Merge tag 'pci-v4.15-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci

Pull PCI updates from Bjorn Helgaas:

  - detach driver before tearing down procfs/sysfs (Alex Williamson)

  - disable PCIe services during shutdown (Sinan Kaya)

  - fix ASPM oops on systems with no Root Ports (Ard Biesheuvel)

  - fix ASPM LTR_L1.2_THRESHOLD programming (Bjorn Helgaas)

  - fix ASPM Common_Mode_Restore_Time computation (Bjorn Helgaas)

  - fix portdrv MSI/MSI-X vector allocation (Dongdong Liu, Bjorn
    Helgaas)

  - report non-fatal AER errors only to the affected endpoint (Gabriele
    Paoloni)

  - distribute bus numbers, MMIO, and I/O space among hotplug bridges to
    allow more devices to be hot-added (Mika Westerberg)

  - fix pciehp races during initialization and surprise link down (Mika
    Westerberg)

  - handle surprise-removed devices in PME handling (Qiang)

  - support resizable BARs for large graphics devices (Christian König)

  - expose SR-IOV offset, stride, and VF device ID via sysfs (Filippo
    Sironi)

  - create SR-IOV virtfn/physfn sysfs links before attaching driver
    (Stuart Hayes)

  - fix SR-IOV "ARI Capable Hierarchy" restore issue (Tony Nguyen)

  - enforce Kconfig IOV/REALLOC dependency (Sascha El-Sharkawy)

  - avoid slot reset if bridge itself is broken (Jan Glauber)

  - clean up pci_reset_function() path (Jan H. Schönherr)

  - make pci_map_rom() fail if the option ROM is invalid (Changbin Du)

  - convert timers to timer_setup() (Kees Cook)

  - move PCI_QUIRKS to PCI bus Kconfig menu (Randy Dunlap)

  - constify pci_dev_type and intel_mid_pci_ops (Bhumika Goyal)

  - remove unnecessary pci_dev, pci_bus, resource, pcibios_set_master()
    declarations (Bjorn Helgaas)

  - fix endpoint framework overflows and BUG()s (Dan Carpenter)

  - fix endpoint framework issues (Kishon Vijay Abraham I)

  - avoid broken Cavium CN8xxx bus reset behavior (David Daney)

  - extend Cavium ACS capability quirks (Vadim Lomovtsev)

  - support Synopsys DesignWare RC in ECAM mode (Ard Biesheuvel)

  - turn off dra7xx clocks cleanly on shutdown (Keerthy)

  - fix Faraday probe error path (Wei Yongjun)

  - support HiSilicon STB SoC PCIe host controller (Jianguo Sun)

  - fix Hyper-V interrupt affinity issue (Dexuan Cui)

  - remove useless ACPI warning for Hyper-V pass-through devices (Vitaly
    Kuznetsov)

  - support multiple MSI on iProc (Sandor Bodo-Merle)

  - support Layerscape LS1012a and LS1046a PCIe host controllers (Hou
    Zhiqiang)

  - fix Layerscape default error response (Minghuan Lian)

  - support MSI on Tango host controller (Marc Gonzalez)

  - support Tegra186 PCIe host controller (Manikanta Maddireddy)

  - use generic accessors on Tegra when possible (Thierry Reding)

  - support V3 Semiconductor PCI host controller (Linus Walleij)

* tag 'pci-v4.15-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci: (85 commits)
  PCI/ASPM: Add L1 Substates definitions
  PCI/ASPM: Reformat ASPM register definitions
  PCI/ASPM: Use correct capability pointer to program LTR_L1.2_THRESHOLD
  PCI/ASPM: Account for downstream device's Port Common_Mode_Restore_Time
  PCI: xgene: Rename xgene_pcie_probe_bridge() to xgene_pcie_probe()
  PCI: xilinx: Rename xilinx_pcie_link_is_up() to xilinx_pcie_link_up()
  PCI: altera: Rename altera_pcie_link_is_up() to altera_pcie_link_up()
  PCI: Fix kernel-doc build warning
  PCI: Fail pci_map_rom() if the option ROM is invalid
  PCI: Move pci_map_rom() error path
  PCI: Move PCI_QUIRKS to the PCI bus menu
  alpha/PCI: Make pdev_save_srm_config() static
  PCI: Remove unused declarations
  PCI: Remove redundant pci_dev, pci_bus, resource declarations
  PCI: Remove redundant pcibios_set_master() declarations
  PCI/PME: Handle invalid data when reading Root Status
  PCI: hv: Use effective affinity mask
  PCI: pciehp: Do not clear Presence Detect Changed during initialization
  PCI: pciehp: Fix race condition handling surprise link down
  PCI: Distribute available resources to hotplug-capable bridges
  ...

15 files changed, 1374 insertions, 145 deletions

diff --git a/drivers/pci/host/Kconfig b/drivers/pci/host/Kconfig
index b868803792d8..38d12980db0f 100644
--- a/drivers/pci/host/Kconfig
+++ b/drivers/pci/host/Kconfig
@@ -95,6 +95,12 @@ config PCI_XGENE_MSI
 	  Say Y here if you want PCIe MSI support for the APM X-Gene v1 SoC.
 	  This MSI driver supports 5 PCIe ports on the APM X-Gene v1 SoC.
 
+config PCI_V3_SEMI
+	bool "V3 Semiconductor PCI controller"
+	depends on OF
+	depends on ARM
+	default ARCH_INTEGRATOR_AP
+
 config PCI_VERSATILE
 	bool "ARM Versatile PB PCI controller"
 	depends on ARCH_VERSATILE
diff --git a/drivers/pci/host/Makefile b/drivers/pci/host/Makefile
index 95f5b80ca52a..34ec1d88f961 100644
--- a/drivers/pci/host/Makefile
+++ b/drivers/pci/host/Makefile
@@ -10,6 +10,7 @@ obj-$(CONFIG_PCI_HOST_COMMON) += pci-host-common.o
 obj-$(CONFIG_PCI_HOST_GENERIC) += pci-host-generic.o
 obj-$(CONFIG_PCIE_XILINX) += pcie-xilinx.o
 obj-$(CONFIG_PCIE_XILINX_NWL) += pcie-xilinx-nwl.o
+obj-$(CONFIG_PCI_V3_SEMI) += pci-v3-semi.o
 obj-$(CONFIG_PCI_XGENE_MSI) += pci-xgene-msi.o
 obj-$(CONFIG_PCI_VERSATILE) += pci-versatile.o
 obj-$(CONFIG_PCIE_IPROC) += pcie-iproc.o
diff --git a/drivers/pci/host/pci-ftpci100.c b/drivers/pci/host/pci-ftpci100.c
index 4ea7d2ebcc5c..b9617d1c1d48 100644
--- a/drivers/pci/host/pci-ftpci100.c
+++ b/drivers/pci/host/pci-ftpci100.c
@@ -371,24 +371,6 @@ static int faraday_pci_setup_cascaded_irq(struct faraday_pci *p)
 	return 0;
 }
 
-static int pci_dma_range_parser_init(struct of_pci_range_parser *parser,
-				     struct device_node *node)
-{
-	const int na = 3, ns = 2;
-	int rlen;
-
-	parser->node = node;
-	parser->pna = of_n_addr_cells(node);
-	parser->np = parser->pna + na + ns;
-
-	parser->range = of_get_property(node, "dma-ranges", &rlen);
-	if (!parser->range)
-		return -ENOENT;
-	parser->end = parser->range + rlen / sizeof(__be32);
-
-	return 0;
-}
-
 static int faraday_pci_parse_map_dma_ranges(struct faraday_pci *p,
 					    struct device_node *np)
 {
@@ -403,7 +385,7 @@ static int faraday_pci_parse_map_dma_ranges(struct faraday_pci *p,
 	int i = 0;
 	u32 val;
 
-	if (pci_dma_range_parser_init(&parser, np)) {
+	if (of_pci_dma_range_parser_init(&parser, np)) {
 		dev_err(dev, "missing dma-ranges property\n");
 		return -EINVAL;
 	}
@@ -482,7 +464,7 @@ static int faraday_pci_probe(struct platform_device *pdev)
 	}
 	p->bus_clk = devm_clk_get(dev, "PCICLK");
 	if (IS_ERR(p->bus_clk))
-		return PTR_ERR(clk);
+		return PTR_ERR(p->bus_clk);
 	ret = clk_prepare_enable(p->bus_clk);
 	if (ret) {
 		dev_err(dev, "could not prepare PCICLK\n");
diff --git a/drivers/pci/host/pci-host-generic.c b/drivers/pci/host/pci-host-generic.c
index 7d709a7e0aa8..2f05511ce718 100644
--- a/drivers/pci/host/pci-host-generic.c
+++ b/drivers/pci/host/pci-host-generic.c
@@ -35,6 +35,40 @@ static struct pci_ecam_ops gen_pci_cfg_cam_bus_ops = {
 	}
 };
 
+static bool pci_dw_valid_device(struct pci_bus *bus, unsigned int devfn)
+{
+	struct pci_config_window *cfg = bus->sysdata;
+
+	/*
+	 * The Synopsys DesignWare PCIe controller in ECAM mode will not filter
+	 * type 0 config TLPs sent to devices 1 and up on its downstream port,
+	 * resulting in devices appearing multiple times on bus 0 unless we
+	 * filter out those accesses here.
+	 */
+	if (bus->number == cfg->busr.start && PCI_SLOT(devfn) > 0)
+		return false;
+
+	return true;
+}
+
+static void __iomem *pci_dw_ecam_map_bus(struct pci_bus *bus,
+					 unsigned int devfn, int where)
+{
+	if (!pci_dw_valid_device(bus, devfn))
+		return NULL;
+
+	return pci_ecam_map_bus(bus, devfn, where);
+}
+
+static struct pci_ecam_ops pci_dw_ecam_bus_ops = {
+	.bus_shift	= 20,
+	.pci_ops	= {
+		.map_bus	= pci_dw_ecam_map_bus,
+		.read		= pci_generic_config_read,
+		.write		= pci_generic_config_write,
+	}
+};
+
 static const struct of_device_id gen_pci_of_match[] = {
 	{ .compatible = "pci-host-cam-generic",
 	  .data = &gen_pci_cfg_cam_bus_ops },
@@ -42,6 +76,15 @@ static const struct of_device_id gen_pci_of_match[] = {
 	{ .compatible = "pci-host-ecam-generic",
 	  .data = &pci_generic_ecam_ops },
 
+	{ .compatible = "marvell,armada8k-pcie-ecam",
+	  .data = &pci_dw_ecam_bus_ops },
+
+	{ .compatible = "socionext,synquacer-pcie-ecam",
+	  .data = &pci_dw_ecam_bus_ops },
+
+	{ .compatible = "snps,dw-pcie-ecam",
+	  .data = &pci_dw_ecam_bus_ops },
+
 	{ },
 };
 
diff --git a/drivers/pci/host/pci-hyperv.c b/drivers/pci/host/pci-hyperv.c
index 0fe3ea164ee5..04dac6a42c9f 100644
--- a/drivers/pci/host/pci-hyperv.c
+++ b/drivers/pci/host/pci-hyperv.c
@@ -879,7 +879,7 @@ static void hv_irq_unmask(struct irq_data *data)
 	int cpu;
 	u64 res;
 
