arm64: dts: qcom: sdm845-db845c: Mark cont splash memory region as reserved

Put cont splash memory region under the reserved-memory
as confirmed by the downstream code as well.

Signed-off-by: Amit Pundir <amit.pundir@linaro.org>
---
 arch/arm64/boot/dts/qcom/sdm845-db845c.dts | 8 ++++++++
 1 file changed, 8 insertions(+)

On 31.01.2023 12:06, Dmitry Baryshkov wrote:
> On Tue, 31 Jan 2023 at 12:54, Bryan O'Donoghue
> <bryan.odonoghue@linaro.org> wrote:
>>
>> On 24/01/2023 18:28, Amit Pundir wrote:
>>> Put cont splash memory region under the reserved-memory
>>> as confirmed by the downstream code as well.
>>>
>>> Signed-off-by: Amit Pundir <amit.pundir@linaro.org>
>>> ---
>>>   arch/arm64/boot/dts/qcom/sdm845-db845c.dts | 8 ++++++++
>>>   1 file changed, 8 insertions(+)
>>>
>>> diff --git a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts
>>> index f41c6d600ea8..2ae59432cbda 100644
>>> --- a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts
>>> +++ b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts
>>> @@ -100,6 +100,14 @@ hdmi_con: endpoint {
>>>               };
>>>       };
>>>
>>> +     reserved-memory {
>>> +             /* Cont splash region set up by the bootloader */
>>> +             cont_splash_mem: framebuffer@9d400000 {
>>> +                     reg = <0x0 0x9d400000 0x0 0x2400000>;
>>> +                     no-map;
>>> +             };
>>> +     };
>>> +
>>>       lt9611_1v8: lt9611-vdd18-regulator {
>>>               compatible = "regulator-fixed";
>>>               regulator-name = "LT9611_1V8";
>>
>> Doesn't this mean we loose 0x2400000 of DRAM for all rb3 platforms
>> though ? About what 37 megabytes.. ?
> 
> I think this memory is further used for display memory allocation. So
> we are not loosing it, but dedicating it to the framebuffer memory.
Not exactly, to do so, you'd have to use the memory-region property
with mdss, which nobody does. Otherwise it's just a hole for Linux.

Konrad
> 
>

On 31/01/2023 14:45, Konrad Dybcio wrote:
> 
> 
> On 31.01.2023 12:06, Dmitry Baryshkov wrote:
>> On Tue, 31 Jan 2023 at 12:54, Bryan O'Donoghue
>> <bryan.odonoghue@linaro.org> wrote:
>>>
>>> On 24/01/2023 18:28, Amit Pundir wrote:
>>>> Put cont splash memory region under the reserved-memory
>>>> as confirmed by the downstream code as well.
>>>>
>>>> Signed-off-by: Amit Pundir <amit.pundir@linaro.org>
>>>> ---
>>>>    arch/arm64/boot/dts/qcom/sdm845-db845c.dts | 8 ++++++++
>>>>    1 file changed, 8 insertions(+)
>>>>
>>>> diff --git a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts
>>>> index f41c6d600ea8..2ae59432cbda 100644
>>>> --- a/arch/arm64/boot/dts/qcom/sdm845-db845c.dts
>>>> +++ b/arch/arm64/boot/dts/qcom/sdm845-db845c.dts
>>>> @@ -100,6 +100,14 @@ hdmi_con: endpoint {
>>>>                };
>>>>        };
>>>>
>>>> +     reserved-memory {
>>>> +             /* Cont splash region set up by the bootloader */
>>>> +             cont_splash_mem: framebuffer@9d400000 {
>>>> +                     reg = <0x0 0x9d400000 0x0 0x2400000>;
>>>> +                     no-map;
>>>> +             };
>>>> +     };
>>>> +
>>>>        lt9611_1v8: lt9611-vdd18-regulator {
>>>>                compatible = "regulator-fixed";
>>>>                regulator-name = "LT9611_1V8";
>>>
>>> Doesn't this mean we loose 0x2400000 of DRAM for all rb3 platforms
>>> though ? About what 37 megabytes.. ?
>>
>> I think this memory is further used for display memory allocation. So
>> we are not loosing it, but dedicating it to the framebuffer memory.
> Not exactly, to do so, you'd have to use the memory-region property
> with mdss, which nobody does. Otherwise it's just a hole for Linux.

Then maybe it's time to start using that property?

> 
> Konrad
>>
>>

On Thu, 9 Feb 2023 at 16:33, Bryan O'Donoghue
<bryan.odonoghue@linaro.org> wrote:
>
> On 09/02/2023 09:05, Amit Pundir wrote:
> > Hi, So what is the verdict on this patch?
> >
> > I submitted this fix to make sure UFS don't map and crash on it, which
> > I have seen happening occassionaly on db845c and Caleb reported
> > similar issues on his sdm845 device iirc. I should have probably put
> > that in my commit message as well.
> >
> > Regards,
> > Amit Pundir
>
> So the memory _is_ being used by ... continuous splash on an Android
> image, i.e. your Android ? limited to Android - image continues on with
> the splash but other blocks erroneously reuse the memory then, UFS as an
> example ?

Hi Bryan,

Yes UFS (reported only on v5.10) tries to map this reserved memory and
system crash and reboot. Plan is to backport this patch to v5.10.y.

Regards,
Amit Pundir

>
> ---
> bod