* [PATCH v3 0/3] Add support for the REFGEN in the IPQ9650 SoC
@ 2026-06-15 8:35 Kathiravan Thirumoorthy
2026-06-15 8:35 ` [PATCH v3 1/3] regulator: qcom-refgen: correct the regulator type to CURRENT Kathiravan Thirumoorthy
` (2 more replies)
0 siblings, 3 replies; 6+ messages in thread
From: Kathiravan Thirumoorthy @ 2026-06-15 8:35 UTC (permalink / raw)
To: Liam Girdwood, Mark Brown, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Konrad Dybcio
Cc: linux-arm-msm, linux-kernel, devicetree, Kathiravan Thirumoorthy,
stable, Konrad Dybcio, Dmitry Baryshkov
IPQ9650 SoC has 2 REFGEN blocks providing the reference current to
the PCIe and USB, UNIPHY PHYs. For the other SoCs, clocks for this block
is enabled on power up but that's not the case for IPQ9650 and we have
to explicitly enable those clocks.
Document the same and add support for it.
Correct the regulator type to REGULATOR_CURRENT, as the REFGEN block
supplies the reference current to PHYs in the SoC, per the REFGEN IP
team, aligning it with the hardware behavior.
Signed-off-by: Kathiravan Thirumoorthy <kathiravan.thirumoorthy@oss.qualcomm.com>
---
Changes in v3:
- Pick up the R-b tags
- Use the lower case hex number in patch 2
- Document the IPQ9650 compatible as separate one not as a fallback and
move the allOf block after the 'required:' section
- Link to v2: https://patch.msgid.link/20260611-ipq9650_refgen-v2-0-d96a91d5b99e@oss.qualcomm.com
Changes in v2:
- New patch 1/3 - change the regulator type to align with HW behavior
- Add the constraints for clock and clock-names property in the binding
- Read the REFGEN_STATUS register to find out the regulator is enabled
- Dropped the unused slab.h
- Link to v1: https://patch.msgid.link/20260602-ipq9650_refgen-v1-0-55e2afa5ff64@oss.qualcomm.com
To: Liam Girdwood <lgirdwood@gmail.com>
To: Mark Brown <broonie@kernel.org>
To: Rob Herring <robh@kernel.org>
To: Krzysztof Kozlowski <krzk+dt@kernel.org>
To: Conor Dooley <conor+dt@kernel.org>
To: Konrad Dybcio <konradybcio@kernel.org>
Cc: linux-arm-msm@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
Cc: devicetree@vger.kernel.org
---
Kathiravan Thirumoorthy (3):
regulator: qcom-refgen: correct the regulator type to CURRENT
regulator: dt-bindings: qcom,sdm845-refgen-regulator: Document IPQ9650
regulator: qcom-refgen: add support for the IPQ9650 SoC
.../regulator/qcom,sdm845-refgen-regulator.yaml | 31 +++++++-
drivers/regulator/qcom-refgen-regulator.c | 93 ++++++++++++++++++++--
2 files changed, 115 insertions(+), 9 deletions(-)
---
base-commit: c425609d6ac4012c8bbf01ec2e10e801b1923a7b
change-id: 20260520-ipq9650_refgen-196b570d8bc0
Best regards,
--
Kathiravan Thirumoorthy <kathiravan.thirumoorthy@oss.qualcomm.com>
^ permalink raw reply [flat|nested] 6+ messages in thread
* [PATCH v3 1/3] regulator: qcom-refgen: correct the regulator type to CURRENT
2026-06-15 8:35 [PATCH v3 0/3] Add support for the REFGEN in the IPQ9650 SoC Kathiravan Thirumoorthy
@ 2026-06-15 8:35 ` Kathiravan Thirumoorthy
2026-06-15 8:35 ` [PATCH v3 2/3] regulator: dt-bindings: qcom,sdm845-refgen-regulator: Document IPQ9650 Kathiravan Thirumoorthy
2026-06-15 8:35 ` [PATCH v3 3/3] regulator: qcom-refgen: add support for the IPQ9650 SoC Kathiravan Thirumoorthy
2 siblings, 0 replies; 6+ messages in thread
From: Kathiravan Thirumoorthy @ 2026-06-15 8:35 UTC (permalink / raw)
To: Liam Girdwood, Mark Brown, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Konrad Dybcio
Cc: linux-arm-msm, linux-kernel, devicetree, Kathiravan Thirumoorthy,
stable, Konrad Dybcio
As per the REFGEN IP team, this block supplies the reference current to
the PHYs in the SoC. So, correct the regulator type to REGULATOR_CURRENT
to match with the HW behavior.
