Linux-libre 4.7.1-gnupck-4.7.1-gnu

18 files changed, 950 insertions, 370 deletions

diff --git a/drivers/pci/host/Kconfig b/drivers/pci/host/Kconfig
index 7a0780d56..5d2374e4e 100644
--- a/drivers/pci/host/Kconfig
+++ b/drivers/pci/host/Kconfig
@@ -69,14 +69,17 @@ config PCI_RCAR_GEN2
 	  There are 3 internal PCI controllers available with a single
 	  built-in EHCI/OHCI host controller present on each one.
 
-config PCI_RCAR_GEN2_PCIE
+config PCIE_RCAR
 	bool "Renesas R-Car PCIe controller"
 	depends on ARCH_RENESAS || (ARM && COMPILE_TEST)
+	select PCI_MSI
+	select PCI_MSI_IRQ_DOMAIN
 	help
-	  Say Y here if you want PCIe controller support on R-Car Gen2 SoCs.
+	  Say Y here if you want PCIe controller support on R-Car SoCs.
 
 config PCI_HOST_COMMON
 	bool
+	select PCI_ECAM
 
 config PCI_HOST_GENERIC
 	bool "Generic PCI host controller"
@@ -231,4 +234,15 @@ config PCI_HOST_THUNDER_ECAM
 	help
 	  Say Y here if you want ECAM support for CN88XX-Pass-1.x Cavium Thunder SoCs.
 
+config PCIE_ARMADA_8K
+	bool "Marvell Armada-8K PCIe controller"
+	depends on ARCH_MVEBU
+	select PCIE_DW
+	select PCIEPORTBUS
+	help
+	  Say Y here if you want to enable PCIe controller support on
+	  Armada-8K SoCs. The PCIe controller on Armada-8K is based on
+	  Designware hardware and therefore the driver re-uses the
+	  Designware core functions to implement the driver.
+
 endmenu
diff --git a/drivers/pci/host/Makefile b/drivers/pci/host/Makefile
index d85b5faf9..9c8698e89 100644
--- a/drivers/pci/host/Makefile
+++ b/drivers/pci/host/Makefile
@@ -7,7 +7,7 @@ obj-$(CONFIG_PCI_HYPERV) += pci-hyperv.o
 obj-$(CONFIG_PCI_MVEBU) += pci-mvebu.o
 obj-$(CONFIG_PCI_TEGRA) += pci-tegra.o
 obj-$(CONFIG_PCI_RCAR_GEN2) += pci-rcar-gen2.o
-obj-$(CONFIG_PCI_RCAR_GEN2_PCIE) += pcie-rcar.o
+obj-$(CONFIG_PCIE_RCAR) += pcie-rcar.o
 obj-$(CONFIG_PCI_HOST_COMMON) += pci-host-common.o
 obj-$(CONFIG_PCI_HOST_GENERIC) += pci-host-generic.o
 obj-$(CONFIG_PCIE_SPEAR13XX) += pcie-spear13xx.o
@@ -28,3 +28,4 @@ obj-$(CONFIG_PCI_HISI) += pcie-hisi.o
 obj-$(CONFIG_PCIE_QCOM) += pcie-qcom.o
 obj-$(CONFIG_PCI_HOST_THUNDER_ECAM) += pci-thunder-ecam.o
 obj-$(CONFIG_PCI_HOST_THUNDER_PEM) += pci-thunder-pem.o
+obj-$(CONFIG_PCIE_ARMADA_8K) += pcie-armada8k.o
diff --git a/drivers/pci/host/pci-dra7xx.c b/drivers/pci/host/pci-dra7xx.c
index 2ca3a1f30..f44113040 100644
--- a/drivers/pci/host/pci-dra7xx.c
+++ b/drivers/pci/host/pci-dra7xx.c
@@ -142,13 +142,13 @@ static void dra7xx_pcie_enable_interrupts(struct pcie_port *pp)
 
 static void dra7xx_pcie_host_init(struct pcie_port *pp)
 {
-	dw_pcie_setup_rc(pp);
-
 	pp->io_base &= DRA7XX_CPU_TO_BUS_ADDR;
 	pp->mem_base &= DRA7XX_CPU_TO_BUS_ADDR;
 	pp->cfg0_base &= DRA7XX_CPU_TO_BUS_ADDR;
 	pp->cfg1_base &= DRA7XX_CPU_TO_BUS_ADDR;
 
+	dw_pcie_setup_rc(pp);
+
 	dra7xx_pcie_establish_link(pp);
 	if (IS_ENABLED(CONFIG_PCI_MSI))
 		dw_pcie_msi_init(pp);
diff --git a/drivers/pci/host/pci-host-common.c b/drivers/pci/host/pci-host-common.c
index e9f850f07..8cba7ab73 100644
--- a/drivers/pci/host/pci-host-common.c
+++ b/drivers/pci/host/pci-host-common.c
@@ -22,27 +22,21 @@
 #include <linux/of_pci.h>
 #include <linux/platform_device.h>
 
-#include "pci-host-common.h"
+#include "../ecam.h"
 
-static void gen_pci_release_of_pci_ranges(struct gen_pci *pci)
-{
-	pci_free_resource_list(&pci->resources);
-}
-
-static int gen_pci_parse_request_of_pci_ranges(struct gen_pci *pci)
+static int gen_pci_parse_request_of_pci_ranges(struct device *dev,
+		       struct list_head *resources, struct resource **bus_range)
 {
 	int err, res_valid = 0;
-	struct device *dev = pci->host.dev.parent;
 	struct device_node *np = dev->of_node;
 	resource_size_t iobase;
 	struct resource_entry *win;
 
-	err = of_pci_get_host_bridge_resources(np, 0, 0xff, &pci->resources,
-					       &iobase);
+	err = of_pci_get_host_bridge_resources(np, 0, 0xff, resources, &iobase);
 	if (err)
 		return err;
 
-	resource_list_for_each_entry(win, &pci->resources) {
+	resource_list_for_each_entry(win, resources) {
 		struct resource *parent, *res = win->res;
 
 		switch (resource_type(res)) {
@@ -60,7 +54,7 @@ static int gen_pci_parse_request_of_pci_ranges(struct gen_pci *pci)
 			res_valid |= !(res->flags & IORESOURCE_PREFETCH);
 			break;
 		case IORESOURCE_BUS:
-			pci->cfg.bus_range = res;
+			*bus_range = res;
 		default:
 			continue;
 		}
@@ -79,65 +73,60 @@ static int gen_pci_parse_request_of_pci_ranges(struct gen_pci *pci)
 	return 0;
 
 out_release_res:
-	gen_pci_release_of_pci_ranges(pci);
 	return err;
 }
 
-static int gen_pci_parse_map_cfg_windows(struct gen_pci *pci)
+static void gen_pci_unmap_cfg(void *ptr)
+{
+	pci_ecam_free((struct pci_config_window *)ptr);
+}
+
+static struct pci_config_window *gen_pci_init(struct device *dev,
+		struct list_head *resources, struct pci_ecam_ops *ops)
 {
 	int err;
-	u8 bus_max;
-	resource_size_t busn;
-	struct resource *bus_range;
-	struct device *dev = pci->host.dev.parent;
-	struct device_node *np = dev->of_node;
-	u32 sz = 1 << pci->cfg.ops->bus_shift;
+	struct resource cfgres;
+	struct resource *bus_range = NULL;
+	struct pci_config_window *cfg;
 
-	err = of_address_to_resource(np, 0, &pci->cfg.res);
+	/* Parse our PCI ranges and request their resources */
+	err = gen_pci_parse_request_of_pci_ranges(dev, resources, &bus_range);
+	if (err)
+		goto err_out;
+
+	err = of_address_to_resource(dev->of_node, 0, &cfgres);
 	if (err) {
 		dev_err(dev, "missing \"reg\" property\n");
-		return err;
+		goto err_out;
 	}
 
-	/* Limit the bus-range to fit within reg */
-	bus_max = pci->cfg.bus_range->start +
-		  (resource_size(&pci->cfg.res) >> pci->cfg.ops->bus_shift) - 1;
-	pci->cfg.bus_range->end = min_t(resource_size_t,
-					pci->cfg.bus_range->end, bus_max);
-
-	pci->cfg.win = devm_kcalloc(dev, resource_size(pci->cfg.bus_range),
-				    sizeof(*pci->cfg.win), GFP_KERNEL);
-	if (!pci->cfg.win)
-		return -ENOMEM;
-
-	/* Map our Configuration Space windows */
-	if (!devm_request_mem_region(dev, pci->cfg.res.start,
-				     resource_size(&pci->cfg.res),
-				     "Configuration Space"))
-		return -ENOMEM;
-
-	bus_range = pci->cfg.bus_range;
-	for (busn = bus_range->start; busn <= bus_range->end; ++busn) {
-		u32 idx = busn - bus_range->start;
-
-		pci->cfg.win[idx] = devm_ioremap(dev,
-						 pci->cfg.res.start + idx * sz,
-						 sz);
-		if (!pci->cfg.win[idx])
-			return -ENOMEM;
+	cfg = pci_ecam_create(dev, &cfgres, bus_range, ops);
+	if (IS_ERR(cfg)) {
+		err = PTR_ERR(cfg);
+		goto err_out;
 	}
 
-	return 0;
+	err = devm_add_action(dev, gen_pci_unmap_cfg, cfg);
+	if (err) {
+		gen_pci_unmap_cfg(cfg);
+		goto err_out;
+	}
+	return cfg;
+
+err_out:
+	pci_free_resource_list(resources);
+	return ERR_PTR(err);
 }
 
 int pci_host_common_probe(struct platform_device *pdev,
-			  struct gen_pci *pci)
+			  struct pci_ecam_ops *ops)
 {
-	int err;
 	const char *type;
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
 	struct pci_bus *bus, *child;
+	struct pci_config_window *cfg;
+	struct list_head resources;
 
 	type = of_get_property(np, "device_type", NULL);
 	if (!type || strcmp(type, "pci")) {
@@ -147,29 +136,18 @@ int pci_host_common_probe(struct platform_device *pdev,
 
 	of_pci_check_probe_only();
 
-	pci->host.dev.parent = dev;
-	INIT_LIST_HEAD(&pci->host.windows);
-	INIT_LIST_HEAD(&pci->resources);
-
-	/* Parse our PCI ranges and request their resources */
-	err = gen_pci_parse_request_of_pci_ranges(pci);
-	if (err)
-		return err;
-
 	/* Parse and map our Configuration Space windows */
-	err = gen_pci_parse_map_cfg_windows(pci);
-	if (err) {
-		gen_pci_release_of_pci_ranges(pci);
-		return err;
-	}
+	INIT_LIST_HEAD(&resources);
+	cfg = gen_pci_init(dev, &resources, ops);
+	if (IS_ERR(cfg))
+		return PTR_ERR(cfg);
 
