Re: [PATCH 1/2] Use POSIX nm to simplify AIX export_symbols_cmds.

[Michael Haubenwallner]

On 03/20/2016 01:04 AM, David Edelsohn wrote:
> I agree with this in principle, but I'm not convinced that the patch
> itself is correct.

Thanks!

> I also would have split the MS-compatible part of the patch as a
> separate step.  It is not listed in the ChangeLog and just confuses
> the patch.

This is just a reordering of existing code - these lines are removed
below, and the ChangeLog part is "Reorder to allow for platform specific
hooks during transformation of global_symbol_pipe into C source code."

> I don't see that this emits TLS symbols.  Global TLS symbols are not
> in the symcode list.

Isn't the "L" for TLS symbols?

+    symcode='[[BDLTVWZ]]'

But indeed I've failed to identify the symcode of "weak TLS" symbols,
except for "L*" with AIX nm in unspecified mode (nm -l, no -B or -P)
Neither AIX nm nor GNU nm docs explicitly tell about weak TLS symbols.
Is it possible for TLS symbols to be weak at all?

> Global symbol pipe and exclude symbols somehow restricts the symbols
> to the non "dot" symbols?

Yes - but this is what the existing code does as well:
'... && ([substr](\$ 1,1,1) != ".") ..'

> The export_symbols_cmds awk command does not have matching quotes, so
> I don't know what is going on.
> 
> awk '\''{ kw = "" } /^[[VWZ]] / { kw = " weak" } { print $ 3 kw }'\''
> 
> you're starting and ending with '\" which seems odd. why aren't these
> complementary?

The awk argument is passed between ['], as it contains ["].
Escaping [\] the ['] is done outside any other string. Read as:
_LT_TAGVAR(...)=['$NM ... | awk '][\']['{ ... }'][\'][' | sort ...']
Indeed I can add [] here if you like.