Fixes: 7cbfbe237960 ("regulator: Introduce Qualcomm REFGEN regulator driver")
Cc: stable@vger.kernel.org
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Signed-off-by: Kathiravan Thirumoorthy <kathiravan.thirumoorthy@oss.qualcomm.com>
---
drivers/regulator/qcom-refgen-regulator.c | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/regulator/qcom-refgen-regulator.c b/drivers/regulator/qcom-refgen-regulator.c
index 299ac3c8c3bc..6a3795469927 100644
--- a/drivers/regulator/qcom-refgen-regulator.c
+++ b/drivers/regulator/qcom-refgen-regulator.c
@@ -66,7 +66,7 @@ static const struct regulator_desc sdm845_refgen_desc = {
.enable_time = 5,
.name = "refgen",
.owner = THIS_MODULE,
- .type = REGULATOR_VOLTAGE,
+ .type = REGULATOR_CURRENT,
.ops = &(const struct regulator_ops) {
.enable = qcom_sdm845_refgen_enable,
.disable = qcom_sdm845_refgen_disable,
@@ -82,7 +82,7 @@ static const struct regulator_desc sm8250_refgen_desc = {
.enable_time = 5,
.name = "refgen",
.owner = THIS_MODULE,
- .type = REGULATOR_VOLTAGE,
+ .type = REGULATOR_CURRENT,
.ops = &(const struct regulator_ops) {
.enable = regulator_enable_regmap,
.disable = regulator_disable_regmap,
--
2.34.1
^ permalink raw reply related [flat|nested] 6+ messages in thread
* [PATCH v3 2/3] regulator: dt-bindings: qcom,sdm845-refgen-regulator: Document IPQ9650
2026-06-15 8:35 [PATCH v3 0/3] Add support for the REFGEN in the IPQ9650 SoC Kathiravan Thirumoorthy
2026-06-15 8:35 ` [PATCH v3 1/3] regulator: qcom-refgen: correct the regulator type to CURRENT Kathiravan Thirumoorthy
@ 2026-06-15 8:35 ` Kathiravan Thirumoorthy
2026-06-15 8:35 ` [PATCH v3 3/3] regulator: qcom-refgen: add support for the IPQ9650 SoC Kathiravan Thirumoorthy
2 siblings, 0 replies; 6+ messages in thread
From: Kathiravan Thirumoorthy @ 2026-06-15 8:35 UTC (permalink / raw)
To: Liam Girdwood, Mark Brown, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Konrad Dybcio
Cc: linux-arm-msm, linux-kernel, devicetree, Kathiravan Thirumoorthy
IPQ9650 has two REFGEN blocks which provide reference current to the PCIe,
USB and UNIPHY PHYs. Unlike other supported platforms, IPQ9650 requires the
REFGEN clocks to be enabled explicitly.
Document the IPQ9650 compatible and the required clocks for it.
While at it, move the allOf block after the 'required' property section.
Signed-off-by: Kathiravan Thirumoorthy <kathiravan.thirumoorthy@oss.qualcomm.com>
---
.../regulator/qcom,sdm845-refgen-regulator.yaml | 31 +++++++++++++++++++---
1 file changed, 28 insertions(+), 3 deletions(-)
diff --git a/Documentation/devicetree/bindings/regulator/qcom,sdm845-refgen-regulator.yaml b/Documentation/devicetree/bindings/regulator/qcom,sdm845-refgen-regulator.yaml
index 40f9223d4c27..0bbf7c806fbc 100644
--- a/Documentation/devicetree/bindings/regulator/qcom,sdm845-refgen-regulator.yaml
+++ b/Documentation/devicetree/bindings/regulator/qcom,sdm845-refgen-regulator.yaml
@@ -13,9 +13,6 @@ description:
The REFGEN (reference voltage generator) regulator provides reference
voltage for on-chip IPs (like PHYs) on some Qualcomm SoCs.
