Merge tag 'pci-v5.2-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci

Pull PCI updates from Bjorn Helgaas:
 "Enumeration changes:

   - Add _HPX Type 3 settings support, which gives firmware more
     influence over device configuration (Alexandru Gagniuc)

   - Support fixed bus numbers from bridge Enhanced Allocation
     capabilities (Subbaraya Sundeep)

   - Add "external-facing" DT property to identify cases where we
     require IOMMU protection against untrusted devices (Jean-Philippe
     Brucker)

   - Enable PCIe services for host controller drivers that use managed
     host bridge alloc (Jean-Philippe Brucker)

   - Log PCIe port service messages with pci_dev, not the pcie_device
     (Frederick Lawler)

   - Convert pciehp from pciehp_debug module parameter to generic
     dynamic debug (Frederick Lawler)

  Peer-to-peer DMA:

   - Add whitelist of Root Complexes that support peer-to-peer DMA
     between Root Ports (Christian König)

  Native controller drivers:

   - Add PCI host bridge DMA ranges for bridges that can't DMA
     everywhere, e.g., iProc (Srinath Mannam)

   - Add Amazon Annapurna Labs PCIe host controller driver (Jonathan
     Chocron)

   - Fix Tegra MSI target allocation so DMA doesn't generate unwanted
     MSIs (Vidya Sagar)

   - Fix of_node reference leaks (Wen Yang)

   - Fix Hyper-V module unload & device removal issues (Dexuan Cui)

   - Cleanup R-Car driver (Marek Vasut)

   - Cleanup Keystone driver (Kishon Vijay Abraham I)

   - Cleanup i.MX6 driver (Andrey Smirnov)

  Significant bug fixes:

   - Reset Lenovo ThinkPad P50 GPU so nouveau works after reboot (Lyude
     Paul)

   - Fix Switchtec firmware update performance issue (Wesley Sheng)

   - Work around Pericom switch link retraining erratum (Stefan Mätje)"

* tag 'pci-v5.2-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci: (141 commits)
  MAINTAINERS: Add Karthikeyan Mitran and Hou Zhiqiang for Mobiveil PCI
  PCI: pciehp: Remove pointless MY_NAME definition
  PCI: pciehp: Remove pointless PCIE_MODULE_NAME definition
  PCI: pciehp: Remove unused dbg/err/info/warn() wrappers
  PCI: pciehp: Log messages with pci_dev, not pcie_device
  PCI: pciehp: Replace pciehp_debug module param with dyndbg
  PCI: pciehp: Remove pciehp_debug uses
  PCI/AER: Log messages with pci_dev, not pcie_device
  PCI/DPC: Log messages with pci_dev, not pcie_device
  PCI/PME: Replace dev_printk(KERN_DEBUG) with dev_info()
  PCI/AER: Replace dev_printk(KERN_DEBUG) with dev_info()
  PCI: Replace dev_printk(KERN_DEBUG) with dev_info(), etc
  PCI: Replace printk(KERN_INFO) with pr_info(), etc
  PCI: Use dev_printk() when possible
  PCI: Cleanup setup-bus.c comments and whitespace
  PCI: imx6: Allow asynchronous probing
  PCI: dwc: Save root bus for driver remove hooks
  PCI: dwc: Use devm_pci_alloc_host_bridge() to simplify code
  PCI: dwc: Free MSI in dw_pcie_host_init() error path
  PCI: dwc: Free MSI IRQ page in dw_pcie_free_msi()
  ...

28 files changed, 1280 insertions, 594 deletions

diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig
index 6ea74b1c0d94..a6ce1ee51b4c 100644
--- a/drivers/pci/controller/dwc/Kconfig
+++ b/drivers/pci/controller/dwc/Kconfig
@@ -103,15 +103,32 @@ config PCIE_SPEAR13XX
 	  Say Y here if you want PCIe support on SPEAr13XX SoCs.
 
 config PCI_KEYSTONE
-	bool "TI Keystone PCIe controller"
-	depends on ARCH_KEYSTONE || (ARM && COMPILE_TEST)
+	bool
+
+config PCI_KEYSTONE_HOST
+	bool "PCI Keystone Host Mode"
+	depends on ARCH_KEYSTONE || ARCH_K3 || ((ARM || ARM64) && COMPILE_TEST)
 	depends on PCI_MSI_IRQ_DOMAIN
 	select PCIE_DW_HOST
+	select PCI_KEYSTONE
+	default y
 	help
-	  Say Y here if you want to enable PCI controller support on Keystone
-	  SoCs. The PCI controller on Keystone is based on DesignWare hardware
-	  and therefore the driver re-uses the DesignWare core functions to
-	  implement the driver.
+	  Enables support for the PCIe controller in the Keystone SoC to
+	  work in host mode. The PCI controller on Keystone is based on
+	  DesignWare hardware and therefore the driver re-uses the
+	  DesignWare core functions to implement the driver.
+
+config PCI_KEYSTONE_EP
+	bool "PCI Keystone Endpoint Mode"
+	depends on ARCH_KEYSTONE || ARCH_K3 || ((ARM || ARM64) && COMPILE_TEST)
+	depends on PCI_ENDPOINT
+	select PCIE_DW_EP
+	select PCI_KEYSTONE
+	help
+	  Enables support for the PCIe controller in the Keystone SoC to
+	  work in endpoint mode. The PCI controller on Keystone is based
+	  on DesignWare hardware and therefore the driver re-uses the
+	  DesignWare core functions to implement the driver.
 
