From: Sriraman Tallam Date: Thu, 4 Dec 2014 19:40:50 +0000 (+0000) Subject: x86-64: Optimize access to globals in PIE with copy reloc X-Git-Url: https://git.libre-soc.org/?a=commitdiff_plain;h=77ad54d911dd7cb88caf697ac213929f6132fdcf;p=gcc.git x86-64: Optimize access to globals in PIE with copy reloc Normally, with -fPIE/-fpie, GCC accesses globals that are extern to the module using the GOT. This is two instructions, one to get the address of the global from the GOT and the other to get the value. If it turns out that the global gets defined in the executable at link-time, it still needs to go through the GOT as it is too late then to generate a direct access. Examples: foo.cc ------ int a_glob; int main () { return a_glob; // defined in this file } With -O2 -fpie -pie, the generated code directly accesses the global via PC-relative insn: 5e0
: mov 0x165a(%rip),%eax # 1c40 foo.cc ------ extern int a_glob; int main () { return a_glob; // defined in this file } With -O2 -fpie -pie, the generated code accesses global via GOT using two memory loads: 6f0
: mov 0x1609(%rip),%rax # 1d00 <_DYNAMIC+0x230> mov (%rax),%eax This is true even if in the latter case the global was defined in the executable through a different file. Some experiments on google benchmarks shows that the extra memory loads affects performance by 1% to 5%. Solution - Copy Relocations: When the linker supports copy relocations, GCC can always assume that the global will be defined in the executable. For globals that are truly extern (come from shared objects), the linker will create copy relocations and have them defined in the executable. Result is that no global access needs to go through the GOT and hence improves performance. This optimization only applies to undefined, non-weak global data. Undefined, weak global data access still must go through the GOT. This patch checks if linker supports PIE with copy reloc, which is enabled in gold and bfd linker in bininutils 2.25, at configure time and enables this optimization if the linker support is available. gcc/ * configure.ac (HAVE_LD_PIE_COPYRELOC): Defined to 1 if Linux/x86-64 linker supports PIE with copy reloc. * config.in: Regenerated. * configure: Likewise. * config/i386/i386.c (legitimate_pic_address_disp_p): Allow pc-relative address for undefined, non-weak, non-function symbol reference in 64-bit PIE if linker supports PIE with copy reloc. * doc/sourcebuild.texi: Document pie_copyreloc target. gcc/testsuite/ * gcc.target/i386/pie-copyrelocs-1.c: New test. * gcc.target/i386/pie-copyrelocs-2.c: Likewise. * gcc.target/i386/pie-copyrelocs-3.c: Likewise. * gcc.target/i386/pie-copyrelocs-4.c: Likewise. * lib/target-supports.exp (check_effective_target_pie_copyreloc): New procedure. Co-Authored-By: H.J. Lu From-SVN: r218397 --- diff --git a/gcc/ChangeLog b/gcc/ChangeLog index 2d41d93b171..18b481e11a0 100644 --- a/gcc/ChangeLog +++ b/gcc/ChangeLog @@ -1,3 +1,18 @@ +2014-12-04 Sriraman Tallam + H.J. Lu + + * configure.ac (HAVE_LD_PIE_COPYRELOC): Defined to 1 if + Linux/x86-64 linker supports PIE with copy reloc. + * config.in: Regenerated. + * configure: Likewise. + + * config/i386/i386.c (legitimate_pic_address_disp_p): Allow + pc-relative address for undefined, non-weak, non-function + symbol reference in 64-bit PIE if linker supports PIE with + copy reloc. + + * doc/sourcebuild.texi: Document pie_copyreloc target. + 2014-12-04 Marek Polacek PR middle-end/56917 diff --git a/gcc/config.in b/gcc/config.in index 65d5e421a90..f34adb57e6d 100644 --- a/gcc/config.in +++ b/gcc/config.in @@ -1411,6 +1411,12 @@ #endif +/* Define 0/1 if your linker supports -pie option with copy reloc. */ +#ifndef USED_FOR_TARGET +#undef HAVE_LD_PIE_COPYRELOC +#endif + + /* Define if your linker links a mix of read-only and read-write sections into a read-write section. */ #ifndef USED_FOR_TARGET diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c index 211c9e6a65e..4f1a18b993a 100644 --- a/gcc/config/i386/i386.c +++ b/gcc/config/i386/i386.c @@ -13113,7 +13113,11 @@ legitimate_pic_address_disp_p (rtx disp) return true; } else if (!SYMBOL_REF_FAR_ADDR_P (op0) - && SYMBOL_REF_LOCAL_P (op0) + && (SYMBOL_REF_LOCAL_P (op0) + || (HAVE_LD_PIE_COPYRELOC + && flag_pie + && !SYMBOL_REF_WEAK (op0) + && !SYMBOL_REF_FUNCTION_P (op0))) && ix86_cmodel != CM_LARGE_PIC) return true; break; diff --git a/gcc/configure b/gcc/configure index 6b46bbb9e4e..811f05dc78a 100755 --- a/gcc/configure +++ b/gcc/configure @@ -27025,6 +27025,53 @@ fi { $as_echo "$as_me:${as_lineno-$LINENO}: result: $gcc_cv_ld_pie" >&5 $as_echo "$gcc_cv_ld_pie" >&6; } +{ $as_echo "$as_me:${as_lineno-$LINENO}: checking linker PIE support with copy reloc" >&5 +$as_echo_n "checking linker PIE support with copy reloc... " >&6; } +gcc_cv_ld_pie_copyreloc=no +if test $gcc_cv_ld_pie = yes ; then + if test $in_tree_ld = yes ; then + if test "$gcc_cv_gld_major_version" -eq 2 -a "$gcc_cv_gld_minor_version" -ge 25 -o "$gcc_cv_gld_major_version" -gt 2; then + gcc_cv_ld_pie_copyreloc=yes + fi + elif test x$gcc_cv_as != x -a x$gcc_cv_ld != x ; then + # Check if linker supports -pie option with copy reloc + case "$target" in + i?86-*-linux* | x86_64-*-linux*) + cat > conftest1.s < conftest2.s < /dev/null 2>&1 \ + && $gcc_cv_ld -shared -melf_x86_64 -o conftest1.so conftest1.o > /dev/null 2>&1 \ + && $gcc_cv_as --64 -o conftest2.o conftest2.s > /dev/null 2>&1 \ + && $gcc_cv_ld -pie -melf_x86_64 -o conftest conftest2.o conftest1.so > /dev/null 2>&1; then + gcc_cv_ld_pie_copyreloc=yes + fi + rm -f conftest conftest1.so conftest1.o conftest2.o conftest1.s conftest2.s + ;; + esac + fi + +cat >>confdefs.h <<_ACEOF +#define HAVE_LD_PIE_COPYRELOC `if test x"$gcc_cv_ld_pie_copyreloc" = xyes; then echo 1; else echo 0; fi` +_ACEOF + +fi +{ $as_echo "$as_me:${as_lineno-$LINENO}: result: $gcc_cv_ld_pie_copyreloc" >&5 +$as_echo "$gcc_cv_ld_pie_copyreloc" >&6; } + { $as_echo "$as_me:${as_lineno-$LINENO}: checking linker EH-compatible garbage collection of sections" >&5 $as_echo_n "checking linker EH-compatible garbage collection of sections... " >&6; } gcc_cv_ld_eh_gc_sections=no diff --git a/gcc/configure.ac b/gcc/configure.ac index 48c8000b249..a33f3a57bb4 100644 --- a/gcc/configure.ac +++ b/gcc/configure.ac @@ -4693,6 +4693,49 @@ if test x"$gcc_cv_ld_pie" = xyes; then fi AC_MSG_RESULT($gcc_cv_ld_pie) +AC_MSG_CHECKING(linker PIE support with copy reloc) +gcc_cv_ld_pie_copyreloc=no +if test $gcc_cv_ld_pie = yes ; then + if test $in_tree_ld = yes ; then + if test "$gcc_cv_gld_major_version" -eq 2 -a "$gcc_cv_gld_minor_version" -ge 25 -o "$gcc_cv_gld_major_version" -gt 2; then + gcc_cv_ld_pie_copyreloc=yes + fi + elif test x$gcc_cv_as != x -a x$gcc_cv_ld != x ; then + # Check if linker supports -pie option with copy reloc + case "$target" in + i?86-*-linux* | x86_64-*-linux*) + cat > conftest1.s < conftest2.s < /dev/null 2>&1 \ + && $gcc_cv_ld -shared -melf_x86_64 -o conftest1.so conftest1.o > /dev/null 2>&1 \ + && $gcc_cv_as --64 -o conftest2.o conftest2.s > /dev/null 2>&1 \ + && $gcc_cv_ld -pie -melf_x86_64 -o conftest conftest2.o conftest1.so > /dev/null 2>&1; then + gcc_cv_ld_pie_copyreloc=yes + fi + rm -f conftest conftest1.so conftest1.o conftest2.o conftest1.s conftest2.s + ;; + esac + fi + AC_DEFINE_UNQUOTED(HAVE_LD_PIE_COPYRELOC, + [`if test x"$gcc_cv_ld_pie_copyreloc" = xyes; then echo 1; else echo 0; fi`], + [Define 0/1 if your linker supports -pie option with copy reloc.]) +fi +AC_MSG_RESULT($gcc_cv_ld_pie_copyreloc) + AC_MSG_CHECKING(linker EH-compatible garbage collection of sections) gcc_cv_ld_eh_gc_sections=no if test $in_tree_ld = yes ; then diff --git a/gcc/doc/sourcebuild.texi b/gcc/doc/sourcebuild.texi index 20a206dbf32..98ba1a67c2a 100644 --- a/gcc/doc/sourcebuild.texi +++ b/gcc/doc/sourcebuild.texi @@ -1717,6 +1717,9 @@ or @code{EM_SPARCV9} executables. @item vect_cmdline_needed Target requires a command line argument to enable a SIMD instruction set. + +@item pie_copyreloc +The x86-64 target linker supports PIE with copy reloc. @end table @subsubsection Environment attributes diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog index 0b3a9d682a9..295a8103acc 100644 --- a/gcc/testsuite/ChangeLog +++ b/gcc/testsuite/ChangeLog @@ -1,3 +1,14 @@ +2014-12-04 Sriraman Tallam + H.J. Lu + + * gcc.target/i386/pie-copyrelocs-1.c: New test. + * gcc.target/i386/pie-copyrelocs-2.c: Likewise. + * gcc.target/i386/pie-copyrelocs-3.c: Likewise. + * gcc.target/i386/pie-copyrelocs-4.c: Likewise. + + * lib/target-supports.exp (check_effective_target_pie_copyreloc): + New procedure. + 2014-12-04 Marek Polacek PR middle-end/56917 diff --git a/gcc/testsuite/gcc.target/i386/pie-copyrelocs-1.c b/gcc/testsuite/gcc.target/i386/pie-copyrelocs-1.c new file mode 100644 index 00000000000..7af851bde9b --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pie-copyrelocs-1.c @@ -0,0 +1,14 @@ +/* Check that GOTPCREL isn't used to access glob_a. */ +/* { dg-do compile { target *-*-linux* } } */ +/* { dg-require-effective-target pie_copyreloc } */ +/* { dg-options "-O2 -fpie" } */ + +extern int glob_a; + +int foo () +{ + return glob_a; +} + +/* glob_a should never be accessed with a GOTPCREL. */ +/* { dg-final { scan-assembler-not "glob_a@GOTPCREL" { target { ! ia32 } } } } */ diff --git a/gcc/testsuite/gcc.target/i386/pie-copyrelocs-2.c b/gcc/testsuite/gcc.target/i386/pie-copyrelocs-2.c new file mode 100644 index 00000000000..19cb97e882c --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pie-copyrelocs-2.c @@ -0,0 +1,14 @@ +/* Check that GOTPCREL isn't used to access glob_a. */ +/* { dg-do compile { target *-*-linux* } } */ +/* { dg-require-effective-target pie_copyreloc } */ +/* { dg-options "-O2 -fpie" } */ + +int glob_a; + +int foo () +{ + return glob_a; +} + +/* glob_a