* Re: [PATCH v5 1/2] dt-bindings: phy: add support for NXPs TJA1145 CAN transceiver
From: Dimitri Fedrau @ 2026-05-22 8:13 UTC (permalink / raw)
To: sashiko-reviews
Cc: Dimitri Fedrau via B4 Relay, linux-phy, conor+dt, devicetree,
vkoul, olteanv, robh, neil.armstrong, krzk+dt
In-Reply-To: <20260514051738.B2D32C2BCB7@smtp.kernel.org>
Am Thu, May 14, 2026 at 05:17:38AM +0000 schrieb sashiko-bot@kernel.org:
> Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
> - [Medium] The dt-binding omits support for the `max-bitrate` property.
> - [Medium] The dt-binding omits support for the `interrupts` property for wake-up routing.
> --
>
> commit 853ad7c93ebe1c2a625ddddde401c4aaad496a8e
> Author: Dimitri Fedrau <dimitri.fedrau@liebherr.com>
>
> dt-bindings: phy: add support for NXPs TJA1145 CAN transceiver
>
> This commit adds documentation for the NXP TJA1145 CAN transceiver, residing
> in the generic PHY subsystem bindings. It describes the required SPI
> configurations and supply properties for the device.
>
> > diff --git a/Documentation/devicetree/bindings/phy/nxp,tja1145.yaml b/Documentation/devicetree/bindings/phy/nxp,tja1145.yaml
> > new file mode 100644
> > --- /dev/null
> > +++ b/Documentation/devicetree/bindings/phy/nxp,tja1145.yaml
>
> [ ... ]
>
> > + vbat-supply:
> > + description:
> > + Battery supply voltage
> > +
> > +required:
> > + - compatible
> > + - reg
> > + - "#phy-cells"
> > + - spi-cpha
> > +
> > +additionalProperties: false
>
> Does this binding need to include the max-bitrate property?
>
No, the max bitrate is know for the device. See:
https://lore.kernel.org/linux-phy/0b4b8291-40cf-4faf-a79f-48c56677f9a2@kernel.org/
> This property is standard for CAN transceivers to describe board-level
> capability constraints where the layout cannot support the chip's theoretical
> maximum speed. Since additionalProperties is set to false, valid device trees
> specifying a maximum bitrate will fail validation.
>
> Also, does this device tree binding need support for the interrupts property?
>
Not at the moment, this can be added later on when there is an
implementation for this features.
> The TJA1145 supports partial networking and wake-up functionality, which can
> route a wake-up signal to an interrupt line on the host processor. With
> additionalProperties set to false, it is impossible to describe this hardware
> interrupt routing in the device tree.
>
> --
> Sashiko AI review · https://sashiko.dev/#/patchset/20260513-tja1145-support-v5-0-38720a7ee63e@liebherr.com?part=1
>
> --
> linux-phy mailing list
> linux-phy@lists.infradead.org
> https://lists.infradead.org/mailman/listinfo/linux-phy
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH 3/4] PCI: qcom: Add Support for Eliza
From: Krzysztof Kozlowski @ 2026-05-22 6:51 UTC (permalink / raw)
To: Krishna Chaitanya Chundru
Cc: Vinod Koul, Neil Armstrong, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Lorenzo Pieralisi, Krzysztof Wilczyński,
Manivannan Sadhasivam, Bjorn Helgaas, Bjorn Andersson,
linux-arm-msm, linux-phy, devicetree, linux-kernel, linux-pci
In-Reply-To: <20260521-eliza-v1-3-97cdbe88389d@oss.qualcomm.com>
On Thu, May 21, 2026 at 07:35:31PM +0530, Krishna Chaitanya Chundru wrote:
> Add support for Eliza soc, which has two PCIe controllers capable
> of 8GT/s X1 and 8GT/s X2, using the cfg_1_9_0 configuration.
>
> Signed-off-by: Krishna Chaitanya Chundru <krishna.chundru@oss.qualcomm.com>
> ---
> drivers/pci/controller/dwc/pcie-qcom.c | 1 +
> 1 file changed, 1 insertion(+)
>
> diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
> index af6bf5cce65b..40f0a5f247eb 100644
> --- a/drivers/pci/controller/dwc/pcie-qcom.c
> +++ b/drivers/pci/controller/dwc/pcie-qcom.c
> @@ -2123,6 +2123,7 @@ static int qcom_pcie_resume_noirq(struct device *dev)
> static const struct of_device_id qcom_pcie_match[] = {
> { .compatible = "qcom,pcie-apq8064", .data = &cfg_2_1_0 },
> { .compatible = "qcom,pcie-apq8084", .data = &cfg_1_0_0 },
> + { .compatible = "qcom,pcie-eliza", .data = &cfg_1_9_0 },
So compatible with sm8550. Why isn't this explained in commit msg of
the binding?
Anyway, drop the change, pointless. Look how other devices handle this -
do you see kaanapali here? No.
Best regards,
Krzysztof
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH 2/4] dt-bindings: PCI: qcom: Document the Eliza PCIe Controller
From: Krzysztof Kozlowski @ 2026-05-22 6:50 UTC (permalink / raw)
To: Krishna Chaitanya Chundru
Cc: Vinod Koul, Neil Armstrong, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Lorenzo Pieralisi, Krzysztof Wilczyński,
Manivannan Sadhasivam, Bjorn Helgaas, Bjorn Andersson,
linux-arm-msm, linux-phy, devicetree, linux-kernel, linux-pci
In-Reply-To: <20260521-eliza-v1-2-97cdbe88389d@oss.qualcomm.com>
On Thu, May 21, 2026 at 07:35:30PM +0530, Krishna Chaitanya Chundru wrote:
> +description:
> + Qualcomm ELIZA SoC (and compatible) PCIe root complex controller is based on
> + the Synopsis DesignWare PCIe IP.
> +
> +properties:
> + compatible:
> + const: qcom,pcie-eliza
All new pcie compatibles moved to correct format.
> +
> + reg:
> + minItems: 5
> + maxItems: 6
> +
> + reg-names:
> + minItems: 5
> + items:
> + - const: parf # Qualcomm specific registers
> + - const: dbi # DesignWare PCIe registers
> + - const: elbi # External local bus interface registers
> + - const: atu # ATU address space
> + - const: config # PCIe configuration space
> + - const: mhi # MHI registers
> +
> + clocks:
> + maxItems: 7
> +
> + clock-names:
> + items:
> + - const: aux # Auxiliary clock
> + - const: cfg # Configuration clock
> + - const: bus_master # Master AXI clock
> + - const: bus_slave # Slave AXI clock
> + - const: slave_q2a # Slave Q2A clock
> + - const: ddrss_sf_tbu # PCIe SF TBU clock
> + - const: cnoc_sf_axi # Config NoC PCIe1 AXI clock
> +
> + interrupts:
> + minItems: 8
This should not be flexible. Neither 'reg'.
> + maxItems: 9
> +
> + interrupt-names:
> + minItems: 8
> + items:
> + - const: msi0
> + - const: msi1
> + - const: msi2
> + - const: msi3
> + - const: msi4
> + - const: msi5
> + - const: msi6
> + - const: msi7
> + - const: global
> +
> + resets:
> + maxItems: 2
> +
> + reset-names:
> + items:
> + - const: pci # PCIe core reset
> + - const: link_down # PCIe link down reset
> +
> +required:
> + - power-domains
> + - resets
> + - reset-names
> +
> +allOf:
> + - $ref: qcom,pcie-common.yaml#
> +
> +unevaluatedProperties: false
> +
> +examples:
> + - |
> + #include <dt-bindings/clock/qcom,eliza-gcc.h>
> + #include <dt-bindings/interrupt-controller/arm-gic.h>
> + #include <dt-bindings/interconnect/qcom,eliza-rpmh.h>
> +
> + soc {
> + #address-cells = <2>;
> + #size-cells = <2>;
> +
> + pcie@1c00000 {
> + compatible = "qcom,pcie-eliza";
> + reg = <0 0x01c00000 0 0x3000>,
> + <0 0x40000000 0 0xf1d>,
> + <0 0x40000f20 0 0xa8>,
> + <0 0x40001000 0 0x1000>,
> + <0 0x40100000 0 0x100000>;
> + reg-names = "parf", "dbi", "elbi", "atu", "config";
> + ranges = <0x01000000 0x0 0x00000000 0x0 0x40200000 0x0 0x100000>,
> + <0x02000000 0x0 0x40300000 0x0 0x40300000 0x0 0x3d00000>;
> +
> + bus-range = <0x00 0xff>;
> + device_type = "pci";
> + linux,pci-domain = <0>;
> + num-lanes = <1>;
> +
> + #address-cells = <3>;
> + #size-cells = <2>;
> +
> + clocks = <&gcc GCC_PCIE_0_AUX_CLK>,
> + <&gcc GCC_PCIE_0_CFG_AHB_CLK>,
> + <&gcc GCC_PCIE_0_MSTR_AXI_CLK>,
> + <&gcc GCC_PCIE_0_SLV_AXI_CLK>,
> + <&gcc GCC_PCIE_0_SLV_Q2A_AXI_CLK>,
> + <&gcc GCC_DDRSS_PCIE_SF_QTB_CLK>,
> + <&gcc GCC_CNOC_PCIE_SF_AXI_CLK>;
> + clock-names = "aux",
> + "cfg",
> + "bus_master",
> + "bus_slave",
> + "slave_q2a",
> + "ddrss_sf_tbu",
> + "cnoc_sf_axi";
> +
> + dma-coherent;
> +
> + interrupts = <GIC_SPI 376 IRQ_TYPE_LEVEL_HIGH>,
> + <GIC_SPI 478 IRQ_TYPE_LEVEL_HIGH>,
> + <GIC_SPI 479 IRQ_TYPE_LEVEL_HIGH>,
> + <GIC_SPI 535 IRQ_TYPE_LEVEL_HIGH>,
> + <GIC_SPI 536 IRQ_TYPE_LEVEL_HIGH>,
> + <GIC_SPI 537 IRQ_TYPE_LEVEL_HIGH>,
> + <GIC_SPI 540 IRQ_TYPE_LEVEL_HIGH>,
> + <GIC_SPI 653 IRQ_TYPE_LEVEL_HIGH>,
> + <GIC_SPI 370 IRQ_TYPE_LEVEL_HIGH>;
> + interrupt-names = "msi0", "msi1", "msi2", "msi3",
> + "msi4", "msi5", "msi6", "msi7", "global";
> + #interrupt-cells = <1>;
> + interrupt-map-mask = <0 0 0 0x7>;
> + interrupt-map = <0 0 0 1 &intc 0 0 0 564 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
> + <0 0 0 2 &intc 0 0 0 565 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
> + <0 0 0 3 &intc 0 0 0 566 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
> + <0 0 0 4 &intc 0 0 0 567 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
> +
> + interconnects = <&pcie_noc MASTER_PCIE_0 0 &mc_virt SLAVE_EBI1 0>,
> + <&gem_noc MASTER_APPSS_PROC 0 &cnoc_main SLAVE_PCIE_0 0>;
> + interconnect-names = "pcie-mem", "cpu-pcie";
> +
> + iommu-map = <0x0 &apps_smmu 0x1480 0x1>,
> + <0x100 &apps_smmu 0x1481 0x1>;
> +
> + pinctrl-0 = <&pcie0_default_state>;
> + pinctrl-names = "default";
> +
> + power-domains = <&gcc GCC_PCIE_0_GDSC>;
> +
> + resets = <&gcc GCC_PCIE_0_BCR>,
> + <&gcc GCC_PCIE_0_LINK_DOWN_BCR>;
> + reset-names = "pci",
> + "link_down";
> +
Drop stray blank line.
> + };
> + };
>
> --
> 2.34.1
>
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH 1/4] dt-bindings: phy: sc8280xp-qmp-pcie: Document Eliza PCIe phy
From: Krzysztof Kozlowski @ 2026-05-22 6:46 UTC (permalink / raw)
To: Krishna Chaitanya Chundru
Cc: Vinod Koul, Neil Armstrong, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Lorenzo Pieralisi, Krzysztof Wilczyński,
Manivannan Sadhasivam, Bjorn Helgaas, Bjorn Andersson,
linux-arm-msm, linux-phy, devicetree, linux-kernel, linux-pci
In-Reply-To: <20260521-eliza-v1-1-97cdbe88389d@oss.qualcomm.com>
On Thu, May 21, 2026 at 07:35:29PM +0530, Krishna Chaitanya Chundru wrote:
> Add compatibles for the Eliza PCIe QMP PHY's, which supports Gen3x1 and
> Gen3x2 configurations.
>
> Signed-off-by: Krishna Chaitanya Chundru <krishna.chundru@oss.qualcomm.com>
> ---
> .../devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml | 6 ++++++
> 1 file changed, 6 insertions(+)
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Best regards,
Krzysztof
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH v9 2/5] dt-bindings: phy: Add documentation for Airoha AN7581 USB PHY
From: Krzysztof Kozlowski @ 2026-05-22 6:06 UTC (permalink / raw)
To: Christian Marangi
Cc: Michael Turquette, Stephen Boyd, Brian Masney, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Vinod Koul, Neil Armstrong,
Lorenzo Bianconi, Felix Fietkau, linux-clk, devicetree,
linux-kernel, linux-arm-kernel, linux-phy
In-Reply-To: <20260521153645.7028-3-ansuelsmth@gmail.com>
On Thu, May 21, 2026 at 05:35:53PM +0200, Christian Marangi wrote:
> Add documentation for Airoha AN7581 USB PHY that describe the USB PHY
> for the USB controller.
>
> Airoha AN7581 SoC support a maximum of 2 USB port. The USB 2.0 mode is
> always supported. The USB 3.0 mode is optional and depends on the Serdes
> mode currently configured on the system for the relevant USB port.
>
> To correctly calibrate, the USB 2.0 port require correct value in
> "airoha,usb2-monitor-clk-sel" property. Both the 2 USB 2.0 port permit
> selecting one of the 4 monitor clock for calibration (internal clock not
> exposed to the system) but each port have only one of the 4 actually
> connected in HW hence the correct value needs to be specified in DT
> based on board and the physical port. Normally it's monitor clock 1 for
> USB1 and monitor clock 2 for USB2.
>
> To correctly setup the Serdes mode attached to the USB 3.0 mode, a phys
> property is required with the phandle pointing to the correct Serdes port
> provided by the SCU node. Providing the phys property is optional if USB
> 3.0 is not used.
>
> Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
> ---
> .../bindings/phy/airoha,an7581-usb-phy.yaml | 62 +++++++++++++++++++
> MAINTAINERS | 6 ++
> 2 files changed, 68 insertions(+)
> create mode 100644 Documentation/devicetree/bindings/phy/airoha,an7581-usb-phy.yaml
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Best regards,
Krzysztof
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH 5/5] drm/rockchip: cdn-dp: Add multiple bridges to support PHY port selection
From: Chaoyi Chen @ 2026-05-22 2:37 UTC (permalink / raw)
To: sashiko-reviews; +Cc: vkoul, linux-phy, neil.armstrong, olteanv, Heiko Stuebner
In-Reply-To: <20260521062223.913FB1F000E9@smtp.kernel.org>
Oh! Interesting AI. It really did uncover some issues.
On 5/21/2026 2:22 PM, sashiko-bot@kernel.org wrote:
> Thank you for your contribution! Sashiko AI review found 11 potential issue(s) to consider:
> - [High] Prematurely dropping the reference count of the last bridge in `cdn_bridge_add()` will cause a use-after-free.
> - [High] The `prev_port` pointer is used uninitialized in `cdn_dp_bridge_edid_read()`, leading to a kernel crash.
> - [High] `cdn_dp_connected_port()` ignores connection status for extcon configurations, breaking hotplug detection.
> - [High] Missing bounds check in `cdn_dp_parse_next_bridge_dt()` allows an out-of-bounds write to the `next_bridge_list` array.
> - [High] The `lanes` stack array is read out-of-bounds or uninitialized in `cdn_dp_connected_port()`.
> - [High] DRM bridge references are leaked on error paths during DT parsing and driver binding.
> - [High] If link training fails in `cdn_dp_switch_port()`, it returns an error but leaves the DP controller erroneously marked as active.
> - [High] `cdn_dp_switch_port()` incorrectly aborts hardware switching when the DP controller is active, causing EDID reads from the wrong port.
> - [High] Disabling an inactive bridge erroneously disables the active DP controller for another bridge.
> - [Medium] Overwriting `connector->fwnode` in `cdn_bridge_add()` causes a memory leak.
> - [Medium] Incorrect check for the active port treats valid index 0 as invalid.
> --
>
> Hi,
>
> I have reviewed the patch and found some potential issues to share.
>
> commit 082c705aa7547b521ad9df20ac76e0592b41864f
> Author: Chaoyi Chen <chaoyi.chen@rock-chips.com>
>
> drm/rockchip: cdn-dp: Add multiple bridges to support PHY port selection
>
> This commit adds support for multiple bridges to the Rockchip cdn-dp driver
> to allow switching between two USB/DP combo PHYs. It changes the driver to
> use the DRM AUX HPD bridge and adds DT parsing logic to register multiple
> bridges.
>
>> @@ -192,14 +193,27 @@ static int cdn_dp_get_sink_count(struct cdn_dp_device *dp, u8 *sink_count)
>> static struct cdn_dp_port *cdn_dp_connected_port(struct cdn_dp_device *dp)
>> {
>> struct cdn_dp_port *port;
>> - int i, lanes;
>> + int i, lanes[MAX_PHY];
>>
>> for (i = 0; i < dp->ports; i++) {
>> port = dp->port[i];
>> - lanes = cdn_dp_get_port_lanes(port);
>> - if (lanes)
>> + lanes[i] = cdn_dp_get_port_lanes(port);
>> + if (!dp->next_bridge_valid)
>> return port;
>
> [Severity: High]
> Does this unconditionally return the first port without checking if it is
> actually connected? If dp->next_bridge_valid is false (which is the case for
> extcon setups), it appears to return port on the first iteration regardless
> of lanes[i], completely breaking hotplug detection.
>
>> }
No.
>> +
>> + if (dp->next_bridge_valid) {
>> + /* If more than one port is available, pick the last active port */
>> + if (dp->active_port > 0 && lanes[dp->active_port])
>
> [Severity: Medium]
> Since dp->active_port is initialized to -1, valid port indices are 0 and 1.
> Does the check dp->active_port > 0 incorrectly evaluate to false when the
> active port is 0, skipping the active port?
>
That's right. Will fix in v2.
>> + return dp->port[dp->active_port];
>> +
>> + /* If the last active port is not available, pick an available port in order */
>> + for (i = 0; i < dp->bridge_count; i++) {
>> + if (lanes[i])
>
> [Severity: High]
> Can this read uninitialized stack memory? The lanes stack array is populated
> in a loop bounded by dp->ports, but accessed here in a loop bounded by
> dp->bridge_count.
>
> If dp->bridge_count > dp->ports, this will read uninitialized values.
> Furthermore, since lanes is sized to MAX_PHY, if dp->bridge_count > MAX_PHY,
> it will perform an out-of-bounds stack read.
>
No.
>> + return dp->port[i];
>> + }
>> + }
>> +
>> return NULL;
>> }
>
> [ ... ]
>
>> @@ -254,12 +268,45 @@ static const struct drm_edid *
>> cdn_dp_bridge_edid_read(struct drm_bridge *bridge, struct drm_connector *connector)
>> {
>> struct cdn_dp_device *dp = bridge_to_dp(bridge);
>> - const struct drm_edid *drm_edid;
>> + struct cdn_dp_bridge *dp_bridge = bridge_to_dp_bridge(bridge);
>> + struct cdn_dp_port *port = dp->port[dp_bridge->id];
>> + struct cdn_dp_port *prev_port;
>> + const struct drm_edid *drm_edid = NULL;
>> int i, ret;
>>
>> mutex_lock(&dp->lock);
>> +
>> + /* More than one port is available */
>> + if (dp->bridge_count > 1 && !port->phy_enabled) {
>> + for (i = 0; i < dp->bridge_count; i++) {
>> + /* Another port already enable */
>> + if (dp->bridge_list[i] != dp_bridge && dp->bridge_list[i]->enabled)
>> + goto get_cache;
>> + /* Find already enabled port */
>> + if (dp->port[i]->phy_enabled)
>> + prev_port = dp->port[i];
>> + }
>> +
>> + /* Switch to current port */
>> + if (prev_port) {
>
> [Severity: High]
> Can this lead to a kernel crash by dereferencing an uninitialized pointer?