-allOf:
- - $ref: regulator.yaml#
-
properties:
compatible:
oneOf:
@@ -39,16 +36,44 @@ properties:
- const: qcom,sm8250-refgen-regulator
- enum:
+ - qcom,ipq9650-refgen-regulator
- qcom,sdm845-refgen-regulator
- qcom,sm8250-refgen-regulator
reg:
maxItems: 1
+ clocks:
+ items:
+ - description: Core reference clock
+ - description: AHB interface clock
+
+ clock-names:
+ items:
+ - const: core
+ - const: hclk
+
required:
- compatible
- reg
+allOf:
+ - $ref: regulator.yaml#
+
+ - if:
+ properties:
+ compatible:
+ contains:
+ const: qcom,ipq9650-refgen-regulator
+ then:
+ required:
+ - clocks
+ - clock-names
+ else:
+ properties:
+ clocks: false
+ clock-names: false
+
unevaluatedProperties: false
examples:
--
2.34.1
^ permalink raw reply related [flat|nested] 6+ messages in thread
* [PATCH v3 3/3] regulator: qcom-refgen: add support for the IPQ9650 SoC
2026-06-15 8:35 [PATCH v3 0/3] Add support for the REFGEN in the IPQ9650 SoC Kathiravan Thirumoorthy
2026-06-15 8:35 ` [PATCH v3 1/3] regulator: qcom-refgen: correct the regulator type to CURRENT Kathiravan Thirumoorthy
2026-06-15 8:35 ` [PATCH v3 2/3] regulator: dt-bindings: qcom,sdm845-refgen-regulator: Document IPQ9650 Kathiravan Thirumoorthy
@ 2026-06-15 8:35 ` Kathiravan Thirumoorthy
2026-06-15 8:46 ` sashiko-bot
2 siblings, 1 reply; 6+ messages in thread
From: Kathiravan Thirumoorthy @ 2026-06-15 8:35 UTC (permalink / raw)
To: Liam Girdwood, Mark Brown, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Konrad Dybcio
Cc: linux-arm-msm, linux-kernel, devicetree, Kathiravan Thirumoorthy,
Dmitry Baryshkov
IPQ9650 SoC has 2 REFGEN blocks providing the reference current to the
PCIe and USB, UNIPHY PHYs. For the other SoCs, clock for this block is
enabled on power up but that's not the case for IPQ9650 and we have to
enable those clocks explicitly to bring up the PHYs properly.
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Signed-off-by: Kathiravan Thirumoorthy <kathiravan.thirumoorthy@oss.qualcomm.com>
---
drivers/regulator/qcom-refgen-regulator.c | 89 +++++++++++++++++++++++++++++--
1 file changed, 85 insertions(+), 4 deletions(-)
diff --git a/drivers/regulator/qcom-refgen-regulator.c b/drivers/regulator/qcom-refgen-regulator.c
index 6a3795469927..4b8aa40d7efe 100644
--- a/drivers/regulator/qcom-refgen-regulator.c
+++ b/drivers/regulator/qcom-refgen-regulator.c
@@ -3,6 +3,7 @@
// Copyright (c) 2023, Linaro Limited
#include <linux/bitfield.h>
+#include <linux/clk.h>
#include <linux/module.h>
#include <linux/of.h>
#include <linux/platform_device.h>
@@ -16,6 +17,10 @@
#define REFGEN_BIAS_EN_ENABLE 0x7
#define REFGEN_BIAS_EN_DISABLE 0x6
+#define REFGEN_REG_REFGEN_STATUS 0xc
+#define REFGEN_STATUS_OUT_MASK BIT(3)
+ #define REFGEN_STATUS_OUT_ENABLE 0x8
+
#define REFGEN_REG_BG_CTRL 0x14
#define REFGEN_BG_CTRL_MASK GENMASK(2, 1)
#define REFGEN_BG_CTRL_ENABLE 0x3
@@ -25,6 +30,16 @@
#define REFGEN_PWRDWN_CTRL5_MASK BIT(0)
#define REFGEN_PWRDWN_CTRL5_ENABLE 0x1
+struct qcom_refgen_regulator_data {
+ const struct regulator_desc *rdesc;
+ bool has_clocks;
+};
+
