Merge branch 'next' into for-linus

Prepare input updates for 5.15 merge window.

35 files changed, 2164 insertions, 591 deletions

diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index 5aa8977d7b0f..2f2c8a1729f9 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -41,7 +41,6 @@ config PCI_TEGRA
 	bool "NVIDIA Tegra PCIe controller"
 	depends on ARCH_TEGRA || COMPILE_TEST
 	depends on PCI_MSI_IRQ_DOMAIN
-	select PCI_MSI_ARCH_FALLBACKS
 	help
 	  Say Y here if you want support for the PCIe host controller found
 	  on NVIDIA Tegra SoCs.
@@ -59,7 +58,6 @@ config PCIE_RCAR_HOST
 	bool "Renesas R-Car PCIe host controller"
 	depends on ARCH_RENESAS || COMPILE_TEST
 	depends on PCI_MSI_IRQ_DOMAIN
-	select PCI_MSI_ARCH_FALLBACKS
 	help
 	  Say Y here if you want PCIe controller support on R-Car SoCs in host
 	  mode.
@@ -88,7 +86,7 @@ config PCI_HOST_GENERIC
 config PCIE_XILINX
 	bool "Xilinx AXI PCIe host bridge support"
 	depends on OF || COMPILE_TEST
-	select PCI_MSI_ARCH_FALLBACKS
+	depends on PCI_MSI_IRQ_DOMAIN
 	help
 	  Say 'Y' here if you want kernel to support the Xilinx AXI PCIe
 	  Host Bridge driver.
@@ -233,6 +231,19 @@ config PCIE_MEDIATEK
 	  Say Y here if you want to enable PCIe controller support on
 	  MediaTek SoCs.
 
+config PCIE_MEDIATEK_GEN3
+	tristate "MediaTek Gen3 PCIe controller"
+	depends on ARCH_MEDIATEK || COMPILE_TEST
+	depends on PCI_MSI_IRQ_DOMAIN
+	help
+	  Adds support for PCIe Gen3 MAC controller for MediaTek SoCs.
+	  This PCIe controller is compatible with Gen3, Gen2 and Gen1 speed,
+	  and support up to 256 MSI interrupt numbers for
+	  multi-function devices.
+
+	  Say Y here if you want to enable Gen3 PCIe controller support on
+	  MediaTek SoCs.
+
 config VMD
 	depends on PCI_MSI && X86_64 && SRCU
 	tristate "Intel Volume Management Device Driver"
diff --git a/drivers/pci/controller/Makefile b/drivers/pci/controller/Makefile
index e4559f2182f2..63e3880a3e87 100644
--- a/drivers/pci/controller/Makefile
+++ b/drivers/pci/controller/Makefile
@@ -11,10 +11,13 @@ obj-$(CONFIG_PCIE_RCAR_HOST) += pcie-rcar.o pcie-rcar-host.o
 obj-$(CONFIG_PCIE_RCAR_EP) += pcie-rcar.o pcie-rcar-ep.o
 obj-$(CONFIG_PCI_HOST_COMMON) += pci-host-common.o
 obj-$(CONFIG_PCI_HOST_GENERIC) += pci-host-generic.o
+obj-$(CONFIG_PCI_HOST_THUNDER_ECAM) += pci-thunder-ecam.o
+obj-$(CONFIG_PCI_HOST_THUNDER_PEM) += pci-thunder-pem.o
 obj-$(CONFIG_PCIE_XILINX) += pcie-xilinx.o
 obj-$(CONFIG_PCIE_XILINX_NWL) += pcie-xilinx-nwl.o
 obj-$(CONFIG_PCIE_XILINX_CPM) += pcie-xilinx-cpm.o
 obj-$(CONFIG_PCI_V3_SEMI) += pci-v3-semi.o
+obj-$(CONFIG_PCI_XGENE) += pci-xgene.o
 obj-$(CONFIG_PCI_XGENE_MSI) += pci-xgene-msi.o
 obj-$(CONFIG_PCI_VERSATILE) += pci-versatile.o
 obj-$(CONFIG_PCIE_IPROC) += pcie-iproc.o
@@ -27,6 +30,7 @@ obj-$(CONFIG_PCIE_ROCKCHIP) += pcie-rockchip.o
 obj-$(CONFIG_PCIE_ROCKCHIP_EP) += pcie-rockchip-ep.o
 obj-$(CONFIG_PCIE_ROCKCHIP_HOST) += pcie-rockchip-host.o
 obj-$(CONFIG_PCIE_MEDIATEK) += pcie-mediatek.o
+obj-$(CONFIG_PCIE_MEDIATEK_GEN3) += pcie-mediatek-gen3.o
 obj-$(CONFIG_PCIE_MICROCHIP_HOST) += pcie-microchip-host.o
 obj-$(CONFIG_VMD) += vmd.o
 obj-$(CONFIG_PCIE_BRCMSTB) += pcie-brcmstb.o
@@ -47,8 +51,10 @@ obj-y				+= mobiveil/
 # ARM64 and use internal ifdefs to only build the pieces we need
 # depending on whether ACPI, the DT driver, or both are enabled.
 
-ifdef CONFIG_PCI
+ifdef CONFIG_ACPI
+ifdef CONFIG_PCI_QUIRKS
 obj-$(CONFIG_ARM64) += pci-thunder-ecam.o
 obj-$(CONFIG_ARM64) += pci-thunder-pem.o
 obj-$(CONFIG_ARM64) += pci-xgene.o
 endif
+endif
diff --git a/drivers/pci/controller/cadence/pci-j721e.c b/drivers/pci/controller/cadence/pci-j721e.c
index 849f1e416ea5..35e61048e133 100644
--- a/drivers/pci/controller/cadence/pci-j721e.c
+++ b/drivers/pci/controller/cadence/pci-j721e.c
@@ -1,11 +1,12 @@
 // SPDX-License-Identifier: GPL-2.0
-/**
+/*
  * pci-j721e - PCIe controller driver for TI's J721E SoCs
  *
  * Copyright (C) 2020 Texas Instruments Incorporated - http://www.ti.com
  * Author: Kishon Vijay Abraham I <kishon@ti.com>
  */
 
+#include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
 #include <linux/io.h>
@@ -50,6 +51,7 @@ enum link_status {
 
 struct j721e_pcie {
 	struct device		*dev;
+	struct clk		*refclk;
 	u32			mode;
 	u32			num_lanes;
 	struct cdns_pcie	*cdns_pcie;
@@ -312,6 +314,7 @@ static int j721e_pcie_probe(struct platform_device *pdev)
 	struct cdns_pcie_ep *ep;
 	struct gpio_desc *gpiod;
 	void __iomem *base;
+	struct clk *clk;
 	u32 num_lanes;
 	u32 mode;
 	int ret;
@@ -411,6 +414,20 @@ static int j721e_pcie_probe(struct platform_device *pdev)
 			goto err_get_sync;
 		}
 
+		clk = devm_clk_get_optional(dev, "pcie_refclk");
+		if (IS_ERR(clk)) {
+			ret = PTR_ERR(clk);
+			dev_err(dev, "failed to get pcie_refclk\n");
+			goto err_pcie_setup;
+		}
+
+		ret = clk_prepare_enable(clk);
+		if (ret) {
+			dev_err(dev, "failed to enable pcie_refclk\n");
+			goto err_get_sync;
+		}
+		pcie->refclk = clk;
+
 		/*
 		 * "Power Sequencing and Reset Signal Timings" table in
 		 * PCI EXPRESS CARD ELECTROMECHANICAL SPECIFICATION, REV. 3.0
@@ -425,8 +442,10 @@ static int j721e_pcie_probe(struct platform_device *pdev)
 		}
 
 		ret = cdns_pcie_host_setup(rc);
-		if (ret < 0)
+		if (ret < 0) {
+			clk_disable_unprepare(pcie->refclk);
 			goto err_pcie_setup;
+		}
 
 		break;
 	case PCI_MODE_EP:
@@ -479,6 +498,7 @@ static int j721e_pcie_remove(struct platform_device *pdev)
 	struct cdns_pcie *cdns_pcie = pcie->cdns_pcie;
 	struct device *dev = &pdev->dev;
 
+	clk_disable_unprepare(pcie->refclk);
 	cdns_pcie_disable_phy(cdns_pcie);
 	pm_runtime_put(dev);
 	pm_runtime_disable(dev);
diff --git a/drivers/pci/controller/cadence/pcie-cadence-host.c b/drivers/pci/controller/cadence/pcie-cadence-host.c
index 73dcf8cf98fb..ae1c55503513 100644
--- a/drivers/pci/controller/cadence/pcie-cadence-host.c
+++ b/drivers/pci/controller/cadence/pcie-cadence-host.c
@@ -345,7 +345,8 @@ static int cdns_pcie_host_bar_config(struct cdns_pcie_rc *rc,
 	return 0;
 }
 
-static int cdns_pcie_host_dma_ranges_cmp(void *priv, struct list_head *a, struct list_head *b)
+static int cdns_pcie_host_dma_ranges_cmp(void *priv, const struct list_head *a,
+					 const struct list_head *b)
 {
 	struct resource_entry *entry1, *entry2;
 
diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig
index 22c5529e9a65..423d35872ce4 100644
--- a/drivers/pci/controller/dwc/Kconfig
+++ b/drivers/pci/controller/dwc/Kconfig
@@ -280,7 +280,7 @@ config PCIE_TEGRA194_EP
 	select PCIE_TEGRA194
 	help
 	  Enables support for the PCIe controller in the NVIDIA Tegra194 SoC to
-	  work in host mode. There are two instances of PCIe controllers in
+	  work in endpoint mode. There are two instances of PCIe controllers in
 	  Tegra194. This controller can work either as EP or RC. In order to
 	  enable host-specific features PCIE_TEGRA194_HOST must be selected and
 	  in order to enable device-specific features PCIE_TEGRA194_EP must be
@@ -311,6 +311,7 @@ config PCIE_AL
 	depends on OF && (ARM64 || COMPILE_TEST)
 	depends on PCI_MSI_IRQ_DOMAIN
 	select PCIE_DW_HOST
+	select PCI_ECAM
 	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
@@ -318,4 +319,13 @@ config PCIE_AL
 	  required only for DT-based platforms. ACPI platforms with the
 	  Annapurna Labs PCIe controller don't need to enable this.
 
+config PCIE_FU740
+	bool "SiFive FU740 PCIe host controller"
+	depends on PCI_MSI_IRQ_DOMAIN
+	depends on SOC_SIFIVE || COMPILE_TEST
+	select PCIE_DW_HOST
+	help
+	  Say Y here if you want PCIe controller support for the SiFive
+	  FU740.
+
 endmenu
diff --git a/drivers/pci/controller/dwc/Makefile b/drivers/pci/controller/dwc/Makefile
index a751553fa0db..9e6ce0dc2f53 100644
--- a/drivers/pci/controller/dwc/Makefile
+++ b/drivers/pci/controller/dwc/Makefile
@@ -5,6 +5,7 @@ obj-$(CONFIG_PCIE_DW_EP) += pcie-designware-ep.o
 obj-$(CONFIG_PCIE_DW_PLAT) += pcie-designware-plat.o
 obj-$(CONFIG_PCI_DRA7XX) += pci-dra7xx.o
 obj-$(CONFIG_PCI_EXYNOS) += pci-exynos.o
+obj-$(CONFIG_PCIE_FU740) += pcie-fu740.o
 obj-$(CONFIG_PCI_IMX6) += pci-imx6.o
 obj-$(CONFIG_PCIE_SPEAR13XX) += pcie-spear13xx.o
 obj-$(CONFIG_PCI_KEYSTONE) += pci-keystone.o
@@ -31,7 +32,13 @@ obj-$(CONFIG_PCIE_UNIPHIER_EP) += pcie-uniphier-ep.o
 # ARM64 and use internal ifdefs to only build the pieces we need
 # depending on whether ACPI, the DT driver, or both are enabled.
 
-ifdef CONFIG_PCI
+obj-$(CONFIG_PCIE_AL) += pcie-al.o
+obj-$(CONFIG_PCI_HISI) += pcie-hisi.o
+
+ifdef CONFIG_ACPI
+ifdef CONFIG_PCI_QUIRKS
 obj-$(CONFIG_ARM64) += pcie-al.o
 obj-$(CONFIG_ARM64) += pcie-hisi.o
+obj-$(CONFIG_ARM64) += pcie-tegra194-acpi.o
+endif
 endif
diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c
index b105af63854a..047cfbdc1330 100644
--- a/drivers/pci/controller/dwc/pci-dra7xx.c
+++ b/drivers/pci/controller/dwc/pci-dra7xx.c
@@ -443,8 +443,8 @@ static const struct dw_pcie_ep_ops pcie_ep_ops = {
 	.get_features = dra7xx_pcie_get_features,
 };
 
-static int __init dra7xx_add_pcie_ep(struct dra7xx_pcie *dra7xx,
-				     struct platform_device *pdev)
+static int dra7xx_add_pcie_ep(struct dra7xx_pcie *dra7xx,
+			      struct platform_device *pdev)
 {
 	int ret;
 	struct dw_pcie_ep *ep;
@@ -472,8 +472,8 @@ static int __init dra7xx_add_pcie_ep(struct dra7xx_pcie *dra7xx,
 	return 0;
 }
 
-static int __init dra7xx_add_pcie_port(struct dra7xx_pcie *dra7xx,
-				       struct platform_device *pdev)
+static int dra7xx_add_pcie_port(struct dra7xx_pcie *dra7xx,
+				struct platform_device *pdev)
 {
 	int ret;
 	struct dw_pcie *pci = dra7xx->pci;
@@ -682,7 +682,7 @@ static int dra7xx_pcie_configure_two_lane(struct device *dev,
 	return 0;
 }
 
-static int __init dra7xx_pcie_probe(struct platform_device *pdev)
+static int dra7xx_pcie_probe(struct platform_device *pdev)
 {
 	u32 reg;
 	int ret;
@@ -938,6 +938,7 @@ static const struct dev_pm_ops dra7xx_pcie_pm_ops = {
 };
 
 static struct platform_driver dra7xx_pcie_driver = {
+	.probe = dra7xx_pcie_probe,
 	.driver = {
 		.name	= "dra7-pcie",
 		.of_match_table = of_dra7xx_pcie_match,
@@ -946,4 +947,4 @@ static struct platform_driver dra7xx_pcie_driver = {
 	},
 	.shutdown = dra7xx_pcie_shutdown,
 };
-builtin_platform_driver_probe(dra7xx_pcie_driver, dra7xx_pcie_probe);
+builtin_platform_driver(dra7xx_pcie_driver);
diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index 53aa35cb3a49..bde3b2824e89 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -346,8 +346,9 @@ static const struct irq_domain_ops ks_pcie_legacy_irq_domain_ops = {
 };
 
 /**
- * ks_pcie_set_dbi_mode() - Set DBI mode to access overlaid BAR mask
- * registers
+ * ks_pcie_set_dbi_mode() - Set DBI mode to access overlaid BAR mask registers
+ * @ks_pcie: A pointer to the keystone_pcie structure which holds the KeyStone
+ *	     PCIe host controller driver information.
  *
  * Since modification of dbi_cs2 involves different clock domain, read the
  * status back to ensure the transition is complete.
@@ -367,6 +368,8 @@ static void ks_pcie_set_dbi_mode(struct keystone_pcie *ks_pcie)
 
 /**
  * ks_pcie_clear_dbi_mode() - Disable DBI mode
+ * @ks_pcie: A pointer to the keystone_pcie structure which holds the KeyStone
+ *	     PCIe host controller driver information.
  *
  * Since modification of dbi_cs2 involves different clock domain, read the
  * status back to ensure the transition is complete.
@@ -449,6 +452,7 @@ static struct pci_ops ks_child_pcie_ops = {
 
 /**
  * ks_pcie_v3_65_add_bus() - keystone add_bus post initialization
+ * @bus: A pointer to the PCI bus structure.
  *
  * This sets BAR0 to enable inbound access for MSI_IRQ register
  */
@@ -488,6 +492,8 @@ static struct pci_ops ks_pcie_ops = {
 
 /**
  * ks_pcie_link_up() - Check if link up
+ * @pci: A pointer to the dw_pcie structure which holds the DesignWare PCIe host
+ *	 controller driver information.
  */
 static int ks_pcie_link_up(struct dw_pcie *pci)
 {
@@ -605,7 +611,6 @@ static void ks_pcie_msi_irq_handler(struct irq_desc *desc)
 
 /**
  * ks_pcie_legacy_irq_handler() - Handle legacy interrupt
- * @irq: IRQ line for legacy interrupts
  * @desc: Pointer to irq descriptor
  *
  * Traverse through pending legacy interrupts and invoke handler for each. Also
@@ -798,7 +803,8 @@ static int __init ks_pcie_host_init(struct pcie_port *pp)
 	int ret;
 
 	pp->bridge->ops = &ks_pcie_ops;
-	pp->bridge->child_ops = &ks_child_pcie_ops;
+	if (!ks_pcie->is_am6)
+		pp->bridge->child_ops = &ks_child_pcie_ops;
 
 	ret = ks_pcie_config_legacy_irq(ks_pcie);
 	if (ret)
diff --git a/drivers/pci/controller/dwc/pci-layerscape-ep.c b/drivers/pci/controller/dwc/pci-layerscape-ep.c
index 39fe2ed5a6a2..39f4664bd84c 100644
--- a/drivers/pci/controller/dwc/pci-layerscape-ep.c
+++ b/drivers/pci/controller/dwc/pci-layerscape-ep.c
@@ -154,7 +154,7 @@ static int __init ls_pcie_ep_probe(struct platform_device *pdev)
 	pci->dev = dev;
 	pci->ops = pcie->drvdata->dw_pcie_ops;
 
-	ls_epc->bar_fixed_64bit = (1 << BAR_2) | (1 << BAR_4),
+	ls_epc->bar_fixed_64bit = (1 << BAR_2) | (1 << BAR_4);
 
 	pcie->pci = pci;
 	pcie->ls_epc = ls_epc;
diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 1c25d8337151..8d028a88b375 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -705,6 +705,8 @@ int dw_pcie_ep_init(struct dw_pcie_ep *ep)
 		}
 	}
 
+	dw_pcie_iatu_detect(pci);
+
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "addr_space");
 	if (!res)
 		return -EINVAL;
diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index 7e55b2b66182..a608ae1fad57 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -398,9 +398,9 @@ int dw_pcie_host_init(struct pcie_port *pp)
 		if (ret)
 			goto err_free_msi;
 	}
+	dw_pcie_iatu_detect(pci);
 
 	dw_pcie_setup_rc(pp);
-	dw_pcie_msi_init(pp);
 
 	if (!dw_pcie_link_up(pci) && pci->ops && pci->ops->start_link) {
 		ret = pci->ops->start_link(pci);
@@ -551,6 +551,8 @@ void dw_pcie_setup_rc(struct pcie_port *pp)
 		}
 	}
 
+	dw_pcie_msi_init(pp);
+
 	/* Setup RC BARs */
 	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 0x00000004);
 	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_1, 0x00000000);
diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c
index 004cb860e266..a945f0c0e73d 100644
--- a/drivers/pci/controller/dwc/pcie-designware.c
+++ b/drivers/pci/controller/dwc/pcie-designware.c
@@ -660,11 +660,9 @@ static void dw_pcie_iatu_detect_regions(struct dw_pcie *pci)
 	pci->num_ob_windows = ob;
 }
 
