PCI/bwctrl: Add pcie_set_target_speed() to set PCIe Link Speed

Currently, PCIe Link Speeds are adjusted by custom code rather than in a
common function provided in PCI core. The PCIe bandwidth controller
(bwctrl) introduces an in-kernel API, pcie_set_target_speed(), to set PCIe
Link Speed.

Convert Target Speed quirk to use the new API. The Target Speed quirk runs
very early when bwctrl is not yet probed for a Port and can also run later
when bwctrl is already setup for the Port, which requires the per port
mutex (set_speed_mutex) to be only taken if the bwctrl setup is already
complete.

The new API is also intended to be used in an upcoming commit that adds a
thermal cooling device to throttle PCIe bandwidth when thermal thresholds
are reached.

The PCIe bandwidth control procedure is as follows. The highest speed
supported by the Port and the PCIe device which is not higher than the
requested speed is selected and written into the Target Link Speed in the
Link Control 2 Register. Then bandwidth controller retrains the PCIe Link.

Bandwidth Notifications enable the cur_bus_speed in the struct pci_bus to
keep track PCIe Link Speed changes. While Bandwidth Notifications should
also be generated when bandwidth controller alters the PCIe Link Speed, a
few platforms do not deliver LMBS interrupt after Link Training as
expected. Thus, after changing the Link Speed, bandwidth controller makes
additional read for the Link Status Register to ensure cur_bus_speed is
consistent with the new PCIe Link Speed.

Link: https://lore.kernel.org/r/[e-mail]
Signed-off-by: Ilpo Järvinen <[e-mail]>
[bhelgaas: squash devm_mutex_init() error checking from
https://lore.kernel.org/r/[e-mail],
drop export of pcie_set_target_speed()]
Signed-off-by: Bjorn Helgaas <[e-mail]>
Reviewed-by: Jonathan Cameron <[e-mail]>

drivers/pci/pci.h

···
 struct pci_bus *pci_bus_get(struct pci_bus *bus);
 void pci_bus_put(struct pci_bus *bus);
 
+#define PCIE_LNKCAP_SLS2SPEED(lnkcap)					\
+({									\
+	((lnkcap) == PCI_EXP_LNKCAP_SLS_64_0GB ? PCIE_SPEED_64_0GT :	\
+	 (lnkcap) == PCI_EXP_LNKCAP_SLS_32_0GB ? PCIE_SPEED_32_0GT :	\
+	 (lnkcap) == PCI_EXP_LNKCAP_SLS_16_0GB ? PCIE_SPEED_16_0GT :	\
+	 (lnkcap) == PCI_EXP_LNKCAP_SLS_8_0GB ? PCIE_SPEED_8_0GT :	\
+	 (lnkcap) == PCI_EXP_LNKCAP_SLS_5_0GB ? PCIE_SPEED_5_0GT :	\
+	 (lnkcap) == PCI_EXP_LNKCAP_SLS_2_5GB ? PCIE_SPEED_2_5GT :	\
+	 PCI_SPEED_UNKNOWN);						\
+})
+
 /* PCIe link information from Link Capabilities 2 */
 #define PCIE_LNKCAP2_SLS2SPEED(lnkcap2) \
 	((lnkcap2) & PCI_EXP_LNKCAP2_SLS_64_0GB ? PCIE_SPEED_64_0GT : \
···
 	 (lnkcap2) & PCI_EXP_LNKCAP2_SLS_8_0GB ? PCIE_SPEED_8_0GT : \
 	 (lnkcap2) & PCI_EXP_LNKCAP2_SLS_5_0GB ? PCIE_SPEED_5_0GT : \
 	 (lnkcap2) & PCI_EXP_LNKCAP2_SLS_2_5GB ? PCIE_SPEED_2_5GT : \
+	 PCI_SPEED_UNKNOWN)
+
+#define PCIE_LNKCTL2_TLS2SPEED(lnkctl2) \
+	((lnkctl2) == PCI_EXP_LNKCTL2_TLS_64_0GT ? PCIE_SPEED_64_0GT : \
+	 (lnkctl2) == PCI_EXP_LNKCTL2_TLS_32_0GT ? PCIE_SPEED_32_0GT : \
+	 (lnkctl2) == PCI_EXP_LNKCTL2_TLS_16_0GT ? PCIE_SPEED_16_0GT : \
+	 (lnkctl2) == PCI_EXP_LNKCTL2_TLS_8_0GT ? PCIE_SPEED_8_0GT : \
+	 (lnkctl2) == PCI_EXP_LNKCTL2_TLS_5_0GT ? PCIE_SPEED_5_0GT : \
+	 (lnkctl2) == PCI_EXP_LNKCTL2_TLS_2_5GT ? PCIE_SPEED_2_5GT : \
 	 PCI_SPEED_UNKNOWN)
 