 	/* Do not reassign resources if probe only */
 	if (!pci_has_flag(PCI_PROBE_ONLY))
 		pci_add_flags(PCI_REASSIGN_ALL_RSRC | PCI_REASSIGN_ALL_BUS);
 
-
-	bus = pci_scan_root_bus(dev, pci->cfg.bus_range->start,
-				&pci->cfg.ops->ops, pci, &pci->resources);
+	bus = pci_scan_root_bus(dev, cfg->busr.start, &ops->pci_ops, cfg,
+				&resources);
 	if (!bus) {
 		dev_err(dev, "Scanning rootbus failed");
 		return -ENODEV;
diff --git a/drivers/pci/host/pci-host-common.h b/drivers/pci/host/pci-host-common.h
deleted file mode 100644
index 09f3fa0a5..000000000
--- a/drivers/pci/host/pci-host-common.h
+++ /dev/null
@@ -1,47 +0,0 @@
-/*
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it will be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program.  If not, see <http://www.gnu.org/licenses/>.
- *
- * Copyright (C) 2014 ARM Limited
- *
- * Author: Will Deacon <will.deacon@arm.com>
- */
-
-#ifndef _PCI_HOST_COMMON_H
-#define _PCI_HOST_COMMON_H
-
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
-
-struct gen_pci_cfg_bus_ops {
-	u32 bus_shift;
-	struct pci_ops ops;
-};
-
-struct gen_pci_cfg_windows {
-	struct resource				res;
-	struct resource				*bus_range;
-	void __iomem				**win;
-
-	struct gen_pci_cfg_bus_ops		*ops;
-};
-
-struct gen_pci {
-	struct pci_host_bridge			host;
-	struct gen_pci_cfg_windows		cfg;
-	struct list_head			resources;
-};
-
-int pci_host_common_probe(struct platform_device *pdev,
-			  struct gen_pci *pci);
-
-#endif /* _PCI_HOST_COMMON_H */
diff --git a/drivers/pci/host/pci-host-generic.c b/drivers/pci/host/pci-host-generic.c
index e8aa78faa..6eaceab1b 100644
--- a/drivers/pci/host/pci-host-generic.c
+++ b/drivers/pci/host/pci-host-generic.c
@@ -25,41 +25,12 @@
 #include <linux/of_pci.h>
 #include <linux/platform_device.h>
 
-#include "pci-host-common.h"
+#include "../ecam.h"
 
-static void __iomem *gen_pci_map_cfg_bus_cam(struct pci_bus *bus,
-					     unsigned int devfn,
-					     int where)
-{
-	struct gen_pci *pci = bus->sysdata;
-	resource_size_t idx = bus->number - pci->cfg.bus_range->start;
-
-	return pci->cfg.win[idx] + ((devfn << 8) | where);
-}
-
-static struct gen_pci_cfg_bus_ops gen_pci_cfg_cam_bus_ops = {
+static struct pci_ecam_ops gen_pci_cfg_cam_bus_ops = {
 	.bus_shift	= 16,
-	.ops		= {
-		.map_bus	= gen_pci_map_cfg_bus_cam,
-		.read		= pci_generic_config_read,
-		.write		= pci_generic_config_write,
-	}
-};
-
-static void __iomem *gen_pci_map_cfg_bus_ecam(struct pci_bus *bus,
-					      unsigned int devfn,
-					      int where)
-{
-	struct gen_pci *pci = bus->sysdata;
-	resource_size_t idx = bus->number - pci->cfg.bus_range->start;
-
-	return pci->cfg.win[idx] + ((devfn << 12) | where);
-}
-
-static struct gen_pci_cfg_bus_ops gen_pci_cfg_ecam_bus_ops = {
-	.bus_shift	= 20,
-	.ops		= {
-		.map_bus	= gen_pci_map_cfg_bus_ecam,
+	.pci_ops	= {
+		.map_bus	= pci_ecam_map_bus,
 		.read		= pci_generic_config_read,
 		.write		= pci_generic_config_write,
 	}
@@ -70,25 +41,22 @@ static const struct of_device_id gen_pci_of_match[] = {
 	  .data = &gen_pci_cfg_cam_bus_ops },
 
 	{ .compatible = "pci-host-ecam-generic",
-	  .data = &gen_pci_cfg_ecam_bus_ops },
+	  .data = &pci_generic_ecam_ops },
 
 	{ },
 };
+
 MODULE_DEVICE_TABLE(of, gen_pci_of_match);
 
 static int gen_pci_probe(struct platform_device *pdev)
 {
-	struct device *dev = &pdev->dev;
 	const struct of_device_id *of_id;
-	struct gen_pci *pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL);
-
-	if (!pci)
-		return -ENOMEM;
+	struct pci_ecam_ops *ops;
 
-	of_id = of_match_node(gen_pci_of_match, dev->of_node);
-	pci->cfg.ops = (struct gen_pci_cfg_bus_ops *)of_id->data;
+	of_id = of_match_node(gen_pci_of_match, pdev->dev.of_node);
+	ops = (struct pci_ecam_ops *)of_id->data;
 
-	return pci_host_common_probe(pdev, pci);
+	return pci_host_common_probe(pdev, ops);
 }
 
 static struct platform_driver gen_pci_driver = {
diff --git a/drivers/pci/host/pci-hyperv.c b/drivers/pci/host/pci-hyperv.c
index ed651baa7..7e9b2de2a 100644
--- a/drivers/pci/host/pci-hyperv.c
+++ b/drivers/pci/host/pci-hyperv.c
@@ -553,6 +553,8 @@ static void _hv_pcifront_read_config(struct hv_pci_dev *hpdev, int where,
 		spin_lock_irqsave(&hpdev->hbus->config_lock, flags);
 		/* Choose the function to be read. (See comment above) */
 		writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr);
+		/* Make sure the function was chosen before we start reading. */
+		mb();
 		/* Read from that function's config space. */
 		switch (size) {
 		case 1:
@@ -565,6 +567,11 @@ static void _hv_pcifront_read_config(struct hv_pci_dev *hpdev, int where,
 			*val = readl(addr);
 			break;
 		}
+		/*
+		 * Make sure the write was done before we release the spinlock
+		 * allowing consecutive reads/writes.
+		 */
+		mb();
 		spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags);
 	} else {
 		dev_err(&hpdev->hbus->hdev->device,
@@ -592,6 +599,8 @@ static void _hv_pcifront_write_config(struct hv_pci_dev *hpdev, int where,
 		spin_lock_irqsave(&hpdev->hbus->config_lock, flags);
 		/* Choose the function to be written. (See comment above) */
 		writel(hpdev->desc.win_slot.slot, hpdev->hbus->cfg_addr);
+		/* Make sure the function was chosen before we start writing. */
+		wmb();
 		/* Write to that function's config space. */
 		switch (size) {
 		case 1:
@@ -604,6 +613,11 @@ static void _hv_pcifront_write_config(struct hv_pci_dev *hpdev, int where,
 			writel(val, addr);
 			break;
 		}
+		/*
+		 * Make sure the write was done before we release the spinlock
+		 * allowing consecutive reads/writes.
+		 */
+		mb();
 		spin_unlock_irqrestore(&hpdev->hbus->config_lock, flags);
 	} else {
 		dev_err(&hpdev->hbus->hdev->device,
@@ -1795,14 +1809,14 @@ static void hv_pci_free_bridge_windows(struct hv_pcibus_device *hbus)
 
 	if (hbus->low_mmio_space && hbus->low_mmio_res) {
 		hbus->low_mmio_res->flags |= IORESOURCE_BUSY;
-		release_mem_region(hbus->low_mmio_res->start,
-				   resource_size(hbus->low_mmio_res));
+		vmbus_free_mmio(hbus->low_mmio_res->start,
+				resource_size(hbus->low_mmio_res));
 	}
 
 	if (hbus->high_mmio_space && hbus->high_mmio_res) {
 		hbus->high_mmio_res->flags |= IORESOURCE_BUSY;
-		release_mem_region(hbus->high_mmio_res->start,
-				   resource_size(hbus->high_mmio_res));
+		vmbus_free_mmio(hbus->high_mmio_res->start,
+				resource_size(hbus->high_mmio_res));
 	}
 }
 
@@ -1880,8 +1894,8 @@ static int hv_pci_allocate_bridge_windows(struct hv_pcibus_device *hbus)
 
 release_low_mmio:
 	if (hbus->low_mmio_res) {
-		release_mem_region(hbus->low_mmio_res->start,
-				   resource_size(hbus->low_mmio_res));
+		vmbus_free_mmio(hbus->low_mmio_res->start,
+				resource_size(hbus->low_mmio_res));
 	}
 
 	return ret;
@@ -1924,7 +1938,7 @@ static int hv_allocate_config_window(struct hv_pcibus_device *hbus)
 
 static void hv_free_config_window(struct hv_pcibus_device *hbus)
 {
-	release_mem_region(hbus->mem_config->start, PCI_CONFIG_MMIO_LENGTH);
+	vmbus_free_mmio(hbus->mem_config->start, PCI_CONFIG_MMIO_LENGTH);
 }
 
 /**
@@ -2268,11 +2282,6 @@ static int hv_pci_remove(struct hv_device *hdev)
 
 	hbus = hv_get_drvdata(hdev);
 
-	ret = hv_send_resources_released(hdev);
-	if (ret)
-		dev_err(&hdev->device,
-			"Couldn't send resources released packet(s)\n");
-
 	memset(&pkt.teardown_packet, 0, sizeof(pkt.teardown_packet));
 	init_completion(&comp_pkt.host_event);
 	pkt.teardown_packet.completion_func = hv_pci_generic_compl;
@@ -2295,6 +2304,11 @@ static int hv_pci_remove(struct hv_device *hdev)
 		pci_unlock_rescan_remove();
 	}
 
+	ret = hv_send_resources_released(hdev);
+	if (ret)
+		dev_err(&hdev->device,
+			"Couldn't send resources released packet(s)\n");
+
 	vmbus_close(hdev->channel);
 
 	/* Delete any children which might still exist. */
diff --git a/drivers/pci/host/pci-imx6.c b/drivers/pci/host/pci-imx6.c
index 2f817fa4c..b741a36a6 100644
--- a/drivers/pci/host/pci-imx6.c
+++ b/drivers/pci/host/pci-imx6.c
@@ -19,6 +19,7 @@
 #include <linux/mfd/syscon/imx6q-iomuxc-gpr.h>
 #include <linux/module.h>
 #include <linux/of_gpio.h>
+#include <linux/of_device.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
@@ -31,19 +32,29 @@
 
 #define to_imx6_pcie(x)	container_of(x, struct imx6_pcie, pp)
 