> The prev_port variable is not initialized. If no ports are currently enabled
> (which is common at boot), the for loop will complete without assigning
> anything to prev_port.
>
> Then if (prev_port) evaluates garbage memory, and calling cdn_dp_switch_port
> with it will cause a kernel panic.
>
No.
>> + ret = cdn_dp_switch_port(dp, prev_port, port);
>> + if (ret)
>> + goto get_cache;
>> + }
>> + }
>
> [ ... ]
>
>> @@ -551,6 +599,54 @@ static bool cdn_dp_check_link_status(struct cdn_dp_device *dp)
>> return drm_dp_channel_eq_ok(link_status, min(port->lanes, sink_lanes));
>> }
>>
>> +static int cdn_dp_switch_port(struct cdn_dp_device *dp, struct cdn_dp_port *prev_port,
>> + struct cdn_dp_port *port)
>> +{
>> + int ret;
>> +
>> + if (dp->active)
>> + return 0;
>
> [Severity: High]
> Does this incorrectly abort hardware switching? If the DP controller is
> already active but currently on a different port, returning 0 skips the
> actual port switch. The caller cdn_dp_bridge_edid_read() will proceed with
> reading EDID from the wrong (already-active) port and caching it for the
> new port.
>
Actually, this is a redundant check. When dp->active is true,
this function is never called at all.
>> +
>> + ret = cdn_dp_disable_phy(dp, prev_port);
>> + if (ret)
>> + goto out;
>> + ret = cdn_dp_enable_phy(dp, port);
>> + if (ret)
>> + goto out;
>> +
>> + ret = cdn_dp_get_sink_capability(dp);
>> + if (ret) {
>> + cdn_dp_disable_phy(dp, port);
>> + goto out;
>> + }
>> +
>> + dp->active = true;
>> + dp->lanes = port->lanes;
>> +
>> + if (!cdn_dp_check_link_status(dp)) {
>> + dev_info(dp->dev, "Connected with sink; re-train link\n");
>> +
>> + ret = cdn_dp_train_link(dp);
>> + if (ret) {
>> + dev_err(dp->dev, "Training link failed: %d\n", ret);
>> + goto out;
>
> [Severity: High]
> If link training fails, this jumps to out and returns the error code, but
> leaves dp->active = true. Does this trap the port in a permanently broken,
> untrained state since subsequent calls to cdn_dp_switch_port() will
> immediately return 0?
>
The redundant assignment, as mentioned above, should be removed.
>> + }
>
> [ ... ]
>
>> @@ -639,9 +740,11 @@ static void cdn_dp_bridge_atomic_enable(struct drm_bridge *bridge, struct drm_at
>> static void cdn_dp_bridge_atomic_disable(struct drm_bridge *bridge, struct drm_atomic_state *state)
>> {
>> struct cdn_dp_device *dp = bridge_to_dp(bridge);
>> + struct cdn_dp_bridge *dp_bridge = bridge_to_dp_bridge(bridge);
>> int ret;
>>
>> mutex_lock(&dp->lock);
>> + dp_bridge->enabled = false;
>>
>> if (dp->active) {
>> ret = cdn_dp_disable(dp);
>
> [Severity: High]
> Does this accidentally disable the active DP controller when another inactive
> bridge is disabled? If dp->active is true, the entire DP controller is
> disabled, without checking if the bridge being disabled (dp_bridge) is
> actually the one driving the active DP port. This would break an active
> Bridge A if userspace disables an inactive Bridge B.
>
> [ ... ]
>
No.
>> @@ -967,28 +1085,16 @@ static int cdn_dp_pd_event(struct notifier_block *nb,
>> return NOTIFY_DONE;
>> }
>>
>> -static int cdn_dp_bind(struct device *dev, struct device *master, void *data)
>> +static int cdn_bridge_add(struct device *dev,
>> + struct drm_bridge *bridge,
>> + struct drm_bridge *next_bridge,
>> + struct drm_encoder *encoder)
>> {
>> struct cdn_dp_device *dp = dev_get_drvdata(dev);
>> - struct drm_encoder *encoder;
>> + struct drm_device *drm_dev = dp->drm_dev;
>> + struct drm_bridge *last_bridge __free(drm_bridge_put) = NULL;
>
> [Severity: High]
> Will this cause a reference count underflow and a use-after-free
> vulnerability? The last_bridge pointer is populated by
> drm_bridge_chain_get_last_bridge(), which returns a raw pointer without
> incrementing the bridge's reference count. When last_bridge goes out of
> scope, the automatic drm_bridge_put() will prematurely decrement the
> refcount.
>
No.
>> struct drm_connector *connector;
>> - struct cdn_dp_port *port;
>> - struct drm_device *drm_dev = data;
>> - int ret, i;
>> -
>
> [ ... ]
>
>> + if (next_bridge) {
>> + ret = drm_bridge_attach(encoder, next_bridge, bridge,
>> + DRM_BRIDGE_ATTACH_NO_CONNECTOR);
>> + if (ret)
>> + return ret;
>> +
>> + last_bridge = drm_bridge_chain_get_last_bridge(bridge->encoder);
>> + }
>> +
>> connector = drm_bridge_connector_init(drm_dev, encoder);
>> if (IS_ERR(connector)) {
>> ret = PTR_ERR(connector);
>> @@ -1030,8 +1145,99 @@ static int cdn_dp_bind(struct device *dev, struct device *master, void *data)
>> return ret;
>> }
>>
>> + if (last_bridge)
>> + connector->fwnode = fwnode_handle_get(of_fwnode_handle(last_bridge->of_node));
>
> [Severity: Medium]
> Is this assignment leaking an fwnode reference? drm_bridge_connector_init()
> automatically sets connector->fwnode using the of_node of the last bridge
> and acquires a reference via fwnode_handle_get(). Overwriting it here without
> dropping the original reference will cause a memory leak.
>
Yes, the old fwnode should be put.
>> +
>> drm_connector_attach_encoder(connector, encoder);
>>
>> + return 0;
>> +}
>> +
>> +static int cdn_dp_parse_next_bridge_dt(struct cdn_dp_device *dp)
>> +{
>> + struct device_node *np = dp->dev->of_node;
>> + struct device_node *port __free(device_node) = of_graph_get_port_by_id(np, 1);
>> + struct drm_bridge *bridge;
>> + int count = 0;
>> + int ret = 0;
>> + int i;
>> +
>> + /* If device use extcon, do not use hpd bridge */
>> + for (i = 0; i < dp->ports; i++) {
>> + if (dp->port[i]->extcon) {
>> + dp->bridge_count = 1;
>> + return 0;
>> + }
>> + }
>> +
>> + /* One endpoint may correspond to one next bridge. */
>> + for_each_of_graph_port_endpoint(port, dp_ep) {
>> + struct device_node *next_bridge_node __free(device_node) =
>> + of_graph_get_remote_port_parent(dp_ep);
>> +
>> + bridge = of_drm_find_bridge(next_bridge_node);
>> + if (!bridge) {
>> + ret = -EPROBE_DEFER;
>> + goto out;
>
> [Severity: High]
> Does this leak the DRM bridge references acquired in earlier loop iterations?
> If of_drm_find_bridge() returns NULL on a subsequent iteration, it jumps to
> out and returns -EPROBE_DEFER without releasing the references previously
> obtained with drm_bridge_get().
>
Yes, it should be put.
>> + }
>> +
>> + dp->next_bridge_valid = true;
>> + dp->next_bridge_list[count] = drm_bridge_get(bridge);
>> + count++;
>
> [Severity: High]
> Could this overflow the next_bridge_list array? next_bridge_list is sized to
> MAX_PHY (2). If a device tree specifies more than two endpoints, count will
> exceed the array bounds and corrupt adjacent fields in the cdn_dp_device
> struct.
>
No.
>> + }
>> +
>> +out:
>> + dp->bridge_count = count ? count : 1;
>> + return ret;
>> +}
>> +
>> +static int cdn_dp_bind(struct device *dev, struct device *master, void *data)
>> +{
>
> [ ... ]
>
>> + for (i = 0; i < dp->bridge_count; i++) {
>> + encoder = &dp->bridge_list[i]->encoder.encoder;
>> + bridge = &dp->bridge_list[i]->bridge;
>> + next_bridge = dp->next_bridge_list[i];
>> + ret = cdn_bridge_add(dev, bridge, next_bridge, encoder);
>> + if (ret)
>> + return ret;
>
> [Severity: High]
> Does this leak the bridge references acquired in cdn_dp_parse_next_bridge_dt
> if cdn_bridge_add() fails? Returning directly without a cleanup path means
> drm_bridge_put() is never called for dp->next_bridge_list.
>
>> + }
>
Yes, it should be put.
--
Best,
Chaoyi
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH v6 2/2] phy: qcom-mipi-csi2: Add a CSI2 MIPI DPHY driver
From: Bryan O'Donoghue @ 2026-05-21 15:58 UTC (permalink / raw)
To: sashiko-reviews
Cc: devicetree, vkoul, robh, olteanv, linux-phy, neil.armstrong,
conor+dt
In-Reply-To: <20260521124947.4BE4B1F000E9@smtp.kernel.org>
On 21/05/2026 13:49, sashiko-bot@kernel.org wrote:
> Thank you for your contribution! Sashiko AI review found 10 potential issue(s) to consider:
> - [High] Extensive resource leaks on error paths in power_on and set_clock_rates, and missing OPP rate reset in power_off.
> - [High] phy_qcom_mipi_csi2_configure overrides the DT-parsed lane count without bounds checking against the physical layout.
> - [High] Unconditional dereference of pd_list leads to a NULL pointer dereference panic.
> - [High] Division by zero occurs if the timer clock rate resolves to 0.
> - [High] Settle count calculation can underflow to a very large positive value.
> - [Medium] The ops->lanes_disable callback is omitted in phy_qcom_mipi_csi2_power_off.
> - [Medium] Clock lane positioning and lane polarities are parsed but entirely ignored.
> - [Medium] The probe function allows the absence of an OPP table, but power_on strictly requires it.
> - [Medium] qcom_csi2_phy_xlate accesses PHY arguments without checking args_count.
> - [Medium] Unvalidated data-lanes integer from DT can cause an out-of-bounds bitwise shift.
> --
>
> commit 3c373b3ab7783a677ec4c98f344d8b1c57e2e110
> Author: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
>
> phy: qcom-mipi-csi2: Add a CSI2 MIPI DPHY driver
>
> Add a new MIPI CSI2 driver in DPHY mode initially. The entire set of
> existing CAMSS CSI PHY init sequences are imported in order to save time
> and effort in later patches.
>
>> diff --git a/drivers/phy/qualcomm/phy-qcom-mipi-csi2-3ph-dphy.c b/drivers/phy/qualcomm/phy-qcom-mipi-csi2-3ph-dphy.c
>> index 0000000000000..8cdff35be2da9
>> --- /dev/null
>> +++ b/drivers/phy/qualcomm/phy-qcom-mipi-csi2-3ph-dphy.c
> [ ... ]
>> +static u8 phy_qcom_mipi_csi2_settle_cnt_calc(s64 link_freq, u32 timer_clk_rate)
>> +{
> [ ... ]
>> + timer_period_ps = div_u64(PSEC_PER_SEC, timer_clk_rate);
>> + settle_cnt = t_hs_settle_ps / timer_period_ps - 6;
>
> [Severity: High]
> Can this subtraction underflow to a very large positive value?
>
> If the system has a low timer clock rate resulting in a high
> timer_period_ps, the division could yield a value less than 6. Since
> settle_cnt is an unsigned 8-bit integer, wrapping around to a large
> value could severely misconfigure the PHY hardware timings.
I'm not sure it is really worthwhile writing defensive code for this case.
We audit every DT binding for clock frequency sanity so you have to
input junk into a device tree and upstream it and we aren't generally in
the habit of verifying those inputs.
>
>> +
>> + return settle_cnt;
>> +}
> [ ... ]
>> +static int phy_qcom_mipi_csi2_lanes_enable(struct mipi_csi2phy_device *csi2phy,
>> + struct mipi_csi2phy_stream_cfg *cfg)
>> +{
> [ ... ]
>> + settle_cnt = phy_qcom_mipi_csi2_settle_cnt_calc(cfg->link_freq, csi2phy->timer_clk_rate);
>> +
>> + val = CSIPHY_3PH_CMN_CSI_COMMON_CTRL5_CLK_ENABLE;
>
> [Severity: Medium]
> The commit message states that data-lane and clock lane positioning and
> polarity selection are supported. Are the polarity fields ignored here?
Exactly the same situation as we already have for this PHY in CAMSS
since forever.
We parse but don't program the various fields.
> It appears the clock lane enable bit is hardcoded and the polarity fields
> parsed from the DT are not programmed into the PHY registers.
>> + for (i = 0; i < cfg->num_data_lanes; i++)
>> + val |= BIT(lane_cfg->data[i].pos * 2);
Yeah this is longstanding behaviour but, its probably worthwhile to
update it since we consume the data from DT anyway.
> [Severity: Medium]
> Can this result in an out-of-bounds shift?
>
> The pos value is read from the device tree as an unvalidated 32-bit
> integer. A malformed DT with large lane positions (e.g. > 15) could
> result in a shift value >= 32, which is undefined behavior and might
> truncate the hardware configuration mask.
Still no - not going to spend time picking through what goes into DT in
the driver.
For example we don't sanity check register values or IRQ vector numbers.
>
>> +
>> + writel(val, csi2phy->base +
>> + CSIPHY_3PH_CMN_CSI_COMMON_CTRLn(regs->common_regs_offset, 5));
> [ ... ]
>> diff --git a/drivers/phy/qualcomm/phy-qcom-mipi-csi2-core.c b/drivers/phy/qualcomm/phy-qcom-mipi-csi2-core.c
>> index 0000000000000..d8bdb2dd3c2ac
>> --- /dev/null
>> +++ b/drivers/phy/qualcomm/phy-qcom-mipi-csi2-core.c
> [ ... ]
>> +static int
>> +phy_qcom_mipi_csi2_set_clock_rates(struct mipi_csi2phy_device *csi2phy,
>> + s64 link_freq)
>> +{
> [ ... ]
>> + opp = dev_pm_opp_find_freq_ceil(dev, &opp_rate);
>> + if (IS_ERR(opp)) {
>
> [Severity: Medium]
> Since the probe function tolerates -ENODEV for the OPP table, won't
> power_on unconditionally fail here if the table is actually missing?
>
>> + dev_err(csi2phy->dev, "Couldn't find ceiling for %lld Hz\n",
>> + link_freq);
>> + return PTR_ERR(opp);
>> + }
>> +
>> + for (int i = 0; i < csi2phy->pd_list->num_pds; i++) {
>
> [Severity: High]
> What happens to pd_list if CONFIG_PM is disabled?
>
> devm_pm_domain_attach_list() returns 0 when CONFIG_PM is disabled, but
> pd_list will remain NULL. This would cause a NULL pointer dereference
> here and in phy_qcom_mipi_csi2_power_off().
No idea, lets find out.
>> + unsigned int perf = dev_pm_opp_get_required_pstate(opp, i);
>> +
>> + ret = dev_pm_genpd_set_performance_state(csi2phy->pd_list->pd_devs[i], perf);
>> + if (ret) {
>> + dev_err(csi2phy->dev, "Couldn't set perf state %u\n",
>> + perf);
>> + dev_pm_opp_put(opp);
>> + return ret;
>
> [Severity: High]
> Does this leak the performance state for previously set domains?
>
> If the loop fails on a later iteration, it appears to return without resetting
> the domains that were already successfully configured.
True we need to unwind.
>> + }
>> + }
>> + dev_pm_opp_put(opp);
>> +
>> + ret = dev_pm_opp_set_rate(dev, opp_rate);
>> + if (ret) {
>> + dev_err(csi2phy->dev, "dev_pm_opp_set_rate() fail\n");
>> + return ret;
>> + }
>> +
>> + timer_rate = clk_round_rate(csi2phy->timer_clk, link_freq / 4);
>> + if (timer_rate < 0)
>> + return timer_rate;
>> +
>> + ret = clk_set_rate(csi2phy->timer_clk, timer_rate);
>> + if (ret)
>> + return ret;
>> +
>> + csi2phy->timer_clk_rate = timer_rate;
>
> [Severity: High]
> What if clk_round_rate() returns 0?
>
> If the clock is disabled or misconfigured, timer_rate could be 0. Later,
> phy_qcom_mipi_csi2_settle_cnt_calc() calls
> div_u64(PSEC_PER_SEC, timer_clk_rate), which would result in a division
> by zero and a kernel panic.
An esoteric ask since you again have to have bugs in your DT but, for
the sake of not being spammed by a static analysis tool, sure lets check
for zero.
>> +
>> + return 0;
>> +}
>> +
>> +static int phy_qcom_mipi_csi2_configure(struct phy *phy,
>> + union phy_configure_opts *opts)
>> +{
> [ ... ]
>> + stream_cfg->link_freq = dphy_cfg->hs_clk_rate;
>> + stream_cfg->num_data_lanes = dphy_cfg->lanes;
>
> [Severity: High]
> Does this blindly overwrite the DT-parsed lane count without bounds
> checking against the physical layout?
It takes the lanes_count from the controller DT field.
> If a consumer requests more lanes than are physically mapped in the
> device tree, the hardware configuration could iterate out-of-bounds of
> the initialized array elements, repeatedly applying bitmasks for physical
> position 0.
No the value comes from the controller DT data-lanes field but since we
are consuming data-lanes from the PHY its actually a worthwhile test to
validate what the controller says to what we have an -EINVAL if they
don't agree.
>
>> +
>> + return 0;
>> +}
>> +
>> +static int phy_qcom_mipi_csi2_power_on(struct phy *phy)
>> +{
> [ ... ]
>> + ret = clk_bulk_prepare_enable(csi2phy->soc_cfg->num_clk,
>> + csi2phy->clks);
>> + if (ret) {
>> + dev_err(dev, "failed to enable clocks, %d\n", ret);
>> + goto poweroff_phy;
>> + }
>> +
> [ ... ]
>> +poweroff_phy:
>> + regulator_bulk_disable(csi2phy->soc_cfg->num_supplies,
>> + csi2phy->supplies);
>> +
>> + return ret;
>
> [Severity: High]
> Does this error path leak the performance state and OPP rate?
>
> It seems to only disable regulators, completely missing the cleanup for
> dev_pm_genpd_set_performance_state() and dev_pm_opp_set_rate().
>
When the clocks disable the perf state _should_ drop back but, I will check.
>> +}
>> +
>> +static int phy_qcom_mipi_csi2_power_off(struct phy *phy)
>> +{
>> + struct mipi_csi2phy_device *csi2phy = phy_get_drvdata(phy);
>> + int i;
>> +
>> + for (i = 0; i < csi2phy->pd_list->num_pds; i++)
>> + dev_pm_genpd_set_performance_state(csi2phy->pd_list->pd_devs[i], 0);
>
> [Severity: High]
> Does this leave the OPP frequency vote elevated?
>
> It doesn't look like dev_pm_opp_set_rate(dev, 0) is called to release
> the OPP frequency vote.
>
> [Severity: Medium]
> Is the ops->lanes_disable() callback intentionally omitted here?
>
> Disabling the clocks and regulators without invoking the callback
> bypasses the hardware-specific teardown sequence (like clearing
> CLK_ENABLE and COMMON_PWRDN_B). Could this leave the PHY in an invalid
> logical state for the next power-on cycle?
I mean, when power goes off you loose the state in the regs ... but for
the sake of completeness sure, I will add this.
>> +
>> + clk_bulk_disable_unprepare(csi2phy->soc_cfg->num_clk,
>> + csi2phy->clks);
>> + regulator_bulk_disable(csi2phy->soc_cfg->num_supplies,
>> + csi2phy->supplies);
>> +
>> + return 0;
>> +}
> [ ... ]
>> +static struct phy *qcom_csi2_phy_xlate(struct device *dev,
>> + const struct of_phandle_args *args)
>> +{
>> + struct mipi_csi2phy_device *csi2phy = dev_get_drvdata(dev);
>> +
>> + if (args->args[0] != PHY_TYPE_DPHY) {
>
> [Severity: Medium]
> Can this access uninitialized stack memory?
