It is possible when using out-of-line register saves or store multiple to save some registers unnecessarily, for example one reg in the block saved might be unused. We don't need to emit eh_frame info for those registers as that just bloats the eh_frame info, and also can result in an ICE when shrink-wrap gives multiple paths through the function saving different sets of registers. All the join points need to have identical eh_frame register save state.
This patch reverts the previous fix for PR80939 "Use SAVE_MULTIPLE only if we restore what it saves (PR80938)" and instead fixes the PR by correcting the eh_frame info. The change to rs6000_savres_strategy is an optimization, but note that it hides the underlying problem in the PR testcase. Bootstrapped and regression tested powerpc64-linux (-m32 too) and powerpc64le-linux, with https://gcc.gnu.org/ml/gcc-patches/2017-08/msg00774.html and https://gcc.gnu.org/ml/gcc-patches/2017-08/msg00775.html applied. OK to apply? PR target/80938 * config/rs6000/rs6000.c (rs6000_savres_strategy): Revert 2017-08-09. Don't use store multiple if only one reg needs saving. (rs6000_frame_related): Don't emit eh_frame for regs that don't need saving. (rs6000_emit_epilogue): Likewise. diff --git a/gcc/config/rs6000/rs6000.c b/gcc/config/rs6000/rs6000.c index 2070648..abc55bd 100644 --- a/gcc/config/rs6000/rs6000.c +++ b/gcc/config/rs6000/rs6000.c @@ -24432,20 +24432,37 @@ rs6000_savres_strategy (rs6000_stack_t *info, && flag_shrink_wrap_separate && optimize_function_for_speed_p (cfun))) { - /* Prefer store multiple for saves over out-of-line routines, - since the store-multiple instruction will always be smaller. */ - strategy |= SAVE_INLINE_GPRS | SAVE_MULTIPLE; - - /* The situation is more complicated with load multiple. We'd - prefer to use the out-of-line routines for restores, since the - "exit" out-of-line routines can handle the restore of LR and the - frame teardown. However if doesn't make sense to use the - out-of-line routine if that is the only reason we'd need to save - LR, and we can't use the "exit" out-of-line gpr restore if we - have saved some fprs; In those cases it is advantageous to use - load multiple when available. */ - if (info->first_fp_reg_save != 64 || !lr_save_p) - strategy |= REST_INLINE_GPRS | REST_MULTIPLE; + int count; + + for (count = 0, i = info->first_gp_reg_save; i < 32; i++) + if (save_reg_p (i)) + count += 1; + + if (count <= 1) + /* Don't use store multiple if only one reg needs to be + saved. This can occur for example when the ABI_V4 pic reg + (r30) needs to be saved to make calls, but r31 is not + used. */ + strategy |= SAVE_INLINE_GPRS | REST_INLINE_GPRS; + else + { + /* Prefer store multiple for saves over out-of-line + routines, since the store-multiple instruction will + always be smaller. */ + strategy |= SAVE_INLINE_GPRS | SAVE_MULTIPLE; + + /* The situation is more complicated with load multiple. + We'd prefer to use the out-of-line routines for restores, + since the "exit" out-of-line routines can handle the + restore of LR and the frame teardown. However if doesn't + make sense to use the out-of-line routine if that is the + only reason we'd need to save LR, and we can't use the + "exit" out-of-line gpr restore if we have saved some + fprs; In those cases it is advantageous to use load + multiple when available. */ + if (info->first_fp_reg_save != 64 || !lr_save_p) + strategy |= REST_INLINE_GPRS | REST_MULTIPLE; + } } /* Using the "exit" out-of-line routine does not improve code size @@ -24454,21 +24471,6 @@ rs6000_savres_strategy (rs6000_stack_t *info, else if (!lr_save_p && info->first_gp_reg_save > 29) strategy |= SAVE_INLINE_GPRS | REST_INLINE_GPRS; - /* We can only use save multiple if we need to save all the registers from - first_gp_reg_save. Otherwise, the CFI gets messed up (we save some - register we do not restore). */ - if (strategy & SAVE_MULTIPLE) - { - int i; - - for (i = info->first_gp_reg_save; i < 32; i++) - if (fixed_reg_p (i) || !save_reg_p (i)) - { - strategy &= ~SAVE_MULTIPLE; - break; - } - } - /* Don't ever restore fixed regs. */ if ((strategy & (REST_INLINE_GPRS | REST_MULTIPLE)) != REST_INLINE_GPRS) for (i = info->first_gp_reg_save; i < 32; i++) @@ -25681,9 +25683,15 @@ rs6000_frame_related (rtx_insn *insn, rtx reg, HOST_WIDE_INT val, register save functions, or store multiple, then omit eh_frame info for any user-defined global regs. If eh_frame info is supplied, frame unwinding will - restore a user reg. */ + restore a user reg. Also omit eh_frame info for any + reg we don't need to save, as that bloats eh_frame + and can cause problems with shrink wrapping. Saves + of r0 are actually saving LR, so don't omit those. */ if (!REG_P (SET_SRC (set)) - || !fixed_reg_p (REGNO (SET_SRC (set)))) + || REGNO (SET_SRC (set)) == 0 + || REGNO (SET_SRC (set)) == CR2_REGNO + || (!fixed_reg_p (REGNO (SET_SRC (set))) + && save_reg_p (REGNO (SET_SRC (set))))) RTX_FRAME_RELATED_P (set) = 1; } RTX_FRAME_RELATED_P (insn) = 1; @@ -25720,9 +25728,13 @@ rs6000_frame_related (rtx_insn *insn, rtx reg, HOST_WIDE_INT val, set = simplify_replace_rtx (set, reg2, repl2); XVECEXP (pat, 0, i) = set; - /* Omit eh_frame info for any user-defined global regs. */ + /* Omit eh_frame info for any user-defined global regs or + regs that don't need to be saved. */ if (!REG_P (SET_SRC (set)) - || !fixed_reg_p (REGNO (SET_SRC (set)))) + || REGNO (SET_SRC (set)) == 0 + || REGNO (SET_SRC (set)) == CR2_REGNO + || (!fixed_reg_p (REGNO (SET_SRC (set))) + && save_reg_p (REGNO (SET_SRC (set))))) RTX_FRAME_RELATED_P (set) = 1; } } @@ -27945,7 +27957,8 @@ rs6000_emit_epilogue (int sibcall) RTVEC_ELT (p, j++) = gen_frame_load (reg, frame_reg_rtx, info->gp_save_offset + reg_size * i); - if (flag_shrink_wrap) + if (flag_shrink_wrap + && save_reg_p (info->first_gp_reg_save + i)) cfa_restores = alloc_reg_note (REG_CFA_RESTORE, reg, cfa_restores); } for (i = 0; info->first_altivec_reg_save + i <= LAST_ALTIVEC_REGNO; i++) @@ -27954,7 +27967,8 @@ rs6000_emit_epilogue (int sibcall) RTVEC_ELT (p, j++) = gen_frame_load (reg, frame_reg_rtx, info->altivec_save_offset + 16 * i); - if (flag_shrink_wrap) + if (flag_shrink_wrap + && save_reg_p (info->first_altivec_reg_save + i)) cfa_restores = alloc_reg_note (REG_CFA_RESTORE, reg, cfa_restores); } for (i = 0; info->first_fp_reg_save + i <= 63; i++) @@ -27964,7 +27978,8 @@ rs6000_emit_epilogue (int sibcall) info->first_fp_reg_save + i); RTVEC_ELT (p, j++) = gen_frame_load (reg, frame_reg_rtx, info->fp_save_offset + 8 * i); - if (flag_shrink_wrap) + if (flag_shrink_wrap + && save_reg_p (info->first_fp_reg_save + i)) cfa_restores = alloc_reg_note (REG_CFA_RESTORE, reg, cfa_restores); } RTVEC_ELT (p, j++) @@ -28085,7 +28100,8 @@ rs6000_emit_epilogue (int sibcall) && (flag_shrink_wrap || (offset_below_red_zone_p (info->altivec_save_offset - + 16 * (i - info->first_altivec_reg_save))))) + + 16 * (i - info->first_altivec_reg_save)))) + && save_reg_p (i)) { rtx reg = gen_rtx_REG (V4SImode, i); cfa_restores = alloc_reg_note (REG_CFA_RESTORE, reg, cfa_restores); @@ -28297,7 +28313,8 @@ rs6000_emit_epilogue (int sibcall) for (i = info->first_altivec_reg_save; i <= LAST_ALTIVEC_REGNO; ++i) if (((strategy & REST_INLINE_VRS) == 0 || (info->vrsave_mask & ALTIVEC_REG_BIT (i)) != 0) - && (DEFAULT_ABI == ABI_V4 || flag_shrink_wrap)) + && (DEFAULT_ABI == ABI_V4 || flag_shrink_wrap) + && save_reg_p (i)) { rtx reg = gen_rtx_REG (V4SImode, i); cfa_restores = alloc_reg_note (REG_CFA_RESTORE, reg, cfa_restores); @@ -28643,7 +28660,8 @@ rs6000_emit_epilogue (int sibcall) RTVEC_ELT (p, elt++) = gen_frame_load (reg, sp_reg_rtx, info->fp_save_offset + 8 * i); - if (flag_shrink_wrap) + if (flag_shrink_wrap + && save_reg_p (info->first_fp_reg_save + i)) cfa_restores = alloc_reg_note (REG_CFA_RESTORE, reg, cfa_restores); } -- Alan Modra Australia Development Lab, IBM