1 files changed, 255 insertions, 94 deletions

diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 1325fbae2f28..e6a34db77826 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -9,6 +9,8 @@
 #include <linux/pci.h>
 #include <linux/msi.h>
 #include <linux/of_pci.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
 #include <linux/pci_hotplug.h>
 #include <linux/slab.h>
 #include <linux/module.h>
@@ -95,7 +97,7 @@ static void release_pcibus_dev(struct device *dev)
 	kfree(pci_bus);
 }
 
-static struct class pcibus_class = {
+static const struct class pcibus_class = {
 	.name		= "pci_bus",
 	.dev_release	= &release_pcibus_dev,
 	.dev_groups	= pcibus_groups,
@@ -165,40 +167,66 @@ static inline unsigned long decode_bar(struct pci_dev *dev, u32 bar)
 #define PCI_COMMAND_DECODE_ENABLE	(PCI_COMMAND_MEMORY | PCI_COMMAND_IO)
 
 /**
+ * __pci_size_bars - Read the raw BAR mask for a range of PCI BARs
+ * @dev: the PCI device
+ * @count: number of BARs to size
+ * @pos: starting config space position
+ * @sizes: array to store mask values
+ * @rom: indicate whether to use ROM mask, which avoids enabling ROM BARs
+ *
+ * Provided @sizes array must be sufficiently sized to store results for
+ * @count u32 BARs.  Caller is responsible for disabling decode to specified
+ * BAR range around calling this function.  This function is intended to avoid
+ * disabling decode around sizing each BAR individually, which can result in
+ * non-trivial overhead in virtualized environments with very large PCI BARs.
+ */
+static void __pci_size_bars(struct pci_dev *dev, int count,
+			    unsigned int pos, u32 *sizes, bool rom)
+{
+	u32 orig, mask = rom ? PCI_ROM_ADDRESS_MASK : ~0;
+	int i;
+
+	for (i = 0; i < count; i++, pos += 4, sizes++) {
+		pci_read_config_dword(dev, pos, &orig);
+		pci_write_config_dword(dev, pos, mask);
+		pci_read_config_dword(dev, pos, sizes);
+		pci_write_config_dword(dev, pos, orig);
+	}
+}
+
+void __pci_size_stdbars(struct pci_dev *dev, int count,
+			unsigned int pos, u32 *sizes)
+{
+	__pci_size_bars(dev, count, pos, sizes, false);
+}
+
+static void __pci_size_rom(struct pci_dev *dev, unsigned int pos, u32 *sizes)
+{
+	__pci_size_bars(dev, 1, pos, sizes, true);
+}
+
+/**
  * __pci_read_base - Read a PCI BAR
  * @dev: the PCI device
  * @type: type of the BAR
  * @res: resource buffer to be filled in
  * @pos: BAR position in the config space
+ * @sizes: array of one or more pre-read BAR masks
  *
  * Returns 1 if the BAR is 64-bit, or 0 if 32-bit.
  */
 int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
-		    struct resource *res, unsigned int pos)
+		    struct resource *res, unsigned int pos, u32 *sizes)
 {
-	u32 l = 0, sz = 0, mask;
+	u32 l = 0, sz;
 	u64 l64, sz64, mask64;
-	u16 orig_cmd;
 	struct pci_bus_region region, inverted_region;
 	const char *res_name = pci_resource_name(dev, res - dev->resource);
 
-	mask = type ? PCI_ROM_ADDRESS_MASK : ~0;
-
-	/* No printks while decoding is disabled! */
-	if (!dev->mmio_always_on) {
-		pci_read_config_word(dev, PCI_COMMAND, &orig_cmd);
-		if (orig_cmd & PCI_COMMAND_DECODE_ENABLE) {
-			pci_write_config_word(dev, PCI_COMMAND,
-				orig_cmd & ~PCI_COMMAND_DECODE_ENABLE);
-		}
-	}
-
 	res->name = pci_name(dev);
 
 	pci_read_config_dword(dev, pos, &l);
-	pci_write_config_dword(dev, pos, l | mask);
-	pci_read_config_dword(dev, pos, &sz);
-	pci_write_config_dword(dev, pos, l);
+	sz = sizes[0];
 
