Update Linux to v5.4.2

Change-Id: Idf6911045d9d382da2cfe01b1edff026404ac8fd
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index 028b287..70e0782 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -9,12 +9,14 @@
 	depends on MVEBU_MBUS
 	depends on ARM
 	depends on OF
+	select PCI_BRIDGE_EMUL
 
 config PCI_AARDVARK
 	bool "Aardvark PCIe controller"
 	depends on (ARCH_MVEBU && ARM64) || COMPILE_TEST
 	depends on OF
 	depends on PCI_MSI_IRQ_DOMAIN
+	select PCI_BRIDGE_EMUL
 	help
 	 Add support for Aardvark 64bit PCIe Host Controller. This
 	 controller is part of the South Bridge of the Marvel Armada
@@ -172,14 +174,14 @@
 	  PCIe controller
 
 config PCIE_ALTERA
-	bool "Altera PCIe controller"
-	depends on ARM || NIOS2 || COMPILE_TEST
+	tristate "Altera PCIe controller"
+	depends on ARM || NIOS2 || ARM64 || COMPILE_TEST
 	help
 	  Say Y here if you want to enable PCIe controller support on Altera
 	  FPGA.
 
 config PCIE_ALTERA_MSI
-	bool "Altera PCIe MSI feature"
+	tristate "Altera PCIe MSI feature"
 	depends on PCIE_ALTERA
 	depends on PCI_MSI_IRQ_DOMAIN
 	help
@@ -231,7 +233,7 @@
 	  available to support GEN2 with 4 slots.
 
 config PCIE_MEDIATEK
-	bool "MediaTek PCIe controller"
+	tristate "MediaTek PCIe controller"
 	depends on ARCH_MEDIATEK || COMPILE_TEST
 	depends on OF
 	depends on PCI_MSI_IRQ_DOMAIN
@@ -265,6 +267,7 @@
 
 config VMD
 	depends on PCI_MSI && X86_64 && SRCU
+	select X86_DEV_DMA_OPS
 	tristate "Intel Volume Management Device Driver"
 	---help---
 	  Adds support for the Intel Volume Management Device (VMD). VMD is a
@@ -278,5 +281,12 @@
 	  To compile this driver as a module, choose M here: the
 	  module will be called vmd.
 
+config PCI_HYPERV_INTERFACE
+	tristate "Hyper-V PCI Interface"
+	depends on X86 && HYPERV && PCI_MSI && PCI_MSI_IRQ_DOMAIN && X86_64
+	help
+	  The Hyper-V PCI Interface is a helper driver allows other drivers to
+	  have a common interface with the Hyper-V PCI frontend driver.
+
 source "drivers/pci/controller/dwc/Kconfig"
 endmenu
diff --git a/drivers/pci/controller/Makefile b/drivers/pci/controller/Makefile
index d56a507..a2a22c9 100644
--- a/drivers/pci/controller/Makefile
+++ b/drivers/pci/controller/Makefile
@@ -4,6 +4,7 @@
 obj-$(CONFIG_PCIE_CADENCE_EP) += pcie-cadence-ep.o
 obj-$(CONFIG_PCI_FTPCI100) += pci-ftpci100.o
 obj-$(CONFIG_PCI_HYPERV) += pci-hyperv.o
+obj-$(CONFIG_PCI_HYPERV_INTERFACE) += pci-hyperv-intf.o
 obj-$(CONFIG_PCI_MVEBU) += pci-mvebu.o
 obj-$(CONFIG_PCI_AARDVARK) += pci-aardvark.o
 obj-$(CONFIG_PCI_TEGRA) += pci-tegra.o
diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig
index 91b0194..0ba988b 100644
--- a/drivers/pci/controller/dwc/Kconfig
+++ b/drivers/pci/controller/dwc/Kconfig
@@ -89,8 +89,8 @@
 	select PCIE_DW_HOST
 
 config PCI_IMX6
-	bool "Freescale i.MX6 PCIe controller"
-	depends on SOC_IMX6Q || (ARM && COMPILE_TEST)
+	bool "Freescale i.MX6/7/8 PCIe controller"
+	depends on ARCH_MXC || COMPILE_TEST
 	depends on PCI_MSI_IRQ_DOMAIN
 	select PCIE_DW_HOST
 
@@ -103,24 +103,57 @@
 	  Say Y here if you want PCIe support on SPEAr13XX SoCs.
 
 config PCI_KEYSTONE
-	bool "TI Keystone PCIe controller"
-	depends on ARCH_KEYSTONE || (ARM && COMPILE_TEST)
+	bool
+
+config PCI_KEYSTONE_HOST
+	bool "PCI Keystone Host Mode"
+	depends on ARCH_KEYSTONE || ARCH_K3 || ((ARM || ARM64) && COMPILE_TEST)
 	depends on PCI_MSI_IRQ_DOMAIN
 	select PCIE_DW_HOST
+	select PCI_KEYSTONE
+	default y
 	help
-	  Say Y here if you want to enable PCI controller support on Keystone
-	  SoCs. The PCI controller on Keystone is based on DesignWare hardware
-	  and therefore the driver re-uses the DesignWare core functions to
-	  implement the driver.
+	  Enables support for the PCIe controller in the Keystone SoC to
+	  work in host mode. The PCI controller on Keystone is based on
+	  DesignWare hardware and therefore the driver re-uses the
+	  DesignWare core functions to implement the driver.
+
+config PCI_KEYSTONE_EP
+	bool "PCI Keystone Endpoint Mode"
+	depends on ARCH_KEYSTONE || ARCH_K3 || ((ARM || ARM64) && COMPILE_TEST)
+	depends on PCI_ENDPOINT
+	select PCIE_DW_EP
+	select PCI_KEYSTONE
+	help
+	  Enables support for the PCIe controller in the Keystone SoC to
+	  work in endpoint mode. The PCI controller on Keystone is based
+	  on DesignWare hardware and therefore the driver re-uses the
+	  DesignWare core functions to implement the driver.
 
 config PCI_LAYERSCAPE
-	bool "Freescale Layerscape PCIe controller"
+	bool "Freescale Layerscape PCIe controller - Host mode"
 	depends on OF && (ARM || ARCH_LAYERSCAPE || COMPILE_TEST)
 	depends on PCI_MSI_IRQ_DOMAIN
 	select MFD_SYSCON
 	select PCIE_DW_HOST
 	help
-	  Say Y here if you want PCIe controller support on Layerscape SoCs.
+	  Say Y here if you want to enable PCIe controller support on Layerscape
+	  SoCs to work in Host mode.
+	  This controller can work either as EP or RC. The RCW[HOST_AGT_PEX]
+	  determines which PCIe controller works in EP mode and which PCIe
+	  controller works in RC mode.
+
+config PCI_LAYERSCAPE_EP
+	bool "Freescale Layerscape PCIe controller - Endpoint mode"
+	depends on OF && (ARM || ARCH_LAYERSCAPE || COMPILE_TEST)
+	depends on PCI_ENDPOINT
+	select PCIE_DW_EP
+	help
+	  Say Y here if you want to enable PCIe controller support on Layerscape
+	  SoCs to work in Endpoint mode.
+	  This controller can work either as EP or RC. The RCW[HOST_AGT_PEX]
+	  determines which PCIe controller works in EP mode and which PCIe
+	  controller works in RC mode.
 
 config PCI_HISI
 	depends on OF && (ARM64 || COMPILE_TEST)
@@ -193,4 +226,46 @@
 	help
           Say Y here if you want PCIe controller support on HiSilicon STB SoCs
 
+config PCI_MESON
+	bool "MESON PCIe controller"
+	depends on PCI_MSI_IRQ_DOMAIN
+	select PCIE_DW_HOST
+	help
+	  Say Y here if you want to enable PCI controller support on Amlogic
+	  SoCs. The PCI controller on Amlogic is based on DesignWare hardware
+	  and therefore the driver re-uses the DesignWare core functions to
+	  implement the driver.
+
+config PCIE_TEGRA194
+	tristate "NVIDIA Tegra194 (and later) PCIe controller"
+	depends on ARCH_TEGRA_194_SOC || COMPILE_TEST
+	depends on PCI_MSI_IRQ_DOMAIN
+	select PCIE_DW_HOST
+	select PHY_TEGRA194_P2U
+	help
+	  Say Y here if you want support for DesignWare core based PCIe host
+	  controller found in NVIDIA Tegra194 SoC.
+
+config PCIE_UNIPHIER
+	bool "Socionext UniPhier PCIe controllers"
+	depends on ARCH_UNIPHIER || COMPILE_TEST
+	depends on OF && HAS_IOMEM
+	depends on PCI_MSI_IRQ_DOMAIN
+	select PCIE_DW_HOST
+	help
+	  Say Y here if you want PCIe controller support on UniPhier SoCs.
+	  This driver supports LD20 and PXs3 SoCs.
+
+config PCIE_AL
+	bool "Amazon Annapurna Labs PCIe controller"
+	depends on OF && (ARM64 || COMPILE_TEST)
+	depends on PCI_MSI_IRQ_DOMAIN
+	select PCIE_DW_HOST
+	help
+	  Say Y here to enable support of the Amazon's Annapurna Labs PCIe
+	  controller IP on Amazon SoCs. The PCIe controller uses the DesignWare
+	  core plus Annapurna Labs proprietary hardware wrappers. This is
+	  required only for DT-based platforms. ACPI platforms with the
+	  Annapurna Labs PCIe controller don't need to enable this.
+
 endmenu
diff --git a/drivers/pci/controller/dwc/Makefile b/drivers/pci/controller/dwc/Makefile
index 5d2ce72..69faff3 100644
--- a/drivers/pci/controller/dwc/Makefile
+++ b/drivers/pci/controller/dwc/Makefile
@@ -7,13 +7,17 @@
 obj-$(CONFIG_PCI_EXYNOS) += pci-exynos.o
 obj-$(CONFIG_PCI_IMX6) += pci-imx6.o
 obj-$(CONFIG_PCIE_SPEAR13XX) += pcie-spear13xx.o
-obj-$(CONFIG_PCI_KEYSTONE) += pci-keystone-dw.o pci-keystone.o
+obj-$(CONFIG_PCI_KEYSTONE) += pci-keystone.o
 obj-$(CONFIG_PCI_LAYERSCAPE) += pci-layerscape.o
+obj-$(CONFIG_PCI_LAYERSCAPE_EP) += pci-layerscape-ep.o
 obj-$(CONFIG_PCIE_QCOM) += pcie-qcom.o
 obj-$(CONFIG_PCIE_ARMADA_8K) += pcie-armada8k.o
 obj-$(CONFIG_PCIE_ARTPEC6) += pcie-artpec6.o
 obj-$(CONFIG_PCIE_KIRIN) += pcie-kirin.o
 obj-$(CONFIG_PCIE_HISI_STB) += pcie-histb.o
+obj-$(CONFIG_PCI_MESON) += pci-meson.o
+obj-$(CONFIG_PCIE_TEGRA194) += pcie-tegra194.o
+obj-$(CONFIG_PCIE_UNIPHIER) += pcie-uniphier.o
 
 # The following drivers are for devices that use the generic ACPI
 # pci_root.c driver but don't support standard ECAM config access.
@@ -26,5 +30,6 @@
 # depending on whether ACPI, the DT driver, or both are enabled.
 
 ifdef CONFIG_PCI
+obj-$(CONFIG_ARM64) += pcie-al.o
 obj-$(CONFIG_ARM64) += pcie-hisi.o
 endif
diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c
index a32d6dd..4234ddb 100644
--- a/drivers/pci/controller/dwc/pci-dra7xx.c
+++ b/drivers/pci/controller/dwc/pci-dra7xx.c
@@ -26,6 +26,7 @@
 #include <linux/types.h>
 #include <linux/mfd/syscon.h>
 #include <linux/regmap.h>
+#include <linux/gpio/consumer.h>
 
 #include "../../pci.h"
 #include "pcie-designware.h"
@@ -81,6 +82,10 @@
 #define MSI_REQ_GRANT					BIT(0)
 #define MSI_VECTOR_SHIFT				7
 
+#define PCIE_1LANE_2LANE_SELECTION			BIT(13)
+#define PCIE_B1C0_MODE_SEL				BIT(2)
+#define PCIE_B0_B1_TSYNCEN				BIT(0)
+
 struct dra7xx_pcie {
 	struct dw_pcie		*pci;
 	void __iomem		*base;		/* DT ti_conf */
@@ -93,6 +98,7 @@
 
 struct dra7xx_pcie_of_data {
 	enum dw_pcie_device_mode mode;
+	u32 b1co_mode_sel_mask;
 };
 
 #define to_dra7xx_pcie(x)	dev_get_drvdata((x)->dev)
@@ -242,6 +248,7 @@
 
 	dra7xx->irq_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX,
 						   &intx_domain_ops, pp);
+	of_node_put(pcie_intc_node);
 	if (!dra7xx->irq_domain) {
 		dev_err(dev, "Failed to get a INTx IRQ domain\n");
 		return -ENODEV;
@@ -389,9 +396,22 @@
 	return 0;
 }
 
-static struct dw_pcie_ep_ops pcie_ep_ops = {
+static const struct pci_epc_features dra7xx_pcie_epc_features = {
+	.linkup_notifier = true,
+	.msi_capable = true,
+	.msix_capable = false,
+};
+
+static const struct pci_epc_features*
+dra7xx_pcie_get_features(struct dw_pcie_ep *ep)
+{
+	return &dra7xx_pcie_epc_features;
+}
+
+static const struct dw_pcie_ep_ops pcie_ep_ops = {
 	.ep_init = dra7xx_pcie_ep_init,
 	.raise_irq = dra7xx_pcie_raise_irq,
+	.get_features = dra7xx_pcie_get_features,
 };
 
 static int __init dra7xx_add_pcie_ep(struct dra7xx_pcie *dra7xx,
@@ -499,6 +519,10 @@
 	int i;
 
 	for (i = 0; i < phy_count; i++) {
+		ret = phy_set_mode(dra7xx->phy[i], PHY_MODE_PCIE);
+		if (ret < 0)
+			goto err_phy;
+
 		ret = phy_init(dra7xx->phy[i]);
 		if (ret < 0)
 			goto err_phy;
@@ -529,6 +553,26 @@
 	.mode = DW_PCIE_EP_TYPE,
 };
 
+static const struct dra7xx_pcie_of_data dra746_pcie_rc_of_data = {
+	.b1co_mode_sel_mask = BIT(2),
+	.mode = DW_PCIE_RC_TYPE,
+};
+
+static const struct dra7xx_pcie_of_data dra726_pcie_rc_of_data = {
+	.b1co_mode_sel_mask = GENMASK(3, 2),
+	.mode = DW_PCIE_RC_TYPE,
+};
+
+static const struct dra7xx_pcie_of_data dra746_pcie_ep_of_data = {
+	.b1co_mode_sel_mask = BIT(2),
+	.mode = DW_PCIE_EP_TYPE,
+};
+
+static const struct dra7xx_pcie_of_data dra726_pcie_ep_of_data = {
+	.b1co_mode_sel_mask = GENMASK(3, 2),
+	.mode = DW_PCIE_EP_TYPE,
+};
+
 static const struct of_device_id of_dra7xx_pcie_match[] = {
 	{
 		.compatible = "ti,dra7-pcie",
@@ -538,6 +582,22 @@
 		.compatible = "ti,dra7-pcie-ep",
 		.data = &dra7xx_pcie_ep_of_data,
 	},
+	{
+		.compatible = "ti,dra746-pcie-rc",
+		.data = &dra746_pcie_rc_of_data,
+	},
+	{
+		.compatible = "ti,dra726-pcie-rc",
+		.data = &dra726_pcie_rc_of_data,
+	},
+	{
+		.compatible = "ti,dra746-pcie-ep",
+		.data = &dra746_pcie_ep_of_data,
+	},
+	{
+		.compatible = "ti,dra726-pcie-ep",
+		.data = &dra726_pcie_ep_of_data,
+	},
 	{},
 };
 
@@ -583,6 +643,34 @@
 	return ret;
 }
 
+static int dra7xx_pcie_configure_two_lane(struct device *dev,
+					  u32 b1co_mode_sel_mask)
+{
+	struct device_node *np = dev->of_node;
+	struct regmap *pcie_syscon;
+	unsigned int pcie_reg;
+	u32 mask;
+	u32 val;
+
+	pcie_syscon = syscon_regmap_lookup_by_phandle(np, "ti,syscon-lane-sel");
+	if (IS_ERR(pcie_syscon)) {
+		dev_err(dev, "unable to get ti,syscon-lane-sel\n");
+		return -EINVAL;
+	}
+
+	if (of_property_read_u32_index(np, "ti,syscon-lane-sel", 1,
+				       &pcie_reg)) {
+		dev_err(dev, "couldn't get lane selection reg offset\n");
+		return -EINVAL;
+	}
+
+	mask = b1co_mode_sel_mask | PCIE_B0_B1_TSYNCEN;
+	val = PCIE_B1C0_MODE_SEL | PCIE_B0_B1_TSYNCEN;
+	regmap_update_bits(pcie_syscon, pcie_reg, mask, val);
+
+	return 0;
+}
+
 static int __init dra7xx_pcie_probe(struct platform_device *pdev)
 {
 	u32 reg;
@@ -603,6 +691,7 @@
 	const struct of_device_id *match;
 	const struct dra7xx_pcie_of_data *data;
 	enum dw_pcie_device_mode mode;
+	u32 b1co_mode_sel_mask;
 
 	match = of_match_device(of_match_ptr(of_dra7xx_pcie_match), dev);
 	if (!match)
@@ -610,6 +699,7 @@
 
 	data = (struct dra7xx_pcie_of_data *)match->data;
 	mode = (enum dw_pcie_device_mode)data->mode;
+	b1co_mode_sel_mask = data->b1co_mode_sel_mask;
 
 	dra7xx = devm_kzalloc(dev, sizeof(*dra7xx), GFP_KERNEL);
 	if (!dra7xx)
@@ -665,6 +755,12 @@
 	dra7xx->pci = pci;
 	dra7xx->phy_count = phy_count;
 
+	if (phy_count == 2) {
+		ret = dra7xx_pcie_configure_two_lane(dev, b1co_mode_sel_mask);
+		if (ret < 0)
+			dra7xx->phy_count = 1; /* Fallback to x1 lane mode */
+	}
+
 	ret = dra7xx_pcie_enable_phy(dra7xx);
 	if (ret) {
 		dev_err(dev, "failed to enable phy\n");
diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c
index cee5f2f..14a6ba4 100644
--- a/drivers/pci/controller/dwc/pci-exynos.c
+++ b/drivers/pci/controller/dwc/pci-exynos.c
@@ -465,7 +465,7 @@
 
 	ep->phy = devm_of_phy_get(dev, np, NULL);
 	if (IS_ERR(ep->phy)) {
-		if (PTR_ERR(ep->phy) == -EPROBE_DEFER)
+		if (PTR_ERR(ep->phy) != -ENODEV)
 			return PTR_ERR(ep->phy);
 
 		ep->phy = NULL;
diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index 975050a..acfbd34 100644
--- a/drivers/pci/controller/dwc/pci-imx6.c
+++ b/drivers/pci/controller/dwc/pci-imx6.c
@@ -8,6 +8,7 @@
  * Author: Sean Cross <xobs@kosagi.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/gpio.h>
@@ -18,6 +19,7 @@
 #include <linux/module.h>
 #include <linux/of_gpio.h>
 #include <linux/of_device.h>
+#include <linux/of_address.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
@@ -27,9 +29,17 @@
 #include <linux/types.h>
 #include <linux/interrupt.h>
 #include <linux/reset.h>
+#include <linux/pm_domain.h>
+#include <linux/pm_runtime.h>
 
 #include "pcie-designware.h"
 
+#define IMX8MQ_GPR_PCIE_REF_USE_PAD		BIT(9)
+#define IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN	BIT(10)
+#define IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE	BIT(11)
+#define IMX8MQ_GPR12_PCIE2_CTRL_DEVICE_TYPE	GENMASK(11, 8)
+#define IMX8MQ_PCIE2_BASE_ADDR			0x33c00000
+
 #define to_imx6_pcie(x)	dev_get_drvdata((x)->dev)
 
 enum imx6_pcie_variants {
@@ -37,6 +47,17 @@
 	IMX6SX,
 	IMX6QP,
 	IMX7D,
+	IMX8MQ,
+};
+
+#define IMX6_PCIE_FLAG_IMX6_PHY			BIT(0)
+#define IMX6_PCIE_FLAG_IMX6_SPEED_CHANGE	BIT(1)
+#define IMX6_PCIE_FLAG_SUPPORTS_SUSPEND		BIT(2)
+
+struct imx6_pcie_drvdata {
+	enum imx6_pcie_variants variant;
+	u32 flags;
+	int dbi_length;
 };
 
 struct imx6_pcie {
@@ -47,10 +68,12 @@
 	struct clk		*pcie_phy;
 	struct clk		*pcie_inbound_axi;
 	struct clk		*pcie;
+	struct clk		*pcie_aux;
 	struct regmap		*iomuxc_gpr;
+	u32			controller_id;
 	struct reset_control	*pciephy_reset;
 	struct reset_control	*apps_reset;
-	enum imx6_pcie_variants variant;
+	struct reset_control	*turnoff_reset;
 	u32			tx_deemph_gen1;
 	u32			tx_deemph_gen2_3p5db;
 	u32			tx_deemph_gen2_6db;
@@ -58,14 +81,21 @@
 	u32			tx_swing_low;
 	int			link_gen;
 	struct regulator	*vpcie;
+	void __iomem		*phy_base;
+
+	/* power domain for pcie */
+	struct device		*pd_pcie;
+	/* power domain for pcie phy */
+	struct device		*pd_pcie_phy;
+	const struct imx6_pcie_drvdata *drvdata;
 };
 
 /* Parameters for the waiting for PCIe PHY PLL to lock on i.MX7 */
-#define PHY_PLL_LOCK_WAIT_MAX_RETRIES	2000
-#define PHY_PLL_LOCK_WAIT_USLEEP_MIN	50
 #define PHY_PLL_LOCK_WAIT_USLEEP_MAX	200
+#define PHY_PLL_LOCK_WAIT_TIMEOUT	(2000 * PHY_PLL_LOCK_WAIT_USLEEP_MAX)
 
 /* PCIe Root Complex registers (memory-mapped) */
+#define PCIE_RC_IMX6_MSI_CAP			0x50
 #define PCIE_RC_LCR				0x7c
 #define PCIE_RC_LCR_MAX_LINK_SPEEDS_GEN1	0x1
 #define PCIE_RC_LCR_MAX_LINK_SPEEDS_GEN2	0x2
@@ -75,43 +105,64 @@
 
 /* PCIe Port Logic registers (memory-mapped) */
 #define PL_OFFSET 0x700
-#define PCIE_PL_PFLR (PL_OFFSET + 0x08)
-#define PCIE_PL_PFLR_LINK_STATE_MASK		(0x3f << 16)
-#define PCIE_PL_PFLR_FORCE_LINK			(1 << 15)
-#define PCIE_PHY_DEBUG_R0 (PL_OFFSET + 0x28)
-#define PCIE_PHY_DEBUG_R1 (PL_OFFSET + 0x2c)
 
 #define PCIE_PHY_CTRL (PL_OFFSET + 0x114)
-#define PCIE_PHY_CTRL_DATA_LOC 0
-#define PCIE_PHY_CTRL_CAP_ADR_LOC 16
-#define PCIE_PHY_CTRL_CAP_DAT_LOC 17
-#define PCIE_PHY_CTRL_WR_LOC 18
-#define PCIE_PHY_CTRL_RD_LOC 19
+#define PCIE_PHY_CTRL_DATA(x)		FIELD_PREP(GENMASK(15, 0), (x))
+#define PCIE_PHY_CTRL_CAP_ADR		BIT(16)
+#define PCIE_PHY_CTRL_CAP_DAT		BIT(17)
+#define PCIE_PHY_CTRL_WR		BIT(18)
+#define PCIE_PHY_CTRL_RD		BIT(19)
 
 #define PCIE_PHY_STAT (PL_OFFSET + 0x110)
-#define PCIE_PHY_STAT_ACK_LOC 16
+#define PCIE_PHY_STAT_ACK		BIT(16)
 
 #define PCIE_LINK_WIDTH_SPEED_CONTROL	0x80C
-#define PORT_LOGIC_SPEED_CHANGE		(0x1 << 17)
 
 /* PHY registers (not memory-mapped) */
+#define PCIE_PHY_ATEOVRD			0x10
+#define  PCIE_PHY_ATEOVRD_EN			BIT(2)
+#define  PCIE_PHY_ATEOVRD_REF_CLKDIV_SHIFT	0
+#define  PCIE_PHY_ATEOVRD_REF_CLKDIV_MASK	0x1
+
+#define PCIE_PHY_MPLL_OVRD_IN_LO		0x11
+#define  PCIE_PHY_MPLL_MULTIPLIER_SHIFT		2
+#define  PCIE_PHY_MPLL_MULTIPLIER_MASK		0x7f
+#define  PCIE_PHY_MPLL_MULTIPLIER_OVRD		BIT(9)
+
 #define PCIE_PHY_RX_ASIC_OUT 0x100D
 #define PCIE_PHY_RX_ASIC_OUT_VALID	(1 << 0)
 
-#define PHY_RX_OVRD_IN_LO 0x1005
-#define PHY_RX_OVRD_IN_LO_RX_DATA_EN (1 << 5)
-#define PHY_RX_OVRD_IN_LO_RX_PLL_EN (1 << 3)
+/* iMX7 PCIe PHY registers */
+#define PCIE_PHY_CMN_REG4		0x14
+/* These are probably the bits that *aren't* DCC_FB_EN */
+#define PCIE_PHY_CMN_REG4_DCC_FB_EN	0x29
 
-static int pcie_phy_poll_ack(struct imx6_pcie *imx6_pcie, int exp_val)
+#define PCIE_PHY_CMN_REG15	        0x54
+#define PCIE_PHY_CMN_REG15_DLY_4	BIT(2)
+#define PCIE_PHY_CMN_REG15_PLL_PD	BIT(5)
+#define PCIE_PHY_CMN_REG15_OVRD_PLL_PD	BIT(7)
+
+#define PCIE_PHY_CMN_REG24		0x90
+#define PCIE_PHY_CMN_REG24_RX_EQ	BIT(6)
+#define PCIE_PHY_CMN_REG24_RX_EQ_SEL	BIT(3)
+
+#define PCIE_PHY_CMN_REG26		0x98
+#define PCIE_PHY_CMN_REG26_ATT_MODE	0xBC
+
+#define PHY_RX_OVRD_IN_LO 0x1005
+#define PHY_RX_OVRD_IN_LO_RX_DATA_EN		BIT(5)
+#define PHY_RX_OVRD_IN_LO_RX_PLL_EN		BIT(3)
+
+static int pcie_phy_poll_ack(struct imx6_pcie *imx6_pcie, bool exp_val)
 {
 	struct dw_pcie *pci = imx6_pcie->pci;
-	u32 val;
+	bool val;
 	u32 max_iterations = 10;
 	u32 wait_counter = 0;
 
 	do {
-		val = dw_pcie_readl_dbi(pci, PCIE_PHY_STAT);
-		val = (val >> PCIE_PHY_STAT_ACK_LOC) & 0x1;
+		val = dw_pcie_readl_dbi(pci, PCIE_PHY_STAT) &
+			PCIE_PHY_STAT_ACK;
 		wait_counter++;
 
 		if (val == exp_val)
@@ -129,27 +180,27 @@
 	u32 val;
 	int ret;
 
-	val = addr << PCIE_PHY_CTRL_DATA_LOC;
+	val = PCIE_PHY_CTRL_DATA(addr);
 	dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, val);
 
-	val |= (0x1 << PCIE_PHY_CTRL_CAP_ADR_LOC);
+	val |= PCIE_PHY_CTRL_CAP_ADR;
 	dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, val);
 
-	ret = pcie_phy_poll_ack(imx6_pcie, 1);
+	ret = pcie_phy_poll_ack(imx6_pcie, true);
 	if (ret)
 		return ret;
 
-	val = addr << PCIE_PHY_CTRL_DATA_LOC;
+	val = PCIE_PHY_CTRL_DATA(addr);
 	dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, val);
 
-	return pcie_phy_poll_ack(imx6_pcie, 0);
+	return pcie_phy_poll_ack(imx6_pcie, false);
 }
 
 /* Read from the 16-bit PCIe PHY control registers (not memory-mapped) */
-static int pcie_phy_read(struct imx6_pcie *imx6_pcie, int addr, int *data)
+static int pcie_phy_read(struct imx6_pcie *imx6_pcie, int addr, u16 *data)
 {
 	struct dw_pcie *pci = imx6_pcie->pci;
-	u32 val, phy_ctl;
+	u32 phy_ctl;
 	int ret;
 
 	ret = pcie_phy_wait_ack(imx6_pcie, addr);
@@ -157,23 +208,22 @@
 		return ret;
 
 	/* assert Read signal */
-	phy_ctl = 0x1 << PCIE_PHY_CTRL_RD_LOC;
+	phy_ctl = PCIE_PHY_CTRL_RD;
 	dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, phy_ctl);
 
-	ret = pcie_phy_poll_ack(imx6_pcie, 1);
+	ret = pcie_phy_poll_ack(imx6_pcie, true);
 	if (ret)
 		return ret;
 
-	val = dw_pcie_readl_dbi(pci, PCIE_PHY_STAT);
-	*data = val & 0xffff;
+	*data = dw_pcie_readl_dbi(pci, PCIE_PHY_STAT);
 
 	/* deassert Read signal */
 	dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, 0x00);
 
-	return pcie_phy_poll_ack(imx6_pcie, 0);
+	return pcie_phy_poll_ack(imx6_pcie, false);
 }
 
-static int pcie_phy_write(struct imx6_pcie *imx6_pcie, int addr, int data)
+static int pcie_phy_write(struct imx6_pcie *imx6_pcie, int addr, u16 data)
 {
 	struct dw_pcie *pci = imx6_pcie->pci;
 	u32 var;
@@ -185,41 +235,41 @@
 	if (ret)
 		return ret;
 
-	var = data << PCIE_PHY_CTRL_DATA_LOC;
+	var = PCIE_PHY_CTRL_DATA(data);
 	dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, var);
 
 	/* capture data */
-	var |= (0x1 << PCIE_PHY_CTRL_CAP_DAT_LOC);
+	var |= PCIE_PHY_CTRL_CAP_DAT;
 	dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, var);
 
-	ret = pcie_phy_poll_ack(imx6_pcie, 1);
+	ret = pcie_phy_poll_ack(imx6_pcie, true);
 	if (ret)
 		return ret;
 
 	/* deassert cap data */
-	var = data << PCIE_PHY_CTRL_DATA_LOC;
+	var = PCIE_PHY_CTRL_DATA(data);
 	dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, var);
 
 	/* wait for ack de-assertion */
-	ret = pcie_phy_poll_ack(imx6_pcie, 0);
+	ret = pcie_phy_poll_ack(imx6_pcie, false);
 	if (ret)
 		return ret;
 
 	/* assert wr signal */
-	var = 0x1 << PCIE_PHY_CTRL_WR_LOC;
+	var = PCIE_PHY_CTRL_WR;
 	dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, var);
 
 	/* wait for ack */
-	ret = pcie_phy_poll_ack(imx6_pcie, 1);
+	ret = pcie_phy_poll_ack(imx6_pcie, true);
 	if (ret)
 		return ret;
 
 	/* deassert wr signal */
-	var = data << PCIE_PHY_CTRL_DATA_LOC;
+	var = PCIE_PHY_CTRL_DATA(data);
 	dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, var);
 
 	/* wait for ack de-assertion */
-	ret = pcie_phy_poll_ack(imx6_pcie, 0);
+	ret = pcie_phy_poll_ack(imx6_pcie, false);
 	if (ret)
 		return ret;
 
@@ -230,7 +280,10 @@
 
 static void imx6_pcie_reset_phy(struct imx6_pcie *imx6_pcie)
 {
-	u32 tmp;
+	u16 tmp;
+
+	if (!(imx6_pcie->drvdata->flags & IMX6_PCIE_FLAG_IMX6_PHY))
+		return;
 
 	pcie_phy_read(imx6_pcie, PHY_RX_OVRD_IN_LO, &tmp);
 	tmp |= (PHY_RX_OVRD_IN_LO_RX_DATA_EN |
@@ -245,6 +298,7 @@
 	pcie_phy_write(imx6_pcie, PHY_RX_OVRD_IN_LO, tmp);
 }
 
+#ifdef CONFIG_ARM
 /*  Added for PCI abort handling */
 static int imx6q_pcie_abort_handler(unsigned long addr,
 		unsigned int fsr, struct pt_regs *regs)
@@ -278,13 +332,55 @@
 
 	return 1;
 }
+#endif
+
+static int imx6_pcie_attach_pd(struct device *dev)
+{
+	struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev);
+	struct device_link *link;
+
+	/* Do nothing when in a single power domain */
+	if (dev->pm_domain)
+		return 0;
+
+	imx6_pcie->pd_pcie = dev_pm_domain_attach_by_name(dev, "pcie");
+	if (IS_ERR(imx6_pcie->pd_pcie))
+		return PTR_ERR(imx6_pcie->pd_pcie);
+	/* Do nothing when power domain missing */
+	if (!imx6_pcie->pd_pcie)
+		return 0;
+	link = device_link_add(dev, imx6_pcie->pd_pcie,
+			DL_FLAG_STATELESS |
+			DL_FLAG_PM_RUNTIME |
+			DL_FLAG_RPM_ACTIVE);
+	if (!link) {
+		dev_err(dev, "Failed to add device_link to pcie pd.\n");
+		return -EINVAL;
+	}
+
+	imx6_pcie->pd_pcie_phy = dev_pm_domain_attach_by_name(dev, "pcie_phy");
+	if (IS_ERR(imx6_pcie->pd_pcie_phy))
+		return PTR_ERR(imx6_pcie->pd_pcie_phy);
+
+	link = device_link_add(dev, imx6_pcie->pd_pcie_phy,
+			DL_FLAG_STATELESS |
+			DL_FLAG_PM_RUNTIME |
+			DL_FLAG_RPM_ACTIVE);
+	if (!link) {
+		dev_err(dev, "Failed to add device_link to pcie_phy pd.\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
 
 static void imx6_pcie_assert_core_reset(struct imx6_pcie *imx6_pcie)
 {
 	struct device *dev = imx6_pcie->pci->dev;
 
-	switch (imx6_pcie->variant) {
+	switch (imx6_pcie->drvdata->variant) {
 	case IMX7D:
+	case IMX8MQ:
 		reset_control_assert(imx6_pcie->pciephy_reset);
 		reset_control_assert(imx6_pcie->apps_reset);
 		break;
@@ -319,13 +415,20 @@
 	}
 }
 
+static unsigned int imx6_pcie_grp_offset(const struct imx6_pcie *imx6_pcie)
+{
+	WARN_ON(imx6_pcie->drvdata->variant != IMX8MQ);
+	return imx6_pcie->controller_id == 1 ? IOMUXC_GPR16 : IOMUXC_GPR14;
+}
+
 static int imx6_pcie_enable_ref_clk(struct imx6_pcie *imx6_pcie)
 {
 	struct dw_pcie *pci = imx6_pcie->pci;
 	struct device *dev = pci->dev;
+	unsigned int offset;
 	int ret = 0;
 
-	switch (imx6_pcie->variant) {
+	switch (imx6_pcie->drvdata->variant) {
 	case IMX6SX:
 		ret = clk_prepare_enable(imx6_pcie->pcie_inbound_axi);
 		if (ret) {
@@ -347,12 +450,31 @@
 		 * reset time is too short, cannot meet the requirement.
 		 * add one ~10us delay here.
 		 */
-		udelay(10);
+		usleep_range(10, 100);
 		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
 				   IMX6Q_GPR1_PCIE_REF_CLK_EN, 1 << 16);
 		break;
 	case IMX7D:
 		break;
+	case IMX8MQ:
+		ret = clk_prepare_enable(imx6_pcie->pcie_aux);
+		if (ret) {
+			dev_err(dev, "unable to enable pcie_aux clock\n");
+			break;
+		}
+
+		offset = imx6_pcie_grp_offset(imx6_pcie);
+		/*
+		 * Set the over ride low and enabled
+		 * make sure that REF_CLK is turned on.
+		 */
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, offset,
+				   IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE,
+				   0);
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, offset,
+				   IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN,
+				   IMX8MQ_GPR_PCIE_CLK_REQ_OVERRIDE_EN);
+		break;
 	}
 
 	return ret;
@@ -361,20 +483,14 @@
 static void imx7d_pcie_wait_for_phy_pll_lock(struct imx6_pcie *imx6_pcie)
 {
 	u32 val;
-	unsigned int retries;
 	struct device *dev = imx6_pcie->pci->dev;
 
-	for (retries = 0; retries < PHY_PLL_LOCK_WAIT_MAX_RETRIES; retries++) {
-		regmap_read(imx6_pcie->iomuxc_gpr, IOMUXC_GPR22, &val);
-
-		if (val & IMX7D_GPR22_PCIE_PHY_PLL_LOCKED)
-			return;
-
-		usleep_range(PHY_PLL_LOCK_WAIT_USLEEP_MIN,
-			     PHY_PLL_LOCK_WAIT_USLEEP_MAX);
-	}
-
-	dev_err(dev, "PCIe PLL lock timeout\n");
+	if (regmap_read_poll_timeout(imx6_pcie->iomuxc_gpr,
+				     IOMUXC_GPR22, val,
+				     val & IMX7D_GPR22_PCIE_PHY_PLL_LOCKED,
+				     PHY_PLL_LOCK_WAIT_USLEEP_MAX,
+				     PHY_PLL_LOCK_WAIT_TIMEOUT))
+		dev_err(dev, "PCIe PLL lock timeout\n");
 }
 
 static void imx6_pcie_deassert_core_reset(struct imx6_pcie *imx6_pcie)
@@ -428,9 +544,32 @@
 					!imx6_pcie->gpio_active_high);
 	}
 
-	switch (imx6_pcie->variant) {
+	switch (imx6_pcie->drvdata->variant) {
+	case IMX8MQ:
+		reset_control_deassert(imx6_pcie->pciephy_reset);
+		break;
 	case IMX7D:
 		reset_control_deassert(imx6_pcie->pciephy_reset);
+
+		/* Workaround for ERR010728, failure of PCI-e PLL VCO to
+		 * oscillate, especially when cold.  This turns off "Duty-cycle
+		 * Corrector" and other mysterious undocumented things.
+		 */
+		if (likely(imx6_pcie->phy_base)) {
+			/* De-assert DCC_FB_EN */
+			writel(PCIE_PHY_CMN_REG4_DCC_FB_EN,
+			       imx6_pcie->phy_base + PCIE_PHY_CMN_REG4);
+			/* Assert RX_EQS and RX_EQS_SEL */
+			writel(PCIE_PHY_CMN_REG24_RX_EQ_SEL
+				| PCIE_PHY_CMN_REG24_RX_EQ,
+			       imx6_pcie->phy_base + PCIE_PHY_CMN_REG24);
+			/* Assert ATT_MODE */
+			writel(PCIE_PHY_CMN_REG26_ATT_MODE,
+			       imx6_pcie->phy_base + PCIE_PHY_CMN_REG26);
+		} else {
+			dev_warn(dev, "Unable to apply ERR010728 workaround. DT missing fsl,imx7d-pcie-phy phandle ?\n");
+		}
+
 		imx7d_pcie_wait_for_phy_pll_lock(imx6_pcie);
 		break;
 	case IMX6SX:
@@ -464,9 +603,37 @@
 	}
 }
 
+static void imx6_pcie_configure_type(struct imx6_pcie *imx6_pcie)
+{
+	unsigned int mask, val;
+
+	if (imx6_pcie->drvdata->variant == IMX8MQ &&
+	    imx6_pcie->controller_id == 1) {
+		mask   = IMX8MQ_GPR12_PCIE2_CTRL_DEVICE_TYPE;
+		val    = FIELD_PREP(IMX8MQ_GPR12_PCIE2_CTRL_DEVICE_TYPE,
+				    PCI_EXP_TYPE_ROOT_PORT);
+	} else {
+		mask = IMX6Q_GPR12_DEVICE_TYPE;
+		val  = FIELD_PREP(IMX6Q_GPR12_DEVICE_TYPE,
+				  PCI_EXP_TYPE_ROOT_PORT);
+	}
+
+	regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, mask, val);
+}
+
 static void imx6_pcie_init_phy(struct imx6_pcie *imx6_pcie)
 {
-	switch (imx6_pcie->variant) {
+	switch (imx6_pcie->drvdata->variant) {
+	case IMX8MQ:
+		/*
+		 * TODO: Currently this code assumes external
+		 * oscillator is being used
+		 */
+		regmap_update_bits(imx6_pcie->iomuxc_gpr,
+				   imx6_pcie_grp_offset(imx6_pcie),
+				   IMX8MQ_GPR_PCIE_REF_USE_PAD,
+				   IMX8MQ_GPR_PCIE_REF_USE_PAD);
+		break;
 	case IMX7D:
 		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
 				   IMX7D_GPR12_PCIE_PHY_REFCLK_SEL, 0);
@@ -502,23 +669,54 @@
 		break;
 	}
 
-	regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
-			IMX6Q_GPR12_DEVICE_TYPE, PCI_EXP_TYPE_ROOT_PORT << 12);
+	imx6_pcie_configure_type(imx6_pcie);
 }
 
-static int imx6_pcie_wait_for_link(struct imx6_pcie *imx6_pcie)
+static int imx6_setup_phy_mpll(struct imx6_pcie *imx6_pcie)
 {
-	struct dw_pcie *pci = imx6_pcie->pci;
-	struct device *dev = pci->dev;
+	unsigned long phy_rate = clk_get_rate(imx6_pcie->pcie_phy);
+	int mult, div;
+	u16 val;
 
-	/* check if the link is up or not */
-	if (!dw_pcie_wait_for_link(pci))
+	if (!(imx6_pcie->drvdata->flags & IMX6_PCIE_FLAG_IMX6_PHY))
 		return 0;
 
-	dev_dbg(dev, "DEBUG_R0: 0x%08x, DEBUG_R1: 0x%08x\n",
-		dw_pcie_readl_dbi(pci, PCIE_PHY_DEBUG_R0),
-		dw_pcie_readl_dbi(pci, PCIE_PHY_DEBUG_R1));
-	return -ETIMEDOUT;
+	switch (phy_rate) {
+	case 125000000:
+		/*
+		 * The default settings of the MPLL are for a 125MHz input
+		 * clock, so no need to reconfigure anything in that case.
+		 */
+		return 0;
+	case 100000000:
+		mult = 25;
+		div = 0;
+		break;
+	case 200000000:
+		mult = 25;
+		div = 1;
+		break;
+	default:
+		dev_err(imx6_pcie->pci->dev,
+			"Unsupported PHY reference clock rate %lu\n", phy_rate);
+		return -EINVAL;
+	}
+
+	pcie_phy_read(imx6_pcie, PCIE_PHY_MPLL_OVRD_IN_LO, &val);
+	val &= ~(PCIE_PHY_MPLL_MULTIPLIER_MASK <<
+		 PCIE_PHY_MPLL_MULTIPLIER_SHIFT);
+	val |= mult << PCIE_PHY_MPLL_MULTIPLIER_SHIFT;
+	val |= PCIE_PHY_MPLL_MULTIPLIER_OVRD;
+	pcie_phy_write(imx6_pcie, PCIE_PHY_MPLL_OVRD_IN_LO, val);
+
+	pcie_phy_read(imx6_pcie, PCIE_PHY_ATEOVRD, &val);
+	val &= ~(PCIE_PHY_ATEOVRD_REF_CLKDIV_MASK <<
+		 PCIE_PHY_ATEOVRD_REF_CLKDIV_SHIFT);
+	val |= div << PCIE_PHY_ATEOVRD_REF_CLKDIV_SHIFT;
+	val |= PCIE_PHY_ATEOVRD_EN;
+	pcie_phy_write(imx6_pcie, PCIE_PHY_ATEOVRD, val);
+
+	return 0;
 }
 
 static int imx6_pcie_wait_for_speed_change(struct imx6_pcie *imx6_pcie)
@@ -537,7 +735,26 @@
 	}
 
 	dev_err(dev, "Speed change timeout\n");
-	return -EINVAL;
+	return -ETIMEDOUT;
+}
+
+static void imx6_pcie_ltssm_enable(struct device *dev)
+{
+	struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev);
+
+	switch (imx6_pcie->drvdata->variant) {
+	case IMX6Q:
+	case IMX6SX:
+	case IMX6QP:
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
+				   IMX6Q_GPR12_PCIE_CTL_2,
+				   IMX6Q_GPR12_PCIE_CTL_2);
+		break;
+	case IMX7D:
+	case IMX8MQ:
+		reset_control_deassert(imx6_pcie->apps_reset);
+		break;
+	}
 }
 
 static int imx6_pcie_establish_link(struct imx6_pcie *imx6_pcie)
@@ -558,13 +775,9 @@
 	dw_pcie_writel_dbi(pci, PCIE_RC_LCR, tmp);
 
 	/* Start LTSSM. */
-	if (imx6_pcie->variant == IMX7D)
-		reset_control_deassert(imx6_pcie->apps_reset);
-	else
-		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
-				   IMX6Q_GPR12_PCIE_CTL_2, 1 << 10);
+	imx6_pcie_ltssm_enable(dev);
 
-	ret = imx6_pcie_wait_for_link(imx6_pcie);
+	ret = dw_pcie_wait_for_link(pci);
 	if (ret)
 		goto err_reset_phy;
 
@@ -583,7 +796,8 @@
 		tmp |= PORT_LOGIC_SPEED_CHANGE;
 		dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, tmp);
 
-		if (imx6_pcie->variant != IMX7D) {
+		if (imx6_pcie->drvdata->flags &
+		    IMX6_PCIE_FLAG_IMX6_SPEED_CHANGE) {
 			/*
 			 * On i.MX7, DIRECT_SPEED_CHANGE behaves differently
 			 * from i.MX6 family when no link speed transition
@@ -601,7 +815,7 @@
 		}
 
 		/* Make sure link training is finished as well! */
-		ret = imx6_pcie_wait_for_link(imx6_pcie);
+		ret = dw_pcie_wait_for_link(pci);
 		if (ret) {
 			dev_err(dev, "Failed to bring link up!\n");
 			goto err_reset_phy;
@@ -616,8 +830,8 @@
 
 err_reset_phy:
 	dev_dbg(dev, "PHY DEBUG_R0=0x%08x DEBUG_R1=0x%08x\n",
-		dw_pcie_readl_dbi(pci, PCIE_PHY_DEBUG_R0),
-		dw_pcie_readl_dbi(pci, PCIE_PHY_DEBUG_R1));
+		dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG0),
+		dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG1));
 	imx6_pcie_reset_phy(imx6_pcie);
 	return ret;
 }
@@ -630,6 +844,7 @@
 	imx6_pcie_assert_core_reset(imx6_pcie);
 	imx6_pcie_init_phy(imx6_pcie);
 	imx6_pcie_deassert_core_reset(imx6_pcie);
+	imx6_setup_phy_mpll(imx6_pcie);
 	dw_pcie_setup_rc(pp);
 	imx6_pcie_establish_link(imx6_pcie);
 
@@ -674,14 +889,135 @@
 	/* No special ops needed, but pcie-designware still expects this struct */
 };
 
+#ifdef CONFIG_PM_SLEEP
+static void imx6_pcie_ltssm_disable(struct device *dev)
+{
+	struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev);
+
+	switch (imx6_pcie->drvdata->variant) {
+	case IMX6SX:
+	case IMX6QP:
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
+				   IMX6Q_GPR12_PCIE_CTL_2, 0);
+		break;
+	case IMX7D:
+		reset_control_assert(imx6_pcie->apps_reset);
+		break;
+	default:
+		dev_err(dev, "ltssm_disable not supported\n");
+	}
+}
+
+static void imx6_pcie_pm_turnoff(struct imx6_pcie *imx6_pcie)
+{
+	struct device *dev = imx6_pcie->pci->dev;
+
+	/* Some variants have a turnoff reset in DT */
+	if (imx6_pcie->turnoff_reset) {
+		reset_control_assert(imx6_pcie->turnoff_reset);
+		reset_control_deassert(imx6_pcie->turnoff_reset);
+		goto pm_turnoff_sleep;
+	}
+
+	/* Others poke directly at IOMUXC registers */
+	switch (imx6_pcie->drvdata->variant) {
+	case IMX6SX:
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
+				IMX6SX_GPR12_PCIE_PM_TURN_OFF,
+				IMX6SX_GPR12_PCIE_PM_TURN_OFF);
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
+				IMX6SX_GPR12_PCIE_PM_TURN_OFF, 0);
+		break;
+	default:
+		dev_err(dev, "PME_Turn_Off not implemented\n");
+		return;
+	}
+
+	/*
+	 * Components with an upstream port must respond to
+	 * PME_Turn_Off with PME_TO_Ack but we can't check.
+	 *
+	 * The standard recommends a 1-10ms timeout after which to
+	 * proceed anyway as if acks were received.
+	 */
+pm_turnoff_sleep:
+	usleep_range(1000, 10000);
+}
+
+static void imx6_pcie_clk_disable(struct imx6_pcie *imx6_pcie)
+{
+	clk_disable_unprepare(imx6_pcie->pcie);
+	clk_disable_unprepare(imx6_pcie->pcie_phy);
+	clk_disable_unprepare(imx6_pcie->pcie_bus);
+
+	switch (imx6_pcie->drvdata->variant) {
+	case IMX6SX:
+		clk_disable_unprepare(imx6_pcie->pcie_inbound_axi);
+		break;
+	case IMX7D:
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
+				   IMX7D_GPR12_PCIE_PHY_REFCLK_SEL,
+				   IMX7D_GPR12_PCIE_PHY_REFCLK_SEL);
+		break;
+	case IMX8MQ:
+		clk_disable_unprepare(imx6_pcie->pcie_aux);
+		break;
+	default:
+		break;
+	}
+}
+
+static int imx6_pcie_suspend_noirq(struct device *dev)
+{
+	struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev);
+
+	if (!(imx6_pcie->drvdata->flags & IMX6_PCIE_FLAG_SUPPORTS_SUSPEND))
+		return 0;
+
+	imx6_pcie_pm_turnoff(imx6_pcie);
+	imx6_pcie_clk_disable(imx6_pcie);
+	imx6_pcie_ltssm_disable(dev);
+
+	return 0;
+}
+
+static int imx6_pcie_resume_noirq(struct device *dev)
+{
+	int ret;
+	struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev);
+	struct pcie_port *pp = &imx6_pcie->pci->pp;
+
+	if (!(imx6_pcie->drvdata->flags & IMX6_PCIE_FLAG_SUPPORTS_SUSPEND))
+		return 0;
+
+	imx6_pcie_assert_core_reset(imx6_pcie);
+	imx6_pcie_init_phy(imx6_pcie);
+	imx6_pcie_deassert_core_reset(imx6_pcie);
+	dw_pcie_setup_rc(pp);
+
+	ret = imx6_pcie_establish_link(imx6_pcie);
+	if (ret < 0)
+		dev_info(dev, "pcie link is down after resume.\n");
+
+	return 0;
+}
+#endif
+
+static const struct dev_pm_ops imx6_pcie_pm_ops = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(imx6_pcie_suspend_noirq,
+				      imx6_pcie_resume_noirq)
+};
+
 static int imx6_pcie_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct dw_pcie *pci;
 	struct imx6_pcie *imx6_pcie;
+	struct device_node *np;
 	struct resource *dbi_base;
 	struct device_node *node = dev->of_node;
 	int ret;
+	u16 val;
 
 	imx6_pcie = devm_kzalloc(dev, sizeof(*imx6_pcie), GFP_KERNEL);
 	if (!imx6_pcie)
@@ -695,8 +1031,24 @@
 	pci->ops = &dw_pcie_ops;
 
 	imx6_pcie->pci = pci;
-	imx6_pcie->variant =
-		(enum imx6_pcie_variants)of_device_get_match_data(dev);
+	imx6_pcie->drvdata = of_device_get_match_data(dev);
+
+	/* Find the PHY if one is defined, only imx7d uses it */
+	np = of_parse_phandle(node, "fsl,imx7d-pcie-phy", 0);
+	if (np) {
+		struct resource res;
+
+		ret = of_address_to_resource(np, 0, &res);
+		if (ret) {
+			dev_err(dev, "Unable to map PCIe PHY\n");
+			return ret;
+		}
+		imx6_pcie->phy_base = devm_ioremap_resource(dev, &res);
+		if (IS_ERR(imx6_pcie->phy_base)) {
+			dev_err(dev, "Unable to map PCIe PHY\n");
+			return PTR_ERR(imx6_pcie->phy_base);
+		}
+	}
 
 	dbi_base = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	pci->dbi_base = devm_ioremap_resource(dev, dbi_base);
@@ -740,7 +1092,7 @@
 		return PTR_ERR(imx6_pcie->pcie);
 	}
 
-	switch (imx6_pcie->variant) {
+	switch (imx6_pcie->drvdata->variant) {
 	case IMX6SX:
 		imx6_pcie->pcie_inbound_axi = devm_clk_get(dev,
 							   "pcie_inbound_axi");
@@ -749,7 +1101,17 @@
 			return PTR_ERR(imx6_pcie->pcie_inbound_axi);
 		}
 		break;
+	case IMX8MQ:
+		imx6_pcie->pcie_aux = devm_clk_get(dev, "pcie_aux");
+		if (IS_ERR(imx6_pcie->pcie_aux)) {
+			dev_err(dev, "pcie_aux clock source missing or invalid\n");
+			return PTR_ERR(imx6_pcie->pcie_aux);
+		}
+		/* fall through */
 	case IMX7D:
+		if (dbi_base->start == IMX8MQ_PCIE2_BASE_ADDR)
+			imx6_pcie->controller_id = 1;
+
 		imx6_pcie->pciephy_reset = devm_reset_control_get_exclusive(dev,
 									    "pciephy");
 		if (IS_ERR(imx6_pcie->pciephy_reset)) {
@@ -768,6 +1130,13 @@
 		break;
 	}
 
+	/* Grab turnoff reset */
+	imx6_pcie->turnoff_reset = devm_reset_control_get_optional_exclusive(dev, "turnoff");
+	if (IS_ERR(imx6_pcie->turnoff_reset)) {
+		dev_err(dev, "Failed to get TURNOFF reset control\n");
+		return PTR_ERR(imx6_pcie->turnoff_reset);
+	}
+
 	/* Grab GPR config register range */
 	imx6_pcie->iomuxc_gpr =
 		 syscon_regmap_lookup_by_compatible("fsl,imx6q-iomuxc-gpr");
@@ -805,17 +1174,29 @@
 
 	imx6_pcie->vpcie = devm_regulator_get_optional(&pdev->dev, "vpcie");
 	if (IS_ERR(imx6_pcie->vpcie)) {
-		if (PTR_ERR(imx6_pcie->vpcie) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
+		if (PTR_ERR(imx6_pcie->vpcie) != -ENODEV)
+			return PTR_ERR(imx6_pcie->vpcie);
 		imx6_pcie->vpcie = NULL;
 	}
 
 	platform_set_drvdata(pdev, imx6_pcie);
 
+	ret = imx6_pcie_attach_pd(dev);
+	if (ret)
+		return ret;
+
 	ret = imx6_add_pcie_port(imx6_pcie, pdev);
 	if (ret < 0)
 		return ret;
 
+	if (pci_msi_enabled()) {
+		val = dw_pcie_readw_dbi(pci, PCIE_RC_IMX6_MSI_CAP +
+					PCI_MSI_FLAGS);
+		val |= PCI_MSI_FLAGS_ENABLE;
+		dw_pcie_writew_dbi(pci, PCIE_RC_IMX6_MSI_CAP + PCI_MSI_FLAGS,
+				   val);
+	}
+
 	return 0;
 }
 
@@ -827,11 +1208,39 @@
 	imx6_pcie_assert_core_reset(imx6_pcie);
 }
 
+static const struct imx6_pcie_drvdata drvdata[] = {
+	[IMX6Q] = {
+		.variant = IMX6Q,
+		.flags = IMX6_PCIE_FLAG_IMX6_PHY |
+			 IMX6_PCIE_FLAG_IMX6_SPEED_CHANGE,
+		.dbi_length = 0x200,
+	},
+	[IMX6SX] = {
+		.variant = IMX6SX,
+		.flags = IMX6_PCIE_FLAG_IMX6_PHY |
+			 IMX6_PCIE_FLAG_IMX6_SPEED_CHANGE |
+			 IMX6_PCIE_FLAG_SUPPORTS_SUSPEND,
+	},
+	[IMX6QP] = {
+		.variant = IMX6QP,
+		.flags = IMX6_PCIE_FLAG_IMX6_PHY |
+			 IMX6_PCIE_FLAG_IMX6_SPEED_CHANGE,
+	},
+	[IMX7D] = {
+		.variant = IMX7D,
+		.flags = IMX6_PCIE_FLAG_SUPPORTS_SUSPEND,
+	},
+	[IMX8MQ] = {
+		.variant = IMX8MQ,
+	},
+};
+
 static const struct of_device_id imx6_pcie_of_match[] = {
-	{ .compatible = "fsl,imx6q-pcie",  .data = (void *)IMX6Q,  },
-	{ .compatible = "fsl,imx6sx-pcie", .data = (void *)IMX6SX, },
-	{ .compatible = "fsl,imx6qp-pcie", .data = (void *)IMX6QP, },
-	{ .compatible = "fsl,imx7d-pcie",  .data = (void *)IMX7D,  },
+	{ .compatible = "fsl,imx6q-pcie",  .data = &drvdata[IMX6Q],  },
+	{ .compatible = "fsl,imx6sx-pcie", .data = &drvdata[IMX6SX], },
+	{ .compatible = "fsl,imx6qp-pcie", .data = &drvdata[IMX6QP], },
+	{ .compatible = "fsl,imx7d-pcie",  .data = &drvdata[IMX7D],  },
+	{ .compatible = "fsl,imx8mq-pcie", .data = &drvdata[IMX8MQ], } ,
 	{},
 };
 
@@ -840,13 +1249,47 @@
 		.name	= "imx6q-pcie",
 		.of_match_table = imx6_pcie_of_match,
 		.suppress_bind_attrs = true,
+		.pm = &imx6_pcie_pm_ops,
+		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
 	},
 	.probe    = imx6_pcie_probe,
 	.shutdown = imx6_pcie_shutdown,
 };
 
+static void imx6_pcie_quirk(struct pci_dev *dev)
+{
+	struct pci_bus *bus = dev->bus;
+	struct pcie_port *pp = bus->sysdata;
+
+	/* Bus parent is the PCI bridge, its parent is this platform driver */
+	if (!bus->dev.parent || !bus->dev.parent->parent)
+		return;
+
+	/* Make sure we only quirk devices associated with this driver */
+	if (bus->dev.parent->parent->driver != &imx6_pcie_driver.driver)
+		return;
+
+	if (bus->number == pp->root_bus_nr) {
+		struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+		struct imx6_pcie *imx6_pcie = to_imx6_pcie(pci);
+
+		/*
+		 * Limit config length to avoid the kernel reading beyond
+		 * the register set and causing an abort on i.MX 6Quad
+		 */
+		if (imx6_pcie->drvdata->dbi_length) {
+			dev->cfg_size = imx6_pcie->drvdata->dbi_length;
+			dev_info(&dev->dev, "Limiting cfg_size to %d\n",
+					dev->cfg_size);
+		}
+	}
+}
+DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_SYNOPSYS, 0xabcd,
+			PCI_CLASS_BRIDGE_PCI, 8, imx6_pcie_quirk);
+
 static int __init imx6_pcie_init(void)
 {
+#ifdef CONFIG_ARM
 	/*
 	 * Since probe() can be deferred we need to make sure that
 	 * hook_fault_code is not called after __init memory is freed
@@ -856,6 +1299,7 @@
 	 */
 	hook_fault_code(8, imx6q_pcie_abort_handler, SIGBUS, 0,
 			"external abort on non-linefetch");
+#endif
 
 	return platform_driver_register(&imx6_pcie_driver);
 }
diff --git a/drivers/pci/controller/dwc/pci-keystone-dw.c b/drivers/pci/controller/dwc/pci-keystone-dw.c
deleted file mode 100644
index 0682213..0000000
--- a/drivers/pci/controller/dwc/pci-keystone-dw.c
+++ /dev/null
@@ -1,484 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * DesignWare application register space functions for Keystone PCI controller
- *
- * Copyright (C) 2013-2014 Texas Instruments., Ltd.
- *		http://www.ti.com
- *
- * Author: Murali Karicheri <m-karicheri2@ti.com>
- */
-
-#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>
-#include <linux/pci.h>
-#include <linux/platform_device.h>
-
-#include "pcie-designware.h"
-#include "pci-keystone.h"
-
-/* Application register defines */
-#define LTSSM_EN_VAL		        1
-#define LTSSM_STATE_MASK		0x1f
-#define LTSSM_STATE_L0			0x11
-#define DBI_CS2_EN_VAL			0x20
-#define OB_XLAT_EN_VAL		        2
-
-/* Application registers */
-#define CMD_STATUS			0x004
-#define CFG_SETUP			0x008
-#define OB_SIZE				0x030
-#define CFG_PCIM_WIN_SZ_IDX		3
-#define CFG_PCIM_WIN_CNT		32
-#define SPACE0_REMOTE_CFG_OFFSET	0x1000
-#define OB_OFFSET_INDEX(n)		(0x200 + (8 * n))
-#define OB_OFFSET_HI(n)			(0x204 + (8 * n))
-
-/* IRQ register defines */
-#define IRQ_EOI				0x050
-#define IRQ_STATUS			0x184
-#define IRQ_ENABLE_SET			0x188
-#define IRQ_ENABLE_CLR			0x18c
-
-#define MSI_IRQ				0x054
-#define MSI0_IRQ_STATUS			0x104
-#define MSI0_IRQ_ENABLE_SET		0x108
-#define MSI0_IRQ_ENABLE_CLR		0x10c
-#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
-
-#define to_keystone_pcie(x)	dev_get_drvdata((x)->dev)
-
-static inline void update_reg_offset_bit_pos(u32 offset, u32 *reg_offset,
-					     u32 *bit_pos)
-{
-	*reg_offset = offset % 8;
-	*bit_pos = offset >> 3;
-}
-
-phys_addr_t ks_dw_pcie_get_msi_addr(struct pcie_port *pp)
-{
-	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
-	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
-
-	return ks_pcie->app.start + MSI_IRQ;
-}
-
-static u32 ks_dw_app_readl(struct keystone_pcie *ks_pcie, u32 offset)
-{
-	return readl(ks_pcie->va_app_base + offset);
-}
-
-static void ks_dw_app_writel(struct keystone_pcie *ks_pcie, u32 offset, u32 val)
-{
-	writel(val, ks_pcie->va_app_base + offset);
-}
-
-void ks_dw_pcie_handle_msi_irq(struct keystone_pcie *ks_pcie, int offset)
-{
-	struct dw_pcie *pci = ks_pcie->pci;
-	struct pcie_port *pp = &pci->pp;
-	struct device *dev = pci->dev;
-	u32 pending, vector;
-	int src, virq;
-
-	pending = ks_dw_app_readl(ks_pcie, MSI0_IRQ_STATUS + (offset << 4));
-
-	/*
-	 * MSI0 status bit 0-3 shows vectors 0, 8, 16, 24, MSI1 status bit
-	 * shows 1, 9, 17, 25 and so forth
-	 */
-	for (src = 0; src < 4; src++) {
-		if (BIT(src) & pending) {
-			vector = offset + (src << 3);
-			virq = irq_linear_revmap(pp->irq_domain, vector);
-			dev_dbg(dev, "irq: bit %d, vector %d, virq %d\n",
-				src, vector, virq);
-			generic_handle_irq(virq);
-		}
-	}
-}
-
-void ks_dw_pcie_msi_irq_ack(int irq, struct pcie_port *pp)
-{
-	u32 reg_offset, bit_pos;
-	struct keystone_pcie *ks_pcie;
-	struct dw_pcie *pci;
-
-	pci = to_dw_pcie_from_pp(pp);
-	ks_pcie = to_keystone_pcie(pci);
-	update_reg_offset_bit_pos(irq, &reg_offset, &bit_pos);
-
-	ks_dw_app_writel(ks_pcie, MSI0_IRQ_STATUS + (reg_offset << 4),
-			 BIT(bit_pos));
-	ks_dw_app_writel(ks_pcie, IRQ_EOI, reg_offset + MSI_IRQ_OFFSET);
-}
-
-void ks_dw_pcie_msi_set_irq(struct pcie_port *pp, int irq)
-{
-	u32 reg_offset, bit_pos;
-	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
-	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
-
-	update_reg_offset_bit_pos(irq, &reg_offset, &bit_pos);
-	ks_dw_app_writel(ks_pcie, MSI0_IRQ_ENABLE_SET + (reg_offset << 4),
-			 BIT(bit_pos));
-}
-
-void ks_dw_pcie_msi_clear_irq(struct pcie_port *pp, int irq)
-{
-	u32 reg_offset, bit_pos;
-	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
-	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
-
-	update_reg_offset_bit_pos(irq, &reg_offset, &bit_pos);
-	ks_dw_app_writel(ks_pcie, MSI0_IRQ_ENABLE_CLR + (reg_offset << 4),
-			 BIT(bit_pos));
-}
-
-int ks_dw_pcie_msi_host_init(struct pcie_port *pp)
-{
-	return dw_pcie_allocate_domains(pp);
-}
-
-void ks_dw_pcie_enable_legacy_irqs(struct keystone_pcie *ks_pcie)
-{
-	int i;
-
-	for (i = 0; i < PCI_NUM_INTX; i++)
-		ks_dw_app_writel(ks_pcie, IRQ_ENABLE_SET + (i << 4), 0x1);
-}
-
-void ks_dw_pcie_handle_legacy_irq(struct keystone_pcie *ks_pcie, int offset)
-{
-	struct dw_pcie *pci = ks_pcie->pci;
-	struct device *dev = pci->dev;
-	u32 pending;
-	int virq;
-
-	pending = ks_dw_app_readl(ks_pcie, IRQ_STATUS + (offset << 4));
-
-	if (BIT(0) & pending) {
-		virq = irq_linear_revmap(ks_pcie->legacy_irq_domain, offset);
-		dev_dbg(dev, ": irq: irq_offset %d, virq %d\n", offset, virq);
-		generic_handle_irq(virq);
-	}
-
-	/* EOI the INTx interrupt */
-	ks_dw_app_writel(ks_pcie, IRQ_EOI, offset);
-}
-
-void ks_dw_pcie_enable_error_irq(struct keystone_pcie *ks_pcie)
-{
-	ks_dw_app_writel(ks_pcie, ERR_IRQ_ENABLE_SET, ERR_IRQ_ALL);
-}
-
-irqreturn_t ks_dw_pcie_handle_error_irq(struct keystone_pcie *ks_pcie)
-{
-	u32 status;
-
-	status = ks_dw_app_readl(ks_pcie, ERR_IRQ_STATUS_RAW) & ERR_IRQ_ALL;
-	if (!status)
-		return IRQ_NONE;
-
-	if (status & ERR_FATAL_IRQ)
-		dev_err(ks_pcie->pci->dev, "fatal error (status %#010x)\n",
-			status);
-
-	/* Ack the IRQ; status bits are RW1C */
-	ks_dw_app_writel(ks_pcie, ERR_IRQ_STATUS, status);
-	return IRQ_HANDLED;
-}
-
-static void ks_dw_pcie_ack_legacy_irq(struct irq_data *d)
-{
-}
-
-static void ks_dw_pcie_mask_legacy_irq(struct irq_data *d)
-{
-}
-
-static void ks_dw_pcie_unmask_legacy_irq(struct irq_data *d)
-{
-}
-
-static struct irq_chip ks_dw_pcie_legacy_irq_chip = {
-	.name = "Keystone-PCI-Legacy-IRQ",
-	.irq_ack = ks_dw_pcie_ack_legacy_irq,
-	.irq_mask = ks_dw_pcie_mask_legacy_irq,
-	.irq_unmask = ks_dw_pcie_unmask_legacy_irq,
-};
-
-static int ks_dw_pcie_init_legacy_irq_map(struct irq_domain *d,
-				unsigned int irq, irq_hw_number_t hw_irq)
-{
-	irq_set_chip_and_handler(irq, &ks_dw_pcie_legacy_irq_chip,
-				 handle_level_irq);
-	irq_set_chip_data(irq, d->host_data);
-
-	return 0;
-}
-
-static const struct irq_domain_ops ks_dw_pcie_legacy_irq_domain_ops = {
-	.map = ks_dw_pcie_init_legacy_irq_map,
-	.xlate = irq_domain_xlate_onetwocell,
-};
-
-/**
- * ks_dw_pcie_set_dbi_mode() - Set DBI mode to access overlaid BAR mask
- * registers
- *
- * Since modification of dbi_cs2 involves different clock domain, read the
- * status back to ensure the transition is complete.
- */
-static void ks_dw_pcie_set_dbi_mode(struct keystone_pcie *ks_pcie)
-{
-	u32 val;
-
-	val = ks_dw_app_readl(ks_pcie, CMD_STATUS);
-	ks_dw_app_writel(ks_pcie, CMD_STATUS, DBI_CS2_EN_VAL | val);
-
-	do {
-		val = ks_dw_app_readl(ks_pcie, CMD_STATUS);
-	} while (!(val & DBI_CS2_EN_VAL));
-}
-
-/**
- * ks_dw_pcie_clear_dbi_mode() - Disable DBI mode
- *
- * Since modification of dbi_cs2 involves different clock domain, read the
- * status back to ensure the transition is complete.
- */
-static void ks_dw_pcie_clear_dbi_mode(struct keystone_pcie *ks_pcie)
-{
-	u32 val;
-
-	val = ks_dw_app_readl(ks_pcie, CMD_STATUS);
-	ks_dw_app_writel(ks_pcie, CMD_STATUS, ~DBI_CS2_EN_VAL & val);
-
-	do {
-		val = ks_dw_app_readl(ks_pcie, CMD_STATUS);
-	} while (val & DBI_CS2_EN_VAL);
-}
-
-void ks_dw_pcie_setup_rc_app_regs(struct keystone_pcie *ks_pcie)
-{
-	struct dw_pcie *pci = ks_pcie->pci;
-	struct pcie_port *pp = &pci->pp;
-	u32 start = pp->mem->start, end = pp->mem->end;
-	int i, tr_size;
-	u32 val;
-
-	/* Disable BARs for inbound access */
-	ks_dw_pcie_set_dbi_mode(ks_pcie);
-	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 0);
-	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_1, 0);
-	ks_dw_pcie_clear_dbi_mode(ks_pcie);
-
-	/* Set outbound translation size per window division */
-	ks_dw_app_writel(ks_pcie, OB_SIZE, CFG_PCIM_WIN_SZ_IDX & 0x7);
-
-	tr_size = (1 << (CFG_PCIM_WIN_SZ_IDX & 0x7)) * SZ_1M;
-
-	/* Using Direct 1:1 mapping of RC <-> PCI memory space */
-	for (i = 0; (i < CFG_PCIM_WIN_CNT) && (start < end); i++) {
-		ks_dw_app_writel(ks_pcie, OB_OFFSET_INDEX(i), start | 1);
-		ks_dw_app_writel(ks_pcie, OB_OFFSET_HI(i), 0);
-		start += tr_size;
-	}
-
-	/* Enable OB translation */
-	val = ks_dw_app_readl(ks_pcie, CMD_STATUS);
-	ks_dw_app_writel(ks_pcie, CMD_STATUS, OB_XLAT_EN_VAL | val);
-}
-
-/**
- * ks_pcie_cfg_setup() - Set up configuration space address for a device
- *
- * @ks_pcie: ptr to keystone_pcie structure
- * @bus: Bus number the device is residing on
- * @devfn: device, function number info
- *
- * Forms and returns the address of configuration space mapped in PCIESS
- * address space 0.  Also configures CFG_SETUP for remote configuration space
- * access.
- *
- * The address space has two regions to access configuration - local and remote.
- * We access local region for bus 0 (as RC is attached on bus 0) and remote
- * region for others with TYPE 1 access when bus > 1.  As for device on bus = 1,
- * we will do TYPE 0 access as it will be on our secondary bus (logical).
- * CFG_SETUP is needed only for remote configuration access.
- */
-static void __iomem *ks_pcie_cfg_setup(struct keystone_pcie *ks_pcie, u8 bus,
-				       unsigned int devfn)
-{
-	u8 device = PCI_SLOT(devfn), function = PCI_FUNC(devfn);
-	struct dw_pcie *pci = ks_pcie->pci;
-	struct pcie_port *pp = &pci->pp;
-	u32 regval;
-
-	if (bus == 0)
-		return pci->dbi_base;
-
-	regval = (bus << 16) | (device << 8) | function;
-
-	/*
-	 * Since Bus#1 will be a virtual bus, we need to have TYPE0
-	 * access only.
-	 * TYPE 1
-	 */
-	if (bus != 1)
-		regval |= BIT(24);
-
-	ks_dw_app_writel(ks_pcie, CFG_SETUP, regval);
-	return pp->va_cfg0_base;
-}
-
-int ks_dw_pcie_rd_other_conf(struct pcie_port *pp, struct pci_bus *bus,
-			     unsigned int devfn, int where, int size, u32 *val)
-{
-	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
-	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
-	u8 bus_num = bus->number;
-	void __iomem *addr;
-
-	addr = ks_pcie_cfg_setup(ks_pcie, bus_num, devfn);
-
-	return dw_pcie_read(addr + where, size, val);
-}
-
-int ks_dw_pcie_wr_other_conf(struct pcie_port *pp, struct pci_bus *bus,
-			     unsigned int devfn, int where, int size, u32 val)
-{
-	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
-	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
-	u8 bus_num = bus->number;
-	void __iomem *addr;
-
-	addr = ks_pcie_cfg_setup(ks_pcie, bus_num, devfn);
-
-	return dw_pcie_write(addr + where, size, val);
-}
-
-/**
- * ks_dw_pcie_v3_65_scan_bus() - keystone scan_bus post initialization
- *
- * This sets BAR0 to enable inbound access for MSI_IRQ register
- */
-void ks_dw_pcie_v3_65_scan_bus(struct pcie_port *pp)
-{
-	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
-	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
-
-	/* Configure and set up BAR0 */
-	ks_dw_pcie_set_dbi_mode(ks_pcie);
-
-	/* Enable BAR0 */
-	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 1);
-	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, SZ_4K - 1);
-
-	ks_dw_pcie_clear_dbi_mode(ks_pcie);
-
-	 /*
-	  * For BAR0, just setting bus address for inbound writes (MSI) should
-	  * be sufficient.  Use physical address to avoid any conflicts.
-	  */
-	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, ks_pcie->app.start);
-}
-
-/**
- * ks_dw_pcie_link_up() - Check if link up
- */
-int ks_dw_pcie_link_up(struct dw_pcie *pci)
-{
-	u32 val;
-
-	val = dw_pcie_readl_dbi(pci, DEBUG0);
-	return (val & LTSSM_STATE_MASK) == LTSSM_STATE_L0;
-}
-
-void ks_dw_pcie_initiate_link_train(struct keystone_pcie *ks_pcie)
-{
-	u32 val;
-
-	/* Disable Link training */
-	val = ks_dw_app_readl(ks_pcie, CMD_STATUS);
-	val &= ~LTSSM_EN_VAL;
-	ks_dw_app_writel(ks_pcie, CMD_STATUS, LTSSM_EN_VAL | val);
-
-	/* Initiate Link Training */
-	val = ks_dw_app_readl(ks_pcie, CMD_STATUS);
-	ks_dw_app_writel(ks_pcie, CMD_STATUS, LTSSM_EN_VAL | val);
-}
-
-/**
- * ks_dw_pcie_host_init() - initialize host for v3_65 dw hardware
- *
- * Ioremap the register resources, initialize legacy irq domain
- * and call dw_pcie_v3_65_host_init() API to initialize the Keystone
- * PCI host controller.
- */
-int __init ks_dw_pcie_host_init(struct keystone_pcie *ks_pcie,
-				struct device_node *msi_intc_np)
-{
-	struct dw_pcie *pci = ks_pcie->pci;
-	struct pcie_port *pp = &pci->pp;
-	struct device *dev = pci->dev;
-	struct platform_device *pdev = to_platform_device(dev);
-	struct resource *res;
-
-	/* Index 0 is the config reg. space address */
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	pci->dbi_base = devm_pci_remap_cfg_resource(dev, res);
-	if (IS_ERR(pci->dbi_base))
-		return PTR_ERR(pci->dbi_base);
-
-	/*
-	 * We set these same and is used in pcie rd/wr_other_conf
-	 * functions
-	 */
-	pp->va_cfg0_base = pci->dbi_base + SPACE0_REMOTE_CFG_OFFSET;
-	pp->va_cfg1_base = pp->va_cfg0_base;
-
-	/* Index 1 is the application reg. space address */
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
-	ks_pcie->va_app_base = devm_ioremap_resource(dev, res);
-	if (IS_ERR(ks_pcie->va_app_base))
-		return PTR_ERR(ks_pcie->va_app_base);
-
-	ks_pcie->app = *res;
-
-	/* Create legacy IRQ domain */
-	ks_pcie->legacy_irq_domain =
-			irq_domain_add_linear(ks_pcie->legacy_intc_np,
-					PCI_NUM_INTX,
-					&ks_dw_pcie_legacy_irq_domain_ops,
-					NULL);
-	if (!ks_pcie->legacy_irq_domain) {
-		dev_err(dev, "Failed to add irq domain for legacy irqs\n");
-		return -EINVAL;
-	}
-
-	return dw_pcie_host_init(pp);
-}
diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index e88bd22..af67725 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -9,40 +9,532 @@
  * Implementation based on pci-exynos.c and pcie-designware.c
  */
 
