Merge branches 'pci/host-designware', 'pci/host-designware-common',...

Merge branches 'pci/host-designware', 'pci/host-designware-common', 'pci/host-generic', 'pci/host-imx6', 'pci/host-iproc' and 'pci/host-xgene' into next

* pci/host-designware:
  PCI: designware: Use iATU0 for cfg and IO, iATU1 for MEM
  PCI: designware: Consolidate outbound iATU programming functions
  PCI: designware: Add support for x8 links

* pci/host-designware-common:
  PCI: designware: Wait for link to come up with consistent style
  PCI: layerscape: Factor out ls_pcie_establish_link()
  PCI: layerscape: Use dw_pcie_link_up() consistently
  PCI: dra7xx: Use dw_pcie_link_up() consistently
  PCI: imx6: Rename imx6_pcie_start_link() to imx6_pcie_establish_link()

* pci/host-generic:
  of/pci: Fix pci_address_to_pio() conversion of CPU address to I/O port

* pci/host-imx6:
  PCI: imx6: Add #define PCIE_RC_LCSR
  PCI: imx6: Use "u32", not "uint32_t"
  PCI: imx6: Add speed change timeout message

* pci/host-iproc:
  PCI: iproc: Free resource list after registration
  PCI: iproc: Directly add PCI resources
  PCI: iproc: Add BCMA PCIe driver
  PCI: iproc: Allow override of device tree IRQ mapping function

* pci/host-xgene:
  arm64: dts: Add APM X-Gene PCIe MSI nodes
  PCI: xgene: Add APM X-Gene v1 PCIe MSI/MSIX termination driver

Documentation/devicetree/bindings/pci/xgene-pci-msi.txt

+* AppliedMicro X-Gene v1 PCIe MSI controller
+
+Required properties:
+
+- compatible: should be "apm,xgene1-msi" to identify
+	      X-Gene v1 PCIe MSI controller block.
+- msi-controller: indicates that this is X-Gene v1 PCIe MSI controller node
+- reg: physical base address (0x79000000) and length (0x900000) for controller
+       registers. These registers include the MSI termination address and data
+       registers as well as the MSI interrupt status registers.
+- reg-names: not required
+- interrupts: A list of 16 interrupt outputs of the controller, starting from
+	      interrupt number 0x10 to 0x1f.
+- interrupt-names: not required
+
+Each PCIe node needs to have property msi-parent that points to msi controller node
+
+Examples:
+
+SoC DTSI:
+
+	+ MSI node:
+	msi@79000000 {
+		compatible = "apm,xgene1-msi";
+		msi-controller;
+		reg = <0x00 0x79000000 0x0 0x900000>;
+		interrupts = 	<0x0 0x10 0x4>
+				<0x0 0x11 0x4>
+				<0x0 0x12 0x4>
+				<0x0 0x13 0x4>
+				<0x0 0x14 0x4>
+				<0x0 0x15 0x4>
+				<0x0 0x16 0x4>
+				<0x0 0x17 0x4>
+				<0x0 0x18 0x4>
+				<0x0 0x19 0x4>
+				<0x0 0x1a 0x4>
+				<0x0 0x1b 0x4>
+				<0x0 0x1c 0x4>
+				<0x0 0x1d 0x4>
+				<0x0 0x1e 0x4>
+				<0x0 0x1f 0x4>;
+	};
+
+	+ PCIe controller node with msi-parent property pointing to MSI node:
+	pcie0: pcie@1f2b0000 {
+		status = "disabled";
+		device_type = "pci";
+		compatible = "apm,xgene-storm-pcie", "apm,xgene-pcie";
+		#interrupt-cells = <1>;
+		#size-cells = <2>;
+		#address-cells = <3>;
+		reg = < 0x00 0x1f2b0000 0x0 0x00010000   /* Controller registers */
+			0xe0 0xd0000000 0x0 0x00040000>; /* PCI config space */
+		reg-names = "csr", "cfg";
+		ranges = <0x01000000 0x00 0x00000000 0xe0 0x10000000 0x00 0x00010000   /* io */
+			  0x02000000 0x00 0x80000000 0xe1 0x80000000 0x00 0x80000000>; /* mem */
+		dma-ranges = <0x42000000 0x80 0x00000000 0x80 0x00000000 0x00 0x80000000
+			      0x42000000 0x00 0x00000000 0x00 0x00000000 0x80 0x00000000>;
+		interrupt-map-mask = <0x0 0x0 0x0 0x7>;
+		interrupt-map = <0x0 0x0 0x0 0x1 &gic 0x0 0xc2 0x1
+				 0x0 0x0 0x0 0x2 &gic 0x0 0xc3 0x1
+				 0x0 0x0 0x0 0x3 &gic 0x0 0xc4 0x1
+				 0x0 0x0 0x0 0x4 &gic 0x0 0xc5 0x1>;
+		dma-coherent;
+		clocks = <&pcie0clk 0>;
+		msi-parent= <&msi>;
+	};

MAINTAINERS

@@ -7564,6 +7564,14 @@ L:	linux-pci@vger.kernel.org
 S:	Orphan
 F:	drivers/pci/host/*spear*
 
+PCI MSI DRIVER FOR APPLIEDMICRO XGENE
+M:	Duc Dang <dhdang@apm.com>
+L:	linux-pci@vger.kernel.org
+L:	linux-arm-kernel@lists.infradead.org
+S:	Maintained
+F:	Documentation/devicetree/bindings/pci/xgene-pci-msi.txt
+F:	drivers/pci/host/pci-xgene-msi.c
+
 PCMCIA SUBSYSTEM
 P:	Linux PCMCIA Team
 L:	linux-pcmcia@lists.infradead.org

arch/arm64/boot/dts/apm/apm-storm.dtsi

@@ -374,6 +374,28 @@
 			};
 		};
 
+		msi: msi@79000000 {
+			compatible = "apm,xgene1-msi";
+			msi-controller;
+			reg = <0x00 0x79000000 0x0 0x900000>;
+			interrupts = <  0x0 0x10 0x4
+					0x0 0x11 0x4
+					0x0 0x12 0x4
+					0x0 0x13 0x4
+					0x0 0x14 0x4
+					0x0 0x15 0x4
+					0x0 0x16 0x4
+					0x0 0x17 0x4
+					0x0 0x18 0x4
+					0x0 0x19 0x4
+					0x0 0x1a 0x4
+					0x0 0x1b 0x4
+					0x0 0x1c 0x4
+					0x0 0x1d 0x4
+					0x0 0x1e 0x4
+					0x0 0x1f 0x4>;
+		};
+
 		pcie0: pcie@1f2b0000 {
 			status = "disabled";
 			device_type = "pci";
@@ -395,6 +417,7 @@
 					 0x0 0x0 0x0 0x4 &gic 0x0 0xc5 0x1>;
 			dma-coherent;
 			clocks = <&pcie0clk 0>;
+			msi-parent = <&msi>;
 		};
 
 		pcie1: pcie@1f2c0000 {
@@ -418,6 +441,7 @@
 					 0x0 0x0 0x0 0x4 &gic 0x0 0xcb 0x1>;
 			dma-coherent;
 			clocks = <&pcie1clk 0>;
+			msi-parent = <&msi>;
 		};
 
 		pcie2: pcie@1f2d0000 {
@@ -441,6 +465,7 @@
 					 0x0 0x0 0x0 0x4 &gic 0x0 0xd1 0x1>;
 			dma-coherent;
 			clocks = <&pcie2clk 0>;
+			msi-parent = <&msi>;
 		};
 
 		pcie3: pcie@1f500000 {
@@ -464,6 +489,7 @@
 					 0x0 0x0 0x0 0x4 &gic 0x0 0xd7 0x1>;
 			dma-coherent;
 			clocks = <&pcie3clk 0>;
+			msi-parent = <&msi>;
 		};
 
 		pcie4: pcie@1f510000 {
@@ -487,6 +513,7 @@
 					 0x0 0x0 0x0 0x4 &gic 0x0 0xdd 0x1>;
 			dma-coherent;
 			clocks = <&pcie4clk 0>;
+			msi-parent = <&msi>;
 		};
 
 		serial0: serial@1c020000 {

drivers/of/address.c

@@ -765,7 +765,7 @@ unsigned long __weak pci_address_to_pio(phys_addr_t address)
 	spin_lock(&io_range_lock);
 	list_for_each_entry(res, &io_range_list, list) {
 		if (address >= res->start && address < res->start + res->size) {
-			addr = res->start - address + offset;
+			addr = address - res->start + offset;
 			break;
 		}
 		offset += res->size;

drivers/pci/host/Kconfig

@@ -89,11 +89,20 @@ config PCI_XGENE
 	depends on ARCH_XGENE
 	depends on OF
 	select PCIEPORTBUS
+	select PCI_MSI_IRQ_DOMAIN if PCI_MSI
 	help
 	  Say Y here if you want internal PCI support on APM X-Gene SoC.
 	  There are 5 internal PCIe ports available. Each port is GEN3 capable
 	  and have varied lanes from x1 to x8.
 