 config PCI_LAYERSCAPE
 	bool "Freescale Layerscape PCIe controller"
diff --git a/drivers/pci/controller/dwc/Makefile b/drivers/pci/controller/dwc/Makefile
index b5f3b83cc2b3..b085dfd4fab7 100644
--- a/drivers/pci/controller/dwc/Makefile
+++ b/drivers/pci/controller/dwc/Makefile
@@ -28,5 +28,6 @@ obj-$(CONFIG_PCIE_UNIPHIER) += pcie-uniphier.o
 # depending on whether ACPI, the DT driver, or both are enabled.
 
 ifdef CONFIG_PCI
+obj-$(CONFIG_ARM64) += pcie-al.o
 obj-$(CONFIG_ARM64) += pcie-hisi.o
 endif
diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c
index ae84a69ae63a..419451efd58c 100644
--- a/drivers/pci/controller/dwc/pci-dra7xx.c
+++ b/drivers/pci/controller/dwc/pci-dra7xx.c
@@ -247,6 +247,7 @@ static int dra7xx_pcie_init_irq_domain(struct pcie_port *pp)
 
 	dra7xx->irq_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX,
 						   &intx_domain_ops, pp);
+	of_node_put(pcie_intc_node);
 	if (!dra7xx->irq_domain) {
 		dev_err(dev, "Failed to get a INTx IRQ domain\n");
 		return -ENODEV;
@@ -406,7 +407,7 @@ dra7xx_pcie_get_features(struct dw_pcie_ep *ep)
 	return &dra7xx_pcie_epc_features;
 }
 
-static struct dw_pcie_ep_ops pcie_ep_ops = {
+static const struct dw_pcie_ep_ops pcie_ep_ops = {
 	.ep_init = dra7xx_pcie_ep_init,
 	.raise_irq = dra7xx_pcie_raise_irq,
 	.get_features = dra7xx_pcie_get_features,
diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index 3d627f94a166..9b5cb5b70389 100644
--- a/drivers/pci/controller/dwc/pci-imx6.c
+++ b/drivers/pci/controller/dwc/pci-imx6.c
@@ -52,6 +52,7 @@ enum imx6_pcie_variants {
 
 #define IMX6_PCIE_FLAG_IMX6_PHY			BIT(0)
 #define IMX6_PCIE_FLAG_IMX6_SPEED_CHANGE	BIT(1)
+#define IMX6_PCIE_FLAG_SUPPORTS_SUSPEND		BIT(2)
 
 struct imx6_pcie_drvdata {
 	enum imx6_pcie_variants variant;
@@ -89,9 +90,8 @@ struct imx6_pcie {
 };
 
 /* Parameters for the waiting for PCIe PHY PLL to lock on i.MX7 */
-#define PHY_PLL_LOCK_WAIT_MAX_RETRIES	2000
-#define PHY_PLL_LOCK_WAIT_USLEEP_MIN	50
 #define PHY_PLL_LOCK_WAIT_USLEEP_MAX	200
+#define PHY_PLL_LOCK_WAIT_TIMEOUT	(2000 * PHY_PLL_LOCK_WAIT_USLEEP_MAX)
 
 /* PCIe Root Complex registers (memory-mapped) */
 #define PCIE_RC_IMX6_MSI_CAP			0x50
@@ -104,34 +104,29 @@ struct imx6_pcie {
 
 /* PCIe Port Logic registers (memory-mapped) */
 #define PL_OFFSET 0x700
-#define PCIE_PL_PFLR (PL_OFFSET + 0x08)
-#define PCIE_PL_PFLR_LINK_STATE_MASK		(0x3f << 16)
-#define PCIE_PL_PFLR_FORCE_LINK			(1 << 15)
-#define PCIE_PHY_DEBUG_R0 (PL_OFFSET + 0x28)
-#define PCIE_PHY_DEBUG_R1 (PL_OFFSET + 0x2c)
 
 #define PCIE_PHY_CTRL (PL_OFFSET + 0x114)
-#define PCIE_PHY_CTRL_DATA_LOC 0
-#define PCIE_PHY_CTRL_CAP_ADR_LOC 16
-#define PCIE_PHY_CTRL_CAP_DAT_LOC 17
-#define PCIE_PHY_CTRL_WR_LOC 18
-#define PCIE_PHY_CTRL_RD_LOC 19
+#define PCIE_PHY_CTRL_DATA(x)		FIELD_PREP(GENMASK(15, 0), (x))
+#define PCIE_PHY_CTRL_CAP_ADR		BIT(16)
+#define PCIE_PHY_CTRL_CAP_DAT		BIT(17)
+#define PCIE_PHY_CTRL_WR		BIT(18)
+#define PCIE_PHY_CTRL_RD		BIT(19)
 