+struct qcom_refgen_drvdata {
+ struct clk_bulk_data *clks;
+ int num_clks;
+};
+
static int qcom_sdm845_refgen_enable(struct regulator_dev *rdev)
{
regmap_update_bits(rdev->regmap, REFGEN_REG_BG_CTRL, REFGEN_BG_CTRL_MASK,
@@ -62,6 +77,42 @@ static int qcom_sdm845_refgen_is_enabled(struct regulator_dev *rdev)
return 1;
}
+static int qcom_ipq9650_refgen_enable(struct regulator_dev *rdev)
+{
+ struct qcom_refgen_drvdata *drvdata = rdev_get_drvdata(rdev);
+ int ret;
+
+ ret = clk_bulk_prepare_enable(drvdata->num_clks, drvdata->clks);
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
+static int qcom_ipq9650_refgen_disable(struct regulator_dev *rdev)
+{
+ struct qcom_refgen_drvdata *drvdata = rdev_get_drvdata(rdev);
+
+ clk_bulk_disable_unprepare(drvdata->num_clks, drvdata->clks);
+
+ return 0;
+}
+
+static const struct regulator_desc ipq9650_refgen_desc = {
+ .enable_reg = REFGEN_REG_REFGEN_STATUS,
+ .enable_mask = REFGEN_STATUS_OUT_MASK,
+ .enable_val = REFGEN_STATUS_OUT_ENABLE,
+ .enable_time = 5,
+ .name = "refgen",
+ .owner = THIS_MODULE,
+ .type = REGULATOR_CURRENT,
+ .ops = &(const struct regulator_ops) {
+ .enable = qcom_ipq9650_refgen_enable,
+ .disable = qcom_ipq9650_refgen_disable,
+ .is_enabled = regulator_is_enabled_regmap,
+ },
+};
+
static const struct regulator_desc sdm845_refgen_desc = {
.enable_time = 5,
.name = "refgen",
@@ -90,6 +141,19 @@ static const struct regulator_desc sm8250_refgen_desc = {
},
};
+static const struct qcom_refgen_regulator_data ipq9650_data = {
+ .rdesc = &ipq9650_refgen_desc,
+ .has_clocks = true,
+};
+
+static const struct qcom_refgen_regulator_data sdm845_data = {
+ .rdesc = &sdm845_refgen_desc,
+};
+
+static const struct qcom_refgen_regulator_data sm8250_data = {
+ .rdesc = &sm8250_refgen_desc,
+};
+
static const struct regmap_config qcom_refgen_regmap_config = {
.reg_bits = 32,
.reg_stride = 4,
@@ -98,6 +162,8 @@ static const struct regmap_config qcom_refgen_regmap_config = {
static int qcom_refgen_probe(struct platform_device *pdev)
{
+ const struct qcom_refgen_regulator_data *data;
+ struct qcom_refgen_drvdata *drvdata = NULL;
struct regulator_init_data *init_data;
struct regulator_config config = {};
const struct regulator_desc *rdesc;
@@ -106,10 +172,23 @@ static int qcom_refgen_probe(struct platform_device *pdev)
struct regmap *regmap;
void __iomem *base;
- rdesc = of_device_get_match_data(dev);
- if (!rdesc)
+ data = of_device_get_match_data(dev);
+ if (!data)
return -ENODATA;
+ if (data->has_clocks) {
+ drvdata = devm_kzalloc(dev, sizeof(*drvdata), GFP_KERNEL);
+ if (!drvdata)
+ return -ENOMEM;
+
+ drvdata->num_clks = devm_clk_bulk_get_all(dev, &drvdata->clks);
+ if (drvdata->num_clks < 0)
+ return dev_err_probe(dev, drvdata->num_clks,
+ "failed to get clocks\n");
+ }
+
+ rdesc = data->rdesc;
+
base = devm_platform_ioremap_resource(pdev, 0);
if (IS_ERR(base))
return PTR_ERR(base);
@@ -126,6 +205,7 @@ static int qcom_refgen_probe(struct platform_device *pdev)
config.init_data = init_data;
config.of_node = dev->of_node;
config.regmap = regmap;
+ config.driver_data = drvdata;
