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 Link Speed.
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@xxxxxxxxxxxxxxx>
Acked-by: Rafael J. Wysocki <rafael@xxxxxxxxxx> # From the cooling device interface perspective
---
MAINTAINERS | 2 +
drivers/pci/pcie/bwctrl.c | 8 ++++
drivers/thermal/Kconfig | 10 ++++
drivers/thermal/Makefile | 2 +
drivers/thermal/pcie_cooling.c | 84 ++++++++++++++++++++++++++++++++++
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
diff --git a/MAINTAINERS b/MAINTAINERS
index bd420cb09821..3a94ae81b13f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -17104,6 +17104,8 @@ M: Ilpo Järvinen <ilpo.jarvinen@xxxxxxxxxxxxxxx>
L: linux-pci@xxxxxxxxxxxxxxx
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@xxxxxxxxxx>
diff --git a/drivers/pci/pcie/bwctrl.c b/drivers/pci/pcie/bwctrl.c
index e97665848158..5d1df9e6a349 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;
};
static bool pcie_valid_speed(enum pci_bus_speed speed)
@@ -287,6 +290,8 @@ static int pcie_bwnotif_probe(struct pcie_device *srv)
pcie_bwnotif_enable(srv);
pci_info(port, "enabled with IRQ %d\n", srv->irq);
+ port->link_bwctrl->cdev = pcie_cooling_device_register(port);
+
return 0;
}
@@ -294,6 +299,9 @@ static void pcie_bwnotif_remove(struct pcie_device *srv)
{
struct pcie_bwctrl_data *data = get_service_data(srv);
+ if (data->cdev)
+ pcie_cooling_device_unregister(data->cdev);
+
scoped_guard(rwsem_write, &pcie_bwctrl_remove_rwsem)
srv->port->link_bwctrl = NULL;
diff --git a/drivers/thermal/Kconfig b/drivers/thermal/Kconfig
index 204ed89a3ec9..7ddc44be4701 100644
--- a/drivers/thermal/Kconfig
+++ b/drivers/thermal/Kconfig
@@ -211,6 +211,16 @@ 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_BWCTRL
+ 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 5cdf7d68687f..5b9bf8e80eb6 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..367290d57e99
--- /dev/null
+++ b/drivers/thermal/pcie_cooling.c
@@ -0,0 +1,84 @@
+// 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/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)
+{
+ struct thermal_cooling_device *cdev;
+ char *name;
+
+ name = kasprintf(GFP_KERNEL, COOLING_DEV_TYPE_PREFIX "%s", pci_name(port));
+ if (!name)
+ return ERR_PTR(-ENOMEM);
+
+ cdev = thermal_cooling_device_register(name, port, &pcie_cooling_ops);
+ kfree(name);
+
+ return cdev;
+}
+
+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@xxxxxxxxxxxxxxx>");
+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
--
2.39.2
