Merge branch 'next' into for-linus

Prepare input updates for 5.20 (or 6.0) merge window.

36 files changed, 1663 insertions, 843 deletions

diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index 601f2531ee91..b8d96d38064d 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -10,6 +10,10 @@ config PCI_MVEBU
 	depends on ARM
 	depends on OF
 	select PCI_BRIDGE_EMUL
+	help
+	 Add support for Marvell EBU PCIe controller. This PCIe controller
+	 is used on 32-bit Marvell ARM SoCs: Dove, Kirkwood, Armada 370,
+	 Armada XP, Armada 375, Armada 38x and Armada 39x.
 
 config PCI_AARDVARK
 	tristate "Aardvark PCIe controller"
diff --git a/drivers/pci/controller/cadence/pci-j721e.c b/drivers/pci/controller/cadence/pci-j721e.c
index 768d33f9ebc8..a82f845cc4b5 100644
--- a/drivers/pci/controller/cadence/pci-j721e.c
+++ b/drivers/pci/controller/cadence/pci-j721e.c
@@ -69,6 +69,7 @@ struct j721e_pcie_data {
 	enum j721e_pcie_mode	mode;
 	unsigned int		quirk_retrain_flag:1;
 	unsigned int		quirk_detect_quiet_flag:1;
+	unsigned int		quirk_disable_flr:1;
 	u32			linkdown_irq_regfield;
 	unsigned int		byte_access_allowed:1;
 };
@@ -307,6 +308,7 @@ static const struct j721e_pcie_data j7200_pcie_rc_data = {
 static const struct j721e_pcie_data j7200_pcie_ep_data = {
 	.mode = PCI_MODE_EP,
 	.quirk_detect_quiet_flag = true,
+	.quirk_disable_flr = true,
 };
 
 static const struct j721e_pcie_data am64_pcie_rc_data = {
@@ -405,6 +407,7 @@ static int j721e_pcie_probe(struct platform_device *pdev)
 			return -ENOMEM;
 
 		ep->quirk_detect_quiet_flag = data->quirk_detect_quiet_flag;
+		ep->quirk_disable_flr = data->quirk_disable_flr;
 
 		cdns_pcie = &ep->pcie;
 		cdns_pcie->dev = dev;
diff --git a/drivers/pci/controller/cadence/pcie-cadence-ep.c b/drivers/pci/controller/cadence/pcie-cadence-ep.c
index 88e05b9c2e5b..b8b655d4047e 100644
--- a/drivers/pci/controller/cadence/pcie-cadence-ep.c
+++ b/drivers/pci/controller/cadence/pcie-cadence-ep.c
@@ -187,8 +187,7 @@ static int cdns_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, u8 vfn,
 	struct cdns_pcie *pcie = &ep->pcie;
 	u32 r;
 
-	r = find_first_zero_bit(&ep->ob_region_map,
-				sizeof(ep->ob_region_map) * BITS_PER_LONG);
+	r = find_first_zero_bit(&ep->ob_region_map, BITS_PER_LONG);
 	if (r >= ep->max_regions - 1) {
 		dev_err(&epc->dev, "no free outbound region\n");
 		return -EINVAL;
@@ -565,7 +564,8 @@ static int cdns_pcie_ep_start(struct pci_epc *epc)
 	struct cdns_pcie_ep *ep = epc_get_drvdata(epc);
 	struct cdns_pcie *pcie = &ep->pcie;
 	struct device *dev = pcie->dev;
-	int ret;
+	int max_epfs = sizeof(epc->function_num_map) * 8;
+	int ret, value, epf;
 
 	/*
 	 * BIT(0) is hardwired to 1, hence function 0 is always enabled
@@ -573,6 +573,21 @@ static int cdns_pcie_ep_start(struct pci_epc *epc)
 	 */
 	cdns_pcie_writel(pcie, CDNS_PCIE_LM_EP_FUNC_CFG, epc->function_num_map);
 
+	if (ep->quirk_disable_flr) {
+		for (epf = 0; epf < max_epfs; epf++) {
+			if (!(epc->function_num_map & BIT(epf)))
+				continue;
+
+			value = cdns_pcie_ep_fn_readl(pcie, epf,
+					CDNS_PCIE_EP_FUNC_DEV_CAP_OFFSET +
+					PCI_EXP_DEVCAP);
+			value &= ~PCI_EXP_DEVCAP_FLR;
+			cdns_pcie_ep_fn_writel(pcie, epf,
+					CDNS_PCIE_EP_FUNC_DEV_CAP_OFFSET +
+					PCI_EXP_DEVCAP, value);
+		}
+	}
+
 	ret = cdns_pcie_start_link(pcie);
 	if (ret) {
 		dev_err(dev, "Failed to start link\n");
diff --git a/drivers/pci/controller/cadence/pcie-cadence-host.c b/drivers/pci/controller/cadence/pcie-cadence-host.c
index fb96d37a135c..940c7dd701d6 100644
--- a/drivers/pci/controller/cadence/pcie-cadence-host.c
+++ b/drivers/pci/controller/cadence/pcie-cadence-host.c
@@ -123,6 +123,14 @@ static int cdns_pcie_retrain(struct cdns_pcie *pcie)
 	return ret;
 }
 
+static void cdns_pcie_host_enable_ptm_response(struct cdns_pcie *pcie)
+{
+	u32 val;
+
+	val = cdns_pcie_readl(pcie, CDNS_PCIE_LM_PTM_CTRL);
+	cdns_pcie_writel(pcie, CDNS_PCIE_LM_PTM_CTRL, val | CDNS_PCIE_LM_TPM_CTRL_PTMRSEN);
+}
+
 static int cdns_pcie_host_start_link(struct cdns_pcie_rc *rc)
 {
 	struct cdns_pcie *pcie = &rc->pcie;
@@ -501,6 +509,8 @@ int cdns_pcie_host_setup(struct cdns_pcie_rc *rc)
 	if (rc->quirk_detect_quiet_flag)
 		cdns_pcie_detect_quiet_min_delay_set(&rc->pcie);
 
+	cdns_pcie_host_enable_ptm_response(pcie);
+
 	ret = cdns_pcie_start_link(pcie);
 	if (ret) {
 		dev_err(dev, "Failed to start link\n");
diff --git a/drivers/pci/controller/cadence/pcie-cadence.h b/drivers/pci/controller/cadence/pcie-cadence.h
index c8a27b6290ce..190786e47df9 100644
--- a/drivers/pci/controller/cadence/pcie-cadence.h
+++ b/drivers/pci/controller/cadence/pcie-cadence.h
@@ -116,6 +116,10 @@
 #define LM_RC_BAR_CFG_APERTURE(bar, aperture)		\
 					(((aperture) - 2) << ((bar) * 8))
 
+/* PTM Control Register */
+#define CDNS_PCIE_LM_PTM_CTRL 	(CDNS_PCIE_LM_BASE + 0x0da8)
+#define CDNS_PCIE_LM_TPM_CTRL_PTMRSEN 	BIT(17)
+
 /*
  * Endpoint Function Registers (PCI configuration space for endpoint functions)
  */
@@ -123,6 +127,7 @@
 
 #define CDNS_PCIE_EP_FUNC_MSI_CAP_OFFSET	0x90
 #define CDNS_PCIE_EP_FUNC_MSIX_CAP_OFFSET	0xb0
+#define CDNS_PCIE_EP_FUNC_DEV_CAP_OFFSET	0xc0
 #define CDNS_PCIE_EP_FUNC_SRIOV_CAP_OFFSET	0x200
 
 /*
@@ -357,6 +362,7 @@ struct cdns_pcie_epf {
  *        minimize time between read and write
  * @epf: Structure to hold info about endpoint function
  * @quirk_detect_quiet_flag: LTSSM Detect Quiet min delay set as quirk
+ * @quirk_disable_flr: Disable FLR (Function Level Reset) quirk flag
  */
 struct cdns_pcie_ep {
 	struct cdns_pcie	pcie;
@@ -372,6 +378,7 @@ struct cdns_pcie_ep {
 	spinlock_t		lock;
 	struct cdns_pcie_epf	*epf;
 	unsigned int		quirk_detect_quiet_flag:1;
+	unsigned int		quirk_disable_flr:1;
 };
 
 
diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index 6974bd5aa116..7a285fb0f619 100644
--- a/drivers/pci/controller/dwc/pci-imx6.c
+++ b/drivers/pci/controller/dwc/pci-imx6.c
@@ -408,6 +408,11 @@ static void imx6_pcie_assert_core_reset(struct imx6_pcie *imx6_pcie)
 			dev_err(dev, "failed to disable vpcie regulator: %d\n",
 				ret);
 	}
+
+	/* Some boards don't have PCIe reset GPIO. */
+	if (gpio_is_valid(imx6_pcie->reset_gpio))
+		gpio_set_value_cansleep(imx6_pcie->reset_gpio,
+					imx6_pcie->gpio_active_high);
 }
 
 static unsigned int imx6_pcie_grp_offset(const struct imx6_pcie *imx6_pcie)
@@ -453,10 +458,6 @@ static int imx6_pcie_enable_ref_clk(struct imx6_pcie *imx6_pcie)
 	case IMX7D:
 		break;
 	case IMX8MM:
-		ret = clk_prepare_enable(imx6_pcie->pcie_aux);
-		if (ret)
-			dev_err(dev, "unable to enable pcie_aux clock\n");
-		break;
 	case IMX8MQ:
 		ret = clk_prepare_enable(imx6_pcie->pcie_aux);
 		if (ret) {
@@ -544,15 +545,6 @@ static void imx6_pcie_deassert_core_reset(struct imx6_pcie *imx6_pcie)
 	/* allow the clocks to stabilize */
 	usleep_range(200, 500);
 
-	/* Some boards don't have PCIe reset GPIO. */
-	if (gpio_is_valid(imx6_pcie->reset_gpio)) {
-		gpio_set_value_cansleep(imx6_pcie->reset_gpio,
-					imx6_pcie->gpio_active_high);
-		msleep(100);
-		gpio_set_value_cansleep(imx6_pcie->reset_gpio,
-					!imx6_pcie->gpio_active_high);
-	}
-
 	switch (imx6_pcie->drvdata->variant) {
 	case IMX8MQ:
 		reset_control_deassert(imx6_pcie->pciephy_reset);
@@ -599,6 +591,15 @@ static void imx6_pcie_deassert_core_reset(struct imx6_pcie *imx6_pcie)
 		break;
 	}
 
+	/* Some boards don't have PCIe reset GPIO. */
+	if (gpio_is_valid(imx6_pcie->reset_gpio)) {
+		msleep(100);
+		gpio_set_value_cansleep(imx6_pcie->reset_gpio,
+					!imx6_pcie->gpio_active_high);
+		/* Wait for 100ms after PERST# deassertion (PCIe r5.0, 6.6.1) */
+		msleep(100);
+	}
+
 	return;
 
 err_ref_clk:
@@ -809,9 +810,7 @@ static int imx6_pcie_start_link(struct dw_pcie *pci)
 	/* Start LTSSM. */
 	imx6_pcie_ltssm_enable(dev);
 
-	ret = dw_pcie_wait_for_link(pci);
-	if (ret)
-		goto err_reset_phy;
+	dw_pcie_wait_for_link(pci);
 
 	if (pci->link_gen == 2) {
 		/* Allow Gen2 mode after the link is up. */
@@ -847,11 +846,7 @@ static int imx6_pcie_start_link(struct dw_pcie *pci)
 		}
 
 		/* Make sure link training is finished as well! */
-		ret = dw_pcie_wait_for_link(pci);
-		if (ret) {
-			dev_err(dev, "Failed to bring link up!\n");
-			goto err_reset_phy;
-		}
+		dw_pcie_wait_for_link(pci);
 	} else {
 		dev_info(dev, "Link: Gen2 disabled\n");
 	}
@@ -923,6 +918,7 @@ static void imx6_pcie_pm_turnoff(struct imx6_pcie *imx6_pcie)
 	/* Others poke directly at IOMUXC registers */
 	switch (imx6_pcie->drvdata->variant) {
 	case IMX6SX:
+	case IMX6QP:
 		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
 				IMX6SX_GPR12_PCIE_PM_TURN_OFF,
 				IMX6SX_GPR12_PCIE_PM_TURN_OFF);
@@ -983,6 +979,7 @@ static int imx6_pcie_suspend_noirq(struct device *dev)
 	case IMX8MM:
 		if (phy_power_off(imx6_pcie->phy))
 			dev_err(dev, "unable to power off PHY\n");
+		phy_exit(imx6_pcie->phy);
 		break;
 	default:
 		break;
@@ -1252,7 +1249,8 @@ static const struct imx6_pcie_drvdata drvdata[] = {
 	[IMX6QP] = {
 		.variant = IMX6QP,
 		.flags = IMX6_PCIE_FLAG_IMX6_PHY |
-			 IMX6_PCIE_FLAG_IMX6_SPEED_CHANGE,
+			 IMX6_PCIE_FLAG_IMX6_SPEED_CHANGE |
+			 IMX6_PCIE_FLAG_SUPPORTS_SUSPEND,
 		.dbi_length = 0x200,
 	},
 	[IMX7D] = {
diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index 1c2ee4e13f1c..d10e5fd0f83c 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -531,13 +531,13 @@ static void ks_pcie_quirk(struct pci_dev *dev)
 	struct pci_dev *bridge;
 	static const struct pci_device_id rc_pci_devids[] = {
 		{ PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2HK),
-		 .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, },
+		 .class = PCI_CLASS_BRIDGE_PCI_NORMAL, .class_mask = ~0, },
 		{ PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2E),
-		 .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, },
+		 .class = PCI_CLASS_BRIDGE_PCI_NORMAL, .class_mask = ~0, },
 		{ PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2L),
-		 .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, },
+		 .class = PCI_CLASS_BRIDGE_PCI_NORMAL, .class_mask = ~0, },
 		{ PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2G),
-		 .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, },
+		 .class = PCI_CLASS_BRIDGE_PCI_NORMAL, .class_mask = ~0, },
 		{ 0, },
 	};
 
diff --git a/drivers/pci/controller/dwc/pci-meson.c b/drivers/pci/controller/dwc/pci-meson.c
index 686ded034f22..f44bf347904a 100644
--- a/drivers/pci/controller/dwc/pci-meson.c
+++ b/drivers/pci/controller/dwc/pci-meson.c
@@ -313,14 +313,14 @@ static int meson_pcie_rd_own_conf(struct pci_bus *bus, u32 devfn,
 	 * cannot program the PCI_CLASS_DEVICE register, so we must fabricate
 	 * the return value in the config accessors.
 	 */
-	if (where == PCI_CLASS_REVISION && size == 4)
-		*val = (PCI_CLASS_BRIDGE_PCI << 16) | (*val & 0xffff);
-	else if (where == PCI_CLASS_DEVICE && size == 2)
-		*val = PCI_CLASS_BRIDGE_PCI;
-	else if (where == PCI_CLASS_DEVICE && size == 1)
-		*val = PCI_CLASS_BRIDGE_PCI & 0xff;
-	else if (where == PCI_CLASS_DEVICE + 1 && size == 1)
-		*val = (PCI_CLASS_BRIDGE_PCI >> 8) & 0xff;
+	if ((where & ~3) == PCI_CLASS_REVISION) {
+		if (size <= 2)
+			*val = (*val & ((1 << (size * 8)) - 1)) << (8 * (where & 3));
+		*val &= ~0xffffff00;
+		*val |= PCI_CLASS_BRIDGE_PCI_NORMAL << 8;
+		if (size <= 2)
+			*val = (*val >> (8 * (where & 3))) & ((1 << (size * 8)) - 1);
+	}
 
 	return PCIBIOS_SUCCESSFUL;
 }
diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index f4755f3a03be..9979302532b7 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -362,6 +362,12 @@ int dw_pcie_host_init(struct pcie_port *pp)
 			if (ret < 0)
 				return ret;
 		} else if (pp->has_msi_ctrl) {
+			u32 ctrl, num_ctrls;
+
+			num_ctrls = pp->num_vectors / MAX_MSI_IRQS_PER_CTRL;
+			for (ctrl = 0; ctrl < num_ctrls; ctrl++)
+				pp->irq_mask[ctrl] = ~0;
+
 			if (!pp->msi_irq) {
 				pp->msi_irq = platform_get_irq_byname_optional(pdev, "msi");
 				if (pp->msi_irq < 0) {
@@ -390,7 +396,8 @@ int dw_pcie_host_init(struct pcie_port *pp)
 						      sizeof(pp->msi_msg),
 						      DMA_FROM_DEVICE,
 						      DMA_ATTR_SKIP_CPU_SYNC);
-			if (dma_mapping_error(pci->dev, pp->msi_data)) {
+			ret = dma_mapping_error(pci->dev, pp->msi_data);
+			if (ret) {
 				dev_err(pci->dev, "Failed to map MSI data\n");
 				pp->msi_data = 0;
 				goto err_free_msi;
@@ -541,7 +548,6 @@ void dw_pcie_setup_rc(struct pcie_port *pp)
 
 		/* Initialize IRQ Status array */
 		for (ctrl = 0; ctrl < num_ctrls; ctrl++) {
-			pp->irq_mask[ctrl] = ~0;
 			dw_pcie_writel_dbi(pci, PCIE_MSI_INTR0_MASK +
 					    (ctrl * MSI_REG_CTRL_BLOCK_SIZE),
 					    pp->irq_mask[ctrl]);
diff --git a/drivers/pci/controller/dwc/pcie-dw-rockchip.c b/drivers/pci/controller/dwc/pcie-dw-rockchip.c
index c9b341e55cbb..8c5bb9d7cc36 100644
--- a/drivers/pci/controller/dwc/pcie-dw-rockchip.c
+++ b/drivers/pci/controller/dwc/pcie-dw-rockchip.c
@@ -10,9 +10,12 @@
 
 #include <linux/clk.h>
 #include <linux/gpio/consumer.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
 #include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/of_device.h>
+#include <linux/of_irq.h>
 #include <linux/phy/phy.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
@@ -26,6 +29,7 @@
  */
 #define HIWORD_UPDATE(mask, val) (((mask) << 16) | (val))
 #define HIWORD_UPDATE_BIT(val)	HIWORD_UPDATE(val, val)
+#define HIWORD_DISABLE_BIT(val)	HIWORD_UPDATE(val, ~val)
 
 #define to_rockchip_pcie(x) dev_get_drvdata((x)->dev)
 
@@ -36,10 +40,12 @@
 #define PCIE_LINKUP			(PCIE_SMLH_LINKUP | PCIE_RDLH_LINKUP)
 #define PCIE_L0S_ENTRY			0x11
 #define PCIE_CLIENT_GENERAL_CONTROL	0x0
+#define PCIE_CLIENT_INTR_STATUS_LEGACY	0x8
+#define PCIE_CLIENT_INTR_MASK_LEGACY	0x1c
 #define PCIE_CLIENT_GENERAL_DEBUG	0x104
-#define PCIE_CLIENT_HOT_RESET_CTRL      0x180
+#define PCIE_CLIENT_HOT_RESET_CTRL	0x180
 #define PCIE_CLIENT_LTSSM_STATUS	0x300
-#define PCIE_LTSSM_ENABLE_ENHANCE       BIT(4)
+#define PCIE_LTSSM_ENABLE_ENHANCE	BIT(4)
 #define PCIE_LTSSM_STATUS_MASK		GENMASK(5, 0)
 
 struct rockchip_pcie {
@@ -51,6 +57,7 @@ struct rockchip_pcie {
 	struct reset_control		*rst;
 	struct gpio_desc		*rst_gpio;
 	struct regulator                *vpcie3v3;
+	struct irq_domain		*irq_domain;
 };
 
 static int rockchip_pcie_readl_apb(struct rockchip_pcie *rockchip,
@@ -65,6 +72,78 @@ static void rockchip_pcie_writel_apb(struct rockchip_pcie *rockchip,
 	writel_relaxed(val, rockchip->apb_base + reg);
 }
 
+static void rockchip_pcie_legacy_int_handler(struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct rockchip_pcie *rockchip = irq_desc_get_handler_data(desc);
+	unsigned long reg, hwirq;
+
+	chained_irq_enter(chip, desc);
+
+	reg = rockchip_pcie_readl_apb(rockchip, PCIE_CLIENT_INTR_STATUS_LEGACY);
+
+	for_each_set_bit(hwirq, &reg, 4)
+		generic_handle_domain_irq(rockchip->irq_domain, hwirq);
+
+	chained_irq_exit(chip, desc);
+}
+
+static void rockchip_intx_mask(struct irq_data *data)
+{
+	rockchip_pcie_writel_apb(irq_data_get_irq_chip_data(data),
+				 HIWORD_UPDATE_BIT(BIT(data->hwirq)),
+				 PCIE_CLIENT_INTR_MASK_LEGACY);
+};
+
+static void rockchip_intx_unmask(struct irq_data *data)
+{
+	rockchip_pcie_writel_apb(irq_data_get_irq_chip_data(data),
+				 HIWORD_DISABLE_BIT(BIT(data->hwirq)),
+				 PCIE_CLIENT_INTR_MASK_LEGACY);
+};
+
+static struct irq_chip rockchip_intx_irq_chip = {
+	.name			= "INTx",
+	.irq_mask		= rockchip_intx_mask,
+	.irq_unmask		= rockchip_intx_unmask,
+	.flags			= IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND,
+};
+
+static int rockchip_pcie_intx_map(struct irq_domain *domain, unsigned int irq,
+				  irq_hw_number_t hwirq)
+{
+	irq_set_chip_and_handler(irq, &rockchip_intx_irq_chip, handle_level_irq);
+	irq_set_chip_data(irq, domain->host_data);
+
+	return 0;
+}
+
+static const struct irq_domain_ops intx_domain_ops = {
+	.map = rockchip_pcie_intx_map,
+};
+
+static int rockchip_pcie_init_irq_domain(struct rockchip_pcie *rockchip)
+{
+	struct device *dev = rockchip->pci.dev;
+	struct device_node *intc;
+
+	intc = of_get_child_by_name(dev->of_node, "legacy-interrupt-controller");
+	if (!intc) {
+		dev_err(dev, "missing child interrupt-controller node\n");
+		return -EINVAL;
+	}
+
+	rockchip->irq_domain = irq_domain_add_linear(intc, PCI_NUM_INTX,
+						    &intx_domain_ops, rockchip);
+	of_node_put(intc);
+	if (!rockchip->irq_domain) {
+		dev_err(dev, "failed to get a INTx IRQ domain\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static void rockchip_pcie_enable_ltssm(struct rockchip_pcie *rockchip)
 {
 	rockchip_pcie_writel_apb(rockchip, PCIE_CLIENT_ENABLE_LTSSM,
@@ -111,7 +190,20 @@ static int rockchip_pcie_host_init(struct pcie_port *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct rockchip_pcie *rockchip = to_rockchip_pcie(pci);
+	struct device *dev = rockchip->pci.dev;
 	u32 val = HIWORD_UPDATE_BIT(PCIE_LTSSM_ENABLE_ENHANCE);
+	int irq, ret;
+
+	irq = of_irq_get_byname(dev->of_node, "legacy");
+	if (irq < 0)
+		return irq;
+
+	ret = rockchip_pcie_init_irq_domain(rockchip);
+	if (ret < 0)
+		dev_err(dev, "failed to init irq domain\n");
+
+	irq_set_chained_handler_and_data(irq, rockchip_pcie_legacy_int_handler,
+					 rockchip);
 
 	/* LTSSM enable control mode */
 	rockchip_pcie_writel_apb(rockchip, val, PCIE_CLIENT_HOT_RESET_CTRL);
@@ -152,6 +244,11 @@ static int rockchip_pcie_resource_get(struct platform_device *pdev,
 	if (IS_ERR(rockchip->rst_gpio))
 		return PTR_ERR(rockchip->rst_gpio);
 
+	rockchip->rst = devm_reset_control_array_get_exclusive(&pdev->dev);
+	if (IS_ERR(rockchip->rst))
+		return dev_err_probe(&pdev->dev, PTR_ERR(rockchip->rst),
+				     "failed to get reset lines\n");
+
 	return 0;
 }
 
@@ -182,18 +279,6 @@ static void rockchip_pcie_phy_deinit(struct rockchip_pcie *rockchip)
 	phy_power_off(rockchip->phy);
 }
 
-static int rockchip_pcie_reset_control_release(struct rockchip_pcie *rockchip)
-{
-	struct device *dev = rockchip->pci.dev;
-
-	rockchip->rst = devm_reset_control_array_get_exclusive(dev);
-	if (IS_ERR(rockchip->rst))
-		return dev_err_probe(dev, PTR_ERR(rockchip->rst),
-				     "failed to get reset lines\n");
-
-	return reset_control_deassert(rockchip->rst);
-}
-
 static const struct dw_pcie_ops dw_pcie_ops = {
 	.link_up = rockchip_pcie_link_up,
 	.start_link = rockchip_pcie_start_link,
@@ -222,6 +307,10 @@ static int rockchip_pcie_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
+	ret = reset_control_assert(rockchip->rst);
+	if (ret)
+		return ret;
+
 	/* DON'T MOVE ME: must be enable before PHY init */
 	rockchip->vpcie3v3 = devm_regulator_get_optional(dev, "vpcie3v3");
 	if (IS_ERR(rockchip->vpcie3v3)) {
@@ -241,7 +330,7 @@ static int rockchip_pcie_probe(struct platform_device *pdev)
 	if (ret)
 		goto disable_regulator;
 