-void dw_pcie_setup(struct dw_pcie *pci)
+void dw_pcie_iatu_detect(struct dw_pcie *pci)
 {
-	u32 val;
 	struct device *dev = pci->dev;
-	struct device_node *np = dev->of_node;
 	struct platform_device *pdev = to_platform_device(dev);
 
 	if (pci->version >= 0x480A || (!pci->version &&
@@ -693,6 +691,13 @@ void dw_pcie_setup(struct dw_pcie *pci)
 
 	dev_info(pci->dev, "Detected iATU regions: %u outbound, %u inbound",
 		 pci->num_ob_windows, pci->num_ib_windows);
+}
+
+void dw_pcie_setup(struct dw_pcie *pci)
+{
+	u32 val;
+	struct device *dev = pci->dev;
+	struct device_node *np = dev->of_node;
 
 	if (pci->link_gen > 0)
 		dw_pcie_link_set_max_speed(pci, pci->link_gen);
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index 7247c8b01f04..7d6e9b7576be 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -306,6 +306,7 @@ int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, u8 func_no, int index,
 void dw_pcie_disable_atu(struct dw_pcie *pci, int index,
 			 enum dw_pcie_region_type type);
 void dw_pcie_setup(struct dw_pcie *pci);
+void dw_pcie_iatu_detect(struct dw_pcie *pci);
 
 static inline void dw_pcie_writel_dbi(struct dw_pcie *pci, u32 reg, u32 val)
 {
diff --git a/drivers/pci/controller/dwc/pcie-fu740.c b/drivers/pci/controller/dwc/pcie-fu740.c
new file mode 100644
index 000000000000..00cde9a248b5
--- /dev/null
+++ b/drivers/pci/controller/dwc/pcie-fu740.c
@@ -0,0 +1,309 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * FU740 DesignWare PCIe Controller integration
+ * Copyright (C) 2019-2021 SiFive, Inc.
+ * Paul Walmsley
+ * Greentime Hu
+ *
+ * Based in part on the i.MX6 PCIe host controller shim which is:
+ *
+ * Copyright (C) 2013 Kosagi
+ *		https://www.kosagi.com
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/gpio.h>
+#include <linux/gpio/consumer.h>
+#include <linux/kernel.h>
+#include <linux/mfd/syscon.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/consumer.h>
+#include <linux/resource.h>
+#include <linux/types.h>
+#include <linux/interrupt.h>
+#include <linux/iopoll.h>
+#include <linux/reset.h>
+
+#include "pcie-designware.h"
+
+#define to_fu740_pcie(x)	dev_get_drvdata((x)->dev)
+
+struct fu740_pcie {
+	struct dw_pcie pci;
+	void __iomem *mgmt_base;
+	struct gpio_desc *reset;
+	struct gpio_desc *pwren;
+	struct clk *pcie_aux;
+	struct reset_control *rst;
+};
+
+#define SIFIVE_DEVICESRESETREG		0x28
+
+#define PCIEX8MGMT_PERST_N		0x0
+#define PCIEX8MGMT_APP_LTSSM_ENABLE	0x10
+#define PCIEX8MGMT_APP_HOLD_PHY_RST	0x18
+#define PCIEX8MGMT_DEVICE_TYPE		0x708
+#define PCIEX8MGMT_PHY0_CR_PARA_ADDR	0x860
+#define PCIEX8MGMT_PHY0_CR_PARA_RD_EN	0x870
+#define PCIEX8MGMT_PHY0_CR_PARA_RD_DATA	0x878
+#define PCIEX8MGMT_PHY0_CR_PARA_SEL	0x880
+#define PCIEX8MGMT_PHY0_CR_PARA_WR_DATA	0x888
+#define PCIEX8MGMT_PHY0_CR_PARA_WR_EN	0x890
+#define PCIEX8MGMT_PHY0_CR_PARA_ACK	0x898
+#define PCIEX8MGMT_PHY1_CR_PARA_ADDR	0x8a0
+#define PCIEX8MGMT_PHY1_CR_PARA_RD_EN	0x8b0
+#define PCIEX8MGMT_PHY1_CR_PARA_RD_DATA	0x8b8
+#define PCIEX8MGMT_PHY1_CR_PARA_SEL	0x8c0
+#define PCIEX8MGMT_PHY1_CR_PARA_WR_DATA	0x8c8
+#define PCIEX8MGMT_PHY1_CR_PARA_WR_EN	0x8d0
+#define PCIEX8MGMT_PHY1_CR_PARA_ACK	0x8d8
+
+#define PCIEX8MGMT_PHY_CDR_TRACK_EN	BIT(0)
+#define PCIEX8MGMT_PHY_LOS_THRSHLD	BIT(5)
+#define PCIEX8MGMT_PHY_TERM_EN		BIT(9)
+#define PCIEX8MGMT_PHY_TERM_ACDC	BIT(10)
+#define PCIEX8MGMT_PHY_EN		BIT(11)
+#define PCIEX8MGMT_PHY_INIT_VAL		(PCIEX8MGMT_PHY_CDR_TRACK_EN|\
+					 PCIEX8MGMT_PHY_LOS_THRSHLD|\
+					 PCIEX8MGMT_PHY_TERM_EN|\
+					 PCIEX8MGMT_PHY_TERM_ACDC|\
+					 PCIEX8MGMT_PHY_EN)
+
+#define PCIEX8MGMT_PHY_LANEN_DIG_ASIC_RX_OVRD_IN_3	0x1008
+#define PCIEX8MGMT_PHY_LANE_OFF		0x100
+#define PCIEX8MGMT_PHY_LANE0_BASE	(PCIEX8MGMT_PHY_LANEN_DIG_ASIC_RX_OVRD_IN_3 + 0x100 * 0)
+#define PCIEX8MGMT_PHY_LANE1_BASE	(PCIEX8MGMT_PHY_LANEN_DIG_ASIC_RX_OVRD_IN_3 + 0x100 * 1)
+#define PCIEX8MGMT_PHY_LANE2_BASE	(PCIEX8MGMT_PHY_LANEN_DIG_ASIC_RX_OVRD_IN_3 + 0x100 * 2)
+#define PCIEX8MGMT_PHY_LANE3_BASE	(PCIEX8MGMT_PHY_LANEN_DIG_ASIC_RX_OVRD_IN_3 + 0x100 * 3)
+
+static void fu740_pcie_assert_reset(struct fu740_pcie *afp)
+{
+	/* Assert PERST_N GPIO */
+	gpiod_set_value_cansleep(afp->reset, 0);
+	/* Assert controller PERST_N */
+	writel_relaxed(0x0, afp->mgmt_base + PCIEX8MGMT_PERST_N);
+}
+
+static void fu740_pcie_deassert_reset(struct fu740_pcie *afp)
+{
+	/* Deassert controller PERST_N */
+	writel_relaxed(0x1, afp->mgmt_base + PCIEX8MGMT_PERST_N);
+	/* Deassert PERST_N GPIO */
+	gpiod_set_value_cansleep(afp->reset, 1);
+}
+
+static void fu740_pcie_power_on(struct fu740_pcie *afp)
+{
+	gpiod_set_value_cansleep(afp->pwren, 1);
+	/*
+	 * Ensure that PERST has been asserted for at least 100 ms.
+	 * Section 2.2 of PCI Express Card Electromechanical Specification
+	 * Revision 3.0
+	 */
+	msleep(100);
+}
+
+static void fu740_pcie_drive_reset(struct fu740_pcie *afp)
+{
+	fu740_pcie_assert_reset(afp);
+	fu740_pcie_power_on(afp);
+	fu740_pcie_deassert_reset(afp);
+}
+
+static void fu740_phyregwrite(const uint8_t phy, const uint16_t addr,
+			      const uint16_t wrdata, struct fu740_pcie *afp)
+{
+	struct device *dev = afp->pci.dev;
+	void __iomem *phy_cr_para_addr;
+	void __iomem *phy_cr_para_wr_data;
+	void __iomem *phy_cr_para_wr_en;
+	void __iomem *phy_cr_para_ack;
+	int ret, val;
+
+	/* Setup */
+	if (phy) {
+		phy_cr_para_addr = afp->mgmt_base + PCIEX8MGMT_PHY1_CR_PARA_ADDR;
+		phy_cr_para_wr_data = afp->mgmt_base + PCIEX8MGMT_PHY1_CR_PARA_WR_DATA;
+		phy_cr_para_wr_en = afp->mgmt_base + PCIEX8MGMT_PHY1_CR_PARA_WR_EN;
+		phy_cr_para_ack = afp->mgmt_base + PCIEX8MGMT_PHY1_CR_PARA_ACK;
+	} else {
+		phy_cr_para_addr = afp->mgmt_base + PCIEX8MGMT_PHY0_CR_PARA_ADDR;
+		phy_cr_para_wr_data = afp->mgmt_base + PCIEX8MGMT_PHY0_CR_PARA_WR_DATA;
+		phy_cr_para_wr_en = afp->mgmt_base + PCIEX8MGMT_PHY0_CR_PARA_WR_EN;
+		phy_cr_para_ack = afp->mgmt_base + PCIEX8MGMT_PHY0_CR_PARA_ACK;
+	}
+
+	writel_relaxed(addr, phy_cr_para_addr);
+	writel_relaxed(wrdata, phy_cr_para_wr_data);
+	writel_relaxed(1, phy_cr_para_wr_en);
+
+	/* Wait for wait_idle */
+	ret = readl_poll_timeout(phy_cr_para_ack, val, val, 10, 5000);
+	if (ret)
+		dev_warn(dev, "Wait for wait_idle state failed!\n");
+
+	/* Clear */
+	writel_relaxed(0, phy_cr_para_wr_en);
+
+	/* Wait for ~wait_idle */
+	ret = readl_poll_timeout(phy_cr_para_ack, val, !val, 10, 5000);
+	if (ret)
+		dev_warn(dev, "Wait for !wait_idle state failed!\n");
+}
+
+static void fu740_pcie_init_phy(struct fu740_pcie *afp)
+{
+	/* Enable phy cr_para_sel interfaces */
+	writel_relaxed(0x1, afp->mgmt_base + PCIEX8MGMT_PHY0_CR_PARA_SEL);
+	writel_relaxed(0x1, afp->mgmt_base + PCIEX8MGMT_PHY1_CR_PARA_SEL);
+
+	/*
+	 * Wait 10 cr_para cycles to guarantee that the registers are ready
+	 * to be edited.
+	 */
+	ndelay(10);
+
+	/* Set PHY AC termination mode */
+	fu740_phyregwrite(0, PCIEX8MGMT_PHY_LANE0_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp);
+	fu740_phyregwrite(0, PCIEX8MGMT_PHY_LANE1_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp);
+	fu740_phyregwrite(0, PCIEX8MGMT_PHY_LANE2_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp);
+	fu740_phyregwrite(0, PCIEX8MGMT_PHY_LANE3_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp);
+	fu740_phyregwrite(1, PCIEX8MGMT_PHY_LANE0_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp);
+	fu740_phyregwrite(1, PCIEX8MGMT_PHY_LANE1_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp);
+	fu740_phyregwrite(1, PCIEX8MGMT_PHY_LANE2_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp);
+	fu740_phyregwrite(1, PCIEX8MGMT_PHY_LANE3_BASE, PCIEX8MGMT_PHY_INIT_VAL, afp);
+}
+
+static int fu740_pcie_start_link(struct dw_pcie *pci)
+{
+	struct device *dev = pci->dev;
+	struct fu740_pcie *afp = dev_get_drvdata(dev);
+
+	/* Enable LTSSM */
+	writel_relaxed(0x1, afp->mgmt_base + PCIEX8MGMT_APP_LTSSM_ENABLE);
+	return 0;
+}
+
+static int fu740_pcie_host_init(struct pcie_port *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct fu740_pcie *afp = to_fu740_pcie(pci);
+	struct device *dev = pci->dev;
+	int ret;
+
+	/* Power on reset */
+	fu740_pcie_drive_reset(afp);
+
+	/* Enable pcieauxclk */
+	ret = clk_prepare_enable(afp->pcie_aux);
+	if (ret) {
+		dev_err(dev, "unable to enable pcie_aux clock\n");
+		return ret;
+	}
+
+	/*
+	 * Assert hold_phy_rst (hold the controller LTSSM in reset after
+	 * power_up_rst_n for register programming with cr_para)
+	 */
+	writel_relaxed(0x1, afp->mgmt_base + PCIEX8MGMT_APP_HOLD_PHY_RST);
+
+	/* Deassert power_up_rst_n */
+	ret = reset_control_deassert(afp->rst);
+	if (ret) {
+		dev_err(dev, "unable to deassert pcie_power_up_rst_n\n");
+		return ret;
+	}
+
+	fu740_pcie_init_phy(afp);
+
+	/* Disable pcieauxclk */
+	clk_disable_unprepare(afp->pcie_aux);
+	/* Clear hold_phy_rst */
+	writel_relaxed(0x0, afp->mgmt_base + PCIEX8MGMT_APP_HOLD_PHY_RST);
+	/* Enable pcieauxclk */
+	ret = clk_prepare_enable(afp->pcie_aux);
+	/* Set RC mode */
+	writel_relaxed(0x4, afp->mgmt_base + PCIEX8MGMT_DEVICE_TYPE);
+
+	return 0;
+}
+
+static const struct dw_pcie_host_ops fu740_pcie_host_ops = {
+	.host_init = fu740_pcie_host_init,
+};
+
+static const struct dw_pcie_ops dw_pcie_ops = {
+	.start_link = fu740_pcie_start_link,
+};
+
+static int fu740_pcie_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct dw_pcie *pci;
+	struct fu740_pcie *afp;
+
+	afp = devm_kzalloc(dev, sizeof(*afp), GFP_KERNEL);
+	if (!afp)
+		return -ENOMEM;
+	pci = &afp->pci;
+	pci->dev = dev;
+	pci->ops = &dw_pcie_ops;
+	pci->pp.ops = &fu740_pcie_host_ops;
+
+	/* SiFive specific region: mgmt */
+	afp->mgmt_base = devm_platform_ioremap_resource_byname(pdev, "mgmt");
+	if (IS_ERR(afp->mgmt_base))
+		return PTR_ERR(afp->mgmt_base);
+
+	/* Fetch GPIOs */
+	afp->reset = devm_gpiod_get_optional(dev, "reset-gpios", GPIOD_OUT_LOW);
+	if (IS_ERR(afp->reset))
+		return dev_err_probe(dev, PTR_ERR(afp->reset), "unable to get reset-gpios\n");
+
+	afp->pwren = devm_gpiod_get_optional(dev, "pwren-gpios", GPIOD_OUT_LOW);
+	if (IS_ERR(afp->pwren))
+		return dev_err_probe(dev, PTR_ERR(afp->pwren), "unable to get pwren-gpios\n");
+
+	/* Fetch clocks */
+	afp->pcie_aux = devm_clk_get(dev, "pcie_aux");
+	if (IS_ERR(afp->pcie_aux))
+		return dev_err_probe(dev, PTR_ERR(afp->pcie_aux),
+					     "pcie_aux clock source missing or invalid\n");
+
+	/* Fetch reset */
+	afp->rst = devm_reset_control_get_exclusive(dev, NULL);
+	if (IS_ERR(afp->rst))
+		return dev_err_probe(dev, PTR_ERR(afp->rst), "unable to get reset\n");
+
+	platform_set_drvdata(pdev, afp);
+
+	return dw_pcie_host_init(&pci->pp);
+}
+
+static void fu740_pcie_shutdown(struct platform_device *pdev)
+{
+	struct fu740_pcie *afp = platform_get_drvdata(pdev);
+
+	/* Bring down link, so bootloader gets clean state in case of reboot */
+	fu740_pcie_assert_reset(afp);
+}
+
+static const struct of_device_id fu740_pcie_of_match[] = {
+	{ .compatible = "sifive,fu740-pcie", },
+	{},
+};
+
+static struct platform_driver fu740_pcie_driver = {
+	.driver = {
+		   .name = "fu740-pcie",
+		   .of_match_table = fu740_pcie_of_match,
+		   .suppress_bind_attrs = true,
+	},
+	.probe = fu740_pcie_probe,
+	.shutdown = fu740_pcie_shutdown,
+};
+
+builtin_platform_driver(fu740_pcie_driver);
diff --git a/drivers/pci/controller/dwc/pcie-intel-gw.c b/drivers/pci/controller/dwc/pcie-intel-gw.c
index 0cedd1f95f37..f89a7d24ba28 100644
--- a/drivers/pci/controller/dwc/pcie-intel-gw.c
+++ b/drivers/pci/controller/dwc/pcie-intel-gw.c
@@ -81,11 +81,6 @@ static void pcie_update_bits(void __iomem *base, u32 ofs, u32 mask, u32 val)
 		writel(val, base + ofs);
 }
 
-static inline u32 pcie_app_rd(struct intel_pcie_port *lpp, u32 ofs)
-{
-	return readl(lpp->app_base + ofs);
-}
-
 static inline void pcie_app_wr(struct intel_pcie_port *lpp, u32 ofs, u32 val)
 {
 	writel(val, lpp->app_base + ofs);
diff --git a/drivers/pci/controller/dwc/pcie-tegra194-acpi.c b/drivers/pci/controller/dwc/pcie-tegra194-acpi.c
new file mode 100644
index 000000000000..c2de6ed4d86f
--- /dev/null
+++ b/drivers/pci/controller/dwc/pcie-tegra194-acpi.c
@@ -0,0 +1,108 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * ACPI quirks for Tegra194 PCIe host controller
+ *
+ * Copyright (C) 2021 NVIDIA Corporation.
+ *
+ * Author: Vidya Sagar <vidyas@nvidia.com>
+ */
+
+#include <linux/pci.h>
+#include <linux/pci-acpi.h>
+#include <linux/pci-ecam.h>
+
+#include "pcie-designware.h"
+
+struct tegra194_pcie_ecam  {
+	void __iomem *config_base;
+	void __iomem *iatu_base;
+	void __iomem *dbi_base;
+};
+
+static int tegra194_acpi_init(struct pci_config_window *cfg)
+{
+	struct device *dev = cfg->parent;
+	struct tegra194_pcie_ecam *pcie_ecam;
+
+	pcie_ecam = devm_kzalloc(dev, sizeof(*pcie_ecam), GFP_KERNEL);
+	if (!pcie_ecam)
+		return -ENOMEM;
+
+	pcie_ecam->config_base = cfg->win;
+	pcie_ecam->iatu_base = cfg->win + SZ_256K;
+	pcie_ecam->dbi_base = cfg->win + SZ_512K;
+	cfg->priv = pcie_ecam;
+
+	return 0;
+}
+
+static void atu_reg_write(struct tegra194_pcie_ecam *pcie_ecam, int index,
+			  u32 val, u32 reg)
+{
+	u32 offset = PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(index);
+
+	writel(val, pcie_ecam->iatu_base + offset + reg);
+}
+
+static void program_outbound_atu(struct tegra194_pcie_ecam *pcie_ecam,
+				 int index, int type, u64 cpu_addr,
+				 u64 pci_addr, u64 size)
+{
+	atu_reg_write(pcie_ecam, index, lower_32_bits(cpu_addr),
+		      PCIE_ATU_LOWER_BASE);
+	atu_reg_write(pcie_ecam, index, upper_32_bits(cpu_addr),
+		      PCIE_ATU_UPPER_BASE);
+	atu_reg_write(pcie_ecam, index, lower_32_bits(pci_addr),
+		      PCIE_ATU_LOWER_TARGET);
+	atu_reg_write(pcie_ecam, index, lower_32_bits(cpu_addr + size - 1),
+		      PCIE_ATU_LIMIT);
+	atu_reg_write(pcie_ecam, index, upper_32_bits(pci_addr),
+		      PCIE_ATU_UPPER_TARGET);
+	atu_reg_write(pcie_ecam, index, type, PCIE_ATU_CR1);
+	atu_reg_write(pcie_ecam, index, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
+}
+
+static void __iomem *tegra194_map_bus(struct pci_bus *bus,
+				      unsigned int devfn, int where)
+{
+	struct pci_config_window *cfg = bus->sysdata;
+	struct tegra194_pcie_ecam *pcie_ecam = cfg->priv;
+	u32 busdev;
+	int type;
+
+	if (bus->number < cfg->busr.start || bus->number > cfg->busr.end)
+		return NULL;
+
+	if (bus->number == cfg->busr.start) {
+		if (PCI_SLOT(devfn) == 0)
+			return pcie_ecam->dbi_base + where;
+		else
+			return NULL;
+	}
+
+	busdev = PCIE_ATU_BUS(bus->number) | PCIE_ATU_DEV(PCI_SLOT(devfn)) |
+		 PCIE_ATU_FUNC(PCI_FUNC(devfn));
+
+	if (bus->parent->number == cfg->busr.start) {
+		if (PCI_SLOT(devfn) == 0)
+			type = PCIE_ATU_TYPE_CFG0;
+		else
+			return NULL;
+	} else {
+		type = PCIE_ATU_TYPE_CFG1;
+	}
+
+	program_outbound_atu(pcie_ecam, 0, type, cfg->res.start, busdev,
+			     SZ_256K);
+
+	return pcie_ecam->config_base + where;
+}
+
+const struct pci_ecam_ops tegra194_pcie_ops = {
+	.init		= tegra194_acpi_init,
+	.pci_ops	= {
+		.map_bus	= tegra194_map_bus,
+		.read		= pci_generic_config_read,
+		.write		= pci_generic_config_write,
+	}
+};
diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c
index 6fa216e52d14..504669e3afe0 100644
--- a/drivers/pci/controller/dwc/pcie-tegra194.c
+++ b/drivers/pci/controller/dwc/pcie-tegra194.c
@@ -245,24 +245,6 @@ static const unsigned int pcie_gen_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;
@@ -594,6 +576,24 @@ static struct pci_ops tegra_pci_ops = {
 };
 
 #if defined(CONFIG_PCIEASPM)
+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
+};
+
 static void disable_aspm_l11(struct tegra_pcie_dw *pcie)
 {
 	u32 val;
@@ -1019,7 +1019,7 @@ static const struct dw_pcie_ops tegra_dw_pcie_ops = {
 	.stop_link = tegra_pcie_dw_stop_link,
 };
 
-static struct dw_pcie_host_ops tegra_pcie_dw_host_ops = {
+static const struct dw_pcie_host_ops tegra_pcie_dw_host_ops = {
 	.host_init = tegra_pcie_dw_host_init,
 };
 
@@ -1645,7 +1645,7 @@ static void pex_ep_event_pex_rst_deassert(struct tegra_pcie_dw *pcie)
 	if (pcie->ep_state == EP_STATE_ENABLED)
 		return;
 
-	ret = pm_runtime_get_sync(dev);
+	ret = pm_runtime_resume_and_get(dev);
 	if (ret < 0) {
 		dev_err(dev, "Failed to get runtime sync for PCIe dev: %d\n",
 			ret);
@@ -1881,7 +1881,7 @@ tegra_pcie_ep_get_features(struct dw_pcie_ep *ep)
 	return &tegra_pcie_epc_features;
 }
 
-static struct dw_pcie_ep_ops pcie_ep_ops = {
+static const struct dw_pcie_ep_ops pcie_ep_ops = {
 	.raise_irq = tegra_pcie_ep_raise_irq,
 	.get_features = tegra_pcie_ep_get_features,
 };
diff --git a/drivers/pci/controller/mobiveil/Kconfig b/drivers/pci/controller/mobiveil/Kconfig
index a62d247018cf..e4643fb94e78 100644
--- a/drivers/pci/controller/mobiveil/Kconfig
+++ b/drivers/pci/controller/mobiveil/Kconfig
@@ -24,8 +24,7 @@ config PCIE_MOBIVEIL_PLAT
 
 config PCIE_LAYERSCAPE_GEN4
 	bool "Freescale Layerscape PCIe Gen4 controller"
-	depends on PCI
-	depends on OF && (ARM64 || ARCH_LAYERSCAPE)
+	depends on ARCH_LAYERSCAPE || COMPILE_TEST
 	depends on PCI_MSI_IRQ_DOMAIN
 	select PCIE_MOBIVEIL_HOST
 	help
diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index 051b48bd7985..e3f5e7ab7606 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -514,7 +514,7 @@ static int advk_pcie_wait_pio(struct advk_pcie *pcie)
 		udelay(PIO_RETRY_DELAY);
 	}
 
-	dev_err(dev, "config read/write timed out\n");
+	dev_err(dev, "PIO read/write transfer time out\n");
 	return -ETIMEDOUT;
 }
 
@@ -657,6 +657,35 @@ static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus,
 	return true;
 }
 
+static bool advk_pcie_pio_is_running(struct advk_pcie *pcie)
+{
+	struct device *dev = &pcie->pdev->dev;
+
+	/*
+	 * Trying to start a new PIO transfer when previous has not completed
+	 * cause External Abort on CPU which results in kernel panic:
+	 *
+	 *     SError Interrupt on CPU0, code 0xbf000002 -- SError
+	 *     Kernel panic - not syncing: Asynchronous SError Interrupt
+	 *
+	 * Functions advk_pcie_rd_conf() and advk_pcie_wr_conf() are protected
+	 * by raw_spin_lock_irqsave() at pci_lock_config() level to prevent
+	 * concurrent calls at the same time. But because PIO transfer may take
+	 * about 1.5s when link is down or card is disconnected, it means that
+	 * advk_pcie_wait_pio() does not always have to wait for completion.
+	 *
+	 * Some versions of ARM Trusted Firmware handles this External Abort at
+	 * EL3 level and mask it to prevent kernel panic. Relevant TF-A commit:
+	 * https://git.trustedfirmware.org/TF-A/trusted-firmware-a.git/commit/?id=3c7dcdac5c50
+	 */
+	if (advk_readl(pcie, PIO_START)) {
+		dev_err(dev, "Previous PIO read/write transfer is still running\n");
+		return true;
+	}
+
+	return false;
+}
+
 static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 			     int where, int size, u32 *val)
 {
@@ -673,9 +702,10 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 		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);
+	if (advk_pcie_pio_is_running(pcie)) {
+		*val = 0xffffffff;
+		return PCIBIOS_SET_FAILED;
+	}
 
 	/* Program the control register */
 	reg = advk_readl(pcie, PIO_CTRL);
@@ -694,7 +724,8 @@ static int advk_pcie_rd_conf(struct pci_bus *bus, u32 devfn,
 	/* Program the data strobe */
 	advk_writel(pcie, 0xf, PIO_WR_DATA_STRB);
 
-	/* Start the transfer */
+	/* Clear PIO DONE ISR and start the transfer */
+	advk_writel(pcie, 1, PIO_ISR);
 	advk_writel(pcie, 1, PIO_START);
 
 	ret = advk_pcie_wait_pio(pcie);
@@ -734,9 +765,8 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 	if (where % size)
 		return PCIBIOS_SET_FAILED;
 
-	/* Start PIO */
-	advk_writel(pcie, 0, PIO_START);
-	advk_writel(pcie, 1, PIO_ISR);
+	if (advk_pcie_pio_is_running(pcie))
+		return PCIBIOS_SET_FAILED;
 
 	/* Program the control register */
 	reg = advk_readl(pcie, PIO_CTRL);
@@ -763,7 +793,8 @@ static int advk_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 	/* Program the data strobe */
 	advk_writel(pcie, data_strobe, PIO_WR_DATA_STRB);
 
-	/* Start the transfer */
+	/* Clear PIO DONE ISR and start the transfer */
+	advk_writel(pcie, 1, PIO_ISR);
 	advk_writel(pcie, 1, PIO_START);
 
 	ret = advk_pcie_wait_pio(pcie);
diff --git a/drivers/pci/controller/pci-host-common.c b/drivers/pci/controller/pci-host-common.c
index 6ab694f8d283..d3924a44db02 100644
--- a/drivers/pci/controller/pci-host-common.c
+++ b/drivers/pci/controller/pci-host-common.c
@@ -79,6 +79,7 @@ int pci_host_common_probe(struct platform_device *pdev)
 
 	bridge->sysdata = cfg;
 	bridge->ops = (struct pci_ops *)&ops->pci_ops;
+	bridge->msi_domain = true;
 
 	return pci_host_probe(bridge);
 }
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 27a17a1e4a7c..6511648271b2 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -473,7 +473,6 @@ struct hv_pcibus_device {
 	struct list_head dr_list;
 
 	struct msi_domain_info msi_info;
-	struct msi_controller msi_chip;
 	struct irq_domain *irq_domain;
 
 	spinlock_t retarget_msi_interrupt_lock;
@@ -1292,7 +1291,7 @@ exit_unlock:
 	 * resumes, hv_pci_restore_msi_state() is able to correctly restore
 	 * the interrupt with the correct affinity.
 	 */
-	if (res && hbus->state != hv_pcibus_removing)
+	if (!hv_result_success(res) && hbus->state != hv_pcibus_removing)
 		dev_err(&hbus->hdev->device,
 			"%s() failed: %#llx", __func__, res);
 
@@ -1458,7 +1457,7 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 	 * Prevents hv_pci_onchannelcallback() from running concurrently
 	 * in the tasklet.
 	 */
-	tasklet_disable(&channel->callback_event);
+	tasklet_disable_in_atomic(&channel->callback_event);
 
 	/*
 	 * Since this function is called with IRQ locks held, can't
@@ -1866,9 +1865,6 @@ static int create_root_hv_pci_bus(struct hv_pcibus_device *hbus)
 	if (!hbus->pci_bus)
 		return -ENODEV;
 
-	hbus->pci_bus->msi = &hbus->msi_chip;
-	hbus->pci_bus->msi->dev = &hbus->hdev->device;
-
 	pci_lock_rescan_remove();
 	pci_scan_child_bus(hbus->pci_bus);
 	hv_pci_assign_numa_node(hbus);
diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index 8fcabed7c6a6..8069bd9232d4 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -21,6 +21,7 @@
 #include <linux/interrupt.h>
 #include <linux/iopoll.h>
 #include <linux/irq.h>
+#include <linux/irqchip/chained_irq.h>
 #include <linux/irqdomain.h>
 #include <linux/kernel.h>
 #include <linux/init.h>
@@ -78,23 +79,8 @@
 #define AFI_MSI_FPCI_BAR_ST	0x64
 #define AFI_MSI_AXI_BAR_ST	0x68
 
-#define AFI_MSI_VEC0		0x6c
-#define AFI_MSI_VEC1		0x70
-#define AFI_MSI_VEC2		0x74
-#define AFI_MSI_VEC3		0x78
-#define AFI_MSI_VEC4		0x7c
-#define AFI_MSI_VEC5		0x80
-#define AFI_MSI_VEC6		0x84
-#define AFI_MSI_VEC7		0x88
-
-#define AFI_MSI_EN_VEC0		0x8c
-#define AFI_MSI_EN_VEC1		0x90
-#define AFI_MSI_EN_VEC2		0x94
-#define AFI_MSI_EN_VEC3		0x98
-#define AFI_MSI_EN_VEC4		0x9c
-#define AFI_MSI_EN_VEC5		0xa0
-#define AFI_MSI_EN_VEC6		0xa4
-#define AFI_MSI_EN_VEC7		0xa8
+#define AFI_MSI_VEC(x)		(0x6c + ((x) * 4))
+#define AFI_MSI_EN_VEC(x)	(0x8c + ((x) * 4))
 
 #define AFI_CONFIGURATION		0xac
 #define  AFI_CONFIGURATION_EN_FPCI		(1 << 0)
@@ -280,10 +266,10 @@
 #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;
-	struct mutex lock;
+	struct mutex map_lock;
+	spinlock_t mask_lock;
 	void *virt;
 	dma_addr_t phys;
 	int irq;
@@ -333,11 +319,6 @@ struct tegra_pcie_soc {
 	} ectl;
 };
 
-static inline struct tegra_msi *to_tegra_msi(struct msi_controller *chip)
-{
-	return container_of(chip, struct tegra_msi, chip);
-}
-
 struct tegra_pcie {
 	struct device *dev;
 
@@ -372,6 +353,11 @@ struct tegra_pcie {
 	struct dentry *debugfs;
 };
 
+static inline struct tegra_pcie *msi_to_pcie(struct tegra_msi *msi)
+{
+	return container_of(msi, struct tegra_pcie, msi);
+}
+
 struct tegra_pcie_port {
 	struct tegra_pcie *pcie;
 	struct device_node *np;
@@ -1432,7 +1418,6 @@ static void tegra_pcie_phys_put(struct tegra_pcie *pcie)
 	}
 }
 
-
 static int tegra_pcie_get_resources(struct tegra_pcie *pcie)
 {
 	struct device *dev = pcie->dev;
@@ -1509,6 +1494,7 @@ static int tegra_pcie_get_resources(struct tegra_pcie *pcie)
 phys_put:
 	if (soc->program_uphy)
 		tegra_pcie_phys_put(pcie);
+
 	return err;
 }
 
@@ -1551,161 +1537,227 @@ static void tegra_pcie_pme_turnoff(struct tegra_pcie_port *port)
 	afi_writel(pcie, val, AFI_PCIE_PME);
 }
 
-static int tegra_msi_alloc(struct tegra_msi *chip)
-{
-	int msi;
-
-	mutex_lock(&chip->lock);
-
-	msi = find_first_zero_bit(chip->used, INT_PCI_MSI_NR);
-	if (msi < INT_PCI_MSI_NR)
-		set_bit(msi, chip->used);
-	else
-		msi = -ENOSPC;
-
-	mutex_unlock(&chip->lock);
-
-	return msi;
-}
-
-static void tegra_msi_free(struct tegra_msi *chip, unsigned long irq)
+static void tegra_pcie_msi_irq(struct irq_desc *desc)
 {
-	struct device *dev = chip->chip.dev;
-
-	mutex_lock(&chip->lock);
-
-	if (!test_bit(irq, chip->used))
-		dev_err(dev, "trying to free unused MSI#%lu\n", irq);
-	else
-		clear_bit(irq, chip->used);
-
-	mutex_unlock(&chip->lock);
-}
-
-static irqreturn_t tegra_pcie_msi_irq(int irq, void *data)
-{
-	struct tegra_pcie *pcie = data;
-	struct device *dev = pcie->dev;
+	struct tegra_pcie *pcie = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct tegra_msi *msi = &pcie->msi;
-	unsigned int i, processed = 0;
+	struct device *dev = pcie->dev;
+	unsigned int i;
+
+	chained_irq_enter(chip, desc);
 
 	for (i = 0; i < 8; i++) {
-		unsigned long reg = afi_readl(pcie, AFI_MSI_VEC0 + i * 4);
+		unsigned long reg = afi_readl(pcie, AFI_MSI_VEC(i));
 
 		while (reg) {
 			unsigned int offset = find_first_bit(&reg, 32);
 			unsigned int index = i * 32 + offset;
 			unsigned int irq;
 
-			/* clear the interrupt */
-			afi_writel(pcie, 1 << offset, AFI_MSI_VEC0 + i * 4);
-
-			irq = irq_find_mapping(msi->domain, index);
+			irq = irq_find_mapping(msi->domain->parent, index);
 			if (irq) {
-				if (test_bit(index, msi->used))
-					generic_handle_irq(irq);
-				else
-					dev_info(dev, "unhandled MSI\n");
+				generic_handle_irq(irq);
 			} else {
 				/*
 				 * that's weird who triggered this?
 				 * just clear it
 				 */
 				dev_info(dev, "unexpected MSI\n");
+				afi_writel(pcie, BIT(index % 32), AFI_MSI_VEC(index));
 			}
 
 			/* see if there's any more pending in this vector */
-			reg = afi_readl(pcie, AFI_MSI_VEC0 + i * 4);
-
-			processed++;
+			reg = afi_readl(pcie, AFI_MSI_VEC(i));
 		}
 	}
 
-	return processed > 0 ? IRQ_HANDLED : IRQ_NONE;
+	chained_irq_exit(chip, desc);
 }
 
-static int tegra_msi_setup_irq(struct msi_controller *chip,
-			       struct pci_dev *pdev, struct msi_desc *desc)
+static void tegra_msi_top_irq_ack(struct irq_data *d)
 {
-	struct tegra_msi *msi = to_tegra_msi(chip);
-	struct msi_msg msg;
-	unsigned int irq;
-	int hwirq;
+	irq_chip_ack_parent(d);
+}
 
-	hwirq = tegra_msi_alloc(msi);
-	if (hwirq < 0)
-		return hwirq;
+static void tegra_msi_top_irq_mask(struct irq_data *d)
+{
+	pci_msi_mask_irq(d);
+	irq_chip_mask_parent(d);
+}
 
-	irq = irq_create_mapping(msi->domain, hwirq);
-	if (!irq) {
-		tegra_msi_free(msi, hwirq);
-		return -EINVAL;
-	}
+static void tegra_msi_top_irq_unmask(struct irq_data *d)
+{
+	pci_msi_unmask_irq(d);
+	irq_chip_unmask_parent(d);
+}
+
+static struct irq_chip tegra_msi_top_chip = {
+	.name		= "Tegra PCIe MSI",
+	.irq_ack	= tegra_msi_top_irq_ack,
+	.irq_mask	= tegra_msi_top_irq_mask,
+	.irq_unmask	= tegra_msi_top_irq_unmask,
+};
 
-	irq_set_msi_desc(irq, desc);
+static void tegra_msi_irq_ack(struct irq_data *d)
+{
+	struct tegra_msi *msi = irq_data_get_irq_chip_data(d);
+	struct tegra_pcie *pcie = msi_to_pcie(msi);
+	unsigned int index = d->hwirq / 32;
 
-	msg.address_lo = lower_32_bits(msi->phys);
-	msg.address_hi = upper_32_bits(msi->phys);
-	msg.data = hwirq;
+	/* clear the interrupt */
+	afi_writel(pcie, BIT(d->hwirq % 32), AFI_MSI_VEC(index));
+}
 
-	pci_write_msi_msg(irq, &msg);
+static void tegra_msi_irq_mask(struct irq_data *d)
+{
+	struct tegra_msi *msi = irq_data_get_irq_chip_data(d);
+	struct tegra_pcie *pcie = msi_to_pcie(msi);
+	unsigned int index = d->hwirq / 32;
+	unsigned long flags;
+	u32 value;
 
-	return 0;
+	spin_lock_irqsave(&msi->mask_lock, flags);
+	value = afi_readl(pcie, AFI_MSI_EN_VEC(index));
+	value &= ~BIT(d->hwirq % 32);
+	afi_writel(pcie, value, AFI_MSI_EN_VEC(index));
+	spin_unlock_irqrestore(&msi->mask_lock, flags);
 }
 
-static void tegra_msi_teardown_irq(struct msi_controller *chip,
-				   unsigned int irq)
+static void tegra_msi_irq_unmask(struct irq_data *d)
 {
-	struct tegra_msi *msi = to_tegra_msi(chip);
-	struct irq_data *d = irq_get_irq_data(irq);
-	irq_hw_number_t hwirq = irqd_to_hwirq(d);
+	struct tegra_msi *msi = irq_data_get_irq_chip_data(d);
+	struct tegra_pcie *pcie = msi_to_pcie(msi);
+	unsigned int index = d->hwirq / 32;
+	unsigned long flags;
+	u32 value;
 
-	irq_dispose_mapping(irq);
-	tegra_msi_free(msi, hwirq);
+	spin_lock_irqsave(&msi->mask_lock, flags);
+	value = afi_readl(pcie, AFI_MSI_EN_VEC(index));
+	value |= BIT(d->hwirq % 32);
+	afi_writel(pcie, value, AFI_MSI_EN_VEC(index));
+	spin_unlock_irqrestore(&msi->mask_lock, flags);
 }
 
-static struct irq_chip tegra_msi_irq_chip = {
-	.name = "Tegra PCIe MSI",
-	.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 int tegra_msi_set_affinity(struct irq_data *d, const struct cpumask *mask, bool force)
+{
+	return -EINVAL;
+}
+
+static void tegra_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	struct tegra_msi *msi = irq_data_get_irq_chip_data(data);
+
+	msg->address_lo = lower_32_bits(msi->phys);
+	msg->address_hi = upper_32_bits(msi->phys);
+	msg->data = data->hwirq;
+}
+
+static struct irq_chip tegra_msi_bottom_chip = {
+	.name			= "Tegra MSI",
+	.irq_ack		= tegra_msi_irq_ack,
+	.irq_mask		= tegra_msi_irq_mask,
+	.irq_unmask		= tegra_msi_irq_unmask,
+	.irq_set_affinity 	= tegra_msi_set_affinity,
+	.irq_compose_msi_msg	= tegra_compose_msi_msg,
 };
 
-static int tegra_msi_map(struct irq_domain *domain, unsigned int irq,
-			 irq_hw_number_t hwirq)
+static int tegra_msi_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				  unsigned int nr_irqs, void *args)
 {
-	irq_set_chip_and_handler(irq, &tegra_msi_irq_chip, handle_simple_irq);
-	irq_set_chip_data(irq, domain->host_data);
+	struct tegra_msi *msi = domain->host_data;
+	unsigned int i;
+	int hwirq;
+
+	mutex_lock(&msi->map_lock);
+
+	hwirq = bitmap_find_free_region(msi->used, INT_PCI_MSI_NR, order_base_2(nr_irqs));
+
+	mutex_unlock(&msi->map_lock);
+
+	if (hwirq < 0)
+		return -ENOSPC;
+
+	for (i = 0; i < nr_irqs; i++)
+		irq_domain_set_info(domain, virq + i, hwirq + i,
+				    &tegra_msi_bottom_chip, domain->host_data,
+				    handle_edge_irq, NULL, NULL);
 
 	tegra_cpuidle_pcie_irqs_in_use();
 
 	return 0;
 }
 
-static const struct irq_domain_ops msi_domain_ops = {
-	.map = tegra_msi_map,
+static void tegra_msi_domain_free(struct irq_domain *domain, unsigned int virq,
+				  unsigned int nr_irqs)
+{
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+	struct tegra_msi *msi = domain->host_data;
+
+	mutex_lock(&msi->map_lock);
+
+	bitmap_release_region(msi->used, d->hwirq, order_base_2(nr_irqs));
+
+	mutex_unlock(&msi->map_lock);
+}
+
+static const struct irq_domain_ops tegra_msi_domain_ops = {
+	.alloc = tegra_msi_domain_alloc,
+	.free = tegra_msi_domain_free,
+};
+
+static struct msi_domain_info tegra_msi_info = {
+	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+		   MSI_FLAG_PCI_MSIX),
+	.chip	= &tegra_msi_top_chip,
 };
 