-#include <linux/irqchip/chained_irq.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
-#include <linux/interrupt.h>
-#include <linux/irqdomain.h>
+#include <linux/gpio/consumer.h>
 #include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/mfd/syscon.h>
 #include <linux/msi.h>
-#include <linux/of_irq.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_irq.h>
 #include <linux/of_pci.h>
-#include <linux/platform_device.h>
 #include <linux/phy/phy.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
 #include <linux/resource.h>
 #include <linux/signal.h>
 
+#include "../../pci.h"
 #include "pcie-designware.h"
-#include "pci-keystone.h"
 
-#define DRIVER_NAME	"keystone-pcie"
+#define PCIE_VENDORID_MASK	0xffff
+#define PCIE_DEVICEID_SHIFT	16
 
-/* DEV_STAT_CTRL */
-#define PCIE_CAP_BASE		0x70
+/* Application registers */
+#define CMD_STATUS			0x004
+#define LTSSM_EN_VAL		        BIT(0)
+#define OB_XLAT_EN_VAL		        BIT(1)
+#define DBI_CS2				BIT(5)
+
+#define CFG_SETUP			0x008
+#define CFG_BUS(x)			(((x) & 0xff) << 16)
+#define CFG_DEVICE(x)			(((x) & 0x1f) << 8)
+#define CFG_FUNC(x)			((x) & 0x7)
+#define CFG_TYPE1			BIT(24)
+
+#define OB_SIZE				0x030
+#define OB_OFFSET_INDEX(n)		(0x200 + (8 * (n)))
+#define OB_OFFSET_HI(n)			(0x204 + (8 * (n)))
+#define OB_ENABLEN			BIT(0)
+#define OB_WIN_SIZE			8	/* 8MB */
+
+#define PCIE_LEGACY_IRQ_ENABLE_SET(n)	(0x188 + (0x10 * ((n) - 1)))
+#define PCIE_LEGACY_IRQ_ENABLE_CLR(n)	(0x18c + (0x10 * ((n) - 1)))
+#define PCIE_EP_IRQ_SET			0x64
+#define PCIE_EP_IRQ_CLR			0x68
+#define INT_ENABLE			BIT(0)
+
+/* IRQ register defines */
+#define IRQ_EOI				0x050
+
+#define MSI_IRQ				0x054
+#define MSI_IRQ_STATUS(n)		(0x104 + ((n) << 4))
+#define MSI_IRQ_ENABLE_SET(n)		(0x108 + ((n) << 4))
+#define MSI_IRQ_ENABLE_CLR(n)		(0x10c + ((n) << 4))
+#define MSI_IRQ_OFFSET			4
+
+#define IRQ_STATUS(n)			(0x184 + ((n) << 4))
+#define IRQ_ENABLE_SET(n)		(0x188 + ((n) << 4))
+#define INTx_EN				BIT(0)
+
+#define ERR_IRQ_STATUS			0x1c4
+#define ERR_IRQ_ENABLE_SET		0x1c8
+#define ERR_AER				BIT(5)	/* ECRC error */
+#define AM6_ERR_AER			BIT(4)	/* AM6 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 error */
+#define ERR_IRQ_ALL			(ERR_AER | ERR_AXI | ERR_CORR | \
+					 ERR_NONFATAL | ERR_FATAL | ERR_SYS)
 
 /* PCIE controller device IDs */
-#define PCIE_RC_K2HK		0xb008
-#define PCIE_RC_K2E		0xb009
-#define PCIE_RC_K2L		0xb00a
+#define PCIE_RC_K2HK			0xb008
+#define PCIE_RC_K2E			0xb009
+#define PCIE_RC_K2L			0xb00a
+#define PCIE_RC_K2G			0xb00b
 
-#define to_keystone_pcie(x)	dev_get_drvdata((x)->dev)
+#define KS_PCIE_DEV_TYPE_MASK		(0x3 << 1)
+#define KS_PCIE_DEV_TYPE(mode)		((mode) << 1)
 
-static void quirk_limit_mrrs(struct pci_dev *dev)
+#define EP				0x0
+#define LEG_EP				0x1
+#define RC				0x2
+
+#define EXP_CAP_ID_OFFSET		0x70
+
+#define KS_PCIE_SYSCLOCKOUTEN		BIT(0)
+
+#define AM654_PCIE_DEV_TYPE_MASK	0x3
+#define AM654_WIN_SIZE			SZ_64K
+
+#define APP_ADDR_SPACE_0		(16 * SZ_1K)
+
+#define to_keystone_pcie(x)		dev_get_drvdata((x)->dev)
+
+struct ks_pcie_of_data {
+	enum dw_pcie_device_mode mode;
+	const struct dw_pcie_host_ops *host_ops;
+	const struct dw_pcie_ep_ops *ep_ops;
+	unsigned int version;
+};
+
+struct keystone_pcie {
+	struct dw_pcie		*pci;
+	/* PCI Device ID */
+	u32			device_id;
+	int			legacy_host_irqs[PCI_NUM_INTX];
+	struct			device_node *legacy_intc_np;
+
+	int			msi_host_irq;
+	int			num_lanes;
+	u32			num_viewport;
+	struct phy		**phy;
+	struct device_link	**link;
+	struct			device_node *msi_intc_np;
+	struct irq_domain	*legacy_irq_domain;
+	struct device_node	*np;
+
+	/* Application register space */
+	void __iomem		*va_app_base;	/* DT 1st resource */
+	struct resource		app;
+	bool			is_am6;
+};
+
+static u32 ks_pcie_app_readl(struct keystone_pcie *ks_pcie, u32 offset)
+{
+	return readl(ks_pcie->va_app_base + offset);
+}
+
+static void ks_pcie_app_writel(struct keystone_pcie *ks_pcie, u32 offset,
+			       u32 val)
+{
+	writel(val, ks_pcie->va_app_base + offset);
+}
+
+static void ks_pcie_msi_irq_ack(struct irq_data *data)
+{
+	struct pcie_port *pp  = irq_data_get_irq_chip_data(data);
+	struct keystone_pcie *ks_pcie;
+	u32 irq = data->hwirq;
+	struct dw_pcie *pci;
+	u32 reg_offset;
+	u32 bit_pos;
+
+	pci = to_dw_pcie_from_pp(pp);
+	ks_pcie = to_keystone_pcie(pci);
+
+	reg_offset = irq % 8;
+	bit_pos = irq >> 3;
+
+	ks_pcie_app_writel(ks_pcie, MSI_IRQ_STATUS(reg_offset),
+			   BIT(bit_pos));
+	ks_pcie_app_writel(ks_pcie, IRQ_EOI, reg_offset + MSI_IRQ_OFFSET);
+}
+
+static void ks_pcie_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	struct pcie_port *pp = irq_data_get_irq_chip_data(data);
+	struct keystone_pcie *ks_pcie;
+	struct dw_pcie *pci;
+	u64 msi_target;
+
+	pci = to_dw_pcie_from_pp(pp);
+	ks_pcie = to_keystone_pcie(pci);
+
+	msi_target = ks_pcie->app.start + MSI_IRQ;
+	msg->address_lo = lower_32_bits(msi_target);
+	msg->address_hi = upper_32_bits(msi_target);
+	msg->data = data->hwirq;
+
+	dev_dbg(pci->dev, "msi#%d address_hi %#x address_lo %#x\n",
+		(int)data->hwirq, msg->address_hi, msg->address_lo);
+}
+
+static int ks_pcie_msi_set_affinity(struct irq_data *irq_data,
+				    const struct cpumask *mask, bool force)
+{
+	return -EINVAL;
+}
+
+static void ks_pcie_msi_mask(struct irq_data *data)
+{
+	struct pcie_port *pp = irq_data_get_irq_chip_data(data);
+	struct keystone_pcie *ks_pcie;
+	u32 irq = data->hwirq;
+	struct dw_pcie *pci;
+	unsigned long flags;
+	u32 reg_offset;
+	u32 bit_pos;
+
+	raw_spin_lock_irqsave(&pp->lock, flags);
+
+	pci = to_dw_pcie_from_pp(pp);
+	ks_pcie = to_keystone_pcie(pci);
+
+	reg_offset = irq % 8;
+	bit_pos = irq >> 3;
+
+	ks_pcie_app_writel(ks_pcie, MSI_IRQ_ENABLE_CLR(reg_offset),
+			   BIT(bit_pos));
+
+	raw_spin_unlock_irqrestore(&pp->lock, flags);
+}
+
+static void ks_pcie_msi_unmask(struct irq_data *data)
+{
+	struct pcie_port *pp = irq_data_get_irq_chip_data(data);
+	struct keystone_pcie *ks_pcie;
+	u32 irq = data->hwirq;
+	struct dw_pcie *pci;
+	unsigned long flags;
+	u32 reg_offset;
+	u32 bit_pos;
+
+	raw_spin_lock_irqsave(&pp->lock, flags);
+
+	pci = to_dw_pcie_from_pp(pp);
+	ks_pcie = to_keystone_pcie(pci);
+
+	reg_offset = irq % 8;
+	bit_pos = irq >> 3;
+
+	ks_pcie_app_writel(ks_pcie, MSI_IRQ_ENABLE_SET(reg_offset),
+			   BIT(bit_pos));
+
+	raw_spin_unlock_irqrestore(&pp->lock, flags);
+}
+
+static struct irq_chip ks_pcie_msi_irq_chip = {
+	.name = "KEYSTONE-PCI-MSI",
+	.irq_ack = ks_pcie_msi_irq_ack,
+	.irq_compose_msi_msg = ks_pcie_compose_msi_msg,
+	.irq_set_affinity = ks_pcie_msi_set_affinity,
+	.irq_mask = ks_pcie_msi_mask,
+	.irq_unmask = ks_pcie_msi_unmask,
+};
+
+static int ks_pcie_msi_host_init(struct pcie_port *pp)
+{
+	pp->msi_irq_chip = &ks_pcie_msi_irq_chip;
+	return dw_pcie_allocate_domains(pp);
+}
+
+static void ks_pcie_handle_legacy_irq(struct keystone_pcie *ks_pcie,
+				      int offset)
+{
+	struct dw_pcie *pci = ks_pcie->pci;
+	struct device *dev = pci->dev;
+	u32 pending;
+	int virq;
+
+	pending = ks_pcie_app_readl(ks_pcie, IRQ_STATUS(offset));
+
+	if (BIT(0) & pending) {
+		virq = irq_linear_revmap(ks_pcie->legacy_irq_domain, offset);
+		dev_dbg(dev, ": irq: irq_offset %d, virq %d\n", offset, virq);
+		generic_handle_irq(virq);
+	}
+
+	/* EOI the INTx interrupt */
+	ks_pcie_app_writel(ks_pcie, IRQ_EOI, offset);
+}
+
+/*
+ * Dummy function so that DW core doesn't configure MSI
+ */
+static int ks_pcie_am654_msi_host_init(struct pcie_port *pp)
+{
+	return 0;
+}
+
+static void ks_pcie_enable_error_irq(struct keystone_pcie *ks_pcie)
+{
+	ks_pcie_app_writel(ks_pcie, ERR_IRQ_ENABLE_SET, ERR_IRQ_ALL);
+}
+
+static irqreturn_t ks_pcie_handle_error_irq(struct keystone_pcie *ks_pcie)
+{
+	u32 reg;
+	struct device *dev = ks_pcie->pci->dev;
+
+	reg = ks_pcie_app_readl(ks_pcie, ERR_IRQ_STATUS);
+	if (!reg)
+		return IRQ_NONE;
+
+	if (reg & ERR_SYS)
+		dev_err(dev, "System Error\n");
+
+	if (reg & ERR_FATAL)
+		dev_err(dev, "Fatal Error\n");
+
+	if (reg & ERR_NONFATAL)
+		dev_dbg(dev, "Non Fatal Error\n");
+
+	if (reg & ERR_CORR)
+		dev_dbg(dev, "Correctable Error\n");
+
+	if (!ks_pcie->is_am6 && (reg & ERR_AXI))
+		dev_err(dev, "AXI tag lookup fatal Error\n");
+
+	if (reg & ERR_AER || (ks_pcie->is_am6 && (reg & AM6_ERR_AER)))
+		dev_err(dev, "ECRC Error\n");
+
+	ks_pcie_app_writel(ks_pcie, ERR_IRQ_STATUS, reg);
+
+	return IRQ_HANDLED;
+}
+
+static void ks_pcie_ack_legacy_irq(struct irq_data *d)
+{
+}
+
+static void ks_pcie_mask_legacy_irq(struct irq_data *d)
+{
+}
+
+static void ks_pcie_unmask_legacy_irq(struct irq_data *d)
+{
+}
+
+static struct irq_chip ks_pcie_legacy_irq_chip = {
+	.name = "Keystone-PCI-Legacy-IRQ",
+	.irq_ack = ks_pcie_ack_legacy_irq,
+	.irq_mask = ks_pcie_mask_legacy_irq,
+	.irq_unmask = ks_pcie_unmask_legacy_irq,
+};
+
+static int ks_pcie_init_legacy_irq_map(struct irq_domain *d,
+				       unsigned int irq,
+				       irq_hw_number_t hw_irq)
+{
+	irq_set_chip_and_handler(irq, &ks_pcie_legacy_irq_chip,
+				 handle_level_irq);
+	irq_set_chip_data(irq, d->host_data);
+
+	return 0;
+}
+
+static const struct irq_domain_ops ks_pcie_legacy_irq_domain_ops = {
+	.map = ks_pcie_init_legacy_irq_map,
+	.xlate = irq_domain_xlate_onetwocell,
+};
+
+/**
+ * ks_pcie_set_dbi_mode() - Set DBI mode to access overlaid BAR mask
+ * registers
+ *
+ * Since modification of dbi_cs2 involves different clock domain, read the
+ * status back to ensure the transition is complete.
+ */
+static void ks_pcie_set_dbi_mode(struct keystone_pcie *ks_pcie)
+{
+	u32 val;
+
+	val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
+	val |= DBI_CS2;
+	ks_pcie_app_writel(ks_pcie, CMD_STATUS, val);
+
+	do {
+		val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
+	} while (!(val & DBI_CS2));
+}
+
+/**
+ * ks_pcie_clear_dbi_mode() - Disable DBI mode
+ *
+ * Since modification of dbi_cs2 involves different clock domain, read the
+ * status back to ensure the transition is complete.
+ */
+static void ks_pcie_clear_dbi_mode(struct keystone_pcie *ks_pcie)
+{
+	u32 val;
+
+	val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
+	val &= ~DBI_CS2;
+	ks_pcie_app_writel(ks_pcie, CMD_STATUS, val);
+
+	do {
+		val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
+	} while (val & DBI_CS2);
+}
+
+static void ks_pcie_setup_rc_app_regs(struct keystone_pcie *ks_pcie)
+{
+	u32 val;
+	u32 num_viewport = ks_pcie->num_viewport;
+	struct dw_pcie *pci = ks_pcie->pci;
+	struct pcie_port *pp = &pci->pp;
+	u64 start = pp->mem->start;
+	u64 end = pp->mem->end;
+	int i;
+
+	/* Disable BARs for inbound access */
+	ks_pcie_set_dbi_mode(ks_pcie);
+	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 0);
+	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_1, 0);
+	ks_pcie_clear_dbi_mode(ks_pcie);
+
+	if (ks_pcie->is_am6)
+		return;
+
+	val = ilog2(OB_WIN_SIZE);
+	ks_pcie_app_writel(ks_pcie, OB_SIZE, val);
+
+	/* Using Direct 1:1 mapping of RC <-> PCI memory space */
+	for (i = 0; i < num_viewport && (start < end); i++) {
+		ks_pcie_app_writel(ks_pcie, OB_OFFSET_INDEX(i),
+				   lower_32_bits(start) | OB_ENABLEN);
+		ks_pcie_app_writel(ks_pcie, OB_OFFSET_HI(i),
+				   upper_32_bits(start));
+		start += OB_WIN_SIZE;
+	}
+
+	val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
+	val |= OB_XLAT_EN_VAL;
+	ks_pcie_app_writel(ks_pcie, CMD_STATUS, val);
+}
+
+static int ks_pcie_rd_other_conf(struct pcie_port *pp, struct pci_bus *bus,
+				 unsigned int devfn, int where, int size,
+				 u32 *val)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
+	u32 reg;
+
+	reg = CFG_BUS(bus->number) | CFG_DEVICE(PCI_SLOT(devfn)) |
+		CFG_FUNC(PCI_FUNC(devfn));
+	if (bus->parent->number != pp->root_bus_nr)
+		reg |= CFG_TYPE1;
+	ks_pcie_app_writel(ks_pcie, CFG_SETUP, reg);
+
+	return dw_pcie_read(pp->va_cfg0_base + where, size, val);
+}
+
+static int ks_pcie_wr_other_conf(struct pcie_port *pp, struct pci_bus *bus,
+				 unsigned int devfn, int where, int size,
+				 u32 val)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
+	u32 reg;
+
+	reg = CFG_BUS(bus->number) | CFG_DEVICE(PCI_SLOT(devfn)) |
+		CFG_FUNC(PCI_FUNC(devfn));
+	if (bus->parent->number != pp->root_bus_nr)
+		reg |= CFG_TYPE1;
+	ks_pcie_app_writel(ks_pcie, CFG_SETUP, reg);
+
+	return dw_pcie_write(pp->va_cfg0_base + where, size, val);
+}
+
+/**
+ * ks_pcie_v3_65_scan_bus() - keystone scan_bus post initialization
+ *
+ * This sets BAR0 to enable inbound access for MSI_IRQ register
+ */
+static void ks_pcie_v3_65_scan_bus(struct pcie_port *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
+
+	/* Configure and set up BAR0 */
+	ks_pcie_set_dbi_mode(ks_pcie);
+
+	/* Enable BAR0 */
+	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 1);
+	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, SZ_4K - 1);
+
+	ks_pcie_clear_dbi_mode(ks_pcie);
+
+	 /*
+	  * For BAR0, just setting bus address for inbound writes (MSI) should
+	  * be sufficient.  Use physical address to avoid any conflicts.
+	  */
+	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, ks_pcie->app.start);
+}
+
+/**
+ * ks_pcie_link_up() - Check if link up
+ */
+static int ks_pcie_link_up(struct dw_pcie *pci)
+{
+	u32 val;
+
+	val = dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG0);
+	val &= PORT_LOGIC_LTSSM_STATE_MASK;
+	return (val == PORT_LOGIC_LTSSM_STATE_L0);
+}
+
+static void ks_pcie_stop_link(struct dw_pcie *pci)
+{
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
+	u32 val;
+
+	/* Disable Link training */
+	val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
+	val &= ~LTSSM_EN_VAL;
+	ks_pcie_app_writel(ks_pcie, CMD_STATUS, LTSSM_EN_VAL | val);
+}
+
+static int ks_pcie_start_link(struct dw_pcie *pci)
+{
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
+	struct device *dev = pci->dev;
+	u32 val;
+
+	if (dw_pcie_link_up(pci)) {
+		dev_dbg(dev, "link is already up\n");
+		return 0;
+	}
+
+	/* Initiate Link Training */
+	val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
+	ks_pcie_app_writel(ks_pcie, CMD_STATUS, LTSSM_EN_VAL | val);
+
+	return 0;
+}
+
+static void ks_pcie_quirk(struct pci_dev *dev)
 {
 	struct pci_bus *bus = dev->bus;
-	struct pci_dev *bridge = bus->self;
+	struct pci_dev *bridge;
 	static const struct pci_device_id rc_pci_devids[] = {
 		{ PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2HK),
 		 .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, },
@@ -50,11 +542,13 @@
 		 .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, },
 		{ PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2L),
 		 .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, },
+		{ PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2G),
+		 .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, },
 		{ 0, },
 	};
 
 	if (pci_is_root_bus(bus))
-		return;
+		bridge = dev;
 
 	/* look for the host bridge */
 	while (!pci_is_root_bus(bus)) {
@@ -62,56 +556,34 @@
 		bus = bus->parent;
 	}
 
-	if (bridge) {
-		/*
-		 * Keystone PCI controller has a h/w limitation of
-		 * 256 bytes maximum read request size.  It can't handle
-		 * anything higher than this.  So force this limit on
-		 * all downstream devices.
-		 */
-		if (pci_match_id(rc_pci_devids, bridge)) {
-			if (pcie_get_readrq(dev) > 256) {
-				dev_info(&dev->dev, "limiting MRRS to 256\n");
-				pcie_set_readrq(dev, 256);
-			}
+	if (!bridge)
+		return;
+
+	/*
+	 * Keystone PCI controller has a h/w limitation of
+	 * 256 bytes maximum read request size.  It can't handle
+	 * anything higher than this.  So force this limit on
+	 * all downstream devices.
+	 */
+	if (pci_match_id(rc_pci_devids, bridge)) {
+		if (pcie_get_readrq(dev) > 256) {
+			dev_info(&dev->dev, "limiting MRRS to 256\n");
+			pcie_set_readrq(dev, 256);
 		}
 	}
 }
-DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, quirk_limit_mrrs);
-
-static int ks_pcie_establish_link(struct keystone_pcie *ks_pcie)
-{
-	struct dw_pcie *pci = ks_pcie->pci;
-	struct pcie_port *pp = &pci->pp;
-	struct device *dev = pci->dev;
-	unsigned int retries;
-
-	dw_pcie_setup_rc(pp);
-
-	if (dw_pcie_link_up(pci)) {
-		dev_info(dev, "Link already up\n");
-		return 0;
-	}
-
-	/* check if the link is up or not */
-	for (retries = 0; retries < 5; retries++) {
-		ks_dw_pcie_initiate_link_train(ks_pcie);
-		if (!dw_pcie_wait_for_link(pci))
-			return 0;
-	}
-
-	dev_err(dev, "phy link never came up\n");
-	return -ETIMEDOUT;
-}
+DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, ks_pcie_quirk);
 
 static void ks_pcie_msi_irq_handler(struct irq_desc *desc)
 {
-	unsigned int irq = irq_desc_get_irq(desc);
+	unsigned int irq = desc->irq_data.hwirq;
 	struct keystone_pcie *ks_pcie = irq_desc_get_handler_data(desc);
-	u32 offset = irq - ks_pcie->msi_host_irqs[0];
+	u32 offset = irq - ks_pcie->msi_host_irq;
 	struct dw_pcie *pci = ks_pcie->pci;
+	struct pcie_port *pp = &pci->pp;
 	struct device *dev = pci->dev;
 	struct irq_chip *chip = irq_desc_get_chip(desc);
+	u32 vector, virq, reg, pos;
 
 	dev_dbg(dev, "%s, irq %d\n", __func__, irq);
 
@@ -121,7 +593,23 @@
 	 * ack operation.
 	 */
 	chained_irq_enter(chip, desc);
-	ks_dw_pcie_handle_msi_irq(ks_pcie, offset);
+
+	reg = ks_pcie_app_readl(ks_pcie, MSI_IRQ_STATUS(offset));
+	/*
+	 * MSI0 status bit 0-3 shows vectors 0, 8, 16, 24, MSI1 status bit
+	 * shows 1, 9, 17, 25 and so forth
+	 */
+	for (pos = 0; pos < 4; pos++) {
+		if (!(reg & BIT(pos)))
+			continue;
+
+		vector = offset + (pos << 3);
+		virq = irq_linear_revmap(pp->irq_domain, vector);
+		dev_dbg(dev, "irq: bit %d, vector %d, virq %d\n", pos, vector,
+			virq);
+		generic_handle_irq(virq);
+	}
+
 	chained_irq_exit(chip, desc);
 }
 
@@ -150,100 +638,130 @@
 	 * ack operation.
 	 */
 	chained_irq_enter(chip, desc);
-	ks_dw_pcie_handle_legacy_irq(ks_pcie, irq_offset);
+	ks_pcie_handle_legacy_irq(ks_pcie, irq_offset);
 	chained_irq_exit(chip, desc);
 }
 
-static int ks_pcie_get_irq_controller_info(struct keystone_pcie *ks_pcie,
-					   char *controller, int *num_irqs)
+static int ks_pcie_config_msi_irq(struct keystone_pcie *ks_pcie)
 {
-	int temp, max_host_irqs, legacy = 1, *host_irqs;
 	struct device *dev = ks_pcie->pci->dev;
-	struct device_node *np_pcie = dev->of_node, **np_temp;
+	struct device_node *np = ks_pcie->np;
+	struct device_node *intc_np;
+	struct irq_data *irq_data;
+	int irq_count, irq, ret, i;
 
-	if (!strcmp(controller, "msi-interrupt-controller"))
-		legacy = 0;
-
-	if (legacy) {
-		np_temp = &ks_pcie->legacy_intc_np;
-		max_host_irqs = PCI_NUM_INTX;
-		host_irqs = &ks_pcie->legacy_host_irqs[0];
-	} else {
-		np_temp = &ks_pcie->msi_intc_np;
-		max_host_irqs = MAX_MSI_HOST_IRQS;
-		host_irqs =  &ks_pcie->msi_host_irqs[0];
-	}
-
-	/* interrupt controller is in a child node */
-	*np_temp = of_get_child_by_name(np_pcie, controller);
-	if (!(*np_temp)) {
-		dev_err(dev, "Node for %s is absent\n", controller);
-		return -EINVAL;
-	}
-
-	temp = of_irq_count(*np_temp);
-	if (!temp) {
-		dev_err(dev, "No IRQ entries in %s\n", controller);
-		of_node_put(*np_temp);
-		return -EINVAL;
-	}
-
-	if (temp > max_host_irqs)
-		dev_warn(dev, "Too many %s interrupts defined %u\n",
-			(legacy ? "legacy" : "MSI"), temp);
-
-	/*
-	 * support upto max_host_irqs. In dt from index 0 to 3 (legacy) or 0 to
-	 * 7 (MSI)
-	 */
-	for (temp = 0; temp < max_host_irqs; temp++) {
-		host_irqs[temp] = irq_of_parse_and_map(*np_temp, temp);
-		if (!host_irqs[temp])
-			break;
-	}
-
-	of_node_put(*np_temp);
-
-	if (temp) {
-		*num_irqs = temp;
+	if (!IS_ENABLED(CONFIG_PCI_MSI))
 		return 0;
+
+	intc_np = of_get_child_by_name(np, "msi-interrupt-controller");
+	if (!intc_np) {
+		if (ks_pcie->is_am6)
+			return 0;
+		dev_warn(dev, "msi-interrupt-controller node is absent\n");
+		return -EINVAL;
 	}
 
-	return -EINVAL;
+	irq_count = of_irq_count(intc_np);
+	if (!irq_count) {
+		dev_err(dev, "No IRQ entries in msi-interrupt-controller\n");
+		ret = -EINVAL;
+		goto err;
+	}
+
+	for (i = 0; i < irq_count; i++) {
+		irq = irq_of_parse_and_map(intc_np, i);
+		if (!irq) {
+			ret = -EINVAL;
+			goto err;
+		}
+
+		if (!ks_pcie->msi_host_irq) {
+			irq_data = irq_get_irq_data(irq);
+			if (!irq_data) {
+				ret = -EINVAL;
+				goto err;
+			}
+			ks_pcie->msi_host_irq = irq_data->hwirq;
+		}
+
+		irq_set_chained_handler_and_data(irq, ks_pcie_msi_irq_handler,
+						 ks_pcie);
+	}
+
+	of_node_put(intc_np);
+	return 0;
+
+err:
+	of_node_put(intc_np);
+	return ret;
 }
 
-static void ks_pcie_setup_interrupts(struct keystone_pcie *ks_pcie)
+static int ks_pcie_config_legacy_irq(struct keystone_pcie *ks_pcie)
 {
-	int i;
+	struct device *dev = ks_pcie->pci->dev;
+	struct irq_domain *legacy_irq_domain;
+	struct device_node *np = ks_pcie->np;
+	struct device_node *intc_np;
+	int irq_count, irq, ret = 0, i;
 
-	/* Legacy IRQ */
-	for (i = 0; i < ks_pcie->num_legacy_host_irqs; i++) {
-		irq_set_chained_handler_and_data(ks_pcie->legacy_host_irqs[i],
+	intc_np = of_get_child_by_name(np, "legacy-interrupt-controller");
+	if (!intc_np) {
+		/*
+		 * Since legacy interrupts are modeled as edge-interrupts in
+		 * AM6, keep it disabled for now.
+		 */
+		if (ks_pcie->is_am6)
+			return 0;
+		dev_warn(dev, "legacy-interrupt-controller node is absent\n");
+		return -EINVAL;
+	}
+
+	irq_count = of_irq_count(intc_np);
+	if (!irq_count) {
+		dev_err(dev, "No IRQ entries in legacy-interrupt-controller\n");
+		ret = -EINVAL;
+		goto err;
+	}
+
+	for (i = 0; i < irq_count; i++) {
+		irq = irq_of_parse_and_map(intc_np, i);
+		if (!irq) {
+			ret = -EINVAL;
+			goto err;
+		}
+		ks_pcie->legacy_host_irqs[i] = irq;
+
+		irq_set_chained_handler_and_data(irq,
 						 ks_pcie_legacy_irq_handler,
 						 ks_pcie);
 	}
-	ks_dw_pcie_enable_legacy_irqs(ks_pcie);
 
-	/* MSI IRQ */
-	if (IS_ENABLED(CONFIG_PCI_MSI)) {
-		for (i = 0; i < ks_pcie->num_msi_host_irqs; i++) {
-			irq_set_chained_handler_and_data(ks_pcie->msi_host_irqs[i],
-							 ks_pcie_msi_irq_handler,
-							 ks_pcie);
-		}
+	legacy_irq_domain =
+		irq_domain_add_linear(intc_np, PCI_NUM_INTX,
+				      &ks_pcie_legacy_irq_domain_ops, NULL);
+	if (!legacy_irq_domain) {
+		dev_err(dev, "Failed to add irq domain for legacy irqs\n");
+		ret = -EINVAL;
+		goto err;
 	}
+	ks_pcie->legacy_irq_domain = legacy_irq_domain;
 
-	if (ks_pcie->error_irq > 0)
-		ks_dw_pcie_enable_error_irq(ks_pcie);
+	for (i = 0; i < PCI_NUM_INTX; i++)
+		ks_pcie_app_writel(ks_pcie, IRQ_ENABLE_SET(i), INTx_EN);
+
+err:
+	of_node_put(intc_np);
+	return ret;
 }
 
+#ifdef CONFIG_ARM
 /*
  * When a PCI device does not exist during config cycles, keystone host gets a
  * bus error instead of returning 0xffffffff. This handler always returns 0
  * for this kind of faults.
  */
-static int keystone_pcie_fault(unsigned long addr, unsigned int fsr,
-				struct pt_regs *regs)
+static int ks_pcie_fault(unsigned long addr, unsigned int fsr,
+			 struct pt_regs *regs)
 {
 	unsigned long instr = *(unsigned long *) instruction_pointer(regs);
 
@@ -256,99 +774,110 @@
 
 	return 0;
 }
+#endif
+
+static int __init ks_pcie_init_id(struct keystone_pcie *ks_pcie)
+{
+	int ret;
+	unsigned int id;
+	struct regmap *devctrl_regs;
+	struct dw_pcie *pci = ks_pcie->pci;
+	struct device *dev = pci->dev;
+	struct device_node *np = dev->of_node;
+
+	devctrl_regs = syscon_regmap_lookup_by_phandle(np, "ti,syscon-pcie-id");
+	if (IS_ERR(devctrl_regs))
+		return PTR_ERR(devctrl_regs);
+
+	ret = regmap_read(devctrl_regs, 0, &id);
+	if (ret)
+		return ret;
+
+	dw_pcie_dbi_ro_wr_en(pci);
+	dw_pcie_writew_dbi(pci, PCI_VENDOR_ID, id & PCIE_VENDORID_MASK);
+	dw_pcie_writew_dbi(pci, PCI_DEVICE_ID, id >> PCIE_DEVICEID_SHIFT);
+	dw_pcie_dbi_ro_wr_dis(pci);
+
+	return 0;
+}
 
 static int __init ks_pcie_host_init(struct pcie_port *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
-	u32 val;
+	int ret;
 
-	ks_pcie_establish_link(ks_pcie);
-	ks_dw_pcie_setup_rc_app_regs(ks_pcie);
-	ks_pcie_setup_interrupts(ks_pcie);
+	ret = ks_pcie_config_legacy_irq(ks_pcie);
+	if (ret)
+		return ret;
+
+	ret = ks_pcie_config_msi_irq(ks_pcie);
+	if (ret)
+		return ret;
+
+	dw_pcie_setup_rc(pp);
+
+	ks_pcie_stop_link(pci);
+	ks_pcie_setup_rc_app_regs(ks_pcie);
 	writew(PCI_IO_RANGE_TYPE_32 | (PCI_IO_RANGE_TYPE_32 << 8),
 			pci->dbi_base + PCI_IO_BASE);
 
-	/* update the Vendor ID */
-	writew(ks_pcie->device_id, pci->dbi_base + PCI_DEVICE_ID);
+	ret = ks_pcie_init_id(ks_pcie);
+	if (ret < 0)
+		return ret;
 
-	/* update the DEV_STAT_CTRL to publish right mrrs */
-	val = readl(pci->dbi_base + PCIE_CAP_BASE + PCI_EXP_DEVCTL);
-	val &= ~PCI_EXP_DEVCTL_READRQ;
-	/* set the mrrs to 256 bytes */
-	val |= BIT(12);
-	writel(val, pci->dbi_base + PCIE_CAP_BASE + PCI_EXP_DEVCTL);
-
+#ifdef CONFIG_ARM
 	/*
 	 * PCIe access errors that result into OCP errors are caught by ARM as
 	 * "External aborts"
 	 */
-	hook_fault_code(17, keystone_pcie_fault, SIGBUS, 0,
+	hook_fault_code(17, ks_pcie_fault, SIGBUS, 0,
 			"Asynchronous external abort");
+#endif
+
+	ks_pcie_start_link(pci);
+	dw_pcie_wait_for_link(pci);
 
 	return 0;
 }
 
-static const struct dw_pcie_host_ops keystone_pcie_host_ops = {
-	.rd_other_conf = ks_dw_pcie_rd_other_conf,
-	.wr_other_conf = ks_dw_pcie_wr_other_conf,
+static const struct dw_pcie_host_ops ks_pcie_host_ops = {
+	.rd_other_conf = ks_pcie_rd_other_conf,
+	.wr_other_conf = ks_pcie_wr_other_conf,
 	.host_init = ks_pcie_host_init,
-	.msi_set_irq = ks_dw_pcie_msi_set_irq,
-	.msi_clear_irq = ks_dw_pcie_msi_clear_irq,
-	.get_msi_addr = ks_dw_pcie_get_msi_addr,
-	.msi_host_init = ks_dw_pcie_msi_host_init,
-	.msi_irq_ack = ks_dw_pcie_msi_irq_ack,
-	.scan_bus = ks_dw_pcie_v3_65_scan_bus,
+	.msi_host_init = ks_pcie_msi_host_init,
+	.scan_bus = ks_pcie_v3_65_scan_bus,
 };
 
-static irqreturn_t pcie_err_irq_handler(int irq, void *priv)
+static const struct dw_pcie_host_ops ks_pcie_am654_host_ops = {
+	.host_init = ks_pcie_host_init,
+	.msi_host_init = ks_pcie_am654_msi_host_init,
+};
+
+static irqreturn_t ks_pcie_err_irq_handler(int irq, void *priv)
 {
 	struct keystone_pcie *ks_pcie = priv;
 
-	return ks_dw_pcie_handle_error_irq(ks_pcie);
+	return ks_pcie_handle_error_irq(ks_pcie);
 }
 
-static int __init ks_add_pcie_port(struct keystone_pcie *ks_pcie,
-			 struct platform_device *pdev)
+static int __init ks_pcie_add_pcie_port(struct keystone_pcie *ks_pcie,
+					struct platform_device *pdev)
 {
 	struct dw_pcie *pci = ks_pcie->pci;
 	struct pcie_port *pp = &pci->pp;
 	struct device *dev = &pdev->dev;
+	struct resource *res;
 	int ret;
 
-	ret = ks_pcie_get_irq_controller_info(ks_pcie,
-					"legacy-interrupt-controller",
-					&ks_pcie->num_legacy_host_irqs);
-	if (ret)
-		return ret;
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "config");
+	pp->va_cfg0_base = devm_pci_remap_cfg_resource(dev, res);
+	if (IS_ERR(pp->va_cfg0_base))
+		return PTR_ERR(pp->va_cfg0_base);
 
-	if (IS_ENABLED(CONFIG_PCI_MSI)) {
-		ret = ks_pcie_get_irq_controller_info(ks_pcie,
-						"msi-interrupt-controller",
-						&ks_pcie->num_msi_host_irqs);
-		if (ret)
-			return ret;
-	}
+	pp->va_cfg1_base = pp->va_cfg0_base;
 
-	/*
-	 * 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(dev, "no error IRQ defined\n");
-	else {
-		ret = request_irq(ks_pcie->error_irq, pcie_err_irq_handler,
-				  IRQF_SHARED, "pcie-error-irq", ks_pcie);
-		if (ret < 0) {
-			dev_err(dev, "failed to request error IRQ %d\n",
-				ks_pcie->error_irq);
-			return ret;
-		}
-	}
-
-	pp->ops = &keystone_pcie_host_ops;
-	ret = ks_dw_pcie_host_init(ks_pcie, ks_pcie->msi_intc_np);
+	ret = dw_pcie_host_init(pp);
 	if (ret) {
 		dev_err(dev, "failed to initialize host\n");
 		return ret;
@@ -357,36 +886,336 @@
 	return 0;
 }
 
-static const struct of_device_id ks_pcie_of_match[] = {
-	{
-		.type = "pci",
-		.compatible = "ti,keystone-pcie",
-	},
-	{ },
-};
-
-static const struct dw_pcie_ops dw_pcie_ops = {
-	.link_up = ks_dw_pcie_link_up,
-};
-
-static int __exit ks_pcie_remove(struct platform_device *pdev)
+static u32 ks_pcie_am654_read_dbi2(struct dw_pcie *pci, void __iomem *base,
+				   u32 reg, size_t size)
 {
-	struct keystone_pcie *ks_pcie = platform_get_drvdata(pdev);
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
+	u32 val;
 
-	clk_disable_unprepare(ks_pcie->clk);
+	ks_pcie_set_dbi_mode(ks_pcie);
+	dw_pcie_read(base + reg, size, &val);
+	ks_pcie_clear_dbi_mode(ks_pcie);
+	return val;
+}
+
+static void ks_pcie_am654_write_dbi2(struct dw_pcie *pci, void __iomem *base,
+				     u32 reg, size_t size, u32 val)
+{
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
+
+	ks_pcie_set_dbi_mode(ks_pcie);
+	dw_pcie_write(base + reg, size, val);
+	ks_pcie_clear_dbi_mode(ks_pcie);
+}
+
+static const struct dw_pcie_ops ks_pcie_dw_pcie_ops = {
+	.start_link = ks_pcie_start_link,
+	.stop_link = ks_pcie_stop_link,
+	.link_up = ks_pcie_link_up,
+	.read_dbi2 = ks_pcie_am654_read_dbi2,
+	.write_dbi2 = ks_pcie_am654_write_dbi2,
+};
+
+static void ks_pcie_am654_ep_init(struct dw_pcie_ep *ep)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	int flags;
+
+	ep->page_size = AM654_WIN_SIZE;
+	flags = PCI_BASE_ADDRESS_SPACE_MEMORY | PCI_BASE_ADDRESS_MEM_TYPE_32;
+	dw_pcie_writel_dbi2(pci, PCI_BASE_ADDRESS_0, APP_ADDR_SPACE_0 - 1);
+	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, flags);
+}
+
+static void ks_pcie_am654_raise_legacy_irq(struct keystone_pcie *ks_pcie)
+{
+	struct dw_pcie *pci = ks_pcie->pci;
+	u8 int_pin;
+
+	int_pin = dw_pcie_readb_dbi(pci, PCI_INTERRUPT_PIN);
+	if (int_pin == 0 || int_pin > 4)
+		return;
+
+	ks_pcie_app_writel(ks_pcie, PCIE_LEGACY_IRQ_ENABLE_SET(int_pin),
+			   INT_ENABLE);
+	ks_pcie_app_writel(ks_pcie, PCIE_EP_IRQ_SET, INT_ENABLE);
+	mdelay(1);
+	ks_pcie_app_writel(ks_pcie, PCIE_EP_IRQ_CLR, INT_ENABLE);
+	ks_pcie_app_writel(ks_pcie, PCIE_LEGACY_IRQ_ENABLE_CLR(int_pin),
+			   INT_ENABLE);
+}
+
+static int ks_pcie_am654_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
+				   enum pci_epc_irq_type type,
+				   u16 interrupt_num)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
+
+	switch (type) {
+	case PCI_EPC_IRQ_LEGACY:
+		ks_pcie_am654_raise_legacy_irq(ks_pcie);
+		break;
+	case PCI_EPC_IRQ_MSI:
+		dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
+		break;
+	default:
+		dev_err(pci->dev, "UNKNOWN IRQ type\n");
+		return -EINVAL;
+	}
 
 	return 0;
 }
 
+static const struct pci_epc_features ks_pcie_am654_epc_features = {
+	.linkup_notifier = false,
+	.msi_capable = true,
+	.msix_capable = false,
+	.reserved_bar = 1 << BAR_0 | 1 << BAR_1,
+	.bar_fixed_64bit = 1 << BAR_0,
+	.bar_fixed_size[2] = SZ_1M,
+	.bar_fixed_size[3] = SZ_64K,
+	.bar_fixed_size[4] = 256,
+	.bar_fixed_size[5] = SZ_1M,
+	.align = SZ_1M,
+};
+
+static const struct pci_epc_features*
+ks_pcie_am654_get_features(struct dw_pcie_ep *ep)
+{
+	return &ks_pcie_am654_epc_features;
+}
+
+static const struct dw_pcie_ep_ops ks_pcie_am654_ep_ops = {
+	.ep_init = ks_pcie_am654_ep_init,
+	.raise_irq = ks_pcie_am654_raise_irq,
+	.get_features = &ks_pcie_am654_get_features,
+};
+
+static int __init ks_pcie_add_pcie_ep(struct keystone_pcie *ks_pcie,
+				      struct platform_device *pdev)
+{
+	int ret;
+	struct dw_pcie_ep *ep;
+	struct resource *res;
+	struct device *dev = &pdev->dev;
+	struct dw_pcie *pci = ks_pcie->pci;
+
+	ep = &pci->ep;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "addr_space");
+	if (!res)
+		return -EINVAL;
+
+	ep->phys_base = res->start;
+	ep->addr_size = resource_size(res);
+
+	ret = dw_pcie_ep_init(ep);
+	if (ret) {
+		dev_err(dev, "failed to initialize endpoint\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static void ks_pcie_disable_phy(struct keystone_pcie *ks_pcie)
+{
+	int num_lanes = ks_pcie->num_lanes;
+
+	while (num_lanes--) {
+		phy_power_off(ks_pcie->phy[num_lanes]);
+		phy_exit(ks_pcie->phy[num_lanes]);
+	}
+}
+
+static int ks_pcie_enable_phy(struct keystone_pcie *ks_pcie)
+{
+	int i;
+	int ret;
+	int num_lanes = ks_pcie->num_lanes;
+
+	for (i = 0; i < num_lanes; i++) {
+		ret = phy_reset(ks_pcie->phy[i]);
+		if (ret < 0)
+			goto err_phy;
+
+		ret = phy_init(ks_pcie->phy[i]);
+		if (ret < 0)
+			goto err_phy;
+
+		ret = phy_power_on(ks_pcie->phy[i]);
+		if (ret < 0) {
+			phy_exit(ks_pcie->phy[i]);
+			goto err_phy;
+		}
+	}
+
+	return 0;
+
+err_phy:
+	while (--i >= 0) {
+		phy_power_off(ks_pcie->phy[i]);
+		phy_exit(ks_pcie->phy[i]);
+	}
+
+	return ret;
+}
+
+static int ks_pcie_set_mode(struct device *dev)
+{
+	struct device_node *np = dev->of_node;
+	struct regmap *syscon;
+	u32 val;
+	u32 mask;
+	int ret = 0;
+
+	syscon = syscon_regmap_lookup_by_phandle(np, "ti,syscon-pcie-mode");
+	if (IS_ERR(syscon))
+		return 0;
+
+	mask = KS_PCIE_DEV_TYPE_MASK | KS_PCIE_SYSCLOCKOUTEN;
+	val = KS_PCIE_DEV_TYPE(RC) | KS_PCIE_SYSCLOCKOUTEN;
+
+	ret = regmap_update_bits(syscon, 0, mask, val);
+	if (ret) {
+		dev_err(dev, "failed to set pcie mode\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int ks_pcie_am654_set_mode(struct device *dev,
+				  enum dw_pcie_device_mode mode)
+{
+	struct device_node *np = dev->of_node;
+	struct regmap *syscon;
+	u32 val;
+	u32 mask;
+	int ret = 0;
+
+	syscon = syscon_regmap_lookup_by_phandle(np, "ti,syscon-pcie-mode");
+	if (IS_ERR(syscon))
+		return 0;
+
+	mask = AM654_PCIE_DEV_TYPE_MASK;
+
+	switch (mode) {
+	case DW_PCIE_RC_TYPE:
+		val = RC;
+		break;
+	case DW_PCIE_EP_TYPE:
+		val = EP;
+		break;
+	default:
+		dev_err(dev, "INVALID device type %d\n", mode);
+		return -EINVAL;
+	}
+
+	ret = regmap_update_bits(syscon, 0, mask, val);
+	if (ret) {
+		dev_err(dev, "failed to set pcie mode\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static void ks_pcie_set_link_speed(struct dw_pcie *pci, int link_speed)
+{
+	u32 val;
+
+	dw_pcie_dbi_ro_wr_en(pci);
+
+	val = dw_pcie_readl_dbi(pci, EXP_CAP_ID_OFFSET + PCI_EXP_LNKCAP);
+	if ((val & PCI_EXP_LNKCAP_SLS) != link_speed) {
+		val &= ~((u32)PCI_EXP_LNKCAP_SLS);
+		val |= link_speed;
+		dw_pcie_writel_dbi(pci, EXP_CAP_ID_OFFSET + PCI_EXP_LNKCAP,
+				   val);
+	}
+
+	val = dw_pcie_readl_dbi(pci, EXP_CAP_ID_OFFSET + PCI_EXP_LNKCTL2);
+	if ((val & PCI_EXP_LNKCAP_SLS) != link_speed) {
+		val &= ~((u32)PCI_EXP_LNKCAP_SLS);
+		val |= link_speed;
+		dw_pcie_writel_dbi(pci, EXP_CAP_ID_OFFSET + PCI_EXP_LNKCTL2,
+				   val);
+	}
+
+	dw_pcie_dbi_ro_wr_dis(pci);
+}
+
+static const struct ks_pcie_of_data ks_pcie_rc_of_data = {
+	.host_ops = &ks_pcie_host_ops,
+	.version = 0x365A,
+};
+
+static const struct ks_pcie_of_data ks_pcie_am654_rc_of_data = {
+	.host_ops = &ks_pcie_am654_host_ops,
+	.mode = DW_PCIE_RC_TYPE,
+	.version = 0x490A,
+};
+
+static const struct ks_pcie_of_data ks_pcie_am654_ep_of_data = {
+	.ep_ops = &ks_pcie_am654_ep_ops,
+	.mode = DW_PCIE_EP_TYPE,
+	.version = 0x490A,
+};
+
+static const struct of_device_id ks_pcie_of_match[] = {
+	{
+		.type = "pci",
+		.data = &ks_pcie_rc_of_data,
+		.compatible = "ti,keystone-pcie",
+	},
+	{
+		.data = &ks_pcie_am654_rc_of_data,
+		.compatible = "ti,am654-pcie-rc",
+	},
+	{
+		.data = &ks_pcie_am654_ep_of_data,
+		.compatible = "ti,am654-pcie-ep",
+	},
+	{ },
+};
+
 static int __init ks_pcie_probe(struct platform_device *pdev)
 {
+	const struct dw_pcie_host_ops *host_ops;
+	const struct dw_pcie_ep_ops *ep_ops;
 	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
+	const struct ks_pcie_of_data *data;
+	const struct of_device_id *match;
+	enum dw_pcie_device_mode mode;
 	struct dw_pcie *pci;
 	struct keystone_pcie *ks_pcie;
+	struct device_link **link;
+	struct gpio_desc *gpiod;
+	void __iomem *atu_base;
 	struct resource *res;
-	void __iomem *reg_p;
-	struct phy *phy;
+	unsigned int version;
+	void __iomem *base;
+	u32 num_viewport;
+	struct phy **phy;
+	int link_speed;
+	u32 num_lanes;
+	char name[10];
 	int ret;
+	int irq;
+	int i;
+
+	match = of_match_device(of_match_ptr(ks_pcie_of_match), dev);
+	data = (struct ks_pcie_of_data *)match->data;
+	if (!data)
+		return -EINVAL;
+
+	version = data->version;
+	host_ops = data->host_ops;
+	ep_ops = data->ep_ops;
+	mode = data->mode;
 
 	ks_pcie = devm_kzalloc(dev, sizeof(*ks_pcie), GFP_KERNEL);
 	if (!ks_pcie)
@@ -396,55 +1225,204 @@
 	if (!pci)
 		return -ENOMEM;
 
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "app");
+	ks_pcie->va_app_base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(ks_pcie->va_app_base))
+		return PTR_ERR(ks_pcie->va_app_base);
+
+	ks_pcie->app = *res;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbics");
+	base = devm_pci_remap_cfg_resource(dev, res);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	if (of_device_is_compatible(np, "ti,am654-pcie-rc"))
+		ks_pcie->is_am6 = true;
+
+	pci->dbi_base = base;
+	pci->dbi_base2 = base;
 	pci->dev = dev;
-	pci->ops = &dw_pcie_ops;
+	pci->ops = &ks_pcie_dw_pcie_ops;
+	pci->version = version;
 
-	ks_pcie->pci = pci;
-
-	/* initialize SerDes Phy if present */
-	phy = devm_phy_get(dev, "pcie-phy");
-	if (PTR_ERR_OR_ZERO(phy) == -EPROBE_DEFER)
-		return PTR_ERR(phy);
-
-	if (!IS_ERR_OR_NULL(phy)) {
-		ret = phy_init(phy);
-		if (ret < 0)
-			return ret;
+	irq = platform_get_irq(pdev, 0);
+	if (irq < 0) {
+		dev_err(dev, "missing IRQ resource: %d\n", irq);
+		return irq;
 	}
 
-	/* index 2 is to read PCI DEVICE_ID */
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 2);
-	reg_p = devm_ioremap_resource(dev, res);
-	if (IS_ERR(reg_p))
-		return PTR_ERR(reg_p);
-	ks_pcie->device_id = readl(reg_p) >> 16;
-	devm_iounmap(dev, reg_p);
-	devm_release_mem_region(dev, res->start, resource_size(res));
-
-	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)) {
-		dev_err(dev, "Failed to get pcie rc clock\n");
-		return PTR_ERR(ks_pcie->clk);
-	}
-	ret = clk_prepare_enable(ks_pcie->clk);
-	if (ret)
+	ret = request_irq(irq, ks_pcie_err_irq_handler, IRQF_SHARED,
+			  "ks-pcie-error-irq", ks_pcie);
+	if (ret < 0) {
+		dev_err(dev, "failed to request error IRQ %d\n",
+			irq);
 		return ret;
+	}
+
+	ret = of_property_read_u32(np, "num-lanes", &num_lanes);
+	if (ret)
+		num_lanes = 1;
+
+	phy = devm_kzalloc(dev, sizeof(*phy) * num_lanes, GFP_KERNEL);
+	if (!phy)
+		return -ENOMEM;
+
+	link = devm_kzalloc(dev, sizeof(*link) * num_lanes, GFP_KERNEL);
+	if (!link)
+		return -ENOMEM;
+
+	for (i = 0; i < num_lanes; i++) {
+		snprintf(name, sizeof(name), "pcie-phy%d", i);
+		phy[i] = devm_phy_optional_get(dev, name);
+		if (IS_ERR(phy[i])) {
+			ret = PTR_ERR(phy[i]);
+			goto err_link;
+		}
+
+		if (!phy[i])
+			continue;
+
+		link[i] = device_link_add(dev, &phy[i]->dev, DL_FLAG_STATELESS);
+		if (!link[i]) {
+			ret = -EINVAL;
+			goto err_link;
+		}
+	}
+
+	ks_pcie->np = np;
+	ks_pcie->pci = pci;
+	ks_pcie->link = link;
+	ks_pcie->num_lanes = num_lanes;
+	ks_pcie->phy = phy;
+
+	gpiod = devm_gpiod_get_optional(dev, "reset",
+					GPIOD_OUT_LOW);
+	if (IS_ERR(gpiod)) {
+		ret = PTR_ERR(gpiod);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "Failed to get reset GPIO\n");
+		goto err_link;
+	}
+
+	ret = ks_pcie_enable_phy(ks_pcie);
+	if (ret) {
+		dev_err(dev, "failed to enable phy\n");
+		goto err_link;
+	}
 
 	platform_set_drvdata(pdev, ks_pcie);
+	pm_runtime_enable(dev);
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		dev_err(dev, "pm_runtime_get_sync failed\n");
+		goto err_get_sync;
+	}
 
-	ret = ks_add_pcie_port(ks_pcie, pdev);
-	if (ret < 0)
-		goto fail_clk;
+	if (pci->version >= 0x480A) {
+		res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "atu");
+		atu_base = devm_ioremap_resource(dev, res);
+		if (IS_ERR(atu_base)) {
+			ret = PTR_ERR(atu_base);
+			goto err_get_sync;
+		}
+
+		pci->atu_base = atu_base;
+
+		ret = ks_pcie_am654_set_mode(dev, mode);
+		if (ret < 0)
+			goto err_get_sync;
+	} else {
+		ret = ks_pcie_set_mode(dev);
+		if (ret < 0)
+			goto err_get_sync;
+	}
+
+	link_speed = of_pci_get_max_link_speed(np);
+	if (link_speed < 0)
+		link_speed = 2;
+
+	ks_pcie_set_link_speed(pci, link_speed);
+
+	switch (mode) {
+	case DW_PCIE_RC_TYPE:
+		if (!IS_ENABLED(CONFIG_PCI_KEYSTONE_HOST)) {
+			ret = -ENODEV;
+			goto err_get_sync;
+		}
+
+		ret = of_property_read_u32(np, "num-viewport", &num_viewport);
+		if (ret < 0) {
+			dev_err(dev, "unable to read *num-viewport* property\n");
+			return ret;
+		}
+
+		/*
+		 * "Power Sequencing and Reset Signal Timings" table in
+		 * PCI EXPRESS CARD ELECTROMECHANICAL SPECIFICATION, REV. 2.0
+		 * indicates PERST# should be deasserted after minimum of 100us
+		 * once REFCLK is stable. The REFCLK to the connector in RC
+		 * mode is selected while enabling the PHY. So deassert PERST#
+		 * after 100 us.
+		 */
+		if (gpiod) {
+			usleep_range(100, 200);
+			gpiod_set_value_cansleep(gpiod, 1);
+		}
+
+		ks_pcie->num_viewport = num_viewport;
+		pci->pp.ops = host_ops;
+		ret = ks_pcie_add_pcie_port(ks_pcie, pdev);
+		if (ret < 0)
+			goto err_get_sync;
+		break;
+	case DW_PCIE_EP_TYPE:
+		if (!IS_ENABLED(CONFIG_PCI_KEYSTONE_EP)) {
+			ret = -ENODEV;
+			goto err_get_sync;
+		}
+
+		pci->ep.ops = ep_ops;
+		ret = ks_pcie_add_pcie_ep(ks_pcie, pdev);
+		if (ret < 0)
+			goto err_get_sync;
+		break;
+	default:
+		dev_err(dev, "INVALID device type %d\n", mode);
+	}
+
+	ks_pcie_enable_error_irq(ks_pcie);
 
 	return 0;
-fail_clk:
-	clk_disable_unprepare(ks_pcie->clk);
+
+err_get_sync:
+	pm_runtime_put(dev);
+	pm_runtime_disable(dev);
+	ks_pcie_disable_phy(ks_pcie);
+
+err_link:
+	while (--i >= 0 && link[i])
+		device_link_del(link[i]);
 
 	return ret;
 }
 
+static int __exit ks_pcie_remove(struct platform_device *pdev)
+{
+	struct keystone_pcie *ks_pcie = platform_get_drvdata(pdev);
+	struct device_link **link = ks_pcie->link;
+	int num_lanes = ks_pcie->num_lanes;
+	struct device *dev = &pdev->dev;
+
+	pm_runtime_put(dev);
+	pm_runtime_disable(dev);
+	ks_pcie_disable_phy(ks_pcie);
+	while (num_lanes--)
+		device_link_del(link[num_lanes]);
+
+	return 0;
+}
+
 static struct platform_driver ks_pcie_driver __refdata = {
 	.probe  = ks_pcie_probe,
 	.remove = __exit_p(ks_pcie_remove),
diff --git a/drivers/pci/controller/dwc/pci-keystone.h b/drivers/pci/controller/dwc/pci-keystone.h
deleted file mode 100644
index 8a13da3..0000000
--- a/drivers/pci/controller/dwc/pci-keystone.h
+++ /dev/null
@@ -1,57 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Keystone PCI Controller's common includes
- *
- * Copyright (C) 2013-2014 Texas Instruments., Ltd.
- *		http://www.ti.com
- *
- * Author: Murali Karicheri <m-karicheri2@ti.com>
- */
-
-#define MAX_MSI_HOST_IRQS		8
-
-struct keystone_pcie {
-	struct dw_pcie		*pci;
-	struct	clk		*clk;
-	/* PCI Device ID */
-	u32			device_id;
-	int			num_legacy_host_irqs;
-	int			legacy_host_irqs[PCI_NUM_INTX];
-	struct			device_node *legacy_intc_np;
-
-	int			num_msi_host_irqs;
-	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;	/* DT 1st resource */
-	struct resource		app;
-};
-
-/* Keystone DW specific MSI controller APIs/definitions */
-void ks_dw_pcie_handle_msi_irq(struct keystone_pcie *ks_pcie, int offset);
-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(struct keystone_pcie *ks_pcie);
-irqreturn_t ks_dw_pcie_handle_error_irq(struct keystone_pcie *ks_pcie);
-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,
-		unsigned int devfn, int where, int size, u32 val);
-int ks_dw_pcie_rd_other_conf(struct pcie_port *pp, struct pci_bus *bus,
-		unsigned int devfn, int where, int size, u32 *val);
-void ks_dw_pcie_setup_rc_app_regs(struct keystone_pcie *ks_pcie);
-void ks_dw_pcie_initiate_link_train(struct keystone_pcie *ks_pcie);
-void ks_dw_pcie_msi_irq_ack(int i, struct pcie_port *pp);
-void ks_dw_pcie_msi_set_irq(struct pcie_port *pp, int irq);
-void ks_dw_pcie_msi_clear_irq(struct pcie_port *pp, int irq);
-void ks_dw_pcie_v3_65_scan_bus(struct pcie_port *pp);
-int ks_dw_pcie_msi_host_init(struct pcie_port *pp);
-int ks_dw_pcie_link_up(struct dw_pcie *pci);
diff --git a/drivers/pci/controller/dwc/pci-layerscape-ep.c b/drivers/pci/controller/dwc/pci-layerscape-ep.c
new file mode 100644
index 0000000..ca9aa45
--- /dev/null
+++ b/drivers/pci/controller/dwc/pci-layerscape-ep.c
@@ -0,0 +1,157 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PCIe controller EP driver for Freescale Layerscape SoCs
+ *
+ * Copyright (C) 2018 NXP Semiconductor.
+ *
+ * Author: Xiaowei Bao <xiaowei.bao@nxp.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/of_pci.h>
+#include <linux/of_platform.h>
+#include <linux/of_address.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/resource.h>
+
+#include "pcie-designware.h"
+
+#define PCIE_DBI2_OFFSET		0x1000	/* DBI2 base address*/
+
+struct ls_pcie_ep {
+	struct dw_pcie		*pci;
+};
+
+#define to_ls_pcie_ep(x)	dev_get_drvdata((x)->dev)
+
+static int ls_pcie_establish_link(struct dw_pcie *pci)
+{
+	return 0;
+}
+
+static const struct dw_pcie_ops ls_pcie_ep_ops = {
+	.start_link = ls_pcie_establish_link,
+};
+
+static const struct of_device_id ls_pcie_ep_of_match[] = {
+	{ .compatible = "fsl,ls-pcie-ep",},
+	{ },
+};
+
+static const struct pci_epc_features ls_pcie_epc_features = {
+	.linkup_notifier = false,
+	.msi_capable = true,
+	.msix_capable = false,
+	.bar_fixed_64bit = (1 << BAR_2) | (1 << BAR_4),
+};
+
+static const struct pci_epc_features*
+ls_pcie_ep_get_features(struct dw_pcie_ep *ep)
+{
+	return &ls_pcie_epc_features;
+}
+
+static void ls_pcie_ep_init(struct dw_pcie_ep *ep)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	enum pci_barno bar;
+
+	for (bar = BAR_0; bar <= BAR_5; bar++)
+		dw_pcie_ep_reset_bar(pci, bar);
+}
+
+static int ls_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
+				  enum pci_epc_irq_type type, u16 interrupt_num)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+
+	switch (type) {
+	case PCI_EPC_IRQ_LEGACY:
+		return dw_pcie_ep_raise_legacy_irq(ep, func_no);
+	case PCI_EPC_IRQ_MSI:
+		return dw_pcie_ep_raise_msi_irq(ep, func_no, interrupt_num);
+	case PCI_EPC_IRQ_MSIX:
+		return dw_pcie_ep_raise_msix_irq(ep, func_no, interrupt_num);
+	default:
+		dev_err(pci->dev, "UNKNOWN IRQ type\n");
+		return -EINVAL;
+	}
+}
+
+static const struct dw_pcie_ep_ops pcie_ep_ops = {
+	.ep_init = ls_pcie_ep_init,
+	.raise_irq = ls_pcie_ep_raise_irq,
+	.get_features = ls_pcie_ep_get_features,
+};
+
+static int __init ls_add_pcie_ep(struct ls_pcie_ep *pcie,
+					struct platform_device *pdev)
+{
+	struct dw_pcie *pci = pcie->pci;
+	struct device *dev = pci->dev;
+	struct dw_pcie_ep *ep;
+	struct resource *res;
+	int ret;
+
+	ep = &pci->ep;
+	ep->ops = &pcie_ep_ops;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "addr_space");
+	if (!res)
+		return -EINVAL;
+
+	ep->phys_base = res->start;
+	ep->addr_size = resource_size(res);
+
+	ret = dw_pcie_ep_init(ep);
+	if (ret) {
+		dev_err(dev, "failed to initialize endpoint\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int __init ls_pcie_ep_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct dw_pcie *pci;
+	struct ls_pcie_ep *pcie;
+	struct resource *dbi_base;
+	int ret;
+
+	pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL);
+	if (!pcie)
+		return -ENOMEM;
+
+	pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL);
+	if (!pci)
+		return -ENOMEM;
+
+	dbi_base = platform_get_resource_byname(pdev, IORESOURCE_MEM, "regs");
+	pci->dbi_base = devm_pci_remap_cfg_resource(dev, dbi_base);
+	if (IS_ERR(pci->dbi_base))
+		return PTR_ERR(pci->dbi_base);
+
+	pci->dbi_base2 = pci->dbi_base + PCIE_DBI2_OFFSET;
+	pci->dev = dev;
+	pci->ops = &ls_pcie_ep_ops;
+	pcie->pci = pci;
+
+	platform_set_drvdata(pdev, pcie);
+
+	ret = ls_add_pcie_ep(pcie, pdev);
+
+	return ret;
+}
+
+static struct platform_driver ls_pcie_ep_driver = {
+	.driver = {
+		.name = "layerscape-pcie-ep",
+		.of_match_table = ls_pcie_ep_of_match,
+		.suppress_bind_attrs = true,
+	},
+};
+builtin_platform_driver_probe(ls_pcie_ep_driver, ls_pcie_ep_probe);
diff --git a/drivers/pci/controller/dwc/pci-layerscape.c b/drivers/pci/controller/dwc/pci-layerscape.c
index 7aa9a82..3a5fa26 100644
--- a/drivers/pci/controller/dwc/pci-layerscape.c
+++ b/drivers/pci/controller/dwc/pci-layerscape.c
@@ -201,6 +201,7 @@
 		return -EINVAL;
 	}
 
+	of_node_put(msi_node);
 	return 0;
 }
 
@@ -222,12 +223,12 @@
 	.link_up = ls_pcie_link_up,
 };
 
-static struct ls_pcie_drvdata ls1021_drvdata = {
+static const struct ls_pcie_drvdata ls1021_drvdata = {
 	.ops = &ls1021_pcie_host_ops,
 	.dw_pcie_ops = &dw_ls1021_pcie_ops,
 };
 
-static struct ls_pcie_drvdata ls1043_drvdata = {
+static const struct ls_pcie_drvdata ls1043_drvdata = {
 	.lut_offset = 0x10000,
 	.ltssm_shift = 24,
 	.lut_dbg = 0x7fc,
@@ -235,7 +236,7 @@
 	.dw_pcie_ops = &dw_ls_pcie_ops,
 };
 
-static struct ls_pcie_drvdata ls1046_drvdata = {
+static const struct ls_pcie_drvdata ls1046_drvdata = {
 	.lut_offset = 0x80000,
 	.ltssm_shift = 24,
 	.lut_dbg = 0x407fc,
@@ -243,7 +244,7 @@
 	.dw_pcie_ops = &dw_ls_pcie_ops,
 };
 
-static struct ls_pcie_drvdata ls2080_drvdata = {
+static const struct ls_pcie_drvdata ls2080_drvdata = {
 	.lut_offset = 0x80000,
 	.ltssm_shift = 0,
 	.lut_dbg = 0x7fc,
@@ -251,7 +252,7 @@
 	.dw_pcie_ops = &dw_ls_pcie_ops,
 };
 
