* [PATCH v3 0/3] PCI: ultrarisc: Add DP1000 PCIe clock support
@ 2026-07-14 1:11 Jia Wang via B4 Relay
2026-07-14 1:11 ` [PATCH v3 1/3] dt-bindings: pci: ultrarisc: add required DP1000 PCIe clocks Jia Wang via B4 Relay
` (2 more replies)
0 siblings, 3 replies; 7+ messages in thread
From: Jia Wang via B4 Relay @ 2026-07-14 1:11 UTC (permalink / raw)
To: Xincheng Zhang, Lorenzo Pieralisi, Krzysztof Wilczyński,
Manivannan Sadhasivam, Rob Herring, Bjorn Helgaas,
Krzysztof Kozlowski, Conor Dooley
Cc: linux-pci, devicetree, linux-kernel, Jia Wang,
Krzysztof Kozlowski, Conor Dooley
Add clock handling for the UltraRISC DP1000 DesignWare PCIe host
controller.
The DP1000 PCIe controller depends on three input clocks: core, dbi, and
aux. The driver accesses DBI registers during host initialization, so the
clocks must be enabled before the controller registers are touched.
This series documents the required clocks in the device tree binding,
enables the core, dbi, and aux clocks before DesignWare host
initialization, and keeps them managed across probe failure, detach, and
system suspend/resume. It also switches the driver to
module_platform_driver() so the existing tristate Kconfig option builds
correctly as a module.
Testing:
- Build and module build tested with ARCH=riscv.
- Boot tested on UltraRISC DP1000.
- Validated the PCIe binding with dt_binding_check and dtbs_check.
Signed-off-by: Jia Wang <wangjia@ultrarisc.com>
---
Changes in v3:
- Track whether the PCIe clocks are enabled and make clock enable/disable
helpers idempotent.
- Skip dw_pcie_suspend_noirq() when the controller is already suspended to
avoid register access with clocks disabled after a failed resume.
- Disable clocks again if dw_pcie_resume_noirq() fails after clocks were
re-enabled.
- Add a remove callback to deinitialize the DesignWare host when the module
build support is added.
- Link to v2: https://patch.msgid.link/20260706-ultrarisc-pci-clk-v2-0-2f3fb6fba66b@ultrarisc.com
Changes in v2:
- Add Fixes and Acked-by tags to the binding patch.
- Add a Fixes tag to the driver clock handling patch.
- Fix the suspend/resume clock handling so clocks are disabled only after a
successful suspend and kept enabled on resume failure.
- Add a module build fix by switching to module_platform_driver().
- Link to v1: https://patch.msgid.link/20260629-ultrarisc-pci-clk-v1-0-5ea3308fdab3@ultrarisc.com
To: Xincheng Zhang <zhangxincheng@ultrarisc.com>
To: Jia Wang <wangjia@ultrarisc.com>
To: Lorenzo Pieralisi <lpieralisi@kernel.org>
To: Krzysztof Wilczyński <kwilczynski@kernel.org>
To: Manivannan Sadhasivam <mani@kernel.org>
To: Rob Herring <robh@kernel.org>
To: Bjorn Helgaas <bhelgaas@google.com>
To: Krzysztof Kozlowski <krzk+dt@kernel.org>
To: Conor Dooley <conor+dt@kernel.org>
Cc: Krzysztof Kozlowski <krzysztof.kozlowski@oss.qualcomm.com>
Cc: linux-pci@vger.kernel.org
Cc: devicetree@vger.kernel.org
Cc: linux-kernel@vger.kernel.org
---
Jia Wang (3):
dt-bindings: pci: ultrarisc: add required DP1000 PCIe clocks
PCI: ultrarisc: get and enable DP1000 PCIe clocks
PCI: ultrarisc: allow DP1000 driver to build as module
.../bindings/pci/ultrarisc,dp1000-pcie.yaml | 16 +++
drivers/pci/controller/dwc/pcie-ultrarisc.c | 112 +++++++++++++++++++--
2 files changed, 120 insertions(+), 8 deletions(-)
---
base-commit: a13c140cc289c0b7b3770bce5b3ad42ab35074aa
change-id: 20260617-ultrarisc-pci-clk-ac19047af1ea
Best regards,
--
Jia Wang <wangjia@ultrarisc.com>
^ permalink raw reply [flat|nested] 7+ messages in thread