+static int tegra_allocate_domains(struct tegra_msi *msi)
+{
+	struct tegra_pcie *pcie = msi_to_pcie(msi);
+	struct fwnode_handle *fwnode = dev_fwnode(pcie->dev);
+	struct irq_domain *parent;
+
+	parent = irq_domain_create_linear(fwnode, INT_PCI_MSI_NR,
+					  &tegra_msi_domain_ops, msi);
+	if (!parent) {
+		dev_err(pcie->dev, "failed to create IRQ domain\n");
+		return -ENOMEM;
+	}
+	irq_domain_update_bus_token(parent, DOMAIN_BUS_NEXUS);
+
+	msi->domain = pci_msi_create_irq_domain(fwnode, &tegra_msi_info, parent);
+	if (!msi->domain) {
+		dev_err(pcie->dev, "failed to create MSI domain\n");
+		irq_domain_remove(parent);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void tegra_free_domains(struct tegra_msi *msi)
+{
+	struct irq_domain *parent = msi->domain->parent;
+
+	irq_domain_remove(msi->domain);
+	irq_domain_remove(parent);
+}
+
 static int tegra_pcie_msi_setup(struct tegra_pcie *pcie)
 {
-	struct pci_host_bridge *host = pci_host_bridge_from_priv(pcie);
 	struct platform_device *pdev = to_platform_device(pcie->dev);
 	struct tegra_msi *msi = &pcie->msi;
 	struct device *dev = pcie->dev;
 	int err;
 
-	mutex_init(&msi->lock);
-
-	msi->chip.dev = dev;
-	msi->chip.setup_irq = tegra_msi_setup_irq;
-	msi->chip.teardown_irq = tegra_msi_teardown_irq;
+	mutex_init(&msi->map_lock);
+	spin_lock_init(&msi->mask_lock);
 
-	msi->domain = irq_domain_add_linear(dev->of_node, INT_PCI_MSI_NR,
-					    &msi_domain_ops, &msi->chip);
-	if (!msi->domain) {
-		dev_err(dev, "failed to create IRQ domain\n");
-		return -ENOMEM;
+	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+		err = tegra_allocate_domains(msi);
+		if (err)
+			return err;
 	}
 
 	err = platform_get_irq_byname(pdev, "msi");
@@ -1714,12 +1766,7 @@ static int tegra_pcie_msi_setup(struct tegra_pcie *pcie)
 
 	msi->irq = err;
 
-	err = request_irq(msi->irq, tegra_pcie_msi_irq, IRQF_NO_THREAD,
-			  tegra_msi_irq_chip.name, pcie);
-	if (err < 0) {
-		dev_err(dev, "failed to request IRQ: %d\n", err);
-		goto free_irq_domain;
-	}
+	irq_set_chained_handler_and_data(msi->irq, tegra_pcie_msi_irq, pcie);
 
 	/* Though the PCIe controller can address >32-bit address space, to
 	 * facilitate endpoints that support only 32-bit MSI target address,
@@ -1740,14 +1787,14 @@ static int tegra_pcie_msi_setup(struct tegra_pcie *pcie)
 		goto free_irq;
 	}
 
-	host->msi = &msi->chip;
-
 	return 0;
 
 free_irq:
-	free_irq(msi->irq, pcie);
+	irq_set_chained_handler_and_data(msi->irq, NULL, NULL);
 free_irq_domain:
-	irq_domain_remove(msi->domain);
+	if (IS_ENABLED(CONFIG_PCI_MSI))
+		tegra_free_domains(msi);
+
 	return err;
 }
 
@@ -1755,22 +1802,18 @@ static void tegra_pcie_enable_msi(struct tegra_pcie *pcie)
 {
 	const struct tegra_pcie_soc *soc = pcie->soc;
 	struct tegra_msi *msi = &pcie->msi;
-	u32 reg;
+	u32 reg, msi_state[INT_PCI_MSI_NR / 32];
+	int i;
 
 	afi_writel(pcie, msi->phys >> soc->msi_base_shift, AFI_MSI_FPCI_BAR_ST);
 	afi_writel(pcie, msi->phys, AFI_MSI_AXI_BAR_ST);
 	/* this register is in 4K increments */
 	afi_writel(pcie, 1, AFI_MSI_BAR_SZ);
 
-	/* enable all MSI vectors */
-	afi_writel(pcie, 0xffffffff, AFI_MSI_EN_VEC0);
-	afi_writel(pcie, 0xffffffff, AFI_MSI_EN_VEC1);
-	afi_writel(pcie, 0xffffffff, AFI_MSI_EN_VEC2);
-	afi_writel(pcie, 0xffffffff, AFI_MSI_EN_VEC3);
-	afi_writel(pcie, 0xffffffff, AFI_MSI_EN_VEC4);
-	afi_writel(pcie, 0xffffffff, AFI_MSI_EN_VEC5);
-	afi_writel(pcie, 0xffffffff, AFI_MSI_EN_VEC6);
-	afi_writel(pcie, 0xffffffff, AFI_MSI_EN_VEC7);
+	/* Restore the MSI allocation state */
+	bitmap_to_arr32(msi_state, msi->used, INT_PCI_MSI_NR);
+	for (i = 0; i < ARRAY_SIZE(msi_state); i++)
+		afi_writel(pcie, msi_state[i], AFI_MSI_EN_VEC(i));
 
 	/* and unmask the MSI interrupt */
 	reg = afi_readl(pcie, AFI_INTR_MASK);
@@ -1786,16 +1829,16 @@ static void tegra_pcie_msi_teardown(struct tegra_pcie *pcie)
 	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);
-
 	for (i = 0; i < INT_PCI_MSI_NR; i++) {
 		irq = irq_find_mapping(msi->domain, i);
 		if (irq > 0)
-			irq_dispose_mapping(irq);
+			irq_domain_free_irqs(irq, 1);
 	}
 
-	irq_domain_remove(msi->domain);
+	irq_set_chained_handler_and_data(msi->irq, NULL, NULL);
+
+	if (IS_ENABLED(CONFIG_PCI_MSI))
+		tegra_free_domains(msi);
 }
 
 static int tegra_pcie_disable_msi(struct tegra_pcie *pcie)
@@ -1807,16 +1850,6 @@ static int tegra_pcie_disable_msi(struct tegra_pcie *pcie)
 	value &= ~AFI_INTR_MASK_MSI_MASK;
 	afi_writel(pcie, value, AFI_INTR_MASK);
 
-	/* disable all MSI vectors */
-	afi_writel(pcie, 0, AFI_MSI_EN_VEC0);
-	afi_writel(pcie, 0, AFI_MSI_EN_VEC1);
-	afi_writel(pcie, 0, AFI_MSI_EN_VEC2);
-	afi_writel(pcie, 0, AFI_MSI_EN_VEC3);
-	afi_writel(pcie, 0, AFI_MSI_EN_VEC4);
-	afi_writel(pcie, 0, AFI_MSI_EN_VEC5);
-	afi_writel(pcie, 0, AFI_MSI_EN_VEC6);
-	afi_writel(pcie, 0, AFI_MSI_EN_VEC7);
-
 	return 0;
 }
 
diff --git a/drivers/pci/controller/pci-thunder-ecam.c b/drivers/pci/controller/pci-thunder-ecam.c
index f964fd26f7e0..ffd84656544f 100644
--- a/drivers/pci/controller/pci-thunder-ecam.c
+++ b/drivers/pci/controller/pci-thunder-ecam.c
@@ -116,7 +116,7 @@ static int thunder_ecam_p2_config_read(struct pci_bus *bus, unsigned int devfn,
 	 * the config space access window.  Since we are working with
 	 * the high-order 32 bits, shift everything down by 32 bits.
 	 */
-	node_bits = (cfg->res.start >> 32) & (1 << 12);
+	node_bits = upper_32_bits(cfg->res.start) & (1 << 12);
 
 	v |= node_bits;
 	set_val(v, where, size, val);
diff --git a/drivers/pci/controller/pci-thunder-pem.c b/drivers/pci/controller/pci-thunder-pem.c
index 1a3f70ac61fc..0660b9da204f 100644
--- a/drivers/pci/controller/pci-thunder-pem.c
+++ b/drivers/pci/controller/pci-thunder-pem.c
@@ -12,6 +12,7 @@
 #include <linux/pci-acpi.h>
 #include <linux/pci-ecam.h>
 #include <linux/platform_device.h>
+#include <linux/io-64-nonatomic-lo-hi.h>
 #include "../pci.h"
 
 #if defined(CONFIG_PCI_HOST_THUNDER_PEM) || (defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS))
@@ -324,9 +325,9 @@ static int thunder_pem_init(struct device *dev, struct pci_config_window *cfg,
 	 * structure here for the BAR.
 	 */
 	bar4_start = res_pem->start + 0xf00000;
-	pem_pci->ea_entry[0] = (u32)bar4_start | 2;
-	pem_pci->ea_entry[1] = (u32)(res_pem->end - bar4_start) & ~3u;
-	pem_pci->ea_entry[2] = (u32)(bar4_start >> 32);
+	pem_pci->ea_entry[0] = lower_32_bits(bar4_start) | 2;
+	pem_pci->ea_entry[1] = lower_32_bits(res_pem->end - bar4_start) & ~3u;
+	pem_pci->ea_entry[2] = upper_32_bits(bar4_start);
 
 	cfg->priv = pem_pci;
 	return 0;
@@ -334,9 +335,9 @@ static int thunder_pem_init(struct device *dev, struct pci_config_window *cfg,
 
 #if defined(CONFIG_ACPI) && defined(CONFIG_PCI_QUIRKS)
 
-#define PEM_RES_BASE		0x87e0c0000000UL
-#define PEM_NODE_MASK		GENMASK(45, 44)
-#define PEM_INDX_MASK		GENMASK(26, 24)
+#define PEM_RES_BASE		0x87e0c0000000ULL
+#define PEM_NODE_MASK		GENMASK_ULL(45, 44)
+#define PEM_INDX_MASK		GENMASK_ULL(26, 24)
 #define PEM_MIN_DOM_IN_NODE	4
 #define PEM_MAX_DOM_IN_NODE	10
 
diff --git a/drivers/pci/controller/pci-xgene.c b/drivers/pci/controller/pci-xgene.c
index 2afdc865253e..7f503dd4ff81 100644
--- a/drivers/pci/controller/pci-xgene.c
+++ b/drivers/pci/controller/pci-xgene.c
@@ -354,7 +354,8 @@ static int xgene_pcie_map_reg(struct xgene_pcie_port *port,
 	if (IS_ERR(port->csr_base))
 		return PTR_ERR(port->csr_base);
 
-	port->cfg_base = devm_platform_ioremap_resource_byname(pdev, "cfg");
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "cfg");
+	port->cfg_base = devm_ioremap_resource(dev, res);
 	if (IS_ERR(port->cfg_base))
 		return PTR_ERR(port->cfg_base);
 	port->cfg_addr = res->start;
diff --git a/drivers/pci/controller/pcie-altera-msi.c b/drivers/pci/controller/pcie-altera-msi.c
index 42691dd8ebef..98aa1dccc6e6 100644
--- a/drivers/pci/controller/pcie-altera-msi.c
+++ b/drivers/pci/controller/pcie-altera-msi.c
@@ -236,10 +236,8 @@ static int altera_msi_probe(struct platform_device *pdev)
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
 					   "vector_slave");
 	msi->vector_base = devm_ioremap_resource(&pdev->dev, res);
-	if (IS_ERR(msi->vector_base)) {
-		dev_err(&pdev->dev, "failed to map vector_slave memory\n");
+	if (IS_ERR(msi->vector_base))
 		return PTR_ERR(msi->vector_base);
-	}
 
 	msi->vector_phy = res->start;
 
diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c
index e330e6811f0b..08bc788d9422 100644
--- a/drivers/pci/controller/pcie-brcmstb.c
+++ b/drivers/pci/controller/pcie-brcmstb.c
@@ -1148,6 +1148,7 @@ static int brcm_pcie_suspend(struct device *dev)
 
 	brcm_pcie_turn_off(pcie);
 	ret = brcm_phy_stop(pcie);
+	reset_control_rearm(pcie->rescal);
 	clk_disable_unprepare(pcie->clk);
 
 	return ret;
@@ -1163,9 +1164,13 @@ static int brcm_pcie_resume(struct device *dev)
 	base = pcie->base;
 	clk_prepare_enable(pcie->clk);
 
+	ret = reset_control_reset(pcie->rescal);
+	if (ret)
+		goto err_disable_clk;
+
 	ret = brcm_phy_start(pcie);
 	if (ret)
-		goto err;
+		goto err_reset;
 
 	/* Take bridge out of reset so we can access the SERDES reg */
 	pcie->bridge_sw_init_set(pcie, 0);
@@ -1180,14 +1185,16 @@ static int brcm_pcie_resume(struct device *dev)
 
 	ret = brcm_pcie_setup(pcie);
 	if (ret)
-		goto err;
+		goto err_reset;
 
 	if (pcie->msi)
 		brcm_msi_set_regs(pcie->msi);
 
 	return 0;
 
-err:
+err_reset:
+	reset_control_rearm(pcie->rescal);
+err_disable_clk:
 	clk_disable_unprepare(pcie->clk);
 	return ret;
 }
@@ -1197,7 +1204,7 @@ static void __brcm_pcie_remove(struct brcm_pcie *pcie)
 	brcm_msi_remove(pcie);
 	brcm_pcie_turn_off(pcie);
 	brcm_phy_stop(pcie);
-	reset_control_assert(pcie->rescal);
+	reset_control_rearm(pcie->rescal);
 	clk_disable_unprepare(pcie->clk);
 }
 
@@ -1278,13 +1285,13 @@ static int brcm_pcie_probe(struct platform_device *pdev)
 		return PTR_ERR(pcie->perst_reset);
 	}
 
-	ret = reset_control_deassert(pcie->rescal);
+	ret = reset_control_reset(pcie->rescal);
 	if (ret)
 		dev_err(&pdev->dev, "failed to deassert 'rescal'\n");
 
 	ret = brcm_phy_start(pcie);
 	if (ret) {
-		reset_control_assert(pcie->rescal);
+		reset_control_rearm(pcie->rescal);
 		clk_disable_unprepare(pcie->clk);
 		return ret;
 	}
@@ -1296,6 +1303,7 @@ static int brcm_pcie_probe(struct platform_device *pdev)
 	pcie->hw_rev = readl(pcie->base + PCIE_MISC_REVISION);
 	if (pcie->type == BCM4908 && pcie->hw_rev >= BRCM_PCIE_HW_REV_3_20) {
 		dev_err(pcie->dev, "hardware revision with unsupported PERST# setup\n");
+		ret = -ENODEV;
 		goto fail;
 	}
 
diff --git a/drivers/pci/controller/pcie-iproc-msi.c b/drivers/pci/controller/pcie-iproc-msi.c
index 908475d27e0e..eede4e8f3f75 100644
--- a/drivers/pci/controller/pcie-iproc-msi.c
+++ b/drivers/pci/controller/pcie-iproc-msi.c
@@ -271,7 +271,7 @@ static int iproc_msi_irq_domain_alloc(struct irq_domain *domain,
 				    NULL, NULL);
 	}
 
