diff --git a/Documentation/PCI/pci-iov-howto.rst b/Documentation/PCI/pci-iov-howto.rst
index b9fd003..27d3593 100644
--- a/Documentation/PCI/pci-iov-howto.rst
+++ b/Documentation/PCI/pci-iov-howto.rst
@@ -125,14 +125,14 @@
 		...
 	}
 
-	static int dev_suspend(struct pci_dev *dev, pm_message_t state)
+	static int dev_suspend(struct device *dev)
 	{
 		...
 
 		return 0;
 	}
 
-	static int dev_resume(struct pci_dev *dev)
+	static int dev_resume(struct device *dev)
 	{
 		...
 
@@ -165,8 +165,7 @@
 		.id_table =	dev_id_table,
 		.probe =	dev_probe,
 		.remove =	dev_remove,
-		.suspend =	dev_suspend,
-		.resume =	dev_resume,
+		.driver.pm =	&dev_pm_ops,
 		.shutdown =	dev_shutdown,
 		.sriov_configure = dev_sriov_configure,
 	};
diff --git a/Documentation/PCI/sysfs-pci.rst b/Documentation/PCI/sysfs-pci.rst
index 742fbd2..f495185 100644
--- a/Documentation/PCI/sysfs-pci.rst
+++ b/Documentation/PCI/sysfs-pci.rst
@@ -125,7 +125,7 @@
 mmap() through files in /proc/bus/pci, platforms may also set HAVE_PCI_MMAP.
 
 Alternatively, platforms which set HAVE_PCI_MMAP may provide their own
-implementation of pci_mmap_page_range() instead of defining
+implementation of pci_mmap_resource_range() instead of defining
 ARCH_GENERIC_PCI_MMAP_RESOURCE.
 