Thanks!
/haubi/

> 
> Thanks, David
> 
> On Wed, Mar 2, 2016 at 11:19 AM, Michael Haubenwallner
> <address@hidden> wrote:
>> * m4/libtool.m4 (LT_PATH_NM): Detect POSIX-compatible nm for AIX.  In
>> BSD mode, the AIX nm does not tell whether a symbol is weak, need to use
>> POSIX mode instead.
>> (_LT_CMD_GLOBAL_SYMBOLS): Support POSIX-compatible nm.  Reorder to allow
>> for platform specific hooks during transformation of global_symbol_pipe
>> into C source code.  For AIX, set hook to transform even weak text
>> symbols as text symbols.
>> (_LT_LINKER_SHLIBS): Use global_symbol_pipe to simplify forming the
>> export_symbols_cmds for AIX.
>> ---
>>  m4/libtool.m4 | 101 
>> ++++++++++++++++++++++++++++++++--------------------------
>>  1 file changed, 55 insertions(+), 46 deletions(-)
>>
>> diff --git a/m4/libtool.m4 b/m4/libtool.m4
>> index 2c0e657..6134522 100644
>> --- a/m4/libtool.m4
>> +++ b/m4/libtool.m4
>> @@ -3755,10 +3755,10 @@ _LT_DECL([], [want_nocaseglob], [1],
>>
>>  # LT_PATH_NM
>>  # ----------
>> -# find the pathname to a BSD- or MS-compatible name lister
>> +# find the pathname to a BSD-, POSIX- or MS-compatible name lister
>>  AC_DEFUN([LT_PATH_NM],
>>  [AC_REQUIRE([AC_PROG_CC])dnl
>> -AC_CACHE_CHECK([for BSD- or MS-compatible name lister (nm)], lt_cv_path_NM,
>> +AC_CACHE_CHECK([for BSD-, POSIX- or MS-compatible name lister (nm)], 
>> lt_cv_path_NM,
>>  [if test -n "$NM"; the
>>    # Let the user override the test.
>>    lt_cv_path_NM=$NM
>> @@ -3808,6 +3808,26 @@ else
>>    : ${lt_cv_path_NM=no}
>>  fi])
>>  if test no != "$lt_cv_path_NM"; then
>> +  case $host_os in
>> +  aix[[4-9]]*)
>> +    # With AIX nm we need the '-l' flag to get the "weak" information
>> +    # for the Import File, but '-l' is ignored with the '-B' flag.  So
>> +    # we use the '-P' (POSIX) flag instead.  As users often provide the
>> +    # '-B' flag, which conflicts with '-P', we drop any provided flag.
>> +    # AIX nm needs the '-C' flag to disable demangling.  For both GNU
>> +    # and AIX nm, the '-g' flag shows public (global) symbols only,
>> +    # and the '-p' flag disables sorting to improve performance.
>> +    set dummy $lt_cv_path_NM
>> +    case address@hidden|@2 -V 2>&1` in
>> +    *GNU* | *'with BFD'*)
>> +      lt_cv_path_NM="@S|@2 -Bgp"
>> +      ;;
>> +    *)
>> +      lt_cv_path_NM="@S|@2 -PlCgp"
>> +      ;;
>> +    esac
>> +    ;;
>> +  esac
>>    NM=$lt_cv_path_NM
>>  else
>>    # Didn't find any BSD compatible name lister, look for dumpbin.
>> @@ -3832,7 +3852,7 @@ fi
>>  test -z "$NM" && NM=nm
>>  _LT_SET_TOOL_ABI_FLAG([NM])
>>  AC_SUBST([NM])
>> -_LT_DECL([], [NM], [1], [A BSD- or MS-compatible name lister])dnl
>> +_LT_DECL([], [NM], [1], [A BSD-, POSIX- or MS-compatible name lister])dnl
>>
>>  AC_CACHE_CHECK([the name lister ($NM) interface], [lt_cv_nm_interface],
>>    [lt_cv_nm_interface="BSD nm"
>> @@ -3847,6 +3867,8 @@ AC_CACHE_CHECK([the name lister ($NM) interface], 
>> [lt_cv_nm_interface],
>>    cat conftest.out >&AS_MESSAGE_LOG_FD
>>    if $GREP 'External.*some_variable' conftest.out > /dev/null; then
>>      lt_cv_nm_interface="MS dumpbin"
>> +  elif $GREP '^[[       ]]*_*some_variable' conftest.out > /dev/null; then
>> +    lt_cv_nm_interface="POSIX nm"
>>    fi
>>    rm -f conftest*])
>>  ])# LT_PATH_NM
