Merge tag 'pci-v4.20-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci

Pull PCI updates from Bjorn Helgaas:

 - Fix ASPM link_state teardown on removal (Lukas Wunner)

 - Fix misleading _OSC ASPM message (Sinan Kaya)

 - Make _OSC optional for PCI (Sinan Kaya)

 - Don't initialize ASPM link state when ACPI_FADT_NO_ASPM is set
   (Patrick Talbert)

 - Remove x86 and arm64 node-local allocation for host bridge structures
   (Punit Agrawal)

 - Pay attention to device-specific _PXM node values (Jonathan Cameron)

 - Support new Immediate Readiness bit (Felipe Balbi)

 - Differentiate between pciehp surprise and safe removal (Lukas Wunner)

 - Remove unnecessary pciehp includes (Lukas Wunner)

 - Drop pciehp hotplug_slot_ops wrappers (Lukas Wunner)

 - Tolerate PCIe Slot Presence Detect being hardwired to zero to
   workaround broken hardware, e.g., the Wilocity switch/wireless device
   (Lukas Wunner)

 - Unify pciehp controller & slot structs (Lukas Wunner)

 - Constify hotplug_slot_ops (Lukas Wunner)

 - Drop hotplug_slot_info (Lukas Wunner)

 - Embed hotplug_slot struct into users instead of allocating it
   separately (Lukas Wunner)

 - Initialize PCIe port service drivers directly instead of relying on
   initcall ordering (Keith Busch)

 - Restore PCI config state after a slot reset (Keith Busch)

 - Save/restore DPC config state along with other PCI config state
   (Keith Busch)

 - Reference count devices during AER handling to avoid race issue with
   concurrent hot removal (Keith Busch)

 - If an Upstream Port reports ERR_FATAL, don't try to read the Port's
   config space because it is probably unreachable (Keith Busch)

 - During error handling, use slot-specific reset instead of secondary
   bus reset to avoid link up/down issues on hotplug ports (Keith Busch)

 - Restore previous AER/DPC handling that does not remove and
   re-enumerate devices on ERR_FATAL (Keith Busch)

 - Notify all drivers that may be affected by error recovery resets
   (Keith Busch)

 - Always generate error recovery uevents, even if a driver doesn't have
   error callbacks (Keith Busch)

 - Make PCIe link active reporting detection generic (Keith Busch)

 - Support D3cold in PCIe hierarchies during system sleep and runtime,
   including hotplug and Thunderbolt ports (Mika Westerberg)

 - Handle hpmemsize/hpiosize kernel parameters uniformly, whether slots
   are empty or occupied (Jon Derrick)

 - Remove duplicated include from pci/pcie/err.c and unused variable
   from cpqphp (YueHaibing)

 - Remove driver pci_cleanup_aer_uncorrect_error_status() calls (Oza
   Pawandeep)

 - Uninline PCI bus accessors for better ftracing (Keith Busch)

 - Remove unused AER Root Port .error_resume method (Keith Busch)

 - Use kfifo in AER instead of a local version (Keith Busch)

 - Use threaded IRQ in AER bottom half (Keith Busch)

 - Use managed resources in AER core (Keith Busch)

 - Reuse pcie_port_find_device() for AER injection (Keith Busch)

 - Abstract AER interrupt handling to disconnect error injection (Keith
   Busch)

 - Refactor AER injection callbacks to simplify future improvments
   (Keith Busch)

 - Remove unused Netronome NFP32xx Device IDs (Jakub Kicinski)

 - Use bitmap_zalloc() for dma_alias_mask (Andy Shevchenko)

 - Add switch fall-through annotations (Gustavo A. R. Silva)

 - Remove unused Switchtec quirk variable (Joshua Abraham)

 - Fix pci.c kernel-doc warning (Randy Dunlap)

 - Remove trivial PCI wrappers for DMA APIs (Christoph Hellwig)

 - Add Intel GPU device IDs to spurious interrupt quirk (Bin Meng)

 - Run Switchtec DMA aliasing quirk only on NTB endpoints to avoid
   useless dmesg errors (Logan Gunthorpe)

 - Update Switchtec NTB documentation (Wesley Yung)

 - Remove redundant "default n" from Kconfig (Bartlomiej Zolnierkiewicz)

 - Avoid panic when drivers enable MSI/MSI-X twice (Tonghao Zhang)

 - Add PCI support for peer-to-peer DMA (Logan Gunthorpe)

 - Add sysfs group for PCI peer-to-peer memory statistics (Logan
   Gunthorpe)

 - Add PCI peer-to-peer DMA scatterlist mapping interface (Logan
   Gunthorpe)

 - Add PCI configfs/sysfs helpers for use by peer-to-peer users (Logan
   Gunthorpe)

 - Add PCI peer-to-peer DMA driver writer's documentation (Logan
   Gunthorpe)

 - Add block layer flag to indicate driver support for PCI peer-to-peer
   DMA (Logan Gunthorpe)

 - Map Infiniband scatterlists for peer-to-peer DMA if they contain P2P
   memory (Logan Gunthorpe)

 - Register nvme-pci CMB buffer as PCI peer-to-peer memory (Logan
   Gunthorpe)

 - Add nvme-pci support for PCI peer-to-peer memory in requests (Logan
   Gunthorpe)

 - Use PCI peer-to-peer memory in nvme (Stephen Bates, Steve Wise,
   Christoph Hellwig, Logan Gunthorpe)

 - Cache VF config space size to optimize enumeration of many VFs
   (KarimAllah Ahmed)

 - Remove unnecessary <linux/pci-ats.h> include (Bjorn Helgaas)

 - Fix VMD AERSID quirk Device ID matching (Jon Derrick)

 - Fix Cadence PHY handling during probe (Alan Douglas)

 - Signal Cadence Endpoint interrupts via AXI region 0 instead of last
   region (Alan Douglas)