+enum imx6_pcie_variants {
+	IMX6Q,
+	IMX6SX,
+	IMX6QP,
+};
+
 struct imx6_pcie {
 	int			reset_gpio;
+	bool			gpio_active_high;
 	struct clk		*pcie_bus;
 	struct clk		*pcie_phy;
+	struct clk		*pcie_inbound_axi;
 	struct clk		*pcie;
 	struct pcie_port	pp;
 	struct regmap		*iomuxc_gpr;
+	enum imx6_pcie_variants variant;
 	void __iomem		*mem_base;
 	u32			tx_deemph_gen1;
 	u32			tx_deemph_gen2_3p5db;
 	u32			tx_deemph_gen2_6db;
 	u32			tx_swing_full;
 	u32			tx_swing_low;
+	int			link_gen;
 };
 
 /* PCIe Root Complex registers (memory-mapped) */
@@ -236,37 +247,93 @@ static int imx6_pcie_assert_core_reset(struct pcie_port *pp)
 	struct imx6_pcie *imx6_pcie = to_imx6_pcie(pp);
 	u32 val, gpr1, gpr12;
 
-	/*
-	 * If the bootloader already enabled the link we need some special
-	 * handling to get the core back into a state where it is safe to
-	 * touch it for configuration.  As there is no dedicated reset signal
-	 * wired up for MX6QDL, we need to manually force LTSSM into "detect"
-	 * state before completely disabling LTSSM, which is a prerequisite
-	 * for core configuration.
-	 *
-	 * If both LTSSM_ENABLE and REF_SSP_ENABLE are active we have a strong
-	 * indication that the bootloader activated the link.
-	 */
-	regmap_read(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1, &gpr1);
-	regmap_read(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, &gpr12);
+	switch (imx6_pcie->variant) {
+	case IMX6SX:
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
+				   IMX6SX_GPR12_PCIE_TEST_POWERDOWN,
+				   IMX6SX_GPR12_PCIE_TEST_POWERDOWN);
+		/* Force PCIe PHY reset */
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR5,
+				   IMX6SX_GPR5_PCIE_BTNRST_RESET,
+				   IMX6SX_GPR5_PCIE_BTNRST_RESET);
+		break;
+	case IMX6QP:
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
+				   IMX6Q_GPR1_PCIE_SW_RST,
+				   IMX6Q_GPR1_PCIE_SW_RST);
+		break;
+	case IMX6Q:
+		/*
+		 * If the bootloader already enabled the link we need some
+		 * special handling to get the core back into a state where
+		 * it is safe to touch it for configuration.  As there is
+		 * no dedicated reset signal wired up for MX6QDL, we need
+		 * to manually force LTSSM into "detect" state before
+		 * completely disabling LTSSM, which is a prerequisite for
+		 * core configuration.
+		 *
+		 * If both LTSSM_ENABLE and REF_SSP_ENABLE are active we
+		 * have a strong indication that the bootloader activated
+		 * the link.
+		 */
+		regmap_read(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1, &gpr1);
+		regmap_read(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, &gpr12);
+
+		if ((gpr1 & IMX6Q_GPR1_PCIE_REF_CLK_EN) &&
+		    (gpr12 & IMX6Q_GPR12_PCIE_CTL_2)) {
+			val = readl(pp->dbi_base + PCIE_PL_PFLR);
+			val &= ~PCIE_PL_PFLR_LINK_STATE_MASK;
+			val |= PCIE_PL_PFLR_FORCE_LINK;
+			writel(val, pp->dbi_base + PCIE_PL_PFLR);
+
+			regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
+					   IMX6Q_GPR12_PCIE_CTL_2, 0 << 10);
+		}
+
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
+				   IMX6Q_GPR1_PCIE_TEST_PD, 1 << 18);
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
+				   IMX6Q_GPR1_PCIE_REF_CLK_EN, 0 << 16);
+		break;
+	}
+
+	return 0;
+}
+
+static int imx6_pcie_enable_ref_clk(struct imx6_pcie *imx6_pcie)
+{
+	struct pcie_port *pp = &imx6_pcie->pp;
+	int ret = 0;
 
-	if ((gpr1 & IMX6Q_GPR1_PCIE_REF_CLK_EN) &&
-	    (gpr12 & IMX6Q_GPR12_PCIE_CTL_2)) {
-		val = readl(pp->dbi_base + PCIE_PL_PFLR);
-		val &= ~PCIE_PL_PFLR_LINK_STATE_MASK;
-		val |= PCIE_PL_PFLR_FORCE_LINK;
-		writel(val, pp->dbi_base + PCIE_PL_PFLR);
+	switch (imx6_pcie->variant) {
+	case IMX6SX:
+		ret = clk_prepare_enable(imx6_pcie->pcie_inbound_axi);
+		if (ret) {
+			dev_err(pp->dev, "unable to enable pcie_axi clock\n");
+			break;
+		}
 
 		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
-				IMX6Q_GPR12_PCIE_CTL_2, 0 << 10);
+				   IMX6SX_GPR12_PCIE_TEST_POWERDOWN, 0);
+		break;
+	case IMX6QP: 		/* FALLTHROUGH */
+	case IMX6Q:
+		/* power up core phy and enable ref clock */
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
+				   IMX6Q_GPR1_PCIE_TEST_PD, 0 << 18);
+		/*
+		 * the async reset input need ref clock to sync internally,
+		 * when the ref clock comes after reset, internal synced
+		 * reset time is too short, cannot meet the requirement.
+		 * add one ~10us delay here.
+		 */
+		udelay(10);
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
+				   IMX6Q_GPR1_PCIE_REF_CLK_EN, 1 << 16);
+		break;
 	}
 
-	regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
-			IMX6Q_GPR1_PCIE_TEST_PD, 1 << 18);
-	regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
-			IMX6Q_GPR1_PCIE_REF_CLK_EN, 0 << 16);
-
-	return 0;
+	return ret;
 }
 
 static int imx6_pcie_deassert_core_reset(struct pcie_port *pp)
@@ -292,43 +359,60 @@ static int imx6_pcie_deassert_core_reset(struct pcie_port *pp)
 		goto err_pcie;
 	}
 
-	/* power up core phy and enable ref clock */
-	regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
-			IMX6Q_GPR1_PCIE_TEST_PD, 0 << 18);
-	/*
-	 * the async reset input need ref clock to sync internally,
-	 * when the ref clock comes after reset, internal synced
-	 * reset time is too short, cannot meet the requirement.
-	 * add one ~10us delay here.
-	 */
-	udelay(10);
-	regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
-			IMX6Q_GPR1_PCIE_REF_CLK_EN, 1 << 16);
+	ret = imx6_pcie_enable_ref_clk(imx6_pcie);
+	if (ret) {
+		dev_err(pp->dev, "unable to enable pcie ref clock\n");
+		goto err_ref_clk;
+	}
 
 	/* allow the clocks to stabilize */
 	usleep_range(200, 500);
 
 	/* Some boards don't have PCIe reset GPIO. */
 	if (gpio_is_valid(imx6_pcie->reset_gpio)) {
-		gpio_set_value_cansleep(imx6_pcie->reset_gpio, 0);
+		gpio_set_value_cansleep(imx6_pcie->reset_gpio,
+					imx6_pcie->gpio_active_high);
 		msleep(100);
-		gpio_set_value_cansleep(imx6_pcie->reset_gpio, 1);
+		gpio_set_value_cansleep(imx6_pcie->reset_gpio,
+					!imx6_pcie->gpio_active_high);
 	}
+
+	switch (imx6_pcie->variant) {
+	case IMX6SX:
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR5,
+				   IMX6SX_GPR5_PCIE_BTNRST_RESET, 0);
+		break;
+	case IMX6QP:
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
+				   IMX6Q_GPR1_PCIE_SW_RST, 0);
+
+		usleep_range(200, 500);
+		break;
+	case IMX6Q:		/* Nothing to do */
+		break;
+	}
+
 	return 0;
 
+err_ref_clk:
+	clk_disable_unprepare(imx6_pcie->pcie);
 err_pcie:
 	clk_disable_unprepare(imx6_pcie->pcie_bus);
 err_pcie_bus:
 	clk_disable_unprepare(imx6_pcie->pcie_phy);
 err_pcie_phy:
 	return ret;
-
 }
 
 static void imx6_pcie_init_phy(struct pcie_port *pp)
 {
 	struct imx6_pcie *imx6_pcie = to_imx6_pcie(pp);
 
+	if (imx6_pcie->variant == IMX6SX)
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
+				   IMX6SX_GPR12_PCIE_RX_EQ_MASK,
+				   IMX6SX_GPR12_PCIE_RX_EQ_2);
+
 	regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
 			IMX6Q_GPR12_PCIE_CTL_2, 0 << 10);
 
@@ -417,11 +501,15 @@ static int imx6_pcie_establish_link(struct pcie_port *pp)
 		goto err_reset_phy;
 	}
 
-	/* Allow Gen2 mode after the link is up. */
-	tmp = readl(pp->dbi_base + PCIE_RC_LCR);
-	tmp &= ~PCIE_RC_LCR_MAX_LINK_SPEEDS_MASK;
-	tmp |= PCIE_RC_LCR_MAX_LINK_SPEEDS_GEN2;
-	writel(tmp, pp->dbi_base + PCIE_RC_LCR);
+	if (imx6_pcie->link_gen == 2) {
+		/* Allow Gen2 mode after the link is up. */
+		tmp = readl(pp->dbi_base + PCIE_RC_LCR);
+		tmp &= ~PCIE_RC_LCR_MAX_LINK_SPEEDS_MASK;
+		tmp |= PCIE_RC_LCR_MAX_LINK_SPEEDS_GEN2;
+		writel(tmp, pp->dbi_base + PCIE_RC_LCR);
+	} else {
+		dev_info(pp->dev, "Link: Gen2 disabled\n");
+	}
 
 	/*
 	 * Start Directed Speed Change so the best possible speed both link
@@ -445,8 +533,7 @@ static int imx6_pcie_establish_link(struct pcie_port *pp)
 	}
 
 	tmp = readl(pp->dbi_base + PCIE_RC_LCSR);
-	dev_dbg(pp->dev, "Link up, Gen=%i\n", (tmp >> 16) & 0xf);
-
+	dev_info(pp->dev, "Link up, Gen%i\n", (tmp >> 16) & 0xf);
 	return 0;
 
 err_reset_phy:
@@ -535,6 +622,9 @@ static int __init imx6_pcie_probe(struct platform_device *pdev)
 	pp = &imx6_pcie->pp;
 	pp->dev = &pdev->dev;
 
+	imx6_pcie->variant =
+		(enum imx6_pcie_variants)of_device_get_match_data(&pdev->dev);
+
 	/* Added for PCI abort handling */
 	hook_fault_code(16 + 6, imx6q_pcie_abort_handler, SIGBUS, 0,
 		"imprecise external abort");
@@ -546,9 +636,14 @@ static int __init imx6_pcie_probe(struct platform_device *pdev)
 