-	dest = irq_data_get_affinity_mask(data);
+	dest = irq_data_get_effective_affinity_mask(data);
 	pdev = msi_desc_to_pci_dev(msi_desc);
 	pbus = pdev->bus;
 	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
@@ -1042,6 +1042,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 	struct hv_pci_dev *hpdev;
 	struct pci_bus *pbus;
 	struct pci_dev *pdev;
+	struct cpumask *dest;
 	struct compose_comp_ctxt comp;
 	struct tran_int_desc *int_desc;
 	struct {
@@ -1056,6 +1057,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 	int ret;
 
 	pdev = msi_desc_to_pci_dev(irq_data_get_msi_desc(data));
+	dest = irq_data_get_effective_affinity_mask(data);
 	pbus = pdev->bus;
 	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
 	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn));
@@ -1081,14 +1083,14 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 	switch (pci_protocol_version) {
 	case PCI_PROTOCOL_VERSION_1_1:
 		size = hv_compose_msi_req_v1(&ctxt.int_pkts.v1,
-					irq_data_get_affinity_mask(data),
+					dest,
 					hpdev->desc.win_slot.slot,
 					cfg->vector);
 		break;
 
 	case PCI_PROTOCOL_VERSION_1_2:
 		size = hv_compose_msi_req_v2(&ctxt.int_pkts.v2,
-					irq_data_get_affinity_mask(data),
+					dest,
 					hpdev->desc.win_slot.slot,
 					cfg->vector);
 		break;
diff --git a/drivers/pci/host/pci-rcar-gen2.c b/drivers/pci/host/pci-rcar-gen2.c
index 6f879685fedd..e46de69f0380 100644
--- a/drivers/pci/host/pci-rcar-gen2.c
+++ b/drivers/pci/host/pci-rcar-gen2.c
@@ -293,24 +293,6 @@ static struct pci_ops rcar_pci_ops = {
 	.write	= pci_generic_config_write,
 };
 
-static int pci_dma_range_parser_init(struct of_pci_range_parser *parser,
-				     struct device_node *node)
-{
-	const int na = 3, ns = 2;
-	int rlen;
-
-	parser->node = node;
-	parser->pna = of_n_addr_cells(node);
-	parser->np = parser->pna + na + ns;
-
-	parser->range = of_get_property(node, "dma-ranges", &rlen);
-	if (!parser->range)
-		return -ENOENT;
-
-	parser->end = parser->range + rlen / sizeof(__be32);
-	return 0;
-}
-
 static int rcar_pci_parse_map_dma_ranges(struct rcar_pci_priv *pci,
 					 struct device_node *np)
 {
@@ -320,7 +302,7 @@ static int rcar_pci_parse_map_dma_ranges(struct rcar_pci_priv *pci,
 	int index = 0;
 
 	/* Failure to parse is ok as we fall back to defaults */
-	if (pci_dma_range_parser_init(&parser, np))
+	if (of_pci_dma_range_parser_init(&parser, np))
 		return 0;
 
 	/* Get the dma-ranges from DT */
diff --git a/drivers/pci/host/pci-tegra.c b/drivers/pci/host/pci-tegra.c
index 1987fec1f126..f9d3960dc39f 100644
--- a/drivers/pci/host/pci-tegra.c
+++ b/drivers/pci/host/pci-tegra.c
@@ -159,10 +159,13 @@
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_SINGLE	(0x0 << 20)
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_420	(0x0 << 20)
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_X2_X1	(0x0 << 20)
+#define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_401	(0x0 << 20)
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_DUAL	(0x1 << 20)
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_222	(0x1 << 20)
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_X4_X1	(0x1 << 20)
+#define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_211	(0x1 << 20)
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_411	(0x2 << 20)
+#define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_111	(0x2 << 20)
 
 #define AFI_FUSE			0x104
 #define  AFI_FUSE_PCIE_T0_GEN2_DIS	(1 << 2)
@@ -253,6 +256,7 @@ struct tegra_pcie_soc {
 	bool has_cml_clk;
 	bool has_gen2;
 	bool force_pca_enable;
+	bool program_uphy;
 };
 
 static inline struct tegra_msi *to_tegra_msi(struct msi_controller *chip)
@@ -492,12 +496,32 @@ static void __iomem *tegra_pcie_map_bus(struct pci_bus *bus,
 	return addr;
 }
 
+static int tegra_pcie_config_read(struct pci_bus *bus, unsigned int devfn,
+				  int where, int size, u32 *value)
+{
+	if (bus->number == 0)
+		return pci_generic_config_read32(bus, devfn, where, size,
+						 value);
+
+	return pci_generic_config_read(bus, devfn, where, size, value);
+}
+
+static int tegra_pcie_config_write(struct pci_bus *bus, unsigned int devfn,
+				   int where, int size, u32 value)
+{
+	if (bus->number == 0)
+		return pci_generic_config_write32(bus, devfn, where, size,
+						  value);
+
+	return pci_generic_config_write(bus, devfn, where, size, value);
+}
+
 static struct pci_ops tegra_pcie_ops = {
 	.add_bus = tegra_pcie_add_bus,
 	.remove_bus = tegra_pcie_remove_bus,
 	.map_bus = tegra_pcie_map_bus,
-	.read = pci_generic_config_read32,
-	.write = pci_generic_config_write32,
+	.read = tegra_pcie_config_read,
+	.write = tegra_pcie_config_write,
 };
 
 static unsigned long tegra_pcie_port_get_pex_ctrl(struct tegra_pcie_port *port)
@@ -1013,10 +1037,12 @@ static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 		afi_writel(pcie, value, AFI_FUSE);
 	}
 
-	err = tegra_pcie_phy_power_on(pcie);
-	if (err < 0) {
-		dev_err(dev, "failed to power on PHY(s): %d\n", err);
-		return err;
+	if (soc->program_uphy) {
+		err = tegra_pcie_phy_power_on(pcie);
+		if (err < 0) {
+			dev_err(dev, "failed to power on PHY(s): %d\n", err);
+			return err;
+		}
 	}
 
 	/* take the PCIe interface module out of reset */
@@ -1049,19 +1075,23 @@ static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 static void tegra_pcie_power_off(struct tegra_pcie *pcie)
 {
 	struct device *dev = pcie->dev;
+	const struct tegra_pcie_soc *soc = pcie->soc;
 	int err;
 
 	/* TODO: disable and unprepare clocks? */
 
-	err = tegra_pcie_phy_power_off(pcie);
-	if (err < 0)
-		dev_err(dev, "failed to power off PHY(s): %d\n", err);
+	if (soc->program_uphy) {
+		err = tegra_pcie_phy_power_off(pcie);
+		if (err < 0)
+			dev_err(dev, "failed to power off PHY(s): %d\n", err);
+	}
 
 	reset_control_assert(pcie->pcie_xrst);
 	reset_control_assert(pcie->afi_rst);
 	reset_control_assert(pcie->pex_rst);
 
-	tegra_powergate_power_off(TEGRA_POWERGATE_PCIE);
+	if (!dev->pm_domain)
+		tegra_powergate_power_off(TEGRA_POWERGATE_PCIE);
 
 	err = regulator_bulk_disable(pcie->num_supplies, pcie->supplies);
 	if (err < 0)
@@ -1078,19 +1108,29 @@ static int tegra_pcie_power_on(struct tegra_pcie *pcie)
 	reset_control_assert(pcie->afi_rst);
 	reset_control_assert(pcie->pex_rst);
 
-	tegra_powergate_power_off(TEGRA_POWERGATE_PCIE);
+	if (!dev->pm_domain)
+		tegra_powergate_power_off(TEGRA_POWERGATE_PCIE);
 
 	/* enable regulators */
 	err = regulator_bulk_enable(pcie->num_supplies, pcie->supplies);
 	if (err < 0)
 		dev_err(dev, "failed to enable regulators: %d\n", err);
 
-	err = tegra_powergate_sequence_power_up(TEGRA_POWERGATE_PCIE,
-						pcie->pex_clk,
-						pcie->pex_rst);
-	if (err) {
-		dev_err(dev, "powerup sequence failed: %d\n", err);
-		return err;
+	if (dev->pm_domain) {
+		err = clk_prepare_enable(pcie->pex_clk);
+		if (err) {
+			dev_err(dev, "failed to enable PEX clock: %d\n", err);
+			return err;
+		}
+		reset_control_deassert(pcie->pex_rst);
+	} else {
+		err = tegra_powergate_sequence_power_up(TEGRA_POWERGATE_PCIE,
+							pcie->pex_clk,
+							pcie->pex_rst);
+		if (err) {
+			dev_err(dev, "powerup sequence failed: %d\n", err);
+			return err;
+		}
 	}
 
 	reset_control_deassert(pcie->afi_rst);
@@ -1263,6 +1303,7 @@ static int tegra_pcie_get_resources(struct tegra_pcie *pcie)
 	struct device *dev = pcie->dev;
 	struct platform_device *pdev = to_platform_device(dev);
 	struct resource *pads, *afi, *res;
+	const struct tegra_pcie_soc *soc = pcie->soc;
 	int err;
 
 	err = tegra_pcie_clocks_get(pcie);
@@ -1277,10 +1318,12 @@ static int tegra_pcie_get_resources(struct tegra_pcie *pcie)
 		return err;
 	}
 
-	err = tegra_pcie_phys_get(pcie);
-	if (err < 0) {
-		dev_err(dev, "failed to get PHYs: %d\n", err);
-		return err;
+	if (soc->program_uphy) {
+		err = tegra_pcie_phys_get(pcie);
+		if (err < 0) {
+			dev_err(dev, "failed to get PHYs: %d\n", err);
+			return err;
+		}
 	}
 
 	err = tegra_pcie_power_on(pcie);
@@ -1342,6 +1385,7 @@ poweroff:
 static int tegra_pcie_put_resources(struct tegra_pcie *pcie)
 {
 	struct device *dev = pcie->dev;
+	const struct tegra_pcie_soc *soc = pcie->soc;
 	int err;
 
 	if (pcie->irq > 0)
@@ -1349,9 +1393,11 @@ static int tegra_pcie_put_resources(struct tegra_pcie *pcie)
 
 	tegra_pcie_power_off(pcie);
 
-	err = phy_exit(pcie->phy);
-	if (err < 0)
-		dev_err(dev, "failed to teardown PHY: %d\n", err);
+	if (soc->program_uphy) {
+		err = phy_exit(pcie->phy);
+		if (err < 0)
+			dev_err(dev, "failed to teardown PHY: %d\n", err);
+	}
 
 	return 0;
 }
@@ -1606,8 +1652,32 @@ static int tegra_pcie_get_xbar_config(struct tegra_pcie *pcie, u32 lanes,
 	struct device *dev = pcie->dev;
 	struct device_node *np = dev->of_node;
 
-	if (of_device_is_compatible(np, "nvidia,tegra124-pcie") ||
-	    of_device_is_compatible(np, "nvidia,tegra210-pcie")) {
+	if (of_device_is_compatible(np, "nvidia,tegra186-pcie")) {
+		switch (lanes) {
+		case 0x010004:
+			dev_info(dev, "4x1, 1x1 configuration\n");
+			*xbar = AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_401;
+			return 0;
+
+		case 0x010102:
+			dev_info(dev, "2x1, 1X1, 1x1 configuration\n");
+			*xbar = AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_211;
+			return 0;
+
+		case 0x010101:
+			dev_info(dev, "1x1, 1x1, 1x1 configuration\n");
+			*xbar = AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_111;
+			return 0;
+
+		default:
+			dev_info(dev, "wrong configuration updated in DT, "
+				 "switching to default 2x1, 1x1, 1x1 "
+				 "configuration\n");
+			*xbar = AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_211;
+			return 0;
+		}
+	} else if (of_device_is_compatible(np, "nvidia,tegra124-pcie") ||
+		   of_device_is_compatible(np, "nvidia,tegra210-pcie")) {
 		switch (lanes) {
 		case 0x0000104:
 			dev_info(dev, "4x1, 1x1 configuration\n");
@@ -1727,7 +1797,20 @@ static int tegra_pcie_get_regulators(struct tegra_pcie *pcie, u32 lane_mask)
 	struct device_node *np = dev->of_node;
 	unsigned int i = 0;
 
-	if (of_device_is_compatible(np, "nvidia,tegra210-pcie")) {
+	if (of_device_is_compatible(np, "nvidia,tegra186-pcie")) {
+		pcie->num_supplies = 4;
+
+		pcie->supplies = devm_kcalloc(pcie->dev, pcie->num_supplies,
+					      sizeof(*pcie->supplies),
+					      GFP_KERNEL);
+		if (!pcie->supplies)
+			return -ENOMEM;
+
+		pcie->supplies[i++].supply = "dvdd-pex";
+		pcie->supplies[i++].supply = "hvdd-pex-pll";
+		pcie->supplies[i++].supply = "hvdd-pex";
+		pcie->supplies[i++].supply = "vddio-pexctl-aud";
+	} else if (of_device_is_compatible(np, "nvidia,tegra210-pcie")) {
 		pcie->num_supplies = 6;
 
 		pcie->supplies = devm_kcalloc(pcie->dev, pcie->num_supplies,
@@ -2066,6 +2149,7 @@ static const struct tegra_pcie_soc tegra20_pcie = {
 	.has_cml_clk = false,
 	.has_gen2 = false,
 	.force_pca_enable = false,
+	.program_uphy = true,
 };
 
 static const struct tegra_pcie_soc tegra30_pcie = {
@@ -2081,6 +2165,7 @@ static const struct tegra_pcie_soc tegra30_pcie = {
 	.has_cml_clk = true,
 	.has_gen2 = false,
 	.force_pca_enable = false,
+	.program_uphy = true,
 };
 
 static const struct tegra_pcie_soc tegra124_pcie = {
@@ -2095,6 +2180,7 @@ static const struct tegra_pcie_soc tegra124_pcie = {
 	.has_cml_clk = true,
 	.has_gen2 = true,
 	.force_pca_enable = false,
+	.program_uphy = true,
 };
 
 static const struct tegra_pcie_soc tegra210_pcie = {
@@ -2109,9 +2195,27 @@ static const struct tegra_pcie_soc tegra210_pcie = {
 	.has_cml_clk = true,
 	.has_gen2 = true,
 	.force_pca_enable = true,
+	.program_uphy = true,
+};
+
+static const struct tegra_pcie_soc tegra186_pcie = {
+	.num_ports = 3,
+	.msi_base_shift = 8,
+	.pads_pll_ctl = PADS_PLL_CTL_TEGRA30,
+	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN,
+	.pads_refclk_cfg0 = 0x80b880b8,
+	.pads_refclk_cfg1 = 0x000480b8,
+	.has_pex_clkreq_en = true,
+	.has_pex_bias_ctrl = true,
+	.has_intr_prsnt_sense = true,
+	.has_cml_clk = false,
+	.has_gen2 = true,
+	.force_pca_enable = false,
+	.program_uphy = false,
 };
 
 static const struct of_device_id tegra_pcie_of_match[] = {
+	{ .compatible = "nvidia,tegra186-pcie", .data = &tegra186_pcie },
 	{ .compatible = "nvidia,tegra210-pcie", .data = &tegra210_pcie },
 	{ .compatible = "nvidia,tegra124-pcie", .data = &tegra124_pcie },
 	{ .compatible = "nvidia,tegra30-pcie", .data = &tegra30_pcie },
diff --git a/drivers/pci/host/pci-v3-semi.c b/drivers/pci/host/pci-v3-semi.c
new file mode 100644
index 000000000000..02f6e1e3a421
--- /dev/null
+++ b/drivers/pci/host/pci-v3-semi.c
@@ -0,0 +1,959 @@
+/*
+ * Support for V3 Semiconductor PCI Local Bus to PCI Bridge
+ * Copyright (C) 2017 Linus Walleij <linus.walleij@linaro.org>
+ *
+ * Based on the code from arch/arm/mach-integrator/pci_v3.c
+ * Copyright (C) 1999 ARM Limited
+ * Copyright (C) 2000-2001 Deep Blue Solutions Ltd
+ *
+ * Contributors to the old driver include:
+ * Russell King <linux@armlinux.org.uk>
+ * David A. Rusling <david.rusling@linaro.org> (uHAL, ARM Firmware suite)
+ * Rob Herring <robh@kernel.org>
+ * Liviu Dudau <Liviu.Dudau@arm.com>
+ * Grant Likely <grant.likely@secretlab.ca>
+ * Arnd Bergmann <arnd@arndb.de>
+ * Bjorn Helgaas <bhelgaas@google.com>
+ */
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
+#include <linux/of_pci.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/slab.h>
+#include <linux/bitops.h>
+#include <linux/irq.h>
+#include <linux/mfd/syscon.h>
+#include <linux/regmap.h>
+#include <linux/clk.h>
+
+#define V3_PCI_VENDOR			0x00000000
+#define V3_PCI_DEVICE			0x00000002
+#define V3_PCI_CMD			0x00000004
+#define V3_PCI_STAT			0x00000006
+#define V3_PCI_CC_REV			0x00000008
+#define V3_PCI_HDR_CFG			0x0000000C
+#define V3_PCI_IO_BASE			0x00000010
+#define V3_PCI_BASE0			0x00000014
+#define V3_PCI_BASE1			0x00000018
+#define V3_PCI_SUB_VENDOR		0x0000002C
+#define V3_PCI_SUB_ID			0x0000002E
+#define V3_PCI_ROM			0x00000030
+#define V3_PCI_BPARAM			0x0000003C
+#define V3_PCI_MAP0			0x00000040
+#define V3_PCI_MAP1			0x00000044
+#define V3_PCI_INT_STAT			0x00000048
+#define V3_PCI_INT_CFG			0x0000004C
+#define V3_LB_BASE0			0x00000054
+#define V3_LB_BASE1			0x00000058
+#define V3_LB_MAP0			0x0000005E
+#define V3_LB_MAP1			0x00000062
+#define V3_LB_BASE2			0x00000064
+#define V3_LB_MAP2			0x00000066
+#define V3_LB_SIZE			0x00000068
+#define V3_LB_IO_BASE			0x0000006E
+#define V3_FIFO_CFG			0x00000070
+#define V3_FIFO_PRIORITY		0x00000072
+#define V3_FIFO_STAT			0x00000074
+#define V3_LB_ISTAT			0x00000076
+#define V3_LB_IMASK			0x00000077
+#define V3_SYSTEM			0x00000078
+#define V3_LB_CFG			0x0000007A
+#define V3_PCI_CFG			0x0000007C
+#define V3_DMA_PCI_ADR0			0x00000080
+#define V3_DMA_PCI_ADR1			0x00000090
+#define V3_DMA_LOCAL_ADR0		0x00000084
+#define V3_DMA_LOCAL_ADR1		0x00000094
+#define V3_DMA_LENGTH0			0x00000088
+#define V3_DMA_LENGTH1			0x00000098
+#define V3_DMA_CSR0			0x0000008B
+#define V3_DMA_CSR1			0x0000009B
+#define V3_DMA_CTLB_ADR0		0x0000008C
+#define V3_DMA_CTLB_ADR1		0x0000009C
+#define V3_DMA_DELAY			0x000000E0
+#define V3_MAIL_DATA			0x000000C0
+#define V3_PCI_MAIL_IEWR		0x000000D0
+#define V3_PCI_MAIL_IERD		0x000000D2
+#define V3_LB_MAIL_IEWR			0x000000D4
+#define V3_LB_MAIL_IERD			0x000000D6
+#define V3_MAIL_WR_STAT			0x000000D8
+#define V3_MAIL_RD_STAT			0x000000DA
+#define V3_QBA_MAP			0x000000DC
+
+/* PCI STATUS bits */
+#define V3_PCI_STAT_PAR_ERR		BIT(15)
+#define V3_PCI_STAT_SYS_ERR		BIT(14)
+#define V3_PCI_STAT_M_ABORT_ERR		BIT(13)
+#define V3_PCI_STAT_T_ABORT_ERR		BIT(12)
+
+/* LB ISTAT bits */
+#define V3_LB_ISTAT_MAILBOX		BIT(7)
+#define V3_LB_ISTAT_PCI_RD		BIT(6)
+#define V3_LB_ISTAT_PCI_WR		BIT(5)
+#define V3_LB_ISTAT_PCI_INT		BIT(4)
+#define V3_LB_ISTAT_PCI_PERR		BIT(3)
+#define V3_LB_ISTAT_I2O_QWR		BIT(2)
+#define V3_LB_ISTAT_DMA1		BIT(1)
+#define V3_LB_ISTAT_DMA0		BIT(0)
+
+/* PCI COMMAND bits */
+#define V3_COMMAND_M_FBB_EN		BIT(9)
+#define V3_COMMAND_M_SERR_EN		BIT(8)
+#define V3_COMMAND_M_PAR_EN		BIT(6)
+#define V3_COMMAND_M_MASTER_EN		BIT(2)
+#define V3_COMMAND_M_MEM_EN		BIT(1)
+#define V3_COMMAND_M_IO_EN		BIT(0)
+
+/* SYSTEM bits */
+#define V3_SYSTEM_M_RST_OUT		BIT(15)
+#define V3_SYSTEM_M_LOCK		BIT(14)
+#define V3_SYSTEM_UNLOCK		0xa05f
+
+/* PCI CFG bits */
+#define V3_PCI_CFG_M_I2O_EN		BIT(15)
+#define V3_PCI_CFG_M_IO_REG_DIS		BIT(14)
+#define V3_PCI_CFG_M_IO_DIS		BIT(13)
+#define V3_PCI_CFG_M_EN3V		BIT(12)
+#define V3_PCI_CFG_M_RETRY_EN		BIT(10)
+#define V3_PCI_CFG_M_AD_LOW1		BIT(9)
+#define V3_PCI_CFG_M_AD_LOW0		BIT(8)
+/*
+ * This is the value applied to C/BE[3:1], with bit 0 always held 0
+ * during DMA access.
+ */
+#define V3_PCI_CFG_M_RTYPE_SHIFT	5
+#define V3_PCI_CFG_M_WTYPE_SHIFT	1
+#define V3_PCI_CFG_TYPE_DEFAULT		0x3
+
+/* PCI BASE bits (PCI -> Local Bus) */
+#define V3_PCI_BASE_M_ADR_BASE		0xFFF00000U
+#define V3_PCI_BASE_M_ADR_BASEL		0x000FFF00U
+#define V3_PCI_BASE_M_PREFETCH		BIT(3)
+#define V3_PCI_BASE_M_TYPE		(3 << 1)
+#define V3_PCI_BASE_M_IO		BIT(0)
+
+/* PCI MAP bits (PCI -> Local bus) */
+#define V3_PCI_MAP_M_MAP_ADR		0xFFF00000U
+#define V3_PCI_MAP_M_RD_POST_INH	BIT(15)
+#define V3_PCI_MAP_M_ROM_SIZE		(3 << 10)
+#define V3_PCI_MAP_M_SWAP		(3 << 8)
+#define V3_PCI_MAP_M_ADR_SIZE		0x000000F0U
+#define V3_PCI_MAP_M_REG_EN		BIT(1)
+#define V3_PCI_MAP_M_ENABLE		BIT(0)
+
+/* LB_BASE0,1 bits (Local bus -> PCI) */
+#define V3_LB_BASE_ADR_BASE		0xfff00000U
+#define V3_LB_BASE_SWAP			(3 << 8)
+#define V3_LB_BASE_ADR_SIZE		(15 << 4)
+#define V3_LB_BASE_PREFETCH		BIT(3)
+#define V3_LB_BASE_ENABLE		BIT(0)
+
+#define V3_LB_BASE_ADR_SIZE_1MB		(0 << 4)
+#define V3_LB_BASE_ADR_SIZE_2MB		(1 << 4)
+#define V3_LB_BASE_ADR_SIZE_4MB		(2 << 4)
+#define V3_LB_BASE_ADR_SIZE_8MB		(3 << 4)
+#define V3_LB_BASE_ADR_SIZE_16MB	(4 << 4)
+#define V3_LB_BASE_ADR_SIZE_32MB	(5 << 4)
+#define V3_LB_BASE_ADR_SIZE_64MB	(6 << 4)
+#define V3_LB_BASE_ADR_SIZE_128MB	(7 << 4)
+#define V3_LB_BASE_ADR_SIZE_256MB	(8 << 4)
+#define V3_LB_BASE_ADR_SIZE_512MB	(9 << 4)
+#define V3_LB_BASE_ADR_SIZE_1GB		(10 << 4)
+#define V3_LB_BASE_ADR_SIZE_2GB		(11 << 4)
+
+#define v3_addr_to_lb_base(a)	((a) & V3_LB_BASE_ADR_BASE)
+
+/* LB_MAP0,1 bits (Local bus -> PCI) */
+#define V3_LB_MAP_MAP_ADR		0xfff0U
+#define V3_LB_MAP_TYPE			(7 << 1)
+#define V3_LB_MAP_AD_LOW_EN		BIT(0)
+
+#define V3_LB_MAP_TYPE_IACK		(0 << 1)
+#define V3_LB_MAP_TYPE_IO		(1 << 1)
+#define V3_LB_MAP_TYPE_MEM		(3 << 1)
+#define V3_LB_MAP_TYPE_CONFIG		(5 << 1)
+#define V3_LB_MAP_TYPE_MEM_MULTIPLE	(6 << 1)
+
+#define v3_addr_to_lb_map(a)	(((a) >> 16) & V3_LB_MAP_MAP_ADR)
+
+/* LB_BASE2 bits (Local bus -> PCI IO) */
+#define V3_LB_BASE2_ADR_BASE		0xff00U
+#define V3_LB_BASE2_SWAP_AUTO		(3 << 6)
+#define V3_LB_BASE2_ENABLE		BIT(0)
+
+#define v3_addr_to_lb_base2(a)	(((a) >> 16) & V3_LB_BASE2_ADR_BASE)
+
+/* LB_MAP2 bits (Local bus -> PCI IO) */
+#define V3_LB_MAP2_MAP_ADR		0xff00U
+
+#define v3_addr_to_lb_map2(a)	(((a) >> 16) & V3_LB_MAP2_MAP_ADR)
+
+/* FIFO priority bits */
+#define V3_FIFO_PRIO_LOCAL		BIT(12)
+#define V3_FIFO_PRIO_LB_RD1_FLUSH_EOB	BIT(10)
+#define V3_FIFO_PRIO_LB_RD1_FLUSH_AP1	BIT(11)
+#define V3_FIFO_PRIO_LB_RD1_FLUSH_ANY	(BIT(10)|BIT(11))
+#define V3_FIFO_PRIO_LB_RD0_FLUSH_EOB	BIT(8)
+#define V3_FIFO_PRIO_LB_RD0_FLUSH_AP1	BIT(9)
+#define V3_FIFO_PRIO_LB_RD0_FLUSH_ANY	(BIT(8)|BIT(9))
+#define V3_FIFO_PRIO_PCI		BIT(4)
+#define V3_FIFO_PRIO_PCI_RD1_FLUSH_EOB	BIT(2)
+#define V3_FIFO_PRIO_PCI_RD1_FLUSH_AP1	BIT(3)
+#define V3_FIFO_PRIO_PCI_RD1_FLUSH_ANY	(BIT(2)|BIT(3))
+#define V3_FIFO_PRIO_PCI_RD0_FLUSH_EOB	BIT(0)
+#define V3_FIFO_PRIO_PCI_RD0_FLUSH_AP1	BIT(1)
+#define V3_FIFO_PRIO_PCI_RD0_FLUSH_ANY	(BIT(0)|BIT(1))
+
+/* Local bus configuration bits */
+#define V3_LB_CFG_LB_TO_64_CYCLES	0x0000
+#define V3_LB_CFG_LB_TO_256_CYCLES	BIT(13)
+#define V3_LB_CFG_LB_TO_512_CYCLES	BIT(14)
+#define V3_LB_CFG_LB_TO_1024_CYCLES	(BIT(13)|BIT(14))
+#define V3_LB_CFG_LB_RST		BIT(12)
+#define V3_LB_CFG_LB_PPC_RDY		BIT(11)
+#define V3_LB_CFG_LB_LB_INT		BIT(10)
+#define V3_LB_CFG_LB_ERR_EN		BIT(9)
+#define V3_LB_CFG_LB_RDY_EN		BIT(8)
+#define V3_LB_CFG_LB_BE_IMODE		BIT(7)
+#define V3_LB_CFG_LB_BE_OMODE		BIT(6)
+#define V3_LB_CFG_LB_ENDIAN		BIT(5)
+#define V3_LB_CFG_LB_PARK_EN		BIT(4)
+#define V3_LB_CFG_LB_FBB_DIS		BIT(2)
+
+/* ARM Integrator-specific extended control registers */
+#define INTEGRATOR_SC_PCI_OFFSET	0x18
+#define INTEGRATOR_SC_PCI_ENABLE	BIT(0)
+#define INTEGRATOR_SC_PCI_INTCLR	BIT(1)
+#define INTEGRATOR_SC_LBFADDR_OFFSET	0x20
+#define INTEGRATOR_SC_LBFCODE_OFFSET	0x24
+
+struct v3_pci {
+	struct device *dev;
+	void __iomem *base;
+	void __iomem *config_base;
+	struct pci_bus *bus;
+	u32 config_mem;
+	u32 io_mem;
+	u32 non_pre_mem;
+	u32 pre_mem;
+	phys_addr_t io_bus_addr;
+	phys_addr_t non_pre_bus_addr;
+	phys_addr_t pre_bus_addr;
+	struct regmap *map;
+};
+
+/*
+ * The V3 PCI interface chip in Integrator provides several windows from
+ * local bus memory into the PCI memory areas. Unfortunately, there
+ * are not really enough windows for our usage, therefore we reuse
+ * one of the windows for access to PCI configuration space. On the
+ * Integrator/AP, the memory map is as follows:
+ *
+ * Local Bus Memory         Usage
+ *
+ * 40000000 - 4FFFFFFF      PCI memory.  256M non-prefetchable
+ * 50000000 - 5FFFFFFF      PCI memory.  256M prefetchable
+ * 60000000 - 60FFFFFF      PCI IO.  16M
+ * 61000000 - 61FFFFFF      PCI Configuration. 16M
+ *
+ * There are three V3 windows, each described by a pair of V3 registers.
+ * These are LB_BASE0/LB_MAP0, LB_BASE1/LB_MAP1 and LB_BASE2/LB_MAP2.
+ * Base0 and Base1 can be used for any type of PCI memory access.   Base2
+ * can be used either for PCI I/O or for I20 accesses.  By default, uHAL
+ * uses this only for PCI IO space.
+ *
+ * Normally these spaces are mapped using the following base registers:
+ *
+ * Usage Local Bus Memory         Base/Map registers used
+ *
+ * Mem   40000000 - 4FFFFFFF      LB_BASE0/LB_MAP0
+ * Mem   50000000 - 5FFFFFFF      LB_BASE1/LB_MAP1
+ * IO    60000000 - 60FFFFFF      LB_BASE2/LB_MAP2
+ * Cfg   61000000 - 61FFFFFF
+ *
+ * This means that I20 and PCI configuration space accesses will fail.
+ * When PCI configuration accesses are needed (via the uHAL PCI
+ * configuration space primitives) we must remap the spaces as follows:
+ *
+ * Usage Local Bus Memory         Base/Map registers used
+ *
+ * Mem   40000000 - 4FFFFFFF      LB_BASE0/LB_MAP0
+ * Mem   50000000 - 5FFFFFFF      LB_BASE0/LB_MAP0
+ * IO    60000000 - 60FFFFFF      LB_BASE2/LB_MAP2
+ * Cfg   61000000 - 61FFFFFF      LB_BASE1/LB_MAP1
+ *
+ * To make this work, the code depends on overlapping windows working.
+ * The V3 chip translates an address by checking its range within
+ * each of the BASE/MAP pairs in turn (in ascending register number
+ * order).  It will use the first matching pair.   So, for example,
+ * if the same address is mapped by both LB_BASE0/LB_MAP0 and
+ * LB_BASE1/LB_MAP1, the V3 will use the translation from
+ * LB_BASE0/LB_MAP0.
+ *
+ * To allow PCI Configuration space access, the code enlarges the
+ * window mapped by LB_BASE0/LB_MAP0 from 256M to 512M.  This occludes
+ * the windows currently mapped by LB_BASE1/LB_MAP1 so that it can
+ * be remapped for use by configuration cycles.
+ *
+ * At the end of the PCI Configuration space accesses,
+ * LB_BASE1/LB_MAP1 is reset to map PCI Memory.  Finally the window
+ * mapped by LB_BASE0/LB_MAP0 is reduced in size from 512M to 256M to
+ * reveal the now restored LB_BASE1/LB_MAP1 window.
+ *
+ * NOTE: We do not set up I2O mapping.  I suspect that this is only
+ * for an intelligent (target) device.  Using I2O disables most of
+ * the mappings into PCI memory.
+ */
+static void __iomem *v3_map_bus(struct pci_bus *bus,
+				unsigned int devfn, int offset)
+{
+	struct v3_pci *v3 = bus->sysdata;
+	unsigned int address, mapaddress, busnr;
+
+	busnr = bus->number;
+	if (busnr == 0) {
+		int slot = PCI_SLOT(devfn);
+
+		/*
+		 * local bus segment so need a type 0 config cycle
+		 *
+		 * build the PCI configuration "address" with one-hot in
+		 * A31-A11
+		 *
+		 * mapaddress:
+		 *  3:1 = config cycle (101)
+		 *  0   = PCI A1 & A0 are 0 (0)
+		 */
+		address = PCI_FUNC(devfn) << 8;
+		mapaddress = V3_LB_MAP_TYPE_CONFIG;
+
+		if (slot > 12)
+			/*
+			 * high order bits are handled by the MAP register
+			 */
+			mapaddress |= BIT(slot - 5);
+		else
+			/*
+			 * low order bits handled directly in the address
+			 */
+			address |= BIT(slot + 11);
+	} else {
+		/*
+		 * not the local bus segment so need a type 1 config cycle
+		 *
+		 * address:
+		 *  23:16 = bus number
+		 *  15:11 = slot number (7:3 of devfn)
+		 *  10:8  = func number (2:0 of devfn)
+		 *
+		 * mapaddress:
+		 *  3:1 = config cycle (101)
+		 *  0   = PCI A1 & A0 from host bus (1)
+		 */
+		mapaddress = V3_LB_MAP_TYPE_CONFIG | V3_LB_MAP_AD_LOW_EN;
+		address = (busnr << 16) | (devfn << 8);
+	}
+
+	/*
+	 * Set up base0 to see all 512Mbytes of memory space (not
+	 * prefetchable), this frees up base1 for re-use by
+	 * configuration memory
+	 */
+	writel(v3_addr_to_lb_base(v3->non_pre_mem) |
+	       V3_LB_BASE_ADR_SIZE_512MB | V3_LB_BASE_ENABLE,
+	       v3->base + V3_LB_BASE0);
+
+	/*
+	 * Set up base1/map1 to point into configuration space.
+	 * The config mem is always 16MB.
+	 */
+	writel(v3_addr_to_lb_base(v3->config_mem) |
+	       V3_LB_BASE_ADR_SIZE_16MB | V3_LB_BASE_ENABLE,
+	       v3->base + V3_LB_BASE1);
+	writew(mapaddress, v3->base + V3_LB_MAP1);
+
+	return v3->config_base + address + offset;
+}
+
+static void v3_unmap_bus(struct v3_pci *v3)
+{
+	/*
+	 * Reassign base1 for use by prefetchable PCI memory
+	 */
+	writel(v3_addr_to_lb_base(v3->pre_mem) |
+	       V3_LB_BASE_ADR_SIZE_256MB | V3_LB_BASE_PREFETCH |
+	       V3_LB_BASE_ENABLE,
+	       v3->base + V3_LB_BASE1);
+	writew(v3_addr_to_lb_map(v3->pre_bus_addr) |
+	       V3_LB_MAP_TYPE_MEM, /* was V3_LB_MAP_TYPE_MEM_MULTIPLE */
+	       v3->base + V3_LB_MAP1);
+
+	/*
+	 * And shrink base0 back to a 256M window (NOTE: MAP0 already correct)
+	 */
+	writel(v3_addr_to_lb_base(v3->non_pre_mem) |
+	       V3_LB_BASE_ADR_SIZE_256MB | V3_LB_BASE_ENABLE,
+	       v3->base + V3_LB_BASE0);
+}
+
+static int v3_pci_read_config(struct pci_bus *bus, unsigned int fn,
+			      int config, int size, u32 *value)
+{
+	struct v3_pci *v3 = bus->sysdata;
+	int ret;
+
+	dev_dbg(&bus->dev,
+		"[read]  slt: %.2d, fnc: %d, cnf: 0x%.2X, val (%d bytes): 0x%.8X\n",
+		PCI_SLOT(fn), PCI_FUNC(fn), config, size, *value);
+	ret = pci_generic_config_read(bus, fn, config, size, value);
+	v3_unmap_bus(v3);
+	return ret;
+}
+
+static int v3_pci_write_config(struct pci_bus *bus, unsigned int fn,
+				    int config, int size, u32 value)
+{
+	struct v3_pci *v3 = bus->sysdata;
+	int ret;
+
+	dev_dbg(&bus->dev,
+		"[write] slt: %.2d, fnc: %d, cnf: 0x%.2X, val (%d bytes): 0x%.8X\n",
+		PCI_SLOT(fn), PCI_FUNC(fn), config, size, value);
+	ret = pci_generic_config_write(bus, fn, config, size, value);
+	v3_unmap_bus(v3);
+	return ret;
+}
+
+static struct pci_ops v3_pci_ops = {
+	.map_bus = v3_map_bus,
+	.read = v3_pci_read_config,
+	.write = v3_pci_write_config,
+};
+
+static irqreturn_t v3_irq(int irq, void *data)
+{
+	struct v3_pci *v3 = data;
+	struct device *dev = v3->dev;
+	u32 status;
+
+	status = readw(v3->base + V3_PCI_STAT);
+	if (status & V3_PCI_STAT_PAR_ERR)
+		dev_err(dev, "parity error interrupt\n");
+	if (status & V3_PCI_STAT_SYS_ERR)
+		dev_err(dev, "system error interrupt\n");
+	if (status & V3_PCI_STAT_M_ABORT_ERR)
+		dev_err(dev, "master abort error interrupt\n");
+	if (status & V3_PCI_STAT_T_ABORT_ERR)
+		dev_err(dev, "target abort error interrupt\n");
+	writew(status, v3->base + V3_PCI_STAT);
+
+	status = readb(v3->base + V3_LB_ISTAT);
+	if (status & V3_LB_ISTAT_MAILBOX)
+		dev_info(dev, "PCI mailbox interrupt\n");
+	if (status & V3_LB_ISTAT_PCI_RD)
+		dev_err(dev, "PCI target LB->PCI READ abort interrupt\n");
+	if (status & V3_LB_ISTAT_PCI_WR)
+		dev_err(dev, "PCI target LB->PCI WRITE abort interrupt\n");
+	if (status &  V3_LB_ISTAT_PCI_INT)
+		dev_info(dev, "PCI pin interrupt\n");
+	if (status & V3_LB_ISTAT_PCI_PERR)
+		dev_err(dev, "PCI parity error interrupt\n");
+	if (status & V3_LB_ISTAT_I2O_QWR)
+		dev_info(dev, "I2O inbound post queue interrupt\n");
+	if (status & V3_LB_ISTAT_DMA1)
+		dev_info(dev, "DMA channel 1 interrupt\n");
+	if (status & V3_LB_ISTAT_DMA0)
+		dev_info(dev, "DMA channel 0 interrupt\n");
+	/* Clear all possible interrupts on the local bus */
+	writeb(0, v3->base + V3_LB_ISTAT);
+	if (v3->map)
+		regmap_write(v3->map, INTEGRATOR_SC_PCI_OFFSET,
+			     INTEGRATOR_SC_PCI_ENABLE |
+			     INTEGRATOR_SC_PCI_INTCLR);
+
+	return IRQ_HANDLED;
+}
+
+static int v3_integrator_init(struct v3_pci *v3)
+{
+	unsigned int val;
+
+	v3->map =
+		syscon_regmap_lookup_by_compatible("arm,integrator-ap-syscon");
+	if (IS_ERR(v3->map)) {
+		dev_err(v3->dev, "no syscon\n");
+		return -ENODEV;
+	}
+
+	regmap_read(v3->map, INTEGRATOR_SC_PCI_OFFSET, &val);
+	/* Take the PCI bridge out of reset, clear IRQs */
+	regmap_write(v3->map, INTEGRATOR_SC_PCI_OFFSET,
+		     INTEGRATOR_SC_PCI_ENABLE |
+		     INTEGRATOR_SC_PCI_INTCLR);
+
+	if (!(val & INTEGRATOR_SC_PCI_ENABLE)) {
+		/* If we were in reset we need to sleep a bit */
+		msleep(230);
+
+		/* Set the physical base for the controller itself */
+		writel(0x6200, v3->base + V3_LB_IO_BASE);
+
+		/* Wait for the mailbox to settle after reset */
+		do {
+			writeb(0xaa, v3->base + V3_MAIL_DATA);
+			writeb(0x55, v3->base + V3_MAIL_DATA + 4);
+		} while (readb(v3->base + V3_MAIL_DATA) != 0xaa &&
+			 readb(v3->base + V3_MAIL_DATA) != 0x55);
+	}
+
+	dev_info(v3->dev, "initialized PCI V3 Integrator/AP integration\n");
+
+	return 0;
+}
+
+static int v3_pci_setup_resource(struct v3_pci *v3,
+				 resource_size_t io_base,
+				 struct pci_host_bridge *host,
+				 struct resource_entry *win)
+{
+	struct device *dev = v3->dev;
+	struct resource *mem;
+	struct resource *io;
+	int ret;
+
+	switch (resource_type(win->res)) {
+	case IORESOURCE_IO:
+		io = win->res;
+		io->name = "V3 PCI I/O";
+		v3->io_mem = io_base;
+		v3->io_bus_addr = io->start - win->offset;
+		dev_dbg(dev, "I/O window %pR, bus addr %pap\n",
+			io, &v3->io_bus_addr);
+		ret = pci_remap_iospace(io, io_base);
+		if (ret) {
+			dev_warn(dev,
+				 "error %d: failed to map resource %pR\n",
+				 ret, io);
+			return ret;
+		}
+		/* Setup window 2 - PCI I/O */
+		writel(v3_addr_to_lb_base2(v3->io_mem) |
+		       V3_LB_BASE2_ENABLE,
+		       v3->base + V3_LB_BASE2);
+		writew(v3_addr_to_lb_map2(v3->io_bus_addr),
+		       v3->base + V3_LB_MAP2);
+		break;
+	case IORESOURCE_MEM:
+		mem = win->res;
+		if (mem->flags & IORESOURCE_PREFETCH) {
+			mem->name = "V3 PCI PRE-MEM";
+			v3->pre_mem = mem->start;
+			v3->pre_bus_addr = mem->start - win->offset;
+			dev_dbg(dev, "PREFETCHABLE MEM window %pR, bus addr %pap\n",
+				mem, &v3->pre_bus_addr);
+			if (resource_size(mem) != SZ_256M) {
+				dev_err(dev, "prefetchable memory range is not 256MB\n");
+				return -EINVAL;
+			}
+			if (v3->non_pre_mem &&
+			    (mem->start != v3->non_pre_mem + SZ_256M)) {
+				dev_err(dev,
+					"prefetchable memory is not adjacent to non-prefetchable memory\n");
+				return -EINVAL;
+			}
+			/* Setup window 1 - PCI prefetchable memory */
+			writel(v3_addr_to_lb_base(v3->pre_mem) |
+			       V3_LB_BASE_ADR_SIZE_256MB |
+			       V3_LB_BASE_PREFETCH |
+			       V3_LB_BASE_ENABLE,
+			       v3->base + V3_LB_BASE1);
+			writew(v3_addr_to_lb_map(v3->pre_bus_addr) |
+			       V3_LB_MAP_TYPE_MEM, /* Was V3_LB_MAP_TYPE_MEM_MULTIPLE */
+			       v3->base + V3_LB_MAP1);
+		} else {
+			mem->name = "V3 PCI NON-PRE-MEM";
+			v3->non_pre_mem = mem->start;
+			v3->non_pre_bus_addr = mem->start - win->offset;
+			dev_dbg(dev, "NON-PREFETCHABLE MEM window %pR, bus addr %pap\n",
+				mem, &v3->non_pre_bus_addr);
+			if (resource_size(mem) != SZ_256M) {
+				dev_err(dev,
+					"non-prefetchable memory range is not 256MB\n");
+				return -EINVAL;
+			}
+			/* Setup window 0 - PCI non-prefetchable memory */
+			writel(v3_addr_to_lb_base(v3->non_pre_mem) |
+			       V3_LB_BASE_ADR_SIZE_256MB |
+			       V3_LB_BASE_ENABLE,
+			       v3->base + V3_LB_BASE0);
+			writew(v3_addr_to_lb_map(v3->non_pre_bus_addr) |
+			       V3_LB_MAP_TYPE_MEM,
+			       v3->base + V3_LB_MAP0);
+		}
+		break;
+	case IORESOURCE_BUS:
+		dev_dbg(dev, "BUS %pR\n", win->res);
+		host->busnr = win->res->start;
+		break;
+	default:
+		dev_info(dev, "Unknown resource type %lu\n",
+			 resource_type(win->res));
+		break;
+	}
+
+	return 0;
+}
+
+static int v3_get_dma_range_config(struct v3_pci *v3,
+				   struct of_pci_range *range,
+				   u32 *pci_base, u32 *pci_map)
+{
+	struct device *dev = v3->dev;
+	u64 cpu_end = range->cpu_addr + range->size - 1;
+	u64 pci_end = range->pci_addr + range->size - 1;
+	u32 val;
+
+	if (range->pci_addr & ~V3_PCI_BASE_M_ADR_BASE) {
+		dev_err(dev, "illegal range, only PCI bits 31..20 allowed\n");
+		return -EINVAL;
+	}
+	val = ((u32)range->pci_addr) & V3_PCI_BASE_M_ADR_BASE;
+	*pci_base = val;
+
+	if (range->cpu_addr & ~V3_PCI_MAP_M_MAP_ADR) {
+		dev_err(dev, "illegal range, only CPU bits 31..20 allowed\n");
+		return -EINVAL;
+	}
+	val = ((u32)range->cpu_addr) & V3_PCI_MAP_M_MAP_ADR;
+
+	switch (range->size) {
+	case SZ_1M:
+		val |= V3_LB_BASE_ADR_SIZE_1MB;
+		break;
+	case SZ_2M:
+		val |= V3_LB_BASE_ADR_SIZE_2MB;
+		break;
+	case SZ_4M:
+		val |= V3_LB_BASE_ADR_SIZE_4MB;
+		break;
+	case SZ_8M:
+		val |= V3_LB_BASE_ADR_SIZE_8MB;
+		break;
+	case SZ_16M:
+		val |= V3_LB_BASE_ADR_SIZE_16MB;
+		break;
+	case SZ_32M:
+		val |= V3_LB_BASE_ADR_SIZE_32MB;
+		break;
+	case SZ_64M:
+		val |= V3_LB_BASE_ADR_SIZE_64MB;
+		break;
+	case SZ_128M:
+		val |= V3_LB_BASE_ADR_SIZE_128MB;
+		break;
+	case SZ_256M:
+		val |= V3_LB_BASE_ADR_SIZE_256MB;
+		break;
+	case SZ_512M:
+		val |= V3_LB_BASE_ADR_SIZE_512MB;
+		break;
+	case SZ_1G:
+		val |= V3_LB_BASE_ADR_SIZE_1GB;
+		break;
+	case SZ_2G:
+		val |= V3_LB_BASE_ADR_SIZE_2GB;
+		break;
+	default:
+		dev_err(v3->dev, "illegal dma memory chunk size\n");
+		return -EINVAL;
+		break;
+	};
+	val |= V3_PCI_MAP_M_REG_EN | V3_PCI_MAP_M_ENABLE;
+	*pci_map = val;
+
+	dev_dbg(dev,
+		"DMA MEM CPU: 0x%016llx -> 0x%016llx => "
+		"PCI: 0x%016llx -> 0x%016llx base %08x map %08x\n",
+		range->cpu_addr, cpu_end,
+		range->pci_addr, pci_end,
+		*pci_base, *pci_map);
+
+	return 0;
+}
+
+static int v3_pci_parse_map_dma_ranges(struct v3_pci *v3,
+				       struct device_node *np)
+{
+	struct of_pci_range range;
+	struct of_pci_range_parser parser;
+	struct device *dev = v3->dev;
+	int i = 0;
+
+	if (of_pci_dma_range_parser_init(&parser, np)) {
+		dev_err(dev, "missing dma-ranges property\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Get the dma-ranges from the device tree
+	 */
+	for_each_of_pci_range(&parser, &range) {
+		int ret;
+		u32 pci_base, pci_map;
+
+		ret = v3_get_dma_range_config(v3, &range, &pci_base, &pci_map);
+		if (ret)
+			return ret;
+
+		if (i == 0) {
+			writel(pci_base, v3->base + V3_PCI_BASE0);
+			writel(pci_map, v3->base + V3_PCI_MAP0);
+		} else if (i == 1) {
+			writel(pci_base, v3->base + V3_PCI_BASE1);
+			writel(pci_map, v3->base + V3_PCI_MAP1);
+		} else {
+			dev_err(dev, "too many ranges, only two supported\n");
+			dev_err(dev, "range %d ignored\n", i);
+		}
+		i++;
+	}
+	return 0;
+}
+
+static int v3_pci_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	resource_size_t io_base;
+	struct resource *regs;
+	struct resource_entry *win;
+	struct v3_pci *v3;
+	struct pci_host_bridge *host;
+	struct clk *clk;
+	u16 val;
+	int irq;
+	int ret;
+	LIST_HEAD(res);
+
+	host = pci_alloc_host_bridge(sizeof(*v3));
+	if (!host)
+		return -ENOMEM;
+
+	host->dev.parent = dev;
+	host->ops = &v3_pci_ops;
+	host->busnr = 0;
+	host->msi = NULL;
+	host->map_irq = of_irq_parse_and_map_pci;
+	host->swizzle_irq = pci_common_swizzle;
+	v3 = pci_host_bridge_priv(host);
+	host->sysdata = v3;
+	v3->dev = dev;
+
+	/* Get and enable host clock */
+	clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(clk)) {
+		dev_err(dev, "clock not found\n");
+		return PTR_ERR(clk);
+	}
+	ret = clk_prepare_enable(clk);
+	if (ret) {
+		dev_err(dev, "unable to enable clock\n");
+		return ret;
+	}
+
+	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	v3->base = devm_ioremap_resource(dev, regs);
+	if (IS_ERR(v3->base))
+		return PTR_ERR(v3->base);
+	/*
+	 * The hardware has a register with the physical base address
+	 * of the V3 controller itself, verify that this is the same
+	 * as the physical memory we've remapped it from.
+	 */
+	if (readl(v3->base + V3_LB_IO_BASE) != (regs->start >> 16))
+		dev_err(dev, "V3_LB_IO_BASE = %08x but device is @%pR\n",
+			readl(v3->base + V3_LB_IO_BASE), regs);
+
+	/* Configuration space is 16MB directly mapped */
+	regs = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	if (resource_size(regs) != SZ_16M) {
+		dev_err(dev, "config mem is not 16MB!\n");
+		return -EINVAL;
+	}
+	v3->config_mem = regs->start;
+	v3->config_base = devm_ioremap_resource(dev, regs);
+	if (IS_ERR(v3->config_base))
+		return PTR_ERR(v3->config_base);
+
+	ret = of_pci_get_host_bridge_resources(np, 0, 0xff, &res, &io_base);
+	if (ret)
+		return ret;
+
+	ret = devm_request_pci_bus_resources(dev, &res);
+	if (ret)
+		return ret;
+
+	/* Get and request error IRQ resource */
+	irq = platform_get_irq(pdev, 0);
+	if (irq <= 0) {
+		dev_err(dev, "unable to obtain PCIv3 error IRQ\n");
+		return -ENODEV;
+	}
+	ret = devm_request_irq(dev, irq, v3_irq, 0,
+			"PCIv3 error", v3);
+	if (ret < 0) {
+		dev_err(dev,
+			"unable to request PCIv3 error IRQ %d (%d)\n",
+			irq, ret);
+		return ret;
+	}
+
+	/*
+	 * Unlock V3 registers, but only if they were previously locked.
+	 */
+	if (readw(v3->base + V3_SYSTEM) & V3_SYSTEM_M_LOCK)
+		writew(V3_SYSTEM_UNLOCK, v3->base + V3_SYSTEM);
+
+	/* Disable all slave access while we set up the windows */
+	val = readw(v3->base + V3_PCI_CMD);
+	val &= ~(PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER);
+	writew(val, v3->base + V3_PCI_CMD);
+
+	/* Put the PCI bus into reset */
+	val = readw(v3->base + V3_SYSTEM);
+	val &= ~V3_SYSTEM_M_RST_OUT;
+	writew(val, v3->base + V3_SYSTEM);
+
+	/* Retry until we're ready */
+	val = readw(v3->base + V3_PCI_CFG);
+	val |= V3_PCI_CFG_M_RETRY_EN;
+	writew(val, v3->base + V3_PCI_CFG);
+
+	/* Set up the local bus protocol */
+	val = readw(v3->base + V3_LB_CFG);
+	val |= V3_LB_CFG_LB_BE_IMODE; /* Byte enable input */
+	val |= V3_LB_CFG_LB_BE_OMODE; /* Byte enable output */
+	val &= ~V3_LB_CFG_LB_ENDIAN; /* Little endian */
+	val &= ~V3_LB_CFG_LB_PPC_RDY; /* TODO: when using on PPC403Gx, set to 1 */
+	writew(val, v3->base + V3_LB_CFG);
+
+	/* Enable the PCI bus master */
+	val = readw(v3->base + V3_PCI_CMD);
+	val |= PCI_COMMAND_MASTER;
+	writew(val, v3->base + V3_PCI_CMD);
+
+	/* Get the I/O and memory ranges from DT */
+	resource_list_for_each_entry(win, &res) {
+		ret = v3_pci_setup_resource(v3, io_base, host, win);
+		if (ret) {
+			dev_err(dev, "error setting up resources\n");
+			return ret;
+		}
+	}
+	ret = v3_pci_parse_map_dma_ranges(v3, np);
+	if (ret)
+		return ret;
+
+	/*
+	 * Disable PCI to host IO cycles, enable I/O buffers @3.3V,
+	 * set AD_LOW0 to 1 if one of the LB_MAP registers choose
+	 * to use this (should be unused).
+	 */
+	writel(0x00000000, v3->base + V3_PCI_IO_BASE);
+	val = V3_PCI_CFG_M_IO_REG_DIS | V3_PCI_CFG_M_IO_DIS |
+		V3_PCI_CFG_M_EN3V | V3_PCI_CFG_M_AD_LOW0;
+	/*
+	 * DMA read and write from PCI bus commands types
+	 */
+	val |=  V3_PCI_CFG_TYPE_DEFAULT << V3_PCI_CFG_M_RTYPE_SHIFT;
+	val |=  V3_PCI_CFG_TYPE_DEFAULT << V3_PCI_CFG_M_WTYPE_SHIFT;
+	writew(val, v3->base + V3_PCI_CFG);
+
+	/*
+	 * Set the V3 FIFO such that writes have higher priority than
+	 * reads, and local bus write causes local bus read fifo flush
+	 * on aperture 1. Same for PCI.
+	 */
+	writew(V3_FIFO_PRIO_LB_RD1_FLUSH_AP1 |
+	       V3_FIFO_PRIO_LB_RD0_FLUSH_AP1 |
+	       V3_FIFO_PRIO_PCI_RD1_FLUSH_AP1 |
+	       V3_FIFO_PRIO_PCI_RD0_FLUSH_AP1,
+	       v3->base + V3_FIFO_PRIORITY);
+
+
+	/*
+	 * Clear any error interrupts, and enable parity and write error
+	 * interrupts
+	 */
+	writeb(0, v3->base + V3_LB_ISTAT);
+	val = readw(v3->base + V3_LB_CFG);
+	val |= V3_LB_CFG_LB_LB_INT;
+	writew(val, v3->base + V3_LB_CFG);
+	writeb(V3_LB_ISTAT_PCI_WR | V3_LB_ISTAT_PCI_PERR,
+	       v3->base + V3_LB_IMASK);
+
+	/* Special Integrator initialization */
+	if (of_device_is_compatible(np, "arm,integrator-ap-pci")) {
+		ret = v3_integrator_init(v3);
+		if (ret)
+			return ret;
+	}
+
+	/* Post-init: enable PCI memory and invalidate (master already on) */
+	val = readw(v3->base + V3_PCI_CMD);
+	val |= PCI_COMMAND_MEMORY | PCI_COMMAND_INVALIDATE;
+	writew(val, v3->base + V3_PCI_CMD);
+
+	/* Clear pending interrupts */
+	writeb(0, v3->base + V3_LB_ISTAT);
+	/* Read or write errors and parity errors cause interrupts */
+	writeb(V3_LB_ISTAT_PCI_RD | V3_LB_ISTAT_PCI_WR | V3_LB_ISTAT_PCI_PERR,
+	       v3->base + V3_LB_IMASK);
+
+	/* Take the PCI bus out of reset so devices can initialize */
+	val = readw(v3->base + V3_SYSTEM);
+	val |= V3_SYSTEM_M_RST_OUT;
+	writew(val, v3->base + V3_SYSTEM);
+
+	/*
+	 * Re-lock the system register.
+	 */
+	val = readw(v3->base + V3_SYSTEM);
+	val |= V3_SYSTEM_M_LOCK;
+	writew(val, v3->base + V3_SYSTEM);
+
+	list_splice_init(&res, &host->windows);
+	ret = pci_scan_root_bus_bridge(host);
+	if (ret) {
+		dev_err(dev, "failed to register host: %d\n", ret);
+		return ret;
+	}
+	v3->bus = host->bus;
+
+	pci_bus_assign_resources(v3->bus);
+	pci_bus_add_devices(v3->bus);
+
+	return 0;
+}
+
+static const struct of_device_id v3_pci_of_match[] = {
+	{
+		.compatible = "v3,v360epc-pci",
+	},
+	{},
+};
+
+static struct platform_driver v3_pci_driver = {
+	.driver = {
+		.name = "pci-v3-semi",
+		.of_match_table = of_match_ptr(v3_pci_of_match),
+		.suppress_bind_attrs = true,
+	},
+	.probe  = v3_pci_probe,
+};
+builtin_platform_driver(v3_pci_driver);
diff --git a/drivers/pci/host/pci-xgene.c b/drivers/pci/host/pci-xgene.c
index 087645116ecb..465aa2a1b38d 100644
--- a/drivers/pci/host/pci-xgene.c
+++ b/drivers/pci/host/pci-xgene.c
@@ -542,24 +542,6 @@ static void xgene_pcie_setup_ib_reg(struct xgene_pcie_port *port,
 	xgene_pcie_setup_pims(port, pim_reg, pci_addr, ~(size - 1));
 }
 
-static int pci_dma_range_parser_init(struct of_pci_range_parser *parser,
-				     struct device_node *node)
-{
-	const int na = 3, ns = 2;
-	int rlen;
-
-	parser->node = node;
-	parser->pna = of_n_addr_cells(node);
-	parser->np = parser->pna + na + ns;
-
-	parser->range = of_get_property(node, "dma-ranges", &rlen);
-	if (!parser->range)
-		return -ENOENT;
-	parser->end = parser->range + rlen / sizeof(__be32);
-
-	return 0;
-}
-
 static int xgene_pcie_parse_map_dma_ranges(struct xgene_pcie_port *port)
 {
 	struct device_node *np = port->node;
@@ -568,7 +550,7 @@ static int xgene_pcie_parse_map_dma_ranges(struct xgene_pcie_port *port)
 	struct device *dev = port->dev;
 	u8 ib_reg_mask = 0;
 
-	if (pci_dma_range_parser_init(&parser, np)) {
+	if (of_pci_dma_range_parser_init(&parser, np)) {
 		dev_err(dev, "missing dma-ranges property\n");
 		return -EINVAL;
 	}
@@ -628,7 +610,7 @@ static struct pci_ops xgene_pcie_ops = {
 	.write = pci_generic_config_write32,
 };
 
-static int xgene_pcie_probe_bridge(struct platform_device *pdev)
+static int xgene_pcie_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *dn = dev->of_node;
@@ -709,7 +691,7 @@ static struct platform_driver xgene_pcie_driver = {
 		.of_match_table = of_match_ptr(xgene_pcie_match_table),
 		.suppress_bind_attrs = true,
 	},
-	.probe = xgene_pcie_probe_bridge,
+	.probe = xgene_pcie_probe,
 };
 builtin_platform_driver(xgene_pcie_driver);
 #endif
diff --git a/drivers/pci/host/pcie-altera.c b/drivers/pci/host/pcie-altera.c
index b468b8cccf8d..5cc4f594d79a 100644
--- a/drivers/pci/host/pcie-altera.c
+++ b/drivers/pci/host/pcie-altera.c
@@ -105,7 +105,7 @@ static inline u32 cra_readl(struct altera_pcie *pcie, const u32 reg)
 	return readl_relaxed(pcie->cra_base + reg);
 }
 
-static bool altera_pcie_link_is_up(struct altera_pcie *pcie)
+static bool altera_pcie_link_up(struct altera_pcie *pcie)
 {
 	return !!((cra_readl(pcie, RP_LTSSM) & RP_LTSSM_MASK) == LTSSM_L0);
 }
@@ -142,7 +142,7 @@ static bool altera_pcie_valid_device(struct altera_pcie *pcie,
 {
 	/* If there is no link, then there is no device */
 	if (bus->number != pcie->root_bus_nr) {
-		if (!altera_pcie_link_is_up(pcie))
+		if (!altera_pcie_link_up(pcie))
 			return false;
 	}
 
@@ -412,7 +412,7 @@ static void altera_wait_link_retrain(struct altera_pcie *pcie)
 	/* Wait for link is up */
 	start_jiffies = jiffies;
 	for (;;) {
-		if (altera_pcie_link_is_up(pcie))
+		if (altera_pcie_link_up(pcie))
 			break;
 
 		if (time_after(jiffies, start_jiffies + LINK_UP_TIMEOUT)) {
@@ -427,7 +427,7 @@ static void altera_pcie_retrain(struct altera_pcie *pcie)
 {
 	u16 linkcap, linkstat, linkctl;
 
-	if (!altera_pcie_link_is_up(pcie))
+	if (!altera_pcie_link_up(pcie))
 		return;
 
 	/*
diff --git a/drivers/pci/host/pcie-iproc-msi.c b/drivers/pci/host/pcie-iproc-msi.c
index 2d0f535a2f69..990fc906d73d 100644
--- a/drivers/pci/host/pcie-iproc-msi.c
+++ b/drivers/pci/host/pcie-iproc-msi.c
@@ -179,7 +179,7 @@ static struct irq_chip iproc_msi_irq_chip = {
 
 static struct msi_domain_info iproc_msi_domain_info = {
 	.flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
-		MSI_FLAG_PCI_MSIX,
+		MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX,
 	.chip = &iproc_msi_irq_chip,
 };
 
@@ -237,7 +237,7 @@ static void iproc_msi_irq_compose_msi_msg(struct irq_data *data,
 	addr = msi->msi_addr + iproc_msi_addr_offset(msi, data->hwirq);
 	msg->address_lo = lower_32_bits(addr);
 	msg->address_hi = upper_32_bits(addr);
-	msg->data = data->hwirq;
+	msg->data = data->hwirq << 5;
 }
 
 static struct irq_chip iproc_msi_bottom_irq_chip = {
@@ -251,7 +251,7 @@ static int iproc_msi_irq_domain_alloc(struct irq_domain *domain,
 				      void *args)
 {
 	struct iproc_msi *msi = domain->host_data;
-	int hwirq;
+	int hwirq, i;
 
 	mutex_lock(&msi->bitmap_lock);
 
@@ -267,10 +267,14 @@ static int iproc_msi_irq_domain_alloc(struct irq_domain *domain,
 
 	mutex_unlock(&msi->bitmap_lock);
 
-	irq_domain_set_info(domain, virq, hwirq, &iproc_msi_bottom_irq_chip,
-			    domain->host_data, handle_simple_irq, NULL, NULL);
+	for (i = 0; i < nr_irqs; i++) {
+		irq_domain_set_info(domain, virq + i, hwirq + i,
+				    &iproc_msi_bottom_irq_chip,
+				    domain->host_data, handle_simple_irq,
+				    NULL, NULL);
+	}
 
-	return 0;
+	return hwirq;
 }
 
 static void iproc_msi_irq_domain_free(struct irq_domain *domain,
@@ -302,7 +306,8 @@ static inline u32 decode_msi_hwirq(struct iproc_msi *msi, u32 eq, u32 head)
 
 	offs = iproc_msi_eq_offset(msi, eq) + head * sizeof(u32);
 	msg = (u32 *)(msi->eq_cpu + offs);
-	hwirq = *msg & IPROC_MSI_EQ_MASK;
+	hwirq = readl(msg);
+	hwirq = (hwirq >> 5) + (hwirq & 0x1f);
 
 	/*
 	 * Since we have multiple hwirq mapped to a single MSI vector,
diff --git a/drivers/pci/host/pcie-iproc.c b/drivers/pci/host/pcie-iproc.c
index 3a8b9d20ee57..935909bbe5c4 100644
--- a/drivers/pci/host/pcie-iproc.c
+++ b/drivers/pci/host/pcie-iproc.c
@@ -1097,24 +1097,6 @@ err_ib:
 	return ret;
 }
 
-static int pci_dma_range_parser_init(struct of_pci_range_parser *parser,
-				     struct device_node *node)
-{
-	const int na = 3, ns = 2;
-	int rlen;
-
-	parser->node = node;
-	parser->pna = of_n_addr_cells(node);
-	parser->np = parser->pna + na + ns;
-
-	parser->range = of_get_property(node, "dma-ranges", &rlen);
-	if (!parser->range)
-		return -ENOENT;
-
-	parser->end = parser->range + rlen / sizeof(__be32);
-	return 0;
-}
-
 static int iproc_pcie_map_dma_ranges(struct iproc_pcie *pcie)
 {
 	struct of_pci_range range;
@@ -1122,7 +1104,7 @@ static int iproc_pcie_map_dma_ranges(struct iproc_pcie *pcie)
 	int ret;
 
 	/* Get the dma-ranges from DT */
-	ret = pci_dma_range_parser_init(&parser, pcie->dev->of_node);
+	ret = of_pci_dma_range_parser_init(&parser, pcie->dev->of_node);
 	if (ret)
 		return ret;
 
diff --git a/drivers/pci/host/pcie-rcar.c b/drivers/pci/host/pcie-rcar.c
index 4e0b25d09b0c..12796eccb2be 100644
--- a/drivers/pci/host/pcie-rcar.c
+++ b/drivers/pci/host/pcie-rcar.c
@@ -1027,24 +1027,6 @@ static int rcar_pcie_inbound_ranges(struct rcar_pcie *pcie,
 	return 0;
 }
 