-static struct ls_pcie_drvdata ls2088_drvdata = {
+static const struct ls_pcie_drvdata ls2088_drvdata = {
 	.lut_offset = 0x80000,
 	.ltssm_shift = 0,
 	.lut_dbg = 0x407fc,
diff --git a/drivers/pci/controller/dwc/pci-meson.c b/drivers/pci/controller/dwc/pci-meson.c
new file mode 100644
index 0000000..e35e9ea
--- /dev/null
+++ b/drivers/pci/controller/dwc/pci-meson.c
@@ -0,0 +1,593 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PCIe host controller driver for Amlogic MESON SoCs
+ *
+ * Copyright (c) 2018 Amlogic, inc.
+ * Author: Yue Wang <yue.wang@amlogic.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/gpio/consumer.h>
+#include <linux/of_device.h>
+#include <linux/of_gpio.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+#include <linux/resource.h>
+#include <linux/types.h>
+
+#include "pcie-designware.h"
+
+#define to_meson_pcie(x) dev_get_drvdata((x)->dev)
+
+/* External local bus interface registers */
+#define PLR_OFFSET			0x700
+#define PCIE_PORT_LINK_CTRL_OFF		(PLR_OFFSET + 0x10)
+#define FAST_LINK_MODE			BIT(7)
+#define LINK_CAPABLE_MASK		GENMASK(21, 16)
+#define LINK_CAPABLE_X1			BIT(16)
+
+#define PCIE_GEN2_CTRL_OFF		(PLR_OFFSET + 0x10c)
+#define NUM_OF_LANES_MASK		GENMASK(12, 8)
+#define NUM_OF_LANES_X1			BIT(8)
+#define DIRECT_SPEED_CHANGE		BIT(17)
+
+#define TYPE1_HDR_OFFSET		0x0
+#define PCIE_STATUS_COMMAND		(TYPE1_HDR_OFFSET + 0x04)
+#define PCI_IO_EN			BIT(0)
+#define PCI_MEM_SPACE_EN		BIT(1)
+#define PCI_BUS_MASTER_EN		BIT(2)
+
+#define PCIE_BASE_ADDR0			(TYPE1_HDR_OFFSET + 0x10)
+#define PCIE_BASE_ADDR1			(TYPE1_HDR_OFFSET + 0x14)
+
+#define PCIE_CAP_OFFSET			0x70
+#define PCIE_DEV_CTRL_DEV_STUS		(PCIE_CAP_OFFSET + 0x08)
+#define PCIE_CAP_MAX_PAYLOAD_MASK	GENMASK(7, 5)
+#define PCIE_CAP_MAX_PAYLOAD_SIZE(x)	((x) << 5)
+#define PCIE_CAP_MAX_READ_REQ_MASK	GENMASK(14, 12)
+#define PCIE_CAP_MAX_READ_REQ_SIZE(x)	((x) << 12)
+
+/* PCIe specific config registers */
+#define PCIE_CFG0			0x0
+#define APP_LTSSM_ENABLE		BIT(7)
+
+#define PCIE_CFG_STATUS12		0x30
+#define IS_SMLH_LINK_UP(x)		((x) & (1 << 6))
+#define IS_RDLH_LINK_UP(x)		((x) & (1 << 16))
+#define IS_LTSSM_UP(x)			((((x) >> 10) & 0x1f) == 0x11)
+
+#define PCIE_CFG_STATUS17		0x44
+#define PM_CURRENT_STATE(x)		(((x) >> 7) & 0x1)
+
+#define WAIT_LINKUP_TIMEOUT		4000
+#define PORT_CLK_RATE			100000000UL
+#define MAX_PAYLOAD_SIZE		256
+#define MAX_READ_REQ_SIZE		256
+#define MESON_PCIE_PHY_POWERUP		0x1c
+#define PCIE_RESET_DELAY		500
+#define PCIE_SHARED_RESET		1
+#define PCIE_NORMAL_RESET		0
+
+enum pcie_data_rate {
+	PCIE_GEN1,
+	PCIE_GEN2,
+	PCIE_GEN3,
+	PCIE_GEN4
+};
+
+struct meson_pcie_mem_res {
+	void __iomem *elbi_base;
+	void __iomem *cfg_base;
+	void __iomem *phy_base;
+};
+
+struct meson_pcie_clk_res {
+	struct clk *clk;
+	struct clk *mipi_gate;
+	struct clk *port_clk;
+	struct clk *general_clk;
+};
+
+struct meson_pcie_rc_reset {
+	struct reset_control *phy;
+	struct reset_control *port;
+	struct reset_control *apb;
+};
+
+struct meson_pcie {
+	struct dw_pcie pci;
+	struct meson_pcie_mem_res mem_res;
+	struct meson_pcie_clk_res clk_res;
+	struct meson_pcie_rc_reset mrst;
+	struct gpio_desc *reset_gpio;
+};
+
+static struct reset_control *meson_pcie_get_reset(struct meson_pcie *mp,
+						  const char *id,
+						  u32 reset_type)
+{
+	struct device *dev = mp->pci.dev;
+	struct reset_control *reset;
+
+	if (reset_type == PCIE_SHARED_RESET)
+		reset = devm_reset_control_get_shared(dev, id);
+	else
+		reset = devm_reset_control_get(dev, id);
+
+	return reset;
+}
+
+static int meson_pcie_get_resets(struct meson_pcie *mp)
+{
+	struct meson_pcie_rc_reset *mrst = &mp->mrst;
+
+	mrst->phy = meson_pcie_get_reset(mp, "phy", PCIE_SHARED_RESET);
+	if (IS_ERR(mrst->phy))
+		return PTR_ERR(mrst->phy);
+	reset_control_deassert(mrst->phy);
+
+	mrst->port = meson_pcie_get_reset(mp, "port", PCIE_NORMAL_RESET);
+	if (IS_ERR(mrst->port))
+		return PTR_ERR(mrst->port);
+	reset_control_deassert(mrst->port);
+
+	mrst->apb = meson_pcie_get_reset(mp, "apb", PCIE_SHARED_RESET);
+	if (IS_ERR(mrst->apb))
+		return PTR_ERR(mrst->apb);
+	reset_control_deassert(mrst->apb);
+
+	return 0;
+}
+
+static void __iomem *meson_pcie_get_mem(struct platform_device *pdev,
+					struct meson_pcie *mp,
+					const char *id)
+{
+	struct device *dev = mp->pci.dev;
+	struct resource *res;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, id);
+
+	return devm_ioremap_resource(dev, res);
+}
+
+static void __iomem *meson_pcie_get_mem_shared(struct platform_device *pdev,
+					       struct meson_pcie *mp,
+					       const char *id)
+{
+	struct device *dev = mp->pci.dev;
+	struct resource *res;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, id);
+	if (!res) {
+		dev_err(dev, "No REG resource %s\n", id);
+		return ERR_PTR(-ENXIO);
+	}
+
+	return devm_ioremap(dev, res->start, resource_size(res));
+}
+
+static int meson_pcie_get_mems(struct platform_device *pdev,
+			       struct meson_pcie *mp)
+{
+	mp->mem_res.elbi_base = meson_pcie_get_mem(pdev, mp, "elbi");
+	if (IS_ERR(mp->mem_res.elbi_base))
+		return PTR_ERR(mp->mem_res.elbi_base);
+
+	mp->mem_res.cfg_base = meson_pcie_get_mem(pdev, mp, "cfg");
+	if (IS_ERR(mp->mem_res.cfg_base))
+		return PTR_ERR(mp->mem_res.cfg_base);
+
+	/* Meson SoC has two PCI controllers use same phy register*/
+	mp->mem_res.phy_base = meson_pcie_get_mem_shared(pdev, mp, "phy");
+	if (IS_ERR(mp->mem_res.phy_base))
+		return PTR_ERR(mp->mem_res.phy_base);
+
+	return 0;
+}
+
+static void meson_pcie_power_on(struct meson_pcie *mp)
+{
+	writel(MESON_PCIE_PHY_POWERUP, mp->mem_res.phy_base);
+}
+
+static void meson_pcie_reset(struct meson_pcie *mp)
+{
+	struct meson_pcie_rc_reset *mrst = &mp->mrst;
+
+	reset_control_assert(mrst->phy);
+	udelay(PCIE_RESET_DELAY);
+	reset_control_deassert(mrst->phy);
+	udelay(PCIE_RESET_DELAY);
+
+	reset_control_assert(mrst->port);
+	reset_control_assert(mrst->apb);
+	udelay(PCIE_RESET_DELAY);
+	reset_control_deassert(mrst->port);
+	reset_control_deassert(mrst->apb);
+	udelay(PCIE_RESET_DELAY);
+}
+
+static inline struct clk *meson_pcie_probe_clock(struct device *dev,
+						 const char *id, u64 rate)
+{
+	struct clk *clk;
+	int ret;
+
+	clk = devm_clk_get(dev, id);
+	if (IS_ERR(clk))
+		return clk;
+
+	if (rate) {
+		ret = clk_set_rate(clk, rate);
+		if (ret) {
+			dev_err(dev, "set clk rate failed, ret = %d\n", ret);
+			return ERR_PTR(ret);
+		}
+	}
+
+	ret = clk_prepare_enable(clk);
+	if (ret) {
+		dev_err(dev, "couldn't enable clk\n");
+		return ERR_PTR(ret);
+	}
+
+	devm_add_action_or_reset(dev,
+				 (void (*) (void *))clk_disable_unprepare,
+				 clk);
+
+	return clk;
+}
+
+static int meson_pcie_probe_clocks(struct meson_pcie *mp)
+{
+	struct device *dev = mp->pci.dev;
+	struct meson_pcie_clk_res *res = &mp->clk_res;
+
+	res->port_clk = meson_pcie_probe_clock(dev, "port", PORT_CLK_RATE);
+	if (IS_ERR(res->port_clk))
+		return PTR_ERR(res->port_clk);
+
+	res->mipi_gate = meson_pcie_probe_clock(dev, "pcie_mipi_en", 0);
+	if (IS_ERR(res->mipi_gate))
+		return PTR_ERR(res->mipi_gate);
+
+	res->general_clk = meson_pcie_probe_clock(dev, "pcie_general", 0);
+	if (IS_ERR(res->general_clk))
+		return PTR_ERR(res->general_clk);
+
+	res->clk = meson_pcie_probe_clock(dev, "pcie", 0);
+	if (IS_ERR(res->clk))
+		return PTR_ERR(res->clk);
+
+	return 0;
+}
+
+static inline void meson_elb_writel(struct meson_pcie *mp, u32 val, u32 reg)
+{
+	writel(val, mp->mem_res.elbi_base + reg);
+}
+
+static inline u32 meson_elb_readl(struct meson_pcie *mp, u32 reg)
+{
+	return readl(mp->mem_res.elbi_base + reg);
+}
+
+static inline u32 meson_cfg_readl(struct meson_pcie *mp, u32 reg)
+{
+	return readl(mp->mem_res.cfg_base + reg);
+}
+
+static inline void meson_cfg_writel(struct meson_pcie *mp, u32 val, u32 reg)
+{
+	writel(val, mp->mem_res.cfg_base + reg);
+}
+
+static void meson_pcie_assert_reset(struct meson_pcie *mp)
+{
+	gpiod_set_value_cansleep(mp->reset_gpio, 0);
+	udelay(500);
+	gpiod_set_value_cansleep(mp->reset_gpio, 1);
+}
+
+static void meson_pcie_init_dw(struct meson_pcie *mp)
+{
+	u32 val;
+
+	val = meson_cfg_readl(mp, PCIE_CFG0);
+	val |= APP_LTSSM_ENABLE;
+	meson_cfg_writel(mp, val, PCIE_CFG0);
+
+	val = meson_elb_readl(mp, PCIE_PORT_LINK_CTRL_OFF);
+	val &= ~LINK_CAPABLE_MASK;
+	meson_elb_writel(mp, val, PCIE_PORT_LINK_CTRL_OFF);
+
+	val = meson_elb_readl(mp, PCIE_PORT_LINK_CTRL_OFF);
+	val |= LINK_CAPABLE_X1 | FAST_LINK_MODE;
+	meson_elb_writel(mp, val, PCIE_PORT_LINK_CTRL_OFF);
+
+	val = meson_elb_readl(mp, PCIE_GEN2_CTRL_OFF);
+	val &= ~NUM_OF_LANES_MASK;
+	meson_elb_writel(mp, val, PCIE_GEN2_CTRL_OFF);
+
+	val = meson_elb_readl(mp, PCIE_GEN2_CTRL_OFF);
+	val |= NUM_OF_LANES_X1 | DIRECT_SPEED_CHANGE;
+	meson_elb_writel(mp, val, PCIE_GEN2_CTRL_OFF);
+
+	meson_elb_writel(mp, 0x0, PCIE_BASE_ADDR0);
+	meson_elb_writel(mp, 0x0, PCIE_BASE_ADDR1);
+}
+
+static int meson_size_to_payload(struct meson_pcie *mp, int size)
+{
+	struct device *dev = mp->pci.dev;
+
+	/*
+	 * dwc supports 2^(val+7) payload size, which val is 0~5 default to 1.
+	 * So if input size is not 2^order alignment or less than 2^7 or bigger
+	 * than 2^12, just set to default size 2^(1+7).
+	 */
+	if (!is_power_of_2(size) || size < 128 || size > 4096) {
+		dev_warn(dev, "payload size %d, set to default 256\n", size);
+		return 1;
+	}
+
+	return fls(size) - 8;
+}
+
+static void meson_set_max_payload(struct meson_pcie *mp, int size)
+{
+	u32 val;
+	int max_payload_size = meson_size_to_payload(mp, size);
+
+	val = meson_elb_readl(mp, PCIE_DEV_CTRL_DEV_STUS);
+	val &= ~PCIE_CAP_MAX_PAYLOAD_MASK;
+	meson_elb_writel(mp, val, PCIE_DEV_CTRL_DEV_STUS);
+
+	val = meson_elb_readl(mp, PCIE_DEV_CTRL_DEV_STUS);
+	val |= PCIE_CAP_MAX_PAYLOAD_SIZE(max_payload_size);
+	meson_elb_writel(mp, val, PCIE_DEV_CTRL_DEV_STUS);
+}
+
+static void meson_set_max_rd_req_size(struct meson_pcie *mp, int size)
+{
+	u32 val;
+	int max_rd_req_size = meson_size_to_payload(mp, size);
+
+	val = meson_elb_readl(mp, PCIE_DEV_CTRL_DEV_STUS);
+	val &= ~PCIE_CAP_MAX_READ_REQ_MASK;
+	meson_elb_writel(mp, val, PCIE_DEV_CTRL_DEV_STUS);
+
+	val = meson_elb_readl(mp, PCIE_DEV_CTRL_DEV_STUS);
+	val |= PCIE_CAP_MAX_READ_REQ_SIZE(max_rd_req_size);
+	meson_elb_writel(mp, val, PCIE_DEV_CTRL_DEV_STUS);
+}
+
+static inline void meson_enable_memory_space(struct meson_pcie *mp)
+{
+	/* Set the RC Bus Master, Memory Space and I/O Space enables */
+	meson_elb_writel(mp, PCI_IO_EN | PCI_MEM_SPACE_EN | PCI_BUS_MASTER_EN,
+			 PCIE_STATUS_COMMAND);
+}
+
+static int meson_pcie_establish_link(struct meson_pcie *mp)
+{
+	struct dw_pcie *pci = &mp->pci;
+	struct pcie_port *pp = &pci->pp;
+
+	meson_pcie_init_dw(mp);
+	meson_set_max_payload(mp, MAX_PAYLOAD_SIZE);
+	meson_set_max_rd_req_size(mp, MAX_READ_REQ_SIZE);
+
+	dw_pcie_setup_rc(pp);
+	meson_enable_memory_space(mp);
+
+	meson_pcie_assert_reset(mp);
+
+	return dw_pcie_wait_for_link(pci);
+}
+
+static void meson_pcie_enable_interrupts(struct meson_pcie *mp)
+{
+	if (IS_ENABLED(CONFIG_PCI_MSI))
+		dw_pcie_msi_init(&mp->pci.pp);
+}
+
+static int meson_pcie_rd_own_conf(struct pcie_port *pp, int where, int size,
+				  u32 *val)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	int ret;
+
+	ret = dw_pcie_read(pci->dbi_base + where, size, val);
+	if (ret != PCIBIOS_SUCCESSFUL)
+		return ret;
+
+	/*
+	 * There is a bug in the MESON AXG PCIe controller whereby software
+	 * cannot program the PCI_CLASS_DEVICE register, so we must fabricate
+	 * the return value in the config accessors.
+	 */
+	if (where == PCI_CLASS_REVISION && size == 4)
+		*val = (PCI_CLASS_BRIDGE_PCI << 16) | (*val & 0xffff);
+	else if (where == PCI_CLASS_DEVICE && size == 2)
+		*val = PCI_CLASS_BRIDGE_PCI;
+	else if (where == PCI_CLASS_DEVICE && size == 1)
+		*val = PCI_CLASS_BRIDGE_PCI & 0xff;
+	else if (where == PCI_CLASS_DEVICE + 1 && size == 1)
+		*val = (PCI_CLASS_BRIDGE_PCI >> 8) & 0xff;
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int meson_pcie_wr_own_conf(struct pcie_port *pp, int where,
+				  int size, u32 val)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+
+	return dw_pcie_write(pci->dbi_base + where, size, val);
+}
+
+static int meson_pcie_link_up(struct dw_pcie *pci)
+{
+	struct meson_pcie *mp = to_meson_pcie(pci);
+	struct device *dev = pci->dev;
+	u32 speed_okay = 0;
+	u32 cnt = 0;
+	u32 state12, state17, smlh_up, ltssm_up, rdlh_up;
+
+	do {
+		state12 = meson_cfg_readl(mp, PCIE_CFG_STATUS12);
+		state17 = meson_cfg_readl(mp, PCIE_CFG_STATUS17);
+		smlh_up = IS_SMLH_LINK_UP(state12);
+		rdlh_up = IS_RDLH_LINK_UP(state12);
+		ltssm_up = IS_LTSSM_UP(state12);
+
+		if (PM_CURRENT_STATE(state17) < PCIE_GEN3)
+			speed_okay = 1;
+
+		if (smlh_up)
+			dev_dbg(dev, "smlh_link_up is on\n");
+		if (rdlh_up)
+			dev_dbg(dev, "rdlh_link_up is on\n");
+		if (ltssm_up)
+			dev_dbg(dev, "ltssm_up is on\n");
+		if (speed_okay)
+			dev_dbg(dev, "speed_okay\n");
+
+		if (smlh_up && rdlh_up && ltssm_up && speed_okay)
+			return 1;
+
+		cnt++;
+
+		udelay(10);
+	} while (cnt < WAIT_LINKUP_TIMEOUT);
+
+	dev_err(dev, "error: wait linkup timeout\n");
+	return 0;
+}
+
+static int meson_pcie_host_init(struct pcie_port *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct meson_pcie *mp = to_meson_pcie(pci);
+	int ret;
+
+	ret = meson_pcie_establish_link(mp);
+	if (ret)
+		return ret;
+
+	meson_pcie_enable_interrupts(mp);
+
+	return 0;
+}
+
+static const struct dw_pcie_host_ops meson_pcie_host_ops = {
+	.rd_own_conf = meson_pcie_rd_own_conf,
+	.wr_own_conf = meson_pcie_wr_own_conf,
+	.host_init = meson_pcie_host_init,
+};
+
+static int meson_add_pcie_port(struct meson_pcie *mp,
+			       struct platform_device *pdev)
+{
+	struct dw_pcie *pci = &mp->pci;
+	struct pcie_port *pp = &pci->pp;
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+		pp->msi_irq = platform_get_irq(pdev, 0);
+		if (pp->msi_irq < 0) {
+			dev_err(dev, "failed to get MSI IRQ\n");
+			return pp->msi_irq;
+		}
+	}
+
+	pp->ops = &meson_pcie_host_ops;
+	pci->dbi_base = mp->mem_res.elbi_base;
+
+	ret = dw_pcie_host_init(pp);
+	if (ret) {
+		dev_err(dev, "failed to initialize host\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct dw_pcie_ops dw_pcie_ops = {
+	.link_up = meson_pcie_link_up,
+};
+
+static int meson_pcie_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct dw_pcie *pci;
+	struct meson_pcie *mp;
+	int ret;
+
+	mp = devm_kzalloc(dev, sizeof(*mp), GFP_KERNEL);
+	if (!mp)
+		return -ENOMEM;
+
+	pci = &mp->pci;
+	pci->dev = dev;
+	pci->ops = &dw_pcie_ops;
+
+	mp->reset_gpio = devm_gpiod_get(dev, "reset", GPIOD_OUT_LOW);
+	if (IS_ERR(mp->reset_gpio)) {
+		dev_err(dev, "get reset gpio failed\n");
+		return PTR_ERR(mp->reset_gpio);
+	}
+
+	ret = meson_pcie_get_resets(mp);
+	if (ret) {
+		dev_err(dev, "get reset resource failed, %d\n", ret);
+		return ret;
+	}
+
+	ret = meson_pcie_get_mems(pdev, mp);
+	if (ret) {
+		dev_err(dev, "get memory resource failed, %d\n", ret);
+		return ret;
+	}
+
+	meson_pcie_power_on(mp);
+	meson_pcie_reset(mp);
+
+	ret = meson_pcie_probe_clocks(mp);
+	if (ret) {
+		dev_err(dev, "init clock resources failed, %d\n", ret);
+		return ret;
+	}
+
+	platform_set_drvdata(pdev, mp);
+
+	ret = meson_add_pcie_port(mp, pdev);
+	if (ret < 0) {
+		dev_err(dev, "Add PCIe port failed, %d\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct of_device_id meson_pcie_of_match[] = {
+	{
+		.compatible = "amlogic,axg-pcie",
+	},
+	{},
+};
+
+static struct platform_driver meson_pcie_driver = {
+	.probe = meson_pcie_probe,
+	.driver = {
+		.name = "meson-pcie",
+		.of_match_table = meson_pcie_of_match,
+	},
+};
+
+builtin_platform_driver(meson_pcie_driver);
diff --git a/drivers/pci/controller/dwc/pcie-al.c b/drivers/pci/controller/dwc/pcie-al.c
new file mode 100644
index 0000000..1eeda2f
--- /dev/null
+++ b/drivers/pci/controller/dwc/pcie-al.c
@@ -0,0 +1,458 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PCIe host controller driver for Amazon's Annapurna Labs IP (used in chips
+ * such as Graviton and Alpine)
+ *
+ * Copyright 2019 Amazon.com, Inc. or its affiliates. All Rights Reserved.
+ *
+ * Author: Jonathan Chocron <jonnyc@amazon.com>
+ */
+
+#include <linux/pci.h>
+#include <linux/pci-ecam.h>
+#include <linux/pci-acpi.h>
+#include "../../pci.h"
+
+#if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)
+
+struct al_pcie_acpi  {
+	void __iomem *dbi_base;
+};
+
+static void __iomem *al_pcie_map_bus(struct pci_bus *bus, unsigned int devfn,
+				     int where)
+{
+	struct pci_config_window *cfg = bus->sysdata;
+	struct al_pcie_acpi *pcie = cfg->priv;
+	void __iomem *dbi_base = pcie->dbi_base;
+
+	if (bus->number == cfg->busr.start) {
+		/*
+		 * The DW PCIe core doesn't filter out transactions to other
+		 * devices/functions on the root bus num, so we do this here.
+		 */
+		if (PCI_SLOT(devfn) > 0)
+			return NULL;
+		else
+			return dbi_base + where;
+	}
+
+	return pci_ecam_map_bus(bus, devfn, where);
+}
+
+static int al_pcie_init(struct pci_config_window *cfg)
+{
+	struct device *dev = cfg->parent;
+	struct acpi_device *adev = to_acpi_device(dev);
+	struct acpi_pci_root *root = acpi_driver_data(adev);
+	struct al_pcie_acpi *al_pcie;
+	struct resource *res;
+	int ret;
+
+	al_pcie = devm_kzalloc(dev, sizeof(*al_pcie), GFP_KERNEL);
+	if (!al_pcie)
+		return -ENOMEM;
+
+	res = devm_kzalloc(dev, sizeof(*res), GFP_KERNEL);
+	if (!res)
+		return -ENOMEM;
+
+	ret = acpi_get_rc_resources(dev, "AMZN0001", root->segment, res);
+	if (ret) {
+		dev_err(dev, "can't get rc dbi base address for SEG %d\n",
+			root->segment);
+		return ret;
+	}
+
+	dev_dbg(dev, "Root port dbi res: %pR\n", res);
+
+	al_pcie->dbi_base = devm_pci_remap_cfg_resource(dev, res);
+	if (IS_ERR(al_pcie->dbi_base)) {
+		long err = PTR_ERR(al_pcie->dbi_base);
+
+		dev_err(dev, "couldn't remap dbi base %pR (err:%ld)\n",
+			res, err);
+		return err;
+	}
+
+	cfg->priv = al_pcie;
+
+	return 0;
+}
+
+struct pci_ecam_ops al_pcie_ops = {
+	.bus_shift    = 20,
+	.init         =  al_pcie_init,
+	.pci_ops      = {
+		.map_bus    = al_pcie_map_bus,
+		.read       = pci_generic_config_read,
+		.write      = pci_generic_config_write,
+	}
+};
+
+#endif /* defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS) */
+
+#ifdef CONFIG_PCIE_AL
+
+#include <linux/of_pci.h>
+#include "pcie-designware.h"
+
+#define AL_PCIE_REV_ID_2	2
+#define AL_PCIE_REV_ID_3	3
+#define AL_PCIE_REV_ID_4	4
+
+#define AXI_BASE_OFFSET		0x0
+
+#define DEVICE_ID_OFFSET	0x16c
+
+#define DEVICE_REV_ID			0x0
+#define DEVICE_REV_ID_DEV_ID_MASK	GENMASK(31, 16)
+
+#define DEVICE_REV_ID_DEV_ID_X4		0
+#define DEVICE_REV_ID_DEV_ID_X8		2
+#define DEVICE_REV_ID_DEV_ID_X16	4
+
+#define OB_CTRL_REV1_2_OFFSET	0x0040
+#define OB_CTRL_REV3_5_OFFSET	0x0030
+
+#define CFG_TARGET_BUS			0x0
+#define CFG_TARGET_BUS_MASK_MASK	GENMASK(7, 0)
+#define CFG_TARGET_BUS_BUSNUM_MASK	GENMASK(15, 8)
+
+#define CFG_CONTROL			0x4
+#define CFG_CONTROL_SUBBUS_MASK		GENMASK(15, 8)
+#define CFG_CONTROL_SEC_BUS_MASK	GENMASK(23, 16)
+
+struct al_pcie_reg_offsets {
+	unsigned int ob_ctrl;
+};
+
+struct al_pcie_target_bus_cfg {
+	u8 reg_val;
+	u8 reg_mask;
+	u8 ecam_mask;
+};
+
+struct al_pcie {
+	struct dw_pcie *pci;
+	void __iomem *controller_base; /* base of PCIe unit (not DW core) */
+	struct device *dev;
+	resource_size_t ecam_size;
+	unsigned int controller_rev_id;
+	struct al_pcie_reg_offsets reg_offsets;
+	struct al_pcie_target_bus_cfg target_bus_cfg;
+};
+
+#define PCIE_ECAM_DEVFN(x)		(((x) & 0xff) << 12)
+
+#define to_al_pcie(x)		dev_get_drvdata((x)->dev)
+
+static inline u32 al_pcie_controller_readl(struct al_pcie *pcie, u32 offset)
+{
+	return readl_relaxed(pcie->controller_base + offset);
+}
+
+static inline void al_pcie_controller_writel(struct al_pcie *pcie, u32 offset,
+					     u32 val)
+{
+	writel_relaxed(val, pcie->controller_base + offset);
+}
+
+static int al_pcie_rev_id_get(struct al_pcie *pcie, unsigned int *rev_id)
+{
+	u32 dev_rev_id_val;
+	u32 dev_id_val;
+
+	dev_rev_id_val = al_pcie_controller_readl(pcie, AXI_BASE_OFFSET +
+						  DEVICE_ID_OFFSET +
+						  DEVICE_REV_ID);
+	dev_id_val = FIELD_GET(DEVICE_REV_ID_DEV_ID_MASK, dev_rev_id_val);
+
+	switch (dev_id_val) {
+	case DEVICE_REV_ID_DEV_ID_X4:
+		*rev_id = AL_PCIE_REV_ID_2;
+		break;
+	case DEVICE_REV_ID_DEV_ID_X8:
+		*rev_id = AL_PCIE_REV_ID_3;
+		break;
+	case DEVICE_REV_ID_DEV_ID_X16:
+		*rev_id = AL_PCIE_REV_ID_4;
+		break;
+	default:
+		dev_err(pcie->dev, "Unsupported dev_id_val (0x%x)\n",
+			dev_id_val);
+		return -EINVAL;
+	}
+
+	dev_dbg(pcie->dev, "dev_id_val: 0x%x\n", dev_id_val);
+
+	return 0;
+}
+
+static int al_pcie_reg_offsets_set(struct al_pcie *pcie)
+{
+	switch (pcie->controller_rev_id) {
+	case AL_PCIE_REV_ID_2:
+		pcie->reg_offsets.ob_ctrl = OB_CTRL_REV1_2_OFFSET;
+		break;
+	case AL_PCIE_REV_ID_3:
+	case AL_PCIE_REV_ID_4:
+		pcie->reg_offsets.ob_ctrl = OB_CTRL_REV3_5_OFFSET;
+		break;
+	default:
+		dev_err(pcie->dev, "Unsupported controller rev_id: 0x%x\n",
+			pcie->controller_rev_id);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static inline void al_pcie_target_bus_set(struct al_pcie *pcie,
+					  u8 target_bus,
+					  u8 mask_target_bus)
+{
+	u32 reg;
+
+	reg = FIELD_PREP(CFG_TARGET_BUS_MASK_MASK, mask_target_bus) |
+	      FIELD_PREP(CFG_TARGET_BUS_BUSNUM_MASK, target_bus);
+
+	al_pcie_controller_writel(pcie, AXI_BASE_OFFSET +
+				  pcie->reg_offsets.ob_ctrl + CFG_TARGET_BUS,
+				  reg);
+}
+
+static void __iomem *al_pcie_conf_addr_map(struct al_pcie *pcie,
+					   unsigned int busnr,
+					   unsigned int devfn)
+{
+	struct al_pcie_target_bus_cfg *target_bus_cfg = &pcie->target_bus_cfg;
+	unsigned int busnr_ecam = busnr & target_bus_cfg->ecam_mask;
+	unsigned int busnr_reg = busnr & target_bus_cfg->reg_mask;
+	struct pcie_port *pp = &pcie->pci->pp;
+	void __iomem *pci_base_addr;
+
+	pci_base_addr = (void __iomem *)((uintptr_t)pp->va_cfg0_base +
+					 (busnr_ecam << 20) +
+					 PCIE_ECAM_DEVFN(devfn));
+
+	if (busnr_reg != target_bus_cfg->reg_val) {
+		dev_dbg(pcie->pci->dev, "Changing target bus busnum val from 0x%x to 0x%x\n",
+			target_bus_cfg->reg_val, busnr_reg);
+		target_bus_cfg->reg_val = busnr_reg;
+		al_pcie_target_bus_set(pcie,
+				       target_bus_cfg->reg_val,
+				       target_bus_cfg->reg_mask);
+	}
+
+	return pci_base_addr;
+}
+
+static int al_pcie_rd_other_conf(struct pcie_port *pp, struct pci_bus *bus,
+				 unsigned int devfn, int where, int size,
+				 u32 *val)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct al_pcie *pcie = to_al_pcie(pci);
+	unsigned int busnr = bus->number;
+	void __iomem *pci_addr;
+	int rc;
+
+	pci_addr = al_pcie_conf_addr_map(pcie, busnr, devfn);
+
+	rc = dw_pcie_read(pci_addr + where, size, val);
+
+	dev_dbg(pci->dev, "%d-byte config read from %04x:%02x:%02x.%d offset 0x%x (pci_addr: 0x%px) - val:0x%x\n",
+		size, pci_domain_nr(bus), bus->number,
+		PCI_SLOT(devfn), PCI_FUNC(devfn), where,
+		(pci_addr + where), *val);
+
+	return rc;
+}
+
+static int al_pcie_wr_other_conf(struct pcie_port *pp, struct pci_bus *bus,
+				 unsigned int devfn, int where, int size,
+				 u32 val)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct al_pcie *pcie = to_al_pcie(pci);
+	unsigned int busnr = bus->number;
+	void __iomem *pci_addr;
+	int rc;
+
+	pci_addr = al_pcie_conf_addr_map(pcie, busnr, devfn);
+
+	rc = dw_pcie_write(pci_addr + where, size, val);
+
+	dev_dbg(pci->dev, "%d-byte config write to %04x:%02x:%02x.%d offset 0x%x (pci_addr: 0x%px) - val:0x%x\n",
+		size, pci_domain_nr(bus), bus->number,
+		PCI_SLOT(devfn), PCI_FUNC(devfn), where,
+		(pci_addr + where), val);
+
+	return rc;
+}
+
+static void al_pcie_config_prepare(struct al_pcie *pcie)
+{
+	struct al_pcie_target_bus_cfg *target_bus_cfg;
+	struct pcie_port *pp = &pcie->pci->pp;
+	unsigned int ecam_bus_mask;
+	u32 cfg_control_offset;
+	u8 subordinate_bus;
+	u8 secondary_bus;
+	u32 cfg_control;
+	u32 reg;
+
+	target_bus_cfg = &pcie->target_bus_cfg;
+
+	ecam_bus_mask = (pcie->ecam_size >> 20) - 1;
+	if (ecam_bus_mask > 255) {
+		dev_warn(pcie->dev, "ECAM window size is larger than 256MB. Cutting off at 256\n");
+		ecam_bus_mask = 255;
+	}
+
+	/* This portion is taken from the transaction address */
+	target_bus_cfg->ecam_mask = ecam_bus_mask;
+	/* This portion is taken from the cfg_target_bus reg */
+	target_bus_cfg->reg_mask = ~target_bus_cfg->ecam_mask;
+	target_bus_cfg->reg_val = pp->busn->start & target_bus_cfg->reg_mask;
+
+	al_pcie_target_bus_set(pcie, target_bus_cfg->reg_val,
+			       target_bus_cfg->reg_mask);
+
+	secondary_bus = pp->busn->start + 1;
+	subordinate_bus = pp->busn->end;
+
+	/* Set the valid values of secondary and subordinate buses */
+	cfg_control_offset = AXI_BASE_OFFSET + pcie->reg_offsets.ob_ctrl +
+			     CFG_CONTROL;
+
+	cfg_control = al_pcie_controller_readl(pcie, cfg_control_offset);
+
+	reg = cfg_control &
+	      ~(CFG_CONTROL_SEC_BUS_MASK | CFG_CONTROL_SUBBUS_MASK);
+
+	reg |= FIELD_PREP(CFG_CONTROL_SUBBUS_MASK, subordinate_bus) |
+	       FIELD_PREP(CFG_CONTROL_SEC_BUS_MASK, secondary_bus);
+
+	al_pcie_controller_writel(pcie, cfg_control_offset, reg);
+}
+
+static int al_pcie_host_init(struct pcie_port *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct al_pcie *pcie = to_al_pcie(pci);
+	int rc;
+
+	rc = al_pcie_rev_id_get(pcie, &pcie->controller_rev_id);
+	if (rc)
+		return rc;
+
+	rc = al_pcie_reg_offsets_set(pcie);
+	if (rc)
+		return rc;
+
+	al_pcie_config_prepare(pcie);
+
+	return 0;
+}
+
+static const struct dw_pcie_host_ops al_pcie_host_ops = {
+	.rd_other_conf = al_pcie_rd_other_conf,
+	.wr_other_conf = al_pcie_wr_other_conf,
+	.host_init = al_pcie_host_init,
+};
+
+static int al_add_pcie_port(struct pcie_port *pp,
+			    struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	pp->ops = &al_pcie_host_ops;
+
+	ret = dw_pcie_host_init(pp);
+	if (ret) {
+		dev_err(dev, "failed to initialize host\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct dw_pcie_ops dw_pcie_ops = {
+};
+
+static int al_pcie_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct resource *controller_res;
+	struct resource *ecam_res;
+	struct resource *dbi_res;
+	struct al_pcie *al_pcie;
+	struct dw_pcie *pci;
+
+	al_pcie = devm_kzalloc(dev, sizeof(*al_pcie), GFP_KERNEL);
+	if (!al_pcie)
+		return -ENOMEM;
+
+	pci = devm_kzalloc(dev, sizeof(*pci), GFP_KERNEL);
+	if (!pci)
+		return -ENOMEM;
+
+	pci->dev = dev;
+	pci->ops = &dw_pcie_ops;
+
+	al_pcie->pci = pci;
+	al_pcie->dev = dev;
+
+	dbi_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi");
+	pci->dbi_base = devm_pci_remap_cfg_resource(dev, dbi_res);
+	if (IS_ERR(pci->dbi_base)) {
+		dev_err(dev, "couldn't remap dbi base %pR\n", dbi_res);
+		return PTR_ERR(pci->dbi_base);
+	}
+
+	ecam_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "config");
+	if (!ecam_res) {
+		dev_err(dev, "couldn't find 'config' reg in DT\n");
+		return -ENOENT;
+	}
+	al_pcie->ecam_size = resource_size(ecam_res);
+
+	controller_res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						      "controller");
+	al_pcie->controller_base = devm_ioremap_resource(dev, controller_res);
+	if (IS_ERR(al_pcie->controller_base)) {
+		dev_err(dev, "couldn't remap controller base %pR\n",
+			controller_res);
+		return PTR_ERR(al_pcie->controller_base);
+	}
+
+	dev_dbg(dev, "From DT: dbi_base: %pR, controller_base: %pR\n",
+		dbi_res, controller_res);
+
+	platform_set_drvdata(pdev, al_pcie);
+
+	return al_add_pcie_port(&pci->pp, pdev);
+}
+
+static const struct of_device_id al_pcie_of_match[] = {
+	{ .compatible = "amazon,al-alpine-v2-pcie",
+	},
+	{ .compatible = "amazon,al-alpine-v3-pcie",
+	},
+	{},
+};
+
+static struct platform_driver al_pcie_driver = {
+	.driver = {
+		.name	= "al-pcie",
+		.of_match_table = al_pcie_of_match,
+		.suppress_bind_attrs = true,
+	},
+	.probe = al_pcie_probe,
+};
+builtin_platform_driver(al_pcie_driver);
+
+#endif /* CONFIG_PCIE_AL*/
diff --git a/drivers/pci/controller/dwc/pcie-armada8k.c b/drivers/pci/controller/dwc/pcie-armada8k.c
index 0c389a30..4959654 100644
--- a/drivers/pci/controller/dwc/pcie-armada8k.c
+++ b/drivers/pci/controller/dwc/pcie-armada8k.c
@@ -25,10 +25,14 @@
 
 #include "pcie-designware.h"
 
+#define ARMADA8K_PCIE_MAX_LANES PCIE_LNK_X4
+
 struct armada8k_pcie {
 	struct dw_pcie *pci;
 	struct clk *clk;
 	struct clk *clk_reg;
+	struct phy *phy[ARMADA8K_PCIE_MAX_LANES];
+	unsigned int phy_count;
 };
 
 #define PCIE_VENDOR_REGS_OFFSET		0x8000
@@ -55,7 +59,7 @@
 #define PCIE_ARUSER_REG			(PCIE_VENDOR_REGS_OFFSET + 0x5C)
 #define PCIE_AWUSER_REG			(PCIE_VENDOR_REGS_OFFSET + 0x60)
 /*
- * AR/AW Cache defauls: Normal memory, Write-Back, Read / Write
+ * AR/AW Cache defaults: Normal memory, Write-Back, Read / Write
  * allocate
  */
 #define ARCACHE_DEFAULT_VALUE		0x3511
@@ -67,6 +71,75 @@
 
 #define to_armada8k_pcie(x)	dev_get_drvdata((x)->dev)
 
+static void armada8k_pcie_disable_phys(struct armada8k_pcie *pcie)
+{
+	int i;
+
+	for (i = 0; i < ARMADA8K_PCIE_MAX_LANES; i++) {
+		phy_power_off(pcie->phy[i]);
+		phy_exit(pcie->phy[i]);
+	}
+}
+
+static int armada8k_pcie_enable_phys(struct armada8k_pcie *pcie)
+{
+	int ret;
+	int i;
+
+	for (i = 0; i < ARMADA8K_PCIE_MAX_LANES; i++) {
+		ret = phy_init(pcie->phy[i]);
+		if (ret)
+			return ret;
+
+		ret = phy_set_mode_ext(pcie->phy[i], PHY_MODE_PCIE,
+				       pcie->phy_count);
+		if (ret) {
+			phy_exit(pcie->phy[i]);
+			return ret;
+		}
+
+		ret = phy_power_on(pcie->phy[i]);
+		if (ret) {
+			phy_exit(pcie->phy[i]);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int armada8k_pcie_setup_phys(struct armada8k_pcie *pcie)
+{
+	struct dw_pcie *pci = pcie->pci;
+	struct device *dev = pci->dev;
+	struct device_node *node = dev->of_node;
+	int ret = 0;
+	int i;
+
+	for (i = 0; i < ARMADA8K_PCIE_MAX_LANES; i++) {
+		pcie->phy[i] = devm_of_phy_get_by_index(dev, node, i);
+		if (IS_ERR(pcie->phy[i])) {
+			if (PTR_ERR(pcie->phy[i]) != -ENODEV)
+				return PTR_ERR(pcie->phy[i]);
+
+			pcie->phy[i] = NULL;
+			continue;
+		}
+
+		pcie->phy_count++;
+	}
+
+	/* Old bindings miss the PHY handle, so just warn if there is no PHY */
+	if (!pcie->phy_count)
+		dev_warn(dev, "No available PHY\n");
+
+	ret = armada8k_pcie_enable_phys(pcie);
+	if (ret)
+		dev_err(dev, "Failed to initialize PHY(s) (%d)\n", ret);
+
+	return ret;
+}
+
 static int armada8k_pcie_link_up(struct dw_pcie *pci)
 {
 	u32 reg;
@@ -249,14 +322,20 @@
 		goto fail_clkreg;
 	}
 
+	ret = armada8k_pcie_setup_phys(pcie);
+	if (ret)
+		goto fail_clkreg;
+
 	platform_set_drvdata(pdev, pcie);
 
 	ret = armada8k_add_pcie_port(pcie, pdev);
 	if (ret)
-		goto fail_clkreg;
+		goto disable_phy;
 
 	return 0;
 
+disable_phy:
+	armada8k_pcie_disable_phys(pcie);
 fail_clkreg:
 	clk_disable_unprepare(pcie->clk_reg);
 fail:
diff --git a/drivers/pci/controller/dwc/pcie-artpec6.c b/drivers/pci/controller/dwc/pcie-artpec6.c
index dba83ab..d00252b 100644
--- a/drivers/pci/controller/dwc/pcie-artpec6.c
+++ b/drivers/pci/controller/dwc/pcie-artpec6.c
@@ -444,7 +444,7 @@
 	return 0;
 }
 
-static struct dw_pcie_ep_ops pcie_ep_ops = {
+static const struct dw_pcie_ep_ops pcie_ep_ops = {
 	.ep_init = artpec6_pcie_ep_init,
 	.raise_irq = artpec6_pcie_raise_irq,
 };
diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index de8635a..3dd2e26 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -40,39 +40,6 @@
 	__dw_pcie_ep_reset_bar(pci, bar, 0);
 }
 
-static u8 __dw_pcie_ep_find_next_cap(struct dw_pcie *pci, u8 cap_ptr,
-			      u8 cap)
-{
-	u8 cap_id, next_cap_ptr;
-	u16 reg;
-
-	reg = dw_pcie_readw_dbi(pci, cap_ptr);
-	next_cap_ptr = (reg & 0xff00) >> 8;
-	cap_id = (reg & 0x00ff);
-
-	if (!next_cap_ptr || cap_id > PCI_CAP_ID_MAX)
-		return 0;
-
-	if (cap_id == cap)
-		return cap_ptr;
-
-	return __dw_pcie_ep_find_next_cap(pci, next_cap_ptr, cap);
-}
-
-static u8 dw_pcie_ep_find_capability(struct dw_pcie *pci, u8 cap)
-{
-	u8 next_cap_ptr;
-	u16 reg;
-
-	reg = dw_pcie_readw_dbi(pci, PCI_CAPABILITY_LIST);
-	next_cap_ptr = (reg & 0x00ff);
-
-	if (!next_cap_ptr)
-		return 0;
-
-	return __dw_pcie_ep_find_next_cap(pci, next_cap_ptr, cap);
-}
-
 static int dw_pcie_ep_write_header(struct pci_epc *epc, u8 func_no,
 				   struct pci_epf_header *hdr)
 {
@@ -355,6 +322,17 @@
 	return pci->ops->start_link(pci);
 }
 
+static const struct pci_epc_features*
+dw_pcie_ep_get_features(struct pci_epc *epc, u8 func_no)
+{
+	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
+
+	if (!ep->ops->get_features)
+		return NULL;
+
+	return ep->ops->get_features(ep);
+}
+
 static const struct pci_epc_ops epc_ops = {
 	.write_header		= dw_pcie_ep_write_header,
 	.set_bar		= dw_pcie_ep_set_bar,
@@ -368,6 +346,7 @@
 	.raise_irq		= dw_pcie_ep_raise_irq,
 	.start			= dw_pcie_ep_start,
 	.stop			= dw_pcie_ep_stop,
+	.get_features		= dw_pcie_ep_get_features,
 };
 
 int dw_pcie_ep_raise_legacy_irq(struct dw_pcie_ep *ep, u8 func_no)
@@ -385,6 +364,7 @@
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct pci_epc *epc = ep->epc;
+	unsigned int aligned_offset;
 	u16 msg_ctrl, msg_data;
 	u32 msg_addr_lower, msg_addr_upper, reg;
 	u64 msg_addr;
@@ -410,13 +390,15 @@
 		reg = ep->msi_cap + PCI_MSI_DATA_32;
 		msg_data = dw_pcie_readw_dbi(pci, reg);
 	}
-	msg_addr = ((u64) msg_addr_upper) << 32 | msg_addr_lower;
+	aligned_offset = msg_addr_lower & (epc->mem->page_size - 1);
+	msg_addr = ((u64)msg_addr_upper) << 32 |
+			(msg_addr_lower & ~aligned_offset);
 	ret = dw_pcie_ep_map_addr(epc, func_no, ep->msi_mem_phys, msg_addr,
 				  epc->mem->page_size);
 	if (ret)
 		return ret;
 
-	writel(msg_data | (interrupt_num - 1), ep->msi_mem);
+	writel(msg_data | (interrupt_num - 1), ep->msi_mem + aligned_offset);
 
 	dw_pcie_ep_unmap_addr(epc, func_no, ep->msi_mem_phys);
 
@@ -465,8 +447,10 @@
 
 	iounmap(msix_tbl);
 
-	if (vec_ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT)
+	if (vec_ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT) {
+		dev_dbg(pci->dev, "MSI-X entry ctrl set\n");
 		return -EPERM;
+	}
 
 	ret = dw_pcie_ep_map_addr(epc, func_no, ep->msi_mem_phys, msg_addr,
 				  epc->mem->page_size);
@@ -490,10 +474,33 @@
 	pci_epc_mem_exit(epc);
 }
 
+static unsigned int dw_pcie_ep_find_ext_capability(struct dw_pcie *pci, int cap)
+{
+	u32 header;
+	int pos = PCI_CFG_SPACE_SIZE;
+
+	while (pos) {
+		header = dw_pcie_readl_dbi(pci, pos);
+		if (PCI_EXT_CAP_ID(header) == cap)
+			return pos;
+
+		pos = PCI_EXT_CAP_NEXT(header);
+		if (!pos)
+			break;
+	}
+
+	return 0;
+}
+
 int dw_pcie_ep_init(struct dw_pcie_ep *ep)
 {
+	int i;
 	int ret;
+	u32 reg;
 	void *addr;
+	u8 hdr_type;
+	unsigned int nbars;
+	unsigned int offset;
 	struct pci_epc *epc;
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct device *dev = pci->dev;
@@ -556,6 +563,13 @@
 	if (ep->ops->ep_init)
 		ep->ops->ep_init(ep);
 
+	hdr_type = dw_pcie_readb_dbi(pci, PCI_HEADER_TYPE);
+	if (hdr_type != PCI_HEADER_TYPE_NORMAL) {
+		dev_err(pci->dev, "PCIe controller is not set to EP mode (hdr_type:0x%x)!\n",
+			hdr_type);
+		return -EIO;
+	}
+
 	ret = of_property_read_u8(np, "max-functions", &epc->max_functions);
 	if (ret < 0)
 		epc->max_functions = 1;
@@ -573,9 +587,21 @@
 		dev_err(dev, "Failed to reserve memory for MSI/MSI-X\n");
 		return -ENOMEM;
 	}
-	ep->msi_cap = dw_pcie_ep_find_capability(pci, PCI_CAP_ID_MSI);
+	ep->msi_cap = dw_pcie_find_capability(pci, PCI_CAP_ID_MSI);
 
-	ep->msix_cap = dw_pcie_ep_find_capability(pci, PCI_CAP_ID_MSIX);
+	ep->msix_cap = dw_pcie_find_capability(pci, PCI_CAP_ID_MSIX);
+
+	offset = dw_pcie_ep_find_ext_capability(pci, PCI_EXT_CAP_ID_REBAR);
+	if (offset) {
+		reg = dw_pcie_readl_dbi(pci, offset + PCI_REBAR_CTRL);
+		nbars = (reg & PCI_REBAR_CTRL_NBAR_MASK) >>
+			PCI_REBAR_CTRL_NBAR_SHIFT;
+
+		dw_pcie_dbi_ro_wr_en(pci);
+		for (i = 0; i < nbars; i++, offset += PCI_REBAR_CTRL)
+			dw_pcie_writel_dbi(pci, offset + PCI_REBAR_CAP, 0x0);
+		dw_pcie_dbi_ro_wr_dis(pci);
+	}
 
 	dw_pcie_setup(pci);
 
diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index 29a0575..0f36a92 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -99,9 +99,6 @@
 					       (i * MAX_MSI_IRQS_PER_CTRL) +
 					       pos);
 			generic_handle_irq(irq);
-			dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_STATUS +
-						(i * MSI_REG_CTRL_BLOCK_SIZE),
-					    4, 1 << pos);
 			pos++;
 		}
 	}
@@ -123,90 +120,77 @@
 	chained_irq_exit(chip, desc);
 }
 
-static void dw_pci_setup_msi_msg(struct irq_data *data, struct msi_msg *msg)
+static void dw_pci_setup_msi_msg(struct irq_data *d, struct msi_msg *msg)
 {
-	struct pcie_port *pp = irq_data_get_irq_chip_data(data);
+	struct pcie_port *pp = irq_data_get_irq_chip_data(d);
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	u64 msi_target;
 
-	if (pp->ops->get_msi_addr)
-		msi_target = pp->ops->get_msi_addr(pp);
-	else
-		msi_target = (u64)pp->msi_data;
+	msi_target = (u64)pp->msi_data;
 
 	msg->address_lo = lower_32_bits(msi_target);
 	msg->address_hi = upper_32_bits(msi_target);
 
-	if (pp->ops->get_msi_data)
-		msg->data = pp->ops->get_msi_data(pp, data->hwirq);
-	else
-		msg->data = data->hwirq;
+	msg->data = d->hwirq;
 
 	dev_dbg(pci->dev, "msi#%d address_hi %#x address_lo %#x\n",
-		(int)data->hwirq, msg->address_hi, msg->address_lo);
+		(int)d->hwirq, msg->address_hi, msg->address_lo);
 }
 
-static int dw_pci_msi_set_affinity(struct irq_data *irq_data,
+static int dw_pci_msi_set_affinity(struct irq_data *d,
 				   const struct cpumask *mask, bool force)
 {
 	return -EINVAL;
 }
 
-static void dw_pci_bottom_mask(struct irq_data *data)
+static void dw_pci_bottom_mask(struct irq_data *d)
 {
-	struct pcie_port *pp = irq_data_get_irq_chip_data(data);
+	struct pcie_port *pp = irq_data_get_irq_chip_data(d);
 	unsigned int res, bit, ctrl;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&pp->lock, flags);
 
-	if (pp->ops->msi_clear_irq) {
-		pp->ops->msi_clear_irq(pp, data->hwirq);
-	} else {
-		ctrl = data->hwirq / MAX_MSI_IRQS_PER_CTRL;
-		res = ctrl * MSI_REG_CTRL_BLOCK_SIZE;
-		bit = data->hwirq % MAX_MSI_IRQS_PER_CTRL;
+	ctrl = d->hwirq / MAX_MSI_IRQS_PER_CTRL;
+	res = ctrl * MSI_REG_CTRL_BLOCK_SIZE;
+	bit = d->hwirq % MAX_MSI_IRQS_PER_CTRL;
 
-		pp->irq_status[ctrl] &= ~(1 << bit);
-		dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_ENABLE + res, 4,
-				    pp->irq_status[ctrl]);
-	}
+	pp->irq_mask[ctrl] |= BIT(bit);
+	dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_MASK + res, 4,
+			    pp->irq_mask[ctrl]);
 
 	raw_spin_unlock_irqrestore(&pp->lock, flags);
 }
 
-static void dw_pci_bottom_unmask(struct irq_data *data)
+static void dw_pci_bottom_unmask(struct irq_data *d)
 {
-	struct pcie_port *pp = irq_data_get_irq_chip_data(data);
+	struct pcie_port *pp = irq_data_get_irq_chip_data(d);
 	unsigned int res, bit, ctrl;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&pp->lock, flags);
 
-	if (pp->ops->msi_set_irq) {
-		pp->ops->msi_set_irq(pp, data->hwirq);
-	} else {
-		ctrl = data->hwirq / MAX_MSI_IRQS_PER_CTRL;
-		res = ctrl * MSI_REG_CTRL_BLOCK_SIZE;
-		bit = data->hwirq % MAX_MSI_IRQS_PER_CTRL;
+	ctrl = d->hwirq / MAX_MSI_IRQS_PER_CTRL;
+	res = ctrl * MSI_REG_CTRL_BLOCK_SIZE;
+	bit = d->hwirq % MAX_MSI_IRQS_PER_CTRL;
 
-		pp->irq_status[ctrl] |= 1 << bit;
-		dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_ENABLE + res, 4,
-				    pp->irq_status[ctrl]);
-	}
+	pp->irq_mask[ctrl] &= ~BIT(bit);
+	dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_MASK + res, 4,
+			    pp->irq_mask[ctrl]);
 
 	raw_spin_unlock_irqrestore(&pp->lock, flags);
 }
 
 static void dw_pci_bottom_ack(struct irq_data *d)
 {
-	struct msi_desc *msi = irq_data_get_msi_desc(d);
-	struct pcie_port *pp;
+	struct pcie_port *pp  = irq_data_get_irq_chip_data(d);
+	unsigned int res, bit, ctrl;
 
-	pp = msi_desc_to_pci_sysdata(msi);
+	ctrl = d->hwirq / MAX_MSI_IRQS_PER_CTRL;
+	res = ctrl * MSI_REG_CTRL_BLOCK_SIZE;
+	bit = d->hwirq % MAX_MSI_IRQS_PER_CTRL;
 
-	if (pp->ops->msi_irq_ack)
-		pp->ops->msi_irq_ack(d->hwirq, pp);
+	dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_STATUS + res, 4, BIT(bit));
 }
 
 static struct irq_chip dw_pci_msi_bottom_irq_chip = {
@@ -239,7 +223,7 @@
 
 	for (i = 0; i < nr_irqs; i++)
 		irq_domain_set_info(domain, virq + i, bit + i,
-				    &dw_pci_msi_bottom_irq_chip,
+				    pp->msi_irq_chip,
 				    pp, handle_edge_irq,
 				    NULL, NULL);
 
@@ -249,13 +233,13 @@
 static void dw_pcie_irq_domain_free(struct irq_domain *domain,
 				    unsigned int virq, unsigned int nr_irqs)
 {
-	struct irq_data *data = irq_domain_get_irq_data(domain, virq);
-	struct pcie_port *pp = irq_data_get_irq_chip_data(data);
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+	struct pcie_port *pp = irq_data_get_irq_chip_data(d);
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&pp->lock, flags);
 
-	bitmap_release_region(pp->msi_irq_in_use, data->hwirq,
+	bitmap_release_region(pp->msi_irq_in_use, d->hwirq,
 			      order_base_2(nr_irqs));
 
 	raw_spin_unlock_irqrestore(&pp->lock, flags);
@@ -292,25 +276,31 @@
 
 void dw_pcie_free_msi(struct pcie_port *pp)
 {
-	irq_set_chained_handler(pp->msi_irq, NULL);
-	irq_set_handler_data(pp->msi_irq, NULL);
+	if (pp->msi_irq) {
+		irq_set_chained_handler(pp->msi_irq, NULL);
+		irq_set_handler_data(pp->msi_irq, NULL);
+	}
 
 	irq_domain_remove(pp->msi_domain);
 	irq_domain_remove(pp->irq_domain);
+
+	if (pp->msi_page)
+		__free_page(pp->msi_page);
 }
 
 void dw_pcie_msi_init(struct pcie_port *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct device *dev = pci->dev;
-	struct page *page;
 	u64 msi_target;
 
-	page = alloc_page(GFP_KERNEL);
-	pp->msi_data = dma_map_page(dev, page, 0, PAGE_SIZE, DMA_FROM_DEVICE);
+	pp->msi_page = alloc_page(GFP_KERNEL);
+	pp->msi_data = dma_map_page(dev, pp->msi_page, 0, PAGE_SIZE,
+				    DMA_FROM_DEVICE);
 	if (dma_mapping_error(dev, pp->msi_data)) {
 		dev_err(dev, "Failed to map MSI data\n");
-		__free_page(page);
+		__free_page(pp->msi_page);
+		pp->msi_page = NULL;
 		return;
 	}
 	msi_target = (u64)pp->msi_data;
@@ -321,6 +311,7 @@
 	dw_pcie_wr_own_conf(pp, PCIE_MSI_ADDR_HI, 4,
 			    upper_32_bits(msi_target));
 }
+EXPORT_SYMBOL_GPL(dw_pcie_msi_init);
 
 int dw_pcie_host_init(struct pcie_port *pp)
 {
@@ -329,9 +320,10 @@
 	struct device_node *np = dev->of_node;
 	struct platform_device *pdev = to_platform_device(dev);
 	struct resource_entry *win, *tmp;
-	struct pci_bus *bus, *child;
+	struct pci_bus *child;
 	struct pci_host_bridge *bridge;
 	struct resource *cfg_res;
+	u32 hdr_type;
 	int ret;
 
 	raw_spin_lock_init(&pci->pp.lock);
@@ -346,7 +338,7 @@
 		dev_err(dev, "Missing *config* reg space\n");
 	}
 
-	bridge = pci_alloc_host_bridge(0);
+	bridge = devm_pci_alloc_host_bridge(dev, 0);
 	if (!bridge)
 		return -ENOMEM;
 
@@ -357,7 +349,7 @@
 
 	ret = devm_request_pci_bus_resources(dev, &bridge->windows);
 	if (ret)
-		goto error;
+		return ret;
 
 	/* Get the I/O and memory ranges from DT */
 	resource_list_for_each_entry_safe(win, tmp, &bridge->windows) {
@@ -401,8 +393,7 @@
 						resource_size(pp->cfg));
 		if (!pci->dbi_base) {
 			dev_err(dev, "Error with ioremap\n");
-			ret = -ENOMEM;
-			goto error;
+			return -ENOMEM;
 		}
 	}
 
@@ -413,8 +404,7 @@
 					pp->cfg0_base, pp->cfg0_size);
 		if (!pp->va_cfg0_base) {
 			dev_err(dev, "Error with ioremap in function\n");
-			ret = -ENOMEM;
-			goto error;
+			return -ENOMEM;
 		}
 	}
 
@@ -424,8 +414,7 @@
 						pp->cfg1_size);
 		if (!pp->va_cfg1_base) {
 			dev_err(dev, "Error with ioremap\n");
-			ret = -ENOMEM;
-			goto error;
+			return -ENOMEM;
 		}
 	}
 
@@ -433,7 +422,7 @@
 	if (ret)
 		pci->num_viewport = 2;
 
-	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+	if (pci_msi_enabled()) {
 		/*
 		 * If a specific SoC driver needs to change the
 		 * default number of vectors, it needs to implement
@@ -448,14 +437,16 @@
 			    pp->num_vectors == 0) {
 				dev_err(dev,
 					"Invalid number of vectors\n");
-				goto error;
+				return -EINVAL;
 			}
 		}
 
 		if (!pp->ops->msi_host_init) {
+			pp->msi_irq_chip = &dw_pci_msi_bottom_irq_chip;
+
 			ret = dw_pcie_allocate_domains(pp);
 			if (ret)
-				goto error;
+				return ret;
 
 			if (pp->msi_irq)
 				irq_set_chained_handler_and_data(pp->msi_irq,
@@ -464,14 +455,29 @@
 		} else {
 			ret = pp->ops->msi_host_init(pp);
 			if (ret < 0)
-				goto error;
+				return ret;
 		}
 	}
 
 	if (pp->ops->host_init) {
 		ret = pp->ops->host_init(pp);
 		if (ret)
-			goto error;
+			goto err_free_msi;
+	}
+
+	ret = dw_pcie_rd_own_conf(pp, PCI_HEADER_TYPE, 1, &hdr_type);
+	if (ret != PCIBIOS_SUCCESSFUL) {
+		dev_err(pci->dev, "Failed reading PCI_HEADER_TYPE cfg space reg (ret: 0x%x)\n",
+			ret);
+		ret = pcibios_err_to_errno(ret);
+		goto err_free_msi;
+	}
+	if (hdr_type != PCI_HEADER_TYPE_BRIDGE) {
+		dev_err(pci->dev,
+			"PCIe controller is not set to bridge type (hdr_type: 0x%x)!\n",
+			hdr_type);
+		ret = -EIO;
+		goto err_free_msi;
 	}
 
 	pp->root_bus_nr = pp->busn->start;
@@ -485,103 +491,99 @@
 
 	ret = pci_scan_root_bus_bridge(bridge);
 	if (ret)
-		goto error;
+		goto err_free_msi;
 
-	bus = bridge->bus;
+	pp->root_bus = bridge->bus;
 
 	if (pp->ops->scan_bus)
 		pp->ops->scan_bus(pp);
 
-	pci_bus_size_bridges(bus);
-	pci_bus_assign_resources(bus);
+	pci_bus_size_bridges(pp->root_bus);
+	pci_bus_assign_resources(pp->root_bus);
 
-	list_for_each_entry(child, &bus->children, node)
+	list_for_each_entry(child, &pp->root_bus->children, node)
 		pcie_bus_configure_settings(child);
 
-	pci_bus_add_devices(bus);
+	pci_bus_add_devices(pp->root_bus);
 	return 0;
 
-error:
-	pci_free_host_bridge(bridge);
+err_free_msi:
+	if (pci_msi_enabled() && !pp->ops->msi_host_init)
+		dw_pcie_free_msi(pp);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dw_pcie_host_init);
+
+void dw_pcie_host_deinit(struct pcie_port *pp)
+{
+	pci_stop_root_bus(pp->root_bus);
+	pci_remove_root_bus(pp->root_bus);
+	if (pci_msi_enabled() && !pp->ops->msi_host_init)
+		dw_pcie_free_msi(pp);
+}
+EXPORT_SYMBOL_GPL(dw_pcie_host_deinit);
+
+static int dw_pcie_access_other_conf(struct pcie_port *pp, struct pci_bus *bus,
+				     u32 devfn, int where, int size, u32 *val,
+				     bool write)
+{
+	int ret, type;
+	u32 busdev, cfg_size;
+	u64 cpu_addr;
+	void __iomem *va_cfg_base;
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+
+	busdev = PCIE_ATU_BUS(bus->number) | PCIE_ATU_DEV(PCI_SLOT(devfn)) |
+		 PCIE_ATU_FUNC(PCI_FUNC(devfn));
+
+	if (bus->parent->number == pp->root_bus_nr) {
+		type = PCIE_ATU_TYPE_CFG0;
+		cpu_addr = pp->cfg0_base;
+		cfg_size = pp->cfg0_size;
+		va_cfg_base = pp->va_cfg0_base;
+	} else {
+		type = PCIE_ATU_TYPE_CFG1;
+		cpu_addr = pp->cfg1_base;
+		cfg_size = pp->cfg1_size;
+		va_cfg_base = pp->va_cfg1_base;
+	}
+
+	dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX1,
+				  type, cpu_addr,
+				  busdev, cfg_size);
+	if (write)
+		ret = dw_pcie_write(va_cfg_base + where, size, *val);
+	else
+		ret = dw_pcie_read(va_cfg_base + where, size, val);
+
+	if (pci->num_viewport <= 2)
+		dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX1,
+					  PCIE_ATU_TYPE_IO, pp->io_base,
+					  pp->io_bus_addr, pp->io_size);
+
 	return ret;
 }
 
 static int dw_pcie_rd_other_conf(struct pcie_port *pp, struct pci_bus *bus,
 				 u32 devfn, int where, int size, u32 *val)
 {
-	int ret, type;
-	u32 busdev, cfg_size;
-	u64 cpu_addr;
-	void __iomem *va_cfg_base;
-	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
-
 	if (pp->ops->rd_other_conf)
-		return pp->ops->rd_other_conf(pp, bus, devfn, where, size, val);
+		return pp->ops->rd_other_conf(pp, bus, devfn, where,
+					      size, val);
 
-	busdev = PCIE_ATU_BUS(bus->number) | PCIE_ATU_DEV(PCI_SLOT(devfn)) |
-		 PCIE_ATU_FUNC(PCI_FUNC(devfn));
-
-	if (bus->parent->number == pp->root_bus_nr) {
-		type = PCIE_ATU_TYPE_CFG0;
-		cpu_addr = pp->cfg0_base;
-		cfg_size = pp->cfg0_size;
-		va_cfg_base = pp->va_cfg0_base;
-	} else {
-		type = PCIE_ATU_TYPE_CFG1;
-		cpu_addr = pp->cfg1_base;
-		cfg_size = pp->cfg1_size;
-		va_cfg_base = pp->va_cfg1_base;
-	}
-
-	dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX1,
-				  type, cpu_addr,
-				  busdev, cfg_size);
-	ret = dw_pcie_read(va_cfg_base + where, size, val);
-	if (pci->num_viewport <= 2)
-		dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX1,
-					  PCIE_ATU_TYPE_IO, pp->io_base,
-					  pp->io_bus_addr, pp->io_size);
-
-	return ret;
+	return dw_pcie_access_other_conf(pp, bus, devfn, where, size, val,
+					 false);
 }
 
 static int dw_pcie_wr_other_conf(struct pcie_port *pp, struct pci_bus *bus,
 				 u32 devfn, int where, int size, u32 val)
 {
-	int ret, type;
-	u32 busdev, cfg_size;
-	u64 cpu_addr;
-	void __iomem *va_cfg_base;
-	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
-
 	if (pp->ops->wr_other_conf)
-		return pp->ops->wr_other_conf(pp, bus, devfn, where, size, val);
+		return pp->ops->wr_other_conf(pp, bus, devfn, where,
+					      size, val);
 
-	busdev = PCIE_ATU_BUS(bus->number) | PCIE_ATU_DEV(PCI_SLOT(devfn)) |
-		 PCIE_ATU_FUNC(PCI_FUNC(devfn));
-
-	if (bus->parent->number == pp->root_bus_nr) {
-		type = PCIE_ATU_TYPE_CFG0;
-		cpu_addr = pp->cfg0_base;
-		cfg_size = pp->cfg0_size;
-		va_cfg_base = pp->va_cfg0_base;
-	} else {
-		type = PCIE_ATU_TYPE_CFG1;
-		cpu_addr = pp->cfg1_base;
-		cfg_size = pp->cfg1_size;
-		va_cfg_base = pp->va_cfg1_base;
-	}
-
-	dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX1,
-				  type, cpu_addr,
-				  busdev, cfg_size);
-	ret = dw_pcie_write(va_cfg_base + where, size, val);
-	if (pci->num_viewport <= 2)
-		dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX1,
-					  PCIE_ATU_TYPE_IO, pp->io_base,
-					  pp->io_bus_addr, pp->io_size);
-
-	return ret;
+	return dw_pcie_access_other_conf(pp, bus, devfn, where, size, &val,
+					 true);
 }
 
 static int dw_pcie_valid_device(struct pcie_port *pp, struct pci_bus *bus,
@@ -637,43 +639,43 @@
 	.write = dw_pcie_wr_conf,
 };
 
-static u8 dw_pcie_iatu_unroll_enabled(struct dw_pcie *pci)
-{
-	u32 val;
-
-	val = dw_pcie_readl_dbi(pci, PCIE_ATU_VIEWPORT);
-	if (val == 0xffffffff)
-		return 1;
-
-	return 0;
-}
-
 void dw_pcie_setup_rc(struct pcie_port *pp)
 {
 	u32 val, ctrl, num_ctrls;
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 
+	/*
+	 * Enable DBI read-only registers for writing/updating configuration.
+	 * Write permission gets disabled towards the end of this function.
+	 */
+	dw_pcie_dbi_ro_wr_en(pci);
+
 	dw_pcie_setup(pci);
 
-	num_ctrls = pp->num_vectors / MAX_MSI_IRQS_PER_CTRL;
+	if (!pp->ops->msi_host_init) {
+		num_ctrls = pp->num_vectors / MAX_MSI_IRQS_PER_CTRL;
 
-	/* Initialize IRQ Status array */
-	for (ctrl = 0; ctrl < num_ctrls; ctrl++)
-		dw_pcie_rd_own_conf(pp, PCIE_MSI_INTR0_ENABLE +
-					(ctrl * MSI_REG_CTRL_BLOCK_SIZE),
-				    4, &pp->irq_status[ctrl]);
+		/* Initialize IRQ Status array */
+		for (ctrl = 0; ctrl < num_ctrls; ctrl++) {
+			pp->irq_mask[ctrl] = ~0;
+			dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_MASK +
+					    (ctrl * MSI_REG_CTRL_BLOCK_SIZE),
+					    4, pp->irq_mask[ctrl]);
+			dw_pcie_wr_own_conf(pp, PCIE_MSI_INTR0_ENABLE +
+					    (ctrl * MSI_REG_CTRL_BLOCK_SIZE),
+					    4, ~0);
+		}
+	}
 
 	/* Setup RC BARs */
 	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 0x00000004);
 	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_1, 0x00000000);
 
 	/* Setup interrupt pins */
-	dw_pcie_dbi_ro_wr_en(pci);
 	val = dw_pcie_readl_dbi(pci, PCI_INTERRUPT_LINE);
 	val &= 0xffff00ff;
 	val |= 0x00000100;
 	dw_pcie_writel_dbi(pci, PCI_INTERRUPT_LINE, val);
-	dw_pcie_dbi_ro_wr_dis(pci);
 
 	/* Setup bus numbers */
 	val = dw_pcie_readl_dbi(pci, PCI_PRIMARY_BUS);
@@ -694,11 +696,6 @@
 	 * we should not program the ATU here.
 	 */
 	if (!pp->ops->rd_other_conf) {
-		/* Get iATU unroll support */
-		pci->iatu_unroll_enabled = dw_pcie_iatu_unroll_enabled(pci);
-		dev_dbg(pci->dev, "iATU unroll: %s\n",
-			pci->iatu_unroll_enabled ? "enabled" : "disabled");
-
 		dw_pcie_prog_outbound_atu(pci, PCIE_ATU_REGION_INDEX0,
 					  PCIE_ATU_TYPE_MEM, pp->mem_base,
 					  pp->mem_bus_addr, pp->mem_size);
@@ -710,14 +707,13 @@
 
 	dw_pcie_wr_own_conf(pp, PCI_BASE_ADDRESS_0, 4, 0);
 
-	/* Enable write permission for the DBI read-only register */
-	dw_pcie_dbi_ro_wr_en(pci);
 	/* Program correct class for RC */
 	dw_pcie_wr_own_conf(pp, PCI_CLASS_DEVICE, 2, PCI_CLASS_BRIDGE_PCI);
-	/* Better disable write permission right after the update */
-	dw_pcie_dbi_ro_wr_dis(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);
+
+	dw_pcie_dbi_ro_wr_dis(pci);
 }
+EXPORT_SYMBOL_GPL(dw_pcie_setup_rc);
diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c
index c12bf79..b58fdcb 100644
--- a/drivers/pci/controller/dwc/pcie-designware-plat.c
+++ b/drivers/pci/controller/dwc/pcie-designware-plat.c
@@ -13,11 +13,9 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/of_device.h>
-#include <linux/of_gpio.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
 #include <linux/resource.h>
-#include <linux/signal.h>
 #include <linux/types.h>
 #include <linux/regmap.h>
 
@@ -70,14 +68,10 @@
 static void dw_plat_pcie_ep_init(struct dw_pcie_ep *ep)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	struct pci_epc *epc = ep->epc;
 	enum pci_barno bar;
 
 	for (bar = BAR_0; bar <= BAR_5; bar++)
 		dw_pcie_ep_reset_bar(pci, bar);
-
-	epc->features |= EPC_FEATURE_NO_LINKUP_NOTIFIER;
-	epc->features |= EPC_FEATURE_MSIX_AVAILABLE;
 }
 
 static int dw_plat_pcie_ep_raise_irq(struct dw_pcie_ep *ep, u8 func_no,
@@ -100,9 +94,22 @@
 	return 0;
 }
 
-static struct dw_pcie_ep_ops pcie_ep_ops = {
+static const struct pci_epc_features dw_plat_pcie_epc_features = {
+	.linkup_notifier = false,
+	.msi_capable = true,
+	.msix_capable = true,
+};
+
+static const struct pci_epc_features*
+dw_plat_pcie_get_features(struct dw_pcie_ep *ep)
+{
+	return &dw_plat_pcie_epc_features;
+}
+
+static const struct dw_pcie_ep_ops pcie_ep_ops = {
 	.ep_init = dw_plat_pcie_ep_init,
 	.raise_irq = dw_plat_pcie_ep_raise_irq,
+	.get_features = dw_plat_pcie_get_features,
 };
 
 static int dw_plat_add_pcie_port(struct dw_plat_pcie *dw_plat_pcie,
diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c
index 2153956..820488d 100644
--- a/drivers/pci/controller/dwc/pcie-designware.c
+++ b/drivers/pci/controller/dwc/pcie-designware.c
@@ -14,15 +14,89 @@
 
 #include "pcie-designware.h"
 