* [PATCH v3 1/3] dt-bindings: pci: ultrarisc: add required DP1000 PCIe clocks
2026-07-14 1:11 [PATCH v3 0/3] PCI: ultrarisc: Add DP1000 PCIe clock support Jia Wang via B4 Relay
@ 2026-07-14 1:11 ` Jia Wang via B4 Relay
2026-07-14 1:24 ` sashiko-bot
2026-07-14 1:11 ` [PATCH v3 2/3] PCI: ultrarisc: get and enable " Jia Wang via B4 Relay
2026-07-14 1:11 ` [PATCH v3 3/3] PCI: ultrarisc: allow DP1000 driver to build as module Jia Wang via B4 Relay
2 siblings, 1 reply; 7+ messages in thread
From: Jia Wang via B4 Relay @ 2026-07-14 1:11 UTC (permalink / raw)
To: Xincheng Zhang, Lorenzo Pieralisi, Krzysztof Wilczyński,
Manivannan Sadhasivam, Rob Herring, Bjorn Helgaas,
Krzysztof Kozlowski, Conor Dooley
Cc: linux-pci, devicetree, linux-kernel, Jia Wang,
Krzysztof Kozlowski, Conor Dooley
From: Jia Wang <wangjia@ultrarisc.com>
Require the DP1000 PCIe controller nodes to provide clocks and
clock-names, using the standard DesignWare clock names "core",
"dbi", and "aux".
Fixes: d9ff07f45955 ("dt-bindings: PCI: Add UltraRISC DP1000 PCIe controller")
Signed-off-by: Jia Wang <wangjia@ultrarisc.com>
Acked-by: Conor Dooley <conor.dooley@microchip.com>
---
.../devicetree/bindings/pci/ultrarisc,dp1000-pcie.yaml | 16 ++++++++++++++++
1 file changed, 16 insertions(+)
diff --git a/Documentation/devicetree/bindings/pci/ultrarisc,dp1000-pcie.yaml b/Documentation/devicetree/bindings/pci/ultrarisc,dp1000-pcie.yaml
index 512b935bf5d1..d9d1488e915a 100644
--- a/Documentation/devicetree/bindings/pci/ultrarisc,dp1000-pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/ultrarisc,dp1000-pcie.yaml
@@ -43,6 +43,18 @@ properties:
- description: Legacy INTC interrupt
- description: Legacy INTD interrupt
+ clocks:
+ items:
+ - description: PCIe core clock
+ - description: Data Bus Interface (DBI) clock
+ - description: Auxiliary clock
+
+ clock-names:
+ items:
+ - const: core
+ - const: dbi
+ - const: aux
+
interrupt-names:
items:
- const: msi
@@ -55,6 +67,8 @@ required:
- compatible
- reg
- reg-names
+ - clocks
+ - clock-names
- interrupts
- interrupt-names
@@ -71,6 +85,8 @@ examples:
reg = <0x0 0x21000000 0x0 0x01000000>,
<0x0 0x4fff0000 0x0 0x00010000>;
reg-names = "dbi", "config";
+ clocks = <&clkc 9>, <&clkc 7>, <&clkc 10>;
+ clock-names = "core", "dbi", "aux";
ranges = <0x81000000 0x0 0x4fbf0000 0x0 0x4fbf0000 0x0 0x00400000>,
<0x82000000 0x0 0x40000000 0x0 0x40000000 0x0 0x0fbf0000>,
<0xc3000000 0x40 0x00000000 0x40 0x00000000 0xd 0x00000000>;
--
2.34.1
^ permalink raw reply related [flat|nested] 7+ messages in thread
* [PATCH v3 2/3] PCI: ultrarisc: get and enable DP1000 PCIe clocks
2026-07-14 1:11 [PATCH v3 0/3] PCI: ultrarisc: Add DP1000 PCIe clock support Jia Wang via B4 Relay
2026-07-14 1:11 ` [PATCH v3 1/3] dt-bindings: pci: ultrarisc: add required DP1000 PCIe clocks Jia Wang via B4 Relay
@ 2026-07-14 1:11 ` Jia Wang via B4 Relay
2026-07-14 1:18 ` sashiko-bot
2026-07-14 1:11 ` [PATCH v3 3/3] PCI: ultrarisc: allow DP1000 driver to build as module Jia Wang via B4 Relay
2 siblings, 1 reply; 7+ messages in thread
From: Jia Wang via B4 Relay @ 2026-07-14 1:11 UTC (permalink / raw)
To: Xincheng Zhang, Lorenzo Pieralisi, Krzysztof Wilczyński,
Manivannan Sadhasivam, Rob Herring, Bjorn Helgaas,
Krzysztof Kozlowski, Conor Dooley
Cc: linux-pci, devicetree, linux-kernel, Jia Wang,
Krzysztof Kozlowski
From: Jia Wang <wangjia@ultrarisc.com>
Add the required core, dbi, and aux clocks for the DP1000 PCIe
controller and enable them before initializing the DesignWare host.