-static int pci_dma_range_parser_init(struct of_pci_range_parser *parser,
-				     struct device_node *node)
-{
-	const int na = 3, ns = 2;
-	int rlen;
-
-	parser->node = node;
-	parser->pna = of_n_addr_cells(node);
-	parser->np = parser->pna + na + ns;
-
-	parser->range = of_get_property(node, "dma-ranges", &rlen);
-	if (!parser->range)
-		return -ENOENT;
-
-	parser->end = parser->range + rlen / sizeof(__be32);
-	return 0;
-}
-
 static int rcar_pcie_parse_map_dma_ranges(struct rcar_pcie *pcie,
 					  struct device_node *np)
 {
@@ -1053,7 +1035,7 @@ static int rcar_pcie_parse_map_dma_ranges(struct rcar_pcie *pcie,
 	int index = 0;
 	int err;
 
-	if (pci_dma_range_parser_init(&parser, np))
+	if (of_pci_dma_range_parser_init(&parser, np))
 		return -EINVAL;
 
 	/* Get the dma-ranges from DT */
diff --git a/drivers/pci/host/pcie-tango.c b/drivers/pci/host/pcie-tango.c
index 95049de4131c..21a208da3f59 100644
--- a/drivers/pci/host/pcie-tango.c
+++ b/drivers/pci/host/pcie-tango.c
@@ -1,13 +1,173 @@
 // SPDX-License-Identifier: GPL-2.0
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
 #include <linux/pci-ecam.h>
 #include <linux/delay.h>
-#include <linux/of.h>
+#include <linux/msi.h>
+#include <linux/of_address.h>
+
+#define MSI_MAX			256
 
 #define SMP8759_MUX		0x48
 #define SMP8759_TEST_OUT	0x74
+#define SMP8759_DOORBELL	0x7c
+#define SMP8759_STATUS		0x80
+#define SMP8759_ENABLE		0xa0
 
 struct tango_pcie {
-	void __iomem *base;
+	DECLARE_BITMAP(used_msi, MSI_MAX);
+	u64			msi_doorbell;
+	spinlock_t		used_msi_lock;
+	void __iomem		*base;
+	struct irq_domain	*dom;
+};
+
+static void tango_msi_isr(struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct tango_pcie *pcie = irq_desc_get_handler_data(desc);
+	unsigned long status, base, virq, idx, pos = 0;
+
+	chained_irq_enter(chip, desc);
+	spin_lock(&pcie->used_msi_lock);
+
+	while ((pos = find_next_bit(pcie->used_msi, MSI_MAX, pos)) < MSI_MAX) {
+		base = round_down(pos, 32);
+		status = readl_relaxed(pcie->base + SMP8759_STATUS + base / 8);
+		for_each_set_bit(idx, &status, 32) {
+			virq = irq_find_mapping(pcie->dom, base + idx);
+			generic_handle_irq(virq);
+		}
+		pos = base + 32;
+	}
+
+	spin_unlock(&pcie->used_msi_lock);
+	chained_irq_exit(chip, desc);
+}
+
+static void tango_ack(struct irq_data *d)
+{
+	struct tango_pcie *pcie = d->chip_data;
+	u32 offset = (d->hwirq / 32) * 4;
+	u32 bit = BIT(d->hwirq % 32);
+
+	writel_relaxed(bit, pcie->base + SMP8759_STATUS + offset);
+}
+
+static void update_msi_enable(struct irq_data *d, bool unmask)
+{
+	unsigned long flags;
+	struct tango_pcie *pcie = d->chip_data;
+	u32 offset = (d->hwirq / 32) * 4;
+	u32 bit = BIT(d->hwirq % 32);
+	u32 val;
+
+	spin_lock_irqsave(&pcie->used_msi_lock, flags);
+	val = readl_relaxed(pcie->base + SMP8759_ENABLE + offset);
+	val = unmask ? val | bit : val & ~bit;
+	writel_relaxed(val, pcie->base + SMP8759_ENABLE + offset);
+	spin_unlock_irqrestore(&pcie->used_msi_lock, flags);
+}
+
+static void tango_mask(struct irq_data *d)
+{
+	update_msi_enable(d, false);
+}
+
+static void tango_unmask(struct irq_data *d)
+{
+	update_msi_enable(d, true);
+}
+
+static int tango_set_affinity(struct irq_data *d, const struct cpumask *mask,
+			      bool force)
+{
+	return -EINVAL;
+}
+
+static void tango_compose_msi_msg(struct irq_data *d, struct msi_msg *msg)
+{
+	struct tango_pcie *pcie = d->chip_data;
+	msg->address_lo = lower_32_bits(pcie->msi_doorbell);
+	msg->address_hi = upper_32_bits(pcie->msi_doorbell);
+	msg->data = d->hwirq;
+}
+
+static struct irq_chip tango_chip = {
+	.irq_ack		= tango_ack,
+	.irq_mask		= tango_mask,
+	.irq_unmask		= tango_unmask,
+	.irq_set_affinity	= tango_set_affinity,
+	.irq_compose_msi_msg	= tango_compose_msi_msg,
+};
+
+static void msi_ack(struct irq_data *d)
+{
+	irq_chip_ack_parent(d);
+}
+
+static void msi_mask(struct irq_data *d)
+{
+	pci_msi_mask_irq(d);
+	irq_chip_mask_parent(d);
+}
+
+static void msi_unmask(struct irq_data *d)
+{
+	pci_msi_unmask_irq(d);
+	irq_chip_unmask_parent(d);
+}
+
+static struct irq_chip msi_chip = {
+	.name = "MSI",
+	.irq_ack = msi_ack,
+	.irq_mask = msi_mask,
+	.irq_unmask = msi_unmask,
+};
+
+static struct msi_domain_info msi_dom_info = {
+	.flags	= MSI_FLAG_PCI_MSIX
+		| MSI_FLAG_USE_DEF_DOM_OPS
+		| MSI_FLAG_USE_DEF_CHIP_OPS,
+	.chip	= &msi_chip,
+};
+
+static int tango_irq_domain_alloc(struct irq_domain *dom, unsigned int virq,
+				  unsigned int nr_irqs, void *args)
+{
+	struct tango_pcie *pcie = dom->host_data;
+	unsigned long flags;
+	int pos;
+
+	spin_lock_irqsave(&pcie->used_msi_lock, flags);
+	pos = find_first_zero_bit(pcie->used_msi, MSI_MAX);
+	if (pos >= MSI_MAX) {
+		spin_unlock_irqrestore(&pcie->used_msi_lock, flags);
+		return -ENOSPC;
+	}
+	__set_bit(pos, pcie->used_msi);
+	spin_unlock_irqrestore(&pcie->used_msi_lock, flags);
+	irq_domain_set_info(dom, virq, pos, &tango_chip,
+			pcie, handle_edge_irq, NULL, NULL);
+
+	return 0;
+}
+
+static void tango_irq_domain_free(struct irq_domain *dom, unsigned int virq,
+				  unsigned int nr_irqs)
+{
+	unsigned long flags;
+	struct irq_data *d = irq_domain_get_irq_data(dom, virq);
+	struct tango_pcie *pcie = d->chip_data;
+
+	spin_lock_irqsave(&pcie->used_msi_lock, flags);
+	__clear_bit(d->hwirq, pcie->used_msi);
+	spin_unlock_irqrestore(&pcie->used_msi_lock, flags);
+}
+
+static const struct irq_domain_ops dom_ops = {
+	.alloc	= tango_irq_domain_alloc,
+	.free	= tango_irq_domain_free,
 };
 
 static int smp8759_config_read(struct pci_bus *bus, unsigned int devfn,
@@ -77,7 +237,11 @@ static int tango_pcie_probe(struct platform_device *pdev)
 	struct device *dev = &pdev->dev;
 	struct tango_pcie *pcie;
 	struct resource *res;
-	int ret;
+	struct fwnode_handle *fwnode = of_node_to_fwnode(dev->of_node);
+	struct irq_domain *msi_dom, *irq_dom;
+	struct of_pci_range_parser parser;
+	struct of_pci_range range;
+	int virq, offset;
 
 	dev_warn(dev, "simultaneous PCI config and MMIO accesses may cause data corruption\n");
 	add_taint(TAINT_CRAP, LOCKDEP_STILL_OK);
@@ -96,6 +260,41 @@ static int tango_pcie_probe(struct platform_device *pdev)
 	if (!tango_pcie_link_up(pcie))
 		return -ENODEV;
 
+	if (of_pci_dma_range_parser_init(&parser, dev->of_node) < 0)
+		return -ENOENT;
+
+	if (of_pci_range_parser_one(&parser, &range) == NULL)
+		return -ENOENT;
+
+	range.pci_addr += range.size;
+	pcie->msi_doorbell = range.pci_addr + res->start + SMP8759_DOORBELL;
+
+	for (offset = 0; offset < MSI_MAX / 8; offset += 4)
+		writel_relaxed(0, pcie->base + SMP8759_ENABLE + offset);
+
+	virq = platform_get_irq(pdev, 1);
+	if (virq <= 0) {
+		dev_err(dev, "Failed to map IRQ\n");
+		return -ENXIO;
+	}
+
+	irq_dom = irq_domain_create_linear(fwnode, MSI_MAX, &dom_ops, pcie);
+	if (!irq_dom) {
+		dev_err(dev, "Failed to create IRQ domain\n");
+		return -ENOMEM;
+	}
+
+	msi_dom = pci_msi_create_irq_domain(fwnode, &msi_dom_info, irq_dom);
+	if (!msi_dom) {
+		dev_err(dev, "Failed to create MSI domain\n");
+		irq_domain_remove(irq_dom);
+		return -ENOMEM;
+	}
+
+	pcie->dom = irq_dom;
+	spin_lock_init(&pcie->used_msi_lock);
+	irq_set_chained_handler_and_data(virq, tango_msi_isr, pcie);
+
 	return pci_host_common_probe(pdev, &smp8759_ecam_ops);
 }
 
diff --git a/drivers/pci/host/pcie-xilinx.c b/drivers/pci/host/pcie-xilinx.c
index 94e13cb8608f..7b5325990f5e 100644
--- a/drivers/pci/host/pcie-xilinx.c
+++ b/drivers/pci/host/pcie-xilinx.c
@@ -129,7 +129,7 @@ static inline void pcie_write(struct xilinx_pcie_port *port, u32 val, u32 reg)
 	writel(val, port->reg_base + reg);
 }
 
-static inline bool xilinx_pcie_link_is_up(struct xilinx_pcie_port *port)
+static inline bool xilinx_pcie_link_up(struct xilinx_pcie_port *port)
 {
 	return (pcie_read(port, XILINX_PCIE_REG_PSCR) &
 		XILINX_PCIE_REG_PSCR_LNKUP) ? 1 : 0;
@@ -165,7 +165,7 @@ static bool xilinx_pcie_valid_device(struct pci_bus *bus, unsigned int devfn)
 
 	/* Check if link is up when trying to access downstream ports */
 	if (bus->number != port->root_busno)
-		if (!xilinx_pcie_link_is_up(port))
+		if (!xilinx_pcie_link_up(port))
 			return false;
 
 	/* Only one device down on each root port */
@@ -541,7 +541,7 @@ static void xilinx_pcie_init_port(struct xilinx_pcie_port *port)
 {
 	struct device *dev = port->dev;
 
-	if (xilinx_pcie_link_is_up(port))
+	if (xilinx_pcie_link_up(port))
 		dev_info(dev, "PCIe Link is UP\n");
 	else
 		dev_info(dev, "PCIe Link is DOWN\n");