-/* PCIe Port Logic registers */
-#define PLR_OFFSET			0x700
-#define PCIE_PHY_DEBUG_R1		(PLR_OFFSET + 0x2c)
-#define PCIE_PHY_DEBUG_R1_LINK_UP	(0x1 << 4)
-#define PCIE_PHY_DEBUG_R1_LINK_IN_TRAINING	(0x1 << 29)
+/*
+ * These interfaces resemble the pci_find_*capability() interfaces, but these
+ * are for configuring host controllers, which are bridges *to* PCI devices but
+ * are not PCI devices themselves.
+ */
+static u8 __dw_pcie_find_next_cap(struct dw_pcie *pci, u8 cap_ptr,
+				  u8 cap)
+{
+	u8 cap_id, next_cap_ptr;
+	u16 reg;
+
+	if (!cap_ptr)
+		return 0;
+
+	reg = dw_pcie_readw_dbi(pci, cap_ptr);
+	cap_id = (reg & 0x00ff);
+
+	if (cap_id > PCI_CAP_ID_MAX)
+		return 0;
+
+	if (cap_id == cap)
+		return cap_ptr;
+
+	next_cap_ptr = (reg & 0xff00) >> 8;
+	return __dw_pcie_find_next_cap(pci, next_cap_ptr, cap);
+}
+
+u8 dw_pcie_find_capability(struct dw_pcie *pci, u8 cap)
+{
+	u8 next_cap_ptr;
+	u16 reg;
+
+	reg = dw_pcie_readw_dbi(pci, PCI_CAPABILITY_LIST);
+	next_cap_ptr = (reg & 0x00ff);
+
+	return __dw_pcie_find_next_cap(pci, next_cap_ptr, cap);
+}
+EXPORT_SYMBOL_GPL(dw_pcie_find_capability);
+
+static u16 dw_pcie_find_next_ext_capability(struct dw_pcie *pci, u16 start,
+					    u8 cap)
+{
+	u32 header;
+	int ttl;
+	int pos = PCI_CFG_SPACE_SIZE;
+
+	/* minimum 8 bytes per capability */
+	ttl = (PCI_CFG_SPACE_EXP_SIZE - PCI_CFG_SPACE_SIZE) / 8;
+
+	if (start)
+		pos = start;
+
+	header = dw_pcie_readl_dbi(pci, pos);
+	/*
+	 * If we have no capabilities, this is indicated by cap ID,
+	 * cap version and next pointer all being 0.
+	 */
+	if (header == 0)
+		return 0;
+
+	while (ttl-- > 0) {
+		if (PCI_EXT_CAP_ID(header) == cap && pos != start)
+			return pos;
+
+		pos = PCI_EXT_CAP_NEXT(header);
+		if (pos < PCI_CFG_SPACE_SIZE)
+			break;
+
+		header = dw_pcie_readl_dbi(pci, pos);
+	}
+
+	return 0;
+}
+
+u16 dw_pcie_find_ext_capability(struct dw_pcie *pci, u8 cap)
+{
+	return dw_pcie_find_next_ext_capability(pci, 0, cap);
+}
+EXPORT_SYMBOL_GPL(dw_pcie_find_ext_capability);
 
 int dw_pcie_read(void __iomem *addr, int size, u32 *val)
 {
-	if ((uintptr_t)addr & (size - 1)) {
+	if (!IS_ALIGNED((uintptr_t)addr, size)) {
 		*val = 0;
 		return PCIBIOS_BAD_REGISTER_NUMBER;
 	}
@@ -40,10 +114,11 @@
 
 	return PCIBIOS_SUCCESSFUL;
 }
+EXPORT_SYMBOL_GPL(dw_pcie_read);
 
 int dw_pcie_write(void __iomem *addr, int size, u32 val)
 {
-	if ((uintptr_t)addr & (size - 1))
+	if (!IS_ALIGNED((uintptr_t)addr, size))
 		return PCIBIOS_BAD_REGISTER_NUMBER;
 
 	if (size == 4)
@@ -57,43 +132,102 @@
 
 	return PCIBIOS_SUCCESSFUL;
 }
+EXPORT_SYMBOL_GPL(dw_pcie_write);
 
-u32 __dw_pcie_read_dbi(struct dw_pcie *pci, void __iomem *base, u32 reg,
-		       size_t size)
+u32 dw_pcie_read_dbi(struct dw_pcie *pci, u32 reg, size_t size)
 {
 	int ret;
 	u32 val;
 
 	if (pci->ops->read_dbi)
-		return pci->ops->read_dbi(pci, base, reg, size);
+		return pci->ops->read_dbi(pci, pci->dbi_base, reg, size);
 
-	ret = dw_pcie_read(base + reg, size, &val);
+	ret = dw_pcie_read(pci->dbi_base + reg, size, &val);
 	if (ret)
 		dev_err(pci->dev, "Read DBI address failed\n");
 
 	return val;
 }
+EXPORT_SYMBOL_GPL(dw_pcie_read_dbi);
 
-void __dw_pcie_write_dbi(struct dw_pcie *pci, void __iomem *base, u32 reg,
-			 size_t size, u32 val)
+void dw_pcie_write_dbi(struct dw_pcie *pci, u32 reg, size_t size, u32 val)
 {
 	int ret;
 
 	if (pci->ops->write_dbi) {
-		pci->ops->write_dbi(pci, base, reg, size, val);
+		pci->ops->write_dbi(pci, pci->dbi_base, reg, size, val);
 		return;
 	}
 
-	ret = dw_pcie_write(base + reg, size, val);
+	ret = dw_pcie_write(pci->dbi_base + reg, size, val);
 	if (ret)
 		dev_err(pci->dev, "Write DBI address failed\n");
 }
+EXPORT_SYMBOL_GPL(dw_pcie_write_dbi);
+
+u32 dw_pcie_read_dbi2(struct dw_pcie *pci, u32 reg, size_t size)
+{
+	int ret;
+	u32 val;
+
+	if (pci->ops->read_dbi2)
+		return pci->ops->read_dbi2(pci, pci->dbi_base2, reg, size);
+
+	ret = dw_pcie_read(pci->dbi_base2 + reg, size, &val);
+	if (ret)
+		dev_err(pci->dev, "read DBI address failed\n");
+
+	return val;
+}
+
+void dw_pcie_write_dbi2(struct dw_pcie *pci, u32 reg, size_t size, u32 val)
+{
+	int ret;
+
+	if (pci->ops->write_dbi2) {
+		pci->ops->write_dbi2(pci, pci->dbi_base2, reg, size, val);
+		return;
+	}
+
+	ret = dw_pcie_write(pci->dbi_base2 + reg, size, val);
+	if (ret)
+		dev_err(pci->dev, "write DBI address failed\n");
+}
+
+u32 dw_pcie_read_atu(struct dw_pcie *pci, u32 reg, size_t size)
+{
+	int ret;
+	u32 val;
+
+	if (pci->ops->read_dbi)
+		return pci->ops->read_dbi(pci, pci->atu_base, reg, size);
+
+	ret = dw_pcie_read(pci->atu_base + reg, size, &val);
+	if (ret)
+		dev_err(pci->dev, "Read ATU address failed\n");
+
+	return val;
+}
+
+void dw_pcie_write_atu(struct dw_pcie *pci, u32 reg, size_t size, u32 val)
+{
+	int ret;
+
+	if (pci->ops->write_dbi) {
+		pci->ops->write_dbi(pci, pci->atu_base, reg, size, val);
+		return;
+	}
+
+	ret = dw_pcie_write(pci->atu_base + reg, size, val);
+	if (ret)
+		dev_err(pci->dev, "Write ATU address failed\n");
+}
 
 static u32 dw_pcie_readl_ob_unroll(struct dw_pcie *pci, u32 index, u32 reg)
 {
 	u32 offset = PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(index);
 
-	return dw_pcie_readl_dbi(pci, offset + reg);
+	return dw_pcie_readl_atu(pci, offset + reg);
 }
 
 static void dw_pcie_writel_ob_unroll(struct dw_pcie *pci, u32 index, u32 reg,
@@ -101,7 +235,7 @@
 {
 	u32 offset = PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(index);
 
-	dw_pcie_writel_dbi(pci, offset + reg, val);
+	dw_pcie_writel_atu(pci, offset + reg, val);
 }
 
 static void dw_pcie_prog_outbound_atu_unroll(struct dw_pcie *pci, int index,
@@ -187,7 +321,7 @@
 {
 	u32 offset = PCIE_GET_ATU_INB_UNR_REG_OFFSET(index);
 
-	return dw_pcie_readl_dbi(pci, offset + reg);
+	return dw_pcie_readl_atu(pci, offset + reg);
 }
 
 static void dw_pcie_writel_ib_unroll(struct dw_pcie *pci, u32 index, u32 reg,
@@ -195,7 +329,7 @@
 {
 	u32 offset = PCIE_GET_ATU_INB_UNR_REG_OFFSET(index);
 
-	dw_pcie_writel_dbi(pci, offset + reg, val);
+	dw_pcie_writel_atu(pci, offset + reg, val);
 }
 
 static int dw_pcie_prog_inbound_atu_unroll(struct dw_pcie *pci, int index,
@@ -306,7 +440,7 @@
 	}
 
 	dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT, region | index);
-	dw_pcie_writel_dbi(pci, PCIE_ATU_CR2, ~PCIE_ATU_ENABLE);
+	dw_pcie_writel_dbi(pci, PCIE_ATU_CR2, (u32)~PCIE_ATU_ENABLE);
 }
 
 int dw_pcie_wait_for_link(struct dw_pcie *pci)
@@ -322,10 +456,11 @@
 		usleep_range(LINK_WAIT_USLEEP_MIN, LINK_WAIT_USLEEP_MAX);
 	}
 
-	dev_err(pci->dev, "Phy link never came up\n");
+	dev_info(pci->dev, "Phy link never came up\n");
 
 	return -ETIMEDOUT;
 }
+EXPORT_SYMBOL_GPL(dw_pcie_wait_for_link);
 
 int dw_pcie_link_up(struct dw_pcie *pci)
 {
@@ -334,9 +469,20 @@
 	if (pci->ops->link_up)
 		return pci->ops->link_up(pci);
 
-	val = readl(pci->dbi_base + PCIE_PHY_DEBUG_R1);
-	return ((val & PCIE_PHY_DEBUG_R1_LINK_UP) &&
-		(!(val & PCIE_PHY_DEBUG_R1_LINK_IN_TRAINING)));
+	val = readl(pci->dbi_base + PCIE_PORT_DEBUG1);
+	return ((val & PCIE_PORT_DEBUG1_LINK_UP) &&
+		(!(val & PCIE_PORT_DEBUG1_LINK_IN_TRAINING)));
+}
+
+static u8 dw_pcie_iatu_unroll_enabled(struct dw_pcie *pci)
+{
+	u32 val;
+
+	val = dw_pcie_readl_dbi(pci, PCIE_ATU_VIEWPORT);
+	if (val == 0xffffffff)
+		return 1;
+
+	return 0;
 }
 
 void dw_pcie_setup(struct dw_pcie *pci)
@@ -347,9 +493,21 @@
 	struct device *dev = pci->dev;
 	struct device_node *np = dev->of_node;
 
+	if (pci->version >= 0x480A || (!pci->version &&
+				       dw_pcie_iatu_unroll_enabled(pci))) {
+		pci->iatu_unroll_enabled = true;
+		if (!pci->atu_base)
+			pci->atu_base = pci->dbi_base + DEFAULT_DBI_ATU_OFFSET;
+	}
+	dev_dbg(pci->dev, "iATU unroll: %s\n", pci->iatu_unroll_enabled ?
+		"enabled" : "disabled");
+
+
 	ret = of_property_read_u32(np, "num-lanes", &lanes);
-	if (ret)
-		lanes = 0;
+	if (ret) {
+		dev_dbg(pci->dev, "property num-lanes isn't found\n");
+		return;
+	}
 
 	/* Set the number of lanes */
 	val = dw_pcie_readl_dbi(pci, PCIE_PORT_LINK_CONTROL);
@@ -391,4 +549,11 @@
 		break;
 	}
 	dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val);
+
+	if (of_property_read_bool(np, "snps,enable-cdm-check")) {
+		val = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS);
+		val |= PCIE_PL_CHK_REG_CHK_REG_CONTINUOUS |
+		       PCIE_PL_CHK_REG_CHK_REG_START;
+		dw_pcie_writel_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS, val);
+	}
 }
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index 9f1a5e3..5a18e94 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -11,6 +11,7 @@
 #ifndef _PCIE_DESIGNWARE_H
 #define _PCIE_DESIGNWARE_H
 
+#include <linux/bitfield.h>
 #include <linux/dma-mapping.h>
 #include <linux/irq.h>
 #include <linux/msi.h>
@@ -30,19 +31,28 @@
 
 /* Synopsys-specific PCIe configuration registers */
 #define PCIE_PORT_LINK_CONTROL		0x710
-#define PORT_LINK_MODE_MASK		(0x3f << 16)
-#define PORT_LINK_MODE_1_LANES		(0x1 << 16)
-#define PORT_LINK_MODE_2_LANES		(0x3 << 16)
-#define PORT_LINK_MODE_4_LANES		(0x7 << 16)
-#define PORT_LINK_MODE_8_LANES		(0xf << 16)
+#define PORT_LINK_MODE_MASK		GENMASK(21, 16)
+#define PORT_LINK_MODE(n)		FIELD_PREP(PORT_LINK_MODE_MASK, n)
+#define PORT_LINK_MODE_1_LANES		PORT_LINK_MODE(0x1)
+#define PORT_LINK_MODE_2_LANES		PORT_LINK_MODE(0x3)
+#define PORT_LINK_MODE_4_LANES		PORT_LINK_MODE(0x7)
+#define PORT_LINK_MODE_8_LANES		PORT_LINK_MODE(0xf)
+
+#define PCIE_PORT_DEBUG0		0x728
+#define PORT_LOGIC_LTSSM_STATE_MASK	0x1f
+#define PORT_LOGIC_LTSSM_STATE_L0	0x11
+#define PCIE_PORT_DEBUG1		0x72C
+#define PCIE_PORT_DEBUG1_LINK_UP		BIT(4)
+#define PCIE_PORT_DEBUG1_LINK_IN_TRAINING	BIT(29)
 
 #define PCIE_LINK_WIDTH_SPEED_CONTROL	0x80C
-#define PORT_LOGIC_SPEED_CHANGE		(0x1 << 17)
-#define PORT_LOGIC_LINK_WIDTH_MASK	(0x1f << 8)
-#define PORT_LOGIC_LINK_WIDTH_1_LANES	(0x1 << 8)
-#define PORT_LOGIC_LINK_WIDTH_2_LANES	(0x2 << 8)
-#define PORT_LOGIC_LINK_WIDTH_4_LANES	(0x4 << 8)
-#define PORT_LOGIC_LINK_WIDTH_8_LANES	(0x8 << 8)
+#define PORT_LOGIC_SPEED_CHANGE		BIT(17)
+#define PORT_LOGIC_LINK_WIDTH_MASK	GENMASK(12, 8)
+#define PORT_LOGIC_LINK_WIDTH(n)	FIELD_PREP(PORT_LOGIC_LINK_WIDTH_MASK, n)
+#define PORT_LOGIC_LINK_WIDTH_1_LANES	PORT_LOGIC_LINK_WIDTH(0x1)
+#define PORT_LOGIC_LINK_WIDTH_2_LANES	PORT_LOGIC_LINK_WIDTH(0x2)
+#define PORT_LOGIC_LINK_WIDTH_4_LANES	PORT_LOGIC_LINK_WIDTH(0x4)
+#define PORT_LOGIC_LINK_WIDTH_8_LANES	PORT_LOGIC_LINK_WIDTH(0x8)
 
 #define PCIE_MSI_ADDR_LO		0x820
 #define PCIE_MSI_ADDR_HI		0x824
@@ -51,30 +61,39 @@
 #define PCIE_MSI_INTR0_STATUS		0x830
 
 #define PCIE_ATU_VIEWPORT		0x900
-#define PCIE_ATU_REGION_INBOUND		(0x1 << 31)
-#define PCIE_ATU_REGION_OUTBOUND	(0x0 << 31)
-#define PCIE_ATU_REGION_INDEX2		(0x2 << 0)
-#define PCIE_ATU_REGION_INDEX1		(0x1 << 0)
-#define PCIE_ATU_REGION_INDEX0		(0x0 << 0)
+#define PCIE_ATU_REGION_INBOUND		BIT(31)
+#define PCIE_ATU_REGION_OUTBOUND	0
+#define PCIE_ATU_REGION_INDEX2		0x2
+#define PCIE_ATU_REGION_INDEX1		0x1
+#define PCIE_ATU_REGION_INDEX0		0x0
 #define PCIE_ATU_CR1			0x904
-#define PCIE_ATU_TYPE_MEM		(0x0 << 0)
-#define PCIE_ATU_TYPE_IO		(0x2 << 0)
-#define PCIE_ATU_TYPE_CFG0		(0x4 << 0)
-#define PCIE_ATU_TYPE_CFG1		(0x5 << 0)
+#define PCIE_ATU_TYPE_MEM		0x0
+#define PCIE_ATU_TYPE_IO		0x2
+#define PCIE_ATU_TYPE_CFG0		0x4
+#define PCIE_ATU_TYPE_CFG1		0x5
 #define PCIE_ATU_CR2			0x908
-#define PCIE_ATU_ENABLE			(0x1 << 31)
-#define PCIE_ATU_BAR_MODE_ENABLE	(0x1 << 30)
+#define PCIE_ATU_ENABLE			BIT(31)
+#define PCIE_ATU_BAR_MODE_ENABLE	BIT(30)
 #define PCIE_ATU_LOWER_BASE		0x90C
 #define PCIE_ATU_UPPER_BASE		0x910
 #define PCIE_ATU_LIMIT			0x914
 #define PCIE_ATU_LOWER_TARGET		0x918
-#define PCIE_ATU_BUS(x)			(((x) & 0xff) << 24)
-#define PCIE_ATU_DEV(x)			(((x) & 0x1f) << 19)
-#define PCIE_ATU_FUNC(x)		(((x) & 0x7) << 16)
+#define PCIE_ATU_BUS(x)			FIELD_PREP(GENMASK(31, 24), x)
+#define PCIE_ATU_DEV(x)			FIELD_PREP(GENMASK(23, 19), x)
+#define PCIE_ATU_FUNC(x)		FIELD_PREP(GENMASK(18, 16), x)
 #define PCIE_ATU_UPPER_TARGET		0x91C
 
 #define PCIE_MISC_CONTROL_1_OFF		0x8BC
-#define PCIE_DBI_RO_WR_EN		(0x1 << 0)
+#define PCIE_DBI_RO_WR_EN		BIT(0)
+
+#define PCIE_PL_CHK_REG_CONTROL_STATUS			0xB20
+#define PCIE_PL_CHK_REG_CHK_REG_START			BIT(0)
+#define PCIE_PL_CHK_REG_CHK_REG_CONTINUOUS		BIT(1)
+#define PCIE_PL_CHK_REG_CHK_REG_COMPARISON_ERROR	BIT(16)
+#define PCIE_PL_CHK_REG_CHK_REG_LOGIC_ERROR		BIT(17)
+#define PCIE_PL_CHK_REG_CHK_REG_COMPLETE		BIT(18)
+
+#define PCIE_PL_CHK_REG_ERR_ADDR			0xB28
 
 /*
  * iATU Unroll-specific register definitions
@@ -88,12 +107,20 @@
 #define PCIE_ATU_UNR_LOWER_TARGET	0x14
 #define PCIE_ATU_UNR_UPPER_TARGET	0x18
 
-/* Register address builder */
-#define PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(region)	\
-			((0x3 << 20) | ((region) << 9))
+/*
+ * The default address offset between dbi_base and atu_base. Root controller
+ * drivers are not required to initialize atu_base if the offset matches this
+ * default; the driver core automatically derives atu_base from dbi_base using
+ * this offset, if atu_base not set.
+ */
+#define DEFAULT_DBI_ATU_OFFSET (0x3 << 20)
 
-#define PCIE_GET_ATU_INB_UNR_REG_OFFSET(region)				\
-			((0x3 << 20) | ((region) << 9) | (0x1 << 8))
+/* Register address builder */
+#define PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(region) \
+		((region) << 9)
+
+#define PCIE_GET_ATU_INB_UNR_REG_OFFSET(region) \
+		(((region) << 9) | BIT(8))
 
 #define MAX_MSI_IRQS			256
 #define MAX_MSI_IRQS_PER_CTRL		32
@@ -130,14 +157,9 @@
 	int (*wr_other_conf)(struct pcie_port *pp, struct pci_bus *bus,
 			     unsigned int devfn, int where, int size, u32 val);
 	int (*host_init)(struct pcie_port *pp);
-	void (*msi_set_irq)(struct pcie_port *pp, int irq);
-	void (*msi_clear_irq)(struct pcie_port *pp, int irq);
-	phys_addr_t (*get_msi_addr)(struct pcie_port *pp);
-	u32 (*get_msi_data)(struct pcie_port *pp, int pos);
 	void (*scan_bus)(struct pcie_port *pp);
 	void (*set_num_vectors)(struct pcie_port *pp);
 	int (*msi_host_init)(struct pcie_port *pp);
-	void (*msi_irq_ack)(int irq, struct pcie_port *pp);
 };
 
 struct pcie_port {
@@ -164,8 +186,11 @@
 	struct irq_domain	*irq_domain;
 	struct irq_domain	*msi_domain;
 	dma_addr_t		msi_data;
+	struct page		*msi_page;
+	struct irq_chip		*msi_irq_chip;
 	u32			num_vectors;
-	u32			irq_status[MAX_MSI_CTRLS];
+	u32			irq_mask[MAX_MSI_CTRLS];
+	struct pci_bus		*root_bus;
 	raw_spinlock_t		lock;
 	DECLARE_BITMAP(msi_irq_in_use, MAX_MSI_IRQS);
 };
@@ -180,11 +205,12 @@
 	void	(*ep_init)(struct dw_pcie_ep *ep);
 	int	(*raise_irq)(struct dw_pcie_ep *ep, u8 func_no,
 			     enum pci_epc_irq_type type, u16 interrupt_num);
+	const struct pci_epc_features* (*get_features)(struct dw_pcie_ep *ep);
 };
 
 struct dw_pcie_ep {
 	struct pci_epc		*epc;
-	struct dw_pcie_ep_ops	*ops;
+	const struct dw_pcie_ep_ops *ops;
 	phys_addr_t		phys_base;
 	size_t			addr_size;
 	size_t			page_size;
@@ -206,6 +232,10 @@
 			    size_t size);
 	void	(*write_dbi)(struct dw_pcie *pcie, void __iomem *base, u32 reg,
 			     size_t size, u32 val);
+	u32     (*read_dbi2)(struct dw_pcie *pcie, void __iomem *base, u32 reg,
+			     size_t size);
+	void    (*write_dbi2)(struct dw_pcie *pcie, void __iomem *base, u32 reg,
+			      size_t size, u32 val);
 	int	(*link_up)(struct dw_pcie *pcie);
 	int	(*start_link)(struct dw_pcie *pcie);
 	void	(*stop_link)(struct dw_pcie *pcie);
@@ -215,11 +245,14 @@
 	struct device		*dev;
 	void __iomem		*dbi_base;
 	void __iomem		*dbi_base2;
+	/* Used when iatu_unroll_enabled is true */
+	void __iomem		*atu_base;
 	u32			num_viewport;
 	u8			iatu_unroll_enabled;
 	struct pcie_port	pp;
 	struct dw_pcie_ep	ep;
 	const struct dw_pcie_ops *ops;
+	unsigned int		version;
 };
 
 #define to_dw_pcie_from_pp(port) container_of((port), struct dw_pcie, pp)
@@ -227,13 +260,18 @@
 #define to_dw_pcie_from_ep(endpoint)   \
 		container_of((endpoint), struct dw_pcie, ep)
 
+u8 dw_pcie_find_capability(struct dw_pcie *pci, u8 cap);
+u16 dw_pcie_find_ext_capability(struct dw_pcie *pci, u8 cap);
+
 int dw_pcie_read(void __iomem *addr, int size, u32 *val);
 int dw_pcie_write(void __iomem *addr, int size, u32 val);
 
-u32 __dw_pcie_read_dbi(struct dw_pcie *pci, void __iomem *base, u32 reg,
-		       size_t size);
-void __dw_pcie_write_dbi(struct dw_pcie *pci, void __iomem *base, u32 reg,
-			 size_t size, u32 val);
+u32 dw_pcie_read_dbi(struct dw_pcie *pci, u32 reg, size_t size);
+void dw_pcie_write_dbi(struct dw_pcie *pci, u32 reg, size_t size, u32 val);
+u32 dw_pcie_read_dbi2(struct dw_pcie *pci, u32 reg, size_t size);
+void dw_pcie_write_dbi2(struct dw_pcie *pci, u32 reg, size_t size, u32 val);
+u32 dw_pcie_read_atu(struct dw_pcie *pci, u32 reg, size_t size);
+void dw_pcie_write_atu(struct dw_pcie *pci, u32 reg, size_t size, u32 val);
 int dw_pcie_link_up(struct dw_pcie *pci);
 int dw_pcie_wait_for_link(struct dw_pcie *pci);
 void dw_pcie_prog_outbound_atu(struct dw_pcie *pci, int index,
@@ -247,42 +285,52 @@
 
 static inline void dw_pcie_writel_dbi(struct dw_pcie *pci, u32 reg, u32 val)
 {
-	__dw_pcie_write_dbi(pci, pci->dbi_base, reg, 0x4, val);
+	dw_pcie_write_dbi(pci, reg, 0x4, val);
 }
 
 static inline u32 dw_pcie_readl_dbi(struct dw_pcie *pci, u32 reg)
 {
-	return __dw_pcie_read_dbi(pci, pci->dbi_base, reg, 0x4);
+	return dw_pcie_read_dbi(pci, reg, 0x4);
 }
 
 static inline void dw_pcie_writew_dbi(struct dw_pcie *pci, u32 reg, u16 val)
 {
-	__dw_pcie_write_dbi(pci, pci->dbi_base, reg, 0x2, val);
+	dw_pcie_write_dbi(pci, reg, 0x2, val);
 }
 
 static inline u16 dw_pcie_readw_dbi(struct dw_pcie *pci, u32 reg)
 {
-	return __dw_pcie_read_dbi(pci, pci->dbi_base, reg, 0x2);
+	return dw_pcie_read_dbi(pci, reg, 0x2);
 }
 
 static inline void dw_pcie_writeb_dbi(struct dw_pcie *pci, u32 reg, u8 val)
 {
-	__dw_pcie_write_dbi(pci, pci->dbi_base, reg, 0x1, val);
+	dw_pcie_write_dbi(pci, reg, 0x1, val);
 }
 
 static inline u8 dw_pcie_readb_dbi(struct dw_pcie *pci, u32 reg)
 {
-	return __dw_pcie_read_dbi(pci, pci->dbi_base, reg, 0x1);
+	return dw_pcie_read_dbi(pci, reg, 0x1);
 }
 
 static inline void dw_pcie_writel_dbi2(struct dw_pcie *pci, u32 reg, u32 val)
 {
-	__dw_pcie_write_dbi(pci, pci->dbi_base2, reg, 0x4, val);
+	dw_pcie_write_dbi2(pci, reg, 0x4, val);
 }
 
 static inline u32 dw_pcie_readl_dbi2(struct dw_pcie *pci, u32 reg)
 {
-	return __dw_pcie_read_dbi(pci, pci->dbi_base2, reg, 0x4);
+	return dw_pcie_read_dbi2(pci, reg, 0x4);
+}
+
+static inline void dw_pcie_writel_atu(struct dw_pcie *pci, u32 reg, u32 val)
+{
+	dw_pcie_write_atu(pci, reg, 0x4, val);
+}
+
+static inline u32 dw_pcie_readl_atu(struct dw_pcie *pci, u32 reg)
+{
+	return dw_pcie_read_atu(pci, reg, 0x4);
 }
 
 static inline void dw_pcie_dbi_ro_wr_en(struct dw_pcie *pci)
@@ -313,6 +361,7 @@
 void dw_pcie_free_msi(struct pcie_port *pp);
 void dw_pcie_setup_rc(struct pcie_port *pp);
 int dw_pcie_host_init(struct pcie_port *pp);
+void dw_pcie_host_deinit(struct pcie_port *pp);
 int dw_pcie_allocate_domains(struct pcie_port *pp);
 #else
 static inline irqreturn_t dw_handle_msi_irq(struct pcie_port *pp)
@@ -337,6 +386,10 @@
 	return 0;
 }
 
+static inline void dw_pcie_host_deinit(struct pcie_port *pp)
+{
+}
+
 static inline int dw_pcie_allocate_domains(struct pcie_port *pp)
 {
 	return 0;
diff --git a/drivers/pci/controller/dwc/pcie-histb.c b/drivers/pci/controller/dwc/pcie-histb.c
index 7b32e61..811b5c6 100644
--- a/drivers/pci/controller/dwc/pcie-histb.c
+++ b/drivers/pci/controller/dwc/pcie-histb.c
@@ -202,7 +202,7 @@
 	return 0;
 }
 
-static struct dw_pcie_host_ops histb_pcie_host_ops = {
+static const struct dw_pcie_host_ops histb_pcie_host_ops = {
 	.rd_own_conf = histb_pcie_rd_own_conf,
 	.wr_own_conf = histb_pcie_wr_own_conf,
 	.host_init = histb_pcie_host_init,
@@ -340,8 +340,8 @@
 
 	hipcie->vpcie = devm_regulator_get_optional(dev, "vpcie");
 	if (IS_ERR(hipcie->vpcie)) {
-		if (PTR_ERR(hipcie->vpcie) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
+		if (PTR_ERR(hipcie->vpcie) != -ENODEV)
+			return PTR_ERR(hipcie->vpcie);
 		hipcie->vpcie = NULL;
 	}
 
diff --git a/drivers/pci/controller/dwc/pcie-kirin.c b/drivers/pci/controller/dwc/pcie-kirin.c
index 5352e0c..c19617a 100644
--- a/drivers/pci/controller/dwc/pcie-kirin.c
+++ b/drivers/pci/controller/dwc/pcie-kirin.c
@@ -2,7 +2,7 @@
 /*
  * PCIe host controller driver for Kirin Phone SoCs
  *
- * Copyright (C) 2017 Hilisicon Electronics Co., Ltd.
+ * Copyright (C) 2017 HiSilicon Electronics Co., Ltd.
  *		http://www.huawei.com
  *
  * Author: Xiaowei Song <songxiaowei@huawei.com>
@@ -436,7 +436,7 @@
 	return 0;
 }
 
-static struct dw_pcie_ops kirin_dw_pcie_ops = {
+static const struct dw_pcie_ops kirin_dw_pcie_ops = {
 	.read_dbi = kirin_pcie_read_dbi,
 	.write_dbi = kirin_pcie_write_dbi,
 	.link_up = kirin_pcie_link_up,
@@ -467,8 +467,8 @@
 	return 0;
 }
 
-static int __init kirin_add_pcie_port(struct dw_pcie *pci,
-				      struct platform_device *pdev)
+static int kirin_add_pcie_port(struct dw_pcie *pci,
+			       struct platform_device *pdev)
 {
 	int ret;
 
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index 4352c1c..7e58174 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -112,10 +112,10 @@
 	struct regulator_bulk_data supplies[QCOM_PCIE_2_3_2_MAX_SUPPLY];
 };
 
+#define QCOM_PCIE_2_4_0_MAX_CLOCKS	4
 struct qcom_pcie_resources_2_4_0 {
-	struct clk *aux_clk;
-	struct clk *master_clk;
-	struct clk *slave_clk;
+	struct clk_bulk_data clks[QCOM_PCIE_2_4_0_MAX_CLOCKS];
+	int num_clks;
 	struct reset_control *axi_m_reset;
 	struct reset_control *axi_s_reset;
 	struct reset_control *pipe_reset;
@@ -178,6 +178,8 @@
 
 static void qcom_ep_reset_deassert(struct qcom_pcie *pcie)
 {
+	/* Ensure that PERST has been asserted for at least 100 ms */
+	msleep(100);
 	gpiod_set_value_cansleep(pcie->reset, 0);
 	usleep_range(PERST_DELAY_US, PERST_DELAY_US + 500);
 }
@@ -638,18 +640,20 @@
 	struct qcom_pcie_resources_2_4_0 *res = &pcie->res.v2_4_0;
 	struct dw_pcie *pci = pcie->pci;
 	struct device *dev = pci->dev;
+	bool is_ipq = of_device_is_compatible(dev->of_node, "qcom,pcie-ipq4019");
+	int ret;
 
-	res->aux_clk = devm_clk_get(dev, "aux");
-	if (IS_ERR(res->aux_clk))
-		return PTR_ERR(res->aux_clk);
+	res->clks[0].id = "aux";
+	res->clks[1].id = "master_bus";
+	res->clks[2].id = "slave_bus";
+	res->clks[3].id = "iface";
 
-	res->master_clk = devm_clk_get(dev, "master_bus");
-	if (IS_ERR(res->master_clk))
-		return PTR_ERR(res->master_clk);
+	/* qcom,pcie-ipq4019 is defined without "iface" */
+	res->num_clks = is_ipq ? 3 : 4;
 
-	res->slave_clk = devm_clk_get(dev, "slave_bus");
-	if (IS_ERR(res->slave_clk))
-		return PTR_ERR(res->slave_clk);
+	ret = devm_clk_bulk_get(dev, res->num_clks, res->clks);
+	if (ret < 0)
+		return ret;
 
 	res->axi_m_reset = devm_reset_control_get_exclusive(dev, "axi_m");
 	if (IS_ERR(res->axi_m_reset))
@@ -659,27 +663,33 @@
 	if (IS_ERR(res->axi_s_reset))
 		return PTR_ERR(res->axi_s_reset);
 
-	res->pipe_reset = devm_reset_control_get_exclusive(dev, "pipe");
-	if (IS_ERR(res->pipe_reset))
-		return PTR_ERR(res->pipe_reset);
+	if (is_ipq) {
+		/*
+		 * These resources relates to the PHY or are secure clocks, but
+		 * are controlled here for IPQ4019
+		 */
+		res->pipe_reset = devm_reset_control_get_exclusive(dev, "pipe");
+		if (IS_ERR(res->pipe_reset))
+			return PTR_ERR(res->pipe_reset);
 
-	res->axi_m_vmid_reset = devm_reset_control_get_exclusive(dev,
-								 "axi_m_vmid");
-	if (IS_ERR(res->axi_m_vmid_reset))
-		return PTR_ERR(res->axi_m_vmid_reset);
+		res->axi_m_vmid_reset = devm_reset_control_get_exclusive(dev,
+									 "axi_m_vmid");
+		if (IS_ERR(res->axi_m_vmid_reset))
+			return PTR_ERR(res->axi_m_vmid_reset);
 
-	res->axi_s_xpu_reset = devm_reset_control_get_exclusive(dev,
-								"axi_s_xpu");
-	if (IS_ERR(res->axi_s_xpu_reset))
-		return PTR_ERR(res->axi_s_xpu_reset);
+		res->axi_s_xpu_reset = devm_reset_control_get_exclusive(dev,
+									"axi_s_xpu");
+		if (IS_ERR(res->axi_s_xpu_reset))
+			return PTR_ERR(res->axi_s_xpu_reset);
 
-	res->parf_reset = devm_reset_control_get_exclusive(dev, "parf");
-	if (IS_ERR(res->parf_reset))
-		return PTR_ERR(res->parf_reset);
+		res->parf_reset = devm_reset_control_get_exclusive(dev, "parf");
+		if (IS_ERR(res->parf_reset))
+			return PTR_ERR(res->parf_reset);
 
-	res->phy_reset = devm_reset_control_get_exclusive(dev, "phy");
-	if (IS_ERR(res->phy_reset))
-		return PTR_ERR(res->phy_reset);
+		res->phy_reset = devm_reset_control_get_exclusive(dev, "phy");
+		if (IS_ERR(res->phy_reset))
+			return PTR_ERR(res->phy_reset);
+	}
 
 	res->axi_m_sticky_reset = devm_reset_control_get_exclusive(dev,
 								   "axi_m_sticky");
@@ -699,9 +709,11 @@
 	if (IS_ERR(res->ahb_reset))
 		return PTR_ERR(res->ahb_reset);
 
-	res->phy_ahb_reset = devm_reset_control_get_exclusive(dev, "phy_ahb");
-	if (IS_ERR(res->phy_ahb_reset))
-		return PTR_ERR(res->phy_ahb_reset);
+	if (is_ipq) {
+		res->phy_ahb_reset = devm_reset_control_get_exclusive(dev, "phy_ahb");
+		if (IS_ERR(res->phy_ahb_reset))
+			return PTR_ERR(res->phy_ahb_reset);
+	}
 
 	return 0;
 }
@@ -719,9 +731,7 @@
 	reset_control_assert(res->axi_m_sticky_reset);
 	reset_control_assert(res->pwr_reset);
 	reset_control_assert(res->ahb_reset);
-	clk_disable_unprepare(res->aux_clk);
-	clk_disable_unprepare(res->master_clk);
-	clk_disable_unprepare(res->slave_clk);
+	clk_bulk_disable_unprepare(res->num_clks, res->clks);
 }
 
 static int qcom_pcie_init_2_4_0(struct qcom_pcie *pcie)
@@ -850,23 +860,9 @@
 
 	usleep_range(10000, 12000);
 
-	ret = clk_prepare_enable(res->aux_clk);
-	if (ret) {
-		dev_err(dev, "cannot prepare/enable iface clock\n");
-		goto err_clk_aux;
-	}
-
-	ret = clk_prepare_enable(res->master_clk);
-	if (ret) {
-		dev_err(dev, "cannot prepare/enable core clock\n");
-		goto err_clk_axi_m;
-	}
-
-	ret = clk_prepare_enable(res->slave_clk);
-	if (ret) {
-		dev_err(dev, "cannot prepare/enable phy clock\n");
-		goto err_clk_axi_s;
-	}
+	ret = clk_bulk_prepare_enable(res->num_clks, res->clks);
+	if (ret)
+		goto err_clks;
 
 	/* enable PCIe clocks and resets */
 	val = readl(pcie->parf + PCIE20_PARF_PHY_CTRL);
@@ -891,11 +887,7 @@
 
 	return 0;
 
-err_clk_axi_s:
-	clk_disable_unprepare(res->master_clk);
-err_clk_axi_m:
-	clk_disable_unprepare(res->aux_clk);
-err_clk_aux:
+err_clks:
 	reset_control_assert(res->ahb_reset);
 err_rst_ahb:
 	reset_control_assert(res->pwr_reset);
@@ -1089,7 +1081,6 @@
 	struct qcom_pcie *pcie = to_qcom_pcie(pci);
 	int ret;
 
-	pm_runtime_get_sync(pci->dev);
 	qcom_ep_reset_assert(pcie);
 
 	ret = pcie->ops->init(pcie);
@@ -1126,30 +1117,12 @@
 	phy_power_off(pcie->phy);
 err_deinit:
 	pcie->ops->deinit(pcie);
-	pm_runtime_put(pci->dev);
 
 	return ret;
 }
 
-static int qcom_pcie_rd_own_conf(struct pcie_port *pp, int where, int size,
-				 u32 *val)
-{
-	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
-
-	/* the device class is not reported correctly from the register */
-	if (where == PCI_CLASS_REVISION && size == 4) {
-		*val = readl(pci->dbi_base + PCI_CLASS_REVISION);
-		*val &= 0xff;	/* keep revision id */
-		*val |= PCI_CLASS_BRIDGE_PCI << 16;
-		return PCIBIOS_SUCCESSFUL;
-	}
-
-	return dw_pcie_read(pci->dbi_base + where, size, val);
-}
-
 static const struct dw_pcie_host_ops qcom_pcie_dw_ops = {
 	.host_init = qcom_pcie_host_init,
-	.rd_own_conf = qcom_pcie_rd_own_conf,
 };
 
 /* Qcom IP rev.: 2.1.0	Synopsys IP rev.: 4.01a */
@@ -1216,6 +1189,12 @@
 		return -ENOMEM;
 
 	pm_runtime_enable(dev);
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		pm_runtime_disable(dev);
+		return ret;
+	}
+
 	pci->dev = dev;
 	pci->ops = &dw_pcie_ops;
 	pp = &pci->pp;
@@ -1224,45 +1203,57 @@
 
 	pcie->ops = of_device_get_match_data(dev);
 
-	pcie->reset = devm_gpiod_get_optional(dev, "perst", GPIOD_OUT_LOW);
-	if (IS_ERR(pcie->reset))
-		return PTR_ERR(pcie->reset);
+	pcie->reset = devm_gpiod_get_optional(dev, "perst", GPIOD_OUT_HIGH);
+	if (IS_ERR(pcie->reset)) {
+		ret = PTR_ERR(pcie->reset);
+		goto err_pm_runtime_put;
+	}
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "parf");
 	pcie->parf = devm_ioremap_resource(dev, res);
-	if (IS_ERR(pcie->parf))
-		return PTR_ERR(pcie->parf);
+	if (IS_ERR(pcie->parf)) {
+		ret = PTR_ERR(pcie->parf);
+		goto err_pm_runtime_put;
+	}
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi");
 	pci->dbi_base = devm_pci_remap_cfg_resource(dev, res);
-	if (IS_ERR(pci->dbi_base))
-		return PTR_ERR(pci->dbi_base);
+	if (IS_ERR(pci->dbi_base)) {
+		ret = PTR_ERR(pci->dbi_base);
+		goto err_pm_runtime_put;
+	}
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "elbi");
 	pcie->elbi = devm_ioremap_resource(dev, res);
-	if (IS_ERR(pcie->elbi))
-		return PTR_ERR(pcie->elbi);
+	if (IS_ERR(pcie->elbi)) {
+		ret = PTR_ERR(pcie->elbi);
+		goto err_pm_runtime_put;
+	}
 
 	pcie->phy = devm_phy_optional_get(dev, "pciephy");
-	if (IS_ERR(pcie->phy))
-		return PTR_ERR(pcie->phy);
+	if (IS_ERR(pcie->phy)) {
+		ret = PTR_ERR(pcie->phy);
+		goto err_pm_runtime_put;
+	}
 
 	ret = pcie->ops->get_resources(pcie);
 	if (ret)
-		return ret;
+		goto err_pm_runtime_put;
 
 	pp->ops = &qcom_pcie_dw_ops;
 
 	if (IS_ENABLED(CONFIG_PCI_MSI)) {
 		pp->msi_irq = platform_get_irq_byname(pdev, "msi");
-		if (pp->msi_irq < 0)
-			return pp->msi_irq;
+		if (pp->msi_irq < 0) {
+			ret = pp->msi_irq;
+			goto err_pm_runtime_put;
+		}
 	}
 
 	ret = phy_init(pcie->phy);
 	if (ret) {
 		pm_runtime_disable(&pdev->dev);
-		return ret;
+		goto err_pm_runtime_put;
 	}
 
 	platform_set_drvdata(pdev, pcie);
@@ -1271,10 +1262,16 @@
 	if (ret) {
 		dev_err(dev, "cannot initialize host\n");
 		pm_runtime_disable(&pdev->dev);
-		return ret;
+		goto err_pm_runtime_put;
 	}
 
 	return 0;
+
+err_pm_runtime_put:
+	pm_runtime_put(dev);
+	pm_runtime_disable(dev);
+
+	return ret;
 }
 
 static const struct of_device_id qcom_pcie_match[] = {
@@ -1284,9 +1281,16 @@
 	{ .compatible = "qcom,pcie-msm8996", .data = &ops_2_3_2 },
 	{ .compatible = "qcom,pcie-ipq8074", .data = &ops_2_3_3 },
 	{ .compatible = "qcom,pcie-ipq4019", .data = &ops_2_4_0 },
+	{ .compatible = "qcom,pcie-qcs404", .data = &ops_2_4_0 },
 	{ }
 };
 
