Port-arm archive

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index][Old Index]

Re: Cortex-A53 GCC erratum compiler options



>> Hello, GCC for AArch64 has the following compiler options to work
>> around Cortex-A53 CPU bugs. I assume they are not enabled by default
>> by GCC.
>> 
>> Anyone knows if these options should always be enabled when building
>> software for this CPU? If yes, does NetBSD already enable them for
>> kernel and userland programs? If it doesn't, then should it?
>> 
>> 
>> -mfix-cortex-a53-835769
>> -mno-fix-cortex-a53-835769
>> Enable or disable the workaround for the ARM Cortex-A53 erratum number
>> 835769. This involves inserting a NOP instruction between memory
>> instructions and 64-bit integer multiply-accumulate instructions.
>> 
>> -mfix-cortex-a53-843419
>> -mno-fix-cortex-a53-843419
>> Enable or disable the workaround for the ARM Cortex-A53 erratum number
>> 843419. This erratum workaround is made at link time and this will
>> only pass the corresponding flag to the linker.
>
>
>OK found them, looks like they are enabled by default in NetBSD GCC
>compilers for AArch64, as can be seen with "gcc -v" output.

for errata 843419, not only compiler options but also ld.elf_so and kobj_machdep.c
should be fixed, but they are currently not.

There're still some errata left around aarch64 core and SoC,
but they have not been addressed sufficiently.
We need to do this, including Spectre.

Unfortunately, that work still hasn't gone underway...

-- 
ryo shimizu


Home | Main Index | Thread Index | Old Index