+config PCI_XGENE_MSI
+	bool "X-Gene v1 PCIe MSI feature"
+	depends on PCI_XGENE && PCI_MSI
+	default y
+	help
+	  Say Y here if you want PCIe MSI support for the APM X-Gene v1 SoC.
+	  This MSI driver supports 5 PCIe ports on the APM X-Gene v1 SoC.
+
 config PCI_LAYERSCAPE
 	bool "Freescale Layerscape PCIe controller"
 	depends on OF && ARM
@@ -125,4 +134,15 @@ config PCIE_IPROC_PLATFORM
 	  Say Y here if you want to use the Broadcom iProc PCIe controller
 	  through the generic platform bus interface
 
+config PCIE_IPROC_BCMA
+	bool "Broadcom iProc PCIe BCMA bus driver"
+	depends on ARCH_BCM_IPROC || (ARM && COMPILE_TEST)
+	select PCIE_IPROC
+	select BCMA
+	select PCI_DOMAINS
+	default ARCH_BCM_5301X
+	help
+	  Say Y here if you want to use the Broadcom iProc PCIe controller
+	  through the BCMA bus interface
+
 endmenu

drivers/pci/host/Makefile

@@ -11,7 +11,9 @@ obj-$(CONFIG_PCIE_SPEAR13XX) += pcie-spear13xx.o
 obj-$(CONFIG_PCI_KEYSTONE) += pci-keystone-dw.o pci-keystone.o
 obj-$(CONFIG_PCIE_XILINX) += pcie-xilinx.o
 obj-$(CONFIG_PCI_XGENE) += pci-xgene.o
+obj-$(CONFIG_PCI_XGENE_MSI) += pci-xgene-msi.o
 obj-$(CONFIG_PCI_LAYERSCAPE) += pci-layerscape.o
 obj-$(CONFIG_PCI_VERSATILE) += pci-versatile.o
 obj-$(CONFIG_PCIE_IPROC) += pcie-iproc.o
 obj-$(CONFIG_PCIE_IPROC_PLATFORM) += pcie-iproc-platform.o
+obj-$(CONFIG_PCIE_IPROC_BCMA) += pcie-iproc-bcma.o

drivers/pci/host/pci-dra7xx.c

@@ -93,9 +93,9 @@ static int dra7xx_pcie_link_up(struct pcie_port *pp)
 
 static int dra7xx_pcie_establish_link(struct pcie_port *pp)
 {
-	u32 reg;
-	unsigned int retries = 1000;
 	struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pp);
+	u32 reg;
+	unsigned int retries;
 
 	if (dw_pcie_link_up(pp)) {
 		dev_err(pp->dev, "link is already up\n");
@@ -106,19 +106,14 @@ static int dra7xx_pcie_establish_link(struct pcie_port *pp)
 	reg |= LTSSM_EN;
 	dra7xx_pcie_writel(dra7xx, PCIECTRL_DRA7XX_CONF_DEVICE_CMD, reg);
 
-	while (retries--) {
-		reg = dra7xx_pcie_readl(dra7xx,	PCIECTRL_DRA7XX_CONF_PHY_CS);
-		if (reg & LINK_UP)
-			break;
+	for (retries = 0; retries < 1000; retries++) {
+		if (dw_pcie_link_up(pp))
+			return 0;
 		usleep_range(10, 20);
 	}
 
-	if (retries == 0) {
 	dev_err(pp->dev, "link is not up\n");
-		return -ETIMEDOUT;
-	}
-
-	return 0;
+	return -EINVAL;
 }
 
 static void dra7xx_pcie_enable_interrupts(struct pcie_port *pp)

drivers/pci/host/pci-exynos.c

@@ -316,9 +316,9 @@ static void exynos_pcie_assert_reset(struct pcie_port *pp)
 
 static int exynos_pcie_establish_link(struct pcie_port *pp)
 {
-	u32 val;
-	int count = 0;
 	struct exynos_pcie *exynos_pcie = to_exynos_pcie(pp);
+	u32 val;
+	unsigned int retries;
 
 	if (dw_pcie_link_up(pp)) {
 		dev_err(pp->dev, "Link already up\n");
@@ -357,14 +357,16 @@ static int exynos_pcie_establish_link(struct pcie_port *pp)
 			  PCIE_APP_LTSSM_ENABLE);
 
 	/* check if the link is up or not */
-	while (!dw_pcie_link_up(pp)) {
+	for (retries = 0; retries < 10; retries++) {
+		if (dw_pcie_link_up(pp)) {
+			dev_info(pp->dev, "Link up\n");
+			return 0;
+		}
 		mdelay(100);
-		count++;
-		if (count == 10) {
-			while (exynos_phy_readl(exynos_pcie,
-						PCIE_PHY_PLL_LOCKED) == 0) {
-				val = exynos_blk_readl(exynos_pcie,
-						       PCIE_PHY_PLL_LOCKED);
+	}
+
+	while (exynos_phy_readl(exynos_pcie, PCIE_PHY_PLL_LOCKED) == 0) {
+		val = exynos_blk_readl(exynos_pcie, PCIE_PHY_PLL_LOCKED);
 		dev_info(pp->dev, "PLL Locked: 0x%x\n", val);
 	}
 	/* power off phy */
@@ -372,12 +374,6 @@ static int exynos_pcie_establish_link(struct pcie_port *pp)
 
 	dev_err(pp->dev, "PCIe Link Fail\n");
 	return -EINVAL;
-		}
-	}
-
-	dev_info(pp->dev, "Link up\n");
-
-	return 0;
 }
 
 static void exynos_pcie_clear_irq_pulse(struct pcie_port *pp)

drivers/pci/host/pci-imx6.c

@@ -47,6 +47,8 @@ struct imx6_pcie {
 #define PCIE_RC_LCR_MAX_LINK_SPEEDS_GEN2	0x2
 #define PCIE_RC_LCR_MAX_LINK_SPEEDS_MASK	0xf
 
+#define PCIE_RC_LCSR				0x80
+
 /* PCIe Port Logic registers (memory-mapped) */
 #define PL_OFFSET 0x700
 #define PCIE_PL_PFLR (PL_OFFSET + 0x08)
@@ -335,21 +337,36 @@ static void imx6_pcie_init_phy(struct pcie_port *pp)
 
 static int imx6_pcie_wait_for_link(struct pcie_port *pp)
 {
-	int count = 200;
+	unsigned int retries;
 
-	while (!dw_pcie_link_up(pp)) {
+	for (retries = 0; retries < 200; retries++) {
+		if (dw_pcie_link_up(pp))
+			return 0;
 		usleep_range(100, 1000);
-		if (--count)
-			continue;
+	}
 
 	dev_err(pp->dev, "phy link never came up\n");
 	dev_dbg(pp->dev, "DEBUG_R0: 0x%08x, DEBUG_R1: 0x%08x\n",
 		readl(pp->dbi_base + PCIE_PHY_DEBUG_R0),
 		readl(pp->dbi_base + PCIE_PHY_DEBUG_R1));
 	return -EINVAL;
-	}
+}
+
+static int imx6_pcie_wait_for_speed_change(struct pcie_port *pp)
+{
+	u32 tmp;
+	unsigned int retries;
 
