* Re: [PATCH v3 4/9] ASoC: dt-bindings: loongson,ls-audio-card: Use common sound card
From: sashiko-bot @ 2026-06-26 2:37 UTC (permalink / raw)
To: Binbin Zhou; +Cc: devicetree, robh, conor+dt
In-Reply-To: <fa72a429a9d076d381f7d514184f19d5a35ffa51.1782439646.git.zhoubinbin@loongson.cn>
Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
Pre-existing issues:
- [High] Global state corruption via in-place modification of static DAI links array and codec string buffer.
- [High] Sysfs and ASoC component name collision via illegal `dev_set_name` override during probe.
- [High] Bitwise read-modify-write bug without clearing target bitfields causes incorrect APB DMA routing.
--
commit 864c9404304a7ef17062fbe81f6d13b229c50a0d
Author: Binbin Zhou <zhoubinbin@loongson.cn>
Subject: ASoC: dt-bindings: loongson,ls-audio-card: Use common sound card
This commit updates the loongson,ls-audio-card binding to reference the common
sound card schema. It removes the user specified model property and
transitions to evaluating additional properties via unevaluatedProperties.
> diff --git a/Documentation/devicetree/bindings/sound/loongson,ls-audio-card.yaml b/Documentation/devicetree/bindings/sound/loongson,ls-audio-card.yaml
> index 61e8babed402f..e1b7445a8b22f 100644
> --- a/Documentation/devicetree/bindings/sound/loongson,ls-audio-card.yaml
> +++ b/Documentation/devicetree/bindings/sound/loongson,ls-audio-card.yaml
[ ... ]
While reviewing the related sound driver for this binding, I noticed a few
pre-existing items in the driver code.
[Severity: High]
This is a pre-existing issue, but I noticed a potential problem in the
sound card driver when handling multiple instances.
In sound/soc/loongson/loongson_card.c:loongson_card_parse_acpi():
loongson_dai_links[i].platforms->name = dev_name(phy_dev);
loongson_dai_links[i].codecs->name = codec_name;
loongson_dai_links[i].codecs->dai_name = codec_dai_name;
And similarly in sound/soc/loongson/loongson_card.c:loongson_card_parse_of():
ret = snd_soc_of_get_dlc(cpu, NULL, loongson_dai_links[i].cpus, 0);
...
loongson_dai_links[i].platforms->of_node =
loongson_dai_links[i].cpus->of_node;
ret = snd_soc_of_get_dlc(codec, NULL, loongson_dai_links[i].codecs, 0);
Will this corrupt the shared static loongson_dai_links array if multiple
sound cards are instantiated via the device tree or ACPI tables?
If multiple instances are probed, they might overwrite each other's
DAI links and codec strings. Should these structures be dynamically
allocated instead of mutating shared static memory?
[Severity: High]
This is a pre-existing issue, but there might be a sysfs naming collision
in the I2S platform driver.
In sound/soc/loongson/loongson_i2s_plat.c:loongson_i2s_plat_probe():
dev_set_name(dev, LS_I2S_DRVNAME);
Could this override cause duplicate ASoC component names if multiple I2S
controllers are instantiated in the device tree?
Calling dev_set_name during probe after the device is added to sysfs might
break internal kernel tracking and cause probe failures for subsequent
instances.
[Severity: High]
This is a pre-existing issue, but there appears to be a bitwise
read-modify-write problem in the APB DMA configuration.
In sound/soc/loongson/loongson_i2s_plat.c:loongson_i2s_apbdma_config():
val |= LOONGSON_DMA2_CONF << LOONGSON_I2S_TX_DMA_OFFSET;
val |= LOONGSON_DMA3_CONF << LOONGSON_I2S_RX_DMA_OFFSET;
Does this code correctly handle cases where the bootloader or previous
firmware left the DMA configuration register in a non-zero state?
Since LOONGSON_DMA2_CONF occupies multiple bits, if other bits are
already set, the bitwise OR will blend the values instead of strictly
setting the field.
Should the target bitfields be cleared via a bitwise AND mask before
applying the new configuration?
--
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1782439646.git.zhoubinbin@loongson.cn?part=4
^ permalink raw reply
* Re: [PATCH v3 3/9] ASoC: loongson: Add Loongson-2K0300 I2S controller support
From: sashiko-bot @ 2026-06-26 2:37 UTC (permalink / raw)
To: Binbin Zhou; +Cc: robh, devicetree, conor+dt
In-Reply-To: <4d3caa62d4275e1495505387198408f4d30d453c.1782439646.git.zhoubinbin@loongson.cn>
Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
New issues:
- [High] Missing hardware quirk reset sequence on system resume.
- [Medium] Read-Modify-Write on a volatile control register can unintentionally re-enable transient hardware states during soft reset.
Pre-existing issues:
- [High] Illegal overriding of platform device name during probe leading to Use-After-Free and sysfs corruption.
--
commit b9499f3634cc6b7a7bad0f418f80a05c56aa0954
Author: Binbin Zhou <zhoubinbin@loongson.cn>
ASoC: loongson: Add Loongson-2K0300 I2S controller support
The Loongson-2K0300 I2S interface differs significantly from the
Loongson-2K1000. Although both utilize external DMA controllers, the
Loongson-2K0300 does not require additional registers for routing
configuration.
Due to hardware design flaw, an extra controller reset sequence is
required during probe.
> diff --git a/sound/soc/loongson/loongson_i2s_plat.c b/sound/soc/loongson/loongson_i2s_plat.c
> index ac054b6ce6322..82d95c6644ef0 100644
> --- a/sound/soc/loongson/loongson_i2s_plat.c
> +++ b/sound/soc/loongson/loongson_i2s_plat.c
[ ... ]
> @@ -87,11 +108,17 @@ static int loongson_i2s_plat_probe(struct platform_device *pdev)
> if (IS_ERR(i2s_clk))
> return dev_err_probe(dev, PTR_ERR(i2s_clk), "clock property invalid\n");
> i2s->clk_rate = clk_get_rate(i2s_clk);
> + i2s->rev_id = plat_config->rev_id;
>
> dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
> dev_set_name(dev, LS_I2S_DRVNAME);
[Severity: High]
This is a pre-existing issue, but does calling dev_set_name() on an already
registered platform device cause a use-after-free?
Calling dev_set_name() here frees the existing kobj->name without renaming
the underlying sysfs directory.
Could this corrupt the kobject state and lead to kernel warnings upon device
removal?
> dev_set_drvdata(dev, i2s);
>
> + if (i2s->rev_id == 1) {
> + regmap_update_bits(i2s->regmap, LS_I2S_CTRL, I2S_CTRL_RESET, I2S_CTRL_RESET);
[Severity: High]
Since this controller requires a reset due to a hardware flaw, does it also
need this reset applied in the resume path?
When the system suspends, power to the controller is typically lost. Upon
resume, the shared i2s_resume() function is called:
sound/soc/loongson/loongson_i2s.c:i2s_resume() {
struct loongson_i2s *i2s = dev_get_drvdata(dev);
regcache_cache_only(i2s->regmap, false);
return regcache_sync(i2s->regmap);
}
Because LS_I2S_CTRL is typically a volatile register, regcache_sync() will
not automatically restore it. Will this leave the hardware design flaw
unmitigated after a suspend/resume cycle?
[Severity: Medium]
Does using regmap_update_bits() on a volatile control register risk
preserving unintended active states during the soft reset?
Since this performs a read-modify-write, if the bootloader or previous
uninitialized state left other functional bits active, they might be
logically preserved and kept enabled during the reset sequence.
Would it be safer to use regmap_write() to assert the reset while explicitly
ensuring all other functional bits are zeroed out?
> + fsleep(200);
> + }
> +
> ret = devm_snd_soc_register_component(dev, &loongson_i2s_edma_component,
> &loongson_i2s_dai, 1);
> if (ret)
--
Sashiko AI review · https://sashiko.dev/#/patchset/cover.1782439646.git.zhoubinbin@loongson.cn?part=3
^ permalink raw reply
* [PATCH V3 8/8] arm64: dts: imx8qxp-mek: Describe the PCIe M.2 Key E connector
From: Sherry Sun (OSS) @ 2026-06-26 2:31 UTC (permalink / raw)
To: robh, krzk+dt, conor+dt, Frank.Li, s.hauer, kernel, festevam,
amitkumar.karwar, neeraj.sanjaykale, marcel, luiz.dentz,
hongxing.zhu, l.stach, lpieralisi, kwilczynski, mani, bhelgaas,
brgl
Cc: imx, linux-pci, linux-arm-kernel, devicetree, linux-kernel,
linux-bluetooth, linux-pm, sherry.sun
In-Reply-To: <20260626023126.2189931-1-sherry.sun@oss.nxp.com>
From: Sherry Sun <sherry.sun@nxp.com>
The i.MX8QXP-MEK has the PCIe M.2 Mechanical Key E connector to connect
wireless connectivity cards over PCIe and UART interfaces. Hence,
describe the connector node and link it with the PCIe b Root Port and
LPUART1 nodes through graph port/endpoint.
The M.2 Key E connector is powered by a 3.3V fixed regulator
(reg_3v3) on board.
Signed-off-by: Sherry Sun <sherry.sun@nxp.com>
---
arch/arm64/boot/dts/freescale/imx8qxp-mek.dts | 54 ++++++++++++++-----
1 file changed, 41 insertions(+), 13 deletions(-)
diff --git a/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts b/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts
index a9b967d0a9be..c9fe4034cc2d 100644
--- a/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts
+++ b/arch/arm64/boot/dts/freescale/imx8qxp-mek.dts
@@ -40,6 +40,37 @@ memory@80000000 {
reg = <0x00000000 0x80000000 0 0x40000000>;
};
+ m2-connector {
+ compatible = "pcie-m2-e-connector";
+ vpcie3v3-supply = <®_3v3>;
+ w-disable1-gpios = <&pca9557_a 2 GPIO_ACTIVE_LOW>;
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0>;
+ m2_e_pcie_ep: endpoint@0 {
+ reg = <0>;
+ remote-endpoint = <&pcieb_port0_ep>;
+ };
+ };
+
+ port@3 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <3>;
+ m2_e_uart_ep: endpoint@0 {
+ reg = <0>;
+ remote-endpoint = <&lpuart1_ep>;
+ };
+ };
+ };
+ };
+
reg_usdhc2_vmmc: usdhc2-vmmc {
compatible = "regulator-fixed";
regulator-name = "SD1_SPWR";
@@ -157,15 +188,6 @@ reg_3v3: regulator-3v3 {
regulator-max-microvolt = <3300000>;
};
- reg_pcieb: regulator-pcie {
- compatible = "regulator-fixed";
- regulator-max-microvolt = <3300000>;
- regulator-min-microvolt = <3300000>;
- regulator-name = "mpcie_3v3";
- gpio = <&pca9557_a 2 GPIO_ACTIVE_HIGH>;
- enable-active-high;
- };
-
reg_audio: regulator-audio {
compatible = "regulator-fixed";
regulator-max-microvolt = <3300000>;
@@ -696,8 +718,10 @@ &lpuart1 {
pinctrl-0 = <&pinctrl_lpuart1>;
status = "okay";
- bluetooth {
- compatible = "nxp,88w8987-bt";
+ port {
+ lpuart1_ep: endpoint {
+ remote-endpoint = <&m2_e_uart_ep>;
+ };
};
};
@@ -746,8 +770,12 @@ &pcie0_ep {
&pcieb_port0 {
reset-gpios = <&lsio_gpio4 0 GPIO_ACTIVE_LOW>;
- vpcie-supply = <®_pcieb>;
- vpcie3v3aux-supply = <®_pcieb>;
+
+ port {
+ pcieb_port0_ep: endpoint {
+ remote-endpoint = <&m2_e_pcie_ep>;
+ };
+ };
};
&scu_key {
--
2.50.1
^ permalink raw reply related
* [PATCH V3 7/8] arm64: dts: imx8qm-mek: Describe the PCIe M.2 Key E connector
From: Sherry Sun (OSS) @ 2026-06-26 2:31 UTC (permalink / raw)
To: robh, krzk+dt, conor+dt, Frank.Li, s.hauer, kernel, festevam,
amitkumar.karwar, neeraj.sanjaykale, marcel, luiz.dentz,
hongxing.zhu, l.stach, lpieralisi, kwilczynski, mani, bhelgaas,
brgl
Cc: imx, linux-pci, linux-arm-kernel, devicetree, linux-kernel,
linux-bluetooth, linux-pm, sherry.sun
In-Reply-To: <20260626023126.2189931-1-sherry.sun@oss.nxp.com>
From: Sherry Sun <sherry.sun@nxp.com>
The i.MX8QM-MEK has the PCIe M.2 Mechanical Key E connector to connect
wireless connectivity cards over PCIe and UART interfaces. Hence,
describe the connector node and link it with the PCIe a Root Port and
LPUART1 nodes through graph port/endpoint.