 - Write Cadence Endpoint MSI interrupts with 32 bits of data (Alan
   Douglas)

 - Remove redundant controller tests for "device_type == pci" (Rob
   Herring)

 - Document R-Car E3 (R8A77990) bindings (Tho Vu)

 - Add device tree support for R-Car r8a7744 (Biju Das)

 - Drop unused mvebu PCIe capability code (Thomas Petazzoni)

 - Add shared PCI bridge emulation code (Thomas Petazzoni)

 - Convert mvebu to use shared PCI bridge emulation (Thomas Petazzoni)

 - Add aardvark Root Port emulation (Thomas Petazzoni)

 - Support 100MHz/200MHz refclocks for i.MX6 (Lucas Stach)

 - Add initial power management for i.MX7 (Leonard Crestez)

 - Add PME_Turn_Off support for i.MX7 (Leonard Crestez)

 - Fix qcom runtime power management error handling (Bjorn Andersson)

 - Update TI dra7xx unaligned access errata workaround for host mode as
   well as endpoint mode (Vignesh R)

 - Fix kirin section mismatch warning (Nathan Chancellor)

 - Remove iproc PAXC slot check to allow VF support (Jitendra Bhivare)

 - Quirk Keystone K2G to limit MRRS to 256 (Kishon Vijay Abraham I)

 - Update Keystone to use MRRS quirk for host bridge instead of open
   coding (Kishon Vijay Abraham I)

 - Refactor Keystone link establishment (Kishon Vijay Abraham I)

 - Simplify and speed up Keystone link training (Kishon Vijay Abraham I)

 - Remove unused Keystone host_init argument (Kishon Vijay Abraham I)

 - Merge Keystone driver files into one (Kishon Vijay Abraham I)

 - Remove redundant Keystone platform_set_drvdata() (Kishon Vijay
   Abraham I)

 - Rename Keystone functions for uniformity (Kishon Vijay Abraham I)

 - Add Keystone device control module DT binding (Kishon Vijay Abraham
   I)

 - Use SYSCON API to get Keystone control module device IDs (Kishon
   Vijay Abraham I)

 - Clean up Keystone PHY handling (Kishon Vijay Abraham I)

 - Use runtime PM APIs to enable Keystone clock (Kishon Vijay Abraham I)

 - Clean up Keystone config space access checks (Kishon Vijay Abraham I)

 - Get Keystone outbound window count from DT (Kishon Vijay Abraham I)

 - Clean up Keystone outbound window configuration (Kishon Vijay Abraham
   I)

 - Clean up Keystone DBI setup (Kishon Vijay Abraham I)

 - Clean up Keystone ks_pcie_link_up() (Kishon Vijay Abraham I)

 - Fix Keystone IRQ status checking (Kishon Vijay Abraham I)

 - Add debug messages for all Keystone errors (Kishon Vijay Abraham I)

 - Clean up Keystone includes and macros (Kishon Vijay Abraham I)

 - Fix Mediatek unchecked return value from devm_pci_remap_iospace()
   (Gustavo A. R. Silva)

 - Fix Mediatek endpoint/port matching logic (Honghui Zhang)

 - Change Mediatek Root Port Class Code to PCI_CLASS_BRIDGE_PCI (Honghui
   Zhang)

 - Remove redundant Mediatek PM domain check (Honghui Zhang)

 - Convert Mediatek to pci_host_probe() (Honghui Zhang)

 - Fix Mediatek MSI enablement (Honghui Zhang)

 - Add Mediatek system PM support for MT2712 and MT7622 (Honghui Zhang)

 - Add Mediatek loadable module support (Honghui Zhang)

 - Detach VMD resources after stopping root bus to prevent orphan
   resources (Jon Derrick)

 - Convert pcitest build process to that used by other tools (iio, perf,
   etc) (Gustavo Pimentel)

* tag 'pci-v4.20-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci: (140 commits)
  PCI/AER: Refactor error injection fallbacks
  PCI/AER: Abstract AER interrupt handling
  PCI/AER: Reuse existing pcie_port_find_device() interface
  PCI/AER: Use managed resource allocations
  PCI: pcie: Remove redundant 'default n' from Kconfig
  PCI: aardvark: Implement emulated root PCI bridge config space
  PCI: mvebu: Convert to PCI emulated bridge config space
  PCI: mvebu: Drop unused PCI express capability code
  PCI: Introduce PCI bridge emulated config space common logic
  PCI: vmd: Detach resources after stopping root bus
  nvmet: Optionally use PCI P2P memory
  nvmet: Introduce helper functions to allocate and free request SGLs
  nvme-pci: Add support for P2P memory in requests
  nvme-pci: Use PCI p2pmem subsystem to manage the CMB
  IB/core: Ensure we map P2P memory correctly in rdma_rw_ctx_[init|destroy]()
  block: Add PCI P2P flag for request queue
  PCI/P2PDMA: Add P2P DMA driver writer's documentation
  docs-rst: Add a new directory for PCI documentation
  PCI/P2PDMA: Introduce configfs/sysfs enable attribute helpers
  PCI/P2PDMA: Add PCI p2pmem DMA mappings to adjust the bus offset
  ...

1 files changed, 677 insertions, 111 deletions

diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index e88bd221fffe..14f2b0b4ed5e 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -9,40 +9,510 @@
  * Implementation based on pci-exynos.c and pcie-designware.c
  */
 
-#include <linux/irqchip/chained_irq.h>
 #include <linux/clk.h>
 #include <linux/delay.h>
+#include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/irqchip/chained_irq.h>
 #include <linux/irqdomain.h>
-#include <linux/init.h>
+#include <linux/mfd/syscon.h>
 #include <linux/msi.h>
-#include <linux/of_irq.h>
 #include <linux/of.h>
+#include <linux/of_irq.h>
 #include <linux/of_pci.h>
-#include <linux/platform_device.h>
 #include <linux/phy/phy.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
 #include <linux/resource.h>
 #include <linux/signal.h>
 
 #include "pcie-designware.h"
-#include "pci-keystone.h"
 
-#define DRIVER_NAME	"keystone-pcie"
+#define PCIE_VENDORID_MASK	0xffff
+#define PCIE_DEVICEID_SHIFT	16
+
+/* Application registers */
+#define CMD_STATUS			0x004
+#define LTSSM_EN_VAL		        BIT(0)
+#define OB_XLAT_EN_VAL		        BIT(1)
+#define DBI_CS2				BIT(5)
+
+#define CFG_SETUP			0x008
+#define CFG_BUS(x)			(((x) & 0xff) << 16)
+#define CFG_DEVICE(x)			(((x) & 0x1f) << 8)
+#define CFG_FUNC(x)			((x) & 0x7)
+#define CFG_TYPE1			BIT(24)
+
+#define OB_SIZE				0x030
+#define 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 */
+
+/* IRQ register defines */
+#define IRQ_EOI				0x050
+#define IRQ_STATUS			0x184
+#define IRQ_ENABLE_SET			0x188
+#define IRQ_ENABLE_CLR			0x18c
+
+#define MSI_IRQ				0x054
+#define MSI0_IRQ_STATUS			0x104
+#define MSI0_IRQ_ENABLE_SET		0x108
+#define MSI0_IRQ_ENABLE_CLR		0x10c
+#define IRQ_STATUS			0x184
+#define MSI_IRQ_OFFSET			4
+
+#define ERR_IRQ_STATUS			0x1c4
+#define ERR_IRQ_ENABLE_SET		0x1c8
+#define ERR_AER				BIT(5)	/* ECRC error */
+#define ERR_AXI				BIT(4)	/* AXI tag lookup fatal error */
+#define ERR_CORR			BIT(3)	/* Correctable error */
+#define ERR_NONFATAL			BIT(2)	/* Non-fatal error */
+#define ERR_FATAL			BIT(1)	/* Fatal error */
+#define ERR_SYS				BIT(0)	/* System error */
+#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 to_keystone_pcie(x)		dev_get_drvdata((x)->dev)
+
+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			num_lanes;
+	u32			num_viewport;
+	struct phy		**phy;
+	struct device_link	**link;
+	struct			device_node *msi_intc_np;
+	struct irq_domain	*legacy_irq_domain;
+	struct device_node	*np;
+
+	int error_irq;
+
+	/* Application register space */
+	void __iomem		*va_app_base;	/* DT 1st resource */
+	struct resource		app;
+};
 
-/* DEV_STAT_CTRL */
-#define PCIE_CAP_BASE		0x70
+static inline void update_reg_offset_bit_pos(u32 offset, u32 *reg_offset,
+					     u32 *bit_pos)
+{
+	*reg_offset = offset % 8;
+	*bit_pos = offset >> 3;
+}
 
-/* PCIE controller device IDs */
-#define PCIE_RC_K2HK		0xb008
-#define PCIE_RC_K2E		0xb009
-#define PCIE_RC_K2L		0xb00a
+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);
+}
+
+static void ks_pcie_app_writel(struct keystone_pcie *ks_pcie, u32 offset,
+			       u32 val)
+{
+	writel(val, ks_pcie->va_app_base + offset);
+}
+
+static void ks_pcie_handle_msi_irq(struct keystone_pcie *ks_pcie, int offset)
+{
+	struct dw_pcie *pci = ks_pcie->pci;
+	struct pcie_port *pp = &pci->pp;
+	struct device *dev = pci->dev;
+	u32 pending, vector;
+	int src, virq;
+
+	pending = ks_pcie_app_readl(ks_pcie, MSI0_IRQ_STATUS + (offset << 4));
+
+	/*
+	 * MSI0 status bit 0-3 shows vectors 0, 8, 16, 24, MSI1 status bit
+	 * shows 1, 9, 17, 25 and so forth
+	 */
+	for (src = 0; src < 4; src++) {
+		if (BIT(src) & pending) {
+			vector = offset + (src << 3);
+			virq = irq_linear_revmap(pp->irq_domain, vector);
+			dev_dbg(dev, "irq: bit %d, vector %d, virq %d\n",
+				src, vector, virq);
+			generic_handle_irq(virq);
+		}
+	}
+}
+
+static void ks_pcie_msi_irq_ack(int irq, struct pcie_port *pp)
+{
+	u32 reg_offset, bit_pos;
+	struct keystone_pcie *ks_pcie;
+	struct dw_pcie *pci;
+
+	pci = to_dw_pcie_from_pp(pp);
+	ks_pcie = to_keystone_pcie(pci);
+	update_reg_offset_bit_pos(irq, &reg_offset, &bit_pos);
+
+	ks_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);
+}
+
+static void ks_pcie_msi_set_irq(struct pcie_port *pp, int irq)
+{
+	u32 reg_offset, bit_pos;
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
+
+	update_reg_offset_bit_pos(irq, &reg_offset, &bit_pos);
+	ks_pcie_app_writel(ks_pcie, MSI0_IRQ_ENABLE_SET + (reg_offset << 4),
+			   BIT(bit_pos));
+}
+
+static void ks_pcie_msi_clear_irq(struct pcie_port *pp, int irq)
+{
+	u32 reg_offset, bit_pos;
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
+
+	update_reg_offset_bit_pos(irq, &reg_offset, &bit_pos);
+	ks_pcie_app_writel(ks_pcie, MSI0_IRQ_ENABLE_CLR + (reg_offset << 4),
+			   BIT(bit_pos));
+}
+
+static int ks_pcie_msi_host_init(struct pcie_port *pp)
+{
+	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)
+{
+	struct dw_pcie *pci = ks_pcie->pci;
+	struct device *dev = pci->dev;
+	u32 pending;
+	int virq;
+
+	pending = ks_pcie_app_readl(ks_pcie, IRQ_STATUS + (offset << 4));
+
+	if (BIT(0) & pending) {
+		virq = irq_linear_revmap(ks_pcie->legacy_irq_domain, offset);
+		dev_dbg(dev, ": irq: irq_offset %d, virq %d\n", offset, virq);
+		generic_handle_irq(virq);
+	}
+
+	/* EOI the INTx interrupt */
+	ks_pcie_app_writel(ks_pcie, IRQ_EOI, offset);
+}
+
+static void ks_pcie_enable_error_irq(struct keystone_pcie *ks_pcie)
+{
+	ks_pcie_app_writel(ks_pcie, ERR_IRQ_ENABLE_SET, ERR_IRQ_ALL);
+}
+
+static irqreturn_t ks_pcie_handle_error_irq(struct keystone_pcie *ks_pcie)
+{
+	u32 reg;
+	struct device *dev = ks_pcie->pci->dev;
+
+	reg = ks_pcie_app_readl(ks_pcie, ERR_IRQ_STATUS);
+	if (!reg)
+		return IRQ_NONE;
+
+	if (reg & ERR_SYS)
+		dev_err(dev, "System Error\n");
+
+	if (reg & ERR_FATAL)
+		dev_err(dev, "Fatal Error\n");
+
+	if (reg & ERR_NONFATAL)
+		dev_dbg(dev, "Non Fatal Error\n");
+
+	if (reg & ERR_CORR)
+		dev_dbg(dev, "Correctable Error\n");
+
+	if (reg & ERR_AXI)
+		dev_err(dev, "AXI tag lookup fatal Error\n");
+
+	if (reg & ERR_AER)
+		dev_err(dev, "ECRC Error\n");
+
+	ks_pcie_app_writel(ks_pcie, ERR_IRQ_STATUS, reg);
+
+	return IRQ_HANDLED;
+}
+
+static void ks_pcie_ack_legacy_irq(struct irq_data *d)
+{
+}
+
+static void ks_pcie_mask_legacy_irq(struct irq_data *d)
+{
+}
+
+static void ks_pcie_unmask_legacy_irq(struct irq_data *d)
+{
+}
+
+static struct irq_chip ks_pcie_legacy_irq_chip = {
+	.name = "Keystone-PCI-Legacy-IRQ",
+	.irq_ack = ks_pcie_ack_legacy_irq,
+	.irq_mask = ks_pcie_mask_legacy_irq,
+	.irq_unmask = ks_pcie_unmask_legacy_irq,
+};
+
+static int ks_pcie_init_legacy_irq_map(struct irq_domain *d,
+				       unsigned int irq,
+				       irq_hw_number_t hw_irq)
+{
+	irq_set_chip_and_handler(irq, &ks_pcie_legacy_irq_chip,
+				 handle_level_irq);
+	irq_set_chip_data(irq, d->host_data);
+
+	return 0;
+}
+
+static const struct irq_domain_ops ks_pcie_legacy_irq_domain_ops = {
+	.map = ks_pcie_init_legacy_irq_map,
+	.xlate = irq_domain_xlate_onetwocell,
+};
+
+/**
+ * ks_pcie_set_dbi_mode() - Set DBI mode to access overlaid BAR mask
+ * registers
+ *
+ * Since modification of dbi_cs2 involves different clock domain, read the
+ * status back to ensure the transition is complete.
+ */
+static void ks_pcie_set_dbi_mode(struct keystone_pcie *ks_pcie)
+{
+	u32 val;
+
+	val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
+	val |= DBI_CS2;
+	ks_pcie_app_writel(ks_pcie, CMD_STATUS, val);
+
+	do {
+		val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
+	} while (!(val & DBI_CS2));
+}
+
+/**
+ * ks_pcie_clear_dbi_mode() - Disable DBI mode
+ *
+ * Since modification of dbi_cs2 involves different clock domain, read the
+ * status back to ensure the transition is complete.
+ */
+static void ks_pcie_clear_dbi_mode(struct keystone_pcie *ks_pcie)
+{
+	u32 val;
+
+	val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
+	val &= ~DBI_CS2;
+	ks_pcie_app_writel(ks_pcie, CMD_STATUS, val);
+
+	do {
+		val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
+	} while (val & DBI_CS2);
+}
+
+static void ks_pcie_setup_rc_app_regs(struct keystone_pcie *ks_pcie)
+{
+	u32 val;
+	u32 num_viewport = ks_pcie->num_viewport;
+	struct dw_pcie *pci = ks_pcie->pci;
+	struct pcie_port *pp = &pci->pp;
+	u64 start = pp->mem->start;
+	u64 end = pp->mem->end;
+	int i;
+
+	/* Disable BARs for inbound access */
+	ks_pcie_set_dbi_mode(ks_pcie);
+	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 0);
+	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_1, 0);
+	ks_pcie_clear_dbi_mode(ks_pcie);
+
+	val = ilog2(OB_WIN_SIZE);
+	ks_pcie_app_writel(ks_pcie, OB_SIZE, val);
+
+	/* Using Direct 1:1 mapping of RC <-> PCI memory space */
+	for (i = 0; i < num_viewport && (start < end); i++) {
+		ks_pcie_app_writel(ks_pcie, OB_OFFSET_INDEX(i),
+				   lower_32_bits(start) | OB_ENABLEN);
+		ks_pcie_app_writel(ks_pcie, OB_OFFSET_HI(i),
+				   upper_32_bits(start));
+		start += OB_WIN_SIZE;
+	}
+
+	val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
+	val |= OB_XLAT_EN_VAL;
+	ks_pcie_app_writel(ks_pcie, CMD_STATUS, val);
+}
+
+static int ks_pcie_rd_other_conf(struct pcie_port *pp, struct pci_bus *bus,
+				 unsigned int devfn, int where, int size,
+				 u32 *val)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
+	u32 reg;
+
+	reg = CFG_BUS(bus->number) | CFG_DEVICE(PCI_SLOT(devfn)) |
+		CFG_FUNC(PCI_FUNC(devfn));
+	if (bus->parent->number != pp->root_bus_nr)
+		reg |= CFG_TYPE1;
+	ks_pcie_app_writel(ks_pcie, CFG_SETUP, reg);
+
+	return dw_pcie_read(pp->va_cfg0_base + where, size, val);
+}
+
+static int ks_pcie_wr_other_conf(struct pcie_port *pp, struct pci_bus *bus,
+				 unsigned int devfn, int where, int size,
+				 u32 val)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
+	u32 reg;
+
+	reg = CFG_BUS(bus->number) | CFG_DEVICE(PCI_SLOT(devfn)) |
+		CFG_FUNC(PCI_FUNC(devfn));
+	if (bus->parent->number != pp->root_bus_nr)
+		reg |= CFG_TYPE1;
+	ks_pcie_app_writel(ks_pcie, CFG_SETUP, reg);
+
+	return dw_pcie_write(pp->va_cfg0_base + where, size, val);
+}
+
+/**
+ * ks_pcie_v3_65_scan_bus() - keystone scan_bus post initialization
+ *
+ * This sets BAR0 to enable inbound access for MSI_IRQ register
+ */
+static void ks_pcie_v3_65_scan_bus(struct pcie_port *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
+
+	/* Configure and set up BAR0 */
+	ks_pcie_set_dbi_mode(ks_pcie);
+
+	/* Enable BAR0 */
+	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 1);
+	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, SZ_4K - 1);
+
+	ks_pcie_clear_dbi_mode(ks_pcie);
+
+	 /*
+	  * For BAR0, just setting bus address for inbound writes (MSI) should
+	  * be sufficient.  Use physical address to avoid any conflicts.
+	  */
+	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, ks_pcie->app.start);
+}
+
+/**
+ * ks_pcie_link_up() - Check if link up
+ */
+static int ks_pcie_link_up(struct dw_pcie *pci)
+{
+	u32 val;
+
+	val = dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG0);
+	val &= PORT_LOGIC_LTSSM_STATE_MASK;
+	return (val == PORT_LOGIC_LTSSM_STATE_L0);
+}
+
+static void ks_pcie_initiate_link_train(struct keystone_pcie *ks_pcie)
+{
+	u32 val;
 
-#define to_keystone_pcie(x)	dev_get_drvdata((x)->dev)
+	/* Disable Link training */
+	val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
+	val &= ~LTSSM_EN_VAL;
+	ks_pcie_app_writel(ks_pcie, CMD_STATUS, LTSSM_EN_VAL | val);
 
-static void quirk_limit_mrrs(struct pci_dev *dev)
+	/* Initiate Link Training */
+	val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
+	ks_pcie_app_writel(ks_pcie, CMD_STATUS, LTSSM_EN_VAL | val);
+}
+
+/**
+ * ks_pcie_dw_host_init() - initialize host for v3_65 dw hardware
+ *
+ * Ioremap the register resources, initialize legacy irq domain
+ * and call dw_pcie_v3_65_host_init() API to initialize the Keystone
+ * PCI host controller.
+ */
+static int __init ks_pcie_dw_host_init(struct keystone_pcie *ks_pcie)
+{
+	struct dw_pcie *pci = ks_pcie->pci;
+	struct pcie_port *pp = &pci->pp;
+	struct device *dev = pci->dev;
+	struct platform_device *pdev = to_platform_device(dev);
+	struct resource *res;
+
+	/* Index 0 is the config reg. space address */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	pci->dbi_base = devm_pci_remap_cfg_resource(dev, res);
+	if (IS_ERR(pci->dbi_base))
+		return PTR_ERR(pci->dbi_base);
+
+	/*
+	 * We set these same and is used in pcie rd/wr_other_conf
+	 * functions
+	 */
+	pp->va_cfg0_base = pci->dbi_base + SPACE0_REMOTE_CFG_OFFSET;
+	pp->va_cfg1_base = pp->va_cfg0_base;
+
+	/* Index 1 is the application reg. space address */
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 1);
+	ks_pcie->va_app_base = devm_ioremap_resource(dev, res);
+	if (IS_ERR(ks_pcie->va_app_base))
+		return PTR_ERR(ks_pcie->va_app_base);
+
+	ks_pcie->app = *res;
+
+	/* Create legacy IRQ domain */
+	ks_pcie->legacy_irq_domain =
+			irq_domain_add_linear(ks_pcie->legacy_intc_np,
+					      PCI_NUM_INTX,
+					      &ks_pcie_legacy_irq_domain_ops,
+					      NULL);
+	if (!ks_pcie->legacy_irq_domain) {
+		dev_err(dev, "Failed to add irq domain for legacy irqs\n");
+		return -EINVAL;
+	}
+
+	return dw_pcie_host_init(pp);
+}
+
+static void ks_pcie_quirk(struct pci_dev *dev)
 {
 	struct pci_bus *bus = dev->bus;
-	struct pci_dev *bridge = bus->self;
+	struct pci_dev *bridge;
 	static const struct pci_device_id rc_pci_devids[] = {
 		{ PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2HK),
 		 .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, },
@@ -50,11 +520,13 @@ static void quirk_limit_mrrs(struct pci_dev *dev)
 		 .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, },
 		{ PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2L),
 		 .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, },
+		{ PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2G),
+		 .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, },
 		{ 0, },
 	};
 
 	if (pci_is_root_bus(bus))
-		return;
+		bridge = dev;
 
 	/* look for the host bridge */
 	while (!pci_is_root_bus(bus)) {
@@ -62,43 +534,39 @@ static void quirk_limit_mrrs(struct pci_dev *dev)
 		bus = bus->parent;
 	}
 
-	if (bridge) {
-		/*
-		 * Keystone PCI controller has a h/w limitation of
-		 * 256 bytes maximum read request size.  It can't handle
-		 * anything higher than this.  So force this limit on
-		 * all downstream devices.
-		 */
-		if (pci_match_id(rc_pci_devids, bridge)) {
-			if (pcie_get_readrq(dev) > 256) {
-				dev_info(&dev->dev, "limiting MRRS to 256\n");
-				pcie_set_readrq(dev, 256);
-			}
+	if (!bridge)
+		return;
+
+	/*
+	 * Keystone PCI controller has a h/w limitation of
+	 * 256 bytes maximum read request size.  It can't handle
+	 * anything higher than this.  So force this limit on
+	 * all downstream devices.
+	 */
+	if (pci_match_id(rc_pci_devids, bridge)) {
+		if (pcie_get_readrq(dev) > 256) {
+			dev_info(&dev->dev, "limiting MRRS to 256\n");
+			pcie_set_readrq(dev, 256);
 		}
 	}
 }
-DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, quirk_limit_mrrs);
+DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, ks_pcie_quirk);
 
 static int ks_pcie_establish_link(struct keystone_pcie *ks_pcie)
 {
 	struct dw_pcie *pci = ks_pcie->pci;
-	struct pcie_port *pp = &pci->pp;
 	struct device *dev = pci->dev;
-	unsigned int retries;
-
-	dw_pcie_setup_rc(pp);
 
 	if (dw_pcie_link_up(pci)) {
 		dev_info(dev, "Link already up\n");
 		return 0;
 	}
 
+	ks_pcie_initiate_link_train(ks_pcie);
+
 	/* check if the link is up or not */
-	for (retries = 0; retries < 5; retries++) {
-		ks_dw_pcie_initiate_link_train(ks_pcie);
-		if (!dw_pcie_wait_for_link(pci))
-			return 0;
-	}
+	if (!dw_pcie_wait_for_link(pci))
+		return 0;
 
 	dev_err(dev, "phy link never came up\n");
 	return -ETIMEDOUT;
@@ -121,7 +589,7 @@ static void ks_pcie_msi_irq_handler(struct irq_desc *desc)
 	 * ack operation.
 	 */
 	chained_irq_enter(chip, desc);
-	ks_dw_pcie_handle_msi_irq(ks_pcie, offset);
+	ks_pcie_handle_msi_irq(ks_pcie, offset);
 	chained_irq_exit(chip, desc);
 }
 
@@ -150,7 +618,7 @@ static void ks_pcie_legacy_irq_handler(struct irq_desc *desc)
 	 * ack operation.
 	 */
 	chained_irq_enter(chip, desc);
-	ks_dw_pcie_handle_legacy_irq(ks_pcie, irq_offset);
+	ks_pcie_handle_legacy_irq(ks_pcie, irq_offset);
 	chained_irq_exit(chip, desc);
 }
 
@@ -222,7 +690,7 @@ static void ks_pcie_setup_interrupts(struct keystone_pcie *ks_pcie)
 						 ks_pcie_legacy_irq_handler,
 						 ks_pcie);
 	}
-	ks_dw_pcie_enable_legacy_irqs(ks_pcie);
+	ks_pcie_enable_legacy_irqs(ks_pcie);
 
 	/* MSI IRQ */
 	if (IS_ENABLED(CONFIG_PCI_MSI)) {
@@ -234,7 +702,7 @@ static void ks_pcie_setup_interrupts(struct keystone_pcie *ks_pcie)
 	}
 
 	if (ks_pcie->error_irq > 0)
-		ks_dw_pcie_enable_error_irq(ks_pcie);
+		ks_pcie_enable_error_irq(ks_pcie);
 }
 
 /*
@@ -242,8 +710,8 @@ static void ks_pcie_setup_interrupts(struct keystone_pcie *ks_pcie)
  * bus error instead of returning 0xffffffff. This handler always returns 0
  * for this kind of faults.
  */
-static int keystone_pcie_fault(unsigned long addr, unsigned int fsr,
-				struct pt_regs *regs)
+static int ks_pcie_fault(unsigned long addr, unsigned int fsr,
+			 struct pt_regs *regs)
 {
 	unsigned long instr = *(unsigned long *) instruction_pointer(regs);
 
@@ -257,59 +725,78 @@ static int keystone_pcie_fault(unsigned long addr, unsigned int fsr,
 	return 0;
 }
 
+static int __init ks_pcie_init_id(struct keystone_pcie *ks_pcie)
+{
+	int ret;
+	unsigned int id;
+	struct regmap *devctrl_regs;
+	struct dw_pcie *pci = ks_pcie->pci;
+	struct device *dev = pci->dev;
+	struct device_node *np = dev->of_node;
+
+	devctrl_regs = syscon_regmap_lookup_by_phandle(np, "ti,syscon-pcie-id");
+	if (IS_ERR(devctrl_regs))
+		return PTR_ERR(devctrl_regs);
+
+	ret = regmap_read(devctrl_regs, 0, &id);
+	if (ret)
+		return ret;
+
+	dw_pcie_writew_dbi(pci, PCI_VENDOR_ID, id & PCIE_VENDORID_MASK);
+	dw_pcie_writew_dbi(pci, PCI_DEVICE_ID, id >> PCIE_DEVICEID_SHIFT);
+
+	return 0;
+}
+
 static int __init ks_pcie_host_init(struct pcie_port *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
-	u32 val;
+	int ret;
+
+	dw_pcie_setup_rc(pp);
 
 	ks_pcie_establish_link(ks_pcie);
-	ks_dw_pcie_setup_rc_app_regs(ks_pcie);
+	ks_pcie_setup_rc_app_regs(ks_pcie);
 	ks_pcie_setup_interrupts(ks_pcie);
 	writew(PCI_IO_RANGE_TYPE_32 | (PCI_IO_RANGE_TYPE_32 << 8),
 			pci->dbi_base + PCI_IO_BASE);
 
-	/* update the Vendor ID */
-	writew(ks_pcie->device_id, pci->dbi_base + PCI_DEVICE_ID);
-
-	/* update the DEV_STAT_CTRL to publish right mrrs */
-	val = readl(pci->dbi_base + PCIE_CAP_BASE + PCI_EXP_DEVCTL);
-	val &= ~PCI_EXP_DEVCTL_READRQ;
-	/* set the mrrs to 256 bytes */
-	val |= BIT(12);
-	writel(val, pci->dbi_base + PCIE_CAP_BASE + PCI_EXP_DEVCTL);
+	ret = ks_pcie_init_id(ks_pcie);
+	if (ret < 0)
+		return ret;
 
 	/*
 	 * PCIe access errors that result into OCP errors are caught by ARM as
 	 * "External aborts"
 	 */
-	hook_fault_code(17, keystone_pcie_fault, SIGBUS, 0,
+	hook_fault_code(17, ks_pcie_fault, SIGBUS, 0,
 			"Asynchronous external abort");
 
 	return 0;
 }
 
-static const struct dw_pcie_host_ops keystone_pcie_host_ops = {
-	.rd_other_conf = ks_dw_pcie_rd_other_conf,
-	.wr_other_conf = ks_dw_pcie_wr_other_conf,
+static const struct dw_pcie_host_ops ks_pcie_host_ops = {
+	.rd_other_conf = ks_pcie_rd_other_conf,
+	.wr_other_conf = ks_pcie_wr_other_conf,
 	.host_init = ks_pcie_host_init,
-	.msi_set_irq = ks_dw_pcie_msi_set_irq,
-	.msi_clear_irq = ks_dw_pcie_msi_clear_irq,
-	.get_msi_addr = ks_dw_pcie_get_msi_addr,
-	.msi_host_init = ks_dw_pcie_msi_host_init,
-	.msi_irq_ack = ks_dw_pcie_msi_irq_ack,
-	.scan_bus = ks_dw_pcie_v3_65_scan_bus,
+	.msi_set_irq = ks_pcie_msi_set_irq,
+	.msi_clear_irq = ks_pcie_msi_clear_irq,
+	.get_msi_addr = ks_pcie_get_msi_addr,
+	.msi_host_init = ks_pcie_msi_host_init,
+	.msi_irq_ack = ks_pcie_msi_irq_ack,
+	.scan_bus = ks_pcie_v3_65_scan_bus,
 };
 
-static irqreturn_t pcie_err_irq_handler(int irq, void *priv)
+static irqreturn_t ks_pcie_err_irq_handler(int irq, void *priv)
 {
 	struct keystone_pcie *ks_pcie = priv;
 
-	return ks_dw_pcie_handle_error_irq(ks_pcie);
+	return ks_pcie_handle_error_irq(ks_pcie);
 }
 
-static int __init ks_add_pcie_port(struct keystone_pcie *ks_pcie,
-			 struct platform_device *pdev)
+static int __init ks_pcie_add_pcie_port(struct keystone_pcie *ks_pcie,
+					struct platform_device *pdev)
 {
 	struct dw_pcie *pci = ks_pcie->pci;
 	struct pcie_port *pp = &pci->pp;
@@ -338,7 +825,7 @@ static int __init ks_add_pcie_port(struct keystone_pcie *ks_pcie,
 	if (ks_pcie->error_irq <= 0)
 		dev_info(dev, "no error IRQ defined\n");
 	else {
-		ret = request_irq(ks_pcie->error_irq, pcie_err_irq_handler,
+		ret = request_irq(ks_pcie->error_irq, ks_pcie_err_irq_handler,
 				  IRQF_SHARED, "pcie-error-irq", ks_pcie);
 		if (ret < 0) {
 			dev_err(dev, "failed to request error IRQ %d\n",
@@ -347,8 +834,8 @@ static int __init ks_add_pcie_port(struct keystone_pcie *ks_pcie,
 		}
 	}
 
-	pp->ops = &keystone_pcie_host_ops;
-	ret = ks_dw_pcie_host_init(ks_pcie, ks_pcie->msi_intc_np);
+	pp->ops = &ks_pcie_host_ops;
+	ret = ks_pcie_dw_host_init(ks_pcie);
 	if (ret) {
 		dev_err(dev, "failed to initialize host\n");
 		return ret;
@@ -365,28 +852,62 @@ static const struct of_device_id ks_pcie_of_match[] = {
 	{ },
 };
 
-static const struct dw_pcie_ops dw_pcie_ops = {
-	.link_up = ks_dw_pcie_link_up,
+static const struct dw_pcie_ops ks_pcie_dw_pcie_ops = {
+	.link_up = ks_pcie_link_up,
 };
 
-static int __exit ks_pcie_remove(struct platform_device *pdev)
+static void ks_pcie_disable_phy(struct keystone_pcie *ks_pcie)
 {
-	struct keystone_pcie *ks_pcie = platform_get_drvdata(pdev);
+	int num_lanes = ks_pcie->num_lanes;
 
-	clk_disable_unprepare(ks_pcie->clk);
+	while (num_lanes--) {
+		phy_power_off(ks_pcie->phy[num_lanes]);
+		phy_exit(ks_pcie->phy[num_lanes]);
+	}
+}
+
+static int ks_pcie_enable_phy(struct keystone_pcie *ks_pcie)
+{
+	int i;
+	int ret;
+	int num_lanes = ks_pcie->num_lanes;
+
+	for (i = 0; i < num_lanes; i++) {
+		ret = phy_init(ks_pcie->phy[i]);
+		if (ret < 0)
+			goto err_phy;
+
+		ret = phy_power_on(ks_pcie->phy[i]);
+		if (ret < 0) {
+			phy_exit(ks_pcie->phy[i]);
+			goto err_phy;
+		}
+	}
 
 	return 0;
+
+err_phy:
+	while (--i >= 0) {
+		phy_power_off(ks_pcie->phy[i]);
+		phy_exit(ks_pcie->phy[i]);
+	}
+
+	return ret;
 }
 
 static int __init ks_pcie_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
+	struct device_node *np = dev->of_node;
 	struct dw_pcie *pci;
 	struct keystone_pcie *ks_pcie;
-	struct resource *res;
-	void __iomem *reg_p;
-	struct phy *phy;
+	struct device_link **link;
+	u32 num_viewport;
+	struct phy **phy;
+	u32 num_lanes;
+	char name[10];
 	int ret;
+	int i;
 
 	ks_pcie = devm_kzalloc(dev, sizeof(*ks_pcie), GFP_KERNEL);
 	if (!ks_pcie)
@@ -397,54 +918,99 @@ static int __init ks_pcie_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	pci->dev = dev;
-	pci->ops = &dw_pcie_ops;
+	pci->ops = &ks_pcie_dw_pcie_ops;
 
-	ks_pcie->pci = pci;
+	ret = of_property_read_u32(np, "num-viewport", &num_viewport);
+	if (ret < 0) {
+		dev_err(dev, "unable to read *num-viewport* property\n");
+		return ret;
+	}
 
-	/* initialize SerDes Phy if present */
-	phy = devm_phy_get(dev, "pcie-phy");
-	if (PTR_ERR_OR_ZERO(phy) == -EPROBE_DEFER)
-		return PTR_ERR(phy);
+	ret = of_property_read_u32(np, "num-lanes", &num_lanes);
+	if (ret)
+		num_lanes = 1;
 
-	if (!IS_ERR_OR_NULL(phy)) {
-		ret = phy_init(phy);
-		if (ret < 0)
-			return ret;
+	phy = devm_kzalloc(dev, sizeof(*phy) * num_lanes, GFP_KERNEL);
+	if (!phy)
+		return -ENOMEM;
+
+	link = devm_kzalloc(dev, sizeof(*link) * num_lanes, GFP_KERNEL);
+	if (!link)
+		return -ENOMEM;
+
+	for (i = 0; i < num_lanes; i++) {
+		snprintf(name, sizeof(name), "pcie-phy%d", i);
+		phy[i] = devm_phy_optional_get(dev, name);
+		if (IS_ERR(phy[i])) {
+			ret = PTR_ERR(phy[i]);
+			goto err_link;
+		}
+
+		if (!phy[i])
+			continue;
+
+		link[i] = device_link_add(dev, &phy[i]->dev, DL_FLAG_STATELESS);
+		if (!link[i]) {
+			ret = -EINVAL;
+			goto err_link;
+		}
 	}
 
-	/* index 2 is to read PCI DEVICE_ID */
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 2);
-	reg_p = devm_ioremap_resource(dev, res);
-	if (IS_ERR(reg_p))
-		return PTR_ERR(reg_p);
-	ks_pcie->device_id = readl(reg_p) >> 16;
-	devm_iounmap(dev, reg_p);
-	devm_release_mem_region(dev, res->start, resource_size(res));
+	ks_pcie->np = np;
+	ks_pcie->pci = pci;
+	ks_pcie->link = link;
+	ks_pcie->num_lanes = num_lanes;
+	ks_pcie->num_viewport = num_viewport;
+	ks_pcie->phy = phy;
 
-	ks_pcie->np = dev->of_node;
-	platform_set_drvdata(pdev, ks_pcie);
-	ks_pcie->clk = devm_clk_get(dev, "pcie");
-	if (IS_ERR(ks_pcie->clk)) {
-		dev_err(dev, "Failed to get pcie rc clock\n");
-		return PTR_ERR(ks_pcie->clk);
+	ret = ks_pcie_enable_phy(ks_pcie);
+	if (ret) {
+		dev_err(dev, "failed to enable phy\n");
+		goto err_link;
 	}
-	ret = clk_prepare_enable(ks_pcie->clk);
-	if (ret)
-		return ret;
 
 	platform_set_drvdata(pdev, ks_pcie);
+	pm_runtime_enable(dev);
+	ret = pm_runtime_get_sync(dev);
+	if (ret < 0) {
+		dev_err(dev, "pm_runtime_get_sync failed\n");
+		goto err_get_sync;
+	}
 
-	ret = ks_add_pcie_port(ks_pcie, pdev);
+	ret = ks_pcie_add_pcie_port(ks_pcie, pdev);
 	if (ret < 0)
-		goto fail_clk;
+		goto err_get_sync;
 
 	return 0;
-fail_clk:
-	clk_disable_unprepare(ks_pcie->clk);
+
+err_get_sync:
+	pm_runtime_put(dev);
+	pm_runtime_disable(dev);
+	ks_pcie_disable_phy(ks_pcie);
+
+err_link:
+	while (--i >= 0 && link[i])
+		device_link_del(link[i]);
 
 	return ret;
 }
 
+static int __exit ks_pcie_remove(struct platform_device *pdev)
+{
+	struct keystone_pcie *ks_pcie = platform_get_drvdata(pdev);
+	struct device_link **link = ks_pcie->link;
+	int num_lanes = ks_pcie->num_lanes;
+	struct device *dev = &pdev->dev;
+
+	pm_runtime_put(dev);
+	pm_runtime_disable(dev);
+	ks_pcie_disable_phy(ks_pcie);
+	while (num_lanes--)
+		device_link_del(link[num_lanes]);
+
+	return 0;
+}
+
 static struct platform_driver ks_pcie_driver __refdata = {
 	.probe  = ks_pcie_probe,
 	.remove = __exit_p(ks_pcie_remove),