+	for (retries = 0; retries < 200; retries++) {
+		tmp = readl(pp->dbi_base + PCIE_LINK_WIDTH_SPEED_CONTROL);
+		/* Test if the speed change finished. */
+		if (!(tmp & PORT_LOGIC_SPEED_CHANGE))
 			return 0;
+		usleep_range(100, 1000);
+	}
+
+	dev_err(pp->dev, "Speed change timeout\n");
+	return -EINVAL;
 }
 
 static irqreturn_t imx6_pcie_msi_handler(int irq, void *arg)
@@ -359,11 +376,11 @@ static irqreturn_t imx6_pcie_msi_handler(int irq, void *arg)
 	return dw_handle_msi_irq(pp);
 }
 
-static int imx6_pcie_start_link(struct pcie_port *pp)
+static int imx6_pcie_establish_link(struct pcie_port *pp)
 {
 	struct imx6_pcie *imx6_pcie = to_imx6_pcie(pp);
-	uint32_t tmp;
-	int ret, count;
+	u32 tmp;
+	int ret;
 
 	/*
 	 * Force Gen1 operation when starting the link.  In case the link is
@@ -397,29 +414,22 @@ static int imx6_pcie_start_link(struct pcie_port *pp)
 	tmp |= PORT_LOGIC_SPEED_CHANGE;
 	writel(tmp, pp->dbi_base + PCIE_LINK_WIDTH_SPEED_CONTROL);
 
-	count = 200;
-	while (count--) {
-		tmp = readl(pp->dbi_base + PCIE_LINK_WIDTH_SPEED_CONTROL);
-		/* Test if the speed change finished. */
-		if (!(tmp & PORT_LOGIC_SPEED_CHANGE))
-			break;
-		usleep_range(100, 1000);
+	ret = imx6_pcie_wait_for_speed_change(pp);
+	if (ret) {
+		dev_err(pp->dev, "Failed to bring link up!\n");
+		return ret;
 	}
 
 	/* Make sure link training is finished as well! */
-	if (count)
 	ret = imx6_pcie_wait_for_link(pp);
-	else
-		ret = -EINVAL;
-
 	if (ret) {
 		dev_err(pp->dev, "Failed to bring link up!\n");
-	} else {
-		tmp = readl(pp->dbi_base + 0x80);
-		dev_dbg(pp->dev, "Link up, Gen=%i\n", (tmp >> 16) & 0xf);
+		return ret;
 	}
 
-	return ret;
+	tmp = readl(pp->dbi_base + PCIE_RC_LCSR);
+	dev_dbg(pp->dev, "Link up, Gen=%i\n", (tmp >> 16) & 0xf);
+	return 0;
 }
 
 static void imx6_pcie_host_init(struct pcie_port *pp)
@@ -432,7 +442,7 @@ static void imx6_pcie_host_init(struct pcie_port *pp)
 
 	dw_pcie_setup_rc(pp);
 
-	imx6_pcie_start_link(pp);
+	imx6_pcie_establish_link(pp);
 
 	if (IS_ENABLED(CONFIG_PCI_MSI))
 		dw_pcie_msi_init(pp);
@@ -440,19 +450,19 @@ static void imx6_pcie_host_init(struct pcie_port *pp)
 
 static void imx6_pcie_reset_phy(struct pcie_port *pp)
 {
-	uint32_t temp;
+	u32 tmp;
 
-	pcie_phy_read(pp->dbi_base, PHY_RX_OVRD_IN_LO, &temp);
-	temp |= (PHY_RX_OVRD_IN_LO_RX_DATA_EN |
+	pcie_phy_read(pp->dbi_base, PHY_RX_OVRD_IN_LO, &tmp);
+	tmp |= (PHY_RX_OVRD_IN_LO_RX_DATA_EN |
 		PHY_RX_OVRD_IN_LO_RX_PLL_EN);
-	pcie_phy_write(pp->dbi_base, PHY_RX_OVRD_IN_LO, temp);
+	pcie_phy_write(pp->dbi_base, PHY_RX_OVRD_IN_LO, tmp);
 
 	usleep_range(2000, 3000);
 
-	pcie_phy_read(pp->dbi_base, PHY_RX_OVRD_IN_LO, &temp);
-	temp &= ~(PHY_RX_OVRD_IN_LO_RX_DATA_EN |
+	pcie_phy_read(pp->dbi_base, PHY_RX_OVRD_IN_LO, &tmp);
+	tmp &= ~(PHY_RX_OVRD_IN_LO_RX_DATA_EN |
 		  PHY_RX_OVRD_IN_LO_RX_PLL_EN);
-	pcie_phy_write(pp->dbi_base, PHY_RX_OVRD_IN_LO, temp);
+	pcie_phy_write(pp->dbi_base, PHY_RX_OVRD_IN_LO, tmp);
 }
 
 static int imx6_pcie_link_up(struct pcie_port *pp)

drivers/pci/host/pci-keystone.c

@@ -88,7 +88,7 @@ DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, quirk_limit_mrrs);
 static int ks_pcie_establish_link(struct keystone_pcie *ks_pcie)
 {
 	struct pcie_port *pp = &ks_pcie->pp;
-	int count = 200;
+	unsigned int retries;
 
 	dw_pcie_setup_rc(pp);
 
@@ -99,17 +99,15 @@ static int ks_pcie_establish_link(struct keystone_pcie *ks_pcie)
 
 	ks_dw_pcie_initiate_link_train(ks_pcie);
 	/* check if the link is up or not */
-	while (!dw_pcie_link_up(pp)) {
+	for (retries = 0; retries < 200; retries++) {
+		if (dw_pcie_link_up(pp))
+			return 0;
 		usleep_range(100, 1000);
-		if (--count) {
 		ks_dw_pcie_initiate_link_train(ks_pcie);
-			continue;
 	}
+
 	dev_err(pp->dev, "phy link never came up\n");
 	return -EINVAL;
-	}
-
-	return 0;
 }
 
 static void ks_pcie_msi_irq_handler(unsigned int irq, struct irq_desc *desc)

drivers/pci/host/pci-layerscape.c

@@ -62,22 +62,27 @@ static int ls_pcie_link_up(struct pcie_port *pp)
 	return 1;
 }
 
+static int ls_pcie_establish_link(struct pcie_port *pp)
+{
+	unsigned int retries;
+
+	for (retries = 0; retries < 200; retries++) {
+		if (dw_pcie_link_up(pp))
+			return 0;
+		usleep_range(100, 1000);
+	}
+
+	dev_err(pp->dev, "phy link never came up\n");
+	return -EINVAL;
+}
+
 static void ls_pcie_host_init(struct pcie_port *pp)
 {
 	struct ls_pcie *pcie = to_ls_pcie(pp);
-	int count = 0;
 	u32 val;
 
 	dw_pcie_setup_rc(pp);
-
-	while (!ls_pcie_link_up(pp)) {
-		usleep_range(100, 1000);
-		count++;
-		if (count >= 200) {
-			dev_err(pp->dev, "phy link never came up\n");
-			return;
-		}
-	}
+	ls_pcie_establish_link(pp);
 
