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

From: Mathieu Poirier <mathieu.poirier@linaro.org>
To: Suman Anna <s-anna@ti.com>
Cc: Bjorn Andersson <bjorn.andersson@linaro.org>,
	Grzegorz Jaszczyk <grzegorz.jaszczyk@linaro.org>,
	Jan Kiszka <jan.kiszka@siemens.com>,
	Lokesh Vutla <lokeshvutla@ti.com>,
	Vignesh Raghavendra <vigneshr@ti.com>,
	linux-remoteproc <linux-remoteproc@vger.kernel.org>,
	linux-omap@vger.kernel.org,
	linux-arm-kernel <linux-arm-kernel@lists.infradead.org>,
	Linux Kernel Mailing List <linux-kernel@vger.kernel.org>
Subject: Re: [PATCH] remoteproc: pru: Fix firmware loading crashes on K3 SoCs
Date: Thu, 25 Mar 2021 11:36:14 -0600	[thread overview]
Message-ID: <CANLsYkw75yTfzXBOV4u03XETYH4zfOPUozKRxp=RroYvzfXR9Q@mail.gmail.com> (raw)
In-Reply-To: <2f8bfc4f-e43d-5e38-fc6d-7045c69af364@ti.com>

On Wed, 24 Mar 2021 at 11:09, Suman Anna <s-anna@ti.com> wrote:
>
> On 3/23/21 6:20 PM, Mathieu Poirier wrote:
> > 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@ti.com>
> >
> > Probably a good idea to CC stable as well...
> >
> > Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org>
>
> Thanks Mathieu. This patch is already staged on Bjorn's rproc-fixes branch
> though and part of linux-next since next-20210319. I have posted an additional
> 3-patch series for some more PRU fixes. Do you want me to post a v2 for those
> with stable Cc'd?

I didn't notice Bjorn had already picked it up.  Since the object is
now public there is no need to send a V2 for this one.  I haven't
looked at your other 3-patch series but if you think it is stable
material then yes, please send a new revision that CC stable.

Mathieu

>
> regards
> Suman
>
> >
> >> ---
> >>  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
> >>
>