+static void qcom_fixup_class(struct pci_dev *dev)
+{
+	dev->class = PCI_CLASS_BRIDGE_PCI << 8;
+}
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, PCI_ANY_ID, qcom_fixup_class);
+
 static struct platform_driver qcom_pcie_driver = {
 	.probe = qcom_pcie_probe,
 	.driver = {
diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c
new file mode 100644
index 0000000..f89f5ac
--- /dev/null
+++ b/drivers/pci/controller/dwc/pcie-tegra194.c
@@ -0,0 +1,1732 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * PCIe host controller driver for Tegra194 SoC
+ *
+ * Copyright (C) 2019 NVIDIA Corporation.
+ *
+ * Author: Vidya Sagar <vidyas@nvidia.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/debugfs.h>
+#include <linux/delay.h>
+#include <linux/gpio.h>
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/of_gpio.h>
+#include <linux/of_irq.h>
+#include <linux/of_pci.h>
+#include <linux/pci.h>
+#include <linux/phy/phy.h>
+#include <linux/pinctrl/consumer.h>
+#include <linux/platform_device.h>
+#include <linux/pm_runtime.h>
+#include <linux/random.h>
+#include <linux/reset.h>
+#include <linux/resource.h>
+#include <linux/types.h>
+#include "pcie-designware.h"
+#include <soc/tegra/bpmp.h>
+#include <soc/tegra/bpmp-abi.h>
+#include "../../pci.h"
+
+#define APPL_PINMUX				0x0
+#define APPL_PINMUX_PEX_RST			BIT(0)
+#define APPL_PINMUX_CLKREQ_OVERRIDE_EN		BIT(2)
+#define APPL_PINMUX_CLKREQ_OVERRIDE		BIT(3)
+#define APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE_EN	BIT(4)
+#define APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE	BIT(5)
+#define APPL_PINMUX_CLKREQ_OUT_OVRD_EN		BIT(9)
+#define APPL_PINMUX_CLKREQ_OUT_OVRD		BIT(10)
+
+#define APPL_CTRL				0x4
+#define APPL_CTRL_SYS_PRE_DET_STATE		BIT(6)
+#define APPL_CTRL_LTSSM_EN			BIT(7)
+#define APPL_CTRL_HW_HOT_RST_EN			BIT(20)
+#define APPL_CTRL_HW_HOT_RST_MODE_MASK		GENMASK(1, 0)
+#define APPL_CTRL_HW_HOT_RST_MODE_SHIFT		22
+#define APPL_CTRL_HW_HOT_RST_MODE_IMDT_RST	0x1
+
+#define APPL_INTR_EN_L0_0			0x8
+#define APPL_INTR_EN_L0_0_LINK_STATE_INT_EN	BIT(0)
+#define APPL_INTR_EN_L0_0_MSI_RCV_INT_EN	BIT(4)
+#define APPL_INTR_EN_L0_0_INT_INT_EN		BIT(8)
+#define APPL_INTR_EN_L0_0_CDM_REG_CHK_INT_EN	BIT(19)
+#define APPL_INTR_EN_L0_0_SYS_INTR_EN		BIT(30)
+#define APPL_INTR_EN_L0_0_SYS_MSI_INTR_EN	BIT(31)
+
+#define APPL_INTR_STATUS_L0			0xC
+#define APPL_INTR_STATUS_L0_LINK_STATE_INT	BIT(0)
+#define APPL_INTR_STATUS_L0_INT_INT		BIT(8)
+#define APPL_INTR_STATUS_L0_CDM_REG_CHK_INT	BIT(18)
+
+#define APPL_INTR_EN_L1_0_0				0x1C
+#define APPL_INTR_EN_L1_0_0_LINK_REQ_RST_NOT_INT_EN	BIT(1)
+
+#define APPL_INTR_STATUS_L1_0_0				0x20
+#define APPL_INTR_STATUS_L1_0_0_LINK_REQ_RST_NOT_CHGED	BIT(1)
+
+#define APPL_INTR_STATUS_L1_1			0x2C
+#define APPL_INTR_STATUS_L1_2			0x30
+#define APPL_INTR_STATUS_L1_3			0x34
+#define APPL_INTR_STATUS_L1_6			0x3C
+#define APPL_INTR_STATUS_L1_7			0x40
+
+#define APPL_INTR_EN_L1_8_0			0x44
+#define APPL_INTR_EN_L1_8_BW_MGT_INT_EN		BIT(2)
+#define APPL_INTR_EN_L1_8_AUTO_BW_INT_EN	BIT(3)
+#define APPL_INTR_EN_L1_8_INTX_EN		BIT(11)
+#define APPL_INTR_EN_L1_8_AER_INT_EN		BIT(15)
+
+#define APPL_INTR_STATUS_L1_8_0			0x4C
+#define APPL_INTR_STATUS_L1_8_0_EDMA_INT_MASK	GENMASK(11, 6)
+#define APPL_INTR_STATUS_L1_8_0_BW_MGT_INT_STS	BIT(2)
+#define APPL_INTR_STATUS_L1_8_0_AUTO_BW_INT_STS	BIT(3)
+
+#define APPL_INTR_STATUS_L1_9			0x54
+#define APPL_INTR_STATUS_L1_10			0x58
+#define APPL_INTR_STATUS_L1_11			0x64
+#define APPL_INTR_STATUS_L1_13			0x74
+#define APPL_INTR_STATUS_L1_14			0x78
+#define APPL_INTR_STATUS_L1_15			0x7C
+#define APPL_INTR_STATUS_L1_17			0x88
+
+#define APPL_INTR_EN_L1_18				0x90
+#define APPL_INTR_EN_L1_18_CDM_REG_CHK_CMPLT		BIT(2)
+#define APPL_INTR_EN_L1_18_CDM_REG_CHK_CMP_ERR		BIT(1)
+#define APPL_INTR_EN_L1_18_CDM_REG_CHK_LOGIC_ERR	BIT(0)
+
+#define APPL_INTR_STATUS_L1_18				0x94
+#define APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMPLT	BIT(2)
+#define APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMP_ERR	BIT(1)
+#define APPL_INTR_STATUS_L1_18_CDM_REG_CHK_LOGIC_ERR	BIT(0)
+
+#define APPL_MSI_CTRL_2				0xB0
+
+#define APPL_LTR_MSG_1				0xC4
+#define LTR_MSG_REQ				BIT(15)
+#define LTR_MST_NO_SNOOP_SHIFT			16
+
+#define APPL_LTR_MSG_2				0xC8
+#define APPL_LTR_MSG_2_LTR_MSG_REQ_STATE	BIT(3)
+
+#define APPL_LINK_STATUS			0xCC
+#define APPL_LINK_STATUS_RDLH_LINK_UP		BIT(0)
+
+#define APPL_DEBUG				0xD0
+#define APPL_DEBUG_PM_LINKST_IN_L2_LAT		BIT(21)
+#define APPL_DEBUG_PM_LINKST_IN_L0		0x11
+#define APPL_DEBUG_LTSSM_STATE_MASK		GENMASK(8, 3)
+#define APPL_DEBUG_LTSSM_STATE_SHIFT		3
+#define LTSSM_STATE_PRE_DETECT			5
+
+#define APPL_RADM_STATUS			0xE4
+#define APPL_PM_XMT_TURNOFF_STATE		BIT(0)
+
+#define APPL_DM_TYPE				0x100
+#define APPL_DM_TYPE_MASK			GENMASK(3, 0)
+#define APPL_DM_TYPE_RP				0x4
+#define APPL_DM_TYPE_EP				0x0
+
+#define APPL_CFG_BASE_ADDR			0x104
+#define APPL_CFG_BASE_ADDR_MASK			GENMASK(31, 12)
+
+#define APPL_CFG_IATU_DMA_BASE_ADDR		0x108
+#define APPL_CFG_IATU_DMA_BASE_ADDR_MASK	GENMASK(31, 18)
+
+#define APPL_CFG_MISC				0x110
+#define APPL_CFG_MISC_SLV_EP_MODE		BIT(14)
+#define APPL_CFG_MISC_ARCACHE_MASK		GENMASK(13, 10)
+#define APPL_CFG_MISC_ARCACHE_SHIFT		10
+#define APPL_CFG_MISC_ARCACHE_VAL		3
+
+#define APPL_CFG_SLCG_OVERRIDE			0x114
+#define APPL_CFG_SLCG_OVERRIDE_SLCG_EN_MASTER	BIT(0)
+
+#define APPL_CAR_RESET_OVRD				0x12C
+#define APPL_CAR_RESET_OVRD_CYA_OVERRIDE_CORE_RST_N	BIT(0)
+
+#define IO_BASE_IO_DECODE				BIT(0)
+#define IO_BASE_IO_DECODE_BIT8				BIT(8)
+
+#define CFG_PREF_MEM_LIMIT_BASE_MEM_DECODE		BIT(0)
+#define CFG_PREF_MEM_LIMIT_BASE_MEM_LIMIT_DECODE	BIT(16)
+
+#define CFG_TIMER_CTRL_MAX_FUNC_NUM_OFF	0x718
+#define CFG_TIMER_CTRL_ACK_NAK_SHIFT	(19)
+
+#define EVENT_COUNTER_ALL_CLEAR		0x3
+#define EVENT_COUNTER_ENABLE_ALL	0x7
+#define EVENT_COUNTER_ENABLE_SHIFT	2
+#define EVENT_COUNTER_EVENT_SEL_MASK	GENMASK(7, 0)
+#define EVENT_COUNTER_EVENT_SEL_SHIFT	16
+#define EVENT_COUNTER_EVENT_Tx_L0S	0x2
+#define EVENT_COUNTER_EVENT_Rx_L0S	0x3
+#define EVENT_COUNTER_EVENT_L1		0x5
+#define EVENT_COUNTER_EVENT_L1_1	0x7
+#define EVENT_COUNTER_EVENT_L1_2	0x8
+#define EVENT_COUNTER_GROUP_SEL_SHIFT	24
+#define EVENT_COUNTER_GROUP_5		0x5
+
+#define PORT_LOGIC_ACK_F_ASPM_CTRL			0x70C
+#define ENTER_ASPM					BIT(30)
+#define L0S_ENTRANCE_LAT_SHIFT				24
+#define L0S_ENTRANCE_LAT_MASK				GENMASK(26, 24)
+#define L1_ENTRANCE_LAT_SHIFT				27
+#define L1_ENTRANCE_LAT_MASK				GENMASK(29, 27)
+#define N_FTS_SHIFT					8
+#define N_FTS_MASK					GENMASK(7, 0)
+#define N_FTS_VAL					52
+
+#define PORT_LOGIC_GEN2_CTRL				0x80C
+#define PORT_LOGIC_GEN2_CTRL_DIRECT_SPEED_CHANGE	BIT(17)
+#define FTS_MASK					GENMASK(7, 0)
+#define FTS_VAL						52
+
+#define PORT_LOGIC_MSI_CTRL_INT_0_EN		0x828
+
+#define GEN3_EQ_CONTROL_OFF			0x8a8
+#define GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC_SHIFT	8
+#define GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC_MASK	GENMASK(23, 8)
+#define GEN3_EQ_CONTROL_OFF_FB_MODE_MASK	GENMASK(3, 0)
+
+#define GEN3_RELATED_OFF			0x890
+#define GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL	BIT(0)
+#define GEN3_RELATED_OFF_GEN3_EQ_DISABLE	BIT(16)
+#define GEN3_RELATED_OFF_RATE_SHADOW_SEL_SHIFT	24
+#define GEN3_RELATED_OFF_RATE_SHADOW_SEL_MASK	GENMASK(25, 24)
+
+#define PORT_LOGIC_AMBA_ERROR_RESPONSE_DEFAULT	0x8D0
+#define AMBA_ERROR_RESPONSE_CRS_SHIFT		3
+#define AMBA_ERROR_RESPONSE_CRS_MASK		GENMASK(1, 0)
+#define AMBA_ERROR_RESPONSE_CRS_OKAY		0
+#define AMBA_ERROR_RESPONSE_CRS_OKAY_FFFFFFFF	1
+#define AMBA_ERROR_RESPONSE_CRS_OKAY_FFFF0001	2
+
+#define PORT_LOGIC_MSIX_DOORBELL			0x948
+
+#define CAP_SPCIE_CAP_OFF			0x154
+#define CAP_SPCIE_CAP_OFF_DSP_TX_PRESET0_MASK	GENMASK(3, 0)
+#define CAP_SPCIE_CAP_OFF_USP_TX_PRESET0_MASK	GENMASK(11, 8)
+#define CAP_SPCIE_CAP_OFF_USP_TX_PRESET0_SHIFT	8
+
+#define PME_ACK_TIMEOUT 10000
+
+#define LTSSM_TIMEOUT 50000	/* 50ms */
+
+#define GEN3_GEN4_EQ_PRESET_INIT	5
+
+#define GEN1_CORE_CLK_FREQ	62500000
+#define GEN2_CORE_CLK_FREQ	125000000
+#define GEN3_CORE_CLK_FREQ	250000000
+#define GEN4_CORE_CLK_FREQ	500000000
+
+static const unsigned int pcie_gen_freq[] = {
+	GEN1_CORE_CLK_FREQ,
+	GEN2_CORE_CLK_FREQ,
+	GEN3_CORE_CLK_FREQ,
+	GEN4_CORE_CLK_FREQ
+};
+
+static const u32 event_cntr_ctrl_offset[] = {
+	0x1d8,
+	0x1a8,
+	0x1a8,
+	0x1a8,
+	0x1c4,
+	0x1d8
+};
+
+static const u32 event_cntr_data_offset[] = {
+	0x1dc,
+	0x1ac,
+	0x1ac,
+	0x1ac,
+	0x1c8,
+	0x1dc
+};
+
+struct tegra_pcie_dw {
+	struct device *dev;
+	struct resource *appl_res;
+	struct resource *dbi_res;
+	struct resource *atu_dma_res;
+	void __iomem *appl_base;
+	struct clk *core_clk;
+	struct reset_control *core_apb_rst;
+	struct reset_control *core_rst;
+	struct dw_pcie pci;
+	struct tegra_bpmp *bpmp;
+
+	bool supports_clkreq;
+	bool enable_cdm_check;
+	bool link_state;
+	bool update_fc_fixup;
+	u8 init_link_width;
+	u32 msi_ctrl_int;
+	u32 num_lanes;
+	u32 max_speed;
+	u32 cid;
+	u32 cfg_link_cap_l1sub;
+	u32 pcie_cap_base;
+	u32 aspm_cmrt;
+	u32 aspm_pwr_on_t;
+	u32 aspm_l0s_enter_lat;
+
+	struct regulator *pex_ctl_supply;
+	struct regulator *slot_ctl_3v3;
+	struct regulator *slot_ctl_12v;
+
+	unsigned int phy_count;
+	struct phy **phys;
+
+	struct dentry *debugfs;
+};
+
+static inline struct tegra_pcie_dw *to_tegra_pcie(struct dw_pcie *pci)
+{
+	return container_of(pci, struct tegra_pcie_dw, pci);
+}
+
+static inline void appl_writel(struct tegra_pcie_dw *pcie, const u32 value,
+			       const u32 reg)
+{
+	writel_relaxed(value, pcie->appl_base + reg);
+}
+
+static inline u32 appl_readl(struct tegra_pcie_dw *pcie, const u32 reg)
+{
+	return readl_relaxed(pcie->appl_base + reg);
+}
+
+struct tegra_pcie_soc {
+	enum dw_pcie_device_mode mode;
+};
+
+static void apply_bad_link_workaround(struct pcie_port *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
+	u32 current_link_width;
+	u16 val;
+
+	/*
+	 * NOTE:- Since this scenario is uncommon and link as such is not
+	 * stable anyway, not waiting to confirm if link is really
+	 * transitioning to Gen-2 speed
+	 */
+	val = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA);
+	if (val & PCI_EXP_LNKSTA_LBMS) {
+		current_link_width = (val & PCI_EXP_LNKSTA_NLW) >>
+				     PCI_EXP_LNKSTA_NLW_SHIFT;
+		if (pcie->init_link_width > current_link_width) {
+			dev_warn(pci->dev, "PCIe link is bad, width reduced\n");
+			val = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base +
+						PCI_EXP_LNKCTL2);
+			val &= ~PCI_EXP_LNKCTL2_TLS;
+			val |= PCI_EXP_LNKCTL2_TLS_2_5GT;
+			dw_pcie_writew_dbi(pci, pcie->pcie_cap_base +
+					   PCI_EXP_LNKCTL2, val);
+
+			val = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base +
+						PCI_EXP_LNKCTL);
+			val |= PCI_EXP_LNKCTL_RL;
+			dw_pcie_writew_dbi(pci, pcie->pcie_cap_base +
+					   PCI_EXP_LNKCTL, val);
+		}
+	}
+}
+
+static irqreturn_t tegra_pcie_rp_irq_handler(struct tegra_pcie_dw *pcie)
+{
+	struct dw_pcie *pci = &pcie->pci;
+	struct pcie_port *pp = &pci->pp;
+	u32 val, tmp;
+	u16 val_w;
+
+	val = appl_readl(pcie, APPL_INTR_STATUS_L0);
+	if (val & APPL_INTR_STATUS_L0_LINK_STATE_INT) {
+		val = appl_readl(pcie, APPL_INTR_STATUS_L1_0_0);
+		if (val & APPL_INTR_STATUS_L1_0_0_LINK_REQ_RST_NOT_CHGED) {
+			appl_writel(pcie, val, APPL_INTR_STATUS_L1_0_0);
+
+			/* SBR & Surprise Link Down WAR */
+			val = appl_readl(pcie, APPL_CAR_RESET_OVRD);
+			val &= ~APPL_CAR_RESET_OVRD_CYA_OVERRIDE_CORE_RST_N;
+			appl_writel(pcie, val, APPL_CAR_RESET_OVRD);
+			udelay(1);
+			val = appl_readl(pcie, APPL_CAR_RESET_OVRD);
+			val |= APPL_CAR_RESET_OVRD_CYA_OVERRIDE_CORE_RST_N;
+			appl_writel(pcie, val, APPL_CAR_RESET_OVRD);
+
+			val = dw_pcie_readl_dbi(pci, PORT_LOGIC_GEN2_CTRL);
+			val |= PORT_LOGIC_GEN2_CTRL_DIRECT_SPEED_CHANGE;
+			dw_pcie_writel_dbi(pci, PORT_LOGIC_GEN2_CTRL, val);
+		}
+	}
+
+	if (val & APPL_INTR_STATUS_L0_INT_INT) {
+		val = appl_readl(pcie, APPL_INTR_STATUS_L1_8_0);
+		if (val & APPL_INTR_STATUS_L1_8_0_AUTO_BW_INT_STS) {
+			appl_writel(pcie,
+				    APPL_INTR_STATUS_L1_8_0_AUTO_BW_INT_STS,
+				    APPL_INTR_STATUS_L1_8_0);
+			apply_bad_link_workaround(pp);
+		}
+		if (val & APPL_INTR_STATUS_L1_8_0_BW_MGT_INT_STS) {
+			appl_writel(pcie,
+				    APPL_INTR_STATUS_L1_8_0_BW_MGT_INT_STS,
+				    APPL_INTR_STATUS_L1_8_0);
+
+			val_w = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base +
+						  PCI_EXP_LNKSTA);
+			dev_dbg(pci->dev, "Link Speed : Gen-%u\n", val_w &
+				PCI_EXP_LNKSTA_CLS);
+		}
+	}
+
+	val = appl_readl(pcie, APPL_INTR_STATUS_L0);
+	if (val & APPL_INTR_STATUS_L0_CDM_REG_CHK_INT) {
+		val = appl_readl(pcie, APPL_INTR_STATUS_L1_18);
+		tmp = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS);
+		if (val & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMPLT) {
+			dev_info(pci->dev, "CDM check complete\n");
+			tmp |= PCIE_PL_CHK_REG_CHK_REG_COMPLETE;
+		}
+		if (val & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMP_ERR) {
+			dev_err(pci->dev, "CDM comparison mismatch\n");
+			tmp |= PCIE_PL_CHK_REG_CHK_REG_COMPARISON_ERROR;
+		}
+		if (val & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_LOGIC_ERR) {
+			dev_err(pci->dev, "CDM Logic error\n");
+			tmp |= PCIE_PL_CHK_REG_CHK_REG_LOGIC_ERROR;
+		}
+		dw_pcie_writel_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS, tmp);
+		tmp = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_ERR_ADDR);
+		dev_err(pci->dev, "CDM Error Address Offset = 0x%08X\n", tmp);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t tegra_pcie_irq_handler(int irq, void *arg)
+{
+	struct tegra_pcie_dw *pcie = arg;
+
+	return tegra_pcie_rp_irq_handler(pcie);
+}
+
+static int tegra_pcie_dw_rd_own_conf(struct pcie_port *pp, int where, int size,
+				     u32 *val)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+
+	/*
+	 * This is an endpoint mode specific register happen to appear even
+	 * when controller is operating in root port mode and system hangs
+	 * when it is accessed with link being in ASPM-L1 state.
+	 * So skip accessing it altogether
+	 */
+	if (where == PORT_LOGIC_MSIX_DOORBELL) {
+		*val = 0x00000000;
+		return PCIBIOS_SUCCESSFUL;
+	}
+
+	return dw_pcie_read(pci->dbi_base + where, size, val);
+}
+
+static int tegra_pcie_dw_wr_own_conf(struct pcie_port *pp, int where, int size,
+				     u32 val)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+
+	/*
+	 * This is an endpoint mode specific register happen to appear even
+	 * when controller is operating in root port mode and system hangs
+	 * when it is accessed with link being in ASPM-L1 state.
+	 * So skip accessing it altogether
+	 */
+	if (where == PORT_LOGIC_MSIX_DOORBELL)
+		return PCIBIOS_SUCCESSFUL;
+
+	return dw_pcie_write(pci->dbi_base + where, size, val);
+}
+
+#if defined(CONFIG_PCIEASPM)
+static void disable_aspm_l11(struct tegra_pcie_dw *pcie)
+{
+	u32 val;
+
+	val = dw_pcie_readl_dbi(&pcie->pci, pcie->cfg_link_cap_l1sub);
+	val &= ~PCI_L1SS_CAP_ASPM_L1_1;
+	dw_pcie_writel_dbi(&pcie->pci, pcie->cfg_link_cap_l1sub, val);
+}
+
+static void disable_aspm_l12(struct tegra_pcie_dw *pcie)
+{
+	u32 val;
+
+	val = dw_pcie_readl_dbi(&pcie->pci, pcie->cfg_link_cap_l1sub);
+	val &= ~PCI_L1SS_CAP_ASPM_L1_2;
+	dw_pcie_writel_dbi(&pcie->pci, pcie->cfg_link_cap_l1sub, val);
+}
+
+static inline u32 event_counter_prog(struct tegra_pcie_dw *pcie, u32 event)
+{
+	u32 val;
+
+	val = dw_pcie_readl_dbi(&pcie->pci, event_cntr_ctrl_offset[pcie->cid]);
+	val &= ~(EVENT_COUNTER_EVENT_SEL_MASK << EVENT_COUNTER_EVENT_SEL_SHIFT);
+	val |= EVENT_COUNTER_GROUP_5 << EVENT_COUNTER_GROUP_SEL_SHIFT;
+	val |= event << EVENT_COUNTER_EVENT_SEL_SHIFT;
+	val |= EVENT_COUNTER_ENABLE_ALL << EVENT_COUNTER_ENABLE_SHIFT;
+	dw_pcie_writel_dbi(&pcie->pci, event_cntr_ctrl_offset[pcie->cid], val);
+	val = dw_pcie_readl_dbi(&pcie->pci, event_cntr_data_offset[pcie->cid]);
+
+	return val;
+}
+
+static int aspm_state_cnt(struct seq_file *s, void *data)
+{
+	struct tegra_pcie_dw *pcie = (struct tegra_pcie_dw *)
+				     dev_get_drvdata(s->private);
+	u32 val;
+
+	seq_printf(s, "Tx L0s entry count : %u\n",
+		   event_counter_prog(pcie, EVENT_COUNTER_EVENT_Tx_L0S));
+
+	seq_printf(s, "Rx L0s entry count : %u\n",
+		   event_counter_prog(pcie, EVENT_COUNTER_EVENT_Rx_L0S));
+
+	seq_printf(s, "Link L1 entry count : %u\n",
+		   event_counter_prog(pcie, EVENT_COUNTER_EVENT_L1));
+
+	seq_printf(s, "Link L1.1 entry count : %u\n",
+		   event_counter_prog(pcie, EVENT_COUNTER_EVENT_L1_1));
+
+	seq_printf(s, "Link L1.2 entry count : %u\n",
+		   event_counter_prog(pcie, EVENT_COUNTER_EVENT_L1_2));
+
+	/* Clear all counters */
+	dw_pcie_writel_dbi(&pcie->pci, event_cntr_ctrl_offset[pcie->cid],
+			   EVENT_COUNTER_ALL_CLEAR);
+
+	/* Re-enable counting */
+	val = EVENT_COUNTER_ENABLE_ALL << EVENT_COUNTER_ENABLE_SHIFT;
+	val |= EVENT_COUNTER_GROUP_5 << EVENT_COUNTER_GROUP_SEL_SHIFT;
+	dw_pcie_writel_dbi(&pcie->pci, event_cntr_ctrl_offset[pcie->cid], val);
+
+	return 0;
+}
+
+static void init_host_aspm(struct tegra_pcie_dw *pcie)
+{
+	struct dw_pcie *pci = &pcie->pci;
+	u32 val;
+
+	val = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_L1SS);
+	pcie->cfg_link_cap_l1sub = val + PCI_L1SS_CAP;
+
+	/* Enable ASPM counters */
+	val = EVENT_COUNTER_ENABLE_ALL << EVENT_COUNTER_ENABLE_SHIFT;
+	val |= EVENT_COUNTER_GROUP_5 << EVENT_COUNTER_GROUP_SEL_SHIFT;
+	dw_pcie_writel_dbi(pci, event_cntr_ctrl_offset[pcie->cid], val);
+
+	/* Program T_cmrt and T_pwr_on values */
+	val = dw_pcie_readl_dbi(pci, pcie->cfg_link_cap_l1sub);
+	val &= ~(PCI_L1SS_CAP_CM_RESTORE_TIME | PCI_L1SS_CAP_P_PWR_ON_VALUE);
+	val |= (pcie->aspm_cmrt << 8);
+	val |= (pcie->aspm_pwr_on_t << 19);
+	dw_pcie_writel_dbi(pci, pcie->cfg_link_cap_l1sub, val);
+
+	/* Program L0s and L1 entrance latencies */
+	val = dw_pcie_readl_dbi(pci, PORT_LOGIC_ACK_F_ASPM_CTRL);
+	val &= ~L0S_ENTRANCE_LAT_MASK;
+	val |= (pcie->aspm_l0s_enter_lat << L0S_ENTRANCE_LAT_SHIFT);
+	val |= ENTER_ASPM;
+	dw_pcie_writel_dbi(pci, PORT_LOGIC_ACK_F_ASPM_CTRL, val);
+}
+
+static int init_debugfs(struct tegra_pcie_dw *pcie)
+{
+	struct dentry *d;
+
+	d = debugfs_create_devm_seqfile(pcie->dev, "aspm_state_cnt",
+					pcie->debugfs, aspm_state_cnt);
+	if (IS_ERR_OR_NULL(d))
+		dev_err(pcie->dev,
+			"Failed to create debugfs file \"aspm_state_cnt\"\n");
+
+	return 0;
+}
+#else
+static inline void disable_aspm_l12(struct tegra_pcie_dw *pcie) { return; }
+static inline void disable_aspm_l11(struct tegra_pcie_dw *pcie) { return; }
+static inline void init_host_aspm(struct tegra_pcie_dw *pcie) { return; }
+static inline int init_debugfs(struct tegra_pcie_dw *pcie) { return 0; }
+#endif
+
+static void tegra_pcie_enable_system_interrupts(struct pcie_port *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
+	u32 val;
+	u16 val_w;
+
+	val = appl_readl(pcie, APPL_INTR_EN_L0_0);
+	val |= APPL_INTR_EN_L0_0_LINK_STATE_INT_EN;
+	appl_writel(pcie, val, APPL_INTR_EN_L0_0);
+
+	val = appl_readl(pcie, APPL_INTR_EN_L1_0_0);
+	val |= APPL_INTR_EN_L1_0_0_LINK_REQ_RST_NOT_INT_EN;
+	appl_writel(pcie, val, APPL_INTR_EN_L1_0_0);
+
+	if (pcie->enable_cdm_check) {
+		val = appl_readl(pcie, APPL_INTR_EN_L0_0);
+		val |= APPL_INTR_EN_L0_0_CDM_REG_CHK_INT_EN;
+		appl_writel(pcie, val, APPL_INTR_EN_L0_0);
+
+		val = appl_readl(pcie, APPL_INTR_EN_L1_18);
+		val |= APPL_INTR_EN_L1_18_CDM_REG_CHK_CMP_ERR;
+		val |= APPL_INTR_EN_L1_18_CDM_REG_CHK_LOGIC_ERR;
+		appl_writel(pcie, val, APPL_INTR_EN_L1_18);
+	}
+
+	val_w = dw_pcie_readw_dbi(&pcie->pci, pcie->pcie_cap_base +
+				  PCI_EXP_LNKSTA);
+	pcie->init_link_width = (val_w & PCI_EXP_LNKSTA_NLW) >>
+				PCI_EXP_LNKSTA_NLW_SHIFT;
+
+	val_w = dw_pcie_readw_dbi(&pcie->pci, pcie->pcie_cap_base +
+				  PCI_EXP_LNKCTL);
+	val_w |= PCI_EXP_LNKCTL_LBMIE;
+	dw_pcie_writew_dbi(&pcie->pci, pcie->pcie_cap_base + PCI_EXP_LNKCTL,
+			   val_w);
+}
+
+static void tegra_pcie_enable_legacy_interrupts(struct pcie_port *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
+	u32 val;
+
+	/* Enable legacy interrupt generation */
+	val = appl_readl(pcie, APPL_INTR_EN_L0_0);
+	val |= APPL_INTR_EN_L0_0_SYS_INTR_EN;
+	val |= APPL_INTR_EN_L0_0_INT_INT_EN;
+	appl_writel(pcie, val, APPL_INTR_EN_L0_0);
+
+	val = appl_readl(pcie, APPL_INTR_EN_L1_8_0);
+	val |= APPL_INTR_EN_L1_8_INTX_EN;
+	val |= APPL_INTR_EN_L1_8_AUTO_BW_INT_EN;
+	val |= APPL_INTR_EN_L1_8_BW_MGT_INT_EN;
+	if (IS_ENABLED(CONFIG_PCIEAER))
+		val |= APPL_INTR_EN_L1_8_AER_INT_EN;
+	appl_writel(pcie, val, APPL_INTR_EN_L1_8_0);
+}
+
+static void tegra_pcie_enable_msi_interrupts(struct pcie_port *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
+	u32 val;
+
+	dw_pcie_msi_init(pp);
+
+	/* Enable MSI interrupt generation */
+	val = appl_readl(pcie, APPL_INTR_EN_L0_0);
+	val |= APPL_INTR_EN_L0_0_SYS_MSI_INTR_EN;
+	val |= APPL_INTR_EN_L0_0_MSI_RCV_INT_EN;
+	appl_writel(pcie, val, APPL_INTR_EN_L0_0);
+}
+
+static void tegra_pcie_enable_interrupts(struct pcie_port *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
+
+	/* Clear interrupt statuses before enabling interrupts */
+	appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L0);
+	appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_0_0);
+	appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_1);
+	appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_2);
+	appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_3);
+	appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_6);
+	appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_7);
+	appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_8_0);
+	appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_9);
+	appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_10);
+	appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_11);
+	appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_13);
+	appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_14);
+	appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_15);
+	appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L1_17);
+
+	tegra_pcie_enable_system_interrupts(pp);
+	tegra_pcie_enable_legacy_interrupts(pp);
+	if (IS_ENABLED(CONFIG_PCI_MSI))
+		tegra_pcie_enable_msi_interrupts(pp);
+}
+
+static void config_gen3_gen4_eq_presets(struct tegra_pcie_dw *pcie)
+{
+	struct dw_pcie *pci = &pcie->pci;
+	u32 val, offset, i;
+
+	/* Program init preset */
+	for (i = 0; i < pcie->num_lanes; i++) {
+		dw_pcie_read(pci->dbi_base + CAP_SPCIE_CAP_OFF
+				 + (i * 2), 2, &val);
+		val &= ~CAP_SPCIE_CAP_OFF_DSP_TX_PRESET0_MASK;
+		val |= GEN3_GEN4_EQ_PRESET_INIT;
+		val &= ~CAP_SPCIE_CAP_OFF_USP_TX_PRESET0_MASK;
+		val |= (GEN3_GEN4_EQ_PRESET_INIT <<
+			   CAP_SPCIE_CAP_OFF_USP_TX_PRESET0_SHIFT);
+		dw_pcie_write(pci->dbi_base + CAP_SPCIE_CAP_OFF
+				 + (i * 2), 2, val);
+
+		offset = dw_pcie_find_ext_capability(pci,
+						     PCI_EXT_CAP_ID_PL_16GT) +
+				PCI_PL_16GT_LE_CTRL;
+		dw_pcie_read(pci->dbi_base + offset + i, 1, &val);
+		val &= ~PCI_PL_16GT_LE_CTRL_DSP_TX_PRESET_MASK;
+		val |= GEN3_GEN4_EQ_PRESET_INIT;
+		val &= ~PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_MASK;
+		val |= (GEN3_GEN4_EQ_PRESET_INIT <<
+			PCI_PL_16GT_LE_CTRL_USP_TX_PRESET_SHIFT);
+		dw_pcie_write(pci->dbi_base + offset + i, 1, val);
+	}
+
+	val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF);
+	val &= ~GEN3_RELATED_OFF_RATE_SHADOW_SEL_MASK;
+	dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val);
+
+	val = dw_pcie_readl_dbi(pci, GEN3_EQ_CONTROL_OFF);
+	val &= ~GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC_MASK;
+	val |= (0x3ff << GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC_SHIFT);
+	val &= ~GEN3_EQ_CONTROL_OFF_FB_MODE_MASK;
+	dw_pcie_writel_dbi(pci, GEN3_EQ_CONTROL_OFF, val);
+
+	val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF);
+	val &= ~GEN3_RELATED_OFF_RATE_SHADOW_SEL_MASK;
+	val |= (0x1 << GEN3_RELATED_OFF_RATE_SHADOW_SEL_SHIFT);
+	dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val);
+
+	val = dw_pcie_readl_dbi(pci, GEN3_EQ_CONTROL_OFF);
+	val &= ~GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC_MASK;
+	val |= (0x360 << GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC_SHIFT);
+	val &= ~GEN3_EQ_CONTROL_OFF_FB_MODE_MASK;
+	dw_pcie_writel_dbi(pci, GEN3_EQ_CONTROL_OFF, val);
+
+	val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF);
+	val &= ~GEN3_RELATED_OFF_RATE_SHADOW_SEL_MASK;
+	dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val);
+}
+
+static void tegra_pcie_prepare_host(struct pcie_port *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
+	u32 val;
+
+	val = dw_pcie_readl_dbi(pci, PCI_IO_BASE);
+	val &= ~(IO_BASE_IO_DECODE | IO_BASE_IO_DECODE_BIT8);
+	dw_pcie_writel_dbi(pci, PCI_IO_BASE, val);
+
+	val = dw_pcie_readl_dbi(pci, PCI_PREF_MEMORY_BASE);
+	val |= CFG_PREF_MEM_LIMIT_BASE_MEM_DECODE;
+	val |= CFG_PREF_MEM_LIMIT_BASE_MEM_LIMIT_DECODE;
+	dw_pcie_writel_dbi(pci, PCI_PREF_MEMORY_BASE, val);
+
+	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 0);
+
+	/* Configure FTS */
+	val = dw_pcie_readl_dbi(pci, PORT_LOGIC_ACK_F_ASPM_CTRL);
+	val &= ~(N_FTS_MASK << N_FTS_SHIFT);
+	val |= N_FTS_VAL << N_FTS_SHIFT;
+	dw_pcie_writel_dbi(pci, PORT_LOGIC_ACK_F_ASPM_CTRL, val);
+
+	val = dw_pcie_readl_dbi(pci, PORT_LOGIC_GEN2_CTRL);
+	val &= ~FTS_MASK;
+	val |= FTS_VAL;
+	dw_pcie_writel_dbi(pci, PORT_LOGIC_GEN2_CTRL, val);
+
+	/* Enable as 0xFFFF0001 response for CRS */
+	val = dw_pcie_readl_dbi(pci, PORT_LOGIC_AMBA_ERROR_RESPONSE_DEFAULT);
+	val &= ~(AMBA_ERROR_RESPONSE_CRS_MASK << AMBA_ERROR_RESPONSE_CRS_SHIFT);
+	val |= (AMBA_ERROR_RESPONSE_CRS_OKAY_FFFF0001 <<
+		AMBA_ERROR_RESPONSE_CRS_SHIFT);
+	dw_pcie_writel_dbi(pci, PORT_LOGIC_AMBA_ERROR_RESPONSE_DEFAULT, val);
+
+	/* Configure Max Speed from DT */
+	if (pcie->max_speed && pcie->max_speed != -EINVAL) {
+		val = dw_pcie_readl_dbi(pci, pcie->pcie_cap_base +
+					PCI_EXP_LNKCAP);
+		val &= ~PCI_EXP_LNKCAP_SLS;
+		val |= pcie->max_speed;
+		dw_pcie_writel_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKCAP,
+				   val);
+	}
+
+	/* Configure Max lane width from DT */
+	val = dw_pcie_readl_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKCAP);
+	val &= ~PCI_EXP_LNKCAP_MLW;
+	val |= (pcie->num_lanes << PCI_EXP_LNKSTA_NLW_SHIFT);
+	dw_pcie_writel_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKCAP, val);
+
+	config_gen3_gen4_eq_presets(pcie);
+
+	init_host_aspm(pcie);
+
+	val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF);
+	val &= ~GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL;
+	dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val);
+
+	if (pcie->update_fc_fixup) {
+		val = dw_pcie_readl_dbi(pci, CFG_TIMER_CTRL_MAX_FUNC_NUM_OFF);
+		val |= 0x1 << CFG_TIMER_CTRL_ACK_NAK_SHIFT;
+		dw_pcie_writel_dbi(pci, CFG_TIMER_CTRL_MAX_FUNC_NUM_OFF, val);
+	}
+
+	dw_pcie_setup_rc(pp);
+
+	clk_set_rate(pcie->core_clk, GEN4_CORE_CLK_FREQ);
+
+	/* Assert RST */
+	val = appl_readl(pcie, APPL_PINMUX);
+	val &= ~APPL_PINMUX_PEX_RST;
+	appl_writel(pcie, val, APPL_PINMUX);
+
+	usleep_range(100, 200);
+
+	/* Enable LTSSM */
+	val = appl_readl(pcie, APPL_CTRL);
+	val |= APPL_CTRL_LTSSM_EN;
+	appl_writel(pcie, val, APPL_CTRL);
+
+	/* De-assert RST */
+	val = appl_readl(pcie, APPL_PINMUX);
+	val |= APPL_PINMUX_PEX_RST;
+	appl_writel(pcie, val, APPL_PINMUX);
+
+	msleep(100);
+}
+
+static int tegra_pcie_dw_host_init(struct pcie_port *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
+	u32 val, tmp, offset, speed;
+
+	tegra_pcie_prepare_host(pp);
+
+	if (dw_pcie_wait_for_link(pci)) {
+		/*
+		 * There are some endpoints which can't get the link up if
+		 * root port has Data Link Feature (DLF) enabled.
+		 * Refer Spec rev 4.0 ver 1.0 sec 3.4.2 & 7.7.4 for more info
+		 * on Scaled Flow Control and DLF.
+		 * So, need to confirm that is indeed the case here and attempt
+		 * link up once again with DLF disabled.
+		 */
+		val = appl_readl(pcie, APPL_DEBUG);
+		val &= APPL_DEBUG_LTSSM_STATE_MASK;
+		val >>= APPL_DEBUG_LTSSM_STATE_SHIFT;
+		tmp = appl_readl(pcie, APPL_LINK_STATUS);
+		tmp &= APPL_LINK_STATUS_RDLH_LINK_UP;
+		if (!(val == 0x11 && !tmp)) {
+			/* Link is down for all good reasons */
+			return 0;
+		}
+
+		dev_info(pci->dev, "Link is down in DLL");
+		dev_info(pci->dev, "Trying again with DLFE disabled\n");
+		/* Disable LTSSM */
+		val = appl_readl(pcie, APPL_CTRL);
+		val &= ~APPL_CTRL_LTSSM_EN;
+		appl_writel(pcie, val, APPL_CTRL);
+
+		reset_control_assert(pcie->core_rst);
+		reset_control_deassert(pcie->core_rst);
+
+		offset = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_DLF);
+		val = dw_pcie_readl_dbi(pci, offset + PCI_DLF_CAP);
+		val &= ~PCI_DLF_EXCHANGE_ENABLE;
+		dw_pcie_writel_dbi(pci, offset, val);
+
+		tegra_pcie_prepare_host(pp);
+
+		if (dw_pcie_wait_for_link(pci))
+			return 0;
+	}
+
+	speed = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA) &
+		PCI_EXP_LNKSTA_CLS;
+	clk_set_rate(pcie->core_clk, pcie_gen_freq[speed - 1]);
+
+	tegra_pcie_enable_interrupts(pp);
+
+	return 0;
+}
+
+static int tegra_pcie_dw_link_up(struct dw_pcie *pci)
+{
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
+	u32 val = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA);
+
+	return !!(val & PCI_EXP_LNKSTA_DLLLA);
+}
+
+static void tegra_pcie_set_msi_vec_num(struct pcie_port *pp)
+{
+	pp->num_vectors = MAX_MSI_IRQS;
+}
+
+static const struct dw_pcie_ops tegra_dw_pcie_ops = {
+	.link_up = tegra_pcie_dw_link_up,
+};
+
+static struct dw_pcie_host_ops tegra_pcie_dw_host_ops = {
+	.rd_own_conf = tegra_pcie_dw_rd_own_conf,
+	.wr_own_conf = tegra_pcie_dw_wr_own_conf,
+	.host_init = tegra_pcie_dw_host_init,
+	.set_num_vectors = tegra_pcie_set_msi_vec_num,
+};
+
+static void tegra_pcie_disable_phy(struct tegra_pcie_dw *pcie)
+{
+	unsigned int phy_count = pcie->phy_count;
+
+	while (phy_count--) {
+		phy_power_off(pcie->phys[phy_count]);
+		phy_exit(pcie->phys[phy_count]);
+	}
+}
+
+static int tegra_pcie_enable_phy(struct tegra_pcie_dw *pcie)
+{
+	unsigned int i;
+	int ret;
+
+	for (i = 0; i < pcie->phy_count; i++) {
+		ret = phy_init(pcie->phys[i]);
+		if (ret < 0)
+			goto phy_power_off;
+
+		ret = phy_power_on(pcie->phys[i]);
+		if (ret < 0)
+			goto phy_exit;
+	}
+
+	return 0;
+
+phy_power_off:
+	while (i--) {
+		phy_power_off(pcie->phys[i]);
+phy_exit:
+		phy_exit(pcie->phys[i]);
+	}
+
+	return ret;
+}
+
+static int tegra_pcie_dw_parse_dt(struct tegra_pcie_dw *pcie)
+{
+	struct device_node *np = pcie->dev->of_node;
+	int ret;
+
+	ret = of_property_read_u32(np, "nvidia,aspm-cmrt-us", &pcie->aspm_cmrt);
+	if (ret < 0) {
+		dev_info(pcie->dev, "Failed to read ASPM T_cmrt: %d\n", ret);
+		return ret;
+	}
+
+	ret = of_property_read_u32(np, "nvidia,aspm-pwr-on-t-us",
+				   &pcie->aspm_pwr_on_t);
+	if (ret < 0)
+		dev_info(pcie->dev, "Failed to read ASPM Power On time: %d\n",
+			 ret);
+
+	ret = of_property_read_u32(np, "nvidia,aspm-l0s-entrance-latency-us",
+				   &pcie->aspm_l0s_enter_lat);
+	if (ret < 0)
+		dev_info(pcie->dev,
+			 "Failed to read ASPM L0s Entrance latency: %d\n", ret);
+
+	ret = of_property_read_u32(np, "num-lanes", &pcie->num_lanes);
+	if (ret < 0) {
+		dev_err(pcie->dev, "Failed to read num-lanes: %d\n", ret);
+		return ret;
+	}
+
+	pcie->max_speed = of_pci_get_max_link_speed(np);
+
+	ret = of_property_read_u32_index(np, "nvidia,bpmp", 1, &pcie->cid);
+	if (ret) {
+		dev_err(pcie->dev, "Failed to read Controller-ID: %d\n", ret);
+		return ret;
+	}
+
+	ret = of_property_count_strings(np, "phy-names");
+	if (ret < 0) {
+		dev_err(pcie->dev, "Failed to find PHY entries: %d\n",
+			ret);
+		return ret;
+	}
+	pcie->phy_count = ret;
+
+	if (of_property_read_bool(np, "nvidia,update-fc-fixup"))
+		pcie->update_fc_fixup = true;
+
+	pcie->supports_clkreq =
+		of_property_read_bool(pcie->dev->of_node, "supports-clkreq");
+
+	pcie->enable_cdm_check =
+		of_property_read_bool(np, "snps,enable-cdm-check");
+
+	return 0;
+}
+
+static int tegra_pcie_bpmp_set_ctrl_state(struct tegra_pcie_dw *pcie,
+					  bool enable)
+{
+	struct mrq_uphy_response resp;
+	struct tegra_bpmp_message msg;
+	struct mrq_uphy_request req;
+
+	/* Controller-5 doesn't need to have its state set by BPMP-FW */
+	if (pcie->cid == 5)
+		return 0;
+
+	memset(&req, 0, sizeof(req));
+	memset(&resp, 0, sizeof(resp));
+
+	req.cmd = CMD_UPHY_PCIE_CONTROLLER_STATE;
+	req.controller_state.pcie_controller = pcie->cid;
+	req.controller_state.enable = enable;
+
+	memset(&msg, 0, sizeof(msg));
+	msg.mrq = MRQ_UPHY;
+	msg.tx.data = &req;
+	msg.tx.size = sizeof(req);
+	msg.rx.data = &resp;
+	msg.rx.size = sizeof(resp);
+
+	return tegra_bpmp_transfer(pcie->bpmp, &msg);
+}
+
+static void tegra_pcie_downstream_dev_to_D0(struct tegra_pcie_dw *pcie)
+{
+	struct pcie_port *pp = &pcie->pci.pp;
+	struct pci_bus *child, *root_bus = NULL;
+	struct pci_dev *pdev;
+
+	/*
+	 * link doesn't go into L2 state with some of the endpoints with Tegra
+	 * if they are not in D0 state. So, need to make sure that immediate
+	 * downstream devices are in D0 state before sending PME_TurnOff to put
+	 * link into L2 state.
+	 * This is as per PCI Express Base r4.0 v1.0 September 27-2017,
+	 * 5.2 Link State Power Management (Page #428).
+	 */
+
+	list_for_each_entry(child, &pp->root_bus->children, node) {
+		/* Bring downstream devices to D0 if they are not already in */
+		if (child->parent == pp->root_bus) {
+			root_bus = child;
+			break;
+		}
+	}
+
+	if (!root_bus) {
+		dev_err(pcie->dev, "Failed to find downstream devices\n");
+		return;
+	}
+
+	list_for_each_entry(pdev, &root_bus->devices, bus_list) {
+		if (PCI_SLOT(pdev->devfn) == 0) {
+			if (pci_set_power_state(pdev, PCI_D0))
+				dev_err(pcie->dev,
+					"Failed to transition %s to D0 state\n",
+					dev_name(&pdev->dev));
+		}
+	}
+}
+
+static int tegra_pcie_get_slot_regulators(struct tegra_pcie_dw *pcie)
+{
+	pcie->slot_ctl_3v3 = devm_regulator_get_optional(pcie->dev, "vpcie3v3");
+	if (IS_ERR(pcie->slot_ctl_3v3)) {
+		if (PTR_ERR(pcie->slot_ctl_3v3) != -ENODEV)
+			return PTR_ERR(pcie->slot_ctl_3v3);
+
+		pcie->slot_ctl_3v3 = NULL;
+	}
+
+	pcie->slot_ctl_12v = devm_regulator_get_optional(pcie->dev, "vpcie12v");
+	if (IS_ERR(pcie->slot_ctl_12v)) {
+		if (PTR_ERR(pcie->slot_ctl_12v) != -ENODEV)
+			return PTR_ERR(pcie->slot_ctl_12v);
+
+		pcie->slot_ctl_12v = NULL;
+	}
+
+	return 0;
+}
+
+static int tegra_pcie_enable_slot_regulators(struct tegra_pcie_dw *pcie)
+{
+	int ret;
+
+	if (pcie->slot_ctl_3v3) {
+		ret = regulator_enable(pcie->slot_ctl_3v3);
+		if (ret < 0) {
+			dev_err(pcie->dev,
+				"Failed to enable 3.3V slot supply: %d\n", ret);
+			return ret;
+		}
+	}
+
+	if (pcie->slot_ctl_12v) {
+		ret = regulator_enable(pcie->slot_ctl_12v);
+		if (ret < 0) {
+			dev_err(pcie->dev,
+				"Failed to enable 12V slot supply: %d\n", ret);
+			goto fail_12v_enable;
+		}
+	}
+
+	/*
+	 * According to PCI Express Card Electromechanical Specification
+	 * Revision 1.1, Table-2.4, T_PVPERL (Power stable to PERST# inactive)
+	 * should be a minimum of 100ms.
+	 */
+	if (pcie->slot_ctl_3v3 || pcie->slot_ctl_12v)
+		msleep(100);
+
+	return 0;
+
+fail_12v_enable:
+	if (pcie->slot_ctl_3v3)
+		regulator_disable(pcie->slot_ctl_3v3);
+	return ret;
+}
+
+static void tegra_pcie_disable_slot_regulators(struct tegra_pcie_dw *pcie)
+{
+	if (pcie->slot_ctl_12v)
+		regulator_disable(pcie->slot_ctl_12v);
+	if (pcie->slot_ctl_3v3)
+		regulator_disable(pcie->slot_ctl_3v3);
+}
+
+static int tegra_pcie_config_controller(struct tegra_pcie_dw *pcie,
+					bool en_hw_hot_rst)
+{
+	int ret;
+	u32 val;
+
+	ret = tegra_pcie_bpmp_set_ctrl_state(pcie, true);
+	if (ret) {
+		dev_err(pcie->dev,
+			"Failed to enable controller %u: %d\n", pcie->cid, ret);
+		return ret;
+	}
+
+	ret = tegra_pcie_enable_slot_regulators(pcie);
+	if (ret < 0)
+		goto fail_slot_reg_en;
+
+	ret = regulator_enable(pcie->pex_ctl_supply);
+	if (ret < 0) {
+		dev_err(pcie->dev, "Failed to enable regulator: %d\n", ret);
+		goto fail_reg_en;
+	}
+
+	ret = clk_prepare_enable(pcie->core_clk);
+	if (ret) {
+		dev_err(pcie->dev, "Failed to enable core clock: %d\n", ret);
+		goto fail_core_clk;
+	}
+
+	ret = reset_control_deassert(pcie->core_apb_rst);
+	if (ret) {
+		dev_err(pcie->dev, "Failed to deassert core APB reset: %d\n",
+			ret);
+		goto fail_core_apb_rst;
+	}
+
+	if (en_hw_hot_rst) {
+		/* Enable HW_HOT_RST mode */
+		val = appl_readl(pcie, APPL_CTRL);
+		val &= ~(APPL_CTRL_HW_HOT_RST_MODE_MASK <<
+			 APPL_CTRL_HW_HOT_RST_MODE_SHIFT);
+		val |= APPL_CTRL_HW_HOT_RST_EN;
+		appl_writel(pcie, val, APPL_CTRL);
+	}
+
+	ret = tegra_pcie_enable_phy(pcie);
+	if (ret) {
+		dev_err(pcie->dev, "Failed to enable PHY: %d\n", ret);
+		goto fail_phy;
+	}
+
+	/* Update CFG base address */
+	appl_writel(pcie, pcie->dbi_res->start & APPL_CFG_BASE_ADDR_MASK,
+		    APPL_CFG_BASE_ADDR);
+
+	/* Configure this core for RP mode operation */
+	appl_writel(pcie, APPL_DM_TYPE_RP, APPL_DM_TYPE);
+
+	appl_writel(pcie, 0x0, APPL_CFG_SLCG_OVERRIDE);
+
+	val = appl_readl(pcie, APPL_CTRL);
+	appl_writel(pcie, val | APPL_CTRL_SYS_PRE_DET_STATE, APPL_CTRL);
+
+	val = appl_readl(pcie, APPL_CFG_MISC);
+	val |= (APPL_CFG_MISC_ARCACHE_VAL << APPL_CFG_MISC_ARCACHE_SHIFT);
+	appl_writel(pcie, val, APPL_CFG_MISC);
+
+	if (!pcie->supports_clkreq) {
+		val = appl_readl(pcie, APPL_PINMUX);
+		val |= APPL_PINMUX_CLKREQ_OUT_OVRD_EN;
+		val |= APPL_PINMUX_CLKREQ_OUT_OVRD;
+		appl_writel(pcie, val, APPL_PINMUX);
+	}
+
+	/* Update iATU_DMA base address */
+	appl_writel(pcie,
+		    pcie->atu_dma_res->start & APPL_CFG_IATU_DMA_BASE_ADDR_MASK,
+		    APPL_CFG_IATU_DMA_BASE_ADDR);
+
+	reset_control_deassert(pcie->core_rst);
+
+	pcie->pcie_cap_base = dw_pcie_find_capability(&pcie->pci,
+						      PCI_CAP_ID_EXP);
+
+	/* Disable ASPM-L1SS advertisement as there is no CLKREQ routing */
+	if (!pcie->supports_clkreq) {
+		disable_aspm_l11(pcie);
+		disable_aspm_l12(pcie);
+	}
+
+	return ret;
+
+fail_phy:
+	reset_control_assert(pcie->core_apb_rst);
+fail_core_apb_rst:
+	clk_disable_unprepare(pcie->core_clk);
+fail_core_clk:
+	regulator_disable(pcie->pex_ctl_supply);
+fail_reg_en:
+	tegra_pcie_disable_slot_regulators(pcie);
+fail_slot_reg_en:
+	tegra_pcie_bpmp_set_ctrl_state(pcie, false);
+
+	return ret;
+}
+
+static int __deinit_controller(struct tegra_pcie_dw *pcie)
+{
+	int ret;
+
+	ret = reset_control_assert(pcie->core_rst);
+	if (ret) {
+		dev_err(pcie->dev, "Failed to assert \"core\" reset: %d\n",
+			ret);
+		return ret;
+	}
+
+	tegra_pcie_disable_phy(pcie);
+
+	ret = reset_control_assert(pcie->core_apb_rst);
+	if (ret) {
+		dev_err(pcie->dev, "Failed to assert APB reset: %d\n", ret);
+		return ret;
+	}
+
+	clk_disable_unprepare(pcie->core_clk);
+
+	ret = regulator_disable(pcie->pex_ctl_supply);
+	if (ret) {
+		dev_err(pcie->dev, "Failed to disable regulator: %d\n", ret);
+		return ret;
+	}
+
+	tegra_pcie_disable_slot_regulators(pcie);
+
+	ret = tegra_pcie_bpmp_set_ctrl_state(pcie, false);
+	if (ret) {
+		dev_err(pcie->dev, "Failed to disable controller %d: %d\n",
+			pcie->cid, ret);
+		return ret;
+	}
+
+	return ret;
+}
+
+static int tegra_pcie_init_controller(struct tegra_pcie_dw *pcie)
+{
+	struct dw_pcie *pci = &pcie->pci;
+	struct pcie_port *pp = &pci->pp;
+	int ret;
+
+	ret = tegra_pcie_config_controller(pcie, false);
+	if (ret < 0)
+		return ret;
+
+	pp->ops = &tegra_pcie_dw_host_ops;
+
+	ret = dw_pcie_host_init(pp);
+	if (ret < 0) {
+		dev_err(pcie->dev, "Failed to add PCIe port: %d\n", ret);
+		goto fail_host_init;
+	}
+
+	return 0;
+
+fail_host_init:
+	return __deinit_controller(pcie);
+}
+
+static int tegra_pcie_try_link_l2(struct tegra_pcie_dw *pcie)
+{
+	u32 val;
+
+	if (!tegra_pcie_dw_link_up(&pcie->pci))
+		return 0;
+
+	val = appl_readl(pcie, APPL_RADM_STATUS);
+	val |= APPL_PM_XMT_TURNOFF_STATE;
+	appl_writel(pcie, val, APPL_RADM_STATUS);
+
+	return readl_poll_timeout_atomic(pcie->appl_base + APPL_DEBUG, val,
+				 val & APPL_DEBUG_PM_LINKST_IN_L2_LAT,
+				 1, PME_ACK_TIMEOUT);
+}
+
+static void tegra_pcie_dw_pme_turnoff(struct tegra_pcie_dw *pcie)
+{
+	u32 data;
+	int err;
+
+	if (!tegra_pcie_dw_link_up(&pcie->pci)) {
+		dev_dbg(pcie->dev, "PCIe link is not up...!\n");
+		return;
+	}
+
+	if (tegra_pcie_try_link_l2(pcie)) {
+		dev_info(pcie->dev, "Link didn't transition to L2 state\n");
+		/*
+		 * TX lane clock freq will reset to Gen1 only if link is in L2
+		 * or detect state.
+		 * So apply pex_rst to end point to force RP to go into detect
+		 * state
+		 */
+		data = appl_readl(pcie, APPL_PINMUX);
+		data &= ~APPL_PINMUX_PEX_RST;
+		appl_writel(pcie, data, APPL_PINMUX);
+
+		err = readl_poll_timeout_atomic(pcie->appl_base + APPL_DEBUG,
+						data,
+						((data &
+						APPL_DEBUG_LTSSM_STATE_MASK) >>
+						APPL_DEBUG_LTSSM_STATE_SHIFT) ==
+						LTSSM_STATE_PRE_DETECT,
+						1, LTSSM_TIMEOUT);
+		if (err) {
+			dev_info(pcie->dev, "Link didn't go to detect state\n");
+		} else {
+			/* Disable LTSSM after link is in detect state */
+			data = appl_readl(pcie, APPL_CTRL);
+			data &= ~APPL_CTRL_LTSSM_EN;
+			appl_writel(pcie, data, APPL_CTRL);
+		}
+	}
+	/*
+	 * DBI registers may not be accessible after this as PLL-E would be
+	 * down depending on how CLKREQ is pulled by end point
+	 */
+	data = appl_readl(pcie, APPL_PINMUX);
+	data |= (APPL_PINMUX_CLKREQ_OVERRIDE_EN | APPL_PINMUX_CLKREQ_OVERRIDE);
+	/* Cut REFCLK to slot */
+	data |= APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE_EN;
+	data &= ~APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE;
+	appl_writel(pcie, data, APPL_PINMUX);
+}
+
+static int tegra_pcie_deinit_controller(struct tegra_pcie_dw *pcie)
+{
+	tegra_pcie_downstream_dev_to_D0(pcie);
+	dw_pcie_host_deinit(&pcie->pci.pp);
+	tegra_pcie_dw_pme_turnoff(pcie);
+
+	return __deinit_controller(pcie);
+}
+
+static int tegra_pcie_config_rp(struct tegra_pcie_dw *pcie)
+{
+	struct pcie_port *pp = &pcie->pci.pp;
+	struct device *dev = pcie->dev;
+	char *name;
+	int ret;
+
+	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+		pp->msi_irq = of_irq_get_byname(dev->of_node, "msi");
+		if (!pp->msi_irq) {
+			dev_err(dev, "Failed to get MSI interrupt\n");
+			return -ENODEV;
+		}
+	}
+
+	pm_runtime_enable(dev);
+
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		dev_err(dev, "Failed to get runtime sync for PCIe dev: %d\n",
+			ret);
+		goto fail_pm_get_sync;
+	}
+
+	ret = pinctrl_pm_select_default_state(dev);
+	if (ret < 0) {
+		dev_err(dev, "Failed to configure sideband pins: %d\n", ret);
+		goto fail_pinctrl;
+	}
+
+	tegra_pcie_init_controller(pcie);
+
+	pcie->link_state = tegra_pcie_dw_link_up(&pcie->pci);
+	if (!pcie->link_state) {
+		ret = -ENOMEDIUM;
+		goto fail_host_init;
+	}
+
+	name = devm_kasprintf(dev, GFP_KERNEL, "%pOFP", dev->of_node);
+	if (!name) {
+		ret = -ENOMEM;
+		goto fail_host_init;
+	}
+
+	pcie->debugfs = debugfs_create_dir(name, NULL);
+	if (!pcie->debugfs)
+		dev_err(dev, "Failed to create debugfs\n");
+	else
+		init_debugfs(pcie);
+
+	return ret;
+
+fail_host_init:
+	tegra_pcie_deinit_controller(pcie);
+fail_pinctrl:
+	pm_runtime_put_sync(dev);
+fail_pm_get_sync:
+	pm_runtime_disable(dev);
+	return ret;
+}
+
+static int tegra_pcie_dw_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct resource *atu_dma_res;
+	struct tegra_pcie_dw *pcie;
+	struct resource *dbi_res;
+	struct pcie_port *pp;
+	struct dw_pcie *pci;
+	struct phy **phys;
+	char *name;
+	int ret;
+	u32 i;
+
+	pcie = devm_kzalloc(dev, sizeof(*pcie), GFP_KERNEL);
+	if (!pcie)
+		return -ENOMEM;
+
+	pci = &pcie->pci;
+	pci->dev = &pdev->dev;
+	pci->ops = &tegra_dw_pcie_ops;
+	pp = &pci->pp;
+	pcie->dev = &pdev->dev;
+
+	ret = tegra_pcie_dw_parse_dt(pcie);
+	if (ret < 0) {
+		dev_err(dev, "Failed to parse device tree: %d\n", ret);
+		return ret;
+	}
+
+	ret = tegra_pcie_get_slot_regulators(pcie);
+	if (ret < 0) {
+		dev_err(dev, "Failed to get slot regulators: %d\n", ret);
+		return ret;
+	}
+
+	pcie->pex_ctl_supply = devm_regulator_get(dev, "vddio-pex-ctl");
+	if (IS_ERR(pcie->pex_ctl_supply)) {
+		ret = PTR_ERR(pcie->pex_ctl_supply);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "Failed to get regulator: %ld\n",
+				PTR_ERR(pcie->pex_ctl_supply));
+		return ret;
+	}
+
+	pcie->core_clk = devm_clk_get(dev, "core");
+	if (IS_ERR(pcie->core_clk)) {
+		dev_err(dev, "Failed to get core clock: %ld\n",
+			PTR_ERR(pcie->core_clk));
+		return PTR_ERR(pcie->core_clk);
+	}
+
+	pcie->appl_res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						      "appl");
+	if (!pcie->appl_res) {
+		dev_err(dev, "Failed to find \"appl\" region\n");
+		return -ENODEV;
+	}
+
+	pcie->appl_base = devm_ioremap_resource(dev, pcie->appl_res);
+	if (IS_ERR(pcie->appl_base))
+		return PTR_ERR(pcie->appl_base);
+
+	pcie->core_apb_rst = devm_reset_control_get(dev, "apb");
+	if (IS_ERR(pcie->core_apb_rst)) {
+		dev_err(dev, "Failed to get APB reset: %ld\n",
+			PTR_ERR(pcie->core_apb_rst));
+		return PTR_ERR(pcie->core_apb_rst);
+	}
+
+	phys = devm_kcalloc(dev, pcie->phy_count, sizeof(*phys), GFP_KERNEL);
+	if (!phys)
+		return -ENOMEM;
+
+	for (i = 0; i < pcie->phy_count; i++) {
+		name = kasprintf(GFP_KERNEL, "p2u-%u", i);
+		if (!name) {
+			dev_err(dev, "Failed to create P2U string\n");
+			return -ENOMEM;
+		}
+		phys[i] = devm_phy_get(dev, name);
+		kfree(name);
+		if (IS_ERR(phys[i])) {
+			ret = PTR_ERR(phys[i]);
+			if (ret != -EPROBE_DEFER)
+				dev_err(dev, "Failed to get PHY: %d\n", ret);
+			return ret;
+		}
+	}
+
+	pcie->phys = phys;
+
+	dbi_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi");
+	if (!dbi_res) {
+		dev_err(dev, "Failed to find \"dbi\" region\n");
+		return -ENODEV;
+	}
+	pcie->dbi_res = dbi_res;
+
+	pci->dbi_base = devm_ioremap_resource(dev, dbi_res);
+	if (IS_ERR(pci->dbi_base))
+		return PTR_ERR(pci->dbi_base);
+
+	/* Tegra HW locates DBI2 at a fixed offset from DBI */
+	pci->dbi_base2 = pci->dbi_base + 0x1000;
+
+	atu_dma_res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
+						   "atu_dma");
+	if (!atu_dma_res) {
+		dev_err(dev, "Failed to find \"atu_dma\" region\n");
+		return -ENODEV;
+	}
+	pcie->atu_dma_res = atu_dma_res;
+
+	pci->atu_base = devm_ioremap_resource(dev, atu_dma_res);
+	if (IS_ERR(pci->atu_base))
+		return PTR_ERR(pci->atu_base);
+
+	pcie->core_rst = devm_reset_control_get(dev, "core");
+	if (IS_ERR(pcie->core_rst)) {
+		dev_err(dev, "Failed to get core reset: %ld\n",
+			PTR_ERR(pcie->core_rst));
+		return PTR_ERR(pcie->core_rst);
+	}
+
+	pp->irq = platform_get_irq_byname(pdev, "intr");
+	if (!pp->irq) {
+		dev_err(dev, "Failed to get \"intr\" interrupt\n");
+		return -ENODEV;
+	}
+
+	ret = devm_request_irq(dev, pp->irq, tegra_pcie_irq_handler,
+			       IRQF_SHARED, "tegra-pcie-intr", pcie);
+	if (ret) {
+		dev_err(dev, "Failed to request IRQ %d: %d\n", pp->irq, ret);
+		return ret;
+	}
+
+	pcie->bpmp = tegra_bpmp_get(dev);
+	if (IS_ERR(pcie->bpmp))
+		return PTR_ERR(pcie->bpmp);
+
+	platform_set_drvdata(pdev, pcie);
+
+	ret = tegra_pcie_config_rp(pcie);
+	if (ret && ret != -ENOMEDIUM)
+		goto fail;
+	else
+		return 0;
+
+fail:
+	tegra_bpmp_put(pcie->bpmp);
+	return ret;
+}
+
+static int tegra_pcie_dw_remove(struct platform_device *pdev)
+{
+	struct tegra_pcie_dw *pcie = platform_get_drvdata(pdev);
+
+	if (!pcie->link_state)
+		return 0;
+
+	debugfs_remove_recursive(pcie->debugfs);
+	tegra_pcie_deinit_controller(pcie);
+	pm_runtime_put_sync(pcie->dev);
+	pm_runtime_disable(pcie->dev);
+	tegra_bpmp_put(pcie->bpmp);
+
+	return 0;
+}
+
+static int tegra_pcie_dw_suspend_late(struct device *dev)
+{
+	struct tegra_pcie_dw *pcie = dev_get_drvdata(dev);
+	u32 val;
+
+	if (!pcie->link_state)
+		return 0;
+
+	/* Enable HW_HOT_RST mode */
+	val = appl_readl(pcie, APPL_CTRL);
+	val &= ~(APPL_CTRL_HW_HOT_RST_MODE_MASK <<
+		 APPL_CTRL_HW_HOT_RST_MODE_SHIFT);
+	val |= APPL_CTRL_HW_HOT_RST_EN;
+	appl_writel(pcie, val, APPL_CTRL);
+
+	return 0;
+}
+
+static int tegra_pcie_dw_suspend_noirq(struct device *dev)
+{
+	struct tegra_pcie_dw *pcie = dev_get_drvdata(dev);
+
+	if (!pcie->link_state)
+		return 0;
+
+	/* Save MSI interrupt vector */
+	pcie->msi_ctrl_int = dw_pcie_readl_dbi(&pcie->pci,
+					       PORT_LOGIC_MSI_CTRL_INT_0_EN);
+	tegra_pcie_downstream_dev_to_D0(pcie);
+	tegra_pcie_dw_pme_turnoff(pcie);
+
+	return __deinit_controller(pcie);
+}
+
+static int tegra_pcie_dw_resume_noirq(struct device *dev)
+{
+	struct tegra_pcie_dw *pcie = dev_get_drvdata(dev);
+	int ret;
+
+	if (!pcie->link_state)
+		return 0;
+
+	ret = tegra_pcie_config_controller(pcie, true);
+	if (ret < 0)
+		return ret;
+
+	ret = tegra_pcie_dw_host_init(&pcie->pci.pp);
+	if (ret < 0) {
+		dev_err(dev, "Failed to init host: %d\n", ret);
+		goto fail_host_init;
+	}
+
+	/* Restore MSI interrupt vector */
+	dw_pcie_writel_dbi(&pcie->pci, PORT_LOGIC_MSI_CTRL_INT_0_EN,
+			   pcie->msi_ctrl_int);
+
+	return 0;
+
+fail_host_init:
+	return __deinit_controller(pcie);
+}
+
+static int tegra_pcie_dw_resume_early(struct device *dev)
+{
+	struct tegra_pcie_dw *pcie = dev_get_drvdata(dev);
+	u32 val;
+
+	if (!pcie->link_state)
+		return 0;
+
+	/* Disable HW_HOT_RST mode */
+	val = appl_readl(pcie, APPL_CTRL);
+	val &= ~(APPL_CTRL_HW_HOT_RST_MODE_MASK <<
+		 APPL_CTRL_HW_HOT_RST_MODE_SHIFT);
+	val |= APPL_CTRL_HW_HOT_RST_MODE_IMDT_RST <<
+	       APPL_CTRL_HW_HOT_RST_MODE_SHIFT;
+	val &= ~APPL_CTRL_HW_HOT_RST_EN;
+	appl_writel(pcie, val, APPL_CTRL);
+
+	return 0;
+}
+
+static void tegra_pcie_dw_shutdown(struct platform_device *pdev)
+{
+	struct tegra_pcie_dw *pcie = platform_get_drvdata(pdev);
+
+	if (!pcie->link_state)
+		return;
+
+	debugfs_remove_recursive(pcie->debugfs);
+	tegra_pcie_downstream_dev_to_D0(pcie);
+
+	disable_irq(pcie->pci.pp.irq);
+	if (IS_ENABLED(CONFIG_PCI_MSI))
+		disable_irq(pcie->pci.pp.msi_irq);
+
+	tegra_pcie_dw_pme_turnoff(pcie);
+	__deinit_controller(pcie);
+}
+
+static const struct of_device_id tegra_pcie_dw_of_match[] = {
+	{
+		.compatible = "nvidia,tegra194-pcie",
+	},
+	{},
+};
+
+static const struct dev_pm_ops tegra_pcie_dw_pm_ops = {
+	.suspend_late = tegra_pcie_dw_suspend_late,
+	.suspend_noirq = tegra_pcie_dw_suspend_noirq,
+	.resume_noirq = tegra_pcie_dw_resume_noirq,
+	.resume_early = tegra_pcie_dw_resume_early,
+};
+
+static struct platform_driver tegra_pcie_dw_driver = {
+	.probe = tegra_pcie_dw_probe,
+	.remove = tegra_pcie_dw_remove,
+	.shutdown = tegra_pcie_dw_shutdown,
+	.driver = {
+		.name	= "tegra194-pcie",
+		.pm = &tegra_pcie_dw_pm_ops,
+		.of_match_table = tegra_pcie_dw_of_match,
+	},
+};
+module_platform_driver(tegra_pcie_dw_driver);
+
+MODULE_DEVICE_TABLE(of, tegra_pcie_dw_of_match);
+
+MODULE_AUTHOR("Vidya Sagar <vidyas@nvidia.com>");
+MODULE_DESCRIPTION("NVIDIA PCIe host controller driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/controller/dwc/pcie-uniphier.c b/drivers/pci/controller/dwc/pcie-uniphier.c
new file mode 100644
index 0000000..3f30ee4
--- /dev/null
+++ b/drivers/pci/controller/dwc/pcie-uniphier.c
@@ -0,0 +1,476 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PCIe host controller driver for UniPhier SoCs
+ * Copyright 2018 Socionext Inc.
+ * Author: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
+ */
+
+#include <linux/bitops.h>
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/module.h>
+#include <linux/of_irq.h>
+#include <linux/pci.h>
+#include <linux/phy/phy.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+
+#include "pcie-designware.h"
+
+#define PCL_PINCTRL0			0x002c
+#define PCL_PERST_PLDN_REGEN		BIT(12)
+#define PCL_PERST_NOE_REGEN		BIT(11)
+#define PCL_PERST_OUT_REGEN		BIT(8)
+#define PCL_PERST_PLDN_REGVAL		BIT(4)
+#define PCL_PERST_NOE_REGVAL		BIT(3)
+#define PCL_PERST_OUT_REGVAL		BIT(0)
+
+#define PCL_PIPEMON			0x0044
+#define PCL_PCLK_ALIVE			BIT(15)
+
+#define PCL_APP_READY_CTRL		0x8008
+#define PCL_APP_LTSSM_ENABLE		BIT(0)
+
+#define PCL_APP_PM0			0x8078
+#define PCL_SYS_AUX_PWR_DET		BIT(8)
+
+#define PCL_RCV_INT			0x8108
+#define PCL_RCV_INT_ALL_ENABLE		GENMASK(20, 17)
+#define PCL_CFG_BW_MGT_STATUS		BIT(4)
+#define PCL_CFG_LINK_AUTO_BW_STATUS	BIT(3)
+#define PCL_CFG_AER_RC_ERR_MSI_STATUS	BIT(2)
+#define PCL_CFG_PME_MSI_STATUS		BIT(1)
+
+#define PCL_RCV_INTX			0x810c
+#define PCL_RCV_INTX_ALL_ENABLE		GENMASK(19, 16)
+#define PCL_RCV_INTX_ALL_MASK		GENMASK(11, 8)
+#define PCL_RCV_INTX_MASK_SHIFT		8
+#define PCL_RCV_INTX_ALL_STATUS		GENMASK(3, 0)
+#define PCL_RCV_INTX_STATUS_SHIFT	0
+
+#define PCL_STATUS_LINK			0x8140
+#define PCL_RDLH_LINK_UP		BIT(1)
+#define PCL_XMLH_LINK_UP		BIT(0)
+
+struct uniphier_pcie_priv {
+	void __iomem *base;
+	struct dw_pcie pci;
+	struct clk *clk;
+	struct reset_control *rst;
+	struct phy *phy;
+	struct irq_domain *legacy_irq_domain;
+};
+
+#define to_uniphier_pcie(x)	dev_get_drvdata((x)->dev)
+
+static void uniphier_pcie_ltssm_enable(struct uniphier_pcie_priv *priv,
+				       bool enable)
+{
+	u32 val;
+
+	val = readl(priv->base + PCL_APP_READY_CTRL);
+	if (enable)
+		val |= PCL_APP_LTSSM_ENABLE;
+	else
+		val &= ~PCL_APP_LTSSM_ENABLE;
+	writel(val, priv->base + PCL_APP_READY_CTRL);
+}
+
+static void uniphier_pcie_init_rc(struct uniphier_pcie_priv *priv)
+{
+	u32 val;
+
+	/* use auxiliary power detection */
+	val = readl(priv->base + PCL_APP_PM0);
+	val |= PCL_SYS_AUX_PWR_DET;
+	writel(val, priv->base + PCL_APP_PM0);
+
+	/* assert PERST# */
+	val = readl(priv->base + PCL_PINCTRL0);
+	val &= ~(PCL_PERST_NOE_REGVAL | PCL_PERST_OUT_REGVAL
+		 | PCL_PERST_PLDN_REGVAL);
+	val |= PCL_PERST_NOE_REGEN | PCL_PERST_OUT_REGEN
+		| PCL_PERST_PLDN_REGEN;
+	writel(val, priv->base + PCL_PINCTRL0);
+
+	uniphier_pcie_ltssm_enable(priv, false);
+
+	usleep_range(100000, 200000);
+
+	/* deassert PERST# */
+	val = readl(priv->base + PCL_PINCTRL0);
+	val |= PCL_PERST_OUT_REGVAL | PCL_PERST_OUT_REGEN;
+	writel(val, priv->base + PCL_PINCTRL0);
+}
+
+static int uniphier_pcie_wait_rc(struct uniphier_pcie_priv *priv)
+{
+	u32 status;
+	int ret;
+
+	/* wait PIPE clock */
+	ret = readl_poll_timeout(priv->base + PCL_PIPEMON, status,
+				 status & PCL_PCLK_ALIVE, 100000, 1000000);
+	if (ret) {
+		dev_err(priv->pci.dev,
+			"Failed to initialize controller in RC mode\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int uniphier_pcie_link_up(struct dw_pcie *pci)
+{
+	struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci);
+	u32 val, mask;
+
+	val = readl(priv->base + PCL_STATUS_LINK);
+	mask = PCL_RDLH_LINK_UP | PCL_XMLH_LINK_UP;
+
+	return (val & mask) == mask;
+}
+
+static int uniphier_pcie_establish_link(struct dw_pcie *pci)
+{
+	struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci);
+
+	if (dw_pcie_link_up(pci))
+		return 0;
+
+	uniphier_pcie_ltssm_enable(priv, true);
+
+	return dw_pcie_wait_for_link(pci);
+}
+
+static void uniphier_pcie_stop_link(struct dw_pcie *pci)
+{
+	struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci);
+
+	uniphier_pcie_ltssm_enable(priv, false);
+}
+
+static void uniphier_pcie_irq_enable(struct uniphier_pcie_priv *priv)
+{
+	writel(PCL_RCV_INT_ALL_ENABLE, priv->base + PCL_RCV_INT);
+	writel(PCL_RCV_INTX_ALL_ENABLE, priv->base + PCL_RCV_INTX);
+}
+
+static void uniphier_pcie_irq_disable(struct uniphier_pcie_priv *priv)
+{
+	writel(0, priv->base + PCL_RCV_INT);
+	writel(0, priv->base + PCL_RCV_INTX);
+}
+
+static void uniphier_pcie_irq_ack(struct irq_data *d)
+{
+	struct pcie_port *pp = irq_data_get_irq_chip_data(d);
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci);
+	u32 val;
+
+	val = readl(priv->base + PCL_RCV_INTX);
+	val &= ~PCL_RCV_INTX_ALL_STATUS;
+	val |= BIT(irqd_to_hwirq(d) + PCL_RCV_INTX_STATUS_SHIFT);
+	writel(val, priv->base + PCL_RCV_INTX);
+}
+
+static void uniphier_pcie_irq_mask(struct irq_data *d)
+{
+	struct pcie_port *pp = irq_data_get_irq_chip_data(d);
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci);
+	u32 val;
+
+	val = readl(priv->base + PCL_RCV_INTX);
+	val &= ~PCL_RCV_INTX_ALL_MASK;
+	val |= BIT(irqd_to_hwirq(d) + PCL_RCV_INTX_MASK_SHIFT);
+	writel(val, priv->base + PCL_RCV_INTX);
+}
+
+static void uniphier_pcie_irq_unmask(struct irq_data *d)
+{
+	struct pcie_port *pp = irq_data_get_irq_chip_data(d);
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci);
+	u32 val;
+
+	val = readl(priv->base + PCL_RCV_INTX);
+	val &= ~PCL_RCV_INTX_ALL_MASK;
+	val &= ~BIT(irqd_to_hwirq(d) + PCL_RCV_INTX_MASK_SHIFT);
+	writel(val, priv->base + PCL_RCV_INTX);
+}
+
+static struct irq_chip uniphier_pcie_irq_chip = {
+	.name = "PCI",
+	.irq_ack = uniphier_pcie_irq_ack,
+	.irq_mask = uniphier_pcie_irq_mask,
+	.irq_unmask = uniphier_pcie_irq_unmask,
+};
+
+static int uniphier_pcie_intx_map(struct irq_domain *domain, unsigned int irq,
+				  irq_hw_number_t hwirq)
+{
+	irq_set_chip_and_handler(irq, &uniphier_pcie_irq_chip,
+				 handle_level_irq);
+	irq_set_chip_data(irq, domain->host_data);
+
+	return 0;
+}
+
+static const struct irq_domain_ops uniphier_intx_domain_ops = {
+	.map = uniphier_pcie_intx_map,
+};
+
+static void uniphier_pcie_irq_handler(struct irq_desc *desc)
+{
+	struct pcie_port *pp = irq_desc_get_handler_data(desc);
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	unsigned long reg;
+	u32 val, bit, virq;
+
+	/* INT for debug */
+	val = readl(priv->base + PCL_RCV_INT);
+
+	if (val & PCL_CFG_BW_MGT_STATUS)
+		dev_dbg(pci->dev, "Link Bandwidth Management Event\n");
+	if (val & PCL_CFG_LINK_AUTO_BW_STATUS)
+		dev_dbg(pci->dev, "Link Autonomous Bandwidth Event\n");
+	if (val & PCL_CFG_AER_RC_ERR_MSI_STATUS)
+		dev_dbg(pci->dev, "Root Error\n");
+	if (val & PCL_CFG_PME_MSI_STATUS)
+		dev_dbg(pci->dev, "PME Interrupt\n");
+
+	writel(val, priv->base + PCL_RCV_INT);
+
+	/* INTx */
+	chained_irq_enter(chip, desc);
+
+	val = readl(priv->base + PCL_RCV_INTX);
+	reg = FIELD_GET(PCL_RCV_INTX_ALL_STATUS, val);
+
+	for_each_set_bit(bit, &reg, PCI_NUM_INTX) {
+		virq = irq_linear_revmap(priv->legacy_irq_domain, bit);
+		generic_handle_irq(virq);
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
+static int uniphier_pcie_config_legacy_irq(struct pcie_port *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci);
+	struct device_node *np = pci->dev->of_node;
+	struct device_node *np_intc;
+	int ret = 0;
+
+	np_intc = of_get_child_by_name(np, "legacy-interrupt-controller");
+	if (!np_intc) {
+		dev_err(pci->dev, "Failed to get legacy-interrupt-controller node\n");
+		return -EINVAL;
+	}
+
+	pp->irq = irq_of_parse_and_map(np_intc, 0);
+	if (!pp->irq) {
+		dev_err(pci->dev, "Failed to get an IRQ entry in legacy-interrupt-controller\n");
+		ret = -EINVAL;
+		goto out_put_node;
+	}
+
+	priv->legacy_irq_domain = irq_domain_add_linear(np_intc, PCI_NUM_INTX,
+						&uniphier_intx_domain_ops, pp);
+	if (!priv->legacy_irq_domain) {
+		dev_err(pci->dev, "Failed to get INTx domain\n");
+		ret = -ENODEV;
+		goto out_put_node;
+	}
+
+	irq_set_chained_handler_and_data(pp->irq, uniphier_pcie_irq_handler,
+					 pp);
+
+out_put_node:
+	of_node_put(np_intc);
+	return ret;
+}
+
+static int uniphier_pcie_host_init(struct pcie_port *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct uniphier_pcie_priv *priv = to_uniphier_pcie(pci);
+	int ret;
+
+	ret = uniphier_pcie_config_legacy_irq(pp);
+	if (ret)
+		return ret;
+
+	uniphier_pcie_irq_enable(priv);
+
+	dw_pcie_setup_rc(pp);
+	ret = uniphier_pcie_establish_link(pci);
+	if (ret)
+		return ret;
+
+	if (IS_ENABLED(CONFIG_PCI_MSI))
+		dw_pcie_msi_init(pp);
+
+	return 0;
+}
+
+static const struct dw_pcie_host_ops uniphier_pcie_host_ops = {
+	.host_init = uniphier_pcie_host_init,
+};
+
+static int uniphier_add_pcie_port(struct uniphier_pcie_priv *priv,
+				  struct platform_device *pdev)
+{
+	struct dw_pcie *pci = &priv->pci;
+	struct pcie_port *pp = &pci->pp;
+	struct device *dev = &pdev->dev;
+	int ret;
+
+	pp->ops = &uniphier_pcie_host_ops;
+
+	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+		pp->msi_irq = platform_get_irq_byname(pdev, "msi");
+		if (pp->msi_irq < 0)
+			return pp->msi_irq;
+	}
+
+	ret = dw_pcie_host_init(pp);
+	if (ret) {
+		dev_err(dev, "Failed to initialize host (%d)\n", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int uniphier_pcie_host_enable(struct uniphier_pcie_priv *priv)
+{
+	int ret;
+
+	ret = clk_prepare_enable(priv->clk);
+	if (ret)
+		return ret;
+
+	ret = reset_control_deassert(priv->rst);
+	if (ret)
+		goto out_clk_disable;
+
+	uniphier_pcie_init_rc(priv);
+
+	ret = phy_init(priv->phy);
+	if (ret)
+		goto out_rst_assert;
+
+	ret = uniphier_pcie_wait_rc(priv);
+	if (ret)
+		goto out_phy_exit;
+
+	return 0;
+
+out_phy_exit:
+	phy_exit(priv->phy);
+out_rst_assert:
+	reset_control_assert(priv->rst);
+out_clk_disable:
+	clk_disable_unprepare(priv->clk);
+
+	return ret;
+}
+
+static void uniphier_pcie_host_disable(struct uniphier_pcie_priv *priv)
+{
+	uniphier_pcie_irq_disable(priv);
+	phy_exit(priv->phy);
+	reset_control_assert(priv->rst);
+	clk_disable_unprepare(priv->clk);
+}
+
+static const struct dw_pcie_ops dw_pcie_ops = {
+	.start_link = uniphier_pcie_establish_link,
+	.stop_link = uniphier_pcie_stop_link,
+	.link_up = uniphier_pcie_link_up,
+};
+
+static int uniphier_pcie_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct uniphier_pcie_priv *priv;
+	struct resource *res;
+	int ret;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->pci.dev = dev;
+	priv->pci.ops = &dw_pcie_ops;
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi");
+	priv->pci.dbi_base = devm_pci_remap_cfg_resource(dev, res);
+	if (IS_ERR(priv->pci.dbi_base))
+		return PTR_ERR(priv->pci.dbi_base);
+
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "link");
+	priv->base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(priv->base))
+		return PTR_ERR(priv->base);
+
+	priv->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(priv->clk))
+		return PTR_ERR(priv->clk);
+
+	priv->rst = devm_reset_control_get_shared(dev, NULL);
+	if (IS_ERR(priv->rst))
+		return PTR_ERR(priv->rst);
+
+	priv->phy = devm_phy_optional_get(dev, "pcie-phy");
+	if (IS_ERR(priv->phy))
+		return PTR_ERR(priv->phy);
+
+	platform_set_drvdata(pdev, priv);
+
+	ret = uniphier_pcie_host_enable(priv);
+	if (ret)
+		return ret;
+
+	return uniphier_add_pcie_port(priv, pdev);
+}
+
+static int uniphier_pcie_remove(struct platform_device *pdev)
+{
+	struct uniphier_pcie_priv *priv = platform_get_drvdata(pdev);
+
+	uniphier_pcie_host_disable(priv);
+
+	return 0;
+}
+
+static const struct of_device_id uniphier_pcie_match[] = {
+	{ .compatible = "socionext,uniphier-pcie", },
+	{ /* sentinel */ },
+};
+MODULE_DEVICE_TABLE(of, uniphier_pcie_match);
+
+static struct platform_driver uniphier_pcie_driver = {
+	.probe  = uniphier_pcie_probe,
+	.remove = uniphier_pcie_remove,
+	.driver = {
+		.name = "uniphier-pcie",
+		.of_match_table = uniphier_pcie_match,
+	},
+};
+builtin_platform_driver(uniphier_pcie_driver);
+
+MODULE_AUTHOR("Kunihiko Hayashi <hayashi.kunihiko@socionext.com>");
+MODULE_DESCRIPTION("UniPhier PCIe host controller driver");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index 6b4555f..fc0fe4d 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -20,12 +20,16 @@
 #include <linux/of_pci.h>
 
 #include "../pci.h"
+#include "../pci-bridge-emul.h"
 
 /* PCIe core registers */
+#define PCIE_CORE_DEV_ID_REG					0x0
 #define PCIE_CORE_CMD_STATUS_REG				0x4
 #define     PCIE_CORE_CMD_IO_ACCESS_EN				BIT(0)
 #define     PCIE_CORE_CMD_MEM_ACCESS_EN				BIT(1)
 #define     PCIE_CORE_CMD_MEM_IO_REQ_EN				BIT(2)
+#define PCIE_CORE_DEV_REV_REG					0x8
+#define PCIE_CORE_PCIEXP_CAP					0xc0
 #define PCIE_CORE_DEV_CTRL_STATS_REG				0xc8
 #define     PCIE_CORE_DEV_CTRL_STATS_RELAX_ORDER_DISABLE	(0 << 4)
 #define     PCIE_CORE_DEV_CTRL_STATS_MAX_PAYLOAD_SZ_SHIFT	5
@@ -41,7 +45,10 @@
 #define     PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX_EN			BIT(6)
 #define     PCIE_CORE_ERR_CAPCTL_ECRC_CHCK			BIT(7)
 #define     PCIE_CORE_ERR_CAPCTL_ECRC_CHCK_RCV			BIT(8)
-
+#define     PCIE_CORE_INT_A_ASSERT_ENABLE			1
+#define     PCIE_CORE_INT_B_ASSERT_ENABLE			2
+#define     PCIE_CORE_INT_C_ASSERT_ENABLE			3
+#define     PCIE_CORE_INT_D_ASSERT_ENABLE			4
 /* PIO registers base address and register offsets */
 #define PIO_BASE_ADDR				0x4000
 #define PIO_CTRL				(PIO_BASE_ADDR + 0x0)
@@ -93,7 +100,9 @@
 #define     PCIE_CORE_CTRL2_STRICT_ORDER_ENABLE	BIT(5)
 #define     PCIE_CORE_CTRL2_OB_WIN_ENABLE	BIT(6)
 #define     PCIE_CORE_CTRL2_MSI_ENABLE		BIT(10)
+#define PCIE_MSG_LOG_REG			(CONTROL_BASE_ADDR + 0x30)
 #define PCIE_ISR0_REG				(CONTROL_BASE_ADDR + 0x40)
+#define PCIE_MSG_PM_PME_MASK			BIT(7)
 #define PCIE_ISR0_MASK_REG			(CONTROL_BASE_ADDR + 0x44)
 #define     PCIE_ISR0_MSI_INT_PENDING		BIT(24)
 #define     PCIE_ISR0_INTX_ASSERT(val)		BIT(16 + (val))
@@ -189,6 +198,7 @@
 	struct mutex msi_used_lock;
 	u16 msi_msg;
 	int root_bus_nr;
+	struct pci_bridge_emul bridge;
 };
 
 static inline void advk_writel(struct advk_pcie *pcie, u32 val, u64 reg)
@@ -298,7 +308,7 @@
 
 	advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_MASK_REG);
 
-	/* Unmask all MSI's */
+	/* Unmask all MSIs */
 	advk_writel(pcie, 0, PCIE_MSI_MASK_REG);
 
 	/* Enable summary interrupt for GIC SPI source */
@@ -390,6 +400,109 @@
 	return -ETIMEDOUT;
 }
 
+
+static pci_bridge_emul_read_status_t
+advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge,
+				    int reg, u32 *value)
+{
+	struct advk_pcie *pcie = bridge->data;
+
+
+	switch (reg) {
+	case PCI_EXP_SLTCTL:
+		*value = PCI_EXP_SLTSTA_PDS << 16;
+		return PCI_BRIDGE_EMUL_HANDLED;
+
+	case PCI_EXP_RTCTL: {
+		u32 val = advk_readl(pcie, PCIE_ISR0_MASK_REG);
+		*value = (val & PCIE_MSG_PM_PME_MASK) ? PCI_EXP_RTCTL_PMEIE : 0;
+		return PCI_BRIDGE_EMUL_HANDLED;
+	}
+
+	case PCI_EXP_RTSTA: {
+		u32 isr0 = advk_readl(pcie, PCIE_ISR0_REG);
+		u32 msglog = advk_readl(pcie, PCIE_MSG_LOG_REG);
+		*value = (isr0 & PCIE_MSG_PM_PME_MASK) << 16 | (msglog >> 16);
+		return PCI_BRIDGE_EMUL_HANDLED;
+	}
+
+	case PCI_CAP_LIST_ID:
+	case PCI_EXP_DEVCAP:
+	case PCI_EXP_DEVCTL:
+	case PCI_EXP_LNKCAP:
+	case PCI_EXP_LNKCTL:
+		*value = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg);
+		return PCI_BRIDGE_EMUL_HANDLED;
+	default:
+		return PCI_BRIDGE_EMUL_NOT_HANDLED;
+	}
+
+}
+
+static void
+advk_pci_bridge_emul_pcie_conf_write(struct pci_bridge_emul *bridge,
+				     int reg, u32 old, u32 new, u32 mask)
+{
+	struct advk_pcie *pcie = bridge->data;
+
+	switch (reg) {
+	case PCI_EXP_DEVCTL:
+	case PCI_EXP_LNKCTL:
+		advk_writel(pcie, new, PCIE_CORE_PCIEXP_CAP + reg);
+		break;
+
+	case PCI_EXP_RTCTL:
+		new = (new & PCI_EXP_RTCTL_PMEIE) << 3;
+		advk_writel(pcie, new, PCIE_ISR0_MASK_REG);
+		break;
+
+	case PCI_EXP_RTSTA:
+		new = (new & PCI_EXP_RTSTA_PME) >> 9;
+		advk_writel(pcie, new, PCIE_ISR0_REG);
+		break;
+
+	default:
+		break;
+	}
+}
+
+static struct pci_bridge_emul_ops advk_pci_bridge_emul_ops = {
+	.read_pcie = advk_pci_bridge_emul_pcie_conf_read,
+	.write_pcie = advk_pci_bridge_emul_pcie_conf_write,
+};
+
+/*
+ * Initialize the configuration space of the PCI-to-PCI bridge
+ * associated with the given PCIe interface.
+ */
+static void advk_sw_pci_bridge_init(struct advk_pcie *pcie)
+{
+	struct pci_bridge_emul *bridge = &pcie->bridge;
+
+	bridge->conf.vendor = advk_readl(pcie, PCIE_CORE_DEV_ID_REG) & 0xffff;
+	bridge->conf.device = advk_readl(pcie, PCIE_CORE_DEV_ID_REG) >> 16;
+	bridge->conf.class_revision =
+		advk_readl(pcie, PCIE_CORE_DEV_REV_REG) & 0xff;
+
+	/* Support 32 bits I/O addressing */
+	bridge->conf.iobase = PCI_IO_RANGE_TYPE_32;
+	bridge->conf.iolimit = PCI_IO_RANGE_TYPE_32;
+
+	/* Support 64 bits memory pref */
+	bridge->conf.pref_mem_base = PCI_PREF_RANGE_TYPE_64;
+	bridge->conf.pref_mem_limit = PCI_PREF_RANGE_TYPE_64;
+
+	/* Support interrupt A for MSI feature */
+	bridge->conf.intpin = PCIE_CORE_INT_A_ASSERT_ENABLE;
+
+	bridge->has_pcie = true;
+	bridge->data = pcie;
+	bridge->ops = &advk_pci_bridge_emul_ops;
+
+	pci_bridge_emul_init(bridge, 0);
+
+}
+
 static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus,
 				  int devfn)
 {
@@ -411,6 +524,10 @@
 		return PCIBIOS_DEVICE_NOT_FOUND;
 	}
 
+	if (bus->number == pcie->root_bus_nr)
+		return pci_bridge_emul_conf_read(&pcie->bridge, where,
+						 size, val);
+
 	/* Start PIO */
 	advk_writel(pcie, 0, PIO_START);
 	advk_writel(pcie, 1, PIO_ISR);
@@ -418,7 +535,7 @@
 	/* Program the control register */
 	reg = advk_readl(pcie, PIO_CTRL);
 	reg &= ~PIO_CTRL_TYPE_MASK;
-	if (bus->number ==  pcie->root_bus_nr)
+	if (bus->primary ==  pcie->root_bus_nr)
 		reg |= PCIE_CONFIG_RD_TYPE0;
 	else
 		reg |= PCIE_CONFIG_RD_TYPE1;
@@ -463,6 +580,10 @@
 	if (!advk_pcie_valid_device(pcie, bus, devfn))
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
+	if (bus->number == pcie->root_bus_nr)
+		return pci_bridge_emul_conf_write(&pcie->bridge, where,
+						  size, val);
+
 	if (where % size)
 		return PCIBIOS_SET_FAILED;
 
@@ -473,7 +594,7 @@
 	/* Program the control register */
 	reg = advk_readl(pcie, PIO_CTRL);
 	reg &= ~PIO_CTRL_TYPE_MASK;
-	if (bus->number == pcie->root_bus_nr)
+	if (bus->primary == pcie->root_bus_nr)
 		reg |= PCIE_CONFIG_WR_TYPE0;
 	else
 		reg |= PCIE_CONFIG_WR_TYPE1;
@@ -673,6 +794,7 @@
 	struct device_node *node = dev->of_node;
 	struct device_node *pcie_intc_node;
 	struct irq_chip *irq_chip;
+	int ret = 0;
 
 	pcie_intc_node =  of_get_next_child(node, NULL);
 	if (!pcie_intc_node) {
@@ -685,8 +807,8 @@
 	irq_chip->name = devm_kasprintf(dev, GFP_KERNEL, "%s-irq",
 					dev_name(dev));
 	if (!irq_chip->name) {
-		of_node_put(pcie_intc_node);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto out_put_node;
 	}
 
 	irq_chip->irq_mask = advk_pcie_irq_mask;
@@ -698,11 +820,13 @@
 				      &advk_pcie_irq_domain_ops, pcie);
 	if (!pcie->irq_domain) {
 		dev_err(dev, "Failed to get a INTx IRQ domain\n");
-		of_node_put(pcie_intc_node);
-		return -ENOMEM;
+		ret = -ENOMEM;
+		goto out_put_node;
 	}
 
-	return 0;
+out_put_node:
+	of_node_put(pcie_intc_node);
+	return ret;
 }
 
 static void advk_pcie_remove_irq_domain(struct advk_pcie *pcie)
@@ -875,6 +999,8 @@
 
 	advk_pcie_setup_hw(pcie);
 
+	advk_sw_pci_bridge_init(pcie);
+
 	ret = advk_pcie_init_irq_domain(pcie);
 	if (ret) {
 		dev_err(dev, "Failed to initialize irq\n");
diff --git a/drivers/pci/controller/pci-host-common.c b/drivers/pci/controller/pci-host-common.c
index d8f1045..c8cb9c5 100644
--- a/drivers/pci/controller/pci-host-common.c
+++ b/drivers/pci/controller/pci-host-common.c
@@ -43,9 +43,8 @@
 		goto err_out;
 	}
 
-	err = devm_add_action(dev, gen_pci_unmap_cfg, cfg);
+	err = devm_add_action_or_reset(dev, gen_pci_unmap_cfg, cfg);
 	if (err) {
-		gen_pci_unmap_cfg(cfg);
 		goto err_out;
 	}
 	return cfg;
@@ -58,9 +57,7 @@
 int pci_host_common_probe(struct platform_device *pdev,
 			  struct pci_ecam_ops *ops)
 {
-	const char *type;
 	struct device *dev = &pdev->dev;
-	struct device_node *np = dev->of_node;
 	struct pci_host_bridge *bridge;
 	struct pci_config_window *cfg;
 	struct list_head resources;
@@ -70,12 +67,6 @@
 	if (!bridge)
 		return -ENOMEM;
 
-	type = of_get_property(np, "device_type", NULL);
-	if (!type || strcmp(type, "pci")) {
-		dev_err(dev, "invalid \"device_type\" %s\n", type);
-		return -EINVAL;
-	}
-
 	of_pci_check_probe_only();
 
 	/* Parse and map our Configuration Space windows */
diff --git a/drivers/pci/controller/pci-host-generic.c b/drivers/pci/controller/pci-host-generic.c
index dea3ec7..75a2fb9 100644
--- a/drivers/pci/controller/pci-host-generic.c
+++ b/drivers/pci/controller/pci-host-generic.c
@@ -1,6 +1,6 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Simple, generic PCI host controller driver targetting firmware-initialised
+ * Simple, generic PCI host controller driver targeting firmware-initialised
  * systems and virtual machines (e.g. the PCI emulation provided by kvmtool).
  *
  * Copyright (C) 2014 ARM Limited
diff --git a/drivers/pci/controller/pci-hyperv-intf.c b/drivers/pci/controller/pci-hyperv-intf.c
new file mode 100644
index 0000000..cc96be4
--- /dev/null
+++ b/drivers/pci/controller/pci-hyperv-intf.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) Microsoft Corporation.
+ *
+ * Author:
+ *   Haiyang Zhang <haiyangz@microsoft.com>
+ *
+ * This small module is a helper driver allows other drivers to
+ * have a common interface with the Hyper-V PCI frontend driver.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/hyperv.h>
+
+struct hyperv_pci_block_ops hvpci_block_ops;
+EXPORT_SYMBOL_GPL(hvpci_block_ops);
+
+int hyperv_read_cfg_blk(struct pci_dev *dev, void *buf, unsigned int buf_len,
+			unsigned int block_id, unsigned int *bytes_returned)
+{
+	if (!hvpci_block_ops.read_block)
+		return -EOPNOTSUPP;
+
+	return hvpci_block_ops.read_block(dev, buf, buf_len, block_id,
+					  bytes_returned);
+}
+EXPORT_SYMBOL_GPL(hyperv_read_cfg_blk);
+
+int hyperv_write_cfg_blk(struct pci_dev *dev, void *buf, unsigned int len,
+			 unsigned int block_id)
+{
+	if (!hvpci_block_ops.write_block)
+		return -EOPNOTSUPP;
+
+	return hvpci_block_ops.write_block(dev, buf, len, block_id);
+}
+EXPORT_SYMBOL_GPL(hyperv_write_cfg_blk);
+
+int hyperv_reg_block_invalidate(struct pci_dev *dev, void *context,
+				void (*block_invalidate)(void *context,
+							 u64 block_mask))
+{
+	if (!hvpci_block_ops.reg_blk_invalidate)
+		return -EOPNOTSUPP;
+
+	return hvpci_block_ops.reg_blk_invalidate(dev, context,
+						  block_invalidate);
+}
+EXPORT_SYMBOL_GPL(hyperv_reg_block_invalidate);
+
+static void __exit exit_hv_pci_intf(void)
+{
+}
+
+static int __init init_hv_pci_intf(void)
+{
+	return 0;
+}
+
+module_init(init_hv_pci_intf);
+module_exit(exit_hv_pci_intf);
+
+MODULE_DESCRIPTION("Hyper-V PCI Interface");
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 9ba4d12..f1f3002 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -365,6 +365,39 @@
 	struct tran_int_desc int_desc;
 } __packed;
 
+/*
+ * Note: the VM must pass a valid block id, wslot and bytes_requested.
+ */
+struct pci_read_block {
+	struct pci_message message_type;
+	u32 block_id;
+	union win_slot_encoding wslot;
+	u32 bytes_requested;
+} __packed;
+
+struct pci_read_block_response {
+	struct vmpacket_descriptor hdr;
+	u32 status;
+	u8 bytes[HV_CONFIG_BLOCK_SIZE_MAX];
+} __packed;
+
+/*
+ * Note: the VM must pass a valid block id, wslot and byte_count.
+ */
+struct pci_write_block {
+	struct pci_message message_type;
+	u32 block_id;
+	union win_slot_encoding wslot;
+	u32 byte_count;
+	u8 bytes[HV_CONFIG_BLOCK_SIZE_MAX];
+} __packed;
+
+struct pci_dev_inval_block {
+	struct pci_incoming_message incoming;
+	union win_slot_encoding wslot;
+	u64 block_mask;
+} __packed;
+
 struct pci_dev_incoming {
 	struct pci_incoming_message incoming;
 	union win_slot_encoding wslot;
@@ -391,14 +424,6 @@
 	u32	data;
 };
 
-#define HV_VP_SET_BANK_COUNT_MAX	5 /* current implementation limit */
-
-struct hv_vp_set {
-	u64	format;			/* 0 (HvGenericSetSparse4k) */
-	u64	valid_banks;
-	u64	masks[HV_VP_SET_BANK_COUNT_MAX];
-};
-
 /*
  * flags for hv_device_interrupt_target.flags
  */
@@ -410,7 +435,7 @@
 	u32	flags;
 	union {
 		u64		 vp_mask;
-		struct hv_vp_set vp_set;
+		struct hv_vpset vp_set;
 	};
 };
 