 	/*
 	 * LS1021A Workaround for internal TKT228622

drivers/pci/host/pci-xgene-msi.c

+/*
+ * APM X-Gene MSI Driver
+ *
+ * Copyright (c) 2014, Applied Micro Circuits Corporation
+ * Author: Tanmay Inamdar <tinamdar@apm.com>
+ *	   Duc Dang <dhdang@apm.com>
+ *
+ * This program is free software; you can redistribute  it and/or modify it
+ * under  the terms of  the GNU General  Public License as published by the
+ * Free Software Foundation;  either version 2 of the  License, or (at your
+ * option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+#include <linux/cpu.h>
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/msi.h>
+#include <linux/of_irq.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+#include <linux/of_pci.h>
+
+#define MSI_IR0			0x000000
+#define MSI_INT0		0x800000
+#define IDX_PER_GROUP		8
+#define IRQS_PER_IDX		16
+#define NR_HW_IRQS		16
+#define NR_MSI_VEC		(IDX_PER_GROUP * IRQS_PER_IDX * NR_HW_IRQS)
+
+struct xgene_msi_group {
+	struct xgene_msi	*msi;
+	int			gic_irq;
+	u32			msi_grp;
+};
+
+struct xgene_msi {
+	struct device_node	*node;
+	struct msi_controller	mchip;
+	struct irq_domain	*domain;
+	u64			msi_addr;
+	void __iomem		*msi_regs;
+	unsigned long		*bitmap;
+	struct mutex		bitmap_lock;
+	struct xgene_msi_group	*msi_groups;
+	int			num_cpus;
+};
+
+/* Global data */
+static struct xgene_msi xgene_msi_ctrl;
+
+static struct irq_chip xgene_msi_top_irq_chip = {
+	.name		= "X-Gene1 MSI",
+	.irq_enable	= pci_msi_unmask_irq,
+	.irq_disable	= pci_msi_mask_irq,
+	.irq_mask	= pci_msi_mask_irq,
+	.irq_unmask	= pci_msi_unmask_irq,
+};
+
+static struct  msi_domain_info xgene_msi_domain_info = {
+	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+		  MSI_FLAG_PCI_MSIX),
+	.chip	= &xgene_msi_top_irq_chip,
+};
+
+/*
+ * X-Gene v1 has 16 groups of MSI termination registers MSInIRx, where
+ * n is group number (0..F), x is index of registers in each group (0..7)
+ * The register layout is as follows:
+ * MSI0IR0			base_addr
+ * MSI0IR1			base_addr +  0x10000
+ * ...				...
+ * MSI0IR6			base_addr +  0x60000
+ * MSI0IR7			base_addr +  0x70000
+ * MSI1IR0			base_addr +  0x80000
+ * MSI1IR1			base_addr +  0x90000
+ * ...				...
+ * MSI1IR7			base_addr +  0xF0000
+ * MSI2IR0			base_addr + 0x100000
+ * ...				...
+ * MSIFIR0			base_addr + 0x780000
+ * MSIFIR1			base_addr + 0x790000
+ * ...				...
+ * MSIFIR7			base_addr + 0x7F0000
+ * MSIINT0			base_addr + 0x800000
+ * MSIINT1			base_addr + 0x810000
+ * ...				...
+ * MSIINTF			base_addr + 0x8F0000
+ *
+ * Each index register supports 16 MSI vectors (0..15) to generate interrupt.
+ * There are total 16 GIC IRQs assigned for these 16 groups of MSI termination
+ * registers.
+ *
+ * Each MSI termination group has 1 MSIINTn register (n is 0..15) to indicate
+ * the MSI pending status caused by 1 of its 8 index registers.
+ */
+
+/* MSInIRx read helper */
+static u32 xgene_msi_ir_read(struct xgene_msi *msi,
+				    u32 msi_grp, u32 msir_idx)
+{
+	return readl_relaxed(msi->msi_regs + MSI_IR0 +
+			      (msi_grp << 19) + (msir_idx << 16));
+}
+
+/* MSIINTn read helper */
+static u32 xgene_msi_int_read(struct xgene_msi *msi, u32 msi_grp)
+{
+	return readl_relaxed(msi->msi_regs + MSI_INT0 + (msi_grp << 16));
+}
+
+/*
+ * With 2048 MSI vectors supported, the MSI message can be constructed using
+ * following scheme:
+ * - Divide into 8 256-vector groups
+ *		Group 0: 0-255
+ *		Group 1: 256-511
+ *		Group 2: 512-767
+ *		...
+ *		Group 7: 1792-2047
+ * - Each 256-vector group is divided into 16 16-vector groups
+ *	As an example: 16 16-vector groups for 256-vector group 0-255 is
+ *		Group 0: 0-15
+ *		Group 1: 16-32
+ *		...
+ *		Group 15: 240-255
+ * - The termination address of MSI vector in 256-vector group n and 16-vector
+ *   group x is the address of MSIxIRn
+ * - The data for MSI vector in 16-vector group x is x
+ */
+static u32 hwirq_to_reg_set(unsigned long hwirq)
+{
+	return (hwirq / (NR_HW_IRQS * IRQS_PER_IDX));
+}
+
+static u32 hwirq_to_group(unsigned long hwirq)
+{
+	return (hwirq % NR_HW_IRQS);
+}
+
+static u32 hwirq_to_msi_data(unsigned long hwirq)
+{
+	return ((hwirq / NR_HW_IRQS) % IRQS_PER_IDX);
+}
+
+static void xgene_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
+{
+	struct xgene_msi *msi = irq_data_get_irq_chip_data(data);
+	u32 reg_set = hwirq_to_reg_set(data->hwirq);
+	u32 group = hwirq_to_group(data->hwirq);
+	u64 target_addr = msi->msi_addr + (((8 * group) + reg_set) << 16);
+
+	msg->address_hi = upper_32_bits(target_addr);
+	msg->address_lo = lower_32_bits(target_addr);
+	msg->data = hwirq_to_msi_data(data->hwirq);
+}
+
+/*
+ * X-Gene v1 only has 16 MSI GIC IRQs for 2048 MSI vectors.  To maintain
+ * the expected behaviour of .set_affinity for each MSI interrupt, the 16
+ * MSI GIC IRQs are statically allocated to 8 X-Gene v1 cores (2 GIC IRQs
+ * for each core).  The MSI vector is moved fom 1 MSI GIC IRQ to another
+ * MSI GIC IRQ to steer its MSI interrupt to correct X-Gene v1 core.  As a
+ * consequence, the total MSI vectors that X-Gene v1 supports will be
+ * reduced to 256 (2048/8) vectors.
+ */
+static int hwirq_to_cpu(unsigned long hwirq)
+{
+	return (hwirq % xgene_msi_ctrl.num_cpus);
+}
+
+static unsigned long hwirq_to_canonical_hwirq(unsigned long hwirq)
+{
+	return (hwirq - hwirq_to_cpu(hwirq));
+}
+
+static int xgene_msi_set_affinity(struct irq_data *irqdata,
+				  const struct cpumask *mask, bool force)
+{
+	int target_cpu = cpumask_first(mask);
+	int curr_cpu;
+
+	curr_cpu = hwirq_to_cpu(irqdata->hwirq);
+	if (curr_cpu == target_cpu)
+		return IRQ_SET_MASK_OK_DONE;
+
+	/* Update MSI number to target the new CPU */
+	irqdata->hwirq = hwirq_to_canonical_hwirq(irqdata->hwirq) + target_cpu;
+
+	return IRQ_SET_MASK_OK;
+}
+
+static struct irq_chip xgene_msi_bottom_irq_chip = {
+	.name			= "MSI",
+	.irq_set_affinity       = xgene_msi_set_affinity,
+	.irq_compose_msi_msg	= xgene_compose_msi_msg,
+};
+
+static int xgene_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				  unsigned int nr_irqs, void *args)
+{
+	struct xgene_msi *msi = domain->host_data;
+	int msi_irq;
+
+	mutex_lock(&msi->bitmap_lock);
+
+	msi_irq = bitmap_find_next_zero_area(msi->bitmap, NR_MSI_VEC, 0,
+					     msi->num_cpus, 0);
+	if (msi_irq < NR_MSI_VEC)
+		bitmap_set(msi->bitmap, msi_irq, msi->num_cpus);
+	else
+		msi_irq = -ENOSPC;
+
+	mutex_unlock(&msi->bitmap_lock);
+
+	if (msi_irq < 0)
+		return msi_irq;
+
+	irq_domain_set_info(domain, virq, msi_irq,
+			    &xgene_msi_bottom_irq_chip, domain->host_data,
+			    handle_simple_irq, NULL, NULL);
+	set_irq_flags(virq, IRQF_VALID);
+
+	return 0;
+}
+
+static void xgene_irq_domain_free(struct irq_domain *domain,
+				  unsigned int virq, unsigned int nr_irqs)
+{
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+	struct xgene_msi *msi = irq_data_get_irq_chip_data(d);
+	u32 hwirq;
+
+	mutex_lock(&msi->bitmap_lock);
+
+	hwirq = hwirq_to_canonical_hwirq(d->hwirq);
+	bitmap_clear(msi->bitmap, hwirq, msi->num_cpus);
+
+	mutex_unlock(&msi->bitmap_lock);
+
+	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
+}
+
+static const struct irq_domain_ops msi_domain_ops = {
+	.alloc  = xgene_irq_domain_alloc,
+	.free   = xgene_irq_domain_free,
+};
+
+static int xgene_allocate_domains(struct xgene_msi *msi)
+{
+	msi->domain = irq_domain_add_linear(NULL, NR_MSI_VEC,
+					    &msi_domain_ops, msi);
+	if (!msi->domain)
+		return -ENOMEM;
+
+	msi->mchip.domain = pci_msi_create_irq_domain(msi->mchip.of_node,
+						      &xgene_msi_domain_info,
+						      msi->domain);
+
+	if (!msi->mchip.domain) {
+		irq_domain_remove(msi->domain);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void xgene_free_domains(struct xgene_msi *msi)
+{
+	if (msi->mchip.domain)
+		irq_domain_remove(msi->mchip.domain);
+	if (msi->domain)
+		irq_domain_remove(msi->domain);
+}
+
+static int xgene_msi_init_allocator(struct xgene_msi *xgene_msi)
+{
+	int size = BITS_TO_LONGS(NR_MSI_VEC) * sizeof(long);
+
+	xgene_msi->bitmap = kzalloc(size, GFP_KERNEL);