-	return hwirq;
+	return 0;
 }
 
 static void iproc_msi_irq_domain_free(struct irq_domain *domain,
diff --git a/drivers/pci/controller/pcie-mediatek-gen3.c b/drivers/pci/controller/pcie-mediatek-gen3.c
new file mode 100644
index 000000000000..3c5b97716d40
--- /dev/null
+++ b/drivers/pci/controller/pcie-mediatek-gen3.c
@@ -0,0 +1,1027 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * MediaTek PCIe host controller driver.
+ *
+ * Copyright (c) 2020 MediaTek Inc.
+ * Author: Jianjun Wang <jianjun.wang@mediatek.com>
+ */
+
+#include <linux/clk.h>
+#include <linux/delay.h>
+#include <linux/iopoll.h>
+#include <linux/irq.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/msi.h>
+#include <linux/pci.h>
+#include <linux/phy/phy.h>
+#include <linux/platform_device.h>
+#include <linux/pm_domain.h>
+#include <linux/pm_runtime.h>
+#include <linux/reset.h>
+
+#include "../pci.h"
+
+#define PCIE_SETTING_REG		0x80
+#define PCIE_PCI_IDS_1			0x9c
+#define PCI_CLASS(class)		(class << 8)
+#define PCIE_RC_MODE			BIT(0)
+
+#define PCIE_CFGNUM_REG			0x140
+#define PCIE_CFG_DEVFN(devfn)		((devfn) & GENMASK(7, 0))
+#define PCIE_CFG_BUS(bus)		(((bus) << 8) & GENMASK(15, 8))
+#define PCIE_CFG_BYTE_EN(bytes)		(((bytes) << 16) & GENMASK(19, 16))
+#define PCIE_CFG_FORCE_BYTE_EN		BIT(20)
+#define PCIE_CFG_OFFSET_ADDR		0x1000
+#define PCIE_CFG_HEADER(bus, devfn) \
+	(PCIE_CFG_BUS(bus) | PCIE_CFG_DEVFN(devfn))
+
+#define PCIE_RST_CTRL_REG		0x148
+#define PCIE_MAC_RSTB			BIT(0)
+#define PCIE_PHY_RSTB			BIT(1)
+#define PCIE_BRG_RSTB			BIT(2)
+#define PCIE_PE_RSTB			BIT(3)
+
+#define PCIE_LTSSM_STATUS_REG		0x150
+#define PCIE_LTSSM_STATE_MASK		GENMASK(28, 24)
+#define PCIE_LTSSM_STATE(val)		((val & PCIE_LTSSM_STATE_MASK) >> 24)
+#define PCIE_LTSSM_STATE_L2_IDLE	0x14
+
+#define PCIE_LINK_STATUS_REG		0x154
+#define PCIE_PORT_LINKUP		BIT(8)
+
+#define PCIE_MSI_SET_NUM		8
+#define PCIE_MSI_IRQS_PER_SET		32
+#define PCIE_MSI_IRQS_NUM \
+	(PCIE_MSI_IRQS_PER_SET * PCIE_MSI_SET_NUM)
+
+#define PCIE_INT_ENABLE_REG		0x180
+#define PCIE_MSI_ENABLE			GENMASK(PCIE_MSI_SET_NUM + 8 - 1, 8)
+#define PCIE_MSI_SHIFT			8
+#define PCIE_INTX_SHIFT			24
+#define PCIE_INTX_ENABLE \
+	GENMASK(PCIE_INTX_SHIFT + PCI_NUM_INTX - 1, PCIE_INTX_SHIFT)
+
+#define PCIE_INT_STATUS_REG		0x184
+#define PCIE_MSI_SET_ENABLE_REG		0x190
+#define PCIE_MSI_SET_ENABLE		GENMASK(PCIE_MSI_SET_NUM - 1, 0)
+
+#define PCIE_MSI_SET_BASE_REG		0xc00
+#define PCIE_MSI_SET_OFFSET		0x10
+#define PCIE_MSI_SET_STATUS_OFFSET	0x04
+#define PCIE_MSI_SET_ENABLE_OFFSET	0x08
+
+#define PCIE_MSI_SET_ADDR_HI_BASE	0xc80
+#define PCIE_MSI_SET_ADDR_HI_OFFSET	0x04
+
+#define PCIE_ICMD_PM_REG		0x198
+#define PCIE_TURN_OFF_LINK		BIT(4)
+
+#define PCIE_TRANS_TABLE_BASE_REG	0x800
+#define PCIE_ATR_SRC_ADDR_MSB_OFFSET	0x4
+#define PCIE_ATR_TRSL_ADDR_LSB_OFFSET	0x8
+#define PCIE_ATR_TRSL_ADDR_MSB_OFFSET	0xc
+#define PCIE_ATR_TRSL_PARAM_OFFSET	0x10
+#define PCIE_ATR_TLB_SET_OFFSET		0x20
+
+#define PCIE_MAX_TRANS_TABLES		8
+#define PCIE_ATR_EN			BIT(0)
+#define PCIE_ATR_SIZE(size) \
+	(((((size) - 1) << 1) & GENMASK(6, 1)) | PCIE_ATR_EN)
+#define PCIE_ATR_ID(id)			((id) & GENMASK(3, 0))
+#define PCIE_ATR_TYPE_MEM		PCIE_ATR_ID(0)
+#define PCIE_ATR_TYPE_IO		PCIE_ATR_ID(1)
+#define PCIE_ATR_TLP_TYPE(type)		(((type) << 16) & GENMASK(18, 16))
+#define PCIE_ATR_TLP_TYPE_MEM		PCIE_ATR_TLP_TYPE(0)
+#define PCIE_ATR_TLP_TYPE_IO		PCIE_ATR_TLP_TYPE(2)
+
+/**
+ * struct mtk_msi_set - MSI information for each set
+ * @base: IO mapped register base
+ * @msg_addr: MSI message address
+ * @saved_irq_state: IRQ enable state saved at suspend time
+ */
+struct mtk_msi_set {
+	void __iomem *base;
+	phys_addr_t msg_addr;
+	u32 saved_irq_state;
+};
+
+/**
+ * struct mtk_pcie_port - PCIe port information
+ * @dev: pointer to PCIe device
+ * @base: IO mapped register base
+ * @reg_base: physical register base
+ * @mac_reset: MAC reset control
+ * @phy_reset: PHY reset control
+ * @phy: PHY controller block
+ * @clks: PCIe clocks
+ * @num_clks: PCIe clocks count for this port
+ * @irq: PCIe controller interrupt number
+ * @saved_irq_state: IRQ enable state saved at suspend time
+ * @irq_lock: lock protecting IRQ register access
+ * @intx_domain: legacy INTx IRQ domain
+ * @msi_domain: MSI IRQ domain
+ * @msi_bottom_domain: MSI IRQ bottom domain
+ * @msi_sets: MSI sets information
+ * @lock: lock protecting IRQ bit map
+ * @msi_irq_in_use: bit map for assigned MSI IRQ
+ */
+struct mtk_pcie_port {
+	struct device *dev;
+	void __iomem *base;
+	phys_addr_t reg_base;
+	struct reset_control *mac_reset;
+	struct reset_control *phy_reset;
+	struct phy *phy;
+	struct clk_bulk_data *clks;
+	int num_clks;
+
+	int irq;
+	u32 saved_irq_state;
+	raw_spinlock_t irq_lock;
+	struct irq_domain *intx_domain;
+	struct irq_domain *msi_domain;
+	struct irq_domain *msi_bottom_domain;
+	struct mtk_msi_set msi_sets[PCIE_MSI_SET_NUM];
+	struct mutex lock;
+	DECLARE_BITMAP(msi_irq_in_use, PCIE_MSI_IRQS_NUM);
+};
+
+/**
+ * mtk_pcie_config_tlp_header() - Configure a configuration TLP header
+ * @bus: PCI bus to query
+ * @devfn: device/function number
+ * @where: offset in config space
+ * @size: data size in TLP header
+ *
+ * Set byte enable field and device information in configuration TLP header.
+ */
+static void mtk_pcie_config_tlp_header(struct pci_bus *bus, unsigned int devfn,
+					int where, int size)
+{
+	struct mtk_pcie_port *port = bus->sysdata;
+	int bytes;
+	u32 val;
+
+	bytes = (GENMASK(size - 1, 0) & 0xf) << (where & 0x3);
+
+	val = PCIE_CFG_FORCE_BYTE_EN | PCIE_CFG_BYTE_EN(bytes) |
+	      PCIE_CFG_HEADER(bus->number, devfn);
+
+	writel_relaxed(val, port->base + PCIE_CFGNUM_REG);
+}
+
+static void __iomem *mtk_pcie_map_bus(struct pci_bus *bus, unsigned int devfn,
+				      int where)
+{
+	struct mtk_pcie_port *port = bus->sysdata;
+
+	return port->base + PCIE_CFG_OFFSET_ADDR + where;
+}
+
+static int mtk_pcie_config_read(struct pci_bus *bus, unsigned int devfn,
+				int where, int size, u32 *val)
+{
+	mtk_pcie_config_tlp_header(bus, devfn, where, size);
+
+	return pci_generic_config_read32(bus, devfn, where, size, val);
+}
+
+static int mtk_pcie_config_write(struct pci_bus *bus, unsigned int devfn,
+				 int where, int size, u32 val)
+{
+	mtk_pcie_config_tlp_header(bus, devfn, where, size);
+
+	if (size <= 2)
+		val <<= (where & 0x3) * 8;
+
+	return pci_generic_config_write32(bus, devfn, where, 4, val);
+}
+
+static struct pci_ops mtk_pcie_ops = {
+	.map_bus = mtk_pcie_map_bus,
+	.read  = mtk_pcie_config_read,
+	.write = mtk_pcie_config_write,
+};
+
+static int mtk_pcie_set_trans_table(struct mtk_pcie_port *port,
+				    resource_size_t cpu_addr,
+				    resource_size_t pci_addr,
+				    resource_size_t size,
+				    unsigned long type, int num)
+{
+	void __iomem *table;
+	u32 val;
+
+	if (num >= PCIE_MAX_TRANS_TABLES) {
+		dev_err(port->dev, "not enough translate table for addr: %#llx, limited to [%d]\n",
+			(unsigned long long)cpu_addr, PCIE_MAX_TRANS_TABLES);
+		return -ENODEV;
+	}
+
+	table = port->base + PCIE_TRANS_TABLE_BASE_REG +
+		num * PCIE_ATR_TLB_SET_OFFSET;
+
+	writel_relaxed(lower_32_bits(cpu_addr) | PCIE_ATR_SIZE(fls(size) - 1),
+		       table);
+	writel_relaxed(upper_32_bits(cpu_addr),
+		       table + PCIE_ATR_SRC_ADDR_MSB_OFFSET);
+	writel_relaxed(lower_32_bits(pci_addr),
+		       table + PCIE_ATR_TRSL_ADDR_LSB_OFFSET);
+	writel_relaxed(upper_32_bits(pci_addr),
+		       table + PCIE_ATR_TRSL_ADDR_MSB_OFFSET);
+
+	if (type == IORESOURCE_IO)
+		val = PCIE_ATR_TYPE_IO | PCIE_ATR_TLP_TYPE_IO;
+	else
+		val = PCIE_ATR_TYPE_MEM | PCIE_ATR_TLP_TYPE_MEM;
+
+	writel_relaxed(val, table + PCIE_ATR_TRSL_PARAM_OFFSET);
+
+	return 0;
+}
+
+static void mtk_pcie_enable_msi(struct mtk_pcie_port *port)
+{
+	int i;
+	u32 val;
+
+	for (i = 0; i < PCIE_MSI_SET_NUM; i++) {
+		struct mtk_msi_set *msi_set = &port->msi_sets[i];
+
+		msi_set->base = port->base + PCIE_MSI_SET_BASE_REG +
+				i * PCIE_MSI_SET_OFFSET;
+		msi_set->msg_addr = port->reg_base + PCIE_MSI_SET_BASE_REG +
+				    i * PCIE_MSI_SET_OFFSET;
+
+		/* Configure the MSI capture address */
+		writel_relaxed(lower_32_bits(msi_set->msg_addr), msi_set->base);
+		writel_relaxed(upper_32_bits(msi_set->msg_addr),
+			       port->base + PCIE_MSI_SET_ADDR_HI_BASE +
+			       i * PCIE_MSI_SET_ADDR_HI_OFFSET);
+	}
+
+	val = readl_relaxed(port->base + PCIE_MSI_SET_ENABLE_REG);
+	val |= PCIE_MSI_SET_ENABLE;
+	writel_relaxed(val, port->base + PCIE_MSI_SET_ENABLE_REG);
+
+	val = readl_relaxed(port->base + PCIE_INT_ENABLE_REG);
+	val |= PCIE_MSI_ENABLE;
+	writel_relaxed(val, port->base + PCIE_INT_ENABLE_REG);
+}
+
+static int mtk_pcie_startup_port(struct mtk_pcie_port *port)
+{
+	struct resource_entry *entry;
+	struct pci_host_bridge *host = pci_host_bridge_from_priv(port);
+	unsigned int table_index = 0;
+	int err;
+	u32 val;
+
+	/* Set as RC mode */
+	val = readl_relaxed(port->base + PCIE_SETTING_REG);
+	val |= PCIE_RC_MODE;
+	writel_relaxed(val, port->base + PCIE_SETTING_REG);
+
+	/* Set class code */
+	val = readl_relaxed(port->base + PCIE_PCI_IDS_1);
+	val &= ~GENMASK(31, 8);
+	val |= PCI_CLASS(PCI_CLASS_BRIDGE_PCI << 8);
+	writel_relaxed(val, port->base + PCIE_PCI_IDS_1);
+
+	/* Mask all INTx interrupts */
+	val = readl_relaxed(port->base + PCIE_INT_ENABLE_REG);
+	val &= ~PCIE_INTX_ENABLE;
+	writel_relaxed(val, port->base + PCIE_INT_ENABLE_REG);
+
+	/* Assert all reset signals */
+	val = readl_relaxed(port->base + PCIE_RST_CTRL_REG);
+	val |= PCIE_MAC_RSTB | PCIE_PHY_RSTB | PCIE_BRG_RSTB | PCIE_PE_RSTB;
+	writel_relaxed(val, port->base + PCIE_RST_CTRL_REG);
+
+	/*
+	 * Described in PCIe CEM specification setctions 2.2 (PERST# Signal)
+	 * and 2.2.1 (Initial Power-Up (G3 to S0)).
+	 * The deassertion of PERST# should be delayed 100ms (TPVPERL)
+	 * for the power and clock to become stable.
+	 */
+	msleep(100);
+
+	/* De-assert reset signals */
+	val &= ~(PCIE_MAC_RSTB | PCIE_PHY_RSTB | PCIE_BRG_RSTB | PCIE_PE_RSTB);
+	writel_relaxed(val, port->base + PCIE_RST_CTRL_REG);
+
+	/* Check if the link is up or not */
+	err = readl_poll_timeout(port->base + PCIE_LINK_STATUS_REG, val,
+				 !!(val & PCIE_PORT_LINKUP), 20,
+				 PCI_PM_D3COLD_WAIT * USEC_PER_MSEC);
+	if (err) {
+		val = readl_relaxed(port->base + PCIE_LTSSM_STATUS_REG);
+		dev_err(port->dev, "PCIe link down, ltssm reg val: %#x\n", val);
+		return err;
+	}
+
+	mtk_pcie_enable_msi(port);
+
+	/* Set PCIe translation windows */
+	resource_list_for_each_entry(entry, &host->windows) {
+		struct resource *res = entry->res;
+		unsigned long type = resource_type(res);
+		resource_size_t cpu_addr;
+		resource_size_t pci_addr;
+		resource_size_t size;
+		const char *range_type;
+
+		if (type == IORESOURCE_IO) {
+			cpu_addr = pci_pio_to_address(res->start);
+			range_type = "IO";
+		} else if (type == IORESOURCE_MEM) {
+			cpu_addr = res->start;
+			range_type = "MEM";
+		} else {
+			continue;
+		}
+
+		pci_addr = res->start - entry->offset;
+		size = resource_size(res);
+		err = mtk_pcie_set_trans_table(port, cpu_addr, pci_addr, size,
+					       type, table_index);
+		if (err)
+			return err;
+
+		dev_dbg(port->dev, "set %s trans window[%d]: cpu_addr = %#llx, pci_addr = %#llx, size = %#llx\n",
+			range_type, table_index, (unsigned long long)cpu_addr,
+			(unsigned long long)pci_addr, (unsigned long long)size);
+
+		table_index++;
+	}
+
+	return 0;
+}
+
+static int mtk_pcie_set_affinity(struct irq_data *data,
+				 const struct cpumask *mask, bool force)
+{
+	return -EINVAL;
+}
+
+static void mtk_pcie_msi_irq_mask(struct irq_data *data)
+{
+	pci_msi_mask_irq(data);
+	irq_chip_mask_parent(data);
+}
+
+static void mtk_pcie_msi_irq_unmask(struct irq_data *data)
+{
+	pci_msi_unmask_irq(data);
+	irq_chip_unmask_parent(data);
+}
+
+static struct irq_chip mtk_msi_irq_chip = {
+	.irq_ack = irq_chip_ack_parent,
+	.irq_mask = mtk_pcie_msi_irq_mask,
+	.irq_unmask = mtk_pcie_msi_irq_unmask,
+	.name = "MSI",
+};
+
+static struct msi_domain_info mtk_msi_domain_info = {
+	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+		   MSI_FLAG_PCI_MSIX | MSI_FLAG_MULTI_PCI_MSI),
+	.chip	= &mtk_msi_irq_chip,
+};
+
+static void mtk_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	struct mtk_msi_set *msi_set = irq_data_get_irq_chip_data(data);
+	struct mtk_pcie_port *port = data->domain->host_data;
+	unsigned long hwirq;
+
+	hwirq =	data->hwirq % PCIE_MSI_IRQS_PER_SET;
+
+	msg->address_hi = upper_32_bits(msi_set->msg_addr);
+	msg->address_lo = lower_32_bits(msi_set->msg_addr);
+	msg->data = hwirq;
+	dev_dbg(port->dev, "msi#%#lx address_hi %#x address_lo %#x data %d\n",
+		hwirq, msg->address_hi, msg->address_lo, msg->data);
+}
+
+static void mtk_msi_bottom_irq_ack(struct irq_data *data)
+{
+	struct mtk_msi_set *msi_set = irq_data_get_irq_chip_data(data);
+	unsigned long hwirq;
+
+	hwirq =	data->hwirq % PCIE_MSI_IRQS_PER_SET;
+
+	writel_relaxed(BIT(hwirq), msi_set->base + PCIE_MSI_SET_STATUS_OFFSET);
+}
+
+static void mtk_msi_bottom_irq_mask(struct irq_data *data)
+{
+	struct mtk_msi_set *msi_set = irq_data_get_irq_chip_data(data);
+	struct mtk_pcie_port *port = data->domain->host_data;
+	unsigned long hwirq, flags;
+	u32 val;
+
+	hwirq =	data->hwirq % PCIE_MSI_IRQS_PER_SET;
+
+	raw_spin_lock_irqsave(&port->irq_lock, flags);
+	val = readl_relaxed(msi_set->base + PCIE_MSI_SET_ENABLE_OFFSET);
+	val &= ~BIT(hwirq);
+	writel_relaxed(val, msi_set->base + PCIE_MSI_SET_ENABLE_OFFSET);
+	raw_spin_unlock_irqrestore(&port->irq_lock, flags);
+}
+
+static void mtk_msi_bottom_irq_unmask(struct irq_data *data)
+{
+	struct mtk_msi_set *msi_set = irq_data_get_irq_chip_data(data);
+	struct mtk_pcie_port *port = data->domain->host_data;
+	unsigned long hwirq, flags;
+	u32 val;
+
+	hwirq =	data->hwirq % PCIE_MSI_IRQS_PER_SET;
+
+	raw_spin_lock_irqsave(&port->irq_lock, flags);
+	val = readl_relaxed(msi_set->base + PCIE_MSI_SET_ENABLE_OFFSET);
+	val |= BIT(hwirq);
+	writel_relaxed(val, msi_set->base + PCIE_MSI_SET_ENABLE_OFFSET);
+	raw_spin_unlock_irqrestore(&port->irq_lock, flags);
+}
+
+static struct irq_chip mtk_msi_bottom_irq_chip = {
+	.irq_ack		= mtk_msi_bottom_irq_ack,
+	.irq_mask		= mtk_msi_bottom_irq_mask,
+	.irq_unmask		= mtk_msi_bottom_irq_unmask,
+	.irq_compose_msi_msg	= mtk_compose_msi_msg,
+	.irq_set_affinity	= mtk_pcie_set_affinity,
+	.name			= "MSI",
+};
+
+static int mtk_msi_bottom_domain_alloc(struct irq_domain *domain,
+				       unsigned int virq, unsigned int nr_irqs,
+				       void *arg)
+{
+	struct mtk_pcie_port *port = domain->host_data;
+	struct mtk_msi_set *msi_set;
+	int i, hwirq, set_idx;
+
+	mutex_lock(&port->lock);
+
+	hwirq = bitmap_find_free_region(port->msi_irq_in_use, PCIE_MSI_IRQS_NUM,
+					order_base_2(nr_irqs));
+
+	mutex_unlock(&port->lock);
+
+	if (hwirq < 0)
+		return -ENOSPC;
+
+	set_idx = hwirq / PCIE_MSI_IRQS_PER_SET;
+	msi_set = &port->msi_sets[set_idx];
+
+	for (i = 0; i < nr_irqs; i++)
+		irq_domain_set_info(domain, virq + i, hwirq + i,
+				    &mtk_msi_bottom_irq_chip, msi_set,
+				    handle_edge_irq, NULL, NULL);
+
+	return 0;
+}
+
+static void mtk_msi_bottom_domain_free(struct irq_domain *domain,
+				       unsigned int virq, unsigned int nr_irqs)
+{
+	struct mtk_pcie_port *port = domain->host_data;
+	struct irq_data *data = irq_domain_get_irq_data(domain, virq);
+
+	mutex_lock(&port->lock);
+
+	bitmap_release_region(port->msi_irq_in_use, data->hwirq,
+			      order_base_2(nr_irqs));
+
+	mutex_unlock(&port->lock);
+
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+}
+
+static const struct irq_domain_ops mtk_msi_bottom_domain_ops = {
+	.alloc = mtk_msi_bottom_domain_alloc,
+	.free = mtk_msi_bottom_domain_free,
+};
+
+static void mtk_intx_mask(struct irq_data *data)
+{
+	struct mtk_pcie_port *port = irq_data_get_irq_chip_data(data);
+	unsigned long flags;
+	u32 val;
+
+	raw_spin_lock_irqsave(&port->irq_lock, flags);
+	val = readl_relaxed(port->base + PCIE_INT_ENABLE_REG);
+	val &= ~BIT(data->hwirq + PCIE_INTX_SHIFT);
+	writel_relaxed(val, port->base + PCIE_INT_ENABLE_REG);
+	raw_spin_unlock_irqrestore(&port->irq_lock, flags);
+}
+
+static void mtk_intx_unmask(struct irq_data *data)
+{
+	struct mtk_pcie_port *port = irq_data_get_irq_chip_data(data);
+	unsigned long flags;
+	u32 val;
+
+	raw_spin_lock_irqsave(&port->irq_lock, flags);
+	val = readl_relaxed(port->base + PCIE_INT_ENABLE_REG);
+	val |= BIT(data->hwirq + PCIE_INTX_SHIFT);
+	writel_relaxed(val, port->base + PCIE_INT_ENABLE_REG);
+	raw_spin_unlock_irqrestore(&port->irq_lock, flags);
+}
+
+/**
+ * mtk_intx_eoi() - Clear INTx IRQ status at the end of interrupt
+ * @data: pointer to chip specific data
+ *
+ * As an emulated level IRQ, its interrupt status will remain
+ * until the corresponding de-assert message is received; hence that
+ * the status can only be cleared when the interrupt has been serviced.
+ */
+static void mtk_intx_eoi(struct irq_data *data)
+{
+	struct mtk_pcie_port *port = irq_data_get_irq_chip_data(data);
+	unsigned long hwirq;
+
+	hwirq = data->hwirq + PCIE_INTX_SHIFT;
+	writel_relaxed(BIT(hwirq), port->base + PCIE_INT_STATUS_REG);
+}
+
+static struct irq_chip mtk_intx_irq_chip = {
+	.irq_mask		= mtk_intx_mask,
+	.irq_unmask		= mtk_intx_unmask,
+	.irq_eoi		= mtk_intx_eoi,
+	.irq_set_affinity	= mtk_pcie_set_affinity,
+	.name			= "INTx",
+};
+
+static int mtk_pcie_intx_map(struct irq_domain *domain, unsigned int irq,
+			     irq_hw_number_t hwirq)
+{
+	irq_set_chip_data(irq, domain->host_data);
+	irq_set_chip_and_handler_name(irq, &mtk_intx_irq_chip,
+				      handle_fasteoi_irq, "INTx");
+	return 0;
+}
+
+static const struct irq_domain_ops intx_domain_ops = {
+	.map = mtk_pcie_intx_map,
+};
+
+static int mtk_pcie_init_irq_domains(struct mtk_pcie_port *port)
+{
+	struct device *dev = port->dev;
+	struct device_node *intc_node, *node = dev->of_node;
+	int ret;
+
+	raw_spin_lock_init(&port->irq_lock);
+
+	/* Setup INTx */
+	intc_node = of_get_child_by_name(node, "interrupt-controller");
+	if (!intc_node) {
+		dev_err(dev, "missing interrupt-controller node\n");
+		return -ENODEV;
+	}
+
+	port->intx_domain = irq_domain_add_linear(intc_node, PCI_NUM_INTX,
+						  &intx_domain_ops, port);
+	if (!port->intx_domain) {
+		dev_err(dev, "failed to create INTx IRQ domain\n");
+		return -ENODEV;
+	}
+
+	/* Setup MSI */
+	mutex_init(&port->lock);
+
+	port->msi_bottom_domain = irq_domain_add_linear(node, PCIE_MSI_IRQS_NUM,
+				  &mtk_msi_bottom_domain_ops, port);
+	if (!port->msi_bottom_domain) {
+		dev_err(dev, "failed to create MSI bottom domain\n");
+		ret = -ENODEV;
+		goto err_msi_bottom_domain;
+	}
+
+	port->msi_domain = pci_msi_create_irq_domain(dev->fwnode,
+						     &mtk_msi_domain_info,
+						     port->msi_bottom_domain);
+	if (!port->msi_domain) {
+		dev_err(dev, "failed to create MSI domain\n");
+		ret = -ENODEV;
+		goto err_msi_domain;
+	}
+
+	return 0;
+
+err_msi_domain:
+	irq_domain_remove(port->msi_bottom_domain);
+err_msi_bottom_domain:
+	irq_domain_remove(port->intx_domain);
+
+	return ret;
+}
+
+static void mtk_pcie_irq_teardown(struct mtk_pcie_port *port)
+{
+	irq_set_chained_handler_and_data(port->irq, NULL, NULL);
+
+	if (port->intx_domain)
+		irq_domain_remove(port->intx_domain);
+
+	if (port->msi_domain)
+		irq_domain_remove(port->msi_domain);
+
+	if (port->msi_bottom_domain)
+		irq_domain_remove(port->msi_bottom_domain);
+
+	irq_dispose_mapping(port->irq);
+}
+
+static void mtk_pcie_msi_handler(struct mtk_pcie_port *port, int set_idx)
+{
+	struct mtk_msi_set *msi_set = &port->msi_sets[set_idx];
+	unsigned long msi_enable, msi_status;
+	unsigned int virq;
+	irq_hw_number_t bit, hwirq;
+
+	msi_enable = readl_relaxed(msi_set->base + PCIE_MSI_SET_ENABLE_OFFSET);
+
+	do {
+		msi_status = readl_relaxed(msi_set->base +
+					   PCIE_MSI_SET_STATUS_OFFSET);
+		msi_status &= msi_enable;
+		if (!msi_status)
+			break;
+
+		for_each_set_bit(bit, &msi_status, PCIE_MSI_IRQS_PER_SET) {
+			hwirq = bit + set_idx * PCIE_MSI_IRQS_PER_SET;
+			virq = irq_find_mapping(port->msi_bottom_domain, hwirq);
+			generic_handle_irq(virq);
+		}
+	} while (true);
+}
+
+static void mtk_pcie_irq_handler(struct irq_desc *desc)
+{
+	struct mtk_pcie_port *port = irq_desc_get_handler_data(desc);
+	struct irq_chip *irqchip = irq_desc_get_chip(desc);
+	unsigned long status;
+	unsigned int virq;
+	irq_hw_number_t irq_bit = PCIE_INTX_SHIFT;
+
+	chained_irq_enter(irqchip, desc);
+
+	status = readl_relaxed(port->base + PCIE_INT_STATUS_REG);
+	for_each_set_bit_from(irq_bit, &status, PCI_NUM_INTX +
+			      PCIE_INTX_SHIFT) {
+		virq = irq_find_mapping(port->intx_domain,
+					irq_bit - PCIE_INTX_SHIFT);
+		generic_handle_irq(virq);
+	}
+
+	irq_bit = PCIE_MSI_SHIFT;
+	for_each_set_bit_from(irq_bit, &status, PCIE_MSI_SET_NUM +
+			      PCIE_MSI_SHIFT) {
+		mtk_pcie_msi_handler(port, irq_bit - PCIE_MSI_SHIFT);
+
+		writel_relaxed(BIT(irq_bit), port->base + PCIE_INT_STATUS_REG);
+	}
+
+	chained_irq_exit(irqchip, desc);
+}
+
+static int mtk_pcie_setup_irq(struct mtk_pcie_port *port)
+{
+	struct device *dev = port->dev;
+	struct platform_device *pdev = to_platform_device(dev);
+	int err;
+
+	err = mtk_pcie_init_irq_domains(port);
+	if (err)
+		return err;
+
+	port->irq = platform_get_irq(pdev, 0);
+	if (port->irq < 0)
+		return port->irq;
+
+	irq_set_chained_handler_and_data(port->irq, mtk_pcie_irq_handler, port);
+
+	return 0;
+}
+
+static int mtk_pcie_parse_port(struct mtk_pcie_port *port)
+{
+	struct device *dev = port->dev;
+	struct platform_device *pdev = to_platform_device(dev);
+	struct resource *regs;
+	int ret;
+
+	regs = platform_get_resource_byname(pdev, IORESOURCE_MEM, "pcie-mac");
+	if (!regs)
+		return -EINVAL;
+	port->base = devm_ioremap_resource(dev, regs);
+	if (IS_ERR(port->base)) {
+		dev_err(dev, "failed to map register base\n");
+		return PTR_ERR(port->base);
+	}
+
+	port->reg_base = regs->start;
+
+	port->phy_reset = devm_reset_control_get_optional_exclusive(dev, "phy");
+	if (IS_ERR(port->phy_reset)) {
+		ret = PTR_ERR(port->phy_reset);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get PHY reset\n");
+
+		return ret;
+	}
+
+	port->mac_reset = devm_reset_control_get_optional_exclusive(dev, "mac");
+	if (IS_ERR(port->mac_reset)) {
+		ret = PTR_ERR(port->mac_reset);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get MAC reset\n");
+
+		return ret;
+	}
+
+	port->phy = devm_phy_optional_get(dev, "pcie-phy");
+	if (IS_ERR(port->phy)) {
+		ret = PTR_ERR(port->phy);
+		if (ret != -EPROBE_DEFER)
+			dev_err(dev, "failed to get PHY\n");
+
+		return ret;
+	}
+
+	port->num_clks = devm_clk_bulk_get_all(dev, &port->clks);
+	if (port->num_clks < 0) {
+		dev_err(dev, "failed to get clocks\n");
+		return port->num_clks;
+	}
+
+	return 0;
+}
+
+static int mtk_pcie_power_up(struct mtk_pcie_port *port)
+{
+	struct device *dev = port->dev;
+	int err;
+
+	/* PHY power on and enable pipe clock */
+	reset_control_deassert(port->phy_reset);
+
+	err = phy_init(port->phy);
+	if (err) {
+		dev_err(dev, "failed to initialize PHY\n");
+		goto err_phy_init;
+	}
+
+	err = phy_power_on(port->phy);
+	if (err) {
+		dev_err(dev, "failed to power on PHY\n");
+		goto err_phy_on;
+	}
+
+	/* MAC power on and enable transaction layer clocks */
+	reset_control_deassert(port->mac_reset);
+
+	pm_runtime_enable(dev);
+	pm_runtime_get_sync(dev);
+
+	err = clk_bulk_prepare_enable(port->num_clks, port->clks);
+	if (err) {
+		dev_err(dev, "failed to enable clocks\n");
+		goto err_clk_init;
+	}
+
+	return 0;
+
+err_clk_init:
+	pm_runtime_put_sync(dev);
+	pm_runtime_disable(dev);
+	reset_control_assert(port->mac_reset);
+	phy_power_off(port->phy);
+err_phy_on:
+	phy_exit(port->phy);
+err_phy_init:
+	reset_control_assert(port->phy_reset);
+
+	return err;
+}
+
+static void mtk_pcie_power_down(struct mtk_pcie_port *port)
+{
+	clk_bulk_disable_unprepare(port->num_clks, port->clks);
+
+	pm_runtime_put_sync(port->dev);
+	pm_runtime_disable(port->dev);
+	reset_control_assert(port->mac_reset);
+
+	phy_power_off(port->phy);
+	phy_exit(port->phy);
+	reset_control_assert(port->phy_reset);
+}
+
+static int mtk_pcie_setup(struct mtk_pcie_port *port)
+{
+	int err;
+
+	err = mtk_pcie_parse_port(port);
+	if (err)
+		return err;
+
+	/* Don't touch the hardware registers before power up */
+	err = mtk_pcie_power_up(port);
+	if (err)
+		return err;
+
+	/* Try link up */
+	err = mtk_pcie_startup_port(port);
+	if (err)
+		goto err_setup;
+
+	err = mtk_pcie_setup_irq(port);
+	if (err)
+		goto err_setup;
+
+	return 0;
+
+err_setup:
+	mtk_pcie_power_down(port);
+
+	return err;
+}
+
+static int mtk_pcie_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct mtk_pcie_port *port;
+	struct pci_host_bridge *host;
+	int err;
+
+	host = devm_pci_alloc_host_bridge(dev, sizeof(*port));
+	if (!host)
+		return -ENOMEM;
+
+	port = pci_host_bridge_priv(host);
+
+	port->dev = dev;
+	platform_set_drvdata(pdev, port);
+
+	err = mtk_pcie_setup(port);
+	if (err)
+		return err;
+
+	host->ops = &mtk_pcie_ops;
+	host->sysdata = port;
+
+	err = pci_host_probe(host);
+	if (err) {
+		mtk_pcie_irq_teardown(port);
+		mtk_pcie_power_down(port);
+		return err;
+	}
+
+	return 0;
+}
+
+static int mtk_pcie_remove(struct platform_device *pdev)
+{
+	struct mtk_pcie_port *port = platform_get_drvdata(pdev);
+	struct pci_host_bridge *host = pci_host_bridge_from_priv(port);
+
+	pci_lock_rescan_remove();
+	pci_stop_root_bus(host->bus);
+	pci_remove_root_bus(host->bus);
+	pci_unlock_rescan_remove();
+
+	mtk_pcie_irq_teardown(port);
+	mtk_pcie_power_down(port);
+
+	return 0;
+}
+
+static void __maybe_unused mtk_pcie_irq_save(struct mtk_pcie_port *port)
+{
+	int i;
+
+	raw_spin_lock(&port->irq_lock);
+
+	port->saved_irq_state = readl_relaxed(port->base + PCIE_INT_ENABLE_REG);
+
+	for (i = 0; i < PCIE_MSI_SET_NUM; i++) {
+		struct mtk_msi_set *msi_set = &port->msi_sets[i];
+
+		msi_set->saved_irq_state = readl_relaxed(msi_set->base +
+					   PCIE_MSI_SET_ENABLE_OFFSET);
+	}
+
+	raw_spin_unlock(&port->irq_lock);
+}
+
+static void __maybe_unused mtk_pcie_irq_restore(struct mtk_pcie_port *port)
+{
+	int i;
+
+	raw_spin_lock(&port->irq_lock);
+
+	writel_relaxed(port->saved_irq_state, port->base + PCIE_INT_ENABLE_REG);
+
+	for (i = 0; i < PCIE_MSI_SET_NUM; i++) {
+		struct mtk_msi_set *msi_set = &port->msi_sets[i];
+
+		writel_relaxed(msi_set->saved_irq_state,
+			       msi_set->base + PCIE_MSI_SET_ENABLE_OFFSET);
+	}
+
+	raw_spin_unlock(&port->irq_lock);
+}
+
+static int __maybe_unused mtk_pcie_turn_off_link(struct mtk_pcie_port *port)
+{
+	u32 val;
+
+	val = readl_relaxed(port->base + PCIE_ICMD_PM_REG);
+	val |= PCIE_TURN_OFF_LINK;
+	writel_relaxed(val, port->base + PCIE_ICMD_PM_REG);
+
+	/* Check the link is L2 */
+	return readl_poll_timeout(port->base + PCIE_LTSSM_STATUS_REG, val,
+				  (PCIE_LTSSM_STATE(val) ==
+				   PCIE_LTSSM_STATE_L2_IDLE), 20,
+				   50 * USEC_PER_MSEC);
+}
+
+static int __maybe_unused mtk_pcie_suspend_noirq(struct device *dev)
+{
+	struct mtk_pcie_port *port = dev_get_drvdata(dev);
+	int err;
+	u32 val;
+
+	/* Trigger link to L2 state */
+	err = mtk_pcie_turn_off_link(port);
+	if (err) {
+		dev_err(port->dev, "cannot enter L2 state\n");
+		return err;
+	}
+
+	/* Pull down the PERST# pin */
+	val = readl_relaxed(port->base + PCIE_RST_CTRL_REG);
+	val |= PCIE_PE_RSTB;
+	writel_relaxed(val, port->base + PCIE_RST_CTRL_REG);
+
+	dev_dbg(port->dev, "entered L2 states successfully");
+
+	mtk_pcie_irq_save(port);
+	mtk_pcie_power_down(port);
+
+	return 0;
+}
+
+static int __maybe_unused mtk_pcie_resume_noirq(struct device *dev)
+{
+	struct mtk_pcie_port *port = dev_get_drvdata(dev);
+	int err;
+
+	err = mtk_pcie_power_up(port);
+	if (err)
+		return err;
+
+	err = mtk_pcie_startup_port(port);
+	if (err) {
+		mtk_pcie_power_down(port);
+		return err;
+	}
+
+	mtk_pcie_irq_restore(port);
+
+	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 of_device_id mtk_pcie_of_match[] = {
+	{ .compatible = "mediatek,mt8192-pcie" },
+	{},
+};
+
+static struct platform_driver mtk_pcie_driver = {
+	.probe = mtk_pcie_probe,
+	.remove = mtk_pcie_remove,
+	.driver = {
+		.name = "mtk-pcie",
+		.of_match_table = mtk_pcie_of_match,
+		.pm = &mtk_pcie_pm_ops,
+	},
+};
+
+module_platform_driver(mtk_pcie_driver);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c
index 23548b517e4b..62a042e75d9a 100644
--- a/drivers/pci/controller/pcie-mediatek.c
+++ b/drivers/pci/controller/pcie-mediatek.c
@@ -143,6 +143,7 @@ struct mtk_pcie_port;
  * 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
+ * @no_msi: Bridge has no MSI support, and relies on an external block
  * @device_id: device ID which this host need to be fixed
  * @ops: pointer to configuration access functions
  * @startup: pointer to controller setting functions
@@ -151,6 +152,7 @@ struct mtk_pcie_port;
 struct mtk_pcie_soc {
 	bool need_fix_class_id;
 	bool need_fix_device_id;
+	bool no_msi;
 	unsigned int device_id;
 	struct pci_ops *ops;
 	int (*startup)(struct mtk_pcie_port *port);
@@ -760,7 +762,7 @@ static struct pci_ops mtk_pcie_ops = {
 static int mtk_pcie_startup_port(struct mtk_pcie_port *port)
 {
 	struct mtk_pcie *pcie = port->pcie;
-	u32 func = PCI_FUNC(port->slot << 3);
+	u32 func = PCI_FUNC(port->slot);
 	u32 slot = PCI_SLOT(port->slot << 3);
 	u32 val;
 	int err;
@@ -1087,6 +1089,7 @@ static int mtk_pcie_probe(struct platform_device *pdev)
 