 /* PCIe speed to Mb/s reduced by encoding overhead */

drivers/pci/pcie/bwctrl.c

···
  * Copyright (C) 2019 Dell Inc
  * Copyright (C) 2023-2024 Intel Corporation
  *
+ * The PCIe bandwidth controller provides a way to alter PCIe Link Speeds
+ * and notify the operating system when the Link Width or Speed changes. The
+ * notification capability is required for all Root Ports and Downstream
+ * Ports supporting Link Width wider than x1 and/or multiple Link Speeds.
+ *
  * This service port driver hooks into the Bandwidth Notification interrupt
  * watching for changes or links becoming degraded in operation. It updates
  * the cached Current Link Speed that is exposed to user space through sysfs.
···
 #define dev_fmt(fmt) "bwctrl: " fmt
 
 #include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/bits.h>
 #include <linux/cleanup.h>
 #include <linux/errno.h>
 #include <linux/interrupt.h>
+#include <linux/mutex.h>
 #include <linux/pci.h>
 #include <linux/rwsem.h>
 #include <linux/slab.h>
···
 
 /**
  * struct pcie_bwctrl_data - PCIe bandwidth controller
+ * @set_speed_mutex:	Serializes link speed changes
  * @lbms_count:		Count for LBMS (since last reset)
  */
 struct pcie_bwctrl_data {
+	struct mutex set_speed_mutex;
 	atomic_t lbms_count;
 };
 
-/* Prevents port removal during LBMS count accessors */
+/*
+ * Prevent port removal during LBMS count accessors and Link Speed changes.
+ *
+ * These have to be differentiated because pcie_bwctrl_change_speed() calls
+ * pcie_retrain_link() which uses LBMS count reset accessor on success
+ * (using just one rwsem triggers "possible recursive locking detected"
+ * warning).
+ */
 static DECLARE_RWSEM(pcie_bwctrl_lbms_rwsem);
+static DECLARE_RWSEM(pcie_bwctrl_setspeed_rwsem);
+
+static bool pcie_valid_speed(enum pci_bus_speed speed)
+{
+	return (speed >= PCIE_SPEED_2_5GT) && (speed <= PCIE_SPEED_64_0GT);
+}
+
+static u16 pci_bus_speed2lnkctl2(enum pci_bus_speed speed)
+{
+	static const u8 speed_conv[] = {
+		[PCIE_SPEED_2_5GT] = PCI_EXP_LNKCTL2_TLS_2_5GT,
+		[PCIE_SPEED_5_0GT] = PCI_EXP_LNKCTL2_TLS_5_0GT,
+		[PCIE_SPEED_8_0GT] = PCI_EXP_LNKCTL2_TLS_8_0GT,
+		[PCIE_SPEED_16_0GT] = PCI_EXP_LNKCTL2_TLS_16_0GT,
+		[PCIE_SPEED_32_0GT] = PCI_EXP_LNKCTL2_TLS_32_0GT,
+		[PCIE_SPEED_64_0GT] = PCI_EXP_LNKCTL2_TLS_64_0GT,
+	};
+
+	if (WARN_ON_ONCE(!pcie_valid_speed(speed)))
+		return 0;
+
+	return speed_conv[speed];
+}
+
+static inline u16 pcie_supported_speeds2target_speed(u8 supported_speeds)
+{
+	return __fls(supported_speeds);
+}
+
+/**
+ * pcie_bwctrl_select_speed - Select Target Link Speed
+ * @port:	PCIe Port
+ * @speed_req:	Requested PCIe Link Speed
+ *
+ * Select Target Link Speed by take into account Supported Link Speeds of
+ * both the Root Port and the Endpoint.
+ *
+ * Return: Target Link Speed (1=2.5GT/s, 2=5GT/s, 3=8GT/s, etc.)
+ */
+static u16 pcie_bwctrl_select_speed(struct pci_dev *port, enum pci_bus_speed speed_req)
+{
+	struct pci_bus *bus = port->subordinate;
+	u8 desired_speeds, supported_speeds;
+	struct pci_dev *dev;
+
+	desired_speeds = GENMASK(pci_bus_speed2lnkctl2(speed_req),
+				 __fls(PCI_EXP_LNKCAP2_SLS_2_5GB));
+
+	supported_speeds = port->supported_speeds;
+	if (bus) {
+		down_read(&pci_bus_sem);
+		dev = list_first_entry_or_null(&bus->devices, struct pci_dev, bus_list);
+		if (dev)
+			supported_speeds &= dev->supported_speeds;
+		up_read(&pci_bus_sem);
+	}
+	if (!supported_speeds)
+		return PCI_EXP_LNKCAP2_SLS_2_5GB;
+
+	return pcie_supported_speeds2target_speed(supported_speeds & desired_speeds);
+}
+
+static int pcie_bwctrl_change_speed(struct pci_dev *port, u16 target_speed, bool use_lt)
+{
+	int ret;
+
+	ret = pcie_capability_clear_and_set_word(port, PCI_EXP_LNKCTL2,
+						 PCI_EXP_LNKCTL2_TLS, target_speed);
+	if (ret != PCIBIOS_SUCCESSFUL)
+		return pcibios_err_to_errno(ret);
+
+	ret = pcie_retrain_link(port, use_lt);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Ensure link speed updates also with platforms that have problems
+	 * with notifications.
+	 */
+	if (port->subordinate)
+		pcie_update_link_speed(port->subordinate);
+
+	return 0;
+}
+
+/**
+ * pcie_set_target_speed - Set downstream Link Speed for PCIe Port
+ * @port:	PCIe Port
+ * @speed_req:	Requested PCIe Link Speed
+ * @use_lt:	Wait for the LT or DLLLA bit to detect the end of link training
+ *
+ * Attempt to set PCIe Port Link Speed to @speed_req. @speed_req may be
+ * adjusted downwards to the best speed supported by both the Port and PCIe
+ * Device underneath it.
+ *
+ * Return:
+ * * 0		- on success
+ * * -EINVAL	- @speed_req is not a PCIe Link Speed
+ * * -ENODEV	- @port is not controllable
+ * * -ETIMEDOUT	- changing Link Speed took too long
+ * * -EAGAIN	- Link Speed was changed but @speed_req was not achieved
+ */
+int pcie_set_target_speed(struct pci_dev *port, enum pci_bus_speed speed_req,
+			  bool use_lt)
+{
+	struct pci_bus *bus = port->subordinate;
+	u16 target_speed;
+	int ret;
+
+	if (WARN_ON_ONCE(!pcie_valid_speed(speed_req)))
+		return -EINVAL;
+
+	if (bus && bus->cur_bus_speed == speed_req)
+		return 0;
+
+	target_speed = pcie_bwctrl_select_speed(port, speed_req);
+
+	scoped_guard(rwsem_read, &pcie_bwctrl_setspeed_rwsem) {
+		struct pcie_bwctrl_data *data = port->link_bwctrl;
+
+		/*
+		 * port->link_bwctrl is NULL during initial scan when called
+		 * e.g. from the Target Speed quirk.
+		 */
+		if (data)
+			mutex_lock(&data->set_speed_mutex);
+
+		ret = pcie_bwctrl_change_speed(port, target_speed, use_lt);
+
+		if (data)
+			mutex_unlock(&data->set_speed_mutex);
+	}
+
+	/*
+	 * Despite setting higher speed into the Target Link Speed, empty
+	 * bus won't train to 5GT+ speeds.
+	 */
+	if (!ret && bus && bus->cur_bus_speed != speed_req &&
+	    !list_empty(&bus->devices))
+		ret = -EAGAIN;
+
+	return ret;
+}
 
 static void pcie_bwnotif_enable(struct pcie_device *srv)
 {
···
 	if (!data)
 		return -ENOMEM;
 