+	if (!xgene_msi->bitmap)
+		return -ENOMEM;
+
+	mutex_init(&xgene_msi->bitmap_lock);
+
+	xgene_msi->msi_groups = kcalloc(NR_HW_IRQS,
+					sizeof(struct xgene_msi_group),
+					GFP_KERNEL);
+	if (!xgene_msi->msi_groups)
+		return -ENOMEM;
+
+	return 0;
+}
+
+static void xgene_msi_isr(unsigned int irq, struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct xgene_msi_group *msi_groups;
+	struct xgene_msi *xgene_msi;
+	unsigned int virq;
+	int msir_index, msir_val, hw_irq;
+	u32 intr_index, grp_select, msi_grp;
+
+	chained_irq_enter(chip, desc);
+
+	msi_groups = irq_desc_get_handler_data(desc);
+	xgene_msi = msi_groups->msi;
+	msi_grp = msi_groups->msi_grp;
+
+	/*
+	 * MSIINTn (n is 0..F) indicates if there is a pending MSI interrupt
+	 * If bit x of this register is set (x is 0..7), one or more interupts
+	 * corresponding to MSInIRx is set.
+	 */
+	grp_select = xgene_msi_int_read(xgene_msi, msi_grp);
+	while (grp_select) {
+		msir_index = ffs(grp_select) - 1;
+		/*
+		 * Calculate MSInIRx address to read to check for interrupts
+		 * (refer to termination address and data assignment
+		 * described in xgene_compose_msi_msg() )
+		 */
+		msir_val = xgene_msi_ir_read(xgene_msi, msi_grp, msir_index);
+		while (msir_val) {
+			intr_index = ffs(msir_val) - 1;
+			/*
+			 * Calculate MSI vector number (refer to the termination
+			 * address and data assignment described in
+			 * xgene_compose_msi_msg function)
+			 */
+			hw_irq = (((msir_index * IRQS_PER_IDX) + intr_index) *
+				 NR_HW_IRQS) + msi_grp;
+			/*
+			 * As we have multiple hw_irq that maps to single MSI,
+			 * always look up the virq using the hw_irq as seen from
+			 * CPU0
+			 */
+			hw_irq = hwirq_to_canonical_hwirq(hw_irq);
+			virq = irq_find_mapping(xgene_msi->domain, hw_irq);
+			WARN_ON(!virq);
+			if (virq != 0)
+				generic_handle_irq(virq);
+			msir_val &= ~(1 << intr_index);
+		}
+		grp_select &= ~(1 << msir_index);
+
+		if (!grp_select) {
+			/*
+			 * We handled all interrupts happened in this group,
+			 * resample this group MSI_INTx register in case
+			 * something else has been made pending in the meantime
+			 */
+			grp_select = xgene_msi_int_read(xgene_msi, msi_grp);
+		}
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
+static int xgene_msi_remove(struct platform_device *pdev)
+{
+	int virq, i;
+	struct xgene_msi *msi = platform_get_drvdata(pdev);
+
+	for (i = 0; i < NR_HW_IRQS; i++) {
+		virq = msi->msi_groups[i].gic_irq;
+		if (virq != 0) {
+			irq_set_chained_handler(virq, NULL);
+			irq_set_handler_data(virq, NULL);
+		}
+	}
+	kfree(msi->msi_groups);
+
+	kfree(msi->bitmap);
+	msi->bitmap = NULL;
+
+	xgene_free_domains(msi);
+
+	return 0;
+}
+
+static int xgene_msi_hwirq_alloc(unsigned int cpu)
+{
+	struct xgene_msi *msi = &xgene_msi_ctrl;
+	struct xgene_msi_group *msi_group;
+	cpumask_var_t mask;
+	int i;
+	int err;
+
+	for (i = cpu; i < NR_HW_IRQS; i += msi->num_cpus) {
+		msi_group = &msi->msi_groups[i];
+		if (!msi_group->gic_irq)
+			continue;
+
+		irq_set_chained_handler(msi_group->gic_irq,
+					xgene_msi_isr);
+		err = irq_set_handler_data(msi_group->gic_irq, msi_group);
+		if (err) {
+			pr_err("failed to register GIC IRQ handler\n");
+			return -EINVAL;
+		}
+		/*
+		 * Statically allocate MSI GIC IRQs to each CPU core.
+		 * With 8-core X-Gene v1, 2 MSI GIC IRQs are allocated
+		 * to each core.
+		 */
+		if (alloc_cpumask_var(&mask, GFP_KERNEL)) {
+			cpumask_clear(mask);
+			cpumask_set_cpu(cpu, mask);
+			err = irq_set_affinity(msi_group->gic_irq, mask);
+			if (err)
+				pr_err("failed to set affinity for GIC IRQ");
+			free_cpumask_var(mask);
+		} else {
+			pr_err("failed to alloc CPU mask for affinity\n");
+			err = -EINVAL;
+		}
+
+		if (err) {
+			irq_set_chained_handler(msi_group->gic_irq, NULL);
+			irq_set_handler_data(msi_group->gic_irq, NULL);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+static void xgene_msi_hwirq_free(unsigned int cpu)
+{
+	struct xgene_msi *msi = &xgene_msi_ctrl;
+	struct xgene_msi_group *msi_group;
+	int i;
+
+	for (i = cpu; i < NR_HW_IRQS; i += msi->num_cpus) {
+		msi_group = &msi->msi_groups[i];
+		if (!msi_group->gic_irq)
+			continue;
+
+		irq_set_chained_handler(msi_group->gic_irq, NULL);
+		irq_set_handler_data(msi_group->gic_irq, NULL);
+	}
+}
+
+static int xgene_msi_cpu_callback(struct notifier_block *nfb,
+				  unsigned long action, void *hcpu)
+{
+	unsigned cpu = (unsigned long)hcpu;
+
+	switch (action) {
+	case CPU_ONLINE:
+	case CPU_ONLINE_FROZEN:
+		xgene_msi_hwirq_alloc(cpu);
+		break;
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		xgene_msi_hwirq_free(cpu);
+		break;
+	default:
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block xgene_msi_cpu_notifier = {
+	.notifier_call = xgene_msi_cpu_callback,
+};
+
+static const struct of_device_id xgene_msi_match_table[] = {
+	{.compatible = "apm,xgene1-msi"},
+	{},
+};
+
+static int xgene_msi_probe(struct platform_device *pdev)
+{
+	struct resource *res;
+	int rc, irq_index;
+	struct xgene_msi *xgene_msi;
+	unsigned int cpu;
+	int virt_msir;
+	u32 msi_val, msi_idx;
+
+	xgene_msi = &xgene_msi_ctrl;
+
+	platform_set_drvdata(pdev, xgene_msi);
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	xgene_msi->msi_regs = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(xgene_msi->msi_regs)) {
+		dev_err(&pdev->dev, "no reg space\n");
+		rc = -EINVAL;
+		goto error;
+	}
+	xgene_msi->msi_addr = res->start;
+
+	xgene_msi->num_cpus = num_possible_cpus();
+
+	rc = xgene_msi_init_allocator(xgene_msi);
+	if (rc) {
+		dev_err(&pdev->dev, "Error allocating MSI bitmap\n");
+		goto error;
+	}
+
+	rc = xgene_allocate_domains(xgene_msi);
+	if (rc) {
+		dev_err(&pdev->dev, "Failed to allocate MSI domain\n");
+		goto error;
+	}
+
+	for (irq_index = 0; irq_index < NR_HW_IRQS; irq_index++) {
+		virt_msir = platform_get_irq(pdev, irq_index);
+		if (virt_msir < 0) {
+			dev_err(&pdev->dev, "Cannot translate IRQ index %d\n",
+				irq_index);
+			rc = -EINVAL;
+			goto error;
+		}
+		xgene_msi->msi_groups[irq_index].gic_irq = virt_msir;
+		xgene_msi->msi_groups[irq_index].msi_grp = irq_index;
+		xgene_msi->msi_groups[irq_index].msi = xgene_msi;
+	}
+
+	/*
+	 * MSInIRx registers are read-to-clear; before registering
+	 * interrupt handlers, read all of them to clear spurious
+	 * interrupts that may occur before the driver is probed.
+	 */
+	for (irq_index = 0; irq_index < NR_HW_IRQS; irq_index++) {
+		for (msi_idx = 0; msi_idx < IDX_PER_GROUP; msi_idx++)
+			msi_val = xgene_msi_ir_read(xgene_msi, irq_index,
+						    msi_idx);
+		/* Read MSIINTn to confirm */
+		msi_val = xgene_msi_int_read(xgene_msi, irq_index);
+		if (msi_val) {
+			dev_err(&pdev->dev, "Failed to clear spurious IRQ\n");
+			rc = -EINVAL;
+			goto error;
+		}
+	}
+
+	cpu_notifier_register_begin();
+
+	for_each_online_cpu(cpu)
+		if (xgene_msi_hwirq_alloc(cpu)) {
+			dev_err(&pdev->dev, "failed to register MSI handlers\n");
+			cpu_notifier_register_done();
+			goto error;
+		}
+
+	rc = __register_hotcpu_notifier(&xgene_msi_cpu_notifier);
+	if (rc) {
+		dev_err(&pdev->dev, "failed to add CPU MSI notifier\n");
+		cpu_notifier_register_done();
+		goto error;
+	}
+
+	cpu_notifier_register_done();
+
+	xgene_msi->mchip.of_node = pdev->dev.of_node;
+	rc = of_pci_msi_chip_add(&xgene_msi->mchip);
+	if (rc) {
+		dev_err(&pdev->dev, "failed to add MSI controller chip\n");
+		goto error_notifier;
+	}
+
+	dev_info(&pdev->dev, "APM X-Gene PCIe MSI driver loaded\n");
+
+	return 0;
+
+error_notifier:
+	unregister_hotcpu_notifier(&xgene_msi_cpu_notifier);
+error:
+	xgene_msi_remove(pdev);
+	return rc;
+}
+
+static struct platform_driver xgene_msi_driver = {
+	.driver = {
+		.name = "xgene-msi",
+		.owner = THIS_MODULE,
+		.of_match_table = xgene_msi_match_table,
+	},
+	.probe = xgene_msi_probe,
+	.remove = xgene_msi_remove,
+};
+
+static int __init xgene_pcie_msi_init(void)
+{
+	return platform_driver_register(&xgene_msi_driver);
+}
+subsys_initcall(xgene_pcie_msi_init);