-	ret = rockchip_pcie_reset_control_release(rockchip);
+	ret = reset_control_deassert(rockchip->rst);
 	if (ret)
 		goto deinit_phy;
 
diff --git a/drivers/pci/controller/dwc/pcie-fu740.c b/drivers/pci/controller/dwc/pcie-fu740.c
index 00cde9a248b5..02cc70d8cc06 100644
--- a/drivers/pci/controller/dwc/pcie-fu740.c
+++ b/drivers/pci/controller/dwc/pcie-fu740.c
@@ -181,10 +181,59 @@ static int fu740_pcie_start_link(struct dw_pcie *pci)
 {
 	struct device *dev = pci->dev;
 	struct fu740_pcie *afp = dev_get_drvdata(dev);
+	u8 cap_exp = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
+	int ret;
+	u32 orig, tmp;
+
+	/*
+	 * Force 2.5GT/s when starting the link, due to some devices not
+	 * probing at higher speeds. This happens with the PCIe switch
+	 * on the Unmatched board when U-Boot has not initialised the PCIe.
+	 * The fix in U-Boot is to force 2.5GT/s, which then gets cleared
+	 * by the soft reset done by this driver.
+	 */
+	dev_dbg(dev, "cap_exp at %x\n", cap_exp);
+	dw_pcie_dbi_ro_wr_en(pci);
+
+	tmp = dw_pcie_readl_dbi(pci, cap_exp + PCI_EXP_LNKCAP);
+	orig = tmp & PCI_EXP_LNKCAP_SLS;
+	tmp &= ~PCI_EXP_LNKCAP_SLS;
+	tmp |= PCI_EXP_LNKCAP_SLS_2_5GB;
+	dw_pcie_writel_dbi(pci, cap_exp + PCI_EXP_LNKCAP, tmp);
 
 	/* Enable LTSSM */
 	writel_relaxed(0x1, afp->mgmt_base + PCIEX8MGMT_APP_LTSSM_ENABLE);
-	return 0;
+
+	ret = dw_pcie_wait_for_link(pci);
+	if (ret) {
+		dev_err(dev, "error: link did not start\n");
+		goto err;
+	}
+
+	tmp = dw_pcie_readl_dbi(pci, cap_exp + PCI_EXP_LNKCAP);
+	if ((tmp & PCI_EXP_LNKCAP_SLS) != orig) {
+		dev_dbg(dev, "changing speed back to original\n");
+
+		tmp &= ~PCI_EXP_LNKCAP_SLS;
+		tmp |= orig;
+		dw_pcie_writel_dbi(pci, cap_exp + PCI_EXP_LNKCAP, tmp);
+
+		tmp = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL);
+		tmp |= PORT_LOGIC_SPEED_CHANGE;
+		dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, tmp);
+
+		ret = dw_pcie_wait_for_link(pci);
+		if (ret) {
+			dev_err(dev, "error: link did not start at new speed\n");
+			goto err;
+		}
+	}
+
+	ret = 0;
+err:
+	WARN_ON(ret);	/* we assume that errors will be very rare */
+	dw_pcie_dbi_ro_wr_dis(pci);
+	return ret;
 }
 
 static int fu740_pcie_host_init(struct pcie_port *pp)
@@ -224,7 +273,7 @@ static int fu740_pcie_host_init(struct pcie_port *pp)
 	/* Clear hold_phy_rst */
 	writel_relaxed(0x0, afp->mgmt_base + PCIEX8MGMT_APP_HOLD_PHY_RST);
 	/* Enable pcieauxclk */
-	ret = clk_prepare_enable(afp->pcie_aux);
+	clk_prepare_enable(afp->pcie_aux);
 	/* Set RC mode */
 	writel_relaxed(0x4, afp->mgmt_base + PCIEX8MGMT_DEVICE_TYPE);
 
@@ -259,11 +308,11 @@ static int fu740_pcie_probe(struct platform_device *pdev)
 		return PTR_ERR(afp->mgmt_base);
 
 	/* Fetch GPIOs */
-	afp->reset = devm_gpiod_get_optional(dev, "reset-gpios", GPIOD_OUT_LOW);
+	afp->reset = devm_gpiod_get_optional(dev, "reset", 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);
+	afp->pwren = devm_gpiod_get_optional(dev, "pwren", GPIOD_OUT_LOW);
 	if (IS_ERR(afp->pwren))
 		return dev_err_probe(dev, PTR_ERR(afp->pwren), "unable to get pwren-gpios\n");
 
diff --git a/drivers/pci/controller/dwc/pcie-kirin.c b/drivers/pci/controller/dwc/pcie-kirin.c
index c625fc6bb287..a52cad269f85 100644
--- a/drivers/pci/controller/dwc/pcie-kirin.c
+++ b/drivers/pci/controller/dwc/pcie-kirin.c
@@ -332,9 +332,6 @@ static int hi3660_pcie_phy_init(struct platform_device *pdev,
 	pcie->phy_priv = phy;
 	phy->dev = dev;
 
-	/* registers */
-	pdev = container_of(dev, struct platform_device, dev);
-
 	ret = hi3660_pcie_phy_get_clk(phy);
 	if (ret)
 		return ret;
diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c
index 6ce8eddf3a37..ec99116ad05c 100644
--- a/drivers/pci/controller/dwc/pcie-qcom-ep.c
+++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c
@@ -223,11 +223,8 @@ static void qcom_pcie_dw_stop_link(struct dw_pcie *pci)
 	disable_irq(pcie_ep->perst_irq);
 }
 
-static int qcom_pcie_perst_deassert(struct dw_pcie *pci)
+static int qcom_pcie_enable_resources(struct qcom_pcie_ep *pcie_ep)
 {
-	struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci);
-	struct device *dev = pci->dev;
-	u32 val, offset;
 	int ret;
 
 	ret = clk_bulk_prepare_enable(ARRAY_SIZE(qcom_pcie_ep_clks),
@@ -247,6 +244,38 @@ static int qcom_pcie_perst_deassert(struct dw_pcie *pci)
 	if (ret)
 		goto err_phy_exit;
 
+	return 0;
+
+err_phy_exit:
+	phy_exit(pcie_ep->phy);
+err_disable_clk:
+	clk_bulk_disable_unprepare(ARRAY_SIZE(qcom_pcie_ep_clks),
+				   qcom_pcie_ep_clks);
+
+	return ret;
+}
+
+static void qcom_pcie_disable_resources(struct qcom_pcie_ep *pcie_ep)
+{
+	phy_power_off(pcie_ep->phy);
+	phy_exit(pcie_ep->phy);
+	clk_bulk_disable_unprepare(ARRAY_SIZE(qcom_pcie_ep_clks),
+				   qcom_pcie_ep_clks);
+}
+
+static int qcom_pcie_perst_deassert(struct dw_pcie *pci)
+{
+	struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci);
+	struct device *dev = pci->dev;
+	u32 val, offset;
+	int ret;
+
+	ret = qcom_pcie_enable_resources(pcie_ep);
+	if (ret) {
+		dev_err(dev, "Failed to enable resources: %d\n", ret);
+		return ret;
+	}
+
 	/* Assert WAKE# to RC to indicate device is ready */
 	gpiod_set_value_cansleep(pcie_ep->wake, 1);
 	usleep_range(WAKE_DELAY_US, WAKE_DELAY_US + 500);
@@ -335,7 +364,7 @@ static int qcom_pcie_perst_deassert(struct dw_pcie *pci)
 	ret = dw_pcie_ep_init_complete(&pcie_ep->pci.ep);
 	if (ret) {
 		dev_err(dev, "Failed to complete initialization: %d\n", ret);
-		goto err_phy_power_off;
+		goto err_disable_resources;
 	}
 
 	/*
@@ -355,13 +384,8 @@ static int qcom_pcie_perst_deassert(struct dw_pcie *pci)
 
 	return 0;
 
-err_phy_power_off:
-	phy_power_off(pcie_ep->phy);
-err_phy_exit:
-	phy_exit(pcie_ep->phy);
-err_disable_clk:
-	clk_bulk_disable_unprepare(ARRAY_SIZE(qcom_pcie_ep_clks),
-				   qcom_pcie_ep_clks);
+err_disable_resources:
+	qcom_pcie_disable_resources(pcie_ep);
 
 	return ret;
 }
@@ -376,10 +400,7 @@ static void qcom_pcie_perst_assert(struct dw_pcie *pci)
 		return;
 	}
 
-	phy_power_off(pcie_ep->phy);
-	phy_exit(pcie_ep->phy);
-	clk_bulk_disable_unprepare(ARRAY_SIZE(qcom_pcie_ep_clks),
-				   qcom_pcie_ep_clks);
+	qcom_pcie_disable_resources(pcie_ep);
 	pcie_ep->link_status = QCOM_PCIE_EP_LINK_DISABLED;
 }
 
@@ -643,43 +664,26 @@ static int qcom_pcie_ep_probe(struct platform_device *pdev)
 	if (ret)
 		return ret;
 
-	ret = clk_bulk_prepare_enable(ARRAY_SIZE(qcom_pcie_ep_clks),
-				      qcom_pcie_ep_clks);
-	if (ret)
+	ret = qcom_pcie_enable_resources(pcie_ep);
+	if (ret) {
+		dev_err(dev, "Failed to enable resources: %d\n", ret);
 		return ret;
-
-	ret = qcom_pcie_ep_core_reset(pcie_ep);
-	if (ret)
-		goto err_disable_clk;
-
-	ret = phy_init(pcie_ep->phy);
-	if (ret)
-		goto err_disable_clk;
-
-	/* PHY needs to be powered on for dw_pcie_ep_init() */
-	ret = phy_power_on(pcie_ep->phy);
-	if (ret)
-		goto err_phy_exit;
+	}
 
 	ret = dw_pcie_ep_init(&pcie_ep->pci.ep);
 	if (ret) {
 		dev_err(dev, "Failed to initialize endpoint: %d\n", ret);
-		goto err_phy_power_off;
+		goto err_disable_resources;
 	}
 
 	ret = qcom_pcie_ep_enable_irq_resources(pdev, pcie_ep);
 	if (ret)
-		goto err_phy_power_off;
+		goto err_disable_resources;
 
 	return 0;
 
-err_phy_power_off:
-	phy_power_off(pcie_ep->phy);
-err_phy_exit:
-	phy_exit(pcie_ep->phy);
-err_disable_clk:
-	clk_bulk_disable_unprepare(ARRAY_SIZE(qcom_pcie_ep_clks),
-				   qcom_pcie_ep_clks);
+err_disable_resources:
+	qcom_pcie_disable_resources(pcie_ep);
 
 	return ret;
 }
@@ -691,10 +695,7 @@ static int qcom_pcie_ep_remove(struct platform_device *pdev)
 	if (pcie_ep->link_status == QCOM_PCIE_EP_LINK_DISABLED)
 		return 0;
 
-	phy_power_off(pcie_ep->phy);
-	phy_exit(pcie_ep->phy);
-	clk_bulk_disable_unprepare(ARRAY_SIZE(qcom_pcie_ep_clks),
-				   qcom_pcie_ep_clks);
+	qcom_pcie_disable_resources(pcie_ep);
 
 	return 0;
 }
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index c19cd506ed3f..2ea13750b492 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -161,7 +161,7 @@ struct qcom_pcie_resources_2_3_3 {
 
 /* 6 clocks typically, 7 for sm8250 */
 struct qcom_pcie_resources_2_7_0 {
-	struct clk_bulk_data clks[7];
+	struct clk_bulk_data clks[9];
 	int num_clks;
 	struct regulator_bulk_data supplies[2];
 	struct reset_control *pci_reset;
@@ -195,6 +195,10 @@ struct qcom_pcie_ops {
 struct qcom_pcie_cfg {
 	const struct qcom_pcie_ops *ops;
 	unsigned int pipe_clk_need_muxing:1;
+	unsigned int has_tbu_clk:1;
+	unsigned int has_ddrss_sf_tbu_clk:1;
+	unsigned int has_aggre0_clk:1;
+	unsigned int has_aggre1_clk:1;
 };
 
 struct qcom_pcie {
@@ -204,8 +208,7 @@ struct qcom_pcie {
 	union qcom_pcie_resources res;
 	struct phy *phy;
 	struct gpio_desc *reset;
-	const struct qcom_pcie_ops *ops;
-	unsigned int pipe_clk_need_muxing:1;
+	const struct qcom_pcie_cfg *cfg;
 };
 
 #define to_qcom_pcie(x)		dev_get_drvdata((x)->dev)
@@ -229,8 +232,8 @@ static int qcom_pcie_start_link(struct dw_pcie *pci)
 	struct qcom_pcie *pcie = to_qcom_pcie(pci);
 
 	/* Enable Link Training state machine */
-	if (pcie->ops->ltssm_enable)
-		pcie->ops->ltssm_enable(pcie);
+	if (pcie->cfg->ops->ltssm_enable)
+		pcie->cfg->ops->ltssm_enable(pcie);
 
 	return 0;
 }
@@ -1146,6 +1149,7 @@ static int qcom_pcie_get_resources_2_7_0(struct qcom_pcie *pcie)
 	struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0;
 	struct dw_pcie *pci = pcie->pci;
 	struct device *dev = pci->dev;
+	unsigned int idx;
 	int ret;
 
 	res->pci_reset = devm_reset_control_get_exclusive(dev, "pci");
@@ -1159,24 +1163,28 @@ static int qcom_pcie_get_resources_2_7_0(struct qcom_pcie *pcie)
 	if (ret)
 		return ret;
 
-	res->clks[0].id = "aux";
-	res->clks[1].id = "cfg";
-	res->clks[2].id = "bus_master";
-	res->clks[3].id = "bus_slave";
-	res->clks[4].id = "slave_q2a";
-	res->clks[5].id = "tbu";
-	if (of_device_is_compatible(dev->of_node, "qcom,pcie-sm8250")) {
-		res->clks[6].id = "ddrss_sf_tbu";
-		res->num_clks = 7;
-	} else {
-		res->num_clks = 6;
-	}
+	idx = 0;
+	res->clks[idx++].id = "aux";
+	res->clks[idx++].id = "cfg";
+	res->clks[idx++].id = "bus_master";
+	res->clks[idx++].id = "bus_slave";
+	res->clks[idx++].id = "slave_q2a";
+	if (pcie->cfg->has_tbu_clk)
+		res->clks[idx++].id = "tbu";
+	if (pcie->cfg->has_ddrss_sf_tbu_clk)
+		res->clks[idx++].id = "ddrss_sf_tbu";
+	if (pcie->cfg->has_aggre0_clk)
+		res->clks[idx++].id = "aggre0";
+	if (pcie->cfg->has_aggre1_clk)
+		res->clks[idx++].id = "aggre1";
+
+	res->num_clks = idx;
 
 	ret = devm_clk_bulk_get(dev, res->num_clks, res->clks);
 	if (ret < 0)
 		return ret;
 
-	if (pcie->pipe_clk_need_muxing) {
+	if (pcie->cfg->pipe_clk_need_muxing) {
 		res->pipe_clk_src = devm_clk_get(dev, "pipe_mux");
 		if (IS_ERR(res->pipe_clk_src))
 			return PTR_ERR(res->pipe_clk_src);
@@ -1209,7 +1217,7 @@ static int qcom_pcie_init_2_7_0(struct qcom_pcie *pcie)
 	}
 
 	/* Set TCXO as clock source for pcie_pipe_clk_src */
-	if (pcie->pipe_clk_need_muxing)
+	if (pcie->cfg->pipe_clk_need_muxing)
 		clk_set_parent(res->pipe_clk_src, res->ref_clk_src);
 
 	ret = clk_bulk_prepare_enable(res->num_clks, res->clks);
@@ -1230,11 +1238,8 @@ static int qcom_pcie_init_2_7_0(struct qcom_pcie *pcie)
 		goto err_disable_clocks;
 	}
 
-	ret = clk_prepare_enable(res->pipe_clk);
-	if (ret) {
-		dev_err(dev, "cannot prepare/enable pipe clock\n");
-		goto err_disable_clocks;
-	}
+	/* Wait for reset to complete, required on SM8450 */
+	usleep_range(1000, 1500);
 
 	/* configure PCIe to RC mode */
 	writel(DEVICE_TYPE_RC, pcie->parf + PCIE20_PARF_DEVICE_TYPE);
@@ -1284,7 +1289,7 @@ static int qcom_pcie_post_init_2_7_0(struct qcom_pcie *pcie)
 	struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0;
 
 	/* Set pipe clock as clock source for pcie_pipe_clk_src */
-	if (pcie->pipe_clk_need_muxing)
+	if (pcie->cfg->pipe_clk_need_muxing)
 		clk_set_parent(res->pipe_clk_src, res->phy_pipe_clk);
 
 	return clk_prepare_enable(res->pipe_clk);
@@ -1384,7 +1389,7 @@ static int qcom_pcie_host_init(struct pcie_port *pp)
 
 	qcom_ep_reset_assert(pcie);
 
-	ret = pcie->ops->init(pcie);
+	ret = pcie->cfg->ops->init(pcie);
 	if (ret)
 		return ret;
 
@@ -1392,16 +1397,16 @@ static int qcom_pcie_host_init(struct pcie_port *pp)
 	if (ret)
 		goto err_deinit;
 
-	if (pcie->ops->post_init) {
-		ret = pcie->ops->post_init(pcie);
+	if (pcie->cfg->ops->post_init) {
+		ret = pcie->cfg->ops->post_init(pcie);
 		if (ret)
 			goto err_disable_phy;
 	}
 
 	qcom_ep_reset_deassert(pcie);
 
-	if (pcie->ops->config_sid) {
-		ret = pcie->ops->config_sid(pcie);
+	if (pcie->cfg->ops->config_sid) {
+		ret = pcie->cfg->ops->config_sid(pcie);
 		if (ret)
 			goto err;
 	}
@@ -1410,12 +1415,12 @@ static int qcom_pcie_host_init(struct pcie_port *pp)
 
 err:
 	qcom_ep_reset_assert(pcie);
-	if (pcie->ops->post_deinit)
-		pcie->ops->post_deinit(pcie);
+	if (pcie->cfg->ops->post_deinit)
+		pcie->cfg->ops->post_deinit(pcie);
 err_disable_phy:
 	phy_power_off(pcie->phy);
 err_deinit:
-	pcie->ops->deinit(pcie);
+	pcie->cfg->ops->deinit(pcie);
 
 	return ret;
 }
@@ -1509,17 +1514,48 @@ static const struct qcom_pcie_cfg ipq4019_cfg = {
 
 static const struct qcom_pcie_cfg sdm845_cfg = {
 	.ops = &ops_2_7_0,
+	.has_tbu_clk = true,
+};
+
+static const struct qcom_pcie_cfg sm8150_cfg = {
+	/* sm8150 has qcom IP rev 1.5.0. However 1.5.0 ops are same as
+	 * 1.9.0, so reuse the same.
+	 */
+	.ops = &ops_1_9_0,
 };
 
 static const struct qcom_pcie_cfg sm8250_cfg = {
 	.ops = &ops_1_9_0,
+	.has_tbu_clk = true,
+	.has_ddrss_sf_tbu_clk = true,
+};
+
+static const struct qcom_pcie_cfg sm8450_pcie0_cfg = {
+	.ops = &ops_1_9_0,
+	.has_ddrss_sf_tbu_clk = true,
+	.pipe_clk_need_muxing = true,
+	.has_aggre0_clk = true,
+	.has_aggre1_clk = true,
+};
+
+static const struct qcom_pcie_cfg sm8450_pcie1_cfg = {
+	.ops = &ops_1_9_0,
+	.has_ddrss_sf_tbu_clk = true,
+	.pipe_clk_need_muxing = true,
+	.has_aggre1_clk = true,
 };
 
 static const struct qcom_pcie_cfg sc7280_cfg = {
 	.ops = &ops_1_9_0,
+	.has_tbu_clk = true,
 	.pipe_clk_need_muxing = true,
 };
 
+static const struct qcom_pcie_cfg sc8180x_cfg = {
+	.ops = &ops_1_9_0,
+	.has_tbu_clk = true,
+};
+
 static const struct dw_pcie_ops dw_pcie_ops = {
 	.link_up = qcom_pcie_link_up,
 	.start_link = qcom_pcie_start_link,
@@ -1559,8 +1595,7 @@ static int qcom_pcie_probe(struct platform_device *pdev)
 
 	pcie->pci = pci;
 
-	pcie->ops = pcie_cfg->ops;
-	pcie->pipe_clk_need_muxing = pcie_cfg->pipe_clk_need_muxing;
+	pcie->cfg = pcie_cfg;
 
 	pcie->reset = devm_gpiod_get_optional(dev, "perst", GPIOD_OUT_HIGH);
 	if (IS_ERR(pcie->reset)) {
@@ -1586,29 +1621,28 @@ static int qcom_pcie_probe(struct platform_device *pdev)
 		goto err_pm_runtime_put;
 	}
 
-	ret = pcie->ops->get_resources(pcie);
+	ret = pcie->cfg->ops->get_resources(pcie);
 	if (ret)
 		goto err_pm_runtime_put;
 
 	pp->ops = &qcom_pcie_dw_ops;
 
 	ret = phy_init(pcie->phy);
-	if (ret) {
-		pm_runtime_disable(&pdev->dev);
+	if (ret)
 		goto err_pm_runtime_put;
-	}
 
 	platform_set_drvdata(pdev, pcie);
 
 	ret = dw_pcie_host_init(pp);
 	if (ret) {
 		dev_err(dev, "cannot initialize host\n");
-		pm_runtime_disable(&pdev->dev);
-		goto err_pm_runtime_put;
+		goto err_phy_exit;
 	}
 
 	return 0;
 
+err_phy_exit:
+	phy_exit(pcie->phy);
 err_pm_runtime_put:
 	pm_runtime_put(dev);
 	pm_runtime_disable(dev);
@@ -1626,15 +1660,18 @@ static const struct of_device_id qcom_pcie_match[] = {
 	{ .compatible = "qcom,pcie-ipq4019", .data = &ipq4019_cfg },
 	{ .compatible = "qcom,pcie-qcs404", .data = &ipq4019_cfg },
 	{ .compatible = "qcom,pcie-sdm845", .data = &sdm845_cfg },
+	{ .compatible = "qcom,pcie-sm8150", .data = &sm8150_cfg },
 	{ .compatible = "qcom,pcie-sm8250", .data = &sm8250_cfg },
-	{ .compatible = "qcom,pcie-sc8180x", .data = &sm8250_cfg },
+	{ .compatible = "qcom,pcie-sc8180x", .data = &sc8180x_cfg },
+	{ .compatible = "qcom,pcie-sm8450-pcie0", .data = &sm8450_pcie0_cfg },
+	{ .compatible = "qcom,pcie-sm8450-pcie1", .data = &sm8450_pcie1_cfg },
 	{ .compatible = "qcom,pcie-sc7280", .data = &sc7280_cfg },
 	{ }
 };
 
 static void qcom_fixup_class(struct pci_dev *dev)
 {
-	dev->class = PCI_CLASS_BRIDGE_PCI << 8;
+	dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL;
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0101, qcom_fixup_class);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0104, qcom_fixup_class);
diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c
index b1b5f836a806..cc2678490162 100644
--- a/drivers/pci/controller/dwc/pcie-tegra194.c
+++ b/drivers/pci/controller/dwc/pcie-tegra194.c
@@ -186,8 +186,6 @@
 #define N_FTS_VAL					52
 #define FTS_VAL						52
 
-#define PORT_LOGIC_MSI_CTRL_INT_0_EN		0x828
-
 #define GEN3_EQ_CONTROL_OFF			0x8a8
 #define GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC_SHIFT	8
 #define GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC_MASK	GENMASK(23, 8)
@@ -2189,9 +2187,6 @@ static int tegra194_pcie_suspend_noirq(struct device *dev)
 	if (!pcie->link_state)
 		return 0;
 
-	/* Save MSI interrupt vector */
-	pcie->msi_ctrl_int = dw_pcie_readl_dbi(&pcie->pci,
-					       PORT_LOGIC_MSI_CTRL_INT_0_EN);
 	tegra_pcie_downstream_dev_to_D0(pcie);
 	tegra194_pcie_pme_turnoff(pcie);
 	tegra_pcie_unconfig_controller(pcie);
@@ -2223,10 +2218,6 @@ static int tegra194_pcie_resume_noirq(struct device *dev)
 	if (ret < 0)
 		goto fail_host_init;
 
-	/* Restore MSI interrupt vector */
-	dw_pcie_writel_dbi(&pcie->pci, PORT_LOGIC_MSI_CTRL_INT_0_EN,
-			   pcie->msi_ctrl_int);
-
 	return 0;
 
 fail_host_init:
diff --git a/drivers/pci/controller/dwc/pcie-uniphier-ep.c b/drivers/pci/controller/dwc/pcie-uniphier-ep.c
index 69810c6b0d58..4d0a587c0ba5 100644
--- a/drivers/pci/controller/dwc/pcie-uniphier-ep.c
+++ b/drivers/pci/controller/dwc/pcie-uniphier-ep.c
@@ -10,6 +10,7 @@
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/init.h>
+#include <linux/iopoll.h>
 #include <linux/of_device.h>
 #include <linux/pci.h>
 #include <linux/phy/phy.h>
@@ -31,6 +32,17 @@
 #define PCL_RSTCTRL2			0x0024
 #define PCL_RSTCTRL_PHY_RESET		BIT(0)
 