 Platforms which support write-combining maps of PCI resources must define
diff --git a/Documentation/devicetree/bindings/pci/mediatek-pcie.txt b/Documentation/devicetree/bindings/pci/mediatek-pcie.txt
index 57ae734..6842275 100644
--- a/Documentation/devicetree/bindings/pci/mediatek-pcie.txt
+++ b/Documentation/devicetree/bindings/pci/mediatek-pcie.txt
@@ -7,6 +7,7 @@
 	"mediatek,mt7622-pcie"
 	"mediatek,mt7623-pcie"
 	"mediatek,mt7629-pcie"
+	"airoha,en7523-pcie"
 - device_type: Must be "pci"
 - reg: Base addresses and lengths of the root ports.
 - reg-names: Names of the above areas to use during resource lookup.
diff --git a/Documentation/devicetree/bindings/pci/nvidia,tegra194-pcie-ep.yaml b/Documentation/devicetree/bindings/pci/nvidia,tegra194-pcie-ep.yaml
new file mode 100644
index 0000000..a24fb83
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/nvidia,tegra194-pcie-ep.yaml
@@ -0,0 +1,319 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pci/nvidia,tegra194-pcie-ep.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: NVIDIA Tegra194 (and later) PCIe Endpoint controller (Synopsys DesignWare Core based)
+
+maintainers:
+  - Thierry Reding <thierry.reding@gmail.com>
+  - Jon Hunter <jonathanh@nvidia.com>
+  - Vidya Sagar <vidyas@nvidia.com>
+
+description: |
+  This PCIe controller is based on the Synopsys DesignWare PCIe IP and thus
+  inherits all the common properties defined in snps,dw-pcie-ep.yaml.  Some
+  of the controller instances are dual mode; they can work either in Root
+  Port mode or Endpoint mode but one at a time.
+
+  On Tegra194, controllers C0, C4 and C5 support Endpoint mode.
+  On Tegra234, controllers C5, C6, C7 and C10 support Endpoint mode.
+
+  Note: On Tegra194's P2972-0000 platform, only C5 controller can be enabled to
+  operate in the Endpoint mode because of the way the platform is designed.
+
+properties:
+  compatible:
+    enum:
+      - nvidia,tegra194-pcie-ep
+      - nvidia,tegra234-pcie-ep
+
+  reg:
+    items:
+      - description: controller's application logic registers
+      - description: iATU and DMA registers. This is where the iATU (internal
+          Address Translation Unit) registers of the PCIe core are made
+          available for software access.
+      - description: aperture where the Root Port's own configuration
+          registers are available.
+      - description: aperture used to map the remote Root Complex address space
+
+  reg-names:
+    items:
+      - const: appl
+      - const: atu_dma
+      - const: dbi
+      - const: addr_space
+
+  interrupts:
+    items:
+      - description: controller interrupt
+
+  interrupt-names:
+    items:
+      - const: intr
+
+  clocks:
+    items:
+      - description: module clock
+
+  clock-names:
+    items:
+      - const: core
+
+  resets:
+    items:
+      - description: APB bus interface reset
+      - description: module reset
+
+  reset-names:
+    items:
+      - const: apb
+      - const: core
+
+  reset-gpios:
+    description: Must contain a phandle to a GPIO controller followed by GPIO
+      that is being used as PERST input signal. Please refer to pci.txt.
+
+  phys:
+    minItems: 1
+    maxItems: 8
+
+  phy-names:
+    minItems: 1
+    items:
+      - const: p2u-0
+      - const: p2u-1
+      - const: p2u-2
+      - const: p2u-3
+      - const: p2u-4
+      - const: p2u-5
+      - const: p2u-6
+      - const: p2u-7
+
+  power-domains:
+    maxItems: 1
+    description: |
+      A phandle to the node that controls power to the respective PCIe
+      controller and a specifier name for the PCIe controller.
+
+      Tegra194 specifiers are defined in "include/dt-bindings/power/tegra194-powergate.h"
+      Tegra234 specifiers are defined in "include/dt-bindings/power/tegra234-powergate.h"
+
+  interconnects:
+    items:
+      - description: memory read client
+      - description: memory write client
+
+  interconnect-names:
+    items:
+      - const: dma-mem # read
+      - const: write
+
+  dma-coherent: true
+
+  nvidia,bpmp:
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    description: |
+      Must contain a pair of phandles to BPMP controller node followed by
+      controller ID. Following are the controller IDs for each controller:
+
+      Tegra194
+
+        0: C0
+        1: C1
+        2: C2
+        3: C3
+        4: C4
+        5: C5
+
+      Tegra234
+
+        0 : C0
+        1 : C1
+        2 : C2
+        3 : C3
+        4 : C4
+        5 : C5
+        6 : C6
+        7 : C7
+        8 : C8
+        9 : C9
+        10: C10
+
+    items:
+      - items:
+          - description: phandle to BPMP controller node
+          - description: PCIe controller ID
+            maximum: 10
+
+  nvidia,aspm-cmrt-us:
+    description: Common Mode Restore Time for proper operation of ASPM to be
+      specified in microseconds
+
+  nvidia,aspm-pwr-on-t-us:
+    description: Power On time for proper operation of ASPM to be specified in
+      microseconds
+
+  nvidia,aspm-l0s-entrance-latency-us:
+    description: ASPM L0s entrance latency to be specified in microseconds
+
+  vddio-pex-ctl-supply:
+    description: A phandle to the regulator supply for PCIe side band signals
+
+  nvidia,refclk-select-gpios:
+    maxItems: 1
+    description: GPIO used to enable REFCLK to controller from the host
+
+  nvidia,enable-ext-refclk:
+    description: |
+      This boolean property needs to be present if the controller is configured
+      to receive Reference Clock from the host.
+      NOTE: This is applicable only for Tegra234.
+
+    $ref: /schemas/types.yaml#/definitions/flag
+
+  nvidia,enable-srns:
+    description: |
+      This boolean property needs to be present if the controller is
+      configured to operate in SRNS (Separate Reference Clocks with No
+      Spread-Spectrum Clocking).  NOTE: This is applicable only for
+      Tegra234.
+
+    $ref: /schemas/types.yaml#/definitions/flag
+
+allOf:
+  - $ref: /schemas/pci/snps,dw-pcie-ep.yaml#
+
+unevaluatedProperties: false
+
+required:
+  - interrupts
+  - interrupt-names
+  - clocks
+  - clock-names
+  - resets
+  - reset-names
+  - power-domains
+  - reset-gpios
+  - vddio-pex-ctl-supply
+  - num-lanes
+  - phys
+  - phy-names
+  - nvidia,bpmp
+
+examples:
+  - |
+    #include <dt-bindings/clock/tegra194-clock.h>
+    #include <dt-bindings/gpio/tegra194-gpio.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/power/tegra194-powergate.h>
+    #include <dt-bindings/reset/tegra194-reset.h>
+
+    bus@0 {
+        #address-cells = <2>;
+        #size-cells = <2>;
+        ranges = <0x0 0x0 0x0 0x8 0x0>;
+
+        pcie-ep@141a0000 {
+            compatible = "nvidia,tegra194-pcie-ep";
+            reg = <0x00 0x141a0000 0x0 0x00020000>, /* appl registers (128K) */
+                  <0x00 0x3a040000 0x0 0x00040000>, /* iATU_DMA reg space (256K)  */
+                  <0x00 0x3a080000 0x0 0x00040000>, /* DBI reg space (256K) */
+                  <0x1c 0x00000000 0x4 0x00000000>; /* Address Space (16G) */
+            reg-names = "appl", "atu_dma", "dbi", "addr_space";
+            interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>; /* controller interrupt */
+            interrupt-names = "intr";
+
+            clocks = <&bpmp TEGRA194_CLK_PEX1_CORE_5>;
+            clock-names = "core";
+
+            resets = <&bpmp TEGRA194_RESET_PEX1_CORE_5_APB>,
+                     <&bpmp TEGRA194_RESET_PEX1_CORE_5>;
+            reset-names = "apb", "core";
+
+            power-domains = <&bpmp TEGRA194_POWER_DOMAIN_PCIEX8A>;
+            pinctrl-names = "default";
+            pinctrl-0 = <&clkreq_c5_bi_dir_state>;
+
+            nvidia,bpmp = <&bpmp 5>;
+
+            nvidia,aspm-cmrt-us = <60>;
+            nvidia,aspm-pwr-on-t-us = <20>;
+            nvidia,aspm-l0s-entrance-latency-us = <3>;
+
+            vddio-pex-ctl-supply = <&vdd_1v8ao>;
+
+            reset-gpios = <&gpio TEGRA194_MAIN_GPIO(GG, 1) GPIO_ACTIVE_LOW>;
+
+            nvidia,refclk-select-gpios = <&gpio_aon TEGRA194_AON_GPIO(AA, 5)
+                                          GPIO_ACTIVE_HIGH>;
+
+            num-lanes = <8>;
+
+            phys = <&p2u_nvhs_0>, <&p2u_nvhs_1>, <&p2u_nvhs_2>,
+                   <&p2u_nvhs_3>, <&p2u_nvhs_4>, <&p2u_nvhs_5>,
+                   <&p2u_nvhs_6>, <&p2u_nvhs_7>;
+
+            phy-names = "p2u-0", "p2u-1", "p2u-2", "p2u-3", "p2u-4",
+                        "p2u-5", "p2u-6", "p2u-7";
+        };
+    };
+
+  - |
+    #include <dt-bindings/clock/tegra234-clock.h>
+    #include <dt-bindings/gpio/tegra234-gpio.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/power/tegra234-powergate.h>
+    #include <dt-bindings/reset/tegra234-reset.h>
+
+    bus@0 {
+        #address-cells = <2>;
+        #size-cells = <2>;
+        ranges = <0x0 0x0 0x0 0x8 0x0>;
+
+        pcie-ep@141a0000 {
+            compatible = "nvidia,tegra234-pcie-ep";
+            power-domains = <&bpmp TEGRA234_POWER_DOMAIN_PCIEX8A>;
+            reg = <0x00 0x141a0000 0x0 0x00020000>, /* appl registers (128K)      */