 	host->ops = pcie->soc->ops;
 	host->sysdata = pcie;
+	host->msi_domain = pcie->soc->no_msi;
 
 	err = pci_host_probe(host);
 	if (err)
@@ -1176,6 +1179,7 @@ static const struct dev_pm_ops mtk_pcie_pm_ops = {
 };
 
 static const struct mtk_pcie_soc mtk_pcie_soc_v1 = {
+	.no_msi = true,
 	.ops = &mtk_pcie_ops,
 	.startup = mtk_pcie_startup_port,
 };
@@ -1210,6 +1214,7 @@ static const struct of_device_id mtk_pcie_ids[] = {
 	{ .compatible = "mediatek,mt7629-pcie", .data = &mtk_pcie_soc_mt7629 },
 	{},
 };
+MODULE_DEVICE_TABLE(of, mtk_pcie_ids);
 
 static struct platform_driver mtk_pcie_driver = {
 	.probe = mtk_pcie_probe,
diff --git a/drivers/pci/controller/pcie-microchip-host.c b/drivers/pci/controller/pcie-microchip-host.c
index 04c19ff81aff..89c68c56d93b 100644
--- a/drivers/pci/controller/pcie-microchip-host.c
+++ b/drivers/pci/controller/pcie-microchip-host.c
@@ -301,27 +301,27 @@ static const struct cause event_cause[NUM_EVENTS] = {
 	LOCAL_EVENT_CAUSE(PM_MSI_INT_SYS_ERR, "system error"),
 };
 
-struct event_map pcie_event_to_event[] = {
+static struct event_map pcie_event_to_event[] = {
 	PCIE_EVENT_TO_EVENT_MAP(L2_EXIT),
 	PCIE_EVENT_TO_EVENT_MAP(HOTRST_EXIT),
 	PCIE_EVENT_TO_EVENT_MAP(DLUP_EXIT),
 };
 
-struct event_map sec_error_to_event[] = {
+static struct event_map sec_error_to_event[] = {
 	SEC_ERROR_TO_EVENT_MAP(TX_RAM_SEC_ERR),
 	SEC_ERROR_TO_EVENT_MAP(RX_RAM_SEC_ERR),
 	SEC_ERROR_TO_EVENT_MAP(PCIE2AXI_RAM_SEC_ERR),
 	SEC_ERROR_TO_EVENT_MAP(AXI2PCIE_RAM_SEC_ERR),
 };
 
-struct event_map ded_error_to_event[] = {
+static struct event_map ded_error_to_event[] = {
 	DED_ERROR_TO_EVENT_MAP(TX_RAM_DED_ERR),
 	DED_ERROR_TO_EVENT_MAP(RX_RAM_DED_ERR),
 	DED_ERROR_TO_EVENT_MAP(PCIE2AXI_RAM_DED_ERR),
 	DED_ERROR_TO_EVENT_MAP(AXI2PCIE_RAM_DED_ERR),
 };
 
-struct event_map local_status_to_event[] = {
+static struct event_map local_status_to_event[] = {
 	LOCAL_STATUS_TO_EVENT_MAP(DMA_END_ENGINE_0),
 	LOCAL_STATUS_TO_EVENT_MAP(DMA_END_ENGINE_1),
 	LOCAL_STATUS_TO_EVENT_MAP(DMA_ERROR_ENGINE_0),
@@ -1023,10 +1023,8 @@ static int mc_platform_init(struct pci_config_window *cfg)
 	}
 
 	irq = platform_get_irq(pdev, 0);
-	if (irq < 0) {
-		dev_err(dev, "unable to request IRQ%d\n", irq);
+	if (irq < 0)
 		return -ENODEV;
-	}
 
 	for (i = 0; i < NUM_EVENTS; i++) {
 		event_irq = irq_create_mapping(port->event_domain, i);
diff --git a/drivers/pci/controller/pcie-rcar-host.c b/drivers/pci/controller/pcie-rcar-host.c
index a728e8f9ad3c..765cf2b45e24 100644
--- a/drivers/pci/controller/pcie-rcar-host.c
+++ b/drivers/pci/controller/pcie-rcar-host.c
@@ -35,18 +35,12 @@
 struct rcar_msi {
 	DECLARE_BITMAP(used, INT_PCI_MSI_NR);
 	struct irq_domain *domain;
-	struct msi_controller chip;
-	unsigned long pages;
-	struct mutex lock;
+	struct mutex map_lock;
+	spinlock_t mask_lock;
 	int irq1;
 	int irq2;
 };
 
-static inline struct rcar_msi *to_rcar_msi(struct msi_controller *chip)
-{
-	return container_of(chip, struct rcar_msi, chip);
-}
-
 /* Structure representing the PCIe interface */
 struct rcar_pcie_host {
 	struct rcar_pcie	pcie;
@@ -56,6 +50,11 @@ struct rcar_pcie_host {
 	int			(*phy_init_fn)(struct rcar_pcie_host *host);
 };
 
