Iain Sandoe <[email protected]> writes:
> This introduces threee customisation points into the function body scans
> code. This allows targets to consume regexes that are written for ABIs and
> asm syntax that is reasonably compatibile with that used by the target.
>
> The initial use-case here is to map from regexes specified in terms of
> ELF syntax and Linux ABIs, but to be consumed by Darwin ABI and mach-o
> binary format.
>
> gcc/testsuite/ChangeLog:
>
> * lib/scanasm.exp (target_regex_skip_line,
> target_regex_verbatim_line, target_substitute_func_regex): New.
> (check-function-bodies): use the customisation points.
> (configure_check-function-bodies): Populate the new customisation
> points for Darwin/Mach-O.
> * lib/target-supports.exp
> (add_options_for_check_function_bodies): Add Darwin criteria.
>
> Signed-off-by: Iain Sandoe <[email protected]>
> ---
> gcc/testsuite/lib/scanasm.exp | 107 ++++++++++++++++++++++++--
> gcc/testsuite/lib/target-supports.exp | 4 +
> 2 files changed, 103 insertions(+), 8 deletions(-)
>
> diff --git a/gcc/testsuite/lib/scanasm.exp b/gcc/testsuite/lib/scanasm.exp
> index 08dbf1a8118..9e7a5896475 100644
> --- a/gcc/testsuite/lib/scanasm.exp
> +++ b/gcc/testsuite/lib/scanasm.exp
> @@ -921,7 +921,7 @@ proc configure_check-function-bodies { config } {
> } elseif { [istarget *-*-darwin*] } {
> set up_config(start) {
> {^_([a-zA-Z_]\S*):$}
> - {^LFB[0-9]+:}
> + {^LFS?B[0-9]+:$}
> }
> } else {
> set up_config(start) {{^([a-zA-Z_]\S*):$}}
> @@ -931,7 +931,7 @@ proc configure_check-function-bodies { config } {
> if { [istarget nvptx*-*-*] } {
> set up_config(end) {^\}$}
> } elseif { [istarget *-*-darwin*] } {
> - set up_config(end) {^LFE[0-9]+}
> + set up_config(end) {^LFE[0-9]+:$}
> } elseif { [istarget *-*-mingw32] } {
> set up_config(end) {seh_endproc}
> } else {
> @@ -944,7 +944,7 @@ proc configure_check-function-bodies { config } {
> # example).
> set up_config(fluff) {^\s*(?://)}
> } elseif { [istarget *-*-darwin*] } {
> - set up_config(fluff) {^\s*(?:\.|//|@)|^L[0-9ABCESV]}
> + set up_config(fluff) {^\s*(?:\.|//|@|#)|^L[ABCESV]}
> } elseif { [istarget s390*-*-*] } {
> # Additionally to the defaults skip lines beginning with a # resulting
> # from inline asm.
> @@ -967,6 +967,92 @@ proc configure_check-function-bodies { config } {
> } else {
> set up_config(line_prefix) {\t}
> }
> +
> + # Set up regex lines that should be skipped for a given object format
> + set up_config(skip_regex_cases) ""
> + if { [istarget *-*-darwin*] } {
> + # Darwin already matches .LF* as part of start/end.
> + # Currently, .cfi_xxx instructions are not used.
> + set up_config(skip_regex_cases) {
> + {^\.LF.*$}
> + {^.*\.cfi_.*$}
> + }
> + }
> +
> + # Set up regex lines that should be copied verbatim for a given object
> + # format
> + if { [istarget *-*-darwin*] } {
> + # Lines starting with a label, for Darwin we accept ELF local labels
> + # (starting with .L) and Mach-O (starting with L). We also accept
> + # numeric assembler labels.
> + set up_config(verbatim_regex_cases) {
> + {^\.?L\[?[0-9].*:$}
> + {^[0-9]+:.*$}
> + }
> + } else {
> + # Lines starting with a local code label ".L" (which are usually the
> + # only entries on a line - or numeric assembler labels, which are
> + # often followed by some instruction.
> + set up_config(verbatim_regex_cases) {
> + {^\.L.*$}
> + {^[0-9]+:.*$}
The comment led me to expect :$ for the .L case. Is not having the
: deliberate? .*$ might as well be dropped, as in the original regexp.
This is admittedly partly pre-existing, but: here and in the
substitutions below, I think it'd be worth allowing an optional "\"
before the ".", to handle cases where the check-function-bodies regexp
itself escapes the ".". I suppose that would make it:
(?:\\)?\.
(untested).
