...it's really a general RTL predicate, rather than something that depends
on the DF state.  Thanks to Segher for the suggestion.

2017-08-30  Richard Sandiford  <richard.sandiford@linaro.org>

gcc/
	* df.h (df_read_modify_subreg_p): Remove in favor of...
	* rtl.h (read_modify_subreg_p): ...this new function.  Take a
	const_rtx instead of an rtx.
	* cprop.c (local_cprop_find_used_regs): Update accordingly.
	* df-problems.c (df_word_lr_mark_ref): Likewise.
	* ira-lives.c (mark_pseudo_reg_live): Likewise.
	(mark_pseudo_reg_dead): Likewise.
	(mark_ref_dead): Likewise.
	* reginfo.c (init_subregs_of_mode): Likewise.
	* sched-deps.c (sched_analyze_1): Likewise.
	* df-scan.c (df_def_record_1): Likewise.
	(df_uses_record): Likewise.
	(df_read_modify_subreg_p): Remove in favor of...
	* rtlanal.c (read_modify_subreg_p): ...this new function.  Take a
	const_rtx instead of an rtx.

From-SVN: r251537