[PATCH-V2 5/7] score/sparc: Add comment on icache flush after trap table update

Gedare Bloom gedare at rtems.org
Wed Jul 9 14:38:53 UTC 2014


On Wed, Jul 9, 2014 at 3:02 AM, Daniel Cederman <cederman at gaisler.com> wrote:
> Changes to the trap table might be missed by other cores.
> If the system state is up, the other cores can be notified
> using SMP messages that they need to flush their icache.
> If the up state has not been reached there is no need to
> notify other cores. They will do an automatic flush of the
> icache just after entering the up state, but before enabling
> interrupts.
> ---
>  cpukit/score/cpu/sparc/cpu.c |   12 +++++++++---
>  1 file changed, 9 insertions(+), 3 deletions(-)
>
> diff --git a/cpukit/score/cpu/sparc/cpu.c b/cpukit/score/cpu/sparc/cpu.c
> index c616de4..88228b7 100644
> --- a/cpukit/score/cpu/sparc/cpu.c
> +++ b/cpukit/score/cpu/sparc/cpu.c
> @@ -210,10 +210,16 @@ void _CPU_ISR_install_raw_handler(
>      (u32_handler & HIGH_BITS_MASK) >> HIGH_BITS_SHIFT;
>    slot->jmp_to_low_of_handler_plus_l4 |= (u32_handler & LOW_BITS_MASK);
>
> -  /* need to flush icache after this !!! */
> -
> +  /*
> +   * Changes to the trap table might be missed by other cores.
> +   * If the system state is up, the other cores can be notified
> +   * using SMP messages that they need to flush their icache.
> +   * If the up state has not been reached there is no need to
> +   * notify other cores. They will do an automatic flush of the
> +   * icache just after entering the up state, but before enabling
> +   * interrupts.
> +   */
This was needed for UP mode also, since stores to the trap table are
cached in d-cache instead of i-cache, you need to flush/invalidate
i-cache so the updated trap table entry will be loaded from memory. It
should be made clear that this is the situation, else someone might
think to make this invalidate conditional on SMP mode...
-Gedare

>    rtems_cache_invalidate_entire_instruction();
> -
>  }
>
>  void _CPU_ISR_install_vector(
> --
> 1.7.9.5
>
> _______________________________________________
> devel mailing list
> devel at rtems.org
> http://lists.rtems.org/mailman/listinfo/devel


More information about the devel mailing list