diff mbox series

[kernel,3/3] powerpc/llvm/lto: Workaround conditional branches in FTR_SECTION_ELSE

Message ID 20220211023125.1790960-4-aik@ozlabs.ru (mailing list archive)
State Changes Requested
Headers show
Series powerpc/llvm/lto: Enable CONFIG_LTO_CLANG_THIN=y | expand

Checks

Context Check Description
snowpatch_ozlabs/github-powerpc_ppctests fail 3 of 8 jobs failed.
snowpatch_ozlabs/github-powerpc_selftests success Successfully ran 8 jobs.
snowpatch_ozlabs/github-powerpc_kernel_qemu fail kernel (corenet64_smp_defconfig, korg-5.5.0, /linux/arch/powerpc/configs/ppc64e-qemu.config) failed at step build.
snowpatch_ozlabs/github-powerpc_sparse fail sparse (ppc64, ubuntu-21.04, ppc64) failed at step Build.
snowpatch_ozlabs/github-powerpc_clang fail 2 of 7 jobs failed.

Commit Message

Alexey Kardashevskiy Feb. 11, 2022, 2:31 a.m. UTC
LTO invites ld/lld to optimize the output binary and this may affect
the FTP alternative section if alt branches use "bc" (Branch Conditional)
which only allows 16 bit offsets. This manifests in errors like:

ld.lld: error: InputSection too large for range extension thunk vmlinux.o:(__ftr_alt_97+0xF0)

This works around the problem by replacing "bc" and its alias(es) in
FTR_SECTION_ELSE with "b" which allows 26 bit offsets.

This catches the problem instructions in vmlinux.o before it LTO'ed:

$ objdump -d -M raw -j __ftr_alt_97 vmlinux.o | egrep '\S+\s*\<bc\>'
  30:   00 00 82 40     bc      4,eq,30 <__ftr_alt_97+0x30>
  f0:   00 00 82 40     bc      4,eq,f0 <__ftr_alt_97+0xf0>

The change in copyuser_64.S is needed even when building default
configs, the other two changes are needed if the kernel config grows.

Signed-off-by: Alexey Kardashevskiy <aik@ozlabs.ru>
---
 arch/powerpc/kernel/exceptions-64s.S | 6 +++++-
 arch/powerpc/lib/copyuser_64.S       | 3 ++-
 arch/powerpc/lib/memcpy_64.S         | 3 ++-
 3 files changed, 9 insertions(+), 3 deletions(-)

Comments

Russell Currey Feb. 11, 2022, 6:44 a.m. UTC | #1
On Fri, 2022-02-11 at 13:31 +1100, Alexey Kardashevskiy wrote:
> diff --git a/arch/powerpc/lib/memcpy_64.S
> b/arch/powerpc/lib/memcpy_64.S
> index 016c91e958d8..286c7e2d0883 100644
> --- a/arch/powerpc/lib/memcpy_64.S
> +++ b/arch/powerpc/lib/memcpy_64.S
> @@ -50,10 +50,11 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY)
>     At the time of writing the only CPU that has this combination of
> bits
>     set is Power6. */
>  test_feature = (SELFTEST_CASE == 1)
> +       beq      .ldst_aligned

Hey Alexey, typo here (should be .Ldst_aligned) that breaks the build
for BE.

>  BEGIN_FTR_SECTION
>         nop
diff mbox series

Patch

diff --git a/arch/powerpc/kernel/exceptions-64s.S b/arch/powerpc/kernel/exceptions-64s.S
index 55caeee37c08..b8d9a2f5f3a5 100644
--- a/arch/powerpc/kernel/exceptions-64s.S
+++ b/arch/powerpc/kernel/exceptions-64s.S
@@ -476,9 +476,13 @@  DEFINE_FIXED_SYMBOL(\name\()_common_real, text)
 		.if IHSRR_IF_HVMODE
 		BEGIN_FTR_SECTION
 		bne	masked_Hinterrupt
+		b	4f
 		FTR_SECTION_ELSE
-		bne	masked_interrupt
+		nop
+		nop
 		ALT_FTR_SECTION_END_IFSET(CPU_FTR_HVMODE | CPU_FTR_ARCH_206)
+		bne	masked_interrupt
+4:
 		.elseif IHSRR
 		bne	masked_Hinterrupt
 		.else
diff --git a/arch/powerpc/lib/copyuser_64.S b/arch/powerpc/lib/copyuser_64.S
index db8719a14846..d07f95eebc65 100644
--- a/arch/powerpc/lib/copyuser_64.S
+++ b/arch/powerpc/lib/copyuser_64.S
@@ -75,10 +75,11 @@  _GLOBAL(__copy_tofrom_user_base)
  * set is Power6.
  */
 test_feature = (SELFTEST_CASE == 1)
+	beq	.Ldst_aligned
 BEGIN_FTR_SECTION
 	nop
 FTR_SECTION_ELSE
-	bne	.Ldst_unaligned
+	b	.Ldst_unaligned
 ALT_FTR_SECTION_END(CPU_FTR_UNALIGNED_LD_STD | CPU_FTR_CP_USE_DCBTZ, \
 		    CPU_FTR_UNALIGNED_LD_STD)
 .Ldst_aligned:
diff --git a/arch/powerpc/lib/memcpy_64.S b/arch/powerpc/lib/memcpy_64.S
index 016c91e958d8..286c7e2d0883 100644
--- a/arch/powerpc/lib/memcpy_64.S
+++ b/arch/powerpc/lib/memcpy_64.S
@@ -50,10 +50,11 @@  ALT_FTR_SECTION_END_IFCLR(CPU_FTR_VMX_COPY)
    At the time of writing the only CPU that has this combination of bits
    set is Power6. */
 test_feature = (SELFTEST_CASE == 1)
+	beq      .ldst_aligned
 BEGIN_FTR_SECTION
 	nop
 FTR_SECTION_ELSE
-	bne	.Ldst_unaligned
+	b	.Ldst_unaligned
 ALT_FTR_SECTION_END(CPU_FTR_UNALIGNED_LD_STD | CPU_FTR_CP_USE_DCBTZ, \
                     CPU_FTR_UNALIGNED_LD_STD)
 .Ldst_aligned: