[PATCH] remoteproc: pru: Fix firmware loading crashes on K3 SoCs

[Mathieu Poirier]

On Mon, Mar 15, 2021 at 03:58:59PM -0500, Suman Anna wrote:
> The K3 PRUs are 32-bit processors and in general have some limitations
> in using the standard ARMv8 memcpy function for loading firmware segments,
> so the driver already uses a custom memcpy implementation. This added
> logic however is limited to only IRAMs at the moment, but the loading
> into Data RAMs is not completely ok either and does generate a kernel
> crash for unaligned accesses.
> 
> Fix these crashes by removing the existing IRAM logic limitation and
> extending the custom memcpy usage to Data RAMs as well for all K3 SoCs.
> 
> Fixes: 1d39f4d19921 ("remoteproc: pru: Add support for various PRU cores on K3 AM65x SoCs")
> Signed-off-by: Suman Anna <s-anna at ti.com>

Probably a good idea to CC stable as well...

Reviewed-by: Mathieu Poirier <mathieu.poirier at linaro.org>

> ---
>  drivers/remoteproc/pru_rproc.c | 2 +-
>  1 file changed, 1 insertion(+), 1 deletion(-)
> 
> diff --git a/drivers/remoteproc/pru_rproc.c b/drivers/remoteproc/pru_rproc.c
> index 2667919d76b3..16979c1cd2f4 100644
> --- a/drivers/remoteproc/pru_rproc.c
> +++ b/drivers/remoteproc/pru_rproc.c
> @@ -585,7 +585,7 @@ pru_rproc_load_elf_segments(struct rproc *rproc, const struct firmware *fw)
>  			break;
>  		}
>  
> -		if (pru->data->is_k3 && is_iram) {
> +		if (pru->data->is_k3) {
>  			ret = pru_rproc_memcpy(ptr, elf_data + phdr->p_offset,
>  					       filesz);
>  			if (ret) {
> -- 
> 2.30.1
>