 	/* Fetch GPIOs */
 	imx6_pcie->reset_gpio = of_get_named_gpio(np, "reset-gpio", 0);
+	imx6_pcie->gpio_active_high = of_property_read_bool(np,
+						"reset-gpio-active-high");
 	if (gpio_is_valid(imx6_pcie->reset_gpio)) {
 		ret = devm_gpio_request_one(&pdev->dev, imx6_pcie->reset_gpio,
-					    GPIOF_OUT_INIT_LOW, "PCIe reset");
+				imx6_pcie->gpio_active_high ?
+					GPIOF_OUT_INIT_HIGH :
+					GPIOF_OUT_INIT_LOW,
+				"PCIe reset");
 		if (ret) {
 			dev_err(&pdev->dev, "unable to get reset gpio\n");
 			return ret;
@@ -577,6 +672,16 @@ static int __init imx6_pcie_probe(struct platform_device *pdev)
 		return PTR_ERR(imx6_pcie->pcie);
 	}
 
+	if (imx6_pcie->variant == IMX6SX) {
+		imx6_pcie->pcie_inbound_axi = devm_clk_get(&pdev->dev,
+							   "pcie_inbound_axi");
+		if (IS_ERR(imx6_pcie->pcie_inbound_axi)) {
+			dev_err(&pdev->dev,
+				"pcie_incbound_axi clock missing or invalid\n");
+			return PTR_ERR(imx6_pcie->pcie_inbound_axi);
+		}
+	}
+
 	/* Grab GPR config register range */
 	imx6_pcie->iomuxc_gpr =
 		 syscon_regmap_lookup_by_compatible("fsl,imx6q-iomuxc-gpr");
@@ -606,6 +711,12 @@ static int __init imx6_pcie_probe(struct platform_device *pdev)
 				 &imx6_pcie->tx_swing_low))
 		imx6_pcie->tx_swing_low = 127;
 
+	/* Limit link speed */
+	ret = of_property_read_u32(pp->dev->of_node, "fsl,max-link-speed",
+				   &imx6_pcie->link_gen);
+	if (ret)
+		imx6_pcie->link_gen = 1;
+
 	ret = imx6_add_pcie_port(pp, pdev);
 	if (ret < 0)
 		return ret;
@@ -623,7 +734,9 @@ static void imx6_pcie_shutdown(struct platform_device *pdev)
 }
 
 static const struct of_device_id imx6_pcie_of_match[] = {
-	{ .compatible = "fsl,imx6q-pcie", },
+	{ .compatible = "fsl,imx6q-pcie",  .data = (void *)IMX6Q,  },
+	{ .compatible = "fsl,imx6sx-pcie", .data = (void *)IMX6SX, },
+	{ .compatible = "fsl,imx6qp-pcie", .data = (void *)IMX6QP, },
 	{},
 };
 MODULE_DEVICE_TABLE(of, imx6_pcie_of_match);
diff --git a/drivers/pci/host/pci-keystone-dw.c b/drivers/pci/host/pci-keystone-dw.c
index 6153853ca..41515092e 100644
--- a/drivers/pci/host/pci-keystone-dw.c
+++ b/drivers/pci/host/pci-keystone-dw.c
@@ -14,6 +14,7 @@
 
 #include <linux/irq.h>
 #include <linux/irqdomain.h>
+#include <linux/irqreturn.h>
 #include <linux/module.h>
 #include <linux/of.h>
 #include <linux/of_pci.h>
@@ -53,6 +54,21 @@
 #define IRQ_STATUS			0x184
 #define MSI_IRQ_OFFSET			4
 
+/* Error IRQ bits */
+#define ERR_AER		BIT(5)	/* ECRC error */
+#define ERR_AXI		BIT(4)	/* AXI tag lookup fatal error */
+#define ERR_CORR	BIT(3)	/* Correctable error */
+#define ERR_NONFATAL	BIT(2)	/* Non-fatal error */
+#define ERR_FATAL	BIT(1)	/* Fatal error */
+#define ERR_SYS		BIT(0)	/* System (fatal, non-fatal, or correctable) */
+#define ERR_IRQ_ALL	(ERR_AER | ERR_AXI | ERR_CORR | \
+			 ERR_NONFATAL | ERR_FATAL | ERR_SYS)
+#define ERR_FATAL_IRQ	(ERR_FATAL | ERR_AXI)
+#define ERR_IRQ_STATUS_RAW		0x1c0
+#define ERR_IRQ_STATUS			0x1c4
+#define ERR_IRQ_ENABLE_SET		0x1c8
+#define ERR_IRQ_ENABLE_CLR		0x1cc
+
 /* Config space registers */
 #define DEBUG0				0x728
 
@@ -243,6 +259,28 @@ void ks_dw_pcie_handle_legacy_irq(struct keystone_pcie *ks_pcie, int offset)
 	writel(offset, ks_pcie->va_app_base + IRQ_EOI);
 }
 
+void ks_dw_pcie_enable_error_irq(void __iomem *reg_base)
+{
+	writel(ERR_IRQ_ALL, reg_base + ERR_IRQ_ENABLE_SET);
+}
+
+irqreturn_t ks_dw_pcie_handle_error_irq(struct device *dev,
+					void __iomem *reg_base)
+{
+	u32 status;
+
+	status = readl(reg_base + ERR_IRQ_STATUS_RAW) & ERR_IRQ_ALL;
+	if (!status)
+		return IRQ_NONE;
+
+	if (status & ERR_FATAL_IRQ)
+		dev_err(dev, "fatal error (status %#010x)\n", status);
+
+	/* Ack the IRQ; status bits are RW1C */
+	writel(status, reg_base + ERR_IRQ_STATUS);
+	return IRQ_HANDLED;
+}
+
 static void ks_dw_pcie_ack_legacy_irq(struct irq_data *d)
 {
 }
diff --git a/drivers/pci/host/pci-keystone.c b/drivers/pci/host/pci-keystone.c
index b71f55bb0..6b8301ef2 100644
--- a/drivers/pci/host/pci-keystone.c
+++ b/drivers/pci/host/pci-keystone.c
@@ -15,6 +15,7 @@
 #include <linux/irqchip/chained_irq.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
+#include <linux/interrupt.h>
 #include <linux/irqdomain.h>
 #include <linux/module.h>
 #include <linux/msi.h>
@@ -159,7 +160,7 @@ static void ks_pcie_legacy_irq_handler(struct irq_desc *desc)
 static int ks_pcie_get_irq_controller_info(struct keystone_pcie *ks_pcie,
 					   char *controller, int *num_irqs)
 {
-	int temp, max_host_irqs, legacy = 1, *host_irqs, ret = -EINVAL;
+	int temp, max_host_irqs, legacy = 1, *host_irqs;
 	struct device *dev = ks_pcie->pp.dev;
 	struct device_node *np_pcie = dev->of_node, **np_temp;
 
@@ -180,11 +181,15 @@ static int ks_pcie_get_irq_controller_info(struct keystone_pcie *ks_pcie,
 	*np_temp = of_find_node_by_name(np_pcie, controller);
 	if (!(*np_temp)) {
 		dev_err(dev, "Node for %s is absent\n", controller);
-		goto out;
+		return -EINVAL;
 	}
+
 	temp = of_irq_count(*np_temp);
-	if (!temp)
-		goto out;
+	if (!temp) {
+		dev_err(dev, "No IRQ entries in %s\n", controller);
+		return -EINVAL;
+	}
+
 	if (temp > max_host_irqs)
 		dev_warn(dev, "Too many %s interrupts defined %u\n",
 			(legacy ? "legacy" : "MSI"), temp);
@@ -198,12 +203,13 @@ static int ks_pcie_get_irq_controller_info(struct keystone_pcie *ks_pcie,
 		if (!host_irqs[temp])
 			break;
 	}
+
 	if (temp) {
 		*num_irqs = temp;
-		ret = 0;
+		return 0;
 	}
-out:
-	return ret;
+
+	return -EINVAL;
 }
 
 static void ks_pcie_setup_interrupts(struct keystone_pcie *ks_pcie)
@@ -226,6 +232,9 @@ static void ks_pcie_setup_interrupts(struct keystone_pcie *ks_pcie)
 							 ks_pcie);
 		}
 	}
+
+	if (ks_pcie->error_irq > 0)
+		ks_dw_pcie_enable_error_irq(ks_pcie->va_app_base);
 }
 
 /*
@@ -289,6 +298,14 @@ static struct pcie_host_ops keystone_pcie_host_ops = {
 	.scan_bus = ks_dw_pcie_v3_65_scan_bus,
 };
 
+static irqreturn_t pcie_err_irq_handler(int irq, void *priv)
+{
+	struct keystone_pcie *ks_pcie = priv;
+
+	return ks_dw_pcie_handle_error_irq(ks_pcie->pp.dev,
+					   ks_pcie->va_app_base);
+}
+
 static int __init ks_add_pcie_port(struct keystone_pcie *ks_pcie,
 			 struct platform_device *pdev)
 {
@@ -309,6 +326,22 @@ static int __init ks_add_pcie_port(struct keystone_pcie *ks_pcie,
 			return ret;
 	}
 
+	/*
+	 * Index 0 is the platform interrupt for error interrupt
+	 * from RC.  This is optional.
+	 */
+	ks_pcie->error_irq = irq_of_parse_and_map(ks_pcie->np, 0);
+	if (ks_pcie->error_irq <= 0)
+		dev_info(&pdev->dev, "no error IRQ defined\n");
+	else {
+		if (request_irq(ks_pcie->error_irq, pcie_err_irq_handler,
+				IRQF_SHARED, "pcie-error-irq", ks_pcie) < 0) {
+			dev_err(&pdev->dev, "failed to request error IRQ %d\n",
+				ks_pcie->error_irq);
+			return ret;
+		}
+	}
+
 	pp->root_bus_nr = -1;
 	pp->ops = &keystone_pcie_host_ops;
 	ret = ks_dw_pcie_host_init(ks_pcie, ks_pcie->msi_intc_np);
@@ -317,7 +350,7 @@ static int __init ks_add_pcie_port(struct keystone_pcie *ks_pcie,
 		return ret;
 	}
 
-	return ret;
+	return 0;
 }
 
 static const struct of_device_id ks_pcie_of_match[] = {
@@ -346,7 +379,7 @@ static int __init ks_pcie_probe(struct platform_device *pdev)
 	struct resource *res;
 	void __iomem *reg_p;
 	struct phy *phy;
-	int ret = 0;
+	int ret;
 
 	ks_pcie = devm_kzalloc(&pdev->dev, sizeof(*ks_pcie),
 				GFP_KERNEL);
@@ -376,6 +409,7 @@ static int __init ks_pcie_probe(struct platform_device *pdev)
 	devm_release_mem_region(dev, res->start, resource_size(res));
 
 	pp->dev = dev;
+	ks_pcie->np = dev->of_node;
 	platform_set_drvdata(pdev, ks_pcie);
 	ks_pcie->clk = devm_clk_get(dev, "pcie");
 	if (IS_ERR(ks_pcie->clk)) {
diff --git a/drivers/pci/host/pci-keystone.h b/drivers/pci/host/pci-keystone.h
index f0944e8c4..a5b0cb2ba 100644
--- a/drivers/pci/host/pci-keystone.h
+++ b/drivers/pci/host/pci-keystone.h
@@ -29,6 +29,9 @@ struct keystone_pcie {
 	int			msi_host_irqs[MAX_MSI_HOST_IRQS];
 	struct			device_node *msi_intc_np;
 	struct irq_domain	*legacy_irq_domain;
+	struct device_node	*np;
+
+	int error_irq;
 
 	/* Application register space */
 	void __iomem		*va_app_base;
@@ -42,6 +45,9 @@ phys_addr_t ks_dw_pcie_get_msi_addr(struct pcie_port *pp);
 /* Keystone specific PCI controller APIs */
 void ks_dw_pcie_enable_legacy_irqs(struct keystone_pcie *ks_pcie);
 void ks_dw_pcie_handle_legacy_irq(struct keystone_pcie *ks_pcie, int offset);
+void ks_dw_pcie_enable_error_irq(void __iomem *reg_base);
+irqreturn_t ks_dw_pcie_handle_error_irq(struct device *dev,
+					void __iomem *reg_base);
 int  ks_dw_pcie_host_init(struct keystone_pcie *ks_pcie,
 			struct device_node *msi_intc_np);
 int ks_dw_pcie_wr_other_conf(struct pcie_port *pp, struct pci_bus *bus,
diff --git a/drivers/pci/host/pci-mvebu.c b/drivers/pci/host/pci-mvebu.c
index 53b79c5f0..6b451df65 100644
--- a/drivers/pci/host/pci-mvebu.c
+++ b/drivers/pci/host/pci-mvebu.c
@@ -1003,6 +1003,7 @@ static void mvebu_pcie_msi_enable(struct mvebu_pcie *pcie)
 		pcie->msi->dev = &pcie->pdev->dev;
 }
 
+#ifdef CONFIG_PM_SLEEP
 static int mvebu_pcie_suspend(struct device *dev)
 {
 	struct mvebu_pcie *pcie;
@@ -1031,6 +1032,7 @@ static int mvebu_pcie_resume(struct device *dev)
 
 	return 0;
 }
+#endif
 
 static void mvebu_pcie_port_clk_put(void *data)
 {
@@ -1298,9 +1300,8 @@ static const struct of_device_id mvebu_pcie_of_match_table[] = {
 };
 MODULE_DEVICE_TABLE(of, mvebu_pcie_of_match_table);
 
-static struct dev_pm_ops mvebu_pcie_pm_ops = {
-	.suspend_noirq = mvebu_pcie_suspend,
-	.resume_noirq = mvebu_pcie_resume,
+static const struct dev_pm_ops mvebu_pcie_pm_ops = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(mvebu_pcie_suspend, mvebu_pcie_resume)
 };
 
 static struct platform_driver mvebu_pcie_driver = {
diff --git a/drivers/pci/host/pci-tegra.c b/drivers/pci/host/pci-tegra.c
index 68d1f41b3..c388468c2 100644
--- a/drivers/pci/host/pci-tegra.c
+++ b/drivers/pci/host/pci-tegra.c
@@ -295,6 +295,7 @@ struct tegra_pcie {
 	struct reset_control *afi_rst;
 	struct reset_control *pcie_xrst;
 
+	bool legacy_phy;
 	struct phy *phy;
 
 	struct tegra_msi msi;
@@ -311,11 +312,14 @@ struct tegra_pcie {
 
 struct tegra_pcie_port {
 	struct tegra_pcie *pcie;
+	struct device_node *np;
 	struct list_head list;
 	struct resource regs;
 	void __iomem *base;
 	unsigned int index;
 	unsigned int lanes;
+
+	struct phy **phys;
 };
 
 struct tegra_pcie_bus {
@@ -860,6 +864,128 @@ static int tegra_pcie_phy_enable(struct tegra_pcie *pcie)
 	return 0;
 }
 
+static int tegra_pcie_phy_disable(struct tegra_pcie *pcie)
+{
+	const struct tegra_pcie_soc_data *soc = pcie->soc_data;
+	u32 value;
+
+	/* disable TX/RX data */
+	value = pads_readl(pcie, PADS_CTL);
+	value &= ~(PADS_CTL_TX_DATA_EN_1L | PADS_CTL_RX_DATA_EN_1L);
+	pads_writel(pcie, value, PADS_CTL);
+
+	/* override IDDQ */
+	value = pads_readl(pcie, PADS_CTL);
+	value |= PADS_CTL_IDDQ_1L;
+	pads_writel(pcie, PADS_CTL, value);
+
+	/* reset PLL */
+	value = pads_readl(pcie, soc->pads_pll_ctl);
+	value &= ~PADS_PLL_CTL_RST_B4SM;
+	pads_writel(pcie, value, soc->pads_pll_ctl);
+
+	usleep_range(20, 100);
+
+	return 0;
+}
+
+static int tegra_pcie_port_phy_power_on(struct tegra_pcie_port *port)
+{
+	struct device *dev = port->pcie->dev;
+	unsigned int i;
+	int err;
+
+	for (i = 0; i < port->lanes; i++) {
+		err = phy_power_on(port->phys[i]);
+		if (err < 0) {
+			dev_err(dev, "failed to power on PHY#%u: %d\n", i,
+				err);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static int tegra_pcie_port_phy_power_off(struct tegra_pcie_port *port)
+{
+	struct device *dev = port->pcie->dev;
+	unsigned int i;
+	int err;
+
+	for (i = 0; i < port->lanes; i++) {
+		err = phy_power_off(port->phys[i]);
+		if (err < 0) {
+			dev_err(dev, "failed to power off PHY#%u: %d\n", i,
+				err);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static int tegra_pcie_phy_power_on(struct tegra_pcie *pcie)
+{
+	struct tegra_pcie_port *port;
+	int err;
+
+	if (pcie->legacy_phy) {
+		if (pcie->phy)
+			err = phy_power_on(pcie->phy);
+		else
+			err = tegra_pcie_phy_enable(pcie);
+
+		if (err < 0)
+			dev_err(pcie->dev, "failed to power on PHY: %d\n", err);
+
+		return err;
+	}
+
+	list_for_each_entry(port, &pcie->ports, list) {
+		err = tegra_pcie_port_phy_power_on(port);
+		if (err < 0) {
+			dev_err(pcie->dev,
+				"failed to power on PCIe port %u PHY: %d\n",
+				port->index, err);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static int tegra_pcie_phy_power_off(struct tegra_pcie *pcie)
+{
+	struct tegra_pcie_port *port;
+	int err;
+
+	if (pcie->legacy_phy) {
+		if (pcie->phy)
+			err = phy_power_off(pcie->phy);
+		else
+			err = tegra_pcie_phy_disable(pcie);
+
+		if (err < 0)
+			dev_err(pcie->dev, "failed to power off PHY: %d\n",
+				err);
+
+		return err;
+	}
+
+	list_for_each_entry(port, &pcie->ports, list) {
+		err = tegra_pcie_port_phy_power_off(port);
+		if (err < 0) {
+			dev_err(pcie->dev,
+				"failed to power off PCIe port %u PHY: %d\n",
+				port->index, err);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
 static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 {
 	const struct tegra_pcie_soc_data *soc = pcie->soc_data;
@@ -899,13 +1025,9 @@ static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 		afi_writel(pcie, value, AFI_FUSE);
 	}
 
-	if (!pcie->phy)
-		err = tegra_pcie_phy_enable(pcie);
-	else
-		err = phy_power_on(pcie->phy);
-
+	err = tegra_pcie_phy_power_on(pcie);
 	if (err < 0) {
-		dev_err(pcie->dev, "failed to power on PHY: %d\n", err);
+		dev_err(pcie->dev, "failed to power on PHY(s): %d\n", err);
 		return err;
 	}
 
@@ -942,9 +1064,9 @@ static void tegra_pcie_power_off(struct tegra_pcie *pcie)
 
 	/* TODO: disable and unprepare clocks? */
 
-	err = phy_power_off(pcie->phy);
+	err = tegra_pcie_phy_power_off(pcie);
 	if (err < 0)
-		dev_warn(pcie->dev, "failed to power off PHY: %d\n", err);
+		dev_err(pcie->dev, "failed to power off PHY(s): %d\n", err);
 
 	reset_control_assert(pcie->pcie_xrst);
 	reset_control_assert(pcie->afi_rst);
@@ -1049,6 +1171,100 @@ static int tegra_pcie_resets_get(struct tegra_pcie *pcie)
 	return 0;
 }
 
+static int tegra_pcie_phys_get_legacy(struct tegra_pcie *pcie)
+{
+	int err;
+
+	pcie->phy = devm_phy_optional_get(pcie->dev, "pcie");
+	if (IS_ERR(pcie->phy)) {
+		err = PTR_ERR(pcie->phy);
+		dev_err(pcie->dev, "failed to get PHY: %d\n", err);
+		return err;
+	}
+
+	err = phy_init(pcie->phy);
+	if (err < 0) {
+		dev_err(pcie->dev, "failed to initialize PHY: %d\n", err);
+		return err;
+	}
+
+	pcie->legacy_phy = true;
+
+	return 0;
+}
+
+static struct phy *devm_of_phy_optional_get_index(struct device *dev,
+						  struct device_node *np,
+						  const char *consumer,
+						  unsigned int index)
+{
+	struct phy *phy;
+	char *name;
+
+	name = kasprintf(GFP_KERNEL, "%s-%u", consumer, index);
+	if (!name)
+		return ERR_PTR(-ENOMEM);
+
+	phy = devm_of_phy_get(dev, np, name);
+	kfree(name);
+
+	if (IS_ERR(phy) && PTR_ERR(phy) == -ENODEV)
+		phy = NULL;
+
+	return phy;
+}
+
+static int tegra_pcie_port_get_phys(struct tegra_pcie_port *port)
+{
+	struct device *dev = port->pcie->dev;
+	struct phy *phy;
+	unsigned int i;
+	int err;
+
+	port->phys = devm_kcalloc(dev, sizeof(phy), port->lanes, GFP_KERNEL);
+	if (!port->phys)
+		return -ENOMEM;
+
+	for (i = 0; i < port->lanes; i++) {
+		phy = devm_of_phy_optional_get_index(dev, port->np, "pcie", i);
+		if (IS_ERR(phy)) {
+			dev_err(dev, "failed to get PHY#%u: %ld\n", i,
+				PTR_ERR(phy));
+			return PTR_ERR(phy);
+		}
+
+		err = phy_init(phy);
+		if (err < 0) {
+			dev_err(dev, "failed to initialize PHY#%u: %d\n", i,
+				err);
+			return err;
+		}
+
+		port->phys[i] = phy;
+	}
+
+	return 0;
+}
+
+static int tegra_pcie_phys_get(struct tegra_pcie *pcie)
+{
+	const struct tegra_pcie_soc_data *soc = pcie->soc_data;
+	struct device_node *np = pcie->dev->of_node;
+	struct tegra_pcie_port *port;
+	int err;
+
+	if (!soc->has_gen2 || of_find_property(np, "phys", NULL) != NULL)
+		return tegra_pcie_phys_get_legacy(pcie);
+
+	list_for_each_entry(port, &pcie->ports, list) {
+		err = tegra_pcie_port_get_phys(port);
+		if (err < 0)
+			return err;
+	}
+
+	return 0;
+}
+
 static int tegra_pcie_get_resources(struct tegra_pcie *pcie)
 {
 	struct platform_device *pdev = to_platform_device(pcie->dev);
@@ -1067,16 +1283,9 @@ static int tegra_pcie_get_resources(struct tegra_pcie *pcie)
 		return err;
 	}
 