@@ -420,7 +445,7 @@
 	struct hv_interrupt_entry int_entry;
 	u64	reserved2;
 	struct hv_device_interrupt_target int_target;
-} __packed;
+} __packed __aligned(8);
 
 /*
  * Driver specific state.
@@ -460,12 +485,16 @@
 	struct msi_controller msi_chip;
 	struct irq_domain *irq_domain;
 
-	/* hypercall arg, must not cross page boundary */
-	struct retarget_msi_interrupt retarget_msi_interrupt_params;
-
 	spinlock_t retarget_msi_interrupt_lock;
 
 	struct workqueue_struct *wq;
+
+	/* hypercall arg, must not cross page boundary */
+	struct retarget_msi_interrupt retarget_msi_interrupt_params;
+
+	/*
+	 * Don't put anything here: retarget_msi_interrupt_params must be last
+	 */
 };
 
 /*
@@ -503,6 +532,9 @@
 	struct hv_pcibus_device *hbus;
 	struct work_struct wrk;
 
+	void (*block_invalidate)(void *context, u64 block_mask);
+	void *invalidate_context;
+
 	/*
 	 * What would be observed if one wrote 0xFFFFFFFF to a BAR and then
 	 * read it back, for each of the BAR offsets within config space.
@@ -821,6 +853,253 @@
 	.write = hv_pcifront_write_config,
 };
 
+/*
+ * Paravirtual backchannel
+ *
+ * Hyper-V SR-IOV provides a backchannel mechanism in software for
+ * communication between a VF driver and a PF driver.  These
+ * "configuration blocks" are similar in concept to PCI configuration space,
+ * but instead of doing reads and writes in 32-bit chunks through a very slow
+ * path, packets of up to 128 bytes can be sent or received asynchronously.
+ *
+ * Nearly every SR-IOV device contains just such a communications channel in
+ * hardware, so using this one in software is usually optional.  Using the
+ * software channel, however, allows driver implementers to leverage software
+ * tools that fuzz the communications channel looking for vulnerabilities.
+ *
+ * The usage model for these packets puts the responsibility for reading or
+ * writing on the VF driver.  The VF driver sends a read or a write packet,
+ * indicating which "block" is being referred to by number.
+ *
+ * If the PF driver wishes to initiate communication, it can "invalidate" one or
+ * more of the first 64 blocks.  This invalidation is delivered via a callback
+ * supplied by the VF driver by this driver.
+ *
+ * No protocol is implied, except that supplied by the PF and VF drivers.
+ */
+
+struct hv_read_config_compl {
+	struct hv_pci_compl comp_pkt;
+	void *buf;
+	unsigned int len;
+	unsigned int bytes_returned;
+};
+
+/**
+ * hv_pci_read_config_compl() - Invoked when a response packet
+ * for a read config block operation arrives.
+ * @context:		Identifies the read config operation
+ * @resp:		The response packet itself
+ * @resp_packet_size:	Size in bytes of the response packet
+ */
+static void hv_pci_read_config_compl(void *context, struct pci_response *resp,
+				     int resp_packet_size)
+{
+	struct hv_read_config_compl *comp = context;
+	struct pci_read_block_response *read_resp =
+		(struct pci_read_block_response *)resp;
+	unsigned int data_len, hdr_len;
+
+	hdr_len = offsetof(struct pci_read_block_response, bytes);
+	if (resp_packet_size < hdr_len) {
+		comp->comp_pkt.completion_status = -1;
+		goto out;
+	}
+
+	data_len = resp_packet_size - hdr_len;
+	if (data_len > 0 && read_resp->status == 0) {
+		comp->bytes_returned = min(comp->len, data_len);
+		memcpy(comp->buf, read_resp->bytes, comp->bytes_returned);
+	} else {
+		comp->bytes_returned = 0;
+	}
+
+	comp->comp_pkt.completion_status = read_resp->status;
+out:
+	complete(&comp->comp_pkt.host_event);
+}
+
+/**
+ * hv_read_config_block() - Sends a read config block request to
+ * the back-end driver running in the Hyper-V parent partition.
+ * @pdev:		The PCI driver's representation for this device.
+ * @buf:		Buffer into which the config block will be copied.
+ * @len:		Size in bytes of buf.
+ * @block_id:		Identifies the config block which has been requested.
+ * @bytes_returned:	Size which came back from the back-end driver.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int hv_read_config_block(struct pci_dev *pdev, void *buf, unsigned int len,
+			 unsigned int block_id, unsigned int *bytes_returned)
+{
+	struct hv_pcibus_device *hbus =
+		container_of(pdev->bus->sysdata, struct hv_pcibus_device,
+			     sysdata);
+	struct {
+		struct pci_packet pkt;
+		char buf[sizeof(struct pci_read_block)];
+	} pkt;
+	struct hv_read_config_compl comp_pkt;
+	struct pci_read_block *read_blk;
+	int ret;
+
+	if (len == 0 || len > HV_CONFIG_BLOCK_SIZE_MAX)
+		return -EINVAL;
+
+	init_completion(&comp_pkt.comp_pkt.host_event);
+	comp_pkt.buf = buf;
+	comp_pkt.len = len;
+
+	memset(&pkt, 0, sizeof(pkt));
+	pkt.pkt.completion_func = hv_pci_read_config_compl;
+	pkt.pkt.compl_ctxt = &comp_pkt;
+	read_blk = (struct pci_read_block *)&pkt.pkt.message;
+	read_blk->message_type.type = PCI_READ_BLOCK;
+	read_blk->wslot.slot = devfn_to_wslot(pdev->devfn);
+	read_blk->block_id = block_id;
+	read_blk->bytes_requested = len;
+
+	ret = vmbus_sendpacket(hbus->hdev->channel, read_blk,
+			       sizeof(*read_blk), (unsigned long)&pkt.pkt,
+			       VM_PKT_DATA_INBAND,
+			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+	if (ret)
+		return ret;
+
+	ret = wait_for_response(hbus->hdev, &comp_pkt.comp_pkt.host_event);
+	if (ret)
+		return ret;
+
+	if (comp_pkt.comp_pkt.completion_status != 0 ||
+	    comp_pkt.bytes_returned == 0) {
+		dev_err(&hbus->hdev->device,
+			"Read Config Block failed: 0x%x, bytes_returned=%d\n",
+			comp_pkt.comp_pkt.completion_status,
+			comp_pkt.bytes_returned);
+		return -EIO;
+	}
+
+	*bytes_returned = comp_pkt.bytes_returned;
+	return 0;
+}
+
+/**
+ * hv_pci_write_config_compl() - Invoked when a response packet for a write
+ * config block operation arrives.
+ * @context:		Identifies the write config operation
+ * @resp:		The response packet itself
+ * @resp_packet_size:	Size in bytes of the response packet
+ */
+static void hv_pci_write_config_compl(void *context, struct pci_response *resp,
+				      int resp_packet_size)
+{
+	struct hv_pci_compl *comp_pkt = context;
+
+	comp_pkt->completion_status = resp->status;
+	complete(&comp_pkt->host_event);
+}
+
+/**
+ * hv_write_config_block() - Sends a write config block request to the
+ * back-end driver running in the Hyper-V parent partition.
+ * @pdev:		The PCI driver's representation for this device.
+ * @buf:		Buffer from which the config block will	be copied.
+ * @len:		Size in bytes of buf.
+ * @block_id:		Identifies the config block which is being written.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int hv_write_config_block(struct pci_dev *pdev, void *buf, unsigned int len,
+			  unsigned int block_id)
+{
+	struct hv_pcibus_device *hbus =
+		container_of(pdev->bus->sysdata, struct hv_pcibus_device,
+			     sysdata);
+	struct {
+		struct pci_packet pkt;
+		char buf[sizeof(struct pci_write_block)];
+		u32 reserved;
+	} pkt;
+	struct hv_pci_compl comp_pkt;
+	struct pci_write_block *write_blk;
+	u32 pkt_size;
+	int ret;
+
+	if (len == 0 || len > HV_CONFIG_BLOCK_SIZE_MAX)
+		return -EINVAL;
+
+	init_completion(&comp_pkt.host_event);
+
+	memset(&pkt, 0, sizeof(pkt));
+	pkt.pkt.completion_func = hv_pci_write_config_compl;
+	pkt.pkt.compl_ctxt = &comp_pkt;
+	write_blk = (struct pci_write_block *)&pkt.pkt.message;
+	write_blk->message_type.type = PCI_WRITE_BLOCK;
+	write_blk->wslot.slot = devfn_to_wslot(pdev->devfn);
+	write_blk->block_id = block_id;
+	write_blk->byte_count = len;
+	memcpy(write_blk->bytes, buf, len);
+	pkt_size = offsetof(struct pci_write_block, bytes) + len;
+	/*
+	 * This quirk is required on some hosts shipped around 2018, because
+	 * these hosts don't check the pkt_size correctly (new hosts have been
+	 * fixed since early 2019). The quirk is also safe on very old hosts
+	 * and new hosts, because, on them, what really matters is the length
+	 * specified in write_blk->byte_count.
+	 */
+	pkt_size += sizeof(pkt.reserved);
+
+	ret = vmbus_sendpacket(hbus->hdev->channel, write_blk, pkt_size,
+			       (unsigned long)&pkt.pkt, VM_PKT_DATA_INBAND,
+			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+	if (ret)
+		return ret;
+
+	ret = wait_for_response(hbus->hdev, &comp_pkt.host_event);
+	if (ret)
+		return ret;
+
+	if (comp_pkt.completion_status != 0) {
+		dev_err(&hbus->hdev->device,
+			"Write Config Block failed: 0x%x\n",
+			comp_pkt.completion_status);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/**
+ * hv_register_block_invalidate() - Invoked when a config block invalidation
+ * arrives from the back-end driver.
+ * @pdev:		The PCI driver's representation for this device.
+ * @context:		Identifies the device.
+ * @block_invalidate:	Identifies all of the blocks being invalidated.
+ *
+ * Return: 0 on success, -errno on failure
+ */
+int hv_register_block_invalidate(struct pci_dev *pdev, void *context,
+				 void (*block_invalidate)(void *context,
+							  u64 block_mask))
+{
+	struct hv_pcibus_device *hbus =
+		container_of(pdev->bus->sysdata, struct hv_pcibus_device,
+			     sysdata);
+	struct hv_pci_dev *hpdev;
+
+	hpdev = get_pcichild_wslot(hbus, devfn_to_wslot(pdev->devfn));
+	if (!hpdev)
+		return -ENODEV;
+
+	hpdev->block_invalidate = block_invalidate;
+	hpdev->invalidate_context = context;
+
+	put_pcichild(hpdev);
+	return 0;
+
+}
+
 /* Interrupt management hooks */
 static void hv_int_desc_free(struct hv_pci_dev *hpdev,
 			     struct tran_int_desc *int_desc)
@@ -910,12 +1189,12 @@
 	struct retarget_msi_interrupt *params;
 	struct hv_pcibus_device *hbus;
 	struct cpumask *dest;
+	cpumask_var_t tmp;
 	struct pci_bus *pbus;
 	struct pci_dev *pdev;
 	unsigned long flags;
 	u32 var_size = 0;
-	int cpu_vmbus;
-	int cpu;
+	int cpu, nr_bank;
 	u64 res;
 
 	dest = irq_data_get_effective_affinity_mask(data);
@@ -955,28 +1234,27 @@
 		 */
 		params->int_target.flags |=
 			HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET;
-		params->int_target.vp_set.valid_banks =
-			(1ull << HV_VP_SET_BANK_COUNT_MAX) - 1;
+
+		if (!alloc_cpumask_var(&tmp, GFP_ATOMIC)) {
+			res = 1;
+			goto exit_unlock;
+		}
+
+		cpumask_and(tmp, dest, cpu_online_mask);
+		nr_bank = cpumask_to_vpset(&params->int_target.vp_set, tmp);
+		free_cpumask_var(tmp);
+
+		if (nr_bank <= 0) {
+			res = 1;
+			goto exit_unlock;
+		}
 
 		/*
 		 * var-sized hypercall, var-size starts after vp_mask (thus
-		 * vp_set.format does not count, but vp_set.valid_banks does).
+		 * vp_set.format does not count, but vp_set.valid_bank_mask
+		 * does).
 		 */
-		var_size = 1 + HV_VP_SET_BANK_COUNT_MAX;
-
-		for_each_cpu_and(cpu, dest, cpu_online_mask) {
-			cpu_vmbus = hv_cpu_number_to_vp_number(cpu);
-
-			if (cpu_vmbus >= HV_VP_SET_BANK_COUNT_MAX * 64) {
-				dev_err(&hbus->hdev->device,
-					"too high CPU %d", cpu_vmbus);
-				res = 1;
-				goto exit_unlock;
-			}
-
-			params->int_target.vp_set.masks[cpu_vmbus / 64] |=
-				(1ULL << (cpu_vmbus & 63));
-		}
+		var_size = 1 + nr_bank;
 	} else {
 		for_each_cpu_and(cpu, dest, cpu_online_mask) {
 			params->int_target.vp_mask |=
@@ -1491,6 +1769,21 @@
 	}
 }
 
+/*
+ * Remove entries in sysfs pci slot directory.
+ */
+static void hv_pci_remove_slots(struct hv_pcibus_device *hbus)
+{
+	struct hv_pci_dev *hpdev;
+
+	list_for_each_entry(hpdev, &hbus->children, list_entry) {
+		if (!hpdev->pci_slot)
+			continue;
+		pci_destroy_slot(hpdev->pci_slot);
+		hpdev->pci_slot = NULL;
+	}
+}
+
 /**
  * create_root_hv_pci_bus() - Expose a new root PCI bus
  * @hbus:	Root PCI bus, as understood by this driver
@@ -1766,6 +2059,10 @@
 		hpdev = list_first_entry(&removed, struct hv_pci_dev,
 					 list_entry);
 		list_del(&hpdev->list_entry);
+
+		if (hpdev->pci_slot)
+			pci_destroy_slot(hpdev->pci_slot);
+
 		put_pcichild(hpdev);
 	}
 
@@ -1861,6 +2158,7 @@
 static void hv_eject_device_work(struct work_struct *work)
 {
 	struct pci_eject_response *ejct_pkt;
+	struct hv_pcibus_device *hbus;
 	struct hv_pci_dev *hpdev;
 	struct pci_dev *pdev;
 	unsigned long flags;
@@ -1871,6 +2169,7 @@
 	} ctxt;
 
 	hpdev = container_of(work, struct hv_pci_dev, wrk);
+	hbus = hpdev->hbus;
 
 	WARN_ON(hpdev->state != hv_pcichild_ejecting);
 
@@ -1881,8 +2180,7 @@
 	 * because hbus->pci_bus may not exist yet.
 	 */
 	wslot = wslot_to_devfn(hpdev->desc.win_slot.slot);
-	pdev = pci_get_domain_bus_and_slot(hpdev->hbus->sysdata.domain, 0,
-					   wslot);
+	pdev = pci_get_domain_bus_and_slot(hbus->sysdata.domain, 0, wslot);
 	if (pdev) {
 		pci_lock_rescan_remove();
 		pci_stop_and_remove_bus_device(pdev);
@@ -1890,9 +2188,9 @@
 		pci_unlock_rescan_remove();
 	}
 
-	spin_lock_irqsave(&hpdev->hbus->device_list_lock, flags);
+	spin_lock_irqsave(&hbus->device_list_lock, flags);
 	list_del(&hpdev->list_entry);
-	spin_unlock_irqrestore(&hpdev->hbus->device_list_lock, flags);
+	spin_unlock_irqrestore(&hbus->device_list_lock, flags);
 
 	if (hpdev->pci_slot)
 		pci_destroy_slot(hpdev->pci_slot);
@@ -1901,13 +2199,18 @@
 	ejct_pkt = (struct pci_eject_response *)&ctxt.pkt.message;
 	ejct_pkt->message_type.type = PCI_EJECTION_COMPLETE;
 	ejct_pkt->wslot.slot = hpdev->desc.win_slot.slot;
-	vmbus_sendpacket(hpdev->hbus->hdev->channel, ejct_pkt,
+	vmbus_sendpacket(hbus->hdev->channel, ejct_pkt,
 			 sizeof(*ejct_pkt), (unsigned long)&ctxt.pkt,
 			 VM_PKT_DATA_INBAND, 0);
 
+	/* For the get_pcichild() in hv_pci_eject_device() */
+	put_pcichild(hpdev);
+	/* For the two refs got in new_pcichild_device() */
 	put_pcichild(hpdev);
 	put_pcichild(hpdev);
-	put_hvpcibus(hpdev->hbus);
+	/* hpdev has been freed. Do not use it any more. */
+
+	put_hvpcibus(hbus);
 }
 
 /**
@@ -1948,6 +2251,7 @@
 	struct pci_response *response;
 	struct pci_incoming_message *new_message;
 	struct pci_bus_relations *bus_rel;
+	struct pci_dev_inval_block *inval;
 	struct pci_dev_incoming *dev_message;
 	struct hv_pci_dev *hpdev;
 
@@ -2025,6 +2329,21 @@
 				}
 				break;
 
+			case PCI_INVALIDATE_BLOCK:
+
+				inval = (struct pci_dev_inval_block *)buffer;
+				hpdev = get_pcichild_wslot(hbus,
+							   inval->wslot.slot);
+				if (hpdev) {
+					if (hpdev->block_invalidate) {
+						hpdev->block_invalidate(
+						    hpdev->invalidate_context,
+						    inval->block_mask);
+					}
+					put_pcichild(hpdev);
+				}
+				break;
+
 			default:
 				dev_warn(&hbus->hdev->device,
 					"Unimplemented protocol message %x\n",
@@ -2490,6 +2809,48 @@
 		complete(&hbus->remove_event);
 }
 
+#define HVPCI_DOM_MAP_SIZE (64 * 1024)
+static DECLARE_BITMAP(hvpci_dom_map, HVPCI_DOM_MAP_SIZE);
+
+/*
+ * PCI domain number 0 is used by emulated devices on Gen1 VMs, so define 0
+ * as invalid for passthrough PCI devices of this driver.
+ */
+#define HVPCI_DOM_INVALID 0
+
+/**
+ * hv_get_dom_num() - Get a valid PCI domain number
+ * Check if the PCI domain number is in use, and return another number if
+ * it is in use.
+ *
+ * @dom: Requested domain number
+ *
+ * return: domain number on success, HVPCI_DOM_INVALID on failure
+ */
+static u16 hv_get_dom_num(u16 dom)
+{
+	unsigned int i;
+
+	if (test_and_set_bit(dom, hvpci_dom_map) == 0)
+		return dom;
+
+	for_each_clear_bit(i, hvpci_dom_map, HVPCI_DOM_MAP_SIZE) {
+		if (test_and_set_bit(i, hvpci_dom_map) == 0)
+			return i;
+	}
+
+	return HVPCI_DOM_INVALID;
+}
+
+/**
+ * hv_put_dom_num() - Mark the PCI domain number as free
+ * @dom: Domain number to be freed
+ */
+static void hv_put_dom_num(u16 dom)
+{
+	clear_bit(dom, hvpci_dom_map);
+}
+
 /**
  * hv_pci_probe() - New VMBus channel probe, for a root PCI bus
  * @hdev:	VMBus's tracking struct for this root PCI bus
@@ -2501,6 +2862,8 @@
 			const struct hv_vmbus_device_id *dev_id)
 {
 	struct hv_pcibus_device *hbus;
+	u16 dom_req, dom;
+	char *name;
 	int ret;
 
 	/*
@@ -2515,19 +2878,34 @@
 	hbus->state = hv_pcibus_init;
 
 	/*
-	 * The PCI bus "domain" is what is called "segment" in ACPI and
-	 * other specs.  Pull it from the instance ID, to get something
-	 * unique.  Bytes 8 and 9 are what is used in Windows guests, so
-	 * do the same thing for consistency.  Note that, since this code
-	 * only runs in a Hyper-V VM, Hyper-V can (and does) guarantee
-	 * that (1) the only domain in use for something that looks like
-	 * a physical PCI bus (which is actually emulated by the
-	 * hypervisor) is domain 0 and (2) there will be no overlap
-	 * between domains derived from these instance IDs in the same
-	 * VM.
+	 * The PCI bus "domain" is what is called "segment" in ACPI and other
+	 * specs. Pull it from the instance ID, to get something usually
+	 * unique. In rare cases of collision, we will find out another number
+	 * not in use.
+	 *
+	 * Note that, since this code only runs in a Hyper-V VM, Hyper-V
+	 * together with this guest driver can guarantee that (1) The only
+	 * domain used by Gen1 VMs for something that looks like a physical
+	 * PCI bus (which is actually emulated by the hypervisor) is domain 0.
+	 * (2) There will be no overlap between domains (after fixing possible
+	 * collisions) in the same VM.
 	 */
-	hbus->sysdata.domain = hdev->dev_instance.b[9] |
-			       hdev->dev_instance.b[8] << 8;
+	dom_req = hdev->dev_instance.b[5] << 8 | hdev->dev_instance.b[4];
+	dom = hv_get_dom_num(dom_req);
+
+	if (dom == HVPCI_DOM_INVALID) {
+		dev_err(&hdev->device,
+			"Unable to use dom# 0x%hx or other numbers", dom_req);
+		ret = -EINVAL;
+		goto free_bus;
+	}
+
+	if (dom != dom_req)
+		dev_info(&hdev->device,
+			 "PCI dom# 0x%hx has collision, using 0x%hx",
+			 dom_req, dom);
+
+	hbus->sysdata.domain = dom;
 
 	hbus->hdev = hdev;
 	refcount_set(&hbus->remove_lock, 1);
@@ -2542,7 +2920,7 @@
 					   hbus->sysdata.domain);
 	if (!hbus->wq) {
 		ret = -ENOMEM;
-		goto free_bus;
+		goto free_dom;
 	}
 
 	ret = vmbus_open(hdev->channel, pci_ring_size, pci_ring_size, NULL, 0,
@@ -2569,7 +2947,14 @@
 		goto free_config;
 	}
 
-	hbus->sysdata.fwnode = irq_domain_alloc_fwnode(hbus);
+	name = kasprintf(GFP_KERNEL, "%pUL", &hdev->dev_instance);
+	if (!name) {
+		ret = -ENOMEM;
+		goto unmap;
+	}
+
+	hbus->sysdata.fwnode = irq_domain_alloc_named_fwnode(name);
+	kfree(name);
 	if (!hbus->sysdata.fwnode) {
 		ret = -ENOMEM;
 		goto unmap;
@@ -2619,6 +3004,8 @@
 	vmbus_close(hdev->channel);
 destroy_wq:
 	destroy_workqueue(hbus->wq);
+free_dom:
+	hv_put_dom_num(hbus->sysdata.domain);
 free_bus:
 	free_page((unsigned long)hbus);
 	return ret;
@@ -2681,6 +3068,7 @@
 		/* Remove the bus from PCI's point of view. */
 		pci_lock_rescan_remove();
 		pci_stop_root_bus(hbus->pci_bus);
+		hv_pci_remove_slots(hbus);
 		pci_remove_root_bus(hbus->pci_bus);
 		pci_unlock_rescan_remove();
 		hbus->state = hv_pcibus_removed;
@@ -2699,6 +3087,9 @@
 	put_hvpcibus(hbus);
 	wait_for_completion(&hbus->remove_event);
 	destroy_workqueue(hbus->wq);
+
+	hv_put_dom_num(hbus->sysdata.domain);
+
 	free_page((unsigned long)hbus);
 	return 0;
 }
@@ -2722,10 +3113,22 @@
 static void __exit exit_hv_pci_drv(void)
 {
 	vmbus_driver_unregister(&hv_pci_drv);
+
+	hvpci_block_ops.read_block = NULL;
+	hvpci_block_ops.write_block = NULL;
+	hvpci_block_ops.reg_blk_invalidate = NULL;
 }
 
 static int __init init_hv_pci_drv(void)
 {
+	/* Set the invalid domain number's bit, so it will not be used */
+	set_bit(HVPCI_DOM_INVALID, hvpci_dom_map);
+
+	/* Initialize PCI block r/w interface */
+	hvpci_block_ops.read_block = hv_read_config_block;
+	hvpci_block_ops.write_block = hv_write_config_block;
+	hvpci_block_ops.reg_blk_invalidate = hv_register_block_invalidate;
+
 	return vmbus_driver_register(&hv_pci_drv);
 }
 
diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c
index a41d79b..d3a0419 100644
--- a/drivers/pci/controller/pci-mvebu.c
+++ b/drivers/pci/controller/pci-mvebu.c
@@ -22,6 +22,7 @@
 #include <linux/of_platform.h>
 
 #include "../pci.h"
+#include "../pci-bridge-emul.h"
 
 /*
  * PCIe unit register offsets.
@@ -63,61 +64,6 @@
 #define PCIE_DEBUG_CTRL         0x1a60
 #define  PCIE_DEBUG_SOFT_RESET		BIT(20)
 
-enum {
-	PCISWCAP = PCI_BRIDGE_CONTROL + 2,
-	PCISWCAP_EXP_LIST_ID	= PCISWCAP + PCI_CAP_LIST_ID,
-	PCISWCAP_EXP_DEVCAP	= PCISWCAP + PCI_EXP_DEVCAP,
-	PCISWCAP_EXP_DEVCTL	= PCISWCAP + PCI_EXP_DEVCTL,
-	PCISWCAP_EXP_LNKCAP	= PCISWCAP + PCI_EXP_LNKCAP,
-	PCISWCAP_EXP_LNKCTL	= PCISWCAP + PCI_EXP_LNKCTL,
-	PCISWCAP_EXP_SLTCAP	= PCISWCAP + PCI_EXP_SLTCAP,
-	PCISWCAP_EXP_SLTCTL	= PCISWCAP + PCI_EXP_SLTCTL,
-	PCISWCAP_EXP_RTCTL	= PCISWCAP + PCI_EXP_RTCTL,
-	PCISWCAP_EXP_RTSTA	= PCISWCAP + PCI_EXP_RTSTA,
-	PCISWCAP_EXP_DEVCAP2	= PCISWCAP + PCI_EXP_DEVCAP2,
-	PCISWCAP_EXP_DEVCTL2	= PCISWCAP + PCI_EXP_DEVCTL2,
-	PCISWCAP_EXP_LNKCAP2	= PCISWCAP + PCI_EXP_LNKCAP2,
-	PCISWCAP_EXP_LNKCTL2	= PCISWCAP + PCI_EXP_LNKCTL2,
-	PCISWCAP_EXP_SLTCAP2	= PCISWCAP + PCI_EXP_SLTCAP2,
-	PCISWCAP_EXP_SLTCTL2	= PCISWCAP + PCI_EXP_SLTCTL2,
-};
-
-/* PCI configuration space of a PCI-to-PCI bridge */
-struct mvebu_sw_pci_bridge {
-	u16 vendor;
-	u16 device;
-	u16 command;
-	u16 status;
-	u16 class;
-	u8 interface;
-	u8 revision;
-	u8 bist;
-	u8 header_type;
-	u8 latency_timer;
-	u8 cache_line_size;
-	u32 bar[2];
-	u8 primary_bus;
-	u8 secondary_bus;
-	u8 subordinate_bus;
-	u8 secondary_latency_timer;
-	u8 iobase;
-	u8 iolimit;
-	u16 secondary_status;
-	u16 membase;
-	u16 memlimit;
-	u16 iobaseupper;
-	u16 iolimitupper;
-	u32 romaddr;
-	u8 intline;
-	u8 intpin;
-	u16 bridgectrl;
-
-	/* PCI express capability */
-	u32 pcie_sltcap;
-	u16 pcie_devctl;
-	u16 pcie_rtctl;
-};
-
 struct mvebu_pcie_port;
 
 /* Structure representing all PCIe interfaces */
@@ -153,7 +99,7 @@
 	struct clk *clk;
 	struct gpio_desc *reset_gpio;
 	char *reset_name;
-	struct mvebu_sw_pci_bridge bridge;
+	struct pci_bridge_emul bridge;
 	struct device_node *dn;
 	struct mvebu_pcie *pcie;
 	struct mvebu_pcie_window memwin;
@@ -415,11 +361,12 @@
 static void mvebu_pcie_handle_iobase_change(struct mvebu_pcie_port *port)
 {
 	struct mvebu_pcie_window desired = {};
+	struct pci_bridge_emul_conf *conf = &port->bridge.conf;
 
 	/* Are the new iobase/iolimit values invalid? */
-	if (port->bridge.iolimit < port->bridge.iobase ||
-	    port->bridge.iolimitupper < port->bridge.iobaseupper ||
-	    !(port->bridge.command & PCI_COMMAND_IO)) {
+	if (conf->iolimit < conf->iobase ||
+	    conf->iolimitupper < conf->iobaseupper ||
+	    !(conf->command & PCI_COMMAND_IO)) {
 		mvebu_pcie_set_window(port, port->io_target, port->io_attr,
 				      &desired, &port->iowin);
 		return;
@@ -438,11 +385,11 @@
 	 * specifications. iobase is the bus address, port->iowin_base
 	 * is the CPU address.
 	 */
-	desired.remap = ((port->bridge.iobase & 0xF0) << 8) |
-			(port->bridge.iobaseupper << 16);
+	desired.remap = ((conf->iobase & 0xF0) << 8) |
+			(conf->iobaseupper << 16);
 	desired.base = port->pcie->io.start + desired.remap;
-	desired.size = ((0xFFF | ((port->bridge.iolimit & 0xF0) << 8) |
-			 (port->bridge.iolimitupper << 16)) -
+	desired.size = ((0xFFF | ((conf->iolimit & 0xF0) << 8) |
+			 (conf->iolimitupper << 16)) -
 			desired.remap) +
 		       1;
 
@@ -453,10 +400,11 @@
 static void mvebu_pcie_handle_membase_change(struct mvebu_pcie_port *port)
 {
 	struct mvebu_pcie_window desired = {.remap = MVEBU_MBUS_NO_REMAP};
+	struct pci_bridge_emul_conf *conf = &port->bridge.conf;
 
 	/* Are the new membase/memlimit values invalid? */
-	if (port->bridge.memlimit < port->bridge.membase ||
-	    !(port->bridge.command & PCI_COMMAND_MEMORY)) {
+	if (conf->memlimit < conf->membase ||
+	    !(conf->command & PCI_COMMAND_MEMORY)) {
 		mvebu_pcie_set_window(port, port->mem_target, port->mem_attr,
 				      &desired, &port->memwin);
 		return;
@@ -468,130 +416,32 @@
 	 * window to setup, according to the PCI-to-PCI bridge
 	 * specifications.
 	 */
-	desired.base = ((port->bridge.membase & 0xFFF0) << 16);
-	desired.size = (((port->bridge.memlimit & 0xFFF0) << 16) | 0xFFFFF) -
+	desired.base = ((conf->membase & 0xFFF0) << 16);
+	desired.size = (((conf->memlimit & 0xFFF0) << 16) | 0xFFFFF) -
 		       desired.base + 1;
 
 	mvebu_pcie_set_window(port, port->mem_target, port->mem_attr, &desired,
 			      &port->memwin);
 }
 
-/*
- * Initialize the configuration space of the PCI-to-PCI bridge
- * associated with the given PCIe interface.
- */
-static void mvebu_sw_pci_bridge_init(struct mvebu_pcie_port *port)
+static pci_bridge_emul_read_status_t
+mvebu_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge,
+				     int reg, u32 *value)
 {
-	struct mvebu_sw_pci_bridge *bridge = &port->bridge;
+	struct mvebu_pcie_port *port = bridge->data;
 
-	memset(bridge, 0, sizeof(struct mvebu_sw_pci_bridge));
-
-	bridge->class = PCI_CLASS_BRIDGE_PCI;
-	bridge->vendor = PCI_VENDOR_ID_MARVELL;
-	bridge->device = mvebu_readl(port, PCIE_DEV_ID_OFF) >> 16;
-	bridge->revision = mvebu_readl(port, PCIE_DEV_REV_OFF) & 0xff;
-	bridge->header_type = PCI_HEADER_TYPE_BRIDGE;
-	bridge->cache_line_size = 0x10;
-
-	/* We support 32 bits I/O addressing */
-	bridge->iobase = PCI_IO_RANGE_TYPE_32;
-	bridge->iolimit = PCI_IO_RANGE_TYPE_32;
-
-	/* Add capabilities */
-	bridge->status = PCI_STATUS_CAP_LIST;
-}
-
-/*
- * Read the configuration space of the PCI-to-PCI bridge associated to
- * the given PCIe interface.
- */
-static int mvebu_sw_pci_bridge_read(struct mvebu_pcie_port *port,
-				  unsigned int where, int size, u32 *value)
-{
-	struct mvebu_sw_pci_bridge *bridge = &port->bridge;
-
-	switch (where & ~3) {
-	case PCI_VENDOR_ID:
-		*value = bridge->device << 16 | bridge->vendor;
-		break;
-
-	case PCI_COMMAND:
-		*value = bridge->command | bridge->status << 16;
-		break;
-
-	case PCI_CLASS_REVISION:
-		*value = bridge->class << 16 | bridge->interface << 8 |
-			 bridge->revision;
-		break;
-
-	case PCI_CACHE_LINE_SIZE:
-		*value = bridge->bist << 24 | bridge->header_type << 16 |
-			 bridge->latency_timer << 8 | bridge->cache_line_size;
-		break;
-
-	case PCI_BASE_ADDRESS_0 ... PCI_BASE_ADDRESS_1:
-		*value = bridge->bar[((where & ~3) - PCI_BASE_ADDRESS_0) / 4];
-		break;
-
-	case PCI_PRIMARY_BUS:
-		*value = (bridge->secondary_latency_timer << 24 |
-			  bridge->subordinate_bus         << 16 |
-			  bridge->secondary_bus           <<  8 |
-			  bridge->primary_bus);
-		break;
-
-	case PCI_IO_BASE:
-		if (!mvebu_has_ioport(port))
-			*value = bridge->secondary_status << 16;
-		else
-			*value = (bridge->secondary_status << 16 |
-				  bridge->iolimit          <<  8 |
-				  bridge->iobase);
-		break;
-
-	case PCI_MEMORY_BASE:
-		*value = (bridge->memlimit << 16 | bridge->membase);
-		break;
-
-	case PCI_PREF_MEMORY_BASE:
-		*value = 0;
-		break;
-
-	case PCI_IO_BASE_UPPER16:
-		*value = (bridge->iolimitupper << 16 | bridge->iobaseupper);
-		break;
-
-	case PCI_CAPABILITY_LIST:
-		*value = PCISWCAP;
-		break;
-
-	case PCI_ROM_ADDRESS1:
-		*value = 0;
-		break;
-
-	case PCI_INTERRUPT_LINE:
-		/* LINE PIN MIN_GNT MAX_LAT */
-		*value = 0;
-		break;
-
-	case PCISWCAP_EXP_LIST_ID:
-		/* Set PCIe v2, root port, slot support */
-		*value = (PCI_EXP_TYPE_ROOT_PORT << 4 | 2 |
-			  PCI_EXP_FLAGS_SLOT) << 16 | PCI_CAP_ID_EXP;
-		break;
-
-	case PCISWCAP_EXP_DEVCAP:
+	switch (reg) {
+	case PCI_EXP_DEVCAP:
 		*value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_DEVCAP);
 		break;
 
-	case PCISWCAP_EXP_DEVCTL:
+	case PCI_EXP_DEVCTL:
 		*value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_DEVCTL) &
 				 ~(PCI_EXP_DEVCTL_URRE | PCI_EXP_DEVCTL_FERE |
 				   PCI_EXP_DEVCTL_NFERE | PCI_EXP_DEVCTL_CERE);
-		*value |= bridge->pcie_devctl;
 		break;
 
-	case PCISWCAP_EXP_LNKCAP:
+	case PCI_EXP_LNKCAP:
 		/*
 		 * PCIe requires the clock power management capability to be
 		 * hard-wired to zero for downstream ports
@@ -600,176 +450,140 @@
 			 ~PCI_EXP_LNKCAP_CLKPM;
 		break;
 
-	case PCISWCAP_EXP_LNKCTL:
+	case PCI_EXP_LNKCTL:
 		*value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCTL);
 		break;
 
-	case PCISWCAP_EXP_SLTCAP:
-		*value = bridge->pcie_sltcap;
-		break;
-
-	case PCISWCAP_EXP_SLTCTL:
+	case PCI_EXP_SLTCTL:
 		*value = PCI_EXP_SLTSTA_PDS << 16;
 		break;
 
-	case PCISWCAP_EXP_RTCTL:
-		*value = bridge->pcie_rtctl;
-		break;
-
-	case PCISWCAP_EXP_RTSTA:
+	case PCI_EXP_RTSTA:
 		*value = mvebu_readl(port, PCIE_RC_RTSTA);
 		break;
 
-	/* PCIe requires the v2 fields to be hard-wired to zero */
-	case PCISWCAP_EXP_DEVCAP2:
-	case PCISWCAP_EXP_DEVCTL2:
-	case PCISWCAP_EXP_LNKCAP2:
-	case PCISWCAP_EXP_LNKCTL2:
-	case PCISWCAP_EXP_SLTCAP2:
-	case PCISWCAP_EXP_SLTCTL2:
 	default:
-		/*
-		 * PCI defines configuration read accesses to reserved or
-		 * unimplemented registers to read as zero and complete
-		 * normally.
-		 */
-		*value = 0;
-		return PCIBIOS_SUCCESSFUL;
+		return PCI_BRIDGE_EMUL_NOT_HANDLED;
 	}
 
-	if (size == 2)
-		*value = (*value >> (8 * (where & 3))) & 0xffff;
-	else if (size == 1)
-		*value = (*value >> (8 * (where & 3))) & 0xff;
-
-	return PCIBIOS_SUCCESSFUL;
+	return PCI_BRIDGE_EMUL_HANDLED;
 }
 
-/* Write to the PCI-to-PCI bridge configuration space */
-static int mvebu_sw_pci_bridge_write(struct mvebu_pcie_port *port,
-				     unsigned int where, int size, u32 value)
+static void
+mvebu_pci_bridge_emul_base_conf_write(struct pci_bridge_emul *bridge,
+				      int reg, u32 old, u32 new, u32 mask)
 {
-	struct mvebu_sw_pci_bridge *bridge = &port->bridge;
-	u32 mask, reg;
-	int err;
+	struct mvebu_pcie_port *port = bridge->data;
+	struct pci_bridge_emul_conf *conf = &bridge->conf;
 
-	if (size == 4)
-		mask = 0x0;
-	else if (size == 2)
-		mask = ~(0xffff << ((where & 3) * 8));
-	else if (size == 1)
-		mask = ~(0xff << ((where & 3) * 8));
-	else
-		return PCIBIOS_BAD_REGISTER_NUMBER;
-
-	err = mvebu_sw_pci_bridge_read(port, where & ~3, 4, &reg);
-	if (err)
-		return err;
-
-	value = (reg & mask) | value << ((where & 3) * 8);
-
-	switch (where & ~3) {
+	switch (reg) {
 	case PCI_COMMAND:
 	{
-		u32 old = bridge->command;
-
 		if (!mvebu_has_ioport(port))
-			value &= ~PCI_COMMAND_IO;
+			conf->command &= ~PCI_COMMAND_IO;
 
-		bridge->command = value & 0xffff;
-		if ((old ^ bridge->command) & PCI_COMMAND_IO)
+		if ((old ^ new) & PCI_COMMAND_IO)
 			mvebu_pcie_handle_iobase_change(port);
-		if ((old ^ bridge->command) & PCI_COMMAND_MEMORY)
+		if ((old ^ new) & PCI_COMMAND_MEMORY)
 			mvebu_pcie_handle_membase_change(port);
+
 		break;
 	}
 
-	case PCI_BASE_ADDRESS_0 ... PCI_BASE_ADDRESS_1:
-		bridge->bar[((where & ~3) - PCI_BASE_ADDRESS_0) / 4] = value;
-		break;
-
 	case PCI_IO_BASE:
 		/*
-		 * We also keep bit 1 set, it is a read-only bit that
+		 * We keep bit 1 set, it is a read-only bit that
 		 * indicates we support 32 bits addressing for the
 		 * I/O
 		 */
-		bridge->iobase = (value & 0xff) | PCI_IO_RANGE_TYPE_32;
-		bridge->iolimit = ((value >> 8) & 0xff) | PCI_IO_RANGE_TYPE_32;
+		conf->iobase |= PCI_IO_RANGE_TYPE_32;
+		conf->iolimit |= PCI_IO_RANGE_TYPE_32;
 		mvebu_pcie_handle_iobase_change(port);
 		break;
 
 	case PCI_MEMORY_BASE:
-		bridge->membase = value & 0xffff;
-		bridge->memlimit = value >> 16;
 		mvebu_pcie_handle_membase_change(port);
 		break;
 
 	case PCI_IO_BASE_UPPER16:
-		bridge->iobaseupper = value & 0xffff;
-		bridge->iolimitupper = value >> 16;
 		mvebu_pcie_handle_iobase_change(port);
 		break;
 
 	case PCI_PRIMARY_BUS:
-		bridge->primary_bus             = value & 0xff;
-		bridge->secondary_bus           = (value >> 8) & 0xff;
-		bridge->subordinate_bus         = (value >> 16) & 0xff;
-		bridge->secondary_latency_timer = (value >> 24) & 0xff;
-		mvebu_pcie_set_local_bus_nr(port, bridge->secondary_bus);
+		mvebu_pcie_set_local_bus_nr(port, conf->secondary_bus);
 		break;
 
-	case PCISWCAP_EXP_DEVCTL:
+	default:
+		break;
+	}
+}
+
+static void
+mvebu_pci_bridge_emul_pcie_conf_write(struct pci_bridge_emul *bridge,
+				      int reg, u32 old, u32 new, u32 mask)
+{
+	struct mvebu_pcie_port *port = bridge->data;
+
+	switch (reg) {
+	case PCI_EXP_DEVCTL:
 		/*
 		 * Armada370 data says these bits must always
 		 * be zero when in root complex mode.
 		 */
-		value &= ~(PCI_EXP_DEVCTL_URRE | PCI_EXP_DEVCTL_FERE |
-			   PCI_EXP_DEVCTL_NFERE | PCI_EXP_DEVCTL_CERE);
+		new &= ~(PCI_EXP_DEVCTL_URRE | PCI_EXP_DEVCTL_FERE |
+			 PCI_EXP_DEVCTL_NFERE | PCI_EXP_DEVCTL_CERE);
 
-		/*
-		 * If the mask is 0xffff0000, then we only want to write
-		 * the device control register, rather than clearing the
-		 * RW1C bits in the device status register.  Mask out the
-		 * status register bits.
-		 */
-		if (mask == 0xffff0000)
-			value &= 0xffff;
-
-		mvebu_writel(port, value, PCIE_CAP_PCIEXP + PCI_EXP_DEVCTL);
+		mvebu_writel(port, new, PCIE_CAP_PCIEXP + PCI_EXP_DEVCTL);
 		break;
 
-	case PCISWCAP_EXP_LNKCTL:
+	case PCI_EXP_LNKCTL:
 		/*
 		 * If we don't support CLKREQ, we must ensure that the
 		 * CLKREQ enable bit always reads zero.  Since we haven't
 		 * had this capability, and it's dependent on board wiring,
 		 * disable it for the time being.
 		 */
-		value &= ~PCI_EXP_LNKCTL_CLKREQ_EN;
+		new &= ~PCI_EXP_LNKCTL_CLKREQ_EN;
 
-		/*
-		 * If the mask is 0xffff0000, then we only want to write
-		 * the link control register, rather than clearing the
-		 * RW1C bits in the link status register.  Mask out the
-		 * RW1C status register bits.
-		 */
-		if (mask == 0xffff0000)
-			value &= ~((PCI_EXP_LNKSTA_LABS |
-				    PCI_EXP_LNKSTA_LBMS) << 16);
-
-		mvebu_writel(port, value, PCIE_CAP_PCIEXP + PCI_EXP_LNKCTL);
+		mvebu_writel(port, new, PCIE_CAP_PCIEXP + PCI_EXP_LNKCTL);
 		break;
 
-	case PCISWCAP_EXP_RTSTA:
-		mvebu_writel(port, value, PCIE_RC_RTSTA);
-		break;
-
-	default:
+	case PCI_EXP_RTSTA:
+		mvebu_writel(port, new, PCIE_RC_RTSTA);
 		break;
 	}
+}
 
-	return PCIBIOS_SUCCESSFUL;
+struct pci_bridge_emul_ops mvebu_pci_bridge_emul_ops = {
+	.write_base = mvebu_pci_bridge_emul_base_conf_write,
+	.read_pcie = mvebu_pci_bridge_emul_pcie_conf_read,
+	.write_pcie = mvebu_pci_bridge_emul_pcie_conf_write,
+};
+
+/*
+ * Initialize the configuration space of the PCI-to-PCI bridge
+ * associated with the given PCIe interface.
+ */
+static void mvebu_pci_bridge_emul_init(struct mvebu_pcie_port *port)
+{
+	struct pci_bridge_emul *bridge = &port->bridge;
+
+	bridge->conf.vendor = PCI_VENDOR_ID_MARVELL;
+	bridge->conf.device = mvebu_readl(port, PCIE_DEV_ID_OFF) >> 16;
+	bridge->conf.class_revision =
+		mvebu_readl(port, PCIE_DEV_REV_OFF) & 0xff;
+
+	if (mvebu_has_ioport(port)) {
+		/* We support 32 bits I/O addressing */
+		bridge->conf.iobase = PCI_IO_RANGE_TYPE_32;
+		bridge->conf.iolimit = PCI_IO_RANGE_TYPE_32;
+	}
+
+	bridge->has_pcie = true;
+	bridge->data = port;
+	bridge->ops = &mvebu_pci_bridge_emul_ops;
+
+	pci_bridge_emul_init(bridge, PCI_BRIDGE_EMUL_NO_PREFETCHABLE_BAR);
 }
 
 static inline struct mvebu_pcie *sys_to_pcie(struct pci_sys_data *sys)
@@ -789,8 +603,8 @@
 		if (bus->number == 0 && port->devfn == devfn)
 			return port;
 		if (bus->number != 0 &&
-		    bus->number >= port->bridge.secondary_bus &&
-		    bus->number <= port->bridge.subordinate_bus)
+		    bus->number >= port->bridge.conf.secondary_bus &&
+		    bus->number <= port->bridge.conf.subordinate_bus)
 			return port;
 	}
 
@@ -811,7 +625,8 @@
 
 	/* Access the emulated PCI-to-PCI bridge */
 	if (bus->number == 0)
-		return mvebu_sw_pci_bridge_write(port, where, size, val);
+		return pci_bridge_emul_conf_write(&port->bridge, where,
+						  size, val);
 
 	if (!mvebu_pcie_link_up(port))
 		return PCIBIOS_DEVICE_NOT_FOUND;
@@ -839,7 +654,8 @@
 
 	/* Access the emulated PCI-to-PCI bridge */
 	if (bus->number == 0)
-		return mvebu_sw_pci_bridge_read(port, where, size, val);
+		return pci_bridge_emul_conf_read(&port->bridge, where,
+						 size, val);
 
 	if (!mvebu_pcie_link_up(port)) {
 		*val = 0xffffffff;
@@ -1297,7 +1113,7 @@
 
 		mvebu_pcie_setup_hw(port);
 		mvebu_pcie_set_local_dev_nr(port, 1);
-		mvebu_sw_pci_bridge_init(port);
+		mvebu_pci_bridge_emul_init(port);
 	}
 
 	pcie->nports = i;
diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index f4f53d0..673a172 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -17,6 +17,7 @@
 #include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/export.h>
+#include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
 #include <linux/iopoll.h>
 #include <linux/irq.h>
@@ -30,6 +31,7 @@
 #include <linux/of_platform.h>
 #include <linux/pci.h>
 #include <linux/phy/phy.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
 #include <linux/sizes.h>
@@ -95,7 +97,8 @@
 #define AFI_MSI_EN_VEC7		0xa8
 
 #define AFI_CONFIGURATION		0xac
-#define  AFI_CONFIGURATION_EN_FPCI	(1 << 0)
+#define  AFI_CONFIGURATION_EN_FPCI		(1 << 0)
+#define  AFI_CONFIGURATION_CLKEN_OVERRIDE	(1 << 31)
 
 #define AFI_FPCI_ERROR_MASKS	0xb0
 
@@ -159,13 +162,14 @@
 #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_PCIE_CONFIG_PCIE_CLKREQ_GPIO(x)		(1 << ((x) + 29))
+#define  AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO_ALL		(0x7 << 29)
 
 #define AFI_FUSE			0x104
 #define  AFI_FUSE_PCIE_T0_GEN2_DIS	(1 << 2)
 
 #define AFI_PEX0_CTRL			0x110
 #define AFI_PEX1_CTRL			0x118
-#define AFI_PEX2_CTRL			0x128
 #define  AFI_PEX_CTRL_RST		(1 << 0)
 #define  AFI_PEX_CTRL_CLKREQ_EN		(1 << 1)
 #define  AFI_PEX_CTRL_REFCLK_EN		(1 << 3)
@@ -177,20 +181,74 @@
 
 #define AFI_PEXBIAS_CTRL_0		0x168
 
+#define RP_PRIV_XP_DL		0x00000494
+#define  RP_PRIV_XP_DL_GEN2_UPD_FC_TSHOLD	(0x1ff << 1)
+
+#define RP_RX_HDR_LIMIT		0x00000e00
+#define  RP_RX_HDR_LIMIT_PW_MASK	(0xff << 8)
+#define  RP_RX_HDR_LIMIT_PW		(0x0e << 8)
+
+#define RP_ECTL_2_R1	0x00000e84
+#define  RP_ECTL_2_R1_RX_CTLE_1C_MASK		0xffff
+
+#define RP_ECTL_4_R1	0x00000e8c
+#define  RP_ECTL_4_R1_RX_CDR_CTRL_1C_MASK	(0xffff << 16)
+#define  RP_ECTL_4_R1_RX_CDR_CTRL_1C_SHIFT	16
+
+#define RP_ECTL_5_R1	0x00000e90
+#define  RP_ECTL_5_R1_RX_EQ_CTRL_L_1C_MASK	0xffffffff
+
+#define RP_ECTL_6_R1	0x00000e94
+#define  RP_ECTL_6_R1_RX_EQ_CTRL_H_1C_MASK	0xffffffff
+
+#define RP_ECTL_2_R2	0x00000ea4
+#define  RP_ECTL_2_R2_RX_CTLE_1C_MASK	0xffff
+
+#define RP_ECTL_4_R2	0x00000eac
+#define  RP_ECTL_4_R2_RX_CDR_CTRL_1C_MASK	(0xffff << 16)
+#define  RP_ECTL_4_R2_RX_CDR_CTRL_1C_SHIFT	16
+
+#define RP_ECTL_5_R2	0x00000eb0
+#define  RP_ECTL_5_R2_RX_EQ_CTRL_L_1C_MASK	0xffffffff
+
+#define RP_ECTL_6_R2	0x00000eb4
+#define  RP_ECTL_6_R2_RX_EQ_CTRL_H_1C_MASK	0xffffffff
+
 #define RP_VEND_XP	0x00000f00
-#define  RP_VEND_XP_DL_UP	(1 << 30)
+#define  RP_VEND_XP_DL_UP			(1 << 30)
+#define  RP_VEND_XP_OPPORTUNISTIC_ACK		(1 << 27)
+#define  RP_VEND_XP_OPPORTUNISTIC_UPDATEFC	(1 << 28)
+#define  RP_VEND_XP_UPDATE_FC_THRESHOLD_MASK	(0xff << 18)
+
+#define RP_VEND_CTL0	0x00000f44
+#define  RP_VEND_CTL0_DSK_RST_PULSE_WIDTH_MASK	(0xf << 12)
+#define  RP_VEND_CTL0_DSK_RST_PULSE_WIDTH	(0x9 << 12)
+
+#define RP_VEND_CTL1	0x00000f48
+#define  RP_VEND_CTL1_ERPT	(1 << 13)
+
+#define RP_VEND_XP_BIST	0x00000f4c
+#define  RP_VEND_XP_BIST_GOTO_L1_L2_AFTER_DLLP_DONE	(1 << 28)
 
 #define RP_VEND_CTL2 0x00000fa8
 #define  RP_VEND_CTL2_PCA_ENABLE (1 << 7)
 
 #define RP_PRIV_MISC	0x00000fe0
-#define  RP_PRIV_MISC_PRSNT_MAP_EP_PRSNT (0xe << 0)
-#define  RP_PRIV_MISC_PRSNT_MAP_EP_ABSNT (0xf << 0)
+#define  RP_PRIV_MISC_PRSNT_MAP_EP_PRSNT		(0xe << 0)
+#define  RP_PRIV_MISC_PRSNT_MAP_EP_ABSNT		(0xf << 0)
+#define  RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD_MASK	(0x7f << 16)
+#define  RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD		(0xf << 16)
+#define  RP_PRIV_MISC_CTLR_CLK_CLAMP_ENABLE		(1 << 23)
+#define  RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD_MASK	(0x7f << 24)
+#define  RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD		(0xf << 24)
+#define  RP_PRIV_MISC_TMS_CLK_CLAMP_ENABLE		(1 << 31)
 
 #define RP_LINK_CONTROL_STATUS			0x00000090
 #define  RP_LINK_CONTROL_STATUS_DL_LINK_ACTIVE	0x20000000
 #define  RP_LINK_CONTROL_STATUS_LINKSTAT_MASK	0x3fff0000
 
+#define RP_LINK_CONTROL_STATUS_2		0x000000b0
+
 #define PADS_CTL_SEL		0x0000009c
 
 #define PADS_CTL		0x000000a0
@@ -226,14 +284,15 @@
 #define PADS_REFCLK_CFG_DRVI_SHIFT		12 /* 15:12 */
 
 #define PME_ACK_TIMEOUT 10000
+#define LINK_RETRAIN_TIMEOUT 100000 /* in usec */
 
 struct tegra_msi {
 	struct msi_controller chip;
 	DECLARE_BITMAP(used, INT_PCI_MSI_NR);
 	struct irq_domain *domain;
-	unsigned long pages;
 	struct mutex lock;
-	u64 phys;
+	void *virt;
+	dma_addr_t phys;
 	int irq;
 };
 
@@ -249,10 +308,12 @@
 	unsigned int num_ports;
 	const struct tegra_pcie_port_soc *ports;
 	unsigned int msi_base_shift;
+	unsigned long afi_pex2_ctrl;
 	u32 pads_pll_ctl;
 	u32 tx_ref_sel;
 	u32 pads_refclk_cfg0;
 	u32 pads_refclk_cfg1;
+	u32 update_fc_threshold;
 	bool has_pex_clkreq_en;
 	bool has_pex_bias_ctrl;
 	bool has_intr_prsnt_sense;
@@ -260,6 +321,24 @@
 	bool has_gen2;
 	bool force_pca_enable;
 	bool program_uphy;
+	bool update_clamp_threshold;
+	bool program_deskew_time;
+	bool raw_violation_fixup;
+	bool update_fc_timer;
+	bool has_cache_bars;
+	struct {
+		struct {
+			u32 rp_ectl_2_r1;
+			u32 rp_ectl_4_r1;
+			u32 rp_ectl_5_r1;
+			u32 rp_ectl_6_r1;
+			u32 rp_ectl_2_r2;
+			u32 rp_ectl_4_r2;
+			u32 rp_ectl_5_r2;
+			u32 rp_ectl_6_r2;
+		} regs;
+		bool enable;
+	} ectl;
 };
 
 static inline struct tegra_msi *to_tegra_msi(struct msi_controller *chip)
@@ -321,6 +400,8 @@
 	unsigned int lanes;
 
 	struct phy **phys;
+
+	struct gpio_desc *reset_gpio;
 };
 
 struct tegra_pcie_bus {
@@ -440,6 +521,7 @@
 
 static unsigned long tegra_pcie_port_get_pex_ctrl(struct tegra_pcie_port *port)
 {
+	const struct tegra_pcie_soc *soc = port->pcie->soc;
 	unsigned long ret = 0;
 
 	switch (port->index) {
@@ -452,7 +534,7 @@
 		break;
 
 	case 2:
-		ret = AFI_PEX2_CTRL;
+		ret = soc->afi_pex2_ctrl;
 		break;
 	}
 
@@ -465,15 +547,162 @@
 	unsigned long value;
 
 	/* pulse reset signal */
-	value = afi_readl(port->pcie, ctrl);
-	value &= ~AFI_PEX_CTRL_RST;
-	afi_writel(port->pcie, value, ctrl);
+	if (port->reset_gpio) {
+		gpiod_set_value(port->reset_gpio, 1);
+	} else {
+		value = afi_readl(port->pcie, ctrl);
+		value &= ~AFI_PEX_CTRL_RST;
+		afi_writel(port->pcie, value, ctrl);
+	}
 
 	usleep_range(1000, 2000);
 
-	value = afi_readl(port->pcie, ctrl);
-	value |= AFI_PEX_CTRL_RST;
-	afi_writel(port->pcie, value, ctrl);
+	if (port->reset_gpio) {
+		gpiod_set_value(port->reset_gpio, 0);
+	} else {
+		value = afi_readl(port->pcie, ctrl);
+		value |= AFI_PEX_CTRL_RST;
+		afi_writel(port->pcie, value, ctrl);
+	}
+}
+
+static void tegra_pcie_enable_rp_features(struct tegra_pcie_port *port)
+{
+	const struct tegra_pcie_soc *soc = port->pcie->soc;
+	u32 value;
+
+	/* Enable AER capability */
+	value = readl(port->base + RP_VEND_CTL1);
+	value |= RP_VEND_CTL1_ERPT;
+	writel(value, port->base + RP_VEND_CTL1);
+
+	/* Optimal settings to enhance bandwidth */
+	value = readl(port->base + RP_VEND_XP);
+	value |= RP_VEND_XP_OPPORTUNISTIC_ACK;
+	value |= RP_VEND_XP_OPPORTUNISTIC_UPDATEFC;
+	writel(value, port->base + RP_VEND_XP);
+
+	/*
+	 * LTSSM will wait for DLLP to finish before entering L1 or L2,
+	 * to avoid truncation of PM messages which results in receiver errors
+	 */
+	value = readl(port->base + RP_VEND_XP_BIST);
+	value |= RP_VEND_XP_BIST_GOTO_L1_L2_AFTER_DLLP_DONE;
+	writel(value, port->base + RP_VEND_XP_BIST);
+
+	value = readl(port->base + RP_PRIV_MISC);
+	value |= RP_PRIV_MISC_CTLR_CLK_CLAMP_ENABLE;
+	value |= RP_PRIV_MISC_TMS_CLK_CLAMP_ENABLE;
+
+	if (soc->update_clamp_threshold) {
+		value &= ~(RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD_MASK |
+				RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD_MASK);
+		value |= RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD |
+			RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD;
+	}
+
+	writel(value, port->base + RP_PRIV_MISC);
+}
+
+static void tegra_pcie_program_ectl_settings(struct tegra_pcie_port *port)
+{
+	const struct tegra_pcie_soc *soc = port->pcie->soc;
+	u32 value;
+
+	value = readl(port->base + RP_ECTL_2_R1);
+	value &= ~RP_ECTL_2_R1_RX_CTLE_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_2_r1;
+	writel(value, port->base + RP_ECTL_2_R1);
+
+	value = readl(port->base + RP_ECTL_4_R1);
+	value &= ~RP_ECTL_4_R1_RX_CDR_CTRL_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_4_r1 <<
+				RP_ECTL_4_R1_RX_CDR_CTRL_1C_SHIFT;
+	writel(value, port->base + RP_ECTL_4_R1);
+
+	value = readl(port->base + RP_ECTL_5_R1);
+	value &= ~RP_ECTL_5_R1_RX_EQ_CTRL_L_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_5_r1;
+	writel(value, port->base + RP_ECTL_5_R1);
+
+	value = readl(port->base + RP_ECTL_6_R1);
+	value &= ~RP_ECTL_6_R1_RX_EQ_CTRL_H_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_6_r1;
+	writel(value, port->base + RP_ECTL_6_R1);
+
+	value = readl(port->base + RP_ECTL_2_R2);
+	value &= ~RP_ECTL_2_R2_RX_CTLE_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_2_r2;
+	writel(value, port->base + RP_ECTL_2_R2);
+
+	value = readl(port->base + RP_ECTL_4_R2);
+	value &= ~RP_ECTL_4_R2_RX_CDR_CTRL_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_4_r2 <<
+				RP_ECTL_4_R2_RX_CDR_CTRL_1C_SHIFT;
+	writel(value, port->base + RP_ECTL_4_R2);
+
+	value = readl(port->base + RP_ECTL_5_R2);
+	value &= ~RP_ECTL_5_R2_RX_EQ_CTRL_L_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_5_r2;
+	writel(value, port->base + RP_ECTL_5_R2);
+
+	value = readl(port->base + RP_ECTL_6_R2);
+	value &= ~RP_ECTL_6_R2_RX_EQ_CTRL_H_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_6_r2;
+	writel(value, port->base + RP_ECTL_6_R2);
+}
+
+static void tegra_pcie_apply_sw_fixup(struct tegra_pcie_port *port)
+{
+	const struct tegra_pcie_soc *soc = port->pcie->soc;
+	u32 value;
+
+	/*
+	 * Sometimes link speed change from Gen2 to Gen1 fails due to
+	 * instability in deskew logic on lane-0. Increase the deskew
+	 * retry time to resolve this issue.
+	 */
+	if (soc->program_deskew_time) {
+		value = readl(port->base + RP_VEND_CTL0);
+		value &= ~RP_VEND_CTL0_DSK_RST_PULSE_WIDTH_MASK;
+		value |= RP_VEND_CTL0_DSK_RST_PULSE_WIDTH;
+		writel(value, port->base + RP_VEND_CTL0);
+	}
+
+	/* Fixup for read after write violation. */
+	if (soc->raw_violation_fixup) {
+		value = readl(port->base + RP_RX_HDR_LIMIT);
+		value &= ~RP_RX_HDR_LIMIT_PW_MASK;
+		value |= RP_RX_HDR_LIMIT_PW;
+		writel(value, port->base + RP_RX_HDR_LIMIT);
+
+		value = readl(port->base + RP_PRIV_XP_DL);
+		value |= RP_PRIV_XP_DL_GEN2_UPD_FC_TSHOLD;
+		writel(value, port->base + RP_PRIV_XP_DL);
+
+		value = readl(port->base + RP_VEND_XP);
+		value &= ~RP_VEND_XP_UPDATE_FC_THRESHOLD_MASK;
+		value |= soc->update_fc_threshold;
+		writel(value, port->base + RP_VEND_XP);
+	}
+
+	if (soc->update_fc_timer) {
+		value = readl(port->base + RP_VEND_XP);
+		value &= ~RP_VEND_XP_UPDATE_FC_THRESHOLD_MASK;
+		value |= soc->update_fc_threshold;
+		writel(value, port->base + RP_VEND_XP);
+	}
+
+	/*
+	 * PCIe link doesn't come up with few legacy PCIe endpoints if
+	 * root port advertises both Gen-1 and Gen-2 speeds in Tegra.
+	 * Hence, the strategy followed here is to initially advertise
+	 * only Gen-1 and after link is up, retrain link to Gen-2 speed
+	 */
+	value = readl(port->base + RP_LINK_CONTROL_STATUS_2);
+	value &= ~PCI_EXP_LNKSTA_CLS;
+	value |= PCI_EXP_LNKSTA_CLS_2_5GB;
+	writel(value, port->base + RP_LINK_CONTROL_STATUS_2);
 }
 
 static void tegra_pcie_port_enable(struct tegra_pcie_port *port)
@@ -500,6 +729,13 @@
 		value |= RP_VEND_CTL2_PCA_ENABLE;
 		writel(value, port->base + RP_VEND_CTL2);
 	}
+
+	tegra_pcie_enable_rp_features(port);
+
+	if (soc->ectl.enable)
+		tegra_pcie_program_ectl_settings(port);
+
+	tegra_pcie_apply_sw_fixup(port);
 }
 
 static void tegra_pcie_port_disable(struct tegra_pcie_port *port)
@@ -521,6 +757,12 @@
 
 	value &= ~AFI_PEX_CTRL_REFCLK_EN;
 	afi_writel(port->pcie, value, ctrl);
+
+	/* disable PCIe port and set CLKREQ# as GPIO to allow PLLE power down */
+	value = afi_readl(port->pcie, AFI_PCIE_CONFIG);
+	value |= AFI_PCIE_CONFIG_PCIE_DISABLE(port->index);
+	value |= AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO(port->index);
+	afi_writel(port->pcie, value, AFI_PCIE_CONFIG);
 }
 
 static void tegra_pcie_port_free(struct tegra_pcie_port *port)
@@ -545,12 +787,15 @@
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0e1c, tegra_pcie_fixup_class);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0e1d, tegra_pcie_fixup_class);
 
-/* Tegra PCIE requires relaxed ordering */
+/* Tegra20 and Tegra30 PCIE requires relaxed ordering */
 static void tegra_pcie_relax_enable(struct pci_dev *dev)
 {
 	pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_RELAX_EN);
 }
-DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, tegra_pcie_relax_enable);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0bf0, tegra_pcie_relax_enable);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0bf1, tegra_pcie_relax_enable);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0e1c, tegra_pcie_relax_enable);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0e1d, tegra_pcie_relax_enable);
 
 static int tegra_pcie_request_resources(struct tegra_pcie *pcie)
 {
@@ -635,7 +880,7 @@
 	 * do not pollute kernel log with master abort reports since they
 	 * happen a lot during enumeration
 	 */
-	if (code == AFI_INTR_MASTER_ABORT)
+	if (code == AFI_INTR_MASTER_ABORT || code == AFI_INTR_PE_PRSNT_SENSE)
 		dev_dbg(dev, "%s, signature: %08x\n", err_msg[code], signature);
 	else
 		dev_err(dev, "%s, signature: %08x\n", err_msg[code], signature);
@@ -704,11 +949,13 @@
 	afi_writel(pcie, 0, AFI_AXI_BAR5_SZ);
 	afi_writel(pcie, 0, AFI_FPCI_BAR5);
 
-	/* map all upstream transactions as uncached */
-	afi_writel(pcie, 0, AFI_CACHE_BAR0_ST);
-	afi_writel(pcie, 0, AFI_CACHE_BAR0_SZ);
-	afi_writel(pcie, 0, AFI_CACHE_BAR1_ST);
-	afi_writel(pcie, 0, AFI_CACHE_BAR1_SZ);
+	if (pcie->soc->has_cache_bars) {
+		/* map all upstream transactions as uncached */
+		afi_writel(pcie, 0, AFI_CACHE_BAR0_ST);
+		afi_writel(pcie, 0, AFI_CACHE_BAR0_SZ);
+		afi_writel(pcie, 0, AFI_CACHE_BAR1_ST);
+		afi_writel(pcie, 0, AFI_CACHE_BAR1_SZ);
+	}
 
 	/* MSI translations are setup only when needed */
 	afi_writel(pcie, 0, AFI_MSI_FPCI_BAR_ST);
@@ -852,7 +1099,6 @@
 static int tegra_pcie_phy_power_on(struct tegra_pcie *pcie)
 {
 	struct device *dev = pcie->dev;
-	const struct tegra_pcie_soc *soc = pcie->soc;
 	struct tegra_pcie_port *port;
 	int err;
 
@@ -878,12 +1124,6 @@
 		}
 	}
 
-	/* Configure the reference clock driver */
-	pads_writel(pcie, soc->pads_refclk_cfg0, PADS_REFCLK_CFG0);
-
-	if (soc->num_ports > 2)
-		pads_writel(pcie, soc->pads_refclk_cfg1, PADS_REFCLK_CFG1);
-
 	return 0;
 }
 
@@ -918,13 +1158,11 @@
 	return 0;
 }
 
-static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
+static void tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 {
-	struct device *dev = pcie->dev;
 	const struct tegra_pcie_soc *soc = pcie->soc;
 	struct tegra_pcie_port *port;
 	unsigned long value;
-	int err;
 
 	/* enable PLL power down */
 	if (pcie->phy) {
@@ -942,9 +1180,12 @@
 	value = afi_readl(pcie, AFI_PCIE_CONFIG);
 	value &= ~AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_MASK;
 	value |= AFI_PCIE_CONFIG_PCIE_DISABLE_ALL | pcie->xbar_config;
+	value |= AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO_ALL;
 
-	list_for_each_entry(port, &pcie->ports, list)
+	list_for_each_entry(port, &pcie->ports, list) {
 		value &= ~AFI_PCIE_CONFIG_PCIE_DISABLE(port->index);
+		value &= ~AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO(port->index);
+	}
 
 	afi_writel(pcie, value, AFI_PCIE_CONFIG);
 
@@ -958,20 +1199,10 @@
 		afi_writel(pcie, value, AFI_FUSE);
 	}
 
-	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 */
-	reset_control_deassert(pcie->pcie_xrst);
-
-	/* finally enable PCIe */
+	/* Disable AFI dynamic clock gating and enable PCIe */
 	value = afi_readl(pcie, AFI_CONFIGURATION);
 	value |= AFI_CONFIGURATION_EN_FPCI;
+	value |= AFI_CONFIGURATION_CLKEN_OVERRIDE;
 	afi_writel(pcie, value, AFI_CONFIGURATION);
 
 	value = AFI_INTR_EN_INI_SLVERR | AFI_INTR_EN_INI_DECERR |
@@ -989,22 +1220,6 @@
 
 	/* disable all exceptions */
 	afi_writel(pcie, 0, AFI_FPCI_ERROR_MASKS);
-
-	return 0;
-}
-
-static void tegra_pcie_disable_controller(struct tegra_pcie *pcie)
-{
-	int err;
-
-	reset_control_assert(pcie->pcie_xrst);
-
-	if (pcie->soc->program_uphy) {
-		err = tegra_pcie_phy_power_off(pcie);
-		if (err < 0)
-			dev_err(pcie->dev, "failed to power off PHY(s): %d\n",
-				err);
-	}
 }
 
 static void tegra_pcie_power_off(struct tegra_pcie *pcie)
@@ -1014,13 +1229,11 @@
 	int err;
 
 	reset_control_assert(pcie->afi_rst);
-	reset_control_assert(pcie->pex_rst);
 
 	clk_disable_unprepare(pcie->pll_e);
 	if (soc->has_cml_clk)
 		clk_disable_unprepare(pcie->cml_clk);
 	clk_disable_unprepare(pcie->afi_clk);
-	clk_disable_unprepare(pcie->pex_clk);
 
 	if (!dev->pm_domain)
 		tegra_powergate_power_off(TEGRA_POWERGATE_PCIE);
@@ -1048,46 +1261,66 @@
 	if (err < 0)
 		dev_err(dev, "failed to enable regulators: %d\n", err);
 
-	if (dev->pm_domain) {
-		err = clk_prepare_enable(pcie->pex_clk);
+	if (!dev->pm_domain) {
+		err = tegra_powergate_power_on(TEGRA_POWERGATE_PCIE);
 		if (err) {
-			dev_err(dev, "failed to enable PEX clock: %d\n", err);
-			return err;
+			dev_err(dev, "failed to power ungate: %d\n", err);
+			goto regulator_disable;
 		}
-		reset_control_deassert(pcie->pex_rst);
-	} else {
-		err = tegra_powergate_sequence_power_up(TEGRA_POWERGATE_PCIE,
-							pcie->pex_clk,
-							pcie->pex_rst);
+		err = tegra_powergate_remove_clamping(TEGRA_POWERGATE_PCIE);
 		if (err) {
-			dev_err(dev, "powerup sequence failed: %d\n", err);
-			return err;
+			dev_err(dev, "failed to remove clamp: %d\n", err);
+			goto powergate;
 		}
 	}
 
-	reset_control_deassert(pcie->afi_rst);
-
 	err = clk_prepare_enable(pcie->afi_clk);
 	if (err < 0) {
 		dev_err(dev, "failed to enable AFI clock: %d\n", err);
-		return err;
+		goto powergate;
 	}
 
 	if (soc->has_cml_clk) {
 		err = clk_prepare_enable(pcie->cml_clk);
 		if (err < 0) {
 			dev_err(dev, "failed to enable CML clock: %d\n", err);
-			return err;
+			goto disable_afi_clk;
 		}
 	}
 
 	err = clk_prepare_enable(pcie->pll_e);
 	if (err < 0) {
 		dev_err(dev, "failed to enable PLLE clock: %d\n", err);
-		return err;
+		goto disable_cml_clk;
 	}
 
+	reset_control_deassert(pcie->afi_rst);
+
 	return 0;
+
+disable_cml_clk:
+	if (soc->has_cml_clk)
+		clk_disable_unprepare(pcie->cml_clk);
+disable_afi_clk:
+	clk_disable_unprepare(pcie->afi_clk);
+powergate:
+	if (!dev->pm_domain)
+		tegra_powergate_power_off(TEGRA_POWERGATE_PCIE);
+regulator_disable:
+	regulator_bulk_disable(pcie->num_supplies, pcie->supplies);
+
+	return err;
+}
+
+static void tegra_pcie_apply_pad_settings(struct tegra_pcie *pcie)
+{
+	const struct tegra_pcie_soc *soc = pcie->soc;
+
+	/* Configure the reference clock driver */
+	pads_writel(pcie, soc->pads_refclk_cfg0, PADS_REFCLK_CFG0);
+
+	if (soc->num_ports > 2)
+		pads_writel(pcie, soc->pads_refclk_cfg1, PADS_REFCLK_CFG1);
 }
 
 static int tegra_pcie_clocks_get(struct tegra_pcie *pcie)
@@ -1536,7 +1769,7 @@
 	err = platform_get_irq_byname(pdev, "msi");
 	if (err < 0) {
 		dev_err(dev, "failed to get IRQ: %d\n", err);
-		goto err;
+		goto free_irq_domain;
 	}
 
 	msi->irq = err;
@@ -1545,17 +1778,35 @@
 			  tegra_msi_irq_chip.name, pcie);
 	if (err < 0) {
 		dev_err(dev, "failed to request IRQ: %d\n", err);
-		goto err;
+		goto free_irq_domain;
 	}
 