drivers/pci/host/pci-xgene.c

@@ -468,6 +468,23 @@ static int xgene_pcie_setup(struct xgene_pcie_port *port,
 	return 0;
 }
 
+static int xgene_pcie_msi_enable(struct pci_bus *bus)
+{
+	struct device_node *msi_node;
+
+	msi_node = of_parse_phandle(bus->dev.of_node,
+					"msi-parent", 0);
+	if (!msi_node)
+		return -ENODEV;
+
+	bus->msi = of_pci_find_msi_chip_by_node(msi_node);
+	if (!bus->msi)
+		return -ENODEV;
+
+	bus->msi->dev = &bus->dev;
+	return 0;
+}
+
 static int xgene_pcie_probe_bridge(struct platform_device *pdev)
 {
 	struct device_node *dn = pdev->dev.of_node;
@@ -504,6 +521,10 @@ static int xgene_pcie_probe_bridge(struct platform_device *pdev)
 	if (!bus)
 		return -ENOMEM;
 
+	if (IS_ENABLED(CONFIG_PCI_MSI))
+		if (xgene_pcie_msi_enable(bus))
+			dev_info(port->dev, "failed to enable MSI\n");
+
 	pci_scan_child_bus(bus);
 	pci_assign_unassigned_bus_resources(bus);
 	pci_bus_add_devices(bus);

drivers/pci/host/pcie-designware.c

@@ -31,6 +31,7 @@
 #define PORT_LINK_MODE_1_LANES		(0x1 << 16)
 #define PORT_LINK_MODE_2_LANES		(0x3 << 16)
 #define PORT_LINK_MODE_4_LANES		(0x7 << 16)
+#define PORT_LINK_MODE_8_LANES		(0xf << 16)
 
 #define PCIE_LINK_WIDTH_SPEED_CONTROL	0x80C
 #define PORT_LOGIC_SPEED_CHANGE		(0x1 << 17)
@@ -38,6 +39,7 @@
 #define PORT_LOGIC_LINK_WIDTH_1_LANES	(0x1 << 8)
 #define PORT_LOGIC_LINK_WIDTH_2_LANES	(0x2 << 8)
 #define PORT_LOGIC_LINK_WIDTH_4_LANES	(0x4 << 8)
+#define PORT_LOGIC_LINK_WIDTH_8_LANES	(0x8 << 8)
 
 #define PCIE_MSI_ADDR_LO		0x820
 #define PCIE_MSI_ADDR_HI		0x824
@@ -150,6 +152,21 @@ static int dw_pcie_wr_own_conf(struct pcie_port *pp, int where, int size,
 	return ret;
 }
 
+static void dw_pcie_prog_outbound_atu(struct pcie_port *pp, int index,
+		int type, u64 cpu_addr, u64 pci_addr, u32 size)
+{
+	dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | index,
+			  PCIE_ATU_VIEWPORT);
+	dw_pcie_writel_rc(pp, lower_32_bits(cpu_addr), PCIE_ATU_LOWER_BASE);
+	dw_pcie_writel_rc(pp, upper_32_bits(cpu_addr), PCIE_ATU_UPPER_BASE);
+	dw_pcie_writel_rc(pp, lower_32_bits(cpu_addr + size - 1),
+			  PCIE_ATU_LIMIT);
+	dw_pcie_writel_rc(pp, lower_32_bits(pci_addr), PCIE_ATU_LOWER_TARGET);
+	dw_pcie_writel_rc(pp, upper_32_bits(pci_addr), PCIE_ATU_UPPER_TARGET);
+	dw_pcie_writel_rc(pp, type, PCIE_ATU_CR1);
+	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
+}
+
 static struct irq_chip dw_msi_irq_chip = {
 	.name = "PCI-MSI",
 	.irq_enable = pci_msi_unmask_irq,
@@ -493,6 +510,11 @@ int dw_pcie_host_init(struct pcie_port *pp)
 	if (pp->ops->host_init)
 		pp->ops->host_init(pp);
 
+	if (!pp->ops->rd_other_conf)
+		dw_pcie_prog_outbound_atu(pp, PCIE_ATU_REGION_INDEX1,
+					  PCIE_ATU_TYPE_MEM, pp->mem_mod_base,
+					  pp->mem_bus_addr, pp->mem_size);
+
 	dw_pcie_wr_own_conf(pp, PCI_BASE_ADDRESS_0, 4, 0);
 
 	/* program correct class for RC */
@@ -515,115 +537,73 @@ int dw_pcie_host_init(struct pcie_port *pp)
 	return 0;
 }
 