 #define PCIE_PHY_STAT (PL_OFFSET + 0x110)
-#define PCIE_PHY_STAT_ACK_LOC 16
+#define PCIE_PHY_STAT_ACK		BIT(16)
 
 #define PCIE_LINK_WIDTH_SPEED_CONTROL	0x80C
 
 /* PHY registers (not memory-mapped) */
 #define PCIE_PHY_ATEOVRD			0x10
-#define  PCIE_PHY_ATEOVRD_EN			(0x1 << 2)
+#define  PCIE_PHY_ATEOVRD_EN			BIT(2)
 #define  PCIE_PHY_ATEOVRD_REF_CLKDIV_SHIFT	0
 #define  PCIE_PHY_ATEOVRD_REF_CLKDIV_MASK	0x1
 
 #define PCIE_PHY_MPLL_OVRD_IN_LO		0x11
 #define  PCIE_PHY_MPLL_MULTIPLIER_SHIFT		2
 #define  PCIE_PHY_MPLL_MULTIPLIER_MASK		0x7f
-#define  PCIE_PHY_MPLL_MULTIPLIER_OVRD		(0x1 << 9)
+#define  PCIE_PHY_MPLL_MULTIPLIER_OVRD		BIT(9)
 
 #define PCIE_PHY_RX_ASIC_OUT 0x100D
 #define PCIE_PHY_RX_ASIC_OUT_VALID	(1 << 0)
@@ -154,19 +149,19 @@ struct imx6_pcie {
 #define PCIE_PHY_CMN_REG26_ATT_MODE	0xBC
 
 #define PHY_RX_OVRD_IN_LO 0x1005
-#define PHY_RX_OVRD_IN_LO_RX_DATA_EN (1 << 5)
-#define PHY_RX_OVRD_IN_LO_RX_PLL_EN (1 << 3)
+#define PHY_RX_OVRD_IN_LO_RX_DATA_EN		BIT(5)
+#define PHY_RX_OVRD_IN_LO_RX_PLL_EN		BIT(3)
 
-static int pcie_phy_poll_ack(struct imx6_pcie *imx6_pcie, int exp_val)
+static int pcie_phy_poll_ack(struct imx6_pcie *imx6_pcie, bool exp_val)
 {
 	struct dw_pcie *pci = imx6_pcie->pci;
-	u32 val;
+	bool val;
 	u32 max_iterations = 10;
 	u32 wait_counter = 0;
 
 	do {
-		val = dw_pcie_readl_dbi(pci, PCIE_PHY_STAT);
-		val = (val >> PCIE_PHY_STAT_ACK_LOC) & 0x1;
+		val = dw_pcie_readl_dbi(pci, PCIE_PHY_STAT) &
+			PCIE_PHY_STAT_ACK;
 		wait_counter++;
 
 		if (val == exp_val)
@@ -184,27 +179,27 @@ static int pcie_phy_wait_ack(struct imx6_pcie *imx6_pcie, int addr)
 	u32 val;
 	int ret;
 
-	val = addr << PCIE_PHY_CTRL_DATA_LOC;
+	val = PCIE_PHY_CTRL_DATA(addr);
 	dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, val);
 
-	val |= (0x1 << PCIE_PHY_CTRL_CAP_ADR_LOC);
+	val |= PCIE_PHY_CTRL_CAP_ADR;
 	dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, val);
 
-	ret = pcie_phy_poll_ack(imx6_pcie, 1);
+	ret = pcie_phy_poll_ack(imx6_pcie, true);
 	if (ret)
 		return ret;
 
-	val = addr << PCIE_PHY_CTRL_DATA_LOC;
+	val = PCIE_PHY_CTRL_DATA(addr);
 	dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, val);
 
-	return pcie_phy_poll_ack(imx6_pcie, 0);
+	return pcie_phy_poll_ack(imx6_pcie, false);
 }
 
 /* Read from the 16-bit PCIe PHY control registers (not memory-mapped) */
-static int pcie_phy_read(struct imx6_pcie *imx6_pcie, int addr, int *data)
+static int pcie_phy_read(struct imx6_pcie *imx6_pcie, int addr, u16 *data)
 {
 	struct dw_pcie *pci = imx6_pcie->pci;
-	u32 val, phy_ctl;
+	u32 phy_ctl;
 	int ret;
 
 	ret = pcie_phy_wait_ack(imx6_pcie, addr);
@@ -212,23 +207,22 @@ static int pcie_phy_read(struct imx6_pcie *imx6_pcie, int addr, int *data)
 		return ret;
 
 	/* assert Read signal */
-	phy_ctl = 0x1 << PCIE_PHY_CTRL_RD_LOC;
+	phy_ctl = PCIE_PHY_CTRL_RD;
 	dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, phy_ctl);
 
-	ret = pcie_phy_poll_ack(imx6_pcie, 1);
+	ret = pcie_phy_poll_ack(imx6_pcie, true);
 	if (ret)
 		return ret;
 
-	val = dw_pcie_readl_dbi(pci, PCIE_PHY_STAT);
-	*data = val & 0xffff;
+	*data = dw_pcie_readl_dbi(pci, PCIE_PHY_STAT);
 