should never be accessed with a GOTPCREL. */ +/* { dg-final { scan-assembler-not "glob_a@GOTPCREL" { target { ! ia32 } } } } */ diff --git a/gcc/testsuite/gcc.target/i386/pie-copyrelocs-3.c b/gcc/testsuite/gcc.target/i386/pie-copyrelocs-3.c new file mode 100644 index 00000000000..c2fa8968e77 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pie-copyrelocs-3.c @@ -0,0 +1,14 @@ +/* Check that PLT is used to access glob_a. */ +/* { dg-do compile { target *-*-linux* } } */ +/* { dg-require-effective-target pie_copyreloc } */ +/* { dg-options "-O2 -fpie" } */ + +extern int glob_a (void); + +int foo () +{ + return glob_a (); +} + +/* glob_a should be accessed with a PLT. */ +/* { dg-final { scan-assembler "glob_a@PLT" { target { ! ia32 } } } } */ diff --git a/gcc/testsuite/gcc.target/i386/pie-copyrelocs-4.c b/gcc/testsuite/gcc.target/i386/pie-copyrelocs-4.c new file mode 100644 index 00000000000..413cdf381c3 --- /dev/null +++ b/gcc/testsuite/gcc.target/i386/pie-copyrelocs-4.c @@ -0,0 +1,17 @@ +/* Check that GOTPCREL is used to access glob_a. */ +/* { dg-do compile { target *-*-linux* } } */ +/* { dg-require-effective-target pie_copyreloc } */ +/* { dg-options "-O2 -fpie" } */ + +extern int glob_a __attribute__((weak)); + +int foo () +{ + if (&glob_a != 0) + return glob_a; + else + return 0; +} + +/* weak glob_a should be accessed with a GOTPCREL. */ +/* { dg-final { scan-assembler "glob_a@GOTPCREL" { target { ! ia32 } } } } */ diff --git a/gcc/testsuite/lib/target-supports.exp b/gcc/testsuite/lib/target-supports.exp index e960e12cd80..4846724378b 100644 --- a/gcc/testsuite/lib/target-supports.exp +++ b/gcc/testsuite/lib/target-supports.exp @@ -6098,3 +6098,54 @@ proc force_conventional_output_for { test } { } } +# Return 1 if the x86-64 target supports PIE with copy reloc, 0 +# otherwise. Cache the result. + +proc check_effective_target_pie_copyreloc { } { + global pie_copyreloc_available_saved + global tool + global GCC_UNDER_TEST + + if { !([istarget x86_64-*-*] || [istarget i?86-*-*]) } { + return 0 + } + + # Need auto-host.h to check linker support. + if { ![file exists ../../auto-host.h ] } { + return 0 + } + + if [info exists pie_copyreloc_available_saved] { + verbose "check_effective_target_pie_copyreloc returning saved $pie_copyreloc_available_saved" 2 + } else { + # Set up and compile to see if linker supports PIE with copy + # reloc. Include the current process ID in the file names to + # prevent conflicts with invocations for multiple testsuites. + + set src pie[pid].c + set obj pie[pid].o + + set f [open $src "w"] + puts $f "#include \"../../auto-host.h\"" + puts $f "#if HAVE_LD_PIE_COPYRELOC == 0" + puts $f "# error Linker does not support PIE with copy reloc." + puts $f "#endif" + close $f + + verbose "check_effective_target_pie_copyreloc compiling testfile $src" 2 + set lines [${tool}_target_compile $src $obj object ""] + + file delete $src + file delete $obj + + if [string match "" $lines] then { + verbose "check_effective_target_pie_copyreloc testfile compilation passed" 2 + set pie_copyreloc_available_saved 1 + } else { + verbose "check_effective_target_pie_copyreloc testfile compilation failed" 2 + set pie_copyreloc_available_saved 0 + } + } + + return $pie_copyreloc_available_saved +}