+#define PCL_PINCTRL0			0x002c
+#define PCL_PERST_PLDN_REGEN		BIT(12)
+#define PCL_PERST_NOE_REGEN		BIT(11)
+#define PCL_PERST_OUT_REGEN		BIT(8)
+#define PCL_PERST_PLDN_REGVAL		BIT(4)
+#define PCL_PERST_NOE_REGVAL		BIT(3)
+#define PCL_PERST_OUT_REGVAL		BIT(0)
+
+#define PCL_PIPEMON			0x0044
+#define PCL_PCLK_ALIVE			BIT(15)
+
 #define PCL_MODE			0x8000
 #define PCL_MODE_REGEN			BIT(8)
 #define PCL_MODE_REGVAL			BIT(0)
@@ -51,6 +63,9 @@
 #define PCL_APP_INTX			0x8074
 #define PCL_APP_INTX_SYS_INT		BIT(0)
 
+#define PCL_APP_PM0			0x8078
+#define PCL_SYS_AUX_PWR_DET		BIT(8)
+
 /* assertion time of INTx in usec */
 #define PCL_INTX_WIDTH_USEC		30
 
@@ -60,7 +75,14 @@ struct uniphier_pcie_ep_priv {
 	struct clk *clk, *clk_gio;
 	struct reset_control *rst, *rst_gio;
 	struct phy *phy;
-	const struct pci_epc_features *features;
+	const struct uniphier_pcie_ep_soc_data *data;
+};
+
+struct uniphier_pcie_ep_soc_data {
+	bool has_gio;
+	void (*init)(struct uniphier_pcie_ep_priv *priv);
+	int (*wait)(struct uniphier_pcie_ep_priv *priv);
+	const struct pci_epc_features features;
 };
 
 #define to_uniphier_pcie(x)	dev_get_drvdata((x)->dev)
@@ -91,7 +113,7 @@ static void uniphier_pcie_phy_reset(struct uniphier_pcie_ep_priv *priv,
 	writel(val, priv->base + PCL_RSTCTRL2);
 }
 
-static void uniphier_pcie_init_ep(struct uniphier_pcie_ep_priv *priv)
+static void uniphier_pcie_pro5_init_ep(struct uniphier_pcie_ep_priv *priv)
 {
 	u32 val;
 
@@ -116,6 +138,55 @@ static void uniphier_pcie_init_ep(struct uniphier_pcie_ep_priv *priv)
 	msleep(100);
 }
 
+static void uniphier_pcie_nx1_init_ep(struct uniphier_pcie_ep_priv *priv)
+{
+	u32 val;
+
+	/* set EP mode */
+	val = readl(priv->base + PCL_MODE);
+	val |= PCL_MODE_REGEN | PCL_MODE_REGVAL;
+	writel(val, priv->base + PCL_MODE);
+
+	/* use auxiliary power detection */
+	val = readl(priv->base + PCL_APP_PM0);
+	val |= PCL_SYS_AUX_PWR_DET;
+	writel(val, priv->base + PCL_APP_PM0);
+
+	/* assert PERST# */
+	val = readl(priv->base + PCL_PINCTRL0);
+	val &= ~(PCL_PERST_NOE_REGVAL | PCL_PERST_OUT_REGVAL
+		 | PCL_PERST_PLDN_REGVAL);
+	val |= PCL_PERST_NOE_REGEN | PCL_PERST_OUT_REGEN
+		| PCL_PERST_PLDN_REGEN;
+	writel(val, priv->base + PCL_PINCTRL0);
+
+	uniphier_pcie_ltssm_enable(priv, false);
+
+	usleep_range(100000, 200000);
+
+	/* deassert PERST# */
+	val = readl(priv->base + PCL_PINCTRL0);
+	val |= PCL_PERST_OUT_REGVAL | PCL_PERST_OUT_REGEN;
+	writel(val, priv->base + PCL_PINCTRL0);
+}
+
+static int uniphier_pcie_nx1_wait_ep(struct uniphier_pcie_ep_priv *priv)
+{
+	u32 status;
+	int ret;
+
+	/* wait PIPE clock */
+	ret = readl_poll_timeout(priv->base + PCL_PIPEMON, status,
+				 status & PCL_PCLK_ALIVE, 100000, 1000000);
+	if (ret) {
+		dev_err(priv->pci.dev,
+			"Failed to initialize controller in EP mode\n");
+		return ret;
+	}
+
+	return 0;
+}
+
 static int uniphier_pcie_start_link(struct dw_pcie *pci)
 {
 	struct uniphier_pcie_ep_priv *priv = to_uniphier_pcie(pci);
@@ -209,7 +280,7 @@ uniphier_pcie_get_features(struct dw_pcie_ep *ep)
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct uniphier_pcie_ep_priv *priv = to_uniphier_pcie(pci);
 
-	return priv->features;
+	return &priv->data->features;
 }
 
 static const struct dw_pcie_ep_ops uniphier_pcie_ep_ops = {
@@ -238,7 +309,8 @@ static int uniphier_pcie_ep_enable(struct uniphier_pcie_ep_priv *priv)
 	if (ret)
 		goto out_rst_assert;
 
-	uniphier_pcie_init_ep(priv);
+	if (priv->data->init)
+		priv->data->init(priv);
 
 	uniphier_pcie_phy_reset(priv, true);
 
@@ -248,8 +320,16 @@ static int uniphier_pcie_ep_enable(struct uniphier_pcie_ep_priv *priv)
 
 	uniphier_pcie_phy_reset(priv, false);
 
+	if (priv->data->wait) {
+		ret = priv->data->wait(priv);
+		if (ret)
+			goto out_phy_exit;
+	}
+
 	return 0;
 
+out_phy_exit:
+	phy_exit(priv->phy);
 out_rst_gio_assert:
 	reset_control_assert(priv->rst_gio);
 out_rst_assert:
@@ -277,8 +357,8 @@ static int uniphier_pcie_ep_probe(struct platform_device *pdev)
 	if (!priv)
 		return -ENOMEM;
 
-	priv->features = of_device_get_match_data(dev);
-	if (WARN_ON(!priv->features))
+	priv->data = of_device_get_match_data(dev);
+	if (WARN_ON(!priv->data))
 		return -EINVAL;
 
 	priv->pci.dev = dev;
@@ -288,13 +368,15 @@ static int uniphier_pcie_ep_probe(struct platform_device *pdev)
 	if (IS_ERR(priv->base))
 		return PTR_ERR(priv->base);
 
-	priv->clk_gio = devm_clk_get(dev, "gio");
-	if (IS_ERR(priv->clk_gio))
-		return PTR_ERR(priv->clk_gio);
+	if (priv->data->has_gio) {
+		priv->clk_gio = devm_clk_get(dev, "gio");
+		if (IS_ERR(priv->clk_gio))
+			return PTR_ERR(priv->clk_gio);
 
-	priv->rst_gio = devm_reset_control_get_shared(dev, "gio");
-	if (IS_ERR(priv->rst_gio))
-		return PTR_ERR(priv->rst_gio);
+		priv->rst_gio = devm_reset_control_get_shared(dev, "gio");
+		if (IS_ERR(priv->rst_gio))
+			return PTR_ERR(priv->rst_gio);
+	}
 
 	priv->clk = devm_clk_get(dev, "link");
 	if (IS_ERR(priv->clk))
@@ -321,13 +403,31 @@ static int uniphier_pcie_ep_probe(struct platform_device *pdev)
 	return dw_pcie_ep_init(&priv->pci.ep);
 }
 
-static const struct pci_epc_features uniphier_pro5_data = {
-	.linkup_notifier = false,
-	.msi_capable = true,
-	.msix_capable = false,
-	.align = 1 << 16,
-	.bar_fixed_64bit = BIT(BAR_0) | BIT(BAR_2) | BIT(BAR_4),
-	.reserved_bar =  BIT(BAR_4),
+static const struct uniphier_pcie_ep_soc_data uniphier_pro5_data = {
+	.has_gio = true,
+	.init = uniphier_pcie_pro5_init_ep,
+	.wait = NULL,
+	.features = {
+		.linkup_notifier = false,
+		.msi_capable = true,
+		.msix_capable = false,
+		.align = 1 << 16,
+		.bar_fixed_64bit = BIT(BAR_0) | BIT(BAR_2) | BIT(BAR_4),
+		.reserved_bar =  BIT(BAR_4),
+	},
+};
+
+static const struct uniphier_pcie_ep_soc_data uniphier_nx1_data = {
+	.has_gio = false,
+	.init = uniphier_pcie_nx1_init_ep,
+	.wait = uniphier_pcie_nx1_wait_ep,
+	.features = {
+		.linkup_notifier = false,
+		.msi_capable = true,
+		.msix_capable = false,
+		.align = 1 << 12,
+		.bar_fixed_64bit = BIT(BAR_0) | BIT(BAR_2) | BIT(BAR_4),
+	},
 };
 
 static const struct of_device_id uniphier_pcie_ep_match[] = {
@@ -335,6 +435,10 @@ static const struct of_device_id uniphier_pcie_ep_match[] = {
 		.compatible = "socionext,uniphier-pro5-pcie-ep",
 		.data = &uniphier_pro5_data,
 	},
+	{
+		.compatible = "socionext,uniphier-nx1-pcie-ep",
+		.data = &uniphier_nx1_data,
+	},
 	{ /* sentinel */ },
 };
 
diff --git a/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c b/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c
index f3547aa60140..31a7bdebe540 100644
--- a/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c
+++ b/drivers/pci/controller/mobiveil/pcie-mobiveil-host.c
@@ -295,7 +295,7 @@ int mobiveil_host_init(struct mobiveil_pcie *pcie, bool reinit)
 	/* fixup for PCIe class register */
 	value = mobiveil_csr_readl(pcie, PAB_INTP_AXI_PIO_CLASS);
 	value &= 0xff;
-	value |= (PCI_CLASS_BRIDGE_PCI << 16);
+	value |= PCI_CLASS_BRIDGE_PCI_NORMAL << 8;
 	mobiveil_csr_writel(pcie, value, PAB_INTP_AXI_PIO_CLASS);
 
 	return 0;
diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index 4f5b44827d21..ffec82c8a523 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -38,10 +38,6 @@
 #define     PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX_EN			BIT(6)
 #define     PCIE_CORE_ERR_CAPCTL_ECRC_CHCK			BIT(7)
 #define     PCIE_CORE_ERR_CAPCTL_ECRC_CHCK_RCV			BIT(8)
-#define     PCIE_CORE_INT_A_ASSERT_ENABLE			1
-#define     PCIE_CORE_INT_B_ASSERT_ENABLE			2
-#define     PCIE_CORE_INT_C_ASSERT_ENABLE			3
-#define     PCIE_CORE_INT_D_ASSERT_ENABLE			4
 /* PIO registers base address and register offsets */
 #define PIO_BASE_ADDR				0x4000
 #define PIO_CTRL				(PIO_BASE_ADDR + 0x0)
@@ -102,6 +98,10 @@
 #define PCIE_MSG_PM_PME_MASK			BIT(7)
 #define PCIE_ISR0_MASK_REG			(CONTROL_BASE_ADDR + 0x44)
 #define     PCIE_ISR0_MSI_INT_PENDING		BIT(24)
+#define     PCIE_ISR0_CORR_ERR			BIT(11)
+#define     PCIE_ISR0_NFAT_ERR			BIT(12)
+#define     PCIE_ISR0_FAT_ERR			BIT(13)
+#define     PCIE_ISR0_ERR_MASK			GENMASK(13, 11)
 #define     PCIE_ISR0_INTX_ASSERT(val)		BIT(16 + (val))
 #define     PCIE_ISR0_INTX_DEASSERT(val)	BIT(20 + (val))
 #define     PCIE_ISR0_ALL_MASK			GENMASK(31, 0)
@@ -272,17 +272,15 @@ struct advk_pcie {
 		u32 actions;
 	} wins[OB_WIN_COUNT];
 	u8 wins_count;
+	struct irq_domain *rp_irq_domain;
 	struct irq_domain *irq_domain;
 	struct irq_chip irq_chip;
 	raw_spinlock_t irq_lock;
 	struct irq_domain *msi_domain;
 	struct irq_domain *msi_inner_domain;
-	struct irq_chip msi_bottom_irq_chip;
-	struct irq_chip msi_irq_chip;
-	struct msi_domain_info msi_domain_info;
+	raw_spinlock_t msi_irq_lock;
 	DECLARE_BITMAP(msi_used, MSI_IRQ_NUM);
 	struct mutex msi_used_lock;
-	u16 msi_msg;
 	int link_gen;
 	struct pci_bridge_emul bridge;
 	struct gpio_desc *reset_gpio;
@@ -477,6 +475,7 @@ static void advk_pcie_disable_ob_win(struct advk_pcie *pcie, u8 win_num)
 
 static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 {
+	phys_addr_t msi_addr;
 	u32 reg;
 	int i;
 
@@ -529,7 +528,7 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 	 */
 	reg = advk_readl(pcie, PCIE_CORE_DEV_REV_REG);
 	reg &= ~0xffffff00;
-	reg |= (PCI_CLASS_BRIDGE_PCI << 8) << 8;
+	reg |= PCI_CLASS_BRIDGE_PCI_NORMAL << 8;
 	advk_writel(pcie, reg, PCIE_CORE_DEV_REV_REG);
 
 	/* Disable Root Bridge I/O space, memory space and bus mastering */
@@ -565,6 +564,11 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 	reg |= LANE_COUNT_1;
 	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
 
+	/* Set MSI address */
+	msi_addr = virt_to_phys(pcie);
+	advk_writel(pcie, lower_32_bits(msi_addr), PCIE_MSI_ADDR_LOW_REG);
+	advk_writel(pcie, upper_32_bits(msi_addr), PCIE_MSI_ADDR_HIGH_REG);
+
 	/* Enable MSI */
 	reg = advk_readl(pcie, PCIE_CORE_CTRL2_REG);
 	reg |= PCIE_CORE_CTRL2_MSI_ENABLE;
@@ -576,15 +580,20 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 	advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_REG);
 	advk_writel(pcie, PCIE_IRQ_ALL_MASK, HOST_CTRL_INT_STATUS_REG);
 
-	/* Disable All ISR0/1 Sources */
-	reg = PCIE_ISR0_ALL_MASK;
+	/* Disable All ISR0/1 and MSI Sources */
+	advk_writel(pcie, PCIE_ISR0_ALL_MASK, PCIE_ISR0_MASK_REG);
+	advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_MASK_REG);
+	advk_writel(pcie, PCIE_MSI_ALL_MASK, PCIE_MSI_MASK_REG);
+
+	/* Unmask summary MSI interrupt */
+	reg = advk_readl(pcie, PCIE_ISR0_MASK_REG);
 	reg &= ~PCIE_ISR0_MSI_INT_PENDING;
 	advk_writel(pcie, reg, PCIE_ISR0_MASK_REG);
 
-	advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_MASK_REG);
-
-	/* Unmask all MSIs */
-	advk_writel(pcie, ~(u32)PCIE_MSI_ALL_MASK, PCIE_MSI_MASK_REG);
+	/* Unmask PME interrupt for processing of PME requester */
+	reg = advk_readl(pcie, PCIE_ISR0_MASK_REG);
+	reg &= ~PCIE_MSG_PM_PME_MASK;
+	advk_writel(pcie, reg, PCIE_ISR0_MASK_REG);
 
 	/* Enable summary interrupt for GIC SPI source */
 	reg = PCIE_IRQ_ALL_MASK & (~PCIE_IRQ_ENABLE_INTS_MASK);
@@ -778,11 +787,15 @@ advk_pci_bridge_emul_base_conf_read(struct pci_bridge_emul *bridge,
 	case PCI_INTERRUPT_LINE: {
 		/*
 		 * From the whole 32bit register we support reading from HW only
-		 * one bit: PCI_BRIDGE_CTL_BUS_RESET.
+		 * two bits: PCI_BRIDGE_CTL_BUS_RESET and PCI_BRIDGE_CTL_SERR.
 		 * Other bits are retrieved only from emulated config buffer.
 		 */
 		__le32 *cfgspace = (__le32 *)&bridge->conf;
 		u32 val = le32_to_cpu(cfgspace[PCI_INTERRUPT_LINE / 4]);
+		if (advk_readl(pcie, PCIE_ISR0_MASK_REG) & PCIE_ISR0_ERR_MASK)
+			val &= ~(PCI_BRIDGE_CTL_SERR << 16);
+		else
+			val |= PCI_BRIDGE_CTL_SERR << 16;
 		if (advk_readl(pcie, PCIE_CORE_CTRL1_REG) & HOT_RESET_GEN)
 			val |= PCI_BRIDGE_CTL_BUS_RESET << 16;
 		else
@@ -808,6 +821,19 @@ advk_pci_bridge_emul_base_conf_write(struct pci_bridge_emul *bridge,
 		break;
 
 	case PCI_INTERRUPT_LINE:
+		/*
+		 * According to Figure 6-3: Pseudo Logic Diagram for Error
+		 * Message Controls in PCIe base specification, SERR# Enable bit
+		 * in Bridge Control register enable receiving of ERR_* messages
+		 */
+		if (mask & (PCI_BRIDGE_CTL_SERR << 16)) {
+			u32 val = advk_readl(pcie, PCIE_ISR0_MASK_REG);
+			if (new & (PCI_BRIDGE_CTL_SERR << 16))
+				val &= ~PCIE_ISR0_ERR_MASK;
+			else
+				val |= PCIE_ISR0_ERR_MASK;
+			advk_writel(pcie, val, PCIE_ISR0_MASK_REG);
+		}
 		if (mask & (PCI_BRIDGE_CTL_BUS_RESET << 16)) {
 			u32 val = advk_readl(pcie, PCIE_CORE_CTRL1_REG);
 			if (new & (PCI_BRIDGE_CTL_BUS_RESET << 16))
@@ -835,20 +861,11 @@ advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge,
 		*value = PCI_EXP_SLTSTA_PDS << 16;
 		return PCI_BRIDGE_EMUL_HANDLED;
 
-	case PCI_EXP_RTCTL: {
-		u32 val = advk_readl(pcie, PCIE_ISR0_MASK_REG);
-		*value = (val & PCIE_MSG_PM_PME_MASK) ? 0 : PCI_EXP_RTCTL_PMEIE;
-		*value |= le16_to_cpu(bridge->pcie_conf.rootctl) & PCI_EXP_RTCTL_CRSSVE;
-		*value |= PCI_EXP_RTCAP_CRSVIS << 16;
-		return PCI_BRIDGE_EMUL_HANDLED;
-	}
-
-	case PCI_EXP_RTSTA: {
-		u32 isr0 = advk_readl(pcie, PCIE_ISR0_REG);
-		u32 msglog = advk_readl(pcie, PCIE_MSG_LOG_REG);
-		*value = (isr0 & PCIE_MSG_PM_PME_MASK) << 16 | (msglog >> 16);
-		return PCI_BRIDGE_EMUL_HANDLED;
-	}
+	/*
+	 * PCI_EXP_RTCTL and PCI_EXP_RTSTA are also supported, but do not need
+	 * to be handled here, because their values are stored in emulated
+	 * config space buffer, and we read them from there when needed.
+	 */
 
 	case PCI_EXP_LNKCAP: {
 		u32 val = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg);
@@ -903,19 +920,18 @@ advk_pci_bridge_emul_pcie_conf_write(struct pci_bridge_emul *bridge,
 		break;
 
 	case PCI_EXP_RTCTL: {
-		/* Only mask/unmask PME interrupt */
-		u32 val = advk_readl(pcie, PCIE_ISR0_MASK_REG) &
-			~PCIE_MSG_PM_PME_MASK;
-		if ((new & PCI_EXP_RTCTL_PMEIE) == 0)
-			val |= PCIE_MSG_PM_PME_MASK;
-		advk_writel(pcie, val, PCIE_ISR0_MASK_REG);
+		u16 rootctl = le16_to_cpu(bridge->pcie_conf.rootctl);
+		/* Only emulation of PMEIE and CRSSVE bits is provided */
+		rootctl &= PCI_EXP_RTCTL_PMEIE | PCI_EXP_RTCTL_CRSSVE;
+		bridge->pcie_conf.rootctl = cpu_to_le16(rootctl);
 		break;
 	}
 
-	case PCI_EXP_RTSTA:
-		new = (new & PCI_EXP_RTSTA_PME) >> 9;
-		advk_writel(pcie, new, PCIE_ISR0_REG);
-		break;
+	/*
+	 * PCI_EXP_RTSTA is also supported, but does not need to be handled
+	 * here, because its value is stored in emulated config space buffer,
+	 * and we write it there when needed.
+	 */
 
 	case PCI_EXP_DEVCTL:
 	case PCI_EXP_DEVCTL2:
@@ -928,7 +944,7 @@ advk_pci_bridge_emul_pcie_conf_write(struct pci_bridge_emul *bridge,
 	}
 }
 
-static struct pci_bridge_emul_ops advk_pci_bridge_emul_ops = {
+static const struct pci_bridge_emul_ops advk_pci_bridge_emul_ops = {
 	.read_base = advk_pci_bridge_emul_base_conf_read,
 	.write_base = advk_pci_bridge_emul_base_conf_write,
 	.read_pcie = advk_pci_bridge_emul_pcie_conf_read,
@@ -959,7 +975,7 @@ static int advk_sw_pci_bridge_init(struct advk_pcie *pcie)
 	bridge->conf.pref_mem_limit = cpu_to_le16(PCI_PREF_RANGE_TYPE_64);
 
 	/* Support interrupt A for MSI feature */
-	bridge->conf.intpin = PCIE_CORE_INT_A_ASSERT_ENABLE;
+	bridge->conf.intpin = PCI_INTERRUPT_INTA;
 
 	/* Aardvark HW provides PCIe Capability structure in version 2 */
 	bridge->pcie_conf.cap = cpu_to_le16(2);
@@ -981,8 +997,12 @@ static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus,
 		return false;
 
 	/*
-	 * If the link goes down after we check for link-up, nothing bad
-	 * happens but the config access times out.
+	 * If the link goes down after we check for link-up, we have a problem:
+	 * if a PIO request is executed while link-down, the whole controller
+	 * gets stuck in a non-functional state, and even after link comes up
+	 * again, PIO requests won't work anymore, and a reset of the whole PCIe
+	 * controller is needed. Therefore we need to prevent sending PIO
+	 * requests while the link is down.
 	 */
 	if (!pci_is_root_bus(bus) && !advk_pcie_link_up(pcie))
 		return false;
@@ -1180,11 +1200,11 @@ static void advk_msi_irq_compose_msi_msg(struct irq_data *data,
 					 struct msi_msg *msg)
 {
 	struct advk_pcie *pcie = irq_data_get_irq_chip_data(data);
-	phys_addr_t msi_msg = virt_to_phys(&pcie->msi_msg);
+	phys_addr_t msi_addr = virt_to_phys(pcie);
 
-	msg->address_lo = lower_32_bits(msi_msg);
-	msg->address_hi = upper_32_bits(msi_msg);
-	msg->data = data->irq;
+	msg->address_lo = lower_32_bits(msi_addr);
+	msg->address_hi = upper_32_bits(msi_addr);
+	msg->data = data->hwirq;
 }
 
 static int advk_msi_set_affinity(struct irq_data *irq_data,
@@ -1193,6 +1213,54 @@ static int advk_msi_set_affinity(struct irq_data *irq_data,
 	return -EINVAL;
 }
 
+static void advk_msi_irq_mask(struct irq_data *d)
+{
+	struct advk_pcie *pcie = d->domain->host_data;
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
+	unsigned long flags;
+	u32 mask;
+
+	raw_spin_lock_irqsave(&pcie->msi_irq_lock, flags);
+	mask = advk_readl(pcie, PCIE_MSI_MASK_REG);
+	mask |= BIT(hwirq);
+	advk_writel(pcie, mask, PCIE_MSI_MASK_REG);
+	raw_spin_unlock_irqrestore(&pcie->msi_irq_lock, flags);
+}
+
+static void advk_msi_irq_unmask(struct irq_data *d)
+{
+	struct advk_pcie *pcie = d->domain->host_data;
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
+	unsigned long flags;
+	u32 mask;
+
+	raw_spin_lock_irqsave(&pcie->msi_irq_lock, flags);
+	mask = advk_readl(pcie, PCIE_MSI_MASK_REG);
+	mask &= ~BIT(hwirq);
+	advk_writel(pcie, mask, PCIE_MSI_MASK_REG);
+	raw_spin_unlock_irqrestore(&pcie->msi_irq_lock, flags);
+}
+
+static void advk_msi_top_irq_mask(struct irq_data *d)
+{
+	pci_msi_mask_irq(d);
+	irq_chip_mask_parent(d);
+}
+
+static void advk_msi_top_irq_unmask(struct irq_data *d)
+{
+	pci_msi_unmask_irq(d);
+	irq_chip_unmask_parent(d);
+}
+
+static struct irq_chip advk_msi_bottom_irq_chip = {
+	.name			= "MSI",
+	.irq_compose_msi_msg	= advk_msi_irq_compose_msi_msg,
+	.irq_set_affinity	= advk_msi_set_affinity,
+	.irq_mask		= advk_msi_irq_mask,
+	.irq_unmask		= advk_msi_irq_unmask,
+};
+
 static int advk_msi_irq_domain_alloc(struct irq_domain *domain,
 				     unsigned int virq,
 				     unsigned int nr_irqs, void *args)
@@ -1201,19 +1269,15 @@ static int advk_msi_irq_domain_alloc(struct irq_domain *domain,
 	int hwirq, i;
 
 	mutex_lock(&pcie->msi_used_lock);
-	hwirq = bitmap_find_next_zero_area(pcie->msi_used, MSI_IRQ_NUM,
-					   0, nr_irqs, 0);
-	if (hwirq >= MSI_IRQ_NUM) {
-		mutex_unlock(&pcie->msi_used_lock);
-		return -ENOSPC;
-	}
-
-	bitmap_set(pcie->msi_used, hwirq, nr_irqs);
+	hwirq = bitmap_find_free_region(pcie->msi_used, MSI_IRQ_NUM,
+					order_base_2(nr_irqs));
 	mutex_unlock(&pcie->msi_used_lock);
+	if (hwirq < 0)
+		return -ENOSPC;
 
 	for (i = 0; i < nr_irqs; i++)
 		irq_domain_set_info(domain, virq + i, hwirq + i,
-				    &pcie->msi_bottom_irq_chip,
+				    &advk_msi_bottom_irq_chip,
 				    domain->host_data, handle_simple_irq,
 				    NULL, NULL);
 
