Message ID | 1407146220-5608-1-git-send-email-will.newton@linaro.org |
---|---|
State | Accepted |
Headers | show |
On 4 August 2014 10:57, Will Newton <will.newton@linaro.org> wrote: > At the moment it is possible to configure binutils for these triples > but the resulting linker defaults to little endian with huge numbers > of testsuite failures, which on the face of it does not appear to make > much sense. > > This patch makes the behaviour similar to armeb-elf and the testsuite > is clean. > > bfd/ChangeLog: > > 2014-08-04 Will Newton <will.newton@linaro.org> > > * config.bfd: Default armeb-*-eabi* to big endian. > > ld/ChangeLog: > > 2014-08-04 Will Newton <will.newton@linaro.org> > > * configure.tgt: Default armeb-*-eabi* to big endian. > --- > bfd/config.bfd | 2 +- > ld/configure.tgt | 3 ++- > 2 files changed, 3 insertions(+), 2 deletions(-) Ping? > diff --git a/bfd/config.bfd b/bfd/config.bfd > index 1950ca0..3272076 100644 > --- a/bfd/config.bfd > +++ b/bfd/config.bfd > @@ -328,7 +328,7 @@ case "${targ}" in > targ_defvec=arm_elf32_le_vec > targ_selvecs=arm_elf32_be_vec > ;; > - armeb-*-elf | arm*b-*-freebsd* | arm*b-*-linux-*) > + armeb-*-elf | arm*b-*-freebsd* | arm*b-*-linux-* | armeb-*-eabi*) > targ_defvec=arm_elf32_be_vec > targ_selvecs=arm_elf32_le_vec > ;; > diff --git a/ld/configure.tgt b/ld/configure.tgt > index 33fb378..fc99a54 100644 > --- a/ld/configure.tgt > +++ b/ld/configure.tgt > @@ -95,7 +95,8 @@ arm-*-netbsd*) targ_emul=armnbsd; > arm-*-nto*) targ_emul=armnto ;; > arm-*-openbsd*) targ_emul=armnbsd ;; > arm-*-rtems*) targ_emul=armelf ;; > -armeb-*-elf) targ_emul=armelfb ;; > +armeb-*-elf | armeb-*-eabi*) > + targ_emul=armelfb ;; > arm-*-elf | arm*-*-eabi*) > targ_emul=armelf ;; > arm*-*-symbianelf*) targ_emul=armsymbian;; > -- > 1.9.3 >
> From: Will Newton [mailto:will.newton@linaro.org] > Sent: Monday, August 04, 2014 5:57 PM > > At the moment it is possible to configure binutils for these triples > but the resulting linker defaults to little endian with huge numbers > of testsuite failures, which on the face of it does not appear to make > much sense. > > This patch makes the behaviour similar to armeb-elf and the testsuite > is clean. I encountered the same problem when I wanted to test that a fix for a big endian bug in GCC didn't introduce new regression. The patch allowed me to move forward and I didn't encountered any problem with it. Best regards, Thomas
Hi Will, >> bfd/ChangeLog: >> >> 2014-08-04 Will Newton <will.newton@linaro.org> >> >> * config.bfd: Default armeb-*-eabi* to big endian. >> >> ld/ChangeLog: >> >> 2014-08-04 Will Newton <will.newton@linaro.org> >> >> * configure.tgt: Default armeb-*-eabi* to big endian. Approved - please apply. Cheers Nick
diff --git a/bfd/config.bfd b/bfd/config.bfd index 1950ca0..3272076 100644 --- a/bfd/config.bfd +++ b/bfd/config.bfd @@ -328,7 +328,7 @@ case "${targ}" in targ_defvec=arm_elf32_le_vec targ_selvecs=arm_elf32_be_vec ;; - armeb-*-elf | arm*b-*-freebsd* | arm*b-*-linux-*) + armeb-*-elf | arm*b-*-freebsd* | arm*b-*-linux-* | armeb-*-eabi*) targ_defvec=arm_elf32_be_vec targ_selvecs=arm_elf32_le_vec ;; diff --git a/ld/configure.tgt b/ld/configure.tgt index 33fb378..fc99a54 100644 --- a/ld/configure.tgt +++ b/ld/configure.tgt @@ -95,7 +95,8 @@ arm-*-netbsd*) targ_emul=armnbsd; arm-*-nto*) targ_emul=armnto ;; arm-*-openbsd*) targ_emul=armnbsd ;; arm-*-rtems*) targ_emul=armelf ;; -armeb-*-elf) targ_emul=armelfb ;; +armeb-*-elf | armeb-*-eabi*) + targ_emul=armelfb ;; arm-*-elf | arm*-*-eabi*) targ_emul=armelf ;; arm*-*-symbianelf*) targ_emul=armsymbian;;