[PATCH 09/10] thermal: Add PCIe cooling driver

["Ilpo Järvinen" <ilpo.jarvinen@linux.intel.com>]

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.

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

Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 MAINTAINERS                    |   1 +
 drivers/pci/pcie/bwctrl.c      |  11 ++++
 drivers/thermal/Kconfig        |  10 +++
 drivers/thermal/Makefile       |   2 +
 drivers/thermal/pcie_cooling.c | 107 +++++++++++++++++++++++++++++++++
 include/linux/pci-bwctrl.h     |  15 +++++
 6 files changed, 146 insertions(+)
 create mode 100644 drivers/thermal/pcie_cooling.c

diff --git a/MAINTAINERS b/MAINTAINERS
index d2eed2883a43..a0b40253fd5a 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -16421,6 +16421,7 @@ PCIE BANDWIDTH CONTROLLER
 M:	Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
 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
diff --git a/drivers/pci/pcie/bwctrl.c b/drivers/pci/pcie/bwctrl.c
index e3172d69476f..13c73546244e 100644
--- a/drivers/pci/pcie/bwctrl.c
+++ b/drivers/pci/pcie/bwctrl.c
@@ -34,9 +34,11 @@
 /**
  * struct bwctrl_service_data - PCIe Port Bandwidth Controller
  * @set_speed_mutex: serializes link speed changes
+ * @cdev: thermal cooling device associated with the port
  */
 struct bwctrl_service_data {
 	struct mutex set_speed_mutex;
+	struct thermal_cooling_device *cdev;
 };
 
 static bool bwctrl_valid_pcie_speed(enum pci_bus_speed speed)
@@ -253,8 +255,16 @@ static int pcie_bandwidth_notification_probe(struct pcie_device *srv)
 	pcie_enable_link_bandwidth_notification(port);
 	pci_info(port, "enabled with IRQ %d\n", srv->irq);
 
+	data->cdev = pcie_cooling_device_register(port, srv);
+	if (IS_ERR(data->cdev)) {
+		ret = PTR_ERR(data->cdev);
+		goto disable_notifications;
+	}
 	return 0;
 
+disable_notifications:
+	pcie_disable_link_bandwidth_notification(srv->port);
+	kfree(data);
 free_irq:
 	free_irq(srv->irq, srv);
 	return ret;
@@ -264,6 +274,7 @@ static void pcie_bandwidth_notification_remove(struct pcie_device *srv)
 {
 	struct bwctrl_service_data *data = get_service_data(srv);
 
+	pcie_cooling_device_unregister(data->cdev);
 	pcie_disable_link_bandwidth_notification(srv->port);
 	free_irq(srv->irq, srv);
 	mutex_destroy(&data->set_speed_mutex);
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index 19a4b33cb564..7deda3a0237d 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -219,6 +219,16 @@ config DEVFREQ_THERMAL
 
 	  If you want this support, you should say Y here.
 
+config PCIE_THERMAL
+	bool "PCIe cooling support"
+	depends on PCIEPORTBUS
+	select PCIE_BW
+	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 058664bc3ec0..065972a08c84 100644
--- a/drivers/thermal/Makefile
+++ b/drivers/thermal/Makefile
@@ -30,6 +30,8 @@ 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..d86265c03e80
--- /dev/null
+++ b/drivers/thermal/pcie_cooling.c
@@ -0,0 +1,107 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * PCIe cooling device
+ *
+ * Copyright (C) 2023 Intel Corporation.
+ */
+
+#include <linux/build_bug.h>
+#include <linux/err.h>
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/pci-bwctrl.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/thermal.h>
+
+#define COOLING_DEV_TYPE_PREFIX		"PCIe_Port_"
+
+struct pcie_cooling_device {
+	struct pci_dev *port;
+	struct pcie_device *pdev;
+};
+
+static int pcie_cooling_get_max_level(struct thermal_cooling_device *cdev, unsigned long *state)
+{
+	struct pcie_cooling_device *pcie_cdev = cdev->devdata;
+
+	/* cooling state 0 is same as the maximum PCIe speed */
+	*state = pcie_cdev->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 pcie_cooling_device *pcie_cdev = cdev->devdata;
+
+	/* cooling state 0 is same as the maximum PCIe speed */
+	*state = cdev->max_state -
+		 (pcie_cdev->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 pcie_cooling_device *pcie_cdev = 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 bwctrl_set_current_speed(pcie_cdev->pdev, speed);
+}
+
+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,
+							    struct pcie_device *pdev)
+{
+	struct pcie_cooling_device *pcie_cdev;
+	struct thermal_cooling_device *cdev;
+	size_t name_len;
+	char *name;
+
+	pcie_cdev = kzalloc(sizeof(*pcie_cdev), GFP_KERNEL);
+	if (!pcie_cdev)
+		return ERR_PTR(-ENOMEM);
+
+	pcie_cdev->port = port;
+	pcie_cdev->pdev = pdev;
+
+	name_len = strlen(COOLING_DEV_TYPE_PREFIX) + strlen(pci_name(port)) + 1;
+	name = kzalloc(name_len, GFP_KERNEL);
+	if (!name) {
+		kfree(pcie_cdev);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	snprintf(name, name_len, COOLING_DEV_TYPE_PREFIX "%s", pci_name(port));
+	cdev = thermal_cooling_device_register(name, pcie_cdev, &pcie_cooling_ops);
+	kfree(name);
+
+	return cdev;
+}
+
+void pcie_cooling_device_unregister(struct thermal_cooling_device *cdev)
+{
+	struct pcie_cooling_device *pcie_cdev = cdev->devdata;
+
+	thermal_cooling_device_unregister(cdev);
+	kfree(pcie_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
index 46026fa25deb..366445517b72 100644
--- a/include/linux/pci-bwctrl.h
+++ b/include/linux/pci-bwctrl.h
@@ -15,4 +15,19 @@ struct thermal_cooling_device;
 
 int bwctrl_set_current_speed(struct pcie_device *srv, enum pci_bus_speed speed);
 
+#ifdef CONFIG_PCIE_THERMAL
+struct thermal_cooling_device *pcie_cooling_device_register(struct pci_dev *port,
+							    struct pcie_device *pdev);
+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,
+									  struct pcie_device *pdev)
+{
+	return NULL;
+}
+static inline void pcie_cooling_device_unregister(struct thermal_cooling_device *cdev)
+{
+}
+#endif
+
 #endif
-- 
2.30.2