 	/*
 	 * All bits set in sz means the device isn't working properly.
@@ -238,18 +266,13 @@ int __pci_read_base(struct pci_dev *dev, enum pci_bar_type type,
 
 	if (res->flags & IORESOURCE_MEM_64) {
 		pci_read_config_dword(dev, pos + 4, &l);
-		pci_write_config_dword(dev, pos + 4, ~0);
-		pci_read_config_dword(dev, pos + 4, &sz);
-		pci_write_config_dword(dev, pos + 4, l);
+		sz = sizes[1];
 
 		l64 |= ((u64)l << 32);
 		sz64 |= ((u64)sz << 32);
 		mask64 |= ((u64)~0 << 32);
 	}
 
-	if (!dev->mmio_always_on && (orig_cmd & PCI_COMMAND_DECODE_ENABLE))
-		pci_write_config_word(dev, PCI_COMMAND, orig_cmd);
-
 	if (!sz64)
 		goto fail;
 
@@ -318,9 +341,14 @@ out:
 	return (res->flags & IORESOURCE_MEM_64) ? 1 : 0;
 }
 
-static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom)
+static __always_inline void pci_read_bases(struct pci_dev *dev,
+					   unsigned int howmany, int rom)
 {
+	u32 rombar, stdbars[PCI_STD_NUM_BARS];
 	unsigned int pos, reg;
+	u16 orig_cmd;
+
+	BUILD_BUG_ON(statically_true(howmany > PCI_STD_NUM_BARS));
 
 	if (dev->non_compliant_bars)
 		return;
@@ -329,10 +357,28 @@ static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom)
 	if (dev->is_virtfn)
 		return;
 
+	/* No printks while decoding is disabled! */
+	if (!dev->mmio_always_on) {
+		pci_read_config_word(dev, PCI_COMMAND, &orig_cmd);
+		if (orig_cmd & PCI_COMMAND_DECODE_ENABLE) {
+			pci_write_config_word(dev, PCI_COMMAND,
+				orig_cmd & ~PCI_COMMAND_DECODE_ENABLE);
+		}
+	}
+
+	__pci_size_stdbars(dev, howmany, PCI_BASE_ADDRESS_0, stdbars);
+	if (rom)
+		__pci_size_rom(dev, rom, &rombar);
+
+	if (!dev->mmio_always_on &&
+	    (orig_cmd & PCI_COMMAND_DECODE_ENABLE))
+		pci_write_config_word(dev, PCI_COMMAND, orig_cmd);
+
 	for (pos = 0; pos < howmany; pos++) {
 		struct resource *res = &dev->resource[pos];
 		reg = PCI_BASE_ADDRESS_0 + (pos << 2);
-		pos += __pci_read_base(dev, pci_bar_unknown, res, reg);
+		pos += __pci_read_base(dev, pci_bar_unknown,
+				       res, reg, &stdbars[pos]);
 	}
 
 	if (rom) {
@@ -340,7 +386,7 @@ static void pci_read_bases(struct pci_dev *dev, unsigned int howmany, int rom)
 		dev->rom_base_reg = rom;
 		res->flags = IORESOURCE_MEM | IORESOURCE_PREFETCH |
 				IORESOURCE_READONLY | IORESOURCE_SIZEALIGN;
-		__pci_read_base(dev, pci_bar_mem32, res, rom);
+		__pci_read_base(dev, pci_bar_mem32, res, rom, &rombar);
 	}
 }
 
@@ -543,15 +589,15 @@ void pci_read_bridge_bases(struct pci_bus *child)
 	pci_read_bridge_mmio(child->self, child->resource[1], false);
 	pci_read_bridge_mmio_pref(child->self, child->resource[2], false);
 
-	if (dev->transparent) {
-		pci_bus_for_each_resource(child->parent, res) {
-			if (res && res->flags) {
-				pci_bus_add_resource(child, res,
-						     PCI_SUBTRACTIVE_DECODE);
-				pci_info(dev, "  bridge window %pR (subtractive decode)\n",
-					   res);
-			}
-		}
+	if (!dev->transparent)
+		return;
+
+	pci_bus_for_each_resource(child->parent, res) {
+		if (!res || !res->flags)
+			continue;
+
+		pci_bus_add_resource(child, res);
+		pci_info(dev, "  bridge window %pR (subtractive decode)\n", res);
 	}
 }
 