@@ -1227,7 +1291,7 @@ static void advk_msi_irq_domain_free(struct irq_domain *domain,
 	struct advk_pcie *pcie = domain->host_data;
 
 	mutex_lock(&pcie->msi_used_lock);
-	bitmap_clear(pcie->msi_used, d->hwirq, nr_irqs);
+	bitmap_release_region(pcie->msi_used, d->hwirq, order_base_2(nr_irqs));
 	mutex_unlock(&pcie->msi_used_lock);
 }
 
@@ -1269,7 +1333,6 @@ static int advk_pcie_irq_map(struct irq_domain *h,
 {
 	struct advk_pcie *pcie = h->host_data;
 
-	advk_pcie_irq_mask(irq_get_irq_data(virq));
 	irq_set_status_flags(virq, IRQ_LEVEL);
 	irq_set_chip_and_handler(virq, &pcie->irq_chip,
 				 handle_level_irq);
@@ -1283,37 +1346,25 @@ static const struct irq_domain_ops advk_pcie_irq_domain_ops = {
 	.xlate = irq_domain_xlate_onecell,
 };
 
+static struct irq_chip advk_msi_irq_chip = {
+	.name		= "advk-MSI",
+	.irq_mask	= advk_msi_top_irq_mask,
+	.irq_unmask	= advk_msi_top_irq_unmask,
+};
+
+static struct msi_domain_info advk_msi_domain_info = {
+	.flags	= MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+		  MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX,
+	.chip	= &advk_msi_irq_chip,
+};
+
 static int advk_pcie_init_msi_irq_domain(struct advk_pcie *pcie)
 {
 	struct device *dev = &pcie->pdev->dev;
-	struct device_node *node = dev->of_node;
-	struct irq_chip *bottom_ic, *msi_ic;
-	struct msi_domain_info *msi_di;
-	phys_addr_t msi_msg_phys;
 
+	raw_spin_lock_init(&pcie->msi_irq_lock);
 	mutex_init(&pcie->msi_used_lock);
 
-	bottom_ic = &pcie->msi_bottom_irq_chip;
-
-	bottom_ic->name = "MSI";
-	bottom_ic->irq_compose_msi_msg = advk_msi_irq_compose_msi_msg;
-	bottom_ic->irq_set_affinity = advk_msi_set_affinity;
-
-	msi_ic = &pcie->msi_irq_chip;
-	msi_ic->name = "advk-MSI";
-
-	msi_di = &pcie->msi_domain_info;
-	msi_di->flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
-		MSI_FLAG_MULTI_PCI_MSI;
-	msi_di->chip = msi_ic;
-
-	msi_msg_phys = virt_to_phys(&pcie->msi_msg);
-
-	advk_writel(pcie, lower_32_bits(msi_msg_phys),
-		    PCIE_MSI_ADDR_LOW_REG);
-	advk_writel(pcie, upper_32_bits(msi_msg_phys),
-		    PCIE_MSI_ADDR_HIGH_REG);
-
 	pcie->msi_inner_domain =
 		irq_domain_add_linear(NULL, MSI_IRQ_NUM,
 				      &advk_msi_domain_ops, pcie);
@@ -1321,8 +1372,9 @@ static int advk_pcie_init_msi_irq_domain(struct advk_pcie *pcie)
 		return -ENOMEM;
 
 	pcie->msi_domain =
-		pci_msi_create_irq_domain(of_node_to_fwnode(node),
-					  msi_di, pcie->msi_inner_domain);
+		pci_msi_create_irq_domain(dev_fwnode(dev),
+					  &advk_msi_domain_info,
+					  pcie->msi_inner_domain);
 	if (!pcie->msi_domain) {
 		irq_domain_remove(pcie->msi_inner_domain);
 		return -ENOMEM;
@@ -1363,7 +1415,6 @@ static int advk_pcie_init_irq_domain(struct advk_pcie *pcie)
 	}
 
 	irq_chip->irq_mask = advk_pcie_irq_mask;
-	irq_chip->irq_mask_ack = advk_pcie_irq_mask;
 	irq_chip->irq_unmask = advk_pcie_irq_unmask;
 
 	pcie->irq_domain =
@@ -1385,10 +1436,73 @@ static void advk_pcie_remove_irq_domain(struct advk_pcie *pcie)
 	irq_domain_remove(pcie->irq_domain);
 }
 
+static struct irq_chip advk_rp_irq_chip = {
+	.name = "advk-RP",
+};
+
+static int advk_pcie_rp_irq_map(struct irq_domain *h,
+				unsigned int virq, irq_hw_number_t hwirq)
+{
+	struct advk_pcie *pcie = h->host_data;
+
+	irq_set_chip_and_handler(virq, &advk_rp_irq_chip, handle_simple_irq);
+	irq_set_chip_data(virq, pcie);
+
+	return 0;
+}
+
+static const struct irq_domain_ops advk_pcie_rp_irq_domain_ops = {
+	.map = advk_pcie_rp_irq_map,
+	.xlate = irq_domain_xlate_onecell,
+};
+
+static int advk_pcie_init_rp_irq_domain(struct advk_pcie *pcie)
+{
+	pcie->rp_irq_domain = irq_domain_add_linear(NULL, 1,
+						    &advk_pcie_rp_irq_domain_ops,
+						    pcie);
+	if (!pcie->rp_irq_domain) {
+		dev_err(&pcie->pdev->dev, "Failed to add Root Port IRQ domain\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void advk_pcie_remove_rp_irq_domain(struct advk_pcie *pcie)
+{
+	irq_domain_remove(pcie->rp_irq_domain);
+}
+
+static void advk_pcie_handle_pme(struct advk_pcie *pcie)
+{
+	u32 requester = advk_readl(pcie, PCIE_MSG_LOG_REG) >> 16;
+
+	advk_writel(pcie, PCIE_MSG_PM_PME_MASK, PCIE_ISR0_REG);
+
+	/*
+	 * PCIE_MSG_LOG_REG contains the last inbound message, so store
+	 * the requester ID only when PME was not asserted yet.
+	 * Also do not trigger PME interrupt when PME is still asserted.
+	 */
+	if (!(le32_to_cpu(pcie->bridge.pcie_conf.rootsta) & PCI_EXP_RTSTA_PME)) {
+		pcie->bridge.pcie_conf.rootsta = cpu_to_le32(requester | PCI_EXP_RTSTA_PME);
+
+		/*
+		 * Trigger PME interrupt only if PMEIE bit in Root Control is set.
+		 * Aardvark HW returns zero for PCI_EXP_FLAGS_IRQ, so use PCIe interrupt 0.
+		 */
+		if (!(le16_to_cpu(pcie->bridge.pcie_conf.rootctl) & PCI_EXP_RTCTL_PMEIE))
+			return;
+
+		if (generic_handle_domain_irq(pcie->rp_irq_domain, 0) == -EINVAL)
+			dev_err_ratelimited(&pcie->pdev->dev, "unhandled PME IRQ\n");
+	}
+}
+
 static void advk_pcie_handle_msi(struct advk_pcie *pcie)
 {
 	u32 msi_val, msi_mask, msi_status, msi_idx;
-	u16 msi_data;
 
 	msi_mask = advk_readl(pcie, PCIE_MSI_MASK_REG);
 	msi_val = advk_readl(pcie, PCIE_MSI_STATUS_REG);
@@ -1398,13 +1512,9 @@ static void advk_pcie_handle_msi(struct advk_pcie *pcie)
 		if (!(BIT(msi_idx) & msi_status))
 			continue;
 
-		/*
-		 * msi_idx contains bits [4:0] of the msi_data and msi_data
-		 * contains 16bit MSI interrupt number
-		 */
 		advk_writel(pcie, BIT(msi_idx), PCIE_MSI_STATUS_REG);
-		msi_data = advk_readl(pcie, PCIE_MSI_PAYLOAD_REG) & PCIE_MSI_DATA_MASK;
-		generic_handle_irq(msi_data);
+		if (generic_handle_domain_irq(pcie->msi_inner_domain, msi_idx) == -EINVAL)
+			dev_err_ratelimited(&pcie->pdev->dev, "unexpected MSI 0x%02x\n", msi_idx);
 	}
 
 	advk_writel(pcie, PCIE_ISR0_MSI_INT_PENDING,
@@ -1425,6 +1535,22 @@ static void advk_pcie_handle_int(struct advk_pcie *pcie)
 	isr1_mask = advk_readl(pcie, PCIE_ISR1_MASK_REG);
 	isr1_status = isr1_val & ((~isr1_mask) & PCIE_ISR1_ALL_MASK);
 
+	/* Process PME interrupt as the first one to do not miss PME requester id */
+	if (isr0_status & PCIE_MSG_PM_PME_MASK)
+		advk_pcie_handle_pme(pcie);
+
+	/* Process ERR interrupt */
+	if (isr0_status & PCIE_ISR0_ERR_MASK) {
+		advk_writel(pcie, PCIE_ISR0_ERR_MASK, PCIE_ISR0_REG);
+
+		/*
+		 * Aardvark HW returns zero for PCI_ERR_ROOT_AER_IRQ, so use
+		 * PCIe interrupt 0
+		 */
+		if (generic_handle_domain_irq(pcie->rp_irq_domain, 0) == -EINVAL)
+			dev_err_ratelimited(&pcie->pdev->dev, "unhandled ERR IRQ\n");
+	}
+
 	/* Process MSI interrupts */
 	if (isr0_status & PCIE_ISR0_MSI_INT_PENDING)
 		advk_pcie_handle_msi(pcie);
@@ -1437,7 +1563,9 @@ static void advk_pcie_handle_int(struct advk_pcie *pcie)
 		advk_writel(pcie, PCIE_ISR1_INTX_ASSERT(i),
 			    PCIE_ISR1_REG);
 
-		generic_handle_domain_irq(pcie->irq_domain, i);
+		if (generic_handle_domain_irq(pcie->irq_domain, i) == -EINVAL)
+			dev_err_ratelimited(&pcie->pdev->dev, "unexpected INT%c IRQ\n",
+					    (char)i + 'A');
 	}
 }
 
@@ -1458,7 +1586,22 @@ static irqreturn_t advk_pcie_irq_handler(int irq, void *arg)
 	return IRQ_HANDLED;
 }
 
-static void __maybe_unused advk_pcie_disable_phy(struct advk_pcie *pcie)
+static int advk_pcie_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+{
+	struct advk_pcie *pcie = dev->bus->sysdata;
+
+	/*
+	 * Emulated root bridge has its own emulated irq chip and irq domain.
+	 * Argument pin is the INTx pin (1=INTA, 2=INTB, 3=INTC, 4=INTD) and
+	 * hwirq for irq_create_mapping() is indexed from zero.
+	 */
+	if (pci_is_root_bus(dev->bus))
+		return irq_create_mapping(pcie->rp_irq_domain, pin - 1);
+	else
+		return of_irq_parse_and_map_pci(dev, slot, pin);
+}
+
+static void advk_pcie_disable_phy(struct advk_pcie *pcie)
 {
 	phy_power_off(pcie->phy);
 	phy_exit(pcie->phy);
@@ -1482,9 +1625,7 @@ static int advk_pcie_enable_phy(struct advk_pcie *pcie)
 	}
 
 	ret = phy_power_on(pcie->phy);
-	if (ret == -EOPNOTSUPP) {
-		dev_warn(&pcie->pdev->dev, "PHY unsupported by firmware\n");
-	} else if (ret) {
+	if (ret) {
 		phy_exit(pcie->phy);
 		return ret;
 	}
@@ -1667,11 +1808,21 @@ static int advk_pcie_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	ret = advk_pcie_init_rp_irq_domain(pcie);
+	if (ret) {
+		dev_err(dev, "Failed to initialize irq\n");
+		advk_pcie_remove_msi_irq_domain(pcie);
+		advk_pcie_remove_irq_domain(pcie);
+		return ret;
+	}
+
 	bridge->sysdata = pcie;
 	bridge->ops = &advk_pcie_ops;
+	bridge->map_irq = advk_pcie_map_irq;
 
 	ret = pci_host_probe(bridge);
 	if (ret < 0) {
+		advk_pcie_remove_rp_irq_domain(pcie);
 		advk_pcie_remove_msi_irq_domain(pcie);
 		advk_pcie_remove_irq_domain(pcie);
 		return ret;
@@ -1720,6 +1871,7 @@ static int advk_pcie_remove(struct platform_device *pdev)
 	advk_writel(pcie, PCIE_IRQ_ALL_MASK, HOST_CTRL_INT_STATUS_REG);
 
 	/* Remove IRQ domains */
+	advk_pcie_remove_rp_irq_domain(pcie);
 	advk_pcie_remove_msi_irq_domain(pcie);
 	advk_pcie_remove_irq_domain(pcie);
 
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index ae0bc2fee4ca..db814f7b93ba 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -92,6 +92,13 @@ static enum pci_protocol_version_t pci_protocol_versions[] = {
 #define SLOT_NAME_SIZE 11
 
 /*
+ * Size of requestor for VMbus; the value is based on the observation
+ * that having more than one request outstanding is 'rare', and so 64
+ * should be generous in ensuring that we don't ever run out.
+ */
+#define HV_PCI_RQSTOR_SIZE 64
+
+/*
  * Message Types
  */
 
@@ -604,17 +611,137 @@ static unsigned int hv_msi_get_int_vector(struct irq_data *data)
 	return cfg->vector;
 }
 
-static void hv_set_msi_entry_from_desc(union hv_msi_entry *msi_entry,
-				       struct msi_desc *msi_desc)
+static int hv_msi_prepare(struct irq_domain *domain, struct device *dev,
+			  int nvec, msi_alloc_info_t *info)
 {
-	msi_entry->address.as_uint32 = msi_desc->msg.address_lo;
-	msi_entry->data.as_uint32 = msi_desc->msg.data;
+	int ret = pci_msi_prepare(domain, dev, nvec, info);
+
+	/*
+	 * By using the interrupt remapper in the hypervisor IOMMU, contiguous
+	 * CPU vectors is not needed for multi-MSI
+	 */
+	if (info->type == X86_IRQ_ALLOC_TYPE_PCI_MSI)
+		info->flags &= ~X86_IRQ_ALLOC_CONTIGUOUS_VECTORS;
+
+	return ret;
 }
 
-static int hv_msi_prepare(struct irq_domain *domain, struct device *dev,
-			  int nvec, msi_alloc_info_t *info)
+/**
+ * hv_arch_irq_unmask() - "Unmask" the IRQ by setting its current
+ * affinity.
+ * @data:	Describes the IRQ
+ *
+ * Build new a destination for the MSI and make a hypercall to
+ * update the Interrupt Redirection Table. "Device Logical ID"
+ * is built out of this PCI bus's instance GUID and the function
+ * number of the device.
+ */
+static void hv_arch_irq_unmask(struct irq_data *data)
 {
-	return pci_msi_prepare(domain, dev, nvec, info);
+	struct msi_desc *msi_desc = irq_data_get_msi_desc(data);
+	struct hv_retarget_device_interrupt *params;
+	struct tran_int_desc *int_desc;
+	struct hv_pcibus_device *hbus;
+	struct cpumask *dest;
+	cpumask_var_t tmp;
+	struct pci_bus *pbus;
+	struct pci_dev *pdev;
+	unsigned long flags;
+	u32 var_size = 0;
+	int cpu, nr_bank;
+	u64 res;
+
+	dest = irq_data_get_effective_affinity_mask(data);
+	pdev = msi_desc_to_pci_dev(msi_desc);
+	pbus = pdev->bus;
+	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
+	int_desc = data->chip_data;
+
+	spin_lock_irqsave(&hbus->retarget_msi_interrupt_lock, flags);
+
+	params = &hbus->retarget_msi_interrupt_params;
+	memset(params, 0, sizeof(*params));
+	params->partition_id = HV_PARTITION_ID_SELF;
+	params->int_entry.source = HV_INTERRUPT_SOURCE_MSI;
+	params->int_entry.msi_entry.address.as_uint32 = int_desc->address & 0xffffffff;
+	params->int_entry.msi_entry.data.as_uint32 = int_desc->data;
+	params->device_id = (hbus->hdev->dev_instance.b[5] << 24) |
+			   (hbus->hdev->dev_instance.b[4] << 16) |
+			   (hbus->hdev->dev_instance.b[7] << 8) |
+			   (hbus->hdev->dev_instance.b[6] & 0xf8) |
+			   PCI_FUNC(pdev->devfn);
+	params->int_target.vector = hv_msi_get_int_vector(data);
+
+	/*
+	 * Honoring apic->delivery_mode set to APIC_DELIVERY_MODE_FIXED by
+	 * setting the HV_DEVICE_INTERRUPT_TARGET_MULTICAST flag results in a
+	 * spurious interrupt storm. Not doing so does not seem to have a
+	 * negative effect (yet?).
+	 */
+
+	if (hbus->protocol_version >= PCI_PROTOCOL_VERSION_1_2) {
+		/*
+		 * PCI_PROTOCOL_VERSION_1_2 supports the VP_SET version of the
+		 * HVCALL_RETARGET_INTERRUPT hypercall, which also coincides
+		 * with >64 VP support.
+		 * ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED
+		 * is not sufficient for this hypercall.
+		 */
+		params->int_target.flags |=
+			HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET;
+
+		if (!alloc_cpumask_var(&tmp, GFP_ATOMIC)) {
+			res = 1;
+			goto exit_unlock;
+		}
+
+		cpumask_and(tmp, dest, cpu_online_mask);
+		nr_bank = cpumask_to_vpset(&params->int_target.vp_set, tmp);
+		free_cpumask_var(tmp);
+
+		if (nr_bank <= 0) {
+			res = 1;
+			goto exit_unlock;
+		}
+
+		/*
+		 * var-sized hypercall, var-size starts after vp_mask (thus
+		 * vp_set.format does not count, but vp_set.valid_bank_mask
+		 * does).
+		 */
+		var_size = 1 + nr_bank;
+	} else {
+		for_each_cpu_and(cpu, dest, cpu_online_mask) {
+			params->int_target.vp_mask |=
+				(1ULL << hv_cpu_number_to_vp_number(cpu));
+		}
+	}
+
+	res = hv_do_hypercall(HVCALL_RETARGET_INTERRUPT | (var_size << 17),
+			      params, NULL);
+
+exit_unlock:
+	spin_unlock_irqrestore(&hbus->retarget_msi_interrupt_lock, flags);
+
+	/*
+	 * During hibernation, when a CPU is offlined, the kernel tries
+	 * to move the interrupt to the remaining CPUs that haven't
+	 * been offlined yet. In this case, the below hv_do_hypercall()
+	 * always fails since the vmbus channel has been closed:
+	 * refer to cpu_disable_common() -> fixup_irqs() ->
+	 * irq_migrate_all_off_this_cpu() -> migrate_one_irq().
+	 *
+	 * Suppress the error message for hibernation because the failure
+	 * during hibernation does not matter (at this time all the devices
+	 * have been frozen). Note: the correct affinity info is still updated
+	 * into the irqdata data structure in migrate_one_irq() ->
+	 * irq_do_set_affinity() -> hv_set_affinity(), so later when the VM
+	 * resumes, hv_pci_restore_msi_state() is able to correctly restore
+	 * the interrupt with the correct affinity.
+	 */
+	if (!hv_result_success(res) && hbus->state != hv_pcibus_removing)
+		dev_err(&hbus->hdev->device,
+			"%s() failed: %#llx", __func__, res);
 }
 #elif defined(CONFIG_ARM64)
 /*
@@ -651,14 +778,6 @@ static unsigned int hv_msi_get_int_vector(struct irq_data *irqd)
 	return irqd->parent_data->hwirq;
 }
 
-static void hv_set_msi_entry_from_desc(union hv_msi_entry *msi_entry,
-				       struct msi_desc *msi_desc)
-{
-	msi_entry->address = ((u64)msi_desc->msg.address_hi << 32) |
-			      msi_desc->msg.address_lo;
-	msi_entry->data = msi_desc->msg.data;
-}
-
 /*
  * @nr_bm_irqs:		Indicates the number of IRQs that were allocated from
  *			the bitmap.
@@ -839,6 +958,12 @@ static struct irq_domain *hv_pci_get_root_domain(void)
 {
 	return hv_msi_gic_irq_domain;
 }
+
+/*
+ * SPIs are used for interrupts of PCI devices and SPIs is managed via GICD
+ * registers which Hyper-V already supports, so no hypercall needed.
+ */
+static void hv_arch_irq_unmask(struct irq_data *data) { }
 #endif /* CONFIG_ARM64 */
 
 /**
@@ -856,11 +981,7 @@ static void hv_pci_generic_compl(void *context, struct pci_response *resp,
 {
 	struct hv_pci_compl *comp_pkt = context;
 
-	if (resp_packet_size >= offsetofend(struct pci_response, status))
-		comp_pkt->completion_status = resp->status;
-	else
-		comp_pkt->completion_status = -1;
-
+	comp_pkt->completion_status = resp->status;
 	complete(&comp_pkt->host_event);
 }
 
@@ -1400,6 +1521,10 @@ static void hv_int_desc_free(struct hv_pci_dev *hpdev,
 		u8 buffer[sizeof(struct pci_delete_interrupt)];
 	} ctxt;
 
+	if (!int_desc->vector_count) {
+		kfree(int_desc);
+		return;
+	}
 	memset(&ctxt, 0, sizeof(ctxt));
 	int_pkt = (struct pci_delete_interrupt *)&ctxt.pkt.message;
 	int_pkt->message_type.type =
@@ -1407,7 +1532,7 @@ static void hv_int_desc_free(struct hv_pci_dev *hpdev,
 	int_pkt->wslot.slot = hpdev->desc.win_slot.slot;
 	int_pkt->int_desc = *int_desc;
 	vmbus_sendpacket(hpdev->hbus->hdev->channel, int_pkt, sizeof(*int_pkt),
-			 (unsigned long)&ctxt.pkt, VM_PKT_DATA_INBAND, 0);
+			 0, VM_PKT_DATA_INBAND, 0);
 	kfree(int_desc);
 }
 
@@ -1456,119 +1581,9 @@ static void hv_irq_mask(struct irq_data *data)
 		irq_chip_mask_parent(data);
 }
 
