diff mbox

Avoid an extra branch to PLT for -z now

Message ID 20160504181716.GA21077@intel.com
State New, archived
Headers show

Commit Message

H.J. Lu May 4, 2016, 6:17 p.m. UTC
When --enable-bind-now is used to configure glibc build, we can avoid
an extra branch to the PLT entry by using indirect branch via the GOT
slot instead, which is similar to the first instructuon in the PLT
entry.  Changes in the shared library sizes in text sections:

Shared library    Before (bytes)   After (bytes)
libm.so             1060813          1060797
libmvec.so           160881           160805
libpthread.so         94992            94984
librt.so              25064            25048

Tested on x86-64.  OK for master?

H.J.
---
	* config.h.in (BIND_NOW): New.
	* configure.ac (BIND_NOW): New.  Defined for --enable-bind-now.
	* configure: Regenerated.
	* sysdeps/x86_64/sysdep.h (JUMPTARGET): Defined to indirect
	branch via the GOT slot.
---
 config.h.in             | 3 +++
 configure               | 4 ++++
 configure.ac            | 3 +++
 sysdeps/x86_64/sysdep.h | 8 ++++++--
 4 files changed, 16 insertions(+), 2 deletions(-)

Comments

H.J. Lu May 18, 2016, 6:02 p.m. UTC | #1
On Wed, May 4, 2016 at 11:17 AM, H.J. Lu <hongjiu.lu@intel.com> wrote:
> When --enable-bind-now is used to configure glibc build, we can avoid
> an extra branch to the PLT entry by using indirect branch via the GOT
> slot instead, which is similar to the first instructuon in the PLT
> entry.  Changes in the shared library sizes in text sections:
>
> Shared library    Before (bytes)   After (bytes)
> libm.so             1060813          1060797
> libmvec.so           160881           160805
> libpthread.so         94992            94984
> librt.so              25064            25048
>
> Tested on x86-64.  OK for master?
>
> H.J.
> ---
>         * config.h.in (BIND_NOW): New.
>         * configure.ac (BIND_NOW): New.  Defined for --enable-bind-now.
>         * configure: Regenerated.
>         * sysdeps/x86_64/sysdep.h (JUMPTARGET): Defined to indirect
>         branch via the GOT slot.
> ---
>  config.h.in             | 3 +++
>  configure               | 4 ++++
>  configure.ac            | 3 +++
>  sysdeps/x86_64/sysdep.h | 8 ++++++--
>  4 files changed, 16 insertions(+), 2 deletions(-)
>
> diff --git a/config.h.in b/config.h.in
> index 0147ba3..2c902b0 100644
> --- a/config.h.in
> +++ b/config.h.in
> @@ -87,6 +87,9 @@
>     include/libc-symbols.h that avoid PLT slots in the shared objects.  */
>  #undef NO_HIDDEN
>
> +/* Define this to disable lazy relocations in DSOs.  */
> +#undef BIND_NOW
> +
>  /* AArch64 big endian ABI */
>  #undef HAVE_AARCH64_BE
>
> diff --git a/configure b/configure
> index 8fe5937..19a4829 100755
> --- a/configure
> +++ b/configure
> @@ -3416,6 +3416,10 @@ else
>  fi
>
>
> +if test "x$bindnow" = xyes; then
> +  $as_echo "#define BIND_NOW 1" >>confdefs.h
> +
> +fi
>
>  # Check whether --enable-static-nss was given.
>  if test "${enable_static_nss+set}" = set; then :
> diff --git a/configure.ac b/configure.ac
> index 3c766b7..123f0d2 100644
> --- a/configure.ac
> +++ b/configure.ac
> @@ -231,6 +231,9 @@ AC_ARG_ENABLE([bind-now],
>               [bindnow=$enableval],
>               [bindnow=no])
>  AC_SUBST(bindnow)
> +if test "x$bindnow" = xyes; then
> +  AC_DEFINE(BIND_NOW)
> +fi
>
>  dnl On some platforms we cannot use dynamic loading.  We must provide
>  dnl static NSS modules.
> diff --git a/sysdeps/x86_64/sysdep.h b/sysdeps/x86_64/sysdep.h
> index fbe3560..75ac747 100644
> --- a/sysdeps/x86_64/sysdep.h
> +++ b/sysdeps/x86_64/sysdep.h
> @@ -90,9 +90,13 @@ lose:                                                                              \
>
>  #undef JUMPTARGET
>  #ifdef PIC
> -#define JUMPTARGET(name)       name##@PLT
> +# ifdef BIND_NOW
> +#  define JUMPTARGET(name)     *name##@GOTPCREL(%rip)
> +# else
> +#  define JUMPTARGET(name)     name##@PLT
> +# endif
>  #else
> -#define JUMPTARGET(name)       name
> +# define JUMPTARGET(name)      name
>  #endif
>
>  /* Local label name for asm code. */
> --
> 2.5.5
>