-	pcie->phy = devm_phy_optional_get(pcie->dev, "pcie");
-	if (IS_ERR(pcie->phy)) {
-		err = PTR_ERR(pcie->phy);
-		dev_err(&pdev->dev, "failed to get PHY: %d\n", err);
-		return err;
-	}
-
-	err = phy_init(pcie->phy);
+	err = tegra_pcie_phys_get(pcie);
 	if (err < 0) {
-		dev_err(&pdev->dev, "failed to initialize PHY: %d\n", err);
+		dev_err(&pdev->dev, "failed to get PHYs: %d\n", err);
 		return err;
 	}
 
@@ -1752,6 +1961,7 @@ static int tegra_pcie_parse_dt(struct tegra_pcie *pcie)
 		rp->index = index;
 		rp->lanes = value;
 		rp->pcie = pcie;
+		rp->np = port;
 
 		rp->base = devm_ioremap_resource(pcie->dev, &rp->regs);
 		if (IS_ERR(rp->base))
diff --git a/drivers/pci/host/pci-thunder-ecam.c b/drivers/pci/host/pci-thunder-ecam.c
index d71935cb2..540d03061 100644
--- a/drivers/pci/host/pci-thunder-ecam.c
+++ b/drivers/pci/host/pci-thunder-ecam.c
@@ -13,18 +13,7 @@
 #include <linux/of.h>
 #include <linux/platform_device.h>
 
-#include "pci-host-common.h"
-
-/* Mapping is standard ECAM */
-static void __iomem *thunder_ecam_map_bus(struct pci_bus *bus,
-					  unsigned int devfn,
-					  int where)
-{
-	struct gen_pci *pci = bus->sysdata;
-	resource_size_t idx = bus->number - pci->cfg.bus_range->start;
-
-	return pci->cfg.win[idx] + ((devfn << 12) | where);
-}
+#include "../ecam.h"
 
 static void set_val(u32 v, int where, int size, u32 *val)
 {
@@ -99,7 +88,7 @@ static int handle_ea_bar(u32 e0, int bar, struct pci_bus *bus,
 static int thunder_ecam_p2_config_read(struct pci_bus *bus, unsigned int devfn,
 				       int where, int size, u32 *val)
 {
-	struct gen_pci *pci = bus->sysdata;
+	struct pci_config_window *cfg = bus->sysdata;
 	int where_a = where & ~3;
 	void __iomem *addr;
 	u32 node_bits;
@@ -129,7 +118,7 @@ static int thunder_ecam_p2_config_read(struct pci_bus *bus, unsigned int devfn,
 	 * the config space access window.  Since we are working with
 	 * the high-order 32 bits, shift everything down by 32 bits.
 	 */
-	node_bits = (pci->cfg.res.start >> 32) & (1 << 12);
+	node_bits = (cfg->res.start >> 32) & (1 << 12);
 
 	v |= node_bits;
 	set_val(v, where, size, val);
@@ -358,36 +347,24 @@ static int thunder_ecam_config_write(struct pci_bus *bus, unsigned int devfn,
 	return pci_generic_config_write(bus, devfn, where, size, val);
 }
 
-static struct gen_pci_cfg_bus_ops thunder_ecam_bus_ops = {
+static struct pci_ecam_ops pci_thunder_ecam_ops = {
 	.bus_shift	= 20,
-	.ops		= {
-		.map_bus        = thunder_ecam_map_bus,
+	.pci_ops	= {
+		.map_bus        = pci_ecam_map_bus,
 		.read           = thunder_ecam_config_read,
 		.write          = thunder_ecam_config_write,
 	}
 };
 
 static const struct of_device_id thunder_ecam_of_match[] = {
-	{ .compatible = "cavium,pci-host-thunder-ecam",
-	  .data = &thunder_ecam_bus_ops },
-
+	{ .compatible = "cavium,pci-host-thunder-ecam" },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, thunder_ecam_of_match);
 
 static int thunder_ecam_probe(struct platform_device *pdev)
 {
-	struct device *dev = &pdev->dev;
-	const struct of_device_id *of_id;
-	struct gen_pci *pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL);
-
-	if (!pci)
-		return -ENOMEM;
-
-	of_id = of_match_node(thunder_ecam_of_match, dev->of_node);
-	pci->cfg.ops = (struct gen_pci_cfg_bus_ops *)of_id->data;
-
-	return pci_host_common_probe(pdev, pci);
+	return pci_host_common_probe(pdev, &pci_thunder_ecam_ops);
 }
 
 static struct platform_driver thunder_ecam_driver = {
diff --git a/drivers/pci/host/pci-thunder-pem.c b/drivers/pci/host/pci-thunder-pem.c
index cabb92a51..9b8ab94f3 100644
--- a/drivers/pci/host/pci-thunder-pem.c
+++ b/drivers/pci/host/pci-thunder-pem.c
@@ -20,34 +20,22 @@
 #include <linux/of_pci.h>
 #include <linux/platform_device.h>
 
-#include "pci-host-common.h"
+#include "../ecam.h"
 
 #define PEM_CFG_WR 0x28
 #define PEM_CFG_RD 0x30
 
 struct thunder_pem_pci {
-	struct gen_pci	gen_pci;
 	u32		ea_entry[3];
 	void __iomem	*pem_reg_base;
 };
 
-static void __iomem *thunder_pem_map_bus(struct pci_bus *bus,
-					 unsigned int devfn, int where)
-{
-	struct gen_pci *pci = bus->sysdata;
-	resource_size_t idx = bus->number - pci->cfg.bus_range->start;
-
-	return pci->cfg.win[idx] + ((devfn << 16) | where);
-}
-
 static int thunder_pem_bridge_read(struct pci_bus *bus, unsigned int devfn,
 				   int where, int size, u32 *val)
 {
 	u64 read_val;
-	struct thunder_pem_pci *pem_pci;
-	struct gen_pci *pci = bus->sysdata;
-
-	pem_pci = container_of(pci, struct thunder_pem_pci, gen_pci);
+	struct pci_config_window *cfg = bus->sysdata;
+	struct thunder_pem_pci *pem_pci = (struct thunder_pem_pci *)cfg->priv;
 
 	if (devfn != 0 || where >= 2048) {
 		*val = ~0;
@@ -132,17 +120,17 @@ static int thunder_pem_bridge_read(struct pci_bus *bus, unsigned int devfn,
 static int thunder_pem_config_read(struct pci_bus *bus, unsigned int devfn,
 				   int where, int size, u32 *val)
 {
-	struct gen_pci *pci = bus->sysdata;
+	struct pci_config_window *cfg = bus->sysdata;
 
-	if (bus->number < pci->cfg.bus_range->start ||
-	    bus->number > pci->cfg.bus_range->end)
+	if (bus->number < cfg->busr.start ||
+	    bus->number > cfg->busr.end)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
 	/*
 	 * The first device on the bus is the PEM PCIe bridge.
 	 * Special case its config access.
 	 */
-	if (bus->number == pci->cfg.bus_range->start)
+	if (bus->number == cfg->busr.start)
 		return thunder_pem_bridge_read(bus, devfn, where, size, val);
 
 	return pci_generic_config_read(bus, devfn, where, size, val);
@@ -153,11 +141,11 @@ static int thunder_pem_config_read(struct pci_bus *bus, unsigned int devfn,
  * reserved bits, this makes the code simpler and is OK as the bits
  * are not affected by writing zeros to them.
  */
-static u32 thunder_pem_bridge_w1c_bits(int where)
+static u32 thunder_pem_bridge_w1c_bits(u64 where_aligned)
 {
 	u32 w1c_bits = 0;
 
-	switch (where & ~3) {
+	switch (where_aligned) {
 	case 0x04: /* Command/Status */
 	case 0x1c: /* Base and I/O Limit/Secondary Status */
 		w1c_bits = 0xff000000;
@@ -184,15 +172,36 @@ static u32 thunder_pem_bridge_w1c_bits(int where)
 	return w1c_bits;
 }
 
+/* Some bits must be written to one so they appear to be read-only. */
+static u32 thunder_pem_bridge_w1_bits(u64 where_aligned)
+{
+	u32 w1_bits;
+
+	switch (where_aligned) {
+	case 0x1c: /* I/O Base / I/O Limit, Secondary Status */
+		/* Force 32-bit I/O addressing. */
+		w1_bits = 0x0101;
+		break;
+	case 0x24: /* Prefetchable Memory Base / Prefetchable Memory Limit */
+		/* Force 64-bit addressing */
+		w1_bits = 0x00010001;
+		break;
+	default:
+		w1_bits = 0;
+		break;
+	}
+	return w1_bits;
+}
+
 static int thunder_pem_bridge_write(struct pci_bus *bus, unsigned int devfn,
 				    int where, int size, u32 val)
 {
-	struct gen_pci *pci = bus->sysdata;
-	struct thunder_pem_pci *pem_pci;
+	struct pci_config_window *cfg = bus->sysdata;
+	struct thunder_pem_pci *pem_pci = (struct thunder_pem_pci *)cfg->priv;
 	u64 write_val, read_val;
+	u64 where_aligned = where & ~3ull;
 	u32 mask = 0;
 