+                  <0x00 0x3a040000 0x0 0x00040000>, /* iATU_DMA reg space (256K)  */
+                  <0x00 0x3a080000 0x0 0x00040000>, /* DBI reg space (256K)       */
+                  <0x27 0x40000000 0x4 0x00000000>; /* Address Space (16G)        */
+            reg-names = "appl", "atu_dma", "dbi", "addr_space";
+
+            interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>; /* controller interrupt */
+            interrupt-names = "intr";
+
+            clocks = <&bpmp TEGRA234_CLK_PEX1_C5_CORE>;
+            clock-names = "core";
+
+            resets = <&bpmp TEGRA234_RESET_PEX1_CORE_5_APB>,
+                     <&bpmp TEGRA234_RESET_PEX1_CORE_5>;
+            reset-names = "apb", "core";
+
+            nvidia,bpmp = <&bpmp 5>;
+
+            nvidia,enable-ext-refclk;
+            nvidia,aspm-cmrt-us = <60>;
+            nvidia,aspm-pwr-on-t-us = <20>;
+            nvidia,aspm-l0s-entrance-latency-us = <3>;
+
+            vddio-pex-ctl-supply = <&p3701_vdd_1v8_ls>;
+
+            reset-gpios = <&gpio TEGRA234_MAIN_GPIO(AF, 1) GPIO_ACTIVE_LOW>;
+
+            nvidia,refclk-select-gpios = <&gpio_aon
+                                          TEGRA234_AON_GPIO(AA, 4)
+                                          GPIO_ACTIVE_HIGH>;
+
+            num-lanes = <8>;
+
+            phys = <&p2u_nvhs_0>, <&p2u_nvhs_1>, <&p2u_nvhs_2>,
+                   <&p2u_nvhs_3>, <&p2u_nvhs_4>, <&p2u_nvhs_5>,
+                   <&p2u_nvhs_6>, <&p2u_nvhs_7>;
+
+            phy-names = "p2u-0", "p2u-1", "p2u-2", "p2u-3", "p2u-4",
+                        "p2u-5", "p2u-6", "p2u-7";
+        };
+    };
diff --git a/Documentation/devicetree/bindings/pci/nvidia,tegra194-pcie.txt b/Documentation/devicetree/bindings/pci/nvidia,tegra194-pcie.txt
deleted file mode 100644
index 8e4f9bf..0000000
--- a/Documentation/devicetree/bindings/pci/nvidia,tegra194-pcie.txt
+++ /dev/null
@@ -1,245 +0,0 @@
-NVIDIA Tegra PCIe controller (Synopsys DesignWare Core based)
-
-This PCIe controller is based on the Synopsis Designware PCIe IP
-and thus inherits all the common properties defined in snps,dw-pcie.yaml and
-snps,dw-pcie-ep.yaml.
-Some of the controller instances are dual mode where in they can work either
-in root port mode or endpoint mode but one at a time.
-
-Required properties:
-- power-domains: A phandle to the node that controls power to the respective
-  PCIe controller and a specifier name for the PCIe controller. Following are
-  the specifiers for the different PCIe controllers
-    TEGRA194_POWER_DOMAIN_PCIEX8B: C0
-    TEGRA194_POWER_DOMAIN_PCIEX1A: C1
-    TEGRA194_POWER_DOMAIN_PCIEX1A: C2
-    TEGRA194_POWER_DOMAIN_PCIEX1A: C3
-    TEGRA194_POWER_DOMAIN_PCIEX4A: C4
-    TEGRA194_POWER_DOMAIN_PCIEX8A: C5
-  these specifiers are defined in
-  "include/dt-bindings/power/tegra194-powergate.h" file.
-- reg: A list of physical base address and length pairs for each set of
-  controller registers. Must contain an entry for each entry in the reg-names
-  property.
-- reg-names: Must include the following entries:
-  "appl": Controller's application logic registers
-  "config": As per the definition in snps,dw-pcie.yaml
-  "atu_dma": iATU and DMA registers. This is where the iATU (internal Address
-             Translation Unit) registers of the PCIe core are made available
-             for SW access.
-  "dbi": The aperture where root port's own configuration registers are
-         available
-- interrupts: A list of interrupt outputs of the controller. Must contain an
-  entry for each entry in the interrupt-names property.
-- interrupt-names: Must include the following entries:
-  "intr": The Tegra interrupt that is asserted for controller interrupts
-- clocks: Must contain an entry for each entry in clock-names.
-  See ../clocks/clock-bindings.txt for details.
-- clock-names: Must include the following entries:
-  - core
-- resets: Must contain an entry for each entry in reset-names.
-  See ../reset/reset.txt for details.
-- reset-names: Must include the following entries:
-  - apb
-  - core
-- phys: Must contain a phandle to P2U PHY for each entry in phy-names.
-- phy-names: Must include an entry for each active lane.
-  "p2u-N": where N ranges from 0 to one less than the total number of lanes
-- nvidia,bpmp: Must contain a pair of phandle to BPMP controller node followed
-  by controller-id. Following are the controller ids for each controller.
-    0: C0
-    1: C1
-    2: C2
-    3: C3
-    4: C4
-    5: C5
-- vddio-pex-ctl-supply: Regulator supply for PCIe side band signals
-
-RC mode:
-- compatible: Tegra19x must contain  "nvidia,tegra194-pcie"
-- device_type: Must be "pci" for RC mode
-- interrupt-names: Must include the following entries:
-  "msi": The Tegra interrupt that is asserted when an MSI is received
-- bus-range: Range of bus numbers associated with this controller
-- #address-cells: Address representation for root ports (must be 3)
-  - cell 0 specifies the bus and device numbers of the root port:
-    [23:16]: bus number
-    [15:11]: device number
-  - cell 1 denotes the upper 32 address bits and should be 0
-  - cell 2 contains the lower 32 address bits and is used to translate to the
-    CPU address space
-- #size-cells: Size representation for root ports (must be 2)
-- ranges: Describes the translation of addresses for root ports and standard
-  PCI regions. The entries must be 7 cells each, where the first three cells
-  correspond to the address as described for the #address-cells property
-  above, the fourth and fifth cells are for the physical CPU address to
-  translate to and the sixth and seventh cells are as described for the
-  #size-cells property above.
-  - Entries setup the mapping for the standard I/O, memory and
-    prefetchable PCI regions. The first cell determines the type of region
-    that is setup:
-    - 0x81000000: I/O memory region
-    - 0x82000000: non-prefetchable memory region
-    - 0xc2000000: prefetchable memory region
-  Please refer to the standard PCI bus binding document for a more detailed
-  explanation.
-- #interrupt-cells: Size representation for interrupts (must be 1)
-- interrupt-map-mask and interrupt-map: Standard PCI IRQ mapping properties
-  Please refer to the standard PCI bus binding document for a more detailed
-  explanation.
-
-EP mode:
-In Tegra194, Only controllers C0, C4 & C5 support EP mode.
-- compatible: Tegra19x must contain "nvidia,tegra194-pcie-ep"
-- reg-names: Must include the following entries:
-  "addr_space": Used to map remote RC address space
-- reset-gpios: Must contain a phandle to a GPIO controller followed by
-  GPIO that is being used as PERST input signal. Please refer to pci.txt
-  document.
-
-Optional properties:
-- pinctrl-names: A list of pinctrl state names.
-  It is mandatory for C5 controller and optional for other controllers.
-  - "default": Configures PCIe I/O for proper operation.
-- pinctrl-0: phandle for the 'default' state of pin configuration.
-  It is mandatory for C5 controller and optional for other controllers.
-- supports-clkreq: Refer to Documentation/devicetree/bindings/pci/pci.txt
-- nvidia,update-fc-fixup: This is a boolean property and needs to be present to
-    improve performance when a platform is designed in such a way that it
-    satisfies at least one of the following conditions thereby enabling root
-    port to exchange optimum number of FC (Flow Control) credits with
-    downstream devices
-    1. If C0/C4/C5 run at x1/x2 link widths (irrespective of speed and MPS)
-    2. If C0/C1/C2/C3/C4/C5 operate at their respective max link widths and
-       a) speed is Gen-2 and MPS is 256B
-       b) speed is >= Gen-3 with any MPS
-- nvidia,aspm-cmrt-us: Common Mode Restore Time for proper operation of ASPM
-   to be specified in microseconds
-- nvidia,aspm-pwr-on-t-us: Power On time for proper operation of ASPM to be
-   specified in microseconds
-- nvidia,aspm-l0s-entrance-latency-us: ASPM L0s entrance latency to be
-   specified in microseconds
-
-RC mode:
-- vpcie3v3-supply: A phandle to the regulator node that supplies 3.3V to the slot
-  if the platform has one such slot. (Ex:- x16 slot owned by C5 controller
-  in p2972-0000 platform).
-- vpcie12v-supply: A phandle to the regulator node that supplies 12V to the slot
-  if the platform has one such slot. (Ex:- x16 slot owned by C5 controller
-  in p2972-0000 platform).
-
-EP mode:
-- nvidia,refclk-select-gpios: Must contain a phandle to a GPIO controller
-  followed by GPIO that is being used to enable REFCLK to controller from host
-
-NOTE:- On Tegra194's P2972-0000 platform, only C5 controller can be enabled to
-operate in the endpoint mode because of the way the platform is designed.
-
-Examples:
-=========
-
-Tegra194 RC mode:
------------------
-
-	pcie@14180000 {
-		compatible = "nvidia,tegra194-pcie";
-		power-domains = <&bpmp TEGRA194_POWER_DOMAIN_PCIEX8B>;
-		reg = <0x00 0x14180000 0x0 0x00020000   /* appl registers (128K)      */
-		       0x00 0x38000000 0x0 0x00040000   /* configuration space (256K) */
-		       0x00 0x38040000 0x0 0x00040000>; /* iATU_DMA reg space (256K)  */
-		reg-names = "appl", "config", "atu_dma";
-
-		#address-cells = <3>;
-		#size-cells = <2>;
-		device_type = "pci";
-		num-lanes = <8>;
-		linux,pci-domain = <0>;
-
-		pinctrl-names = "default";
-		pinctrl-0 = <&pex_rst_c5_out_state>, <&clkreq_c5_bi_dir_state>;
-
-		clocks = <&bpmp TEGRA194_CLK_PEX0_CORE_0>;
-		clock-names = "core";
-
-		resets = <&bpmp TEGRA194_RESET_PEX0_CORE_0_APB>,
-			 <&bpmp TEGRA194_RESET_PEX0_CORE_0>;
-		reset-names = "apb", "core";
-
-		interrupts = <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>,	/* controller interrupt */
-			     <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>;	/* MSI interrupt */
-		interrupt-names = "intr", "msi";
-
-		#interrupt-cells = <1>;
-		interrupt-map-mask = <0 0 0 0>;
-		interrupt-map = <0 0 0 0 &gic GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>;
-
-		nvidia,bpmp = <&bpmp 0>;
-
-		supports-clkreq;
-		nvidia,aspm-cmrt-us = <60>;
-		nvidia,aspm-pwr-on-t-us = <20>;
-		nvidia,aspm-l0s-entrance-latency-us = <3>;
-
-		bus-range = <0x0 0xff>;
-		ranges = <0x81000000 0x0  0x38100000 0x0  0x38100000 0x0 0x00100000    /* downstream I/O (1MB) */
-			  0x82000000 0x0  0x38200000 0x0  0x38200000 0x0 0x01E00000    /* non-prefetchable memory (30MB) */
-			  0xc2000000 0x18 0x00000000 0x18 0x00000000 0x4 0x00000000>;  /* prefetchable memory (16GB) */
-
-		vddio-pex-ctl-supply = <&vdd_1v8ao>;
-		vpcie3v3-supply = <&vdd_3v3_pcie>;
-		vpcie12v-supply = <&vdd_12v_pcie>;
-
-		phys = <&p2u_hsio_2>, <&p2u_hsio_3>, <&p2u_hsio_4>,
-		       <&p2u_hsio_5>;
-		phy-names = "p2u-0", "p2u-1", "p2u-2", "p2u-3";
-	};
-
-Tegra194 EP mode:
------------------
-
-	pcie-ep@141a0000 {
-		compatible = "nvidia,tegra194-pcie-ep", "snps,dw-pcie-ep";
-		power-domains = <&bpmp TEGRA194_POWER_DOMAIN_PCIEX8A>;
-		reg = <0x00 0x141a0000 0x0 0x00020000   /* appl registers (128K)      */
-		       0x00 0x3a040000 0x0 0x00040000   /* iATU_DMA reg space (256K)  */
-		       0x00 0x3a080000 0x0 0x00040000   /* DBI reg space (256K)       */
-		       0x1c 0x00000000 0x4 0x00000000>; /* Address Space (16G)        */
-		reg-names = "appl", "atu_dma", "dbi", "addr_space";
-
-		num-lanes = <8>;
-		num-ib-windows = <2>;
-		num-ob-windows = <8>;
-
-		pinctrl-names = "default";
-		pinctrl-0 = <&clkreq_c5_bi_dir_state>;
-
-		clocks = <&bpmp TEGRA194_CLK_PEX1_CORE_5>;
-		clock-names = "core";
-
-		resets = <&bpmp TEGRA194_RESET_PEX1_CORE_5_APB>,
-			 <&bpmp TEGRA194_RESET_PEX1_CORE_5>;
-		reset-names = "apb", "core";
-
-		interrupts = <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>;	/* controller interrupt */
-		interrupt-names = "intr";
-
-		nvidia,bpmp = <&bpmp 5>;
-
-		nvidia,aspm-cmrt-us = <60>;
-		nvidia,aspm-pwr-on-t-us = <20>;
-		nvidia,aspm-l0s-entrance-latency-us = <3>;
-
-		vddio-pex-ctl-supply = <&vdd_1v8ao>;
-
-		reset-gpios = <&gpio TEGRA194_MAIN_GPIO(GG, 1) GPIO_ACTIVE_LOW>;
-
-		nvidia,refclk-select-gpios = <&gpio_aon TEGRA194_AON_GPIO(AA, 5)
-					      GPIO_ACTIVE_HIGH>;
-
-		phys = <&p2u_nvhs_0>, <&p2u_nvhs_1>, <&p2u_nvhs_2>,
-		       <&p2u_nvhs_3>, <&p2u_nvhs_4>, <&p2u_nvhs_5>,
-		       <&p2u_nvhs_6>, <&p2u_nvhs_7>;
-
-		phy-names = "p2u-0", "p2u-1", "p2u-2", "p2u-3", "p2u-4",
-			    "p2u-5", "p2u-6", "p2u-7";
-	};
diff --git a/Documentation/devicetree/bindings/pci/nvidia,tegra194-pcie.yaml b/Documentation/devicetree/bindings/pci/nvidia,tegra194-pcie.yaml
new file mode 100644
index 0000000..75da3e8
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/nvidia,tegra194-pcie.yaml
@@ -0,0 +1,350 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pci/nvidia,tegra194-pcie.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: NVIDIA Tegra194 (and later) PCIe controller (Synopsys DesignWare Core based)
+
+maintainers:
+  - Thierry Reding <thierry.reding@gmail.com>
+  - Jon Hunter <jonathanh@nvidia.com>
+  - Vidya Sagar <vidyas@nvidia.com>
+
+description: |
+  This PCIe controller is based on the Synopsys DesignWare PCIe IP and thus
+  inherits all the common properties defined in snps,dw-pcie.yaml. Some of
+  the controller instances are dual mode where in they can work either in
+  Root Port mode or Endpoint mode but one at a time.
+
+  See nvidia,tegra194-pcie-ep.yaml for details on the Endpoint mode device
+  tree bindings.
+
+properties:
+  compatible:
+    enum:
+      - nvidia,tegra194-pcie
+      - nvidia,tegra234-pcie
+
+  reg:
+    items:
+      - description: controller's application logic registers
+      - description: configuration registers
+      - description: iATU and DMA registers. This is where the iATU (internal
+          Address Translation Unit) registers of the PCIe core are made
+          available for software access.
+      - description: aperture where the Root Port's own configuration
+          registers are available.
+
+  reg-names:
+    items:
+      - const: appl
+      - const: config
+      - const: atu_dma
+      - const: dbi
+
+  interrupts:
+    items:
+      - description: controller interrupt
+      - description: MSI interrupt
+
+  interrupt-names:
+    items:
+      - const: intr
+      - const: msi
+
+  clocks:
+    items:
+      - description: module clock
+
+  clock-names:
+    items:
+      - const: core
+
+  resets:
+    items:
+      - description: APB bus interface reset
+      - description: module reset
+
+  reset-names:
+    items:
+      - const: apb
+      - const: core
+
+  phys:
+    minItems: 1
+    maxItems: 8
+
+  phy-names:
+    minItems: 1
+    items:
+      - const: p2u-0
+      - const: p2u-1
+      - const: p2u-2
+      - const: p2u-3
+      - const: p2u-4
+      - const: p2u-5
+      - const: p2u-6
+      - const: p2u-7
+
+  power-domains:
+    maxItems: 1
+    description: |
+      A phandle to the node that controls power to the respective PCIe
+      controller and a specifier name for the PCIe controller.
+
+      Tegra194 specifiers defined in "include/dt-bindings/power/tegra194-powergate.h"
+      Tegra234 specifiers defined in "include/dt-bindings/power/tegra234-powergate.h"
+
+  interconnects:
+    items:
+      - description: memory read client
+      - description: memory write client
+
+  interconnect-names:
+    items:
+      - const: dma-mem # read
+      - const: write
+
+  dma-coherent: true
+
+  nvidia,bpmp:
+    $ref: /schemas/types.yaml#/definitions/phandle-array
+    description: |
+      Must contain a pair of phandles to BPMP controller node followed by
+      controller ID. Following are the controller IDs for each controller:
+
+      Tegra194
+
+        0: C0
+        1: C1
+        2: C2
+        3: C3
+        4: C4
+        5: C5
+
+      Tegra234
+
+        0 : C0
+        1 : C1
+        2 : C2
+        3 : C3
+        4 : C4
+        5 : C5
+        6 : C6
+        7 : C7
+        8 : C8
+        9 : C9
+        10: C10
+
+    items:
+      - items:
+          - description: phandle to BPMP controller node
+          - description: PCIe controller ID
+            maximum: 10
+
+  nvidia,update-fc-fixup:
+    description: |
+      This is a boolean property and needs to be present to improve performance
+      when a platform is designed in such a way that it satisfies at least one
+      of the following conditions thereby enabling Root Port to exchange
+      optimum number of FC (Flow Control) credits with downstream devices:
+
+      NOTE: This is applicable only for Tegra194.
+
+        1. If C0/C4/C5 run at x1/x2 link widths (irrespective of speed and MPS)
+        2. If C0/C1/C2/C3/C4/C5 operate at their respective max link widths and
+          a) speed is Gen-2 and MPS is 256B
+          b) speed is >= Gen-3 with any MPS
+
+    $ref: /schemas/types.yaml#/definitions/flag
+
+  nvidia,aspm-cmrt-us:
+    description: Common Mode Restore Time for proper operation of ASPM to be
+      specified in microseconds
+
+  nvidia,aspm-pwr-on-t-us:
+    description: Power On time for proper operation of ASPM to be specified in
+      microseconds
+
+  nvidia,aspm-l0s-entrance-latency-us:
+    description: ASPM L0s entrance latency to be specified in microseconds
+
+  vddio-pex-ctl-supply:
+    description: A phandle to the regulator supply for PCIe side band signals.
+
+  vpcie3v3-supply:
+    description: A phandle to the regulator node that supplies 3.3V to the slot
+      if the platform has one such slot, e.g., x16 slot owned by C5 controller
+      in p2972-0000 platform.
+
+  vpcie12v-supply:
+    description: A phandle to the regulator node that supplies 12V to the slot
+      if the platform has one such slot, e.g., x16 slot owned by C5 controller
+      in p2972-0000 platform.
+
+  nvidia,enable-srns:
+    description: |
+      This boolean property needs to be present if the controller is
+      configured to operate in SRNS (Separate Reference Clocks with No
+      Spread-Spectrum Clocking).  NOTE: This is applicable only for
+      Tegra234.
+
+    $ref: /schemas/types.yaml#/definitions/flag
+
+  nvidia,enable-ext-refclk:
+    description: |
+      This boolean property needs to be present if the controller is
+      configured to use the reference clocking coming in from an external
+      clock source instead of using the internal clock source.
+
+    $ref: /schemas/types.yaml#/definitions/flag
+
+allOf:
+  - $ref: /schemas/pci/snps,dw-pcie.yaml#
+
+unevaluatedProperties: false
+
+required:
+  - interrupts
+  - interrupt-names
+  - interrupt-map
+  - interrupt-map-mask
+  - clocks
+  - clock-names
+  - resets
+  - reset-names
+  - power-domains
+  - vddio-pex-ctl-supply
+  - num-lanes
+  - phys
+  - phy-names
+  - nvidia,bpmp
+
+examples:
+  - |
+    #include <dt-bindings/clock/tegra194-clock.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/power/tegra194-powergate.h>
+    #include <dt-bindings/reset/tegra194-reset.h>
+
+    bus@0 {
+        #address-cells = <2>;
+        #size-cells = <2>;
+        ranges = <0x0 0x0 0x0 0x8 0x0>;
+
+        pcie@14180000 {
+            compatible = "nvidia,tegra194-pcie";
+            power-domains = <&bpmp TEGRA194_POWER_DOMAIN_PCIEX8B>;
+            reg = <0x0 0x14180000 0x0 0x00020000>, /* appl registers (128K)      */
+                  <0x0 0x38000000 0x0 0x00040000>, /* configuration space (256K) */
+                  <0x0 0x38040000 0x0 0x00040000>, /* iATU_DMA reg space (256K)  */
+                  <0x0 0x38080000 0x0 0x00040000>; /* DBI reg space (256K)       */
+            reg-names = "appl", "config", "atu_dma", "dbi";
+
+            #address-cells = <3>;
+            #size-cells = <2>;
+            device_type = "pci";
+            num-lanes = <8>;
+            linux,pci-domain = <0>;
+
+            pinctrl-names = "default";
+            pinctrl-0 = <&pex_rst_c5_out_state>, <&clkreq_c5_bi_dir_state>;
+
+            clocks = <&bpmp TEGRA194_CLK_PEX0_CORE_0>;
+            clock-names = "core";
+
+            resets = <&bpmp TEGRA194_RESET_PEX0_CORE_0_APB>,
+                     <&bpmp TEGRA194_RESET_PEX0_CORE_0>;
+            reset-names = "apb", "core";
+
+            interrupts = <GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>, /* controller interrupt */
+                         <GIC_SPI 73 IRQ_TYPE_LEVEL_HIGH>; /* MSI interrupt */
+            interrupt-names = "intr", "msi";
+
+            #interrupt-cells = <1>;
+            interrupt-map-mask = <0 0 0 0>;
+            interrupt-map = <0 0 0 0 &gic GIC_SPI 72 IRQ_TYPE_LEVEL_HIGH>;
+
+            nvidia,bpmp = <&bpmp 0>;
+
+            supports-clkreq;
+            nvidia,aspm-cmrt-us = <60>;
+            nvidia,aspm-pwr-on-t-us = <20>;
+            nvidia,aspm-l0s-entrance-latency-us = <3>;
+
+            bus-range = <0x0 0xff>;
+            ranges = <0x81000000 0x0  0x38100000 0x0  0x38100000 0x0 0x00100000>, /* downstream I/O */
+                     <0x82000000 0x0  0x38200000 0x0  0x38200000 0x0 0x01e00000>, /* non-prefetch memory */
+                     <0xc2000000 0x18 0x00000000 0x18 0x00000000 0x4 0x00000000>; /* prefetchable memory */
+
+            vddio-pex-ctl-supply = <&vdd_1v8ao>;
+            vpcie3v3-supply = <&vdd_3v3_pcie>;
+            vpcie12v-supply = <&vdd_12v_pcie>;
+
+            phys = <&p2u_hsio_2>, <&p2u_hsio_3>, <&p2u_hsio_4>,
+                   <&p2u_hsio_5>;
+            phy-names = "p2u-0", "p2u-1", "p2u-2", "p2u-3";
+        };
+    };
+
+  - |
+    #include <dt-bindings/clock/tegra234-clock.h>
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/power/tegra234-powergate.h>
+    #include <dt-bindings/reset/tegra234-reset.h>
+
+    bus@0 {
+        #address-cells = <2>;
+        #size-cells = <2>;
+        ranges = <0x0 0x0 0x0 0x8 0x0>;
+
+        pcie@14160000 {
+            compatible = "nvidia,tegra234-pcie";
+            power-domains = <&bpmp TEGRA234_POWER_DOMAIN_PCIEX4BB>;
+            reg = <0x00 0x14160000 0x0 0x00020000>, /* appl registers (128K)      */
+                  <0x00 0x36000000 0x0 0x00040000>, /* configuration space (256K) */
+                  <0x00 0x36040000 0x0 0x00040000>, /* iATU_DMA reg space (256K)  */
+                  <0x00 0x36080000 0x0 0x00040000>; /* DBI reg space (256K)       */
+            reg-names = "appl", "config", "atu_dma", "dbi";
+
+            #address-cells = <3>;
+            #size-cells = <2>;
+            device_type = "pci";
+            num-lanes = <4>;
+            num-viewport = <8>;
+            linux,pci-domain = <4>;
+
+            clocks = <&bpmp TEGRA234_CLK_PEX0_C4_CORE>;
+            clock-names = "core";
+
+            resets = <&bpmp TEGRA234_RESET_PEX0_CORE_4_APB>,
+                     <&bpmp TEGRA234_RESET_PEX0_CORE_4>;
+            reset-names = "apb", "core";
+
+            interrupts = <GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>, /* controller interrupt */
+                         <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>; /* MSI interrupt */
+            interrupt-names = "intr", "msi";
+
+            #interrupt-cells = <1>;
+            interrupt-map-mask = <0 0 0 0>;
+            interrupt-map = <0 0 0 0 &gic GIC_SPI 51 IRQ_TYPE_LEVEL_HIGH>;
+
+            nvidia,bpmp = <&bpmp 4>;
+
+            nvidia,aspm-cmrt-us = <60>;
+            nvidia,aspm-pwr-on-t-us = <20>;
+            nvidia,aspm-l0s-entrance-latency-us = <3>;
+
+            bus-range = <0x0 0xff>;
+            ranges = <0x43000000 0x21 0x40000000 0x21 0x40000000 0x2 0xe8000000>, /* prefetchable */
+                     <0x02000000 0x0  0x40000000 0x24 0x28000000 0x0 0x08000000>, /* non-prefetchable */
+                     <0x01000000 0x0  0x36100000 0x00 0x36100000 0x0 0x00100000>; /* downstream I/O */
+
+            vddio-pex-ctl-supply = <&p3701_vdd_AO_1v8>;
+
+            phys = <&p2u_hsio_4>, <&p2u_hsio_5>, <&p2u_hsio_6>,
+                   <&p2u_hsio_7>;
+            phy-names = "p2u-0", "p2u-1", "p2u-2", "p2u-3";
+        };
+    };
diff --git a/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt b/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt
deleted file mode 100644
index aeba38f..0000000
--- a/Documentation/devicetree/bindings/pci/pci-rcar-gen2.txt
+++ /dev/null
@@ -1,84 +0,0 @@
-Renesas AHB to PCI bridge
--------------------------
-
-This is the bridge used internally to connect the USB controllers to the
-AHB. There is one bridge instance per USB port connected to the internal
-OHCI and EHCI controllers.
-
-Required properties:
-- compatible: "renesas,pci-r8a7742" for the R8A7742 SoC;
-	      "renesas,pci-r8a7743" for the R8A7743 SoC;
-	      "renesas,pci-r8a7744" for the R8A7744 SoC;
-	      "renesas,pci-r8a7745" for the R8A7745 SoC;
-	      "renesas,pci-r8a7790" for the R8A7790 SoC;
-	      "renesas,pci-r8a7791" for the R8A7791 SoC;
-	      "renesas,pci-r8a7793" for the R8A7793 SoC;
-	      "renesas,pci-r8a7794" for the R8A7794 SoC;
-	      "renesas,pci-rcar-gen2" for a generic R-Car Gen2 or
-				      RZ/G1 compatible device.
-
-
-	      When compatible with the generic version, nodes must list the
-	      SoC-specific version corresponding to the platform first
-	      followed by the generic version.
-
-- reg:	A list of physical regions to access the device: the first is
-	the operational registers for the OHCI/EHCI controllers and the
-	second is for the bridge configuration and control registers.
-- interrupts: interrupt for the device.
-- clocks: The reference to the device clock.
-- bus-range: The PCI bus number range; as this is a single bus, the range
-	     should be specified as the same value twice.
-- #address-cells: must be 3.
-- #size-cells: must be 2.
-- #interrupt-cells: must be 1.
-- interrupt-map: standard property used to define the mapping of the PCI
-  interrupts to the GIC interrupts.
-- interrupt-map-mask: standard property that helps to define the interrupt
-  mapping.
-
-Optional properties:
-- dma-ranges: a single range for the inbound memory region. If not supplied,
-  defaults to 1GiB at 0x40000000. Note there are hardware restrictions on the
-  allowed combinations of address and size.
-
-Example SoC configuration:
-
-	pci0: pci@ee090000  {
-		compatible = "renesas,pci-r8a7790", "renesas,pci-rcar-gen2";
-		clocks = <&mstp7_clks R8A7790_CLK_EHCI>;
-		reg = <0x0 0xee090000 0x0 0xc00>,
-		      <0x0 0xee080000 0x0 0x1100>;
-		interrupts = <0 108 IRQ_TYPE_LEVEL_HIGH>;
-		status = "disabled";
-
-		bus-range = <0 0>;
-		#address-cells = <3>;
-		#size-cells = <2>;
-		#interrupt-cells = <1>;
-		dma-ranges = <0x42000000 0 0x40000000 0 0x40000000 0 0x40000000>;
-		interrupt-map-mask = <0xff00 0 0 0x7>;
-		interrupt-map = <0x0000 0 0 1 &gic 0 108 IRQ_TYPE_LEVEL_HIGH
-				 0x0800 0 0 1 &gic 0 108 IRQ_TYPE_LEVEL_HIGH
-				 0x1000 0 0 2 &gic 0 108 IRQ_TYPE_LEVEL_HIGH>;
-
-		usb@1,0 {
-			reg = <0x800 0 0 0 0>;
-			phys = <&usb0 0>;
-			phy-names = "usb";
-		};
-
-		usb@2,0 {
-			reg = <0x1000 0 0 0 0>;
-			phys = <&usb0 0>;
-			phy-names = "usb";
-		};
-	};
-
-Example board setup:
-
-&pci0 {
-	status = "okay";
-	pinctrl-0 = <&usb0_pins>;
-	pinctrl-names = "default";
-};
diff --git a/Documentation/devicetree/bindings/pci/qcom,pcie.yaml b/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
index 0b69b12..7d29e2a 100644
--- a/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/qcom,pcie.yaml
@@ -11,7 +11,7 @@
   - Stanimir Varbanov <svarbanov@mm-sol.com>
 
 description: |
-  Qualcomm PCIe root complex controller is bansed on the Synopsys DesignWare
+  Qualcomm PCIe root complex controller is based on the Synopsys DesignWare
   PCIe IP.
 
 properties:
@@ -43,11 +43,12 @@
     maxItems: 5
 
   interrupts:
-    maxItems: 1
+    minItems: 1
+    maxItems: 8
 
   interrupt-names:
-    items:
-      - const: msi
+    minItems: 1
+    maxItems: 8
 
   # Common definitions for clocks, clock-names and reset.
   # Platform constraints are described later.
@@ -614,7 +615,7 @@
   - if:
       not:
         properties:
-          compatibles:
+          compatible:
             contains:
               enum:
                 - qcom,pcie-msm8996
@@ -623,6 +624,50 @@
         - resets
         - reset-names
 
+    # Newer chipsets support either 1 or 8 MSI vectors
+    # On older chipsets it's always 1 MSI vector
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - qcom,pcie-msm8996
+              - qcom,pcie-sc7280
+              - qcom,pcie-sc8180x
+              - qcom,pcie-sdm845
+              - qcom,pcie-sm8150
+              - qcom,pcie-sm8250
+              - qcom,pcie-sm8450-pcie0
+              - qcom,pcie-sm8450-pcie1
+    then:
+      oneOf:
+        - properties:
+            interrupts:
+              maxItems: 1
+            interrupt-names:
+              items:
+                - const: msi
+        - properties:
+            interrupts:
+              minItems: 8
+            interrupt-names:
+              items:
+                - const: msi0
+                - const: msi1
+                - const: msi2
+                - const: msi3
+                - const: msi4
+                - const: msi5
+                - const: msi6
+                - const: msi7
+    else:
+      properties:
+        interrupts:
+          maxItems: 1
+        interrupt-names:
+          items:
+            - const: msi
+
 unevaluatedProperties: false
 
 examples:
diff --git a/Documentation/devicetree/bindings/pci/renesas,pci-rcar-gen2.yaml b/Documentation/devicetree/bindings/pci/renesas,pci-rcar-gen2.yaml
new file mode 100644
index 0000000..0f18cce
--- /dev/null
+++ b/Documentation/devicetree/bindings/pci/renesas,pci-rcar-gen2.yaml
@@ -0,0 +1,186 @@
+# SPDX-License-Identifier: (GPL-2.0-only OR BSD-2-Clause)
+%YAML 1.2
+---
+$id: http://devicetree.org/schemas/pci/renesas,pci-rcar-gen2.yaml#
+$schema: http://devicetree.org/meta-schemas/core.yaml#
+
+title: Renesas AHB to PCI bridge
+
+maintainers:
+  - Marek Vasut <marek.vasut+renesas@gmail.com>
+  - Yoshihiro Shimoda <yoshihiro.shimoda.uh@renesas.com>
+
+description: |
+  This is the bridge used internally to connect the USB controllers to the
+  AHB. There is one bridge instance per USB port connected to the internal
+  OHCI and EHCI controllers.
+
+properties:
+  compatible:
+    oneOf:
+      - items:
+          - enum:
+              - renesas,pci-r8a7742      # RZ/G1H
+              - renesas,pci-r8a7743      # RZ/G1M
+              - renesas,pci-r8a7744      # RZ/G1N
+              - renesas,pci-r8a7745      # RZ/G1E
+              - renesas,pci-r8a7790      # R-Car H2
+              - renesas,pci-r8a7791      # R-Car M2-W
+              - renesas,pci-r8a7793      # R-Car M2-N
+              - renesas,pci-r8a7794      # R-Car E2
+          - const: renesas,pci-rcar-gen2 # R-Car Gen2 and RZ/G1
+      - items:
+          - enum:
+              - renesas,pci-r9a06g032     # RZ/N1D
+          - const: renesas,pci-rzn1       # RZ/N1
+
+  reg:
+    items:
+      - description: Operational registers for the OHCI/EHCI controllers.
+      - description: Bridge configuration and control registers.
+
+  interrupts:
+    maxItems: 1
+
+  clocks: true
+
+  clock-names: true
+
+  resets:
+    maxItems: 1
+
+  power-domains:
+    maxItems: 1
+
+  bus-range:
+    description: |
+      The PCI bus number range; as this is a single bus, the range
+      should be specified as the same value twice.
+
+  dma-ranges:
+    description: |
+      A single range for the inbound memory region. If not supplied,
+      defaults to 1GiB at 0x40000000. Note there are hardware restrictions on
+      the allowed combinations of address and size.
+    maxItems: 1
+
+patternProperties:
+  'usb@[0-1],0':
+    type: object
+
+    description:
+      This a USB controller PCI device
+
+    properties:
+      reg:
+        description:
+          Identify the correct bus, device and function number in the
+          form <bdf 0 0 0 0>.
+
+        items:
+          minItems: 5
+          maxItems: 5
+
+      phys:
+        description:
+          Reference to the USB phy
+        maxItems: 1
+
+      phy-names:
+        maxItems: 1
+
+    required:
+      - reg
+      - phys
+      - phy-names
+
+    unevaluatedProperties: false
+
+required:
+  - compatible
+  - reg
+  - interrupts
+  - interrupt-map
+  - interrupt-map-mask
+  - clocks
+  - power-domains
+  - bus-range
+  - "#address-cells"
+  - "#size-cells"
+  - "#interrupt-cells"
+
+allOf:
+  - $ref: /schemas/pci/pci-bus.yaml#
+
+  - if:
+      properties:
+        compatible:
+          contains:
+            enum:
+              - renesas,pci-rzn1
+    then:
+      properties:
+        clocks:
+          items:
+            - description: Internal bus clock (AHB) for HOST
+            - description: Internal bus clock (AHB) Power Management
+            - description: PCI clock for USB subsystem
+        clock-names:
+          items:
+            - const: hclkh
+            - const: hclkpm
+            - const: pciclk
+      required:
+        - clock-names
+    else:
+      properties:
+        clocks:
+          items:
+            - description: Device clock
+        clock-names:
+          items:
+            - const: pclk
+      required:
+        - resets
+
+unevaluatedProperties: false
+
+examples:
+  - |
+    #include <dt-bindings/interrupt-controller/arm-gic.h>
+    #include <dt-bindings/clock/r8a7790-cpg-mssr.h>
+    #include <dt-bindings/power/r8a7790-sysc.h>
+
+    pci@ee090000  {
+        compatible = "renesas,pci-r8a7790", "renesas,pci-rcar-gen2";
+        device_type = "pci";
+        reg = <0xee090000 0xc00>,
+              <0xee080000 0x1100>;
+        clocks = <&cpg CPG_MOD 703>;
+        power-domains = <&sysc R8A7790_PD_ALWAYS_ON>;
+        resets = <&cpg 703>;
+        interrupts = <GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>;
+
+        bus-range = <0 0>;
+        #address-cells = <3>;
+        #size-cells = <2>;
+        #interrupt-cells = <1>;
+        ranges = <0x02000000 0 0xee080000 0xee080000 0 0x00010000>;
+        dma-ranges = <0x42000000 0 0x40000000 0x40000000 0 0x40000000>;
+        interrupt-map-mask = <0xf800 0 0 0x7>;
+        interrupt-map = <0x0000 0 0 1 &gic GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>,
+                        <0x0800 0 0 1 &gic GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>,
+                        <0x1000 0 0 2 &gic GIC_SPI 108 IRQ_TYPE_LEVEL_HIGH>;
+
+        usb@1,0 {
+            reg = <0x800 0 0 0 0>;
+            phys = <&usb0 0>;
+            phy-names = "usb";
+        };
+
+        usb@2,0 {
+            reg = <0x1000 0 0 0 0>;
+            phys = <&usb0 0>;
+            phy-names = "usb";
+        };
+    };
diff --git a/Documentation/devicetree/bindings/pci/snps,dw-pcie.yaml b/Documentation/devicetree/bindings/pci/snps,dw-pcie.yaml
index c90e5e2..7287d39 100644
--- a/Documentation/devicetree/bindings/pci/snps,dw-pcie.yaml
+++ b/Documentation/devicetree/bindings/pci/snps,dw-pcie.yaml
@@ -34,8 +34,8 @@
     minItems: 2
     maxItems: 5
     items:
-      enum: [ dbi, dbi2, config, atu, app, elbi, mgmt, ctrl, parf, cfg, link,
-              ulreg, smu, mpu, apb, phy ]
+      enum: [ dbi, dbi2, config, atu, atu_dma, app, appl, elbi, mgmt, ctrl,
+              parf, cfg, link, ulreg, smu, mpu, apb, phy ]
 
   num-lanes:
     description: |
diff --git a/arch/s390/pci/pci_bus.c b/arch/s390/pci/pci_bus.c
index 5d77acb..6a8da1b 100644
--- a/arch/s390/pci/pci_bus.c
+++ b/arch/s390/pci/pci_bus.c
@@ -145,9 +145,6 @@
 	struct zpci_dev *zdev;
 	int devfn, rc, ret = 0;
 
-	if (!zbus->function[0])
-		return 0;
-
 	for (devfn = 0; devfn < ZPCI_FUNCTIONS_PER_BUS; devfn++) {
 		zdev = zbus->function[devfn];
 		if (zdev && zdev->state == ZPCI_FN_STATE_CONFIGURED) {
@@ -184,26 +181,26 @@
 
 /* zpci_bus_create_pci_bus - Create the PCI bus associated with this zbus
  * @zbus: the zbus holding the zdevices
- * @f0: function 0 of the bus
+ * @fr: PCI root function that will determine the bus's domain, and bus speeed
  * @ops: the pci operations
  *
- * Function zero is taken as a parameter as this is used to determine the
- * domain, multifunction property and maximum bus speed of the entire bus.
+ * The PCI function @fr determines the domain (its UID), multifunction property
+ * and maximum bus speed of the entire bus.
  *
  * Return: 0 on success, an error code otherwise
  */
-static int zpci_bus_create_pci_bus(struct zpci_bus *zbus, struct zpci_dev *f0, struct pci_ops *ops)
+static int zpci_bus_create_pci_bus(struct zpci_bus *zbus, struct zpci_dev *fr, struct pci_ops *ops)
 {
 	struct pci_bus *bus;
 	int domain;
 
-	domain = zpci_alloc_domain((u16)f0->uid);
+	domain = zpci_alloc_domain((u16)fr->uid);
 	if (domain < 0)
 		return domain;
 
 	zbus->domain_nr = domain;
-	zbus->multifunction = f0->rid_available;
-	zbus->max_bus_speed = f0->max_bus_speed;
+	zbus->multifunction = fr->rid_available;
+	zbus->max_bus_speed = fr->max_bus_speed;
 
 	/*
 	 * Note that the zbus->resources are taken over and zbus->resources
@@ -303,47 +300,6 @@
 	}
 }
 
-/* zpci_bus_create_hotplug_slots - Add hotplug slot(s) for device added to bus
- * @zdev: the zPCI device that was newly added
- *
- * Add the hotplug slot(s) for the newly added PCI function. Normally this is
- * simply the slot for the function itself. If however we are adding the
- * function 0 on a zbus, it might be that we already registered functions on
- * that zbus but could not create their hotplug slots yet so add those now too.
- *
- * Return: 0 on success, an error code otherwise
- */
-static int zpci_bus_create_hotplug_slots(struct zpci_dev *zdev)
-{
-	struct zpci_bus *zbus = zdev->zbus;
-	int devfn, rc = 0;
-
-	rc = zpci_init_slot(zdev);
-	if (rc)
-		return rc;
-	zdev->has_hp_slot = 1;
-
-	if (zdev->devfn == 0 && zbus->multifunction) {
-		/* Now that function 0 is there we can finally create the
-		 * hotplug slots for those functions with devfn != 0 that have
-		 * been parked in zbus->function[] waiting for us to be able to
-		 * create the PCI bus.
-		 */
-		for  (devfn = 1; devfn < ZPCI_FUNCTIONS_PER_BUS; devfn++) {
-			zdev = zbus->function[devfn];
-			if (zdev && !zdev->has_hp_slot) {
-				rc = zpci_init_slot(zdev);
-				if (rc)
-					return rc;
-				zdev->has_hp_slot = 1;
-			}
-		}
-
-	}
-
-	return rc;
-}
-
 static int zpci_bus_add_device(struct zpci_bus *zbus, struct zpci_dev *zdev)
 {
 	int rc = -EINVAL;
@@ -352,21 +308,19 @@
 		pr_err("devfn %04x is already assigned\n", zdev->devfn);
 		return rc;
 	}
+
 	zdev->zbus = zbus;
 	zbus->function[zdev->devfn] = zdev;
 	zpci_nb_devices++;
 
-	if (zbus->bus) {
-		if (zbus->multifunction && !zdev->rid_available) {
-			WARN_ONCE(1, "rid_available not set for multifunction\n");
-			goto error;
-		}
-
-		zpci_bus_create_hotplug_slots(zdev);
-	} else {
-		/* Hotplug slot will be created once function 0 appears */
-		zbus->multifunction = 1;
+	if (zbus->multifunction && !zdev->rid_available) {
+		WARN_ONCE(1, "rid_available not set for multifunction\n");
+		goto error;
 	}
+	rc = zpci_init_slot(zdev);
+	if (rc)
+		goto error;
+	zdev->has_hp_slot = 1;
 
 	return 0;
 
@@ -400,7 +354,11 @@
 			return -ENOMEM;
 	}
 
-	if (zdev->devfn == 0) {
+	if (!zbus->bus) {
+		/* The UID of the first PCI function registered with a zpci_bus
+		 * is used as the domain number for that bus. Currently there
+		 * is exactly one zpci_bus per domain.
+		 */
 		rc = zpci_bus_create_pci_bus(zbus, zdev, ops);
 		if (rc)
 			goto error;
diff --git a/arch/sparc/include/asm/pci.h b/arch/sparc/include/asm/pci.h
index 4deddf4..dff90dc 100644
--- a/arch/sparc/include/asm/pci.h
+++ b/arch/sparc/include/asm/pci.h
@@ -37,6 +37,7 @@
 #define HAVE_PCI_MMAP
 #define arch_can_pci_mmap_io()	1
 #define HAVE_ARCH_PCI_GET_UNMAPPED_AREA
+#define ARCH_GENERIC_PCI_MMAP_RESOURCE
 #define get_pci_unmapped_area get_fb_unmapped_area
 #endif /* CONFIG_SPARC64 */
 
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index 31b0c19..cb1ef25 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -751,156 +751,15 @@
 }
 