Also manage the clocks across system suspend and resume.
Fixes: 5fc35740c3b3 ("PCI: ultrarisc: Add UltraRISC DP1000 PCIe Root Complex driver")
Signed-off-by: Jia Wang <wangjia@ultrarisc.com>
---
drivers/pci/controller/dwc/pcie-ultrarisc.c | 102 ++++++++++++++++++++++++++--
1 file changed, 95 insertions(+), 7 deletions(-)
diff --git a/drivers/pci/controller/dwc/pcie-ultrarisc.c b/drivers/pci/controller/dwc/pcie-ultrarisc.c
index 6ee661ceff67..72ba5840b62d 100644
--- a/drivers/pci/controller/dwc/pcie-ultrarisc.c
+++ b/drivers/pci/controller/dwc/pcie-ultrarisc.c
@@ -5,6 +5,7 @@
* Copyright (C) 2026 UltraRISC Technology (Shanghai) Co., Ltd.
*/
+#include <linux/clk.h>
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/of_device.h>
@@ -23,6 +24,12 @@
#define ULTRARISC_PCIE_COMP_TIMEOUT_65_210MS 0x6
+struct ultrarisc_pcie {
+ struct dw_pcie pci;
+ struct clk_bulk_data clks[3];
+ bool clks_enabled;
+};
+
static struct pci_ops ultrarisc_pci_ops = {
.map_bus = dw_pcie_own_conf_map_bus,
.read = pci_generic_config_read32,
@@ -98,17 +105,66 @@ static const struct dw_pcie_ops dw_pcie_ops = {
.start_link = ultrarisc_pcie_start_link,
};
+static int ultrarisc_pcie_enable_clks(struct ultrarisc_pcie *ultra)
+{
+ int ret;
+
+ if (ultra->clks_enabled)
+ return 0;
+
+ ret = clk_bulk_prepare_enable(ARRAY_SIZE(ultra->clks), ultra->clks);
+ if (ret)
+ return ret;
+
+ ultra->clks_enabled = true;
+
+ return 0;
+}
+
+static void ultrarisc_pcie_disable_clks(void *data)
+{
+ struct ultrarisc_pcie *ultra = data;
+
+ if (!ultra->clks_enabled)
+ return;
+
+ clk_bulk_disable_unprepare(ARRAY_SIZE(ultra->clks), ultra->clks);
+ ultra->clks_enabled = false;
+}
+
+static int ultrarisc_pcie_init_clks(struct ultrarisc_pcie *ultra)
+{
+ struct device *dev = ultra->pci.dev;
+ int ret;
+
+ ultra->clks[0].id = "core";
+ ultra->clks[1].id = "dbi";
+ ultra->clks[2].id = "aux";
+
+ ret = devm_clk_bulk_get(dev, ARRAY_SIZE(ultra->clks), ultra->clks);
+ if (ret)
+ return dev_err_probe(dev, ret, "Failed to get clocks\n");
+
+ ret = ultrarisc_pcie_enable_clks(ultra);
+ if (ret)
+ return dev_err_probe(dev, ret, "Failed to enable clocks\n");
+
+ return devm_add_action_or_reset(dev, ultrarisc_pcie_disable_clks, ultra);
+}
+
static int ultrarisc_pcie_probe(struct platform_device *pdev)
{
+ struct ultrarisc_pcie *ultra;
struct device *dev = &pdev->dev;
struct dw_pcie_rp *pp;
struct dw_pcie *pci;
int ret;
- pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL);
- if (!pci)
+ ultra = devm_kzalloc(dev, sizeof(*ultra), GFP_KERNEL);
+ if (!ultra)
return -ENOMEM;
+ pci = &ultra->pci;
pci->dev = dev;
pci->ops = &dw_pcie_ops;
@@ -117,7 +173,11 @@ static int ultrarisc_pcie_probe(struct platform_device *pdev)
pp = &pci->pp;
- platform_set_drvdata(pdev, pci);