The M.2 Key E connector is powered by a 3.3V fixed regulator
(reg_3v3) on board.
Signed-off-by: Sherry Sun <sherry.sun@nxp.com>
---
arch/arm64/boot/dts/freescale/imx8qm-mek.dts | 58 +++++++++++++++-----
1 file changed, 43 insertions(+), 15 deletions(-)
diff --git a/arch/arm64/boot/dts/freescale/imx8qm-mek.dts b/arch/arm64/boot/dts/freescale/imx8qm-mek.dts
index 5e725ad8aef9..4c02592cfe14 100644
--- a/arch/arm64/boot/dts/freescale/imx8qm-mek.dts
+++ b/arch/arm64/boot/dts/freescale/imx8qm-mek.dts
@@ -32,6 +32,39 @@ memory@80000000 {
reg = <0x00000000 0x80000000 0 0x40000000>;
};
+ m2-connector {
+ compatible = "pcie-m2-e-connector";
+ pinctrl-0 = <&pinctrl_pciea_reg>;
+ pinctrl-names = "default";
+ vpcie3v3-supply = <®_3v3>;
+ w-disable1-gpios = <&lsio_gpio1 13 GPIO_ACTIVE_LOW>;
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0>;
+ m2_e_pcie_ep: endpoint@0 {
+ reg = <0>;
+ remote-endpoint = <&pciea_port0_ep>;
+ };
+ };
+
+ port@3 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <3>;
+ m2_e_uart_ep: endpoint@0 {
+ reg = <0>;
+ remote-endpoint = <&lpuart1_ep>;
+ };
+ };
+ };
+ };
+
xtal24m: clock-xtal24m {
compatible = "fixed-clock";
#clock-cells = <0>;
@@ -320,17 +353,6 @@ reg_can2_stby: regulator-can2-stby {
vin-supply = <®_can2_en>;
};
- reg_pciea: regulator-pcie {
- compatible = "regulator-fixed";
- pinctrl-0 = <&pinctrl_pciea_reg>;
- pinctrl-names = "default";
- regulator-max-microvolt = <3300000>;
- regulator-min-microvolt = <3300000>;
- regulator-name = "mpcie_3v3";
- gpio = <&lsio_gpio1 13 GPIO_ACTIVE_HIGH>;
- enable-active-high;
- };
-
reg_usb_otg1_vbus: regulator-usbotg1-vbus {
compatible = "regulator-fixed";
regulator-name = "usb_otg1_vbus";
@@ -718,8 +740,10 @@ &lpuart1 {
pinctrl-0 = <&pinctrl_lpuart1>;
status = "okay";
- bluetooth {
- compatible = "nxp,88w8987-bt";
+ port {
+ lpuart1_ep: endpoint {
+ remote-endpoint = <&m2_e_uart_ep>;
+ };
};
};
@@ -818,8 +842,12 @@ &pciea {
&pciea_port0 {
reset-gpios = <&lsio_gpio4 29 GPIO_ACTIVE_LOW>;
- vpcie-supply = <®_pciea>;
- vpcie3v3aux-supply = <®_pciea>;
+
+ port {
+ pciea_port0_ep: endpoint {
+ remote-endpoint = <&m2_e_pcie_ep>;
+ };
+ };
};
&pcieb {
--
2.50.1
^ permalink raw reply related
* [PATCH V3 6/8] arm64: dts: imx8dxl-evk: Describe the PCIe M.2 Key E connector
From: Sherry Sun (OSS) @ 2026-06-26 2:31 UTC (permalink / raw)
To: robh, krzk+dt, conor+dt, Frank.Li, s.hauer, kernel, festevam,
amitkumar.karwar, neeraj.sanjaykale, marcel, luiz.dentz,
hongxing.zhu, l.stach, lpieralisi, kwilczynski, mani, bhelgaas,
brgl
Cc: imx, linux-pci, linux-arm-kernel, devicetree, linux-kernel,
linux-bluetooth, linux-pm, sherry.sun
In-Reply-To: <20260626023126.2189931-1-sherry.sun@oss.nxp.com>
From: Sherry Sun <sherry.sun@nxp.com>
The i.MX8DXL-EVK has the PCIe M.2 Mechanical Key E connector to connect
wireless connectivity cards over PCIe and UART interfaces. Hence,
describe the connector node and link it with the PCIe b Root Port and
LPUART1 nodes through graph port/endpoint.
The M.2 Key E connector is powered by a 3.3V fixed regulator
(reg_audio_3v3), add a reg_3v3 label to avoid confusion.
Signed-off-by: Sherry Sun <sherry.sun@nxp.com>
---
arch/arm64/boot/dts/freescale/imx8dxl-evk.dts | 56 ++++++++++++++-----
1 file changed, 42 insertions(+), 14 deletions(-)
diff --git a/arch/arm64/boot/dts/freescale/imx8dxl-evk.dts b/arch/arm64/boot/dts/freescale/imx8dxl-evk.dts
index 1084164d1381..6afee1f1a9fc 100644
--- a/arch/arm64/boot/dts/freescale/imx8dxl-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8dxl-evk.dts
@@ -42,6 +42,37 @@ memory@80000000 {
reg = <0x00000000 0x80000000 0 0x40000000>;
};
+ m2-connector {
+ compatible = "pcie-m2-e-connector";
+ vpcie3v3-supply = <®_3v3>;
+ w-disable1-gpios = <&pca6416_1 13 GPIO_ACTIVE_LOW>;
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0>;
+ m2_e_pcie_ep: endpoint@0 {
+ reg = <0>;
+ remote-endpoint = <&pcieb_port0_ep>;
+ };
+ };
+
+ port@3 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <3>;
+ m2_e_uart_ep: endpoint@0 {
+ reg = <0>;
+ remote-endpoint = <&lpuart1_ep>;
+ };
+ };
+ };
+ };
+
reserved-memory {
#address-cells = <2>;
#size-cells = <2>;
@@ -182,15 +213,6 @@ mii_select: regulator-4 {
regulator-always-on;
};
- reg_pcieb: regulator-pcieb {
- compatible = "regulator-fixed";
- regulator-max-microvolt = <3300000>;
- regulator-min-microvolt = <3300000>;
- regulator-name = "reg_pcieb";
- gpio = <&pca6416_1 13 GPIO_ACTIVE_HIGH>;
- enable-active-high;
- };
-
reg_audio_5v: regulator-audio-pwr {
compatible = "regulator-fixed";
regulator-name = "audio-5v";
@@ -200,7 +222,7 @@ reg_audio_5v: regulator-audio-pwr {
regulator-boot-on;
};
- reg_audio_3v3: regulator-audio-3v3 {
+ reg_3v3: reg_audio_3v3: regulator-audio-3v3 {
compatible = "regulator-fixed";
regulator-name = "audio-3v3";
regulator-min-microvolt = <3300000>;
@@ -623,8 +645,10 @@ &lpuart1 {
pinctrl-0 = <&pinctrl_lpuart1>;
status = "okay";
- bluetooth {
- compatible = "nxp,88w8987-bt";
+ port {
+ lpuart1_ep: endpoint {
+ remote-endpoint = <&m2_e_uart_ep>;
+ };
};
};
@@ -690,8 +714,12 @@ &pcie0_ep {
&pcieb_port0 {
reset-gpios = <&lsio_gpio4 0 GPIO_ACTIVE_LOW>;
- vpcie-supply = <®_pcieb>;
- vpcie3v3aux-supply = <®_pcieb>;
+
+ port {
+ pcieb_port0_ep: endpoint {
+ remote-endpoint = <&m2_e_pcie_ep>;
+ };
+ };
};
&sai0 {
--
2.50.1
^ permalink raw reply related
* [PATCH V3 5/8] arm64: dts: imx95-19x19-evk: Describe the PCIe M.2 Key E connector
From: Sherry Sun (OSS) @ 2026-06-26 2:31 UTC (permalink / raw)
To: robh, krzk+dt, conor+dt, Frank.Li, s.hauer, kernel, festevam,
amitkumar.karwar, neeraj.sanjaykale, marcel, luiz.dentz,
hongxing.zhu, l.stach, lpieralisi, kwilczynski, mani, bhelgaas,
brgl
Cc: imx, linux-pci, linux-arm-kernel, devicetree, linux-kernel,
linux-bluetooth, linux-pm, sherry.sun
In-Reply-To: <20260626023126.2189931-1-sherry.sun@oss.nxp.com>
From: Sherry Sun <sherry.sun@nxp.com>
The i.MX95-19x19-EVK has the PCIe M.2 Mechanical Key E connector to
connect wireless connectivity cards over PCIe and UART interfaces. Hence,
describe the connector node and link it with the PCIe 0 Root Port and
LPUART5 nodes through graph port/endpoint.
Signed-off-by: Sherry Sun <sherry.sun@nxp.com>
---
.../boot/dts/freescale/imx95-19x19-evk.dts | 55 ++++++++++++++-----
1 file changed, 41 insertions(+), 14 deletions(-)
diff --git a/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts b/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts
index c08731dfb1ee..d2c0345f0d61 100644
--- a/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx95-19x19-evk.dts
@@ -57,6 +57,37 @@ memory@80000000 {
reg = <0x0 0x80000000 0 0x80000000>;
};
+ m2-connector {
+ compatible = "pcie-m2-e-connector";
+ vpcie3v3-supply = <®_m2_pwr>;
+ w-disable1-gpios = <&i2c7_pcal6524 6 GPIO_ACTIVE_LOW>;
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0>;
+ m2_e_pcie_ep: endpoint@0 {
+ reg = <0>;
+ remote-endpoint = <&pcie0_port0_ep>;
+ };
+ };
+
+ port@3 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <3>;
+ m2_e_uart_ep: endpoint@0 {
+ reg = <0>;
+ remote-endpoint = <&lpuart5_ep>;
+ };
+ };
+ };
+ };
+
fan0: pwm-fan {
compatible = "pwm-fan";
#cooling-cells = <2>;
@@ -145,16 +176,6 @@ reg_m2_pwr: regulator-m2-pwr {
startup-delay-us = <5000>;
};
- reg_pcie0: regulator-pcie {
- compatible = "regulator-fixed";
- regulator-name = "PCIE_WLAN_EN";
- regulator-min-microvolt = <3300000>;
- regulator-max-microvolt = <3300000>;
- vin-supply = <®_m2_pwr>;
- gpio = <&i2c7_pcal6524 6 GPIO_ACTIVE_HIGH>;
- enable-active-high;
- };
-
reg_slot_pwr: regulator-slot-pwr {
compatible = "regulator-fixed";
regulator-name = "PCIe slot-power";
@@ -477,8 +498,10 @@ &lpuart5 {
pinctrl-0 = <&pinctrl_uart5>;
status = "okay";
- bluetooth {
- compatible = "nxp,88w8987-bt";
+ port {
+ lpuart5_ep: endpoint {
+ remote-endpoint = <&m2_e_uart_ep>;
+ };
};
};
@@ -555,8 +578,12 @@ &pcie0_ep {
&pcie0_port0 {
reset-gpios = <&i2c7_pcal6524 5 GPIO_ACTIVE_LOW>;
- vpcie-supply = <®_pcie0>;
- vpcie3v3aux-supply = <®_pcie0>;
+
+ port {
+ pcie0_port0_ep: endpoint {
+ remote-endpoint = <&m2_e_pcie_ep>;
+ };
+ };
};
&pcie1 {
--
2.50.1
^ permalink raw reply related
* [PATCH V3 4/8] arm64: dts: imx8mq-evk: Describe the PCIe M.2 Key E connector
From: Sherry Sun (OSS) @ 2026-06-26 2:31 UTC (permalink / raw)
To: robh, krzk+dt, conor+dt, Frank.Li, s.hauer, kernel, festevam,
amitkumar.karwar, neeraj.sanjaykale, marcel, luiz.dentz,
hongxing.zhu, l.stach, lpieralisi, kwilczynski, mani, bhelgaas,
brgl
Cc: imx, linux-pci, linux-arm-kernel, devicetree, linux-kernel,
linux-bluetooth, linux-pm, sherry.sun
In-Reply-To: <20260626023126.2189931-1-sherry.sun@oss.nxp.com>
From: Sherry Sun <sherry.sun@nxp.com>
The i.MX8MQ-EVK has the PCIe M.2 Mechanical Key E connector to connect
wireless connectivity cards over PCIe and UART interfaces. Hence,
describe the connector node and link it with the PCIe 1 Root Port and
UART3 nodes through graph port/endpoint.