 	/* deassert Read signal */
 	dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, 0x00);
 
-	return pcie_phy_poll_ack(imx6_pcie, 0);
+	return pcie_phy_poll_ack(imx6_pcie, false);
 }
 
-static int pcie_phy_write(struct imx6_pcie *imx6_pcie, int addr, int data)
+static int pcie_phy_write(struct imx6_pcie *imx6_pcie, int addr, u16 data)
 {
 	struct dw_pcie *pci = imx6_pcie->pci;
 	u32 var;
@@ -240,41 +234,41 @@ static int pcie_phy_write(struct imx6_pcie *imx6_pcie, int addr, int data)
 	if (ret)
 		return ret;
 
-	var = data << PCIE_PHY_CTRL_DATA_LOC;
+	var = PCIE_PHY_CTRL_DATA(data);
 	dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, var);
 
 	/* capture data */
-	var |= (0x1 << PCIE_PHY_CTRL_CAP_DAT_LOC);
+	var |= PCIE_PHY_CTRL_CAP_DAT;
 	dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, var);
 
-	ret = pcie_phy_poll_ack(imx6_pcie, 1);
+	ret = pcie_phy_poll_ack(imx6_pcie, true);
 	if (ret)
 		return ret;
 
 	/* deassert cap data */
-	var = data << PCIE_PHY_CTRL_DATA_LOC;
+	var = PCIE_PHY_CTRL_DATA(data);
 	dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, var);
 
 	/* wait for ack de-assertion */
-	ret = pcie_phy_poll_ack(imx6_pcie, 0);
+	ret = pcie_phy_poll_ack(imx6_pcie, false);
 	if (ret)
 		return ret;
 
 	/* assert wr signal */
-	var = 0x1 << PCIE_PHY_CTRL_WR_LOC;
+	var = PCIE_PHY_CTRL_WR;
 	dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, var);
 
 	/* wait for ack */
-	ret = pcie_phy_poll_ack(imx6_pcie, 1);
+	ret = pcie_phy_poll_ack(imx6_pcie, true);
 	if (ret)
 		return ret;
 
 	/* deassert wr signal */
-	var = data << PCIE_PHY_CTRL_DATA_LOC;
+	var = PCIE_PHY_CTRL_DATA(data);
 	dw_pcie_writel_dbi(pci, PCIE_PHY_CTRL, var);
 
 	/* wait for ack de-assertion */
-	ret = pcie_phy_poll_ack(imx6_pcie, 0);
+	ret = pcie_phy_poll_ack(imx6_pcie, false);
 	if (ret)
 		return ret;
 
@@ -285,7 +279,7 @@ static int pcie_phy_write(struct imx6_pcie *imx6_pcie, int addr, int data)
 
 static void imx6_pcie_reset_phy(struct imx6_pcie *imx6_pcie)
 {
-	u32 tmp;
+	u16 tmp;
 
 	if (!(imx6_pcie->drvdata->flags & IMX6_PCIE_FLAG_IMX6_PHY))
 		return;
@@ -455,7 +449,7 @@ static int imx6_pcie_enable_ref_clk(struct imx6_pcie *imx6_pcie)
 		 * reset time is too short, cannot meet the requirement.
 		 * add one ~10us delay here.
 		 */
-		udelay(10);
+		usleep_range(10, 100);
 		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
 				   IMX6Q_GPR1_PCIE_REF_CLK_EN, 1 << 16);
 		break;
@@ -488,20 +482,14 @@ static int imx6_pcie_enable_ref_clk(struct imx6_pcie *imx6_pcie)
 static void imx7d_pcie_wait_for_phy_pll_lock(struct imx6_pcie *imx6_pcie)
 {
 	u32 val;
-	unsigned int retries;
 	struct device *dev = imx6_pcie->pci->dev;
 
-	for (retries = 0; retries < PHY_PLL_LOCK_WAIT_MAX_RETRIES; retries++) {
-		regmap_read(imx6_pcie->iomuxc_gpr, IOMUXC_GPR22, &val);
-
-		if (val & IMX7D_GPR22_PCIE_PHY_PLL_LOCKED)
-			return;
-
-		usleep_range(PHY_PLL_LOCK_WAIT_USLEEP_MIN,
-			     PHY_PLL_LOCK_WAIT_USLEEP_MAX);
-	}
-
-	dev_err(dev, "PCIe PLL lock timeout\n");
+	if (regmap_read_poll_timeout(imx6_pcie->iomuxc_gpr,
+				     IOMUXC_GPR22, val,
+				     val & IMX7D_GPR22_PCIE_PHY_PLL_LOCKED,
+				     PHY_PLL_LOCK_WAIT_USLEEP_MAX,
+				     PHY_PLL_LOCK_WAIT_TIMEOUT))
+		dev_err(dev, "PCIe PLL lock timeout\n");
 }
 
 static void imx6_pcie_deassert_core_reset(struct imx6_pcie *imx6_pcie)
@@ -687,7 +675,7 @@ static int imx6_setup_phy_mpll(struct imx6_pcie *imx6_pcie)
 {
 	unsigned long phy_rate = clk_get_rate(imx6_pcie->pcie_phy);
 	int mult, div;
-	u32 val;
+	u16 val;
 
 	if (!(imx6_pcie->drvdata->flags & IMX6_PCIE_FLAG_IMX6_PHY))
 		return 0;
@@ -730,21 +718,6 @@ static int imx6_setup_phy_mpll(struct imx6_pcie *imx6_pcie)
 	return 0;
 }
 
-static int imx6_pcie_wait_for_link(struct imx6_pcie *imx6_pcie)
-{
-	struct dw_pcie *pci = imx6_pcie->pci;
-	struct device *dev = pci->dev;
-
-	/* check if the link is up or not */
-	if (!dw_pcie_wait_for_link(pci))
-		return 0;
-
-	dev_dbg(dev, "DEBUG_R0: 0x%08x, DEBUG_R1: 0x%08x\n",
-		dw_pcie_readl_dbi(pci, PCIE_PHY_DEBUG_R0),
-		dw_pcie_readl_dbi(pci, PCIE_PHY_DEBUG_R1));
-	return -ETIMEDOUT;
-}
-
 static int imx6_pcie_wait_for_speed_change(struct imx6_pcie *imx6_pcie)
 {
 	struct dw_pcie *pci = imx6_pcie->pci;
@@ -761,7 +734,7 @@ static int imx6_pcie_wait_for_speed_change(struct imx6_pcie *imx6_pcie)
 	}
 
 	dev_err(dev, "Speed change timeout\n");
-	return -EINVAL;
+	return -ETIMEDOUT;
 }
 
 static void imx6_pcie_ltssm_enable(struct device *dev)
@@ -803,7 +776,7 @@ static int imx6_pcie_establish_link(struct imx6_pcie *imx6_pcie)
 	/* Start LTSSM. */
 	imx6_pcie_ltssm_enable(dev);
 
-	ret = imx6_pcie_wait_for_link(imx6_pcie);
+	ret = dw_pcie_wait_for_link(pci);
 	if (ret)
 		goto err_reset_phy;
 
@@ -841,7 +814,7 @@ static int imx6_pcie_establish_link(struct imx6_pcie *imx6_pcie)
 		}
 
 		/* Make sure link training is finished as well! */
-		ret = imx6_pcie_wait_for_link(imx6_pcie);
+		ret = dw_pcie_wait_for_link(pci);
 		if (ret) {
 			dev_err(dev, "Failed to bring link up!\n");
 			goto err_reset_phy;
@@ -856,8 +829,8 @@ static int imx6_pcie_establish_link(struct imx6_pcie *imx6_pcie)
 
 err_reset_phy:
 	dev_dbg(dev, "PHY DEBUG_R0=0x%08x DEBUG_R1=0x%08x\n",
-		dw_pcie_readl_dbi(pci, PCIE_PHY_DEBUG_R0),
-		dw_pcie_readl_dbi(pci, PCIE_PHY_DEBUG_R1));
+		dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG0),
+		dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG1));
 	imx6_pcie_reset_phy(imx6_pcie);
 	return ret;
 }
@@ -993,17 +966,11 @@ static void imx6_pcie_clk_disable(struct imx6_pcie *imx6_pcie)
 	}
 }
 
-static inline bool imx6_pcie_supports_suspend(struct imx6_pcie *imx6_pcie)
-{
-	return (imx6_pcie->drvdata->variant == IMX7D ||
-		imx6_pcie->drvdata->variant == IMX6SX);
-}
-
 static int imx6_pcie_suspend_noirq(struct device *dev)
 {
 	struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev);
 
-	if (!imx6_pcie_supports_suspend(imx6_pcie))
+	if (!(imx6_pcie->drvdata->flags & IMX6_PCIE_FLAG_SUPPORTS_SUSPEND))
 		return 0;
 
 	imx6_pcie_pm_turnoff(imx6_pcie);
@@ -1019,7 +986,7 @@ static int imx6_pcie_resume_noirq(struct device *dev)
 	struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev);
 	struct pcie_port *pp = &imx6_pcie->pci->pp;
 
-	if (!imx6_pcie_supports_suspend(imx6_pcie))
+	if (!(imx6_pcie->drvdata->flags & IMX6_PCIE_FLAG_SUPPORTS_SUSPEND))
 		return 0;
 
 	imx6_pcie_assert_core_reset(imx6_pcie);
@@ -1249,7 +1216,8 @@ static const struct imx6_pcie_drvdata drvdata[] = {
 	[IMX6SX] = {
 		.variant = IMX6SX,
 		.flags = IMX6_PCIE_FLAG_IMX6_PHY |
-			 IMX6_PCIE_FLAG_IMX6_SPEED_CHANGE,
+			 IMX6_PCIE_FLAG_IMX6_SPEED_CHANGE |
+			 IMX6_PCIE_FLAG_SUPPORTS_SUSPEND,
 	},
 	[IMX6QP] = {
 		.variant = IMX6QP,
@@ -1258,6 +1226,7 @@ static const struct imx6_pcie_drvdata drvdata[] = {
 	},
 	[IMX7D] = {
 		.variant = IMX7D,
+		.flags = IMX6_PCIE_FLAG_SUPPORTS_SUSPEND,
 	},
 	[IMX8MQ] = {
 		.variant = IMX8MQ,
@@ -1279,6 +1248,7 @@ static struct platform_driver imx6_pcie_driver = {
 		.of_match_table = imx6_pcie_of_match,
 		.suppress_bind_attrs = true,
 		.pm = &imx6_pcie_pm_ops,
+		.probe_type = PROBE_PREFER_ASYNCHRONOUS,
 	},
 	.probe    = imx6_pcie_probe,
 	.shutdown = imx6_pcie_shutdown,
diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index 14f2b0b4ed5e..af677254a072 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -11,6 +11,7 @@
 