> + }
> + }
> +
> + set up_config(regex_substitutions) ""
> + if { [istarget *-*-darwin*] } {
> + # Setup substitution pairs for body regexes
> + # the first entry is what should be matched, the second is what
> should
> + # replace it.
> + set up_config(regex_substitutions) {
> + { {\.LC} {[lL]C} }
> + { {\.L} "L" }
> + }
> + }
> +
> +}
> +
> +# Sometimes the function match regex might include directives that are not
> +# used by a given binary format. Allow these to be skipped.
> +proc target_regex_skip_line { config line } {
> + upvar $config up_config
> + set item 0
> + while { $item < [llength $up_config(skip_regex_cases)] } {
> + if { [regexp [lindex $up_config(skip_regex_cases) $item] $line] } {
> + return 1
> + }
> + incr item
> + }
> + return 0
This loop would be simpler with foreach. Same for the functions below.
LGTM otherwise.
Thanks,
Richard
> +}
> +
> +# Some regex lines (mostly ones starting with a label) should be copied
> +# verbatim (i.e. without prepending config(line_prefix)).
> +
> +proc target_regex_verbatim_line { config line } {
> + upvar $config up_config
> + set item 0
> + while { $item < [llength $up_config(verbatim_regex_cases)] } {
> + if { [regexp [lindex $up_config(verbatim_regex_cases) $item] $line]
> } {
> + return 1
> + }
> + incr item
> + }
> + return 0
> +}
> +
> +# Apply global substitutions to the function body regex as needed by the
> +# target ABI / assembler syntax.
> +
> +proc target_substitute_func_regex { config func_regex } {
> + upvar $config up_config
> + upvar $func_regex up_func_regex
> + set item 0
> + while { $item < [llength $up_config(regex_substitutions)] } {
> + set subs [lindex $up_config(regex_substitutions) $item]
> + regsub -all [lindex $subs 0] $up_func_regex [lindex $subs 1]
> up_func_regex
> + incr item
> + }
> }
>
> # Per CONFIG, read assembly file FILENAME and store a mapping from function
> @@ -1002,7 +1088,7 @@ proc parse_function_bodies { config filename result } {
> set function_name $maybe_function_name
> set in_function 1
> } elseif { [regexp $up_config(end) $line] } {
> - verbose "parse_function_bodies: $function_name:\n$function_body"
> + verbose "parse_function_bodies: found end marker for
> $function_name:\n$function_body"
> set up_result($function_name) $function_body
> set in_function 0
> } elseif { $up_config(matched) ne "" \
> @@ -1188,14 +1274,19 @@ proc check-function-bodies { args } {
> append function_regexp ")"
> } elseif { [string equal $line "..."] } {
> append function_regexp ".*"
> - } elseif { [regexp {^\.L} $line] } {
> - append function_regexp $line "\n"
> - } elseif { [regexp {^[0-9]+:} $line] } {
> - append function_regexp $line "\n"
> + } elseif { [target_regex_skip_line config $line] } {
> + # Drop this line.
> + continue
> + } elseif { [target_regex_verbatim_line config $line] } {
> + # Copy this through.
> + append function_regexp $line "\n"
> } else {
> + # Copy but with a prefix (typically \t).
> append function_regexp $config(line_prefix) $line "\n"
> }
> } elseif { [string equal -length $terminator_len $line $terminator] } {
> + # Do any global substitutions the target ABI/asm syntax needs.
> + target_substitute_func_regex config function_regexp
> if { ![string equal $selector "N"] } {
> if { $xfail_all || [string equal $selector "F"] } {
> setup_xfail "*-*-*"
> diff --git a/gcc/testsuite/lib/target-supports.exp
> b/gcc/testsuite/lib/target-supports.exp
> index cba178b937f..e212cfa9165 100644
> --- a/gcc/testsuite/lib/target-supports.exp
> +++ b/gcc/testsuite/lib/target-supports.exp
> @@ -982,6 +982,10 @@ proc add_options_for_check_function_bodies { flags } {
> # off on Solaris/x86 with as and ld. Similarly it also expects
> # the .LFB/.LFE labels, which aren't emitted for 32-bit.
> return "-fdwarf2-cfi-asm -fasynchronous-unwind-tables $flags "
> + } elseif { [istarget i?86-*-darwin*] || [istarget x86_64-*-darwin*] } {
> + # Darwin does not currently use .cfi_ instructions and also requires
> + # unwind tables to be forced on for 32bit.
> + return "-fno-dwarf2-cfi-asm -fasynchronous-unwind-tables $flags "
> }
> return $flags
> }