-/**
- * hv_irq_unmask() - "Unmask" the IRQ by setting its current
- * affinity.
- * @data:	Describes the IRQ
- *
- * Build new a destination for the MSI and make a hypercall to
- * update the Interrupt Redirection Table. "Device Logical ID"
- * is built out of this PCI bus's instance GUID and the function
- * number of the device.
- */
 static void hv_irq_unmask(struct irq_data *data)
 {
-	struct msi_desc *msi_desc = irq_data_get_msi_desc(data);
-	struct hv_retarget_device_interrupt *params;
-	struct hv_pcibus_device *hbus;
-	struct cpumask *dest;
-	cpumask_var_t tmp;
-	struct pci_bus *pbus;
-	struct pci_dev *pdev;
-	unsigned long flags;
-	u32 var_size = 0;
-	int cpu, nr_bank;
-	u64 res;
-
-	dest = irq_data_get_effective_affinity_mask(data);
-	pdev = msi_desc_to_pci_dev(msi_desc);
-	pbus = pdev->bus;
-	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
-
-	spin_lock_irqsave(&hbus->retarget_msi_interrupt_lock, flags);
-
-	params = &hbus->retarget_msi_interrupt_params;
-	memset(params, 0, sizeof(*params));
-	params->partition_id = HV_PARTITION_ID_SELF;
-	params->int_entry.source = HV_INTERRUPT_SOURCE_MSI;
-	hv_set_msi_entry_from_desc(&params->int_entry.msi_entry, msi_desc);
-	params->device_id = (hbus->hdev->dev_instance.b[5] << 24) |
-			   (hbus->hdev->dev_instance.b[4] << 16) |
-			   (hbus->hdev->dev_instance.b[7] << 8) |
-			   (hbus->hdev->dev_instance.b[6] & 0xf8) |
-			   PCI_FUNC(pdev->devfn);
-	params->int_target.vector = hv_msi_get_int_vector(data);
-
-	/*
-	 * Honoring apic->delivery_mode set to APIC_DELIVERY_MODE_FIXED by
-	 * setting the HV_DEVICE_INTERRUPT_TARGET_MULTICAST flag results in a
-	 * spurious interrupt storm. Not doing so does not seem to have a
-	 * negative effect (yet?).
-	 */
-
-	if (hbus->protocol_version >= PCI_PROTOCOL_VERSION_1_2) {
-		/*
-		 * PCI_PROTOCOL_VERSION_1_2 supports the VP_SET version of the
-		 * HVCALL_RETARGET_INTERRUPT hypercall, which also coincides
-		 * with >64 VP support.
-		 * ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED
-		 * is not sufficient for this hypercall.
-		 */
-		params->int_target.flags |=
-			HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET;
-
-		if (!alloc_cpumask_var(&tmp, GFP_ATOMIC)) {
-			res = 1;
-			goto exit_unlock;
-		}
-
-		cpumask_and(tmp, dest, cpu_online_mask);
-		nr_bank = cpumask_to_vpset(&params->int_target.vp_set, tmp);
-		free_cpumask_var(tmp);
-
-		if (nr_bank <= 0) {
-			res = 1;
-			goto exit_unlock;
-		}
-
-		/*
-		 * var-sized hypercall, var-size starts after vp_mask (thus
-		 * vp_set.format does not count, but vp_set.valid_bank_mask
-		 * does).
-		 */
-		var_size = 1 + nr_bank;
-	} else {
-		for_each_cpu_and(cpu, dest, cpu_online_mask) {
-			params->int_target.vp_mask |=
-				(1ULL << hv_cpu_number_to_vp_number(cpu));
-		}
-	}
-
-	res = hv_do_hypercall(HVCALL_RETARGET_INTERRUPT | (var_size << 17),
-			      params, NULL);
-
-exit_unlock:
-	spin_unlock_irqrestore(&hbus->retarget_msi_interrupt_lock, flags);
-
-	/*
-	 * During hibernation, when a CPU is offlined, the kernel tries
-	 * to move the interrupt to the remaining CPUs that haven't
-	 * been offlined yet. In this case, the below hv_do_hypercall()
-	 * always fails since the vmbus channel has been closed:
-	 * refer to cpu_disable_common() -> fixup_irqs() ->
-	 * irq_migrate_all_off_this_cpu() -> migrate_one_irq().
-	 *
-	 * Suppress the error message for hibernation because the failure
-	 * during hibernation does not matter (at this time all the devices
-	 * have been frozen). Note: the correct affinity info is still updated
-	 * into the irqdata data structure in migrate_one_irq() ->
-	 * irq_do_set_affinity() -> hv_set_affinity(), so later when the VM
-	 * resumes, hv_pci_restore_msi_state() is able to correctly restore
-	 * the interrupt with the correct affinity.
-	 */
-	if (!hv_result_success(res) && hbus->state != hv_pcibus_removing)
-		dev_err(&hbus->hdev->device,
-			"%s() failed: %#llx", __func__, res);
+	hv_arch_irq_unmask(data);
 
 	if (data->parent_data->chip->irq_unmask)
 		irq_chip_unmask_parent(data);
@@ -1587,19 +1602,24 @@ static void hv_pci_compose_compl(void *context, struct pci_response *resp,
 	struct pci_create_int_response *int_resp =
 		(struct pci_create_int_response *)resp;
 
+	if (resp_packet_size < sizeof(*int_resp)) {
+		comp_pkt->comp_pkt.completion_status = -1;
+		goto out;
+	}
 	comp_pkt->comp_pkt.completion_status = resp->status;
 	comp_pkt->int_desc = int_resp->int_desc;
+out:
 	complete(&comp_pkt->comp_pkt.host_event);
 }
 
 static u32 hv_compose_msi_req_v1(
 	struct pci_create_interrupt *int_pkt, struct cpumask *affinity,
-	u32 slot, u8 vector)
+	u32 slot, u8 vector, u8 vector_count)
 {
 	int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE;
 	int_pkt->wslot.slot = slot;
 	int_pkt->int_desc.vector = vector;
-	int_pkt->int_desc.vector_count = 1;
+	int_pkt->int_desc.vector_count = vector_count;
 	int_pkt->int_desc.delivery_mode = DELIVERY_MODE;
 
 	/*
@@ -1622,14 +1642,14 @@ static int hv_compose_msi_req_get_cpu(struct cpumask *affinity)
 
 static u32 hv_compose_msi_req_v2(
 	struct pci_create_interrupt2 *int_pkt, struct cpumask *affinity,
-	u32 slot, u8 vector)
+	u32 slot, u8 vector, u8 vector_count)
 {
 	int cpu;
 
 	int_pkt->message_type.type = PCI_CREATE_INTERRUPT_MESSAGE2;
 	int_pkt->wslot.slot = slot;
 	int_pkt->int_desc.vector = vector;
-	int_pkt->int_desc.vector_count = 1;
+	int_pkt->int_desc.vector_count = vector_count;
 	int_pkt->int_desc.delivery_mode = DELIVERY_MODE;
 	cpu = hv_compose_msi_req_get_cpu(affinity);
 	int_pkt->int_desc.processor_array[0] =
@@ -1641,7 +1661,7 @@ static u32 hv_compose_msi_req_v2(
 
 static u32 hv_compose_msi_req_v3(
 	struct pci_create_interrupt3 *int_pkt, struct cpumask *affinity,
-	u32 slot, u32 vector)
+	u32 slot, u32 vector, u8 vector_count)
 {
 	int cpu;
 
@@ -1649,7 +1669,7 @@ static u32 hv_compose_msi_req_v3(
 	int_pkt->wslot.slot = slot;
 	int_pkt->int_desc.vector = vector;
 	int_pkt->int_desc.reserved = 0;
-	int_pkt->int_desc.vector_count = 1;
+	int_pkt->int_desc.vector_count = vector_count;
 	int_pkt->int_desc.delivery_mode = DELIVERY_MODE;
 	cpu = hv_compose_msi_req_get_cpu(affinity);
 	int_pkt->int_desc.processor_array[0] =
@@ -1680,6 +1700,8 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 	struct cpumask *dest;
 	struct compose_comp_ctxt comp;
 	struct tran_int_desc *int_desc;
+	struct msi_desc *msi_desc;
+	u8 vector, vector_count;
 	struct {
 		struct pci_packet pci_pkt;
 		union {
@@ -1688,11 +1710,21 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 			struct pci_create_interrupt3 v3;
 		} int_pkts;
 	} __packed ctxt;
-
+	u64 trans_id;
 	u32 size;
 	int ret;
 
-	pdev = msi_desc_to_pci_dev(irq_data_get_msi_desc(data));
+	/* Reuse the previous allocation */
+	if (data->chip_data) {
+		int_desc = data->chip_data;
+		msg->address_hi = int_desc->address >> 32;
+		msg->address_lo = int_desc->address & 0xffffffff;
+		msg->data = int_desc->data;
+		return;
+	}
+
+	msi_desc  = irq_data_get_msi_desc(data);
+	pdev = msi_desc_to_pci_dev(msi_desc);
 	dest = irq_data_get_effective_affinity_mask(data);
 	pbus = pdev->bus;
 	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
@@ -1701,17 +1733,40 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 	if (!hpdev)
 		goto return_null_message;
 
-	/* Free any previous message that might have already been composed. */
-	if (data->chip_data) {
-		int_desc = data->chip_data;
-		data->chip_data = NULL;
-		hv_int_desc_free(hpdev, int_desc);
-	}
-
 	int_desc = kzalloc(sizeof(*int_desc), GFP_ATOMIC);
 	if (!int_desc)
 		goto drop_reference;
 
+	if (!msi_desc->pci.msi_attrib.is_msix && msi_desc->nvec_used > 1) {
+		/*
+		 * If this is not the first MSI of Multi MSI, we already have
+		 * a mapping.  Can exit early.
+		 */
+		if (msi_desc->irq != data->irq) {
+			data->chip_data = int_desc;
+			int_desc->address = msi_desc->msg.address_lo |
+					    (u64)msi_desc->msg.address_hi << 32;
+			int_desc->data = msi_desc->msg.data +
+					 (data->irq - msi_desc->irq);
+			msg->address_hi = msi_desc->msg.address_hi;
+			msg->address_lo = msi_desc->msg.address_lo;
+			msg->data = int_desc->data;
+			put_pcichild(hpdev);
+			return;
+		}
+		/*
+		 * The vector we select here is a dummy value.  The correct
+		 * value gets sent to the hypervisor in unmask().  This needs
+		 * to be aligned with the count, and also not zero.  Multi-msi
+		 * is powers of 2 up to 32, so 32 will always work here.
+		 */
+		vector = 32;
+		vector_count = msi_desc->nvec_used;
+	} else {
+		vector = hv_msi_get_int_vector(data);
+		vector_count = 1;
+	}
+
 	memset(&ctxt, 0, sizeof(ctxt));
 	init_completion(&comp.comp_pkt.host_event);
 	ctxt.pci_pkt.completion_func = hv_pci_compose_compl;
@@ -1722,7 +1777,8 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 		size = hv_compose_msi_req_v1(&ctxt.int_pkts.v1,
 					dest,
 					hpdev->desc.win_slot.slot,
-					hv_msi_get_int_vector(data));
+					vector,
+					vector_count);
 		break;
 
 	case PCI_PROTOCOL_VERSION_1_2:
@@ -1730,14 +1786,16 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 		size = hv_compose_msi_req_v2(&ctxt.int_pkts.v2,
 					dest,
 					hpdev->desc.win_slot.slot,
-					hv_msi_get_int_vector(data));
+					vector,
+					vector_count);
 		break;
 
 	case PCI_PROTOCOL_VERSION_1_4:
 		size = hv_compose_msi_req_v3(&ctxt.int_pkts.v3,
 					dest,
 					hpdev->desc.win_slot.slot,
-					hv_msi_get_int_vector(data));
+					vector,
+					vector_count);
 		break;
 
 	default:
@@ -1750,10 +1808,10 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 		goto free_int_desc;
 	}
 
-	ret = vmbus_sendpacket(hpdev->hbus->hdev->channel, &ctxt.int_pkts,
-			       size, (unsigned long)&ctxt.pci_pkt,
-			       VM_PKT_DATA_INBAND,
-			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+	ret = vmbus_sendpacket_getid(hpdev->hbus->hdev->channel, &ctxt.int_pkts,
+				     size, (unsigned long)&ctxt.pci_pkt,
+				     &trans_id, VM_PKT_DATA_INBAND,
+				     VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
 	if (ret) {
 		dev_err(&hbus->hdev->device,
 			"Sending request for interrupt failed: 0x%x",
@@ -1832,6 +1890,15 @@ static void hv_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 
 enable_tasklet:
 	tasklet_enable(&channel->callback_event);
+	/*
+	 * The completion packet on the stack becomes invalid after 'return';
+	 * remove the ID from the VMbus requestor if the identifier is still
+	 * mapped to/associated with the packet.  (The identifier could have
+	 * been 're-used', i.e., already removed and (re-)mapped.)
+	 *
+	 * Cf. hv_pci_onchannelcallback().
+	 */
+	vmbus_request_addr_match(channel, trans_id, (unsigned long)&ctxt.pci_pkt);
 free_int_desc:
 	kfree(int_desc);
 drop_reference:
@@ -2079,12 +2146,17 @@ static void prepopulate_bars(struct hv_pcibus_device *hbus)
 				}
 			}
 			if (high_size <= 1 && low_size <= 1) {
-				/* Set the memory enable bit. */
-				_hv_pcifront_read_config(hpdev, PCI_COMMAND, 2,
-							 &command);
-				command |= PCI_COMMAND_MEMORY;
-				_hv_pcifront_write_config(hpdev, PCI_COMMAND, 2,
-							  command);
+				/*
+				 * No need to set the PCI_COMMAND_MEMORY bit as
+				 * the core PCI driver doesn't require the bit
+				 * to be pre-set. Actually here we intentionally
+				 * keep the bit off so that the PCI BAR probing
+				 * in the core PCI driver doesn't cause Hyper-V
+				 * to unnecessarily unmap/map the virtual BARs
+				 * from/to the physical BARs multiple times.
+				 * This reduces the VM boot time significantly
+				 * if the BAR sizes are huge.
+				 */
 				break;
 			}
 		}
@@ -2220,12 +2292,14 @@ static void q_resource_requirements(void *context, struct pci_response *resp,
 	struct q_res_req_compl *completion = context;
 	struct pci_q_res_req_response *q_res_req =
 		(struct pci_q_res_req_response *)resp;
+	s32 status;
 	int i;
 
-	if (resp->status < 0) {
+	status = (resp_packet_size < sizeof(*q_res_req)) ? -1 : resp->status;
+	if (status < 0) {
 		dev_err(&completion->hpdev->hbus->hdev->device,
 			"query resource requirements failed: %x\n",
-			resp->status);
+			status);
 	} else {
 		for (i = 0; i < PCI_STD_NUM_BARS; i++) {
 			completion->hpdev->probed_bar[i] =
@@ -2649,7 +2723,7 @@ static void hv_eject_device_work(struct work_struct *work)
 	ejct_pkt->message_type.type = PCI_EJECTION_COMPLETE;
 	ejct_pkt->wslot.slot = hpdev->desc.win_slot.slot;
 	vmbus_sendpacket(hbus->hdev->channel, ejct_pkt,
-			 sizeof(*ejct_pkt), (unsigned long)&ctxt.pkt,
+			 sizeof(*ejct_pkt), 0,
 			 VM_PKT_DATA_INBAND, 0);
 
 	/* For the get_pcichild() in hv_pci_eject_device() */
@@ -2696,8 +2770,9 @@ static void hv_pci_onchannelcallback(void *context)
 	const int packet_size = 0x100;
 	int ret;
 	struct hv_pcibus_device *hbus = context;
+	struct vmbus_channel *chan = hbus->hdev->channel;
 	u32 bytes_recvd;
-	u64 req_id;
+	u64 req_id, req_addr;
 	struct vmpacket_descriptor *desc;
 	unsigned char *buffer;
 	int bufferlen = packet_size;
@@ -2709,14 +2784,15 @@ static void hv_pci_onchannelcallback(void *context)
 	struct pci_dev_inval_block *inval;
 	struct pci_dev_incoming *dev_message;
 	struct hv_pci_dev *hpdev;
+	unsigned long flags;
 
 	buffer = kmalloc(bufferlen, GFP_ATOMIC);
 	if (!buffer)
 		return;
 
 	while (1) {
-		ret = vmbus_recvpacket_raw(hbus->hdev->channel, buffer,
-					   bufferlen, &bytes_recvd, &req_id);
+		ret = vmbus_recvpacket_raw(chan, buffer, bufferlen,
+					   &bytes_recvd, &req_id);
 
 		if (ret == -ENOBUFS) {
 			kfree(buffer);
@@ -2743,15 +2819,29 @@ static void hv_pci_onchannelcallback(void *context)
 		switch (desc->type) {
 		case VM_PKT_COMP:
 
+			lock_requestor(chan, flags);
+			req_addr = __vmbus_request_addr_match(chan, req_id,
+							      VMBUS_RQST_ADDR_ANY);
+			if (req_addr == VMBUS_RQST_ERROR) {
+				unlock_requestor(chan, flags);
+				dev_err(&hbus->hdev->device,
+					"Invalid transaction ID %llx\n",
+					req_id);
+				break;
+			}
+			comp_packet = (struct pci_packet *)req_addr;
+			response = (struct pci_response *)buffer;
 			/*
-			 * The host is trusted, and thus it's safe to interpret
-			 * this transaction ID as a pointer.
+			 * Call ->completion_func() within the critical section to make
+			 * sure that the packet pointer is still valid during the call:
+			 * here 'valid' means that there's a task still waiting for the
+			 * completion, and that the packet data is still on the waiting
+			 * task's stack.  Cf. hv_compose_msi_msg().
 			 */
-			comp_packet = (struct pci_packet *)req_id;
-			response = (struct pci_response *)buffer;
 			comp_packet->completion_func(comp_packet->compl_ctxt,
 						     response,
 						     bytes_recvd);
+			unlock_requestor(chan, flags);
 			break;
 
 		case VM_PKT_DATA_INBAND:
@@ -2761,7 +2851,8 @@ static void hv_pci_onchannelcallback(void *context)
 			case PCI_BUS_RELATIONS:
 
 				bus_rel = (struct pci_bus_relations *)buffer;
-				if (bytes_recvd <
+				if (bytes_recvd < sizeof(*bus_rel) ||
+				    bytes_recvd <
 					struct_size(bus_rel, func,
 						    bus_rel->device_count)) {
 					dev_err(&hbus->hdev->device,
@@ -2775,7 +2866,8 @@ static void hv_pci_onchannelcallback(void *context)
 			case PCI_BUS_RELATIONS2:
 
 				bus_rel2 = (struct pci_bus_relations2 *)buffer;
-				if (bytes_recvd <
+				if (bytes_recvd < sizeof(*bus_rel2) ||
+				    bytes_recvd <
 					struct_size(bus_rel2, func,
 						    bus_rel2->device_count)) {
 					dev_err(&hbus->hdev->device,
@@ -2789,6 +2881,11 @@ static void hv_pci_onchannelcallback(void *context)
 			case PCI_EJECT:
 
 				dev_message = (struct pci_dev_incoming *)buffer;
+				if (bytes_recvd < sizeof(*dev_message)) {
+					dev_err(&hbus->hdev->device,
+						"eject message too small\n");
+					break;
+				}
 				hpdev = get_pcichild_wslot(hbus,
 						      dev_message->wslot.slot);
 				if (hpdev) {
@@ -2800,6 +2897,11 @@ static void hv_pci_onchannelcallback(void *context)
 			case PCI_INVALIDATE_BLOCK:
 
 				inval = (struct pci_dev_inval_block *)buffer;
+				if (bytes_recvd < sizeof(*inval)) {
+					dev_err(&hbus->hdev->device,
+						"invalidate message too small\n");
+					break;
+				}
 				hpdev = get_pcichild_wslot(hbus,
 							   inval->wslot.slot);
 				if (hpdev) {
@@ -3404,6 +3506,15 @@ static int hv_pci_probe(struct hv_device *hdev,
 	hbus->bridge->domain_nr = dom;
 #ifdef CONFIG_X86
 	hbus->sysdata.domain = dom;
+#elif defined(CONFIG_ARM64)
+	/*
+	 * Set the PCI bus parent to be the corresponding VMbus
+	 * device. Then the VMbus device will be assigned as the
+	 * ACPI companion in pcibios_root_bridge_prepare() and
+	 * pci_dma_configure() will propagate device coherence
+	 * information to devices created on the bus.
+	 */
+	hbus->sysdata.parent = hdev->device.parent;
 #endif
 
 	hbus->hdev = hdev;
@@ -3419,6 +3530,10 @@ static int hv_pci_probe(struct hv_device *hdev,
 		goto free_dom;
 	}
 
+	hdev->channel->next_request_id_callback = vmbus_next_request_id;
+	hdev->channel->request_addr_callback = vmbus_request_addr;
+	hdev->channel->rqstor_size = HV_PCI_RQSTOR_SIZE;
+
 	ret = vmbus_open(hdev->channel, pci_ring_size, pci_ring_size, NULL, 0,
 			 hv_pci_onchannelcallback, hbus);
 	if (ret)
@@ -3549,6 +3664,7 @@ free_bus:
 static int hv_pci_bus_exit(struct hv_device *hdev, bool keep_devs)
 {
 	struct hv_pcibus_device *hbus = hv_get_drvdata(hdev);
+	struct vmbus_channel *chan = hdev->channel;
 	struct {
 		struct pci_packet teardown_packet;
 		u8 buffer[sizeof(struct pci_message)];
@@ -3556,13 +3672,14 @@ static int hv_pci_bus_exit(struct hv_device *hdev, bool keep_devs)
 	struct hv_pci_compl comp_pkt;
 	struct hv_pci_dev *hpdev, *tmp;
 	unsigned long flags;
+	u64 trans_id;
 	int ret;
 
 	/*
 	 * After the host sends the RESCIND_CHANNEL message, it doesn't
 	 * access the per-channel ringbuffer any longer.
 	 */
-	if (hdev->channel->rescind)
+	if (chan->rescind)
 		return 0;
 
 	if (!keep_devs) {
@@ -3599,16 +3716,26 @@ static int hv_pci_bus_exit(struct hv_device *hdev, bool keep_devs)
 	pkt.teardown_packet.compl_ctxt = &comp_pkt;
 	pkt.teardown_packet.message[0].type = PCI_BUS_D0EXIT;
 
-	ret = vmbus_sendpacket(hdev->channel, &pkt.teardown_packet.message,
-			       sizeof(struct pci_message),
-			       (unsigned long)&pkt.teardown_packet,
-			       VM_PKT_DATA_INBAND,
-			       VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
+	ret = vmbus_sendpacket_getid(chan, &pkt.teardown_packet.message,
+				     sizeof(struct pci_message),
+				     (unsigned long)&pkt.teardown_packet,
+				     &trans_id, VM_PKT_DATA_INBAND,
+				     VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED);
 	if (ret)
 		return ret;
 
-	if (wait_for_completion_timeout(&comp_pkt.host_event, 10 * HZ) == 0)
+	if (wait_for_completion_timeout(&comp_pkt.host_event, 10 * HZ) == 0) {
+		/*
+		 * The completion packet on the stack becomes invalid after
+		 * 'return'; remove the ID from the VMbus requestor if the
+		 * identifier is still mapped to/associated with the packet.
+		 *
+		 * Cf. hv_pci_onchannelcallback().
+		 */
+		vmbus_request_addr_match(chan, trans_id,
+					 (unsigned long)&pkt.teardown_packet);
 		return -ETIMEDOUT;
+	}
 
 	return 0;
 }
@@ -3749,6 +3876,10 @@ static int hv_pci_resume(struct hv_device *hdev)
 
 	hbus->state = hv_pcibus_init;
 
+	hdev->channel->next_request_id_callback = vmbus_next_request_id;
+	hdev->channel->request_addr_callback = vmbus_request_addr;
+	hdev->channel->rqstor_size = HV_PCI_RQSTOR_SIZE;
+
 	ret = vmbus_open(hdev->channel, pci_ring_size, pci_ring_size, NULL, 0,
 			 hv_pci_onchannelcallback, hbus);
 	if (ret)
diff --git a/drivers/pci/controller/pci-loongson.c b/drivers/pci/controller/pci-loongson.c
index 48169b1e3817..50a8e1d6f70a 100644
--- a/drivers/pci/controller/pci-loongson.c
+++ b/drivers/pci/controller/pci-loongson.c
@@ -35,7 +35,7 @@ struct loongson_pci {
 /* Fixup wrong class code in PCIe bridges */
 static void bridge_class_quirk(struct pci_dev *dev)
 {
-	dev->class = PCI_CLASS_BRIDGE_PCI << 8;
+	dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL;
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON,
 			DEV_PCIE_PORT_0, bridge_class_quirk);
diff --git a/drivers/pci/controller/pci-mvebu.c b/drivers/pci/controller/pci-mvebu.c
index f8e82c5e2d87..c1ffdb06c971 100644
--- a/drivers/pci/controller/pci-mvebu.c
+++ b/drivers/pci/controller/pci-mvebu.c
@@ -8,6 +8,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/pci.h>
+#include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/gpio.h>
@@ -32,8 +33,9 @@
 #define PCIE_DEV_REV_OFF	0x0008
 #define PCIE_BAR_LO_OFF(n)	(0x0010 + ((n) << 3))
 #define PCIE_BAR_HI_OFF(n)	(0x0014 + ((n) << 3))
+#define PCIE_SSDEV_ID_OFF	0x002c
 #define PCIE_CAP_PCIEXP		0x0060
-#define PCIE_HEADER_LOG_4_OFF	0x0128
+#define PCIE_CAP_PCIERR_OFF	0x0100
 #define PCIE_BAR_CTRL_OFF(n)	(0x1804 + (((n) - 1) * 4))
 #define PCIE_WIN04_CTRL_OFF(n)	(0x1820 + ((n) << 4))
 #define PCIE_WIN04_BASE_OFF(n)	(0x1824 + ((n) << 4))
@@ -53,9 +55,10 @@
 	 PCIE_CONF_ADDR_EN)
 #define PCIE_CONF_DATA_OFF	0x18fc
 #define PCIE_INT_CAUSE_OFF	0x1900
+#define PCIE_INT_UNMASK_OFF	0x1910
+#define  PCIE_INT_INTX(i)		BIT(24+i)
 #define  PCIE_INT_PM_PME		BIT(28)
-#define PCIE_MASK_OFF		0x1910
-#define  PCIE_MASK_ENABLE_INTS          0x0f000000
+#define  PCIE_INT_ALL_MASK		GENMASK(31, 0)
 #define PCIE_CTRL_OFF		0x1a00
 #define  PCIE_CTRL_X1_MODE		0x0001
 #define  PCIE_CTRL_RC_MODE		BIT(1)
@@ -64,6 +67,12 @@
 #define  PCIE_STAT_BUS                  0xff00
 #define  PCIE_STAT_DEV                  0x1f0000
 #define  PCIE_STAT_LINK_DOWN		BIT(0)
+#define PCIE_SSPL_OFF		0x1a0c
+#define  PCIE_SSPL_VALUE_SHIFT		0
+#define  PCIE_SSPL_VALUE_MASK		GENMASK(7, 0)
+#define  PCIE_SSPL_SCALE_SHIFT		8
+#define  PCIE_SSPL_SCALE_MASK		GENMASK(9, 8)
+#define  PCIE_SSPL_ENABLE		BIT(16)
 #define PCIE_RC_RTSTA		0x1a14
 #define PCIE_DEBUG_CTRL         0x1a60
 #define  PCIE_DEBUG_SOFT_RESET		BIT(20)
@@ -93,6 +102,7 @@ struct mvebu_pcie_port {
 	void __iomem *base;
 	u32 port;
 	u32 lane;
+	bool is_x4;
 	int devfn;
 	unsigned int mem_target;
 	unsigned int mem_attr;
@@ -108,6 +118,11 @@ struct mvebu_pcie_port {
 	struct mvebu_pcie_window iowin;
 	u32 saved_pcie_stat;
 	struct resource regs;
+	u8 slot_power_limit_value;
+	u8 slot_power_limit_scale;
+	struct irq_domain *intx_irq_domain;
+	raw_spinlock_t irq_lock;
+	int intx_irq;
 };
 
 static inline void mvebu_writel(struct mvebu_pcie_port *port, u32 val, u32 reg)
@@ -233,13 +248,25 @@ static void mvebu_pcie_setup_wins(struct mvebu_pcie_port *port)
 
 static void mvebu_pcie_setup_hw(struct mvebu_pcie_port *port)
 {
-	u32 ctrl, cmd, dev_rev, mask;
+	u32 ctrl, lnkcap, cmd, dev_rev, unmask, sspl;
 