-	/* setup AFI/FPCI range */
-	msi->pages = __get_free_pages(GFP_KERNEL, 0);
-	msi->phys = virt_to_phys((void *)msi->pages);
+	/* Though the PCIe controller can address >32-bit address space, to
+	 * facilitate endpoints that support only 32-bit MSI target address,
+	 * the mask is set to 32-bit to make sure that MSI target address is
+	 * always a 32-bit address
+	 */
+	err = dma_set_coherent_mask(dev, DMA_BIT_MASK(32));
+	if (err < 0) {
+		dev_err(dev, "failed to set DMA coherent mask: %d\n", err);
+		goto free_irq;
+	}
+
+	msi->virt = dma_alloc_attrs(dev, PAGE_SIZE, &msi->phys, GFP_KERNEL,
+				    DMA_ATTR_NO_KERNEL_MAPPING);
+	if (!msi->virt) {
+		dev_err(dev, "failed to allocate DMA memory for MSI\n");
+		err = -ENOMEM;
+		goto free_irq;
+	}
+
 	host->msi = &msi->chip;
 
 	return 0;
 
-err:
+free_irq:
+	free_irq(msi->irq, pcie);
+free_irq_domain:
 	irq_domain_remove(msi->domain);
 	return err;
 }
@@ -1592,7 +1843,8 @@
 	struct tegra_msi *msi = &pcie->msi;
 	unsigned int i, irq;
 
-	free_pages(msi->pages, 0);
+	dma_free_attrs(pcie->dev, PAGE_SIZE, msi->virt, msi->phys,
+		       DMA_ATTR_NO_KERNEL_MAPPING);
 
 	if (msi->irq > 0)
 		free_irq(msi->irq, pcie);
@@ -1628,6 +1880,15 @@
 	return 0;
 }
 
+static void tegra_pcie_disable_interrupts(struct tegra_pcie *pcie)
+{
+	u32 value;
+
+	value = afi_readl(pcie, AFI_INTR_MASK);
+	value &= ~AFI_INTR_MASK_INT_MASK;
+	afi_writel(pcie, value, AFI_INTR_MASK);
+}
+
 static int tegra_pcie_get_xbar_config(struct tegra_pcie *pcie, u32 lanes,
 				      u32 *xbar)
 {
@@ -1971,18 +2232,20 @@
 		struct tegra_pcie_port *rp;
 		unsigned int index;
 		u32 value;
+		char *label;
 
 		err = of_pci_get_devfn(port);
 		if (err < 0) {
 			dev_err(dev, "failed to parse address: %d\n", err);
-			return err;
+			goto err_node_put;
 		}
 
 		index = PCI_SLOT(err);
 
 		if (index < 1 || index > soc->num_ports) {
 			dev_err(dev, "invalid port number: %d\n", index);
-			return -EINVAL;
+			err = -EINVAL;
+			goto err_node_put;
 		}
 
 		index--;
@@ -1991,12 +2254,13 @@
 		if (err < 0) {
 			dev_err(dev, "failed to parse # of lanes: %d\n",
 				err);
-			return err;
+			goto err_node_put;
 		}
 
 		if (value > 16) {
 			dev_err(dev, "invalid # of lanes: %u\n", value);
-			return -EINVAL;
+			err = -EINVAL;
+			goto err_node_put;
 		}
 
 		lanes |= value << (index << 3);
@@ -2010,13 +2274,15 @@
 		lane += value;
 
 		rp = devm_kzalloc(dev, sizeof(*rp), GFP_KERNEL);
-		if (!rp)
-			return -ENOMEM;
+		if (!rp) {
+			err = -ENOMEM;
+			goto err_node_put;
+		}
 
 		err = of_address_to_resource(port, 0, &rp->regs);
 		if (err < 0) {
 			dev_err(dev, "failed to parse address: %d\n", err);
-			return err;
+			goto err_node_put;
 		}
 
 		INIT_LIST_HEAD(&rp->list);
@@ -2029,6 +2295,31 @@
 		if (IS_ERR(rp->base))
 			return PTR_ERR(rp->base);
 
+		label = devm_kasprintf(dev, GFP_KERNEL, "pex-reset-%u", index);
+		if (!label) {
+			dev_err(dev, "failed to create reset GPIO label\n");
+			return -ENOMEM;
+		}
+
+		/*
+		 * Returns -ENOENT if reset-gpios property is not populated
+		 * and in this case fall back to using AFI per port register
+		 * to toggle PERST# SFIO line.
+		 */
+		rp->reset_gpio = devm_gpiod_get_from_of_node(dev, port,
+							     "reset-gpios", 0,
+							     GPIOD_OUT_LOW,
+							     label);
+		if (IS_ERR(rp->reset_gpio)) {
+			if (PTR_ERR(rp->reset_gpio) == -ENOENT) {
+				rp->reset_gpio = NULL;
+			} else {
+				dev_err(dev, "failed to get reset GPIO: %d\n",
+					err);
+				return PTR_ERR(rp->reset_gpio);
+			}
+		}
+
 		list_add_tail(&rp->list, &pcie->ports);
 	}
 
@@ -2043,6 +2334,10 @@
 		return err;
 
 	return 0;
+
+err_node_put:
+	of_node_put(port);
+	return err;
 }
 
 /*
@@ -2076,7 +2371,7 @@
 		} while (--timeout);
 
 		if (!timeout) {
-			dev_err(dev, "link %u down, retrying\n", port->index);
+			dev_dbg(dev, "link %u down, retrying\n", port->index);
 			goto retry;
 		}
 
@@ -2098,6 +2393,64 @@
 	return false;
 }
 
+static void tegra_pcie_change_link_speed(struct tegra_pcie *pcie)
+{
+	struct device *dev = pcie->dev;
+	struct tegra_pcie_port *port;
+	ktime_t deadline;
+	u32 value;
+
+	list_for_each_entry(port, &pcie->ports, list) {
+		/*
+		 * "Supported Link Speeds Vector" in "Link Capabilities 2"
+		 * is not supported by Tegra. tegra_pcie_change_link_speed()
+		 * is called only for Tegra chips which support Gen2.
+		 * So there no harm if supported link speed is not verified.
+		 */
+		value = readl(port->base + RP_LINK_CONTROL_STATUS_2);
+		value &= ~PCI_EXP_LNKSTA_CLS;
+		value |= PCI_EXP_LNKSTA_CLS_5_0GB;
+		writel(value, port->base + RP_LINK_CONTROL_STATUS_2);
+
+		/*
+		 * Poll until link comes back from recovery to avoid race
+		 * condition.
+		 */
+		deadline = ktime_add_us(ktime_get(), LINK_RETRAIN_TIMEOUT);
+
+		while (ktime_before(ktime_get(), deadline)) {
+			value = readl(port->base + RP_LINK_CONTROL_STATUS);
+			if ((value & PCI_EXP_LNKSTA_LT) == 0)
+				break;
+
+			usleep_range(2000, 3000);
+		}
+
+		if (value & PCI_EXP_LNKSTA_LT)
+			dev_warn(dev, "PCIe port %u link is in recovery\n",
+				 port->index);
+
+		/* Retrain the link */
+		value = readl(port->base + RP_LINK_CONTROL_STATUS);
+		value |= PCI_EXP_LNKCTL_RL;
+		writel(value, port->base + RP_LINK_CONTROL_STATUS);
+
+		deadline = ktime_add_us(ktime_get(), LINK_RETRAIN_TIMEOUT);
+
+		while (ktime_before(ktime_get(), deadline)) {
+			value = readl(port->base + RP_LINK_CONTROL_STATUS);
+			if ((value & PCI_EXP_LNKSTA_LT) == 0)
+				break;
+
+			usleep_range(2000, 3000);
+		}
+
+		if (value & PCI_EXP_LNKSTA_LT)
+			dev_err(dev, "failed to retrain link of port %u\n",
+				port->index);
+	}
+}
+
 static void tegra_pcie_enable_ports(struct tegra_pcie *pcie)
 {
 	struct device *dev = pcie->dev;
@@ -2108,7 +2461,12 @@
 			 port->index, port->lanes);
 
 		tegra_pcie_port_enable(port);
+	}
 
+	/* Start LTSSM from Tegra side */
+	reset_control_deassert(pcie->pcie_xrst);
+
+	list_for_each_entry_safe(port, tmp, &pcie->ports, list) {
 		if (tegra_pcie_port_check_link(port))
 			continue;
 
@@ -2117,12 +2475,17 @@
 		tegra_pcie_port_disable(port);
 		tegra_pcie_port_free(port);
 	}
+
+	if (pcie->soc->has_gen2)
+		tegra_pcie_change_link_speed(pcie);
 }
 
 static void tegra_pcie_disable_ports(struct tegra_pcie *pcie)
 {
 	struct tegra_pcie_port *port, *tmp;
 
+	reset_control_assert(pcie->pcie_xrst);
+
 	list_for_each_entry_safe(port, tmp, &pcie->ports, list)
 		tegra_pcie_port_disable(port);
 }
@@ -2136,6 +2499,7 @@
 	.num_ports = 2,
 	.ports = tegra20_pcie_ports,
 	.msi_base_shift = 0,
+	.afi_pex2_ctrl = 0x128,
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA20,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_DIV10,
 	.pads_refclk_cfg0 = 0xfa5cfa5c,
@@ -2146,6 +2510,12 @@
 	.has_gen2 = false,
 	.force_pca_enable = false,
 	.program_uphy = true,
+	.update_clamp_threshold = false,
+	.program_deskew_time = false,
+	.raw_violation_fixup = false,
+	.update_fc_timer = false,
+	.has_cache_bars = true,
+	.ectl.enable = false,
 };
 
 static const struct tegra_pcie_port_soc tegra30_pcie_ports[] = {
@@ -2169,6 +2539,12 @@
 	.has_gen2 = false,
 	.force_pca_enable = false,
 	.program_uphy = true,
+	.update_clamp_threshold = false,
+	.program_deskew_time = false,
+	.raw_violation_fixup = false,
+	.update_fc_timer = false,
+	.has_cache_bars = false,
+	.ectl.enable = false,
 };
 
 static const struct tegra_pcie_soc tegra124_pcie = {
@@ -2178,6 +2554,8 @@
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA30,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN,
 	.pads_refclk_cfg0 = 0x44ac44ac,
+	/* FC threshold is bit[25:18] */
+	.update_fc_threshold = 0x03fc0000,
 	.has_pex_clkreq_en = true,
 	.has_pex_bias_ctrl = true,
 	.has_intr_prsnt_sense = true,
@@ -2185,6 +2563,12 @@
 	.has_gen2 = true,
 	.force_pca_enable = false,
 	.program_uphy = true,
+	.update_clamp_threshold = true,
+	.program_deskew_time = false,
+	.raw_violation_fixup = true,
+	.update_fc_timer = false,
+	.has_cache_bars = false,
+	.ectl.enable = false,
 };
 
 static const struct tegra_pcie_soc tegra210_pcie = {
@@ -2194,6 +2578,8 @@
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA30,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN,
 	.pads_refclk_cfg0 = 0x90b890b8,
+	/* FC threshold is bit[25:18] */
+	.update_fc_threshold = 0x01800000,
 	.has_pex_clkreq_en = true,
 	.has_pex_bias_ctrl = true,
 	.has_intr_prsnt_sense = true,
@@ -2201,6 +2587,24 @@
 	.has_gen2 = true,
 	.force_pca_enable = true,
 	.program_uphy = true,
+	.update_clamp_threshold = true,
+	.program_deskew_time = true,
+	.raw_violation_fixup = false,
+	.update_fc_timer = true,
+	.has_cache_bars = false,
+	.ectl = {
+		.regs = {
+			.rp_ectl_2_r1 = 0x0000000f,
+			.rp_ectl_4_r1 = 0x00000067,
+			.rp_ectl_5_r1 = 0x55010000,
+			.rp_ectl_6_r1 = 0x00000001,
+			.rp_ectl_2_r2 = 0x0000008f,
+			.rp_ectl_4_r2 = 0x000000c7,
+			.rp_ectl_5_r2 = 0x55010000,
+			.rp_ectl_6_r2 = 0x00000001,
+		},
+		.enable = true,
+	},
 };
 
 static const struct tegra_pcie_port_soc tegra186_pcie_ports[] = {
@@ -2213,6 +2617,7 @@
 	.num_ports = 3,
 	.ports = tegra186_pcie_ports,
 	.msi_base_shift = 8,
+	.afi_pex2_ctrl = 0x19c,
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA30,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN,
 	.pads_refclk_cfg0 = 0x80b880b8,
@@ -2224,6 +2629,12 @@
 	.has_gen2 = true,
 	.force_pca_enable = false,
 	.program_uphy = false,
+	.update_clamp_threshold = false,
+	.program_deskew_time = false,
+	.raw_violation_fixup = false,
+	.update_fc_timer = false,
+	.has_cache_bars = false,
+	.ectl.enable = false,
 };
 
 static const struct of_device_id tegra_pcie_of_match[] = {
@@ -2466,16 +2877,32 @@
 {
 	struct tegra_pcie *pcie = dev_get_drvdata(dev);
 	struct tegra_pcie_port *port;
+	int err;
 
 	list_for_each_entry(port, &pcie->ports, list)
 		tegra_pcie_pme_turnoff(port);
 
 	tegra_pcie_disable_ports(pcie);
 
+	/*
+	 * AFI_INTR is unmasked in tegra_pcie_enable_controller(), mask it to
+	 * avoid unwanted interrupts raised by AFI after pex_rst is asserted.
+	 */
+	tegra_pcie_disable_interrupts(pcie);
+
+	if (pcie->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->pex_rst);
+	clk_disable_unprepare(pcie->pex_clk);
+
 	if (IS_ENABLED(CONFIG_PCI_MSI))
 		tegra_pcie_disable_msi(pcie);
 
-	tegra_pcie_disable_controller(pcie);
+	pinctrl_pm_select_idle_state(dev);
 	tegra_pcie_power_off(pcie);
 
 	return 0;
@@ -2491,20 +2918,45 @@
 		dev_err(dev, "tegra pcie power on fail: %d\n", err);
 		return err;
 	}
-	err = tegra_pcie_enable_controller(pcie);
-	if (err) {
-		dev_err(dev, "tegra pcie controller enable fail: %d\n", err);
+
+	err = pinctrl_pm_select_default_state(dev);
+	if (err < 0) {
+		dev_err(dev, "failed to disable PCIe IO DPD: %d\n", err);
 		goto poweroff;
 	}
+
+	tegra_pcie_enable_controller(pcie);
 	tegra_pcie_setup_translations(pcie);
 
 	if (IS_ENABLED(CONFIG_PCI_MSI))
 		tegra_pcie_enable_msi(pcie);
 
+	err = clk_prepare_enable(pcie->pex_clk);
+	if (err) {
+		dev_err(dev, "failed to enable PEX clock: %d\n", err);
+		goto pex_dpd_enable;
+	}
+
+	reset_control_deassert(pcie->pex_rst);
+
+	if (pcie->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);
+			goto disable_pex_clk;
+		}
+	}
+
+	tegra_pcie_apply_pad_settings(pcie);
 	tegra_pcie_enable_ports(pcie);
 
 	return 0;
 
+disable_pex_clk:
+	reset_control_assert(pcie->pex_rst);
+	clk_disable_unprepare(pcie->pex_clk);
+pex_dpd_enable:
+	pinctrl_pm_select_idle_state(dev);
 poweroff:
 	tegra_pcie_power_off(pcie);
 
diff --git a/drivers/pci/controller/pcie-altera-msi.c b/drivers/pci/controller/pcie-altera-msi.c
index 025ef7d..16d9389 100644
--- a/drivers/pci/controller/pcie-altera-msi.c
+++ b/drivers/pci/controller/pcie-altera-msi.c
@@ -10,6 +10,7 @@
 #include <linux/interrupt.h>
 #include <linux/irqchip/chained_irq.h>
 #include <linux/init.h>
+#include <linux/module.h>
 #include <linux/msi.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
@@ -288,4 +289,13 @@
 {
 	return platform_driver_register(&altera_msi_driver);
 }
+
+static void __exit altera_msi_exit(void)
+{
+	platform_driver_unregister(&altera_msi_driver);
+}
+
 subsys_initcall(altera_msi_init);
+MODULE_DEVICE_TABLE(of, altera_msi_of_match);
+module_exit(altera_msi_exit);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/controller/pcie-altera.c b/drivers/pci/controller/pcie-altera.c
index 7d05e51..d2497ca 100644
--- a/drivers/pci/controller/pcie-altera.c
+++ b/drivers/pci/controller/pcie-altera.c
@@ -10,7 +10,9 @@
 #include <linux/interrupt.h>
 #include <linux/irqchip/chained_irq.h>
 #include <linux/init.h>
+#include <linux/module.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>
@@ -37,7 +39,14 @@
 #define RP_LTSSM_MASK			0x1f
 #define LTSSM_L0			0xf
 
-#define PCIE_CAP_OFFSET			0x80
+#define S10_RP_TX_CNTRL			0x2004
+#define S10_RP_RXCPL_REG		0x2008
+#define S10_RP_RXCPL_STATUS		0x200C
+#define S10_RP_CFG_ADDR(pcie, reg)	\
+	(((pcie)->hip_base) + (reg) + (1 << 20))
+#define S10_RP_SECONDARY(pcie)		\
+	readb(S10_RP_CFG_ADDR(pcie, PCI_SECONDARY_BUS))
+
 /* TLP configuration type 0 and 1 */
 #define TLP_FMTTYPE_CFGRD0		0x04	/* Configuration Read Type 0 */
 #define TLP_FMTTYPE_CFGWR0		0x44	/* Configuration Write Type 0 */
@@ -48,19 +57,15 @@
 #define TLP_WRITE_TAG			0x10
 #define RP_DEVFN			0
 #define TLP_REQ_ID(bus, devfn)		(((bus) << 8) | (devfn))
-#define TLP_CFGRD_DW0(pcie, bus)					\
-    ((((bus == pcie->root_bus_nr) ? TLP_FMTTYPE_CFGRD0			\
-				    : TLP_FMTTYPE_CFGRD1) << 24) |	\
-     TLP_PAYLOAD_SIZE)
-#define TLP_CFGWR_DW0(pcie, bus)					\
-    ((((bus == pcie->root_bus_nr) ? TLP_FMTTYPE_CFGWR0			\
-				    : TLP_FMTTYPE_CFGWR1) << 24) |	\
-     TLP_PAYLOAD_SIZE)
+#define TLP_CFG_DW0(pcie, cfg)		\
+		(((cfg) << 24) |	\
+		  TLP_PAYLOAD_SIZE)
 #define TLP_CFG_DW1(pcie, tag, be)	\
-    (((TLP_REQ_ID(pcie->root_bus_nr,  RP_DEVFN)) << 16) | (tag << 8) | (be))
+	(((TLP_REQ_ID(pcie->root_bus_nr,  RP_DEVFN)) << 16) | (tag << 8) | (be))
 #define TLP_CFG_DW2(bus, devfn, offset)	\
 				(((bus) << 24) | ((devfn) << 16) | (offset))
 #define TLP_COMP_STATUS(s)		(((s) >> 13) & 7)
+#define TLP_BYTE_COUNT(s)		(((s) >> 0) & 0xfff)
 #define TLP_HDR_SIZE			3
 #define TLP_LOOP			500
 
@@ -69,14 +74,47 @@
 
 #define DWORD_MASK			3
 
+#define S10_TLP_FMTTYPE_CFGRD0		0x05
+#define S10_TLP_FMTTYPE_CFGRD1		0x04
+#define S10_TLP_FMTTYPE_CFGWR0		0x45
+#define S10_TLP_FMTTYPE_CFGWR1		0x44
+
+enum altera_pcie_version {
+	ALTERA_PCIE_V1 = 0,
+	ALTERA_PCIE_V2,
+};
+
 struct altera_pcie {
 	struct platform_device	*pdev;
-	void __iomem		*cra_base;	/* DT Cra */
+	void __iomem		*cra_base;
+	void __iomem		*hip_base;
 	int			irq;
 	u8			root_bus_nr;
 	struct irq_domain	*irq_domain;
 	struct resource		bus_range;
 	struct list_head	resources;
+	const struct altera_pcie_data	*pcie_data;
+};
+
+struct altera_pcie_ops {
+	int (*tlp_read_pkt)(struct altera_pcie *pcie, u32 *value);
+	void (*tlp_write_pkt)(struct altera_pcie *pcie, u32 *headers,
+			      u32 data, bool align);
+	bool (*get_link_status)(struct altera_pcie *pcie);
+	int (*rp_read_cfg)(struct altera_pcie *pcie, int where,
+			   int size, u32 *value);
+	int (*rp_write_cfg)(struct altera_pcie *pcie, u8 busno,
+			    int where, int size, u32 value);
+};
+
+struct altera_pcie_data {
+	const struct altera_pcie_ops *ops;
+	enum altera_pcie_version version;
+	u32 cap_offset;		/* PCIe capability structure register offset */
+	u32 cfgrd0;
+	u32 cfgrd1;
+	u32 cfgwr0;
+	u32 cfgwr1;
 };
 
 struct tlp_rp_regpair_t {
@@ -101,6 +139,15 @@
 	return !!((cra_readl(pcie, RP_LTSSM) & RP_LTSSM_MASK) == LTSSM_L0);
 }
 
+static bool s10_altera_pcie_link_up(struct altera_pcie *pcie)
+{
+	void __iomem *addr = S10_RP_CFG_ADDR(pcie,
+				   pcie->pcie_data->cap_offset +
+				   PCI_EXP_LNKSTA);
+
+	return !!(readw(addr) & PCI_EXP_LNKSTA_DLLLA);
+}
+
 /*
  * Altera PCIe port uses BAR0 of RC's configuration space as the translation
  * from PCI bus to native BUS.  Entire DDR region is mapped into PCIe space
@@ -128,12 +175,18 @@
 	cra_writel(pcie, tlp_rp_regdata->ctrl, RP_TX_CNTRL);
 }
 
+static void s10_tlp_write_tx(struct altera_pcie *pcie, u32 reg0, u32 ctrl)
+{
+	cra_writel(pcie, reg0, RP_TX_REG0);
+	cra_writel(pcie, ctrl, S10_RP_TX_CNTRL);
+}
+
 static bool altera_pcie_valid_device(struct altera_pcie *pcie,
 				     struct pci_bus *bus, int dev)
 {
 	/* If there is no link, then there is no device */
 	if (bus->number != pcie->root_bus_nr) {
-		if (!altera_pcie_link_up(pcie))
+		if (!pcie->pcie_data->ops->get_link_status(pcie))
 			return false;
 	}
 
@@ -183,6 +236,53 @@
 	return PCIBIOS_DEVICE_NOT_FOUND;
 }
 
+static int s10_tlp_read_packet(struct altera_pcie *pcie, u32 *value)
+{
+	u32 ctrl;
+	u32 comp_status;
+	u32 dw[4];
+	u32 count;
+	struct device *dev = &pcie->pdev->dev;
+
+	for (count = 0; count < TLP_LOOP; count++) {
+		ctrl = cra_readl(pcie, S10_RP_RXCPL_STATUS);
+		if (ctrl & RP_RXCPL_SOP) {
+			/* Read first DW */
+			dw[0] = cra_readl(pcie, S10_RP_RXCPL_REG);
+			break;
+		}
+
+		udelay(5);
+	}
+
+	/* SOP detection failed, return error */
+	if (count == TLP_LOOP)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	count = 1;
+
+	/* Poll for EOP */
+	while (count < ARRAY_SIZE(dw)) {
+		ctrl = cra_readl(pcie, S10_RP_RXCPL_STATUS);
+		dw[count++] = cra_readl(pcie, S10_RP_RXCPL_REG);
+		if (ctrl & RP_RXCPL_EOP) {
+			comp_status = TLP_COMP_STATUS(dw[1]);
+			if (comp_status)
+				return PCIBIOS_DEVICE_NOT_FOUND;
+
+			if (value && TLP_BYTE_COUNT(dw[1]) == sizeof(u32) &&
+			    count == 4)
+				*value = dw[3];
+
+			return PCIBIOS_SUCCESSFUL;
+		}
+	}
+
+	dev_warn(dev, "Malformed TLP packet\n");
+
+	return PCIBIOS_DEVICE_NOT_FOUND;
+}
+
 static void tlp_write_packet(struct altera_pcie *pcie, u32 *headers,
 			     u32 data, bool align)
 {
@@ -210,18 +310,44 @@
 	tlp_write_tx(pcie, &tlp_rp_regdata);
 }
 
+static void s10_tlp_write_packet(struct altera_pcie *pcie, u32 *headers,
+				 u32 data, bool dummy)
+{
+	s10_tlp_write_tx(pcie, headers[0], RP_TX_SOP);
+	s10_tlp_write_tx(pcie, headers[1], 0);
+	s10_tlp_write_tx(pcie, headers[2], 0);
+	s10_tlp_write_tx(pcie, data, RP_TX_EOP);
+}
+
+static void get_tlp_header(struct altera_pcie *pcie, u8 bus, u32 devfn,
+			   int where, u8 byte_en, bool read, u32 *headers)
+{
+	u8 cfg;
+	u8 cfg0 = read ? pcie->pcie_data->cfgrd0 : pcie->pcie_data->cfgwr0;
+	u8 cfg1 = read ? pcie->pcie_data->cfgrd1 : pcie->pcie_data->cfgwr1;
+	u8 tag = read ? TLP_READ_TAG : TLP_WRITE_TAG;
+
+	if (pcie->pcie_data->version == ALTERA_PCIE_V1)
+		cfg = (bus == pcie->root_bus_nr) ? cfg0 : cfg1;
+	else
+		cfg = (bus > S10_RP_SECONDARY(pcie)) ? cfg0 : cfg1;
+
+	headers[0] = TLP_CFG_DW0(pcie, cfg);
+	headers[1] = TLP_CFG_DW1(pcie, tag, byte_en);
+	headers[2] = TLP_CFG_DW2(bus, devfn, where);
+}
+
 static int tlp_cfg_dword_read(struct altera_pcie *pcie, u8 bus, u32 devfn,
 			      int where, u8 byte_en, u32 *value)
 {
 	u32 headers[TLP_HDR_SIZE];
 
-	headers[0] = TLP_CFGRD_DW0(pcie, bus);
-	headers[1] = TLP_CFG_DW1(pcie, TLP_READ_TAG, byte_en);
-	headers[2] = TLP_CFG_DW2(bus, devfn, where);
+	get_tlp_header(pcie, bus, devfn, where, byte_en, true,
+		       headers);
 
-	tlp_write_packet(pcie, headers, 0, false);
+	pcie->pcie_data->ops->tlp_write_pkt(pcie, headers, 0, false);
 
-	return tlp_read_packet(pcie, value);
+	return pcie->pcie_data->ops->tlp_read_pkt(pcie, value);
 }
 
 static int tlp_cfg_dword_write(struct altera_pcie *pcie, u8 bus, u32 devfn,
@@ -230,17 +356,18 @@
 	u32 headers[TLP_HDR_SIZE];
 	int ret;
 
-	headers[0] = TLP_CFGWR_DW0(pcie, bus);
-	headers[1] = TLP_CFG_DW1(pcie, TLP_WRITE_TAG, byte_en);
-	headers[2] = TLP_CFG_DW2(bus, devfn, where);
+	get_tlp_header(pcie, bus, devfn, where, byte_en, false,
+		       headers);
 
 	/* check alignment to Qword */
 	if ((where & 0x7) == 0)
-		tlp_write_packet(pcie, headers, value, true);
+		pcie->pcie_data->ops->tlp_write_pkt(pcie, headers,
+						    value, true);
 	else
-		tlp_write_packet(pcie, headers, value, false);
+		pcie->pcie_data->ops->tlp_write_pkt(pcie, headers,
+						    value, false);
 
-	ret = tlp_read_packet(pcie, NULL);
+	ret = pcie->pcie_data->ops->tlp_read_pkt(pcie, NULL);
 	if (ret != PCIBIOS_SUCCESSFUL)
 		return ret;
 
@@ -254,6 +381,53 @@
 	return PCIBIOS_SUCCESSFUL;
 }
 
+static int s10_rp_read_cfg(struct altera_pcie *pcie, int where,
+			   int size, u32 *value)
+{
+	void __iomem *addr = S10_RP_CFG_ADDR(pcie, where);
+
+	switch (size) {
+	case 1:
+		*value = readb(addr);
+		break;
+	case 2:
+		*value = readw(addr);
+		break;
+	default:
+		*value = readl(addr);
+		break;
+	}
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int s10_rp_write_cfg(struct altera_pcie *pcie, u8 busno,
+			    int where, int size, u32 value)
+{
+	void __iomem *addr = S10_RP_CFG_ADDR(pcie, where);
+
+	switch (size) {
+	case 1:
+		writeb(value, addr);
+		break;
+	case 2:
+		writew(value, addr);
+		break;
+	default:
+		writel(value, addr);
+		break;
+	}
+
+	/*
+	 * Monitor changes to PCI_PRIMARY_BUS register on root port
+	 * and update local copy of root bus number accordingly.
+	 */
+	if (busno == pcie->root_bus_nr && where == PCI_PRIMARY_BUS)
+		pcie->root_bus_nr = value & 0xff;
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
 static int _altera_pcie_cfg_read(struct altera_pcie *pcie, u8 busno,
 				 unsigned int devfn, int where, int size,
 				 u32 *value)
@@ -262,6 +436,10 @@
 	u32 data;
 	u8 byte_en;
 
+	if (busno == pcie->root_bus_nr && pcie->pcie_data->ops->rp_read_cfg)
+		return pcie->pcie_data->ops->rp_read_cfg(pcie, where,
+							 size, value);
+
 	switch (size) {
 	case 1:
 		byte_en = 1 << (where & 3);
@@ -302,6 +480,10 @@
 	u32 shift = 8 * (where & 3);
 	u8 byte_en;
 
+	if (busno == pcie->root_bus_nr && pcie->pcie_data->ops->rp_write_cfg)
+		return pcie->pcie_data->ops->rp_write_cfg(pcie, busno,
+						     where, size, value);
+
 	switch (size) {
 	case 1:
 		data32 = (value & 0xff) << shift;
@@ -365,7 +547,8 @@
 	int ret;
 
 	ret = _altera_pcie_cfg_read(pcie, busno, devfn,
-				    PCIE_CAP_OFFSET + offset, sizeof(*value),
+				    pcie->pcie_data->cap_offset + offset,
+				    sizeof(*value),
 				    &data);
 	*value = data;
 	return ret;
@@ -375,7 +558,8 @@
 				 unsigned int devfn, int offset, u16 value)
 {
 	return _altera_pcie_cfg_write(pcie, busno, devfn,
-				      PCIE_CAP_OFFSET + offset, sizeof(value),
+				      pcie->pcie_data->cap_offset + offset,
+				      sizeof(value),
 				      value);
 }
 
@@ -403,7 +587,7 @@
 	/* Wait for link is up */
 	start_jiffies = jiffies;
 	for (;;) {
-		if (altera_pcie_link_up(pcie))
+		if (pcie->pcie_data->ops->get_link_status(pcie))
 			break;
 
 		if (time_after(jiffies, start_jiffies + LINK_UP_TIMEOUT)) {
@@ -418,7 +602,7 @@
 {
 	u16 linkcap, linkstat, linkctl;
 
-	if (!altera_pcie_link_up(pcie))
+	if (!pcie->pcie_data->ops->get_link_status(pcie))
 		return;
 
 	/*
@@ -535,17 +719,32 @@
 	return 0;
 }
 
+static void altera_pcie_irq_teardown(struct altera_pcie *pcie)
+{
+	irq_set_chained_handler_and_data(pcie->irq, NULL, NULL);
+	irq_domain_remove(pcie->irq_domain);
+	irq_dispose_mapping(pcie->irq);
+}
+
 static int altera_pcie_parse_dt(struct altera_pcie *pcie)
 {
 	struct device *dev = &pcie->pdev->dev;
 	struct platform_device *pdev = pcie->pdev;
 	struct resource *cra;
+	struct resource *hip;
 
 	cra = platform_get_resource_byname(pdev, IORESOURCE_MEM, "Cra");
 	pcie->cra_base = devm_ioremap_resource(dev, cra);
 	if (IS_ERR(pcie->cra_base))
 		return PTR_ERR(pcie->cra_base);
 
+	if (pcie->pcie_data->version == ALTERA_PCIE_V2) {
+		hip = platform_get_resource_byname(pdev, IORESOURCE_MEM, "Hip");
+		pcie->hip_base = devm_ioremap_resource(&pdev->dev, hip);
+		if (IS_ERR(pcie->hip_base))
+			return PTR_ERR(pcie->hip_base);
+	}
+
 	/* setup IRQ */
 	pcie->irq = platform_get_irq(pdev, 0);
 	if (pcie->irq < 0) {
@@ -562,6 +761,48 @@
 	altera_pcie_retrain(pcie);
 }
 
+static const struct altera_pcie_ops altera_pcie_ops_1_0 = {
+	.tlp_read_pkt = tlp_read_packet,
+	.tlp_write_pkt = tlp_write_packet,
+	.get_link_status = altera_pcie_link_up,
+};
+
+static const struct altera_pcie_ops altera_pcie_ops_2_0 = {
+	.tlp_read_pkt = s10_tlp_read_packet,
+	.tlp_write_pkt = s10_tlp_write_packet,
+	.get_link_status = s10_altera_pcie_link_up,
+	.rp_read_cfg = s10_rp_read_cfg,
+	.rp_write_cfg = s10_rp_write_cfg,
+};
+
+static const struct altera_pcie_data altera_pcie_1_0_data = {
+	.ops = &altera_pcie_ops_1_0,
+	.cap_offset = 0x80,
+	.version = ALTERA_PCIE_V1,
+	.cfgrd0 = TLP_FMTTYPE_CFGRD0,
+	.cfgrd1 = TLP_FMTTYPE_CFGRD1,
+	.cfgwr0 = TLP_FMTTYPE_CFGWR0,
+	.cfgwr1 = TLP_FMTTYPE_CFGWR1,
+};
+
+static const struct altera_pcie_data altera_pcie_2_0_data = {
+	.ops = &altera_pcie_ops_2_0,
+	.version = ALTERA_PCIE_V2,
+	.cap_offset = 0x70,
+	.cfgrd0 = S10_TLP_FMTTYPE_CFGRD0,
+	.cfgrd1 = S10_TLP_FMTTYPE_CFGRD1,
+	.cfgwr0 = S10_TLP_FMTTYPE_CFGWR0,
+	.cfgwr1 = S10_TLP_FMTTYPE_CFGWR1,
+};
+
+static const struct of_device_id altera_pcie_of_match[] = {
+	{.compatible = "altr,pcie-root-port-1.0",
+	 .data = &altera_pcie_1_0_data },
+	{.compatible = "altr,pcie-root-port-2.0",
+	 .data = &altera_pcie_2_0_data },
+	{},
+};
+
 static int altera_pcie_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -570,6 +811,7 @@
 	struct pci_bus *child;
 	struct pci_host_bridge *bridge;
 	int ret;
+	const struct of_device_id *match;
 
 	bridge = devm_pci_alloc_host_bridge(dev, sizeof(*pcie));
 	if (!bridge)
@@ -577,6 +819,13 @@
 
 	pcie = pci_host_bridge_priv(bridge);
 	pcie->pdev = pdev;
+	platform_set_drvdata(pdev, pcie);
+
+	match = of_match_device(altera_pcie_of_match, &pdev->dev);
+	if (!match)
+		return -ENODEV;
+
+	pcie->pcie_data = match->data;
 
 	ret = altera_pcie_parse_dt(pcie);
 	if (ret) {
@@ -628,18 +877,28 @@
 	return ret;
 }
 
-static const struct of_device_id altera_pcie_of_match[] = {
-	{ .compatible = "altr,pcie-root-port-1.0", },
-	{},
-};
+static int altera_pcie_remove(struct platform_device *pdev)
+{
+	struct altera_pcie *pcie = platform_get_drvdata(pdev);
+	struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie);
+
+	pci_stop_root_bus(bridge->bus);
+	pci_remove_root_bus(bridge->bus);
+	pci_free_resource_list(&pcie->resources);
+	altera_pcie_irq_teardown(pcie);
+
+	return 0;
+}
 
 static struct platform_driver altera_pcie_driver = {
 	.probe		= altera_pcie_probe,
+	.remove		= altera_pcie_remove,
 	.driver = {
 		.name	= "altera-pcie",
 		.of_match_table = altera_pcie_of_match,
-		.suppress_bind_attrs = true,
 	},
 };
 
-builtin_platform_driver(altera_pcie_driver);
+MODULE_DEVICE_TABLE(of, altera_pcie_of_match);
+module_platform_driver(altera_pcie_driver);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/controller/pcie-cadence-ep.c b/drivers/pci/controller/pcie-cadence-ep.c
index 6692654..def7820 100644
--- a/drivers/pci/controller/pcie-cadence-ep.c
+++ b/drivers/pci/controller/pcie-cadence-ep.c
@@ -355,7 +355,7 @@
 		ep->irq_pci_addr = (pci_addr & ~pci_addr_mask);
 		ep->irq_pci_fn = fn;
 	}
-	writew(data, ep->irq_cpu_addr + (pci_addr & pci_addr_mask));
+	writel(data, ep->irq_cpu_addr + (pci_addr & pci_addr_mask));
 
 	return 0;
 }
@@ -396,21 +396,21 @@
 		cfg |= BIT(epf->func_no);
 	cdns_pcie_writel(pcie, CDNS_PCIE_LM_EP_FUNC_CFG, cfg);
 
-	/*
-	 * The PCIe links are automatically established by the controller
-	 * once for all at powerup: the software can neither start nor stop
-	 * those links later at runtime.
-	 *
-	 * Then we only have to notify the EP core that our links are already
-	 * established. However we don't call directly pci_epc_linkup() because
-	 * we've already locked the epc->lock.
-	 */
-	list_for_each_entry(epf, &epc->pci_epf, list)
-		pci_epf_linkup(epf);
-
 	return 0;
 }
 
+static const struct pci_epc_features cdns_pcie_epc_features = {
+	.linkup_notifier = false,
+	.msi_capable = true,
+	.msix_capable = false,
+};
+
+static const struct pci_epc_features*
+cdns_pcie_ep_get_features(struct pci_epc *epc, u8 func_no)
+{
+	return &cdns_pcie_epc_features;
+}
+
 static const struct pci_epc_ops cdns_pcie_epc_ops = {
 	.write_header	= cdns_pcie_ep_write_header,
 	.set_bar	= cdns_pcie_ep_set_bar,
@@ -421,6 +421,7 @@
 	.get_msi	= cdns_pcie_ep_get_msi,
 	.raise_irq	= cdns_pcie_ep_raise_irq,
 	.start		= cdns_pcie_ep_start,
+	.get_features	= cdns_pcie_ep_get_features,
 };
 
 static const struct of_device_id cdns_pcie_ep_of_match[] = {
diff --git a/drivers/pci/controller/pcie-cadence-host.c b/drivers/pci/controller/pcie-cadence-host.c
index ec394f6..97e2510 100644
--- a/drivers/pci/controller/pcie-cadence-host.c
+++ b/drivers/pci/controller/pcie-cadence-host.c
@@ -235,7 +235,6 @@
 
 static int cdns_pcie_host_probe(struct platform_device *pdev)
 {
-	const char *type;
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
 	struct pci_host_bridge *bridge;
@@ -268,12 +267,6 @@
 	rc->device_id = 0xffff;
 	of_property_read_u16(np, "device-id", &rc->device_id);
 
-	type = of_get_property(np, "device_type", NULL);
-	if (!type || strcmp(type, "pci")) {
-		dev_err(dev, "invalid \"device_type\" %s\n", type);
-		return -EINVAL;
-	}
-
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "reg");
 	pcie->reg_base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(pcie->reg_base)) {
diff --git a/drivers/pci/controller/pcie-iproc-msi.c b/drivers/pci/controller/pcie-iproc-msi.c
index 9deb569..0a3f61b 100644
--- a/drivers/pci/controller/pcie-iproc-msi.c
+++ b/drivers/pci/controller/pcie-iproc-msi.c
@@ -367,7 +367,7 @@
 
 		/*
 		 * Now go read the tail pointer again to see if there are new
-		 * oustanding events that came in during the above window.
+		 * outstanding events that came in during the above window.
 		 */
 	} while (true);
 
@@ -602,9 +602,9 @@
 	}
 
 	/* Reserve memory for event queue and make sure memories are zeroed */
-	msi->eq_cpu = dma_zalloc_coherent(pcie->dev,
-					  msi->nr_eq_region * EQ_MEM_REGION_SIZE,
-					  &msi->eq_dma, GFP_KERNEL);
+	msi->eq_cpu = dma_alloc_coherent(pcie->dev,
+					 msi->nr_eq_region * EQ_MEM_REGION_SIZE,
+					 &msi->eq_dma, GFP_KERNEL);
 	if (!msi->eq_cpu) {
 		ret = -ENOMEM;
 		goto free_irqs;
diff --git a/drivers/pci/controller/pcie-iproc-platform.c b/drivers/pci/controller/pcie-iproc-platform.c
index f30f5f3..9ee6200 100644
--- a/drivers/pci/controller/pcie-iproc-platform.c
+++ b/drivers/pci/controller/pcie-iproc-platform.c
@@ -87,18 +87,15 @@
 
 	/*
 	 * DT nodes are not used by all platforms that use the iProc PCIe
-	 * core driver. For platforms that require explict inbound mapping
+	 * core driver. For platforms that require explicit inbound mapping
 	 * configuration, "dma-ranges" would have been present in DT
 	 */
 	pcie->need_ib_cfg = of_property_read_bool(np, "dma-ranges");
 
 	/* PHY use is optional */
-	pcie->phy = devm_phy_get(dev, "pcie-phy");
-	if (IS_ERR(pcie->phy)) {
-		if (PTR_ERR(pcie->phy) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
-		pcie->phy = NULL;
-	}
+	pcie->phy = devm_phy_optional_get(dev, "pcie-phy");
+	if (IS_ERR(pcie->phy))
+		return PTR_ERR(pcie->phy);
 
 	ret = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff, &resources,
 						    &iobase);
diff --git a/drivers/pci/controller/pcie-iproc.c b/drivers/pci/controller/pcie-iproc.c
index 3160e93..2d457bf 100644
--- a/drivers/pci/controller/pcie-iproc.c
+++ b/drivers/pci/controller/pcie-iproc.c
@@ -60,6 +60,10 @@
 #define APB_ERR_EN_SHIFT		0
 #define APB_ERR_EN			BIT(APB_ERR_EN_SHIFT)
 
+#define CFG_RD_SUCCESS			0
+#define CFG_RD_UR			1
+#define CFG_RD_CRS			2
+#define CFG_RD_CA			3
 #define CFG_RETRY_STATUS		0xffff0001
 #define CFG_RETRY_STATUS_TIMEOUT_US	500000 /* 500 milliseconds */
 
@@ -159,7 +163,7 @@
  * @size_unit: inbound mapping region size unit, could be SZ_1K, SZ_1M, or
  * SZ_1G
  * @region_sizes: list of supported inbound mapping region sizes in KB, MB, or
- * GB, depedning on the size unit
+ * GB, depending on the size unit
  * @nr_sizes: number of supported inbound mapping region sizes
  * @nr_windows: number of supported inbound mapping windows for the region
  * @imap_addr_offset: register offset between the upper and lower 32-bit
@@ -289,6 +293,9 @@
 	IPROC_PCIE_IARR4,
 	IPROC_PCIE_IMAP4,
 
+	/* config read status */
+	IPROC_PCIE_CFG_RD_STATUS,
+
 	/* link status */
 	IPROC_PCIE_LINK_STATUS,
 
@@ -350,6 +357,7 @@
 	[IPROC_PCIE_IMAP3]		= 0xe08,
 	[IPROC_PCIE_IARR4]		= 0xe68,
 	[IPROC_PCIE_IMAP4]		= 0xe70,
+	[IPROC_PCIE_CFG_RD_STATUS]	= 0xee0,
 	[IPROC_PCIE_LINK_STATUS]	= 0xf0c,
 	[IPROC_PCIE_APB_ERR_EN]		= 0xf40,
 };
@@ -474,10 +482,12 @@
 	return (pcie->base + offset);
 }
 
-static unsigned int iproc_pcie_cfg_retry(void __iomem *cfg_data_p)
+static unsigned int iproc_pcie_cfg_retry(struct iproc_pcie *pcie,
+					 void __iomem *cfg_data_p)
 {
 	int timeout = CFG_RETRY_STATUS_TIMEOUT_US;
 	unsigned int data;
+	u32 status;
 
 	/*
 	 * As per PCIe spec r3.1, sec 2.3.2, CRS Software Visibility only
@@ -498,6 +508,15 @@
 	 */
 	data = readl(cfg_data_p);
 	while (data == CFG_RETRY_STATUS && timeout--) {
+		/*
+		 * CRS state is set in CFG_RD status register
+		 * This will handle the case where CFG_RETRY_STATUS is
+		 * valid config data.
+		 */
+		status = iproc_pcie_read_reg(pcie, IPROC_PCIE_CFG_RD_STATUS);
+		if (status != CFG_RD_CRS)
+			return data;
+
 		udelay(1);
 		data = readl(cfg_data_p);
 	}
@@ -576,7 +595,7 @@
 	if (!cfg_data_p)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
-	data = iproc_pcie_cfg_retry(cfg_data_p);
+	data = iproc_pcie_cfg_retry(pcie, cfg_data_p);
 
 	*val = data;
 	if (size <= 2)
@@ -630,14 +649,6 @@
 			return (pcie->base + offset);
 	}
 
-	/*
-	 * PAXC is connected to an internally emulated EP within the SoC.  It
-	 * allows only one device.
-	 */
-	if (pcie->ep_is_internal)
-		if (slot > 0)
-			return NULL;
-
 	return iproc_pcie_map_ep_cfg_reg(pcie, busno, slot, fn, where);
 }
 
@@ -944,8 +955,25 @@
 			resource_size_t window_size =
 				ob_map->window_sizes[size_idx] * SZ_1M;
 
-			if (size < window_size)
-				continue;
+			/*
+			 * Keep iterating until we reach the last window and
+			 * with the minimal window size at index zero. In this
+			 * case, we take a compromise by mapping it using the
+			 * minimum window size that can be supported
+			 */
+			if (size < window_size) {
+				if (size_idx > 0 || window_idx > 0)
+					continue;
+
+				/*
+				 * For the corner case of reaching the minimal
+				 * window size that can be supported on the
+				 * last window
+				 */
+				axi_addr = ALIGN_DOWN(axi_addr, window_size);
+				pci_addr = ALIGN_DOWN(pci_addr, window_size);
+				size = window_size;
+			}
 
 			if (!IS_ALIGNED(axi_addr, window_size) ||
 			    !IS_ALIGNED(pci_addr, window_size)) {
@@ -1154,11 +1182,43 @@
 	return ret;
 }
 
+static int iproc_pcie_add_dma_range(struct device *dev,
+				    struct list_head *resources,
+				    struct of_pci_range *range)
+{
+	struct resource *res;
+	struct resource_entry *entry, *tmp;
+	struct list_head *head = resources;
+
+	res = devm_kzalloc(dev, sizeof(struct resource), GFP_KERNEL);
+	if (!res)
+		return -ENOMEM;
+
+	resource_list_for_each_entry(tmp, resources) {
+		if (tmp->res->start < range->cpu_addr)
+			head = &tmp->node;
+	}
+
+	res->start = range->cpu_addr;
+	res->end = res->start + range->size - 1;
+
+	entry = resource_list_create_entry(res, 0);
+	if (!entry)
+		return -ENOMEM;
+
+	entry->offset = res->start - range->cpu_addr;
+	resource_list_add(entry, head);
+
+	return 0;
+}
+
 static int iproc_pcie_map_dma_ranges(struct iproc_pcie *pcie)
 {
+	struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie);
 	struct of_pci_range range;
 	struct of_pci_range_parser parser;
 	int ret;
+	LIST_HEAD(resources);
 
 	/* Get the dma-ranges from DT */
 	ret = of_pci_dma_range_parser_init(&parser, pcie->dev->of_node);
@@ -1166,13 +1226,23 @@
 		return ret;
 
 	for_each_of_pci_range(&parser, &range) {
+		ret = iproc_pcie_add_dma_range(pcie->dev,
+					       &resources,
+					       &range);
+		if (ret)
+			goto out;
 		/* Each range entry corresponds to an inbound mapping region */
 		ret = iproc_pcie_setup_ib(pcie, &range, IPROC_PCIE_IB_MAP_MEM);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
+	list_splice_init(&resources, &host->dma_ranges);
+
 	return 0;
+out:
+	pci_free_resource_list(&resources);
+	return ret;
 }
 
 static int iproce_pcie_get_msi(struct iproc_pcie *pcie,
@@ -1328,14 +1398,18 @@
 	if (pcie->need_msi_steer) {
 		ret = iproc_pcie_msi_steer(pcie, msi_node);
 		if (ret)
-			return ret;
+			goto out_put_node;
 	}
 
 	/*
 	 * If another MSI controller is being used, the call below should fail
 	 * but that is okay
 	 */
-	return iproc_msi_init(pcie, msi_node);
+	ret = iproc_msi_init(pcie, msi_node);
+
+out_put_node:
+	of_node_put(msi_node);
+	return ret;
 }
 
 static void iproc_pcie_msi_disable(struct iproc_pcie *pcie)
@@ -1355,7 +1429,6 @@
 		break;
 	case IPROC_PCIE_PAXB:
 		regs = iproc_pcie_reg_paxb;
-		pcie->iproc_cfg_read = true;
 		pcie->has_apb_err_disable = true;
 		if (pcie->need_ob_cfg) {
 			pcie->ob_map = paxb_ob_map;
@@ -1364,6 +1437,7 @@
 		break;
 	case IPROC_PCIE_PAXB_V2:
 		regs = iproc_pcie_reg_paxb_v2;
+		pcie->iproc_cfg_read = true;
 		pcie->has_apb_err_disable = true;
 		if (pcie->need_ob_cfg) {
 			pcie->ob_map = paxb_v2_ob_map;
diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c
index c5ff6ca..626a7c3 100644
--- a/drivers/pci/controller/pcie-mediatek.c
+++ b/drivers/pci/controller/pcie-mediatek.c
@@ -15,6 +15,7 @@
 #include <linux/irqdomain.h>
 #include <linux/kernel.h>
 #include <linux/msi.h>
+#include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/of_pci.h>
 #include <linux/of_platform.h>
@@ -72,6 +73,7 @@
 #define PCIE_MSI_VECTOR		0x0c0
 
 #define PCIE_CONF_VEND_ID	0x100
+#define PCIE_CONF_DEVICE_ID	0x102
 #define PCIE_CONF_CLASS_ID	0x106
 
 #define PCIE_INT_MASK		0x420
@@ -89,6 +91,12 @@
 #define AHB2PCIE_SIZE(x)	((x) & GENMASK(4, 0))
 #define PCIE_AXI_WINDOW0	0x448
 #define WIN_ENABLE		BIT(7)
+/*
+ * Define PCIe to AHB window size as 2^33 to support max 8GB address space
+ * translate, support least 4GB DRAM size access from EP DMA(physical DRAM
+ * start from 0x40000000).
+ */
+#define PCIE2AHB_SIZE	0x21
 
 /* PCIe V2 configuration transaction header */
 #define PCIE_CFG_HEADER0	0x460
@@ -134,12 +142,16 @@
 /**
  * struct mtk_pcie_soc - differentiate between host generations
  * @need_fix_class_id: whether this host's class ID needed to be fixed or not
+ * @need_fix_device_id: whether this host's device ID needed to be fixed or not
+ * @device_id: device ID which this host need to be fixed
  * @ops: pointer to configuration access functions
  * @startup: pointer to controller setting functions
  * @setup_irq: pointer to initialize IRQ functions
  */
 struct mtk_pcie_soc {
 	bool need_fix_class_id;
+	bool need_fix_device_id;
+	unsigned int device_id;
 	struct pci_ops *ops;
 	int (*startup)(struct mtk_pcie_port *port);
 	int (*setup_irq)(struct mtk_pcie_port *port, struct device_node *node);
@@ -160,8 +172,8 @@
  * @obff_ck: pointer to OBFF functional block operating clock
  * @pipe_ck: pointer to LTSSM and PHY/MAC layer operating clock
  * @phy: pointer to PHY control block
- * @lane: lane count
  * @slot: port slot
+ * @irq: GIC irq
  * @irq_domain: legacy INTx IRQ domain
  * @inner_domain: inner IRQ domain
  * @msi_domain: MSI IRQ domain
@@ -180,8 +192,8 @@
 	struct clk *obff_ck;
 	struct clk *pipe_ck;
 	struct phy *phy;
-	u32 lane;
 	u32 slot;
+	int irq;
 	struct irq_domain *irq_domain;
 	struct irq_domain *inner_domain;
 	struct irq_domain *msi_domain;
@@ -194,29 +206,20 @@
  * @dev: pointer to PCIe device
  * @base: IO mapped register base
  * @free_ck: free-run reference clock
- * @io: IO resource
- * @pio: PIO resource
  * @mem: non-prefetchable memory resource
- * @busn: bus range
- * @offset: IO / Memory offset
  * @ports: pointer to PCIe port information
  * @soc: pointer to SoC-dependent operations
+ * @busnr: root bus number
  */
 struct mtk_pcie {
 	struct device *dev;
 	void __iomem *base;
 	struct clk *free_ck;
 
-	struct resource io;
-	struct resource pio;
 	struct resource mem;
-	struct resource busn;
-	struct {
-		resource_size_t mem;
-		resource_size_t io;
-	} offset;
 	struct list_head ports;
 	const struct mtk_pcie_soc *soc;
+	unsigned int busnr;
 };
 
 static void mtk_pcie_subsys_powerdown(struct mtk_pcie *pcie)
@@ -225,10 +228,8 @@
 
 	clk_disable_unprepare(pcie->free_ck);
 
-	if (dev->pm_domain) {
-		pm_runtime_put_sync(dev);
-		pm_runtime_disable(dev);
-	}
+	pm_runtime_put_sync(dev);
+	pm_runtime_disable(dev);
 }
 
 static void mtk_pcie_port_free(struct mtk_pcie_port *port)
@@ -394,75 +395,6 @@
 	.write = mtk_pcie_config_write,
 };
 
-static int mtk_pcie_startup_port_v2(struct mtk_pcie_port *port)
-{
-	struct mtk_pcie *pcie = port->pcie;
-	struct resource *mem = &pcie->mem;
-	const struct mtk_pcie_soc *soc = port->pcie->soc;
-	u32 val;
-	size_t size;
-	int err;
-
-	/* MT7622 platforms need to enable LTSSM and ASPM from PCIe subsys */
-	if (pcie->base) {
-		val = readl(pcie->base + PCIE_SYS_CFG_V2);
-		val |= PCIE_CSR_LTSSM_EN(port->slot) |
-		       PCIE_CSR_ASPM_L1_EN(port->slot);
-		writel(val, pcie->base + PCIE_SYS_CFG_V2);
-	}
-
-	/* Assert all reset signals */
-	writel(0, port->base + PCIE_RST_CTRL);
-
-	/*
-	 * Enable PCIe link down reset, if link status changed from link up to
-	 * link down, this will reset MAC control registers and configuration
-	 * space.
-	 */
-	writel(PCIE_LINKDOWN_RST_EN, port->base + PCIE_RST_CTRL);
-
-	/* De-assert PHY, PE, PIPE, MAC and configuration reset	*/
-	val = readl(port->base + PCIE_RST_CTRL);
-	val |= PCIE_PHY_RSTB | PCIE_PERSTB | PCIE_PIPE_SRSTB |
-	       PCIE_MAC_SRSTB | PCIE_CRSTB;
-	writel(val, port->base + PCIE_RST_CTRL);
-
-	/* Set up vendor ID and class code */
-	if (soc->need_fix_class_id) {
-		val = PCI_VENDOR_ID_MEDIATEK;
-		writew(val, port->base + PCIE_CONF_VEND_ID);
-
-		val = PCI_CLASS_BRIDGE_HOST;
-		writew(val, port->base + PCIE_CONF_CLASS_ID);
-	}
-
-	/* 100ms timeout value should be enough for Gen1/2 training */
-	err = readl_poll_timeout(port->base + PCIE_LINK_STATUS_V2, val,
-				 !!(val & PCIE_PORT_LINKUP_V2), 20,
-				 100 * USEC_PER_MSEC);
-	if (err)
-		return -ETIMEDOUT;
-
-	/* Set INTx mask */
-	val = readl(port->base + PCIE_INT_MASK);
-	val &= ~INTX_MASK;
-	writel(val, port->base + PCIE_INT_MASK);
-
-	/* Set AHB to PCIe translation windows */
-	size = mem->end - mem->start;
-	val = lower_32_bits(mem->start) | AHB2PCIE_SIZE(fls(size));
-	writel(val, port->base + PCIE_AHB_TRANS_BASE0_L);
-
-	val = upper_32_bits(mem->start);
-	writel(val, port->base + PCIE_AHB_TRANS_BASE0_H);
-
-	/* Set PCIe to AXI translation memory space.*/
-	val = fls(0xffffffff) | WIN_ENABLE;
-	writel(val, port->base + PCIE_AXI_WINDOW0);
-
-	return 0;
-}
-
 static void mtk_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 {
 	struct mtk_pcie_port *port = irq_data_get_irq_chip_data(data);
@@ -601,6 +533,27 @@
 	writel(val, port->base + PCIE_INT_MASK);
 }
 
+static void mtk_pcie_irq_teardown(struct mtk_pcie *pcie)
+{
+	struct mtk_pcie_port *port, *tmp;
+
+	list_for_each_entry_safe(port, tmp, &pcie->ports, list) {
+		irq_set_chained_handler_and_data(port->irq, NULL, NULL);
+
+		if (port->irq_domain)
+			irq_domain_remove(port->irq_domain);
+
+		if (IS_ENABLED(CONFIG_PCI_MSI)) {
+			if (port->msi_domain)
+				irq_domain_remove(port->msi_domain);
+			if (port->inner_domain)
+				irq_domain_remove(port->inner_domain);
+		}
+
+		irq_dispose_mapping(port->irq);
+	}
+}
+
 static int mtk_pcie_intx_map(struct irq_domain *domain, unsigned int irq,
 			     irq_hw_number_t hwirq)
 {
@@ -630,6 +583,7 @@
 
 	port->irq_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX,
 						 &intx_domain_ops, port);
+	of_node_put(pcie_intc_node);
 	if (!port->irq_domain) {
 		dev_err(dev, "failed to get INTx IRQ domain\n");
 		return -ENODEV;
@@ -639,8 +593,6 @@
 		ret = mtk_pcie_allocate_msi_domains(port);
 		if (ret)
 			return ret;
-
-		mtk_pcie_enable_msi(port);
 	}
 
 	return 0;
@@ -683,8 +635,6 @@
 	}
 
 	chained_irq_exit(irqchip, desc);
-
-	return;
 }
 
 static int mtk_pcie_setup_irq(struct mtk_pcie_port *port,
@@ -693,7 +643,7 @@
 	struct mtk_pcie *pcie = port->pcie;
 	struct device *dev = pcie->dev;
 	struct platform_device *pdev = to_platform_device(dev);
-	int err, irq;
+	int err;
 
 	err = mtk_pcie_init_irq_domain(port, node);
 	if (err) {
@@ -701,8 +651,83 @@
 		return err;
 	}
 
-	irq = platform_get_irq(pdev, port->slot);
-	irq_set_chained_handler_and_data(irq, mtk_pcie_intr_handler, port);
+	port->irq = platform_get_irq(pdev, port->slot);
+	irq_set_chained_handler_and_data(port->irq,
+					 mtk_pcie_intr_handler, port);
+
+	return 0;
+}
+
+static int mtk_pcie_startup_port_v2(struct mtk_pcie_port *port)
+{
+	struct mtk_pcie *pcie = port->pcie;
+	struct resource *mem = &pcie->mem;
+	const struct mtk_pcie_soc *soc = port->pcie->soc;
+	u32 val;
+	int err;
+
+	/* MT7622 platforms need to enable LTSSM and ASPM from PCIe subsys */
+	if (pcie->base) {
+		val = readl(pcie->base + PCIE_SYS_CFG_V2);
+		val |= PCIE_CSR_LTSSM_EN(port->slot) |
+		       PCIE_CSR_ASPM_L1_EN(port->slot);
+		writel(val, pcie->base + PCIE_SYS_CFG_V2);
+	}
+
+	/* Assert all reset signals */
+	writel(0, port->base + PCIE_RST_CTRL);
+
+	/*
+	 * Enable PCIe link down reset, if link status changed from link up to
+	 * link down, this will reset MAC control registers and configuration
+	 * space.
+	 */
+	writel(PCIE_LINKDOWN_RST_EN, port->base + PCIE_RST_CTRL);
+
+	/* De-assert PHY, PE, PIPE, MAC and configuration reset	*/
+	val = readl(port->base + PCIE_RST_CTRL);
+	val |= PCIE_PHY_RSTB | PCIE_PERSTB | PCIE_PIPE_SRSTB |
+	       PCIE_MAC_SRSTB | PCIE_CRSTB;
+	writel(val, port->base + PCIE_RST_CTRL);
+
+	/* Set up vendor ID and class code */
+	if (soc->need_fix_class_id) {
+		val = PCI_VENDOR_ID_MEDIATEK;
+		writew(val, port->base + PCIE_CONF_VEND_ID);
+
+		val = PCI_CLASS_BRIDGE_PCI;
+		writew(val, port->base + PCIE_CONF_CLASS_ID);
+	}
+
+	if (soc->need_fix_device_id)
+		writew(soc->device_id, port->base + PCIE_CONF_DEVICE_ID);
+
+	/* 100ms timeout value should be enough for Gen1/2 training */
+	err = readl_poll_timeout(port->base + PCIE_LINK_STATUS_V2, val,
+				 !!(val & PCIE_PORT_LINKUP_V2), 20,
+				 100 * USEC_PER_MSEC);
+	if (err)
+		return -ETIMEDOUT;
+
+	/* Set INTx mask */
+	val = readl(port->base + PCIE_INT_MASK);
+	val &= ~INTX_MASK;
+	writel(val, port->base + PCIE_INT_MASK);
+
+	if (IS_ENABLED(CONFIG_PCI_MSI))
+		mtk_pcie_enable_msi(port);
+
+	/* Set AHB to PCIe translation windows */
+	val = lower_32_bits(mem->start) |
+	      AHB2PCIE_SIZE(fls(resource_size(mem)));
+	writel(val, port->base + PCIE_AHB_TRANS_BASE0_L);
+
+	val = upper_32_bits(mem->start);
+	writel(val, port->base + PCIE_AHB_TRANS_BASE0_H);
+
+	/* Set PCIe to AXI translation memory space.*/
+	val = PCIE2AHB_SIZE | WIN_ENABLE;
+	writel(val, port->base + PCIE_AXI_WINDOW0);
 
 	return 0;
 }
@@ -880,12 +905,6 @@
 	if (!port)
 		return -ENOMEM;
 
-	err = of_property_read_u32(node, "num-lanes", &port->lane);
-	if (err) {
-		dev_err(dev, "missing num-lanes property\n");
-		return err;
-	}
-
 	snprintf(name, sizeof(name), "port%d", slot);
 	regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, name);
 	port->base = devm_ioremap_resource(dev, regs);
@@ -903,49 +922,29 @@
 
 	/* sys_ck might be divided into the following parts in some chips */
 	snprintf(name, sizeof(name), "ahb_ck%d", slot);
-	port->ahb_ck = devm_clk_get(dev, name);
-	if (IS_ERR(port->ahb_ck)) {
-		if (PTR_ERR(port->ahb_ck) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
-
-		port->ahb_ck = NULL;
-	}
+	port->ahb_ck = devm_clk_get_optional(dev, name);
+	if (IS_ERR(port->ahb_ck))
+		return PTR_ERR(port->ahb_ck);
 
 	snprintf(name, sizeof(name), "axi_ck%d", slot);
-	port->axi_ck = devm_clk_get(dev, name);
-	if (IS_ERR(port->axi_ck)) {
-		if (PTR_ERR(port->axi_ck) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
-
-		port->axi_ck = NULL;
-	}
+	port->axi_ck = devm_clk_get_optional(dev, name);
+	if (IS_ERR(port->axi_ck))
+		return PTR_ERR(port->axi_ck);
 
 	snprintf(name, sizeof(name), "aux_ck%d", slot);
-	port->aux_ck = devm_clk_get(dev, name);
-	if (IS_ERR(port->aux_ck)) {
-		if (PTR_ERR(port->aux_ck) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
-
-		port->aux_ck = NULL;
-	}
+	port->aux_ck = devm_clk_get_optional(dev, name);
+	if (IS_ERR(port->aux_ck))
+		return PTR_ERR(port->aux_ck);
 
 	snprintf(name, sizeof(name), "obff_ck%d", slot);
-	port->obff_ck = devm_clk_get(dev, name);
-	if (IS_ERR(port->obff_ck)) {
-		if (PTR_ERR(port->obff_ck) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
-
-		port->obff_ck = NULL;
-	}
+	port->obff_ck = devm_clk_get_optional(dev, name);
+	if (IS_ERR(port->obff_ck))
+		return PTR_ERR(port->obff_ck);
 
 	snprintf(name, sizeof(name), "pipe_ck%d", slot);
-	port->pipe_ck = devm_clk_get(dev, name);
-	if (IS_ERR(port->pipe_ck)) {
-		if (PTR_ERR(port->pipe_ck) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
-
-		port->pipe_ck = NULL;
-	}
+	port->pipe_ck = devm_clk_get_optional(dev, name);
+	if (IS_ERR(port->pipe_ck))
+		return PTR_ERR(port->pipe_ck);
 
 	snprintf(name, sizeof(name), "pcie-rst%d", slot);
 	port->reset = devm_reset_control_get_optional_exclusive(dev, name);
@@ -998,10 +997,8 @@
 		pcie->free_ck = NULL;
 	}
 
-	if (dev->pm_domain) {
-		pm_runtime_enable(dev);
-		pm_runtime_get_sync(dev);
-	}
+	pm_runtime_enable(dev);
+	pm_runtime_get_sync(dev);
 
 	/* enable top level clock */
 	err = clk_prepare_enable(pcie->free_ck);
@@ -1013,10 +1010,8 @@
 	return 0;
 
 err_free_ck:
-	if (dev->pm_domain) {
-		pm_runtime_put_sync(dev);
-		pm_runtime_disable(dev);
-	}
+	pm_runtime_put_sync(dev);
+	pm_runtime_disable(dev);
 
 	return err;
 }
@@ -1025,55 +1020,43 @@
 {
 	struct device *dev = pcie->dev;
 	struct device_node *node = dev->of_node, *child;
-	struct of_pci_range_parser parser;
-	struct of_pci_range range;
-	struct resource res;
 	struct mtk_pcie_port *port, *tmp;
+	struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie);
+	struct list_head *windows = &host->windows;
+	struct resource_entry *win, *tmp_win;
+	resource_size_t io_base;
 	int err;
 
-	if (of_pci_range_parser_init(&parser, node)) {
-		dev_err(dev, "missing \"ranges\" property\n");
-		return -EINVAL;
-	}
+	err = devm_of_pci_get_host_bridge_resources(dev, 0, 0xff,
+						    windows, &io_base);
+	if (err)
+		return err;
 
-	for_each_of_pci_range(&parser, &range) {
-		err = of_pci_range_to_resource(&range, node, &res);
-		if (err < 0)
-			return err;
+	err = devm_request_pci_bus_resources(dev, windows);
+	if (err < 0)
+		return err;
 
-		switch (res.flags & IORESOURCE_TYPE_BITS) {
+	/* Get the I/O and memory ranges from DT */
+	resource_list_for_each_entry_safe(win, tmp_win, windows) {
+		switch (resource_type(win->res)) {
 		case IORESOURCE_IO:
-			pcie->offset.io = res.start - range.pci_addr;
-
-			memcpy(&pcie->pio, &res, sizeof(res));
-			pcie->pio.name = node->full_name;
-
-			pcie->io.start = range.cpu_addr;
-			pcie->io.end = range.cpu_addr + range.size - 1;
-			pcie->io.flags = IORESOURCE_MEM;
-			pcie->io.name = "I/O";
-
-			memcpy(&res, &pcie->io, sizeof(res));
+			err = devm_pci_remap_iospace(dev, win->res, io_base);
+			if (err) {
+				dev_warn(dev, "error %d: failed to map resource %pR\n",
+					 err, win->res);
+				resource_list_destroy_entry(win);
+			}
 			break;
-
 		case IORESOURCE_MEM:
-			pcie->offset.mem = res.start - range.pci_addr;
-
-			memcpy(&pcie->mem, &res, sizeof(res));
+			memcpy(&pcie->mem, win->res, sizeof(*win->res));
 			pcie->mem.name = "non-prefetchable";
 			break;
+		case IORESOURCE_BUS:
+			pcie->busnr = win->res->start;
+			break;
 		}
 	}
 
-	err = of_pci_parse_bus_range(node, &pcie->busn);
-	if (err < 0) {
-		dev_err(dev, "failed to parse bus ranges property: %d\n", err);
-		pcie->busn.name = node->name;
-		pcie->busn.start = 0;
-		pcie->busn.end = 0xff;
-		pcie->busn.flags = IORESOURCE_BUS;
-	}
-
 	for_each_available_child_of_node(node, child) {
 		int slot;
 
@@ -1105,54 +1088,6 @@
 	return 0;
 }
 
-static int mtk_pcie_request_resources(struct mtk_pcie *pcie)
-{
-	struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie);
-	struct list_head *windows = &host->windows;
-	struct device *dev = pcie->dev;
-	int err;
-
-	pci_add_resource_offset(windows, &pcie->pio, pcie->offset.io);
-	pci_add_resource_offset(windows, &pcie->mem, pcie->offset.mem);
-	pci_add_resource(windows, &pcie->busn);
-
-	err = devm_request_pci_bus_resources(dev, windows);
-	if (err < 0)
-		return err;
-
-	devm_pci_remap_iospace(dev, &pcie->pio, pcie->io.start);
-
-	return 0;
-}
-
-static int mtk_pcie_register_host(struct pci_host_bridge *host)
-{
-	struct mtk_pcie *pcie = pci_host_bridge_priv(host);
-	struct pci_bus *child;
-	int err;
-
-	host->busnr = pcie->busn.start;
-	host->dev.parent = pcie->dev;
-	host->ops = pcie->soc->ops;
-	host->map_irq = of_irq_parse_and_map_pci;
-	host->swizzle_irq = pci_common_swizzle;
-	host->sysdata = pcie;
-
-	err = pci_scan_root_bus_bridge(host);
-	if (err < 0)
-		return err;
-
-	pci_bus_size_bridges(host->bus);
-	pci_bus_assign_resources(host->bus);
-
-	list_for_each_entry(child, &host->bus->children, node)
-		pcie_bus_configure_settings(child);
-
-	pci_bus_add_devices(host->bus);
-
-	return 0;
-}
-
 static int mtk_pcie_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -1175,11 +1110,14 @@
 	if (err)
 		return err;
 
-	err = mtk_pcie_request_resources(pcie);
-	if (err)
-		goto put_resources;
+	host->busnr = pcie->busnr;
+	host->dev.parent = pcie->dev;
+	host->ops = pcie->soc->ops;
+	host->map_irq = of_irq_parse_and_map_pci;
+	host->swizzle_irq = pci_common_swizzle;
+	host->sysdata = pcie;
 
-	err = mtk_pcie_register_host(host);
+	err = pci_host_probe(host);
 	if (err)
 		goto put_resources;
 
@@ -1192,6 +1130,80 @@
 	return err;
 }
 
+
+static void mtk_pcie_free_resources(struct mtk_pcie *pcie)
+{
+	struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie);
+	struct list_head *windows = &host->windows;
+
+	pci_free_resource_list(windows);
+}
+
+static int mtk_pcie_remove(struct platform_device *pdev)
+{
+	struct mtk_pcie *pcie = platform_get_drvdata(pdev);
+	struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie);
+
+	pci_stop_root_bus(host->bus);
+	pci_remove_root_bus(host->bus);
+	mtk_pcie_free_resources(pcie);
+
+	mtk_pcie_irq_teardown(pcie);
+
+	mtk_pcie_put_resources(pcie);
+
+	return 0;
+}
+
+static int __maybe_unused mtk_pcie_suspend_noirq(struct device *dev)
+{
+	struct mtk_pcie *pcie = dev_get_drvdata(dev);
+	struct mtk_pcie_port *port;
+
+	if (list_empty(&pcie->ports))
+		return 0;
+
+	list_for_each_entry(port, &pcie->ports, list) {
+		clk_disable_unprepare(port->pipe_ck);
+		clk_disable_unprepare(port->obff_ck);
+		clk_disable_unprepare(port->axi_ck);
+		clk_disable_unprepare(port->aux_ck);
+		clk_disable_unprepare(port->ahb_ck);
+		clk_disable_unprepare(port->sys_ck);
+		phy_power_off(port->phy);
+		phy_exit(port->phy);
+	}
+
+	clk_disable_unprepare(pcie->free_ck);
+
+	return 0;
+}
+
+static int __maybe_unused mtk_pcie_resume_noirq(struct device *dev)
+{
+	struct mtk_pcie *pcie = dev_get_drvdata(dev);
+	struct mtk_pcie_port *port, *tmp;
+
+	if (list_empty(&pcie->ports))
+		return 0;
+
+	clk_prepare_enable(pcie->free_ck);
+
+	list_for_each_entry_safe(port, tmp, &pcie->ports, list)
+		mtk_pcie_enable_port(port);
+
+	/* In case of EP was removed while system suspend. */
+	if (list_empty(&pcie->ports))
+		clk_disable_unprepare(pcie->free_ck);
+
+	return 0;
+}
+
+static const struct dev_pm_ops mtk_pcie_pm_ops = {
+	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(mtk_pcie_suspend_noirq,
+				      mtk_pcie_resume_noirq)
+};
+
 static const struct mtk_pcie_soc mtk_pcie_soc_v1 = {
 	.ops = &mtk_pcie_ops,
 	.startup = mtk_pcie_startup_port,
@@ -1210,20 +1222,33 @@
 	.setup_irq = mtk_pcie_setup_irq,
 };
 