-static void dw_pcie_prog_viewport_cfg0(struct pcie_port *pp, u32 busdev)
-{
-	/* Program viewport 0 : OUTBOUND : CFG0 */
-	dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX0,
-			  PCIE_ATU_VIEWPORT);
-	dw_pcie_writel_rc(pp, pp->cfg0_mod_base, PCIE_ATU_LOWER_BASE);
-	dw_pcie_writel_rc(pp, (pp->cfg0_mod_base >> 32), PCIE_ATU_UPPER_BASE);
-	dw_pcie_writel_rc(pp, pp->cfg0_mod_base + pp->cfg0_size - 1,
-			  PCIE_ATU_LIMIT);
-	dw_pcie_writel_rc(pp, busdev, PCIE_ATU_LOWER_TARGET);
-	dw_pcie_writel_rc(pp, 0, PCIE_ATU_UPPER_TARGET);
-	dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_CFG0, PCIE_ATU_CR1);
-	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
-}
-
-static void dw_pcie_prog_viewport_cfg1(struct pcie_port *pp, u32 busdev)
-{
-	/* Program viewport 1 : OUTBOUND : CFG1 */
-	dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX1,
-			  PCIE_ATU_VIEWPORT);
-	dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_CFG1, PCIE_ATU_CR1);
-	dw_pcie_writel_rc(pp, pp->cfg1_mod_base, PCIE_ATU_LOWER_BASE);
-	dw_pcie_writel_rc(pp, (pp->cfg1_mod_base >> 32), PCIE_ATU_UPPER_BASE);
-	dw_pcie_writel_rc(pp, pp->cfg1_mod_base + pp->cfg1_size - 1,
-			  PCIE_ATU_LIMIT);
-	dw_pcie_writel_rc(pp, busdev, PCIE_ATU_LOWER_TARGET);
-	dw_pcie_writel_rc(pp, 0, PCIE_ATU_UPPER_TARGET);
-	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
-}
-
-static void dw_pcie_prog_viewport_mem_outbound(struct pcie_port *pp)
-{
-	/* Program viewport 0 : OUTBOUND : MEM */
-	dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX0,
-			  PCIE_ATU_VIEWPORT);
-	dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_MEM, PCIE_ATU_CR1);
-	dw_pcie_writel_rc(pp, pp->mem_mod_base, PCIE_ATU_LOWER_BASE);
-	dw_pcie_writel_rc(pp, (pp->mem_mod_base >> 32), PCIE_ATU_UPPER_BASE);
-	dw_pcie_writel_rc(pp, pp->mem_mod_base + pp->mem_size - 1,
-			  PCIE_ATU_LIMIT);
-	dw_pcie_writel_rc(pp, pp->mem_bus_addr, PCIE_ATU_LOWER_TARGET);
-	dw_pcie_writel_rc(pp, upper_32_bits(pp->mem_bus_addr),
-			  PCIE_ATU_UPPER_TARGET);
-	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
-}
-
-static void dw_pcie_prog_viewport_io_outbound(struct pcie_port *pp)
-{
-	/* Program viewport 1 : OUTBOUND : IO */
-	dw_pcie_writel_rc(pp, PCIE_ATU_REGION_OUTBOUND | PCIE_ATU_REGION_INDEX1,
-			  PCIE_ATU_VIEWPORT);
-	dw_pcie_writel_rc(pp, PCIE_ATU_TYPE_IO, PCIE_ATU_CR1);
-	dw_pcie_writel_rc(pp, pp->io_mod_base, PCIE_ATU_LOWER_BASE);
-	dw_pcie_writel_rc(pp, (pp->io_mod_base >> 32), PCIE_ATU_UPPER_BASE);
-	dw_pcie_writel_rc(pp, pp->io_mod_base + pp->io_size - 1,
-			  PCIE_ATU_LIMIT);
-	dw_pcie_writel_rc(pp, pp->io_bus_addr, PCIE_ATU_LOWER_TARGET);
-	dw_pcie_writel_rc(pp, upper_32_bits(pp->io_bus_addr),
-			  PCIE_ATU_UPPER_TARGET);
-	dw_pcie_writel_rc(pp, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
-}
-
 static int dw_pcie_rd_other_conf(struct pcie_port *pp, struct pci_bus *bus,
 		u32 devfn, int where, int size, u32 *val)
 {
-	int ret = PCIBIOS_SUCCESSFUL;
-	u32 address, busdev;
+	int ret, type;
+	u32 address, busdev, cfg_size;
+	u64 cpu_addr;
+	void __iomem *va_cfg_base;
 
 	busdev = PCIE_ATU_BUS(bus->number) | PCIE_ATU_DEV(PCI_SLOT(devfn)) |
 		 PCIE_ATU_FUNC(PCI_FUNC(devfn));
 	address = where & ~0x3;
 
 	if (bus->parent->number == pp->root_bus_nr) {
-		dw_pcie_prog_viewport_cfg0(pp, busdev);
-		ret = dw_pcie_cfg_read(pp->va_cfg0_base + address, where, size,
-				val);
-		dw_pcie_prog_viewport_mem_outbound(pp);
+		type = PCIE_ATU_TYPE_CFG0;
+		cpu_addr = pp->cfg0_mod_base;
+		cfg_size = pp->cfg0_size;
+		va_cfg_base = pp->va_cfg0_base;
 	} else {
-		dw_pcie_prog_viewport_cfg1(pp, busdev);
-		ret = dw_pcie_cfg_read(pp->va_cfg1_base + address, where, size,
-				val);
-		dw_pcie_prog_viewport_io_outbound(pp);
+		type = PCIE_ATU_TYPE_CFG1;
+		cpu_addr = pp->cfg1_mod_base;
+		cfg_size = pp->cfg1_size;
+		va_cfg_base = pp->va_cfg1_base;
 	}
 
+	dw_pcie_prog_outbound_atu(pp, PCIE_ATU_REGION_INDEX0,
+				  type, cpu_addr,
+				  busdev, cfg_size);
+	ret = dw_pcie_cfg_read(va_cfg_base + address, where, size, val);
+	dw_pcie_prog_outbound_atu(pp, PCIE_ATU_REGION_INDEX0,
+				  PCIE_ATU_TYPE_IO, pp->io_mod_base,
+				  pp->io_bus_addr, pp->io_size);
+
 	return ret;
 }
 
 static int dw_pcie_wr_other_conf(struct pcie_port *pp, struct pci_bus *bus,
 		u32 devfn, int where, int size, u32 val)
 {
-	int ret = PCIBIOS_SUCCESSFUL;
-	u32 address, busdev;
+	int ret, type;
+	u32 address, busdev, cfg_size;
+	u64 cpu_addr;
+	void __iomem *va_cfg_base;
 
 	busdev = PCIE_ATU_BUS(bus->number) | PCIE_ATU_DEV(PCI_SLOT(devfn)) |
 		 PCIE_ATU_FUNC(PCI_FUNC(devfn));
 	address = where & ~0x3;
 
 	if (bus->parent->number == pp->root_bus_nr) {
-		dw_pcie_prog_viewport_cfg0(pp, busdev);
-		ret = dw_pcie_cfg_write(pp->va_cfg0_base + address, where, size,
-				val);
-		dw_pcie_prog_viewport_mem_outbound(pp);
+		type = PCIE_ATU_TYPE_CFG0;
+		cpu_addr = pp->cfg0_mod_base;
+		cfg_size = pp->cfg0_size;
+		va_cfg_base = pp->va_cfg0_base;
 	} else {
-		dw_pcie_prog_viewport_cfg1(pp, busdev);
-		ret = dw_pcie_cfg_write(pp->va_cfg1_base + address, where, size,
-				val);
-		dw_pcie_prog_viewport_io_outbound(pp);
+		type = PCIE_ATU_TYPE_CFG1;
+		cpu_addr = pp->cfg1_mod_base;
+		cfg_size = pp->cfg1_size;
+		va_cfg_base = pp->va_cfg1_base;
 	}
 
+	dw_pcie_prog_outbound_atu(pp, PCIE_ATU_REGION_INDEX0,
+				  type, cpu_addr,
+				  busdev, cfg_size);
+	ret = dw_pcie_cfg_write(va_cfg_base + address, where, size, val);
+	dw_pcie_prog_outbound_atu(pp, PCIE_ATU_REGION_INDEX0,
+				  PCIE_ATU_TYPE_IO, pp->io_mod_base,
+				  pp->io_bus_addr, pp->io_size);
+
 	return ret;
 }
 
@@ -776,6 +756,9 @@ void dw_pcie_setup_rc(struct pcie_port *pp)
 	case 4:
 		val |= PORT_LINK_MODE_4_LANES;
 		break;
+	case 8:
+		val |= PORT_LINK_MODE_8_LANES;
+		break;
 	}
 	dw_pcie_writel_rc(pp, val, PCIE_PORT_LINK_CONTROL);
 