 #include <linux/clk.h>
 #include <linux/delay.h>
+#include <linux/gpio/consumer.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
 #include <linux/irqchip/chained_irq.h>
@@ -18,6 +19,7 @@
 #include <linux/mfd/syscon.h>
 #include <linux/msi.h>
 #include <linux/of.h>
+#include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/of_pci.h>
 #include <linux/phy/phy.h>
@@ -26,6 +28,7 @@
 #include <linux/resource.h>
 #include <linux/signal.h>
 
+#include "../../pci.h"
 #include "pcie-designware.h"
 
 #define PCIE_VENDORID_MASK	0xffff
@@ -44,28 +47,34 @@
 #define CFG_TYPE1			BIT(24)
 
 #define OB_SIZE				0x030
-#define SPACE0_REMOTE_CFG_OFFSET	0x1000
 #define OB_OFFSET_INDEX(n)		(0x200 + (8 * (n)))
 #define OB_OFFSET_HI(n)			(0x204 + (8 * (n)))
 #define OB_ENABLEN			BIT(0)
 #define OB_WIN_SIZE			8	/* 8MB */
 
+#define PCIE_LEGACY_IRQ_ENABLE_SET(n)	(0x188 + (0x10 * ((n) - 1)))
+#define PCIE_LEGACY_IRQ_ENABLE_CLR(n)	(0x18c + (0x10 * ((n) - 1)))
+#define PCIE_EP_IRQ_SET			0x64
+#define PCIE_EP_IRQ_CLR			0x68
+#define INT_ENABLE			BIT(0)
+
 /* IRQ register defines */
 #define IRQ_EOI				0x050
-#define IRQ_STATUS			0x184
-#define IRQ_ENABLE_SET			0x188
-#define IRQ_ENABLE_CLR			0x18c
 
 #define MSI_IRQ				0x054
-#define MSI0_IRQ_STATUS			0x104
-#define MSI0_IRQ_ENABLE_SET		0x108
-#define MSI0_IRQ_ENABLE_CLR		0x10c
-#define IRQ_STATUS			0x184
+#define MSI_IRQ_STATUS(n)		(0x104 + ((n) << 4))
+#define MSI_IRQ_ENABLE_SET(n)		(0x108 + ((n) << 4))
+#define MSI_IRQ_ENABLE_CLR(n)		(0x10c + ((n) << 4))
 #define MSI_IRQ_OFFSET			4
 
+#define IRQ_STATUS(n)			(0x184 + ((n) << 4))
+#define IRQ_ENABLE_SET(n)		(0x188 + ((n) << 4))
+#define INTx_EN				BIT(0)
+
 #define ERR_IRQ_STATUS			0x1c4
 #define ERR_IRQ_ENABLE_SET		0x1c8
 #define ERR_AER				BIT(5)	/* ECRC error */
+#define AM6_ERR_AER			BIT(4)	/* AM6 ECRC error */
 #define ERR_AXI				BIT(4)	/* AXI tag lookup fatal error */
 #define ERR_CORR			BIT(3)	/* Correctable error */
 #define ERR_NONFATAL			BIT(2)	/* Non-fatal error */
@@ -74,25 +83,45 @@
 #define ERR_IRQ_ALL			(ERR_AER | ERR_AXI | ERR_CORR | \
 					 ERR_NONFATAL | ERR_FATAL | ERR_SYS)
 
-#define MAX_MSI_HOST_IRQS		8
 /* PCIE controller device IDs */
 #define PCIE_RC_K2HK			0xb008
 #define PCIE_RC_K2E			0xb009
 #define PCIE_RC_K2L			0xb00a
 #define PCIE_RC_K2G			0xb00b
 
+#define KS_PCIE_DEV_TYPE_MASK		(0x3 << 1)
+#define KS_PCIE_DEV_TYPE(mode)		((mode) << 1)
+
+#define EP				0x0
+#define LEG_EP				0x1
+#define RC				0x2
+
+#define EXP_CAP_ID_OFFSET		0x70
+
+#define KS_PCIE_SYSCLOCKOUTEN		BIT(0)
+
+#define AM654_PCIE_DEV_TYPE_MASK	0x3
+#define AM654_WIN_SIZE			SZ_64K
+
+#define APP_ADDR_SPACE_0		(16 * SZ_1K)
+
 #define to_keystone_pcie(x)		dev_get_drvdata((x)->dev)
 
+struct ks_pcie_of_data {
+	enum dw_pcie_device_mode mode;
+	const struct dw_pcie_host_ops *host_ops;
+	const struct dw_pcie_ep_ops *ep_ops;
+	unsigned int version;
+};
+
 struct keystone_pcie {
 	struct dw_pcie		*pci;
 	/* PCI Device ID */
 	u32			device_id;
-	int			num_legacy_host_irqs;
 	int			legacy_host_irqs[PCI_NUM_INTX];
 	struct			device_node *legacy_intc_np;
 
-	int			num_msi_host_irqs;
-	int			msi_host_irqs[MAX_MSI_HOST_IRQS];
+	int			msi_host_irq;
 	int			num_lanes;
 	u32			num_viewport;
 	struct phy		**phy;
@@ -101,28 +130,12 @@ struct keystone_pcie {
 	struct irq_domain	*legacy_irq_domain;
 	struct device_node	*np;
 
-	int error_irq;
-
 	/* Application register space */
 	void __iomem		*va_app_base;	/* DT 1st resource */
 	struct resource		app;
+	bool			is_am6;
 };
 
-static inline void update_reg_offset_bit_pos(u32 offset, u32 *reg_offset,
-					     u32 *bit_pos)
-{
-	*reg_offset = offset % 8;
-	*bit_pos = offset >> 3;
-}
-
-static phys_addr_t ks_pcie_get_msi_addr(struct pcie_port *pp)
-{
-	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
-	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
-
-	return ks_pcie->app.start + MSI_IRQ;
-}
-
 static u32 ks_pcie_app_readl(struct keystone_pcie *ks_pcie, u32 offset)
 {
 	return readl(ks_pcie->va_app_base + offset);
@@ -134,81 +147,114 @@ static void ks_pcie_app_writel(struct keystone_pcie *ks_pcie, u32 offset,
 	writel(val, ks_pcie->va_app_base + offset);
 }
 
-static void ks_pcie_handle_msi_irq(struct keystone_pcie *ks_pcie, int offset)
+static void ks_pcie_msi_irq_ack(struct irq_data *data)
 {
-	struct dw_pcie *pci = ks_pcie->pci;
-	struct pcie_port *pp = &pci->pp;
-	struct device *dev = pci->dev;
-	u32 pending, vector;
-	int src, virq;
+	struct pcie_port *pp  = irq_data_get_irq_chip_data(data);
+	struct keystone_pcie *ks_pcie;
+	u32 irq = data->hwirq;
+	struct dw_pcie *pci;
+	u32 reg_offset;
+	u32 bit_pos;
 
-	pending = ks_pcie_app_readl(ks_pcie, MSI0_IRQ_STATUS + (offset << 4));
+	pci = to_dw_pcie_from_pp(pp);
+	ks_pcie = to_keystone_pcie(pci);
 
-	/*
-	 * MSI0 status bit 0-3 shows vectors 0, 8, 16, 24, MSI1 status bit
-	 * shows 1, 9, 17, 25 and so forth
-	 */
-	for (src = 0; src < 4; src++) {
-		if (BIT(src) & pending) {
-			vector = offset + (src << 3);
-			virq = irq_linear_revmap(pp->irq_domain, vector);
-			dev_dbg(dev, "irq: bit %d, vector %d, virq %d\n",
-				src, vector, virq);
-			generic_handle_irq(virq);
-		}
-	}
+	reg_offset = irq % 8;
+	bit_pos = irq >> 3;
+
+	ks_pcie_app_writel(ks_pcie, MSI_IRQ_STATUS(reg_offset),
+			   BIT(bit_pos));
+	ks_pcie_app_writel(ks_pcie, IRQ_EOI, reg_offset + MSI_IRQ_OFFSET);
 }
 
-static void ks_pcie_msi_irq_ack(int irq, struct pcie_port *pp)
+static void ks_pcie_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 {
-	u32 reg_offset, bit_pos;
+	struct pcie_port *pp = irq_data_get_irq_chip_data(data);
 	struct keystone_pcie *ks_pcie;
 	struct dw_pcie *pci;
+	u64 msi_target;
 
 	pci = to_dw_pcie_from_pp(pp);
 	ks_pcie = to_keystone_pcie(pci);
-	update_reg_offset_bit_pos(irq, &reg_offset, &bit_pos);
 
-	ks_pcie_app_writel(ks_pcie, MSI0_IRQ_STATUS + (reg_offset << 4),
-			   BIT(bit_pos));
-	ks_pcie_app_writel(ks_pcie, IRQ_EOI, reg_offset + MSI_IRQ_OFFSET);
+	msi_target = ks_pcie->app.start + MSI_IRQ;
+	msg->address_lo = lower_32_bits(msi_target);
+	msg->address_hi = upper_32_bits(msi_target);
+	msg->data = data->hwirq;
+
+	dev_dbg(pci->dev, "msi#%d address_hi %#x address_lo %#x\n",
+		(int)data->hwirq, msg->address_hi, msg->address_lo);
 }
 
-static void ks_pcie_msi_set_irq(struct pcie_port *pp, int irq)
+static int ks_pcie_msi_set_affinity(struct irq_data *irq_data,
+				    const struct cpumask *mask, bool force)
 {
-	u32 reg_offset, bit_pos;
-	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
-	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
+	return -EINVAL;
+}
 