+ platform_set_drvdata(pdev, ultra);
+
+ ret = ultrarisc_pcie_init_clks(ultra);
+ if (ret)
+ return ret;
pp->num_vectors = MAX_MSI_IRQS;
/* No L2/L3 Ready indication is available on this platform */
@@ -135,16 +195,44 @@ static int ultrarisc_pcie_probe(struct platform_device *pdev)
static int ultrarisc_pcie_suspend_noirq(struct device *dev)
{
- struct dw_pcie *pci = dev_get_drvdata(dev);
+ struct ultrarisc_pcie *ultra = dev_get_drvdata(dev);
+ struct dw_pcie *pci = &ultra->pci;
+ int ret;
+
+ if (pci->suspended) {
+ ultrarisc_pcie_disable_clks(ultra);
+ return 0;
+ }
+
+ ret = dw_pcie_suspend_noirq(pci);
+ if (ret)
+ return ret;
- return dw_pcie_suspend_noirq(pci);
+ if (pci->suspended)
+ ultrarisc_pcie_disable_clks(ultra);
+
+ return 0;
}
static int ultrarisc_pcie_resume_noirq(struct device *dev)
{
- struct dw_pcie *pci = dev_get_drvdata(dev);
+ struct ultrarisc_pcie *ultra = dev_get_drvdata(dev);
+ struct dw_pcie *pci = &ultra->pci;
+ int ret;
+
+ if (pci->suspended) {
+ ret = ultrarisc_pcie_enable_clks(ultra);
+ if (ret)
+ return ret;
- return dw_pcie_resume_noirq(pci);
+ ret = dw_pcie_resume_noirq(pci);
+ if (ret) {
+ ultrarisc_pcie_disable_clks(ultra);
+ return ret;
+ }
+ }
+
+ return 0;
}
static const struct dev_pm_ops ultrarisc_pcie_pm_ops = {
--
2.34.1
^ permalink raw reply related [flat|nested] 7+ messages in thread
* [PATCH v3 3/3] PCI: ultrarisc: allow DP1000 driver to build as module
2026-07-14 1:11 [PATCH v3 0/3] PCI: ultrarisc: Add DP1000 PCIe clock support Jia Wang via B4 Relay
2026-07-14 1:11 ` [PATCH v3 1/3] dt-bindings: pci: ultrarisc: add required DP1000 PCIe clocks Jia Wang via B4 Relay
2026-07-14 1:11 ` [PATCH v3 2/3] PCI: ultrarisc: get and enable " Jia Wang via B4 Relay
@ 2026-07-14 1:11 ` Jia Wang via B4 Relay
2026-07-14 1:15 ` sashiko-bot
2 siblings, 1 reply; 7+ messages in thread
From: Jia Wang via B4 Relay @ 2026-07-14 1:11 UTC (permalink / raw)
To: Xincheng Zhang, Lorenzo Pieralisi, Krzysztof Wilczyński,
Manivannan Sadhasivam, Rob Herring, Bjorn Helgaas,
Krzysztof Kozlowski, Conor Dooley
Cc: linux-pci, devicetree, linux-kernel, Jia Wang,
Krzysztof Kozlowski
From: Jia Wang <wangjia@ultrarisc.com>
CONFIG_PCIE_ULTRARISC is a tristate option, so the driver can be selected
as a module when COMPILE_TEST or platform configuration allows it. Using
builtin_platform_driver() leaves the module build without the module
init/exit plumbing and causes modpost failures for the generated .ko.
Use module_platform_driver() so the driver works for both module and
built-in builds while keeping the existing tristate Kconfig entry.
Add a remove callback and call dw_pcie_host_deinit() during removal so the
root bus is torn down before devres releases the controller data.