@@ -792,6 +775,9 @@ void dw_pcie_setup_rc(struct pcie_port *pp)
 	case 4:
 		val |= PORT_LOGIC_LINK_WIDTH_4_LANES;
 		break;
+	case 8:
+		val |= PORT_LOGIC_LINK_WIDTH_8_LANES;
+		break;
 	}
 	dw_pcie_writel_rc(pp, val, PCIE_LINK_WIDTH_SPEED_CONTROL);
 

drivers/pci/host/pcie-iproc-bcma.c

+/*
+ * Copyright (C) 2015 Broadcom Corporation
+ * Copyright (C) 2015 Hauke Mehrtens <hauke@hauke-m.de>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation version 2.
+ *
+ * This program is distributed "as is" WITHOUT ANY WARRANTY of any
+ * kind, whether express or implied; without even the implied warranty
+ * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/kernel.h>
+#include <linux/pci.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/phy/phy.h>
+#include <linux/bcma/bcma.h>
+#include <linux/ioport.h>
+
+#include "pcie-iproc.h"
+
+
+/* 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;
+}
+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);
+
+static int iproc_pcie_bcma_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+{
+	struct pci_sys_data *sys = dev->sysdata;
+	struct iproc_pcie *pcie = sys->private_data;
+	struct bcma_device *bdev = container_of(pcie->dev, struct bcma_device, dev);
+
+	return bcma_core_irq(bdev, 5);
+}
+
+static int iproc_pcie_bcma_probe(struct bcma_device *bdev)
+{
+	struct iproc_pcie *pcie;
+	LIST_HEAD(res);
+	struct resource res_mem;
+	int ret;
+
+	pcie = devm_kzalloc(&bdev->dev, sizeof(*pcie), GFP_KERNEL);
+	if (!pcie)
+		return -ENOMEM;
+
+	pcie->dev = &bdev->dev;
+	bcma_set_drvdata(bdev, pcie);
+
+	pcie->base = bdev->io_addr;
+
+	res_mem.start = bdev->addr_s[0];
+	res_mem.end = bdev->addr_s[0] + SZ_128M - 1;
+	res_mem.name = "PCIe MEM space";
+	res_mem.flags = IORESOURCE_MEM;
+	pci_add_resource(&res, &res_mem);
+
+	pcie->map_irq = iproc_pcie_bcma_map_irq;
+
+	ret = iproc_pcie_setup(pcie, &res);
+	if (ret)
+		dev_err(pcie->dev, "PCIe controller setup failed\n");
+
+	pci_free_resource_list(&res);
+
+	return ret;
+}
+
+static void iproc_pcie_bcma_remove(struct bcma_device *bdev)
+{
+	struct iproc_pcie *pcie = bcma_get_drvdata(bdev);
+
+	iproc_pcie_remove(pcie);
+}
+
+static const struct bcma_device_id iproc_pcie_bcma_table[] = {
+	BCMA_CORE(BCMA_MANUF_BCM, BCMA_CORE_NS_PCIEG2, BCMA_ANY_REV, BCMA_ANY_CLASS),
+	{},
+};
+MODULE_DEVICE_TABLE(bcma, iproc_pcie_bcma_table);
+
+static struct bcma_driver iproc_pcie_bcma_driver = {
+	.name		= KBUILD_MODNAME,
+	.id_table	= iproc_pcie_bcma_table,
+	.probe		= iproc_pcie_bcma_probe,
+	.remove		= iproc_pcie_bcma_remove,
+};
+
+static int __init iproc_pcie_bcma_init(void)
+{
+	return bcma_driver_register(&iproc_pcie_bcma_driver);
+}
+module_init(iproc_pcie_bcma_init);
+
+static void __exit iproc_pcie_bcma_exit(void)
+{
+	bcma_driver_unregister(&iproc_pcie_bcma_driver);
+}
+module_exit(iproc_pcie_bcma_exit);
+
+MODULE_AUTHOR("Hauke Mehrtens");
+MODULE_DESCRIPTION("Broadcom iProc PCIe BCMA driver");
+MODULE_LICENSE("GPL v2");

drivers/pci/host/pcie-iproc-platform.c

@@ -69,15 +69,15 @@ static int iproc_pcie_pltfm_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	pcie->resources = &res;
+	pcie->map_irq = of_irq_parse_and_map_pci;
 
-	ret = iproc_pcie_setup(pcie);
-	if (ret) {
+	ret = iproc_pcie_setup(pcie, &res);
+	if (ret)
 		dev_err(pcie->dev, "PCIe controller setup failed\n");
-		return ret;
-	}
 
-	return 0;
+	pci_free_resource_list(&res);
+
+	return ret;
 }
 
 static int iproc_pcie_pltfm_remove(struct platform_device *pdev)

drivers/pci/host/pcie-iproc.c

@@ -183,7 +183,7 @@ static void iproc_pcie_enable(struct iproc_pcie *pcie)
 	writel(SYS_RC_INTX_MASK, pcie->base + SYS_RC_INTX_EN);
 }
 
-int iproc_pcie_setup(struct iproc_pcie *pcie)
+int iproc_pcie_setup(struct iproc_pcie *pcie, struct list_head *res)
 {
 	int ret;
 	struct pci_bus *bus;
@@ -211,7 +211,7 @@ int iproc_pcie_setup(struct iproc_pcie *pcie)
 	pcie->sysdata.private_data = pcie;
 
 	bus = pci_create_root_bus(pcie->dev, 0, &iproc_pcie_ops,
-				  &pcie->sysdata, pcie->resources);
+				  &pcie->sysdata, res);
 	if (!bus) {
 		dev_err(pcie->dev, "unable to create PCI root bus\n");
 		ret = -ENOMEM;
@@ -229,7 +229,7 @@ int iproc_pcie_setup(struct iproc_pcie *pcie)
 
 	pci_scan_child_bus(bus);
 	pci_assign_unassigned_bus_resources(bus);
-	pci_fixup_irqs(pci_common_swizzle, of_irq_parse_and_map_pci);
+	pci_fixup_irqs(pci_common_swizzle, pcie->map_irq);
 	pci_bus_add_devices(bus);
 
 	return 0;

drivers/pci/host/pcie-iproc.h

@@ -29,14 +29,14 @@
 struct iproc_pcie {
 	struct device *dev;
 	void __iomem *base;
-	struct list_head *resources;
 	struct pci_sys_data sysdata;
 	struct pci_bus *root_bus;
 	struct phy *phy;
 	int irqs[IPROC_PCIE_MAX_NUM_IRQS];
+	int (*map_irq)(const struct pci_dev *, u8, u8);
 };
 
-int iproc_pcie_setup(struct iproc_pcie *pcie);
+int iproc_pcie_setup(struct iproc_pcie *pcie, struct list_head *res);
 int iproc_pcie_remove(struct iproc_pcie *pcie);
 
 #endif /* _PCIE_IPROC_H */

drivers/pci/host/pcie-spear13xx.c

@@ -146,10 +146,10 @@ struct pcie_app_reg {
 static int spear13xx_pcie_establish_link(struct pcie_port *pp)
 {
 	u32 val;
-	int count = 0;
 	struct spear13xx_pcie *spear13xx_pcie = to_spear13xx_pcie(pp);
 	struct pcie_app_reg *app_reg = spear13xx_pcie->app_base;
 	u32 exp_cap_off = EXP_CAP_ID_OFFSET;
+	unsigned int retries;
 
 	if (dw_pcie_link_up(pp)) {
 		dev_err(pp->dev, "link already up\n");
@@ -201,17 +201,16 @@ static int spear13xx_pcie_establish_link(struct pcie_port *pp)
 			&app_reg->app_ctrl_0);
 
 	/* check if the link is up or not */
-	while (!dw_pcie_link_up(pp)) {
-		mdelay(100);
-		count++;
-		if (count == 10) {
-			dev_err(pp->dev, "link Fail\n");
-			return -EINVAL;
+	for (retries = 0; retries < 10; retries++) {
+		if (dw_pcie_link_up(pp)) {
+			dev_info(pp->dev, "link up\n");
+			return 0;
 		}
+		mdelay(100);
 	}
-	dev_info(pp->dev, "link up\n");
 
-	return 0;
+	dev_err(pp->dev, "link Fail\n");
+	return -EINVAL;
 }
 
 static irqreturn_t spear13xx_pcie_irq_handler(int irq, void *arg)