Merge: PCI: Update bandwidth management subsystem

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/6615

```
JIRA: https://issues.redhat.com/browse/RHEL-81906

This series includes a set of key fixes related to PCIe's
bandwidth link training from upstream v6.13 by taking in
content from upstream merge request d957ff7 "Merge
branch 'pci/bwctrl'".

Signed-off-by: Myron Stowe <mstowe@redhat.com>
```

Approved-by: John W. Linville <linville@redhat.com>
Approved-by: Desnes Nunes <desnesn@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>
Approved-by: Tony Camuso <tcamuso@redhat.com>

Merged-by: Augusto Caringi <acaringi@redhat.com>

Author: caringi

Documentation/PCI/pciebus-howto.rst

@@ -217,8 +217,12 @@ capability structure except the PCI Express capability structure,
 that is shared between many drivers including the service drivers.
 RMW Capability accessors (pcie_capability_clear_and_set_word(),
 pcie_capability_set_word(), and pcie_capability_clear_word()) protect
-a selected set of PCI Express Capability Registers (Link Control
-Register and Root Control Register). Any change to those registers
-should be performed using RMW accessors to avoid problems due to
-concurrent updates. For the up-to-date list of protected registers,
-see pcie_capability_clear_and_set_word().
+a selected set of PCI Express Capability Registers:
+
+* Link Control Register
+* Root Control Register
+* Link Control 2 Register
+
+Any change to those registers should be performed using RMW accessors to
+avoid problems due to concurrent updates. For the up-to-date list of
+protected registers, see pcie_capability_clear_and_set_word().

MAINTAINERS

@@ -15035,6 +15035,12 @@ F:	include/linux/of_pci.h
 F:	include/linux/pci*
 F:	include/uapi/linux/pci*
 
+PCIE BANDWIDTH CONTROLLER
+M:	Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
+L:	linux-pci@vger.kernel.org
+S:	Supported
+F:	drivers/pci/pcie/bwctrl.c
+
 PCIE DRIVER FOR AMAZON ANNAPURNA LABS
 M:	Jonathan Chocron <jonnyc@amazon.com>
 L:	linux-pci@vger.kernel.org

drivers/pci/hotplug/pciehp_ctrl.c

@@ -19,6 +19,8 @@
 #include <linux/types.h>
 #include <linux/pm_runtime.h>
 #include <linux/pci.h>
+
+#include "../pci.h"
 #include "pciehp.h"
 
 /* The following routines constitute the bulk of the
@@ -127,6 +129,9 @@ static void remove_board(struct controller *ctrl, bool safe_removal)
 
 	pciehp_set_indicators(ctrl, PCI_EXP_SLTCTL_PWR_IND_OFF,
 			      INDICATOR_NOOP);
+
+	/* Don't carry LBMS indications across */
+	pcie_reset_lbms_count(ctrl->pcie->port);
 }
 
 static int pciehp_enable_slot(struct controller *ctrl);

drivers/pci/hotplug/pciehp_hpc.c

@@ -319,7 +319,7 @@ int pciehp_check_link_status(struct controller *ctrl)
 		return -1;
 	}
 
-	pcie_update_link_speed(ctrl->pcie->port->subordinate, lnk_status);
+	__pcie_update_link_speed(ctrl->pcie->port->subordinate, lnk_status);
 
 	if (!found) {
 		ctrl_info(ctrl, "Slot(%s): No device found\n",

drivers/pci/pci.c

@@ -4744,7 +4744,7 @@ int pcie_retrain_link(struct pci_dev *pdev, bool use_lt)
 	 * to track link speed or width changes made by hardware itself
 	 * in attempt to correct unreliable link operation.
 	 */
-	pcie_capability_write_word(pdev, PCI_EXP_LNKSTA, PCI_EXP_LNKSTA_LBMS);
+	pcie_reset_lbms_count(pdev);
 	return rc;
 }
 
@@ -6193,38 +6193,66 @@ u32 pcie_bandwidth_available(struct pci_dev *dev, struct pci_dev **limiting_dev,
 EXPORT_SYMBOL(pcie_bandwidth_available);
 
 /**
- * pcie_get_speed_cap - query for the PCI device's link speed capability
+ * pcie_get_supported_speeds - query Supported Link Speed Vector
  * @dev: PCI device to query
  *
- * Query the PCI device speed capability.  Return the maximum link speed
- * supported by the device.
+ * Query @dev supported link speeds.
+ *
+ * Implementation Note in PCIe r6.0 sec 7.5.3.18 recommends determining
+ * supported link speeds using the Supported Link Speeds Vector in the Link
+ * Capabilities 2 Register (when available).
+ *
+ * Link Capabilities 2 was added in PCIe r3.0, sec 7.8.18.
+ *
+ * Without Link Capabilities 2, i.e., prior to PCIe r3.0, Supported Link
+ * Speeds field in Link Capabilities is used and only 2.5 GT/s and 5.0 GT/s
+ * speeds were defined.
+ *
+ * For @dev without Supported Link Speed Vector, the field is synthesized
+ * from the Max Link Speed field in the Link Capabilities Register.
+ *
+ * Return: Supported Link Speeds Vector (+ reserved 0 at LSB).
  */
-enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev)
+u8 pcie_get_supported_speeds(struct pci_dev *dev)
 {
 	u32 lnkcap2, lnkcap;
+	u8 speeds;
 