Any objections?
Rich Felker May 18, 2016, 6:36 p.m. UTC | #2
On Wed, May 18, 2016 at 11:02:31AM -0700, H.J. Lu wrote:
> On Wed, May 4, 2016 at 11:17 AM, H.J. Lu <hongjiu.lu@intel.com> wrote:
> > When --enable-bind-now is used to configure glibc build, we can avoid
> > an extra branch to the PLT entry by using indirect branch via the GOT
> > slot instead, which is similar to the first instructuon in the PLT
> > entry.  Changes in the shared library sizes in text sections:
> >
> > Shared library    Before (bytes)   After (bytes)
> > libm.so             1060813          1060797
> > libmvec.so           160881           160805
> > libpthread.so         94992            94984
> > librt.so              25064            25048
> >
> > Tested on x86-64.  OK for master?
> >
> > H.J.
> > ---
> >         * config.h.in (BIND_NOW): New.
> >         * configure.ac (BIND_NOW): New.  Defined for --enable-bind-now.
> >         * configure: Regenerated.
> >         * sysdeps/x86_64/sysdep.h (JUMPTARGET): Defined to indirect
> >         branch via the GOT slot.
> > ---
> >  config.h.in             | 3 +++
> >  configure               | 4 ++++
> >  configure.ac            | 3 +++
> >  sysdeps/x86_64/sysdep.h | 8 ++++++--
> >  4 files changed, 16 insertions(+), 2 deletions(-)
> >
> > diff --git a/config.h.in b/config.h.in
> > index 0147ba3..2c902b0 100644
> > --- a/config.h.in
> > +++ b/config.h.in
> > @@ -87,6 +87,9 @@
> >     include/libc-symbols.h that avoid PLT slots in the shared objects.  */
> >  #undef NO_HIDDEN
> >
> > +/* Define this to disable lazy relocations in DSOs.  */
> > +#undef BIND_NOW
> > +
> >  /* AArch64 big endian ABI */
> >  #undef HAVE_AARCH64_BE
> >
> > diff --git a/configure b/configure
> > index 8fe5937..19a4829 100755
> > --- a/configure
> > +++ b/configure
> > @@ -3416,6 +3416,10 @@ else
> >  fi
> >
> >
> > +if test "x$bindnow" = xyes; then
> > +  $as_echo "#define BIND_NOW 1" >>confdefs.h
> > +
> > +fi
> >
> >  # Check whether --enable-static-nss was given.
> >  if test "${enable_static_nss+set}" = set; then :
> > diff --git a/configure.ac b/configure.ac
> > index 3c766b7..123f0d2 100644
> > --- a/configure.ac
> > +++ b/configure.ac
> > @@ -231,6 +231,9 @@ AC_ARG_ENABLE([bind-now],
> >               [bindnow=$enableval],
> >               [bindnow=no])
> >  AC_SUBST(bindnow)
> > +if test "x$bindnow" = xyes; then
> > +  AC_DEFINE(BIND_NOW)
> > +fi
> >
> >  dnl On some platforms we cannot use dynamic loading.  We must provide
> >  dnl static NSS modules.
> > diff --git a/sysdeps/x86_64/sysdep.h b/sysdeps/x86_64/sysdep.h
> > index fbe3560..75ac747 100644
> > --- a/sysdeps/x86_64/sysdep.h
> > +++ b/sysdeps/x86_64/sysdep.h
> > @@ -90,9 +90,13 @@ lose:                                                                              \
> >
> >  #undef JUMPTARGET
> >  #ifdef PIC
> > -#define JUMPTARGET(name)       name##@PLT
> > +# ifdef BIND_NOW
> > +#  define JUMPTARGET(name)     *name##@GOTPCREL(%rip)
> > +# else
> > +#  define JUMPTARGET(name)     name##@PLT
> > +# endif
> >  #else
> > -#define JUMPTARGET(name)       name
> > +# define JUMPTARGET(name)      name
> >  #endif
> >
> >  /* Local label name for asm code. */
> > --
> > 2.5.5
> >
> 
> Any objections?