 	/* Setup PCIe controller to Root Complex mode. */
 	ctrl = mvebu_readl(port, PCIE_CTRL_OFF);
 	ctrl |= PCIE_CTRL_RC_MODE;
 	mvebu_writel(port, ctrl, PCIE_CTRL_OFF);
 
+	/*
+	 * Set Maximum Link Width to X1 or X4 in Root Port's PCIe Link
+	 * Capability register. This register is defined by PCIe specification
+	 * as read-only but this mvebu controller has it as read-write and must
+	 * be set to number of SerDes PCIe lanes (1 or 4). If this register is
+	 * not set correctly then link with endpoint card is not established.
+	 */
+	lnkcap = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCAP);
+	lnkcap &= ~PCI_EXP_LNKCAP_MLW;
+	lnkcap |= (port->is_x4 ? 4 : 1) << 4;
+	mvebu_writel(port, lnkcap, PCIE_CAP_PCIEXP + PCI_EXP_LNKCAP);
+
 	/* Disable Root Bridge I/O space, memory space and bus mastering. */
 	cmd = mvebu_readl(port, PCIE_CMD_OFF);
 	cmd &= ~(PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER);
@@ -268,23 +295,71 @@ static void mvebu_pcie_setup_hw(struct mvebu_pcie_port *port)
 	 */
 	dev_rev = mvebu_readl(port, PCIE_DEV_REV_OFF);
 	dev_rev &= ~0xffffff00;
-	dev_rev |= (PCI_CLASS_BRIDGE_PCI << 8) << 8;
+	dev_rev |= PCI_CLASS_BRIDGE_PCI_NORMAL << 8;
 	mvebu_writel(port, dev_rev, PCIE_DEV_REV_OFF);
 
 	/* Point PCIe unit MBUS decode windows to DRAM space. */
 	mvebu_pcie_setup_wins(port);
 
-	/* Enable interrupt lines A-D. */
-	mask = mvebu_readl(port, PCIE_MASK_OFF);
-	mask |= PCIE_MASK_ENABLE_INTS;
-	mvebu_writel(port, mask, PCIE_MASK_OFF);
+	/*
+	 * Program Root Port to automatically send Set_Slot_Power_Limit
+	 * PCIe Message when changing status from Dl_Down to Dl_Up and valid
+	 * slot power limit was specified.
+	 */
+	sspl = mvebu_readl(port, PCIE_SSPL_OFF);
+	sspl &= ~(PCIE_SSPL_VALUE_MASK | PCIE_SSPL_SCALE_MASK | PCIE_SSPL_ENABLE);
+	if (port->slot_power_limit_value) {
+		sspl |= port->slot_power_limit_value << PCIE_SSPL_VALUE_SHIFT;
+		sspl |= port->slot_power_limit_scale << PCIE_SSPL_SCALE_SHIFT;
+		sspl |= PCIE_SSPL_ENABLE;
+	}
+	mvebu_writel(port, sspl, PCIE_SSPL_OFF);
+
+	/* Mask all interrupt sources. */
+	mvebu_writel(port, ~PCIE_INT_ALL_MASK, PCIE_INT_UNMASK_OFF);
+
+	/* Clear all interrupt causes. */
+	mvebu_writel(port, ~PCIE_INT_ALL_MASK, PCIE_INT_CAUSE_OFF);
+
+	/* Check if "intx" interrupt was specified in DT. */
+	if (port->intx_irq > 0)
+		return;
+
+	/*
+	 * Fallback code when "intx" interrupt was not specified in DT:
+	 * Unmask all legacy INTx interrupts as driver does not provide a way
+	 * for masking and unmasking of individual legacy INTx interrupts.
+	 * Legacy INTx are reported via one shared GIC source and therefore
+	 * kernel cannot distinguish which individual legacy INTx was triggered.
+	 * These interrupts are shared, so it should not cause any issue. Just
+	 * performance penalty as every PCIe interrupt handler needs to be
+	 * called when some interrupt is triggered.
+	 */
+	unmask = mvebu_readl(port, PCIE_INT_UNMASK_OFF);
+	unmask |= PCIE_INT_INTX(0) | PCIE_INT_INTX(1) |
+		  PCIE_INT_INTX(2) | PCIE_INT_INTX(3);
+	mvebu_writel(port, unmask, PCIE_INT_UNMASK_OFF);
 }
 
-static int mvebu_pcie_hw_rd_conf(struct mvebu_pcie_port *port,
-				 struct pci_bus *bus,
-				 u32 devfn, int where, int size, u32 *val)
+static struct mvebu_pcie_port *mvebu_pcie_find_port(struct mvebu_pcie *pcie,
+						    struct pci_bus *bus,
+						    int devfn);
+
+static int mvebu_pcie_child_rd_conf(struct pci_bus *bus, u32 devfn, int where,
+				    int size, u32 *val)
 {
-	void __iomem *conf_data = port->base + PCIE_CONF_DATA_OFF;
+	struct mvebu_pcie *pcie = bus->sysdata;
+	struct mvebu_pcie_port *port;
+	void __iomem *conf_data;
+
+	port = mvebu_pcie_find_port(pcie, bus, devfn);
+	if (!port)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	if (!mvebu_pcie_link_up(port))
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	conf_data = port->base + PCIE_CONF_DATA_OFF;
 
 	mvebu_writel(port, PCIE_CONF_ADDR(bus->number, devfn, where),
 		     PCIE_CONF_ADDR_OFF);
@@ -300,18 +375,27 @@ static int mvebu_pcie_hw_rd_conf(struct mvebu_pcie_port *port,
 		*val = readl_relaxed(conf_data);
 		break;
 	default:
-		*val = 0xffffffff;
 		return PCIBIOS_BAD_REGISTER_NUMBER;
 	}
 
 	return PCIBIOS_SUCCESSFUL;
 }
 
-static int mvebu_pcie_hw_wr_conf(struct mvebu_pcie_port *port,
-				 struct pci_bus *bus,
-				 u32 devfn, int where, int size, u32 val)
+static int mvebu_pcie_child_wr_conf(struct pci_bus *bus, u32 devfn,
+				    int where, int size, u32 val)
 {
-	void __iomem *conf_data = port->base + PCIE_CONF_DATA_OFF;
+	struct mvebu_pcie *pcie = bus->sysdata;
+	struct mvebu_pcie_port *port;
+	void __iomem *conf_data;
+
+	port = mvebu_pcie_find_port(pcie, bus, devfn);
+	if (!port)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	if (!mvebu_pcie_link_up(port))
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	conf_data = port->base + PCIE_CONF_DATA_OFF;
 
 	mvebu_writel(port, PCIE_CONF_ADDR(bus->number, devfn, where),
 		     PCIE_CONF_ADDR_OFF);
@@ -333,6 +417,11 @@ static int mvebu_pcie_hw_wr_conf(struct mvebu_pcie_port *port,
 	return PCIBIOS_SUCCESSFUL;
 }
 
+static struct pci_ops mvebu_pcie_child_ops = {
+	.read = mvebu_pcie_child_rd_conf,
+	.write = mvebu_pcie_child_wr_conf,
+};
+
 /*
  * Remove windows, starting from the largest ones to the smallest
  * ones.
@@ -438,12 +527,6 @@ static int mvebu_pcie_handle_iobase_change(struct mvebu_pcie_port *port)
 		return mvebu_pcie_set_window(port, port->io_target, port->io_attr,
 					     &desired, &port->iowin);
 
-	if (!mvebu_has_ioport(port)) {
-		dev_WARN(&port->pcie->pdev->dev,
-			 "Attempt to set IO when IO is disabled\n");
-		return -EOPNOTSUPP;
-	}
-
 	/*
 	 * We read the PCI-to-PCI bridge emulated registers, and
 	 * calculate the base address and size of the address decoding
@@ -552,20 +635,40 @@ mvebu_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge,
 
 	case PCI_EXP_LNKCAP:
 		/*
-		 * PCIe requires the clock power management capability to be
-		 * hard-wired to zero for downstream ports
+		 * PCIe requires that the Clock Power Management capability bit
+		 * is hard-wired to zero for downstream ports but HW returns 1.
+		 * Additionally enable Data Link Layer Link Active Reporting
+		 * Capable bit as DL_Active indication is provided too.
 		 */
-		*value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCAP) &
-			 ~PCI_EXP_LNKCAP_CLKPM;
+		*value = (mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCAP) &
+			  ~PCI_EXP_LNKCAP_CLKPM) | PCI_EXP_LNKCAP_DLLLARC;
 		break;
 
 	case PCI_EXP_LNKCTL:
-		*value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCTL);
+		/* DL_Active indication is provided via PCIE_STAT_OFF */
+		*value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCTL) |
+			 (mvebu_pcie_link_up(port) ?
+			  (PCI_EXP_LNKSTA_DLLLA << 16) : 0);
 		break;
 
-	case PCI_EXP_SLTCTL:
-		*value = PCI_EXP_SLTSTA_PDS << 16;
+	case PCI_EXP_SLTCTL: {
+		u16 slotctl = le16_to_cpu(bridge->pcie_conf.slotctl);
+		u16 slotsta = le16_to_cpu(bridge->pcie_conf.slotsta);
+		u32 val = 0;
+		/*
+		 * When slot power limit was not specified in DT then
+		 * ASPL_DISABLE bit is stored only in emulated config space.
+		 * Otherwise reflect status of PCIE_SSPL_ENABLE bit in HW.
+		 */
+		if (!port->slot_power_limit_value)
+			val |= slotctl & PCI_EXP_SLTCTL_ASPL_DISABLE;
+		else if (!(mvebu_readl(port, PCIE_SSPL_OFF) & PCIE_SSPL_ENABLE))
+			val |= PCI_EXP_SLTCTL_ASPL_DISABLE;
+		/* This callback is 32-bit and in high bits is slot status. */
+		val |= slotsta << 16;
+		*value = val;
 		break;
+	}
 
 	case PCI_EXP_RTSTA:
 		*value = mvebu_readl(port, PCIE_RC_RTSTA);
@@ -590,6 +693,37 @@ mvebu_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge,
 	return PCI_BRIDGE_EMUL_HANDLED;
 }
 
+static pci_bridge_emul_read_status_t
+mvebu_pci_bridge_emul_ext_conf_read(struct pci_bridge_emul *bridge,
+				    int reg, u32 *value)
+{
+	struct mvebu_pcie_port *port = bridge->data;
+
+	switch (reg) {
+	case 0:
+	case PCI_ERR_UNCOR_STATUS:
+	case PCI_ERR_UNCOR_MASK:
+	case PCI_ERR_UNCOR_SEVER:
+	case PCI_ERR_COR_STATUS:
+	case PCI_ERR_COR_MASK:
+	case PCI_ERR_CAP:
+	case PCI_ERR_HEADER_LOG+0:
+	case PCI_ERR_HEADER_LOG+4:
+	case PCI_ERR_HEADER_LOG+8:
+	case PCI_ERR_HEADER_LOG+12:
+	case PCI_ERR_ROOT_COMMAND:
+	case PCI_ERR_ROOT_STATUS:
+	case PCI_ERR_ROOT_ERR_SRC:
+		*value = mvebu_readl(port, PCIE_CAP_PCIERR_OFF + reg);
+		break;
+
+	default:
+		return PCI_BRIDGE_EMUL_NOT_HANDLED;
+	}
+
+	return PCI_BRIDGE_EMUL_HANDLED;
+}
+
 static void
 mvebu_pci_bridge_emul_base_conf_write(struct pci_bridge_emul *bridge,
 				      int reg, u32 old, u32 new, u32 mask)
@@ -599,24 +733,18 @@ mvebu_pci_bridge_emul_base_conf_write(struct pci_bridge_emul *bridge,
 
 	switch (reg) {
 	case PCI_COMMAND:
-		if (!mvebu_has_ioport(port)) {
-			conf->command = cpu_to_le16(
-				le16_to_cpu(conf->command) & ~PCI_COMMAND_IO);
-			new &= ~PCI_COMMAND_IO;
-		}
-
 		mvebu_writel(port, new, PCIE_CMD_OFF);
 		break;
 
 	case PCI_IO_BASE:
-		if ((mask & 0xffff) && mvebu_pcie_handle_iobase_change(port)) {
+		if ((mask & 0xffff) && mvebu_has_ioport(port) &&
+		    mvebu_pcie_handle_iobase_change(port)) {
 			/* On error disable IO range */
 			conf->iobase &= ~0xf0;
 			conf->iolimit &= ~0xf0;
+			conf->iobase |= 0xf0;
 			conf->iobaseupper = cpu_to_le16(0x0000);
 			conf->iolimitupper = cpu_to_le16(0x0000);
-			if (mvebu_has_ioport(port))
-				conf->iobase |= 0xf0;
 		}
 		break;
 
@@ -630,14 +758,14 @@ mvebu_pci_bridge_emul_base_conf_write(struct pci_bridge_emul *bridge,
 		break;
 
 	case PCI_IO_BASE_UPPER16:
-		if (mvebu_pcie_handle_iobase_change(port)) {
+		if (mvebu_has_ioport(port) &&
+		    mvebu_pcie_handle_iobase_change(port)) {
 			/* On error disable IO range */
 			conf->iobase &= ~0xf0;
 			conf->iolimit &= ~0xf0;
+			conf->iobase |= 0xf0;
 			conf->iobaseupper = cpu_to_le16(0x0000);
 			conf->iolimitupper = cpu_to_le16(0x0000);
-			if (mvebu_has_ioport(port))
-				conf->iobase |= 0xf0;
 		}
 		break;
 
@@ -675,16 +803,31 @@ mvebu_pci_bridge_emul_pcie_conf_write(struct pci_bridge_emul *bridge,
 
 	case PCI_EXP_LNKCTL:
 		/*
-		 * If we don't support CLKREQ, we must ensure that the
-		 * CLKREQ enable bit always reads zero.  Since we haven't
-		 * had this capability, and it's dependent on board wiring,
-		 * disable it for the time being.
+		 * PCIe requires that the Enable Clock Power Management bit
+		 * is hard-wired to zero for downstream ports but HW allows
+		 * to change it.
 		 */
 		new &= ~PCI_EXP_LNKCTL_CLKREQ_EN;
 
 		mvebu_writel(port, new, PCIE_CAP_PCIEXP + PCI_EXP_LNKCTL);
 		break;
 
+	case PCI_EXP_SLTCTL:
+		/*
+		 * Allow to change PCIE_SSPL_ENABLE bit only when slot power
+		 * limit was specified in DT and configured into HW.
+		 */
+		if ((mask & PCI_EXP_SLTCTL_ASPL_DISABLE) &&
+		    port->slot_power_limit_value) {
+			u32 sspl = mvebu_readl(port, PCIE_SSPL_OFF);
+			if (new & PCI_EXP_SLTCTL_ASPL_DISABLE)
+				sspl &= ~PCIE_SSPL_ENABLE;
+			else
+				sspl |= PCIE_SSPL_ENABLE;
+			mvebu_writel(port, sspl, PCIE_SSPL_OFF);
+		}
+		break;
+
 	case PCI_EXP_RTSTA:
 		/*
 		 * PME Status bit in Root Status Register (PCIE_RC_RTSTA)
@@ -709,11 +852,45 @@ mvebu_pci_bridge_emul_pcie_conf_write(struct pci_bridge_emul *bridge,
 	}
 }
 
-static struct pci_bridge_emul_ops mvebu_pci_bridge_emul_ops = {
+static void
+mvebu_pci_bridge_emul_ext_conf_write(struct pci_bridge_emul *bridge,
+				     int reg, u32 old, u32 new, u32 mask)
+{
+	struct mvebu_pcie_port *port = bridge->data;
+
+	switch (reg) {
+	/* These are W1C registers, so clear other bits */
+	case PCI_ERR_UNCOR_STATUS:
+	case PCI_ERR_COR_STATUS:
+	case PCI_ERR_ROOT_STATUS:
+		new &= mask;
+		fallthrough;
+
+	case PCI_ERR_UNCOR_MASK:
+	case PCI_ERR_UNCOR_SEVER:
+	case PCI_ERR_COR_MASK:
+	case PCI_ERR_CAP:
+	case PCI_ERR_HEADER_LOG+0:
+	case PCI_ERR_HEADER_LOG+4:
+	case PCI_ERR_HEADER_LOG+8:
+	case PCI_ERR_HEADER_LOG+12:
+	case PCI_ERR_ROOT_COMMAND:
+	case PCI_ERR_ROOT_ERR_SRC:
+		mvebu_writel(port, new, PCIE_CAP_PCIERR_OFF + reg);
+		break;
+
+	default:
+		break;
+	}
+}
+
+static const struct pci_bridge_emul_ops mvebu_pci_bridge_emul_ops = {
 	.read_base = mvebu_pci_bridge_emul_base_conf_read,
 	.write_base = mvebu_pci_bridge_emul_base_conf_write,
 	.read_pcie = mvebu_pci_bridge_emul_pcie_conf_read,
 	.write_pcie = mvebu_pci_bridge_emul_pcie_conf_write,
+	.read_ext = mvebu_pci_bridge_emul_ext_conf_read,
+	.write_ext = mvebu_pci_bridge_emul_ext_conf_write,
 };
 
 /*
@@ -722,32 +899,57 @@ static struct pci_bridge_emul_ops mvebu_pci_bridge_emul_ops = {
  */
 static int mvebu_pci_bridge_emul_init(struct mvebu_pcie_port *port)
 {
+	unsigned int bridge_flags = PCI_BRIDGE_EMUL_NO_PREFMEM_FORWARD;
 	struct pci_bridge_emul *bridge = &port->bridge;
+	u32 dev_id = mvebu_readl(port, PCIE_DEV_ID_OFF);
+	u32 dev_rev = mvebu_readl(port, PCIE_DEV_REV_OFF);
+	u32 ssdev_id = mvebu_readl(port, PCIE_SSDEV_ID_OFF);
 	u32 pcie_cap = mvebu_readl(port, PCIE_CAP_PCIEXP);
 	u8 pcie_cap_ver = ((pcie_cap >> 16) & PCI_EXP_FLAGS_VERS);
 
-	bridge->conf.vendor = PCI_VENDOR_ID_MARVELL;
-	bridge->conf.device = mvebu_readl(port, PCIE_DEV_ID_OFF) >> 16;
-	bridge->conf.class_revision =
-		mvebu_readl(port, PCIE_DEV_REV_OFF) & 0xff;
+	bridge->conf.vendor = cpu_to_le16(dev_id & 0xffff);
+	bridge->conf.device = cpu_to_le16(dev_id >> 16);
+	bridge->conf.class_revision = cpu_to_le32(dev_rev & 0xff);
 
 	if (mvebu_has_ioport(port)) {
 		/* We support 32 bits I/O addressing */
 		bridge->conf.iobase = PCI_IO_RANGE_TYPE_32;
 		bridge->conf.iolimit = PCI_IO_RANGE_TYPE_32;
+	} else {
+		bridge_flags |= PCI_BRIDGE_EMUL_NO_IO_FORWARD;
 	}
 
 	/*
 	 * Older mvebu hardware provides PCIe Capability structure only in
 	 * version 1. New hardware provides it in version 2.
+	 * Enable slot support which is emulated.
 	 */
-	bridge->pcie_conf.cap = cpu_to_le16(pcie_cap_ver);
+	bridge->pcie_conf.cap = cpu_to_le16(pcie_cap_ver | PCI_EXP_FLAGS_SLOT);
 
+	/*
+	 * Set Presence Detect State bit permanently as there is no support for
+	 * unplugging PCIe card from the slot. Assume that PCIe card is always
+	 * connected in slot.
+	 *
+	 * Set physical slot number to port+1 as mvebu ports are indexed from
+	 * zero and zero value is reserved for ports within the same silicon
+	 * as Root Port which is not mvebu case.
+	 *
+	 * Also set correct slot power limit.
+	 */
+	bridge->pcie_conf.slotcap = cpu_to_le32(
+		FIELD_PREP(PCI_EXP_SLTCAP_SPLV, port->slot_power_limit_value) |
+		FIELD_PREP(PCI_EXP_SLTCAP_SPLS, port->slot_power_limit_scale) |
+		FIELD_PREP(PCI_EXP_SLTCAP_PSN, port->port+1));
+	bridge->pcie_conf.slotsta = cpu_to_le16(PCI_EXP_SLTSTA_PDS);
+
+	bridge->subsystem_vendor_id = ssdev_id & 0xffff;
+	bridge->subsystem_id = ssdev_id >> 16;
 	bridge->has_pcie = true;
 	bridge->data = port;
 	bridge->ops = &mvebu_pci_bridge_emul_ops;
 
-	return pci_bridge_emul_init(bridge, PCI_BRIDGE_EMUL_NO_PREFETCHABLE_BAR);
+	return pci_bridge_emul_init(bridge, bridge_flags);
 }
 
 static inline struct mvebu_pcie *sys_to_pcie(struct pci_sys_data *sys)
@@ -784,25 +986,12 @@ static int mvebu_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 {
 	struct mvebu_pcie *pcie = bus->sysdata;
 	struct mvebu_pcie_port *port;
-	int ret;
 
 	port = mvebu_pcie_find_port(pcie, bus, devfn);
 	if (!port)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
-	/* Access the emulated PCI-to-PCI bridge */
-	if (bus->number == 0)
-		return pci_bridge_emul_conf_write(&port->bridge, where,
-						  size, val);
-
-	if (!mvebu_pcie_link_up(port))
-		return PCIBIOS_DEVICE_NOT_FOUND;
-
-	/* Access the real PCIe interface */
-	ret = mvebu_pcie_hw_wr_conf(port, bus, devfn,
-				    where, size, val);
-
-	return ret;
+	return pci_bridge_emul_conf_write(&port->bridge, where, size, val);
 }
 
 /* PCI configuration space read function */
@@ -811,25 +1000,12 @@ static int mvebu_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where,
 {
 	struct mvebu_pcie *pcie = bus->sysdata;
 	struct mvebu_pcie_port *port;
-	int ret;
 
 	port = mvebu_pcie_find_port(pcie, bus, devfn);
 	if (!port)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
-	/* Access the emulated PCI-to-PCI bridge */
-	if (bus->number == 0)
-		return pci_bridge_emul_conf_read(&port->bridge, where,
-						 size, val);
-
-	if (!mvebu_pcie_link_up(port))
-		return PCIBIOS_DEVICE_NOT_FOUND;
-
-	/* Access the real PCIe interface */
-	ret = mvebu_pcie_hw_rd_conf(port, bus, devfn,
-				    where, size, val);
-
-	return ret;
+	return pci_bridge_emul_conf_read(&port->bridge, where, size, val);
 }
 
 static struct pci_ops mvebu_pcie_ops = {
@@ -837,6 +1013,108 @@ static struct pci_ops mvebu_pcie_ops = {
 	.write = mvebu_pcie_wr_conf,
 };
 