+static const struct mtk_pcie_soc mtk_pcie_soc_mt7629 = {
+	.need_fix_class_id = true,
+	.need_fix_device_id = true,
+	.device_id = PCI_DEVICE_ID_MEDIATEK_7629,
+	.ops = &mtk_pcie_ops_v2,
+	.startup = mtk_pcie_startup_port_v2,
+	.setup_irq = mtk_pcie_setup_irq,
+};
+
 static const struct of_device_id mtk_pcie_ids[] = {
 	{ .compatible = "mediatek,mt2701-pcie", .data = &mtk_pcie_soc_v1 },
 	{ .compatible = "mediatek,mt7623-pcie", .data = &mtk_pcie_soc_v1 },
 	{ .compatible = "mediatek,mt2712-pcie", .data = &mtk_pcie_soc_mt2712 },
 	{ .compatible = "mediatek,mt7622-pcie", .data = &mtk_pcie_soc_mt7622 },
+	{ .compatible = "mediatek,mt7629-pcie", .data = &mtk_pcie_soc_mt7629 },
 	{},
 };
 
 static struct platform_driver mtk_pcie_driver = {
 	.probe = mtk_pcie_probe,
+	.remove = mtk_pcie_remove,
 	.driver = {
 		.name = "mtk-pcie",
 		.of_match_table = mtk_pcie_ids,
 		.suppress_bind_attrs = true,
+		.pm = &mtk_pcie_pm_ops,
 	},
 };
-builtin_platform_driver(mtk_pcie_driver);
+module_platform_driver(mtk_pcie_driver);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/controller/pcie-mobiveil.c b/drivers/pci/controller/pcie-mobiveil.c
index a939e8d..a45a644 100644
--- a/drivers/pci/controller/pcie-mobiveil.c
+++ b/drivers/pci/controller/pcie-mobiveil.c
@@ -31,91 +31,103 @@
  * translation tables are grouped into windows, each window registers are
  * grouped into blocks of 4 or 16 registers each
  */
-#define PAB_REG_BLOCK_SIZE	16
-#define PAB_EXT_REG_BLOCK_SIZE	4
+#define PAB_REG_BLOCK_SIZE		16
+#define PAB_EXT_REG_BLOCK_SIZE		4
 
-#define PAB_REG_ADDR(offset, win) (offset + (win * PAB_REG_BLOCK_SIZE))
-#define PAB_EXT_REG_ADDR(offset, win) (offset + (win * PAB_EXT_REG_BLOCK_SIZE))
+#define PAB_REG_ADDR(offset, win)	\
+	(offset + (win * PAB_REG_BLOCK_SIZE))
+#define PAB_EXT_REG_ADDR(offset, win)	\
+	(offset + (win * PAB_EXT_REG_BLOCK_SIZE))
 
-#define LTSSM_STATUS		0x0404
-#define  LTSSM_STATUS_L0_MASK	0x3f
-#define  LTSSM_STATUS_L0	0x2d
+#define LTSSM_STATUS			0x0404
+#define  LTSSM_STATUS_L0_MASK		0x3f
+#define  LTSSM_STATUS_L0		0x2d
 
-#define PAB_CTRL		0x0808
-#define  AMBA_PIO_ENABLE_SHIFT	0
-#define  PEX_PIO_ENABLE_SHIFT	1
-#define  PAGE_SEL_SHIFT	13
-#define  PAGE_SEL_MASK		0x3f
-#define  PAGE_LO_MASK		0x3ff
-#define  PAGE_SEL_EN		0xc00
-#define  PAGE_SEL_OFFSET_SHIFT	10
+#define PAB_CTRL			0x0808
+#define  AMBA_PIO_ENABLE_SHIFT		0
+#define  PEX_PIO_ENABLE_SHIFT		1
+#define  PAGE_SEL_SHIFT			13
+#define  PAGE_SEL_MASK			0x3f
+#define  PAGE_LO_MASK			0x3ff
+#define  PAGE_SEL_OFFSET_SHIFT		10
 
-#define PAB_AXI_PIO_CTRL	0x0840
-#define  APIO_EN_MASK		0xf
+#define PAB_AXI_PIO_CTRL		0x0840
+#define  APIO_EN_MASK			0xf
 
-#define PAB_PEX_PIO_CTRL	0x08c0
-#define  PIO_ENABLE_SHIFT	0
+#define PAB_PEX_PIO_CTRL		0x08c0
+#define  PIO_ENABLE_SHIFT		0
 
 #define PAB_INTP_AMBA_MISC_ENB		0x0b0c
-#define PAB_INTP_AMBA_MISC_STAT	0x0b1c
+#define PAB_INTP_AMBA_MISC_STAT		0x0b1c
 #define  PAB_INTP_INTX_MASK		0x01e0
 #define  PAB_INTP_MSI_MASK		0x8
 
-#define PAB_AXI_AMAP_CTRL(win)	PAB_REG_ADDR(0x0ba0, win)
-#define  WIN_ENABLE_SHIFT	0
-#define  WIN_TYPE_SHIFT	1
+#define PAB_AXI_AMAP_CTRL(win)		PAB_REG_ADDR(0x0ba0, win)
+#define  WIN_ENABLE_SHIFT		0
+#define  WIN_TYPE_SHIFT			1
+#define  WIN_TYPE_MASK			0x3
+#define  WIN_SIZE_MASK			0xfffffc00
 
 #define PAB_EXT_AXI_AMAP_SIZE(win)	PAB_EXT_REG_ADDR(0xbaf0, win)
 
+#define PAB_EXT_AXI_AMAP_AXI_WIN(win)	PAB_EXT_REG_ADDR(0x80a0, win)
 #define PAB_AXI_AMAP_AXI_WIN(win)	PAB_REG_ADDR(0x0ba4, win)
 #define  AXI_WINDOW_ALIGN_MASK		3
 
 #define PAB_AXI_AMAP_PEX_WIN_L(win)	PAB_REG_ADDR(0x0ba8, win)
-#define  PAB_BUS_SHIFT		24
-#define  PAB_DEVICE_SHIFT	19
-#define  PAB_FUNCTION_SHIFT	16
+#define  PAB_BUS_SHIFT			24
+#define  PAB_DEVICE_SHIFT		19
+#define  PAB_FUNCTION_SHIFT		16
 
 #define PAB_AXI_AMAP_PEX_WIN_H(win)	PAB_REG_ADDR(0x0bac, win)
 #define PAB_INTP_AXI_PIO_CLASS		0x474
 
-#define PAB_PEX_AMAP_CTRL(win)	PAB_REG_ADDR(0x4ba0, win)
-#define  AMAP_CTRL_EN_SHIFT	0
-#define  AMAP_CTRL_TYPE_SHIFT	1
+#define PAB_PEX_AMAP_CTRL(win)		PAB_REG_ADDR(0x4ba0, win)
+#define  AMAP_CTRL_EN_SHIFT		0
+#define  AMAP_CTRL_TYPE_SHIFT		1
+#define  AMAP_CTRL_TYPE_MASK		3
 
 #define PAB_EXT_PEX_AMAP_SIZEN(win)	PAB_EXT_REG_ADDR(0xbef0, win)
+#define PAB_EXT_PEX_AMAP_AXI_WIN(win)	PAB_EXT_REG_ADDR(0xb4a0, win)
 #define PAB_PEX_AMAP_AXI_WIN(win)	PAB_REG_ADDR(0x4ba4, win)
 #define PAB_PEX_AMAP_PEX_WIN_L(win)	PAB_REG_ADDR(0x4ba8, win)
 #define PAB_PEX_AMAP_PEX_WIN_H(win)	PAB_REG_ADDR(0x4bac, win)
 
 /* starting offset of INTX bits in status register */
-#define PAB_INTX_START	5
+#define PAB_INTX_START			5
 
 /* supported number of MSI interrupts */
-#define PCI_NUM_MSI	16
+#define PCI_NUM_MSI			16
 
 /* MSI registers */
-#define MSI_BASE_LO_OFFSET	0x04
-#define MSI_BASE_HI_OFFSET	0x08
-#define MSI_SIZE_OFFSET	0x0c
-#define MSI_ENABLE_OFFSET	0x14
-#define MSI_STATUS_OFFSET	0x18
-#define MSI_DATA_OFFSET	0x20
-#define MSI_ADDR_L_OFFSET	0x24
-#define MSI_ADDR_H_OFFSET	0x28
+#define MSI_BASE_LO_OFFSET		0x04
+#define MSI_BASE_HI_OFFSET		0x08
+#define MSI_SIZE_OFFSET			0x0c
+#define MSI_ENABLE_OFFSET		0x14
+#define MSI_STATUS_OFFSET		0x18
+#define MSI_DATA_OFFSET			0x20
+#define MSI_ADDR_L_OFFSET		0x24
+#define MSI_ADDR_H_OFFSET		0x28
 
 /* outbound and inbound window definitions */
-#define WIN_NUM_0		0
-#define WIN_NUM_1		1
-#define CFG_WINDOW_TYPE	0
-#define IO_WINDOW_TYPE		1
-#define MEM_WINDOW_TYPE	2
-#define IB_WIN_SIZE		((u64)256 * 1024 * 1024 * 1024)
-#define MAX_PIO_WINDOWS	8
+#define WIN_NUM_0			0
+#define WIN_NUM_1			1
+#define CFG_WINDOW_TYPE			0
+#define IO_WINDOW_TYPE			1
+#define MEM_WINDOW_TYPE			2
+#define IB_WIN_SIZE			((u64)256 * 1024 * 1024 * 1024)
+#define MAX_PIO_WINDOWS			8
 
 /* Parameters for the waiting for link up routine */
-#define LINK_WAIT_MAX_RETRIES	10
-#define LINK_WAIT_MIN	90000
-#define LINK_WAIT_MAX	100000
+#define LINK_WAIT_MAX_RETRIES		10
+#define LINK_WAIT_MIN			90000
+#define LINK_WAIT_MAX			100000
+
+#define PAGED_ADDR_BNDRY		0xc00
+#define OFFSET_TO_PAGE_ADDR(off)	\
+	((off & PAGE_LO_MASK) | PAGED_ADDR_BNDRY)
+#define OFFSET_TO_PAGE_IDX(off)		\
+	((off >> PAGE_SEL_OFFSET_SHIFT) & PAGE_SEL_MASK)
 
 struct mobiveil_msi {			/* MSI information */
 	struct mutex lock;		/* protect bitmap variable */
@@ -145,15 +157,119 @@
 	struct mobiveil_msi msi;
 };
 
-static inline void csr_writel(struct mobiveil_pcie *pcie, const u32 value,
-		const u32 reg)
+/*
+ * mobiveil_pcie_sel_page - routine to access paged register
+ *
+ * Registers whose address greater than PAGED_ADDR_BNDRY (0xc00) are paged,
+ * for this scheme to work extracted higher 6 bits of the offset will be
+ * written to pg_sel field of PAB_CTRL register and rest of the lower 10
+ * bits enabled with PAGED_ADDR_BNDRY are used as offset of the register.
+ */
+static void mobiveil_pcie_sel_page(struct mobiveil_pcie *pcie, u8 pg_idx)
 {
-	writel_relaxed(value, pcie->csr_axi_slave_base + reg);
+	u32 val;
+
+	val = readl(pcie->csr_axi_slave_base + PAB_CTRL);
+	val &= ~(PAGE_SEL_MASK << PAGE_SEL_SHIFT);
+	val |= (pg_idx & PAGE_SEL_MASK) << PAGE_SEL_SHIFT;
+
+	writel(val, pcie->csr_axi_slave_base + PAB_CTRL);
 }
 
-static inline u32 csr_readl(struct mobiveil_pcie *pcie, const u32 reg)
+static void *mobiveil_pcie_comp_addr(struct mobiveil_pcie *pcie, u32 off)
 {
-	return readl_relaxed(pcie->csr_axi_slave_base + reg);
+	if (off < PAGED_ADDR_BNDRY) {
+		/* For directly accessed registers, clear the pg_sel field */
+		mobiveil_pcie_sel_page(pcie, 0);
+		return pcie->csr_axi_slave_base + off;
+	}
+
+	mobiveil_pcie_sel_page(pcie, OFFSET_TO_PAGE_IDX(off));
+	return pcie->csr_axi_slave_base + OFFSET_TO_PAGE_ADDR(off);
+}
+
+static int mobiveil_pcie_read(void __iomem *addr, int size, u32 *val)
+{
+	if ((uintptr_t)addr & (size - 1)) {
+		*val = 0;
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+	}
+
+	switch (size) {
+	case 4:
+		*val = readl(addr);
+		break;
+	case 2:
+		*val = readw(addr);
+		break;
+	case 1:
+		*val = readb(addr);
+		break;
+	default:
+		*val = 0;
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+	}
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static int mobiveil_pcie_write(void __iomem *addr, int size, u32 val)
+{
+	if ((uintptr_t)addr & (size - 1))
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+
+	switch (size) {
+	case 4:
+		writel(val, addr);
+		break;
+	case 2:
+		writew(val, addr);
+		break;
+	case 1:
+		writeb(val, addr);
+		break;
+	default:
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+	}
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static u32 csr_read(struct mobiveil_pcie *pcie, u32 off, size_t size)
+{
+	void *addr;
+	u32 val;
+	int ret;
+
+	addr = mobiveil_pcie_comp_addr(pcie, off);
+
+	ret = mobiveil_pcie_read(addr, size, &val);
+	if (ret)
+		dev_err(&pcie->pdev->dev, "read CSR address failed\n");
+
+	return val;
+}
+
+static void csr_write(struct mobiveil_pcie *pcie, u32 val, u32 off, size_t size)
+{
+	void *addr;
+	int ret;
+
+	addr = mobiveil_pcie_comp_addr(pcie, off);
+
+	ret = mobiveil_pcie_write(addr, size, val);
+	if (ret)
+		dev_err(&pcie->pdev->dev, "write CSR address failed\n");
+}
+
+static u32 csr_readl(struct mobiveil_pcie *pcie, u32 off)
+{
+	return csr_read(pcie, off, 0x4);
+}
+
+static void csr_writel(struct mobiveil_pcie *pcie, u32 val, u32 off)
+{
+	csr_write(pcie, val, off, 0x4);
 }
 
 static bool mobiveil_pcie_link_up(struct mobiveil_pcie *pcie)
@@ -174,7 +290,7 @@
 	 * Do not read more than one device on the bus directly
 	 * attached to RC
 	 */
-	if ((bus->primary == pcie->root_bus_nr) && (devfn > 0))
+	if ((bus->primary == pcie->root_bus_nr) && (PCI_SLOT(devfn) > 0))
 		return false;
 
 	return true;
@@ -185,17 +301,17 @@
  * root port or endpoint
  */
 static void __iomem *mobiveil_pcie_map_bus(struct pci_bus *bus,
-					unsigned int devfn, int where)
+					   unsigned int devfn, int where)
 {
 	struct mobiveil_pcie *pcie = bus->sysdata;
+	u32 value;
 
 	if (!mobiveil_pcie_valid_device(bus, devfn))
 		return NULL;
 
-	if (bus->number == pcie->root_bus_nr) {
-		/* RC config access */
+	/* RC config access */
+	if (bus->number == pcie->root_bus_nr)
 		return pcie->csr_axi_slave_base + where;
-	}
 
 	/*
 	 * EP config access (in Config/APIO space)
@@ -203,10 +319,12 @@
 	 * (BDF) in PAB_AXI_AMAP_PEX_WIN_L0 Register.
 	 * Relies on pci_lock serialization
 	 */
-	csr_writel(pcie, bus->number << PAB_BUS_SHIFT |
-			PCI_SLOT(devfn) << PAB_DEVICE_SHIFT |
-			PCI_FUNC(devfn) << PAB_FUNCTION_SHIFT,
-			PAB_AXI_AMAP_PEX_WIN_L(WIN_NUM_0));
+	value = bus->number << PAB_BUS_SHIFT |
+		PCI_SLOT(devfn) << PAB_DEVICE_SHIFT |
+		PCI_FUNC(devfn) << PAB_FUNCTION_SHIFT;
+
+	csr_writel(pcie, value, PAB_AXI_AMAP_PEX_WIN_L(WIN_NUM_0));
+
 	return pcie->config_axi_slave_base + where;
 }
 
@@ -241,24 +359,29 @@
 
 	/* Handle INTx */
 	if (intr_status & PAB_INTP_INTX_MASK) {
-		shifted_status = csr_readl(pcie, PAB_INTP_AMBA_MISC_STAT) >>
-			PAB_INTX_START;
+		shifted_status = csr_readl(pcie, PAB_INTP_AMBA_MISC_STAT);
+		shifted_status &= PAB_INTP_INTX_MASK;
+		shifted_status >>= PAB_INTX_START;
 		do {
 			for_each_set_bit(bit, &shifted_status, PCI_NUM_INTX) {
 				virq = irq_find_mapping(pcie->intx_domain,
-						bit + 1);
+							bit + 1);
 				if (virq)
 					generic_handle_irq(virq);
 				else
-					dev_err_ratelimited(dev,
-						"unexpected IRQ, INT%d\n", bit);
+					dev_err_ratelimited(dev, "unexpected IRQ, INT%d\n",
+							    bit);
 
-				/* clear interrupt */
-				csr_writel(pcie,
-					shifted_status << PAB_INTX_START,
-					PAB_INTP_AMBA_MISC_STAT);
+				/* clear interrupt handled */
+				csr_writel(pcie, 1 << (PAB_INTX_START + bit),
+					   PAB_INTP_AMBA_MISC_STAT);
 			}
-		} while ((shifted_status >> PAB_INTX_START) != 0);
+
+			shifted_status = csr_readl(pcie,
+						   PAB_INTP_AMBA_MISC_STAT);
+			shifted_status &= PAB_INTP_INTX_MASK;
+			shifted_status >>= PAB_INTX_START;
+		} while (shifted_status != 0);
 	}
 
 	/* read extra MSI status register */
@@ -266,8 +389,7 @@
 
 	/* handle MSI interrupts */
 	while (msi_status & 1) {
-		msi_data = readl_relaxed(pcie->apb_csr_base
-				+ MSI_DATA_OFFSET);
+		msi_data = readl_relaxed(pcie->apb_csr_base + MSI_DATA_OFFSET);
 
 		/*
 		 * MSI_STATUS_OFFSET register gets updated to zero
@@ -276,18 +398,18 @@
 		 * two dummy reads.
 		 */
 		msi_addr_lo = readl_relaxed(pcie->apb_csr_base +
-				MSI_ADDR_L_OFFSET);
+					    MSI_ADDR_L_OFFSET);
 		msi_addr_hi = readl_relaxed(pcie->apb_csr_base +
-				MSI_ADDR_H_OFFSET);
+					    MSI_ADDR_H_OFFSET);
 		dev_dbg(dev, "MSI registers, data: %08x, addr: %08x:%08x\n",
-				msi_data, msi_addr_hi, msi_addr_lo);
+			msi_data, msi_addr_hi, msi_addr_lo);
 
 		virq = irq_find_mapping(msi->dev_domain, msi_data);
 		if (virq)
 			generic_handle_irq(virq);
 
 		msi_status = readl_relaxed(pcie->apb_csr_base +
-				MSI_STATUS_OFFSET);
+					   MSI_STATUS_OFFSET);
 	}
 
 	/* Clear the interrupt status */
@@ -301,17 +423,10 @@
 	struct platform_device *pdev = pcie->pdev;
 	struct device_node *node = dev->of_node;
 	struct resource *res;
-	const char *type;
-
-	type = of_get_property(node, "device_type", NULL);
-	if (!type || strcmp(type, "pci")) {
-		dev_err(dev, "invalid \"device_type\" %s\n", type);
-		return -EINVAL;
-	}
 
 	/* map config resource */
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-			"config_axi_slave");
+					   "config_axi_slave");
 	pcie->config_axi_slave_base = devm_pci_remap_cfg_resource(dev, res);
 	if (IS_ERR(pcie->config_axi_slave_base))
 		return PTR_ERR(pcie->config_axi_slave_base);
@@ -319,7 +434,7 @@
 
 	/* map csr resource */
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-			"csr_axi_slave");
+					   "csr_axi_slave");
 	pcie->csr_axi_slave_base = devm_pci_remap_cfg_resource(dev, res);
 	if (IS_ERR(pcie->csr_axi_slave_base))
 		return PTR_ERR(pcie->csr_axi_slave_base);
@@ -344,92 +459,53 @@
 		return -ENODEV;
 	}
 
-	irq_set_chained_handler_and_data(pcie->irq, mobiveil_pcie_isr, pcie);
-
 	return 0;
 }
 
-/*
- * select_paged_register - routine to access paged register of root complex
- *
- * registers of RC are paged, for this scheme to work
- * extracted higher 6 bits of the offset will be written to pg_sel
- * field of PAB_CTRL register and rest of the lower 10 bits enabled with
- * PAGE_SEL_EN are used as offset of the register.
- */
-static void select_paged_register(struct mobiveil_pcie *pcie, u32 offset)
-{
-	int pab_ctrl_dw, pg_sel;
-
-	/* clear pg_sel field */
-	pab_ctrl_dw = csr_readl(pcie, PAB_CTRL);
-	pab_ctrl_dw = (pab_ctrl_dw & ~(PAGE_SEL_MASK << PAGE_SEL_SHIFT));
-
-	/* set pg_sel field */
-	pg_sel = (offset >> PAGE_SEL_OFFSET_SHIFT) & PAGE_SEL_MASK;
-	pab_ctrl_dw |= ((pg_sel << PAGE_SEL_SHIFT));
-	csr_writel(pcie, pab_ctrl_dw, PAB_CTRL);
-}
-
-static void write_paged_register(struct mobiveil_pcie *pcie,
-		u32 val, u32 offset)
-{
-	u32 off = (offset & PAGE_LO_MASK) | PAGE_SEL_EN;
-
-	select_paged_register(pcie, offset);
-	csr_writel(pcie, val, off);
-}
-
-static u32 read_paged_register(struct mobiveil_pcie *pcie, u32 offset)
-{
-	u32 off = (offset & PAGE_LO_MASK) | PAGE_SEL_EN;
-
-	select_paged_register(pcie, offset);
-	return csr_readl(pcie, off);
-}
-
 static void program_ib_windows(struct mobiveil_pcie *pcie, int win_num,
-		int pci_addr, u32 type, u64 size)
+			       u64 cpu_addr, u64 pci_addr, u32 type, u64 size)
 {
-	int pio_ctrl_val;
-	int amap_ctrl_dw;
+	u32 value;
 	u64 size64 = ~(size - 1);
 
-	if ((pcie->ib_wins_configured + 1) > pcie->ppio_wins) {
+	if (win_num >= pcie->ppio_wins) {
 		dev_err(&pcie->pdev->dev,
 			"ERROR: max inbound windows reached !\n");
 		return;
 	}
 
-	pio_ctrl_val = csr_readl(pcie, PAB_PEX_PIO_CTRL);
-	csr_writel(pcie,
-		pio_ctrl_val | (1 << PIO_ENABLE_SHIFT), PAB_PEX_PIO_CTRL);
-	amap_ctrl_dw = read_paged_register(pcie, PAB_PEX_AMAP_CTRL(win_num));
-	amap_ctrl_dw = (amap_ctrl_dw | (type << AMAP_CTRL_TYPE_SHIFT));
-	amap_ctrl_dw = (amap_ctrl_dw | (1 << AMAP_CTRL_EN_SHIFT));
+	value = csr_readl(pcie, PAB_PEX_AMAP_CTRL(win_num));
+	value &= ~(AMAP_CTRL_TYPE_MASK << AMAP_CTRL_TYPE_SHIFT | WIN_SIZE_MASK);
+	value |= type << AMAP_CTRL_TYPE_SHIFT | 1 << AMAP_CTRL_EN_SHIFT |
+		 (lower_32_bits(size64) & WIN_SIZE_MASK);
+	csr_writel(pcie, value, PAB_PEX_AMAP_CTRL(win_num));
 
-	write_paged_register(pcie, amap_ctrl_dw | lower_32_bits(size64),
-				PAB_PEX_AMAP_CTRL(win_num));
+	csr_writel(pcie, upper_32_bits(size64),
+		   PAB_EXT_PEX_AMAP_SIZEN(win_num));
 
-	write_paged_register(pcie, upper_32_bits(size64),
-				PAB_EXT_PEX_AMAP_SIZEN(win_num));
+	csr_writel(pcie, lower_32_bits(cpu_addr),
+		   PAB_PEX_AMAP_AXI_WIN(win_num));
+	csr_writel(pcie, upper_32_bits(cpu_addr),
+		   PAB_EXT_PEX_AMAP_AXI_WIN(win_num));
 
-	write_paged_register(pcie, pci_addr, PAB_PEX_AMAP_AXI_WIN(win_num));
-	write_paged_register(pcie, pci_addr, PAB_PEX_AMAP_PEX_WIN_L(win_num));
-	write_paged_register(pcie, 0, PAB_PEX_AMAP_PEX_WIN_H(win_num));
+	csr_writel(pcie, lower_32_bits(pci_addr),
+		   PAB_PEX_AMAP_PEX_WIN_L(win_num));
+	csr_writel(pcie, upper_32_bits(pci_addr),
+		   PAB_PEX_AMAP_PEX_WIN_H(win_num));
+
+	pcie->ib_wins_configured++;
 }
 
 /*
  * routine to program the outbound windows
  */
 static void program_ob_windows(struct mobiveil_pcie *pcie, int win_num,
-		u64 cpu_addr, u64 pci_addr, u32 config_io_bit, u64 size)
+			       u64 cpu_addr, u64 pci_addr, u32 type, u64 size)
 {
-
-	u32 value, type;
+	u32 value;
 	u64 size64 = ~(size - 1);
 
-	if ((pcie->ob_wins_configured + 1) > pcie->apio_wins) {
+	if (win_num >= pcie->apio_wins) {
 		dev_err(&pcie->pdev->dev,
 			"ERROR: max outbound windows reached !\n");
 		return;
@@ -439,28 +515,27 @@
 	 * program Enable Bit to 1, Type Bit to (00) base 2, AXI Window Size Bit
 	 * to 4 KB in PAB_AXI_AMAP_CTRL register
 	 */
-	type = config_io_bit;
 	value = csr_readl(pcie, PAB_AXI_AMAP_CTRL(win_num));
-	csr_writel(pcie, 1 << WIN_ENABLE_SHIFT | type << WIN_TYPE_SHIFT |
-			lower_32_bits(size64), PAB_AXI_AMAP_CTRL(win_num));
+	value &= ~(WIN_TYPE_MASK << WIN_TYPE_SHIFT | WIN_SIZE_MASK);
+	value |= 1 << WIN_ENABLE_SHIFT | type << WIN_TYPE_SHIFT |
+		 (lower_32_bits(size64) & WIN_SIZE_MASK);
+	csr_writel(pcie, value, PAB_AXI_AMAP_CTRL(win_num));
 
-	write_paged_register(pcie, upper_32_bits(size64),
-				PAB_EXT_AXI_AMAP_SIZE(win_num));
+	csr_writel(pcie, upper_32_bits(size64), PAB_EXT_AXI_AMAP_SIZE(win_num));
 
 	/*
 	 * program AXI window base with appropriate value in
 	 * PAB_AXI_AMAP_AXI_WIN0 register
 	 */
-	value = csr_readl(pcie, PAB_AXI_AMAP_AXI_WIN(win_num));
-	csr_writel(pcie, cpu_addr & (~AXI_WINDOW_ALIGN_MASK),
-			PAB_AXI_AMAP_AXI_WIN(win_num));
-
-	value = csr_readl(pcie, PAB_AXI_AMAP_PEX_WIN_H(win_num));
+	csr_writel(pcie, lower_32_bits(cpu_addr) & (~AXI_WINDOW_ALIGN_MASK),
+		   PAB_AXI_AMAP_AXI_WIN(win_num));
+	csr_writel(pcie, upper_32_bits(cpu_addr),
+		   PAB_EXT_AXI_AMAP_AXI_WIN(win_num));
 
 	csr_writel(pcie, lower_32_bits(pci_addr),
-			PAB_AXI_AMAP_PEX_WIN_L(win_num));
+		   PAB_AXI_AMAP_PEX_WIN_L(win_num));
 	csr_writel(pcie, upper_32_bits(pci_addr),
-			PAB_AXI_AMAP_PEX_WIN_H(win_num));
+		   PAB_AXI_AMAP_PEX_WIN_H(win_num));
 
 	pcie->ob_wins_configured++;
 }
@@ -476,7 +551,9 @@
 
 		usleep_range(LINK_WAIT_MIN, LINK_WAIT_MAX);
 	}
+
 	dev_err(&pcie->pdev->dev, "link never came up\n");
+
 	return -ETIMEDOUT;
 }
 
@@ -489,50 +566,55 @@
 	msi->msi_pages_phys = (phys_addr_t)msg_addr;
 
 	writel_relaxed(lower_32_bits(msg_addr),
-		pcie->apb_csr_base + MSI_BASE_LO_OFFSET);
+		       pcie->apb_csr_base + MSI_BASE_LO_OFFSET);
 	writel_relaxed(upper_32_bits(msg_addr),
-		pcie->apb_csr_base + MSI_BASE_HI_OFFSET);
+		       pcie->apb_csr_base + MSI_BASE_HI_OFFSET);
 	writel_relaxed(4096, pcie->apb_csr_base + MSI_SIZE_OFFSET);
 	writel_relaxed(1, pcie->apb_csr_base + MSI_ENABLE_OFFSET);
 }
 
 static int mobiveil_host_init(struct mobiveil_pcie *pcie)
 {
-	u32 value, pab_ctrl, type = 0;
-	int err;
-	struct resource_entry *win, *tmp;
+	u32 value, pab_ctrl, type;
+	struct resource_entry *win;
 
-	err = mobiveil_bringup_link(pcie);
-	if (err) {
-		dev_info(&pcie->pdev->dev, "link bring-up failed\n");
-		return err;
-	}
+	/* setup bus numbers */
+	value = csr_readl(pcie, PCI_PRIMARY_BUS);
+	value &= 0xff000000;
+	value |= 0x00ff0100;
+	csr_writel(pcie, value, PCI_PRIMARY_BUS);
 
 	/*
 	 * program Bus Master Enable Bit in Command Register in PAB Config
 	 * Space
 	 */
 	value = csr_readl(pcie, PCI_COMMAND);
-	csr_writel(pcie, value | PCI_COMMAND_IO | PCI_COMMAND_MEMORY |
-		PCI_COMMAND_MASTER, PCI_COMMAND);
+	value |= PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER;
+	csr_writel(pcie, value, PCI_COMMAND);
 
 	/*
 	 * program PIO Enable Bit to 1 (and PEX PIO Enable to 1) in PAB_CTRL
 	 * register
 	 */
 	pab_ctrl = csr_readl(pcie, PAB_CTRL);
-	csr_writel(pcie, pab_ctrl | (1 << AMBA_PIO_ENABLE_SHIFT) |
-		(1 << PEX_PIO_ENABLE_SHIFT), PAB_CTRL);
+	pab_ctrl |= (1 << AMBA_PIO_ENABLE_SHIFT) | (1 << PEX_PIO_ENABLE_SHIFT);
+	csr_writel(pcie, pab_ctrl, PAB_CTRL);
 
 	csr_writel(pcie, (PAB_INTP_INTX_MASK | PAB_INTP_MSI_MASK),
-		PAB_INTP_AMBA_MISC_ENB);
+		   PAB_INTP_AMBA_MISC_ENB);
 
 	/*
 	 * program PIO Enable Bit to 1 and Config Window Enable Bit to 1 in
 	 * PAB_AXI_PIO_CTRL Register
 	 */
 	value = csr_readl(pcie, PAB_AXI_PIO_CTRL);
-	csr_writel(pcie, value | APIO_EN_MASK, PAB_AXI_PIO_CTRL);
+	value |= APIO_EN_MASK;
+	csr_writel(pcie, value, PAB_AXI_PIO_CTRL);
+
+	/* Enable PCIe PIO master */
+	value = csr_readl(pcie, PAB_PEX_PIO_CTRL);
+	value |= 1 << PIO_ENABLE_SHIFT;
+	csr_writel(pcie, value, PAB_PEX_PIO_CTRL);
 
 	/*
 	 * we'll program one outbound window for config reads and
@@ -542,32 +624,38 @@
 	 */
 
 	/* config outbound translation window */
-	program_ob_windows(pcie, pcie->ob_wins_configured,
-			pcie->ob_io_res->start, 0, CFG_WINDOW_TYPE,
-			resource_size(pcie->ob_io_res));
+	program_ob_windows(pcie, WIN_NUM_0, pcie->ob_io_res->start, 0,
+			   CFG_WINDOW_TYPE, resource_size(pcie->ob_io_res));
 
 	/* memory inbound translation window */
-	program_ib_windows(pcie, WIN_NUM_1, 0, MEM_WINDOW_TYPE, IB_WIN_SIZE);
+	program_ib_windows(pcie, WIN_NUM_0, 0, 0, MEM_WINDOW_TYPE, IB_WIN_SIZE);
 
 	/* Get the I/O and memory ranges from DT */
-	resource_list_for_each_entry_safe(win, tmp, &pcie->resources) {
-		type = 0;
+	resource_list_for_each_entry(win, &pcie->resources) {
 		if (resource_type(win->res) == IORESOURCE_MEM)
 			type = MEM_WINDOW_TYPE;
-		if (resource_type(win->res) == IORESOURCE_IO)
+		else if (resource_type(win->res) == IORESOURCE_IO)
 			type = IO_WINDOW_TYPE;
-		if (type) {
-			/* configure outbound translation window */
-			program_ob_windows(pcie, pcie->ob_wins_configured,
-				win->res->start, 0, type,
-				resource_size(win->res));
-		}
+		else
+			continue;
+
+		/* configure outbound translation window */
+		program_ob_windows(pcie, pcie->ob_wins_configured,
+				   win->res->start,
+				   win->res->start - win->offset,
+				   type, resource_size(win->res));
 	}
 
+	/* fixup for PCIe class register */
+	value = csr_readl(pcie, PAB_INTP_AXI_PIO_CLASS);
+	value &= 0xff;
+	value |= (PCI_CLASS_BRIDGE_PCI << 16);
+	csr_writel(pcie, value, PAB_INTP_AXI_PIO_CLASS);
+
 	/* setup MSI hardware registers */
 	mobiveil_pcie_enable_msi(pcie);
 
-	return err;
+	return 0;
 }
 
 static void mobiveil_mask_intx_irq(struct irq_data *data)
@@ -581,7 +669,8 @@
 	mask = 1 << ((data->hwirq + PAB_INTX_START) - 1);
 	raw_spin_lock_irqsave(&pcie->intx_mask_lock, flags);
 	shifted_val = csr_readl(pcie, PAB_INTP_AMBA_MISC_ENB);
-	csr_writel(pcie, (shifted_val & (~mask)), PAB_INTP_AMBA_MISC_ENB);
+	shifted_val &= ~mask;
+	csr_writel(pcie, shifted_val, PAB_INTP_AMBA_MISC_ENB);
 	raw_spin_unlock_irqrestore(&pcie->intx_mask_lock, flags);
 }
 
@@ -596,7 +685,8 @@
 	mask = 1 << ((data->hwirq + PAB_INTX_START) - 1);
 	raw_spin_lock_irqsave(&pcie->intx_mask_lock, flags);
 	shifted_val = csr_readl(pcie, PAB_INTP_AMBA_MISC_ENB);
-	csr_writel(pcie, (shifted_val | mask), PAB_INTP_AMBA_MISC_ENB);
+	shifted_val |= mask;
+	csr_writel(pcie, shifted_val, PAB_INTP_AMBA_MISC_ENB);
 	raw_spin_unlock_irqrestore(&pcie->intx_mask_lock, flags);
 }
 
@@ -610,10 +700,11 @@
 
 /* routine to setup the INTx related data */
 static int mobiveil_pcie_intx_map(struct irq_domain *domain, unsigned int irq,
-		irq_hw_number_t hwirq)
+				  irq_hw_number_t hwirq)
 {
 	irq_set_chip_and_handler(irq, &intx_irq_chip, handle_level_irq);
 	irq_set_chip_data(irq, domain->host_data);
+
 	return 0;
 }
 
@@ -630,7 +721,7 @@
 
 static struct msi_domain_info mobiveil_msi_domain_info = {
 	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
-		MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX),
+		   MSI_FLAG_PCI_MSIX),
 	.chip	= &mobiveil_msi_irq_chip,
 };
 
@@ -648,7 +739,7 @@
 }
 
 static int mobiveil_msi_set_affinity(struct irq_data *irq_data,
-		const struct cpumask *mask, bool force)
+				     const struct cpumask *mask, bool force)
 {
 	return -EINVAL;
 }
@@ -660,7 +751,8 @@
 };
 
 static int mobiveil_irq_msi_domain_alloc(struct irq_domain *domain,
-		unsigned int virq, unsigned int nr_irqs, void *args)
+					 unsigned int virq,
+					 unsigned int nr_irqs, void *args)
 {
 	struct mobiveil_pcie *pcie = domain->host_data;
 	struct mobiveil_msi *msi = &pcie->msi;
@@ -680,13 +772,13 @@
 	mutex_unlock(&msi->lock);
 
 	irq_domain_set_info(domain, virq, bit, &mobiveil_msi_bottom_irq_chip,
-				domain->host_data, handle_level_irq,
-				NULL, NULL);
+			    domain->host_data, handle_level_irq, NULL, NULL);
 	return 0;
 }
 
 static void mobiveil_irq_msi_domain_free(struct irq_domain *domain,
-		unsigned int virq, unsigned int nr_irqs)
+					 unsigned int virq,
+					 unsigned int nr_irqs)
 {
 	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
 	struct mobiveil_pcie *pcie = irq_data_get_irq_chip_data(d);
@@ -694,12 +786,11 @@
 
 	mutex_lock(&msi->lock);
 
-	if (!test_bit(d->hwirq, msi->msi_irq_in_use)) {
+	if (!test_bit(d->hwirq, msi->msi_irq_in_use))
 		dev_err(&pcie->pdev->dev, "trying to free unused MSI#%lu\n",
 			d->hwirq);
-	} else {
+	else
 		__clear_bit(d->hwirq, msi->msi_irq_in_use);
-	}
 
 	mutex_unlock(&msi->lock);
 }
@@ -723,12 +814,14 @@
 	}
 
 	msi->msi_domain = pci_msi_create_irq_domain(fwnode,
-				&mobiveil_msi_domain_info, msi->dev_domain);
+						    &mobiveil_msi_domain_info,
+						    msi->dev_domain);
 	if (!msi->msi_domain) {
 		dev_err(dev, "failed to create MSI domain\n");
 		irq_domain_remove(msi->dev_domain);
 		return -ENOMEM;
 	}
+
 	return 0;
 }
 
@@ -739,12 +832,12 @@
 	int ret;
 
 	/* setup INTx */
-	pcie->intx_domain = irq_domain_add_linear(node,
-				PCI_NUM_INTX, &intx_domain_ops, pcie);
+	pcie->intx_domain = irq_domain_add_linear(node, PCI_NUM_INTX,
+						  &intx_domain_ops, pcie);
 
 	if (!pcie->intx_domain) {
 		dev_err(dev, "Failed to get a INTx IRQ domain\n");
-		return -ENODEV;
+		return -ENOMEM;
 	}
 
 	raw_spin_lock_init(&pcie->intx_mask_lock);
@@ -770,11 +863,9 @@
 	/* allocate the PCIe port */
 	bridge = devm_pci_alloc_host_bridge(dev, sizeof(*pcie));
 	if (!bridge)
-		return -ENODEV;
+		return -ENOMEM;
 
 	pcie = pci_host_bridge_priv(bridge);
-	if (!pcie)
-		return -ENOMEM;
 
 	pcie->pdev = pdev;
 
@@ -791,7 +882,7 @@
 						    &pcie->resources, &iobase);
 	if (ret) {
 		dev_err(dev, "Getting bridge resources failed\n");
-		return -ENOMEM;
+		return ret;
 	}
 
 	/*
@@ -804,9 +895,6 @@
 		goto error;
 	}
 
-	/* fixup for PCIe class register */
-	csr_writel(pcie, 0x060402ab, PAB_INTP_AXI_PIO_CLASS);
-
 	/* initialize the IRQ domains */
 	ret = mobiveil_pcie_init_irq_domain(pcie);
 	if (ret) {
@@ -814,6 +902,8 @@
 		goto error;
 	}
 
+	irq_set_chained_handler_and_data(pcie->irq, mobiveil_pcie_isr, pcie);
+
 	ret = devm_request_pci_bus_resources(dev, &pcie->resources);
 	if (ret)
 		goto error;
@@ -827,6 +917,12 @@
 	bridge->map_irq = of_irq_parse_and_map_pci;
 	bridge->swizzle_irq = pci_common_swizzle;
 
+	ret = mobiveil_bringup_link(pcie);
+	if (ret) {
+		dev_info(dev, "link bring-up failed\n");
+		goto error;
+	}
+
 	/* setup the kernel resources for the newly added PCIe root bus */
 	ret = pci_scan_root_bus_bridge(bridge);
 	if (ret)
@@ -855,10 +951,10 @@
 static struct platform_driver mobiveil_pcie_driver = {
 	.probe = mobiveil_pcie_probe,
 	.driver = {
-			.name = "mobiveil-pcie",
-			.of_match_table = mobiveil_pcie_of_match,
-			.suppress_bind_attrs = true,
-		},
+		.name = "mobiveil-pcie",
+		.of_match_table = mobiveil_pcie_of_match,
+		.suppress_bind_attrs = true,
+	},
 };
 
 builtin_platform_driver(mobiveil_pcie_driver);
diff --git a/drivers/pci/controller/pcie-rcar.c b/drivers/pci/controller/pcie-rcar.c
index c8febb0..f6a669a 100644
--- a/drivers/pci/controller/pcie-rcar.c
+++ b/drivers/pci/controller/pcie-rcar.c
@@ -46,14 +46,15 @@
 
 /* Transfer control */
 #define PCIETCTLR		0x02000
-#define  CFINIT			1
+#define  DL_DOWN		BIT(3)
+#define  CFINIT			BIT(0)
 #define PCIETSTR		0x02004
-#define  DATA_LINK_ACTIVE	1
+#define  DATA_LINK_ACTIVE	BIT(0)
 #define PCIEERRFR		0x02020
 #define  UNSUPPORTED_REQUEST	BIT(4)
 #define PCIEMSIFR		0x02044
 #define PCIEMSIALR		0x02048
-#define  MSIFE			1
+#define  MSIFE			BIT(0)
 #define PCIEMSIAUR		0x0204c
 #define PCIEMSIIER		0x02050
 
@@ -94,6 +95,7 @@
 #define MACCTLR			0x011058
 #define  SPEED_CHANGE		BIT(24)
 #define  SCRAMBLE_DISABLE	BIT(27)
+#define PMSR			0x01105c
 #define MACS2R			0x011078
 #define MACCGSPSETR		0x011084
 #define  SPCNGRSN		BIT(31)
@@ -152,14 +154,13 @@
 	struct			rcar_msi msi;
 };
 
-static void rcar_pci_write_reg(struct rcar_pcie *pcie, unsigned long val,
-			       unsigned long reg)
+static void rcar_pci_write_reg(struct rcar_pcie *pcie, u32 val,
+			       unsigned int reg)
 {
 	writel(val, pcie->base + reg);
 }
 
-static unsigned long rcar_pci_read_reg(struct rcar_pcie *pcie,
-				       unsigned long reg)
+static u32 rcar_pci_read_reg(struct rcar_pcie *pcie, unsigned int reg)
 {
 	return readl(pcie->base + reg);
 }
@@ -171,7 +172,7 @@
 
 static void rcar_rmw32(struct rcar_pcie *pcie, int where, u32 mask, u32 data)
 {
-	int shift = 8 * (where & 3);
+	unsigned int shift = BITS_PER_BYTE * (where & 3);
 	u32 val = rcar_pci_read_reg(pcie, where & ~3);
 
 	val &= ~(mask << shift);
@@ -181,7 +182,7 @@
 
 static u32 rcar_read_conf(struct rcar_pcie *pcie, int where)
 {
-	int shift = 8 * (where & 3);
+	unsigned int shift = BITS_PER_BYTE * (where & 3);
 	u32 val = rcar_pci_read_reg(pcie, where & ~3);
 
 	return val >> shift;
@@ -192,7 +193,7 @@
 		unsigned char access_type, struct pci_bus *bus,
 		unsigned int devfn, int where, u32 *data)
 {
-	int dev, func, reg, index;
+	unsigned int dev, func, reg, index;
 
 	dev = PCI_SLOT(devfn);
 	func = PCI_FUNC(devfn);
@@ -281,12 +282,12 @@
 	}
 
 	if (size == 1)
-		*val = (*val >> (8 * (where & 3))) & 0xff;
+		*val = (*val >> (BITS_PER_BYTE * (where & 3))) & 0xff;
 	else if (size == 2)
-		*val = (*val >> (8 * (where & 2))) & 0xffff;
+		*val = (*val >> (BITS_PER_BYTE * (where & 2))) & 0xffff;
 
-	dev_dbg(&bus->dev, "pcie-config-read: bus=%3d devfn=0x%04x where=0x%04x size=%d val=0x%08lx\n",
-		bus->number, devfn, where, size, (unsigned long)*val);
+	dev_dbg(&bus->dev, "pcie-config-read: bus=%3d devfn=0x%04x where=0x%04x size=%d val=0x%08x\n",
+		bus->number, devfn, where, size, *val);
 
 	return ret;
 }
@@ -296,23 +297,24 @@
 				int where, int size, u32 val)
 {
 	struct rcar_pcie *pcie = bus->sysdata;
-	int shift, ret;
+	unsigned int shift;
 	u32 data;
+	int ret;
 
 	ret = rcar_pcie_config_access(pcie, RCAR_PCI_ACCESS_READ,
 				      bus, devfn, where, &data);
 	if (ret != PCIBIOS_SUCCESSFUL)
 		return ret;
 
-	dev_dbg(&bus->dev, "pcie-config-write: bus=%3d devfn=0x%04x where=0x%04x size=%d val=0x%08lx\n",
-		bus->number, devfn, where, size, (unsigned long)val);
+	dev_dbg(&bus->dev, "pcie-config-write: bus=%3d devfn=0x%04x where=0x%04x size=%d val=0x%08x\n",
+		bus->number, devfn, where, size, val);
 
 	if (size == 1) {
-		shift = 8 * (where & 3);
+		shift = BITS_PER_BYTE * (where & 3);
 		data &= ~(0xff << shift);
 		data |= ((val & 0xff) << shift);
 	} else if (size == 2) {
-		shift = 8 * (where & 2);
+		shift = BITS_PER_BYTE * (where & 2);
 		data &= ~(0xffff << shift);
 		data |= ((val & 0xffff) << shift);
 	} else
@@ -507,10 +509,10 @@
 }
 
 static void phy_write_reg(struct rcar_pcie *pcie,
-				 unsigned int rate, unsigned int addr,
-				 unsigned int lane, unsigned int data)
+			  unsigned int rate, u32 addr,
+			  unsigned int lane, u32 data)
 {
-	unsigned long phyaddr;
+	u32 phyaddr;
 
 	phyaddr = WRITE_CMD |
 		((rate & 1) << RATE_POS) |
@@ -738,15 +740,15 @@
 
 	while (reg) {
 		unsigned int index = find_first_bit(&reg, 32);
-		unsigned int irq;
+		unsigned int msi_irq;
 
 		/* clear the interrupt */
 		rcar_pci_write_reg(pcie, 1 << index, PCIEMSIFR);
 
-		irq = irq_find_mapping(msi->domain, index);
-		if (irq) {
+		msi_irq = irq_find_mapping(msi->domain, index);
+		if (msi_irq) {
 			if (test_bit(index, msi->used))
-				generic_handle_irq(irq);
+				generic_handle_irq(msi_irq);
 			else
 				dev_info(dev, "unhandled MSI\n");
 		} else {
@@ -890,7 +892,7 @@
 {
 	struct device *dev = pcie->dev;
 	struct rcar_msi *msi = &pcie->msi;
-	unsigned long base;
+	phys_addr_t base;
 	int err, i;
 
 	mutex_init(&msi->lock);
@@ -929,10 +931,14 @@
 
 	/* setup MSI data target */
 	msi->pages = __get_free_pages(GFP_KERNEL, 0);
+	if (!msi->pages) {
+		err = -ENOMEM;
+		goto err;
+	}
 	base = virt_to_phys((void *)msi->pages);
 
-	rcar_pci_write_reg(pcie, base | MSIFE, PCIEMSIALR);
-	rcar_pci_write_reg(pcie, 0, PCIEMSIAUR);
+	rcar_pci_write_reg(pcie, lower_32_bits(base) | MSIFE, PCIEMSIALR);
+	rcar_pci_write_reg(pcie, upper_32_bits(base), PCIEMSIAUR);
 
 	/* enable all MSI interrupts */
 	rcar_pci_write_reg(pcie, 0xffffffff, PCIEMSIIER);
@@ -1118,7 +1124,7 @@
 {
 	struct device *dev = &pdev->dev;
 	struct rcar_pcie *pcie;
-	unsigned int data;
+	u32 data;
 	int err;
 	int (*phy_init_fn)(struct rcar_pcie *);
 	struct pci_host_bridge *bridge;
@@ -1130,6 +1136,7 @@
 	pcie = pci_host_bridge_priv(bridge);
 
 	pcie->dev = dev;
+	platform_set_drvdata(pdev, pcie);
 
 	err = pci_parse_request_of_pci_ranges(dev, &pcie->resources, NULL);
 	if (err)
@@ -1221,10 +1228,28 @@
 	return err;
 }
 
+static int rcar_pcie_resume_noirq(struct device *dev)
+{
+	struct rcar_pcie *pcie = dev_get_drvdata(dev);
+
+	if (rcar_pci_read_reg(pcie, PMSR) &&
+	    !(rcar_pci_read_reg(pcie, PCIETCTLR) & DL_DOWN))
+		return 0;
+
+	/* Re-establish the PCIe link */
+	rcar_pci_write_reg(pcie, CFINIT, PCIETCTLR);
+	return rcar_pcie_wait_for_dl(pcie);
+}
+
+static const struct dev_pm_ops rcar_pcie_pm_ops = {
+	.resume_noirq = rcar_pcie_resume_noirq,
+};
+
 static struct platform_driver rcar_pcie_driver = {
 	.driver = {
 		.name = "rcar-pcie",
 		.of_match_table = rcar_pcie_of_match,
+		.pm = &rcar_pcie_pm_ops,
 		.suppress_bind_attrs = true,
 	},
 	.probe = rcar_pcie_probe,
diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index b8163c5..d743b0a 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -350,7 +350,7 @@
 	struct rockchip_pcie *rockchip = &ep->rockchip;
 	u32 r = ep->max_regions - 1;
 	u32 offset;
-	u16 status;
+	u32 status;
 	u8 msg_code;
 
 	if (unlikely(ep->irq_pci_addr != ROCKCHIP_PCIE_EP_PCI_LEGACY_IRQ_ADDR ||
@@ -499,12 +499,21 @@
 
 	rockchip_pcie_write(rockchip, cfg, PCIE_CORE_PHY_FUNC_CFG);
 
-	list_for_each_entry(epf, &epc->pci_epf, list)
-		pci_epf_linkup(epf);
-
 	return 0;
 }
 
+static const struct pci_epc_features rockchip_pcie_epc_features = {
+	.linkup_notifier = false,
+	.msi_capable = true,
+	.msix_capable = false,
+};
+
+static const struct pci_epc_features*
+rockchip_pcie_ep_get_features(struct pci_epc *epc, u8 func_no)
+{
+	return &rockchip_pcie_epc_features;
+}
+
 static const struct pci_epc_ops rockchip_pcie_epc_ops = {
 	.write_header	= rockchip_pcie_ep_write_header,
 	.set_bar	= rockchip_pcie_ep_set_bar,
@@ -515,6 +524,7 @@
 	.get_msi	= rockchip_pcie_ep_get_msi,
 	.raise_irq	= rockchip_pcie_ep_raise_irq,
 	.start		= rockchip_pcie_ep_start,
+	.get_features	= rockchip_pcie_ep_get_features,
 };
 
 static int rockchip_pcie_parse_ep_dt(struct rockchip_pcie *rockchip,
diff --git a/drivers/pci/controller/pcie-rockchip-host.c b/drivers/pci/controller/pcie-rockchip-host.c
index 1372d27..ef8e677 100644
--- a/drivers/pci/controller/pcie-rockchip-host.c
+++ b/drivers/pci/controller/pcie-rockchip-host.c
@@ -608,29 +608,29 @@
 
 	rockchip->vpcie12v = devm_regulator_get_optional(dev, "vpcie12v");
 	if (IS_ERR(rockchip->vpcie12v)) {
-		if (PTR_ERR(rockchip->vpcie12v) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
+		if (PTR_ERR(rockchip->vpcie12v) != -ENODEV)
+			return PTR_ERR(rockchip->vpcie12v);
 		dev_info(dev, "no vpcie12v regulator found\n");
 	}
 
 	rockchip->vpcie3v3 = devm_regulator_get_optional(dev, "vpcie3v3");
 	if (IS_ERR(rockchip->vpcie3v3)) {
-		if (PTR_ERR(rockchip->vpcie3v3) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
+		if (PTR_ERR(rockchip->vpcie3v3) != -ENODEV)
+			return PTR_ERR(rockchip->vpcie3v3);
 		dev_info(dev, "no vpcie3v3 regulator found\n");
 	}
 
 	rockchip->vpcie1v8 = devm_regulator_get_optional(dev, "vpcie1v8");
 	if (IS_ERR(rockchip->vpcie1v8)) {
-		if (PTR_ERR(rockchip->vpcie1v8) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
+		if (PTR_ERR(rockchip->vpcie1v8) != -ENODEV)
+			return PTR_ERR(rockchip->vpcie1v8);
 		dev_info(dev, "no vpcie1v8 regulator found\n");
 	}
 
 	rockchip->vpcie0v9 = devm_regulator_get_optional(dev, "vpcie0v9");
 	if (IS_ERR(rockchip->vpcie0v9)) {
-		if (PTR_ERR(rockchip->vpcie0v9) == -EPROBE_DEFER)
-			return -EPROBE_DEFER;
+		if (PTR_ERR(rockchip->vpcie0v9) != -ENODEV)
+			return PTR_ERR(rockchip->vpcie0v9);
 		dev_info(dev, "no vpcie0v9 regulator found\n");
 	}
 
@@ -724,6 +724,7 @@
 
 	rockchip->irq_domain = irq_domain_add_linear(intc, PCI_NUM_INTX,
 						    &intx_domain_ops, rockchip);
+	of_node_put(intc);
 	if (!rockchip->irq_domain) {
 		dev_err(dev, "failed to get a INTx IRQ domain\n");
 		return -EINVAL;
diff --git a/drivers/pci/controller/pcie-xilinx-nwl.c b/drivers/pci/controller/pcie-xilinx-nwl.c
index fb32840..45c0f34 100644
--- a/drivers/pci/controller/pcie-xilinx-nwl.c
+++ b/drivers/pci/controller/pcie-xilinx-nwl.c
@@ -438,11 +438,10 @@
 #ifdef CONFIG_PCI_MSI
 static struct irq_chip nwl_msi_irq_chip = {
 	.name = "nwl_pcie:msi",
-	.irq_enable = unmask_msi_irq,
-	.irq_disable = mask_msi_irq,
-	.irq_mask = mask_msi_irq,
-	.irq_unmask = unmask_msi_irq,
-
+	.irq_enable = pci_msi_unmask_irq,
+	.irq_disable = pci_msi_mask_irq,
+	.irq_mask = pci_msi_mask_irq,
+	.irq_unmask = pci_msi_unmask_irq,
 };
 
 static struct msi_domain_info nwl_msi_domain_info = {
@@ -483,15 +482,13 @@
 	int i;
 
 	mutex_lock(&msi->lock);
-	bit = bitmap_find_next_zero_area(msi->bitmap, INT_PCI_MSI_NR, 0,
-					 nr_irqs, 0);
-	if (bit >= INT_PCI_MSI_NR) {
+	bit = bitmap_find_free_region(msi->bitmap, INT_PCI_MSI_NR,
+				      get_count_order(nr_irqs));
+	if (bit < 0) {
 		mutex_unlock(&msi->lock);
 		return -ENOSPC;
 	}
 
-	bitmap_set(msi->bitmap, bit, nr_irqs);
-
 	for (i = 0; i < nr_irqs; i++) {
 		irq_domain_set_info(domain, virq + i, bit + i, &nwl_irq_chip,
 				domain->host_data, handle_simple_irq,
@@ -509,7 +506,8 @@
 	struct nwl_msi *msi = &pcie->msi;
 
 	mutex_lock(&msi->lock);
-	bitmap_clear(msi->bitmap, data->hwirq, nr_irqs);
+	bitmap_release_region(msi->bitmap, data->hwirq,
+			      get_count_order(nr_irqs));
 	mutex_unlock(&msi->lock);
 }
 
@@ -777,16 +775,7 @@
 			     struct platform_device *pdev)
 {
 	struct device *dev = pcie->dev;
-	struct device_node *node = dev->of_node;
 	struct resource *res;
-	const char *type;
-
-	/* Check for device type */
-	type = of_get_property(node, "device_type", NULL);
-	if (!type || strcmp(type, "pci")) {
-		dev_err(dev, "invalid \"device_type\" %s\n", type);
-		return -EINVAL;
-	}
 
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "breg");
 	pcie->breg_base = devm_ioremap_resource(dev, res);
diff --git a/drivers/pci/controller/pcie-xilinx.c b/drivers/pci/controller/pcie-xilinx.c
index 7b1389d..5bf3af3 100644
--- a/drivers/pci/controller/pcie-xilinx.c
+++ b/drivers/pci/controller/pcie-xilinx.c
@@ -336,14 +336,19 @@
  * xilinx_pcie_enable_msi - Enable MSI support
  * @port: PCIe port information
  */
-static void xilinx_pcie_enable_msi(struct xilinx_pcie_port *port)
+static int xilinx_pcie_enable_msi(struct xilinx_pcie_port *port)
 {
 	phys_addr_t msg_addr;
 
 	port->msi_pages = __get_free_pages(GFP_KERNEL, 0);
+	if (!port->msi_pages)
+		return -ENOMEM;
+
 	msg_addr = virt_to_phys((void *)port->msi_pages);
 	pcie_write(port, 0x0, XILINX_PCIE_REG_MSIBASE1);
 	pcie_write(port, msg_addr, XILINX_PCIE_REG_MSIBASE2);
+
+	return 0;
 }
 
 /* INTx Functions */
@@ -498,6 +503,7 @@
 	struct device *dev = port->dev;
 	struct device_node *node = dev->of_node;
 	struct device_node *pcie_intc_node;
+	int ret;
 
 	/* Setup INTx */
 	pcie_intc_node = of_get_next_child(node, NULL);
@@ -526,7 +532,9 @@
 			return -ENODEV;
 		}
 
-		xilinx_pcie_enable_msi(port);
+		ret = xilinx_pcie_enable_msi(port);
+		if (ret)
+			return ret;
 	}
 
 	return 0;
@@ -574,15 +582,8 @@
 	struct device *dev = port->dev;
 	struct device_node *node = dev->of_node;
 	struct resource regs;
-	const char *type;
 	int err;
 
-	type = of_get_property(node, "device_type", NULL);
-	if (!type || strcmp(type, "pci")) {
-		dev_err(dev, "invalid \"device_type\" %s\n", type);
-		return -EINVAL;
-	}
-
 	err = of_address_to_resource(node, 0, &regs);
 	if (err) {
 		dev_err(dev, "missing \"reg\" property\n");
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index fd2dbd7..a35d3f3 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -31,6 +31,9 @@
 #define PCI_REG_VMLOCK		0x70
 #define MB2_SHADOW_EN(vmlock)	(vmlock & 0x2)
 
+#define MB2_SHADOW_OFFSET	0x2000
+#define MB2_SHADOW_SIZE		16
+
 enum vmd_features {
 	/*
 	 * Device may contain registers which hint the physical location of the
@@ -94,11 +97,10 @@
 	struct resource		resources[3];
 	struct irq_domain	*irq_domain;
 	struct pci_bus		*bus;
+	u8			busn_start;
 
-#ifdef CONFIG_X86_DEV_DMA_OPS
 	struct dma_map_ops	dma_ops;
 	struct dma_domain	dma_domain;
-#endif
 };
 
 static inline struct vmd_dev *vmd_from_bus(struct pci_bus *bus)
@@ -293,7 +295,6 @@
 	.chip		= &vmd_msi_controller,
 };
 
-#ifdef CONFIG_X86_DEV_DMA_OPS
 /*
  * VMD replaces the requester ID with its own.  DMA mappings for devices in a
  * VMD domain need to be mapped for the VMD, not the device requiring
@@ -307,39 +308,32 @@
 	return &vmd->dev->dev;
 }
 
-static const struct dma_map_ops *vmd_dma_ops(struct device *dev)
-{
-	return get_dma_ops(to_vmd_dev(dev));
-}
-
 static void *vmd_alloc(struct device *dev, size_t size, dma_addr_t *addr,
 		       gfp_t flag, unsigned long attrs)
 {
-	return vmd_dma_ops(dev)->alloc(to_vmd_dev(dev), size, addr, flag,
-				       attrs);
+	return dma_alloc_attrs(to_vmd_dev(dev), size, addr, flag, attrs);
 }
 
 static void vmd_free(struct device *dev, size_t size, void *vaddr,
 		     dma_addr_t addr, unsigned long attrs)
 {
-	return vmd_dma_ops(dev)->free(to_vmd_dev(dev), size, vaddr, addr,
-				      attrs);
+	return dma_free_attrs(to_vmd_dev(dev), size, vaddr, addr, attrs);
 }
 
 static int vmd_mmap(struct device *dev, struct vm_area_struct *vma,
 		    void *cpu_addr, dma_addr_t addr, size_t size,
 		    unsigned long attrs)
 {
-	return vmd_dma_ops(dev)->mmap(to_vmd_dev(dev), vma, cpu_addr, addr,
-				      size, attrs);
+	return dma_mmap_attrs(to_vmd_dev(dev), vma, cpu_addr, addr, size,
+			attrs);
 }
 
 static int vmd_get_sgtable(struct device *dev, struct sg_table *sgt,
 			   void *cpu_addr, dma_addr_t addr, size_t size,
 			   unsigned long attrs)
 {
-	return vmd_dma_ops(dev)->get_sgtable(to_vmd_dev(dev), sgt, cpu_addr,
-					     addr, size, attrs);
+	return dma_get_sgtable_attrs(to_vmd_dev(dev), sgt, cpu_addr, addr, size,
+			attrs);
 }
 
 static dma_addr_t vmd_map_page(struct device *dev, struct page *page,
@@ -347,69 +341,61 @@
 			       enum dma_data_direction dir,
 			       unsigned long attrs)
 {
-	return vmd_dma_ops(dev)->map_page(to_vmd_dev(dev), page, offset, size,
-					  dir, attrs);
+	return dma_map_page_attrs(to_vmd_dev(dev), page, offset, size, dir,
+			attrs);
 }
 
 static void vmd_unmap_page(struct device *dev, dma_addr_t addr, size_t size,
 			   enum dma_data_direction dir, unsigned long attrs)
 {
-	vmd_dma_ops(dev)->unmap_page(to_vmd_dev(dev), addr, size, dir, attrs);
+	dma_unmap_page_attrs(to_vmd_dev(dev), addr, size, dir, attrs);
 }
 
 static int vmd_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 		      enum dma_data_direction dir, unsigned long attrs)
 {
-	return vmd_dma_ops(dev)->map_sg(to_vmd_dev(dev), sg, nents, dir, attrs);
+	return dma_map_sg_attrs(to_vmd_dev(dev), sg, nents, dir, attrs);
 }
 
 static void vmd_unmap_sg(struct device *dev, struct scatterlist *sg, int nents,
 			 enum dma_data_direction dir, unsigned long attrs)
 {
-	vmd_dma_ops(dev)->unmap_sg(to_vmd_dev(dev), sg, nents, dir, attrs);
+	dma_unmap_sg_attrs(to_vmd_dev(dev), sg, nents, dir, attrs);
 }
 
 static void vmd_sync_single_for_cpu(struct device *dev, dma_addr_t addr,
 				    size_t size, enum dma_data_direction dir)
 {
-	vmd_dma_ops(dev)->sync_single_for_cpu(to_vmd_dev(dev), addr, size, dir);
+	dma_sync_single_for_cpu(to_vmd_dev(dev), addr, size, dir);
 }
 
 static void vmd_sync_single_for_device(struct device *dev, dma_addr_t addr,
 				       size_t size, enum dma_data_direction dir)
 {
-	vmd_dma_ops(dev)->sync_single_for_device(to_vmd_dev(dev), addr, size,
-						 dir);
+	dma_sync_single_for_device(to_vmd_dev(dev), addr, size, dir);
 }
 
 static void vmd_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
 				int nents, enum dma_data_direction dir)
 {
-	vmd_dma_ops(dev)->sync_sg_for_cpu(to_vmd_dev(dev), sg, nents, dir);
+	dma_sync_sg_for_cpu(to_vmd_dev(dev), sg, nents, dir);
 }
 
 static void vmd_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
 				   int nents, enum dma_data_direction dir)
 {
-	vmd_dma_ops(dev)->sync_sg_for_device(to_vmd_dev(dev), sg, nents, dir);
-}
-
-static int vmd_mapping_error(struct device *dev, dma_addr_t addr)
-{
-	return vmd_dma_ops(dev)->mapping_error(to_vmd_dev(dev), addr);
+	dma_sync_sg_for_device(to_vmd_dev(dev), sg, nents, dir);
 }
 
 static int vmd_dma_supported(struct device *dev, u64 mask)
 {
-	return vmd_dma_ops(dev)->dma_supported(to_vmd_dev(dev), mask);
+	return dma_supported(to_vmd_dev(dev), mask);
 }
 
-#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK
 static u64 vmd_get_required_mask(struct device *dev)
 {
-	return vmd_dma_ops(dev)->get_required_mask(to_vmd_dev(dev));
+	return dma_get_required_mask(to_vmd_dev(dev));
 }
-#endif
 
 static void vmd_teardown_dma_ops(struct vmd_dev *vmd)
 {
@@ -448,24 +434,18 @@
 	ASSIGN_VMD_DMA_OPS(source, dest, sync_single_for_device);
 	ASSIGN_VMD_DMA_OPS(source, dest, sync_sg_for_cpu);
 	ASSIGN_VMD_DMA_OPS(source, dest, sync_sg_for_device);
-	ASSIGN_VMD_DMA_OPS(source, dest, mapping_error);
 	ASSIGN_VMD_DMA_OPS(source, dest, dma_supported);
-#ifdef ARCH_HAS_DMA_GET_REQUIRED_MASK
 	ASSIGN_VMD_DMA_OPS(source, dest, get_required_mask);
-#endif
 	add_dma_domain(domain);
 }
 #undef ASSIGN_VMD_DMA_OPS
-#else
-static void vmd_teardown_dma_ops(struct vmd_dev *vmd) {}
-static void vmd_setup_dma_ops(struct vmd_dev *vmd) {}
-#endif
 
 static char __iomem *vmd_cfg_addr(struct vmd_dev *vmd, struct pci_bus *bus,
 				  unsigned int devfn, int reg, int len)
 {
 	char __iomem *addr = vmd->cfgbar +
-			     (bus->number << 20) + (devfn << 12) + reg;
+			     ((bus->number - vmd->busn_start) << 20) +
+			     (devfn << 12) + reg;
 
 	if ((addr - vmd->cfgbar) + len >=
 	    resource_size(&vmd->dev->resource[VMD_CFGBAR]))
@@ -588,7 +568,8 @@
 	unsigned long flags;
 	LIST_HEAD(resources);
 	resource_size_t offset[2] = {0};
-	resource_size_t membar2_offset = 0x2000, busn_start = 0;
+	resource_size_t membar2_offset = 0x2000;
+	struct pci_bus *child;
 
 	/*
 	 * Shadow registers may exist in certain VMD device ids which allow
@@ -600,7 +581,7 @@
 		u32 vmlock;
 		int ret;
 
-		membar2_offset = 0x2018;
+		membar2_offset = MB2_SHADOW_OFFSET + MB2_SHADOW_SIZE;
 		ret = pci_read_config_dword(vmd->dev, PCI_REG_VMLOCK, &vmlock);
 		if (ret || vmlock == ~0)
 			return -ENODEV;
@@ -612,9 +593,9 @@
 			if (!membar2)
 				return -ENOMEM;
 			offset[0] = vmd->dev->resource[VMD_MEMBAR1].start -
-						readq(membar2 + 0x2008);
+					readq(membar2 + MB2_SHADOW_OFFSET);
 			offset[1] = vmd->dev->resource[VMD_MEMBAR2].start -
-						readq(membar2 + 0x2010);
+					readq(membar2 + MB2_SHADOW_OFFSET + 8);
 			pci_iounmap(vmd->dev, membar2);
 		}
 	}
@@ -630,14 +611,14 @@
 		pci_read_config_dword(vmd->dev, PCI_REG_VMCONFIG, &vmconfig);
 		if (BUS_RESTRICT_CAP(vmcap) &&
 		    (BUS_RESTRICT_CFG(vmconfig) == 0x1))
-			busn_start = 128;
+			vmd->busn_start = 128;
 	}
 
 	res = &vmd->dev->resource[VMD_CFGBAR];
 	vmd->resources[0] = (struct resource) {
 		.name  = "VMD CFGBAR",
-		.start = busn_start,
-		.end   = busn_start + (resource_size(res) >> 20) - 1,
+		.start = vmd->busn_start,
+		.end   = vmd->busn_start + (resource_size(res) >> 20) - 1,
 		.flags = IORESOURCE_BUS | IORESOURCE_PCI_FIXED,
 	};
 
@@ -651,7 +632,7 @@
 	 * 32-bit resources.  __pci_assign_resource() enforces that
 	 * artificial restriction to make sure everything will fit.
 	 *
-	 * The only way we could use a 64-bit non-prefechable MEMBAR is
+	 * The only way we could use a 64-bit non-prefetchable MEMBAR is
 	 * if its address is <4GB so that we can convert it to a 32-bit
 	 * resource.  To be visible to the host OS, all VMD endpoints must
 	 * be initially configured by platform BIOS, which includes setting
@@ -705,8 +686,8 @@
 	pci_add_resource_offset(&resources, &vmd->resources[1], offset[0]);
 	pci_add_resource_offset(&resources, &vmd->resources[2], offset[1]);
 
-	vmd->bus = pci_create_root_bus(&vmd->dev->dev, busn_start, &vmd_ops,
-				       sd, &resources);
+	vmd->bus = pci_create_root_bus(&vmd->dev->dev, vmd->busn_start,
+				       &vmd_ops, sd, &resources);
 	if (!vmd->bus) {
 		pci_free_resource_list(&resources);
 		irq_domain_remove(vmd->irq_domain);
@@ -716,7 +697,19 @@
 	vmd_attach_resources(vmd);
 	vmd_setup_dma_ops(vmd);
 	dev_set_msi_domain(&vmd->bus->dev, vmd->irq_domain);
-	pci_rescan_bus(vmd->bus);
+
+	pci_scan_child_bus(vmd->bus);
+	pci_assign_unassigned_bus_resources(vmd->bus);
+
+	/*
+	 * VMD root buses are virtual and don't return true on pci_is_pcie()
+	 * and will fail pcie_bus_configure_settings() early. It can instead be
+	 * run on each of the real root ports.
+	 */
+	list_for_each_entry(child, &vmd->bus->children, node)
+		pcie_bus_configure_settings(child);
+
+	pci_bus_add_devices(vmd->bus);
 
 	WARN(sysfs_create_link(&vmd->dev->dev.kobj, &vmd->bus->dev.kobj,
 			       "domain"), "Can't create symlink to domain\n");
@@ -813,12 +806,12 @@
 {
 	struct vmd_dev *vmd = pci_get_drvdata(dev);
 
-	vmd_detach_resources(vmd);
 	sysfs_remove_link(&vmd->dev->dev.kobj, "domain");
 	pci_stop_root_bus(vmd->bus);
 	pci_remove_root_bus(vmd->bus);
 	vmd_cleanup_srcu(vmd);
 	vmd_teardown_dma_ops(vmd);
+	vmd_detach_resources(vmd);
 	irq_domain_remove(vmd->irq_domain);
 }