 	/*
-	 * Link Capabilities 2 was added in PCIe r3.0, sec 7.8.18.  The
-	 * implementation note there recommends using the Supported Link
-	 * Speeds Vector in Link Capabilities 2 when supported.
-	 *
-	 * Without Link Capabilities 2, i.e., prior to PCIe r3.0, software
-	 * should use the Supported Link Speeds field in Link Capabilities,
-	 * where only 2.5 GT/s and 5.0 GT/s speeds were defined.
+	 * Speeds retain the reserved 0 at LSB before PCIe Supported Link
+	 * Speeds Vector to allow using SLS Vector bit defines directly.
 	 */
 	pcie_capability_read_dword(dev, PCI_EXP_LNKCAP2, &lnkcap2);
+	speeds = lnkcap2 & PCI_EXP_LNKCAP2_SLS;
+
+	/* Ignore speeds higher than Max Link Speed */
+	pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &lnkcap);
+	speeds &= GENMASK(lnkcap & PCI_EXP_LNKCAP_SLS, 0);
 
 	/* PCIe r3.0-compliant */
-	if (lnkcap2)
-		return PCIE_LNKCAP2_SLS2SPEED(lnkcap2);
+	if (speeds)
+		return speeds;
 
-	pcie_capability_read_dword(dev, PCI_EXP_LNKCAP, &lnkcap);
+	/* Synthesize from the Max Link Speed field */
 	if ((lnkcap & PCI_EXP_LNKCAP_SLS) == PCI_EXP_LNKCAP_SLS_5_0GB)
-		return PCIE_SPEED_5_0GT;
+		speeds = PCI_EXP_LNKCAP2_SLS_5_0GB | PCI_EXP_LNKCAP2_SLS_2_5GB;
 	else if ((lnkcap & PCI_EXP_LNKCAP_SLS) == PCI_EXP_LNKCAP_SLS_2_5GB)
-		return PCIE_SPEED_2_5GT;
+		speeds = PCI_EXP_LNKCAP2_SLS_2_5GB;
+
+	return speeds;
+}
 
-	return PCI_SPEED_UNKNOWN;
+/**
+ * pcie_get_speed_cap - query for the PCI device's link speed capability
+ * @dev: PCI device to query
+ *
+ * Query the PCI device speed capability.
+ *
+ * Return: the maximum link speed supported by the device.
+ */
+enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev)
+{
+	return PCIE_LNKCAP2_SLS2SPEED(dev->supported_speeds);
 }
 EXPORT_SYMBOL(pcie_get_speed_cap);
 

drivers/pci/pci.h

@@ -318,6 +318,17 @@ void pci_disable_bridge_window(struct pci_dev *dev);
 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 : \
@@ -328,6 +339,15 @@ void pci_bus_put(struct pci_bus *bus);
 	 (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 */
 #define PCIE_SPEED2MBS_ENC(speed) \
 	((speed) == PCIE_SPEED_64_0GT ? 64000*1/1 : \
@@ -360,12 +380,16 @@ static inline int pcie_dev_speed_mbps(enum pci_bus_speed speed)
 	return -EINVAL;
 }
 
+u8 pcie_get_supported_speeds(struct pci_dev *dev);
 const char *pci_speed_string(enum pci_bus_speed speed);
-enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev);
-enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev);
 void __pcie_print_link_status(struct pci_dev *dev, bool verbose);
 void pcie_report_downtraining(struct pci_dev *dev);
-void pcie_update_link_speed(struct pci_bus *bus, u16 link_status);
+
+static inline void __pcie_update_link_speed(struct pci_bus *bus, u16 linksta)
+{
+	bus->cur_bus_speed = pcie_link_speed[linksta & PCI_EXP_LNKSTA_CLS];
+}
+void pcie_update_link_speed(struct pci_bus *bus);
 
 /* Single Root I/O Virtualization */
 struct pci_sriov {
@@ -680,6 +704,17 @@ static inline void pcie_set_ecrc_checking(struct pci_dev *dev) { }
 static inline void pcie_ecrc_get_policy(char *str) { }
 #endif
 
+#ifdef CONFIG_PCIEPORTBUS
+void pcie_reset_lbms_count(struct pci_dev *port);
+int pcie_lbms_count(struct pci_dev *port, unsigned long *val);
+#else
+static inline void pcie_reset_lbms_count(struct pci_dev *port) {}
+static inline int pcie_lbms_count(struct pci_dev *port, unsigned long *val)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
 struct pci_dev_reset_methods {
 	u16 vendor;
 	u16 device;

drivers/pci/pcie/Makefile

@@ -4,7 +4,7 @@
 
 pcieportdrv-y			:= portdrv.o rcec.o
 
-obj-$(CONFIG_PCIEPORTBUS)	+= pcieportdrv.o
+obj-$(CONFIG_PCIEPORTBUS)	+= pcieportdrv.o bwctrl.o
 
 obj-y				+= aspm.o
 obj-$(CONFIG_PCIEAER)		+= aer.o err.o