Signed-off-by: Sherry Sun <sherry.sun@nxp.com>
---
arch/arm64/boot/dts/freescale/imx8mq-evk.dts | 44 ++++++++++++++++++--
1 file changed, 40 insertions(+), 4 deletions(-)
diff --git a/arch/arm64/boot/dts/freescale/imx8mq-evk.dts b/arch/arm64/boot/dts/freescale/imx8mq-evk.dts
index 71504a0af87f..482e5203e879 100644
--- a/arch/arm64/boot/dts/freescale/imx8mq-evk.dts
+++ b/arch/arm64/boot/dts/freescale/imx8mq-evk.dts
@@ -21,6 +21,36 @@ memory@40000000 {
reg = <0x00000000 0x40000000 0 0xc0000000>;
};
+ m2-connector {
+ compatible = "pcie-m2-e-connector";
+ vpcie3v3-supply = <®_pcie1>;
+
+ ports {
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+ port@0 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <0>;
+ m2_e_pcie_ep: endpoint@0 {
+ reg = <0>;
+ remote-endpoint = <&pcie1_port0_ep>;
+ };
+ };
+
+ port@3 {
+ #address-cells = <1>;
+ #size-cells = <0>;
+ reg = <3>;
+ m2_e_uart_ep: endpoint@0 {
+ reg = <0>;
+ remote-endpoint = <&uart3_ep>;
+ };
+ };
+ };
+ };
+
pcie0_refclk: pcie0-refclk {
compatible = "fixed-clock";
#clock-cells = <0>;
@@ -420,8 +450,12 @@ &pcie1_ep {
&pcie1_port0 {
reset-gpios = <&gpio5 12 GPIO_ACTIVE_LOW>;
- vpcie-supply = <®_pcie1>;
- vpcie3v3aux-supply = <®_pcie1>;
+
+ port {
+ pcie1_port0_ep: endpoint {
+ remote-endpoint = <&m2_e_pcie_ep>;
+ };
+ };
};
&pgc_gpu {
@@ -506,8 +540,10 @@ &uart3 { /* BT */
uart-has-rtscts;
status = "okay";
- bluetooth {
- compatible = "nxp,88w8987-bt";
+ port {
+ uart3_ep: endpoint {
+ remote-endpoint = <&m2_e_uart_ep>;
+ };
};
};
--
2.50.1
^ permalink raw reply related
* [PATCH V3 3/8] Bluetooth: btnxpuart: Add M.2 Bluetooth device support using pwrseq
From: Sherry Sun (OSS) @ 2026-06-26 2:31 UTC (permalink / raw)
To: robh, krzk+dt, conor+dt, Frank.Li, s.hauer, kernel, festevam,
amitkumar.karwar, neeraj.sanjaykale, marcel, luiz.dentz,
hongxing.zhu, l.stach, lpieralisi, kwilczynski, mani, bhelgaas,
brgl
Cc: imx, linux-pci, linux-arm-kernel, devicetree, linux-kernel,
linux-bluetooth, linux-pm, sherry.sun
In-Reply-To: <20260626023126.2189931-1-sherry.sun@oss.nxp.com>
From: Sherry Sun <sherry.sun@nxp.com>
Power supply to the M.2 Bluetooth device attached to the host using M.2
connector is controlled using the 'uart' pwrseq device. So add support for
getting the pwrseq device if the OF graph link is present. Once obtained,
pwrseq_power_on() is called to power up the M.2 Bluetooth card. The power
sequencer descriptor is obtained via devm_pwrseq_get(), so the power-off
and cleanup are handled automatically when the device is unbound.
Signed-off-by: Sherry Sun <sherry.sun@nxp.com>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@oss.qualcomm.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
---
drivers/bluetooth/btnxpuart.c | 14 ++++++++++++++
1 file changed, 14 insertions(+)
diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
index e7036a48ce48..438ccaa2b56d 100644
--- a/drivers/bluetooth/btnxpuart.c
+++ b/drivers/bluetooth/btnxpuart.c
@@ -9,6 +9,8 @@
#include <linux/serdev.h>
#include <linux/of.h>
+#include <linux/of_graph.h>
+#include <linux/pwrseq/consumer.h>
#include <linux/skbuff.h>
#include <linux/unaligned.h>
#include <linux/firmware.h>
@@ -1866,6 +1868,18 @@ static int nxp_serdev_probe(struct serdev_device *serdev)
return err;
}
+ if (of_graph_is_present(dev_of_node(&serdev->ctrl->dev))) {
+ struct pwrseq_desc *pwrseq;
+
+ pwrseq = devm_pwrseq_get(&serdev->ctrl->dev, "uart");
+ if (IS_ERR(pwrseq))
+ return PTR_ERR(pwrseq);
+
+ err = pwrseq_power_on(pwrseq);
+ if (err)
+ return err;
+ }
+
/* Initialize and register HCI device */
hdev = hci_alloc_dev();
if (!hdev) {
--
2.50.1
^ permalink raw reply related
* [PATCH V3 2/8] power: sequencing: pcie-m2: Add PCI ID for NXP 88W9098 and AW693 Bluetooth
From: Sherry Sun (OSS) @ 2026-06-26 2:31 UTC (permalink / raw)
To: robh, krzk+dt, conor+dt, Frank.Li, s.hauer, kernel, festevam,
amitkumar.karwar, neeraj.sanjaykale, marcel, luiz.dentz,
hongxing.zhu, l.stach, lpieralisi, kwilczynski, mani, bhelgaas,
brgl
Cc: imx, linux-pci, linux-arm-kernel, devicetree, linux-kernel,
linux-bluetooth, linux-pm, sherry.sun
In-Reply-To: <20260626023126.2189931-1-sherry.sun@oss.nxp.com>
From: Sherry Sun <sherry.sun@nxp.com>
88W9098 is a NXP Wi-Fi/BT combo chip with PCI device ID 0x2b43 under
Marvell Extended vendor ID. AW693 is a NXP Wi-Fi/BT combo chip with
PCI device ID 0x3003 under NXP/Philips vendor ID.
Add both chips to pwrseq_m2_pci_ids[] so that the pwrseq-pcie-m2 driver
can create the Bluetooth serdev device when these cards are inserted into
a PCIe M.2 Key E connector.
Both chips use "nxp,88w8987-bt" as the serdev compatible string, which
is the entry point for the btnxpuart driver. The driver identifies the
actual chip variant at runtime via chip ID auto-detection and loads the
appropriate firmware accordingly.
Signed-off-by: Sherry Sun <sherry.sun@nxp.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Reviewed-by: Manivannan Sadhasivam <mani@kernel.org>
---
drivers/power/sequencing/pwrseq-pcie-m2.c | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/drivers/power/sequencing/pwrseq-pcie-m2.c b/drivers/power/sequencing/pwrseq-pcie-m2.c
index b5ed80d03953..e3ba9169144d 100644
--- a/drivers/power/sequencing/pwrseq-pcie-m2.c
+++ b/drivers/power/sequencing/pwrseq-pcie-m2.c
@@ -186,6 +186,10 @@ static int pwrseq_pcie_m2_match(struct pwrseq_device *pwrseq,
}
static const struct pci_device_id pwrseq_m2_pci_ids[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_MARVELL_EXT, 0x2b43),
+ .driver_data = (kernel_ulong_t)"nxp,88w8987-bt" },
+ { PCI_DEVICE(PCI_VENDOR_ID_PHILIPS, 0x3003),
+ .driver_data = (kernel_ulong_t)"nxp,88w8987-bt" },
{ PCI_DEVICE(PCI_VENDOR_ID_QCOM, 0x1103),
.driver_data = (kernel_ulong_t)"qcom,wcn6855-bt" },
{ PCI_DEVICE(PCI_VENDOR_ID_QCOM, 0x1107),
--
2.50.1
^ permalink raw reply related
* [PATCH V3 1/8] PCI: imx6: Add skip_pwrctrl_off flag support
From: Sherry Sun (OSS) @ 2026-06-26 2:31 UTC (permalink / raw)
To: robh, krzk+dt, conor+dt, Frank.Li, s.hauer, kernel, festevam,
amitkumar.karwar, neeraj.sanjaykale, marcel, luiz.dentz,
hongxing.zhu, l.stach, lpieralisi, kwilczynski, mani, bhelgaas,
brgl
Cc: imx, linux-pci, linux-arm-kernel, devicetree, linux-kernel,
linux-bluetooth, linux-pm, sherry.sun
In-Reply-To: <20260626023126.2189931-1-sherry.sun@oss.nxp.com>
From: Sherry Sun <sherry.sun@nxp.com>
Use dw_pcie_rp::skip_pwrctrl_off to avoid powering off devices during
suspend to preserve wakeup capability of the devices and also not to power
on the devices in the init path.
This allows controller power-off to be skipped when some devices(e.g. M.2
cards key E without auxiliary power) required to support PCIe L2 link state
and wake-up mechanisms.
Move pci_pwrctrl_create_devices() to imx_pcie_probe() so that it is only
called once during probe, similar to other regulator_get calls.
