Merge branch 'pci/enumeration'

- Work around IDT switch ACS Source Validation erratum (James
    Puthukattukaran)

  - Emit diagnostics for all cases of PCIe Link downtraining (Links
    operating slower than they're capable of) (Alexandru Gagniuc)

  - Skip VFs when configuring Max Payload Size (Myron Stowe)

  - Reduce Root Port Max Payload Size if necessary when hot-adding a device
    below it (Myron Stowe)

* pci/enumeration:
  PCI: Match Root Port's MPS to endpoint's MPSS as necessary
  PCI: Skip MPS logic for Virtual Functions (VFs)
  PCI: Check for PCIe Link downtraining
  PCI: Workaround IDT switch ACS Source Validation erratum

drivers/pci/pci.c

@@ -5301,14 +5301,16 @@ u32 pcie_bandwidth_capable(struct pci_dev *dev, enum pci_bus_speed *speed,
 }
 
 /**
- * pcie_print_link_status - Report the PCI device's link speed and width
+ * __pcie_print_link_status - Report the PCI device's link speed and width
  * @dev: PCI device to query
+ * @verbose: Print info even when enough bandwidth is available
  *
- * Report the available bandwidth at the device.  If this is less than the
- * device is capable of, report the device's maximum possible bandwidth and
- * the upstream link that limits its performance to less than that.
+ * If the available bandwidth at the device is less than the device is
+ * capable of, report the device's maximum possible bandwidth and the
+ * upstream link that limits its performance.  If @verbose, always print
+ * the available bandwidth, even if the device isn't constrained.
  */
-void pcie_print_link_status(struct pci_dev *dev)
+void __pcie_print_link_status(struct pci_dev *dev, bool verbose)
 {
 	enum pcie_link_width width, width_cap;
 	enum pci_bus_speed speed, speed_cap;
@@ -5318,11 +5320,11 @@ void pcie_print_link_status(struct pci_dev *dev)
 	bw_cap = pcie_bandwidth_capable(dev, &speed_cap, &width_cap);
 	bw_avail = pcie_bandwidth_available(dev, &limiting_dev, &speed, &width);
 
-	if (bw_avail >= bw_cap)
+	if (bw_avail >= bw_cap && verbose)
 		pci_info(dev, "%u.%03u Gb/s available PCIe bandwidth (%s x%d link)\n",
 			 bw_cap / 1000, bw_cap % 1000,
 			 PCIE_SPEED2STR(speed_cap), width_cap);
-	else
+	else if (bw_avail < bw_cap)
 		pci_info(dev, "%u.%03u Gb/s available PCIe bandwidth, limited by %s x%d link at %s (capable of %u.%03u Gb/s with %s x%d link)\n",
 			 bw_avail / 1000, bw_avail % 1000,
 			 PCIE_SPEED2STR(speed), width,
@@ -5330,6 +5332,17 @@ void pcie_print_link_status(struct pci_dev *dev)
 			 bw_cap / 1000, bw_cap % 1000,
 			 PCIE_SPEED2STR(speed_cap), width_cap);
 }
+
+/**
+ * pcie_print_link_status - Report the PCI device's link speed and width
+ * @dev: PCI device to query
+ *
+ * Report the available bandwidth at the device.
+ */
+void pcie_print_link_status(struct pci_dev *dev)
+{
+	__pcie_print_link_status(dev, true);
+}
 EXPORT_SYMBOL(pcie_print_link_status);
 
 /**

drivers/pci/pci.h

@@ -225,6 +225,10 @@ enum pci_bar_type {
 int pci_configure_extended_tags(struct pci_dev *dev, void *ign);
 bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *pl,
 				int crs_timeout);
+bool pci_bus_generic_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *pl,
+					int crs_timeout);
+int pci_idt_bus_quirk(struct pci_bus *bus, int devfn, u32 *pl, int crs_timeout);
+
 int pci_setup_device(struct pci_dev *dev);
 int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 		    struct resource *res, unsigned int reg);
@@ -259,6 +263,7 @@ enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev);
 enum pcie_link_width pcie_get_width_cap(struct pci_dev *dev);
 u32 pcie_bandwidth_capable(struct pci_dev *dev, enum pci_bus_speed *speed,
 			   enum pcie_link_width *width);
+void __pcie_print_link_status(struct pci_dev *dev, bool verbose);
 