+static struct rcar_pcie_host *msi_to_host(struct rcar_msi *msi)
+{
+	return container_of(msi, struct rcar_pcie_host, msi);
+}
+
 static u32 rcar_read_conf(struct rcar_pcie *pcie, int where)
 {
 	unsigned int shift = BITS_PER_BYTE * (where & 3);
@@ -292,8 +291,6 @@ static int rcar_pcie_enable(struct rcar_pcie_host *host)
 
 	bridge->sysdata = host;
 	bridge->ops = &rcar_pcie_ops;
-	if (IS_ENABLED(CONFIG_PCI_MSI))
-		bridge->msi = &host->msi.chip;
 
 	return pci_host_probe(bridge);
 }
@@ -473,42 +470,6 @@ static int rcar_pcie_phy_init_gen3(struct rcar_pcie_host *host)
 	return err;
 }
 
-static int rcar_msi_alloc(struct rcar_msi *chip)
-{
-	int msi;
-
-	mutex_lock(&chip->lock);
-
-	msi = find_first_zero_bit(chip->used, INT_PCI_MSI_NR);
-	if (msi < INT_PCI_MSI_NR)
-		set_bit(msi, chip->used);
-	else
-		msi = -ENOSPC;
-
-	mutex_unlock(&chip->lock);
-
-	return msi;
-}
-
-static int rcar_msi_alloc_region(struct rcar_msi *chip, int no_irqs)
-{
-	int msi;
-
-	mutex_lock(&chip->lock);
-	msi = bitmap_find_free_region(chip->used, INT_PCI_MSI_NR,
-				      order_base_2(no_irqs));
-	mutex_unlock(&chip->lock);
-
-	return msi;
-}
-
-static void rcar_msi_free(struct rcar_msi *chip, unsigned long irq)
-{
-	mutex_lock(&chip->lock);
-	clear_bit(irq, chip->used);
-	mutex_unlock(&chip->lock);
-}
-
 static irqreturn_t rcar_pcie_msi_irq(int irq, void *data)
 {
 	struct rcar_pcie_host *host = data;
@@ -527,18 +488,13 @@ static irqreturn_t rcar_pcie_msi_irq(int irq, void *data)
 		unsigned int index = find_first_bit(&reg, 32);
 		unsigned int msi_irq;
 
-		/* clear the interrupt */
-		rcar_pci_write_reg(pcie, 1 << index, PCIEMSIFR);
-
-		msi_irq = irq_find_mapping(msi->domain, index);
+		msi_irq = irq_find_mapping(msi->domain->parent, index);
 		if (msi_irq) {
-			if (test_bit(index, msi->used))
-				generic_handle_irq(msi_irq);
-			else
-				dev_info(dev, "unhandled MSI\n");
+			generic_handle_irq(msi_irq);
 		} else {
 			/* Unknown MSI, just clear it */
 			dev_dbg(dev, "unexpected MSI\n");
+			rcar_pci_write_reg(pcie, BIT(index), PCIEMSIFR);
 		}
 
 		/* see if there's any more pending in this vector */
@@ -548,149 +504,169 @@ static irqreturn_t rcar_pcie_msi_irq(int irq, void *data)
 	return IRQ_HANDLED;
 }
 
-static int rcar_msi_setup_irq(struct msi_controller *chip, struct pci_dev *pdev,
-			      struct msi_desc *desc)
+static void rcar_msi_top_irq_ack(struct irq_data *d)
 {
-	struct rcar_msi *msi = to_rcar_msi(chip);
-	struct rcar_pcie_host *host = container_of(chip, struct rcar_pcie_host,
-						   msi.chip);
-	struct rcar_pcie *pcie = &host->pcie;
-	struct msi_msg msg;
-	unsigned int irq;
-	int hwirq;
+	irq_chip_ack_parent(d);
+}
 
-	hwirq = rcar_msi_alloc(msi);
-	if (hwirq < 0)
-		return hwirq;
+static void rcar_msi_top_irq_mask(struct irq_data *d)
+{
+	pci_msi_mask_irq(d);
+	irq_chip_mask_parent(d);
+}
 
-	irq = irq_find_mapping(msi->domain, hwirq);
-	if (!irq) {
-		rcar_msi_free(msi, hwirq);
-		return -EINVAL;
-	}
+static void rcar_msi_top_irq_unmask(struct irq_data *d)
+{
+	pci_msi_unmask_irq(d);
+	irq_chip_unmask_parent(d);
+}
 
-	irq_set_msi_desc(irq, desc);
+static struct irq_chip rcar_msi_top_chip = {
+	.name		= "PCIe MSI",
+	.irq_ack	= rcar_msi_top_irq_ack,
+	.irq_mask	= rcar_msi_top_irq_mask,
+	.irq_unmask	= rcar_msi_top_irq_unmask,
+};
 
-	msg.address_lo = rcar_pci_read_reg(pcie, PCIEMSIALR) & ~MSIFE;
-	msg.address_hi = rcar_pci_read_reg(pcie, PCIEMSIAUR);
-	msg.data = hwirq;
+static void rcar_msi_irq_ack(struct irq_data *d)
+{
+	struct rcar_msi *msi = irq_data_get_irq_chip_data(d);
+	struct rcar_pcie *pcie = &msi_to_host(msi)->pcie;
 
-	pci_write_msi_msg(irq, &msg);
+	/* clear the interrupt */
+	rcar_pci_write_reg(pcie, BIT(d->hwirq), PCIEMSIFR);
+}
 
-	return 0;
+static void rcar_msi_irq_mask(struct irq_data *d)
+{
+	struct rcar_msi *msi = irq_data_get_irq_chip_data(d);
+	struct rcar_pcie *pcie = &msi_to_host(msi)->pcie;
+	unsigned long flags;
+	u32 value;
+
+	spin_lock_irqsave(&msi->mask_lock, flags);
+	value = rcar_pci_read_reg(pcie, PCIEMSIIER);
+	value &= ~BIT(d->hwirq);
+	rcar_pci_write_reg(pcie, value, PCIEMSIIER);
+	spin_unlock_irqrestore(&msi->mask_lock, flags);
 }
 
-static int rcar_msi_setup_irqs(struct msi_controller *chip,
-			       struct pci_dev *pdev, int nvec, int type)
+static void rcar_msi_irq_unmask(struct irq_data *d)
 {
-	struct rcar_msi *msi = to_rcar_msi(chip);
-	struct rcar_pcie_host *host = container_of(chip, struct rcar_pcie_host,
-						   msi.chip);
-	struct rcar_pcie *pcie = &host->pcie;
-	struct msi_desc *desc;
-	struct msi_msg msg;
-	unsigned int irq;
-	int hwirq;
-	int i;
+	struct rcar_msi *msi = irq_data_get_irq_chip_data(d);
+	struct rcar_pcie *pcie = &msi_to_host(msi)->pcie;
+	unsigned long flags;
+	u32 value;
+
+	spin_lock_irqsave(&msi->mask_lock, flags);
+	value = rcar_pci_read_reg(pcie, PCIEMSIIER);
+	value |= BIT(d->hwirq);
+	rcar_pci_write_reg(pcie, value, PCIEMSIIER);
+	spin_unlock_irqrestore(&msi->mask_lock, flags);
+}
 
-	/* MSI-X interrupts are not supported */
-	if (type == PCI_CAP_ID_MSIX)
-		return -EINVAL;
+static int rcar_msi_set_affinity(struct irq_data *d, const struct cpumask *mask, bool force)
+{
+	return -EINVAL;
+}
 
-	WARN_ON(!list_is_singular(&pdev->dev.msi_list));
-	desc = list_entry(pdev->dev.msi_list.next, struct msi_desc, list);
+static void rcar_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	struct rcar_msi *msi = irq_data_get_irq_chip_data(data);
+	struct rcar_pcie *pcie = &msi_to_host(msi)->pcie;
 
-	hwirq = rcar_msi_alloc_region(msi, nvec);
-	if (hwirq < 0)
-		return -ENOSPC;
+	msg->address_lo = rcar_pci_read_reg(pcie, PCIEMSIALR) & ~MSIFE;
+	msg->address_hi = rcar_pci_read_reg(pcie, PCIEMSIAUR);
+	msg->data = data->hwirq;
+}
 
-	irq = irq_find_mapping(msi->domain, hwirq);
-	if (!irq)
-		return -ENOSPC;
+static struct irq_chip rcar_msi_bottom_chip = {
+	.name			= "Rcar MSI",
+	.irq_ack		= rcar_msi_irq_ack,
+	.irq_mask		= rcar_msi_irq_mask,
+	.irq_unmask		= rcar_msi_irq_unmask,
+	.irq_set_affinity 	= rcar_msi_set_affinity,
+	.irq_compose_msi_msg	= rcar_compose_msi_msg,
+};
 
-	for (i = 0; i < nvec; i++) {
-		/*
-		 * irq_create_mapping() called from rcar_pcie_probe() pre-
-		 * allocates descs,  so there is no need to allocate descs here.
-		 * We can therefore assume that if irq_find_mapping() above
-		 * returns non-zero, then the descs are also successfully
-		 * allocated.
-		 */
-		if (irq_set_msi_desc_off(irq, i, desc)) {
-			/* TODO: clear */
-			return -EINVAL;
-		}
-	}
+static int rcar_msi_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				  unsigned int nr_irqs, void *args)
+{
+	struct rcar_msi *msi = domain->host_data;
+	unsigned int i;
+	int hwirq;
 
-	desc->nvec_used = nvec;
-	desc->msi_attrib.multiple = order_base_2(nvec);
+	mutex_lock(&msi->map_lock);
 
-	msg.address_lo = rcar_pci_read_reg(pcie, PCIEMSIALR) & ~MSIFE;
-	msg.address_hi = rcar_pci_read_reg(pcie, PCIEMSIAUR);
-	msg.data = hwirq;
+	hwirq = bitmap_find_free_region(msi->used, INT_PCI_MSI_NR, order_base_2(nr_irqs));
 
-	pci_write_msi_msg(irq, &msg);
+	mutex_unlock(&msi->map_lock);
+
+	if (hwirq < 0)
+		return -ENOSPC;
+
+	for (i = 0; i < nr_irqs; i++)
+		irq_domain_set_info(domain, virq + i, hwirq + i,
+				    &rcar_msi_bottom_chip, domain->host_data,
+				    handle_edge_irq, NULL, NULL);
 
 	return 0;
 }
 
-static void rcar_msi_teardown_irq(struct msi_controller *chip, unsigned int irq)
+static void rcar_msi_domain_free(struct irq_domain *domain, unsigned int virq,
+				  unsigned int nr_irqs)
 {
-	struct rcar_msi *msi = to_rcar_msi(chip);
-	struct irq_data *d = irq_get_irq_data(irq);
-
-	rcar_msi_free(msi, d->hwirq);
-}
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+	struct rcar_msi *msi = domain->host_data;
 
-static struct irq_chip rcar_msi_irq_chip = {
-	.name = "R-Car PCIe MSI",
-	.irq_enable = pci_msi_unmask_irq,
-	.irq_disable = pci_msi_mask_irq,
-	.irq_mask = pci_msi_mask_irq,
-	.irq_unmask = pci_msi_unmask_irq,
-};
+	mutex_lock(&msi->map_lock);
 
-static int rcar_msi_map(struct irq_domain *domain, unsigned int irq,
-			irq_hw_number_t hwirq)
-{
-	irq_set_chip_and_handler(irq, &rcar_msi_irq_chip, handle_simple_irq);
-	irq_set_chip_data(irq, domain->host_data);
+	bitmap_release_region(msi->used, d->hwirq, order_base_2(nr_irqs));
 
-	return 0;
+	mutex_unlock(&msi->map_lock);
 }
 
-static const struct irq_domain_ops msi_domain_ops = {
-	.map = rcar_msi_map,
+static const struct irq_domain_ops rcar_msi_domain_ops = {
+	.alloc	= rcar_msi_domain_alloc,
+	.free	= rcar_msi_domain_free,
+};
+
+static struct msi_domain_info rcar_msi_info = {
+	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+		   MSI_FLAG_MULTI_PCI_MSI),
+	.chip	= &rcar_msi_top_chip,
 };
 
-static void rcar_pcie_unmap_msi(struct rcar_pcie_host *host)
+static int rcar_allocate_domains(struct rcar_msi *msi)
 {
-	struct rcar_msi *msi = &host->msi;
-	int i, irq;
+	struct rcar_pcie *pcie = &msi_to_host(msi)->pcie;
+	struct fwnode_handle *fwnode = dev_fwnode(pcie->dev);
+	struct irq_domain *parent;
+
+	parent = irq_domain_create_linear(fwnode, INT_PCI_MSI_NR,
+					  &rcar_msi_domain_ops, msi);
+	if (!parent) {
+		dev_err(pcie->dev, "failed to create IRQ domain\n");
+		return -ENOMEM;
+	}
+	irq_domain_update_bus_token(parent, DOMAIN_BUS_NEXUS);
 
-	for (i = 0; i < INT_PCI_MSI_NR; i++) {
-		irq = irq_find_mapping(msi->domain, i);
-		if (irq > 0)
-			irq_dispose_mapping(irq);
+	msi->domain = pci_msi_create_irq_domain(fwnode, &rcar_msi_info, parent);
+	if (!msi->domain) {
+		dev_err(pcie->dev, "failed to create MSI domain\n");
+		irq_domain_remove(parent);
+		return -ENOMEM;
 	}
 
-	irq_domain_remove(msi->domain);
+	return 0;
 }
 
-static void rcar_pcie_hw_enable_msi(struct rcar_pcie_host *host)
+static void rcar_free_domains(struct rcar_msi *msi)
 {
-	struct rcar_pcie *pcie = &host->pcie;
-	struct rcar_msi *msi = &host->msi;
-	unsigned long base;
-
-	/* setup MSI data target */
-	base = virt_to_phys((void *)msi->pages);
+	struct irq_domain *parent = msi->domain->parent;
 
-	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);
+	irq_domain_remove(msi->domain);
+	irq_domain_remove(parent);
 }
 
 static int rcar_pcie_enable_msi(struct rcar_pcie_host *host)
@@ -698,29 +674,24 @@ static int rcar_pcie_enable_msi(struct rcar_pcie_host *host)
 	struct rcar_pcie *pcie = &host->pcie;
 	struct device *dev = pcie->dev;
 	struct rcar_msi *msi = &host->msi;
-	int err, i;
-
-	mutex_init(&msi->lock);
+	struct resource res;
+	int err;
 
-	msi->chip.dev = dev;
-	msi->chip.setup_irq = rcar_msi_setup_irq;
-	msi->chip.setup_irqs = rcar_msi_setup_irqs;
-	msi->chip.teardown_irq = rcar_msi_teardown_irq;
+	mutex_init(&msi->map_lock);
+	spin_lock_init(&msi->mask_lock);
 
-	msi->domain = irq_domain_add_linear(dev->of_node, INT_PCI_MSI_NR,
-					    &msi_domain_ops, &msi->chip);
-	if (!msi->domain) {
-		dev_err(dev, "failed to create IRQ domain\n");
-		return -ENOMEM;
-	}
+	err = of_address_to_resource(dev->of_node, 0, &res);
+	if (err)
+		return err;
 
-	for (i = 0; i < INT_PCI_MSI_NR; i++)
-		irq_create_mapping(msi->domain, i);
+	err = rcar_allocate_domains(msi);
+	if (err)
+		return err;
 
 	/* Two irqs are for MSI, but they are also used for non-MSI irqs */
 	err = devm_request_irq(dev, msi->irq1, rcar_pcie_msi_irq,
 			       IRQF_SHARED | IRQF_NO_THREAD,
-			       rcar_msi_irq_chip.name, host);
+			       rcar_msi_bottom_chip.name, host);
 	if (err < 0) {
 		dev_err(dev, "failed to request IRQ: %d\n", err);
 		goto err;
@@ -728,27 +699,32 @@ static int rcar_pcie_enable_msi(struct rcar_pcie_host *host)
 
 	err = devm_request_irq(dev, msi->irq2, rcar_pcie_msi_irq,
 			       IRQF_SHARED | IRQF_NO_THREAD,
-			       rcar_msi_irq_chip.name, host);
+			       rcar_msi_bottom_chip.name, host);
 	if (err < 0) {
 		dev_err(dev, "failed to request IRQ: %d\n", err);
 		goto err;
 	}
 
-	/* setup MSI data target */
-	msi->pages = __get_free_pages(GFP_KERNEL | GFP_DMA32, 0);
-	rcar_pcie_hw_enable_msi(host);
+	/* disable all MSIs */
+	rcar_pci_write_reg(pcie, 0, PCIEMSIIER);
+
+	/*
+	 * Setup MSI data target using RC base address address, which
+	 * is guaranteed to be in the low 32bit range on any RCar HW.
+	 */
+	rcar_pci_write_reg(pcie, lower_32_bits(res.start) | MSIFE, PCIEMSIALR);
+	rcar_pci_write_reg(pcie, upper_32_bits(res.start), PCIEMSIAUR);
 
 	return 0;
 
 err:
-	rcar_pcie_unmap_msi(host);
+	rcar_free_domains(msi);
 	return err;
 }
 
 static void rcar_pcie_teardown_msi(struct rcar_pcie_host *host)
 {
 	struct rcar_pcie *pcie = &host->pcie;
-	struct rcar_msi *msi = &host->msi;
 
 	/* Disable all MSI interrupts */
 	rcar_pci_write_reg(pcie, 0, PCIEMSIIER);
@@ -756,9 +732,7 @@ static void rcar_pcie_teardown_msi(struct rcar_pcie_host *host)
 	/* Disable address decoding of the MSI interrupt, MSIFE */
 	rcar_pci_write_reg(pcie, 0, PCIEMSIALR);
 
-	free_pages(msi->pages, 0);
-
-	rcar_pcie_unmap_msi(host);
+	rcar_free_domains(&host->msi);
 }
 
 static int rcar_pcie_get_resources(struct rcar_pcie_host *host)
@@ -1011,8 +985,17 @@ static int __maybe_unused rcar_pcie_resume(struct device *dev)
 	dev_info(dev, "PCIe x%d: link up\n", (data >> 20) & 0x3f);
 
 	/* Enable MSI */
-	if (IS_ENABLED(CONFIG_PCI_MSI))
-		rcar_pcie_hw_enable_msi(host);
+	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+		struct resource res;
+		u32 val;
+
+		of_address_to_resource(dev->of_node, 0, &res);
+		rcar_pci_write_reg(pcie, upper_32_bits(res.start), PCIEMSIAUR);
+		rcar_pci_write_reg(pcie, lower_32_bits(res.start) | MSIFE, PCIEMSIALR);
+
+		bitmap_to_arr32(&val, host->msi.used, INT_PCI_MSI_NR);
+		rcar_pci_write_reg(pcie, val, PCIEMSIIER);
+	}
 
 	rcar_pcie_hw_enable(host);
 
diff --git a/drivers/pci/controller/pcie-xilinx-nwl.c b/drivers/pci/controller/pcie-xilinx-nwl.c
index 07e36661bbc2..8689311c5ef6 100644
--- a/drivers/pci/controller/pcie-xilinx-nwl.c
+++ b/drivers/pci/controller/pcie-xilinx-nwl.c
@@ -26,6 +26,7 @@
 
 /* Bridge core config registers */
 #define BRCFG_PCIE_RX0			0x00000000
+#define BRCFG_PCIE_RX1			0x00000004
 #define BRCFG_INTERRUPT			0x00000010
 #define BRCFG_PCIE_RX_MSG_FILTER	0x00000020
 
@@ -128,6 +129,7 @@
 #define NWL_ECAM_VALUE_DEFAULT		12
 
 #define CFG_DMA_REG_BAR			GENMASK(2, 0)
+#define CFG_PCIE_CACHE			GENMASK(7, 0)
 
 #define INT_PCI_MSI_NR			(2 * 32)
 
@@ -675,6 +677,11 @@ static int nwl_pcie_bridge_init(struct nwl_pcie *pcie)
 	nwl_bridge_writel(pcie, CFG_ENABLE_MSG_FILTER_MASK,
 			  BRCFG_PCIE_RX_MSG_FILTER);
 
+	/* This routes the PCIe DMA traffic to go through CCI path */
+	if (of_dma_is_coherent(dev->of_node))
+		nwl_bridge_writel(pcie, nwl_bridge_readl(pcie, BRCFG_PCIE_RX1) |
+				  CFG_PCIE_CACHE, BRCFG_PCIE_RX1);
+
 	err = nwl_wait_for_link(pcie);
 	if (err)
 		return err;
diff --git a/drivers/pci/controller/pcie-xilinx.c b/drivers/pci/controller/pcie-xilinx.c
index fa5baeb82653..14001febf59a 100644
--- a/drivers/pci/controller/pcie-xilinx.c
+++ b/drivers/pci/controller/pcie-xilinx.c
@@ -93,25 +93,23 @@
 /**
  * struct xilinx_pcie_port - PCIe port information
  * @reg_base: IO Mapped Register Base
- * @irq: Interrupt number
- * @msi_pages: MSI pages
  * @dev: Device pointer
+ * @msi_map: Bitmap of allocated MSIs
+ * @map_lock: Mutex protecting the MSI allocation
  * @msi_domain: MSI IRQ domain pointer
  * @leg_domain: Legacy IRQ domain pointer
  * @resources: Bus Resources
  */
 struct xilinx_pcie_port {
 	void __iomem *reg_base;
-	u32 irq;
-	unsigned long msi_pages;
 	struct device *dev;
+	unsigned long msi_map[BITS_TO_LONGS(XILINX_NUM_MSI_IRQS)];
+	struct mutex map_lock;
 	struct irq_domain *msi_domain;
 	struct irq_domain *leg_domain;
 	struct list_head resources;
 };
 
-static DECLARE_BITMAP(msi_irq_in_use, XILINX_NUM_MSI_IRQS);
-
 static inline u32 pcie_read(struct xilinx_pcie_port *port, u32 reg)
 {
 	return readl(port->reg_base + reg);
@@ -196,151 +194,118 @@ static struct pci_ops xilinx_pcie_ops = {
 
 /* MSI functions */
 
-/**
- * xilinx_pcie_destroy_msi - Free MSI number
- * @irq: IRQ to be freed
- */
-static void xilinx_pcie_destroy_msi(unsigned int irq)
+static void xilinx_msi_top_irq_ack(struct irq_data *d)
 {
-	struct msi_desc *msi;
-	struct xilinx_pcie_port *port;
-	struct irq_data *d = irq_get_irq_data(irq);
-	irq_hw_number_t hwirq = irqd_to_hwirq(d);
-
-	if (!test_bit(hwirq, msi_irq_in_use)) {
-		msi = irq_get_msi_desc(irq);
-		port = msi_desc_to_pci_sysdata(msi);
-		dev_err(port->dev, "Trying to free unused MSI#%d\n", irq);
-	} else {
-		clear_bit(hwirq, msi_irq_in_use);
-	}
+	/*
+	 * xilinx_pcie_intr_handler() will have performed the Ack.
+	 * Eventually, this should be fixed and the Ack be moved in
+	 * the respective callbacks for INTx and MSI.
+	 */
 }
 
-/**
- * xilinx_pcie_assign_msi - Allocate MSI number
- *
- * Return: A valid IRQ on success and error value on failure.
- */
-static int xilinx_pcie_assign_msi(void)
-{
-	int pos;
-
-	pos = find_first_zero_bit(msi_irq_in_use, XILINX_NUM_MSI_IRQS);
-	if (pos < XILINX_NUM_MSI_IRQS)
-		set_bit(pos, msi_irq_in_use);
-	else
-		return -ENOSPC;
+static struct irq_chip xilinx_msi_top_chip = {
+	.name		= "PCIe MSI",
+	.irq_ack	= xilinx_msi_top_irq_ack,
+};
 
-	return pos;
+static int xilinx_msi_set_affinity(struct irq_data *d, const struct cpumask *mask, bool force)
+{
+	return -EINVAL;
 }
 
-/**
- * xilinx_msi_teardown_irq - Destroy the MSI
- * @chip: MSI Chip descriptor
- * @irq: MSI IRQ to destroy
- */
-static void xilinx_msi_teardown_irq(struct msi_controller *chip,
-				    unsigned int irq)
+static void xilinx_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 {
-	xilinx_pcie_destroy_msi(irq);
-	irq_dispose_mapping(irq);
+	struct xilinx_pcie_port *pcie = irq_data_get_irq_chip_data(data);
+	phys_addr_t pa = ALIGN_DOWN(virt_to_phys(pcie), SZ_4K);
+
+	msg->address_lo = lower_32_bits(pa);
+	msg->address_hi = upper_32_bits(pa);
+	msg->data = data->hwirq;
 }
 
-/**
- * xilinx_pcie_msi_setup_irq - Setup MSI request
- * @chip: MSI chip pointer
- * @pdev: PCIe device pointer
- * @desc: MSI descriptor pointer
- *
- * Return: '0' on success and error value on failure
- */
-static int xilinx_pcie_msi_setup_irq(struct msi_controller *chip,
-				     struct pci_dev *pdev,
-				     struct msi_desc *desc)
-{
-	struct xilinx_pcie_port *port = pdev->bus->sysdata;
-	unsigned int irq;
-	int hwirq;
-	struct msi_msg msg;
-	phys_addr_t msg_addr;
+static struct irq_chip xilinx_msi_bottom_chip = {
+	.name			= "Xilinx MSI",
+	.irq_set_affinity 	= xilinx_msi_set_affinity,
+	.irq_compose_msi_msg	= xilinx_compose_msi_msg,
+};
 
-	hwirq = xilinx_pcie_assign_msi();
-	if (hwirq < 0)
-		return hwirq;
+static int xilinx_msi_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				  unsigned int nr_irqs, void *args)
+{
+	struct xilinx_pcie_port *port = domain->host_data;
+	int hwirq, i;
 
-	irq = irq_create_mapping(port->msi_domain, hwirq);
-	if (!irq)
-		return -EINVAL;
+	mutex_lock(&port->map_lock);
 
-	irq_set_msi_desc(irq, desc);
+	hwirq = bitmap_find_free_region(port->msi_map, XILINX_NUM_MSI_IRQS, order_base_2(nr_irqs));
 
-	msg_addr = virt_to_phys((void *)port->msi_pages);
+	mutex_unlock(&port->map_lock);
 
-	msg.address_hi = 0;
-	msg.address_lo = msg_addr;
-	msg.data = irq;
+	if (hwirq < 0)
+		return -ENOSPC;
 
-	pci_write_msi_msg(irq, &msg);
+	for (i = 0; i < nr_irqs; i++)
+		irq_domain_set_info(domain, virq + i, hwirq + i,
+				    &xilinx_msi_bottom_chip, domain->host_data,
+				    handle_edge_irq, NULL, NULL);
 
 	return 0;
 }
 
-/* MSI Chip Descriptor */
-static struct msi_controller xilinx_pcie_msi_chip = {
-	.setup_irq = xilinx_pcie_msi_setup_irq,
-	.teardown_irq = xilinx_msi_teardown_irq,
-};
+static void xilinx_msi_domain_free(struct irq_domain *domain, unsigned int virq,
+				  unsigned int nr_irqs)
+{
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+	struct xilinx_pcie_port *port = domain->host_data;
 
-/* HW Interrupt Chip Descriptor */
-static struct irq_chip xilinx_msi_irq_chip = {
-	.name = "Xilinx PCIe MSI",
-	.irq_enable = pci_msi_unmask_irq,
-	.irq_disable = pci_msi_mask_irq,
-	.irq_mask = pci_msi_mask_irq,
-	.irq_unmask = pci_msi_unmask_irq,
-};
+	mutex_lock(&port->map_lock);
 
-/**
- * xilinx_pcie_msi_map - Set the handler for the MSI and mark IRQ as valid
- * @domain: IRQ domain
- * @irq: Virtual IRQ number
- * @hwirq: HW interrupt number
- *
- * Return: Always returns 0.
- */
-static int xilinx_pcie_msi_map(struct irq_domain *domain, unsigned int irq,
-			       irq_hw_number_t hwirq)
-{
-	irq_set_chip_and_handler(irq, &xilinx_msi_irq_chip, handle_simple_irq);
-	irq_set_chip_data(irq, domain->host_data);
+	bitmap_release_region(port->msi_map, d->hwirq, order_base_2(nr_irqs));
 
-	return 0;
+	mutex_unlock(&port->map_lock);
 }
 
-/* IRQ Domain operations */
-static const struct irq_domain_ops msi_domain_ops = {
-	.map = xilinx_pcie_msi_map,
+static const struct irq_domain_ops xilinx_msi_domain_ops = {
+	.alloc	= xilinx_msi_domain_alloc,
+	.free	= xilinx_msi_domain_free,
 };
 
-/**
- * xilinx_pcie_enable_msi - Enable MSI support
- * @port: PCIe port information
- */
-static int xilinx_pcie_enable_msi(struct xilinx_pcie_port *port)
+static struct msi_domain_info xilinx_msi_info = {
+	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS),
+	.chip	= &xilinx_msi_top_chip,
+};
+
+static int xilinx_allocate_msi_domains(struct xilinx_pcie_port *pcie)
 {
-	phys_addr_t msg_addr;
+	struct fwnode_handle *fwnode = dev_fwnode(pcie->dev);
+	struct irq_domain *parent;
 
-	port->msi_pages = __get_free_pages(GFP_KERNEL, 0);
-	if (!port->msi_pages)
+	parent = irq_domain_create_linear(fwnode, XILINX_NUM_MSI_IRQS,
+					  &xilinx_msi_domain_ops, pcie);
+	if (!parent) {
+		dev_err(pcie->dev, "failed to create IRQ domain\n");
 		return -ENOMEM;
+	}
+	irq_domain_update_bus_token(parent, DOMAIN_BUS_NEXUS);
 
-	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);
+	pcie->msi_domain = pci_msi_create_irq_domain(fwnode, &xilinx_msi_info, parent);
+	if (!pcie->msi_domain) {
+		dev_err(pcie->dev, "failed to create MSI domain\n");
+		irq_domain_remove(parent);
+		return -ENOMEM;
+	}
 
 	return 0;
 }
 
+static void xilinx_free_msi_domains(struct xilinx_pcie_port *pcie)
+{
+	struct irq_domain *parent = pcie->msi_domain->parent;
+
+	irq_domain_remove(pcie->msi_domain);
+	irq_domain_remove(parent);
+}
+
 /* INTx Functions */
 
 /**
@@ -420,6 +385,8 @@ static irqreturn_t xilinx_pcie_intr_handler(int irq, void *data)
 	}
 
 	if (status & (XILINX_PCIE_INTR_INTX | XILINX_PCIE_INTR_MSI)) {
+		unsigned int irq;
+
 		val = pcie_read(port, XILINX_PCIE_REG_RPIFR1);
 
 		/* Check whether interrupt valid */
@@ -432,20 +399,19 @@ static irqreturn_t xilinx_pcie_intr_handler(int irq, void *data)
 		if (val & XILINX_PCIE_RPIFR1_MSI_INTR) {
 			val = pcie_read(port, XILINX_PCIE_REG_RPIFR2) &
 				XILINX_PCIE_RPIFR2_MSG_DATA;
+			irq = irq_find_mapping(port->msi_domain->parent, val);
 		} else {
 			val = (val & XILINX_PCIE_RPIFR1_INTR_MASK) >>
 				XILINX_PCIE_RPIFR1_INTR_SHIFT;
-			val = irq_find_mapping(port->leg_domain, val);
+			irq = irq_find_mapping(port->leg_domain, val);
 		}
 
 		/* Clear interrupt FIFO register 1 */
 		pcie_write(port, XILINX_PCIE_RPIFR1_ALL_MASK,
 			   XILINX_PCIE_REG_RPIFR1);
 
-		/* Handle the interrupt */
-		if (IS_ENABLED(CONFIG_PCI_MSI) ||
-		    !(val & XILINX_PCIE_RPIFR1_MSI_INTR))
-			generic_handle_irq(val);
+		if (irq)
+			generic_handle_irq(irq);
 	}
 
 	if (status & XILINX_PCIE_INTR_SLV_UNSUPP)
@@ -491,12 +457,11 @@ error:
 static int xilinx_pcie_init_irq_domain(struct xilinx_pcie_port *port)
 {
 	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);
+	pcie_intc_node = of_get_next_child(dev->of_node, NULL);
 	if (!pcie_intc_node) {
 		dev_err(dev, "No PCIe Intc node found\n");
 		return -ENODEV;
@@ -513,18 +478,14 @@ static int xilinx_pcie_init_irq_domain(struct xilinx_pcie_port *port)
 
 	/* Setup MSI */
 	if (IS_ENABLED(CONFIG_PCI_MSI)) {
-		port->msi_domain = irq_domain_add_linear(node,
-							 XILINX_NUM_MSI_IRQS,
-							 &msi_domain_ops,
-							 &xilinx_pcie_msi_chip);
-		if (!port->msi_domain) {
-			dev_err(dev, "Failed to get a MSI IRQ domain\n");
-			return -ENODEV;
-		}
+		phys_addr_t pa = ALIGN_DOWN(virt_to_phys(port), SZ_4K);
 
-		ret = xilinx_pcie_enable_msi(port);
+		ret = xilinx_allocate_msi_domains(port);
 		if (ret)
 			return ret;
+
+		pcie_write(port, upper_32_bits(pa), XILINX_PCIE_REG_MSIBASE1);
+		pcie_write(port, lower_32_bits(pa), XILINX_PCIE_REG_MSIBASE2);
 	}
 
 	return 0;
@@ -572,6 +533,7 @@ static int xilinx_pcie_parse_dt(struct xilinx_pcie_port *port)
 	struct device *dev = port->dev;
 	struct device_node *node = dev->of_node;
 	struct resource regs;
+	unsigned int irq;
 	int err;
 
 	err = of_address_to_resource(node, 0, &regs);
@@ -584,12 +546,12 @@ static int xilinx_pcie_parse_dt(struct xilinx_pcie_port *port)
 	if (IS_ERR(port->reg_base))
 		return PTR_ERR(port->reg_base);
 
-	port->irq = irq_of_parse_and_map(node, 0);
-	err = devm_request_irq(dev, port->irq, xilinx_pcie_intr_handler,
+	irq = irq_of_parse_and_map(node, 0);
+	err = devm_request_irq(dev, irq, xilinx_pcie_intr_handler,
 			       IRQF_SHARED | IRQF_NO_THREAD,
 			       "xilinx-pcie", port);
 	if (err) {
-		dev_err(dev, "unable to request irq %d\n", port->irq);
+		dev_err(dev, "unable to request irq %d\n", irq);
 		return err;
 	}
 
@@ -617,7 +579,7 @@ static int xilinx_pcie_probe(struct platform_device *pdev)
 		return -ENODEV;
 
 	port = pci_host_bridge_priv(bridge);
-
+	mutex_init(&port->map_lock);
 	port->dev = dev;
 
 	err = xilinx_pcie_parse_dt(port);
@@ -637,11 +599,11 @@ static int xilinx_pcie_probe(struct platform_device *pdev)
 	bridge->sysdata = port;
 	bridge->ops = &xilinx_pcie_ops;
 
-#ifdef CONFIG_PCI_MSI
-	xilinx_pcie_msi_chip.dev = dev;
-	bridge->msi = &xilinx_pcie_msi_chip;
-#endif
-	return pci_host_probe(bridge);
+	err = pci_host_probe(bridge);
+	if (err)
+		xilinx_free_msi_domains(port);
+
+	return err;
 }
 
 static const struct of_device_id xilinx_pcie_of_match[] = {
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 5e80f28f0119..e3fcdfec58b3 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -28,6 +28,7 @@
 #define BUS_RESTRICT_CAP(vmcap)	(vmcap & 0x1)
 #define PCI_REG_VMCONFIG	0x44
 #define BUS_RESTRICT_CFG(vmcfg)	((vmcfg >> 8) & 0x3)
+#define VMCONFIG_MSI_REMAP	0x2
 #define PCI_REG_VMLOCK		0x70
 #define MB2_SHADOW_EN(vmlock)	(vmlock & 0x2)
 
@@ -59,6 +60,13 @@ enum vmd_features {
 	 * be used for MSI remapping
 	 */
 	VMD_FEAT_OFFSET_FIRST_VECTOR		= (1 << 3),
+
+	/*
+	 * Device can bypass remapping MSI-X transactions into its MSI-X table,
+	 * avoiding the requirement of a VMD MSI domain for child device
+	 * interrupt handling.
+	 */
+	VMD_FEAT_CAN_BYPASS_MSI_REMAP		= (1 << 4),
 };
 
 /*
@@ -306,6 +314,16 @@ static struct msi_domain_info vmd_msi_domain_info = {
 	.chip		= &vmd_msi_controller,
 };
 
+static void vmd_set_msi_remapping(struct vmd_dev *vmd, bool enable)
+{
+	u16 reg;
+
+	pci_read_config_word(vmd->dev, PCI_REG_VMCONFIG, &reg);
+	reg = enable ? (reg & ~VMCONFIG_MSI_REMAP) :
+		       (reg | VMCONFIG_MSI_REMAP);
+	pci_write_config_word(vmd->dev, PCI_REG_VMCONFIG, reg);
+}
+
 static int vmd_create_irq_domain(struct vmd_dev *vmd)
 {
 	struct fwnode_handle *fn;
@@ -325,6 +343,13 @@ static int vmd_create_irq_domain(struct vmd_dev *vmd)
 
 static void vmd_remove_irq_domain(struct vmd_dev *vmd)
 {
+	/*
+	 * Some production BIOS won't enable remapping between soft reboots.
+	 * Ensure remapping is restored before unloading the driver.
+	 */
+	if (!vmd->msix_count)
+		vmd_set_msi_remapping(vmd, true);
+
 	if (vmd->irq_domain) {
 		struct fwnode_handle *fn = vmd->irq_domain->fwnode;
 
@@ -679,15 +704,32 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features)
 
 	sd->node = pcibus_to_node(vmd->dev->bus);
 
-	ret = vmd_create_irq_domain(vmd);
-	if (ret)
-		return ret;
-
 	/*
-	 * Override the irq domain bus token so the domain can be distinguished
-	 * from a regular PCI/MSI domain.
+	 * Currently MSI remapping must be enabled in guest passthrough mode
+	 * due to some missing interrupt remapping plumbing. This is probably
+	 * acceptable because the guest is usually CPU-limited and MSI
+	 * remapping doesn't become a performance bottleneck.
 	 */
-	irq_domain_update_bus_token(vmd->irq_domain, DOMAIN_BUS_VMD_MSI);
+	if (!(features & VMD_FEAT_CAN_BYPASS_MSI_REMAP) ||
+	    offset[0] || offset[1]) {
+		ret = vmd_alloc_irqs(vmd);
+		if (ret)
+			return ret;
+
+		vmd_set_msi_remapping(vmd, true);
+
+		ret = vmd_create_irq_domain(vmd);
+		if (ret)
+			return ret;
+
+		/*
+		 * Override the IRQ domain bus token so the domain can be
+		 * distinguished from a regular PCI/MSI domain.
+		 */
+		irq_domain_update_bus_token(vmd->irq_domain, DOMAIN_BUS_VMD_MSI);
+	} else {
+		vmd_set_msi_remapping(vmd, false);
+	}
 
 	pci_add_resource(&resources, &vmd->resources[0]);
 	pci_add_resource_offset(&resources, &vmd->resources[1], offset[0]);
@@ -753,10 +795,6 @@ static int vmd_probe(struct pci_dev *dev, const struct pci_device_id *id)
 	if (features & VMD_FEAT_OFFSET_FIRST_VECTOR)
 		vmd->first_vec = 1;
 
-	err = vmd_alloc_irqs(vmd);
-	if (err)
-		return err;
-
 	spin_lock_init(&vmd->cfg_lock);
 	pci_set_drvdata(dev, vmd);
 	err = vmd_enable_domain(vmd, features);
@@ -825,7 +863,8 @@ static const struct pci_device_id vmd_ids[] = {
 		.driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP,},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, PCI_DEVICE_ID_INTEL_VMD_28C0),
 		.driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW |
-				VMD_FEAT_HAS_BUS_RESTRICTIONS,},
+				VMD_FEAT_HAS_BUS_RESTRICTIONS |
+				VMD_FEAT_CAN_BYPASS_MSI_REMAP,},
 	{PCI_DEVICE(PCI_VENDOR_ID_INTEL, 0x467f),
 		.driver_data = VMD_FEAT_HAS_MEMBAR_SHADOW_VSCAP |
 				VMD_FEAT_HAS_BUS_RESTRICTIONS |