Signed-off-by: Sherry Sun <sherry.sun@nxp.com>
---
drivers/pci/controller/dwc/pci-imx6.c | 43 ++++++++++++++++-----------
1 file changed, 25 insertions(+), 18 deletions(-)
diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index 0fa716d1ed75..0685573fee71 100644
--- a/drivers/pci/controller/dwc/pci-imx6.c
+++ b/drivers/pci/controller/dwc/pci-imx6.c
@@ -1382,16 +1382,12 @@ static int imx_pcie_host_init(struct dw_pcie_rp *pp)
}
}
- ret = pci_pwrctrl_create_devices(dev);
- if (ret) {
- dev_err(dev, "failed to create pwrctrl devices\n");
- goto err_reg_disable;
- }
-
- ret = pci_pwrctrl_power_on_devices(dev);
- if (ret) {
- dev_err(dev, "failed to power on pwrctrl devices\n");
- goto err_pwrctrl_destroy;
+ if (!pp->skip_pwrctrl_off) {
+ ret = pci_pwrctrl_power_on_devices(dev);
+ if (ret) {
+ dev_err(dev, "failed to power on pwrctrl devices\n");
+ goto err_reg_disable;
+ }
}
ret = imx_pcie_clk_enable(imx_pcie);
@@ -1460,10 +1456,8 @@ static int imx_pcie_host_init(struct dw_pcie_rp *pp)
err_clk_disable:
imx_pcie_clk_disable(imx_pcie);
err_pwrctrl_power_off:
- pci_pwrctrl_power_off_devices(dev);
-err_pwrctrl_destroy:
- if (ret != -EPROBE_DEFER)
- pci_pwrctrl_destroy_devices(dev);
+ if (!pp->skip_pwrctrl_off)
+ pci_pwrctrl_power_off_devices(dev);
err_reg_disable:
if (imx_pcie->vpcie)
regulator_disable(imx_pcie->vpcie);
@@ -1482,7 +1476,8 @@ static void imx_pcie_host_exit(struct dw_pcie_rp *pp)
}
imx_pcie_clk_disable(imx_pcie);
- pci_pwrctrl_power_off_devices(pci->dev);
+ if (!pci->pp.skip_pwrctrl_off)
+ pci_pwrctrl_power_off_devices(pci->dev);
if (imx_pcie->vpcie)
regulator_disable(imx_pcie->vpcie);
}
@@ -1954,11 +1949,15 @@ static int imx_pcie_probe(struct platform_device *pdev)
if (ret)
return ret;
+ ret = pci_pwrctrl_create_devices(dev);
+ if (ret)
+ return dev_err_probe(dev, ret, "failed to create pwrctrl devices\n");
+
pci->use_parent_dt_ranges = true;
if (imx_pcie->drvdata->mode == DW_PCIE_EP_TYPE) {
ret = imx_add_pcie_ep(imx_pcie, pdev);
if (ret < 0)
- return ret;
+ goto err_pwrctrl_destroy;
/*
* FIXME: Only single Device (EPF) is supported due to the
@@ -1973,7 +1972,7 @@ static int imx_pcie_probe(struct platform_device *pdev)
pci->pp.use_atu_msg = true;
ret = dw_pcie_host_init(&pci->pp);
if (ret < 0)
- return ret;
+ goto err_pwrctrl_destroy;
if (pci_msi_enabled()) {
u8 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_MSI);
@@ -1985,16 +1984,24 @@ static int imx_pcie_probe(struct platform_device *pdev)
}
return 0;
+
+err_pwrctrl_destroy:
+ if (ret != -EPROBE_DEFER)
+ pci_pwrctrl_destroy_devices(dev);
+ return ret;
}
static void imx_pcie_shutdown(struct platform_device *pdev)
{
struct imx_pcie *imx_pcie = platform_get_drvdata(pdev);
+ struct dw_pcie *pci = imx_pcie->pci;
+ struct dw_pcie_rp *pp = &pci->pp;
/* bring down link, so bootloader gets clean state in case of reboot */
imx_pcie_assert_core_reset(imx_pcie);
imx_pcie_assert_perst(imx_pcie, true);
- pci_pwrctrl_power_off_devices(&pdev->dev);
+ if (!pp->skip_pwrctrl_off)
+ pci_pwrctrl_power_off_devices(&pdev->dev);
pci_pwrctrl_destroy_devices(&pdev->dev);
}
--
2.50.1
^ permalink raw reply related
* [PATCH V3 0/8] Add PCIe M.2 Key E connector support for NXP i.MX boards
From: Sherry Sun (OSS) @ 2026-06-26 2:31 UTC (permalink / raw)
To: robh, krzk+dt, conor+dt, Frank.Li, s.hauer, kernel, festevam,
amitkumar.karwar, neeraj.sanjaykale, marcel, luiz.dentz,
hongxing.zhu, l.stach, lpieralisi, kwilczynski, mani, bhelgaas,
brgl
Cc: imx, linux-pci, linux-arm-kernel, devicetree, linux-kernel,
linux-bluetooth, linux-pm, sherry.sun
From: Sherry Sun <sherry.sun@nxp.com>
This series adds support for NXP Wi-Fi/BT combo chips (88W9098, AW693)
inserted into PCIe M.2 Key E connectors on several i.MX EVK/MEK boards.
For M.2 cards that rely on PCIe L2 link state and wake-up mechanisms, the
card must remain powered during suspend. Patch #1 uses the existing
dw_pcie_rp::skip_pwrctrl_off flag to skip power-off during suspend and skip
power-on during the init path.
Also the btnxpuart driver is extended to obtain a pwrseq descriptor via the
OF graph on the UART controller device in patch #3.
Note: Patch #4-8 in this patch set depends on the following [1] and [2]
DTS patches.
[1] https://lore.kernel.org/all/20260616105201.3214395-1-sherry.sun@oss.nxp.com/
[2] https://lore.kernel.org/all/20260520084904.2424253-1-sherry.sun@oss.nxp.com/
---
Changes in V3:
1. Move pci_pwrctrl_create_devices() to imx_pcie_probe() in parch #1,
similar to other regulator_get calls as suggested by Frank.
2. Collected the tags.
Changes in V2:
1. Rebased on top of 7.1.0.
2. Removed the power_off error handling in patch #3 because pwrseq_put()
would call pwrseq_power_off() to automatically clean.
3. Collected the tags.
---
Sherry Sun (8):
PCI: imx6: Add skip_pwrctrl_off flag support
power: sequencing: pcie-m2: Add PCI ID for NXP 88W9098 and AW693
Bluetooth
Bluetooth: btnxpuart: Add M.2 Bluetooth device support using pwrseq
arm64: dts: imx8mq-evk: Describe the PCIe M.2 Key E connector
arm64: dts: imx95-19x19-evk: Describe the PCIe M.2 Key E connector
arm64: dts: imx8dxl-evk: Describe the PCIe M.2 Key E connector
arm64: dts: imx8qm-mek: Describe the PCIe M.2 Key E connector
arm64: dts: imx8qxp-mek: Describe the PCIe M.2 Key E connector
arch/arm64/boot/dts/freescale/imx8dxl-evk.dts | 56 +++++++++++++-----
arch/arm64/boot/dts/freescale/imx8mq-evk.dts | 44 ++++++++++++--
arch/arm64/boot/dts/freescale/imx8qm-mek.dts | 58 ++++++++++++++-----
arch/arm64/boot/dts/freescale/imx8qxp-mek.dts | 54 ++++++++++++-----
.../boot/dts/freescale/imx95-19x19-evk.dts | 55 +++++++++++++-----
drivers/bluetooth/btnxpuart.c | 14 +++++
drivers/pci/controller/dwc/pci-imx6.c | 43 ++++++++------
drivers/power/sequencing/pwrseq-pcie-m2.c | 4 ++
8 files changed, 250 insertions(+), 78 deletions(-)
--
2.50.1
^ permalink raw reply
* [PATCH v3 8/9] ASoC: loongson: Add headphone jack detection and DAPM routing
From: Binbin Zhou @ 2026-06-26 2:27 UTC (permalink / raw)
To: Binbin Zhou, Huacai Chen, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Liam Girdwood, Mark Brown, Jaroslav Kysela,
Takashi Iwai, Keguang Zhang
Cc: Huacai Chen, Xuerui Wang, loongarch, devicetree, linux-sound,
Binbin Zhou
In-Reply-To: <cover.1782439646.git.zhoubinbin@loongson.cn>
Extend the Loongson audio machine driver with jack detection, DAPM
widgets support, enabling proper switching between headphones and
speakers on the Loongson-2K0300 ATK-DL2K0300B board.
Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
---
sound/soc/loongson/loongson_card.c | 131 ++++++++++++++++++++++++++++-
1 file changed, 127 insertions(+), 4 deletions(-)
diff --git a/sound/soc/loongson/loongson_card.c b/sound/soc/loongson/loongson_card.c
index 0e63cbcad57a..25cd12eab4b1 100644
--- a/sound/soc/loongson/loongson_card.c
+++ b/sound/soc/loongson/loongson_card.c
@@ -7,33 +7,126 @@
// Binbin Zhou <zhoubinbin@loongson.cn>
//
-#include <linux/module.h>
-#include <sound/soc.h>
-#include <sound/soc-acpi.h>
#include <linux/acpi.h>
+#include <linux/gpio/consumer.h>
+#include <linux/module.h>
#include <linux/pci.h>
+#include <sound/jack.h>
#include <sound/pcm_params.h>
+#include <sound/soc.h>
+#include <sound/soc-acpi.h>
static char codec_name[SND_ACPI_I2C_ID_LEN];
struct loongson_card_data {
struct snd_soc_card snd_card;
unsigned int mclk_fs;
+ struct gpio_desc *gpiod_hp_det;
+ struct gpio_desc *gpiod_hp_ctl;
+ struct gpio_desc *gpiod_spkr_en;
const struct loongson_card_config *cfg;
};
struct loongson_card_config {
unsigned int fmt;
+ bool add_hp_jack;
+ bool add_dapm_widgets;
+ bool add_dapm_routes;
};
static const struct loongson_card_config ls2k1000_card_config = {
.fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_IB_NF | SND_SOC_DAIFMT_CBC_CFC,
+ .add_hp_jack = false,
+ .add_dapm_widgets = false,
+ .add_dapm_routes = false,
};
static const struct loongson_card_config ls2k0300_forever_pi_card_config = {
.fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBC_CFC,
+ .add_hp_jack = false,
+ .add_dapm_widgets = false,
+ .add_dapm_routes = false,
+};
+
+static const struct loongson_card_config ls2k0300_dl2k0300b_card_config = {
+ .fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBC_CFC,
+ .add_hp_jack = true,
+ .add_dapm_widgets = true,
+ .add_dapm_routes = true,
+};
+
+static int tegra_machine_event(struct snd_soc_dapm_widget *w,
+ struct snd_kcontrol *k, int event)
+{
+ struct snd_soc_card *card = snd_soc_dapm_to_card(w->dapm);
+ struct loongson_card_data *priv = snd_soc_card_get_drvdata(card);
+
+ if (!snd_soc_dapm_widget_name_cmp(w, "Speaker"))
+ gpiod_set_value_cansleep(priv->gpiod_spkr_en,
+ SND_SOC_DAPM_EVENT_ON(event));
+
+ if (!snd_soc_dapm_widget_name_cmp(w, "Headphone"))
+ gpiod_set_value_cansleep(priv->gpiod_hp_ctl,
+ SND_SOC_DAPM_EVENT_ON(event));
+
+ return 0;
+}
+
+static const struct snd_soc_dapm_widget loongson_aosc_dapm_widgets[] = {
+ SND_SOC_DAPM_HP("Headphone", tegra_machine_event),
+ SND_SOC_DAPM_SPK("Speaker", tegra_machine_event),
+};
+
+/* Headphones Jack */
+
+static struct snd_soc_jack loongson_asoc_hp_jack;
+
+static struct snd_soc_jack_pin loongson_asoc_hp_jack_pins[] = {
+ {
+ .pin = "Headphone",
+ .mask = SND_JACK_HEADPHONE
+ },
+ {
+ .pin = "Speaker",
+ .mask = SND_JACK_HEADPHONE,
+ .invert = 1
+ },
+};
+
+static struct snd_soc_jack_gpio loongson_asoc_hp_jack_gpio = {
+ .name = "Headphones detection",
+ .report = SND_JACK_HEADPHONE,
+ .debounce_time = 150,
};
+static int loongson_asoc_machine_init(struct snd_soc_pcm_runtime *rtd)
+{
+ struct snd_soc_card *card = rtd->card;
+ struct loongson_card_data *ls_priv = snd_soc_card_get_drvdata(card);
+ int ret = 0;
+
+ if (!ls_priv->cfg->add_hp_jack || !ls_priv->gpiod_hp_det)
+ return 0;
+
+ ret = snd_soc_card_jack_new_pins(card, "Headphones Jack",
+ SND_JACK_HEADPHONE,
+ &loongson_asoc_hp_jack,
+ loongson_asoc_hp_jack_pins,
+ ARRAY_SIZE(loongson_asoc_hp_jack_pins));
+ if (ret) {
+ dev_err(rtd->dev, "Headphones Jack creation failed: %d\n", ret);
+ return ret;
+ }
+
+ loongson_asoc_hp_jack_gpio.desc = ls_priv->gpiod_hp_det;
+
+ ret = snd_soc_jack_add_gpios(&loongson_asoc_hp_jack, 1, &loongson_asoc_hp_jack_gpio);
+ if (ret)
+ dev_err(rtd->dev, "Headphone GPIO not added: %d\n", ret);
+
+ return ret;
+}
+
static int loongson_card_hw_params(struct snd_pcm_substream *substream,
struct snd_pcm_hw_params *params)
{
@@ -75,6 +168,7 @@ static struct snd_soc_dai_link loongson_dai_links[] = {
{
.name = "Loongson Audio Port",
.stream_name = "Loongson Audio",
+ .init = loongson_asoc_machine_init,
SND_SOC_DAILINK_REG(analog),
.ops = &loongson_ops,
},
@@ -135,16 +229,35 @@ static int loongson_card_parse_acpi(struct loongson_card_data *data)
static int loongson_card_parse_of(struct loongson_card_data *data)
{
- struct device_node *cpu, *codec;
struct snd_soc_card *card = &data->snd_card;
+ struct device_node *cpu, *codec;
struct device *dev = card->dev;
int ret, i;
+ data->gpiod_hp_det = devm_gpiod_get_optional(dev, "hp-det", GPIOD_IN);
+ if (IS_ERR(data->gpiod_hp_det))
+ return PTR_ERR(data->gpiod_hp_det);
+
+ data->gpiod_hp_ctl = devm_gpiod_get_optional(dev, "hp-ctl", GPIOD_OUT_LOW);
+ if (IS_ERR(data->gpiod_hp_ctl))
+ return PTR_ERR(data->gpiod_hp_ctl);
+
+ data->gpiod_spkr_en = devm_gpiod_get_optional(dev, "spkr-en", GPIOD_OUT_LOW);
+ if (IS_ERR(data->gpiod_spkr_en))
+ return PTR_ERR(data->gpiod_spkr_en);
+
+ if (data->cfg->add_dapm_routes) {
+ ret = snd_soc_of_parse_audio_routing(card, "audio-routing");
+ if (ret)
+ return ret;
+ }
+
cpu = of_get_child_by_name(dev->of_node, "cpu");
if (!cpu) {
dev_err(dev, "platform property missing or invalid\n");
return -EINVAL;
}
+
codec = of_get_child_by_name(dev->of_node, "codec");
if (!codec) {
dev_err(dev, "audio-codec property missing or invalid\n");
@@ -199,6 +312,12 @@ static int loongson_asoc_card_probe(struct platform_device *pdev)
card->owner = THIS_MODULE;
card->dai_link = loongson_dai_links;
card->num_links = ARRAY_SIZE(loongson_dai_links);
+
+ if (ls_priv->cfg->add_dapm_widgets) {
+ card->dapm_widgets = loongson_aosc_dapm_widgets;
+ card->num_dapm_widgets = ARRAY_SIZE(loongson_aosc_dapm_widgets);
+ }
+
snd_soc_card_set_drvdata(card, ls_priv);
ret = device_property_read_string(dev, "model", &card->name);
@@ -227,6 +346,10 @@ static const struct of_device_id loongson_asoc_dt_ids[] = {
.compatible = "loongson,ls2k0300-forever-pi-audio-card",
.data = &ls2k0300_forever_pi_card_config
},
+ {
+ .compatible = "loongson,ls2k0300-dl2k0300b-audio-card",
+ .data = &ls2k0300_dl2k0300b_card_config
+ },
{ /* sentinel */ },
};
MODULE_DEVICE_TABLE(of, loongson_asoc_dt_ids);
--
2.52.0
^ permalink raw reply related
* [PATCH v3 9/9] ASoC: es8328: Add DAPM routes from MIC inputs to Mic Bias
From: Binbin Zhou @ 2026-06-26 2:27 UTC (permalink / raw)
To: Binbin Zhou, Huacai Chen, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Liam Girdwood, Mark Brown, Jaroslav Kysela,
Takashi Iwai, Keguang Zhang
Cc: Huacai Chen, Xuerui Wang, loongarch, devicetree, linux-sound,
Binbin Zhou
In-Reply-To: <cover.1782439646.git.zhoubinbin@loongson.cn>
The ES8328 codec has differential/single-ended microphone inputs
(LINPUT1/RINPUT1, LINPUT2/RINPUT2) that require connection to the
internal Mic Bias generator for proper operation. Currently, these
routes are missing, which can cause microphone recording to fail.
