diff mbox series

arm64: dts: allwinner: a523: x96qpro+: overvolting eMMC

Message ID 20260720213832.3763-1-andre.przywara@arm.com (mailing list archive)
State New
Headers
Series arm64: dts: allwinner: a523: x96qpro+: overvolting eMMC |

Commit Message

Andre Przywara July 20, 2026, 9:38 p.m. UTC 
On the X96QPro+ TV box, the eMMC wasn't working properly: the chip would
be detected, but most requests failed, leaving it unusable. Some
"solutions" were circulating downstream, one "popular" one is severely
limiting the clock frequency, with a drastic performance impact.

Instead slightly bumping the I/O voltage on PortC from the canonical
1.8V to 1.9V seemed to do the trick: the eMMC now works and reaches the
expected 120MB/s performance.

Adjust the respective regulator voltage in the .dts to enable eMMC
operation on that device.

Signed-off-by: Andre Przywara <andre.przywara@arm.com>
---
Hi,

I am not super happy with this patch, but it seems to be a pragmatic and
the least hacky solution I have seen.

Cheers,
Andre

 arch/arm64/boot/dts/allwinner/sun55i-h728-x96qpro+.dts | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

Comments

sashiko-bot@kernel.org July 20, 2026, 9:50 p.m. UTC | #1 
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Bumping the eMMC IO regulator (`reg_cldo1`) to 1.9V inadvertently misconfigures the SoC's IO bank (Port C) into 3.3V power mode instead of 1.8V mode, creating a logic threshold mismatch.
--

--- Patch [1]: [PATCH] arm64: dts: allwinner: a523: x96qpro+: overvolting eMMC ---
commit e4c261c388d6e406babdf0d56ac61d104d537230
Author: Andre Przywara <andre.przywara@arm.com>
Date:   Mon Jul 20 21:38:32 2026 +0000

arm64: dts: allwinner: a523: x96qpro+: overvolting eMMC

This commit changes the eMMC IO regulator voltage on PortC from 1.8V to 1.9V
for the X96QPro+ device. The goal is to improve eMMC stability and performance
without drastically limiting the clock frequency.

> diff --git a/arch/arm64/boot/dts/allwinner/sun55i-h728-x96qpro+.dts b/arch/arm64/boot/dts/allwinner/sun55i-h728-x96qpro+.dts
> --- a/arch/arm64/boot/dts/allwinner/sun55i-h728-x96qpro+.dts
> +++ b/arch/arm64/boot/dts/allwinner/sun55i-h728-x96qpro+.dts
[ ... ]
> @@ -194,8 +194,8 @@ reg_bldo4: bldo4 {
>  
>  			reg_cldo1: cldo1 {
>  				regulator-always-on;
> -				regulator-min-microvolt = <1800000>;
> -				regulator-max-microvolt = <1800000>;
> +				regulator-min-microvolt = <1900000>;
> +				regulator-max-microvolt = <1900000>;

[Severity: High]
Does bumping this regulator to 1.9V inadvertently force the SoC's IO bank
(Port C) into 3.3V power mode?

Looking at sunxi_pinctrl_set_io_bias_cfg() in
drivers/pinctrl/sunxi/pinctrl-sunxi.c, the driver uses a strict check when
evaluating the voltage:

    case BIAS_VOLTAGE_PIO_POW_MODE_SEL:
        val = uV <= 1800000 ? 1 : 0;

Since 1900000 is greater than 1800000, this evaluates to 0 and clears the
PIO_POW_MOD_SEL register bit, incorrectly configuring the IO bank for 3.3V
mode while being powered at 1.9V.

Could this mismatch alter input receiver thresholds and drive strengths,
potentially causing signal integrity issues or long-term hardware
degradation?

>  				regulator-name = "vcc-codec-sd";
>  			};
Andre Przywara July 20, 2026, 11:13 p.m. UTC | #2 
On Mon, 20 Jul 2026 21:50:35 +0000
sashiko-bot@kernel.org wrote:

> Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
> - [High] Bumping the eMMC IO regulator (`reg_cldo1`) to 1.9V inadvertently misconfigures the SoC's IO bank (Port C) into 3.3V power mode instead of 1.8V mode, creating a logic threshold mismatch.

Huh, that's interesting, but might actually point to the real root
cause: it seems like the meaning of the bits in the withstand register
is inverted on the A523: 0 encodes 1.8V, a 1 encodes 3.3V. But that's
the opposite of the H6 definition, which we use in the kernel for the
A523 as well. Which means they were wrongly programmed before, but now
the wrong voltage selection turns out to trigger the really correct
setting.

So I will try playing around with those registers instead.

Cheers,
Andre.


> --
> 
> --- Patch [1]: [PATCH] arm64: dts: allwinner: a523: x96qpro+: overvolting eMMC ---
> commit e4c261c388d6e406babdf0d56ac61d104d537230
> Author: Andre Przywara <andre.przywara@arm.com>
> Date:   Mon Jul 20 21:38:32 2026 +0000
> 
> arm64: dts: allwinner: a523: x96qpro+: overvolting eMMC
> 
> This commit changes the eMMC IO regulator voltage on PortC from 1.8V to 1.9V
> for the X96QPro+ device. The goal is to improve eMMC stability and performance
> without drastically limiting the clock frequency.
> 
> > diff --git a/arch/arm64/boot/dts/allwinner/sun55i-h728-x96qpro+.dts b/arch/arm64/boot/dts/allwinner/sun55i-h728-x96qpro+.dts
> > --- a/arch/arm64/boot/dts/allwinner/sun55i-h728-x96qpro+.dts
> > +++ b/arch/arm64/boot/dts/allwinner/sun55i-h728-x96qpro+.dts
> [ ... ]
> > @@ -194,8 +194,8 @@ reg_bldo4: bldo4 {
> >  
> >  			reg_cldo1: cldo1 {
> >  				regulator-always-on;
> > -				regulator-min-microvolt = <1800000>;
> > -				regulator-max-microvolt = <1800000>;
> > +				regulator-min-microvolt = <1900000>;
> > +				regulator-max-microvolt = <1900000>;
> 
> [Severity: High]
> Does bumping this regulator to 1.9V inadvertently force the SoC's IO bank
> (Port C) into 3.3V power mode?
> 
> Looking at sunxi_pinctrl_set_io_bias_cfg() in
> drivers/pinctrl/sunxi/pinctrl-sunxi.c, the driver uses a strict check when
> evaluating the voltage:
> 
>     case BIAS_VOLTAGE_PIO_POW_MODE_SEL:
>         val = uV <= 1800000 ? 1 : 0;
> 
> Since 1900000 is greater than 1800000, this evaluates to 0 and clears the
> PIO_POW_MOD_SEL register bit, incorrectly configuring the IO bank for 3.3V
> mode while being powered at 1.9V.
> 
> Could this mismatch alter input receiver thresholds and drive strengths,
> potentially causing signal integrity issues or long-term hardware
> degradation?
> 
> >  				regulator-name = "vcc-codec-sd";
> >  			};
>
diff mbox series

Patch

diff --git a/arch/arm64/boot/dts/allwinner/sun55i-h728-x96qpro+.dts b/arch/arm64/boot/dts/allwinner/sun55i-h728-x96qpro+.dts
index a96927fbdadd5..5636e95312218 100644
--- a/arch/arm64/boot/dts/allwinner/sun55i-h728-x96qpro+.dts
+++ b/arch/arm64/boot/dts/allwinner/sun55i-h728-x96qpro+.dts
@@ -194,8 +194,8 @@  reg_bldo4: bldo4 {
 
 			reg_cldo1: cldo1 {
 				regulator-always-on;
-				regulator-min-microvolt = <1800000>;
-				regulator-max-microvolt = <1800000>;
+				regulator-min-microvolt = <1900000>;
+				regulator-max-microvolt = <1900000>;
 				regulator-name = "vcc-codec-sd";
 			};