-	pem_pci = container_of(pci, struct thunder_pem_pci, gen_pci);
 
 	if (devfn != 0 || where >= 2048)
 		return PCIBIOS_DEVICE_NOT_FOUND;
@@ -205,8 +214,7 @@ static int thunder_pem_bridge_write(struct pci_bus *bus, unsigned int devfn,
 	 */
 	switch (size) {
 	case 1:
-		read_val = where & ~3ull;
-		writeq(read_val, pem_pci->pem_reg_base + PEM_CFG_RD);
+		writeq(where_aligned, pem_pci->pem_reg_base + PEM_CFG_RD);
 		read_val = readq(pem_pci->pem_reg_base + PEM_CFG_RD);
 		read_val >>= 32;
 		mask = ~(0xff << (8 * (where & 3)));
@@ -215,8 +223,7 @@ static int thunder_pem_bridge_write(struct pci_bus *bus, unsigned int devfn,
 		val |= (u32)read_val;
 		break;
 	case 2:
-		read_val = where & ~3ull;
-		writeq(read_val, pem_pci->pem_reg_base + PEM_CFG_RD);
+		writeq(where_aligned, pem_pci->pem_reg_base + PEM_CFG_RD);
 		read_val = readq(pem_pci->pem_reg_base + PEM_CFG_RD);
 		read_val >>= 32;
 		mask = ~(0xffff << (8 * (where & 3)));
@@ -244,11 +251,17 @@ static int thunder_pem_bridge_write(struct pci_bus *bus, unsigned int devfn,
 	}
 
 	/*
+	 * Some bits must be read-only with value of one.  Since the
+	 * access method allows these to be cleared if a zero is
+	 * written, force them to one before writing.
+	 */
+	val |= thunder_pem_bridge_w1_bits(where_aligned);
+
+	/*
 	 * Low order bits are the config address, the high order 32
 	 * bits are the data to be written.
 	 */
-	write_val = where & ~3ull;
-	write_val |= (((u64)val) << 32);
+	write_val = (((u64)val) << 32) | where_aligned;
 	writeq(write_val, pem_pci->pem_reg_base + PEM_CFG_WR);
 	return PCIBIOS_SUCCESSFUL;
 }
@@ -256,53 +269,38 @@ static int thunder_pem_bridge_write(struct pci_bus *bus, unsigned int devfn,
 static int thunder_pem_config_write(struct pci_bus *bus, unsigned int devfn,
 				    int where, int size, u32 val)
 {
-	struct gen_pci *pci = bus->sysdata;
+	struct pci_config_window *cfg = bus->sysdata;
 
-	if (bus->number < pci->cfg.bus_range->start ||
-	    bus->number > pci->cfg.bus_range->end)
+	if (bus->number < cfg->busr.start ||
+	    bus->number > cfg->busr.end)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 	/*
 	 * The first device on the bus is the PEM PCIe bridge.
 	 * Special case its config access.
 	 */
-	if (bus->number == pci->cfg.bus_range->start)
+	if (bus->number == cfg->busr.start)
 		return thunder_pem_bridge_write(bus, devfn, where, size, val);
 
 
 	return pci_generic_config_write(bus, devfn, where, size, val);
 }
 
-static struct gen_pci_cfg_bus_ops thunder_pem_bus_ops = {
-	.bus_shift	= 24,
-	.ops		= {
-		.map_bus	= thunder_pem_map_bus,
-		.read		= thunder_pem_config_read,
-		.write		= thunder_pem_config_write,
-	}
-};
-
-static const struct of_device_id thunder_pem_of_match[] = {
-	{ .compatible = "cavium,pci-host-thunder-pem",
-	  .data = &thunder_pem_bus_ops },
-
-	{ },
-};
-MODULE_DEVICE_TABLE(of, thunder_pem_of_match);
-
-static int thunder_pem_probe(struct platform_device *pdev)
+static int thunder_pem_init(struct device *dev, struct pci_config_window *cfg)
 {
-	struct device *dev = &pdev->dev;
-	const struct of_device_id *of_id;
 	resource_size_t bar4_start;
 	struct resource *res_pem;
 	struct thunder_pem_pci *pem_pci;
+	struct platform_device *pdev;
+
+	/* Only OF support for now */
+	if (!dev->of_node)
+		return -EINVAL;
 
 	pem_pci = devm_kzalloc(dev, sizeof(*pem_pci), GFP_KERNEL);
 	if (!pem_pci)
 		return -ENOMEM;
 
-	of_id = of_match_node(thunder_pem_of_match, dev->of_node);
-	pem_pci->gen_pci.cfg.ops = (struct gen_pci_cfg_bus_ops *)of_id->data;
+	pdev = to_platform_device(dev);
 
 	/*
 	 * The second register range is the PEM bridge to the PCIe
@@ -330,7 +328,29 @@ static int thunder_pem_probe(struct platform_device *pdev)
 	pem_pci->ea_entry[1] = (u32)(res_pem->end - bar4_start) & ~3u;
 	pem_pci->ea_entry[2] = (u32)(bar4_start >> 32);
 
-	return pci_host_common_probe(pdev, &pem_pci->gen_pci);
+	cfg->priv = pem_pci;
+	return 0;
+}
+
+static struct pci_ecam_ops pci_thunder_pem_ops = {
+	.bus_shift	= 24,
+	.init		= thunder_pem_init,
+	.pci_ops	= {
+		.map_bus	= pci_ecam_map_bus,
+		.read		= thunder_pem_config_read,
+		.write		= thunder_pem_config_write,
+	}
+};
+
+static const struct of_device_id thunder_pem_of_match[] = {
+	{ .compatible = "cavium,pci-host-thunder-pem" },
+	{ },
+};
+MODULE_DEVICE_TABLE(of, thunder_pem_of_match);
+
+static int thunder_pem_probe(struct platform_device *pdev)
+{
+	return pci_host_common_probe(pdev, &pci_thunder_pem_ops);
 }
 