rdev = devm_regulator_register(dev, rdesc, &config);
if (IS_ERR(rdev))
@@ -135,8 +215,9 @@ static int qcom_refgen_probe(struct platform_device *pdev)
}
static const struct of_device_id qcom_refgen_match_table[] = {
- { .compatible = "qcom,sdm845-refgen-regulator", .data = &sdm845_refgen_desc },
- { .compatible = "qcom,sm8250-refgen-regulator", .data = &sm8250_refgen_desc },
+ { .compatible = "qcom,ipq9650-refgen-regulator", .data = &ipq9650_data },
+ { .compatible = "qcom,sdm845-refgen-regulator", .data = &sdm845_data },
+ { .compatible = "qcom,sm8250-refgen-regulator", .data = &sm8250_data },
{ }
};
MODULE_DEVICE_TABLE(of, qcom_refgen_match_table);
--
2.34.1
^ permalink raw reply related [flat|nested] 6+ messages in thread
* Re: [PATCH v3 3/3] regulator: qcom-refgen: add support for the IPQ9650 SoC
2026-06-15 8:35 ` [PATCH v3 3/3] regulator: qcom-refgen: add support for the IPQ9650 SoC Kathiravan Thirumoorthy
@ 2026-06-15 8:46 ` sashiko-bot
2026-06-15 8:54 ` Kathiravan Thirumoorthy
0 siblings, 1 reply; 6+ messages in thread
From: sashiko-bot @ 2026-06-15 8:46 UTC (permalink / raw)
To: Kathiravan Thirumoorthy; +Cc: conor+dt, robh, devicetree
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] The `.is_enabled` callback maps to `regulator_is_enabled_regmap` without enabling clocks, causing a synchronous bus hang on IPQ9650 during probe.
--
commit 57e8a1a06a52f828e01d53b16f6c708e7f6df23e
Author: Kathiravan Thirumoorthy <kathiravan.thirumoorthy@oss.qualcomm.com>
regulator: qcom-refgen: add support for the IPQ9650 SoC
This commit adds support for the IPQ9650 SoC to the qcom-refgen regulator
driver. It introduces explicit clock management for the REFGEN blocks, as
they are not enabled on power up for this specific SoC.
> diff --git a/drivers/regulator/qcom-refgen-regulator.c b/drivers/regulator/qcom-refgen-regulator.c
> index 6a3795469927e..4b8aa40d7efe0 100644
> --- a/drivers/regulator/qcom-refgen-regulator.c
> +++ b/drivers/regulator/qcom-refgen-regulator.c
[ ... ]
> +static const struct regulator_desc ipq9650_refgen_desc = {
> + .enable_reg = REFGEN_REG_REFGEN_STATUS,
> + .enable_mask = REFGEN_STATUS_OUT_MASK,
> + .enable_val = REFGEN_STATUS_OUT_ENABLE,
> + .enable_time = 5,
> + .name = "refgen",
> + .owner = THIS_MODULE,
> + .type = REGULATOR_CURRENT,
> + .ops = &(const struct regulator_ops) {
> + .enable = qcom_ipq9650_refgen_enable,
> + .disable = qcom_ipq9650_refgen_disable,
> + .is_enabled = regulator_is_enabled_regmap,
[Severity: High]
Does this result in an unclocked MMIO read?
During device probe, the regulator core calls the is_enabled callback via
devm_regulator_register() to determine the initial state:
qcom_refgen_probe()
devm_regulator_register()
regulator_is_enabled_regmap()
Since the IPQ9650 clocks are disabled on power up and only enabled later in
qcom_ipq9650_refgen_enable(), regulator_is_enabled_regmap() will perform an
MMIO read on the REFGEN_REG_REFGEN_STATUS register without the required
clocks enabled.
Could this cause a synchronous external abort and a kernel panic during
boot?
