diff options
Diffstat (limited to '0193-Backport-SME-aarch64-Measure-reg_offset-from-the-bot.patch')
| -rw-r--r-- | 0193-Backport-SME-aarch64-Measure-reg_offset-from-the-bot.patch | 198 |
1 files changed, 198 insertions, 0 deletions
diff --git a/0193-Backport-SME-aarch64-Measure-reg_offset-from-the-bot.patch b/0193-Backport-SME-aarch64-Measure-reg_offset-from-the-bot.patch new file mode 100644 index 0000000..c036731 --- /dev/null +++ b/0193-Backport-SME-aarch64-Measure-reg_offset-from-the-bot.patch @@ -0,0 +1,198 @@ +From 3b10711c6a5610bf8e2287b9491557268ee148da Mon Sep 17 00:00:00 2001 +From: Richard Sandiford <richard.sandiford@arm.com> +Date: Tue, 12 Sep 2023 16:05:09 +0100 +Subject: [PATCH 094/157] [Backport][SME] aarch64: Measure reg_offset from the + bottom of the frame + +Reference: https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=67a36b6f5d6be11d280081b461e72910aca2fc54 + +reg_offset was measured from the bottom of the saved register area. +This made perfect sense with the original layout, since the bottom +of the saved register area was also the hard frame pointer address. +It became slightly less obvious with SVE, since we save SVE +registers below the hard frame pointer, but it still made sense. + +However, if we want to allow different frame layouts, it's more +convenient and obvious to measure reg_offset from the bottom of +the frame. After previous patches, it's also a slight simplification +in its own right. + +gcc/ + * config/aarch64/aarch64.h (aarch64_frame): Add comment above + reg_offset. + * config/aarch64/aarch64.cc (aarch64_layout_frame): Walk offsets + from the bottom of the frame, rather than the bottom of the saved + register area. Measure reg_offset from the bottom of the frame + rather than the bottom of the saved register area. + (aarch64_save_callee_saves): Update accordingly. + (aarch64_restore_callee_saves): Likewise. + (aarch64_get_separate_components): Likewise. + (aarch64_process_components): Likewise. +--- + gcc/config/aarch64/aarch64.cc | 53 ++++++++++++++++------------------- + gcc/config/aarch64/aarch64.h | 3 ++ + 2 files changed, 27 insertions(+), 29 deletions(-) + +diff --git a/gcc/config/aarch64/aarch64.cc b/gcc/config/aarch64/aarch64.cc +index 67199a026..df8a83b04 100644 +--- a/gcc/config/aarch64/aarch64.cc ++++ b/gcc/config/aarch64/aarch64.cc +@@ -8739,7 +8739,6 @@ aarch64_needs_frame_chain (void) + static void + aarch64_layout_frame (void) + { +- poly_int64 offset = 0; + int regno, last_fp_reg = INVALID_REGNUM; + machine_mode vector_save_mode = aarch64_reg_save_mode (V8_REGNUM); + poly_int64 vector_save_size = GET_MODE_SIZE (vector_save_mode); +@@ -8817,7 +8816,9 @@ aarch64_layout_frame (void) + gcc_assert (crtl->is_leaf + || maybe_ne (frame.reg_offset[R30_REGNUM], SLOT_NOT_REQUIRED)); + +- frame.bytes_below_saved_regs = crtl->outgoing_args_size; ++ poly_int64 offset = crtl->outgoing_args_size; ++ gcc_assert (multiple_p (offset, STACK_BOUNDARY / BITS_PER_UNIT)); ++ frame.bytes_below_saved_regs = offset; + + /* Now assign stack slots for the registers. Start with the predicate + registers, since predicate LDR and STR have a relatively small +@@ -8829,7 +8830,8 @@ aarch64_layout_frame (void) + offset += BYTES_PER_SVE_PRED; + } + +- if (maybe_ne (offset, 0)) ++ poly_int64 saved_prs_size = offset - frame.bytes_below_saved_regs; ++ if (maybe_ne (saved_prs_size, 0)) + { + /* If we have any vector registers to save above the predicate registers, + the offset of the vector register save slots need to be a multiple +@@ -8847,10 +8849,10 @@ aarch64_layout_frame (void) + offset = aligned_upper_bound (offset, STACK_BOUNDARY / BITS_PER_UNIT); + else + { +- if (known_le (offset, vector_save_size)) +- offset = vector_save_size; +- else if (known_le (offset, vector_save_size * 2)) +- offset = vector_save_size * 2; ++ if (known_le (saved_prs_size, vector_save_size)) ++ offset = frame.bytes_below_saved_regs + vector_save_size; ++ else if (known_le (saved_prs_size, vector_save_size * 2)) ++ offset = frame.bytes_below_saved_regs + vector_save_size * 2; + else + gcc_unreachable (); + } +@@ -8867,9 +8869,10 @@ aarch64_layout_frame (void) + + /* OFFSET is now the offset of the hard frame pointer from the bottom + of the callee save area. */ +- bool saves_below_hard_fp_p = maybe_ne (offset, 0); +- frame.below_hard_fp_saved_regs_size = offset; +- frame.bytes_below_hard_fp = offset + frame.bytes_below_saved_regs; ++ frame.below_hard_fp_saved_regs_size = offset - frame.bytes_below_saved_regs; ++ bool saves_below_hard_fp_p ++ = maybe_ne (frame.below_hard_fp_saved_regs_size, 0); ++ frame.bytes_below_hard_fp = offset; + if (frame.emit_frame_chain) + { + /* FP and LR are placed in the linkage record. */ +@@ -8920,9 +8923,10 @@ aarch64_layout_frame (void) + + offset = aligned_upper_bound (offset, STACK_BOUNDARY / BITS_PER_UNIT); + +- frame.saved_regs_size = offset; ++ frame.saved_regs_size = offset - frame.bytes_below_saved_regs; + +- poly_int64 varargs_and_saved_regs_size = offset + frame.saved_varargs_size; ++ poly_int64 varargs_and_saved_regs_size ++ = frame.saved_regs_size + frame.saved_varargs_size; + + poly_int64 saved_regs_and_above + = aligned_upper_bound (varargs_and_saved_regs_size +@@ -9390,9 +9394,7 @@ aarch64_save_callee_saves (poly_int64 bytes_below_sp, + + machine_mode mode = aarch64_reg_save_mode (regno); + reg = gen_rtx_REG (mode, regno); +- offset = (frame.reg_offset[regno] +- + frame.bytes_below_saved_regs +- - bytes_below_sp); ++ offset = frame.reg_offset[regno] - bytes_below_sp; + rtx base_rtx = stack_pointer_rtx; + poly_int64 sp_offset = offset; + +@@ -9499,9 +9501,7 @@ aarch64_restore_callee_saves (poly_int64 bytes_below_sp, unsigned start, + + machine_mode mode = aarch64_reg_save_mode (regno); + reg = gen_rtx_REG (mode, regno); +- offset = (frame.reg_offset[regno] +- + frame.bytes_below_saved_regs +- - bytes_below_sp); ++ offset = frame.reg_offset[regno] - bytes_below_sp; + rtx base_rtx = stack_pointer_rtx; + if (mode == VNx2DImode && BYTES_BIG_ENDIAN) + aarch64_adjust_sve_callee_save_base (mode, base_rtx, anchor_reg, +@@ -9640,14 +9640,12 @@ aarch64_get_separate_components (void) + it as a stack probe for -fstack-clash-protection. */ + if (flag_stack_clash_protection + && maybe_ne (frame.below_hard_fp_saved_regs_size, 0) +- && known_eq (offset, 0)) ++ && known_eq (offset, frame.bytes_below_saved_regs)) + continue; + + /* Get the offset relative to the register we'll use. */ + if (frame_pointer_needed) +- offset -= frame.below_hard_fp_saved_regs_size; +- else +- offset += frame.bytes_below_saved_regs; ++ offset -= frame.bytes_below_hard_fp; + + /* Check that we can access the stack slot of the register with one + direct load with no adjustments needed. */ +@@ -9794,9 +9792,7 @@ aarch64_process_components (sbitmap components, bool prologue_p) + rtx reg = gen_rtx_REG (mode, regno); + poly_int64 offset = frame.reg_offset[regno]; + if (frame_pointer_needed) +- offset -= frame.below_hard_fp_saved_regs_size; +- else +- offset += frame.bytes_below_saved_regs; ++ offset -= frame.bytes_below_hard_fp; + + rtx addr = plus_constant (Pmode, ptr_reg, offset); + rtx mem = gen_frame_mem (mode, addr); +@@ -9848,9 +9844,7 @@ 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 -= frame.below_hard_fp_saved_regs_size; +- else +- offset2 += frame.bytes_below_saved_regs; ++ offset2 -= frame.bytes_below_hard_fp; + rtx addr2 = plus_constant (Pmode, ptr_reg, offset2); + rtx mem2 = gen_frame_mem (mode, addr2); + rtx set2 = prologue_p ? gen_rtx_SET (mem2, reg2) +@@ -9976,7 +9970,8 @@ aarch64_allocate_and_probe_stack_space (rtx temp1, rtx temp2, + if (final_adjustment_p + && known_eq (frame.below_hard_fp_saved_regs_size, 0)) + { +- poly_int64 lr_offset = frame.reg_offset[LR_REGNUM]; ++ poly_int64 lr_offset = (frame.reg_offset[LR_REGNUM] ++ - frame.bytes_below_saved_regs); + if (known_ge (lr_offset, 0)) + min_probe_threshold -= lr_offset.to_constant (); + else +diff --git a/gcc/config/aarch64/aarch64.h b/gcc/config/aarch64/aarch64.h +index 39abca051..f340237d0 100644 +--- a/gcc/config/aarch64/aarch64.h ++++ b/gcc/config/aarch64/aarch64.h +@@ -790,6 +790,9 @@ extern enum aarch64_processor aarch64_tune; + #ifdef HAVE_POLY_INT_H + struct GTY (()) aarch64_frame + { ++ /* The offset from the bottom of the static frame (the bottom of the ++ outgoing arguments) of each register save slot, or -2 if no save is ++ needed. */ + poly_int64 reg_offset[LAST_SAVED_REGNUM + 1]; + + /* The number of extra stack bytes taken up by register varargs. +-- +2.33.0 + |