-	update_reg_offset_bit_pos(irq, &reg_offset, &bit_pos);
-	ks_pcie_app_writel(ks_pcie, MSI0_IRQ_ENABLE_SET + (reg_offset << 4),
+static void ks_pcie_msi_mask(struct irq_data *data)
+{
+	struct pcie_port *pp = irq_data_get_irq_chip_data(data);
+	struct keystone_pcie *ks_pcie;
+	u32 irq = data->hwirq;
+	struct dw_pcie *pci;
+	unsigned long flags;
+	u32 reg_offset;
+	u32 bit_pos;
+
+	raw_spin_lock_irqsave(&pp->lock, flags);
+
+	pci = to_dw_pcie_from_pp(pp);
+	ks_pcie = to_keystone_pcie(pci);
+
+	reg_offset = irq % 8;
+	bit_pos = irq >> 3;
+
+	ks_pcie_app_writel(ks_pcie, MSI_IRQ_ENABLE_CLR(reg_offset),
 			   BIT(bit_pos));
+
+	raw_spin_unlock_irqrestore(&pp->lock, flags);
 }
 
-static void ks_pcie_msi_clear_irq(struct pcie_port *pp, int irq)
+static void ks_pcie_msi_unmask(struct irq_data *data)
 {
-	u32 reg_offset, bit_pos;
-	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
-	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
+	struct pcie_port *pp = irq_data_get_irq_chip_data(data);
+	struct keystone_pcie *ks_pcie;
+	u32 irq = data->hwirq;
+	struct dw_pcie *pci;
+	unsigned long flags;
+	u32 reg_offset;
+	u32 bit_pos;
+
+	raw_spin_lock_irqsave(&pp->lock, flags);
 
-	update_reg_offset_bit_pos(irq, &reg_offset, &bit_pos);
-	ks_pcie_app_writel(ks_pcie, MSI0_IRQ_ENABLE_CLR + (reg_offset << 4),
+	pci = to_dw_pcie_from_pp(pp);
+	ks_pcie = to_keystone_pcie(pci);
+
+	reg_offset = irq % 8;
+	bit_pos = irq >> 3;
+
+	ks_pcie_app_writel(ks_pcie, MSI_IRQ_ENABLE_SET(reg_offset),
 			   BIT(bit_pos));
+
+	raw_spin_unlock_irqrestore(&pp->lock, flags);
 }
 
+static struct irq_chip ks_pcie_msi_irq_chip = {
+	.name = "KEYSTONE-PCI-MSI",
+	.irq_ack = ks_pcie_msi_irq_ack,
+	.irq_compose_msi_msg = ks_pcie_compose_msi_msg,
+	.irq_set_affinity = ks_pcie_msi_set_affinity,
+	.irq_mask = ks_pcie_msi_mask,
+	.irq_unmask = ks_pcie_msi_unmask,
+};
+
 static int ks_pcie_msi_host_init(struct pcie_port *pp)
 {
+	pp->msi_irq_chip = &ks_pcie_msi_irq_chip;
 	return dw_pcie_allocate_domains(pp);
 }
 
-static void ks_pcie_enable_legacy_irqs(struct keystone_pcie *ks_pcie)
-{
-	int i;
-
-	for (i = 0; i < PCI_NUM_INTX; i++)
-		ks_pcie_app_writel(ks_pcie, IRQ_ENABLE_SET + (i << 4), 0x1);
-}
-
 static void ks_pcie_handle_legacy_irq(struct keystone_pcie *ks_pcie,
 				      int offset)
 {
@@ -217,7 +263,7 @@ static void ks_pcie_handle_legacy_irq(struct keystone_pcie *ks_pcie,
 	u32 pending;
 	int virq;
 
-	pending = ks_pcie_app_readl(ks_pcie, IRQ_STATUS + (offset << 4));
+	pending = ks_pcie_app_readl(ks_pcie, IRQ_STATUS(offset));
 
 	if (BIT(0) & pending) {
 		virq = irq_linear_revmap(ks_pcie->legacy_irq_domain, offset);
@@ -229,6 +275,14 @@ static void ks_pcie_handle_legacy_irq(struct keystone_pcie *ks_pcie,
 	ks_pcie_app_writel(ks_pcie, IRQ_EOI, offset);
 }
 
+/*
+ * Dummy function so that DW core doesn't configure MSI
+ */
+static int ks_pcie_am654_msi_host_init(struct pcie_port *pp)
+{
+	return 0;
+}
+
 static void ks_pcie_enable_error_irq(struct keystone_pcie *ks_pcie)
 {
 	ks_pcie_app_writel(ks_pcie, ERR_IRQ_ENABLE_SET, ERR_IRQ_ALL);
@@ -255,10 +309,10 @@ static irqreturn_t ks_pcie_handle_error_irq(struct keystone_pcie *ks_pcie)
 	if (reg & ERR_CORR)
 		dev_dbg(dev, "Correctable Error\n");
 
-	if (reg & ERR_AXI)
+	if (!ks_pcie->is_am6 && (reg & ERR_AXI))