Is there a reason you need to make it conditional? Just using
*name@GOTPCREL(%rip) unconditionally would force this particular
symbol to be resolved at load time, and doing that for the small
number of affected symbols is not going to make any noticable
difference to startup performance, but may noticably improve runtime
performance.

Rich
H.J. Lu May 18, 2016, 6:46 p.m. UTC | #3
On Wed, May 18, 2016 at 11:36 AM, Rich Felker <dalias@libc.org> wrote:
> On Wed, May 18, 2016 at 11:02:31AM -0700, H.J. Lu wrote:
>> On Wed, May 4, 2016 at 11:17 AM, H.J. Lu <hongjiu.lu@intel.com> wrote:
>> > When --enable-bind-now is used to configure glibc build, we can avoid
>> > an extra branch to the PLT entry by using indirect branch via the GOT
>> > slot instead, which is similar to the first instructuon in the PLT
>> > entry.  Changes in the shared library sizes in text sections:
>> >
>> > Shared library    Before (bytes)   After (bytes)
>> > libm.so             1060813          1060797
>> > libmvec.so           160881           160805
>> > libpthread.so         94992            94984
>> > librt.so              25064            25048
>> >
>> > Tested on x86-64.  OK for master?
>> >
>> > H.J.
>> > ---
>> >         * config.h.in (BIND_NOW): New.
>> >         * configure.ac (BIND_NOW): New.  Defined for --enable-bind-now.
>> >         * configure: Regenerated.
>> >         * sysdeps/x86_64/sysdep.h (JUMPTARGET): Defined to indirect
>> >         branch via the GOT slot.
>> > ---
>> >  config.h.in             | 3 +++
>> >  configure               | 4 ++++
>> >  configure.ac            | 3 +++
>> >  sysdeps/x86_64/sysdep.h | 8 ++++++--
>> >  4 files changed, 16 insertions(+), 2 deletions(-)
>> >
>> > diff --git a/config.h.in b/config.h.in
>> > index 0147ba3..2c902b0 100644
>> > --- a/config.h.in
>> > +++ b/config.h.in
>> > @@ -87,6 +87,9 @@
>> >     include/libc-symbols.h that avoid PLT slots in the shared objects.  */
>> >  #undef NO_HIDDEN
>> >
>> > +/* Define this to disable lazy relocations in DSOs.  */
>> > +#undef BIND_NOW
>> > +
>> >  /* AArch64 big endian ABI */
>> >  #undef HAVE_AARCH64_BE
>> >
>> > diff --git a/configure b/configure
>> > index 8fe5937..19a4829 100755
>> > --- a/configure
>> > +++ b/configure
>> > @@ -3416,6 +3416,10 @@ else
>> >  fi
>> >
>> >
>> > +if test "x$bindnow" = xyes; then
>> > +  $as_echo "#define BIND_NOW 1" >>confdefs.h
>> > +
>> > +fi
>> >
>> >  # Check whether --enable-static-nss was given.
>> >  if test "${enable_static_nss+set}" = set; then :
>> > diff --git a/configure.ac b/configure.ac
>> > index 3c766b7..123f0d2 100644
>> > --- a/configure.ac
>> > +++ b/configure.ac
>> > @@ -231,6 +231,9 @@ AC_ARG_ENABLE([bind-now],
>> >               [bindnow=$enableval],
>> >               [bindnow=no])
>> >  AC_SUBST(bindnow)
>> > +if test "x$bindnow" = xyes; then
>> > +  AC_DEFINE(BIND_NOW)
>> > +fi
>> >
>> >  dnl On some platforms we cannot use dynamic loading.  We must provide
>> >  dnl static NSS modules.
>> > diff --git a/sysdeps/x86_64/sysdep.h b/sysdeps/x86_64/sysdep.h
>> > index fbe3560..75ac747 100644
>> > --- a/sysdeps/x86_64/sysdep.h
>> > +++ b/sysdeps/x86_64/sysdep.h
>> > @@ -90,9 +90,13 @@ lose:                                                                              \
>> >
>> >  #undef JUMPTARGET
>> >  #ifdef PIC
>> > -#define JUMPTARGET(name)       name##@PLT
>> > +# ifdef BIND_NOW
>> > +#  define JUMPTARGET(name)     *name##@GOTPCREL(%rip)
>> > +# else
>> > +#  define JUMPTARGET(name)     name##@PLT
>> > +# endif
>> >  #else
>> > -#define JUMPTARGET(name)       name
>> > +# define JUMPTARGET(name)      name
>> >  #endif
>> >
>> >  /* Local label name for asm code. */
>> > --
>> > 2.5.5
>> >
>>
>> Any objections?
>
> Is there a reason you need to make it conditional? Just using
> *name@GOTPCREL(%rip) unconditionally would force this particular
> symbol to be resolved at load time, and doing that for the small
> number of affected symbols is not going to make any noticable
> difference to startup performance, but may noticably improve runtime
> performance.

In fact, I prefer "*name@GOTPCREL(%rip)" and I will make a proposal
to x86-64 psABI to get rid of PLT all together to enhance security,
But as the first step, I will support lazy binding for now.
Roland McGrath May 20, 2016, 10:29 p.m. UTC | #4
> 	* config.h.in (BIND_NOW): New.
> 	* configure.ac (BIND_NOW): New.  Defined for --enable-bind-now.
> 	* configure: Regenerated.
> 	* sysdeps/x86_64/sysdep.h (JUMPTARGET): Defined to indirect
> 	branch via the GOT slot.

Should be:
	* sysdeps/x86_64/sysdep.h (JUMPTARGET) [BIND_NOW]:
	Defined to indirect branch via the GOT slot.

Otherwise this seems OK to me.
diff mbox

Patch

diff --git a/config.h.in b/config.h.in
index 0147ba3..2c902b0 100644
--- a/config.h.in
+++ b/config.h.in
@@ -87,6 +87,9 @@ 
    include/libc-symbols.h that avoid PLT slots in the shared objects.  */
 #undef	NO_HIDDEN
 
+/* Define this to disable lazy relocations in DSOs.  */
+#undef	BIND_NOW
+
 /* AArch64 big endian ABI */
 #undef HAVE_AARCH64_BE
 
diff --git a/configure b/configure
index 8fe5937..19a4829 100755
--- a/configure
+++ b/configure
@@ -3416,6 +3416,10 @@  else
 fi
 
 
+if test "x$bindnow" = xyes; then
+  $as_echo "#define BIND_NOW 1" >>confdefs.h
+
+fi
 
 # Check whether --enable-static-nss was given.
 if test "${enable_static_nss+set}" = set; then :
diff --git a/configure.ac b/configure.ac
index 3c766b7..123f0d2 100644
--- a/configure.ac
+++ b/configure.ac
@@ -231,6 +231,9 @@  AC_ARG_ENABLE([bind-now],
 	      [bindnow=$enableval],
 	      [bindnow=no])
 AC_SUBST(bindnow)
+if test "x$bindnow" = xyes; then
+  AC_DEFINE(BIND_NOW)
+fi
 
 dnl On some platforms we cannot use dynamic loading.  We must provide
 dnl static NSS modules.
diff --git a/sysdeps/x86_64/sysdep.h b/sysdeps/x86_64/sysdep.h
index fbe3560..75ac747 100644
--- a/sysdeps/x86_64/sysdep.h
+++ b/sysdeps/x86_64/sysdep.h
@@ -90,9 +90,13 @@  lose:									      \
 
 #undef JUMPTARGET
 #ifdef PIC
-#define JUMPTARGET(name)	name##@PLT
+# ifdef BIND_NOW
+#  define JUMPTARGET(name)	*name##@GOTPCREL(%rip)
+# else
+#  define JUMPTARGET(name)	name##@PLT
+# endif
 #else
-#define JUMPTARGET(name)	name
+# define JUMPTARGET(name)	name
 #endif
 
 /* Local label name for asm code. */