Add the missing DAPM routes to link the input pins to the Mic Bias
supply, ensuring the microphone bias voltage is correctly applied.
Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
---
PS:
I'm not sure if this patch is also required for other platforms using
the ES8328. If not, I'll drop the patch and add this DAPM route to the
`audio-routing` property of the Loongson ASoC machine driver.
sound/soc/codecs/es8328.c | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/sound/soc/codecs/es8328.c b/sound/soc/codecs/es8328.c
index 9838fe42cb6f..aaa6646ad4c5 100644
--- a/sound/soc/codecs/es8328.c
+++ b/sound/soc/codecs/es8328.c
@@ -405,6 +405,11 @@ static const struct snd_soc_dapm_route es8328_dapm_routes[] = {
{ "Mic Bias", NULL, "Mic Bias Gen" },
+ { "LINPUT1", NULL, "Mic Bias" },
+ { "RINPUT1", NULL, "Mic Bias" },
+ { "LINPUT2", NULL, "Mic Bias" },
+ { "RINPUT2", NULL, "Mic Bias" },
+
{ "Left Mixer", NULL, "Left DAC" },
{ "Left Mixer", "Left Bypass Switch", "Left Line Mux" },
{ "Left Mixer", "Right Playback Switch", "Right DAC" },
--
2.52.0
^ permalink raw reply related
* [PATCH v3 4/9] ASoC: dt-bindings: loongson,ls-audio-card: Use common sound card
From: Binbin Zhou @ 2026-06-26 2:27 UTC (permalink / raw)
To: Binbin Zhou, Huacai Chen, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Liam Girdwood, Mark Brown, Jaroslav Kysela,
Takashi Iwai, Keguang Zhang
Cc: Huacai Chen, Xuerui Wang, loongarch, devicetree, linux-sound,
Binbin Zhou
In-Reply-To: <cover.1782439646.git.zhoubinbin@loongson.cn>
Reference the common sound card properties. This allows removing the
`model` property and directly using the common `audio-routing` property
later on.
Acked-by: Rob Herring (Arm) <robh@kernel.org>
Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
---
.../bindings/sound/loongson,ls-audio-card.yaml | 11 +++++------
1 file changed, 5 insertions(+), 6 deletions(-)
diff --git a/Documentation/devicetree/bindings/sound/loongson,ls-audio-card.yaml b/Documentation/devicetree/bindings/sound/loongson,ls-audio-card.yaml
index 61e8babed402..e1b7445a8b22 100644
--- a/Documentation/devicetree/bindings/sound/loongson,ls-audio-card.yaml
+++ b/Documentation/devicetree/bindings/sound/loongson,ls-audio-card.yaml
@@ -8,20 +8,20 @@ title: Loongson 7axxx/2kxxx ASoC audio sound card driver
maintainers:
- Yingkun Meng <mengyingkun@loongson.cn>
+ - Binbin Zhou <zhoubinbin@loongson.cn>
description:
The binding describes the sound card present in loongson
7axxx/2kxxx platform. The sound card is an ASoC component
which uses Loongson I2S controller to transfer the audio data.
+allOf:
+ - $ref: sound-card-common.yaml#
+
properties:
compatible:
const: loongson,ls-audio-card
- model:
- $ref: /schemas/types.yaml#/definitions/string
- description: User specified audio sound card name
-
mclk-fs:
$ref: simple-card.yaml#/definitions/mclk-fs
@@ -47,12 +47,11 @@ properties:
required:
- compatible
- - model
- mclk-fs
- cpu
- codec
-additionalProperties: false
+unevaluatedProperties: false
examples:
- |
--
2.52.0
^ permalink raw reply related
* [PATCH v3 7/9] ASoC: dt-bindings: loongson,ls-audio-card: Add ATK-DL2K0300B compatible
From: Binbin Zhou @ 2026-06-26 2:27 UTC (permalink / raw)
To: Binbin Zhou, Huacai Chen, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Liam Girdwood, Mark Brown, Jaroslav Kysela,
Takashi Iwai, Keguang Zhang
Cc: Huacai Chen, Xuerui Wang, loongarch, devicetree, linux-sound,
Binbin Zhou
In-Reply-To: <cover.1782439646.git.zhoubinbin@loongson.cn>
Add new compatible for the ATK-DL2K0300B development board based on
Loongson-2K0300.
Unlike others, this board features GPIO-controlled headphone detection,
headphone control, and speaker enable.
Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
---
.../sound/loongson,ls-audio-card.yaml | 38 +++++++++++++++++++
1 file changed, 38 insertions(+)
diff --git a/Documentation/devicetree/bindings/sound/loongson,ls-audio-card.yaml b/Documentation/devicetree/bindings/sound/loongson,ls-audio-card.yaml
index 8c214e5d04b1..dc7f4afbb777 100644
--- a/Documentation/devicetree/bindings/sound/loongson,ls-audio-card.yaml
+++ b/Documentation/devicetree/bindings/sound/loongson,ls-audio-card.yaml
@@ -23,6 +23,7 @@ properties:
enum:
- loongson,ls-audio-card # Loongson-2K1000/Loongson-2K2000/LS7A
- loongson,ls2k0300-forever-pi-audio-card # CTCISZ Forever Pi
+ - loongson,ls2k0300-dl2k0300b-audio-card # ATK-DL2K0300B
mclk-fs:
$ref: simple-card.yaml#/definitions/mclk-fs
@@ -47,6 +48,18 @@ properties:
required:
- sound-dai
+ spkr-en-gpios:
+ maxItems: 1
+ description: The GPIO that enables the speakers
+
+ hp-ctl-gpios:
+ maxItems: 1
+ description: The GPIO that control the headphones
+
+ hp-det-gpios:
+ maxItems: 1
+ description: The GPIO that detect headphones are plugged in
+
required:
- compatible
- mclk-fs
@@ -69,3 +82,28 @@ examples:
sound-dai = <&es8323>;
};
};
+
+ - |
+ #include <dt-bindings/gpio/gpio.h>
+
+ sound {
+ compatible = "loongson,ls2k0300-dl2k0300b-audio-card";
+ model = "loongson-audio";
+ mclk-fs = <512>;
+ hp-det-gpios = <&gpio 81 GPIO_ACTIVE_HIGH>;
+ spkr-en-gpios = <&gpio 86 GPIO_ACTIVE_HIGH>;
+ hp-ctl-gpios = <&gpio 87 GPIO_ACTIVE_HIGH>;
+ audio-routing =
+ "Headphone", "LOUT1",
+ "Headphone", "ROUT1",
+ "Speaker", "LOUT2",
+ "Speaker", "ROUT2";
+
+ cpu {
+ sound-dai = <&i2s>;
+ };
+
+ codec {
+ sound-dai = <&es8388>;
+ };
+ };
--
2.52.0
^ permalink raw reply related
* [PATCH v3 6/9] ASoC: loongson: Add Loongson-2K0300 CTCISZ Forever Pi sound card support
From: Binbin Zhou @ 2026-06-26 2:27 UTC (permalink / raw)
To: Binbin Zhou, Huacai Chen, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Liam Girdwood, Mark Brown, Jaroslav Kysela,
Takashi Iwai, Keguang Zhang
Cc: Huacai Chen, Xuerui Wang, loongarch, devicetree, linux-sound,
Binbin Zhou
In-Reply-To: <cover.1782439646.git.zhoubinbin@loongson.cn>
The Loongson-2K0300 audio card uses a different DAI format compared to
existing Loongson platforms.
Move the dai_fmt setting from the static DAI link to runtime hw_params
via snd_soc_runtime_set_dai_fmt(), and pass the correct format through
driver match data.
Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
---
sound/soc/loongson/loongson_card.c | 34 +++++++++++++++++++++++++-----
1 file changed, 29 insertions(+), 5 deletions(-)
diff --git a/sound/soc/loongson/loongson_card.c b/sound/soc/loongson/loongson_card.c
index ea895fe6b5e9..0e63cbcad57a 100644
--- a/sound/soc/loongson/loongson_card.c
+++ b/sound/soc/loongson/loongson_card.c
@@ -2,8 +2,9 @@
//
// Loongson ASoC Audio Machine driver
//
-// Copyright (C) 2023 Loongson Technology Corporation Limited
+// Copyright (C) 2023-2026 Loongson Technology Corporation Limited
// Author: Yingkun Meng <mengyingkun@loongson.cn>
+// Binbin Zhou <zhoubinbin@loongson.cn>
//
#include <linux/module.h>
@@ -18,6 +19,19 @@ static char codec_name[SND_ACPI_I2C_ID_LEN];
struct loongson_card_data {
struct snd_soc_card snd_card;
unsigned int mclk_fs;
+ const struct loongson_card_config *cfg;
+};
+
+struct loongson_card_config {
+ unsigned int fmt;
+};
+
+static const struct loongson_card_config ls2k1000_card_config = {
+ .fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_IB_NF | SND_SOC_DAIFMT_CBC_CFC,
+};
+
+static const struct loongson_card_config ls2k0300_forever_pi_card_config = {
+ .fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_NB_NF | SND_SOC_DAIFMT_CBC_CFC,
};
static int loongson_card_hw_params(struct snd_pcm_substream *substream,
@@ -45,7 +59,7 @@ static int loongson_card_hw_params(struct snd_pcm_substream *substream,
return ret;
}
- return 0;
+ return snd_soc_runtime_set_dai_fmt(rtd, ls_card->cfg->fmt);
}
static const struct snd_soc_ops loongson_ops = {
@@ -61,8 +75,6 @@ static struct snd_soc_dai_link loongson_dai_links[] = {
{
.name = "Loongson Audio Port",
.stream_name = "Loongson Audio",
- .dai_fmt = SND_SOC_DAIFMT_I2S | SND_SOC_DAIFMT_IB_NF
- | SND_SOC_DAIFMT_CBC_CFC,
SND_SOC_DAILINK_REG(analog),
.ops = &loongson_ops,
},
@@ -177,6 +189,10 @@ static int loongson_asoc_card_probe(struct platform_device *pdev)
if (!ls_priv)
return -ENOMEM;
+ ls_priv->cfg = (const struct loongson_card_config *)device_get_match_data(dev);
+ if (!ls_priv->cfg)
+ return -EINVAL;
+
card = &ls_priv->snd_card;
card->dev = dev;
@@ -202,7 +218,15 @@ static int loongson_asoc_card_probe(struct platform_device *pdev)
}
static const struct of_device_id loongson_asoc_dt_ids[] = {
- { .compatible = "loongson,ls-audio-card" },
+ /* Loongson-2K1000/Loongson-2K2000/LS7A */
+ {
+ .compatible = "loongson,ls-audio-card",
+ .data = &ls2k1000_card_config
+ },
+ {
+ .compatible = "loongson,ls2k0300-forever-pi-audio-card",
+ .data = &ls2k0300_forever_pi_card_config
+ },
{ /* sentinel */ },
};
MODULE_DEVICE_TABLE(of, loongson_asoc_dt_ids);
--
2.52.0
^ permalink raw reply related
* [PATCH v3 5/9] ASoC: dt-bindings: loongson,ls-audio-card: Add ctcisz forever pi compatible
From: Binbin Zhou @ 2026-06-26 2:27 UTC (permalink / raw)
To: Binbin Zhou, Huacai Chen, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Liam Girdwood, Mark Brown, Jaroslav Kysela,
Takashi Iwai, Keguang Zhang
Cc: Huacai Chen, Xuerui Wang, loongarch, devicetree, linux-sound,
Binbin Zhou
In-Reply-To: <cover.1782439646.git.zhoubinbin@loongson.cn>
Add a new compatible string `loongson,ls2k0300-forever-pi-audio-card`
for the audio card on Loongson-2K0300 ctcisz forever pi SoC. It uses a
different DAI format compared to existing Loongson platforms.
The existing "loongson,ls-audio-card" remains valid for LS7A,
Loongson-2K1000 and Loongson-2K2000.
Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
---
.../devicetree/bindings/sound/loongson,ls-audio-card.yaml | 4 +++-
1 file changed, 3 insertions(+), 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/sound/loongson,ls-audio-card.yaml b/Documentation/devicetree/bindings/sound/loongson,ls-audio-card.yaml
index e1b7445a8b22..8c214e5d04b1 100644
--- a/Documentation/devicetree/bindings/sound/loongson,ls-audio-card.yaml
+++ b/Documentation/devicetree/bindings/sound/loongson,ls-audio-card.yaml
@@ -20,7 +20,9 @@ allOf:
properties:
compatible:
- const: loongson,ls-audio-card
+ enum:
+ - loongson,ls-audio-card # Loongson-2K1000/Loongson-2K2000/LS7A
+ - loongson,ls2k0300-forever-pi-audio-card # CTCISZ Forever Pi
mclk-fs:
$ref: simple-card.yaml#/definitions/mclk-fs
--
2.52.0
^ permalink raw reply related
* [PATCH v3 3/9] ASoC: loongson: Add Loongson-2K0300 I2S controller support
From: Binbin Zhou @ 2026-06-26 2:27 UTC (permalink / raw)
To: Binbin Zhou, Huacai Chen, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Liam Girdwood, Mark Brown, Jaroslav Kysela,
Takashi Iwai, Keguang Zhang
Cc: Huacai Chen, Xuerui Wang, loongarch, devicetree, linux-sound,
Binbin Zhou
In-Reply-To: <cover.1782439646.git.zhoubinbin@loongson.cn>
The Loongson-2K0300 I2S interface differs significantly from the
Loongson-2K1000. Although both utilize external DMA controllers, the
Loongson-2K0300 does not require additional registers for routing
configuration.
Due to hardware design flaw, an extra controller reset sequence is
required during probe.
Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
---
sound/soc/loongson/loongson_i2s_plat.c | 42 +++++++++++++++++++++-----
1 file changed, 35 insertions(+), 7 deletions(-)
diff --git a/sound/soc/loongson/loongson_i2s_plat.c b/sound/soc/loongson/loongson_i2s_plat.c
index ac054b6ce632..82d95c6644ef 100644
--- a/sound/soc/loongson/loongson_i2s_plat.c
+++ b/sound/soc/loongson/loongson_i2s_plat.c
@@ -2,7 +2,7 @@
//
// Loongson I2S controller master mode dirver(platform device)
//
-// Copyright (C) 2023-2024 Loongson Technology Corporation Limited
+// Copyright (C) 2023-2026 Loongson Technology Corporation Limited
//
// Author: Yingkun Meng <mengyingkun@loongson.cn>
// Binbin Zhou <zhoubinbin@loongson.cn>
@@ -21,6 +21,7 @@
#include "loongson_i2s.h"
#include "loongson_dma.h"
+/* Loongson-2K1000 APBDMA routing */
#define LOONGSON_I2S_RX_DMA_OFFSET 21
#define LOONGSON_I2S_TX_DMA_OFFSET 18
@@ -30,6 +31,11 @@
#define LOONGSON_DMA3_CONF 0x3
#define LOONGSON_DMA4_CONF 0x4
+struct loongson_i2s_plat_config {
+ int rev_id;
+ int (*i2s_dma_config)(struct platform_device *pdev);
+};
+
static int loongson_i2s_apbdma_config(struct platform_device *pdev)
{
int val;
@@ -47,8 +53,18 @@ static int loongson_i2s_apbdma_config(struct platform_device *pdev)
return 0;
}
+static const struct loongson_i2s_plat_config ls2k0300_i2s_plat_config = {
+ .rev_id = 1,
+};
+
+static const struct loongson_i2s_plat_config ls2k1000_i2s_plat_config = {
+ .rev_id = 0,
+ .i2s_dma_config = loongson_i2s_apbdma_config,
+};
+
static int loongson_i2s_plat_probe(struct platform_device *pdev)
{
+ const struct loongson_i2s_plat_config *plat_config;
struct device *dev = &pdev->dev;
struct loongson_i2s *i2s;
struct resource *res;
@@ -59,12 +75,17 @@ static int loongson_i2s_plat_probe(struct platform_device *pdev)
if (!i2s)
return -ENOMEM;
- ret = loongson_i2s_apbdma_config(pdev);
- if (ret)
- return ret;
+ plat_config = device_get_match_data(dev);
+ if (!plat_config)
+ return -EINVAL;
- res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
- i2s->reg_base = devm_ioremap_resource(&pdev->dev, res);
+ if (plat_config->i2s_dma_config) {
+ ret = plat_config->i2s_dma_config(pdev);
+ if (ret)
+ return ret;
+ }
+
+ i2s->reg_base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
if (IS_ERR(i2s->reg_base))
return dev_err_probe(dev, PTR_ERR(i2s->reg_base),
"devm_ioremap_resource failed\n");
@@ -87,11 +108,17 @@ static int loongson_i2s_plat_probe(struct platform_device *pdev)
if (IS_ERR(i2s_clk))
return dev_err_probe(dev, PTR_ERR(i2s_clk), "clock property invalid\n");
i2s->clk_rate = clk_get_rate(i2s_clk);
+ i2s->rev_id = plat_config->rev_id;
dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
dev_set_name(dev, LS_I2S_DRVNAME);
dev_set_drvdata(dev, i2s);
+ if (i2s->rev_id == 1) {
+ regmap_update_bits(i2s->regmap, LS_I2S_CTRL, I2S_CTRL_RESET, I2S_CTRL_RESET);
+ fsleep(200);
+ }
+
ret = devm_snd_soc_register_component(dev, &loongson_i2s_edma_component,
&loongson_i2s_dai, 1);
if (ret)
@@ -102,7 +129,8 @@ static int loongson_i2s_plat_probe(struct platform_device *pdev)
}
static const struct of_device_id loongson_i2s_ids[] = {
- { .compatible = "loongson,ls2k1000-i2s" },
+ { .compatible = "loongson,ls2k0300-i2s", .data = &ls2k0300_i2s_plat_config },
+ { .compatible = "loongson,ls2k1000-i2s", .data = &ls2k1000_i2s_plat_config },
{ /* sentinel */ },
};
MODULE_DEVICE_TABLE(of, loongson_i2s_ids);
--
2.52.0
^ permalink raw reply related
* [PATCH v3 2/9] ASoC: dt-bindings: loongson,ls2k1000-i2s: Document Loongson-2K0300 compatible
From: Binbin Zhou @ 2026-06-26 2:27 UTC (permalink / raw)
To: Binbin Zhou, Huacai Chen, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Liam Girdwood, Mark Brown, Jaroslav Kysela,
Takashi Iwai, Keguang Zhang
Cc: Huacai Chen, Xuerui Wang, loongarch, devicetree, linux-sound,
Binbin Zhou, Krzysztof Kozlowski
In-Reply-To: <cover.1782439646.git.zhoubinbin@loongson.cn>
Add a new compatible string `loongson,ls2k0300-i2s` for the I2S
controller found on Loongson-2K0300 SoC.
Unlike Loongson-2K1000, Loongson-2K0300 does not require the second
register region for APB DMA configuration, so update the binding to
allow a single reg entry.
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
---
.../bindings/sound/loongson,ls2k1000-i2s.yaml | 22 ++++++++++++++++++-
1 file changed, 21 insertions(+), 1 deletion(-)
diff --git a/Documentation/devicetree/bindings/sound/loongson,ls2k1000-i2s.yaml b/Documentation/devicetree/bindings/sound/loongson,ls2k1000-i2s.yaml
index da79510bb2d9..51e23c189f7a 100644
--- a/Documentation/devicetree/bindings/sound/loongson,ls2k1000-i2s.yaml
+++ b/Documentation/devicetree/bindings/sound/loongson,ls2k1000-i2s.yaml
@@ -14,9 +14,12 @@ allOf:
properties:
compatible:
- const: loongson,ls2k1000-i2s
+ enum:
+ - loongson,ls2k0300-i2s
+ - loongson,ls2k1000-i2s
reg:
+ minItems: 1
items:
- description: Loongson I2S controller Registers.
- description: APB DMA config register for Loongson I2S controller.
@@ -49,6 +52,23 @@ required:
unevaluatedProperties: false
+if:
+ properties:
+ compatible:
+ contains:
+ enum:
+ - loongson,ls2k1000-i2s
+
+then:
+ properties:
+ reg:
+ minItems: 2
+
+else:
+ properties:
+ reg:
+ maxItems: 1
+
examples:
- |
#include <dt-bindings/clock/loongson,ls2k-clk.h>
--
2.52.0
^ permalink raw reply related
* [PATCH v3 1/9] ASoC: loongson: Fix error handling in ACPI property parsing
From: Binbin Zhou @ 2026-06-26 2:27 UTC (permalink / raw)
To: Binbin Zhou, Huacai Chen, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Liam Girdwood, Mark Brown, Jaroslav Kysela,
Takashi Iwai, Keguang Zhang
Cc: Huacai Chen, Xuerui Wang, loongarch, devicetree, linux-sound,
Binbin Zhou, stable, Sashiko
In-Reply-To: <cover.1782439646.git.zhoubinbin@loongson.cn>
In loongson_card_parse_acpi(), the return value of
device_property_read_string() for the `codec-dai-name` property was
ignored. If the property is missing or invalid, an uninitialized pointer
would be used later, potentially leading to undefined behavior.
Fix this by checking the return value and propagating the error
appropriately.