>
> If the device tree node has #phy-cells = <0>, args_count will be 0, and
> reading args->args[0] might yield uninitialized memory, leading to
> unpredictable behavior or the incorrect rejection of valid PHY bindings.
> Should args->args_count be checked first?
I feel the answer is "no" but I'm not averse to checking.
>
>> + dev_err(csi2phy->dev, "mode %d -EOPNOTSUPP\n", args->args[0]);
>> + return ERR_PTR(-EOPNOTSUPP);
>> + }
>
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* [PATCH v9 5/5] phy: airoha: Add support for Airoha AN7581 USB PHY
From: Christian Marangi @ 2026-05-21 15:35 UTC (permalink / raw)
To: Michael Turquette, Stephen Boyd, Brian Masney, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Christian Marangi, Vinod Koul,
Neil Armstrong, Lorenzo Bianconi, Felix Fietkau, linux-clk,
devicetree, linux-kernel, linux-arm-kernel, linux-phy
In-Reply-To: <20260521153645.7028-1-ansuelsmth@gmail.com>
Add support for Airoha AN7581 USB PHY driver. AN7581 supports up to 2
USB port with USB 2.0 mode always supported and USB 3.0 mode available
only if the Serdes port is correctly configured for USB 3.0.
If the USB 3.0 mode is not configured, the modes needs to be also
disabled in the xHCI node or the driver will report unsable clock and
fail probe.
For USB 2.0 Slew Rate calibration, airoha,usb2-monitor-clk-sel is
mandatory and is used to select the monitor clock for calibration.
Normally it's 1 for USB port 1 and 2 for USB port 2.
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
---
MAINTAINERS | 1 +
drivers/phy/airoha/Kconfig | 11 +
drivers/phy/airoha/Makefile | 1 +
drivers/phy/airoha/phy-an7581-usb.c | 559 ++++++++++++++++++++++++++++
4 files changed, 572 insertions(+)
create mode 100644 drivers/phy/airoha/phy-an7581-usb.c
diff --git a/MAINTAINERS b/MAINTAINERS
index 7bea8c620da8..2f05faa44503 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -776,6 +776,7 @@ M: Christian Marangi <ansuelsmth@gmail.com>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
F: Documentation/devicetree/bindings/phy/airoha,an7581-usb-phy.yaml
+F: drivers/phy/airoha/phy-an7581-usb.c
AIRSPY MEDIA DRIVER
L: linux-media@vger.kernel.org
diff --git a/drivers/phy/airoha/Kconfig b/drivers/phy/airoha/Kconfig
index 9a1b625a7701..634448ee39b5 100644
--- a/drivers/phy/airoha/Kconfig
+++ b/drivers/phy/airoha/Kconfig
@@ -11,3 +11,14 @@ config PHY_AIROHA_AN7581_PCIE
Say Y here to add support for Airoha AN7581 PCIe PHY driver.
This driver create the basic PHY instance and provides initialize
callback for PCIe GEN3 port.
+
+config PHY_AIROHA_AN7581_USB
+ tristate "Airoha AN7581 USB PHY Driver"
+ depends on ARCH_AIROHA || COMPILE_TEST
+ depends on OF
+ select GENERIC_PHY
+ select REGMAP_MMIO
+ help
+ Say 'Y' here to add support for Airoha AN7581 USB PHY driver.
+ This driver create the basic PHY instance and provides initialize
+ callback for USB port.
diff --git a/drivers/phy/airoha/Makefile b/drivers/phy/airoha/Makefile
index 912f3e11a061..944bf842deba 100644
--- a/drivers/phy/airoha/Makefile
+++ b/drivers/phy/airoha/Makefile
@@ -1,3 +1,4 @@
# SPDX-License-Identifier: GPL-2.0
obj-$(CONFIG_PHY_AIROHA_AN7581_PCIE) += phy-an7581-pcie.o
+obj-$(CONFIG_PHY_AIROHA_AN7581_USB) += phy-an7581-usb.o
diff --git a/drivers/phy/airoha/phy-an7581-usb.c b/drivers/phy/airoha/phy-an7581-usb.c
new file mode 100644
index 000000000000..92c5e5c2fbf3
--- /dev/null
+++ b/drivers/phy/airoha/phy-an7581-usb.c
@@ -0,0 +1,559 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Author: Christian Marangi <ansuelsmth@gmail.com>
+ */
+
+#include <dt-bindings/phy/phy.h>
+#include <dt-bindings/soc/airoha,scu-ssr.h>
+#include <linux/bitfield.h>
+#include <linux/math.h>
+#include <linux/module.h>
+#include <linux/mfd/syscon.h>
+#include <linux/phy/phy.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+
+/* U2PHY */
+#define AIROHA_USB_PHY_FMCR0 0x100
+#define AIROHA_USB_PHY_MONCLK_SEL GENMASK(27, 26)
+#define AIROHA_USB_PHY_MONCLK_SEL0 FIELD_PREP_CONST(AIROHA_USB_PHY_MONCLK_SEL, 0x0)
+#define AIROHA_USB_PHY_MONCLK_SEL1 FIELD_PREP_CONST(AIROHA_USB_PHY_MONCLK_SEL, 0x1)
+#define AIROHA_USB_PHY_MONCLK_SEL2 FIELD_PREP_CONST(AIROHA_USB_PHY_MONCLK_SEL, 0x2)
+#define AIROHA_USB_PHY_MONCLK_SEL3 FIELD_PREP_CONST(AIROHA_USB_PHY_MONCLK_SEL, 0x3)
+#define AIROHA_USB_PHY_FREQDET_EN BIT(24)
+#define AIROHA_USB_PHY_CYCLECNT GENMASK(23, 0)
+#define AIROHA_USB_PHY_FMMONR0 0x10c
+#define AIROHA_USB_PHY_USB_FM_OUT GENMASK(31, 0)
+#define AIROHA_USB_PHY_FMMONR1 0x110
+#define AIROHA_USB_PHY_FRCK_EN BIT(8)
+
+#define AIROHA_USB_PHY_USBPHYACR4 0x310
+#define AIROHA_USB_PHY_USB20_FS_CR GENMASK(10, 8)
+#define AIROHA_USB_PHY_USB20_FS_CR_MAX FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_FS_CR, 0x0)
+#define AIROHA_USB_PHY_USB20_FS_CR_NORMAL FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_FS_CR, 0x2)
+#define AIROHA_USB_PHY_USB20_FS_CR_SMALLER FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_FS_CR, 0x4)
+#define AIROHA_USB_PHY_USB20_FS_CR_MIN FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_FS_CR, 0x6)
+#define AIROHA_USB_PHY_USB20_FS_SR GENMASK(2, 0)
+#define AIROHA_USB_PHY_USB20_FS_SR_MAX FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_FS_SR, 0x0)
+#define AIROHA_USB_PHY_USB20_FS_SR_NORMAL FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_FS_SR, 0x2)
+#define AIROHA_USB_PHY_USB20_FS_SR_SMALLER FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_FS_SR, 0x4)
+#define AIROHA_USB_PHY_USB20_FS_SR_MIN FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_FS_SR, 0x6)
+#define AIROHA_USB_PHY_USBPHYACR5 0x314
+#define AIROHA_USB_PHY_USB20_HSTX_SRCAL_EN BIT(15)
+#define AIROHA_USB_PHY_USB20_HSTX_SRCTRL GENMASK(14, 12)
+#define AIROHA_USB_PHY_USBPHYACR6 0x318
+#define AIROHA_USB_PHY_USB20_BC11_SW_EN BIT(23)
+#define AIROHA_USB_PHY_USB20_DISCTH GENMASK(7, 4)
+#define AIROHA_USB_PHY_USB20_DISCTH_400 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_DISCTH, 0x0)
+#define AIROHA_USB_PHY_USB20_DISCTH_420 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_DISCTH, 0x1)
+#define AIROHA_USB_PHY_USB20_DISCTH_440 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_DISCTH, 0x2)
+#define AIROHA_USB_PHY_USB20_DISCTH_460 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_DISCTH, 0x3)
+#define AIROHA_USB_PHY_USB20_DISCTH_480 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_DISCTH, 0x4)
+#define AIROHA_USB_PHY_USB20_DISCTH_500 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_DISCTH, 0x5)
+#define AIROHA_USB_PHY_USB20_DISCTH_520 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_DISCTH, 0x6)
+#define AIROHA_USB_PHY_USB20_DISCTH_540 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_DISCTH, 0x7)
+#define AIROHA_USB_PHY_USB20_DISCTH_560 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_DISCTH, 0x8)
+#define AIROHA_USB_PHY_USB20_DISCTH_580 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_DISCTH, 0x9)
+#define AIROHA_USB_PHY_USB20_DISCTH_600 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_DISCTH, 0xa)
+#define AIROHA_USB_PHY_USB20_DISCTH_620 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_DISCTH, 0xb)
+#define AIROHA_USB_PHY_USB20_DISCTH_640 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_DISCTH, 0xc)
+#define AIROHA_USB_PHY_USB20_DISCTH_660 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_DISCTH, 0xd)
+#define AIROHA_USB_PHY_USB20_DISCTH_680 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_DISCTH, 0xe)
+#define AIROHA_USB_PHY_USB20_DISCTH_700 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_DISCTH, 0xf)
+#define AIROHA_USB_PHY_USB20_SQTH GENMASK(3, 0)
+#define AIROHA_USB_PHY_USB20_SQTH_85 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_SQTH, 0x0)
+#define AIROHA_USB_PHY_USB20_SQTH_90 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_SQTH, 0x1)
+#define AIROHA_USB_PHY_USB20_SQTH_95 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_SQTH, 0x2)
+#define AIROHA_USB_PHY_USB20_SQTH_100 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_SQTH, 0x3)
+#define AIROHA_USB_PHY_USB20_SQTH_105 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_SQTH, 0x4)
+#define AIROHA_USB_PHY_USB20_SQTH_110 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_SQTH, 0x5)
+#define AIROHA_USB_PHY_USB20_SQTH_115 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_SQTH, 0x6)
+#define AIROHA_USB_PHY_USB20_SQTH_120 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_SQTH, 0x7)
+#define AIROHA_USB_PHY_USB20_SQTH_125 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_SQTH, 0x8)
+#define AIROHA_USB_PHY_USB20_SQTH_130 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_SQTH, 0x9)
+#define AIROHA_USB_PHY_USB20_SQTH_135 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_SQTH, 0xa)
+#define AIROHA_USB_PHY_USB20_SQTH_140 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_SQTH, 0xb)
+#define AIROHA_USB_PHY_USB20_SQTH_145 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_SQTH, 0xc)
+#define AIROHA_USB_PHY_USB20_SQTH_150 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_SQTH, 0xd)
+#define AIROHA_USB_PHY_USB20_SQTH_155 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_SQTH, 0xe)
+#define AIROHA_USB_PHY_USB20_SQTH_160 FIELD_PREP_CONST(AIROHA_USB_PHY_USB20_SQTH, 0xf)
+
+#define AIROHA_USB_PHY_U2PHYDTM1 0x36c
+#define AIROHA_USB_PHY_FORCE_IDDIG BIT(9)
+#define AIROHA_USB_PHY_IDDIG BIT(1)
+
+#define AIROHA_USB_PHY_GPIO_CTLD 0x80c
+#define AIROHA_USB_PHY_C60802_GPIO_CTLD GENMASK(31, 0)
+#define AIROHA_USB_PHY_SSUSB_IP_SW_RST BIT(31)
+#define AIROHA_USB_PHY_MCU_BUS_CK_GATE_EN BIT(30)
+#define AIROHA_USB_PHY_FORCE_SSUSB_IP_SW_RST BIT(29)
+#define AIROHA_USB_PHY_SSUSB_SW_RST BIT(28)
+
+#define AIROHA_USB_PHY_U3_PHYA_REG0 0xb00
+#define AIROHA_USB_PHY_SSUSB_BG_DIV GENMASK(29, 28)
+#define AIROHA_USB_PHY_SSUSB_BG_DIV_2 FIELD_PREP_CONST(AIROHA_USB_PHY_SSUSB_BG_DIV, 0x0)
+#define AIROHA_USB_PHY_SSUSB_BG_DIV_4 FIELD_PREP_CONST(AIROHA_USB_PHY_SSUSB_BG_DIV, 0x1)
+#define AIROHA_USB_PHY_SSUSB_BG_DIV_8 FIELD_PREP_CONST(AIROHA_USB_PHY_SSUSB_BG_DIV, 0x2)
+#define AIROHA_USB_PHY_SSUSB_BG_DIV_16 FIELD_PREP_CONST(AIROHA_USB_PHY_SSUSB_BG_DIV, 0x3)
+#define AIROHA_USB_PHY_U3_PHYA_REG1 0xb04
+#define AIROHA_USB_PHY_SSUSB_XTAL_TOP_RESERVE GENMASK(25, 10)
+#define AIROHA_USB_PHY_U3_PHYA_REG6 0xb18
+#define AIROHA_USB_PHY_SSUSB_CDR_RESERVE GENMASK(31, 24)
+#define AIROHA_USB_PHY_U3_PHYA_REG8 0xb20
+#define AIROHA_USB_PHY_SSUSB_CDR_RST_DLY GENMASK(7, 6)
+#define AIROHA_USB_PHY_SSUSB_CDR_RST_DLY_32 FIELD_PREP_CONST(AIROHA_USB_PHY_SSUSB_CDR_RST_DLY, 0x0)
+#define AIROHA_USB_PHY_SSUSB_CDR_RST_DLY_64 FIELD_PREP_CONST(AIROHA_USB_PHY_SSUSB_CDR_RST_DLY, 0x1)
+#define AIROHA_USB_PHY_SSUSB_CDR_RST_DLY_128 FIELD_PREP_CONST(AIROHA_USB_PHY_SSUSB_CDR_RST_DLY, 0x2)
+#define AIROHA_USB_PHY_SSUSB_CDR_RST_DLY_216 FIELD_PREP_CONST(AIROHA_USB_PHY_SSUSB_CDR_RST_DLY, 0x3)
+
+#define AIROHA_USB_PHY_U3_PHYA_DA_REG19 0xc38
+#define AIROHA_USB_PHY_SSUSB_PLL_SSC_DELTA1_U3 GENMASK(15, 0)
+
+#define AIROHA_USB_PHY_U2_FM_DET_CYCLE_CNT 1024
+#define AIROHA_USB_PHY_REF_CK 20
+#define AIROHA_USB_PHY_U2_SR_COEF 28
+#define AIROHA_USB_PHY_U2_SR_COEF_DIVISOR 1000
+
+#define AIROHA_USB_PHY_DEFAULT_SR_CALIBRATION 0x5
+#define AIROHA_USB_PHY_FREQDET_SLEEP 1000 /* 1ms */
+#define AIROHA_USB_PHY_FREQDET_TIMEOUT (AIROHA_USB_PHY_FREQDET_SLEEP * 10)
+
+struct an7581_usb_phy_instance {
+ struct phy *phy;
+ u32 type;
+};
+
+enum an7581_usb_phy_instance_type {
+ AIROHA_PHY_USB2,
+ AIROHA_PHY_USB3,
+
+ AIROHA_PHY_USB_MAX,
+};
+
+struct an7581_usb_phy_priv {
+ struct device *dev;
+ struct regmap *regmap;
+
+ unsigned int monclk_sel;
+
+ struct phy *serdes_phy;
+ struct an7581_usb_phy_instance *phys[AIROHA_PHY_USB_MAX];
+};
+
+static void an7581_usb_phy_u2_slew_rate_calibration(struct an7581_usb_phy_priv *priv)
+{
+ u32 fm_out = 0;
+ u32 srctrl;
+
+ /* Enable HS TX SR calibration */
+ regmap_set_bits(priv->regmap, AIROHA_USB_PHY_USBPHYACR5,
+ AIROHA_USB_PHY_USB20_HSTX_SRCAL_EN);
+
+ usleep_range(1000, 1500);
+
+ /* Enable Free run clock */
+ regmap_set_bits(priv->regmap, AIROHA_USB_PHY_FMMONR1,
+ AIROHA_USB_PHY_FRCK_EN);
+
+ /* Select Monitor Clock */
+ regmap_update_bits(priv->regmap, AIROHA_USB_PHY_FMCR0,
+ AIROHA_USB_PHY_MONCLK_SEL,
+ FIELD_PREP(AIROHA_USB_PHY_MONCLK_SEL,
+ priv->monclk_sel));
+
+ /* Set cyclecnt */
+ regmap_update_bits(priv->regmap, AIROHA_USB_PHY_FMCR0,
+ AIROHA_USB_PHY_CYCLECNT,
+ FIELD_PREP(AIROHA_USB_PHY_CYCLECNT,
+ AIROHA_USB_PHY_U2_FM_DET_CYCLE_CNT));
+
+ /* Enable Frequency meter */
+ regmap_set_bits(priv->regmap, AIROHA_USB_PHY_FMCR0,
+ AIROHA_USB_PHY_FREQDET_EN);
+
+ /* Timeout can happen and we will apply workaround at the end */
+ regmap_read_poll_timeout(priv->regmap, AIROHA_USB_PHY_FMMONR0, fm_out,
+ fm_out, AIROHA_USB_PHY_FREQDET_SLEEP,
+ AIROHA_USB_PHY_FREQDET_TIMEOUT);
+
+ /* Disable Frequency meter */
+ regmap_clear_bits(priv->regmap, AIROHA_USB_PHY_FMCR0,
+ AIROHA_USB_PHY_FREQDET_EN);
+
+ /* Disable Free run clock */
+ regmap_clear_bits(priv->regmap, AIROHA_USB_PHY_FMMONR1,
+ AIROHA_USB_PHY_FRCK_EN);
+
+ /* Disable HS TX SR calibration */
+ regmap_clear_bits(priv->regmap, AIROHA_USB_PHY_USBPHYACR5,
+ AIROHA_USB_PHY_USB20_HSTX_SRCAL_EN);
+
+ usleep_range(1000, 1500);
+
+ /* Frequency was not detected, use default SR calibration value */
+ if (!fm_out) {
+ srctrl = AIROHA_USB_PHY_DEFAULT_SR_CALIBRATION;
+ dev_err(priv->dev, "Frequency not detected, using default SR calibration.\n");
+ } else {
+ /* (1024 / FM_OUT) * REF_CK * U2_SR_COEF (round to the nearest digits) */
+ srctrl = AIROHA_USB_PHY_REF_CK * AIROHA_USB_PHY_U2_SR_COEF;
+ srctrl = (srctrl * AIROHA_USB_PHY_U2_FM_DET_CYCLE_CNT) / fm_out;
+ srctrl = DIV_ROUND_CLOSEST(srctrl, AIROHA_USB_PHY_U2_SR_COEF_DIVISOR);
+ dev_dbg(priv->dev, "SR calibration applied: %x\n", srctrl);
+ }
+
+ regmap_update_bits(priv->regmap, AIROHA_USB_PHY_USBPHYACR5,
+ AIROHA_USB_PHY_USB20_HSTX_SRCTRL,
+ FIELD_PREP(AIROHA_USB_PHY_USB20_HSTX_SRCTRL, srctrl));
+}
+
+static void an7581_usb_phy_u2_init(struct an7581_usb_phy_priv *priv)
+{
+ regmap_update_bits(priv->regmap, AIROHA_USB_PHY_USBPHYACR4,
+ AIROHA_USB_PHY_USB20_FS_CR,
+ AIROHA_USB_PHY_USB20_FS_CR_MIN);
+
+ regmap_update_bits(priv->regmap, AIROHA_USB_PHY_USBPHYACR4,
+ AIROHA_USB_PHY_USB20_FS_SR,
+ AIROHA_USB_PHY_USB20_FS_SR_NORMAL);
+
+ /* FIXME: evaluate if needed */
+ regmap_update_bits(priv->regmap, AIROHA_USB_PHY_USBPHYACR6,
+ AIROHA_USB_PHY_USB20_SQTH,
+ AIROHA_USB_PHY_USB20_SQTH_130);
+
+ regmap_update_bits(priv->regmap, AIROHA_USB_PHY_USBPHYACR6,
+ AIROHA_USB_PHY_USB20_DISCTH,
+ AIROHA_USB_PHY_USB20_DISCTH_600);
+
+ /* Enable the USB port and then disable after calibration */
+ regmap_clear_bits(priv->regmap, AIROHA_USB_PHY_USBPHYACR6,
+ AIROHA_USB_PHY_USB20_BC11_SW_EN);
+
+ an7581_usb_phy_u2_slew_rate_calibration(priv);
+
+ regmap_set_bits(priv->regmap, AIROHA_USB_PHY_USBPHYACR6,
+ AIROHA_USB_PHY_USB20_BC11_SW_EN);
+
+ usleep_range(1000, 1500);
+}
+
+/*
+ * USB 3.0 mode can only work if USB serdes is correctly set.