>> @@ -4012,8 +4034,33 @@ symcode='[[BCDEGRST]]'
>>  # Regexp to match symbols that can be accessed directly from C.
>>  sympat='\([[_A-Za-z]][[_A-Za-z0-9]]*\)'
>>
>> +if test "$lt_cv_nm_interface" = "MS dumpbin"; then
>> +  # Gets list of data symbols to import.
>> +  lt_cv_sys_global_symbol_to_import="sed -n -e 's/^I .* \(.*\)$/\1/p'"
>> +  # Adjust the below global symbol transforms to fixup imported variables.
>> +  lt_cdecl_hook=" -e 's/^I .* \(.*\)$/extern __declspec(dllimport) char 
>> \1;/p'"
>> +  lt_c_name_hook=" -e 's/^I .* \(.*\)$/  {\"\1\", (void *) 0},/p'"
>> +  lt_c_name_lib_hook="\
>> +  -e 's/^I .* \(lib.*\)$/  {\"\1\", (void *) 0},/p'\
>> +  -e 's/^I .* \(.*\)$/  {\"lib\1\", (void *) 0},/p'"
>> +else
>> +  # Disable hooks by default.
>> +  lt_cv_sys_global_symbol_to_import=
>> +  lt_cdecl_hook=
>> +  lt_c_name_hook=
>> +  lt_c_name_lib_hook=
>> +fi
>> +
>>  # Define system-specific variables.
>>  case $host_os in
>> +aix[[4-9]]*)
>> +  case `$NM -V 2>&1` in
>> +  *GNU* | *'with BFD'*) ;;
>> +  *)
>> +    symcode='[[BDLTVWZ]]'
>> +    lt_cdecl_hook=" -e 's/^W/T/p'" # weak text symbol
>> +  esac
>> +  ;;
>>  aix*)
>>    symcode='[[BCDT]]'
>>    ;;
>> @@ -4054,23 +4101,6 @@ case `$NM -V 2>&1` in
>>    symcode='[[ABCDGIRSTW]]' ;;
>>  esac
>>
>> -if test "$lt_cv_nm_interface" = "MS dumpbin"; then
>> -  # Gets list of data symbols to import.
>> -  lt_cv_sys_global_symbol_to_import="sed -n -e 's/^I .* \(.*\)$/\1/p'"
>> -  # Adjust the below global symbol transforms to fixup imported variables.
>> -  lt_cdecl_hook=" -e 's/^I .* \(.*\)$/extern __declspec(dllimport) char 
>> \1;/p'"
>> -  lt_c_name_hook=" -e 's/^I .* \(.*\)$/  {\"\1\", (void *) 0},/p'"
>> -  lt_c_name_lib_hook="\
>> -  -e 's/^I .* \(lib.*\)$/  {\"\1\", (void *) 0},/p'\
>> -  -e 's/^I .* \(.*\)$/  {\"lib\1\", (void *) 0},/p'"
>> -else
>> -  # Disable hooks by default.
>> -  lt_cv_sys_global_symbol_to_import=
>> -  lt_cdecl_hook=
>> -  lt_c_name_hook=
>> -  lt_c_name_lib_hook=
>> -fi
>> -
>>  # Transform an extracted symbol line into a proper C declaration.
>>  # Some systems (esp. on ia64) link data and code symbols differently,
>>  # so use this general approach.
>> @@ -4128,6 +4158,9 @@ for ac_symprfx in "" "_"; do
>>  "     s[1]~/address@hidden/{print f,s[1],s[1]; next};"\
>>  "     s[1]~prfx {split(s[1],t,\"@\"); print 
>> f,t[1],substr(t[1],length(prfx))}"\
>>  "     ' prfx=^$ac_symprfx]"
>> +  elif test "$lt_cv_nm_interface" = "POSIX nm"; then
>> +    symxfrm="\\2 $ac_symprfx\\1 \\1"
>> +    lt_cv_sys_global_symbol_pipe="sed -n -e 's/^[[      
>> ]]*$ac_symprfx$sympat[[         ]][[    ]]*\($symcode$symcode*\)[[      ]][[ 
>>    ]]*.*$opt_cr$/$symxfrm/p'"
>>    else
>>      lt_cv_sys_global_symbol_pipe="sed -n -e 's/^.*[[    
>> ]]\($symcode$symcode*\)[[       ]][[    
>> ]]*$ac_symprfx$sympat$opt_cr$/$symxfrm/p'"
>>    fi
>> @@ -5009,19 +5042,7 @@ m4_if([$1], [CXX], [
>>    _LT_TAGVAR(exclude_expsyms, 
>> $1)=['_GLOBAL_OFFSET_TABLE_|_GLOBAL__F[ID]_.*']
>>    case $host_os in
>>    aix[[4-9]]*)
>> -    # If we're using GNU nm, then we don't want the "-C" option.
>> -    # -C means demangle to GNU nm, but means don't demangle to AIX nm.
>> -    # Without the "-l" option, or with the "-B" option, AIX nm treats
>> -    # weak defined symbols like other global defined symbols, whereas