+	ret = devm_mutex_init(&srv->device, &data->set_speed_mutex);
+	if (ret)
+		return ret;
+
 	ret = devm_request_irq(&srv->device, srv->irq, pcie_bwnotif_irq,
 			       IRQF_SHARED, "PCIe bwctrl", srv);
 	if (ret)
 		return ret;
 
-	scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem) {
-		port->link_bwctrl = no_free_ptr(data);
-		pcie_bwnotif_enable(srv);
+	scoped_guard(rwsem_write, &pcie_bwctrl_setspeed_rwsem) {
+		scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem) {
+			port->link_bwctrl = no_free_ptr(data);
+			pcie_bwnotif_enable(srv);
+		}
 	}
 
 	pci_dbg(port, "enabled with IRQ %d\n", srv->irq);
···
 static void pcie_bwnotif_remove(struct pcie_device *srv)
 {
 	pcie_bwnotif_disable(srv->port);
-	scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem)
-		srv->port->link_bwctrl = NULL;
+
+	scoped_guard(rwsem_write, &pcie_bwctrl_setspeed_rwsem)
+		scoped_guard(rwsem_write, &pcie_bwctrl_lbms_rwsem)
+			srv->port->link_bwctrl = NULL;
 }
 
 static int pcie_bwnotif_suspend(struct pcie_device *srv)

drivers/pci/quirks.c

···
 
 		pci_info(dev, "broken device, retraining non-functional downstream link at 2.5GT/s\n");
 
-		lnkctl2 &= ~PCI_EXP_LNKCTL2_TLS;
-		lnkctl2 |= PCI_EXP_LNKCTL2_TLS_2_5GT;
-		pcie_capability_write_word(dev, PCI_EXP_LNKCTL2, lnkctl2);
-
-		ret = pcie_retrain_link(dev, false);
+		ret = pcie_set_target_speed(dev, PCIE_SPEED_2_5GT, false);
 		if (ret) {
 			pci_info(dev, "retraining failed\n");
-			pcie_capability_write_word(dev, PCI_EXP_LNKCTL2,
-						   oldlnkctl2);
-			pcie_retrain_link(dev, true);
+			pcie_set_target_speed(dev, PCIE_LNKCTL2_TLS2SPEED(oldlnkctl2),
+					      true);
 			return ret;
 		}
 
···
 
 		pci_info(dev, "removing 2.5GT/s downstream link speed restriction\n");
 		pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &lnkcap);
-		lnkctl2 &= ~PCI_EXP_LNKCTL2_TLS;
-		lnkctl2 |= lnkcap & PCI_EXP_LNKCAP_SLS;
-		pcie_capability_write_word(dev, PCI_EXP_LNKCTL2, lnkctl2);
-
-		ret = pcie_retrain_link(dev, false);
+		ret = pcie_set_target_speed(dev, PCIE_LNKCAP_SLS2SPEED(lnkcap), false);
 		if (ret) {
 			pci_info(dev, "retraining failed\n");
 			return ret;

include/linux/pci.h

···
 #ifdef CONFIG_PCIEPORTBUS
 extern bool pcie_ports_disabled;
 extern bool pcie_ports_native;
+
+int pcie_set_target_speed(struct pci_dev *port, enum pci_bus_speed speed_req,
+			  bool use_lt);
 #else
 #define pcie_ports_disabled	true
 #define pcie_ports_native	false
+
+static inline int pcie_set_target_speed(struct pci_dev *port,
+					enum pci_bus_speed speed_req,
+					bool use_lt)
+{
+	return -EOPNOTSUPP;
+}
 #endif
 
 #define PCIE_LINK_STATE_L0S		(BIT(0) | BIT(1)) /* Upstr/dwnstr L0s */