+ * This is validated in xLate function.
+ */
+static void an7581_usb_phy_u3_init(struct an7581_usb_phy_priv *priv)
+{
+ regmap_update_bits(priv->regmap, AIROHA_USB_PHY_U3_PHYA_REG8,
+ AIROHA_USB_PHY_SSUSB_CDR_RST_DLY,
+ AIROHA_USB_PHY_SSUSB_CDR_RST_DLY_32);
+
+ regmap_update_bits(priv->regmap, AIROHA_USB_PHY_U3_PHYA_REG6,
+ AIROHA_USB_PHY_SSUSB_CDR_RESERVE,
+ FIELD_PREP(AIROHA_USB_PHY_SSUSB_CDR_RESERVE, 0xe));
+
+ regmap_update_bits(priv->regmap, AIROHA_USB_PHY_U3_PHYA_REG0,
+ AIROHA_USB_PHY_SSUSB_BG_DIV,
+ AIROHA_USB_PHY_SSUSB_BG_DIV_4);
+
+ regmap_set_bits(priv->regmap, AIROHA_USB_PHY_U3_PHYA_REG1,
+ FIELD_PREP(AIROHA_USB_PHY_SSUSB_XTAL_TOP_RESERVE, 0x600));
+
+ regmap_update_bits(priv->regmap, AIROHA_USB_PHY_U3_PHYA_DA_REG19,
+ AIROHA_USB_PHY_SSUSB_PLL_SSC_DELTA1_U3,
+ FIELD_PREP(AIROHA_USB_PHY_SSUSB_PLL_SSC_DELTA1_U3, 0x43));
+}
+
+static int an7581_usb_phy_init(struct phy *phy)
+{
+ struct an7581_usb_phy_instance *instance = phy_get_drvdata(phy);
+ struct an7581_usb_phy_priv *priv = dev_get_drvdata(phy->dev.parent);
+ int ret;
+
+ switch (instance->type) {
+ case PHY_TYPE_USB2:
+ an7581_usb_phy_u2_init(priv);
+ break;
+ case PHY_TYPE_USB3:
+ ret = phy_set_mode(priv->serdes_phy, PHY_MODE_USB_DEVICE_SS);
+ if (ret)
+ return ret;
+
+ an7581_usb_phy_u3_init(priv);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int an7581_usb_phy_u2_power_on(struct an7581_usb_phy_priv *priv)
+{
+ regmap_clear_bits(priv->regmap, AIROHA_USB_PHY_USBPHYACR6,
+ AIROHA_USB_PHY_USB20_BC11_SW_EN);
+
+ usleep_range(1000, 1500);
+
+ return 0;
+}
+
+static int an7581_usb_phy_u3_power_on(struct an7581_usb_phy_priv *priv)
+{
+ regmap_clear_bits(priv->regmap, AIROHA_USB_PHY_GPIO_CTLD,
+ AIROHA_USB_PHY_SSUSB_IP_SW_RST |
+ AIROHA_USB_PHY_MCU_BUS_CK_GATE_EN |
+ AIROHA_USB_PHY_FORCE_SSUSB_IP_SW_RST |
+ AIROHA_USB_PHY_SSUSB_SW_RST);
+
+ usleep_range(1000, 1500);
+
+ return 0;
+}
+
+static int an7581_usb_phy_power_on(struct phy *phy)
+{
+ struct an7581_usb_phy_instance *instance = phy_get_drvdata(phy);
+ struct an7581_usb_phy_priv *priv = dev_get_drvdata(phy->dev.parent);
+
+ switch (instance->type) {
+ case PHY_TYPE_USB2:
+ an7581_usb_phy_u2_power_on(priv);
+ break;
+ case PHY_TYPE_USB3:
+ an7581_usb_phy_u3_power_on(priv);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int an7581_usb_phy_u2_power_off(struct an7581_usb_phy_priv *priv)
+{
+ regmap_set_bits(priv->regmap, AIROHA_USB_PHY_USBPHYACR6,
+ AIROHA_USB_PHY_USB20_BC11_SW_EN);
+
+ usleep_range(1000, 1500);
+
+ return 0;
+}
+
+static int an7581_usb_phy_u3_power_off(struct an7581_usb_phy_priv *priv)
+{
+ regmap_set_bits(priv->regmap, AIROHA_USB_PHY_GPIO_CTLD,
+ AIROHA_USB_PHY_SSUSB_IP_SW_RST |
+ AIROHA_USB_PHY_FORCE_SSUSB_IP_SW_RST);
+
+ usleep_range(1000, 1500);
+
+ return 0;
+}
+
+static int an7581_usb_phy_power_off(struct phy *phy)
+{
+ struct an7581_usb_phy_instance *instance = phy_get_drvdata(phy);
+ struct an7581_usb_phy_priv *priv = dev_get_drvdata(phy->dev.parent);
+
+ switch (instance->type) {
+ case PHY_TYPE_USB2:
+ an7581_usb_phy_u2_power_off(priv);
+ break;
+ case PHY_TYPE_USB3:
+ an7581_usb_phy_u3_power_off(priv);
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int an7581_usb_phy_u2_set_mode(struct an7581_usb_phy_priv *priv,
+ enum phy_mode mode)
+{
+ u32 val;
+
+ /*
+ * For Device and Host mode, enable force IDDIG.
+ * For Device set IDDIG, for Host clear IDDIG.
+ * For OTG disable force and clear IDDIG bit while at it.
+ */
+ switch (mode) {
+ case PHY_MODE_USB_DEVICE:
+ val = AIROHA_USB_PHY_FORCE_IDDIG |
+ AIROHA_USB_PHY_IDDIG;
+ break;
+ case PHY_MODE_USB_HOST:
+ val = AIROHA_USB_PHY_FORCE_IDDIG;
+ break;
+ case PHY_MODE_USB_OTG:
+ val = 0;
+ break;
+ default:
+ return 0;
+ }
+
+ regmap_update_bits(priv->regmap, AIROHA_USB_PHY_U2PHYDTM1,
+ AIROHA_USB_PHY_FORCE_IDDIG |
+ AIROHA_USB_PHY_IDDIG, val);
+
+ return 0;
+}
+
+static int an7581_usb_phy_set_mode(struct phy *phy, enum phy_mode mode, int submode)
+{
+ struct an7581_usb_phy_instance *instance = phy_get_drvdata(phy);
+ struct an7581_usb_phy_priv *priv = dev_get_drvdata(phy->dev.parent);
+
+ switch (instance->type) {
+ case PHY_TYPE_USB2:
+ return an7581_usb_phy_u2_set_mode(priv, mode);
+ default:
+ return 0;
+ }
+}
+
+static struct phy *an7581_usb_phy_xlate(struct device *dev,
+ const struct of_phandle_args *args)
+{
+ struct an7581_usb_phy_priv *priv = dev_get_drvdata(dev);
+ struct an7581_usb_phy_instance *instance = NULL;
+ unsigned int index, phy_type;
+
+ if (args->args_count != 1) {
+ dev_err(dev, "invalid number of cells in 'phy' property\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ phy_type = args->args[0];
+ if (!(phy_type == PHY_TYPE_USB2 || phy_type == PHY_TYPE_USB3)) {
+ dev_err(dev, "unsupported device type: %d\n", phy_type);
+ return ERR_PTR(-EINVAL);
+ }
+
+ for (index = 0; index < AIROHA_PHY_USB_MAX; index++)
+ if (priv->phys[index] &&
+ phy_type == priv->phys[index]->type) {
+ instance = priv->phys[index];
+ break;
+ }
+
+ if (!instance) {
+ dev_err(dev, "failed to find appropriate phy\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ if (instance->type == PHY_TYPE_USB3 && !priv->serdes_phy) {
+ dev_err(dev, "missing serdes phy for USB 3.0\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ return instance->phy;
+}
+
+static const struct phy_ops airoha_phy = {
+ .init = an7581_usb_phy_init,
+ .power_on = an7581_usb_phy_power_on,
+ .power_off = an7581_usb_phy_power_off,
+ .set_mode = an7581_usb_phy_set_mode,
+ .owner = THIS_MODULE,
+};
+
+static const struct regmap_config an7581_usb_phy_regmap_config = {
+ .reg_bits = 32,
+ .val_bits = 32,
+ .reg_stride = 4,
+};
+
+static int an7581_usb_phy_probe(struct platform_device *pdev)
+{
+ struct phy_provider *phy_provider;
+ struct an7581_usb_phy_priv *priv;
+ struct device *dev = &pdev->dev;
+ unsigned int index;
+ void __iomem *base;
+ int ret;
+
+ priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+
+ priv->dev = dev;
+
+ ret = of_property_read_u32(dev->of_node, "airoha,usb2-monitor-clk-sel",
+ &priv->monclk_sel);
+ if (ret)
+ return dev_err_probe(dev, ret, "Monitor clock selection is mandatory for USB PHY calibration\n");
+
+ if (priv->monclk_sel > 3)
+ return dev_err_probe(dev, -EINVAL, "only 4 Monitor clock are selectable on the SoC\n");
+
+ base = devm_platform_ioremap_resource(pdev, 0);
+ if (IS_ERR(base))
+ return PTR_ERR(base);
+
+ priv->regmap = devm_regmap_init_mmio(dev, base, &an7581_usb_phy_regmap_config);
+ if (IS_ERR(priv->regmap))
+ return PTR_ERR(priv->regmap);
+
+ platform_set_drvdata(pdev, priv);
+
+ for (index = 0; index < AIROHA_PHY_USB_MAX; index++) {
+ struct an7581_usb_phy_instance *instance;
+ u32 phy_type;
+
+ switch (index) {
+ case AIROHA_PHY_USB2:
+ phy_type = PHY_TYPE_USB2;
+ break;
+ case AIROHA_PHY_USB3:
+ phy_type = PHY_TYPE_USB3;
+ break;
+ }
+
+ if (phy_type == PHY_TYPE_USB3) {
+ priv->serdes_phy = devm_phy_optional_get(dev, NULL);
+ if (IS_ERR(priv->serdes_phy))
+ return dev_err_probe(dev, PTR_ERR(priv->serdes_phy), "error on serdes phy for USB 3.0\n");
+ }
+
+ instance = devm_kzalloc(dev, sizeof(*instance), GFP_KERNEL);
+ if (!instance)
+ return -ENOMEM;
+
+ instance->type = phy_type;
+ priv->phys[index] = instance;
+
+ instance->phy = devm_phy_create(dev, NULL, &airoha_phy);
+ if (IS_ERR(instance->phy))
+ return dev_err_probe(dev, PTR_ERR(instance->phy), "failed to create phy\n");
+
+ phy_set_drvdata(instance->phy, instance);
+ }
+
+ phy_provider = devm_of_phy_provider_register(&pdev->dev, an7581_usb_phy_xlate);
+
+ return PTR_ERR_OR_ZERO(phy_provider);
+}
+
+static const struct of_device_id airoha_phy_id_table[] = {
+ { .compatible = "airoha,an7581-usb-phy" },
+ { },
+};
+MODULE_DEVICE_TABLE(of, airoha_phy_id_table);
+
+static struct platform_driver an7581_usb_driver = {
+ .probe = an7581_usb_phy_probe,
+ .driver = {
+ .name = "airoha-an7581-usb-phy",
+ .of_match_table = airoha_phy_id_table,
+ },
+};
+
+module_platform_driver(an7581_usb_driver);
+
+MODULE_DESCRIPTION("Airoha AN7581 USB PHY driver");
+MODULE_AUTHOR("Christian Marangi <ansuelsmth@gmail.com>");
+MODULE_LICENSE("GPL");
--
2.53.0
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* [PATCH v9 4/5] phy: move and rename Airoha PCIe PHY driver to dedicated directory
From: Christian Marangi @ 2026-05-21 15:35 UTC (permalink / raw)
To: Michael Turquette, Stephen Boyd, Brian Masney, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Christian Marangi, Vinod Koul,
Neil Armstrong, Lorenzo Bianconi, Felix Fietkau, linux-clk,
devicetree, linux-kernel, linux-arm-kernel, linux-phy
In-Reply-To: <20260521153645.7028-1-ansuelsmth@gmail.com>
To keep the generic PHY directory tidy, move the PCIe PHY driver for
Airoha AN7581 SoC to a dedicated directory.
Also rename the driver and add the relevant SoC name to the .c and .h
file in preparation for support of PCIe and USB PHY driver for Airoha
AN7583 SoC that use a completely different implementation and
calibration for PHYs and will have their own dedicated drivers.
The rename permits to better identify the specific usage of the driver
in the future once the airoha PHY directory will have multiple driver
for multiple SoC.
The config is changed from PHY_AIROHA_PCIE to PHY_AIROHA_AN7581_PCIE.
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Acked-by: Lorenzo Bianconi <lorenzo@kernel.org>
---
MAINTAINERS | 4 ++--
drivers/phy/Kconfig | 11 +----------
drivers/phy/Makefile | 4 ++--
drivers/phy/airoha/Kconfig | 13 +++++++++++++
drivers/phy/airoha/Makefile | 3 +++
.../phy-an7581-pcie-regs.h} | 2 +-
.../{phy-airoha-pcie.c => airoha/phy-an7581-pcie.c} | 6 +++---
7 files changed, 25 insertions(+), 18 deletions(-)
create mode 100644 drivers/phy/airoha/Kconfig
create mode 100644 drivers/phy/airoha/Makefile
rename drivers/phy/{phy-airoha-pcie-regs.h => airoha/phy-an7581-pcie-regs.h} (99%)
rename drivers/phy/{phy-airoha-pcie.c => airoha/phy-an7581-pcie.c} (99%)
diff --git a/MAINTAINERS b/MAINTAINERS
index 932044785a39..7bea8c620da8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -759,8 +759,8 @@ M: Lorenzo Bianconi <lorenzo@kernel.org>
L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
S: Maintained
F: Documentation/devicetree/bindings/phy/airoha,en7581-pcie-phy.yaml
-F: drivers/phy/phy-airoha-pcie-regs.h
-F: drivers/phy/phy-airoha-pcie.c
+F: drivers/phy/airoha/phy-an7581-pcie-regs.h
+F: drivers/phy/airoha/phy-an7581-pcie.c
AIROHA SPI SNFI DRIVER
M: Lorenzo Bianconi <lorenzo@kernel.org>
diff --git a/drivers/phy/Kconfig b/drivers/phy/Kconfig
index 227b9a4c612e..f9cd765a3ccc 100644
--- a/drivers/phy/Kconfig
+++ b/drivers/phy/Kconfig
@@ -46,16 +46,6 @@ config GENERIC_PHY_MIPI_DPHY
Provides a number of helpers a core functions for MIPI D-PHY
drivers to us.
-config PHY_AIROHA_PCIE
- tristate "Airoha PCIe-PHY Driver"
- depends on ARCH_AIROHA || COMPILE_TEST
- depends on OF
- select GENERIC_PHY
- help
- Say Y here to add support for Airoha PCIe PHY driver.
- This driver create the basic PHY instance and provides initialize
- callback for PCIe GEN3 port.
-
config PHY_CAN_TRANSCEIVER
tristate "CAN transceiver PHY"
select GENERIC_PHY
@@ -133,6 +123,7 @@ config PHY_XGENE
help
This option enables support for APM X-Gene SoC multi-purpose PHY.
+source "drivers/phy/airoha/Kconfig"
source "drivers/phy/allwinner/Kconfig"
source "drivers/phy/amlogic/Kconfig"
source "drivers/phy/apple/Kconfig"
diff --git a/drivers/phy/Makefile b/drivers/phy/Makefile
index f49d83f00a3d..84062279fa63 100644
--- a/drivers/phy/Makefile
+++ b/drivers/phy/Makefile
@@ -7,7 +7,6 @@ obj-$(CONFIG_PHY_COMMON_PROPS) += phy-common-props.o
obj-$(CONFIG_PHY_COMMON_PROPS_TEST) += phy-common-props-test.o
obj-$(CONFIG_GENERIC_PHY) += phy-core.o
obj-$(CONFIG_GENERIC_PHY_MIPI_DPHY) += phy-core-mipi-dphy.o
-obj-$(CONFIG_PHY_AIROHA_PCIE) += phy-airoha-pcie.o
obj-$(CONFIG_PHY_CAN_TRANSCEIVER) += phy-can-transceiver.o
obj-$(CONFIG_PHY_GOOGLE_USB) += phy-google-usb.o
obj-$(CONFIG_USB_LGM_PHY) += phy-lgm-usb.o
@@ -17,7 +16,8 @@ obj-$(CONFIG_PHY_PISTACHIO_USB) += phy-pistachio-usb.o
obj-$(CONFIG_PHY_SNPS_EUSB2) += phy-snps-eusb2.o
obj-$(CONFIG_PHY_XGENE) += phy-xgene.o
-obj-$(CONFIG_GENERIC_PHY) += allwinner/ \
+obj-$(CONFIG_GENERIC_PHY) += airoha/ \
+ allwinner/ \
amlogic/ \
apple/ \
broadcom/ \
diff --git a/drivers/phy/airoha/Kconfig b/drivers/phy/airoha/Kconfig
new file mode 100644
index 000000000000..9a1b625a7701
--- /dev/null
+++ b/drivers/phy/airoha/Kconfig
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Phy drivers for Airoha devices
+#
+config PHY_AIROHA_AN7581_PCIE
+ tristate "Airoha AN7581 PCIe-PHY Driver"
+ depends on ARCH_AIROHA || COMPILE_TEST
+ depends on OF
+ select GENERIC_PHY
+ help
+ Say Y here to add support for Airoha AN7581 PCIe PHY driver.
+ This driver create the basic PHY instance and provides initialize
+ callback for PCIe GEN3 port.
diff --git a/drivers/phy/airoha/Makefile b/drivers/phy/airoha/Makefile
new file mode 100644
index 000000000000..912f3e11a061
--- /dev/null
+++ b/drivers/phy/airoha/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+
+obj-$(CONFIG_PHY_AIROHA_AN7581_PCIE) += phy-an7581-pcie.o
diff --git a/drivers/phy/phy-airoha-pcie-regs.h b/drivers/phy/airoha/phy-an7581-pcie-regs.h
similarity index 99%
rename from drivers/phy/phy-airoha-pcie-regs.h
rename to drivers/phy/airoha/phy-an7581-pcie-regs.h
index 58572c793722..b938a7b468fe 100644
--- a/drivers/phy/phy-airoha-pcie-regs.h
+++ b/drivers/phy/airoha/phy-an7581-pcie-regs.h
@@ -1,4 +1,4 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
+// SPDX-License-Identifier: GPL-2.0-only
/*
* Copyright (c) 2024 AIROHA Inc
* Author: Lorenzo Bianconi <lorenzo@kernel.org>
diff --git a/drivers/phy/phy-airoha-pcie.c b/drivers/phy/airoha/phy-an7581-pcie.c
similarity index 99%
rename from drivers/phy/phy-airoha-pcie.c
rename to drivers/phy/airoha/phy-an7581-pcie.c
index 56e9ade8a9fd..81ddf0e7638b 100644
--- a/drivers/phy/phy-airoha-pcie.c
+++ b/drivers/phy/airoha/phy-an7581-pcie.c
@@ -13,7 +13,7 @@
#include <linux/platform_device.h>
#include <linux/slab.h>
-#include "phy-airoha-pcie-regs.h"
+#include "phy-an7581-pcie-regs.h"
#define LEQ_LEN_CTRL_MAX_VAL 7
#define FREQ_LOCK_MAX_ATTEMPT 10
@@ -1279,12 +1279,12 @@ MODULE_DEVICE_TABLE(of, airoha_pcie_phy_of_match);
static struct platform_driver airoha_pcie_phy_driver = {
.probe = airoha_pcie_phy_probe,
.driver = {
- .name = "airoha-pcie-phy",
+ .name = "airoha-an7581-pcie-phy",
.of_match_table = airoha_pcie_phy_of_match,
},
};
module_platform_driver(airoha_pcie_phy_driver);
-MODULE_DESCRIPTION("Airoha PCIe PHY driver");
+MODULE_DESCRIPTION("Airoha AN7581 PCIe PHY driver");
MODULE_AUTHOR("Lorenzo Bianconi <lorenzo@kernel.org>");
MODULE_LICENSE("GPL");
--
2.53.0
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* [PATCH v9 3/5] clk: en7523: Add support for selecting the Serdes port in SCU
From: Christian Marangi @ 2026-05-21 15:35 UTC (permalink / raw)
To: Michael Turquette, Stephen Boyd, Brian Masney, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Christian Marangi, Vinod Koul,
Neil Armstrong, Lorenzo Bianconi, Felix Fietkau, linux-clk,
devicetree, linux-kernel, linux-arm-kernel, linux-phy
In-Reply-To: <20260521153645.7028-1-ansuelsmth@gmail.com>
In the SCU register for clock and reset, there are also some register to
select the Serdes port mode. The Airoha AN7581 SoC have 4 different Serdes
that can switch between PCIe, USB or Ethernet mode.
Add a simple PHY provider that expose the .set_mode OP to toggle the
requested mode for the Serdes port.
Reviewed-by: Brian Masney <bmasney@redhat.com>
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
---
drivers/clk/Kconfig | 1 +
drivers/clk/clk-en7523.c | 218 ++++++++++++++++++++++++++++++++++++++-
2 files changed, 216 insertions(+), 3 deletions(-)
diff --git a/drivers/clk/Kconfig b/drivers/clk/Kconfig
index b2efbe9f6acb..e60a824b5117 100644
--- a/drivers/clk/Kconfig
+++ b/drivers/clk/Kconfig
@@ -221,6 +221,7 @@ config COMMON_CLK_EN7523
bool "Clock driver for Airoha/EcoNet SoC system clocks"
depends on OF
depends on ARCH_AIROHA || ECONET || COMPILE_TEST
+ select GENERIC_PHY
default ARCH_AIROHA
help
This driver provides the fixed clocks and gates present on Airoha
diff --git a/drivers/clk/clk-en7523.c b/drivers/clk/clk-en7523.c
index 1ab0e2eca5d3..183cf7fe4bda 100644
--- a/drivers/clk/clk-en7523.c
+++ b/drivers/clk/clk-en7523.c
@@ -6,14 +6,18 @@
#include <linux/io.h>
#include <linux/mfd/syscon.h>
#include <linux/platform_device.h>
+#include <linux/phy.h>
+#include <linux/phy/phy.h>
#include <linux/property.h>
#include <linux/regmap.h>
#include <linux/reset-controller.h>
+#include <linux/spinlock.h>
#include <dt-bindings/clock/en7523-clk.h>
#include <dt-bindings/reset/airoha,en7523-reset.h>
#include <dt-bindings/reset/airoha,en7581-reset.h>
#include <dt-bindings/clock/econet,en751221-scu.h>
#include <dt-bindings/reset/econet,en751221-scu.h>
+#include <dt-bindings/soc/airoha,scu-ssr.h>
#define RST_NR_PER_BANK 32
@@ -40,9 +44,22 @@
#define REG_HIR_MASK GENMASK(31, 16)
/* EN7581 */
#define REG_NP_SCU_PCIC 0x88
+#define REG_NP_SCU_SSR3 0x94
+#define REG_SSUSB_HSGMII_SEL_MASK BIT(29)
+#define REG_SSUSB_HSGMII_SEL_HSGMII FIELD_PREP_CONST(REG_SSUSB_HSGMII_SEL_MASK, 0x0)
+#define REG_SSUSB_HSGMII_SEL_USB FIELD_PREP_CONST(REG_SSUSB_HSGMII_SEL_MASK, 0x1)
#define REG_NP_SCU_SSTR 0x9c
#define REG_PCIE_XSI0_SEL_MASK GENMASK(14, 13)
+#define REG_PCIE_XSI0_SEL_PCIE FIELD_PREP_CONST(REG_PCIE_XSI0_SEL_MASK, 0x0)
+#define REG_PCIE_XSI0_SEL_XFI FIELD_PREP_CONST(REG_PCIE_XSI0_SEL_MASK, 0x1)
+#define REG_PCIE_XSI0_SEL_HSGMII FIELD_PREP_CONST(REG_PCIE_XSI0_SEL_MASK, 0x2)
#define REG_PCIE_XSI1_SEL_MASK GENMASK(12, 11)
+#define REG_PCIE_XSI1_SEL_PCIE FIELD_PREP_CONST(REG_PCIE_XSI1_SEL_MASK, 0x0)
+#define REG_PCIE_XSI1_SEL_XFI FIELD_PREP_CONST(REG_PCIE_XSI1_SEL_MASK, 0x1)
+#define REG_PCIE_XSI1_SEL_HSGMII FIELD_PREP_CONST(REG_PCIE_XSI1_SEL_MASK, 0x2)
+#define REG_USB_PCIE_SEL_MASK BIT(3)
+#define REG_USB_PCIE_SEL_PCIE FIELD_PREP_CONST(REG_USB_PCIE_SEL_MASK, 0x0)
+#define REG_USB_PCIE_SEL_USB FIELD_PREP_CONST(REG_USB_PCIE_SEL_MASK, 0x1)
#define REG_CRYPTO_CLKSRC2 0x20c
/* EN751221 */
#define EN751221_REG_SPI_DIV 0x0cc
@@ -81,6 +98,8 @@ enum en_hir {
HIR_MAX = 14,
};
+#define EN_SERDES_PHY_NUM 4
+
struct en_clk_desc {
int id;
const char *name;
@@ -113,6 +132,18 @@ struct en_rst_data {
struct reset_controller_dev rcdev;
};
+struct en_serdes_phy_instance {
+ struct phy *phy;
+ unsigned int serdes_port;
+};
+
+struct en_clk_priv {
+ void __iomem *base;
+ /* protect SCU register */
+ spinlock_t lock;
+ struct en_serdes_phy_instance *serdes_phys[EN_SERDES_PHY_NUM];
+};
+
struct en_clk_soc_data {
u32 num_clocks;
const struct clk_ops pcie_ops;
@@ -830,12 +861,179 @@ static int en7581_reset_register(struct device *dev, void __iomem *base,
return devm_reset_controller_register(dev, &rst_data->rcdev);
}
+static int en7581_serdes_phy_set_mode(struct phy *phy, enum phy_mode mode,
+ int submode)
+{
+ struct en_serdes_phy_instance *instance = phy_get_drvdata(phy);
+ struct en_clk_priv *priv = dev_get_drvdata(phy->dev.parent);
+ u32 reg, mask, sel, val;
+ unsigned long flags;
+
+ switch (instance->serdes_port) {
+ case AIROHA_SCU_SERDES_PCIE1:
+ reg = REG_NP_SCU_SSTR;
+ mask = REG_PCIE_XSI0_SEL_MASK;
+
+ if (mode != PHY_MODE_ETHERNET && mode != PHY_MODE_PCIE)
+ return -EINVAL;
+
+ if (mode == PHY_MODE_ETHERNET) {
+ switch (submode) {
+ case PHY_INTERFACE_MODE_USXGMII:
+ case PHY_INTERFACE_MODE_10GBASER:
+ sel = REG_PCIE_XSI0_SEL_XFI;
+ break;
+ case PHY_INTERFACE_MODE_SGMII:
+ case PHY_INTERFACE_MODE_1000BASEX:
+ case PHY_INTERFACE_MODE_2500BASEX:
+ sel = REG_PCIE_XSI0_SEL_HSGMII;
+ break;
+ default:
+ return -EINVAL;
+ }
+ } else {
+ sel = REG_PCIE_XSI0_SEL_PCIE;
+ }
+
+ break;
+ case AIROHA_SCU_SERDES_PCIE2:
+ reg = REG_NP_SCU_SSTR;
+ mask = REG_PCIE_XSI1_SEL_MASK;
+
+ if (mode != PHY_MODE_ETHERNET && mode != PHY_MODE_PCIE)
+ return -EINVAL;
+
+ if (mode == PHY_MODE_ETHERNET) {
+ switch (submode) {
+ case PHY_INTERFACE_MODE_USXGMII:
+ case PHY_INTERFACE_MODE_10GBASER:
+ sel = REG_PCIE_XSI1_SEL_XFI;
+ break;
+ case PHY_INTERFACE_MODE_SGMII:
+ case PHY_INTERFACE_MODE_1000BASEX:
+ case PHY_INTERFACE_MODE_2500BASEX:
+ sel = REG_PCIE_XSI1_SEL_HSGMII;
+ break;
+ default:
+ return -EINVAL;
+ }
+ } else {
+ sel = REG_PCIE_XSI1_SEL_PCIE;
+ }
+
+ break;
+ case AIROHA_SCU_SERDES_USB1:
+ reg = REG_NP_SCU_SSR3;
+ mask = REG_SSUSB_HSGMII_SEL_MASK;
+
+ if (mode != PHY_MODE_ETHERNET && mode != PHY_MODE_USB_DEVICE &&
+ mode != PHY_MODE_USB_DEVICE_SS)
+ return -EINVAL;
+
+ if (mode == PHY_MODE_ETHERNET)
+ sel = REG_SSUSB_HSGMII_SEL_HSGMII;
+ else
+ sel = REG_SSUSB_HSGMII_SEL_USB;
+
+ break;
+ case AIROHA_SCU_SERDES_USB2:
+ reg = REG_NP_SCU_SSTR;
+ mask = REG_USB_PCIE_SEL_MASK;
+
+ if (mode != PHY_MODE_PCIE && mode != PHY_MODE_USB_DEVICE &&
+ mode != PHY_MODE_USB_DEVICE_SS)
+ return -EINVAL;
+
+ if (mode == PHY_MODE_PCIE)
+ sel = REG_USB_PCIE_SEL_PCIE;
+ else
+ sel = REG_USB_PCIE_SEL_USB;
+
+ break;
+ default:
+ return -EINVAL;
+ }
+
+ spin_lock_irqsave(&priv->lock, flags);
+ val = readl(priv->base + reg);
+ val &= ~mask;
+ val |= sel;
+ writel(val, priv->base + reg);
+ spin_unlock_irqrestore(&priv->lock, flags);
+
+ return 0;
+}
+
+static const struct phy_ops en7581_serdes_phy_ops = {
+ .set_mode = en7581_serdes_phy_set_mode,
+ .owner = THIS_MODULE,
+};
+
+static struct phy *en7581_serdes_phy_xlate(struct device *dev,
+ const struct of_phandle_args *args)
+{
+ struct en_clk_priv *priv = dev_get_drvdata(dev);
+ struct en_serdes_phy_instance *instance;
+ unsigned int serdes_port;
+
+ if (args->args_count != 1) {
+ dev_err(dev, "invalid number of cells in 'phy' property\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ serdes_port = args->args[0];
+ if (serdes_port >= EN_SERDES_PHY_NUM) {
+ dev_err(dev, "invalid serdes port: %d\n", serdes_port);
+ return ERR_PTR(-EINVAL);
+ }
+
+ instance = priv->serdes_phys[serdes_port];
+ if (!instance) {
+ dev_err(dev, "failed to find appropriate serdes phy\n");
+ return ERR_PTR(-EINVAL);
+ }
+
+ return instance->phy;
+}
+
+static int en7581_serdes_phy_register(struct device *dev)
+{
+ struct en_clk_priv *priv = dev_get_drvdata(dev);
+ struct phy_provider *phy_provider;
+ int i;
+
+ for (i = 0; i < EN_SERDES_PHY_NUM; i++) {
+ struct en_serdes_phy_instance *instance;
+
+ instance = devm_kzalloc(dev, sizeof(*instance),
+ GFP_KERNEL);
+ if (!instance)
+ return -ENOMEM;
+
+ instance->phy = devm_phy_create(dev, NULL,
+ &en7581_serdes_phy_ops);
+ if (IS_ERR(instance->phy))
+ return dev_err_probe(dev, PTR_ERR(instance->phy), "failed to create phy\n");
+
+ instance->serdes_port = i;
+ priv->serdes_phys[i] = instance;
+
+ phy_set_drvdata(instance->phy, instance);
+ }
+
+ phy_provider = devm_of_phy_provider_register(dev, en7581_serdes_phy_xlate);
+
+ return PTR_ERR_OR_ZERO(phy_provider);
+}
+
static int en7581_clk_hw_init(struct platform_device *pdev,
struct clk_hw_onecell_data *clk_data)
{
+ struct en_clk_priv *priv = platform_get_drvdata(pdev);
struct regmap *map;
void __iomem *base;
u32 val;
+ int ret;
map = syscon_regmap_lookup_by_compatible("airoha,en7581-chip-scu");
if (IS_ERR(map))
@@ -845,6 +1043,8 @@ static int en7581_clk_hw_init(struct platform_device *pdev,
if (IS_ERR(base))
return PTR_ERR(base);
+ priv->base = base;
+
en7581_register_clocks(&pdev->dev, clk_data, map, base);
val = readl(base + REG_NP_SCU_SSTR);
@@ -853,9 +1053,12 @@ static int en7581_clk_hw_init(struct platform_device *pdev,
val = readl(base + REG_NP_SCU_PCIC);
writel(val | 3, base + REG_NP_SCU_PCIC);
- return en7581_reset_register(&pdev->dev, base, en7581_rst_map,
- ARRAY_SIZE(en7581_rst_map),
- en7581_rst_ofs);
+ ret = en7581_reset_register(&pdev->dev, base, en7581_rst_map,
+ ARRAY_SIZE(en7581_rst_map), en7581_rst_ofs);
+ if (ret)
+ return ret;
+
+ return en7581_serdes_phy_register(&pdev->dev);
}
static enum en_hir get_hw_id(void __iomem *np_base)
@@ -962,16 +1165,25 @@ static int en7523_clk_probe(struct platform_device *pdev)
struct device_node *node = pdev->dev.of_node;
const struct en_clk_soc_data *soc_data;
struct clk_hw_onecell_data *clk_data;
+ struct en_clk_priv *priv;
int r;
soc_data = device_get_match_data(&pdev->dev);
+ priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+
+ spin_lock_init(&priv->lock);
+
clk_data = devm_kzalloc(&pdev->dev,
struct_size(clk_data, hws, soc_data->num_clocks),
GFP_KERNEL);
if (!clk_data)
return -ENOMEM;
+ platform_set_drvdata(pdev, priv);
+
clk_data->num = soc_data->num_clocks;
r = soc_data->hw_init(pdev, clk_data);
if (r)
--
2.53.0
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* [PATCH v9 2/5] dt-bindings: phy: Add documentation for Airoha AN7581 USB PHY
From: Christian Marangi @ 2026-05-21 15:35 UTC (permalink / raw)
To: Michael Turquette, Stephen Boyd, Brian Masney, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Christian Marangi, Vinod Koul,
Neil Armstrong, Lorenzo Bianconi, Felix Fietkau, linux-clk,
devicetree, linux-kernel, linux-arm-kernel, linux-phy
In-Reply-To: <20260521153645.7028-1-ansuelsmth@gmail.com>
Add documentation for Airoha AN7581 USB PHY that describe the USB PHY
for the USB controller.
Airoha AN7581 SoC support a maximum of 2 USB port. The USB 2.0 mode is
always supported. The USB 3.0 mode is optional and depends on the Serdes
mode currently configured on the system for the relevant USB port.
To correctly calibrate, the USB 2.0 port require correct value in
"airoha,usb2-monitor-clk-sel" property. Both the 2 USB 2.0 port permit
selecting one of the 4 monitor clock for calibration (internal clock not
exposed to the system) but each port have only one of the 4 actually
connected in HW hence the correct value needs to be specified in DT
based on board and the physical port. Normally it's monitor clock 1 for
USB1 and monitor clock 2 for USB2.
To correctly setup the Serdes mode attached to the USB 3.0 mode, a phys
property is required with the phandle pointing to the correct Serdes port
provided by the SCU node. Providing the phys property is optional if USB
3.0 is not used.
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
---
.../bindings/phy/airoha,an7581-usb-phy.yaml | 62 +++++++++++++++++++
MAINTAINERS | 6 ++
2 files changed, 68 insertions(+)
create mode 100644 Documentation/devicetree/bindings/phy/airoha,an7581-usb-phy.yaml
diff --git a/Documentation/devicetree/bindings/phy/airoha,an7581-usb-phy.yaml b/Documentation/devicetree/bindings/phy/airoha,an7581-usb-phy.yaml
new file mode 100644
index 000000000000..f42e3d49a61f
--- /dev/null
+++ b/Documentation/devicetree/bindings/phy/airoha,an7581-usb-phy.yaml
@@ -0,0 +1,62 @@
+# SPDX-License-Identifier: GPL-2.0-only OR BSD-2-Clause
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/phy/airoha,an7581-usb-phy.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Airoha AN7581 SoC USB PHY
+
+maintainers:
+ - Christian Marangi <ansuelsmth@gmail.com>
+
+description: >
+ The Airoha AN7581 SoC USB PHY describes the USB PHY for the USB controller.
+
+ Airoha AN7581 SoC support a maximum of 2 USB port. The USB 2.0 mode is
+ always supported. The USB 3.0 mode is optional and depends on the Serdes
+ mode currently configured on the system for the relevant USB port.
+
+properties:
+ compatible:
+ const: airoha,an7581-usb-phy
+
+ reg:
+ maxItems: 1
+
+ airoha,usb2-monitor-clk-sel:
+ description: Describe what oscillator across the available 4
+ should be selected for USB 2.0 Slew Rate calibration.
+ $ref: /schemas/types.yaml#/definitions/uint32
+ enum: [0, 1, 2, 3]
+
+ phys:
+ items:
+ - description: phandle to Serdes PHY. Optional if USB 3.0 is not used.
+
+ '#phy-cells':
+ description: The cell contains the mode, PHY_TYPE_USB2 or PHY_TYPE_USB3,
+ as defined in dt-bindings/phy/phy.h.
+ const: 1
+
+required:
+ - compatible
+ - reg
+ - airoha,usb2-monitor-clk-sel
+ - '#phy-cells'
+
+additionalProperties: false
+
+examples:
+ - |
+ #include <dt-bindings/soc/airoha,scu-ssr.h>
+
+ phy@1fac0000 {
+ compatible = "airoha,an7581-usb-phy";
+ reg = <0x1fac0000 0x10000>;
+
+ airoha,usb2-monitor-clk-sel = <1>;
+ phys = <&scu AIROHA_SCU_SERDES_USB1>;
+
+ #phy-cells = <1>;
+ };
+
diff --git a/MAINTAINERS b/MAINTAINERS
index 21c0ef0b9ce5..932044785a39 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -771,6 +771,12 @@ S: Maintained
F: Documentation/devicetree/bindings/spi/airoha,en7581-snand.yaml
F: drivers/spi/spi-airoha-snfi.c
+AIROHA USB PHY DRIVER
+M: Christian Marangi <ansuelsmth@gmail.com>
+L: linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
+S: Maintained
+F: Documentation/devicetree/bindings/phy/airoha,an7581-usb-phy.yaml
+
AIRSPY MEDIA DRIVER
L: linux-media@vger.kernel.org
S: Orphan
--
2.53.0
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* [PATCH v9 1/5] dt-bindings: clock: airoha: Add PHY binding for Serdes port
From: Christian Marangi @ 2026-05-21 15:35 UTC (permalink / raw)
To: Michael Turquette, Stephen Boyd, Brian Masney, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Christian Marangi, Vinod Koul,
Neil Armstrong, Lorenzo Bianconi, Felix Fietkau, linux-clk,
devicetree, linux-kernel, linux-arm-kernel, linux-phy
Cc: Krzysztof Kozlowski
In-Reply-To: <20260521153645.7028-1-ansuelsmth@gmail.com>
Add PHY cell property for Serdes port selection. Currently supported only
for Airoha AN7581 SoC, that support up to 4 Serdes port.
The Serdes port can support both PCIe, USB3 or Ethernet mode.
- PCIe1 Serdes can support PCIe or Ethernet mode.
- PCIe2 Serdes can support PCIe or Ethernet mode.
- USB1 Serdes can support USB3 or HSGMII mode.
- USB2 Serdes can support USB3 or PCIe mode.
Add bindings to permit correct reference of the Serdes ports in DT.
Values are just symbolic and enumerates the Serdes port with a specific
number for precise reference.
The available Serdes port can be selected following the dt-binding header
in [2].
[2] <include/dt-bindings/soc/airoha,scu-ssr.h>
Signed-off-by: Christian Marangi <ansuelsmth@gmail.com>
Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
---
.../devicetree/bindings/clock/airoha,en7523-scu.yaml | 9 +++++++++
include/dt-bindings/soc/airoha,scu-ssr.h | 11 +++++++++++
2 files changed, 20 insertions(+)
create mode 100644 include/dt-bindings/soc/airoha,scu-ssr.h
diff --git a/Documentation/devicetree/bindings/clock/airoha,en7523-scu.yaml b/Documentation/devicetree/bindings/clock/airoha,en7523-scu.yaml
index eb24a5687639..913ddc16182b 100644
--- a/Documentation/devicetree/bindings/clock/airoha,en7523-scu.yaml
+++ b/Documentation/devicetree/bindings/clock/airoha,en7523-scu.yaml
@@ -23,6 +23,7 @@ description: |
All these identifiers can be found in:
[1]: <include/dt-bindings/clock/en7523-clk.h>.
+ [2]: <include/dt-bindings/soc/airoha,scu-ssr.h>.
The clocks are provided inside a system controller node.
@@ -50,6 +51,12 @@ properties:
description: ID of the controller reset line
const: 1
+ '#phy-cells':
+ description:
+ The first cell indicates the serdes phy number, see [2] for the
+ available serdes port.
+ const: 1
+
required:
- compatible
- reg
@@ -65,6 +72,8 @@ allOf:
reg:
minItems: 2
+ '#phy-cells': false
+
- if:
properties:
compatible:
diff --git a/include/dt-bindings/soc/airoha,scu-ssr.h b/include/dt-bindings/soc/airoha,scu-ssr.h
new file mode 100644
index 000000000000..33c64844ada3
--- /dev/null
+++ b/include/dt-bindings/soc/airoha,scu-ssr.h
@@ -0,0 +1,11 @@
+/* SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause) */
+
+#ifndef __DT_BINDINGS_AIROHA_SCU_SSR_H
+#define __DT_BINDINGS_AIROHA_SCU_SSR_H
+
+#define AIROHA_SCU_SERDES_PCIE1 0
+#define AIROHA_SCU_SERDES_PCIE2 1
+#define AIROHA_SCU_SERDES_USB1 2
+#define AIROHA_SCU_SERDES_USB2 3
+
+#endif /* __DT_BINDINGS_AIROHA_SCU_SSR_H */
--
2.53.0
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* [PATCH v9 0/5] airoha: an7581: USB support
From: Christian Marangi @ 2026-05-21 15:35 UTC (permalink / raw)
To: Michael Turquette, Stephen Boyd, Brian Masney, Rob Herring,
Krzysztof Kozlowski, Conor Dooley, Christian Marangi, Vinod Koul,
Neil Armstrong, Lorenzo Bianconi, Felix Fietkau, linux-clk,
devicetree, linux-kernel, linux-arm-kernel, linux-phy
This is a major rework of the old v2 series.
The SoC always support USB 2.0 but for USB 3.0 it needs additional
configuration for the Serdes port. Such port can be either configured
for USB usage or for PCIe lines or HSGMII and these are configured
in the SCU space.
The previous implementation of a dedicated SSR driver was too
complex and fragile for the simple task of configuring a register
hence it was dropped and the handling is entirely in the PHY driver.
Everything was reducted to the dt-bindings to describe the Serdes line.
Also the property for the PHY are renamed to a more suitable name and
everything is now mandatory to simplify the implementation.
(the PHY are always present and active on the SoC)
Also other unrelated patch are dropped from this series.
Changes v9:
- Add spinlock init
- Add ack tag
- Add review tag
- Add additional comments for phys on USB 3.0
- Add extra logic to make phys optional for USB 3.0
Changes v8:
- Squash header to clk Documentation patch
- Address comments from AI Bot
Link: https://lore.kernel.org/all/20260520150912.11614-1-ansuelsmth@gmail.com/
Changes v7:
- Rework to double PHY implementation
(suggested by Rob)
Now the clk driver expose a PHY for Serdes port
USB PHY driver selects it
- Rebase on top of linux-next
Link: https://lore.kernel.org/all/20260519220813.28468-1-ansuelsmth@gmail.com/
Changes v6:
- Fix kernel test robot (sparse warning)
Link: https://lore.kernel.org/all/20260306190156.22297-1-ansuelsmth@gmail.com/
Changes v5:
- Add Ack and Review tag from Connor
- Implement Ethernet support in the USB driver
(testing support for this Serdes on a special reference board)
- Use an7581 prefix for USB PHY driver
Link: https://lore.kernel.org/all/20251107160251.2307088-1-ansuelsmth@gmail.com/
Changes v4:
- Rename PCIe and USB PHY to AN7581
- Drop airoha,scu (handled directly in driver)
- Drop dt-bindings for monitor clock in favor of raw values
- Better describe the usage of airoha,usb3-serdes
- Simplify values of dt-bindings SSR SERDES
Link: https://lore.kernel.org/all/20251107160251.2307088-1-ansuelsmth@gmail.com/
Changes v3:
- Drop clk changes
- Drop SSR driver
- Rename property in Documentation
- Simplify PHY handling
- Move SSR handling inside the PHY driver
Link: https://lore.kernel.org/all/20251029173713.7670-1-ansuelsmth@gmail.com/
Changes v2:
- Drop changes for simple-mfd
- Rework PHY node structure to single node
- Drop port-id property in favor of serdes-port and
usb2-monitor-clock-sel
- Make the SSR driver probe from the clock driver
Christian Marangi (5):
dt-bindings: clock: airoha: Add PHY binding for Serdes port
dt-bindings: phy: Add documentation for Airoha AN7581 USB PHY
clk: en7523: Add support for selecting the Serdes port in SCU
phy: move and rename Airoha PCIe PHY driver to dedicated directory
phy: airoha: Add support for Airoha AN7581 USB PHY
.../bindings/clock/airoha,en7523-scu.yaml | 9 +
.../bindings/phy/airoha,an7581-usb-phy.yaml | 62 ++
MAINTAINERS | 11 +-
drivers/clk/Kconfig | 1 +
drivers/clk/clk-en7523.c | 218 ++++++-
drivers/phy/Kconfig | 11 +-
drivers/phy/Makefile | 4 +-
drivers/phy/airoha/Kconfig | 24 +
drivers/phy/airoha/Makefile | 4 +
.../phy-an7581-pcie-regs.h} | 2 +-
.../phy-an7581-pcie.c} | 6 +-
drivers/phy/airoha/phy-an7581-usb.c | 559 ++++++++++++++++++
include/dt-bindings/soc/airoha,scu-ssr.h | 11 +
13 files changed, 901 insertions(+), 21 deletions(-)
create mode 100644 Documentation/devicetree/bindings/phy/airoha,an7581-usb-phy.yaml
create mode 100644 drivers/phy/airoha/Kconfig
create mode 100644 drivers/phy/airoha/Makefile
rename drivers/phy/{phy-airoha-pcie-regs.h => airoha/phy-an7581-pcie-regs.h} (99%)
rename drivers/phy/{phy-airoha-pcie.c => airoha/phy-an7581-pcie.c} (99%)
create mode 100644 drivers/phy/airoha/phy-an7581-usb.c
create mode 100644 include/dt-bindings/soc/airoha,scu-ssr.h
--
2.53.0
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH v6 1/2] dt-bindings: phy: qcom: Add CSI2 C-PHY/DPHY schema
From: Bryan O'Donoghue @ 2026-05-21 15:36 UTC (permalink / raw)
To: sashiko-reviews
Cc: vkoul, neil.armstrong, devicetree, conor+dt, olteanv, linux-phy,
robh
In-Reply-To: <20260521122645.3EF9B1F000E9@smtp.kernel.org>
On 21/05/2026 13:26, sashiko-bot@kernel.org wrote:
> Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
> - [Medium] The schema unconditionally requires `clock-lanes` for `port@0`, which incorrectly breaks C-PHY configurations.
> - [Low] The example device tree node is missing required `data-lanes` and `clock-lanes` properties in the `port@0` endpoint.
> --
>
> commit bec75335fd5214a065f090cefeb28f9c895cfd3c
> Author: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
>
> dt-bindings: phy: qcom: Add CSI2 C-PHY/DPHY schema
>
> This commit adds a new base devicetree schema for Qualcomm MIPI CSI2 PHY
> devices, initially for the x1e80100. It supports CPHY, DPHY, and DPHY split
> modes across three ports, allowing per-PHY voltage rails to be individually
> defined and required.
>
>> diff --git a/Documentation/devicetree/bindings/phy/qcom,x1e80100-csi2-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,x1e80100-csi2-phy.yaml
>> new file mode 100644
>> index 0000000000000..c9116246c1e9e
>> --- /dev/null
>> +++ b/Documentation/devicetree/bindings/phy/qcom,x1e80100-csi2-phy.yaml
> [ ... ]
>> + properties:
>> + port@0:
>> + $ref: /schemas/graph.yaml#/$defs/port-base
>> + description: Sensor input. Always present.
>> +
>> + properties:
>> + endpoint:
>> + $ref: /schemas/media/video-interfaces.yaml#
>> + unevaluatedProperties: false
>> + properties:
>> + data-lanes:
>> + minItems: 1
>> + maxItems: 4
>> + clock-lanes:
>> + maxItems: 1
>> + remote-endpoint: true
>> + required:
>> + - data-lanes
>> + - clock-lanes
>
> [Severity: Medium]
> The commit description mentions the PHY supports both C-PHY and D-PHY modes.
> Since C-PHY embeds the clock signal within the 3-phase data lanes, there isn't
> a separate physical clock lane. Does requiring clock-lanes unconditionally
> here break configurations that need to use C-PHY mode?
Fair hadn't thought of that.
>
>> + - remote-endpoint
> [ ... ]
>> +examples:
>> + - |
> [ ... ]
>> + ports {
>> + #address-cells = <1>;
>> + #size-cells = <0>;
>> +
>> + port@0 {
>> + reg = <0>;
>> + csiphy0_in_ep: endpoint {
>> + remote-endpoint = <&sensor_out>;
>
> [Severity: Low]
> The schema definition above explicitly requires data-lanes and clock-lanes to
> be present in the port@0 endpoint. Will omitting them from this example cause
> a validation failure when running dt_binding_check?
Yes this is what happens when you ask the question "should I run the
check one more time" and say no.
>> + };
>> + };
>> +
>> + port@2 {
>> + reg = <2>;
>> + csiphy0_out_ep: endpoint {
>> + remote-endpoint = <&controller_in>;
>> + };
>> + };
>> + };
>> + };
> [ ... ]
>
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH v6 1/2] dt-bindings: phy: qcom: Add CSI2 C-PHY/DPHY schema
From: Rob Herring (Arm) @ 2026-05-21 15:15 UTC (permalink / raw)
To: Bryan O'Donoghue
Cc: linux-arm-msm, linux-media, linux-phy, linux-kernel,
Kishon Vijay Abraham I, Bryan O'Donoghue, devicetree,
Neil Armstrong, Vinod Koul, Krzysztof Kozlowski, Conor Dooley,
Vladimir Zapolskiy
In-Reply-To: <20260521-x1e-csi2-phy-v6-1-9d73d9bd7d20@linaro.org>
On Thu, 21 May 2026 13:20:08 +0100, Bryan O'Donoghue wrote:
> Add a base schema initially compatible with x1e80100 to describe MIPI CSI2
> PHY devices.
>
> The hardware can support both CPHY, DPHY and a special split-mode DPHY.
>
> The schema here defines three ports:
>
> port@0:
> The first input port where a sensor is always required.
>
> port@1:
> A second optional input port which if present implies DPHY split-mode.
>
> port@2:
> A third always required output port which connects to the controller.
>
> The CSIPHY devices have their own pinouts on the SoC as well as their own
> individual voltage rails.
>
> The need to model voltage rails on a per-PHY basis leads us to define
> CSIPHY devices as individual nodes.
>
> Two nice outcomes in terms of schema and DT arise from this change.
>
> 1. The ability to define on a per-PHY basis voltage rails.
> 2. The ability to require those voltage.
>
> We have had a complete bodge upstream for this where a single set of
> voltage rail for all CSIPHYs has been buried inside of CAMSS.
>
> Much like the I2C bus which is dedicated to Camera sensors - the CCI bus in
> CAMSS parlance, the CSIPHY devices should be individually modelled.
>
> Signed-off-by: Bryan O'Donoghue <bryan.odonoghue@linaro.org>
> ---
> .../bindings/phy/qcom,x1e80100-csi2-phy.yaml | 205 +++++++++++++++++++++
> 1 file changed, 205 insertions(+)
>
My bot found errors running 'make dt_binding_check' on your patch:
yamllint warnings/errors:
dtschema/dtc warnings/errors:
/builds/robherring/dt-review-ci/linux/Documentation/devicetree/bindings/phy/qcom,x1e80100-csi2-phy.yaml: port@0: Missing additionalProperties/unevaluatedProperties constraint
/builds/robherring/dt-review-ci/linux/Documentation/devicetree/bindings/phy/qcom,x1e80100-csi2-phy.yaml: port@1: Missing additionalProperties/unevaluatedProperties constraint
/builds/robherring/dt-review-ci/linux/Documentation/devicetree/bindings/phy/qcom,x1e80100-csi2-phy.yaml: port@2: Missing additionalProperties/unevaluatedProperties constraint
/builds/robherring/dt-review-ci/linux/Documentation/devicetree/bindings/phy/qcom,x1e80100-csi2-phy.example.dtb: csiphy@ace4000 (qcom,x1e80100-csi2-phy): ports:port@0:endpoint: 'data-lanes' is a required property
from schema $id: http://devicetree.org/schemas/phy/qcom,x1e80100-csi2-phy.yaml
/builds/robherring/dt-review-ci/linux/Documentation/devicetree/bindings/phy/qcom,x1e80100-csi2-phy.example.dtb: csiphy@ace4000 (qcom,x1e80100-csi2-phy): ports:port@0:endpoint: 'clock-lanes' is a required property
from schema $id: http://devicetree.org/schemas/phy/qcom,x1e80100-csi2-phy.yaml
doc reference errors (make refcheckdocs):
See https://patchwork.kernel.org/project/devicetree/patch/20260521-x1e-csi2-phy-v6-1-9d73d9bd7d20@linaro.org
The base for the series is generally the latest rc1. A different dependency
should be noted in *this* patch.
If you already ran 'make dt_binding_check' and didn't see the above
error(s), then make sure 'yamllint' is installed and dt-schema is up to
date:
pip3 install dtschema --upgrade
Please check and re-submit after running the above command yourself. Note
that DT_SCHEMA_FILES can be set to your schema file to speed up checking
your schema. However, it must be unset to test all examples with your schema.
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH net-next v6] net: phy: sfp: probe for RollBall I2C-to-MDIO bridge in mdio-i2c
From: Maxime Chevallier @ 2026-05-21 14:50 UTC (permalink / raw)
To: Petr Wozniak, netdev
Cc: linux-kernel, andrew, hkallweit1, linux, davem, edumazet, kuba,
pabeni, bjorn, linux-phy, jan
In-Reply-To: <20260521025755.24649-1-petr.wozniak@gmail.com>
Hi,
On 5/21/26 04:57, Petr Wozniak wrote:
> The "OEM"/"SFP-10G-T" quirk entry in sfp_fixup_rollball_cc()
> unconditionally forces MDIO_I2C_ROLLBALL for all modules matching that
> vendor/part-number combination. This works for modules that genuinely
> implement a RollBall I2C-to-MDIO bridge, but silently breaks modules
> that share the same EEPROM strings without having such a bridge.
>
> The Realtek RTL8261BE-CG is one such module: a pure copper 10G SFP+
> media converter with no I2C-to-MDIO bridge. Its EEPROM reports
> vendor="OEM", part="SFP-10G-T-I", and -- critically -- Vendor OUI
> 00:00:00, making OUI-based differentiation impossible. With
> MDIO_I2C_ROLLBALL forced, the module silently ACKs the unlock password
> write, the MDIO bus is created, but no PHY responds; the SFP state
> machine cycles through the RollBall PHY-probe retry window before
> reporting no PHY.
>
> Move the probe into i2c_mii_init_rollball() in mdio-i2c.c, where the
> RollBall protocol constants are already defined. After sending the
> unlock password, issue a CMD_READ and poll for CMD_DONE up to 200 ms
> (10 x 20 ms, matching the existing rollball poll tolerance). A genuine
> RollBall bridge asserts CMD_DONE within that window; modules without a
> bridge never do, so i2c_mii_init_rollball() returns -ENODEV.
> mdio_i2c_alloc() propagates -ENODEV to the caller to signal that no
> bridge is present and PHY probing should be skipped.
> sfp_sm_add_mdio_bus() catches -ENODEV and transitions
> sfp->mdio_protocol to MDIO_I2C_NONE so the rest of the state machine
> skips PHY probing for this module.
>
> Any I2C-level error (NACK, timeout) during the probe is also treated as
> -ENODEV: if the module does not respond at I2C address 0x51 at all,
> there is certainly no RollBall bridge there, and SFP initialization
> should not abort.
>
> The probe writes are safe with respect to SFP EEPROM integrity: only
> modules explicitly listed in the quirk table enter this path, and the
> RollBall password unlock write to 0x51 was already issued by
> i2c_mii_init_rollball() before the probe for all such modules. Any
> module without a device at 0x51 NACKs the transfer and is treated as
> -ENODEV.
>
> Add "OEM"/"SFP-10G-T-I" to the quirk table so RTL8261BE modules enter
> the probe path; genuine RollBall modules continue to work as before.
>
> Signed-off-by: Petr Wozniak <petr.wozniak@gmail.com>
> Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
> ---
>
> Changes since v5 (Sashiko AI review):
> - Treat I2C NACK/errors in i2c_mii_init_rollball() as -ENODEV so
> modules without a 0x51 EEPROM do not abort SFP initialization
> - Replace fixed 70 ms wait with 10 x 20 ms poll (total 200 ms),
> matching the existing i2c_rollball_mii_poll() tolerance and
> preventing false -ENODEV on slow RollBall bridges
>
> Changes since v4 (feedback from Maxime Chevallier):
> - Fix commit message: replace "stalls" with accurate description of
> the RollBall PHY-probe retry window
> - Fix variable declaration order in i2c_mii_probe_rollball() to
> follow reverse-xmas tree (descending line length)
> - Remove spurious alignment space on "SFP-10G-T" quirk entry
> - Document that -ENODEV from mdio_i2c_alloc() means no bridge present,
> PHY probing should be skipped
>
> Changes since v3 (feedback from Jakub Kicinski):
> - Drop spurious Tested-by: tag -- author and tester are the same person
> - Use PATCH net-next subject prefix
> - Move -ENODEV handling from sfp_i2c_mdiobus_create() into
> sfp_sm_add_mdio_bus() so bus-creation code does not mutate
> sfp->mdio_protocol; the state machine is the correct place for
> protocol-state transitions
> - Split combined variable declaration for clarity
>
> Changes since v2:
> - Compile-tested and hardware-tested on BPI-R4 (MT7988A, 6.12.87)
> - RTL8261BE (OEM/SFP-10G-T-I): probes MDIO_I2C_NONE, link Up 10Gbps
> - Genuine RollBall (OEM/SFP-10G-T): bridge detected, link Up 10Gbps
>
> drivers/net/mdio/mdio-i2c.c | 65 ++++++++++++++++++++++++++++++------
> drivers/net/phy/sfp.c | 16 ++++++++--
> 2 files changed, 68 insertions(+), 13 deletions(-)
> --- a/drivers/net/mdio/mdio-i2c.c
> +++ b/drivers/net/mdio/mdio-i2c.c
> @@ -352,6 +352,54 @@
> return 0;
> }
>
> +static int i2c_mii_probe_rollball(struct i2c_adapter *i2c)
> +{
> + u8 data_buf[] = { ROLLBALL_DATA_ADDR, 0x01, 0x00, 0x00 };
> + u8 cmd_buf[] = { ROLLBALL_CMD_ADDR, ROLLBALL_CMD_READ };
> + u8 cmd_addr = ROLLBALL_CMD_ADDR;
> + struct i2c_msg msgs[2];
> + u8 result;
> + int ret;
> + int i;
> +
> + msgs[0].addr = ROLLBALL_PHY_I2C_ADDR;
> + msgs[0].flags = 0;
> + msgs[0].len = sizeof(data_buf);
> + msgs[0].buf = data_buf;
> + msgs[1].addr = ROLLBALL_PHY_I2C_ADDR;
> + msgs[1].flags = 0;
> + msgs[1].len = sizeof(cmd_buf);
> + msgs[1].buf = cmd_buf;
> +
> + ret = i2c_transfer_rollball(i2c, msgs, ARRAY_SIZE(msgs));
> + if (ret < 0)
> + return -ENODEV;
> + if (ret)
> + return ret;
> +
> + msgs[0].addr = ROLLBALL_PHY_I2C_ADDR;
> + msgs[0].flags = 0;
> + msgs[0].len = 1;
> + msgs[0].buf = &cmd_addr;
> + msgs[1].addr = ROLLBALL_PHY_I2C_ADDR;
> + msgs[1].flags = I2C_M_RD;
> + msgs[1].len = 1;
> + msgs[1].buf = &result;
> +
> + for (i = 0; i < 10; i++) {
> + msleep(20);
> + ret = i2c_transfer_rollball(i2c, msgs, ARRAY_SIZE(msgs));
> + if (ret < 0)
> + return -ENODEV;
> + if (ret)
> + return ret;
I think this check is not needed, it seems to me that
i2c_transfer_rollball() always returns either a negative number, or
zero. All the calls in i2c_transfer_rollball() end-up returning the
return value from __i2c_transfer_err(), which is always either negative
or 0.
There's a similar check below that can be simplified as well
Maxime
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH v2 4/4] PCI: qcom: enable Link retain logic for Hamoa
From: sashiko-bot @ 2026-05-21 14:35 UTC (permalink / raw)
To: Krishna Chaitanya Chundru
Cc: olteanv, linux-phy, neil.armstrong, vkoul, linux-pci
In-Reply-To: <20260521-link_retain-v2-4-08ed448b081c@oss.qualcomm.com>
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
Pre-existing issues:
- [High] Setting `link_retain = true` in `cfg_x1e80100` exposes a flawed error handling path in `qcom_pcie_host_init()` that silently ignores `-EPROBE_DEFER` and bypasses critical host configuration.
--
commit 868652002bbdb8222b28dbec2b0655af97d3ceb8
Author: Krishna Chaitanya Chundru <krishna.chundru@oss.qualcomm.com>
PCI: qcom: enable Link retain logic for Hamoa
The Hamoa platform supports keeping the PCIe link active across
bootloader and kernel handoff. To take advantage of this, introduce a
specific configuration (cfg_x1e80100) with link_retain = true and
update the device match table to use it.
> diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
> index b061eaa227b39..8496eb87debbc 100644
> --- a/drivers/pci/controller/dwc/pcie-qcom.c
> +++ b/drivers/pci/controller/dwc/pcie-qcom.c
> @@ -1557,6 +1557,12 @@ static const struct qcom_pcie_cfg cfg_sc8280xp = {
> .no_l0s = true,
> };
>
> +static const struct qcom_pcie_cfg cfg_x1e80100 = {
> + .ops = &ops_1_21_0,
> + .no_l0s = true,
> + .link_retain = true,
> +};
> +
[Severity: High]
This isn't a bug introduced by this patch, but setting link_retain to true
here exposes a pre-existing flawed error handling path in qcom_pcie_host_init()
that silently ignores -EPROBE_DEFER.
If pci_pwrctrl_power_on_devices() returns -EPROBE_DEFER when the power control
driver hasn't bound yet, the error handler intercepts the deferral:
qcom_pcie_host_init() {
...
ret = pci_pwrctrl_power_on_devices(pci->dev);
if (ret)
goto err_pwrctrl_destroy;
...
err_pwrctrl_destroy:
if (pp->link_retain && ret == -EPROBE_DEFER)
return 0;
...
}
Will returning 0 here trick the DWC core (dw_pcie_host_init()) into assuming
host initialization completed successfully?
Since the probe completes without retrying, could this leave the PCIe slot
regulators unmanaged by the kernel, causing them to be disabled later when
regulator_init_complete() runs at late initcall?
Additionally, does returning early skip mandatory initialization steps like
qcom_pcie_clear_aspm_l0s() (which is required by cfg_x1e80100.no_l0s = true),
hiding MSI-X/DPC capabilities, and performing SID configuration? Skipping these
could result in link instability, AER errors, and hardware malfunction.
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260521-link_retain-v2-0-08ed448b081c@oss.qualcomm.com?part=4
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH 1/4] dt-bindings: phy: sc8280xp-qmp-pcie: Document Eliza PCIe phy
From: sashiko-bot @ 2026-05-21 14:21 UTC (permalink / raw)
To: Krishna Chaitanya Chundru
Cc: linux-pci, vkoul, conor+dt, linux-phy, olteanv, neil.armstrong,
robh, devicetree
In-Reply-To: <20260521-eliza-v1-1-97cdbe88389d@oss.qualcomm.com>
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] The new Eliza PCIe PHY compatibles are placed in the wrong conditional blocks, incorrectly constraining them to require 6 clocks and 2 resets.
--
commit 8532696e8f5cf63303348c425688fe2c2383eed6
Author: Krishna Chaitanya Chundru <krishna.chundru@oss.qualcomm.com>
dt-bindings: phy: sc8280xp-qmp-pcie: Document Eliza PCIe phy
Add compatibles for the Eliza PCIe QMP PHY's, which supports Gen3x1 and
Gen3x2 configurations.
> diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
> index 3a35120a77ec0..be4bbc327982f 100644
> --- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
> +++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
[ ... ]
> @@ -181,6 +183,8 @@ allOf:
> compatible:
> contains:
> enum:
> + - qcom,eliza-qmp-gen3x1-pcie-phy
> + - qcom,eliza-qmp-gen3x2-pcie-phy
> - qcom,glymur-qmp-gen4x2-pcie-phy
> - qcom,glymur-qmp-gen5x4-pcie-phy
> - qcom,qcs8300-qmp-gen4x2-pcie-phy
[Severity: High]
Are these compatibles placed in the correct conditional block?
By placing the Eliza compatibles in this group, the schema enforces a
minimum of 6 clocks and 2 resets. However, the driver implementation
introduced in the series expects only 1 reset.
This mismatch will prevent structurally correct device tree nodes from
passing schema validation.
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260521-eliza-v1-0-97cdbe88389d@oss.qualcomm.com?part=1
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH v2 3/4] PCI: qcom: Add link retention support
From: sashiko-bot @ 2026-05-21 14:15 UTC (permalink / raw)
To: Krishna Chaitanya Chundru
Cc: vkoul, neil.armstrong, olteanv, linux-phy, linux-pci
In-Reply-To: <20260521-link_retain-v2-3-08ed448b081c@oss.qualcomm.com>
Thank you for your contribution! Sashiko AI review found 3 potential issue(s) to consider:
- [High] Checking hardware link capabilities instead of negotiated link status to determine current link speed and width.
- [High] Returning 0 instead of -EPROBE_DEFER defeats the probe deferral mechanism and leaves the controller partially initialized.
- [High] Early returns during link retention bypass critical controller software state initialization and hardware capabilities.
--
commit 6dd7e9bfe9f104689a018777f9dcaa31b6e736f8
Author: Krishna Chaitanya Chundru <krishna.chundru@oss.qualcomm.com>
PCI: qcom: Add link retention support
This patch introduces link retention support for Qualcomm PCIe controllers,
skipping reinitialization and PERST# toggling if the bootloader left the
link active in L0 or L1 idle. It falls back to normal initialization and
link retraining if the current link does not meet device tree constraints.
> diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
> index bfe873cbf44f6..b061eaa227b39 100644
> --- a/drivers/pci/controller/dwc/pcie-qcom.c
> +++ b/drivers/pci/controller/dwc/pcie-qcom.c
[ ... ]
> @@ -960,6 +962,42 @@ static int qcom_pcie_get_resources_2_7_0(struct qcom_pcie *pcie)
> return 0;
> }
>
> +/*
> + * Determine whether the link established by the bootloader can be reused.
> + *
> + * Reuse the existing link only if its current speed and lane count match
> + * the max-link-speed and num-lanes specified in Device Tree; otherwise,
> + * retrain the link.
> + */
> +static bool qcom_pcie_check_link_retain(struct qcom_pcie *pcie)
> +{
> + u32 cap, speed, val, ltssm, width;
> + struct dw_pcie *pci = pcie->pci;
> + u8 offset;
> +
> + val = readl(pcie->parf + PARF_LTSSM);
> + ltssm = val & 0x1f;
> + if ((val & LTSSM_EN) &&
> + (ltssm == DW_PCIE_LTSSM_L0 || ltssm == DW_PCIE_LTSSM_L1_IDLE)) {
> + qcom_pcie_configure_dbi_atu_base(pcie);
> +
> + offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
> + cap = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP);
> + speed = FIELD_GET(PCI_EXP_LNKCAP_SLS, cap);
> + width = dw_pcie_link_get_max_link_width(pci);
[Severity: High]
Does this check the maximum hardware capabilities instead of the currently
negotiated link status?
Reading PCI_EXP_LNKCAP (and using dw_pcie_link_get_max_link_width) retrieves
the hardware capabilities rather than the current link speed and width from
PCI_EXP_LNKSTA.
If the bootloader brought up the link at a degraded speed (e.g., Gen1x1 on a
port capable of Gen3x2), could this incorrectly pass the constraint checks
and leave the system with severely degraded PCIe performance?
> +
> + if (pci->max_link_speed > 0 && speed > pci->max_link_speed)
> + return false;
> +
> + if (pci->num_lanes > 0 && width > pci->num_lanes)
> + return false;
> +
> + return true;
> + }
> +
> + return false;
> +}
> +
> static int qcom_pcie_init_2_7_0(struct qcom_pcie *pcie)
> {
> struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0;
> @@ -978,6 +1016,14 @@ static int qcom_pcie_init_2_7_0(struct qcom_pcie *pcie)
> if (ret < 0)
> goto err_disable_regulators;
>
> + if (pcie->cfg->link_retain) {
> + pci->pp.link_retain = qcom_pcie_check_link_retain(pcie);
> + if (pci->pp.link_retain) {
> + dev_info(dev, "Retaining PCIe link\n");
> + return 0;
> + }
> + }
[Severity: High]
Does this early return bypass critical software state initialization?
Returning early here skips the assignment of pci->l1ss_support = true later
in this function. Because struct dw_pcie is zero-initialized, the downstream
DesignWare core might falsely assume ASPM L1 Substates are unsupported and
fail to configure them correctly.
> +
> ret = reset_control_assert(res->rst);
> if (ret) {
> dev_err(dev, "reset assert failed (%d)\n", ret);
> @@ -1038,6 +1084,9 @@ static int qcom_pcie_post_init_2_7_0(struct qcom_pcie *pcie)
> {
> const struct qcom_pcie_cfg *pcie_cfg = pcie->cfg;
>
> + if (pcie->pci->pp.link_retain)
> + return 0;
> +
[Severity: High]
Could this early return skip necessary hot-plug configurations?
By returning early, this skips the call to qcom_pcie_set_slot_nccs() located
further down. Missing the No Command Completed Support (NCCS) configuration
could break PCIe hot-plug command completions and lead to timeouts during
hot-plug operations.
> if (pcie_cfg->override_no_snoop)
> writel(WR_NO_SNOOP_OVERRIDE_EN | RD_NO_SNOOP_OVERRIDE_EN,
> pcie->parf + PARF_NO_SNOOP_OVERRIDE);
[ ... ]
> @@ -1337,8 +1388,9 @@ static int qcom_pcie_host_init(struct dw_pcie_rp *pp)
> err_pwrctrl_power_off:
> pci_pwrctrl_power_off_devices(pci->dev);
> err_pwrctrl_destroy:
> - if (ret != -EPROBE_DEFER)
> - pci_pwrctrl_destroy_devices(pci->dev);
> + if (pp->link_retain && ret == -EPROBE_DEFER)
> + return 0;
[Severity: High]
Does returning 0 here defeat the probe deferral mechanism?
If pci_pwrctrl_power_on_devices() earlier in this function returns
-EPROBE_DEFER, returning 0 instead of propagating the error code causes
the driver core to treat the probe as successful. This means the driver
will not be re-probed when resources become available.
Additionally, returning early from this error cleanup path leaves the rest
of the host initialization incomplete (such as SMMU setup and removing
MSIX/DPC capabilities), potentially leaving the controller in an unusable
state while the kernel believes the probe succeeded.
> + pci_pwrctrl_destroy_devices(pci->dev);
> err_disable_phy:
> qcom_pcie_phy_power_off(pcie);
> err_deinit:
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260521-link_retain-v2-0-08ed448b081c@oss.qualcomm.com?part=3
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* [PATCH 4/4] phy: qcom: qmp-pcie: Add QMP PCIe PHY support for Eliza
From: Krishna Chaitanya Chundru @ 2026-05-21 14:05 UTC (permalink / raw)
To: Vinod Koul, Neil Armstrong, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Lorenzo Pieralisi, Krzysztof Wilczyński,
Manivannan Sadhasivam, Bjorn Helgaas, Bjorn Andersson
Cc: linux-arm-msm, linux-phy, devicetree, linux-kernel, linux-pci,
Krishna Chaitanya Chundru
In-Reply-To: <20260521-eliza-v1-0-97cdbe88389d@oss.qualcomm.com>
Add QMP PCIe PHY support for the Eliza SoC. Introduce a new Gen3x1 PHY
configuration with Eliza-specific initialization tables, and reuse the
existing sm8550 Gen3x2 configuration for the Gen3x2 PHY instance.
Also add the missing QPHY_PCIE_V6_PCS_PCIE_INT_AUX_CLK_CONFIG1 register
definition to the PCIe V6 PCS header.
Signed-off-by: Krishna Chaitanya Chundru <krishna.chundru@oss.qualcomm.com>
---
drivers/phy/qualcomm/phy-qcom-qmp-pcie.c | 139 ++++++++++++++++++++++++
drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6.h | 1 +
2 files changed, 140 insertions(+)
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
index fed2fc9bb311..113c5f8f1dbc 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
@@ -198,6 +198,112 @@ static const struct qmp_phy_init_tbl msm8998_pcie_pcs_tbl[] = {
QMP_PHY_INIT_CFG(QPHY_V3_PCS_SIGDET_CNTRL, 0x03),
};
+static const struct qmp_phy_init_tbl eliza_qmp_gen3x1_pcie_serdes_tbl[] = {
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE1, 0x93),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE1, 0x01),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE1, 0x02),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE1, 0x16),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE1, 0x36),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORECLK_DIV_MODE1, 0x04),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE1, 0x0a),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE1, 0x1a),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE1, 0x34),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE1, 0x55),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE1, 0x55),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE1, 0x01),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_HSCLK_SEL_1, 0x01),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE1_MODE1, 0xB4),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE2_MODE1, 0x03),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE1_MODE0, 0xf8),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_STEP_SIZE2_MODE0, 0x01),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_CP_CTRL_MODE0, 0x02),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_RCTRL_MODE0, 0x16),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_CCTRL_MODE0, 0x36),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP1_MODE0, 0x04),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP2_MODE0, 0x0d),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_DEC_START_MODE0, 0x41),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START1_MODE0, 0xab),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START2_MODE0, 0xaa),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_DIV_FRAC_START3_MODE0, 0x01),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE1_MODE0, 0x24),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_BG_TIMER, 0x0a),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_EN_CENTER, 0x01),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER1, 0x62),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_SSC_PER2, 0x02),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_CLK_ENABLE1, 0x90),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYS_CLK_CTRL, 0x82),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_PLL_IVCO, 0x07),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_SYSCLK_EN_SEL, 0x08),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_LOCK_CMP_EN, 0x42),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_VCO_TUNE_MAP, 0x14),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_CLK_SELECT, 0x34),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_CORE_CLK_EN, 0xA0),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_CMN_CONFIG_1, 0x16),
+ QMP_PHY_INIT_CFG(QSERDES_V6_COM_ADDITIONAL_MISC_3, 0x0F),
+};
+
+static const struct qmp_phy_init_tbl eliza_qmp_gen3x1_pcie_pcs_tbl[] = {
+ QMP_PHY_INIT_CFG(QPHY_V6_PCS_REFGEN_REQ_CONFIG1, 0x05),
+ QMP_PHY_INIT_CFG(QPHY_V6_PCS_G3S2_PRE_GAIN, 0x2E),
+ QMP_PHY_INIT_CFG(QPHY_V6_PCS_RX_SIGDET_LVL, 0x77),
+ QMP_PHY_INIT_CFG(QPHY_V6_PCS_RATE_SLEW_CNTRL1, 0x0B),
+ QMP_PHY_INIT_CFG(QPHY_V6_PCS_PCS_TX_RX_CONFIG, 0x0C),
+ QMP_PHY_INIT_CFG(QPHY_V6_PCS_EQ_CONFIG2, 0x0F),
+};
+
+static const struct qmp_phy_init_tbl eliza_qmp_gen3x1_pcie_misc_pcs_tbl[] = {
+ QMP_PHY_INIT_CFG(QPHY_PCIE_V6_PCS_PCIE_POWER_STATE_CONFIG2, 0x1D),
+ QMP_PHY_INIT_CFG(QPHY_PCIE_V6_PCS_PCIE_ENDPOINT_REFCLK_DRIVE, 0xC1),
+ QMP_PHY_INIT_CFG(QPHY_PCIE_V6_PCS_PCIE_INT_AUX_CLK_CONFIG1, 0x00),
+ QMP_PHY_INIT_CFG(QPHY_PCIE_V6_PCS_PCIE_OSC_DTCT_ACTIONS, 0x00),
+ QMP_PHY_INIT_CFG(QPHY_PCIE_V6_PCS_PCIE_RXEQEVAL_TIME, 0x27),
+};
+
+static const struct qmp_phy_init_tbl eliza_qmp_gen3x1_pcie_tx_tbl[] = {
+ QMP_PHY_INIT_CFG(QSERDES_V6_TX_RES_CODE_LANE_OFFSET_TX, 0x17),
+ QMP_PHY_INIT_CFG(QSERDES_V6_TX_RES_CODE_LANE_OFFSET_RX, 0x06),
+ QMP_PHY_INIT_CFG(QSERDES_V6_TX_LANE_MODE_1, 0x15),
+ QMP_PHY_INIT_CFG(QSERDES_V6_TX_LANE_MODE_4, 0x3F),
+ QMP_PHY_INIT_CFG(QSERDES_V6_TX_RCV_DETECT_LVL_2, 0x12),
+ QMP_PHY_INIT_CFG(QSERDES_V6_TX_PI_QEC_CTRL, 0x02),
+};
+
+static const struct qmp_phy_init_tbl eliza_qmp_gen3x1_pcie_rx_tbl[] = {
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_FO_GAIN, 0x09),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SO_GAIN, 0x05),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SO_SATURATION_AND_ENABLE, 0x7F),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_PI_CONTROLS, 0xF0),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SB2_THRESH1, 0x08),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_UCDR_SB2_THRESH2, 0x08),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_AUX_DATA_TCOARSE_TFINE, 0x30),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_TX_ADAPT_POST_THRESH, 0xF0),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_VGA_CAL_CNTRL1, 0x04),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_VGA_CAL_CNTRL2, 0x0F),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_GM_CAL, 0x0D),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_EQU_ADAPTOR_CNTRL2, 0x0E),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_EQU_ADAPTOR_CNTRL3, 0x4A),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_EQU_ADAPTOR_CNTRL4, 0x0A),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_IDAC_TSETTLE_LOW, 0x07),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_EQ_OFFSET_ADAPTOR_CNTRL1, 0x14),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_SIDGET_ENABLES, 0x0C),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_00_LOW, 0x3F),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_00_HIGH, 0xBF),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_00_HIGH2, 0xBF),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_00_HIGH3, 0xB7),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_00_HIGH4, 0xEA),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_01_LOW, 0xDC),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_01_HIGH, 0x5C),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_01_HIGH2, 0x9C),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_01_HIGH3, 0x1A),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_01_HIGH4, 0x89),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_10_HIGH, 0x94),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_10_HIGH2, 0x5B),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_10_HIGH3, 0x1A),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_RX_MODE_10_HIGH4, 0x89),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_DFE_CTLE_POST_CAL_OFFSET, 0x38),
+ QMP_PHY_INIT_CFG(QSERDES_V6_RX_SIGDET_CAL_TRIM, 0x08),
+};
+
static const struct qmp_phy_init_tbl ipq6018_pcie_serdes_tbl[] = {
QMP_PHY_INIT_CFG(QSERDES_PLL_SSC_PER1, 0x7d),
QMP_PHY_INIT_CFG(QSERDES_PLL_SSC_PER2, 0x01),
@@ -3532,6 +3638,33 @@ static const struct qmp_pcie_offsets qmp_pcie_offsets_v8_50 = {
.txrxz = 0xd000,
};
+static const struct qmp_phy_cfg eliza_qmp_gen3x1_pciephy_cfg = {
+ .lanes = 1,
+
+ .offsets = &qmp_pcie_offsets_v5,
+
+ .tbls = {
+ .serdes = eliza_qmp_gen3x1_pcie_serdes_tbl,
+ .serdes_num = ARRAY_SIZE(eliza_qmp_gen3x1_pcie_serdes_tbl),
+ .tx = eliza_qmp_gen3x1_pcie_tx_tbl,
+ .tx_num = ARRAY_SIZE(eliza_qmp_gen3x1_pcie_tx_tbl),
+ .rx = eliza_qmp_gen3x1_pcie_rx_tbl,
+ .rx_num = ARRAY_SIZE(eliza_qmp_gen3x1_pcie_rx_tbl),
+ .pcs = eliza_qmp_gen3x1_pcie_pcs_tbl,
+ .pcs_num = ARRAY_SIZE(eliza_qmp_gen3x1_pcie_pcs_tbl),
+ .pcs_misc = eliza_qmp_gen3x1_pcie_misc_pcs_tbl,
+ .pcs_misc_num = ARRAY_SIZE(eliza_qmp_gen3x1_pcie_misc_pcs_tbl),
+ },
+ .reset_list = sdm845_pciephy_reset_l,
+ .num_resets = ARRAY_SIZE(sdm845_pciephy_reset_l),
+ .vreg_list = qmp_phy_vreg_l,
+ .num_vregs = ARRAY_SIZE(qmp_phy_vreg_l),
+ .regs = pciephy_v6_regs_layout,
+
+ .pwrdn_ctrl = SW_PWRDN | REFCLK_DRV_DSBL,
+ .phy_status = PHYSTATUS,
+};
+
static const struct qmp_phy_cfg ipq8074_pciephy_cfg = {
.lanes = 1,
@@ -5399,6 +5532,12 @@ static int qmp_pcie_probe(struct platform_device *pdev)
static const struct of_device_id qmp_pcie_of_match_table[] = {
{
+ .compatible = "qcom,eliza-qmp-gen3x1-pcie-phy",
+ .data = &eliza_qmp_gen3x1_pciephy_cfg,
+ }, {
+ .compatible = "qcom,eliza-qmp-gen3x2-pcie-phy",
+ .data = &sm8550_qmp_gen3x2_pciephy_cfg,
+ }, {
.compatible = "qcom,glymur-qmp-gen4x2-pcie-phy",
.data = &glymur_qmp_gen4x2_pciephy_cfg,
}, {
diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6.h b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6.h
index 45397cb3c0c6..17a0f9d18acf 100644
--- a/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6.h
+++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6.h
@@ -12,6 +12,7 @@
#define QPHY_PCIE_V6_PCS_PCIE_POWER_STATE_CONFIG2 0x0c
#define QPHY_PCIE_V6_PCS_PCIE_POWER_STATE_CONFIG4 0x14
#define QPHY_PCIE_V6_PCS_PCIE_ENDPOINT_REFCLK_DRIVE 0x20
+#define QPHY_PCIE_V6_PCS_PCIE_INT_AUX_CLK_CONFIG1 0x54
#define QPHY_PCIE_V6_PCS_PCIE_OSC_DTCT_ACTIONS 0x94
#define QPHY_PCIE_V6_PCS_LANE1_INSIG_SW_CTRL2 0x024
--
2.34.1
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* [PATCH 3/4] PCI: qcom: Add Support for Eliza
From: Krishna Chaitanya Chundru @ 2026-05-21 14:05 UTC (permalink / raw)
To: Vinod Koul, Neil Armstrong, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Lorenzo Pieralisi, Krzysztof Wilczyński,
Manivannan Sadhasivam, Bjorn Helgaas, Bjorn Andersson
Cc: linux-arm-msm, linux-phy, devicetree, linux-kernel, linux-pci,
Krishna Chaitanya Chundru
In-Reply-To: <20260521-eliza-v1-0-97cdbe88389d@oss.qualcomm.com>
Add support for Eliza soc, which has two PCIe controllers capable
of 8GT/s X1 and 8GT/s X2, using the cfg_1_9_0 configuration.
Signed-off-by: Krishna Chaitanya Chundru <krishna.chundru@oss.qualcomm.com>
---
drivers/pci/controller/dwc/pcie-qcom.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index af6bf5cce65b..40f0a5f247eb 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -2123,6 +2123,7 @@ static int qcom_pcie_resume_noirq(struct device *dev)
static const struct of_device_id qcom_pcie_match[] = {
{ .compatible = "qcom,pcie-apq8064", .data = &cfg_2_1_0 },
{ .compatible = "qcom,pcie-apq8084", .data = &cfg_1_0_0 },
+ { .compatible = "qcom,pcie-eliza", .data = &cfg_1_9_0 },
{ .compatible = "qcom,pcie-ipq4019", .data = &cfg_2_4_0 },
{ .compatible = "qcom,pcie-ipq5018", .data = &cfg_2_9_0 },
{ .compatible = "qcom,pcie-ipq6018", .data = &cfg_2_9_0 },
--
2.34.1
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* [PATCH 2/4] dt-bindings: PCI: qcom: Document the Eliza PCIe Controller
From: Krishna Chaitanya Chundru @ 2026-05-21 14:05 UTC (permalink / raw)
To: Vinod Koul, Neil Armstrong, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Lorenzo Pieralisi, Krzysztof Wilczyński,
Manivannan Sadhasivam, Bjorn Helgaas, Bjorn Andersson
Cc: linux-arm-msm, linux-phy, devicetree, linux-kernel, linux-pci,
Krishna Chaitanya Chundru
In-Reply-To: <20260521-eliza-v1-0-97cdbe88389d@oss.qualcomm.com>
Add a dedicated schema for the PCIe root complex controller found on the
Qualcomm Eliza SoC. The controller is based on the Synopsis DesignWare PCIe
IP and requires a platform-specific set of clocks that differ from existing
Qcom PCIe schemas.
Signed-off-by: Krishna Chaitanya Chundru <krishna.chundru@oss.qualcomm.com>
---
.../devicetree/bindings/pci/qcom,pcie-eliza.yaml | 165 +++++++++++++++++++++
1 file changed, 165 insertions(+)
diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie-eliza.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie-eliza.yaml
new file mode 100644
index 000000000000..826e2adf4fda
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie-eliza.yaml
@@ -0,0 +1,165 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pci/qcom,pcie-eliza.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Qualcomm Eliza PCI Express Root Complex
+
+maintainers:
+ - Bjorn Andersson <andersson@kernel.org>
+ - Manivannan Sadhasivam <mani@kernel.org>
+
+description:
+ Qualcomm ELIZA SoC (and compatible) PCIe root complex controller is based on
+ the Synopsis DesignWare PCIe IP.
+
+properties:
+ compatible:
+ const: qcom,pcie-eliza
+
+ reg:
+ minItems: 5
+ maxItems: 6
+
+ reg-names:
+ minItems: 5
+ items:
+ - const: parf # Qualcomm specific registers
+ - const: dbi # DesignWare PCIe registers
+ - const: elbi # External local bus interface registers
+ - const: atu # ATU address space
+ - const: config # PCIe configuration space
+ - const: mhi # MHI registers
+
+ clocks:
+ maxItems: 7
+
+ clock-names:
+ items:
+ - const: aux # Auxiliary clock
+ - const: cfg # Configuration clock
+ - const: bus_master # Master AXI clock
+ - const: bus_slave # Slave AXI clock
+ - const: slave_q2a # Slave Q2A clock
+ - const: ddrss_sf_tbu # PCIe SF TBU clock
+ - const: cnoc_sf_axi # Config NoC PCIe1 AXI clock
+
+ interrupts:
+ minItems: 8
+ maxItems: 9
+
+ interrupt-names:
+ minItems: 8
+ items:
+ - const: msi0
+ - const: msi1
+ - const: msi2
+ - const: msi3
+ - const: msi4
+ - const: msi5
+ - const: msi6
+ - const: msi7
+ - const: global
+
+ resets:
+ maxItems: 2
+
+ reset-names:
+ items:
+ - const: pci # PCIe core reset
+ - const: link_down # PCIe link down reset
+
+required:
+ - power-domains
+ - resets
+ - reset-names
+
+allOf:
+ - $ref: qcom,pcie-common.yaml#
+
+unevaluatedProperties: false
+
+examples:
+ - |
+ #include <dt-bindings/clock/qcom,eliza-gcc.h>
+ #include <dt-bindings/interrupt-controller/arm-gic.h>
+ #include <dt-bindings/interconnect/qcom,eliza-rpmh.h>
+
+ soc {
+ #address-cells = <2>;
+ #size-cells = <2>;
+
+ pcie@1c00000 {
+ compatible = "qcom,pcie-eliza";
+ reg = <0 0x01c00000 0 0x3000>,
+ <0 0x40000000 0 0xf1d>,
+ <0 0x40000f20 0 0xa8>,
+ <0 0x40001000 0 0x1000>,
+ <0 0x40100000 0 0x100000>;
+ reg-names = "parf", "dbi", "elbi", "atu", "config";
+ ranges = <0x01000000 0x0 0x00000000 0x0 0x40200000 0x0 0x100000>,
+ <0x02000000 0x0 0x40300000 0x0 0x40300000 0x0 0x3d00000>;
+
+ bus-range = <0x00 0xff>;
+ device_type = "pci";
+ linux,pci-domain = <0>;
+ num-lanes = <1>;
+
+ #address-cells = <3>;
+ #size-cells = <2>;
+
+ clocks = <&gcc GCC_PCIE_0_AUX_CLK>,
+ <&gcc GCC_PCIE_0_CFG_AHB_CLK>,
+ <&gcc GCC_PCIE_0_MSTR_AXI_CLK>,
+ <&gcc GCC_PCIE_0_SLV_AXI_CLK>,
+ <&gcc GCC_PCIE_0_SLV_Q2A_AXI_CLK>,
+ <&gcc GCC_DDRSS_PCIE_SF_QTB_CLK>,
+ <&gcc GCC_CNOC_PCIE_SF_AXI_CLK>;
+ clock-names = "aux",
+ "cfg",
+ "bus_master",
+ "bus_slave",
+ "slave_q2a",
+ "ddrss_sf_tbu",
+ "cnoc_sf_axi";
+
+ dma-coherent;
+
+ interrupts = <GIC_SPI 376 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 478 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 479 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 535 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 536 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 537 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 540 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 653 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 370 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "msi0", "msi1", "msi2", "msi3",
+ "msi4", "msi5", "msi6", "msi7", "global";
+ #interrupt-cells = <1>;
+ interrupt-map-mask = <0 0 0 0x7>;
+ interrupt-map = <0 0 0 1 &intc 0 0 0 564 IRQ_TYPE_LEVEL_HIGH>, /* int_a */
+ <0 0 0 2 &intc 0 0 0 565 IRQ_TYPE_LEVEL_HIGH>, /* int_b */
+ <0 0 0 3 &intc 0 0 0 566 IRQ_TYPE_LEVEL_HIGH>, /* int_c */
+ <0 0 0 4 &intc 0 0 0 567 IRQ_TYPE_LEVEL_HIGH>; /* int_d */
+
+ interconnects = <&pcie_noc MASTER_PCIE_0 0 &mc_virt SLAVE_EBI1 0>,
+ <&gem_noc MASTER_APPSS_PROC 0 &cnoc_main SLAVE_PCIE_0 0>;
+ interconnect-names = "pcie-mem", "cpu-pcie";
+
+ iommu-map = <0x0 &apps_smmu 0x1480 0x1>,
+ <0x100 &apps_smmu 0x1481 0x1>;
+
+ pinctrl-0 = <&pcie0_default_state>;
+ pinctrl-names = "default";
+
+ power-domains = <&gcc GCC_PCIE_0_GDSC>;
+
+ resets = <&gcc GCC_PCIE_0_BCR>,
+ <&gcc GCC_PCIE_0_LINK_DOWN_BCR>;
+ reset-names = "pci",
+ "link_down";
+
+ };
+ };
--
2.34.1
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* [PATCH 1/4] dt-bindings: phy: sc8280xp-qmp-pcie: Document Eliza PCIe phy
From: Krishna Chaitanya Chundru @ 2026-05-21 14:05 UTC (permalink / raw)
To: Vinod Koul, Neil Armstrong, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Lorenzo Pieralisi, Krzysztof Wilczyński,
Manivannan Sadhasivam, Bjorn Helgaas, Bjorn Andersson
Cc: linux-arm-msm, linux-phy, devicetree, linux-kernel, linux-pci,
Krishna Chaitanya Chundru
In-Reply-To: <20260521-eliza-v1-0-97cdbe88389d@oss.qualcomm.com>
Add compatibles for the Eliza PCIe QMP PHY's, which supports Gen3x1 and
Gen3x2 configurations.
Signed-off-by: Krishna Chaitanya Chundru <krishna.chundru@oss.qualcomm.com>
---
.../devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
index 3a35120a77ec..be4bbc327982 100644
--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
+++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml
@@ -16,6 +16,8 @@ description:
properties:
compatible:
enum:
+ - qcom,eliza-qmp-gen3x1-pcie-phy
+ - qcom,eliza-qmp-gen3x2-pcie-phy
- qcom,glymur-qmp-gen4x2-pcie-phy
- qcom,glymur-qmp-gen5x4-pcie-phy
- qcom,kaanapali-qmp-gen3x2-pcie-phy
@@ -181,6 +183,8 @@ allOf:
compatible:
contains:
enum:
+ - qcom,eliza-qmp-gen3x1-pcie-phy
+ - qcom,eliza-qmp-gen3x2-pcie-phy
- qcom,glymur-qmp-gen4x2-pcie-phy
- qcom,glymur-qmp-gen5x4-pcie-phy
- qcom,qcs8300-qmp-gen4x2-pcie-phy
@@ -206,6 +210,8 @@ allOf:
compatible:
contains:
enum:
+ - qcom,eliza-qmp-gen3x1-pcie-phy
+ - qcom,eliza-qmp-gen3x2-pcie-phy
- qcom,glymur-qmp-gen4x2-pcie-phy
- qcom,glymur-qmp-gen5x4-pcie-phy
- qcom,kaanapali-qmp-gen3x2-pcie-phy
--
2.34.1
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply related
* [PATCH 0/4] PCI: qcom: Add support for Eliza
From: Krishna Chaitanya Chundru @ 2026-05-21 14:05 UTC (permalink / raw)
To: Vinod Koul, Neil Armstrong, Rob Herring, Krzysztof Kozlowski,
Conor Dooley, Lorenzo Pieralisi, Krzysztof Wilczyński,
Manivannan Sadhasivam, Bjorn Helgaas, Bjorn Andersson
Cc: linux-arm-msm, linux-phy, devicetree, linux-kernel, linux-pci,
Krishna Chaitanya Chundru
This series adds PCIe support for the Qualcomm Eliza SoC. Eliza includes
two PCIe root complex controllers capable of 8GT/s x1 and 8GT/s x2,
both using the cfg_1_9_0 configuration.
The QMP PCIe PHY support adds a new Gen3x1 PHY configuration with
Eliza-specific initialization tables, and reuses the existing SM8550
Gen3x2 configuration for the x2 PHY instance.
The series consists of:
- dt-bindings for the Eliza PCIe QMP PHY
- dt-bindings schema for the Eliza PCIe controller
- Driver entry in the Qcom PCIe controller for Eliza
- QMP PCIe PHY initialization tables and configuration for Eliza
Signed-off-by: Krishna Chaitanya Chundru <krishna.chundru@oss.qualcomm.com>
---
Krishna Chaitanya Chundru (4):
dt-bindings: phy: sc8280xp-qmp-pcie: Document Eliza PCIe phy
dt-bindings: PCI: qcom: Document the Eliza PCIe Controller
PCI: qcom: Add Support for Eliza
phy: qcom: qmp-pcie: Add QMP PCIe PHY support for Eliza
.../devicetree/bindings/pci/qcom,pcie-eliza.yaml | 165 +++++++++++++++++++++
.../bindings/phy/qcom,sc8280xp-qmp-pcie-phy.yaml | 6 +
drivers/pci/controller/dwc/pcie-qcom.c | 1 +
drivers/phy/qualcomm/phy-qcom-qmp-pcie.c | 139 +++++++++++++++++
drivers/phy/qualcomm/phy-qcom-qmp-pcs-pcie-v6.h | 1 +
5 files changed, 312 insertions(+)
---
base-commit: 254f49634ee16a731174d2ae34bc50bd5f45e731
change-id: 20260427-eliza-e53155ae8821
Best regards,
--
Krishna Chaitanya Chundru <krishna.chundru@oss.qualcomm.com>
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ permalink raw reply
* Re: [PATCH v2 2/4] PCI: qcom: Keep PERST# GPIO state as-is during probe
From: sashiko-bot @ 2026-05-21 13:43 UTC (permalink / raw)
To: Krishna Chaitanya Chundru
Cc: linux-phy, vkoul, neil.armstrong, linux-pci, olteanv
In-Reply-To: <20260521-link_retain-v2-2-08ed448b081c@oss.qualcomm.com>
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
- [High] Silent hardware control failure due to incorrect GPIO direction when using `GPIOD_ASIS`.
--
commit b4b7937282f9b2dc2dff52265ec3936b1024af9d
Author: Krishna Chaitanya Chundru <krishna.chundru@oss.qualcomm.com>
PCI: qcom: Keep PERST# GPIO state as-is during probe
This commit changes the PERST# GPIO request to use GPIOD_ASIS instead of
GPIOD_OUT_HIGH. This preserves the existing GPIO state configured by the
bootloader or firmware to avoid unintentionally asserting reset during
probe.
> diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
> index af6bf5cce65be..bfe873cbf44f6 100644
> --- a/drivers/pci/controller/dwc/pcie-qcom.c
> +++ b/drivers/pci/controller/dwc/pcie-qcom.c
> @@ -1707,7 +1707,7 @@ static int qcom_pcie_parse_perst(struct qcom_pcie *pcie,
> goto parse_child_node;
>
> reset = devm_fwnode_gpiod_get(dev, of_fwnode_handle(np), "reset",
> - GPIOD_OUT_HIGH, "PERST#");
> + GPIOD_ASIS, "PERST#");
[Severity: High]
If the bootloader leaves the PERST# pin floating or as an input, will
this cause gpiod_set_value_cansleep() to silently fail later?
When using GPIOD_ASIS, if the pin was not previously configured as an
output, GPIOD_FLAG_IS_OUT will not be set in the GPIO descriptor.
Later in qcom_pcie_host_init(), the driver attempts to toggle the reset
pin by calling gpiod_set_value_cansleep() via __qcom_pcie_perst_assert().
Because gpiod_set_value_cansleep() enforces directionality, it will
return -EPERM if the pin is not configured as an output. Since
__qcom_pcie_perst_assert() ignores the return value of
gpiod_set_value_cansleep(), the reset line might never actually be driven.
Could this break PCIe link initialization on platforms where the
bootloader hasn't set the GPIO direction to output?
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260521-link_retain-v2-0-08ed448b081c@oss.qualcomm.com?part=2
--
linux-phy mailing list
linux-phy@lists.infradead.org
https://lists.infradead.org/mailman/listinfo/linux-phy
^ 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