>> -    # GNU nm marks them as "W".
>> -    # While the 'weak' keyword is ignored in the Export File, we need
>> -    # it in the Import File for the 'aix-soname' feature, so we have
>> -    # to replace the "-B" option with "-P" for AIX nm.
>> -    if $NM -V 2>&1 | $GREP 'GNU' > /dev/null; then
>> -      _LT_TAGVAR(export_symbols_cmds, $1)='$NM -Bpg $libobjs $convenience | 
>> awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B") || (\$ 2 == 
>> "W")) && ([substr](\$ 3,1,1) != ".")) { if (\$ 2 == "W") { print \$ 3 " 
>> weak" } else { print \$ 3 } } }'\'' | sort -u > $export_symbols'
>> -    else
>> -      _LT_TAGVAR(export_symbols_cmds, $1)='`func_echo_all $NM | $SED -e 
>> '\''s/B\([[^B]]*\)$/P\1/'\''` -PCpgl $libobjs $convenience | awk '\''{ if 
>> (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B") || (\$ 2 == "L") || (\$ 2 
>> == "W") || (\$ 2 == "V") || (\$ 2 == "Z")) && ([substr](\$ 1,1,1) != ".")) { 
>> if ((\$ 2 == "W") || (\$ 2 == "V") || (\$ 2 == "Z")) { print \$ 1 " weak" } 
>> else { print \$ 1 } } }'\'' | sort -u > $export_symbols'
>> -    fi
>> +    _LT_TAGVAR(export_symbols_cmds, $1)='$NM $libobjs $convenience | 
>> $global_symbol_pipe | $EGREP -v " ($exclude_expsyms)$" | awk '\''{ kw = "" } 
>> /^[[VWZ]] / { kw = " weak" } { print $ 3 kw }'\'' | sort -u > 
>> $export_symbols'
>>      ;;
>>    pw32*)
>>      _LT_TAGVAR(export_symbols_cmds, $1)=$ltdll_cmds
>> @@ -5464,19 +5485,7 @@ _LT_EOF
>>         exp_sym_flag='-Bexport'
>>         no_entry_flag=
>>        else
>> -       # If we're using GNU nm, then we don't want the "-C" option.
>> -       # -C means demangle to GNU nm, but means don't demangle to AIX nm.
>> -       # Without the "-l" option, or with the "-B" option, AIX nm treats
>> -       # weak defined symbols like other global defined symbols, whereas
>> -       # GNU nm marks them as "W".
>> -       # While the 'weak' keyword is ignored in the Export File, we need
>> -       # it in the Import File for the 'aix-soname' feature, so we have
>> -       # to replace the "-B" option with "-P" for AIX nm.
>> -       if $NM -V 2>&1 | $GREP 'GNU' > /dev/null; then
>> -         _LT_TAGVAR(export_symbols_cmds, $1)='$NM -Bpg $libobjs 
>> $convenience | awk '\''{ if (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == 
>> "B") || (\$ 2 == "W")) && ([substr](\$ 3,1,1) != ".")) { if (\$ 2 == "W") { 
>> print \$ 3 " weak" } else { print \$ 3 } } }'\'' | sort -u > $export_symbols'
>> -       else
>> -         _LT_TAGVAR(export_symbols_cmds, $1)='`func_echo_all $NM | $SED -e 
>> '\''s/B\([[^B]]*\)$/P\1/'\''` -PCpgl $libobjs $convenience | awk '\''{ if 
>> (((\$ 2 == "T") || (\$ 2 == "D") || (\$ 2 == "B") || (\$ 2 == "L") || (\$ 2 
>> == "W") || (\$ 2 == "V") || (\$ 2 == "Z")) && ([substr](\$ 1,1,1) != ".")) { 
>> if ((\$ 2 == "W") || (\$ 2 == "V") || (\$ 2 == "Z")) { print \$ 1 " weak" } 
>> else { print \$ 1 } } }'\'' | sort -u > $export_symbols'
>> -       fi
>> +       _LT_TAGVAR(export_symbols_cmds, $1)='$NM $libobjs $convenience | 
>> $global_symbol_pipe | $EGREP -v " ($exclude_expsyms)$" | awk '\''{ kw = "" } 
>> /^[[VWZ]] / { kw = " weak" } { print $ 3 kw }'\'' | sort -u > 
>> $export_symbols'
>>         aix_use_runtimelinking=no
>>
>>         # Test if we are trying to use run time linking or normal
>> --
>> 2.4.6
>>