diff mbox series

[v9,8/9] thermal: Add PCIe cooling driver

Message ID 20241018144755.7875-9-ilpo.jarvinen@linux.intel.com (mailing list archive)
State Accepted
Delegated to: Bjorn Helgaas
Headers show
Series PCI: Add PCIe bandwidth controller | expand

Commit Message

Ilpo Järvinen Oct. 18, 2024, 2:47 p.m. UTC
Add a thermal cooling driver to provide path to access PCIe bandwidth
controller using the usual thermal interfaces.

A cooling device is instantiated for controllable PCIe Ports from the
bwctrl service driver.

If registering the cooling device fails, allow bwctrl's probe to
succeed regardless. As cdev in that case contains IS_ERR() pseudo
"pointer", clean that up inside the probe function so the remove side
doesn't need to suddenly make an odd looking IS_ERR() check.

The thermal side state 0 means no throttling, i.e., maximum supported
PCIe Link Speed.

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Rafael J. Wysocki <rafael@kernel.org> # From the cooling device interface perspective
---
 MAINTAINERS                    |  2 +
 drivers/pci/pcie/bwctrl.c      | 13 ++++++
 drivers/thermal/Kconfig        |  9 ++++
 drivers/thermal/Makefile       |  2 +
 drivers/thermal/pcie_cooling.c | 80 ++++++++++++++++++++++++++++++++++
 include/linux/pci-bwctrl.h     | 28 ++++++++++++
 6 files changed, 134 insertions(+)
 create mode 100644 drivers/thermal/pcie_cooling.c
 create mode 100644 include/linux/pci-bwctrl.h

Comments

Lukas Wunner Nov. 13, 2024, 8:44 a.m. UTC | #1
On Fri, Oct 18, 2024 at 05:47:54PM +0300, Ilpo Järvinen wrote:
>  static void pcie_bwnotif_remove(struct pcie_device *srv)
>  {
> +	struct pcie_bwctrl_data *data = srv->port->link_bwctrl;
> +
> +	if (data->cdev)
> +		pcie_cooling_device_unregister(data->cdev);
> +

Just noting a minor nit here in what is now commit 7206400cda87
on pci/bwctrl:  The NULL pointer check for data->cdev seems
redundant as pcie_cooling_device_unregister() just calls
thermal_cooling_device_unregister(), which in turn contains
this at the top:

	if (!cdev)
		return;

Thanks,

Lukas
Bjorn Helgaas Nov. 15, 2024, 5:28 p.m. UTC | #2
On Wed, Nov 13, 2024 at 09:44:05AM +0100, Lukas Wunner wrote:
> On Fri, Oct 18, 2024 at 05:47:54PM +0300, Ilpo Järvinen wrote:
> >  static void pcie_bwnotif_remove(struct pcie_device *srv)
> >  {
> > +	struct pcie_bwctrl_data *data = srv->port->link_bwctrl;
> > +
> > +	if (data->cdev)
> > +		pcie_cooling_device_unregister(data->cdev);
> > +
> 
> Just noting a minor nit here in what is now commit 7206400cda87
> on pci/bwctrl:  The NULL pointer check for data->cdev seems
> redundant as pcie_cooling_device_unregister() just calls
> thermal_cooling_device_unregister(), which in turn contains
> this at the top:
> 
> 	if (!cdev)
> 		return;

Thanks, I dropped this NULL pointer check locally.
diff mbox series

Patch

diff --git a/MAINTAINERS b/MAINTAINERS
index 8c555b3325d6..393ed7ce5ea1 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17938,6 +17938,8 @@  M:	Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
 L:	linux-pci@vger.kernel.org
 S:	Supported
 F:	drivers/pci/pcie/bwctrl.c
+F:	drivers/thermal/pcie_cooling.c
+F:	include/linux/pci-bwctrl.h
 
 PCIE DRIVER FOR AMAZON ANNAPURNA LABS
 M:	Jonathan Chocron <jonnyc@amazon.com>
diff --git a/drivers/pci/pcie/bwctrl.c b/drivers/pci/pcie/bwctrl.c
index 8a2bd1e887e2..d00675e33ad9 100644
--- a/drivers/pci/pcie/bwctrl.c
+++ b/drivers/pci/pcie/bwctrl.c
@@ -27,6 +27,7 @@ 
 #include <linux/interrupt.h>
 #include <linux/mutex.h>
 #include <linux/pci.h>
+#include <linux/pci-bwctrl.h>
 #include <linux/rwsem.h>
 #include <linux/slab.h>
 #include <linux/types.h>
@@ -38,10 +39,12 @@ 
  * struct pcie_bwctrl_data - PCIe bandwidth controller
  * @set_speed_mutex:	Serializes link speed changes
  * @lbms_count:		Count for LBMS (since last reset)
+ * @cdev:		thermal cooling device associated with the port
  */
 struct pcie_bwctrl_data {
 	struct mutex set_speed_mutex;
 	atomic_t lbms_count;
+	struct thermal_cooling_device *cdev;
 };
 
 /*
@@ -313,11 +316,21 @@  static int pcie_bwnotif_probe(struct pcie_device *srv)
 
 	pci_dbg(port, "enabled with IRQ %d\n", srv->irq);
 
+	/* Don't fail on errors. Don't leave IS_ERR() "pointer" into ->cdev */
+	port->link_bwctrl->cdev = pcie_cooling_device_register(port);
+	if (IS_ERR(port->link_bwctrl->cdev))
+		port->link_bwctrl->cdev = NULL;
+
 	return 0;
 }
 
 static void pcie_bwnotif_remove(struct pcie_device *srv)
 {
+	struct pcie_bwctrl_data *data = srv->port->link_bwctrl;
+
+	if (data->cdev)
+		pcie_cooling_device_unregister(data->cdev);
+
 	pcie_bwnotif_disable(srv->port);
 
 	scoped_guard(rwsem_write, &pcie_bwctrl_setspeed_rwsem)
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index 61e7ae524b1f..d3f9686e26e7 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -220,6 +220,15 @@  config DEVFREQ_THERMAL
 
 	  If you want this support, you should say Y here.
 
+config PCIE_THERMAL
+	bool "PCIe cooling support"
+	depends on PCIEPORTBUS
+	help
+	  This implements PCIe cooling mechanism through bandwidth reduction
+	  for PCIe devices.
+
+	  If you want this support, you should say Y here.
+
 config THERMAL_EMULATION
 	bool "Thermal emulation mode support"
 	help
diff --git a/drivers/thermal/Makefile b/drivers/thermal/Makefile
index 41c4d56beb40..210c16c91461 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -31,6 +31,8 @@  thermal_sys-$(CONFIG_CPU_IDLE_THERMAL)	+= cpuidle_cooling.o
 # devfreq cooling
 thermal_sys-$(CONFIG_DEVFREQ_THERMAL) += devfreq_cooling.o
 
+thermal_sys-$(CONFIG_PCIE_THERMAL) += pcie_cooling.o
+
 obj-$(CONFIG_K3_THERMAL)	+= k3_bandgap.o k3_j72xx_bandgap.o
 # platform thermal drivers
 obj-y				+= broadcom/
diff --git a/drivers/thermal/pcie_cooling.c b/drivers/thermal/pcie_cooling.c
new file mode 100644
index 000000000000..a876d64f1582
--- /dev/null
+++ b/drivers/thermal/pcie_cooling.c
@@ -0,0 +1,80 @@ 
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * PCIe cooling device
+ *
+ * Copyright (C) 2023-2024 Intel Corporation
+ */
+
+#include <linux/build_bug.h>
+#include <linux/cleanup.h>
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/pci-bwctrl.h>
+#include <linux/slab.h>
+#include <linux/sprintf.h>
+#include <linux/thermal.h>
+
+#define COOLING_DEV_TYPE_PREFIX		"PCIe_Port_Link_Speed_"
+
+static int pcie_cooling_get_max_level(struct thermal_cooling_device *cdev, unsigned long *state)
+{
+	struct pci_dev *port = cdev->devdata;
+
+	/* cooling state 0 is same as the maximum PCIe speed */
+	*state = port->subordinate->max_bus_speed - PCIE_SPEED_2_5GT;
+
+	return 0;
+}
+
+static int pcie_cooling_get_cur_level(struct thermal_cooling_device *cdev, unsigned long *state)
+{
+	struct pci_dev *port = cdev->devdata;
+
+	/* cooling state 0 is same as the maximum PCIe speed */
+	*state = cdev->max_state - (port->subordinate->cur_bus_speed - PCIE_SPEED_2_5GT);
+
+	return 0;
+}
+
+static int pcie_cooling_set_cur_level(struct thermal_cooling_device *cdev, unsigned long state)
+{
+	struct pci_dev *port = cdev->devdata;
+	enum pci_bus_speed speed;
+
+	/* cooling state 0 is same as the maximum PCIe speed */
+	speed = (cdev->max_state - state) + PCIE_SPEED_2_5GT;
+
+	return pcie_set_target_speed(port, speed, true);
+}
+
+static struct thermal_cooling_device_ops pcie_cooling_ops = {
+	.get_max_state = pcie_cooling_get_max_level,
+	.get_cur_state = pcie_cooling_get_cur_level,
+	.set_cur_state = pcie_cooling_set_cur_level,
+};
+
+struct thermal_cooling_device *pcie_cooling_device_register(struct pci_dev *port)
+{
+	char *name __free(kfree) =
+		kasprintf(GFP_KERNEL, COOLING_DEV_TYPE_PREFIX "%s", pci_name(port));
+	if (!name)
+		return ERR_PTR(-ENOMEM);
+
+	return thermal_cooling_device_register(name, port, &pcie_cooling_ops);
+}
+
+void pcie_cooling_device_unregister(struct thermal_cooling_device *cdev)
+{
+	thermal_cooling_device_unregister(cdev);
+}
+
+/* For bus_speed <-> state arithmetic */
+static_assert(PCIE_SPEED_2_5GT + 1 == PCIE_SPEED_5_0GT);
+static_assert(PCIE_SPEED_5_0GT + 1 == PCIE_SPEED_8_0GT);
+static_assert(PCIE_SPEED_8_0GT + 1 == PCIE_SPEED_16_0GT);
+static_assert(PCIE_SPEED_16_0GT + 1 == PCIE_SPEED_32_0GT);
+static_assert(PCIE_SPEED_32_0GT + 1 == PCIE_SPEED_64_0GT);
+
+MODULE_AUTHOR("Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>");
+MODULE_DESCRIPTION("PCIe cooling driver");
diff --git a/include/linux/pci-bwctrl.h b/include/linux/pci-bwctrl.h
new file mode 100644
index 000000000000..cee07127455b
--- /dev/null
+++ b/include/linux/pci-bwctrl.h
@@ -0,0 +1,28 @@ 
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * PCIe bandwidth controller
+ *
+ * Copyright (C) 2023-2024 Intel Corporation
+ */
+
+#ifndef LINUX_PCI_BWCTRL_H
+#define LINUX_PCI_BWCTRL_H
+
+#include <linux/pci.h>
+
+struct thermal_cooling_device;
+
+#ifdef CONFIG_PCIE_THERMAL
+struct thermal_cooling_device *pcie_cooling_device_register(struct pci_dev *port);
+void pcie_cooling_device_unregister(struct thermal_cooling_device *cdev);
+#else
+static inline struct thermal_cooling_device *pcie_cooling_device_register(struct pci_dev *port)
+{
+	return NULL;
+}
+static inline void pcie_cooling_device_unregister(struct thermal_cooling_device *cdev)
+{
+}
+#endif
+
+#endif