Fixes: 5fc35740c3b3 ("PCI: ultrarisc: Add UltraRISC DP1000 PCIe Root Complex driver")
Signed-off-by: Jia Wang <wangjia@ultrarisc.com>
---
drivers/pci/controller/dwc/pcie-ultrarisc.c | 10 +++++++++-
1 file changed, 9 insertions(+), 1 deletion(-)
diff --git a/drivers/pci/controller/dwc/pcie-ultrarisc.c b/drivers/pci/controller/dwc/pcie-ultrarisc.c
index 72ba5840b62d..9bee522a20e9 100644
--- a/drivers/pci/controller/dwc/pcie-ultrarisc.c
+++ b/drivers/pci/controller/dwc/pcie-ultrarisc.c
@@ -193,6 +193,13 @@ static int ultrarisc_pcie_probe(struct platform_device *pdev)
return 0;
}
+static void ultrarisc_pcie_remove(struct platform_device *pdev)
+{
+ struct ultrarisc_pcie *ultra = platform_get_drvdata(pdev);
+
+ dw_pcie_host_deinit(&ultra->pci.pp);
+}
+
static int ultrarisc_pcie_suspend_noirq(struct device *dev)
{
struct ultrarisc_pcie *ultra = dev_get_drvdata(dev);
@@ -256,8 +263,9 @@ static struct platform_driver ultrarisc_pcie_driver = {
.pm = &ultrarisc_pcie_pm_ops,
},
.probe = ultrarisc_pcie_probe,
+ .remove = ultrarisc_pcie_remove,
};
-builtin_platform_driver(ultrarisc_pcie_driver);
+module_platform_driver(ultrarisc_pcie_driver);
MODULE_DESCRIPTION("UltraRISC DP1000 DWC PCIe host controller");
MODULE_LICENSE("GPL");
--
2.34.1
^ permalink raw reply related [flat|nested] 7+ messages in thread
* Re: [PATCH v3 3/3] PCI: ultrarisc: allow DP1000 driver to build as module
2026-07-14 1:11 ` [PATCH v3 3/3] PCI: ultrarisc: allow DP1000 driver to build as module Jia Wang via B4 Relay
@ 2026-07-14 1:15 ` sashiko-bot
0 siblings, 0 replies; 7+ messages in thread
From: sashiko-bot @ 2026-07-14 1:15 UTC (permalink / raw)
To: Jia Wang; +Cc: robh, linux-pci, devicetree, conor+dt
> From: Jia Wang <wangjia@ultrarisc.com>
>
> CONFIG_PCIE_ULTRARISC is a tristate option, so the driver can be selected
> as a module when COMPILE_TEST or platform configuration allows it. Using
> builtin_platform_driver() leaves the module build without the module
> init/exit plumbing and causes modpost failures for the generated .ko.
>
> Use module_platform_driver() so the driver works for both module and
> built-in builds while keeping the existing tristate Kconfig entry.
>
> Add a remove callback and call dw_pcie_host_deinit() during removal so the
> root bus is torn down before devres releases the controller data.
>
> Fixes: 5fc35740c3b3 ("PCI: ultrarisc: Add UltraRISC DP1000 PCIe Root Complex driver")
> Signed-off-by: Jia Wang <wangjia@ultrarisc.com>
Sashiko has reviewed this patch and found no issues. It looks great!
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260714-ultrarisc-pci-clk-v3-0-e72723fc0ef1@ultrarisc.com?part=3
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH v3 2/3] PCI: ultrarisc: get and enable DP1000 PCIe clocks
2026-07-14 1:11 ` [PATCH v3 2/3] PCI: ultrarisc: get and enable " Jia Wang via B4 Relay
@ 2026-07-14 1:18 ` sashiko-bot
0 siblings, 0 replies; 7+ messages in thread
From: sashiko-bot @ 2026-07-14 1:18 UTC (permalink / raw)
To: Jia Wang; +Cc: conor+dt, robh, devicetree, linux-pci
> From: Jia Wang <wangjia@ultrarisc.com>
>
> Add the required core, dbi, and aux clocks for the DP1000 PCIe
> controller and enable them before initializing the DesignWare host.
>
> Also manage the clocks across system suspend and resume.
>
> Fixes: 5fc35740c3b3 ("PCI: ultrarisc: Add UltraRISC DP1000 PCIe Root Complex driver")
> Signed-off-by: Jia Wang <wangjia@ultrarisc.com>
Sashiko has reviewed this patch and found no issues. It looks great!
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260714-ultrarisc-pci-clk-v3-0-e72723fc0ef1@ultrarisc.com?part=2
^ permalink raw reply [flat|nested] 7+ messages in thread
* Re: [PATCH v3 1/3] dt-bindings: pci: ultrarisc: add required DP1000 PCIe clocks
2026-07-14 1:11 ` [PATCH v3 1/3] dt-bindings: pci: ultrarisc: add required DP1000 PCIe clocks Jia Wang via B4 Relay
@ 2026-07-14 1:24 ` sashiko-bot
0 siblings, 0 replies; 7+ messages in thread
From: sashiko-bot @ 2026-07-14 1:24 UTC (permalink / raw)
To: Jia Wang; +Cc: conor+dt, robh, devicetree, linux-pci
Thank you for your contribution! Sashiko AI review found 1 potential issue(s) to consider:
Pre-existing issues:
- [High] Missing driver clock management. The DP1000 PCIe driver fails to implement support for the newly mandated `core`, `dbi`, and `aux` clocks, leading to unclocked hardware register accesses.
--
--- Patch [1]: [PATCH v3 1/3] dt-bindings: pci: ultrarisc: add required DP1000 PCIe clocks ---
commit 04ce10fff5fc6c7c7dc6e7380ab1ae6a1209bb14
Author: Jia Wang <wangjia@ultrarisc.com>
dt-bindings: pci: ultrarisc: add required DP1000 PCIe clocks
This commit mandates that DP1000 PCIe controller nodes provide the standard
DesignWare clock names "core", "dbi", and "aux" in the device tree bindings.
> diff --git a/Documentation/devicetree/bindings/pci/ultrarisc,dp1000-pcie.yaml b/Documentation/devicetree/bindings/pci/ultrarisc,dp1000-pcie.yaml
> --- a/Documentation/devicetree/bindings/pci/ultrarisc,dp1000-pcie.yaml
> +++ b/Documentation/devicetree/bindings/pci/ultrarisc,dp1000-pcie.yaml
> @@ -43,6 +43,18 @@ properties:
[ ... ]
> + clocks:
> + items:
> + - description: PCIe core clock
> + - description: Data Bus Interface (DBI) clock
> + - description: Auxiliary clock
> +
> + clock-names:
> + items:
> + - const: core
> + - const: dbi
> + - const: aux
[Severity: High]
This is a pre-existing issue, but since these clocks are now formally required
by the binding, does the pcie-ultrarisc driver also need to be updated to
manage them?
Looking at drivers/pci/controller/dwc/pcie-ultrarisc.c, ultrarisc_pcie_probe()
does not appear to fetch or enable these clocks. Because of this, hardware
registers are accessed before clocks are explicitly enabled by the driver:
drivers/pci/controller/dwc/pcie-ultrarisc.c:ultrarisc_pcie_host_init() {
...
val = dw_pcie_readl_dbi(pci, PCIE_CUS_CORE);
...
}
Will this unclocked hardware register access trigger a synchronous bus error
and kernel panic during the device probe path on boot?
--
Sashiko AI review · https://sashiko.dev/#/patchset/20260714-ultrarisc-pci-clk-v3-0-e72723fc0ef1@ultrarisc.com?part=1
^ permalink raw reply [flat|nested] 7+ messages in thread
end of thread, other threads:[~2026-07-14 1:24 UTC | newest]
Thread overview: 7+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2026-07-14 1:11 [PATCH v3 0/3] PCI: ultrarisc: Add DP1000 PCIe clock support Jia Wang via B4 Relay
2026-07-14 1:11 ` [PATCH v3 1/3] dt-bindings: pci: ultrarisc: add required DP1000 PCIe clocks Jia Wang via B4 Relay
2026-07-14 1:24 ` sashiko-bot
2026-07-14 1:11 ` [PATCH v3 2/3] PCI: ultrarisc: get and enable " Jia Wang via B4 Relay
2026-07-14 1:18 ` sashiko-bot
2026-07-14 1:11 ` [PATCH v3 3/3] PCI: ultrarisc: allow DP1000 driver to build as module Jia Wang via B4 Relay
2026-07-14 1:15 ` sashiko-bot
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox