thermal: Add PCIe cooling driver

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.

Link: https://lore.kernel.org/r/20241018144755.7875-9-ilpo.jarvinen@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
[bhelgaas: dropped data->cdev test per
https://lore.kernel.org/r/ZzRm1SJTwEMRsAr8@wunner.de]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Acked-by: Rafael J. Wysocki <rafael@kernel.org> # From the cooling device interface perspective

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>

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;
 };
 
 /*
@@ -314,11 +317,20 @@ 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;
+
+	pcie_cooling_device_unregister(data->cdev);
+
 	pcie_bwnotif_disable(srv->port);
 
 	scoped_guard(rwsem_write, &pcie_bwctrl_setspeed_rwsem)

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

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/

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");

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