 static struct platform_driver thunder_pem_driver = {
diff --git a/drivers/pci/host/pcie-armada8k.c b/drivers/pci/host/pcie-armada8k.c
new file mode 100644
index 000000000..55723567b
--- /dev/null
+++ b/drivers/pci/host/pcie-armada8k.c
@@ -0,0 +1,262 @@
+/*
+ * PCIe host controller driver for Marvell Armada-8K SoCs
+ *
+ * Armada-8K PCIe Glue Layer Source Code
+ *
+ * Copyright (C) 2016 Marvell Technology Group Ltd.
+ *
+ * This file is licensed under the terms of the GNU General Public
+ * License version 2. This program is licensed "as is" without any
+ * warranty of any kind, whether express or implied.
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/pci.h>
+#include <linux/phy/phy.h>
+#include <linux/platform_device.h>
+#include <linux/resource.h>
+#include <linux/of_pci.h>
+#include <linux/of_irq.h>
+
+#include "pcie-designware.h"
+
+struct armada8k_pcie {
+	void __iomem *base;
+	struct clk *clk;
+	struct pcie_port pp;
+};
+
+#define PCIE_VENDOR_REGS_OFFSET		0x8000
+
+#define PCIE_GLOBAL_CONTROL_REG		0x0
+#define PCIE_APP_LTSSM_EN		BIT(2)
+#define PCIE_DEVICE_TYPE_SHIFT		4
+#define PCIE_DEVICE_TYPE_MASK		0xF
+#define PCIE_DEVICE_TYPE_RC		0x4 /* Root complex */
+
+#define PCIE_GLOBAL_STATUS_REG		0x8
+#define PCIE_GLB_STS_RDLH_LINK_UP	BIT(1)
+#define PCIE_GLB_STS_PHY_LINK_UP	BIT(9)
+
+#define PCIE_GLOBAL_INT_CAUSE1_REG	0x1C
+#define PCIE_GLOBAL_INT_MASK1_REG	0x20
+#define PCIE_INT_A_ASSERT_MASK		BIT(9)
+#define PCIE_INT_B_ASSERT_MASK		BIT(10)
+#define PCIE_INT_C_ASSERT_MASK		BIT(11)
+#define PCIE_INT_D_ASSERT_MASK		BIT(12)
+
+#define PCIE_ARCACHE_TRC_REG		0x50
+#define PCIE_AWCACHE_TRC_REG		0x54
+#define PCIE_ARUSER_REG			0x5C
+#define PCIE_AWUSER_REG			0x60
+/*
+ * AR/AW Cache defauls: Normal memory, Write-Back, Read / Write
+ * allocate
+ */
+#define ARCACHE_DEFAULT_VALUE		0x3511
+#define AWCACHE_DEFAULT_VALUE		0x5311
+
+#define DOMAIN_OUTER_SHAREABLE		0x2
+#define AX_USER_DOMAIN_MASK		0x3
+#define AX_USER_DOMAIN_SHIFT		4
+
+#define to_armada8k_pcie(x)	container_of(x, struct armada8k_pcie, pp)
+
+static int armada8k_pcie_link_up(struct pcie_port *pp)
+{
+	struct armada8k_pcie *pcie = to_armada8k_pcie(pp);
+	u32 reg;
+	u32 mask = PCIE_GLB_STS_RDLH_LINK_UP | PCIE_GLB_STS_PHY_LINK_UP;
+
+	reg = readl(pcie->base + PCIE_GLOBAL_STATUS_REG);
+
+	if ((reg & mask) == mask)
+		return 1;
+
+	dev_dbg(pp->dev, "No link detected (Global-Status: 0x%08x).\n", reg);
+	return 0;
+}
+
+static void armada8k_pcie_establish_link(struct pcie_port *pp)
+{
+	struct armada8k_pcie *pcie = to_armada8k_pcie(pp);
+	void __iomem *base = pcie->base;
+	u32 reg;
+
+	if (!dw_pcie_link_up(pp)) {
+		/* Disable LTSSM state machine to enable configuration */
+		reg = readl(base + PCIE_GLOBAL_CONTROL_REG);
+		reg &= ~(PCIE_APP_LTSSM_EN);
+		writel(reg, base + PCIE_GLOBAL_CONTROL_REG);
+	}
+
+	/* Set the device to root complex mode */
+	reg = readl(base + PCIE_GLOBAL_CONTROL_REG);
+	reg &= ~(PCIE_DEVICE_TYPE_MASK << PCIE_DEVICE_TYPE_SHIFT);
+	reg |= PCIE_DEVICE_TYPE_RC << PCIE_DEVICE_TYPE_SHIFT;
+	writel(reg, base + PCIE_GLOBAL_CONTROL_REG);
+
+	/* Set the PCIe master AxCache attributes */
+	writel(ARCACHE_DEFAULT_VALUE, base + PCIE_ARCACHE_TRC_REG);
+	writel(AWCACHE_DEFAULT_VALUE, base + PCIE_AWCACHE_TRC_REG);
+
+	/* Set the PCIe master AxDomain attributes */
+	reg = readl(base + PCIE_ARUSER_REG);
+	reg &= ~(AX_USER_DOMAIN_MASK << AX_USER_DOMAIN_SHIFT);
+	reg |= DOMAIN_OUTER_SHAREABLE << AX_USER_DOMAIN_SHIFT;
+	writel(reg, base + PCIE_ARUSER_REG);
+
+	reg = readl(base + PCIE_AWUSER_REG);
+	reg &= ~(AX_USER_DOMAIN_MASK << AX_USER_DOMAIN_SHIFT);
+	reg |= DOMAIN_OUTER_SHAREABLE << AX_USER_DOMAIN_SHIFT;
+	writel(reg, base + PCIE_AWUSER_REG);
+
+	/* Enable INT A-D interrupts */
+	reg = readl(base + PCIE_GLOBAL_INT_MASK1_REG);
+	reg |= PCIE_INT_A_ASSERT_MASK | PCIE_INT_B_ASSERT_MASK |
+	       PCIE_INT_C_ASSERT_MASK | PCIE_INT_D_ASSERT_MASK;
+	writel(reg, base + PCIE_GLOBAL_INT_MASK1_REG);
+
+	if (!dw_pcie_link_up(pp)) {
+		/* Configuration done. Start LTSSM */
+		reg = readl(base + PCIE_GLOBAL_CONTROL_REG);
+		reg |= PCIE_APP_LTSSM_EN;
+		writel(reg, base + PCIE_GLOBAL_CONTROL_REG);
+	}
+
+	/* Wait until the link becomes active again */
+	if (dw_pcie_wait_for_link(pp))
+		dev_err(pp->dev, "Link not up after reconfiguration\n");
+}
+
+static void armada8k_pcie_host_init(struct pcie_port *pp)
+{
+	dw_pcie_setup_rc(pp);
+	armada8k_pcie_establish_link(pp);
+}
+
+static irqreturn_t armada8k_pcie_irq_handler(int irq, void *arg)
+{
+	struct pcie_port *pp = arg;
+	struct armada8k_pcie *pcie = to_armada8k_pcie(pp);
+	void __iomem *base = pcie->base;
+	u32 val;
+
+	/*
+	 * Interrupts are directly handled by the device driver of the
+	 * PCI device. However, they are also latched into the PCIe
+	 * controller, so we simply discard them.
+	 */
+	val = readl(base + PCIE_GLOBAL_INT_CAUSE1_REG);
+	writel(val, base + PCIE_GLOBAL_INT_CAUSE1_REG);
+
+	return IRQ_HANDLED;
+}
+
+static struct pcie_host_ops armada8k_pcie_host_ops = {
+	.link_up = armada8k_pcie_link_up,
+	.host_init = armada8k_pcie_host_init,
+};
+
+static int armada8k_add_pcie_port(struct pcie_port *pp,
+				  struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	pp->root_bus_nr = -1;
+	pp->ops = &armada8k_pcie_host_ops;
+
+	pp->irq = platform_get_irq(pdev, 0);
+	if (!pp->irq) {
+		dev_err(dev, "failed to get irq for port\n");
+		return -ENODEV;
+	}
+
+	ret = devm_request_irq(dev, pp->irq, armada8k_pcie_irq_handler,
+			       IRQF_SHARED, "armada8k-pcie", pp);
+	if (ret) {
+		dev_err(dev, "failed to request irq %d\n", pp->irq);
+		return ret;
+	}
+
+	ret = dw_pcie_host_init(pp);
+	if (ret) {
+		dev_err(dev, "failed to initialize host: %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int armada8k_pcie_probe(struct platform_device *pdev)
+{
+	struct armada8k_pcie *pcie;
+	struct pcie_port *pp;
+	struct device *dev = &pdev->dev;
+	struct resource *base;
+	int ret;
+
+	pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL);
+	if (!pcie)
+		return -ENOMEM;
+
+	pcie->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(pcie->clk))
+		return PTR_ERR(pcie->clk);
+
+	clk_prepare_enable(pcie->clk);
+
+	pp = &pcie->pp;
+	pp->dev = dev;
+	platform_set_drvdata(pdev, pcie);
+
+	/* Get the dw-pcie unit configuration/control registers base. */
+	base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "ctrl");
+	pp->dbi_base = devm_ioremap_resource(dev, base);
+	if (IS_ERR(pp->dbi_base)) {
+		dev_err(dev, "couldn't remap regs base %p\n", base);
+		ret = PTR_ERR(pp->dbi_base);
+		goto fail;
+	}
+
+	pcie->base = pp->dbi_base + PCIE_VENDOR_REGS_OFFSET;
+
+	ret = armada8k_add_pcie_port(pp, pdev);
+	if (ret)
+		goto fail;
+
+	return 0;
+
+fail:
+	if (!IS_ERR(pcie->clk))
+		clk_disable_unprepare(pcie->clk);
+
+	return ret;
+}
+
+static const struct of_device_id armada8k_pcie_of_match[] = {
+	{ .compatible = "marvell,armada8k-pcie", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, armada8k_pcie_of_match);
+
+static struct platform_driver armada8k_pcie_driver = {
+	.probe		= armada8k_pcie_probe,
+	.driver = {
+		.name	= "armada8k-pcie",
+		.of_match_table = of_match_ptr(armada8k_pcie_of_match),
+	},
+};
+
+module_platform_driver(armada8k_pcie_driver);
+
+MODULE_DESCRIPTION("Armada 8k PCIe host controller driver");
+MODULE_AUTHOR("Yehuda Yitshak <yehuday@marvell.com>");
+MODULE_AUTHOR("Shadi Ammouri <shadi@marvell.com>");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/host/pcie-designware.c b/drivers/pci/host/pcie-designware.c
index a4cccd356..aafd76654 100644
--- a/drivers/pci/host/pcie-designware.c
+++ b/drivers/pci/host/pcie-designware.c
@@ -434,7 +434,6 @@ int dw_pcie_host_init(struct pcie_port *pp)
 	struct platform_device *pdev = to_platform_device(pp->dev);
 	struct pci_bus *bus, *child;
 	struct resource *cfg_res;
-	u32 val;
 	int i, ret;
 	LIST_HEAD(res);
 	struct resource_entry *win;
@@ -544,25 +543,6 @@ int dw_pcie_host_init(struct pcie_port *pp)
 	if (pp->ops->host_init)
 		pp->ops->host_init(pp);
 
-	/*
-	 * If the platform provides ->rd_other_conf, it means the platform
-	 * uses its own address translation component rather than ATU, so
-	 * we should not program the ATU here.
-	 */
-	if (!pp->ops->rd_other_conf)
-		dw_pcie_prog_outbound_atu(pp, PCIE_ATU_REGION_INDEX1,
-					  PCIE_ATU_TYPE_MEM, pp->mem_base,
-					  pp->mem_bus_addr, pp->mem_size);
-
-	dw_pcie_wr_own_conf(pp, PCI_BASE_ADDRESS_0, 4, 0);
-
-	/* program correct class for RC */
-	dw_pcie_wr_own_conf(pp, PCI_CLASS_DEVICE, 2, PCI_CLASS_BRIDGE_PCI);
-
-	dw_pcie_rd_own_conf(pp, PCIE_LINK_WIDTH_SPEED_CONTROL, 4, &val);
-	val |= PORT_LOGIC_SPEED_CHANGE;
-	dw_pcie_wr_own_conf(pp, PCIE_LINK_WIDTH_SPEED_CONTROL, 4, val);
-
 	pp->root_bus_nr = pp->busn->start;
 	if (IS_ENABLED(CONFIG_PCI_MSI)) {
 		bus = pci_scan_root_bus_msi(pp->dev, pp->root_bus_nr,
@@ -728,8 +708,6 @@ static struct pci_ops dw_pcie_ops = {
 void dw_pcie_setup_rc(struct pcie_port *pp)
 {
 	u32 val;
-	u32 membase;
-	u32 memlimit;
 
 	/* set the number of lanes */
 	dw_pcie_readl_rc(pp, PCIE_PORT_LINK_CONTROL, &val);
@@ -788,18 +766,31 @@ void dw_pcie_setup_rc(struct pcie_port *pp)
 	val |= 0x00010100;
 	dw_pcie_writel_rc(pp, val, PCI_PRIMARY_BUS);
 
-	/* setup memory base, memory limit */
-	membase = ((u32)pp->mem_base & 0xfff00000) >> 16;
-	memlimit = (pp->mem_size + (u32)pp->mem_base) & 0xfff00000;
-	val = memlimit | membase;
-	dw_pcie_writel_rc(pp, val, PCI_MEMORY_BASE);
-
 	/* setup command register */
 	dw_pcie_readl_rc(pp, PCI_COMMAND, &val);
 	val &= 0xffff0000;
 	val |= PCI_COMMAND_IO | PCI_COMMAND_MEMORY |
 		PCI_COMMAND_MASTER | PCI_COMMAND_SERR;
 	dw_pcie_writel_rc(pp, val, PCI_COMMAND);
+
+	/*
+	 * If the platform provides ->rd_other_conf, it means the platform
+	 * uses its own address translation component rather than ATU, so
+	 * we should not program the ATU here.
+	 */
+	if (!pp->ops->rd_other_conf)
+		dw_pcie_prog_outbound_atu(pp, PCIE_ATU_REGION_INDEX1,
+					  PCIE_ATU_TYPE_MEM, pp->mem_base,
+					  pp->mem_bus_addr, pp->mem_size);
+
+	dw_pcie_wr_own_conf(pp, PCI_BASE_ADDRESS_0, 4, 0);
+
+	/* program correct class for RC */
+	dw_pcie_wr_own_conf(pp, PCI_CLASS_DEVICE, 2, PCI_CLASS_BRIDGE_PCI);
+
+	dw_pcie_rd_own_conf(pp, PCIE_LINK_WIDTH_SPEED_CONTROL, 4, &val);
+	val |= PORT_LOGIC_SPEED_CHANGE;
+	dw_pcie_wr_own_conf(pp, PCIE_LINK_WIDTH_SPEED_CONTROL, 4, val);
 }
 
 MODULE_AUTHOR("Jingoo Han <jg1.han@samsung.com>");
diff --git a/drivers/pci/host/pcie-xilinx-nwl.c b/drivers/pci/host/pcie-xilinx-nwl.c
index 5139e6443..3479d30e2 100644
--- a/drivers/pci/host/pcie-xilinx-nwl.c
+++ b/drivers/pci/host/pcie-xilinx-nwl.c
@@ -819,7 +819,7 @@ static int nwl_pcie_probe(struct platform_device *pdev)
 
 	err = nwl_pcie_bridge_init(pcie);
 	if (err) {
-		dev_err(pcie->dev, "HW Initalization failed\n");
+		dev_err(pcie->dev, "HW Initialization failed\n");
 		return err;
 	}