+static void mvebu_pcie_intx_irq_mask(struct irq_data *d)
+{
+	struct mvebu_pcie_port *port = d->domain->host_data;
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
+	unsigned long flags;
+	u32 unmask;
+
+	raw_spin_lock_irqsave(&port->irq_lock, flags);
+	unmask = mvebu_readl(port, PCIE_INT_UNMASK_OFF);
+	unmask &= ~PCIE_INT_INTX(hwirq);
+	mvebu_writel(port, unmask, PCIE_INT_UNMASK_OFF);
+	raw_spin_unlock_irqrestore(&port->irq_lock, flags);
+}
+
+static void mvebu_pcie_intx_irq_unmask(struct irq_data *d)
+{
+	struct mvebu_pcie_port *port = d->domain->host_data;
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
+	unsigned long flags;
+	u32 unmask;
+
+	raw_spin_lock_irqsave(&port->irq_lock, flags);
+	unmask = mvebu_readl(port, PCIE_INT_UNMASK_OFF);
+	unmask |= PCIE_INT_INTX(hwirq);
+	mvebu_writel(port, unmask, PCIE_INT_UNMASK_OFF);
+	raw_spin_unlock_irqrestore(&port->irq_lock, flags);
+}
+
+static struct irq_chip intx_irq_chip = {
+	.name = "mvebu-INTx",
+	.irq_mask = mvebu_pcie_intx_irq_mask,
+	.irq_unmask = mvebu_pcie_intx_irq_unmask,
+};
+
+static int mvebu_pcie_intx_irq_map(struct irq_domain *h,
+				   unsigned int virq, irq_hw_number_t hwirq)
+{
+	struct mvebu_pcie_port *port = h->host_data;
+
+	irq_set_status_flags(virq, IRQ_LEVEL);
+	irq_set_chip_and_handler(virq, &intx_irq_chip, handle_level_irq);
+	irq_set_chip_data(virq, port);
+
+	return 0;
+}
+
+static const struct irq_domain_ops mvebu_pcie_intx_irq_domain_ops = {
+	.map = mvebu_pcie_intx_irq_map,
+	.xlate = irq_domain_xlate_onecell,
+};
+
+static int mvebu_pcie_init_irq_domain(struct mvebu_pcie_port *port)
+{
+	struct device *dev = &port->pcie->pdev->dev;
+	struct device_node *pcie_intc_node;
+
+	raw_spin_lock_init(&port->irq_lock);
+
+	pcie_intc_node = of_get_next_child(port->dn, NULL);
+	if (!pcie_intc_node) {
+		dev_err(dev, "No PCIe Intc node found for %s\n", port->name);
+		return -ENODEV;
+	}
+
+	port->intx_irq_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX,
+						      &mvebu_pcie_intx_irq_domain_ops,
+						      port);
+	of_node_put(pcie_intc_node);
+	if (!port->intx_irq_domain) {
+		dev_err(dev, "Failed to get INTx IRQ domain for %s\n", port->name);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void mvebu_pcie_irq_handler(struct irq_desc *desc)
+{
+	struct mvebu_pcie_port *port = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct device *dev = &port->pcie->pdev->dev;
+	u32 cause, unmask, status;
+	int i;
+
+	chained_irq_enter(chip, desc);
+
+	cause = mvebu_readl(port, PCIE_INT_CAUSE_OFF);
+	unmask = mvebu_readl(port, PCIE_INT_UNMASK_OFF);
+	status = cause & unmask;
+
+	/* Process legacy INTx interrupts */
+	for (i = 0; i < PCI_NUM_INTX; i++) {
+		if (!(status & PCIE_INT_INTX(i)))
+			continue;
+
+		if (generic_handle_domain_irq(port->intx_irq_domain, i) == -EINVAL)
+			dev_err_ratelimited(dev, "unexpected INT%c IRQ\n", (char)i+'A');
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
 static int mvebu_pcie_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	/* Interrupt support on mvebu emulated bridges is not implemented yet */
@@ -985,7 +1263,9 @@ static int mvebu_pcie_parse_port(struct mvebu_pcie *pcie,
 {
 	struct device *dev = &pcie->pdev->dev;
 	enum of_gpio_flags flags;
+	u32 slot_power_limit;
 	int reset_gpio, ret;
+	u32 num_lanes;
 
 	port->pcie = pcie;
 
@@ -998,6 +1278,9 @@ static int mvebu_pcie_parse_port(struct mvebu_pcie *pcie,
 	if (of_property_read_u32(child, "marvell,pcie-lane", &port->lane))
 		port->lane = 0;
 
+	if (!of_property_read_u32(child, "num-lanes", &num_lanes) && num_lanes == 4)
+		port->is_x4 = true;
+
 	port->name = devm_kasprintf(dev, GFP_KERNEL, "pcie%d.%d", port->port,
 				    port->lane);
 	if (!port->name) {
@@ -1030,6 +1313,21 @@ static int mvebu_pcie_parse_port(struct mvebu_pcie *pcie,
 		port->io_attr = -1;
 	}
 
+	/*
+	 * Old DT bindings do not contain "intx" interrupt
+	 * so do not fail probing driver when interrupt does not exist.
+	 */
+	port->intx_irq = of_irq_get_byname(child, "intx");
+	if (port->intx_irq == -EPROBE_DEFER) {
+		ret = port->intx_irq;
+		goto err;
+	}
+	if (port->intx_irq <= 0) {
+		dev_warn(dev, "%s: legacy INTx interrupts cannot be masked individually, "
+			      "%pOF does not contain intx interrupt\n",
+			 port->name, child);
+	}
+
 	reset_gpio = of_get_named_gpio_flags(child, "reset-gpios", 0, &flags);
 	if (reset_gpio == -EPROBE_DEFER) {
 		ret = reset_gpio;
@@ -1066,6 +1364,15 @@ static int mvebu_pcie_parse_port(struct mvebu_pcie *pcie,
 		port->reset_gpio = gpio_to_desc(reset_gpio);
 	}
 
+	slot_power_limit = of_pci_get_slot_power_limit(child,
+				&port->slot_power_limit_value,
+				&port->slot_power_limit_scale);
+	if (slot_power_limit)
+		dev_info(dev, "%s: Slot power limit %u.%uW\n",
+			 port->name,
+			 slot_power_limit / 1000,
+			 (slot_power_limit / 100) % 10);
+
 	port->clk = of_clk_get_by_name(child, NULL);
 	if (IS_ERR(port->clk)) {
 		dev_err(dev, "%s: cannot get clock\n", port->name);
@@ -1226,6 +1533,7 @@ static int mvebu_pcie_probe(struct platform_device *pdev)
 
 	for (i = 0; i < pcie->nports; i++) {
 		struct mvebu_pcie_port *port = &pcie->ports[i];
+		int irq = port->intx_irq;
 
 		child = port->dn;
 		if (!child)
@@ -1253,6 +1561,22 @@ static int mvebu_pcie_probe(struct platform_device *pdev)
 			continue;
 		}
 
+		if (irq > 0) {
+			ret = mvebu_pcie_init_irq_domain(port);
+			if (ret) {
+				dev_err(dev, "%s: cannot init irq domain\n",
+					port->name);
+				pci_bridge_emul_cleanup(&port->bridge);
+				devm_iounmap(dev, port->base);
+				port->base = NULL;
+				mvebu_pcie_powerdown(port);
+				continue;
+			}
+			irq_set_chained_handler_and_data(irq,
+							 mvebu_pcie_irq_handler,
+							 port);
+		}
+
 		/*
 		 * PCIe topology exported by mvebu hw is quite complicated. In
 		 * reality has something like N fully independent host bridges
@@ -1333,10 +1657,9 @@ static int mvebu_pcie_probe(struct platform_device *pdev)
 		mvebu_pcie_set_local_bus_nr(port, 0);
 	}
 
-	pcie->nports = i;
-
 	bridge->sysdata = pcie;
 	bridge->ops = &mvebu_pcie_ops;
+	bridge->child_ops = &mvebu_pcie_child_ops;
 	bridge->align_resource = mvebu_pcie_align_resource;
 	bridge->map_irq = mvebu_pcie_map_irq;
 
@@ -1347,7 +1670,7 @@ static int mvebu_pcie_remove(struct platform_device *pdev)
 {
 	struct mvebu_pcie *pcie = platform_get_drvdata(pdev);
 	struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie);
-	u32 cmd;
+	u32 cmd, sspl;
 	int i;
 
 	/* Remove PCI bus with all devices. */
@@ -1358,6 +1681,7 @@ static int mvebu_pcie_remove(struct platform_device *pdev)
 
 	for (i = 0; i < pcie->nports; i++) {
 		struct mvebu_pcie_port *port = &pcie->ports[i];
+		int irq = port->intx_irq;
 
 		if (!port->base)
 			continue;
@@ -1368,11 +1692,26 @@ static int mvebu_pcie_remove(struct platform_device *pdev)
 		mvebu_writel(port, cmd, PCIE_CMD_OFF);
 
 		/* Mask all interrupt sources. */
-		mvebu_writel(port, 0, PCIE_MASK_OFF);
+		mvebu_writel(port, ~PCIE_INT_ALL_MASK, PCIE_INT_UNMASK_OFF);
+
+		/* Clear all interrupt causes. */
+		mvebu_writel(port, ~PCIE_INT_ALL_MASK, PCIE_INT_CAUSE_OFF);
+
+		if (irq > 0)
+			irq_set_chained_handler_and_data(irq, NULL, NULL);
+
+		/* Remove IRQ domains. */
+		if (port->intx_irq_domain)
+			irq_domain_remove(port->intx_irq_domain);
 
 		/* Free config space for emulated root bridge. */
 		pci_bridge_emul_cleanup(&port->bridge);
 
+		/* Disable sending Set_Slot_Power_Limit PCIe Message. */
+		sspl = mvebu_readl(port, PCIE_SSPL_OFF);
+		sspl &= ~(PCIE_SSPL_VALUE_MASK | PCIE_SSPL_SCALE_MASK | PCIE_SSPL_ENABLE);
+		mvebu_writel(port, sspl, PCIE_SSPL_OFF);
+
 		/* Disable and clear BARs and windows. */
 		mvebu_pcie_disable_wins(port);
 
diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index cb0aa65d6934..0457ec02ab70 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -726,7 +726,7 @@ static void tegra_pcie_port_free(struct tegra_pcie_port *port)
 /* Tegra PCIE root complex wrongly reports device class */
 static void tegra_pcie_fixup_class(struct pci_dev *dev)
 {
-	dev->class = PCI_CLASS_BRIDGE_PCI << 8;
+	dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL;
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0bf0, tegra_pcie_fixup_class);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0bf1, tegra_pcie_fixup_class);
diff --git a/drivers/pci/controller/pci-versatile.c b/drivers/pci/controller/pci-versatile.c
index 653d5d0ecf81..7991d334e0f1 100644
--- a/drivers/pci/controller/pci-versatile.c
+++ b/drivers/pci/controller/pci-versatile.c
@@ -31,10 +31,9 @@ static u32 pci_slot_ignore;
 
 static int __init versatile_pci_slot_ignore(char *str)
 {
-	int retval;
 	int slot;
 
-	while ((retval = get_option(&str, &slot))) {
+	while (get_option(&str, &slot)) {
 		if ((slot < 0) || (slot > 31))
 			pr_err("Illegal slot value: %d\n", slot);
 		else
diff --git a/drivers/pci/controller/pci-xgene.c b/drivers/pci/controller/pci-xgene.c
index 0d5acbfc7143..eb6240958bb0 100644
--- a/drivers/pci/controller/pci-xgene.c
+++ b/drivers/pci/controller/pci-xgene.c
@@ -49,7 +49,6 @@
 #define EN_REG				0x00000001
 #define OB_LO_IO			0x00000002
 #define XGENE_PCIE_DEVICEID		0xE004
-#define SZ_1T				(SZ_1G*1024ULL)
 #define PIPE_PHY_RATE_RD(src)		((0xc000 & (u32)(src)) >> 0xe)
 
 #define XGENE_V1_PCI_EXP_CAP		0x40
@@ -465,7 +464,7 @@ static int xgene_pcie_select_ib_reg(u8 *ib_reg_mask, u64 size)
 		return 1;
 	}
 
-	if ((size > SZ_1K) && (size < SZ_4G) && !(*ib_reg_mask & (1 << 0))) {
+	if ((size > SZ_1K) && (size < SZ_1T) && !(*ib_reg_mask & (1 << 0))) {
 		*ib_reg_mask |= (1 << 0);
 		return 0;
 	}
@@ -479,28 +478,27 @@ static int xgene_pcie_select_ib_reg(u8 *ib_reg_mask, u64 size)
 }
 
 static void xgene_pcie_setup_ib_reg(struct xgene_pcie *port,
-				    struct resource_entry *entry,
-				    u8 *ib_reg_mask)
+				    struct of_pci_range *range, u8 *ib_reg_mask)
 {
 	void __iomem *cfg_base = port->cfg_base;
 	struct device *dev = port->dev;
 	void __iomem *bar_addr;
 	u32 pim_reg;
-	u64 cpu_addr = entry->res->start;
-	u64 pci_addr = cpu_addr - entry->offset;
-	u64 size = resource_size(entry->res);
+	u64 cpu_addr = range->cpu_addr;
+	u64 pci_addr = range->pci_addr;
+	u64 size = range->size;
 	u64 mask = ~(size - 1) | EN_REG;
 	u32 flags = PCI_BASE_ADDRESS_MEM_TYPE_64;
 	u32 bar_low;
 	int region;
 
-	region = xgene_pcie_select_ib_reg(ib_reg_mask, size);
+	region = xgene_pcie_select_ib_reg(ib_reg_mask, range->size);
 	if (region < 0) {
 		dev_warn(dev, "invalid pcie dma-range config\n");
 		return;
 	}
 
-	if (entry->res->flags & IORESOURCE_PREFETCH)
+	if (range->flags & IORESOURCE_PREFETCH)
 		flags |= PCI_BASE_ADDRESS_MEM_PREFETCH;
 
 	bar_low = pcie_bar_low_val((u32)cpu_addr, flags);
@@ -531,13 +529,25 @@ static void xgene_pcie_setup_ib_reg(struct xgene_pcie *port,
 
 static int xgene_pcie_parse_map_dma_ranges(struct xgene_pcie *port)
 {
-	struct pci_host_bridge *bridge = pci_host_bridge_from_priv(port);
-	struct resource_entry *entry;
+	struct device_node *np = port->node;
+	struct of_pci_range range;
+	struct of_pci_range_parser parser;
+	struct device *dev = port->dev;
 	u8 ib_reg_mask = 0;
 
-	resource_list_for_each_entry(entry, &bridge->dma_ranges)
-		xgene_pcie_setup_ib_reg(port, entry, &ib_reg_mask);
+	if (of_pci_dma_range_parser_init(&parser, np)) {
+		dev_err(dev, "missing dma-ranges property\n");
+		return -EINVAL;
+	}
+
+	/* Get the dma-ranges from DT */
+	for_each_of_pci_range(&parser, &range) {
+		u64 end = range.cpu_addr + range.size - 1;
 
+		dev_dbg(dev, "0x%08x 0x%016llx..0x%016llx -> 0x%016llx\n",
+			range.flags, range.cpu_addr, end, range.pci_addr);
+		xgene_pcie_setup_ib_reg(port, &range, &ib_reg_mask);
+	}
 	return 0;
 }
 
diff --git a/drivers/pci/controller/pcie-apple.c b/drivers/pci/controller/pcie-apple.c
index 854d95163112..a2c3c207a04b 100644
--- a/drivers/pci/controller/pcie-apple.c
+++ b/drivers/pci/controller/pcie-apple.c
@@ -219,7 +219,7 @@ static int apple_msi_domain_alloc(struct irq_domain *domain, unsigned int virq,
 	if (hwirq < 0)
 		return -ENOSPC;
 
-	fwspec.param[1] += hwirq;
+	fwspec.param[fwspec.param_count - 2] += hwirq;
 
 	ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, &fwspec);
 	if (ret)
diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c
index 375c0c40bbf8..e61058e13818 100644
--- a/drivers/pci/controller/pcie-brcmstb.c
+++ b/drivers/pci/controller/pcie-brcmstb.c
@@ -24,7 +24,6 @@
 #include <linux/pci.h>
 #include <linux/pci-ecam.h>
 #include <linux/printk.h>
-#include <linux/regulator/consumer.h>
 #include <linux/reset.h>
 #include <linux/sizes.h>
 #include <linux/slab.h>
@@ -196,8 +195,6 @@ static inline void brcm_pcie_bridge_sw_init_set_generic(struct brcm_pcie *pcie,
 static inline void brcm_pcie_perst_set_4908(struct brcm_pcie *pcie, u32 val);
 static inline void brcm_pcie_perst_set_7278(struct brcm_pcie *pcie, u32 val);
 static inline void brcm_pcie_perst_set_generic(struct brcm_pcie *pcie, u32 val);
-static int brcm_pcie_linkup(struct brcm_pcie *pcie);
-static int brcm_pcie_add_bus(struct pci_bus *bus);
 
 enum {
 	RGR1_SW_INIT_1,
@@ -286,14 +283,6 @@ static const struct pcie_cfg_data bcm2711_cfg = {
 	.bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic,
 };
 
-struct subdev_regulators {
-	unsigned int num_supplies;
-	struct regulator_bulk_data supplies[];
-};
-
-static int pci_subdev_regulators_add_bus(struct pci_bus *bus);
-static void pci_subdev_regulators_remove_bus(struct pci_bus *bus);
-
 struct brcm_msi {
 	struct device		*dev;
 	void __iomem		*base;
@@ -331,9 +320,6 @@ struct brcm_pcie {
 	u32			hw_rev;
 	void			(*perst_set)(struct brcm_pcie *pcie, u32 val);
 	void			(*bridge_sw_init_set)(struct brcm_pcie *pcie, u32 val);
-	bool			refusal_mode;
-	struct subdev_regulators *sr;
-	bool			ep_wakeup_capable;
 };
 
 static inline bool is_bmips(const struct brcm_pcie *pcie)
@@ -450,99 +436,6 @@ static int brcm_pcie_set_ssc(struct brcm_pcie *pcie)
 	return ssc && pll ? 0 : -EIO;
 }
 
-static void *alloc_subdev_regulators(struct device *dev)
-{
-	static const char * const supplies[] = {
-		"vpcie3v3",
-		"vpcie3v3aux",
-		"vpcie12v",
-	};
-	const size_t size = sizeof(struct subdev_regulators)
-		+ sizeof(struct regulator_bulk_data) * ARRAY_SIZE(supplies);
-	struct subdev_regulators *sr;
-	int i;
-
-	sr = devm_kzalloc(dev, size, GFP_KERNEL);
-	if (sr) {
-		sr->num_supplies = ARRAY_SIZE(supplies);
-		for (i = 0; i < ARRAY_SIZE(supplies); i++)
-			sr->supplies[i].supply = supplies[i];
-	}
-
-	return sr;
-}
-
-static int pci_subdev_regulators_add_bus(struct pci_bus *bus)
-{
-	struct device *dev = &bus->dev;
-	struct subdev_regulators *sr;
-	int ret;
-
-	if (!dev->of_node || !bus->parent || !pci_is_root_bus(bus->parent))
-		return 0;
-
-	if (dev->driver_data)
-		dev_err(dev, "dev.driver_data unexpectedly non-NULL\n");
-
-	sr = alloc_subdev_regulators(dev);
-	if (!sr)
-		return -ENOMEM;
-
-	dev->driver_data = sr;
-	ret = regulator_bulk_get(dev, sr->num_supplies, sr->supplies);
-	if (ret)
-		return ret;
-
-	ret = regulator_bulk_enable(sr->num_supplies, sr->supplies);
-	if (ret) {
-		dev_err(dev, "failed to enable regulators for downstream device\n");
-		return ret;
-	}
-
-	return 0;
-}
-
-static int brcm_pcie_add_bus(struct pci_bus *bus)
-{
-	struct device *dev = &bus->dev;
-	struct brcm_pcie *pcie = (struct brcm_pcie *) bus->sysdata;
-	int ret;
-
-	if (!dev->of_node || !bus->parent || !pci_is_root_bus(bus->parent))
-		return 0;
-
-	ret = pci_subdev_regulators_add_bus(bus);
-	if (ret)
-		return ret;
-
-	/* Grab the regulators for suspend/resume */
-	pcie->sr = bus->dev.driver_data;
-
-	/*
-	 * If we have failed linkup there is no point to return an error as
-	 * currently it will cause a WARNING() from pci_alloc_child_bus().
-	 * We return 0 and turn on the "refusal_mode" so that any further
-	 * accesses to the pci_dev just get 0xffffffff
-	 */
-	if (brcm_pcie_linkup(pcie) != 0)
-		pcie->refusal_mode = true;
-
-	return 0;
-}
-
-static void pci_subdev_regulators_remove_bus(struct pci_bus *bus)
-{
-	struct device *dev = &bus->dev;
-	struct subdev_regulators *sr = dev->driver_data;
-
-	if (!sr || !bus->parent || !pci_is_root_bus(bus->parent))
-		return;
-
-	if (regulator_bulk_disable(sr->num_supplies, sr->supplies))
-		dev_err(dev, "failed to disable regulators for downstream device\n");
-	dev->driver_data = NULL;
-}
-
 /* Limits operation to a specific generation (1, 2, or 3) */
 static void brcm_pcie_set_gen(struct brcm_pcie *pcie, int gen)
 {
@@ -858,18 +751,6 @@ static void __iomem *brcm_pcie_map_conf(struct pci_bus *bus, unsigned int devfn,
 	/* Accesses to the RC go right to the RC registers if slot==0 */
 	if (pci_is_root_bus(bus))
 		return PCI_SLOT(devfn) ? NULL : base + where;
-	if (pcie->refusal_mode) {
-		/*
-		 * At this point we do not have link.  There will be a CPU
-		 * abort -- a quirk with this controller --if Linux tries
-		 * to read any config-space registers besides those
-		 * targeting the host bridge.  To prevent this we hijack
-		 * the address to point to a safe access that will return
-		 * 0xffffffff.
-		 */
-		writel(0xffffffff, base + PCIE_MISC_RC_BAR2_CONFIG_HI);
-		return base + PCIE_MISC_RC_BAR2_CONFIG_HI + (where & 0x3);
-	}
 
 	/* For devices, write to the config space index register */
 	idx = PCIE_ECAM_OFFSET(bus->number, devfn, 0);
@@ -898,8 +779,6 @@ static struct pci_ops brcm_pcie_ops = {
 	.map_bus = brcm_pcie_map_conf,
 	.read = pci_generic_config_read,
 	.write = pci_generic_config_write,
-	.add_bus = brcm_pcie_add_bus,
-	.remove_bus = pci_subdev_regulators_remove_bus,
 };
 
 static struct pci_ops brcm_pcie_ops32 = {
@@ -1047,9 +926,16 @@ static inline int brcm_pcie_get_rc_bar2_size_and_offset(struct brcm_pcie *pcie,
 
 static int brcm_pcie_setup(struct brcm_pcie *pcie)
 {
+	struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie);
 	u64 rc_bar2_offset, rc_bar2_size;
 	void __iomem *base = pcie->base;
-	int ret, memc;
+	struct device *dev = pcie->dev;
+	struct resource_entry *entry;
+	bool ssc_good = false;
+	struct resource *res;
+	int num_out_wins = 0;
+	u16 nlw, cls, lnksta;
+	int i, ret, memc;
 	u32 tmp, burst, aspm_support;
 
 	/* Reset the bridge */
@@ -1139,40 +1025,6 @@ static int brcm_pcie_setup(struct brcm_pcie *pcie)
 	if (pcie->gen)
 		brcm_pcie_set_gen(pcie, pcie->gen);
 
-	/* Don't advertise L0s capability if 'aspm-no-l0s' */
-	aspm_support = PCIE_LINK_STATE_L1;
-	if (!of_property_read_bool(pcie->np, "aspm-no-l0s"))
-		aspm_support |= PCIE_LINK_STATE_L0S;
-	tmp = readl(base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY);
-	u32p_replace_bits(&tmp, aspm_support,
-		PCIE_RC_CFG_PRIV1_LINK_CAPABILITY_ASPM_SUPPORT_MASK);
-	writel(tmp, base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY);
-
-	/*
-	 * For config space accesses on the RC, show the right class for
-	 * a PCIe-PCIe bridge (the default setting is to be EP mode).
-	 */
-	tmp = readl(base + PCIE_RC_CFG_PRIV1_ID_VAL3);
-	u32p_replace_bits(&tmp, 0x060400,
-			  PCIE_RC_CFG_PRIV1_ID_VAL3_CLASS_CODE_MASK);
-	writel(tmp, base + PCIE_RC_CFG_PRIV1_ID_VAL3);
-
-	return 0;
-}
-
-static int brcm_pcie_linkup(struct brcm_pcie *pcie)
-{
-	struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie);
-	struct device *dev = pcie->dev;
-	void __iomem *base = pcie->base;
-	struct resource_entry *entry;
-	struct resource *res;
-	int num_out_wins = 0;
-	u16 nlw, cls, lnksta;
-	bool ssc_good = false;
-	u32 tmp;
-	int ret, i;
-
 	/* Unassert the fundamental reset */
 	pcie->perst_set(pcie, 0);
 
@@ -1223,6 +1075,24 @@ static int brcm_pcie_linkup(struct brcm_pcie *pcie)
 		num_out_wins++;
 	}
 
+	/* Don't advertise L0s capability if 'aspm-no-l0s' */
+	aspm_support = PCIE_LINK_STATE_L1;
+	if (!of_property_read_bool(pcie->np, "aspm-no-l0s"))
+		aspm_support |= PCIE_LINK_STATE_L0S;
+	tmp = readl(base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY);
+	u32p_replace_bits(&tmp, aspm_support,
+		PCIE_RC_CFG_PRIV1_LINK_CAPABILITY_ASPM_SUPPORT_MASK);
+	writel(tmp, base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY);
+
+	/*
+	 * For config space accesses on the RC, show the right class for
+	 * a PCIe-PCIe bridge (the default setting is to be EP mode).
+	 */
+	tmp = readl(base + PCIE_RC_CFG_PRIV1_ID_VAL3);
+	u32p_replace_bits(&tmp, 0x060400,
+			  PCIE_RC_CFG_PRIV1_ID_VAL3_CLASS_CODE_MASK);
+	writel(tmp, base + PCIE_RC_CFG_PRIV1_ID_VAL3);
+
 	if (pcie->ssc) {
 		ret = brcm_pcie_set_ssc(pcie);
 		if (ret == 0)
@@ -1351,21 +1221,9 @@ static void brcm_pcie_turn_off(struct brcm_pcie *pcie)
 	pcie->bridge_sw_init_set(pcie, 1);
 }
 
-static int pci_dev_may_wakeup(struct pci_dev *dev, void *data)
-{
-	bool *ret = data;
-
-	if (device_may_wakeup(&dev->dev)) {
-		*ret = true;
-		dev_info(&dev->dev, "disable cancelled for wake-up device\n");
-	}
-	return (int) *ret;
-}
-
 static int brcm_pcie_suspend(struct device *dev)
 {
 	struct brcm_pcie *pcie = dev_get_drvdata(dev);
-	struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie);
 	int ret;
 
 	brcm_pcie_turn_off(pcie);
@@ -1383,25 +1241,6 @@ static int brcm_pcie_suspend(struct device *dev)
 		return ret;
 	}
 
-	if (pcie->sr) {
-		/*
-		 * Now turn off the regulators, but if at least one
-		 * downstream device is enabled as a wake-up source, do not
-		 * turn off regulators.
-		 */
-		pcie->ep_wakeup_capable = false;
-		pci_walk_bus(bridge->bus, pci_dev_may_wakeup,
-			     &pcie->ep_wakeup_capable);
-		if (!pcie->ep_wakeup_capable) {
-			ret = regulator_bulk_disable(pcie->sr->num_supplies,
-						     pcie->sr->supplies);
-			if (ret) {
-				dev_err(dev, "Could not turn off regulators\n");
-				reset_control_reset(pcie->rescal);
-				return ret;
-			}
-		}
-	}
 	clk_disable_unprepare(pcie->clk);
 
 	return 0;
@@ -1419,28 +1258,9 @@ static int brcm_pcie_resume(struct device *dev)
 	if (ret)
 		return ret;
 
-	if (pcie->sr) {
-		if (pcie->ep_wakeup_capable) {
-			/*
-			 * We are resuming from a suspend.  In the suspend we
-			 * did not disable the power supplies, so there is
-			 * no need to enable them (and falsely increase their
-			 * usage count).
-			 */
-			pcie->ep_wakeup_capable = false;
-		} else {
-			ret = regulator_bulk_enable(pcie->sr->num_supplies,
-						    pcie->sr->supplies);
-			if (ret) {
-				dev_err(dev, "Could not turn on regulators\n");
-				goto err_disable_clk;
-			}
-		}
-	}
-
 	ret = reset_control_reset(pcie->rescal);
 	if (ret)
-		goto err_regulator;
+		goto err_disable_clk;
 
 	ret = brcm_phy_start(pcie);
 	if (ret)
@@ -1461,10 +1281,6 @@ static int brcm_pcie_resume(struct device *dev)
 	if (ret)
 		goto err_reset;
 
-	ret = brcm_pcie_linkup(pcie);
-	if (ret)
-		goto err_reset;
-
 	if (pcie->msi)
 		brcm_msi_set_regs(pcie->msi);
 
@@ -1472,9 +1288,6 @@ static int brcm_pcie_resume(struct device *dev)
 
 err_reset:
 	reset_control_rearm(pcie->rescal);
-err_regulator:
-	if (pcie->sr)
-		regulator_bulk_disable(pcie->sr->num_supplies, pcie->sr->supplies);
 err_disable_clk:
 	clk_disable_unprepare(pcie->clk);
 	return ret;
@@ -1606,17 +1419,7 @@ static int brcm_pcie_probe(struct platform_device *pdev)
 
 	platform_set_drvdata(pdev, pcie);
 
-	ret = pci_host_probe(bridge);
-	if (!ret && !brcm_pcie_link_up(pcie))
-		ret = -ENODEV;
-
-	if (ret) {
-		brcm_pcie_remove(pdev);
-		return ret;
-	}
-
-	return 0;
-
+	return pci_host_probe(bridge);
 fail:
 	__brcm_pcie_remove(pcie);
 	return ret;
@@ -1625,8 +1428,8 @@ fail:
 MODULE_DEVICE_TABLE(of, brcm_pcie_match);
 
 static const struct dev_pm_ops brcm_pcie_pm_ops = {
-	.suspend_noirq = brcm_pcie_suspend,
-	.resume_noirq = brcm_pcie_resume,
+	.suspend = brcm_pcie_suspend,
+	.resume = brcm_pcie_resume,
 };
 
 static struct platform_driver brcm_pcie_driver = {
diff --git a/drivers/pci/controller/pcie-iproc-bcma.c b/drivers/pci/controller/pcie-iproc-bcma.c
index 54b6e6d5bc64..99a99900444d 100644
--- a/drivers/pci/controller/pcie-iproc-bcma.c
+++ b/drivers/pci/controller/pcie-iproc-bcma.c
@@ -18,7 +18,7 @@
 /* NS: CLASS field is R/O, and set to wrong 0x200 value */
 static void bcma_pcie2_fixup_class(struct pci_dev *dev)
 {
-	dev->class = PCI_CLASS_BRIDGE_PCI << 8;
+	dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL;
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x8011, bcma_pcie2_fixup_class);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x8012, bcma_pcie2_fixup_class);
diff --git a/drivers/pci/controller/pcie-iproc.c b/drivers/pci/controller/pcie-iproc.c
index b3e75bc61ff1..2519201b0e51 100644
--- a/drivers/pci/controller/pcie-iproc.c
+++ b/drivers/pci/controller/pcie-iproc.c
@@ -789,14 +789,13 @@ static int iproc_pcie_check_link(struct iproc_pcie *pcie)
 		return -EFAULT;
 	}
 
-	/* force class to PCI_CLASS_BRIDGE_PCI (0x0604) */
+	/* force class to PCI_CLASS_BRIDGE_PCI_NORMAL (0x060400) */
 #define PCI_BRIDGE_CTRL_REG_OFFSET	0x43c
-#define PCI_CLASS_BRIDGE_MASK		0xffff00
-#define PCI_CLASS_BRIDGE_SHIFT		8
+#define PCI_BRIDGE_CTRL_REG_CLASS_MASK	0xffffff
 	iproc_pci_raw_config_read32(pcie, 0, PCI_BRIDGE_CTRL_REG_OFFSET,
 				    4, &class);
-	class &= ~PCI_CLASS_BRIDGE_MASK;
-	class |= (PCI_CLASS_BRIDGE_PCI << PCI_CLASS_BRIDGE_SHIFT);
+	class &= ~PCI_BRIDGE_CTRL_REG_CLASS_MASK;
+	class |= PCI_CLASS_BRIDGE_PCI_NORMAL;
 	iproc_pci_raw_config_write32(pcie, 0, PCI_BRIDGE_CTRL_REG_OFFSET,
 				     4, class);
 
@@ -1581,7 +1580,7 @@ static void quirk_paxc_bridge(struct pci_dev *pdev)
 	 * code that the bridge is not an Ethernet device.
 	 */
 	if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
-		pdev->class = PCI_CLASS_BRIDGE_PCI << 8;
+		pdev->class = PCI_CLASS_BRIDGE_PCI_NORMAL;
 
 	/*
 	 * MPSS is not being set properly (as it is currently 0).  This is
diff --git a/drivers/pci/controller/pcie-mediatek-gen3.c b/drivers/pci/controller/pcie-mediatek-gen3.c
index 7705d61fba4c..5d9fd36b02d1 100644
--- a/drivers/pci/controller/pcie-mediatek-gen3.c
+++ b/drivers/pci/controller/pcie-mediatek-gen3.c
@@ -292,7 +292,7 @@ static int mtk_pcie_startup_port(struct mtk_gen3_pcie *pcie)
 	/* Set class code */
 	val = readl_relaxed(pcie->base + PCIE_PCI_IDS_1);
 	val &= ~GENMASK(31, 8);
-	val |= PCI_CLASS(PCI_CLASS_BRIDGE_PCI << 8);
+	val |= PCI_CLASS(PCI_CLASS_BRIDGE_PCI_NORMAL);
 	writel_relaxed(val, pcie->base + PCIE_PCI_IDS_1);
 
 	/* Mask all INTx interrupts */
@@ -838,6 +838,14 @@ static int mtk_pcie_setup(struct mtk_gen3_pcie *pcie)
 	if (err)
 		return err;
 
+	/*
+	 * The controller may have been left out of reset by the bootloader
+	 * so make sure that we get a clean start by asserting resets here.
+	 */
+	reset_control_assert(pcie->phy_reset);
+	reset_control_assert(pcie->mac_reset);
+	usleep_range(10, 20);
+
 	/* Don't touch the hardware registers before power up */
 	err = mtk_pcie_power_up(pcie);
 	if (err)
diff --git a/drivers/pci/controller/pcie-mediatek.c b/drivers/pci/controller/pcie-mediatek.c
index ddfbd4aebdec..be8bd919cb88 100644
--- a/drivers/pci/controller/pcie-mediatek.c
+++ b/drivers/pci/controller/pcie-mediatek.c
@@ -1008,6 +1008,7 @@ static int mtk_pcie_subsys_powerup(struct mtk_pcie *pcie)
 					   "mediatek,generic-pciecfg");
 	if (cfg_node) {
 		pcie->cfg = syscon_node_to_regmap(cfg_node);
+		of_node_put(cfg_node);
 		if (IS_ERR(pcie->cfg))
 			return PTR_ERR(pcie->cfg);
 	}
diff --git a/drivers/pci/controller/pcie-microchip-host.c b/drivers/pci/controller/pcie-microchip-host.c
index 29d8e81e4181..dd5dba419047 100644
--- a/drivers/pci/controller/pcie-microchip-host.c
+++ b/drivers/pci/controller/pcie-microchip-host.c
@@ -406,6 +406,7 @@ static void mc_pcie_enable_msi(struct mc_pcie *port, void __iomem *base)
 static void mc_handle_msi(struct irq_desc *desc)
 {
 	struct mc_pcie *port = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct device *dev = port->dev;
 	struct mc_msi *msi = &port->msi;
 	void __iomem *bridge_base_addr =
@@ -414,8 +415,11 @@ static void mc_handle_msi(struct irq_desc *desc)
 	u32 bit;
 	int ret;
 
+	chained_irq_enter(chip, desc);
+
 	status = readl_relaxed(bridge_base_addr + ISTATUS_LOCAL);
 	if (status & PM_MSI_INT_MSI_MASK) {
+		writel_relaxed(status & PM_MSI_INT_MSI_MASK, bridge_base_addr + ISTATUS_LOCAL);
 		status = readl_relaxed(bridge_base_addr + ISTATUS_MSI);
 		for_each_set_bit(bit, &status, msi->num_vectors) {
 			ret = generic_handle_domain_irq(msi->dev_domain, bit);
@@ -424,6 +428,8 @@ static void mc_handle_msi(struct irq_desc *desc)
 						    bit);
 		}
 	}
+
+	chained_irq_exit(chip, desc);
 }
 
 static void mc_msi_bottom_irq_ack(struct irq_data *data)
@@ -432,13 +438,8 @@ static void mc_msi_bottom_irq_ack(struct irq_data *data)
 	void __iomem *bridge_base_addr =
 		port->axi_base_addr + MC_PCIE_BRIDGE_ADDR;
 	u32 bitpos = data->hwirq;
-	unsigned long status;
 
 	writel_relaxed(BIT(bitpos), bridge_base_addr + ISTATUS_MSI);
-	status = readl_relaxed(bridge_base_addr + ISTATUS_MSI);
-	if (!status)
-		writel_relaxed(BIT(PM_MSI_INT_MSI_SHIFT),
-			       bridge_base_addr + ISTATUS_LOCAL);
 }
 
 static void mc_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
@@ -563,6 +564,7 @@ static int mc_allocate_msi_domains(struct mc_pcie *port)
 static void mc_handle_intx(struct irq_desc *desc)
 {
 	struct mc_pcie *port = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct device *dev = port->dev;
 	void __iomem *bridge_base_addr =
 		port->axi_base_addr + MC_PCIE_BRIDGE_ADDR;
@@ -570,6 +572,8 @@ static void mc_handle_intx(struct irq_desc *desc)
 	u32 bit;
 	int ret;
 
+	chained_irq_enter(chip, desc);
+
 	status = readl_relaxed(bridge_base_addr + ISTATUS_LOCAL);
 	if (status & PM_MSI_INT_INTX_MASK) {
 		status &= PM_MSI_INT_INTX_MASK;
@@ -581,6 +585,8 @@ static void mc_handle_intx(struct irq_desc *desc)
 						    bit);
 		}
 	}
+
+	chained_irq_exit(chip, desc);
 }
 
 static void mc_ack_intx_irq(struct irq_data *data)
@@ -1115,7 +1121,7 @@ static const struct of_device_id mc_pcie_of_match[] = {
 	{},
 };
 
-MODULE_DEVICE_TABLE(of, mc_pcie_of_match)
+MODULE_DEVICE_TABLE(of, mc_pcie_of_match);
 
 static struct platform_driver mc_pcie_driver = {
 	.probe = pci_host_common_probe,
diff --git a/drivers/pci/controller/pcie-rcar-host.c b/drivers/pci/controller/pcie-rcar-host.c
index 38b6e02edfa9..997c4df6a1e7 100644
--- a/drivers/pci/controller/pcie-rcar-host.c
+++ b/drivers/pci/controller/pcie-rcar-host.c
@@ -65,6 +65,42 @@ struct rcar_pcie_host {
 	int			(*phy_init_fn)(struct rcar_pcie_host *host);
 };
 
+static DEFINE_SPINLOCK(pmsr_lock);
+
+static int rcar_pcie_wakeup(struct device *pcie_dev, void __iomem *pcie_base)
+{
+	unsigned long flags;
+	u32 pmsr, val;
+	int ret = 0;
+
+	spin_lock_irqsave(&pmsr_lock, flags);
+
+	if (!pcie_base || pm_runtime_suspended(pcie_dev)) {
+		ret = -EINVAL;
+		goto unlock_exit;
+	}
+
+	pmsr = readl(pcie_base + PMSR);
+
+	/*
+	 * Test if the PCIe controller received PM_ENTER_L1 DLLP and
+	 * the PCIe controller is not in L1 link state. If true, apply
+	 * fix, which will put the controller into L1 link state, from
+	 * which it can return to L0s/L0 on its own.
+	 */
+	if ((pmsr & PMEL1RX) && ((pmsr & PMSTATE) != PMSTATE_L1)) {
+		writel(L1IATN, pcie_base + PMCTLR);
+		ret = readl_poll_timeout_atomic(pcie_base + PMSR, val,
+						val & L1FAEG, 10, 1000);
+		WARN(ret, "Timeout waiting for L1 link state, ret=%d\n", ret);
+		writel(L1FAEG | PMEL1RX, pcie_base + PMSR);
+	}
+
+unlock_exit:
+	spin_unlock_irqrestore(&pmsr_lock, flags);
+	return ret;
+}
+
 static struct rcar_pcie_host *msi_to_host(struct rcar_msi *msi)
 {
 	return container_of(msi, struct rcar_pcie_host, msi);
@@ -78,6 +114,54 @@ static u32 rcar_read_conf(struct rcar_pcie *pcie, int where)
 	return val >> shift;
 }
 
+#ifdef CONFIG_ARM
+#define __rcar_pci_rw_reg_workaround(instr)				\
+		"	.arch armv7-a\n"				\
+		"1:	" instr " %1, [%2]\n"				\
+		"2:	isb\n"						\
+		"3:	.pushsection .text.fixup,\"ax\"\n"		\
+		"	.align	2\n"					\
+		"4:	mov	%0, #" __stringify(PCIBIOS_SET_FAILED) "\n" \
+		"	b	3b\n"					\
+		"	.popsection\n"					\
+		"	.pushsection __ex_table,\"a\"\n"		\
+		"	.align	3\n"					\
+		"	.long	1b, 4b\n"				\
+		"	.long	2b, 4b\n"				\
+		"	.popsection\n"
+#endif
+
+static int rcar_pci_write_reg_workaround(struct rcar_pcie *pcie, u32 val,
+					 unsigned int reg)
+{
+	int error = PCIBIOS_SUCCESSFUL;
+#ifdef CONFIG_ARM
+	asm volatile(
+		__rcar_pci_rw_reg_workaround("str")
+	: "+r"(error):"r"(val), "r"(pcie->base + reg) : "memory");
+#else
+	rcar_pci_write_reg(pcie, val, reg);
+#endif
+	return error;
+}
+
+static int rcar_pci_read_reg_workaround(struct rcar_pcie *pcie, u32 *val,
+					unsigned int reg)
+{
+	int error = PCIBIOS_SUCCESSFUL;
+#ifdef CONFIG_ARM
+	asm volatile(
+		__rcar_pci_rw_reg_workaround("ldr")
+	: "+r"(error), "=r"(*val) : "r"(pcie->base + reg) : "memory");
+
+	if (error != PCIBIOS_SUCCESSFUL)
+		PCI_SET_ERROR_RESPONSE(val);
+#else
+	*val = rcar_pci_read_reg(pcie, reg);
+#endif
+	return error;
+}
+
 /* Serialization is provided by 'pci_lock' in drivers/pci/access.c */
 static int rcar_pcie_config_access(struct rcar_pcie_host *host,
 		unsigned char access_type, struct pci_bus *bus,
@@ -85,6 +169,14 @@ static int rcar_pcie_config_access(struct rcar_pcie_host *host,
 {
 	struct rcar_pcie *pcie = &host->pcie;
 	unsigned int dev, func, reg, index;
+	int ret;
+
+	/* Wake the bus up in case it is in L1 state. */
+	ret = rcar_pcie_wakeup(pcie->dev, pcie->base);
+	if (ret) {
+		PCI_SET_ERROR_RESPONSE(data);
+		return PCIBIOS_SET_FAILED;
+	}
 
 	dev = PCI_SLOT(devfn);
 	func = PCI_FUNC(devfn);
@@ -141,14 +233,14 @@ static int rcar_pcie_config_access(struct rcar_pcie_host *host,
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
 	if (access_type == RCAR_PCI_ACCESS_READ)
-		*data = rcar_pci_read_reg(pcie, PCIECDR);
+		ret = rcar_pci_read_reg_workaround(pcie, data, PCIECDR);
 	else
-		rcar_pci_write_reg(pcie, *data, PCIECDR);
+		ret = rcar_pci_write_reg_workaround(pcie, *data, PCIECDR);
 
 	/* Disable the configuration access */
 	rcar_pci_write_reg(pcie, 0, PCIECCTLR);
 
-	return PCIBIOS_SUCCESSFUL;
+	return ret;
 }
 
 static int rcar_pcie_read_conf(struct pci_bus *bus, unsigned int devfn,
@@ -370,7 +462,7 @@ static int rcar_pcie_hw_init(struct rcar_pcie *pcie)
 	 * class to match. Hardware takes care of propagating the IDSETR
 	 * settings, so there is no need to bother with a quirk.
 	 */
-	rcar_pci_write_reg(pcie, PCI_CLASS_BRIDGE_PCI << 16, IDSETR1);
+	rcar_pci_write_reg(pcie, PCI_CLASS_BRIDGE_PCI_NORMAL << 8, IDSETR1);
 
 	/*
 	 * Setup Secondary Bus Number & Subordinate Bus Number, even though
@@ -1050,40 +1142,10 @@ static struct platform_driver rcar_pcie_driver = {
 };
 
 #ifdef CONFIG_ARM
-static DEFINE_SPINLOCK(pmsr_lock);
 static int rcar_pcie_aarch32_abort_handler(unsigned long addr,
 		unsigned int fsr, struct pt_regs *regs)
 {
-	unsigned long flags;
-	u32 pmsr, val;
-	int ret = 0;
-
-	spin_lock_irqsave(&pmsr_lock, flags);
-
-	if (!pcie_base || pm_runtime_suspended(pcie_dev)) {
-		ret = 1;
-		goto unlock_exit;
-	}
-
-	pmsr = readl(pcie_base + PMSR);
-
-	/*
-	 * Test if the PCIe controller received PM_ENTER_L1 DLLP and
-	 * the PCIe controller is not in L1 link state. If true, apply
-	 * fix, which will put the controller into L1 link state, from
-	 * which it can return to L0s/L0 on its own.
-	 */
-	if ((pmsr & PMEL1RX) && ((pmsr & PMSTATE) != PMSTATE_L1)) {
-		writel(L1IATN, pcie_base + PMCTLR);
-		ret = readl_poll_timeout_atomic(pcie_base + PMSR, val,
-						val & L1FAEG, 10, 1000);
-		WARN(ret, "Timeout waiting for L1 link state, ret=%d\n", ret);
-		writel(L1FAEG | PMEL1RX, pcie_base + PMSR);
-	}
-
-unlock_exit:
-	spin_unlock_irqrestore(&pmsr_lock, flags);
-	return ret;
+	return !fixup_exception(regs);
 }
 
 static const struct of_device_id rcar_pcie_abort_handler_of_match[] __initconst = {
diff --git a/drivers/pci/controller/pcie-rockchip-ep.c b/drivers/pci/controller/pcie-rockchip-ep.c
index 5fb9ce6e536e..d1a200b93b2b 100644
--- a/drivers/pci/controller/pcie-rockchip-ep.c
+++ b/drivers/pci/controller/pcie-rockchip-ep.c
@@ -264,8 +264,7 @@ static int rockchip_pcie_ep_map_addr(struct pci_epc *epc, u8 fn, u8 vfn,
 	struct rockchip_pcie *pcie = &ep->rockchip;
 	u32 r;
 
-	r = find_first_zero_bit(&ep->ob_region_map,
-				sizeof(ep->ob_region_map) * BITS_PER_LONG);
+	r = find_first_zero_bit(&ep->ob_region_map, BITS_PER_LONG);
 	/*
 	 * Region 0 is reserved for configuration space and shouldn't
 	 * be used elsewhere per TRM, so leave it out.
diff --git a/drivers/pci/controller/pcie-rockchip-host.c b/drivers/pci/controller/pcie-rockchip-host.c
index 45a28880f322..7f56f99b4116 100644
--- a/drivers/pci/controller/pcie-rockchip-host.c
+++ b/drivers/pci/controller/pcie-rockchip-host.c
@@ -370,7 +370,7 @@ static int rockchip_pcie_host_init_port(struct rockchip_pcie *rockchip)
 	rockchip_pcie_write(rockchip, ROCKCHIP_VENDOR_ID,
 			    PCIE_CORE_CONFIG_VENDOR);
 	rockchip_pcie_write(rockchip,
-			    PCI_CLASS_BRIDGE_PCI << PCIE_RC_CONFIG_SCC_SHIFT,
+			    PCI_CLASS_BRIDGE_PCI_NORMAL << 8,
 			    PCIE_RC_CONFIG_RID_CCR);
 
 	/* Clear THP cap's next cap pointer to remove L1 substate cap */
diff --git a/drivers/pci/controller/pcie-rockchip.h b/drivers/pci/controller/pcie-rockchip.h
index 1650a5087450..32c3a859c26b 100644
--- a/drivers/pci/controller/pcie-rockchip.h
+++ b/drivers/pci/controller/pcie-rockchip.h
@@ -134,7 +134,6 @@
 #define PCIE_RC_CONFIG_NORMAL_BASE	0x800000
 #define PCIE_RC_CONFIG_BASE		0xa00000
 #define PCIE_RC_CONFIG_RID_CCR		(PCIE_RC_CONFIG_BASE + 0x08)
-#define   PCIE_RC_CONFIG_SCC_SHIFT		16
 #define PCIE_RC_CONFIG_DCR		(PCIE_RC_CONFIG_BASE + 0xc4)
 #define   PCIE_RC_CONFIG_DCR_CSPL_SHIFT		18
 #define   PCIE_RC_CONFIG_DCR_CSPL_LIMIT		0xff
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index eb05cceab964..94a14a3d7e55 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -6,7 +6,6 @@
 
 #include <linux/device.h>
 #include <linux/interrupt.h>
-#include <linux/iommu.h>
 #include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -813,8 +812,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features)
 	 * acceptable because the guest is usually CPU-limited and MSI
 	 * remapping doesn't become a performance bottleneck.
 	 */
-	if (iommu_capable(vmd->dev->dev.bus, IOMMU_CAP_INTR_REMAP) ||
-	    !(features & VMD_FEAT_CAN_BYPASS_MSI_REMAP) ||
+	if (!(features & VMD_FEAT_CAN_BYPASS_MSI_REMAP) ||
 	    offset[0] || offset[1]) {
 		ret = vmd_alloc_irqs(vmd);
 		if (ret)
@@ -853,6 +851,9 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features)
 	vmd_attach_resources(vmd);
 	if (vmd->irq_domain)
 		dev_set_msi_domain(&vmd->bus->dev, vmd->irq_domain);
+	else
+		dev_set_msi_domain(&vmd->bus->dev,
+				   dev_get_msi_domain(&vmd->dev->dev));
 
 	vmd_acpi_begin();