Cc: stable@vger.kernel.org
Reported-by: Sashiko <sashiko-bot@kernel.org>
Closes: https://sashiko.dev/#/patchset/cover.1780538113.git.zhoubinbin@loongson.cn?part=5
Fixes: ddb538a3004b ("ASoC: loongson: Factor out loongson_card_acpi_find_device() function")
Signed-off-by: Binbin Zhou <zhoubinbin@loongson.cn>
---
sound/soc/loongson/loongson_card.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/sound/soc/loongson/loongson_card.c b/sound/soc/loongson/loongson_card.c
index 7910d5d9ac4f..ea895fe6b5e9 100644
--- a/sound/soc/loongson/loongson_card.c
+++ b/sound/soc/loongson/loongson_card.c
@@ -91,7 +91,7 @@ static int loongson_card_parse_acpi(struct loongson_card_data *data)
const char *codec_dai_name;
struct acpi_device *adev;
struct device *phy_dev;
- int i;
+ int i, ret;
/* fixup platform name based on reference node */
adev = loongson_card_acpi_find_device(card, "cpu");
@@ -108,7 +108,9 @@ static int loongson_card_parse_acpi(struct loongson_card_data *data)
return -ENOENT;
snprintf(codec_name, sizeof(codec_name), "i2c-%s", acpi_dev_name(adev));
- device_property_read_string(card->dev, "codec-dai-name", &codec_dai_name);
+ ret = device_property_read_string(card->dev, "codec-dai-name", &codec_dai_name);
+ if (ret)
+ return ret;
for (i = 0; i < card->num_links; i++) {
loongson_dai_links[i].platforms->name = dev_name(phy_dev);
--
2.52.0
^ permalink raw reply related
* [PATCH v3 0/9] ASoC: Add Loongson-2K0300 I2S controller and sound card support
From: Binbin Zhou @ 2026-06-26 2:27 UTC (permalink / raw)
To: Binbin Zhou, Huacai Chen, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Liam Girdwood, Mark Brown, Jaroslav Kysela,
Takashi Iwai, Keguang Zhang
Cc: Huacai Chen, Xuerui Wang, loongarch, devicetree, linux-sound,
Binbin Zhou
Hi all:
This series adds ASoC support for the Loongson-2K0300 SoC and its
associated development boards, including the CTCISZ Forever Pi and the
ATK-DL2K0300B.
Key changes:
- Extend DT bindings to support ls2k0300-i2s and new audio card
compatibles.
- Refactor the platform I2S driver to handle SoC differences via per-device
configuration (rev_id, optional APB DMA config, reset sequence).
- Refactor the audio machine driver to support board-specific DAI formats,
GPIO-based headphone detection/control, speaker enable, and DAPM routing.
- Add jack detection and automatic switching between headphones and
speakers for the DL2K0300B board.
The patchset also cleans up the existing audio card binding by
referencing the common sound-card properties, and adds new compatibles
for the Loongson-2K0300 variants with proper DAI format handling.
All changes have been tested on Loongson-2K2000 (PCI), Loongson-2K0300
Forever Pi and Loongson-2K0300 DL2K0300B boards.
Thanks.
Binbin
========
V3:
Patch (1/9):
- New patch;
- Error handling reported by AI Sashiko;
Patch (3/9):
- Mark platform configuration structures as `const`;
Patch (4/9):
- Add Acked-by tag from Rob, thanks;
Patch (5/9):
- Correct commit message;
Patch (7/9):
- Drop `loongson` prefix;
- Change `gpiod_hp_mute` to `gpiod_hp_ctl`;
Patch (8/9):
- Add `add_dapm_routes` to loongson_card_config;
- Move gpiod* register ops into loongson_card_parse_of();
- Change `gpiod_hp_mute` to `gpiod_hp_ctl`;
- Add `ls_priv->gpiod_hp_det` judgment in loongson_asoc_machine_init()
to avoid double-free;
Patch (9/9):
- New patch;
- Add DAPM routes from MIC inputs to Mic Bias.
Link to V2:
https://lore.kernel.org/all/cover.1780538113.git.zhoubinbin@loongson.cn/
v2:
- The first four patches for V1 (related to code cleanup) have been
accepted as a separate series. The link is as follows:
https://lore.kernel.org/all/178041371415.93058.4794135670349989571.b4-ty@b4/
Patch (1/7):
- Add Reviewed-by tag from Krzysztof Kozlowski;
Patch (3/7):
- New patch;
- Reference sound-card-common.yaml, drop custom model property;
Patch (4/7)(5/7):
- New patches;
- Support Forever Pi board with different DAI format;
Patch (6/7)(7/7):
- New patches;
- Implement headphone jack detection and DAPM routing for ATK-DL2K0300B
board.
Link to V1:
https://lore.kernel.org/all/cover.1773107475.git.zhoubinbin@loongson.cn/
Binbin Zhou (9):
ASoC: loongson: Fix error handling in ACPI property parsing
ASoC: dt-bindings: loongson,ls2k1000-i2s: Document Loongson-2K0300
compatible
ASoC: loongson: Add Loongson-2K0300 I2S controller support
ASoC: dt-bindings: loongson,ls-audio-card: Use common sound card
ASoC: dt-bindings: loongson,ls-audio-card: Add ctcisz forever pi
compatible
ASoC: loongson: Add Loongson-2K0300 CTCISZ Forever Pi sound card
support
ASoC: dt-bindings: loongson,ls-audio-card: Add ATK-DL2K0300B
compatible
ASoC: loongson: Add headphone jack detection and DAPM routing
ASoC: es8328: Add DAPM routes from MIC inputs to Mic Bias
.../sound/loongson,ls-audio-card.yaml | 53 +++++-
.../bindings/sound/loongson,ls2k1000-i2s.yaml | 22 ++-
sound/soc/codecs/es8328.c | 5 +
sound/soc/loongson/loongson_card.c | 171 ++++++++++++++++--
sound/soc/loongson/loongson_i2s_plat.c | 42 ++++-
5 files changed, 267 insertions(+), 26 deletions(-)
--
2.52.0
^ permalink raw reply
* Re: [PATCH v6 2/2] drm/bridge: Add Lontium LT9611C(EX/UXD) MIPI DSI to HDMI driver
From: Sunyun Yang @ 2026-06-26 1:55 UTC (permalink / raw)
To: Dmitry Baryshkov
Cc: Krzysztof Kozlowski, robh, krzk+dt, conor+dt, andrzej.hajda,
neil.armstrong, maarten.lankhorst, rfoss, mripard,
Laurent.pinchart, tzimmermann, jonas, jernej.skrabec, devicetree,
dri-devel, linux-kernel, xmzhu, xmzhu, rlyu, xbpeng
In-Reply-To: <tpqutwzasfwhraxzymorkiot7uryef4l2n32fyo3i3fp337sak@fugghdkcqfrj>
Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com> 于2026年6月25日周四 22:57写道：
>
> On Thu, Jun 25, 2026 at 09:26:47PM +0800, Sunyun Yang wrote:
> > Krzysztof Kozlowski <krzk@kernel.org> 于2026年6月25日周四 21:17写道：
> > >
> > > On 25/06/2026 15:14, Sunyun Yang wrote:
> > > > Krzysztof Kozlowski <krzk@kernel.org> 于2026年6月25日周四 20:54写道：
> > > >>
> > > >> On 08/05/2026 15:40, syyang@lontium.com wrote:
> > > >>> +
> > > >>> +static void lt9611c_reset(struct lt9611c *lt9611c)
> > > >>> +{
> > > >>> + gpiod_set_value_cansleep(lt9611c->reset_gpio, 1);
> > > >>> + msleep(20);
> > > >>> +
> > > >>> + gpiod_set_value_cansleep(lt9611c->reset_gpio, 0);
> > > >>> + msleep(20);
> > > >>> +
> > > >>> + gpiod_set_value_cansleep(lt9611c->reset_gpio, 1);
> > > >>
> > > >> This is just plain wrong. Why do you assert, then de-assert and then
> > > >> finally assert AGAIN the reset leaving the device in powerdown stage?
> > > >>
> > > > I am using software to emulate the hardware RESET button on our EVB.
> > > > When the hardware RESET button is pressed while our chip is running,
> > > > the signal level changes from HIGH to LOW and then back to HIGH.
> > > >
> > > > Of course, we can also use the following:
> > > > static void lt9611c_reset(struct lt9611c *lt9611c)
> > > > {
> > > > gpiod_set_value_cansleep(lt9611c->reset_gpio, 0);
> > > > msleep(50);
> > > > gpiod_set_value_cansleep(lt9611c->reset_gpio, 1);
> > > > msleep(20);
> > > > }
> > >
> > > Makes no sense either and you just did not get the point and did not
> > > answer my question. I asked WHY you leave asserted. Answer "we emulate"
> > > is just plain wrong.
> > >
> > > So again please answer:
> > >
> > > Why do you leave device with reset asserted?
> > >
> >
> > devicetree: reset-gpios = <&tlmm 128 GPIO_ACTIVE_HIGH>;
>
> It should be GPIO_ACTIVE_LOW, if the pin as active-low.
>
Yes, I understand that.
I used GPIO_ACTIVE_HIGH intentionally, because I did not want to
modify the existing reset-gpios = <&tlmm 128 GPIO_ACTIVE_HIGH>
property in the lontium-lt9611.yaml device tree file that was
submitted by others. If I used GPIO_ACTIVE_LOW, I would have to change
that line in the device tree binding, and also update the driver files
lontium-lt9611.c and lontium-lt9611uxc.c accordingly. That would add a
significant amount of extra work for me.
Moreover, in much earlier versions, I had added a separate
lontium-lt9611c.yaml file to decouple this new chip from the existing
lontium-lt9611 / lontium-lt9611uxc support. However, Dmitry Baryshkov
considered that unnecessary and asked me to merge lontium-lt9611c
together with the existing drivers. He also told me that the
differences in reset‑pin and VDD/VCC supply did not matter.
The existing device tree and driver code already had issues, and I had
raised them with you before. At that time, you did not seem to care,
and the community reviewers insisted that I must follow your
directions. So I did exactly what you told me to do.
> >
> > GPIO_ACTIVE_HIGH:
> >
> > gpiod_set_value_cansleep(lt9611c->reset_gpio, 0); ------ reset pin
> > is Low level : Clear the register configuration in the chip to stop
> > the chip from working.
> >
> > gpiod_set_value_cansleep(lt9611c->reset_gpio, 1); ------ reset pin
> > is high level: The chip resumes operation.
> >
> >
> >
> > > Best regards,
> > > Krzysztof
>
> --
> With best wishes
> Dmitry
^ permalink raw reply
* Re: [PATCH v6 2/2] drm/bridge: Add Lontium LT9611C(EX/UXD) MIPI DSI to HDMI driver
From: Sunyun Yang @ 2026-06-26 2:15 UTC (permalink / raw)
To: Krzysztof Kozlowski
Cc: robh, krzk+dt, conor+dt, andrzej.hajda, neil.armstrong,
dmitry.baryshkov, maarten.lankhorst, rfoss, mripard,
Laurent.pinchart, tzimmermann, jonas, jernej.skrabec, devicetree,
dri-devel, linux-kernel, xmzhu, xmzhu, rlyu, xbpeng
In-Reply-To: <6371d1d8-cdfb-40fa-84c7-ba3ec4e2ac00@kernel.org>
Krzysztof Kozlowski <krzk@kernel.org> 于2026年6月25日周四 21:51写道：
>
> On 25/06/2026 15:40, Sunyun Yang wrote:
> > Sunyun Yang <syyang@lontium.com> 于2026年6月25日周四 21:26写道：
> >>
> >> Krzysztof Kozlowski <krzk@kernel.org> 于2026年6月25日周四 21:17写道：
> >>>
> >>> On 25/06/2026 15:14, Sunyun Yang wrote:
> >>>> Krzysztof Kozlowski <krzk@kernel.org> 于2026年6月25日周四 20:54写道：
> >>>>>
> >>>>> On 08/05/2026 15:40, syyang@lontium.com wrote:
> >>>>>> +
> >>>>>> +static void lt9611c_reset(struct lt9611c *lt9611c)
> >>>>>> +{
> >>>>>> + gpiod_set_value_cansleep(lt9611c->reset_gpio, 1);
> >>>>>> + msleep(20);
> >>>>>> +
> >>>>>> + gpiod_set_value_cansleep(lt9611c->reset_gpio, 0);
> >>>>>> + msleep(20);
> >>>>>> +
> >>>>>> + gpiod_set_value_cansleep(lt9611c->reset_gpio, 1);
> >>>>>
> >>>>> This is just plain wrong. Why do you assert, then de-assert and then
> >>>>> finally assert AGAIN the reset leaving the device in powerdown stage?