> + },
> +};
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260615-ipq9650_refgen-v3-0-5f611623629c@oss.qualcomm.com?part=3
^ permalink raw reply [flat|nested] 6+ messages in thread
* Re: [PATCH v3 3/3] regulator: qcom-refgen: add support for the IPQ9650 SoC
2026-06-15 8:46 ` sashiko-bot
@ 2026-06-15 8:54 ` Kathiravan Thirumoorthy
0 siblings, 0 replies; 6+ messages in thread
From: Kathiravan Thirumoorthy @ 2026-06-15 8:54 UTC (permalink / raw)
To: sashiko-reviews; +Cc: conor+dt, robh, devicetree
On 6/15/2026 2:16 PM, sashiko-bot@kernel.org wrote:
> Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
> - [High] The `.is_enabled` callback maps to `regulator_is_enabled_regmap` without enabling clocks, causing a synchronous bus hang on IPQ9650 during probe.
> --
>
> commit 57e8a1a06a52f828e01d53b16f6c708e7f6df23e
> Author: Kathiravan Thirumoorthy <kathiravan.thirumoorthy@oss.qualcomm.com>
>
> regulator: qcom-refgen: add support for the IPQ9650 SoC
>
> This commit adds support for the IPQ9650 SoC to the qcom-refgen regulator
> driver. It introduces explicit clock management for the REFGEN blocks, as
> they are not enabled on power up for this specific SoC.
>
>> diff --git a/drivers/regulator/qcom-refgen-regulator.c b/drivers/regulator/qcom-refgen-regulator.c
>> index 6a3795469927e..4b8aa40d7efe0 100644
>> --- a/drivers/regulator/qcom-refgen-regulator.c
>> +++ b/drivers/regulator/qcom-refgen-regulator.c
> [ ... ]
>> +static const struct regulator_desc ipq9650_refgen_desc = {
>> + .enable_reg = REFGEN_REG_REFGEN_STATUS,
>> + .enable_mask = REFGEN_STATUS_OUT_MASK,
>> + .enable_val = REFGEN_STATUS_OUT_ENABLE,
>> + .enable_time = 5,
>> + .name = "refgen",
>> + .owner = THIS_MODULE,
>> + .type = REGULATOR_CURRENT,
>> + .ops = &(const struct regulator_ops) {
>> + .enable = qcom_ipq9650_refgen_enable,
>> + .disable = qcom_ipq9650_refgen_disable,
>> + .is_enabled = regulator_is_enabled_regmap,
> [Severity: High]
> Does this result in an unclocked MMIO read?
>
> During device probe, the regulator core calls the is_enabled callback via
> devm_regulator_register() to determine the initial state:
>
> qcom_refgen_probe()
> devm_regulator_register()
> regulator_is_enabled_regmap()
>
> Since the IPQ9650 clocks are disabled on power up and only enabled later in
> qcom_ipq9650_refgen_enable(), regulator_is_enabled_regmap() will perform an
> MMIO read on the REFGEN_REG_REFGEN_STATUS register without the required
> clocks enabled.
REFGEN block can be accessed without the clocks enabled as part of this
change. Hence there will no issue while checking the STATUS register in
the regulator_is_enabled_regmap().
>
> Could this cause a synchronous external abort and a kernel panic during
> boot?
>
>> + },
>> +};
^ permalink raw reply [flat|nested] 6+ messages in thread
end of thread, other threads:[~2026-06-15 8:54 UTC | newest]
Thread overview: 6+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-06-15 8:35 [PATCH v3 0/3] Add support for the REFGEN in the IPQ9650 SoC Kathiravan Thirumoorthy
2026-06-15 8:35 ` [PATCH v3 1/3] regulator: qcom-refgen: correct the regulator type to CURRENT Kathiravan Thirumoorthy
2026-06-15 8:35 ` [PATCH v3 2/3] regulator: dt-bindings: qcom,sdm845-refgen-regulator: Document IPQ9650 Kathiravan Thirumoorthy
2026-06-15 8:35 ` [PATCH v3 3/3] regulator: qcom-refgen: add support for the IPQ9650 SoC Kathiravan Thirumoorthy
2026-06-15 8:46 ` sashiko-bot
2026-06-15 8:54 ` Kathiravan Thirumoorthy
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox