Merge tag 'pci-v5.3-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci

Pull PCI updates from Bjorn Helgaas:
 "Enumeration changes:

   - Evaluate PCI Boot Configuration _DSM to learn if firmware wants us
     to preserve its resource assignments (Benjamin Herrenschmidt)

   - Simplify resource distribution (Nicholas Johnson)

   - Decode 32 GT/s link speed (Gustavo Pimentel)

  Virtualization:

   - Fix incorrect caching of VF config space size (Alex Williamson)

   - Fix VF driver probing sysfs knobs (Alex Williamson)

  Peer-to-peer DMA:

   - Fix dma_virt_ops check (Logan Gunthorpe)

  Altera host bridge driver:

   - Allow building as module (Ley Foon Tan)

  Armada 8K host bridge driver:

   - add PHYs support (Miquel Raynal)

  DesignWare host bridge driver:

   - Export APIs to support removable loadable module (Vidya Sagar)

   - Enable Relaxed Ordering erratum workaround only on Tegra20 &
     Tegra30 (Vidya Sagar)

  Hyper-V host bridge driver:

   - Fix use-after-free in eject (Dexuan Cui)

  Mobiveil host bridge driver:

   - Clean up and fix many issues, including non-identify mapped
     windows, 64-bit windows, multi-MSI, class code, INTx clearing (Hou
     Zhiqiang)

  Qualcomm host bridge driver:

   - Use clk bulk API for 2.4.0 controllers (Bjorn Andersson)

   - Add QCS404 support (Bjorn Andersson)

   - Assert PERST for at least 100ms (Niklas Cassel)

  R-Car host bridge driver:

   - Add r8a774a1 DT support (Biju Das)

  Tegra host bridge driver:

   - Add support for Gen2, opportunistic UpdateFC and ACK (PCIe protocol
     details) AER, GPIO-based PERST# (Manikanta Maddireddy)

   - Fix many issues, including power-on failure cases, interrupt
     masking in suspend, UPHY settings, AFI dynamic clock gating,
     pending DLL transactions (Manikanta Maddireddy)

  Xilinx host bridge driver:

   - Fix NWL Multi-MSI programming (Bharat Kumar Gogada)

  Endpoint support:

   - Fix 64bit BAR support (Alan Mikhak)

   - Fix pcitest build issues (Alan Mikhak, Andy Shevchenko)

  Bug fixes:

   - Fix NVIDIA GPU multi-function power dependencies (Abhishek Sahu)

   - Fix NVIDIA GPU HDA enablement issue (Lukas Wunner)

   - Ignore lockdep for sysfs "remove" (Marek Vasut)

  Misc:

   - Convert docs to reST (Changbin Du, Mauro Carvalho Chehab)"

* tag 'pci-v5.3-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci: (107 commits)
  PCI: Enable NVIDIA HDA controllers
  tools: PCI: Fix installation when `make tools/pci_install`
  PCI: dwc: pci-dra7xx: Fix compilation when !CONFIG_GPIOLIB
  PCI: Fix typos and whitespace errors
  PCI: mobiveil: Fix INTx interrupt clearing in mobiveil_pcie_isr()
  PCI: mobiveil: Fix infinite-loop in the INTx handling function
  PCI: mobiveil: Move PCIe PIO enablement out of inbound window routine
  PCI: mobiveil: Add upper 32-bit PCI base address setup in inbound window
  PCI: mobiveil: Add upper 32-bit CPU base address setup in outbound window
  PCI: mobiveil: Mask out hardcoded bits in inbound/outbound windows setup
  PCI: mobiveil: Clear the control fields before updating it
  PCI: mobiveil: Add configured inbound windows counter
  PCI: mobiveil: Fix the valid check for inbound and outbound windows
  PCI: mobiveil: Clean-up program_{ib/ob}_windows()
  PCI: mobiveil: Remove an unnecessary return value check
  PCI: mobiveil: Fix error return values
  PCI: mobiveil: Refactor the MEM/IO outbound window initialization
  PCI: mobiveil: Make some register updates more readable
  PCI: mobiveil: Reformat the code for readability
  dt-bindings: PCI: mobiveil: Change gpio_slave and apb_csr to optional
  ...

38 files changed, 1335 insertions, 550 deletions

diff --git a/drivers/pci/ats.c b/drivers/pci/ats.c
index 97c08146534a..e18499243f84 100644
--- a/drivers/pci/ats.c
+++ b/drivers/pci/ats.c
@@ -432,7 +432,7 @@ EXPORT_SYMBOL_GPL(pci_prg_resp_pasid_required);
  * @pdev: PCI device structure
  *
  * Returns negative value when PASID capability is not present.
- * Otherwise it returns the numer of supported PASIDs.
+ * Otherwise it returns the number of supported PASIDs.
  */
 int pci_max_pasids(struct pci_dev *pdev)
 {
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index 011c57cae4b0..fe9f9f13ce11 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -174,14 +174,14 @@ config PCIE_IPROC_MSI
 	  PCIe controller
 
 config PCIE_ALTERA
-	bool "Altera PCIe controller"
+	tristate "Altera PCIe controller"
 	depends on ARM || NIOS2 || ARM64 || COMPILE_TEST
 	help
 	  Say Y here if you want to enable PCIe controller support on Altera
 	  FPGA.
 
 config PCIE_ALTERA_MSI
-	bool "Altera PCIe MSI feature"
+	tristate "Altera PCIe MSI feature"
 	depends on PCIE_ALTERA
 	depends on PCI_MSI_IRQ_DOMAIN
 	help
diff --git a/drivers/pci/controller/dwc/Kconfig b/drivers/pci/controller/dwc/Kconfig
index a6ce1ee51b4c..6ea778ae4877 100644
--- a/drivers/pci/controller/dwc/Kconfig
+++ b/drivers/pci/controller/dwc/Kconfig
@@ -90,7 +90,7 @@ config PCI_EXYNOS
 
 config PCI_IMX6
 	bool "Freescale i.MX6/7/8 PCIe controller"
-	depends on SOC_IMX6Q || SOC_IMX7D || (ARM64 && ARCH_MXC) || COMPILE_TEST
+	depends on ARCH_MXC || COMPILE_TEST
 	depends on PCI_MSI_IRQ_DOMAIN
 	select PCIE_DW_HOST
 
diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c
index 419451efd58c..4234ddb4722f 100644
--- a/drivers/pci/controller/dwc/pci-dra7xx.c
+++ b/drivers/pci/controller/dwc/pci-dra7xx.c
@@ -26,6 +26,7 @@
 #include <linux/types.h>
 #include <linux/mfd/syscon.h>
 #include <linux/regmap.h>
+#include <linux/gpio/consumer.h>
 
 #include "../../pci.h"
 #include "pcie-designware.h"
diff --git a/drivers/pci/controller/dwc/pcie-armada8k.c b/drivers/pci/controller/dwc/pcie-armada8k.c
index 0c389a30ef5d..3d55dc78d999 100644
--- a/drivers/pci/controller/dwc/pcie-armada8k.c
+++ b/drivers/pci/controller/dwc/pcie-armada8k.c
@@ -25,10 +25,14 @@
 
 #include "pcie-designware.h"
 
+#define ARMADA8K_PCIE_MAX_LANES PCIE_LNK_X4
+
 struct armada8k_pcie {
 	struct dw_pcie *pci;
 	struct clk *clk;
 	struct clk *clk_reg;
+	struct phy *phy[ARMADA8K_PCIE_MAX_LANES];
+	unsigned int phy_count;
 };
 
 #define PCIE_VENDOR_REGS_OFFSET		0x8000
@@ -55,7 +59,7 @@ struct armada8k_pcie {
 #define PCIE_ARUSER_REG			(PCIE_VENDOR_REGS_OFFSET + 0x5C)
 #define PCIE_AWUSER_REG			(PCIE_VENDOR_REGS_OFFSET + 0x60)
 /*
- * AR/AW Cache defauls: Normal memory, Write-Back, Read / Write
+ * AR/AW Cache defaults: Normal memory, Write-Back, Read / Write
  * allocate
  */
 #define ARCACHE_DEFAULT_VALUE		0x3511
@@ -67,6 +71,76 @@ struct armada8k_pcie {
 
 #define to_armada8k_pcie(x)	dev_get_drvdata((x)->dev)
 
+static void armada8k_pcie_disable_phys(struct armada8k_pcie *pcie)
+{
+	int i;
+
+	for (i = 0; i < ARMADA8K_PCIE_MAX_LANES; i++) {
+		phy_power_off(pcie->phy[i]);
+		phy_exit(pcie->phy[i]);
+	}
+}
+
+static int armada8k_pcie_enable_phys(struct armada8k_pcie *pcie)
+{
+	int ret;
+	int i;
+
+	for (i = 0; i < ARMADA8K_PCIE_MAX_LANES; i++) {
+		ret = phy_init(pcie->phy[i]);
+		if (ret)
+			return ret;
+
+		ret = phy_set_mode_ext(pcie->phy[i], PHY_MODE_PCIE,
+				       pcie->phy_count);
+		if (ret) {
+			phy_exit(pcie->phy[i]);
+			return ret;
+		}
+
+		ret = phy_power_on(pcie->phy[i]);
+		if (ret) {
+			phy_exit(pcie->phy[i]);
+			return ret;
+		}
+	}
+
+	return 0;
+}
+
+static int armada8k_pcie_setup_phys(struct armada8k_pcie *pcie)
+{
+	struct dw_pcie *pci = pcie->pci;
+	struct device *dev = pci->dev;
+	struct device_node *node = dev->of_node;
+	int ret = 0;
+	int i;
+
+	for (i = 0; i < ARMADA8K_PCIE_MAX_LANES; i++) {
+		pcie->phy[i] = devm_of_phy_get_by_index(dev, node, i);
+		if (IS_ERR(pcie->phy[i]) &&
+		    (PTR_ERR(pcie->phy[i]) == -EPROBE_DEFER))
+			return PTR_ERR(pcie->phy[i]);
+
+		if (IS_ERR(pcie->phy[i])) {
+			pcie->phy[i] = NULL;
+			continue;
+		}
+
+		pcie->phy_count++;
+	}
+
+	/* Old bindings miss the PHY handle, so just warn if there is no PHY */
+	if (!pcie->phy_count)
+		dev_warn(dev, "No available PHY\n");
+
+	ret = armada8k_pcie_enable_phys(pcie);
+	if (ret)
+		dev_err(dev, "Failed to initialize PHY(s) (%d)\n", ret);
+
+	return ret;
+}
+
 static int armada8k_pcie_link_up(struct dw_pcie *pci)
 {
 	u32 reg;
@@ -249,14 +323,20 @@ static int armada8k_pcie_probe(struct platform_device *pdev)
 		goto fail_clkreg;
 	}
 
+	ret = armada8k_pcie_setup_phys(pcie);
+	if (ret)
+		goto fail_clkreg;
+
 	platform_set_drvdata(pdev, pcie);
 
 	ret = armada8k_add_pcie_port(pcie, pdev);
 	if (ret)
-		goto fail_clkreg;
+		goto disable_phy;
 
 	return 0;
 
+disable_phy:
+	armada8k_pcie_disable_phys(pcie);
 fail_clkreg:
 	clk_disable_unprepare(pcie->clk_reg);
 fail:
diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index 77db32529319..f93252d0da5b 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -311,6 +311,7 @@ void dw_pcie_msi_init(struct pcie_port *pp)
 	dw_pcie_wr_own_conf(pp, PCIE_MSI_ADDR_HI, 4,
 			    upper_32_bits(msi_target));
 }
+EXPORT_SYMBOL_GPL(dw_pcie_msi_init);
 
 int dw_pcie_host_init(struct pcie_port *pp)
 {
@@ -495,6 +496,16 @@ err_free_msi:
 		dw_pcie_free_msi(pp);
 	return ret;
 }
+EXPORT_SYMBOL_GPL(dw_pcie_host_init);
+
+void dw_pcie_host_deinit(struct pcie_port *pp)
+{
+	pci_stop_root_bus(pp->root_bus);
+	pci_remove_root_bus(pp->root_bus);
+	if (pci_msi_enabled() && !pp->ops->msi_host_init)
+		dw_pcie_free_msi(pp);
+}
+EXPORT_SYMBOL_GPL(dw_pcie_host_deinit);
 
 static int dw_pcie_access_other_conf(struct pcie_port *pp, struct pci_bus *bus,
 				     u32 devfn, int where, int size, u32 *val,
@@ -687,3 +698,4 @@ void dw_pcie_setup_rc(struct pcie_port *pp)
 	val |= PORT_LOGIC_SPEED_CHANGE;
 	dw_pcie_wr_own_conf(pp, PCIE_LINK_WIDTH_SPEED_CONTROL, 4, val);
 }
+EXPORT_SYMBOL_GPL(dw_pcie_setup_rc);
diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c
index 9d7c51c32b3b..7d25102c304c 100644
--- a/drivers/pci/controller/dwc/pcie-designware.c
+++ b/drivers/pci/controller/dwc/pcie-designware.c
@@ -34,6 +34,7 @@ int dw_pcie_read(void __iomem *addr, int size, u32 *val)
 
 	return PCIBIOS_SUCCESSFUL;
 }
+EXPORT_SYMBOL_GPL(dw_pcie_read);
 
 int dw_pcie_write(void __iomem *addr, int size, u32 val)
 {
@@ -51,69 +52,97 @@ int dw_pcie_write(void __iomem *addr, int size, u32 val)
 
 	return PCIBIOS_SUCCESSFUL;
 }
+EXPORT_SYMBOL_GPL(dw_pcie_write);
 
-u32 __dw_pcie_read_dbi(struct dw_pcie *pci, void __iomem *base, u32 reg,
-		       size_t size)
+u32 dw_pcie_read_dbi(struct dw_pcie *pci, u32 reg, size_t size)
 {
 	int ret;
 	u32 val;
 
 	if (pci->ops->read_dbi)
-		return pci->ops->read_dbi(pci, base, reg, size);
+		return pci->ops->read_dbi(pci, pci->dbi_base, reg, size);
 
-	ret = dw_pcie_read(base + reg, size, &val);
+	ret = dw_pcie_read(pci->dbi_base + reg, size, &val);
 	if (ret)
 		dev_err(pci->dev, "Read DBI address failed\n");
 
 	return val;
 }
+EXPORT_SYMBOL_GPL(dw_pcie_read_dbi);
 
-void __dw_pcie_write_dbi(struct dw_pcie *pci, void __iomem *base, u32 reg,
-			 size_t size, u32 val)
+void dw_pcie_write_dbi(struct dw_pcie *pci, u32 reg, size_t size, u32 val)
 {
 	int ret;
 
 	if (pci->ops->write_dbi) {
-		pci->ops->write_dbi(pci, base, reg, size, val);
+		pci->ops->write_dbi(pci, pci->dbi_base, reg, size, val);
 		return;
 	}
 
-	ret = dw_pcie_write(base + reg, size, val);
+	ret = dw_pcie_write(pci->dbi_base + reg, size, val);
 	if (ret)
 		dev_err(pci->dev, "Write DBI address failed\n");
 }
+EXPORT_SYMBOL_GPL(dw_pcie_write_dbi);
 
-u32 __dw_pcie_read_dbi2(struct dw_pcie *pci, void __iomem *base, u32 reg,
-			size_t size)
+u32 dw_pcie_read_dbi2(struct dw_pcie *pci, u32 reg, size_t size)
 {
 	int ret;
 	u32 val;
 
 	if (pci->ops->read_dbi2)
-		return pci->ops->read_dbi2(pci, base, reg, size);
+		return pci->ops->read_dbi2(pci, pci->dbi_base2, reg, size);
 
-	ret = dw_pcie_read(base + reg, size, &val);
+	ret = dw_pcie_read(pci->dbi_base2 + reg, size, &val);
 	if (ret)
 		dev_err(pci->dev, "read DBI address failed\n");
 
 	return val;
 }
 
-void __dw_pcie_write_dbi2(struct dw_pcie *pci, void __iomem *base, u32 reg,
-			  size_t size, u32 val)
+void dw_pcie_write_dbi2(struct dw_pcie *pci, u32 reg, size_t size, u32 val)
 {
 	int ret;
 
 	if (pci->ops->write_dbi2) {
-		pci->ops->write_dbi2(pci, base, reg, size, val);
+		pci->ops->write_dbi2(pci, pci->dbi_base2, reg, size, val);
 		return;
 	}
 
-	ret = dw_pcie_write(base + reg, size, val);
+	ret = dw_pcie_write(pci->dbi_base2 + reg, size, val);
 	if (ret)
 		dev_err(pci->dev, "write DBI address failed\n");
 }
 
+u32 dw_pcie_read_atu(struct dw_pcie *pci, u32 reg, size_t size)
+{
+	int ret;
+	u32 val;
+
+	if (pci->ops->read_dbi)
+		return pci->ops->read_dbi(pci, pci->atu_base, reg, size);
+
+	ret = dw_pcie_read(pci->atu_base + reg, size, &val);
+	if (ret)
+		dev_err(pci->dev, "Read ATU address failed\n");
+
+	return val;
+}
+
+void dw_pcie_write_atu(struct dw_pcie *pci, u32 reg, size_t size, u32 val)
+{
+	int ret;
+
+	if (pci->ops->write_dbi) {
+		pci->ops->write_dbi(pci, pci->atu_base, reg, size, val);
+		return;
+	}
+
+	ret = dw_pcie_write(pci->atu_base + reg, size, val);
+	if (ret)
+		dev_err(pci->dev, "Write ATU address failed\n");
+}
+
 static u32 dw_pcie_readl_ob_unroll(struct dw_pcie *pci, u32 index, u32 reg)
 {
 	u32 offset = PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(index);
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index b8993f2b78df..ffed084a0b4f 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -254,14 +254,12 @@ struct dw_pcie {
 int dw_pcie_read(void __iomem *addr, int size, u32 *val);
 int dw_pcie_write(void __iomem *addr, int size, u32 val);
 
-u32 __dw_pcie_read_dbi(struct dw_pcie *pci, void __iomem *base, u32 reg,
-		       size_t size);
-void __dw_pcie_write_dbi(struct dw_pcie *pci, void __iomem *base, u32 reg,
-			 size_t size, u32 val);
-u32 __dw_pcie_read_dbi2(struct dw_pcie *pci, void __iomem *base, u32 reg,
-			size_t size);
-void __dw_pcie_write_dbi2(struct dw_pcie *pci, void __iomem *base, u32 reg,
-			  size_t size, u32 val);
+u32 dw_pcie_read_dbi(struct dw_pcie *pci, u32 reg, size_t size);
+void dw_pcie_write_dbi(struct dw_pcie *pci, u32 reg, size_t size, u32 val);
+u32 dw_pcie_read_dbi2(struct dw_pcie *pci, u32 reg, size_t size);
+void dw_pcie_write_dbi2(struct dw_pcie *pci, u32 reg, size_t size, u32 val);
+u32 dw_pcie_read_atu(struct dw_pcie *pci, u32 reg, size_t size);
+void dw_pcie_write_atu(struct dw_pcie *pci, u32 reg, size_t size, u32 val);
 int dw_pcie_link_up(struct dw_pcie *pci);
 int dw_pcie_wait_for_link(struct dw_pcie *pci);
 void dw_pcie_prog_outbound_atu(struct dw_pcie *pci, int index,
@@ -275,52 +273,52 @@ void dw_pcie_setup(struct dw_pcie *pci);
 
 static inline void dw_pcie_writel_dbi(struct dw_pcie *pci, u32 reg, u32 val)
 {
-	__dw_pcie_write_dbi(pci, pci->dbi_base, reg, 0x4, val);
+	dw_pcie_write_dbi(pci, reg, 0x4, val);
 }
 
 static inline u32 dw_pcie_readl_dbi(struct dw_pcie *pci, u32 reg)
 {
-	return __dw_pcie_read_dbi(pci, pci->dbi_base, reg, 0x4);
+	return dw_pcie_read_dbi(pci, reg, 0x4);
 }
 
 static inline void dw_pcie_writew_dbi(struct dw_pcie *pci, u32 reg, u16 val)
 {
-	__dw_pcie_write_dbi(pci, pci->dbi_base, reg, 0x2, val);
+	dw_pcie_write_dbi(pci, reg, 0x2, val);
 }
 
 static inline u16 dw_pcie_readw_dbi(struct dw_pcie *pci, u32 reg)
 {
-	return __dw_pcie_read_dbi(pci, pci->dbi_base, reg, 0x2);
+	return dw_pcie_read_dbi(pci, reg, 0x2);
 }
 
 static inline void dw_pcie_writeb_dbi(struct dw_pcie *pci, u32 reg, u8 val)
 {
-	__dw_pcie_write_dbi(pci, pci->dbi_base, reg, 0x1, val);
+	dw_pcie_write_dbi(pci, reg, 0x1, val);
 }
 
 static inline u8 dw_pcie_readb_dbi(struct dw_pcie *pci, u32 reg)
 {
-	return __dw_pcie_read_dbi(pci, pci->dbi_base, reg, 0x1);
+	return dw_pcie_read_dbi(pci, reg, 0x1);
 }
 
 static inline void dw_pcie_writel_dbi2(struct dw_pcie *pci, u32 reg, u32 val)
 {
-	__dw_pcie_write_dbi2(pci, pci->dbi_base2, reg, 0x4, val);
+	dw_pcie_write_dbi2(pci, reg, 0x4, val);
 }
 
 static inline u32 dw_pcie_readl_dbi2(struct dw_pcie *pci, u32 reg)
 {
-	return __dw_pcie_read_dbi2(pci, pci->dbi_base2, reg, 0x4);
+	return dw_pcie_read_dbi2(pci, reg, 0x4);
 }
 
 static inline void dw_pcie_writel_atu(struct dw_pcie *pci, u32 reg, u32 val)
 {
-	__dw_pcie_write_dbi(pci, pci->atu_base, reg, 0x4, val);
+	dw_pcie_write_atu(pci, reg, 0x4, val);
 }
 
 static inline u32 dw_pcie_readl_atu(struct dw_pcie *pci, u32 reg)
 {
-	return __dw_pcie_read_dbi(pci, pci->atu_base, reg, 0x4);
+	return dw_pcie_read_atu(pci, reg, 0x4);
 }
 
 static inline void dw_pcie_dbi_ro_wr_en(struct dw_pcie *pci)
@@ -351,6 +349,7 @@ void dw_pcie_msi_init(struct pcie_port *pp);
 void dw_pcie_free_msi(struct pcie_port *pp);
 void dw_pcie_setup_rc(struct pcie_port *pp);
 int dw_pcie_host_init(struct pcie_port *pp);
+void dw_pcie_host_deinit(struct pcie_port *pp);
 int dw_pcie_allocate_domains(struct pcie_port *pp);
 #else
 static inline irqreturn_t dw_handle_msi_irq(struct pcie_port *pp)
@@ -375,6 +374,10 @@ static inline int dw_pcie_host_init(struct pcie_port *pp)
 	return 0;
 }
 
+static inline void dw_pcie_host_deinit(struct pcie_port *pp)
+{
+}
+
 static inline int dw_pcie_allocate_domains(struct pcie_port *pp)
 {
 	return 0;
diff --git a/drivers/pci/controller/dwc/pcie-kirin.c b/drivers/pci/controller/dwc/pcie-kirin.c
index 9b599296205d..8df1914226be 100644
--- a/drivers/pci/controller/dwc/pcie-kirin.c
+++ b/drivers/pci/controller/dwc/pcie-kirin.c
@@ -2,7 +2,7 @@
 /*
  * PCIe host controller driver for Kirin Phone SoCs
  *
- * Copyright (C) 2017 Hilisicon Electronics Co., Ltd.
+ * Copyright (C) 2017 HiSilicon Electronics Co., Ltd.
  *		http://www.huawei.com
  *
  * Author: Xiaowei Song <songxiaowei@huawei.com>
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index 0ed235d560e3..7e581748ee9f 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -112,10 +112,10 @@ struct qcom_pcie_resources_2_3_2 {
 	struct regulator_bulk_data supplies[QCOM_PCIE_2_3_2_MAX_SUPPLY];
 };
 
+#define QCOM_PCIE_2_4_0_MAX_CLOCKS	4
 struct qcom_pcie_resources_2_4_0 {
-	struct clk *aux_clk;
-	struct clk *master_clk;
-	struct clk *slave_clk;
+	struct clk_bulk_data clks[QCOM_PCIE_2_4_0_MAX_CLOCKS];
+	int num_clks;
 	struct reset_control *axi_m_reset;
 	struct reset_control *axi_s_reset;
 	struct reset_control *pipe_reset;
@@ -178,6 +178,8 @@ static void qcom_ep_reset_assert(struct qcom_pcie *pcie)
 
 static void qcom_ep_reset_deassert(struct qcom_pcie *pcie)
 {
+	/* Ensure that PERST has been asserted for at least 100 ms */
+	msleep(100);
 	gpiod_set_value_cansleep(pcie->reset, 0);
 	usleep_range(PERST_DELAY_US, PERST_DELAY_US + 500);
 }
@@ -638,18 +640,20 @@ static int qcom_pcie_get_resources_2_4_0(struct qcom_pcie *pcie)
 	struct qcom_pcie_resources_2_4_0 *res = &pcie->res.v2_4_0;
 	struct dw_pcie *pci = pcie->pci;
 	struct device *dev = pci->dev;
+	bool is_ipq = of_device_is_compatible(dev->of_node, "qcom,pcie-ipq4019");
+	int ret;
 
-	res->aux_clk = devm_clk_get(dev, "aux");
-	if (IS_ERR(res->aux_clk))
-		return PTR_ERR(res->aux_clk);
+	res->clks[0].id = "aux";
+	res->clks[1].id = "master_bus";
+	res->clks[2].id = "slave_bus";
+	res->clks[3].id = "iface";
 
-	res->master_clk = devm_clk_get(dev, "master_bus");
-	if (IS_ERR(res->master_clk))
-		return PTR_ERR(res->master_clk);
+	/* qcom,pcie-ipq4019 is defined without "iface" */
+	res->num_clks = is_ipq ? 3 : 4;
 
-	res->slave_clk = devm_clk_get(dev, "slave_bus");
-	if (IS_ERR(res->slave_clk))
-		return PTR_ERR(res->slave_clk);
+	ret = devm_clk_bulk_get(dev, res->num_clks, res->clks);
+	if (ret < 0)
+		return ret;
 
 	res->axi_m_reset = devm_reset_control_get_exclusive(dev, "axi_m");
 	if (IS_ERR(res->axi_m_reset))
@@ -659,27 +663,33 @@ static int qcom_pcie_get_resources_2_4_0(struct qcom_pcie *pcie)
 	if (IS_ERR(res->axi_s_reset))
 		return PTR_ERR(res->axi_s_reset);
 
-	res->pipe_reset = devm_reset_control_get_exclusive(dev, "pipe");
-	if (IS_ERR(res->pipe_reset))
-		return PTR_ERR(res->pipe_reset);
-
-	res->axi_m_vmid_reset = devm_reset_control_get_exclusive(dev,
-								 "axi_m_vmid");
-	if (IS_ERR(res->axi_m_vmid_reset))
-		return PTR_ERR(res->axi_m_vmid_reset);
-
-	res->axi_s_xpu_reset = devm_reset_control_get_exclusive(dev,
-								"axi_s_xpu");
-	if (IS_ERR(res->axi_s_xpu_reset))
-		return PTR_ERR(res->axi_s_xpu_reset);
-
-	res->parf_reset = devm_reset_control_get_exclusive(dev, "parf");
-	if (IS_ERR(res->parf_reset))
-		return PTR_ERR(res->parf_reset);
-
-	res->phy_reset = devm_reset_control_get_exclusive(dev, "phy");
-	if (IS_ERR(res->phy_reset))
-		return PTR_ERR(res->phy_reset);
+	if (is_ipq) {
+		/*
+		 * These resources relates to the PHY or are secure clocks, but
+		 * are controlled here for IPQ4019
+		 */
+		res->pipe_reset = devm_reset_control_get_exclusive(dev, "pipe");
+		if (IS_ERR(res->pipe_reset))
+			return PTR_ERR(res->pipe_reset);
+
+		res->axi_m_vmid_reset = devm_reset_control_get_exclusive(dev,
+									 "axi_m_vmid");
+		if (IS_ERR(res->axi_m_vmid_reset))
+			return PTR_ERR(res->axi_m_vmid_reset);
+
+		res->axi_s_xpu_reset = devm_reset_control_get_exclusive(dev,
+									"axi_s_xpu");
+		if (IS_ERR(res->axi_s_xpu_reset))
+			return PTR_ERR(res->axi_s_xpu_reset);
+
+		res->parf_reset = devm_reset_control_get_exclusive(dev, "parf");
+		if (IS_ERR(res->parf_reset))
+			return PTR_ERR(res->parf_reset);
+
+		res->phy_reset = devm_reset_control_get_exclusive(dev, "phy");
+		if (IS_ERR(res->phy_reset))
+			return PTR_ERR(res->phy_reset);
+	}
 
 	res->axi_m_sticky_reset = devm_reset_control_get_exclusive(dev,
 								   "axi_m_sticky");
@@ -699,9 +709,11 @@ static int qcom_pcie_get_resources_2_4_0(struct qcom_pcie *pcie)
 	if (IS_ERR(res->ahb_reset))
 		return PTR_ERR(res->ahb_reset);
 
-	res->phy_ahb_reset = devm_reset_control_get_exclusive(dev, "phy_ahb");
-	if (IS_ERR(res->phy_ahb_reset))
-		return PTR_ERR(res->phy_ahb_reset);
+	if (is_ipq) {
+		res->phy_ahb_reset = devm_reset_control_get_exclusive(dev, "phy_ahb");
+		if (IS_ERR(res->phy_ahb_reset))
+			return PTR_ERR(res->phy_ahb_reset);
+	}
 
 	return 0;
 }
@@ -719,9 +731,7 @@ static void qcom_pcie_deinit_2_4_0(struct qcom_pcie *pcie)
 	reset_control_assert(res->axi_m_sticky_reset);
 	reset_control_assert(res->pwr_reset);
 	reset_control_assert(res->ahb_reset);
-	clk_disable_unprepare(res->aux_clk);
-	clk_disable_unprepare(res->master_clk);
-	clk_disable_unprepare(res->slave_clk);
+	clk_bulk_disable_unprepare(res->num_clks, res->clks);
 }
 
 static int qcom_pcie_init_2_4_0(struct qcom_pcie *pcie)
@@ -850,23 +860,9 @@ static int qcom_pcie_init_2_4_0(struct qcom_pcie *pcie)
 
 	usleep_range(10000, 12000);
 
-	ret = clk_prepare_enable(res->aux_clk);
-	if (ret) {
-		dev_err(dev, "cannot prepare/enable iface clock\n");
-		goto err_clk_aux;
-	}
-
-	ret = clk_prepare_enable(res->master_clk);
-	if (ret) {
-		dev_err(dev, "cannot prepare/enable core clock\n");
-		goto err_clk_axi_m;
-	}
-
-	ret = clk_prepare_enable(res->slave_clk);
-	if (ret) {
-		dev_err(dev, "cannot prepare/enable phy clock\n");
-		goto err_clk_axi_s;
-	}
+	ret = clk_bulk_prepare_enable(res->num_clks, res->clks);
+	if (ret)
+		goto err_clks;
 
 	/* enable PCIe clocks and resets */
 	val = readl(pcie->parf + PCIE20_PARF_PHY_CTRL);
@@ -891,11 +887,7 @@ static int qcom_pcie_init_2_4_0(struct qcom_pcie *pcie)
 
 	return 0;
 
-err_clk_axi_s:
-	clk_disable_unprepare(res->master_clk);
-err_clk_axi_m:
-	clk_disable_unprepare(res->aux_clk);
-err_clk_aux:
+err_clks:
 	reset_control_assert(res->ahb_reset);
 err_rst_ahb:
 	reset_control_assert(res->pwr_reset);
@@ -1289,6 +1281,7 @@ static const struct of_device_id qcom_pcie_match[] = {
 	{ .compatible = "qcom,pcie-msm8996", .data = &ops_2_3_2 },
 	{ .compatible = "qcom,pcie-ipq8074", .data = &ops_2_3_3 },
 	{ .compatible = "qcom,pcie-ipq4019", .data = &ops_2_4_0 },
+	{ .compatible = "qcom,pcie-qcs404", .data = &ops_2_4_0 },
 	{ }
 };
 
diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index 134e0306ff00..fc0fe4d4de49 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -308,7 +308,7 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 
 	advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_MASK_REG);
 
-	/* Unmask all MSI's */
+	/* Unmask all MSIs */
 	advk_writel(pcie, 0, PCIE_MSI_MASK_REG);
 
 	/* Enable summary interrupt for GIC SPI source */
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 82acd6155adf..40b625458afa 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -1875,6 +1875,7 @@ static void hv_pci_devices_present(struct hv_pcibus_device *hbus,
 static void hv_eject_device_work(struct work_struct *work)
 {
 	struct pci_eject_response *ejct_pkt;
+	struct hv_pcibus_device *hbus;
 	struct hv_pci_dev *hpdev;
 	struct pci_dev *pdev;
 	unsigned long flags;
@@ -1885,6 +1886,7 @@ static void hv_eject_device_work(struct work_struct *work)
 	} ctxt;
 
 	hpdev = container_of(work, struct hv_pci_dev, wrk);
+	hbus = hpdev->hbus;
 
 	WARN_ON(hpdev->state != hv_pcichild_ejecting);
 
@@ -1895,8 +1897,7 @@ static void hv_eject_device_work(struct work_struct *work)
 	 * because hbus->pci_bus may not exist yet.
 	 */
 	wslot = wslot_to_devfn(hpdev->desc.win_slot.slot);
-	pdev = pci_get_domain_bus_and_slot(hpdev->hbus->sysdata.domain, 0,
-					   wslot);
+	pdev = pci_get_domain_bus_and_slot(hbus->sysdata.domain, 0, wslot);
 	if (pdev) {
 		pci_lock_rescan_remove();
 		pci_stop_and_remove_bus_device(pdev);
@@ -1904,9 +1905,9 @@ static void hv_eject_device_work(struct work_struct *work)
 		pci_unlock_rescan_remove();
 	}
 
-	spin_lock_irqsave(&hpdev->hbus->device_list_lock, flags);
+	spin_lock_irqsave(&hbus->device_list_lock, flags);
 	list_del(&hpdev->list_entry);
-	spin_unlock_irqrestore(&hpdev->hbus->device_list_lock, flags);
+	spin_unlock_irqrestore(&hbus->device_list_lock, flags);
 
 	if (hpdev->pci_slot)
 		pci_destroy_slot(hpdev->pci_slot);
@@ -1915,7 +1916,7 @@ static void hv_eject_device_work(struct work_struct *work)
 	ejct_pkt = (struct pci_eject_response *)&ctxt.pkt.message;
 	ejct_pkt->message_type.type = PCI_EJECTION_COMPLETE;
 	ejct_pkt->wslot.slot = hpdev->desc.win_slot.slot;
-	vmbus_sendpacket(hpdev->hbus->hdev->channel, ejct_pkt,
+	vmbus_sendpacket(hbus->hdev->channel, ejct_pkt,
 			 sizeof(*ejct_pkt), (unsigned long)&ctxt.pkt,
 			 VM_PKT_DATA_INBAND, 0);
 
@@ -1924,7 +1925,9 @@ static void hv_eject_device_work(struct work_struct *work)
 	/* For the two refs got in new_pcichild_device() */
 	put_pcichild(hpdev);
 	put_pcichild(hpdev);
-	put_hvpcibus(hpdev->hbus);
+	/* hpdev has been freed. Do not use it any more. */
+
+	put_hvpcibus(hbus);
 }
 
 /**
diff --git a/drivers/pci/controller/pci-tegra.c b/drivers/pci/controller/pci-tegra.c
index 464ba2538d52..9a917b2456f6 100644
--- a/drivers/pci/controller/pci-tegra.c
+++ b/drivers/pci/controller/pci-tegra.c
@@ -17,6 +17,7 @@
 #include <linux/debugfs.h>
 #include <linux/delay.h>
 #include <linux/export.h>
+#include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
 #include <linux/iopoll.h>
 #include <linux/irq.h>
@@ -30,6 +31,7 @@
 #include <linux/of_platform.h>
 #include <linux/pci.h>
 #include <linux/phy/phy.h>
+#include <linux/pinctrl/consumer.h>
 #include <linux/platform_device.h>
 #include <linux/reset.h>
 #include <linux/sizes.h>
@@ -95,7 +97,8 @@
 #define AFI_MSI_EN_VEC7		0xa8
 
 #define AFI_CONFIGURATION		0xac
-#define  AFI_CONFIGURATION_EN_FPCI	(1 << 0)
+#define  AFI_CONFIGURATION_EN_FPCI		(1 << 0)
+#define  AFI_CONFIGURATION_CLKEN_OVERRIDE	(1 << 31)
 
 #define AFI_FPCI_ERROR_MASKS	0xb0
 
@@ -159,13 +162,14 @@
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_211	(0x1 << 20)
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_411	(0x2 << 20)
 #define  AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_111	(0x2 << 20)
+#define  AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO(x)		(1 << ((x) + 29))
+#define  AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO_ALL		(0x7 << 29)
 
 #define AFI_FUSE			0x104
 #define  AFI_FUSE_PCIE_T0_GEN2_DIS	(1 << 2)
 
 #define AFI_PEX0_CTRL			0x110
 #define AFI_PEX1_CTRL			0x118
-#define AFI_PEX2_CTRL			0x128
 #define  AFI_PEX_CTRL_RST		(1 << 0)
 #define  AFI_PEX_CTRL_CLKREQ_EN		(1 << 1)
 #define  AFI_PEX_CTRL_REFCLK_EN		(1 << 3)
@@ -177,20 +181,74 @@
 
 #define AFI_PEXBIAS_CTRL_0		0x168
 
+#define RP_PRIV_XP_DL		0x00000494
+#define  RP_PRIV_XP_DL_GEN2_UPD_FC_TSHOLD	(0x1ff << 1)
+
+#define RP_RX_HDR_LIMIT		0x00000e00
+#define  RP_RX_HDR_LIMIT_PW_MASK	(0xff << 8)
+#define  RP_RX_HDR_LIMIT_PW		(0x0e << 8)
+
+#define RP_ECTL_2_R1	0x00000e84
+#define  RP_ECTL_2_R1_RX_CTLE_1C_MASK		0xffff
+
+#define RP_ECTL_4_R1	0x00000e8c
+#define  RP_ECTL_4_R1_RX_CDR_CTRL_1C_MASK	(0xffff << 16)
+#define  RP_ECTL_4_R1_RX_CDR_CTRL_1C_SHIFT	16
+
+#define RP_ECTL_5_R1	0x00000e90
+#define  RP_ECTL_5_R1_RX_EQ_CTRL_L_1C_MASK	0xffffffff
+
+#define RP_ECTL_6_R1	0x00000e94
+#define  RP_ECTL_6_R1_RX_EQ_CTRL_H_1C_MASK	0xffffffff
+
+#define RP_ECTL_2_R2	0x00000ea4
+#define  RP_ECTL_2_R2_RX_CTLE_1C_MASK	0xffff
+
+#define RP_ECTL_4_R2	0x00000eac
+#define  RP_ECTL_4_R2_RX_CDR_CTRL_1C_MASK	(0xffff << 16)
+#define  RP_ECTL_4_R2_RX_CDR_CTRL_1C_SHIFT	16
+
+#define RP_ECTL_5_R2	0x00000eb0
+#define  RP_ECTL_5_R2_RX_EQ_CTRL_L_1C_MASK	0xffffffff
+
+#define RP_ECTL_6_R2	0x00000eb4
+#define  RP_ECTL_6_R2_RX_EQ_CTRL_H_1C_MASK	0xffffffff
+
 #define RP_VEND_XP	0x00000f00
-#define  RP_VEND_XP_DL_UP	(1 << 30)
+#define  RP_VEND_XP_DL_UP			(1 << 30)
+#define  RP_VEND_XP_OPPORTUNISTIC_ACK		(1 << 27)
+#define  RP_VEND_XP_OPPORTUNISTIC_UPDATEFC	(1 << 28)
+#define  RP_VEND_XP_UPDATE_FC_THRESHOLD_MASK	(0xff << 18)
+
+#define RP_VEND_CTL0	0x00000f44
+#define  RP_VEND_CTL0_DSK_RST_PULSE_WIDTH_MASK	(0xf << 12)
+#define  RP_VEND_CTL0_DSK_RST_PULSE_WIDTH	(0x9 << 12)
+
+#define RP_VEND_CTL1	0x00000f48
+#define  RP_VEND_CTL1_ERPT	(1 << 13)
+
+#define RP_VEND_XP_BIST	0x00000f4c
+#define  RP_VEND_XP_BIST_GOTO_L1_L2_AFTER_DLLP_DONE	(1 << 28)
 
 #define RP_VEND_CTL2 0x00000fa8
 #define  RP_VEND_CTL2_PCA_ENABLE (1 << 7)
 
 #define RP_PRIV_MISC	0x00000fe0
-#define  RP_PRIV_MISC_PRSNT_MAP_EP_PRSNT (0xe << 0)
-#define  RP_PRIV_MISC_PRSNT_MAP_EP_ABSNT (0xf << 0)
+#define  RP_PRIV_MISC_PRSNT_MAP_EP_PRSNT		(0xe << 0)
+#define  RP_PRIV_MISC_PRSNT_MAP_EP_ABSNT		(0xf << 0)
+#define  RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD_MASK	(0x7f << 16)
+#define  RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD		(0xf << 16)
+#define  RP_PRIV_MISC_CTLR_CLK_CLAMP_ENABLE		(1 << 23)
+#define  RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD_MASK	(0x7f << 24)
+#define  RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD		(0xf << 24)
+#define  RP_PRIV_MISC_TMS_CLK_CLAMP_ENABLE		(1 << 31)
 
 #define RP_LINK_CONTROL_STATUS			0x00000090
 #define  RP_LINK_CONTROL_STATUS_DL_LINK_ACTIVE	0x20000000
 #define  RP_LINK_CONTROL_STATUS_LINKSTAT_MASK	0x3fff0000
 
+#define RP_LINK_CONTROL_STATUS_2		0x000000b0
+
 #define PADS_CTL_SEL		0x0000009c
 
 #define PADS_CTL		0x000000a0
@@ -226,6 +284,7 @@
 #define PADS_REFCLK_CFG_DRVI_SHIFT		12 /* 15:12 */
 
 #define PME_ACK_TIMEOUT 10000
+#define LINK_RETRAIN_TIMEOUT 100000 /* in usec */
 
 struct tegra_msi {
 	struct msi_controller chip;
@@ -249,10 +308,12 @@ struct tegra_pcie_soc {
 	unsigned int num_ports;
 	const struct tegra_pcie_port_soc *ports;
 	unsigned int msi_base_shift;
+	unsigned long afi_pex2_ctrl;
 	u32 pads_pll_ctl;
 	u32 tx_ref_sel;
 	u32 pads_refclk_cfg0;
 	u32 pads_refclk_cfg1;
+	u32 update_fc_threshold;
 	bool has_pex_clkreq_en;
 	bool has_pex_bias_ctrl;
 	bool has_intr_prsnt_sense;
@@ -260,6 +321,24 @@ struct tegra_pcie_soc {
 	bool has_gen2;
 	bool force_pca_enable;
 	bool program_uphy;
+	bool update_clamp_threshold;
+	bool program_deskew_time;
+	bool raw_violation_fixup;
+	bool update_fc_timer;
+	bool has_cache_bars;
+	struct {
+		struct {
+			u32 rp_ectl_2_r1;
+			u32 rp_ectl_4_r1;
+			u32 rp_ectl_5_r1;
+			u32 rp_ectl_6_r1;
+			u32 rp_ectl_2_r2;
+			u32 rp_ectl_4_r2;
+			u32 rp_ectl_5_r2;
+			u32 rp_ectl_6_r2;
+		} regs;
+		bool enable;
+	} ectl;
 };
 
 static inline struct tegra_msi *to_tegra_msi(struct msi_controller *chip)
@@ -321,6 +400,8 @@ struct tegra_pcie_port {
 	unsigned int lanes;
 
 	struct phy **phys;
+
+	struct gpio_desc *reset_gpio;
 };
 
 struct tegra_pcie_bus {
@@ -440,6 +521,7 @@ static struct pci_ops tegra_pcie_ops = {
 
 static unsigned long tegra_pcie_port_get_pex_ctrl(struct tegra_pcie_port *port)
 {
+	const struct tegra_pcie_soc *soc = port->pcie->soc;
 	unsigned long ret = 0;
 
 	switch (port->index) {
@@ -452,7 +534,7 @@ static unsigned long tegra_pcie_port_get_pex_ctrl(struct tegra_pcie_port *port)
 		break;
 
 	case 2:
-		ret = AFI_PEX2_CTRL;
+		ret = soc->afi_pex2_ctrl;
 		break;
 	}
 
@@ -465,15 +547,162 @@ static void tegra_pcie_port_reset(struct tegra_pcie_port *port)
 	unsigned long value;
 
 	/* pulse reset signal */
-	value = afi_readl(port->pcie, ctrl);
-	value &= ~AFI_PEX_CTRL_RST;
-	afi_writel(port->pcie, value, ctrl);
+	if (port->reset_gpio) {
+		gpiod_set_value(port->reset_gpio, 1);
+	} else {
+		value = afi_readl(port->pcie, ctrl);
+		value &= ~AFI_PEX_CTRL_RST;
+		afi_writel(port->pcie, value, ctrl);
+	}
 
 	usleep_range(1000, 2000);
 
-	value = afi_readl(port->pcie, ctrl);
-	value |= AFI_PEX_CTRL_RST;
-	afi_writel(port->pcie, value, ctrl);
+	if (port->reset_gpio) {
+		gpiod_set_value(port->reset_gpio, 0);
+	} else {
+		value = afi_readl(port->pcie, ctrl);
+		value |= AFI_PEX_CTRL_RST;
+		afi_writel(port->pcie, value, ctrl);
+	}
+}
+
+static void tegra_pcie_enable_rp_features(struct tegra_pcie_port *port)
+{
+	const struct tegra_pcie_soc *soc = port->pcie->soc;
+	u32 value;
+
+	/* Enable AER capability */
+	value = readl(port->base + RP_VEND_CTL1);
+	value |= RP_VEND_CTL1_ERPT;
+	writel(value, port->base + RP_VEND_CTL1);
+
+	/* Optimal settings to enhance bandwidth */
+	value = readl(port->base + RP_VEND_XP);
+	value |= RP_VEND_XP_OPPORTUNISTIC_ACK;
+	value |= RP_VEND_XP_OPPORTUNISTIC_UPDATEFC;
+	writel(value, port->base + RP_VEND_XP);
+
+	/*
+	 * LTSSM will wait for DLLP to finish before entering L1 or L2,
+	 * to avoid truncation of PM messages which results in receiver errors
+	 */
+	value = readl(port->base + RP_VEND_XP_BIST);
+	value |= RP_VEND_XP_BIST_GOTO_L1_L2_AFTER_DLLP_DONE;
+	writel(value, port->base + RP_VEND_XP_BIST);
+
+	value = readl(port->base + RP_PRIV_MISC);
+	value |= RP_PRIV_MISC_CTLR_CLK_CLAMP_ENABLE;
+	value |= RP_PRIV_MISC_TMS_CLK_CLAMP_ENABLE;
+
+	if (soc->update_clamp_threshold) {
+		value &= ~(RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD_MASK |
+				RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD_MASK);
+		value |= RP_PRIV_MISC_CTLR_CLK_CLAMP_THRESHOLD |
+			RP_PRIV_MISC_TMS_CLK_CLAMP_THRESHOLD;
+	}
+
+	writel(value, port->base + RP_PRIV_MISC);
+}
+
+static void tegra_pcie_program_ectl_settings(struct tegra_pcie_port *port)
+{
+	const struct tegra_pcie_soc *soc = port->pcie->soc;
+	u32 value;
+
+	value = readl(port->base + RP_ECTL_2_R1);
+	value &= ~RP_ECTL_2_R1_RX_CTLE_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_2_r1;
+	writel(value, port->base + RP_ECTL_2_R1);
+
+	value = readl(port->base + RP_ECTL_4_R1);
+	value &= ~RP_ECTL_4_R1_RX_CDR_CTRL_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_4_r1 <<
+				RP_ECTL_4_R1_RX_CDR_CTRL_1C_SHIFT;
+	writel(value, port->base + RP_ECTL_4_R1);
+
+	value = readl(port->base + RP_ECTL_5_R1);
+	value &= ~RP_ECTL_5_R1_RX_EQ_CTRL_L_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_5_r1;
+	writel(value, port->base + RP_ECTL_5_R1);
+
+	value = readl(port->base + RP_ECTL_6_R1);
+	value &= ~RP_ECTL_6_R1_RX_EQ_CTRL_H_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_6_r1;
+	writel(value, port->base + RP_ECTL_6_R1);
+
+	value = readl(port->base + RP_ECTL_2_R2);
+	value &= ~RP_ECTL_2_R2_RX_CTLE_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_2_r2;
+	writel(value, port->base + RP_ECTL_2_R2);
+
+	value = readl(port->base + RP_ECTL_4_R2);
+	value &= ~RP_ECTL_4_R2_RX_CDR_CTRL_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_4_r2 <<
+				RP_ECTL_4_R2_RX_CDR_CTRL_1C_SHIFT;
+	writel(value, port->base + RP_ECTL_4_R2);
+
+	value = readl(port->base + RP_ECTL_5_R2);
+	value &= ~RP_ECTL_5_R2_RX_EQ_CTRL_L_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_5_r2;
+	writel(value, port->base + RP_ECTL_5_R2);
+
+	value = readl(port->base + RP_ECTL_6_R2);
+	value &= ~RP_ECTL_6_R2_RX_EQ_CTRL_H_1C_MASK;
+	value |= soc->ectl.regs.rp_ectl_6_r2;
+	writel(value, port->base + RP_ECTL_6_R2);
+}
+
+static void tegra_pcie_apply_sw_fixup(struct tegra_pcie_port *port)
+{
+	const struct tegra_pcie_soc *soc = port->pcie->soc;
+	u32 value;
+
+	/*
+	 * Sometimes link speed change from Gen2 to Gen1 fails due to
+	 * instability in deskew logic on lane-0. Increase the deskew
+	 * retry time to resolve this issue.
+	 */
+	if (soc->program_deskew_time) {
+		value = readl(port->base + RP_VEND_CTL0);
+		value &= ~RP_VEND_CTL0_DSK_RST_PULSE_WIDTH_MASK;
+		value |= RP_VEND_CTL0_DSK_RST_PULSE_WIDTH;
+		writel(value, port->base + RP_VEND_CTL0);
+	}
+
+	/* Fixup for read after write violation. */
+	if (soc->raw_violation_fixup) {
+		value = readl(port->base + RP_RX_HDR_LIMIT);
+		value &= ~RP_RX_HDR_LIMIT_PW_MASK;
+		value |= RP_RX_HDR_LIMIT_PW;
+		writel(value, port->base + RP_RX_HDR_LIMIT);
+
+		value = readl(port->base + RP_PRIV_XP_DL);
+		value |= RP_PRIV_XP_DL_GEN2_UPD_FC_TSHOLD;
+		writel(value, port->base + RP_PRIV_XP_DL);
+
+		value = readl(port->base + RP_VEND_XP);
+		value &= ~RP_VEND_XP_UPDATE_FC_THRESHOLD_MASK;
+		value |= soc->update_fc_threshold;
+		writel(value, port->base + RP_VEND_XP);
+	}
+
+	if (soc->update_fc_timer) {
+		value = readl(port->base + RP_VEND_XP);
+		value &= ~RP_VEND_XP_UPDATE_FC_THRESHOLD_MASK;
+		value |= soc->update_fc_threshold;
+		writel(value, port->base + RP_VEND_XP);
+	}
+
+	/*
+	 * PCIe link doesn't come up with few legacy PCIe endpoints if
+	 * root port advertises both Gen-1 and Gen-2 speeds in Tegra.
+	 * Hence, the strategy followed here is to initially advertise
+	 * only Gen-1 and after link is up, retrain link to Gen-2 speed
+	 */
+	value = readl(port->base + RP_LINK_CONTROL_STATUS_2);
+	value &= ~PCI_EXP_LNKSTA_CLS;
+	value |= PCI_EXP_LNKSTA_CLS_2_5GB;
+	writel(value, port->base + RP_LINK_CONTROL_STATUS_2);
 }
 
 static void tegra_pcie_port_enable(struct tegra_pcie_port *port)
@@ -500,6 +729,13 @@ static void tegra_pcie_port_enable(struct tegra_pcie_port *port)
 		value |= RP_VEND_CTL2_PCA_ENABLE;
 		writel(value, port->base + RP_VEND_CTL2);
 	}
+
+	tegra_pcie_enable_rp_features(port);
+
+	if (soc->ectl.enable)
+		tegra_pcie_program_ectl_settings(port);
+
+	tegra_pcie_apply_sw_fixup(port);
 }
 
 static void tegra_pcie_port_disable(struct tegra_pcie_port *port)
@@ -521,6 +757,12 @@ static void tegra_pcie_port_disable(struct tegra_pcie_port *port)
 
 	value &= ~AFI_PEX_CTRL_REFCLK_EN;
 	afi_writel(port->pcie, value, ctrl);
+
+	/* disable PCIe port and set CLKREQ# as GPIO to allow PLLE power down */
+	value = afi_readl(port->pcie, AFI_PCIE_CONFIG);
+	value |= AFI_PCIE_CONFIG_PCIE_DISABLE(port->index);
+	value |= AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO(port->index);
+	afi_writel(port->pcie, value, AFI_PCIE_CONFIG);
 }
 
 static void tegra_pcie_port_free(struct tegra_pcie_port *port)
@@ -545,12 +787,15 @@ DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0bf1, tegra_pcie_fixup_class);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0e1c, tegra_pcie_fixup_class);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0e1d, tegra_pcie_fixup_class);
 
-/* Tegra PCIE requires relaxed ordering */
+/* Tegra20 and Tegra30 PCIE requires relaxed ordering */
 static void tegra_pcie_relax_enable(struct pci_dev *dev)
 {
 	pcie_capability_set_word(dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_RELAX_EN);
 }
-DECLARE_PCI_FIXUP_FINAL(PCI_ANY_ID, PCI_ANY_ID, tegra_pcie_relax_enable);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0bf0, tegra_pcie_relax_enable);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0bf1, tegra_pcie_relax_enable);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0e1c, tegra_pcie_relax_enable);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_NVIDIA, 0x0e1d, tegra_pcie_relax_enable);
 
 static int tegra_pcie_request_resources(struct tegra_pcie *pcie)
 {
@@ -635,7 +880,7 @@ static irqreturn_t tegra_pcie_isr(int irq, void *arg)
 	 * do not pollute kernel log with master abort reports since they
 	 * happen a lot during enumeration
 	 */
-	if (code == AFI_INTR_MASTER_ABORT)
+	if (code == AFI_INTR_MASTER_ABORT || code == AFI_INTR_PE_PRSNT_SENSE)
 		dev_dbg(dev, "%s, signature: %08x\n", err_msg[code], signature);
 	else
 		dev_err(dev, "%s, signature: %08x\n", err_msg[code], signature);
@@ -704,11 +949,13 @@ static void tegra_pcie_setup_translations(struct tegra_pcie *pcie)
 	afi_writel(pcie, 0, AFI_AXI_BAR5_SZ);
 	afi_writel(pcie, 0, AFI_FPCI_BAR5);
 
-	/* map all upstream transactions as uncached */
-	afi_writel(pcie, 0, AFI_CACHE_BAR0_ST);
-	afi_writel(pcie, 0, AFI_CACHE_BAR0_SZ);
-	afi_writel(pcie, 0, AFI_CACHE_BAR1_ST);
-	afi_writel(pcie, 0, AFI_CACHE_BAR1_SZ);
+	if (pcie->soc->has_cache_bars) {
+		/* map all upstream transactions as uncached */
+		afi_writel(pcie, 0, AFI_CACHE_BAR0_ST);
+		afi_writel(pcie, 0, AFI_CACHE_BAR0_SZ);
+		afi_writel(pcie, 0, AFI_CACHE_BAR1_ST);
+		afi_writel(pcie, 0, AFI_CACHE_BAR1_SZ);
+	}
 
 	/* MSI translations are setup only when needed */
 	afi_writel(pcie, 0, AFI_MSI_FPCI_BAR_ST);
@@ -852,7 +1099,6 @@ static int tegra_pcie_port_phy_power_off(struct tegra_pcie_port *port)
 static int tegra_pcie_phy_power_on(struct tegra_pcie *pcie)
 {
 	struct device *dev = pcie->dev;
-	const struct tegra_pcie_soc *soc = pcie->soc;
 	struct tegra_pcie_port *port;
 	int err;
 
@@ -878,12 +1124,6 @@ static int tegra_pcie_phy_power_on(struct tegra_pcie *pcie)
 		}
 	}
 
-	/* Configure the reference clock driver */
-	pads_writel(pcie, soc->pads_refclk_cfg0, PADS_REFCLK_CFG0);
-
-	if (soc->num_ports > 2)
-		pads_writel(pcie, soc->pads_refclk_cfg1, PADS_REFCLK_CFG1);
-
 	return 0;
 }
 
@@ -918,13 +1158,11 @@ static int tegra_pcie_phy_power_off(struct tegra_pcie *pcie)
 	return 0;
 }
 
-static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
+static void tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 {
-	struct device *dev = pcie->dev;
 	const struct tegra_pcie_soc *soc = pcie->soc;
 	struct tegra_pcie_port *port;
 	unsigned long value;
-	int err;
 
 	/* enable PLL power down */
 	if (pcie->phy) {
@@ -942,9 +1180,12 @@ static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 	value = afi_readl(pcie, AFI_PCIE_CONFIG);
 	value &= ~AFI_PCIE_CONFIG_SM2TMS0_XBAR_CONFIG_MASK;
 	value |= AFI_PCIE_CONFIG_PCIE_DISABLE_ALL | pcie->xbar_config;
+	value |= AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO_ALL;
 
-	list_for_each_entry(port, &pcie->ports, list)
+	list_for_each_entry(port, &pcie->ports, list) {
 		value &= ~AFI_PCIE_CONFIG_PCIE_DISABLE(port->index);
+		value &= ~AFI_PCIE_CONFIG_PCIE_CLKREQ_GPIO(port->index);
+	}
 
 	afi_writel(pcie, value, AFI_PCIE_CONFIG);
 
@@ -958,20 +1199,10 @@ static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 		afi_writel(pcie, value, AFI_FUSE);
 	}
 
-	if (soc->program_uphy) {
-		err = tegra_pcie_phy_power_on(pcie);
-		if (err < 0) {
-			dev_err(dev, "failed to power on PHY(s): %d\n", err);
-			return err;
-		}
-	}
-
-	/* take the PCIe interface module out of reset */
-	reset_control_deassert(pcie->pcie_xrst);
-
-	/* finally enable PCIe */
+	/* Disable AFI dynamic clock gating and enable PCIe */
 	value = afi_readl(pcie, AFI_CONFIGURATION);
 	value |= AFI_CONFIGURATION_EN_FPCI;
+	value |= AFI_CONFIGURATION_CLKEN_OVERRIDE;
 	afi_writel(pcie, value, AFI_CONFIGURATION);
 
 	value = AFI_INTR_EN_INI_SLVERR | AFI_INTR_EN_INI_DECERR |
@@ -989,22 +1220,6 @@ static int tegra_pcie_enable_controller(struct tegra_pcie *pcie)
 
 	/* disable all exceptions */
 	afi_writel(pcie, 0, AFI_FPCI_ERROR_MASKS);
-
-	return 0;
-}
-
-static void tegra_pcie_disable_controller(struct tegra_pcie *pcie)
-{
-	int err;
-
-	reset_control_assert(pcie->pcie_xrst);
-
-	if (pcie->soc->program_uphy) {
-		err = tegra_pcie_phy_power_off(pcie);
-		if (err < 0)
-			dev_err(pcie->dev, "failed to power off PHY(s): %d\n",
-				err);
-	}
 }
 
 static void tegra_pcie_power_off(struct tegra_pcie *pcie)
@@ -1014,13 +1229,11 @@ static void tegra_pcie_power_off(struct tegra_pcie *pcie)
 	int err;
 
 	reset_control_assert(pcie->afi_rst);
-	reset_control_assert(pcie->pex_rst);
 
 	clk_disable_unprepare(pcie->pll_e);
 	if (soc->has_cml_clk)
 		clk_disable_unprepare(pcie->cml_clk);
 	clk_disable_unprepare(pcie->afi_clk);
-	clk_disable_unprepare(pcie->pex_clk);
 
 	if (!dev->pm_domain)
 		tegra_powergate_power_off(TEGRA_POWERGATE_PCIE);
@@ -1048,46 +1261,66 @@ static int tegra_pcie_power_on(struct tegra_pcie *pcie)
 	if (err < 0)
 		dev_err(dev, "failed to enable regulators: %d\n", err);
 
-	if (dev->pm_domain) {
-		err = clk_prepare_enable(pcie->pex_clk);
+	if (!dev->pm_domain) {
+		err = tegra_powergate_power_on(TEGRA_POWERGATE_PCIE);
 		if (err) {
-			dev_err(dev, "failed to enable PEX clock: %d\n", err);
-			return err;
+			dev_err(dev, "failed to power ungate: %d\n", err);
+			goto regulator_disable;
 		}
-		reset_control_deassert(pcie->pex_rst);
-	} else {
-		err = tegra_powergate_sequence_power_up(TEGRA_POWERGATE_PCIE,
-							pcie->pex_clk,
-							pcie->pex_rst);
+		err = tegra_powergate_remove_clamping(TEGRA_POWERGATE_PCIE);
 		if (err) {
-			dev_err(dev, "powerup sequence failed: %d\n", err);
-			return err;
+			dev_err(dev, "failed to remove clamp: %d\n", err);
+			goto powergate;
 		}
 	}
 
-	reset_control_deassert(pcie->afi_rst);
-
 	err = clk_prepare_enable(pcie->afi_clk);
 	if (err < 0) {
 		dev_err(dev, "failed to enable AFI clock: %d\n", err);
-		return err;
+		goto powergate;
 	}
 
 	if (soc->has_cml_clk) {
 		err = clk_prepare_enable(pcie->cml_clk);
 		if (err < 0) {
 			dev_err(dev, "failed to enable CML clock: %d\n", err);
-			return err;
+			goto disable_afi_clk;
 		}
 	}
 
 	err = clk_prepare_enable(pcie->pll_e);
 	if (err < 0) {
 		dev_err(dev, "failed to enable PLLE clock: %d\n", err);
-		return err;
+		goto disable_cml_clk;
 	}
 
+	reset_control_deassert(pcie->afi_rst);
+
 	return 0;
+
+disable_cml_clk:
+	if (soc->has_cml_clk)
+		clk_disable_unprepare(pcie->cml_clk);
+disable_afi_clk:
+	clk_disable_unprepare(pcie->afi_clk);
+powergate:
+	if (!dev->pm_domain)
+		tegra_powergate_power_off(TEGRA_POWERGATE_PCIE);
+regulator_disable:
+	regulator_bulk_disable(pcie->num_supplies, pcie->supplies);
+
+	return err;
+}
+
+static void tegra_pcie_apply_pad_settings(struct tegra_pcie *pcie)
+{
+	const struct tegra_pcie_soc *soc = pcie->soc;
+
+	/* Configure the reference clock driver */
+	pads_writel(pcie, soc->pads_refclk_cfg0, PADS_REFCLK_CFG0);
+
+	if (soc->num_ports > 2)
+		pads_writel(pcie, soc->pads_refclk_cfg1, PADS_REFCLK_CFG1);
 }
 
 static int tegra_pcie_clocks_get(struct tegra_pcie *pcie)
@@ -1647,6 +1880,15 @@ static int tegra_pcie_disable_msi(struct tegra_pcie *pcie)
 	return 0;
 }
 
+static void tegra_pcie_disable_interrupts(struct tegra_pcie *pcie)
+{
+	u32 value;
+
+	value = afi_readl(pcie, AFI_INTR_MASK);
+	value &= ~AFI_INTR_MASK_INT_MASK;
+	afi_writel(pcie, value, AFI_INTR_MASK);
+}
+
 static int tegra_pcie_get_xbar_config(struct tegra_pcie *pcie, u32 lanes,
 				      u32 *xbar)
 {
@@ -1990,6 +2232,7 @@ static int tegra_pcie_parse_dt(struct tegra_pcie *pcie)
 		struct tegra_pcie_port *rp;
 		unsigned int index;
 		u32 value;
+		char *label;
 
 		err = of_pci_get_devfn(port);
 		if (err < 0) {
@@ -2048,6 +2291,31 @@ static int tegra_pcie_parse_dt(struct tegra_pcie *pcie)
 		if (IS_ERR(rp->base))
 			return PTR_ERR(rp->base);
 
+		label = devm_kasprintf(dev, GFP_KERNEL, "pex-reset-%u", index);
+		if (!label) {
+			dev_err(dev, "failed to create reset GPIO label\n");
+			return -ENOMEM;
+		}
+
+		/*
+		 * Returns -ENOENT if reset-gpios property is not populated
+		 * and in this case fall back to using AFI per port register
+		 * to toggle PERST# SFIO line.
+		 */
+		rp->reset_gpio = devm_gpiod_get_from_of_node(dev, port,
+							     "reset-gpios", 0,
+							     GPIOD_OUT_LOW,
+							     label);
+		if (IS_ERR(rp->reset_gpio)) {
+			if (PTR_ERR(rp->reset_gpio) == -ENOENT) {
+				rp->reset_gpio = NULL;
+			} else {
+				dev_err(dev, "failed to get reset GPIO: %d\n",
+					err);
+				return PTR_ERR(rp->reset_gpio);
+			}
+		}
+
 		list_add_tail(&rp->list, &pcie->ports);
 	}
 
@@ -2095,7 +2363,7 @@ static bool tegra_pcie_port_check_link(struct tegra_pcie_port *port)
 		} while (--timeout);
 
 		if (!timeout) {
-			dev_err(dev, "link %u down, retrying\n", port->index);
+			dev_dbg(dev, "link %u down, retrying\n", port->index);
 			goto retry;
 		}
 
@@ -2117,6 +2385,64 @@ retry:
 	return false;
 }
 
+static void tegra_pcie_change_link_speed(struct tegra_pcie *pcie)
+{
+	struct device *dev = pcie->dev;
+	struct tegra_pcie_port *port;
+	ktime_t deadline;
+	u32 value;
+
+	list_for_each_entry(port, &pcie->ports, list) {
+		/*
+		 * "Supported Link Speeds Vector" in "Link Capabilities 2"
+		 * is not supported by Tegra. tegra_pcie_change_link_speed()
+		 * is called only for Tegra chips which support Gen2.
+		 * So there no harm if supported link speed is not verified.
+		 */
+		value = readl(port->base + RP_LINK_CONTROL_STATUS_2);
+		value &= ~PCI_EXP_LNKSTA_CLS;
+		value |= PCI_EXP_LNKSTA_CLS_5_0GB;
+		writel(value, port->base + RP_LINK_CONTROL_STATUS_2);
+
+		/*
+		 * Poll until link comes back from recovery to avoid race
+		 * condition.
+		 */
+		deadline = ktime_add_us(ktime_get(), LINK_RETRAIN_TIMEOUT);
+
+		while (ktime_before(ktime_get(), deadline)) {
+			value = readl(port->base + RP_LINK_CONTROL_STATUS);
+			if ((value & PCI_EXP_LNKSTA_LT) == 0)
+				break;
+
+			usleep_range(2000, 3000);
+		}
+
+		if (value & PCI_EXP_LNKSTA_LT)
+			dev_warn(dev, "PCIe port %u link is in recovery\n",
+				 port->index);
+
+		/* Retrain the link */
+		value = readl(port->base + RP_LINK_CONTROL_STATUS);
+		value |= PCI_EXP_LNKCTL_RL;
+		writel(value, port->base + RP_LINK_CONTROL_STATUS);
+
+		deadline = ktime_add_us(ktime_get(), LINK_RETRAIN_TIMEOUT);
+
+		while (ktime_before(ktime_get(), deadline)) {
+			value = readl(port->base + RP_LINK_CONTROL_STATUS);
+			if ((value & PCI_EXP_LNKSTA_LT) == 0)
+				break;
+
+			usleep_range(2000, 3000);
+		}
+
+		if (value & PCI_EXP_LNKSTA_LT)
+			dev_err(dev, "failed to retrain link of port %u\n",
+				port->index);
+	}
+}
+
 static void tegra_pcie_enable_ports(struct tegra_pcie *pcie)
 {
 	struct device *dev = pcie->dev;
@@ -2127,7 +2453,12 @@ static void tegra_pcie_enable_ports(struct tegra_pcie *pcie)
 			 port->index, port->lanes);
 
 		tegra_pcie_port_enable(port);
+	}
 
+	/* Start LTSSM from Tegra side */
+	reset_control_deassert(pcie->pcie_xrst);
+
+	list_for_each_entry_safe(port, tmp, &pcie->ports, list) {
 		if (tegra_pcie_port_check_link(port))
 			continue;
 
@@ -2136,12 +2467,17 @@ static void tegra_pcie_enable_ports(struct tegra_pcie *pcie)
 		tegra_pcie_port_disable(port);
 		tegra_pcie_port_free(port);
 	}
+
+	if (pcie->soc->has_gen2)
+		tegra_pcie_change_link_speed(pcie);
 }
 
 static void tegra_pcie_disable_ports(struct tegra_pcie *pcie)
 {
 	struct tegra_pcie_port *port, *tmp;
 
+	reset_control_assert(pcie->pcie_xrst);
+
 	list_for_each_entry_safe(port, tmp, &pcie->ports, list)
 		tegra_pcie_port_disable(port);
 }
@@ -2155,6 +2491,7 @@ static const struct tegra_pcie_soc tegra20_pcie = {
 	.num_ports = 2,
 	.ports = tegra20_pcie_ports,
 	.msi_base_shift = 0,
+	.afi_pex2_ctrl = 0x128,
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA20,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_DIV10,
 	.pads_refclk_cfg0 = 0xfa5cfa5c,
@@ -2165,6 +2502,12 @@ static const struct tegra_pcie_soc tegra20_pcie = {
 	.has_gen2 = false,
 	.force_pca_enable = false,
 	.program_uphy = true,
+	.update_clamp_threshold = false,
+	.program_deskew_time = false,
+	.raw_violation_fixup = false,
+	.update_fc_timer = false,
+	.has_cache_bars = true,
+	.ectl.enable = false,
 };
 
 static const struct tegra_pcie_port_soc tegra30_pcie_ports[] = {
@@ -2188,6 +2531,12 @@ static const struct tegra_pcie_soc tegra30_pcie = {
 	.has_gen2 = false,
 	.force_pca_enable = false,
 	.program_uphy = true,
+	.update_clamp_threshold = false,
+	.program_deskew_time = false,
+	.raw_violation_fixup = false,
+	.update_fc_timer = false,
+	.has_cache_bars = false,
+	.ectl.enable = false,
 };
 
 static const struct tegra_pcie_soc tegra124_pcie = {
@@ -2197,6 +2546,8 @@ static const struct tegra_pcie_soc tegra124_pcie = {
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA30,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN,
 	.pads_refclk_cfg0 = 0x44ac44ac,
+	/* FC threshold is bit[25:18] */
+	.update_fc_threshold = 0x03fc0000,
 	.has_pex_clkreq_en = true,
 	.has_pex_bias_ctrl = true,
 	.has_intr_prsnt_sense = true,
@@ -2204,6 +2555,12 @@ static const struct tegra_pcie_soc tegra124_pcie = {
 	.has_gen2 = true,
 	.force_pca_enable = false,
 	.program_uphy = true,
+	.update_clamp_threshold = true,
+	.program_deskew_time = false,
+	.raw_violation_fixup = true,
+	.update_fc_timer = false,
+	.has_cache_bars = false,
+	.ectl.enable = false,
 };
 
 static const struct tegra_pcie_soc tegra210_pcie = {
@@ -2213,6 +2570,8 @@ static const struct tegra_pcie_soc tegra210_pcie = {
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA30,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN,
 	.pads_refclk_cfg0 = 0x90b890b8,
+	/* FC threshold is bit[25:18] */
+	.update_fc_threshold = 0x01800000,
 	.has_pex_clkreq_en = true,
 	.has_pex_bias_ctrl = true,
 	.has_intr_prsnt_sense = true,
@@ -2220,6 +2579,24 @@ static const struct tegra_pcie_soc tegra210_pcie = {
 	.has_gen2 = true,
 	.force_pca_enable = true,
 	.program_uphy = true,
+	.update_clamp_threshold = true,
+	.program_deskew_time = true,
+	.raw_violation_fixup = false,
+	.update_fc_timer = true,
+	.has_cache_bars = false,
+	.ectl = {
+		.regs = {
+			.rp_ectl_2_r1 = 0x0000000f,
+			.rp_ectl_4_r1 = 0x00000067,
+			.rp_ectl_5_r1 = 0x55010000,
+			.rp_ectl_6_r1 = 0x00000001,
+			.rp_ectl_2_r2 = 0x0000008f,
+			.rp_ectl_4_r2 = 0x000000c7,
+			.rp_ectl_5_r2 = 0x55010000,
+			.rp_ectl_6_r2 = 0x00000001,
+		},
+		.enable = true,
+	},
 };
 
 static const struct tegra_pcie_port_soc tegra186_pcie_ports[] = {
@@ -2232,6 +2609,7 @@ static const struct tegra_pcie_soc tegra186_pcie = {
 	.num_ports = 3,
 	.ports = tegra186_pcie_ports,
 	.msi_base_shift = 8,
+	.afi_pex2_ctrl = 0x19c,
 	.pads_pll_ctl = PADS_PLL_CTL_TEGRA30,
 	.tx_ref_sel = PADS_PLL_CTL_TXCLKREF_BUF_EN,
 	.pads_refclk_cfg0 = 0x80b880b8,
@@ -2243,6 +2621,12 @@ static const struct tegra_pcie_soc tegra186_pcie = {
 	.has_gen2 = true,
 	.force_pca_enable = false,
 	.program_uphy = false,
+	.update_clamp_threshold = false,
+	.program_deskew_time = false,
+	.raw_violation_fixup = false,
+	.update_fc_timer = false,
+	.has_cache_bars = false,
+	.ectl.enable = false,
 };
 
 static const struct of_device_id tegra_pcie_of_match[] = {
@@ -2485,16 +2869,32 @@ static int __maybe_unused tegra_pcie_pm_suspend(struct device *dev)
 {
 	struct tegra_pcie *pcie = dev_get_drvdata(dev);
 	struct tegra_pcie_port *port;
+	int err;
 
 	list_for_each_entry(port, &pcie->ports, list)
 		tegra_pcie_pme_turnoff(port);
 
 	tegra_pcie_disable_ports(pcie);
 
+	/*
+	 * AFI_INTR is unmasked in tegra_pcie_enable_controller(), mask it to
+	 * avoid unwanted interrupts raised by AFI after pex_rst is asserted.
+	 */
+	tegra_pcie_disable_interrupts(pcie);
+
+	if (pcie->soc->program_uphy) {
+		err = tegra_pcie_phy_power_off(pcie);
+		if (err < 0)
+			dev_err(dev, "failed to power off PHY(s): %d\n", err);
+	}
+
+	reset_control_assert(pcie->pex_rst);
+	clk_disable_unprepare(pcie->pex_clk);
+
 	if (IS_ENABLED(CONFIG_PCI_MSI))
 		tegra_pcie_disable_msi(pcie);
 
-	tegra_pcie_disable_controller(pcie);
+	pinctrl_pm_select_idle_state(dev);
 	tegra_pcie_power_off(pcie);
 
 	return 0;
@@ -2510,20 +2910,45 @@ static int __maybe_unused tegra_pcie_pm_resume(struct device *dev)
 		dev_err(dev, "tegra pcie power on fail: %d\n", err);
 		return err;
 	}
-	err = tegra_pcie_enable_controller(pcie);
-	if (err) {
-		dev_err(dev, "tegra pcie controller enable fail: %d\n", err);
+
+	err = pinctrl_pm_select_default_state(dev);
+	if (err < 0) {
+		dev_err(dev, "failed to disable PCIe IO DPD: %d\n", err);
 		goto poweroff;
 	}
+
+	tegra_pcie_enable_controller(pcie);
 	tegra_pcie_setup_translations(pcie);
 
 	if (IS_ENABLED(CONFIG_PCI_MSI))
 		tegra_pcie_enable_msi(pcie);
 
+	err = clk_prepare_enable(pcie->pex_clk);
+	if (err) {
+		dev_err(dev, "failed to enable PEX clock: %d\n", err);
+		goto pex_dpd_enable;
+	}
+
+	reset_control_deassert(pcie->pex_rst);
+
+	if (pcie->soc->program_uphy) {
+		err = tegra_pcie_phy_power_on(pcie);
+		if (err < 0) {
+			dev_err(dev, "failed to power on PHY(s): %d\n", err);
+			goto disable_pex_clk;
+		}
+	}
+
+	tegra_pcie_apply_pad_settings(pcie);
 	tegra_pcie_enable_ports(pcie);
 
 	return 0;
 
+disable_pex_clk:
+	reset_control_assert(pcie->pex_rst);
+	clk_disable_unprepare(pcie->pex_clk);
+pex_dpd_enable:
+	pinctrl_pm_select_idle_state(dev);
 poweroff:
 	tegra_pcie_power_off(pcie);
 
diff --git a/drivers/pci/controller/pcie-altera-msi.c b/drivers/pci/controller/pcie-altera-msi.c
index 025ef7d9a046..16d938920ca5 100644
--- a/drivers/pci/controller/pcie-altera-msi.c
+++ b/drivers/pci/controller/pcie-altera-msi.c
@@ -10,6 +10,7 @@
 #include <linux/interrupt.h>
 #include <linux/irqchip/chained_irq.h>
 #include <linux/init.h>
+#include <linux/module.h>
 #include <linux/msi.h>
 #include <linux/of_address.h>
 #include <linux/of_irq.h>
@@ -288,4 +289,13 @@ static int __init altera_msi_init(void)
 {
 	return platform_driver_register(&altera_msi_driver);
 }
+
+static void __exit altera_msi_exit(void)
+{
+	platform_driver_unregister(&altera_msi_driver);
+}
+
 subsys_initcall(altera_msi_init);
+MODULE_DEVICE_TABLE(of, altera_msi_of_match);
+module_exit(altera_msi_exit);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/controller/pcie-altera.c b/drivers/pci/controller/pcie-altera.c
index 27edcebd1726..d2497ca43828 100644
--- a/drivers/pci/controller/pcie-altera.c
+++ b/drivers/pci/controller/pcie-altera.c
@@ -10,6 +10,7 @@
 #include <linux/interrupt.h>
 #include <linux/irqchip/chained_irq.h>
 #include <linux/init.h>
+#include <linux/module.h>
 #include <linux/of_address.h>
 #include <linux/of_device.h>
 #include <linux/of_irq.h>
@@ -43,6 +44,8 @@
 #define S10_RP_RXCPL_STATUS		0x200C
 #define S10_RP_CFG_ADDR(pcie, reg)	\
 	(((pcie)->hip_base) + (reg) + (1 << 20))
+#define S10_RP_SECONDARY(pcie)		\
+	readb(S10_RP_CFG_ADDR(pcie, PCI_SECONDARY_BUS))
 
 /* TLP configuration type 0 and 1 */
 #define TLP_FMTTYPE_CFGRD0		0x04	/* Configuration Read Type 0 */
@@ -54,14 +57,9 @@
 #define TLP_WRITE_TAG			0x10
 #define RP_DEVFN			0
 #define TLP_REQ_ID(bus, devfn)		(((bus) << 8) | (devfn))
-#define TLP_CFGRD_DW0(pcie, bus)					\
-	((((bus == pcie->root_bus_nr) ? pcie->pcie_data->cfgrd0		\
-				: pcie->pcie_data->cfgrd1) << 24) |	\
-				TLP_PAYLOAD_SIZE)
-#define TLP_CFGWR_DW0(pcie, bus)					\
-	((((bus == pcie->root_bus_nr) ? pcie->pcie_data->cfgwr0		\
-				: pcie->pcie_data->cfgwr1) << 24) |	\
-				TLP_PAYLOAD_SIZE)
+#define TLP_CFG_DW0(pcie, cfg)		\
+		(((cfg) << 24) |	\
+		  TLP_PAYLOAD_SIZE)
 #define TLP_CFG_DW1(pcie, tag, be)	\
 	(((TLP_REQ_ID(pcie->root_bus_nr,  RP_DEVFN)) << 16) | (tag << 8) | (be))
 #define TLP_CFG_DW2(bus, devfn, offset)	\
@@ -321,14 +319,31 @@ static void s10_tlp_write_packet(struct altera_pcie *pcie, u32 *headers,
 	s10_tlp_write_tx(pcie, data, RP_TX_EOP);
 }
 
+static void get_tlp_header(struct altera_pcie *pcie, u8 bus, u32 devfn,
+			   int where, u8 byte_en, bool read, u32 *headers)
+{
+	u8 cfg;
+	u8 cfg0 = read ? pcie->pcie_data->cfgrd0 : pcie->pcie_data->cfgwr0;
+	u8 cfg1 = read ? pcie->pcie_data->cfgrd1 : pcie->pcie_data->cfgwr1;
+	u8 tag = read ? TLP_READ_TAG : TLP_WRITE_TAG;
+
+	if (pcie->pcie_data->version == ALTERA_PCIE_V1)
+		cfg = (bus == pcie->root_bus_nr) ? cfg0 : cfg1;
+	else
+		cfg = (bus > S10_RP_SECONDARY(pcie)) ? cfg0 : cfg1;
+
+	headers[0] = TLP_CFG_DW0(pcie, cfg);
+	headers[1] = TLP_CFG_DW1(pcie, tag, byte_en);
+	headers[2] = TLP_CFG_DW2(bus, devfn, where);
+}
+
 static int tlp_cfg_dword_read(struct altera_pcie *pcie, u8 bus, u32 devfn,
 			      int where, u8 byte_en, u32 *value)
 {
 	u32 headers[TLP_HDR_SIZE];
 
-	headers[0] = TLP_CFGRD_DW0(pcie, bus);
-	headers[1] = TLP_CFG_DW1(pcie, TLP_READ_TAG, byte_en);
-	headers[2] = TLP_CFG_DW2(bus, devfn, where);
+	get_tlp_header(pcie, bus, devfn, where, byte_en, true,
+		       headers);
 
 	pcie->pcie_data->ops->tlp_write_pkt(pcie, headers, 0, false);
 
@@ -341,9 +356,8 @@ static int tlp_cfg_dword_write(struct altera_pcie *pcie, u8 bus, u32 devfn,
 	u32 headers[TLP_HDR_SIZE];
 	int ret;
 
-	headers[0] = TLP_CFGWR_DW0(pcie, bus);
-	headers[1] = TLP_CFG_DW1(pcie, TLP_WRITE_TAG, byte_en);
-	headers[2] = TLP_CFG_DW2(bus, devfn, where);
+	get_tlp_header(pcie, bus, devfn, where, byte_en, false,
+		       headers);
 
 	/* check alignment to Qword */
 	if ((where & 0x7) == 0)
@@ -705,6 +719,13 @@ static int altera_pcie_init_irq_domain(struct altera_pcie *pcie)
 	return 0;
 }
 
+static void altera_pcie_irq_teardown(struct altera_pcie *pcie)
+{
+	irq_set_chained_handler_and_data(pcie->irq, NULL, NULL);
+	irq_domain_remove(pcie->irq_domain);
+	irq_dispose_mapping(pcie->irq);
+}
+
 static int altera_pcie_parse_dt(struct altera_pcie *pcie)
 {
 	struct device *dev = &pcie->pdev->dev;
@@ -798,6 +819,7 @@ static int altera_pcie_probe(struct platform_device *pdev)
 
 	pcie = pci_host_bridge_priv(bridge);
 	pcie->pdev = pdev;
+	platform_set_drvdata(pdev, pcie);
 
 	match = of_match_device(altera_pcie_of_match, &pdev->dev);
 	if (!match)
@@ -855,13 +877,28 @@ static int altera_pcie_probe(struct platform_device *pdev)
 	return ret;
 }
 
+static int altera_pcie_remove(struct platform_device *pdev)
+{
+	struct altera_pcie *pcie = platform_get_drvdata(pdev);
+	struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie);
+
+	pci_stop_root_bus(bridge->bus);
+	pci_remove_root_bus(bridge->bus);
+	pci_free_resource_list(&pcie->resources);
+	altera_pcie_irq_teardown(pcie);
+
+	return 0;
+}
+
 static struct platform_driver altera_pcie_driver = {
 	.probe		= altera_pcie_probe,
+	.remove		= altera_pcie_remove,
 	.driver = {
 		.name	= "altera-pcie",
 		.of_match_table = altera_pcie_of_match,
-		.suppress_bind_attrs = true,
 	},
 };
 
-builtin_platform_driver(altera_pcie_driver);
+MODULE_DEVICE_TABLE(of, altera_pcie_of_match);
+module_platform_driver(altera_pcie_driver);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/pci/controller/pcie-iproc-platform.c b/drivers/pci/controller/pcie-iproc-platform.c
index f30f5f3fb5c1..5a3550b6bb29 100644
--- a/drivers/pci/controller/pcie-iproc-platform.c
+++ b/drivers/pci/controller/pcie-iproc-platform.c
@@ -87,7 +87,7 @@ static int iproc_pcie_pltfm_probe(struct platform_device *pdev)
 
 	/*
 	 * DT nodes are not used by all platforms that use the iProc PCIe
-	 * core driver. For platforms that require explict inbound mapping
+	 * core driver. For platforms that require explicit inbound mapping
 	 * configuration, "dma-ranges" would have been present in DT
 	 */
 	pcie->need_ib_cfg = of_property_read_bool(np, "dma-ranges");
diff --git a/drivers/pci/controller/pcie-iproc.c b/drivers/pci/controller/pcie-iproc.c
index e3ca46497470..2d457bfdaf66 100644
--- a/drivers/pci/controller/pcie-iproc.c
+++ b/drivers/pci/controller/pcie-iproc.c
@@ -163,7 +163,7 @@ enum iproc_pcie_ib_map_type {
  * @size_unit: inbound mapping region size unit, could be SZ_1K, SZ_1M, or
  * SZ_1G
  * @region_sizes: list of supported inbound mapping region sizes in KB, MB, or
- * GB, depedning on the size unit
+ * GB, depending on the size unit
  * @nr_sizes: number of supported inbound mapping region sizes
  * @nr_windows: number of supported inbound mapping windows for the region
  * @imap_addr_offset: register offset between the upper and lower 32-bit
diff --git a/drivers/pci/controller/pcie-mobiveil.c b/drivers/pci/controller/pcie-mobiveil.c
index 77052a0712d0..672e633601c7 100644
--- a/drivers/pci/controller/pcie-mobiveil.c
+++ b/drivers/pci/controller/pcie-mobiveil.c
@@ -31,56 +31,61 @@
  * translation tables are grouped into windows, each window registers are
  * grouped into blocks of 4 or 16 registers each
  */
-#define PAB_REG_BLOCK_SIZE	16
-#define PAB_EXT_REG_BLOCK_SIZE	4
+#define PAB_REG_BLOCK_SIZE		16
+#define PAB_EXT_REG_BLOCK_SIZE		4
 
-#define PAB_REG_ADDR(offset, win) (offset + (win * PAB_REG_BLOCK_SIZE))
-#define PAB_EXT_REG_ADDR(offset, win) (offset + (win * PAB_EXT_REG_BLOCK_SIZE))
+#define PAB_REG_ADDR(offset, win)	\
+	(offset + (win * PAB_REG_BLOCK_SIZE))
+#define PAB_EXT_REG_ADDR(offset, win)	\
+	(offset + (win * PAB_EXT_REG_BLOCK_SIZE))
 
-#define LTSSM_STATUS		0x0404
-#define  LTSSM_STATUS_L0_MASK	0x3f
-#define  LTSSM_STATUS_L0	0x2d
+#define LTSSM_STATUS			0x0404
+#define  LTSSM_STATUS_L0_MASK		0x3f
+#define  LTSSM_STATUS_L0		0x2d
 
-#define PAB_CTRL		0x0808
-#define  AMBA_PIO_ENABLE_SHIFT	0
-#define  PEX_PIO_ENABLE_SHIFT	1
-#define  PAGE_SEL_SHIFT	13
-#define  PAGE_SEL_MASK		0x3f
-#define  PAGE_LO_MASK		0x3ff
-#define  PAGE_SEL_EN		0xc00
-#define  PAGE_SEL_OFFSET_SHIFT	10
+#define PAB_CTRL			0x0808
+#define  AMBA_PIO_ENABLE_SHIFT		0
+#define  PEX_PIO_ENABLE_SHIFT		1
+#define  PAGE_SEL_SHIFT			13
+#define  PAGE_SEL_MASK			0x3f
+#define  PAGE_LO_MASK			0x3ff
+#define  PAGE_SEL_OFFSET_SHIFT		10
 
-#define PAB_AXI_PIO_CTRL	0x0840
-#define  APIO_EN_MASK		0xf
+#define PAB_AXI_PIO_CTRL		0x0840
+#define  APIO_EN_MASK			0xf
 
-#define PAB_PEX_PIO_CTRL	0x08c0
-#define  PIO_ENABLE_SHIFT	0
+#define PAB_PEX_PIO_CTRL		0x08c0
+#define  PIO_ENABLE_SHIFT		0
 
 #define PAB_INTP_AMBA_MISC_ENB		0x0b0c
-#define PAB_INTP_AMBA_MISC_STAT	0x0b1c
+#define PAB_INTP_AMBA_MISC_STAT		0x0b1c
 #define  PAB_INTP_INTX_MASK		0x01e0
 #define  PAB_INTP_MSI_MASK		0x8
 
-#define PAB_AXI_AMAP_CTRL(win)	PAB_REG_ADDR(0x0ba0, win)
-#define  WIN_ENABLE_SHIFT	0
-#define  WIN_TYPE_SHIFT	1
+#define PAB_AXI_AMAP_CTRL(win)		PAB_REG_ADDR(0x0ba0, win)
+#define  WIN_ENABLE_SHIFT		0
+#define  WIN_TYPE_SHIFT			1
+#define  WIN_TYPE_MASK			0x3
+#define  WIN_SIZE_MASK			0xfffffc00
 
 #define PAB_EXT_AXI_AMAP_SIZE(win)	PAB_EXT_REG_ADDR(0xbaf0, win)
 
+#define PAB_EXT_AXI_AMAP_AXI_WIN(win)	PAB_EXT_REG_ADDR(0x80a0, win)
 #define PAB_AXI_AMAP_AXI_WIN(win)	PAB_REG_ADDR(0x0ba4, win)
 #define  AXI_WINDOW_ALIGN_MASK		3
 
 #define PAB_AXI_AMAP_PEX_WIN_L(win)	PAB_REG_ADDR(0x0ba8, win)
-#define  PAB_BUS_SHIFT		24
-#define  PAB_DEVICE_SHIFT	19
-#define  PAB_FUNCTION_SHIFT	16
+#define  PAB_BUS_SHIFT			24
+#define  PAB_DEVICE_SHIFT		19
+#define  PAB_FUNCTION_SHIFT		16
 
 #define PAB_AXI_AMAP_PEX_WIN_H(win)	PAB_REG_ADDR(0x0bac, win)
 #define PAB_INTP_AXI_PIO_CLASS		0x474
 
-#define PAB_PEX_AMAP_CTRL(win)	PAB_REG_ADDR(0x4ba0, win)
-#define  AMAP_CTRL_EN_SHIFT	0
-#define  AMAP_CTRL_TYPE_SHIFT	1
+#define PAB_PEX_AMAP_CTRL(win)		PAB_REG_ADDR(0x4ba0, win)
+#define  AMAP_CTRL_EN_SHIFT		0
+#define  AMAP_CTRL_TYPE_SHIFT		1
+#define  AMAP_CTRL_TYPE_MASK		3
 
 #define PAB_EXT_PEX_AMAP_SIZEN(win)	PAB_EXT_REG_ADDR(0xbef0, win)
 #define PAB_PEX_AMAP_AXI_WIN(win)	PAB_REG_ADDR(0x4ba4, win)
@@ -88,34 +93,40 @@
 #define PAB_PEX_AMAP_PEX_WIN_H(win)	PAB_REG_ADDR(0x4bac, win)
 
 /* starting offset of INTX bits in status register */
-#define PAB_INTX_START	5
+#define PAB_INTX_START			5
 
 /* supported number of MSI interrupts */
-#define PCI_NUM_MSI	16
+#define PCI_NUM_MSI			16
 
 /* MSI registers */
-#define MSI_BASE_LO_OFFSET	0x04
-#define MSI_BASE_HI_OFFSET	0x08
-#define MSI_SIZE_OFFSET	0x0c
-#define MSI_ENABLE_OFFSET	0x14
-#define MSI_STATUS_OFFSET	0x18
-#define MSI_DATA_OFFSET	0x20
-#define MSI_ADDR_L_OFFSET	0x24
-#define MSI_ADDR_H_OFFSET	0x28
+#define MSI_BASE_LO_OFFSET		0x04
+#define MSI_BASE_HI_OFFSET		0x08
+#define MSI_SIZE_OFFSET			0x0c
+#define MSI_ENABLE_OFFSET		0x14
+#define MSI_STATUS_OFFSET		0x18
+#define MSI_DATA_OFFSET			0x20
+#define MSI_ADDR_L_OFFSET		0x24
+#define MSI_ADDR_H_OFFSET		0x28
 
 /* outbound and inbound window definitions */
-#define WIN_NUM_0		0
-#define WIN_NUM_1		1
-#define CFG_WINDOW_TYPE	0
-#define IO_WINDOW_TYPE		1
-#define MEM_WINDOW_TYPE	2
-#define IB_WIN_SIZE		((u64)256 * 1024 * 1024 * 1024)
-#define MAX_PIO_WINDOWS	8
+#define WIN_NUM_0			0
+#define WIN_NUM_1			1
+#define CFG_WINDOW_TYPE			0
+#define IO_WINDOW_TYPE			1
+#define MEM_WINDOW_TYPE			2
+#define IB_WIN_SIZE			((u64)256 * 1024 * 1024 * 1024)
+#define MAX_PIO_WINDOWS			8
 
 /* Parameters for the waiting for link up routine */
-#define LINK_WAIT_MAX_RETRIES	10
-#define LINK_WAIT_MIN	90000
-#define LINK_WAIT_MAX	100000
+#define LINK_WAIT_MAX_RETRIES		10
+#define LINK_WAIT_MIN			90000
+#define LINK_WAIT_MAX			100000
+
+#define PAGED_ADDR_BNDRY		0xc00
+#define OFFSET_TO_PAGE_ADDR(off)	\
+	((off & PAGE_LO_MASK) | PAGED_ADDR_BNDRY)
+#define OFFSET_TO_PAGE_IDX(off)		\
+	((off >> PAGE_SEL_OFFSET_SHIFT) & PAGE_SEL_MASK)
 
 struct mobiveil_msi {			/* MSI information */
 	struct mutex lock;		/* protect bitmap variable */
@@ -145,15 +156,119 @@ struct mobiveil_pcie {
 	struct mobiveil_msi msi;
 };
 
-static inline void csr_writel(struct mobiveil_pcie *pcie, const u32 value,
-		const u32 reg)
+/*
+ * mobiveil_pcie_sel_page - routine to access paged register
+ *
+ * Registers whose address greater than PAGED_ADDR_BNDRY (0xc00) are paged,
+ * for this scheme to work extracted higher 6 bits of the offset will be
+ * written to pg_sel field of PAB_CTRL register and rest of the lower 10
+ * bits enabled with PAGED_ADDR_BNDRY are used as offset of the register.
+ */
+static void mobiveil_pcie_sel_page(struct mobiveil_pcie *pcie, u8 pg_idx)
+{
+	u32 val;
+
+	val = readl(pcie->csr_axi_slave_base + PAB_CTRL);
+	val &= ~(PAGE_SEL_MASK << PAGE_SEL_SHIFT);
+	val |= (pg_idx & PAGE_SEL_MASK) << PAGE_SEL_SHIFT;
+
+	writel(val, pcie->csr_axi_slave_base + PAB_CTRL);
+}
+
+static void *mobiveil_pcie_comp_addr(struct mobiveil_pcie *pcie, u32 off)
+{
+	if (off < PAGED_ADDR_BNDRY) {
+		/* For directly accessed registers, clear the pg_sel field */
+		mobiveil_pcie_sel_page(pcie, 0);
+		return pcie->csr_axi_slave_base + off;
+	}
+
+	mobiveil_pcie_sel_page(pcie, OFFSET_TO_PAGE_IDX(off));
+	return pcie->csr_axi_slave_base + OFFSET_TO_PAGE_ADDR(off);
+}
+
+static int mobiveil_pcie_read(void __iomem *addr, int size, u32 *val)
 {
-	writel_relaxed(value, pcie->csr_axi_slave_base + reg);
+	if ((uintptr_t)addr & (size - 1)) {
+		*val = 0;
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+	}
+
+	switch (size) {
+	case 4:
+		*val = readl(addr);
+		break;
+	case 2:
+		*val = readw(addr);
+		break;
+	case 1:
+		*val = readb(addr);
+		break;
+	default:
+		*val = 0;
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+	}
+
+	return PCIBIOS_SUCCESSFUL;
 }
 
-static inline u32 csr_readl(struct mobiveil_pcie *pcie, const u32 reg)
+static int mobiveil_pcie_write(void __iomem *addr, int size, u32 val)
 {
-	return readl_relaxed(pcie->csr_axi_slave_base + reg);
+	if ((uintptr_t)addr & (size - 1))
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+
+	switch (size) {
+	case 4:
+		writel(val, addr);
+		break;
+	case 2:
+		writew(val, addr);
+		break;
+	case 1:
+		writeb(val, addr);
+		break;
+	default:
+		return PCIBIOS_BAD_REGISTER_NUMBER;
+	}
+
+	return PCIBIOS_SUCCESSFUL;
+}
+
+static u32 csr_read(struct mobiveil_pcie *pcie, u32 off, size_t size)
+{
+	void *addr;
+	u32 val;
+	int ret;
+
+	addr = mobiveil_pcie_comp_addr(pcie, off);
+
+	ret = mobiveil_pcie_read(addr, size, &val);
+	if (ret)
+		dev_err(&pcie->pdev->dev, "read CSR address failed\n");
+
+	return val;
+}
+
+static void csr_write(struct mobiveil_pcie *pcie, u32 val, u32 off, size_t size)
+{
+	void *addr;
+	int ret;
+
+	addr = mobiveil_pcie_comp_addr(pcie, off);
+
+	ret = mobiveil_pcie_write(addr, size, val);
+	if (ret)
+		dev_err(&pcie->pdev->dev, "write CSR address failed\n");
+}
+
+static u32 csr_readl(struct mobiveil_pcie *pcie, u32 off)
+{
+	return csr_read(pcie, off, 0x4);
+}
+
+static void csr_writel(struct mobiveil_pcie *pcie, u32 val, u32 off)
+{
+	csr_write(pcie, val, off, 0x4);
 }
 
 static bool mobiveil_pcie_link_up(struct mobiveil_pcie *pcie)
@@ -174,7 +289,7 @@ static bool mobiveil_pcie_valid_device(struct pci_bus *bus, unsigned int devfn)
 	 * Do not read more than one device on the bus directly
 	 * attached to RC
 	 */
-	if ((bus->primary == pcie->root_bus_nr) && (devfn > 0))
+	if ((bus->primary == pcie->root_bus_nr) && (PCI_SLOT(devfn) > 0))
 		return false;
 
 	return true;
@@ -185,17 +300,17 @@ static bool mobiveil_pcie_valid_device(struct pci_bus *bus, unsigned int devfn)
  * root port or endpoint
  */
 static void __iomem *mobiveil_pcie_map_bus(struct pci_bus *bus,
-					unsigned int devfn, int where)
+					   unsigned int devfn, int where)
 {
 	struct mobiveil_pcie *pcie = bus->sysdata;
+	u32 value;
 
 	if (!mobiveil_pcie_valid_device(bus, devfn))
 		return NULL;
 
-	if (bus->number == pcie->root_bus_nr) {
-		/* RC config access */
+	/* RC config access */
+	if (bus->number == pcie->root_bus_nr)
 		return pcie->csr_axi_slave_base + where;
-	}
 
 	/*
 	 * EP config access (in Config/APIO space)
@@ -203,10 +318,12 @@ static void __iomem *mobiveil_pcie_map_bus(struct pci_bus *bus,
 	 * (BDF) in PAB_AXI_AMAP_PEX_WIN_L0 Register.
 	 * Relies on pci_lock serialization
 	 */
-	csr_writel(pcie, bus->number << PAB_BUS_SHIFT |
-			PCI_SLOT(devfn) << PAB_DEVICE_SHIFT |
-			PCI_FUNC(devfn) << PAB_FUNCTION_SHIFT,
-			PAB_AXI_AMAP_PEX_WIN_L(WIN_NUM_0));
+	value = bus->number << PAB_BUS_SHIFT |
+		PCI_SLOT(devfn) << PAB_DEVICE_SHIFT |
+		PCI_FUNC(devfn) << PAB_FUNCTION_SHIFT;
+
+	csr_writel(pcie, value, PAB_AXI_AMAP_PEX_WIN_L(WIN_NUM_0));
+
 	return pcie->config_axi_slave_base + where;
 }
 
@@ -241,24 +358,29 @@ static void mobiveil_pcie_isr(struct irq_desc *desc)
 
 	/* Handle INTx */
 	if (intr_status & PAB_INTP_INTX_MASK) {
-		shifted_status = csr_readl(pcie, PAB_INTP_AMBA_MISC_STAT) >>
-			PAB_INTX_START;
+		shifted_status = csr_readl(pcie, PAB_INTP_AMBA_MISC_STAT);
+		shifted_status &= PAB_INTP_INTX_MASK;
+		shifted_status >>= PAB_INTX_START;
 		do {
 			for_each_set_bit(bit, &shifted_status, PCI_NUM_INTX) {
 				virq = irq_find_mapping(pcie->intx_domain,
-						bit + 1);
+							bit + 1);
 				if (virq)
 					generic_handle_irq(virq);
 				else
-					dev_err_ratelimited(dev,
-						"unexpected IRQ, INT%d\n", bit);
+					dev_err_ratelimited(dev, "unexpected IRQ, INT%d\n",
+							    bit);
 
-				/* clear interrupt */
-				csr_writel(pcie,
-					shifted_status << PAB_INTX_START,
-					PAB_INTP_AMBA_MISC_STAT);
+				/* clear interrupt handled */
+				csr_writel(pcie, 1 << (PAB_INTX_START + bit),
+					   PAB_INTP_AMBA_MISC_STAT);
 			}
-		} while ((shifted_status >> PAB_INTX_START) != 0);
+
+			shifted_status = csr_readl(pcie,
+						   PAB_INTP_AMBA_MISC_STAT);
+			shifted_status &= PAB_INTP_INTX_MASK;
+			shifted_status >>= PAB_INTX_START;
+		} while (shifted_status != 0);
 	}
 
 	/* read extra MSI status register */
@@ -266,8 +388,7 @@ static void mobiveil_pcie_isr(struct irq_desc *desc)
 
 	/* handle MSI interrupts */
 	while (msi_status & 1) {
-		msi_data = readl_relaxed(pcie->apb_csr_base
-				+ MSI_DATA_OFFSET);
+		msi_data = readl_relaxed(pcie->apb_csr_base + MSI_DATA_OFFSET);
 
 		/*
 		 * MSI_STATUS_OFFSET register gets updated to zero
@@ -276,18 +397,18 @@ static void mobiveil_pcie_isr(struct irq_desc *desc)
 		 * two dummy reads.
 		 */
 		msi_addr_lo = readl_relaxed(pcie->apb_csr_base +
-				MSI_ADDR_L_OFFSET);
+					    MSI_ADDR_L_OFFSET);
 		msi_addr_hi = readl_relaxed(pcie->apb_csr_base +
-				MSI_ADDR_H_OFFSET);
+					    MSI_ADDR_H_OFFSET);
 		dev_dbg(dev, "MSI registers, data: %08x, addr: %08x:%08x\n",
-				msi_data, msi_addr_hi, msi_addr_lo);
+			msi_data, msi_addr_hi, msi_addr_lo);
 
 		virq = irq_find_mapping(msi->dev_domain, msi_data);
 		if (virq)
 			generic_handle_irq(virq);
 
 		msi_status = readl_relaxed(pcie->apb_csr_base +
-				MSI_STATUS_OFFSET);
+					   MSI_STATUS_OFFSET);
 	}
 
 	/* Clear the interrupt status */
@@ -304,7 +425,7 @@ static int mobiveil_pcie_parse_dt(struct mobiveil_pcie *pcie)
 
 	/* map config resource */
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-			"config_axi_slave");
+					   "config_axi_slave");
 	pcie->config_axi_slave_base = devm_pci_remap_cfg_resource(dev, res);
 	if (IS_ERR(pcie->config_axi_slave_base))
 		return PTR_ERR(pcie->config_axi_slave_base);
@@ -312,7 +433,7 @@ static int mobiveil_pcie_parse_dt(struct mobiveil_pcie *pcie)
 
 	/* map csr resource */
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM,
-			"csr_axi_slave");
+					   "csr_axi_slave");
 	pcie->csr_axi_slave_base = devm_pci_remap_cfg_resource(dev, res);
 	if (IS_ERR(pcie->csr_axi_slave_base))
 		return PTR_ERR(pcie->csr_axi_slave_base);
@@ -337,92 +458,50 @@ static int mobiveil_pcie_parse_dt(struct mobiveil_pcie *pcie)
 		return -ENODEV;
 	}
 
-	irq_set_chained_handler_and_data(pcie->irq, mobiveil_pcie_isr, pcie);
-
 	return 0;
 }
 
-/*
- * select_paged_register - routine to access paged register of root complex
- *
- * registers of RC are paged, for this scheme to work
- * extracted higher 6 bits of the offset will be written to pg_sel
- * field of PAB_CTRL register and rest of the lower 10 bits enabled with
- * PAGE_SEL_EN are used as offset of the register.
- */
-static void select_paged_register(struct mobiveil_pcie *pcie, u32 offset)
-{
-	int pab_ctrl_dw, pg_sel;
-
-	/* clear pg_sel field */
-	pab_ctrl_dw = csr_readl(pcie, PAB_CTRL);
-	pab_ctrl_dw = (pab_ctrl_dw & ~(PAGE_SEL_MASK << PAGE_SEL_SHIFT));
-
-	/* set pg_sel field */
-	pg_sel = (offset >> PAGE_SEL_OFFSET_SHIFT) & PAGE_SEL_MASK;
-	pab_ctrl_dw |= ((pg_sel << PAGE_SEL_SHIFT));
-	csr_writel(pcie, pab_ctrl_dw, PAB_CTRL);
-}
-
-static void write_paged_register(struct mobiveil_pcie *pcie,
-		u32 val, u32 offset)
-{
-	u32 off = (offset & PAGE_LO_MASK) | PAGE_SEL_EN;
-
-	select_paged_register(pcie, offset);
-	csr_writel(pcie, val, off);
-}
-
-static u32 read_paged_register(struct mobiveil_pcie *pcie, u32 offset)
-{
-	u32 off = (offset & PAGE_LO_MASK) | PAGE_SEL_EN;
-
-	select_paged_register(pcie, offset);
-	return csr_readl(pcie, off);
-}
-
 static void program_ib_windows(struct mobiveil_pcie *pcie, int win_num,
-		int pci_addr, u32 type, u64 size)
+			       u64 pci_addr, u32 type, u64 size)
 {
-	int pio_ctrl_val;
-	int amap_ctrl_dw;
+	u32 value;
 	u64 size64 = ~(size - 1);
 
-	if ((pcie->ib_wins_configured + 1) > pcie->ppio_wins) {
+	if (win_num >= pcie->ppio_wins) {
 		dev_err(&pcie->pdev->dev,
 			"ERROR: max inbound windows reached !\n");
 		return;
 	}
 
-	pio_ctrl_val = csr_readl(pcie, PAB_PEX_PIO_CTRL);
-	csr_writel(pcie,
-		pio_ctrl_val | (1 << PIO_ENABLE_SHIFT), PAB_PEX_PIO_CTRL);
-	amap_ctrl_dw = read_paged_register(pcie, PAB_PEX_AMAP_CTRL(win_num));
-	amap_ctrl_dw = (amap_ctrl_dw | (type << AMAP_CTRL_TYPE_SHIFT));
-	amap_ctrl_dw = (amap_ctrl_dw | (1 << AMAP_CTRL_EN_SHIFT));
+	value = csr_readl(pcie, PAB_PEX_AMAP_CTRL(win_num));
+	value &= ~(AMAP_CTRL_TYPE_MASK << AMAP_CTRL_TYPE_SHIFT | WIN_SIZE_MASK);
+	value |= type << AMAP_CTRL_TYPE_SHIFT | 1 << AMAP_CTRL_EN_SHIFT |
+		 (lower_32_bits(size64) & WIN_SIZE_MASK);
+	csr_writel(pcie, value, PAB_PEX_AMAP_CTRL(win_num));
+
+	csr_writel(pcie, upper_32_bits(size64),
+		   PAB_EXT_PEX_AMAP_SIZEN(win_num));
 
-	write_paged_register(pcie, amap_ctrl_dw | lower_32_bits(size64),
-				PAB_PEX_AMAP_CTRL(win_num));
+	csr_writel(pcie, pci_addr, PAB_PEX_AMAP_AXI_WIN(win_num));
 
-	write_paged_register(pcie, upper_32_bits(size64),
-				PAB_EXT_PEX_AMAP_SIZEN(win_num));
+	csr_writel(pcie, lower_32_bits(pci_addr),
+		   PAB_PEX_AMAP_PEX_WIN_L(win_num));
+	csr_writel(pcie, upper_32_bits(pci_addr),
+		   PAB_PEX_AMAP_PEX_WIN_H(win_num));
 
-	write_paged_register(pcie, pci_addr, PAB_PEX_AMAP_AXI_WIN(win_num));
-	write_paged_register(pcie, pci_addr, PAB_PEX_AMAP_PEX_WIN_L(win_num));
-	write_paged_register(pcie, 0, PAB_PEX_AMAP_PEX_WIN_H(win_num));
+	pcie->ib_wins_configured++;
 }
 
 /*
  * routine to program the outbound windows
  */
 static void program_ob_windows(struct mobiveil_pcie *pcie, int win_num,
-		u64 cpu_addr, u64 pci_addr, u32 config_io_bit, u64 size)
+			       u64 cpu_addr, u64 pci_addr, u32 type, u64 size)
 {
-
-	u32 value, type;
+	u32 value;
 	u64 size64 = ~(size - 1);
 
-	if ((pcie->ob_wins_configured + 1) > pcie->apio_wins) {
+	if (win_num >= pcie->apio_wins) {
 		dev_err(&pcie->pdev->dev,
 			"ERROR: max outbound windows reached !\n");
 		return;
@@ -432,28 +511,27 @@ static void program_ob_windows(struct mobiveil_pcie *pcie, int win_num,
 	 * program Enable Bit to 1, Type Bit to (00) base 2, AXI Window Size Bit
 	 * to 4 KB in PAB_AXI_AMAP_CTRL register
 	 */
-	type = config_io_bit;
 	value = csr_readl(pcie, PAB_AXI_AMAP_CTRL(win_num));
-	csr_writel(pcie, 1 << WIN_ENABLE_SHIFT | type << WIN_TYPE_SHIFT |
-			lower_32_bits(size64), PAB_AXI_AMAP_CTRL(win_num));
+	value &= ~(WIN_TYPE_MASK << WIN_TYPE_SHIFT | WIN_SIZE_MASK);
+	value |= 1 << WIN_ENABLE_SHIFT | type << WIN_TYPE_SHIFT |
+		 (lower_32_bits(size64) & WIN_SIZE_MASK);
+	csr_writel(pcie, value, PAB_AXI_AMAP_CTRL(win_num));
 
-	write_paged_register(pcie, upper_32_bits(size64),
-				PAB_EXT_AXI_AMAP_SIZE(win_num));
+	csr_writel(pcie, upper_32_bits(size64), PAB_EXT_AXI_AMAP_SIZE(win_num));
 
 	/*
 	 * program AXI window base with appropriate value in
 	 * PAB_AXI_AMAP_AXI_WIN0 register
 	 */
-	value = csr_readl(pcie, PAB_AXI_AMAP_AXI_WIN(win_num));
-	csr_writel(pcie, cpu_addr & (~AXI_WINDOW_ALIGN_MASK),
-			PAB_AXI_AMAP_AXI_WIN(win_num));
-
-	value = csr_readl(pcie, PAB_AXI_AMAP_PEX_WIN_H(win_num));
+	csr_writel(pcie, lower_32_bits(cpu_addr) & (~AXI_WINDOW_ALIGN_MASK),
+		   PAB_AXI_AMAP_AXI_WIN(win_num));
+	csr_writel(pcie, upper_32_bits(cpu_addr),
+		   PAB_EXT_AXI_AMAP_AXI_WIN(win_num));
 
 	csr_writel(pcie, lower_32_bits(pci_addr),
-			PAB_AXI_AMAP_PEX_WIN_L(win_num));
+		   PAB_AXI_AMAP_PEX_WIN_L(win_num));
 	csr_writel(pcie, upper_32_bits(pci_addr),
-			PAB_AXI_AMAP_PEX_WIN_H(win_num));
+		   PAB_AXI_AMAP_PEX_WIN_H(win_num));
 
 	pcie->ob_wins_configured++;
 }
@@ -469,7 +547,9 @@ static int mobiveil_bringup_link(struct mobiveil_pcie *pcie)
 
 		usleep_range(LINK_WAIT_MIN, LINK_WAIT_MAX);
 	}
+
 	dev_err(&pcie->pdev->dev, "link never came up\n");
+
 	return -ETIMEDOUT;
 }
 
@@ -482,50 +562,55 @@ static void mobiveil_pcie_enable_msi(struct mobiveil_pcie *pcie)
 	msi->msi_pages_phys = (phys_addr_t)msg_addr;
 
 	writel_relaxed(lower_32_bits(msg_addr),
-		pcie->apb_csr_base + MSI_BASE_LO_OFFSET);
+		       pcie->apb_csr_base + MSI_BASE_LO_OFFSET);
 	writel_relaxed(upper_32_bits(msg_addr),
-		pcie->apb_csr_base + MSI_BASE_HI_OFFSET);
+		       pcie->apb_csr_base + MSI_BASE_HI_OFFSET);
 	writel_relaxed(4096, pcie->apb_csr_base + MSI_SIZE_OFFSET);
 	writel_relaxed(1, pcie->apb_csr_base + MSI_ENABLE_OFFSET);
 }
 
 static int mobiveil_host_init(struct mobiveil_pcie *pcie)
 {
-	u32 value, pab_ctrl, type = 0;
-	int err;
-	struct resource_entry *win, *tmp;
-
-	err = mobiveil_bringup_link(pcie);
-	if (err) {
-		dev_info(&pcie->pdev->dev, "link bring-up failed\n");
-		return err;
-	}
+	u32 value, pab_ctrl, type;
+	struct resource_entry *win;
+
+	/* setup bus numbers */
+	value = csr_readl(pcie, PCI_PRIMARY_BUS);
+	value &= 0xff000000;
+	value |= 0x00ff0100;
+	csr_writel(pcie, value, PCI_PRIMARY_BUS);
 
 	/*
 	 * program Bus Master Enable Bit in Command Register in PAB Config
 	 * Space
 	 */
 	value = csr_readl(pcie, PCI_COMMAND);
-	csr_writel(pcie, value | PCI_COMMAND_IO | PCI_COMMAND_MEMORY |
-		PCI_COMMAND_MASTER, PCI_COMMAND);
+	value |= PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER;
+	csr_writel(pcie, value, PCI_COMMAND);
 
 	/*
 	 * program PIO Enable Bit to 1 (and PEX PIO Enable to 1) in PAB_CTRL
 	 * register
 	 */
 	pab_ctrl = csr_readl(pcie, PAB_CTRL);
-	csr_writel(pcie, pab_ctrl | (1 << AMBA_PIO_ENABLE_SHIFT) |
-		(1 << PEX_PIO_ENABLE_SHIFT), PAB_CTRL);
+	pab_ctrl |= (1 << AMBA_PIO_ENABLE_SHIFT) | (1 << PEX_PIO_ENABLE_SHIFT);
+	csr_writel(pcie, pab_ctrl, PAB_CTRL);
 
 	csr_writel(pcie, (PAB_INTP_INTX_MASK | PAB_INTP_MSI_MASK),
-		PAB_INTP_AMBA_MISC_ENB);
+		   PAB_INTP_AMBA_MISC_ENB);
 
 	/*
 	 * program PIO Enable Bit to 1 and Config Window Enable Bit to 1 in
 	 * PAB_AXI_PIO_CTRL Register
 	 */
 	value = csr_readl(pcie, PAB_AXI_PIO_CTRL);
-	csr_writel(pcie, value | APIO_EN_MASK, PAB_AXI_PIO_CTRL);
+	value |= APIO_EN_MASK;
+	csr_writel(pcie, value, PAB_AXI_PIO_CTRL);
+
+	/* Enable PCIe PIO master */
+	value = csr_readl(pcie, PAB_PEX_PIO_CTRL);
+	value |= 1 << PIO_ENABLE_SHIFT;
+	csr_writel(pcie, value, PAB_PEX_PIO_CTRL);
 
 	/*
 	 * we'll program one outbound window for config reads and
@@ -535,32 +620,38 @@ static int mobiveil_host_init(struct mobiveil_pcie *pcie)
 	 */
 
 	/* config outbound translation window */
-	program_ob_windows(pcie, pcie->ob_wins_configured,
-			pcie->ob_io_res->start, 0, CFG_WINDOW_TYPE,
-			resource_size(pcie->ob_io_res));
+	program_ob_windows(pcie, WIN_NUM_0, pcie->ob_io_res->start, 0,
+			   CFG_WINDOW_TYPE, resource_size(pcie->ob_io_res));
 
 	/* memory inbound translation window */
-	program_ib_windows(pcie, WIN_NUM_1, 0, MEM_WINDOW_TYPE, IB_WIN_SIZE);
+	program_ib_windows(pcie, WIN_NUM_0, 0, MEM_WINDOW_TYPE, IB_WIN_SIZE);
 
 	/* Get the I/O and memory ranges from DT */
-	resource_list_for_each_entry_safe(win, tmp, &pcie->resources) {
-		type = 0;
+	resource_list_for_each_entry(win, &pcie->resources) {
 		if (resource_type(win->res) == IORESOURCE_MEM)
 			type = MEM_WINDOW_TYPE;
-		if (resource_type(win->res) == IORESOURCE_IO)
+		else if (resource_type(win->res) == IORESOURCE_IO)
 			type = IO_WINDOW_TYPE;
-		if (type) {
-			/* configure outbound translation window */
-			program_ob_windows(pcie, pcie->ob_wins_configured,
-				win->res->start, 0, type,
-				resource_size(win->res));
-		}
+		else
+			continue;
+
+		/* configure outbound translation window */
+		program_ob_windows(pcie, pcie->ob_wins_configured,
+				   win->res->start,
+				   win->res->start - win->offset,
+				   type, resource_size(win->res));
 	}
 
+	/* fixup for PCIe class register */
+	value = csr_readl(pcie, PAB_INTP_AXI_PIO_CLASS);
+	value &= 0xff;
+	value |= (PCI_CLASS_BRIDGE_PCI << 16);
+	csr_writel(pcie, value, PAB_INTP_AXI_PIO_CLASS);
+
 	/* setup MSI hardware registers */
 	mobiveil_pcie_enable_msi(pcie);
 
-	return err;
+	return 0;
 }
 
 static void mobiveil_mask_intx_irq(struct irq_data *data)
@@ -574,7 +665,8 @@ static void mobiveil_mask_intx_irq(struct irq_data *data)
 	mask = 1 << ((data->hwirq + PAB_INTX_START) - 1);
 	raw_spin_lock_irqsave(&pcie->intx_mask_lock, flags);
 	shifted_val = csr_readl(pcie, PAB_INTP_AMBA_MISC_ENB);
-	csr_writel(pcie, (shifted_val & (~mask)), PAB_INTP_AMBA_MISC_ENB);
+	shifted_val &= ~mask;
+	csr_writel(pcie, shifted_val, PAB_INTP_AMBA_MISC_ENB);
 	raw_spin_unlock_irqrestore(&pcie->intx_mask_lock, flags);
 }
 
@@ -589,7 +681,8 @@ static void mobiveil_unmask_intx_irq(struct irq_data *data)
 	mask = 1 << ((data->hwirq + PAB_INTX_START) - 1);
 	raw_spin_lock_irqsave(&pcie->intx_mask_lock, flags);
 	shifted_val = csr_readl(pcie, PAB_INTP_AMBA_MISC_ENB);
-	csr_writel(pcie, (shifted_val | mask), PAB_INTP_AMBA_MISC_ENB);
+	shifted_val |= mask;
+	csr_writel(pcie, shifted_val, PAB_INTP_AMBA_MISC_ENB);
 	raw_spin_unlock_irqrestore(&pcie->intx_mask_lock, flags);
 }
 
@@ -603,10 +696,11 @@ static struct irq_chip intx_irq_chip = {
 
 /* routine to setup the INTx related data */
 static int mobiveil_pcie_intx_map(struct irq_domain *domain, unsigned int irq,
-		irq_hw_number_t hwirq)
+				  irq_hw_number_t hwirq)
 {
 	irq_set_chip_and_handler(irq, &intx_irq_chip, handle_level_irq);
 	irq_set_chip_data(irq, domain->host_data);
+
 	return 0;
 }
 
@@ -623,7 +717,7 @@ static struct irq_chip mobiveil_msi_irq_chip = {
 
 static struct msi_domain_info mobiveil_msi_domain_info = {
 	.flags	= (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
-		MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX),
+		   MSI_FLAG_PCI_MSIX),
 	.chip	= &mobiveil_msi_irq_chip,
 };
 
@@ -641,7 +735,7 @@ static void mobiveil_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 }
 
 static int mobiveil_msi_set_affinity(struct irq_data *irq_data,
-		const struct cpumask *mask, bool force)
+				     const struct cpumask *mask, bool force)
 {
 	return -EINVAL;
 }
@@ -653,7 +747,8 @@ static struct irq_chip mobiveil_msi_bottom_irq_chip = {
 };
 
 static int mobiveil_irq_msi_domain_alloc(struct irq_domain *domain,
-		unsigned int virq, unsigned int nr_irqs, void *args)
+					 unsigned int virq,
+					 unsigned int nr_irqs, void *args)
 {
 	struct mobiveil_pcie *pcie = domain->host_data;
 	struct mobiveil_msi *msi = &pcie->msi;
@@ -673,13 +768,13 @@ static int mobiveil_irq_msi_domain_alloc(struct irq_domain *domain,
 	mutex_unlock(&msi->lock);
 
 	irq_domain_set_info(domain, virq, bit, &mobiveil_msi_bottom_irq_chip,
-				domain->host_data, handle_level_irq,
-				NULL, NULL);
+			    domain->host_data, handle_level_irq, NULL, NULL);
 	return 0;
 }
 
 static void mobiveil_irq_msi_domain_free(struct irq_domain *domain,
-		unsigned int virq, unsigned int nr_irqs)
+					 unsigned int virq,
+					 unsigned int nr_irqs)
 {
 	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
 	struct mobiveil_pcie *pcie = irq_data_get_irq_chip_data(d);
@@ -687,12 +782,11 @@ static void mobiveil_irq_msi_domain_free(struct irq_domain *domain,
 
 	mutex_lock(&msi->lock);
 
-	if (!test_bit(d->hwirq, msi->msi_irq_in_use)) {
+	if (!test_bit(d->hwirq, msi->msi_irq_in_use))
 		dev_err(&pcie->pdev->dev, "trying to free unused MSI#%lu\n",
 			d->hwirq);
-	} else {
+	else
 		__clear_bit(d->hwirq, msi->msi_irq_in_use);
-	}
 
 	mutex_unlock(&msi->lock);
 }
@@ -716,12 +810,14 @@ static int mobiveil_allocate_msi_domains(struct mobiveil_pcie *pcie)
 	}
 
 	msi->msi_domain = pci_msi_create_irq_domain(fwnode,
-				&mobiveil_msi_domain_info, msi->dev_domain);
+						    &mobiveil_msi_domain_info,
+						    msi->dev_domain);
 	if (!msi->msi_domain) {
 		dev_err(dev, "failed to create MSI domain\n");
 		irq_domain_remove(msi->dev_domain);
 		return -ENOMEM;
 	}
+
 	return 0;
 }
 
@@ -732,12 +828,12 @@ static int mobiveil_pcie_init_irq_domain(struct mobiveil_pcie *pcie)
 	int ret;
 
 	/* setup INTx */
-	pcie->intx_domain = irq_domain_add_linear(node,
-				PCI_NUM_INTX, &intx_domain_ops, pcie);
+	pcie->intx_domain = irq_domain_add_linear(node, PCI_NUM_INTX,
+						  &intx_domain_ops, pcie);
 
 	if (!pcie->intx_domain) {
 		dev_err(dev, "Failed to get a INTx IRQ domain\n");
-		return -ENODEV;
+		return -ENOMEM;
 	}
 
 	raw_spin_lock_init(&pcie->intx_mask_lock);
@@ -763,11 +859,9 @@ static int mobiveil_pcie_probe(struct platform_device *pdev)
 	/* allocate the PCIe port */
 	bridge = devm_pci_alloc_host_bridge(dev, sizeof(*pcie));
 	if (!bridge)
-		return -ENODEV;
+		return -ENOMEM;
 
 	pcie = pci_host_bridge_priv(bridge);
-	if (!pcie)
-		return -ENOMEM;
 
 	pcie->pdev = pdev;
 
@@ -784,7 +878,7 @@ static int mobiveil_pcie_probe(struct platform_device *pdev)
 						    &pcie->resources, &iobase);
 	if (ret) {
 		dev_err(dev, "Getting bridge resources failed\n");
-		return -ENOMEM;
+		return ret;
 	}
 
 	/*
@@ -797,9 +891,6 @@ static int mobiveil_pcie_probe(struct platform_device *pdev)
 		goto error;
 	}
 
-	/* fixup for PCIe class register */
-	csr_writel(pcie, 0x060402ab, PAB_INTP_AXI_PIO_CLASS);
-
 	/* initialize the IRQ domains */
 	ret = mobiveil_pcie_init_irq_domain(pcie);
 	if (ret) {
@@ -807,6 +898,8 @@ static int mobiveil_pcie_probe(struct platform_device *pdev)
 		goto error;
 	}
 
+	irq_set_chained_handler_and_data(pcie->irq, mobiveil_pcie_isr, pcie);
+
 	ret = devm_request_pci_bus_resources(dev, &pcie->resources);
 	if (ret)
 		goto error;
@@ -820,6 +913,12 @@ static int mobiveil_pcie_probe(struct platform_device *pdev)
 	bridge->map_irq = of_irq_parse_and_map_pci;
 	bridge->swizzle_irq = pci_common_swizzle;
 
+	ret = mobiveil_bringup_link(pcie);
+	if (ret) {
+		dev_info(dev, "link bring-up failed\n");
+		goto error;
+	}
+
 	/* setup the kernel resources for the newly added PCIe root bus */
 	ret = pci_scan_root_bus_bridge(bridge);
 	if (ret)
@@ -848,10 +947,10 @@ MODULE_DEVICE_TABLE(of, mobiveil_pcie_of_match);
 static struct platform_driver mobiveil_pcie_driver = {
 	.probe = mobiveil_pcie_probe,
 	.driver = {
-			.name = "mobiveil-pcie",
-			.of_match_table = mobiveil_pcie_of_match,
-			.suppress_bind_attrs = true,
-		},
+		.name = "mobiveil-pcie",
+		.of_match_table = mobiveil_pcie_of_match,
+		.suppress_bind_attrs = true,
+	},
 };
 
 builtin_platform_driver(mobiveil_pcie_driver);
diff --git a/drivers/pci/controller/pcie-xilinx-nwl.c b/drivers/pci/controller/pcie-xilinx-nwl.c
index 3b031f00a94a..45c0f344ccd1 100644
--- a/drivers/pci/controller/pcie-xilinx-nwl.c
+++ b/drivers/pci/controller/pcie-xilinx-nwl.c
@@ -482,15 +482,13 @@ static int nwl_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
 	int i;
 
 	mutex_lock(&msi->lock);
-	bit = bitmap_find_next_zero_area(msi->bitmap, INT_PCI_MSI_NR, 0,
-					 nr_irqs, 0);
-	if (bit >= INT_PCI_MSI_NR) {
+	bit = bitmap_find_free_region(msi->bitmap, INT_PCI_MSI_NR,
+				      get_count_order(nr_irqs));
+	if (bit < 0) {
 		mutex_unlock(&msi->lock);
 		return -ENOSPC;
 	}
 
-	bitmap_set(msi->bitmap, bit, nr_irqs);
-
 	for (i = 0; i < nr_irqs; i++) {
 		irq_domain_set_info(domain, virq + i, bit + i, &nwl_irq_chip,
 				domain->host_data, handle_simple_irq,
@@ -508,7 +506,8 @@ static void nwl_irq_domain_free(struct irq_domain *domain, unsigned int virq,
 	struct nwl_msi *msi = &pcie->msi;
 
 	mutex_lock(&msi->lock);
-	bitmap_clear(msi->bitmap, data->hwirq, nr_irqs);
+	bitmap_release_region(msi->bitmap, data->hwirq,
+			      get_count_order(nr_irqs));
 	mutex_unlock(&msi->lock);
 }
 
diff --git a/drivers/pci/controller/vmd.c b/drivers/pci/controller/vmd.c
index 999a5509e57e..4575e0c6dc4b 100644
--- a/drivers/pci/controller/vmd.c
+++ b/drivers/pci/controller/vmd.c
@@ -627,7 +627,7 @@ static int vmd_enable_domain(struct vmd_dev *vmd, unsigned long features)
 	 * 32-bit resources.  __pci_assign_resource() enforces that
 	 * artificial restriction to make sure everything will fit.
 	 *
-	 * The only way we could use a 64-bit non-prefechable MEMBAR is
+	 * The only way we could use a 64-bit non-prefetchable MEMBAR is
 	 * if its address is <4GB so that we can convert it to a 32-bit
 	 * resource.  To be visible to the host OS, all VMD endpoints must
 	 * be initially configured by platform BIOS, which includes setting
diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
index 27806987e93b..1cfe3687a211 100644
--- a/drivers/pci/endpoint/functions/pci-epf-test.c
+++ b/drivers/pci/endpoint/functions/pci-epf-test.c
@@ -381,15 +381,15 @@ static void pci_epf_test_unbind(struct pci_epf *epf)
 		epf_bar = &epf->bar[bar];
 
 		if (epf_test->reg[bar]) {
-			pci_epf_free_space(epf, epf_test->reg[bar], bar);
 			pci_epc_clear_bar(epc, epf->func_no, epf_bar);
+			pci_epf_free_space(epf, epf_test->reg[bar], bar);
 		}
 	}
 }
 
 static int pci_epf_test_set_bar(struct pci_epf *epf)
 {
-	int bar;
+	int bar, add;
 	int ret;
 	struct pci_epf_bar *epf_bar;
 	struct pci_epc *epc = epf->epc;
@@ -400,8 +400,14 @@ static int pci_epf_test_set_bar(struct pci_epf *epf)
 
 	epc_features = epf_test->epc_features;
 
-	for (bar = BAR_0; bar <= BAR_5; bar++) {
+	for (bar = BAR_0; bar <= BAR_5; bar += add) {
 		epf_bar = &epf->bar[bar];
+		/*
+		 * pci_epc_set_bar() sets PCI_BASE_ADDRESS_MEM_TYPE_64
+		 * if the specific implementation required a 64-bit BAR,
+		 * even if we only requested a 32-bit BAR.
+		 */
+		add = (epf_bar->flags & PCI_BASE_ADDRESS_MEM_TYPE_64) ? 2 : 1;
 
 		if (!!(epc_features->reserved_bar & (1 << bar)))
 			continue;
@@ -413,13 +419,6 @@ static int pci_epf_test_set_bar(struct pci_epf *epf)
 			if (bar == test_reg_bar)
 				return ret;
 		}
-		/*
-		 * pci_epc_set_bar() sets PCI_BASE_ADDRESS_MEM_TYPE_64
-		 * if the specific implementation required a 64-bit BAR,
-		 * even if we only requested a 32-bit BAR.
-		 */
-		if (epf_bar->flags & PCI_BASE_ADDRESS_MEM_TYPE_64)
-			bar++;
 	}
 
 	return 0;
@@ -431,13 +430,19 @@ static int pci_epf_test_alloc_space(struct pci_epf *epf)
 	struct device *dev = &epf->dev;
 	struct pci_epf_bar *epf_bar;
 	void *base;
-	int bar;
+	int bar, add;
 	enum pci_barno test_reg_bar = epf_test->test_reg_bar;
 	const struct pci_epc_features *epc_features;
+	size_t test_reg_size;
 
 	epc_features = epf_test->epc_features;
 
-	base = pci_epf_alloc_space(epf, sizeof(struct pci_epf_test_reg),
+	if (epc_features->bar_fixed_size[test_reg_bar])
+		test_reg_size = bar_size[test_reg_bar];
+	else
+		test_reg_size = sizeof(struct pci_epf_test_reg);
+
+	base = pci_epf_alloc_space(epf, test_reg_size,
 				   test_reg_bar, epc_features->align);
 	if (!base) {
 		dev_err(dev, "Failed to allocated register space\n");
@@ -445,8 +450,10 @@ static int pci_epf_test_alloc_space(struct pci_epf *epf)
 	}
 	epf_test->reg[test_reg_bar] = base;
 
-	for (bar = BAR_0; bar <= BAR_5; bar++) {
+	for (bar = BAR_0; bar <= BAR_5; bar += add) {
 		epf_bar = &epf->bar[bar];
+		add = (epf_bar->flags & PCI_BASE_ADDRESS_MEM_TYPE_64) ? 2 : 1;
+
 		if (bar == test_reg_bar)
 			continue;
 
@@ -459,8 +466,6 @@ static int pci_epf_test_alloc_space(struct pci_epf *epf)
 			dev_err(dev, "Failed to allocate space for BAR%d\n",
 				bar);
 		epf_test->reg[bar] = base;
-		if (epf_bar->flags & PCI_BASE_ADDRESS_MEM_TYPE_64)
-			bar++;
 	}
 
 	return 0;
diff --git a/drivers/pci/endpoint/pci-epc-core.c b/drivers/pci/endpoint/pci-epc-core.c
index e4712a0f249c..2091508c1620 100644
--- a/drivers/pci/endpoint/pci-epc-core.c
+++ b/drivers/pci/endpoint/pci-epc-core.c
@@ -519,11 +519,12 @@ void pci_epc_remove_epf(struct pci_epc *epc, struct pci_epf *epf)
 {
 	unsigned long flags;
 
-	if (!epc || IS_ERR(epc))
+	if (!epc || IS_ERR(epc) || !epf)
 		return;
 
 	spin_lock_irqsave(&epc->lock, flags);
 	list_del(&epf->list);
+	epf->epc = NULL;
 	spin_unlock_irqrestore(&epc->lock, flags);
 }
 EXPORT_SYMBOL_GPL(pci_epc_remove_epf);
diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index 3aa115ed3a65..525fd3f272b3 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -132,8 +132,6 @@ static void pci_read_vf_config_common(struct pci_dev *virtfn)
 			     &physfn->sriov->subsystem_vendor);
 	pci_read_config_word(virtfn, PCI_SUBSYSTEM_ID,
 			     &physfn->sriov->subsystem_device);
-
-	physfn->sriov->cfg_size = pci_cfg_space_size(virtfn);
 }
 
 int pci_iov_add_virtfn(struct pci_dev *dev, int id)
diff --git a/drivers/pci/mmap.c b/drivers/pci/mmap.c
index 24505b08de40..b8c9011987f4 100644
--- a/drivers/pci/mmap.c
+++ b/drivers/pci/mmap.c
@@ -73,7 +73,7 @@ int pci_mmap_resource_range(struct pci_dev *pdev, int bar,
 #elif defined(HAVE_PCI_MMAP) /* && !ARCH_GENERIC_PCI_MMAP_RESOURCE */
 
 /*
- * Legacy setup: Impement pci_mmap_resource_range() as a wrapper around
+ * Legacy setup: Implement pci_mmap_resource_range() as a wrapper around
  * the architecture's pci_mmap_page_range(), converting to "user visible"
  * addresses as necessary.
  */
diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
index e039b740fe74..59a6d232f77a 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi.c
@@ -237,7 +237,7 @@ static void msi_set_mask_bit(struct irq_data *data, u32 flag)
 }
 
 /**
- * pci_msi_mask_irq - Generic irq chip callback to mask PCI/MSI interrupts
+ * pci_msi_mask_irq - Generic IRQ chip callback to mask PCI/MSI interrupts
  * @data:	pointer to irqdata associated to that interrupt
  */
 void pci_msi_mask_irq(struct irq_data *data)
@@ -247,7 +247,7 @@ void pci_msi_mask_irq(struct irq_data *data)
 EXPORT_SYMBOL_GPL(pci_msi_mask_irq);
 
 /**
- * pci_msi_unmask_irq - Generic irq chip callback to unmask PCI/MSI interrupts
+ * pci_msi_unmask_irq - Generic IRQ chip callback to unmask PCI/MSI interrupts
  * @data:	pointer to irqdata associated to that interrupt
  */
 void pci_msi_unmask_irq(struct irq_data *data)
@@ -588,11 +588,11 @@ static int msi_verify_entries(struct pci_dev *dev)
  * msi_capability_init - configure device's MSI capability structure
  * @dev: pointer to the pci_dev data structure of MSI device function
  * @nvec: number of interrupts to allocate
- * @affd: description of automatic irq affinity assignments (may be %NULL)
+ * @affd: description of automatic IRQ affinity assignments (may be %NULL)
  *
  * Setup the MSI capability structure of the device with the requested
  * number of interrupts.  A return value of zero indicates the successful
- * setup of an entry with the new MSI irq.  A negative return value indicates
+ * setup of an entry with the new MSI IRQ.  A negative return value indicates
  * an error, and a positive return value indicates the number of interrupts
  * which could have been allocated.
  */
@@ -609,7 +609,7 @@ static int msi_capability_init(struct pci_dev *dev, int nvec,
 	if (!entry)
 		return -ENOMEM;
 
-	/* All MSIs are unmasked by default, Mask them all */
+	/* All MSIs are unmasked by default; mask them all */
 	mask = msi_mask(entry->msi_attrib.multi_cap);
 	msi_mask_irq(entry, mask, mask);
 
@@ -637,7 +637,7 @@ static int msi_capability_init(struct pci_dev *dev, int nvec,
 		return ret;
 	}
 
-	/* Set MSI enabled bits	 */
+	/* Set MSI enabled bits	*/
 	pci_intx_for_msi(dev, 0);
 	pci_msi_set_enable(dev, 1);
 	dev->msi_enabled = 1;
@@ -729,11 +729,11 @@ static void msix_program_entries(struct pci_dev *dev,
  * @dev: pointer to the pci_dev data structure of MSI-X device function
  * @entries: pointer to an array of struct msix_entry entries
  * @nvec: number of @entries
- * @affd: Optional pointer to enable automatic affinity assignement
+ * @affd: Optional pointer to enable automatic affinity assignment
  *
  * Setup the MSI-X capability structure of device function with a
- * single MSI-X irq. A return of zero indicates the successful setup of
- * requested MSI-X entries with allocated irqs or non-zero for otherwise.
+ * single MSI-X IRQ. A return of zero indicates the successful setup of
+ * requested MSI-X entries with allocated IRQs or non-zero for otherwise.
  **/
 static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
 				int nvec, struct irq_affinity *affd)
@@ -789,7 +789,7 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
 out_avail:
 	if (ret < 0) {
 		/*
-		 * If we had some success, report the number of irqs
+		 * If we had some success, report the number of IRQs
 		 * we succeeded in setting up.
 		 */
 		struct msi_desc *entry;
@@ -812,7 +812,7 @@ out_free:
 /**
  * pci_msi_supported - check whether MSI may be enabled on a device
  * @dev: pointer to the pci_dev data structure of MSI device function
- * @nvec: how many MSIs have been requested ?
+ * @nvec: how many MSIs have been requested?
  *
  * Look at global flags, the device itself, and its parent buses
  * to determine if MSI/-X are supported for the device. If MSI/-X is
@@ -896,7 +896,7 @@ static void pci_msi_shutdown(struct pci_dev *dev)
 	/* Keep cached state to be restored */
 	__pci_msi_desc_mask_irq(desc, mask, ~mask);
 
-	/* Restore dev->irq to its default pin-assertion irq */
+	/* Restore dev->irq to its default pin-assertion IRQ */
 	dev->irq = desc->msi_attrib.default_irq;
 	pcibios_alloc_irq(dev);
 }
@@ -958,7 +958,7 @@ static int __pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries,
 		}
 	}
 
-	/* Check whether driver already requested for MSI irq */
+	/* Check whether driver already requested for MSI IRQ */
 	if (dev->msi_enabled) {
 		pci_info(dev, "can't enable MSI-X (MSI IRQ already assigned)\n");
 		return -EINVAL;
@@ -1026,7 +1026,7 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec,
 	if (!pci_msi_supported(dev, minvec))
 		return -EINVAL;
 
-	/* Check whether driver already requested MSI-X irqs */
+	/* Check whether driver already requested MSI-X IRQs */
 	if (dev->msix_enabled) {
 		pci_info(dev, "can't enable MSI (MSI-X already enabled)\n");
 		return -EINVAL;
@@ -1113,8 +1113,8 @@ static int __pci_enable_msix_range(struct pci_dev *dev,
  * pci_enable_msix_range - configure device's MSI-X capability structure
  * @dev: pointer to the pci_dev data structure of MSI-X device function
  * @entries: pointer to an array of MSI-X entries
- * @minvec: minimum number of MSI-X irqs requested
- * @maxvec: maximum number of MSI-X irqs requested
+ * @minvec: minimum number of MSI-X IRQs requested
+ * @maxvec: maximum number of MSI-X IRQs requested
  *
  * Setup the MSI-X capability structure of device function with a maximum
  * possible number of interrupts in the range between @minvec and @maxvec
@@ -1179,7 +1179,7 @@ int pci_alloc_irq_vectors_affinity(struct pci_dev *dev, unsigned int min_vecs,
 			return msi_vecs;
 	}
 
-	/* use legacy irq if allowed */
+	/* use legacy IRQ if allowed */
 	if (flags & PCI_IRQ_LEGACY) {
 		if (min_vecs == 1 && dev->irq) {
 			/*
@@ -1248,7 +1248,7 @@ int pci_irq_vector(struct pci_dev *dev, unsigned int nr)
 EXPORT_SYMBOL(pci_irq_vector);
 
 /**
- * pci_irq_get_affinity - return the affinity of a particular msi vector
+ * pci_irq_get_affinity - return the affinity of a particular MSI vector
  * @dev:	PCI device to operate on
  * @nr:		device-relative interrupt vector index (0-based).
  */
@@ -1280,7 +1280,7 @@ const struct cpumask *pci_irq_get_affinity(struct pci_dev *dev, int nr)
 EXPORT_SYMBOL(pci_irq_get_affinity);
 
 /**
- * pci_irq_get_node - return the numa node of a particular msi vector
+ * pci_irq_get_node - return the NUMA node of a particular MSI vector
  * @pdev:	PCI device to operate on
  * @vec:	device-relative interrupt vector index (0-based).
  */
@@ -1330,7 +1330,7 @@ void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg)
 /**
  * pci_msi_domain_calc_hwirq - Generate a unique ID for an MSI source
  * @dev:	Pointer to the PCI device
- * @desc:	Pointer to the msi descriptor
+ * @desc:	Pointer to the MSI descriptor
  *
  * The ID number is only used within the irqdomain.
  */
@@ -1348,7 +1348,8 @@ static inline bool pci_msi_desc_is_multi_msi(struct msi_desc *desc)
 }
 
 /**
- * pci_msi_domain_check_cap - Verify that @domain supports the capabilities for @dev
+ * pci_msi_domain_check_cap - Verify that @domain supports the capabilities
+ * 			      for @dev
  * @domain:	The interrupt domain to check
  * @info:	The domain info for verification
  * @dev:	The device to check
diff --git a/drivers/pci/p2pdma.c b/drivers/pci/p2pdma.c
index a3073ce16520..234476226529 100644
--- a/drivers/pci/p2pdma.c
+++ b/drivers/pci/p2pdma.c
@@ -195,7 +195,7 @@ EXPORT_SYMBOL_GPL(pci_p2pdma_add_resource);
 
 /*
  * Note this function returns the parent PCI device with a
- * reference taken. It is the caller's responsibily to drop
+ * reference taken. It is the caller's responsibility to drop
  * the reference.
  */
 static struct pci_dev *find_parent_pci_dev(struct device *dev)
@@ -355,7 +355,7 @@ static int upstream_bridge_distance(struct pci_dev *provider,
 
 	/*
 	 * Allow the connection if both devices are on a whitelisted root
-	 * complex, but add an arbitary large value to the distance.
+	 * complex, but add an arbitrary large value to the distance.
 	 */
 	if (root_complex_whitelist(provider) &&
 	    root_complex_whitelist(client))
@@ -414,7 +414,7 @@ static int upstream_bridge_distance_warn(struct pci_dev *provider,
 }
 
 /**
- * pci_p2pdma_distance_many - Determive the cumulative distance between
+ * pci_p2pdma_distance_many - Determine the cumulative distance between
  *	a p2pdma provider and the clients in use.
  * @provider: p2pdma provider to check against the client list
  * @clients: array of devices to check (NULL-terminated)
@@ -443,6 +443,14 @@ int pci_p2pdma_distance_many(struct pci_dev *provider, struct device **clients,
 		return -1;
 
 	for (i = 0; i < num_clients; i++) {
+		if (IS_ENABLED(CONFIG_DMA_VIRT_OPS) &&
+		    clients[i]->dma_ops == &dma_virt_ops) {
+			if (verbose)
+				dev_warn(clients[i],
+					 "cannot be used for peer-to-peer DMA because the driver makes use of dma_virt_ops\n");
+			return -1;
+		}
+
 		pci_client = find_parent_pci_dev(clients[i]);
 		if (!pci_client) {
 			if (verbose)
@@ -721,7 +729,7 @@ int pci_p2pdma_map_sg(struct device *dev, struct scatterlist *sg, int nents,
 	 * p2pdma mappings are not compatible with devices that use
 	 * dma_virt_ops. If the upper layers do the right thing
 	 * this should never happen because it will be prevented
-	 * by the check in pci_p2pdma_add_client()
+	 * by the check in pci_p2pdma_distance_many()
 	 */
 	if (WARN_ON_ONCE(IS_ENABLED(CONFIG_DMA_VIRT_OPS) &&
 			 dev->dma_ops == &dma_virt_ops))
diff --git a/drivers/pci/pci-bridge-emul.c b/drivers/pci/pci-bridge-emul.c
index 83fb077d0b41..06083b86d4f4 100644
--- a/drivers/pci/pci-bridge-emul.c
+++ b/drivers/pci/pci-bridge-emul.c
@@ -305,7 +305,7 @@ int pci_bridge_emul_init(struct pci_bridge_emul *bridge,
 }
 
 /*
- * Cleanup a pci_bridge_emul structure that was previously initilized
+ * Cleanup a pci_bridge_emul structure that was previously initialized
  * using pci_bridge_emul_init().
  */
 void pci_bridge_emul_cleanup(struct pci_bridge_emul *bridge)
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index 36dbe960306b..a8124e47bf6e 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -399,7 +399,8 @@ void __weak pcibios_free_irq(struct pci_dev *dev)
 #ifdef CONFIG_PCI_IOV
 static inline bool pci_device_can_probe(struct pci_dev *pdev)
 {
-	return (!pdev->is_virtfn || pdev->physfn->sriov->drivers_autoprobe);
+	return (!pdev->is_virtfn || pdev->physfn->sriov->drivers_autoprobe ||
+		pdev->driver_override);
 }
 #else
 static inline bool pci_device_can_probe(struct pci_dev *pdev)
@@ -414,6 +415,9 @@ static int pci_device_probe(struct device *dev)
 	struct pci_dev *pci_dev = to_pci_dev(dev);
 	struct pci_driver *drv = to_pci_driver(dev->driver);
 
+	if (!pci_device_can_probe(pci_dev))
+		return -ENODEV;
+
 	pci_assign_irq(pci_dev);
 
 	error = pcibios_alloc_irq(pci_dev);
@@ -421,12 +425,10 @@ static int pci_device_probe(struct device *dev)
 		return error;
 
 	pci_dev_get(pci_dev);
-	if (pci_device_can_probe(pci_dev)) {
-		error = __pci_device_probe(drv, pci_dev);
-		if (error) {
-			pcibios_free_irq(pci_dev);
-			pci_dev_put(pci_dev);
-		}
+	error = __pci_device_probe(drv, pci_dev);
+	if (error) {
+		pcibios_free_irq(pci_dev);
+		pci_dev_put(pci_dev);
 	}
 
 	return error;
diff --git a/drivers/pci/pci-pf-stub.c b/drivers/pci/pci-pf-stub.c
index 9795649fc6f9..ef293e735c55 100644
--- a/drivers/pci/pci-pf-stub.c
+++ b/drivers/pci/pci-pf-stub.c
@@ -1,7 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0
 /* pci-pf-stub - simple stub driver for PCI SR-IOV PF device
  *
- * This driver is meant to act as a "whitelist" for devices that provde
+ * This driver is meant to act as a "whitelist" for devices that provide
  * SR-IOV functionality while at the same time not actually needing a
  * driver of their own.
  */
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index 6d27475e39b2..965c72104150 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -182,6 +182,9 @@ static ssize_t current_link_speed_show(struct device *dev,
 		return -EINVAL;
 
 	switch (linkstat & PCI_EXP_LNKSTA_CLS) {
+	case PCI_EXP_LNKSTA_CLS_32_0GB:
+		speed = "32 GT/s";
+		break;
 	case PCI_EXP_LNKSTA_CLS_16_0GB:
 		speed = "16 GT/s";
 		break;
@@ -477,7 +480,7 @@ static ssize_t remove_store(struct device *dev, struct device_attribute *attr,
 		pci_stop_and_remove_bus_device_locked(to_pci_dev(dev));
 	return count;
 }
-static struct device_attribute dev_remove_attr = __ATTR(remove,
+static struct device_attribute dev_remove_attr = __ATTR_IGNORE_LOCKDEP(remove,
 							(S_IWUSR|S_IWGRP),
 							NULL, remove_store);
 
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index b1f563916036..29ed5ec1ac27 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -4535,7 +4535,7 @@ static int pci_af_flr(struct pci_dev *dev, int probe)
 
 	/*
 	 * Wait for Transaction Pending bit to clear.  A word-aligned test
-	 * is used, so we use the conrol offset rather than status and shift
+	 * is used, so we use the control offset rather than status and shift
 	 * the test bit to match.
 	 */
 	if (!pci_wait_for_pending(dev, pos + PCI_AF_CTRL,
@@ -5669,7 +5669,9 @@ enum pci_bus_speed pcie_get_speed_cap(struct pci_dev *dev)
 	 */
 	pcie_capability_read_dword(dev, PCI_EXP_LNKCAP2, &lnkcap2);
 	if (lnkcap2) { /* PCIe r3.0-compliant */
-		if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_16_0GB)
+		if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_32_0GB)
+			return PCIE_SPEED_32_0GT;
+		else if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_16_0GB)
 			return PCIE_SPEED_16_0GT;
 		else if (lnkcap2 & PCI_EXP_LNKCAP2_SLS_8_0GB)
 			return PCIE_SPEED_8_0GT;
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index 5db6f985f16d..1be03a97cb92 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -298,7 +298,6 @@ struct pci_sriov {
 	u16		driver_max_VFs;	/* Max num VFs driver supports */
 	struct pci_dev	*dev;		/* Lowest numbered PF */
 	struct pci_dev	*self;		/* This PF */
-	u32		cfg_size;	/* VF config space size */
 	u32		class;		/* VF device */
 	u8		hdr_type;	/* VF header type */
 	u16		subsystem_vendor; /* VF subsystem vendor */
diff --git a/drivers/pci/pcie/aer_inject.c b/drivers/pci/pcie/aer_inject.c
index 043b8b0cfcc5..6988fe7389b9 100644
--- a/drivers/pci/pcie/aer_inject.c
+++ b/drivers/pci/pcie/aer_inject.c
@@ -2,7 +2,7 @@
 /*
  * PCIe AER software error injection support.
  *
- * Debuging PCIe AER code is quite difficult because it is hard to
+ * Debugging PCIe AER code is quite difficult because it is hard to
  * trigger various real hardware errors. Software based error
  * injection can fake almost all kinds of errors with the help of a
  * user space helper tool aer-inject, which can be gotten from:
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index f9ef7ad3f75d..a3c7338fad86 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -668,7 +668,7 @@ const unsigned char pcie_link_speed[] = {
 	PCIE_SPEED_5_0GT,		/* 2 */
 	PCIE_SPEED_8_0GT,		/* 3 */
 	PCIE_SPEED_16_0GT,		/* 4 */
-	PCI_SPEED_UNKNOWN,		/* 5 */
+	PCIE_SPEED_32_0GT,		/* 5 */
 	PCI_SPEED_UNKNOWN,		/* 6 */
 	PCI_SPEED_UNKNOWN,		/* 7 */
 	PCI_SPEED_UNKNOWN,		/* 8 */
@@ -1555,17 +1555,6 @@ static int pci_cfg_space_size_ext(struct pci_dev *dev)
 	return PCI_CFG_SPACE_EXP_SIZE;
 }
 
-#ifdef CONFIG_PCI_IOV
-static bool is_vf0(struct pci_dev *dev)
-{
-	if (pci_iov_virtfn_devfn(dev->physfn, 0) == dev->devfn &&
-	    pci_iov_virtfn_bus(dev->physfn, 0) == dev->bus->number)
-		return true;
-
-	return false;
-}
-#endif
-
 int pci_cfg_space_size(struct pci_dev *dev)
 {
 	int pos;
@@ -1573,9 +1562,18 @@ int pci_cfg_space_size(struct pci_dev *dev)
 	u16 class;
 
 #ifdef CONFIG_PCI_IOV
-	/* Read cached value for all VFs except for VF0 */
-	if (dev->is_virtfn && !is_vf0(dev))
-		return dev->physfn->sriov->cfg_size;
+	/*
+	 * Per the SR-IOV specification (rev 1.1, sec 3.5), VFs are required to
+	 * implement a PCIe capability and therefore must implement extended
+	 * config space.  We can skip the NO_EXTCFG test below and the
+	 * reachability/aliasing test in pci_cfg_space_size_ext() by virtue of
+	 * the fact that the SR-IOV capability on the PF resides in extended
+	 * config space and must be accessible and non-aliased to have enabled
+	 * support for this VF.  This is a micro performance optimization for
+	 * systems supporting many VFs.
+	 */
+	if (dev->is_virtfn)
+		return PCI_CFG_SPACE_EXP_SIZE;
 #endif
 
 	if (dev->bus->bus_flags & PCI_BUS_FLAGS_NO_EXTCFG)
diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
index 445b51db75b0..fe7fe678965b 100644
--- a/drivers/pci/proc.c
+++ b/drivers/pci/proc.c
@@ -377,7 +377,7 @@ static int show_device(struct seq_file *m, void *v)
 	}
 	seq_putc(m, '\t');
 	if (drv)
-		seq_printf(m, "%s", drv->name);
+		seq_puts(m, drv->name);
 	seq_putc(m, '\n');
 	return 0;
 }
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 0f16acc323c6..208aacf39329 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -4934,35 +4934,49 @@ static void quirk_fsl_no_msi(struct pci_dev *pdev)
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_FREESCALE, PCI_ANY_ID, quirk_fsl_no_msi);
 
 /*
- * GPUs with integrated HDA controller for streaming audio to attached displays
- * need a device link from the HDA controller (consumer) to the GPU (supplier)
- * so that the GPU is powered up whenever the HDA controller is accessed.
- * The GPU and HDA controller are functions 0 and 1 of the same PCI device.
- * The device link stays in place until shutdown (or removal of the PCI device
- * if it's hotplugged).  Runtime PM is allowed by default on the HDA controller
- * to prevent it from permanently keeping the GPU awake.
+ * Although not allowed by the spec, some multi-function devices have
+ * dependencies of one function (consumer) on another (supplier).  For the
+ * consumer to work in D0, the supplier must also be in D0.  Create a
+ * device link from the consumer to the supplier to enforce this
+ * dependency.  Runtime PM is allowed by default on the consumer to prevent
+ * it from permanently keeping the supplier awake.
  */
-static void quirk_gpu_hda(struct pci_dev *hda)
+static void pci_create_device_link(struct pci_dev *pdev, unsigned int consumer,
+				   unsigned int supplier, unsigned int class,
+				   unsigned int class_shift)
 {
-	struct pci_dev *gpu;
+	struct pci_dev *supplier_pdev;
 
-	if (PCI_FUNC(hda->devfn) != 1)
+	if (PCI_FUNC(pdev->devfn) != consumer)
 		return;
 
-	gpu = pci_get_domain_bus_and_slot(pci_domain_nr(hda->bus),
-					  hda->bus->number,
-					  PCI_DEVFN(PCI_SLOT(hda->devfn), 0));
-	if (!gpu || (gpu->class >> 16) != PCI_BASE_CLASS_DISPLAY) {
-		pci_dev_put(gpu);
+	supplier_pdev = pci_get_domain_bus_and_slot(pci_domain_nr(pdev->bus),
+				pdev->bus->number,
+				PCI_DEVFN(PCI_SLOT(pdev->devfn), supplier));
+	if (!supplier_pdev || (supplier_pdev->class >> class_shift) != class) {
+		pci_dev_put(supplier_pdev);
 		return;
 	}
 
-	if (!device_link_add(&hda->dev, &gpu->dev,
-			     DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME))
-		pci_err(hda, "cannot link HDA to GPU %s\n", pci_name(gpu));
+	if (device_link_add(&pdev->dev, &supplier_pdev->dev,
+			    DL_FLAG_STATELESS | DL_FLAG_PM_RUNTIME))
+		pci_info(pdev, "D0 power state depends on %s\n",
+			 pci_name(supplier_pdev));
+	else
+		pci_err(pdev, "Cannot enforce power dependency on %s\n",
+			pci_name(supplier_pdev));
+
+	pm_runtime_allow(&pdev->dev);
+	pci_dev_put(supplier_pdev);
+}
 
-	pm_runtime_allow(&hda->dev);
-	pci_dev_put(gpu);
+/*
+ * Create device link for GPUs with integrated HDA controller for streaming
+ * audio to attached displays.
+ */
+static void quirk_gpu_hda(struct pci_dev *hda)
+{
+	pci_create_device_link(hda, 1, 0, PCI_BASE_CLASS_DISPLAY, 16);
 }
 DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_ATI, PCI_ANY_ID,
 			      PCI_CLASS_MULTIMEDIA_HD_AUDIO, 8, quirk_gpu_hda);
@@ -4972,6 +4986,62 @@ DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
 			      PCI_CLASS_MULTIMEDIA_HD_AUDIO, 8, quirk_gpu_hda);
 
 /*
+ * Create device link for NVIDIA GPU with integrated USB xHCI Host
+ * controller to VGA.
+ */
+static void quirk_gpu_usb(struct pci_dev *usb)
+{
+	pci_create_device_link(usb, 2, 0, PCI_BASE_CLASS_DISPLAY, 16);
+}
+DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
+			      PCI_CLASS_SERIAL_USB, 8, quirk_gpu_usb);
+
+/*
+ * Create device link for NVIDIA GPU with integrated Type-C UCSI controller
+ * to VGA. Currently there is no class code defined for UCSI device over PCI
+ * so using UNKNOWN class for now and it will be updated when UCSI
+ * over PCI gets a class code.
+ */
+#define PCI_CLASS_SERIAL_UNKNOWN	0x0c80
+static void quirk_gpu_usb_typec_ucsi(struct pci_dev *ucsi)
+{
+	pci_create_device_link(ucsi, 3, 0, PCI_BASE_CLASS_DISPLAY, 16);
+}
+DECLARE_PCI_FIXUP_CLASS_FINAL(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
+			      PCI_CLASS_SERIAL_UNKNOWN, 8,
+			      quirk_gpu_usb_typec_ucsi);
+
+/*
+ * Enable the NVIDIA GPU integrated HDA controller if the BIOS left it
+ * disabled.  https://devtalk.nvidia.com/default/topic/1024022
+ */
+static void quirk_nvidia_hda(struct pci_dev *gpu)
+{
+	u8 hdr_type;
+	u32 val;
+
+	/* There was no integrated HDA controller before MCP89 */
+	if (gpu->device < PCI_DEVICE_ID_NVIDIA_GEFORCE_320M)
+		return;
+
+	/* Bit 25 at offset 0x488 enables the HDA controller */
+	pci_read_config_dword(gpu, 0x488, &val);
+	if (val & BIT(25))
+		return;
+
+	pci_info(gpu, "Enabling HDA controller\n");
+	pci_write_config_dword(gpu, 0x488, val | BIT(25));
+
+	/* The GPU becomes a multi-function device when the HDA is enabled */
+	pci_read_config_byte(gpu, PCI_HEADER_TYPE, &hdr_type);
+	gpu->multifunction = !!(hdr_type & 0x80);
+}
+DECLARE_PCI_FIXUP_CLASS_HEADER(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
+			       PCI_BASE_CLASS_DISPLAY, 16, quirk_nvidia_hda);
+DECLARE_PCI_FIXUP_CLASS_RESUME_EARLY(PCI_VENDOR_ID_NVIDIA, PCI_ANY_ID,
+			       PCI_BASE_CLASS_DISPLAY, 16, quirk_nvidia_hda);
+
+/*
  * Some IDT switches incorrectly flag an ACS Source Validation error on
  * completions for config read requests even though PCIe r4.0, sec
  * 6.12.1.1, says that completions are never affected by ACS Source
diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
index 0cdd5ff389de..79b1fa6519be 100644
--- a/drivers/pci/setup-bus.c
+++ b/drivers/pci/setup-bus.c
@@ -1684,10 +1684,15 @@ static enum enable_type pci_realloc_detect(struct pci_bus *bus,
 					   enum enable_type enable_local)
 {
 	bool unassigned = false;
+	struct pci_host_bridge *host;
 
 	if (enable_local != undefined)
 		return enable_local;
 
+	host = pci_find_host_bridge(bus);
+	if (host->preserve_config)
+		return auto_disabled;
+
 	pci_walk_bus(bus, iov_resources_unassigned, &unassigned);
 	if (unassigned)
 		return auto_enabled;
@@ -1861,16 +1866,6 @@ static void pci_bus_distribute_available_resources(struct pci_bus *bus,
 			     available_mmio_pref);
 
 	/*
-	 * Calculate the total amount of extra resource space we can
-	 * pass to bridges below this one.  This is basically the
-	 * extra space reduced by the minimal required space for the
-	 * non-hotplug bridges.
-	 */
-	remaining_io = available_io;
-	remaining_mmio = available_mmio;
-	remaining_mmio_pref = available_mmio_pref;
-
-	/*
 	 * Calculate how many hotplug bridges and normal bridges there
 	 * are on this bus.  We will distribute the additional available
 	 * resources between hotplug bridges.
@@ -1882,6 +1877,34 @@ static void pci_bus_distribute_available_resources(struct pci_bus *bus,
 			normal_bridges++;
 	}
 
+	/*
+	 * There is only one bridge on the bus so it gets all available
+	 * resources which it can then distribute to the possible hotplug
+	 * bridges below.
+	 */
+	if (hotplug_bridges + normal_bridges == 1) {
+		dev = list_first_entry(&bus->devices, struct pci_dev, bus_list);
+		if (dev->subordinate) {
+			pci_bus_distribute_available_resources(dev->subordinate,
+				add_list, available_io, available_mmio,
+				available_mmio_pref);
+		}
+		return;
+	}
+
+	if (hotplug_bridges == 0)
+		return;
+
+	/*
+	 * Calculate the total amount of extra resource space we can
+	 * pass to bridges below this one.  This is basically the
+	 * extra space reduced by the minimal required space for the
+	 * non-hotplug bridges.
+	 */
+	remaining_io = available_io;
+	remaining_mmio = available_mmio;
+	remaining_mmio_pref = available_mmio_pref;
+
 	for_each_pci_bridge(dev, bus) {
 		const struct resource *res;
 
@@ -1906,21 +1929,6 @@ static void pci_bus_distribute_available_resources(struct pci_bus *bus,
 	}
 
 	/*
-	 * There is only one bridge on the bus so it gets all available
-	 * resources which it can then distribute to the possible hotplug
-	 * bridges below.
-	 */
-	if (hotplug_bridges + normal_bridges == 1) {
-		dev = list_first_entry(&bus->devices, struct pci_dev, bus_list);
-		if (dev->subordinate) {
-			pci_bus_distribute_available_resources(dev->subordinate,
-				add_list, available_io, available_mmio,
-				available_mmio_pref);
-		}
-		return;
-	}
-
-	/*
 	 * Go over devices on this bus and distribute the remaining
 	 * resource space between hotplug bridges.
 	 */
@@ -1936,8 +1944,6 @@ static void pci_bus_distribute_available_resources(struct pci_bus *bus,
 		 * Distribute available extra resources equally between
 		 * hotplug-capable downstream ports taking alignment into
 		 * account.
-		 *
-		 * Here hotplug_bridges is always != 0.
 		 */
 		align = pci_resource_alignment(bridge, io_res);
 		io = div64_ul(available_io, hotplug_bridges);
diff --git a/drivers/pci/slot.c b/drivers/pci/slot.c
index f4d92b1afe7b..ae4aa0e1f2f4 100644
--- a/drivers/pci/slot.c
+++ b/drivers/pci/slot.c
@@ -75,6 +75,7 @@ static const char *pci_bus_speed_strings[] = {
 	"5.0 GT/s PCIe",	/* 0x15 */
 	"8.0 GT/s PCIe",	/* 0x16 */
 	"16.0 GT/s PCIe",	/* 0x17 */
+	"32.0 GT/s PCIe",	/* 0x18 */
 };
 
 static ssize_t bus_speed_read(enum pci_bus_speed speed, char *buf)