> >>>>>
> >>>> I am using software to emulate the hardware RESET button on our EVB.
> >>>> When the hardware RESET button is pressed while our chip is running,
> >>>> the signal level changes from HIGH to LOW and then back to HIGH.
> >>>>
> >>>> Of course, we can also use the following:
> >>>> static void lt9611c_reset(struct lt9611c *lt9611c)
> >>>> {
> >>>> gpiod_set_value_cansleep(lt9611c->reset_gpio, 0);
> >>>> msleep(50);
> >>>> gpiod_set_value_cansleep(lt9611c->reset_gpio, 1);
> >>>> msleep(20);
> >>>> }
> >>>
> >>> Makes no sense either and you just did not get the point and did not
> >>> answer my question. I asked WHY you leave asserted. Answer "we emulate"
> >>> is just plain wrong.
> >>>
> >>> So again please answer:
> >>>
> >>> Why do you leave device with reset asserted?
> >>>
> >>
> >> devicetree: reset-gpios = <&tlmm 128 GPIO_ACTIVE_HIGH>;
> >>
> >> GPIO_ACTIVE_HIGH:
> >>
> >> gpiod_set_value_cansleep(lt9611c->reset_gpio, 0); ------ reset pin
> >> is Low level : Clear the register configuration in the chip to stop
> >> the chip from working.
> >>
> >> gpiod_set_value_cansleep(lt9611c->reset_gpio, 1); ------ reset pin
> >> is high level: The chip resumes operation.
> >>
> >>
> >
> > Our purpose is: pull the level low to clear the register configuration
> > in the chip, and then pull it high to allow the MCU inside the chip to
> > re‑initialize the registers.
>
>
> And you do completely opposite... so that confirms your code is just wrong.
>
The lontium-lt9611.yaml uses GPIO_ACTIVE_HIGH. I am just following the
rule of this device tree. If I modify the device tree to use
GPIO_ACTIVE_LOW,
and use the following code in my driver, then my driver would be correct.
However, would the existing kernel drivers lontium-lt9611uxc.c and
lontium-lt9611.c be affected?
static void lt9611c_reset(struct lt9611c *lt9611c)
{
gpiod_set_value_cansleep(lt9611c->reset_gpio, 1);
msleep(50);
gpiod_set_value_cansleep(lt9611c->reset_gpio, 0);
msleep(20);
}
>
> Best regards,
> Krzysztof
^ permalink raw reply
* Re: [PATCH v2 2/2] arm64: dts: qcom: kaanapali: fix traceNoC probe issue
From: Jie Gan @ 2026-06-26 2:03 UTC (permalink / raw)
To: Leo Yan
Cc: Suzuki K Poulose, Konrad Dybcio, Bjorn Andersson, Konrad Dybcio,
Rob Herring, Krzysztof Kozlowski, Conor Dooley, Tingwei Zhang,
Jingyi Wang, Abel Vesa, Mike Leach, James Clark, Yuanfang Zhang,
linux-arm-msm, devicetree, linux-kernel, coresight,
linux-arm-kernel
In-Reply-To: <20260625085643.GD575984@e132581.arm.com>
On 6/25/2026 4:56 PM, Leo Yan wrote:
> On Thu, Jun 25, 2026 at 09:01:18AM +0800, Jie Gan wrote:
>
> [...]
>
>>>> However, I believe it is acceptable to allocate an ATID for the itNoC device
>>>> and the issue can be fixed with this way.
>>>
>>> I think so.
>>
>> Hi Suzuki/Leo
>>
>> Which solution do you prefer to address the issue?
>
> I will leave this to Suzuki.
>
>> The interconnect traceNoC platform driver is intended for the itnoc device,
>> implying that no TPDM devices are connected to it. So, if I modify it to
>> allocate an ATID, I think it would be better to rename the “itnoc” node
>> accordingly? Or it's ok to leave it as-is?
>>
>> BTW, the traceNoC device definitely is an AMBA device with CID/PID
>> registers.
>
> Just to share a bit thoughts on the driver's design.
>
> I think it would be better to keep the probe function generic. The AMBA
> probe should not be specific to TraceNoC, and the platform probe should
> not be only dedicated to the interconnect TraceNoC. The probe function
> should simply handle a device that appears on either the AMBA bus or the
> platform bus.
>
> So the question is: if allocat an ATID for all traceNoC devices, do you
> still need to distinguish TraceNoC types? If no, then the code can be
> unified.
>
Hi Leo,
To be honest, I would prefer not to modify the interconnect platform
driver. On some Qualcomm platforms, multiple itnoc devices reside within
small blocks(one or more than one for each block) and are connected to a
dummy source. In such cases, two ATIDs are allocated for a path (the
dummy source and the itnoc), which is inefficient. This is why the itnoc
platform driver created to avoid this waste.
The TraceNoC (called as AG TraceNoC) is a generic TraceNoC device which
connected to multiple source and link devices, aggregating data from all
source devices into a single output path.
This device is implemented as an AMBA device but lacks proper hardware
configuration. As a result, it must be handled in the driver as a
workaround, which unfortunately breaks the original design intent.
Thanks,
Jie
> Thanks,
> Leo
^ permalink raw reply
* Re: [PATCH 2/2] arm64: tegra: Add Lenovo ThinkEdge SE70 carrier board DTS
From: sashiko-bot @ 2026-06-26 1:23 UTC (permalink / raw)
To: Jiqi Li; +Cc: robh, conor+dt, devicetree
In-Reply-To: <20260626010950.459899-3-lijq9@lenovo.com>
Thank you for your contribution! Sashiko AI review found 6 potential issue(s) to consider:
- [High] Peripheral overrides and configuration nodes are incorrectly placed at the root of the device tree, failing to override the actual bus children.
- [High] The `fixed-regulators` container lacks the `compatible = "simple-bus"` property, preventing its children from probing.
- [High] The `cd-inverted` property combined with `GPIO_ACTIVE_LOW` causes a double-inversion of the SD card detect signal.
- [Medium] Use of downstream Linux-for-Tegra (L4T) device tree properties that are invalid in mainline.
- [Low] Device tree node names use underscores instead of hyphens.
- [Low] Mismatch between inline code comment and regulator voltage configuration.
--
commit ce1b543209b572c99dba284d418dec1c8ce39718
Author: Jiqi Li <lijq9@lenovo.com>
arm64: tegra: Add Lenovo ThinkEdge SE70 carrier board DTS
ThinkEdge SE70 is a fanless industrial edge gateway built around
NVIDIA Tegra194 Xavier NX SOM. This patch adds a standalone device
tree file describing core carrier board peripherals:
- Custom 40-pin header pinmux configuration
- External SD card slot with dedicated 3.3V fixed regulator
No fan, PWM, tachometer, extra camera/spi peripherals are present
on this passively cooled platform, so unused nodes are explicitly
disabled following mainline device tree best practices.
Static verification passed: dt_binding_check and dtbs compilation
complete without errors.
[ ... ]
> diff --git a/arch/arm64/boot/dts/nvidia/tegra194-lenovo-thinkedge-se70.dts b/arch/arm64/boot/dts/nvidia/tegra194-lenovo-thinkedge-se70.dts
> new file mode 100644
> index 0000000000000..075e057c90954
> --- /dev/null
> +++ b/arch/arm64/boot/dts/nvidia/tegra194-lenovo-thinkedge-se70.dts
> @@ -0,0 +1,167 @@
> +// SPDX-License-Identifier: GPL-2.0
> +/dts-v1/;
> +
> +#include "tegra194-p3668-0001.dtsi"
> +#include "tegra194-p3509-0000.dtsi"
> +
> +/ {
> + model = "Lenovo ThinkEdge SE70";
> + compatible = "lenovo,thinkedge-se70", "nvidia,p3509-0000+p3668-0001", "nvidia,tegra194";
> +
> + chosen {
> + bootargs = "console=ttyTCU0,115200";
> + };
> +
> + /* Fixed 2.3V regulator for external SD card slot */
[Severity: Low]
Is this comment accurate? It mentions a 2.3V regulator, but the configuration
properties below (regulator-min-microvolt and regulator-max-microvolt) enforce
3.3V.
> + fixed-regulators {
[Severity: High]
Does this fixed-regulators container need a compatible = "simple-bus" property?
Without a recognized bus compatible string, of_platform_populate() won't
recurse into this node at boot. This would prevent the ap2306gn_3v3_sd child
regulator from probing, causing the SDHCI controller requesting it to fail with
-EPROBE_DEFER.
> + ap2306gn_3v3_sd: ap2306gn_3v3_sd {
[Severity: Low]
Should this node name use hyphens instead of underscores (e.g.,
ap2306gn-3v3-sd) to comply with Devicetree specification naming rules and avoid
node_name_chars warnings during compilation?
> + compatible = "regulator-fixed";
> + regulator-name = "ap2306gn-3v3-sd";
> + regulator-min-microvolt = <3300000>;
> + regulator-max-microvolt = <3300000>;
[ ... ]
> + /* Custom pinmux configurations for 40-pin expansion header */
> + pinmux@c302000 {
[Severity: High]
Are these peripheral and pinmux configuration nodes incorrectly placed at the
root level of the device tree (/ {}) rather than being children of the SoC bus?
Placing nodes like pinmux@..., i2c@..., and sdhci@... directly under the root
creates disconnected dummy nodes instead of overriding the actual bus-attached
controllers, causing these intended configurations to be completely ignored.
> + status = "okay";
> + touch_clk_pcc4 {
[ ... ]
> + pinmux@2430028 {
> + status = "okay";
> + soc_gpio41_pq5 {
> + nvidia,pins = "soc_gpio41_pq5";
> + nvidia,function = "rsvd2";
> + nvidia,pull = <TEGRA_PIN_PULL_NONE>;
> + nvidia,tristate = <TEGRA_PIN_DISABLE>;
> + nvidia,enable-input = <TEGRA_PIN_DISABLE>;
> + nvidia,lpdr = <TEGRA_PIN_DISABLE>;
> + nvidia,io-high-voltage = <TEGRA_PIN_DISABLE>;
[Severity: Medium]
Are nvidia,lpdr and nvidia,io-high-voltage downstream Linux-for-Tegra (L4T)
properties? They don't appear to exist in the mainline devicetree bindings,
which means they will be ignored by upstream drivers and fail dt_binding_check
schema validation.
> + };
> + };
[ ... ]
> + /* SDMMC3 for external user SD card slot with dedicated 3.3V power */
> + sdhci@3440000 {
[Severity: High]
Similar to the pinmux nodes above, is this sdhci node placed as a direct child
of the root (/ {}) instead of the SoC bus? This creates a new orphaned node
rather than overriding the actual bus-attached SDHCI controller.
> + uhs-mask = <0x78>;
> + mmc-ocr-mask = <0x0>;
[Severity: Medium]
Are uhs-mask and mmc-ocr-mask valid mainline properties? Like the pinmux
properties above, these appear to be downstream L4T properties that will fail
dt_binding_check schema validation.
> + cd-inverted;
> + cd-gpios = <&gpio_aon TEGRA194_AON_GPIO(CC, 4) GPIO_ACTIVE_LOW>;
[Severity: High]
Does combining the cd-inverted property with GPIO_ACTIVE_LOW in cd-gpios cause
a logical double inversion of the SD card detect signal? The GPIO subsystem
will invert the active-low physical signal, and then the MMC core will invert
that result again due to cd-inverted. This could mean an inserted card is seen
as removed and vice versa, breaking card hotplugging.
> + nvidia,cd-wakeup-capable;
[Severity: Medium]
Is nvidia,cd-wakeup-capable another downstream property unsupported in
mainline?
> + vmmc-supply = <&ap2306gn_3v3_sd>;
> + status = "okay";
> + };
[ ... ]
> + pwm@32f0000 {
> + status = "disabled";
> + };
> + generic_pwm_tachometer {
[Severity: Low]
Should this node name use hyphens instead of underscores (e.g.,
generic-pwm-tachometer) to avoid devicetree specification violations and
node_name_chars warnings?
> + status = "disabled";
> + };
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260626010950.459899-1-lijq9@lenovo.com?part=2
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox