarch64-Avoid-a-use-of-callee_offset.patch | 103 |
1 files changed, 103 insertions, 0 deletions
diff --git a/0183-Backport-SME-aarch64-Avoid-a-use-of-callee_offset.patch b/0183-Backport-SME-aarch64-Avoid-a-use-of-callee_offset.patch new file mode 100644 index 0000000..7a2c9e2 --- /dev/null +++ b/0183-Backport-SME-aarch64-Avoid-a-use-of-callee_offset.patch @@ -0,0 +1,103 @@ +From 54a6e52207703a8643fc406175377105f887ebef Mon Sep 17 00:00:00 2001 +From: Richard Sandiford <richard.sandiford@arm.com> +Date: Tue, 12 Sep 2023 16:05:04 +0100 +Subject: [PATCH] [Backport][SME] aarch64: Avoid a use of callee_offset + +Reference: https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=f9ab771fa8cd747f34786c6f33deea32c2eb828b + +When we emit the frame chain, i.e. when we reach Here in this statement +of aarch64_expand_prologue: + + if (emit_frame_chain) + { + // Here + ... + } + +the stack is in one of two states: + +- We've allocated up to the frame chain, but no more. + +- We've allocated the whole frame, and the frame chain is within easy + reach of the new SP. + +The offset of the frame chain from the current SP is available +in aarch64_frame as callee_offset. It is also available as the +chain_offset local variable, where the latter is calculated from other +data. (However, chain_offset is not always equal to callee_offset when +!emit_frame_chain, so chain_offset isn't redundant.) + +In c600df9a4060da3c6121ff4d0b93f179eafd69d1 I switched to using +chain_offset for the initialisation of the hard frame pointer: + + aarch64_add_offset (Pmode, hard_frame_pointer_rtx, +- stack_pointer_rtx, callee_offset, ++ stack_pointer_rtx, chain_offset, + tmp1_rtx, tmp0_rtx, frame_pointer_needed); + +But the later REG_CFA_ADJUST_CFA handling still used callee_offset. + +I think the difference is harmless, but it's more logical for the +CFA note to be in sync, and it's more convenient for later patches +if it uses chain_offset. + +gcc/ + * config/aarch64/aarch64.cc (aarch64_expand_prologue): Use + chain_offset rather than callee_offset. +--- + gcc/config/aarch64/aarch64.cc | 4 +--- + 1 file changed, 1 insertion(+), 3 deletions(-) + +diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc +index b7da1d0be..fbd7a079a 100644 +--- a/gcc/config/aarch64/aarch64.cc ++++ b/gcc/config/aarch64/aarch64.cc +@@ -10263,21 +10263,20 @@ aarch64_epilogue_uses (int regno) + current FP is also set up if it is in use. */ + + void + aarch64_expand_prologue (void) + { + 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 + = 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)) + { +@@ -10376,22 +10375,21 @@ aarch64_expand_prologue (void) + the CFA based on the frame pointer. We therefore need new + DW_CFA_expressions to re-express the save slots with addresses + based on the frame pointer. */ + rtx_insn *insn = get_last_insn (); + gcc_assert (RTX_FRAME_RELATED_P (insn)); + + /* Add an explicit CFA definition if this was previously + implicit. */ + if (!find_reg_note (insn, REG_CFA_ADJUST_CFA, NULL_RTX)) + { +- rtx src = plus_constant (Pmode, stack_pointer_rtx, +- callee_offset); ++ rtx src = plus_constant (Pmode, stack_pointer_rtx, chain_offset); + add_reg_note (insn, REG_CFA_ADJUST_CFA, + gen_rtx_SET (hard_frame_pointer_rtx, src)); + } + + /* Change the save slot expressions for the registers that + we've already saved. */ + aarch64_add_cfa_expression (insn, regno_reg_rtx[reg2], + hard_frame_pointer_rtx, UNITS_PER_WORD); + aarch64_add_cfa_expression (insn, regno_reg_rtx[reg1], + hard_frame_pointer_rtx, 0); +-- +2.38.1.windows.1 + |