 /* Single Root I/O Virtualization */
 struct pci_sriov {

drivers/pci/probe.c

@@ -1724,11 +1724,15 @@ int pci_setup_device(struct pci_dev *dev)
 static void pci_configure_mps(struct pci_dev *dev)
 {
 	struct pci_dev *bridge = pci_upstream_bridge(dev);
-	int mps, p_mps, rc;
+	int mps, mpss, p_mps, rc;
 
 	if (!pci_is_pcie(dev) || !bridge || !pci_is_pcie(bridge))
 		return;
 
+	/* MPS and MRRS fields are of type 'RsvdP' for VFs, short-circuit out */
+	if (dev->is_virtfn)
+		return;
+
 	mps = pcie_get_mps(dev);
 	p_mps = pcie_get_mps(bridge);
 
@@ -1748,6 +1752,14 @@ static void pci_configure_mps(struct pci_dev *dev)
 	if (pcie_bus_config != PCIE_BUS_DEFAULT)
 		return;
 
+	mpss = 128 << dev->pcie_mpss;
+	if (mpss < p_mps && pci_pcie_type(bridge) == PCI_EXP_TYPE_ROOT_PORT) {
+		pcie_set_mps(bridge, mpss);
+		pci_info(dev, "Upstream bridge's Max Payload Size set to %d (was %d, max %d)\n",
+			 mpss, p_mps, 128 << bridge->pcie_mpss);
+		p_mps = pcie_get_mps(bridge);
+	}
+
 	rc = pcie_set_mps(dev, p_mps);
 	if (rc) {
 		pci_warn(dev, "can't set Max Payload Size to %d; if necessary, use \"pci=pcie_bus_safe\" and report a bug\n",
@@ -1756,7 +1768,7 @@ static void pci_configure_mps(struct pci_dev *dev)
 	}
 
 	pci_info(dev, "Max Payload Size set to %d (was %d, max %d)\n",
-		 p_mps, mps, 128 << dev->pcie_mpss);
+		 p_mps, mps, mpss);
 }
 
 static struct hpp_type0 pci_default_type0 = {
@@ -2156,7 +2168,7 @@ static bool pci_bus_wait_crs(struct pci_bus *bus, int devfn, u32 *l,
 	return true;
 }
 
-bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l,
+bool pci_bus_generic_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l,
 					int timeout)
 {
 	if (pci_bus_read_config_dword(bus, devfn, PCI_VENDOR_ID, l))
@@ -2172,6 +2184,24 @@ bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l,
 
 	return true;
 }
+
+bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l,
+				int timeout)
+{
+#ifdef CONFIG_PCI_QUIRKS
+	struct pci_dev *bridge = bus->self;
+
+	/*
+	 * Certain IDT switches have an issue where they improperly trigger
+	 * ACS Source Validation errors on completions for config reads.
+	 */
+	if (bridge && bridge->vendor == PCI_VENDOR_ID_IDT &&
+	    bridge->device == 0x80b5)
+		return pci_idt_bus_quirk(bus, devfn, l, timeout);
+#endif
+
+	return pci_bus_generic_read_dev_vendor_id(bus, devfn, l, timeout);
+}
 EXPORT_SYMBOL(pci_bus_read_dev_vendor_id);
 
 /*
@@ -2205,6 +2235,25 @@ static struct pci_dev *pci_scan_device(struct pci_bus *bus, int devfn)
 	return dev;
 }
 
+static void pcie_report_downtraining(struct pci_dev *dev)
+{
+	if (!pci_is_pcie(dev))
+		return;
+
+	/* Look from the device up to avoid downstream ports with no devices */
+	if ((pci_pcie_type(dev) != PCI_EXP_TYPE_ENDPOINT) &&
+	    (pci_pcie_type(dev) != PCI_EXP_TYPE_LEG_END) &&
+	    (pci_pcie_type(dev) != PCI_EXP_TYPE_UPSTREAM))
+		return;
+
+	/* Multi-function PCIe devices share the same link/status */
+	if (PCI_FUNC(dev->devfn) != 0 || dev->is_virtfn)
+		return;
+
+	/* Print link status only if the device is constrained by the fabric */
+	__pcie_print_link_status(dev, false);
+}
+
 static void pci_init_capabilities(struct pci_dev *dev)
 {
 	/* Enhanced Allocation */
@@ -2240,6 +2289,8 @@ static void pci_init_capabilities(struct pci_dev *dev)
 	/* Advanced Error Reporting */
 	pci_aer_init(dev);
 
+	pcie_report_downtraining(dev);
+
 	if (pci_probe_reset_function(dev) == 0)
 		dev->reset_fn = 1;
 }

drivers/pci/quirks.c

@@ -4753,3 +4753,58 @@ DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_AMD, PCI_ANY_ID,
 			      PCI_CLASS_MULTIMEDIA_HD_AUDIO, 8, quirk_gpu_hda);
 DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
 			      PCI_CLASS_MULTIMEDIA_HD_AUDIO, 8, quirk_gpu_hda);
+
+/*
+ * Some IDT switches incorrectly flag an ACS Source Validation error on
+ * completions for config read requests even though PCIe r4.0, sec
+ * 6.12.1.1, says that completions are never affected by ACS Source
+ * Validation.  Here's the text of IDT 89H32H8G3-YC, erratum #36:
+ *
+ *   Item #36 - Downstream port applies ACS Source Validation to Completions
+ *   Section 6.12.1.1 of the PCI Express Base Specification 3.1 states that
+ *   completions are never affected by ACS Source Validation.  However,
+ *   completions received by a downstream port of the PCIe switch from a
+ *   device that has not yet captured a PCIe bus number are incorrectly
+ *   dropped by ACS Source Validation by the switch downstream port.
+ *
+ * The workaround suggested by IDT is to issue a config write to the
+ * downstream device before issuing the first config read.  This allows the
+ * downstream device to capture its bus and device numbers (see PCIe r4.0,
+ * sec 2.2.9), thus avoiding the ACS error on the completion.
+ *
+ * However, we don't know when the device is ready to accept the config
+ * write, so we do config reads until we receive a non-Config Request Retry
+ * Status, then do the config write.
+ *
+ * To avoid hitting the erratum when doing the config reads, we disable ACS
+ * SV around this process.
+ */
+int pci_idt_bus_quirk(struct pci_bus *bus, int devfn, u32 *l, int timeout)
+{
+	int pos;
+	u16 ctrl = 0;
+	bool found;
+	struct pci_dev *bridge = bus->self;
+
+	pos = pci_find_ext_capability(bridge, PCI_EXT_CAP_ID_ACS);
+
+	/* Disable ACS SV before initial config reads */
+	if (pos) {
+		pci_read_config_word(bridge, pos + PCI_ACS_CTRL, &ctrl);
+		if (ctrl & PCI_ACS_SV)
+			pci_write_config_word(bridge, pos + PCI_ACS_CTRL,
+					      ctrl & ~PCI_ACS_SV);
+	}
+
+	found = pci_bus_generic_read_dev_vendor_id(bus, devfn, l, timeout);
+
+	/* Write Vendor ID (read-only) so the endpoint latches its bus/dev */
+	if (found)
+		pci_bus_write_config_word(bus, devfn, PCI_VENDOR_ID, 0);
+
+	/* Re-enable ACS_SV if it was previously enabled */
+	if (ctrl & PCI_ACS_SV)
+		pci_write_config_word(bridge, pos + PCI_ACS_CTRL, ctrl);
+
+	return found;
+}