@@ -742,9 +788,14 @@ const char *pci_speed_string(enum pci_bus_speed speed)
 }
 EXPORT_SYMBOL_GPL(pci_speed_string);
 
-void pcie_update_link_speed(struct pci_bus *bus, u16 linksta)
+void pcie_update_link_speed(struct pci_bus *bus)
 {
-	bus->cur_bus_speed = pcie_link_speed[linksta & PCI_EXP_LNKSTA_CLS];
+	struct pci_dev *bridge = bus->self;
+	u16 linksta, linksta2;
+
+	pcie_capability_read_word(bridge, PCI_EXP_LNKSTA, &linksta);
+	pcie_capability_read_word(bridge, PCI_EXP_LNKSTA2, &linksta2);
+	__pcie_update_link_speed(bus, linksta, linksta2);
 }
 EXPORT_SYMBOL_GPL(pcie_update_link_speed);
 
@@ -827,13 +878,11 @@ static void pci_set_bus_speed(struct pci_bus *bus)
 
 	if (pci_is_pcie(bridge)) {
 		u32 linkcap;
-		u16 linksta;
 
 		pcie_capability_read_dword(bridge, PCI_EXP_LNKCAP, &linkcap);
 		bus->max_bus_speed = pcie_link_speed[linkcap & PCI_EXP_LNKCAP_SLS];
 
-		pcie_capability_read_word(bridge, PCI_EXP_LNKSTA, &linksta);
-		pcie_update_link_speed(bus, linksta);
+		pcie_update_link_speed(bus);
 	}
 }
 
@@ -889,6 +938,17 @@ static void pci_set_bus_msi_domain(struct pci_bus *bus)
 	dev_set_msi_domain(&bus->dev, d);
 }
 
+static bool pci_preserve_config(struct pci_host_bridge *host_bridge)
+{
+	if (pci_acpi_preserve_config(host_bridge))
+		return true;
+
+	if (host_bridge->dev.parent && host_bridge->dev.parent->of_node)
+		return of_pci_preserve_config(host_bridge->dev.parent->of_node);
+
+	return false;
+}
+
 static int pci_register_host_bridge(struct pci_host_bridge *bridge)
 {
 	struct device *parent = bridge->dev.parent;
@@ -897,6 +957,7 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge)
 	resource_size_t offset, next_offset;
 	LIST_HEAD(resources);
 	struct resource *res, *next_res;
+	bool bus_registered = false;
 	char addr[64], *fmt;
 	const char *name;
 	int err;
@@ -939,10 +1000,9 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge)
 	/* Temporarily move resources off the list */
 	list_splice_init(&bridge->windows, &resources);
 	err = device_add(&bridge->dev);
-	if (err) {
-		put_device(&bridge->dev);
+	if (err)
 		goto free;
-	}
+
 	bus->bridge = get_device(&bridge->dev);
 	device_enable_async_suspend(bus->bridge);
 	pci_set_bus_of_node(bus);
@@ -961,6 +1021,7 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge)
 	name = dev_name(&bus->dev);
 
 	err = device_register(&bus->dev);
+	bus_registered = true;
 	if (err)
 		goto unregister;
 
@@ -983,6 +1044,9 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge)
 	if (nr_node_ids > 1 && pcibus_to_node(bus) == NUMA_NO_NODE)
 		dev_warn(&bus->dev, "Unknown NUMA node; performance will be reduced\n");
 
+	/* Check if the boot configuration by FW needs to be preserved */
+	bridge->preserve_config = pci_preserve_config(bridge);
+
 	/* Coalesce contiguous windows */
 	resource_list_for_each_entry_safe(window, n, &resources) {
 		if (list_is_last(&window->node, &resources))
@@ -1018,7 +1082,7 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge)
 		if (res->flags & IORESOURCE_BUS)
 			pci_bus_insert_busn_res(bus, bus->number, res->end);
 		else
-			pci_bus_add_resource(bus, res, 0);
+			pci_bus_add_resource(bus, res);
 
 		if (offset) {
 			if (resource_type(res) == IORESOURCE_IO)
@@ -1035,6 +1099,8 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge)
 		dev_info(&bus->dev, "root bus resource %pR%s\n", res, addr);
 	}
 
+	of_pci_make_host_bridge_node(bridge);
+
 	down_write(&pci_bus_sem);
 	list_add_tail(&bus->node, &pci_root_buses);
 	up_write(&pci_bus_sem);
@@ -1044,12 +1110,15 @@ static int pci_register_host_bridge(struct pci_host_bridge *bridge)
 unregister:
 	put_device(&bridge->dev);
 	device_del(&bridge->dev);
-
 free:
 #ifdef CONFIG_PCI_DOMAINS_GENERIC
-	pci_bus_release_domain_nr(bus, parent);
+	pci_bus_release_domain_nr(parent, bus->domain_nr);
 #endif
-	kfree(bus);
+	if (bus_registered)
+		put_device(&bus->dev);
+	else
+		kfree(bus);
+
 	return err;
 }
 
@@ -1158,7 +1227,10 @@ static struct pci_bus *pci_alloc_child_bus(struct pci_bus *parent,
 add_dev:
 	pci_set_bus_msi_domain(child);
 	ret = device_register(&child->dev);
-	WARN_ON(ret < 0);
+	if (WARN_ON(ret < 0)) {
+		put_device(&child->dev);
+		return NULL;
+	}
 
 	pcibios_add_bus(child);
 
@@ -1189,15 +1261,17 @@ struct pci_bus *pci_add_new_bus(struct pci_bus *parent, struct pci_dev *dev,
 }
 EXPORT_SYMBOL(pci_add_new_bus);
 
-static void pci_enable_crs(struct pci_dev *pdev)
+static void pci_enable_rrs_sv(struct pci_dev *pdev)
 {
 	u16 root_cap = 0;
 
-	/* Enable CRS Software Visibility if supported */
+	/* Enable Configuration RRS Software Visibility if supported */
 	pcie_capability_read_word(pdev, PCI_EXP_RTCAP, &root_cap);
-	if (root_cap & PCI_EXP_RTCAP_CRSVIS)
+	if (root_cap & PCI_EXP_RTCAP_RRS_SV) {
 		pcie_capability_set_word(pdev, PCI_EXP_RTCTL,
-					 PCI_EXP_RTCTL_CRSSVE);
+					 PCI_EXP_RTCTL_RRS_SVE);
+		pdev->config_rrs_sv = 1;
+	}
 }
 
 static unsigned int pci_scan_child_bus_extend(struct pci_bus *bus,
@@ -1312,8 +1386,6 @@ static int pci_scan_bridge_extend(struct pci_bus *bus, struct pci_dev *dev,
 	pci_write_config_word(dev, PCI_BRIDGE_CONTROL,
 			      bctl & ~PCI_BRIDGE_CTL_MASTER_ABORT);
 
-	pci_enable_crs(dev);
-
 	if ((secondary || subordinate) && !pcibios_assign_all_busses() &&
 	    !is_cardbus && !broken) {
 		unsigned int cmax, buses;
@@ -1482,6 +1554,9 @@ static int pci_scan_bridge_extend(struct pci_bus *bus, struct pci_dev *dev,
 	}
 
 out:
+	/* Clear errors in the Secondary Status Register */
+	pci_write_config_word(dev, PCI_SEC_STATUS, 0xffff);
+
 	pci_write_config_word(dev, PCI_BRIDGE_CONTROL, bctl);
 
 	pm_runtime_put(&dev->dev);
@@ -1551,6 +1626,11 @@ void set_pcie_port_type(struct pci_dev *pdev)
 	pdev->pcie_cap = pos;
 	pci_read_config_word(pdev, pos + PCI_EXP_FLAGS, &reg16);
 	pdev->pcie_flags_reg = reg16;
+
+	type = pci_pcie_type(pdev);
+	if (type == PCI_EXP_TYPE_ROOT_PORT)
+		pci_enable_rrs_sv(pdev);
+
 	pci_read_config_dword(pdev, pos + PCI_EXP_DEVCAP, &pdev->devcap);
 	pdev->pcie_mpss = FIELD_GET(PCI_EXP_DEVCAP_PAYLOAD, pdev->devcap);
 
@@ -1567,7 +1647,6 @@ void set_pcie_port_type(struct pci_dev *pdev)
 	 * correctly so detect impossible configurations here and correct
 	 * the port type accordingly.
 	 */
-	type = pci_pcie_type(pdev);
 	if (type == PCI_EXP_TYPE_DOWNSTREAM) {
 		/*
 		 * If pdev claims to be downstream port but the parent
@@ -1614,23 +1693,33 @@ static void set_pcie_thunderbolt(struct pci_dev *dev)
 
 static void set_pcie_untrusted(struct pci_dev *dev)
 {
-	struct pci_dev *parent;
+	struct pci_dev *parent = pci_upstream_bridge(dev);
 
+	if (!parent)
+		return;
 	/*
-	 * If the upstream bridge is untrusted we treat this device
+	 * If the upstream bridge is untrusted we treat this device as
 	 * untrusted as well.
 	 */
-	parent = pci_upstream_bridge(dev);
-	if (parent && (parent->untrusted || parent->external_facing))
+	if (parent->untrusted) {
+		dev->untrusted = true;
+		return;
+	}
+
+	if (arch_pci_dev_is_removable(dev)) {
+		pci_dbg(dev, "marking as untrusted\n");
 		dev->untrusted = true;
+	}
 }
 
 static void pci_set_removable(struct pci_dev *dev)
 {
 	struct pci_dev *parent = pci_upstream_bridge(dev);
 
+	if (!parent)
+		return;
 	/*
-	 * We (only) consider everything downstream from an external_facing
+	 * We (only) consider everything tunneled below an external_facing
 	 * device to be removable by the user. We're mainly concerned with
 	 * consumer platforms with user accessible thunderbolt ports that are
 	 * vulnerable to DMA attacks, and we expect those ports to be marked by
@@ -1640,9 +1729,15 @@ static void pci_set_removable(struct pci_dev *dev)
 	 * accessible to user / may not be removed by end user, and thus not
 	 * exposed as "removable" to userspace.
 	 */
-	if (parent &&
-	    (parent->external_facing || dev_is_removable(&parent->dev)))
+	if (dev_is_removable(&parent->dev)) {
 		dev_set_removable(&dev->dev, DEVICE_REMOVABLE);
+		return;
+	}
+
+	if (arch_pci_dev_is_removable(dev)) {
+		pci_dbg(dev, "marking as removable\n");
+		dev_set_removable(&dev->dev, DEVICE_REMOVABLE);
+	}
 }
 
 /**
@@ -1928,6 +2023,9 @@ int pci_setup_device(struct pci_dev *dev)
 
 	set_pcie_untrusted(dev);
 
+	if (pci_is_pcie(dev))
+		dev->supported_speeds = pcie_get_supported_speeds(dev);
+
 	/* "Unknown power state" */
 	dev->current_state = PCI_UNKNOWN;
 
@@ -1960,7 +2058,7 @@ int pci_setup_device(struct pci_dev *dev)
 		if (class == PCI_CLASS_BRIDGE_PCI)
 			goto bad;
 		pci_read_irq(dev);
-		pci_read_bases(dev, 6, PCI_ROM_ADDRESS);
+		pci_read_bases(dev, PCI_STD_NUM_BARS, PCI_ROM_ADDRESS);
 
 		pci_subsystem_ids(dev, &dev->subsystem_vendor, &dev->subsystem_device);
 
@@ -2211,8 +2309,8 @@ static void pci_configure_relaxed_ordering(struct pci_dev *dev)
 
 static void pci_configure_eetlp_prefix(struct pci_dev *dev)
 {
-#ifdef CONFIG_PCI_PASID
 	struct pci_dev *bridge;
+	unsigned int eetlp_max;
 	int pcie_type;
 	u32 cap;
 
@@ -2224,15 +2322,19 @@ static void pci_configure_eetlp_prefix(struct pci_dev *dev)
 		return;
 
 	pcie_type = pci_pcie_type(dev);
+
+	eetlp_max = FIELD_GET(PCI_EXP_DEVCAP2_EE_PREFIX_MAX, cap);
+	/* 00b means 4 */
+	eetlp_max = eetlp_max ?: 4;
+
 	if (pcie_type == PCI_EXP_TYPE_ROOT_PORT ||
 	    pcie_type == PCI_EXP_TYPE_RC_END)
-		dev->eetlp_prefix_path = 1;
+		dev->eetlp_prefix_max = eetlp_max;
 	else {
 		bridge = pci_upstream_bridge(dev);
-		if (bridge && bridge->eetlp_prefix_path)
-			dev->eetlp_prefix_path = 1;
+		if (bridge && bridge->eetlp_prefix_max)
+			dev->eetlp_prefix_max = eetlp_max;
 	}
-#endif
 }
 
 static void pci_configure_serr(struct pci_dev *dev)
@@ -2326,28 +2428,23 @@ struct pci_dev *pci_alloc_dev(struct pci_bus *bus)
 }
 EXPORT_SYMBOL(pci_alloc_dev);
 
-static bool pci_bus_crs_vendor_id(u32 l)
-{
-	return (l & 0xffff) == PCI_VENDOR_ID_PCI_SIG;
-}
-
-static bool pci_bus_wait_crs(struct pci_bus *bus, int devfn, u32 *l,
+static bool pci_bus_wait_rrs(struct pci_bus *bus, int devfn, u32 *l,
 			     int timeout)
 {
 	int delay = 1;
 
-	if (!pci_bus_crs_vendor_id(*l))
-		return true;	/* not a CRS completion */
+	if (!pci_bus_rrs_vendor_id(*l))
+		return true;	/* not a Configuration RRS completion */
 
 	if (!timeout)
-		return false;	/* CRS, but caller doesn't want to wait */
+		return false;	/* RRS, but caller doesn't want to wait */
 
 	/*
 	 * We got the reserved Vendor ID that indicates a completion with
-	 * Configuration Request Retry Status (CRS).  Retry until we get a
+	 * Configuration Request Retry Status (RRS).  Retry until we get a
 	 * valid Vendor ID or we time out.
 	 */
-	while (pci_bus_crs_vendor_id(*l)) {
+	while (pci_bus_rrs_vendor_id(*l)) {
 		if (delay > timeout) {
 			pr_warn("pci %04x:%02x:%02x.%d: not ready after %dms; giving up\n",
 				pci_domain_nr(bus), bus->number,
@@ -2386,8 +2483,8 @@ bool pci_bus_generic_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l,
 	    *l == 0x0000ffff || *l == 0xffff0000)
 		return false;
 
-	if (pci_bus_crs_vendor_id(*l))
-		return pci_bus_wait_crs(bus, devfn, l, timeout);
+	if (pci_bus_rrs_vendor_id(*l))
+		return pci_bus_wait_rrs(bus, devfn, l, timeout);
 
 	return true;
 }
@@ -2411,6 +2508,43 @@ bool pci_bus_read_dev_vendor_id(struct pci_bus *bus, int devfn, u32 *l,
 }
 EXPORT_SYMBOL(pci_bus_read_dev_vendor_id);
 
+#if IS_ENABLED(CONFIG_PCI_PWRCTRL)
+static struct platform_device *pci_pwrctrl_create_device(struct pci_bus *bus, int devfn)
+{
+	struct pci_host_bridge *host = pci_find_host_bridge(bus);
+	struct platform_device *pdev;
+	struct device_node *np;
+
+	np = of_pci_find_child_device(dev_of_node(&bus->dev), devfn);
+	if (!np || of_find_device_by_node(np))
+		return NULL;
+
+	/*
+	 * First check whether the pwrctrl device really needs to be created or
+	 * not. This is decided based on at least one of the power supplies
+	 * being defined in the devicetree node of the device.
+	 */
+	if (!of_pci_supply_present(np)) {
+		pr_debug("PCI/pwrctrl: Skipping OF node: %s\n", np->name);
+		return NULL;
+	}
+
+	/* Now create the pwrctrl device */
+	pdev = of_platform_device_create(np, NULL, &host->dev);
+	if (!pdev) {
+		pr_err("PCI/pwrctrl: Failed to create pwrctrl device for node: %s\n", np->name);
+		return NULL;
+	}
+
+	return pdev;
+}
+#else
+static struct platform_device *pci_pwrctrl_create_device(struct pci_bus *bus, int devfn)
+{
+	return NULL;
+}
+#endif
+
 /*
  * Read the config data for a PCI device, sanity-check it,
  * and fill in the dev structure.
@@ -2420,6 +2554,15 @@ static struct pci_dev *pci_scan_device(struct pci_bus *bus, int devfn)
 	struct pci_dev *dev;
 	u32 l;
 
+	/*
+	 * Create pwrctrl device (if required) for the PCI device to handle the
+	 * power state. If the pwrctrl device is created, then skip scanning
+	 * further as the pwrctrl core will rescan the bus after powering on
+	 * the device.
+	 */
+	if (pci_pwrctrl_create_device(bus, devfn))
+		return NULL;
+
 	if (!pci_bus_read_dev_vendor_id(bus, devfn, &l, 60*1000))
 		return NULL;
 
@@ -2481,6 +2624,8 @@ static void pci_init_capabilities(struct pci_dev *dev)
 	pci_dpc_init(dev);		/* Downstream Port Containment */
 	pci_rcec_init(dev);		/* Root Complex Event Collector */
 	pci_doe_init(dev);		/* Data Object Exchange */
+	pci_tph_init(dev);		/* TLP Processing Hints */
+	pci_rebar_init(dev);		/* Resizable BAR */
 
 	pcie_report_downtraining(dev);
 	pci_init_reset_methods(dev);
@@ -2573,9 +2718,12 @@ void pci_device_add(struct pci_dev *dev, struct pci_bus *bus)
 	pci_set_msi_domain(dev);
 
 	/* Notifier could use PCI capabilities */
-	dev->match_driver = false;
 	ret = device_add(&dev->dev);
 	WARN_ON(ret < 0);
+
+	pci_npem_create(dev);
+
+	pci_doe_sysfs_init(dev);
 }
 
 struct pci_dev *pci_scan_single_device(struct pci_bus *bus, int devfn)
@@ -3066,7 +3214,9 @@ int pci_host_probe(struct pci_host_bridge *bridge)
 	struct pci_bus *bus, *child;
 	int ret;
 
+	pci_lock_rescan_remove();
 	ret = pci_scan_root_bus_bridge(bridge);
+	pci_unlock_rescan_remove();
 	if (ret < 0) {
 		dev_err(bridge->dev.parent, "Scanning root bridge failed");
 		return ret;
@@ -3074,22 +3224,33 @@ int pci_host_probe(struct pci_host_bridge *bridge)
 
 	bus = bridge->bus;
 
+	/* If we must preserve the resource configuration, claim now */
+	if (bridge->preserve_config)
+		pci_bus_claim_resources(bus);
+
 	/*
-	 * We insert PCI resources into the iomem_resource and
-	 * ioport_resource trees in either pci_bus_claim_resources()
-	 * or pci_bus_assign_resources().
+	 * Assign whatever was left unassigned. If we didn't claim above,
+	 * this will reassign everything.
 	 */
-	if (pci_has_flag(PCI_PROBE_ONLY)) {
-		pci_bus_claim_resources(bus);
-	} else {
-		pci_bus_size_bridges(bus);
-		pci_bus_assign_resources(bus);
+	pci_assign_unassigned_root_bus_resources(bus);
 
-		list_for_each_entry(child, &bus->children, node)
-			pcie_bus_configure_settings(child);
-	}
+	list_for_each_entry(child, &bus->children, node)
+		pcie_bus_configure_settings(child);
 
+	pci_lock_rescan_remove();
 	pci_bus_add_devices(bus);
+	pci_unlock_rescan_remove();
+
+	/*
+	 * Ensure pm_runtime_enable() is called for the controller drivers
+	 * before calling pci_host_probe(). The PM framework expects that
+	 * if the parent device supports runtime PM, it will be enabled
+	 * before child runtime PM is enabled.
+	 */
+	pm_runtime_set_active(&bridge->dev);
+	pm_runtime_no_callbacks(&bridge->dev);
+	devm_pm_runtime_enable(&bridge->dev);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(pci_host_probe);