 /* Platform support for /proc/bus/pci/X/Y mmap()s. */
-
-/* If the user uses a host-bridge as the PCI device, he may use
- * this to perform a raw mmap() of the I/O or MEM space behind
- * that controller.
- *
- * This can be useful for execution of x86 PCI bios initialization code
- * on a PCI card, like the xfree86 int10 stuff does.
- */
-static int __pci_mmap_make_offset_bus(struct pci_dev *pdev, struct vm_area_struct *vma,
-				      enum pci_mmap_state mmap_state)
+int pci_iobar_pfn(struct pci_dev *pdev, int bar, struct vm_area_struct *vma)
 {
 	struct pci_pbm_info *pbm = pdev->dev.archdata.host_controller;
-	unsigned long space_size, user_offset, user_size;
+	resource_size_t ioaddr = pci_resource_start(pdev, bar);
 
-	if (mmap_state == pci_mmap_io) {
-		space_size = resource_size(&pbm->io_space);
-	} else {
-		space_size = resource_size(&pbm->mem_space);
-	}
-
-	/* Make sure the request is in range. */
-	user_offset = vma->vm_pgoff << PAGE_SHIFT;
-	user_size = vma->vm_end - vma->vm_start;
-
-	if (user_offset >= space_size ||
-	    (user_offset + user_size) > space_size)
+	if (!pbm)
 		return -EINVAL;
 
-	if (mmap_state == pci_mmap_io) {
-		vma->vm_pgoff = (pbm->io_space.start +
-				 user_offset) >> PAGE_SHIFT;
-	} else {
-		vma->vm_pgoff = (pbm->mem_space.start +
-				 user_offset) >> PAGE_SHIFT;
-	}
-
-	return 0;
-}
-
-/* Adjust vm_pgoff of VMA such that it is the physical page offset
- * corresponding to the 32-bit pci bus offset for DEV requested by the user.
- *
- * Basically, the user finds the base address for his device which he wishes
- * to mmap.  They read the 32-bit value from the config space base register,
- * add whatever PAGE_SIZE multiple offset they wish, and feed this into the
- * offset parameter of mmap on /proc/bus/pci/XXX for that device.
- *
- * Returns negative error code on failure, zero on success.
- */
-static int __pci_mmap_make_offset(struct pci_dev *pdev,
-				  struct vm_area_struct *vma,
-				  enum pci_mmap_state mmap_state)
-{
-	unsigned long user_paddr, user_size;
-	int i, err;
-
-	/* First compute the physical address in vma->vm_pgoff,
-	 * making sure the user offset is within range in the
-	 * appropriate PCI space.
-	 */
-	err = __pci_mmap_make_offset_bus(pdev, vma, mmap_state);
-	if (err)
-		return err;
-
-	/* If this is a mapping on a host bridge, any address
-	 * is OK.
-	 */
-	if ((pdev->class >> 8) == PCI_CLASS_BRIDGE_HOST)
-		return err;
-
-	/* Otherwise make sure it's in the range for one of the
-	 * device's resources.
-	 */
-	user_paddr = vma->vm_pgoff << PAGE_SHIFT;
-	user_size = vma->vm_end - vma->vm_start;
-
-	for (i = 0; i <= PCI_ROM_RESOURCE; i++) {
-		struct resource *rp = &pdev->resource[i];
-		resource_size_t aligned_end;
-
-		/* Active? */
-		if (!rp->flags)
-			continue;
-
-		/* Same type? */
-		if (i == PCI_ROM_RESOURCE) {
-			if (mmap_state != pci_mmap_mem)
-				continue;
-		} else {
-			if ((mmap_state == pci_mmap_io &&
-			     (rp->flags & IORESOURCE_IO) == 0) ||
-			    (mmap_state == pci_mmap_mem &&
-			     (rp->flags & IORESOURCE_MEM) == 0))
-				continue;
-		}
-
-		/* Align the resource end to the next page address.
-		 * PAGE_SIZE intentionally added instead of (PAGE_SIZE - 1),
-		 * because actually we need the address of the next byte
-		 * after rp->end.
-		 */
-		aligned_end = (rp->end + PAGE_SIZE) & PAGE_MASK;
-
-		if ((rp->start <= user_paddr) &&
-		    (user_paddr + user_size) <= aligned_end)
-			break;
-	}
-
-	if (i > PCI_ROM_RESOURCE)
-		return -EINVAL;
-
-	return 0;
-}
-
-/* Set vm_page_prot of VMA, as appropriate for this architecture, for a pci
- * device mapping.
- */
-static void __pci_mmap_set_pgprot(struct pci_dev *dev, struct vm_area_struct *vma,
-					     enum pci_mmap_state mmap_state)
-{
-	/* Our io_remap_pfn_range takes care of this, do nothing.  */
-}
-
-/* Perform the actual remap of the pages for a PCI device mapping, as appropriate
- * for this architecture.  The region in the process to map is described by vm_start
- * and vm_end members of VMA, the base physical address is found in vm_pgoff.
- * The pci device structure is provided so that architectures may make mapping
- * decisions on a per-device or per-bus basis.
- *
- * Returns a negative error code on failure, zero on success.
- */
-int pci_mmap_page_range(struct pci_dev *dev, int bar,
-			struct vm_area_struct *vma,
-			enum pci_mmap_state mmap_state, int write_combine)
-{
-	int ret;
-
-	ret = __pci_mmap_make_offset(dev, vma, mmap_state);
-	if (ret < 0)
-		return ret;
-
-	__pci_mmap_set_pgprot(dev, vma, mmap_state);
-
-	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
-	ret = io_remap_pfn_range(vma, vma->vm_start,
-				 vma->vm_pgoff,
-				 vma->vm_end - vma->vm_start,
-				 vma->vm_page_prot);
-	if (ret)
-		return ret;
+	vma->vm_pgoff += (ioaddr + pbm->io_space.start) >> PAGE_SHIFT;
 
 	return 0;
 }
diff --git a/drivers/acpi/pci_mcfg.c b/drivers/acpi/pci_mcfg.c
index 53cab97..860014b 100644
--- a/drivers/acpi/pci_mcfg.c
+++ b/drivers/acpi/pci_mcfg.c
@@ -41,6 +41,8 @@
 static struct mcfg_fixup mcfg_quirks[] = {
 /*	{ OEM_ID, OEM_TABLE_ID, REV, SEGMENT, BUS_RANGE, ops, cfgres }, */
 
+#ifdef CONFIG_ARM64
+
 #define AL_ECAM(table_id, rev, seg, ops) \
 	{ "AMAZON", table_id, rev, seg, MCFG_BUS_ANY, ops }
 
@@ -169,6 +171,17 @@
 	ALTRA_ECAM_QUIRK(1, 13),
 	ALTRA_ECAM_QUIRK(1, 14),
 	ALTRA_ECAM_QUIRK(1, 15),
+#endif /* ARM64 */
+
+#ifdef CONFIG_LOONGARCH
+#define LOONGSON_ECAM_MCFG(table_id, seg) \
+	{ "LOONGS", table_id, 1, seg, MCFG_BUS_ANY, &loongson_pci_ecam_ops }
+
+	LOONGSON_ECAM_MCFG("\0", 0),
+	LOONGSON_ECAM_MCFG("LOONGSON", 0),
+	LOONGSON_ECAM_MCFG("\0", 1),
+	LOONGSON_ECAM_MCFG("LOONGSON", 1),
+#endif /* LOONGARCH */
 };
 
 static char mcfg_oem_id[ACPI_OEM_ID_SIZE];
diff --git a/drivers/clk/qcom/Makefile b/drivers/clk/qcom/Makefile
index 36789f5..0859423 100644
--- a/drivers/clk/qcom/Makefile
+++ b/drivers/clk/qcom/Makefile
@@ -11,6 +11,7 @@
 clk-qcom-y += clk-regmap-divider.o
 clk-qcom-y += clk-regmap-mux.o
 clk-qcom-y += clk-regmap-mux-div.o
+clk-qcom-y += clk-regmap-phy-mux.o
 clk-qcom-$(CONFIG_KRAIT_CLOCKS) += clk-krait.o
 clk-qcom-y += clk-hfpll.o
 clk-qcom-y += reset.o
diff --git a/drivers/clk/qcom/clk-regmap-phy-mux.c b/drivers/clk/qcom/clk-regmap-phy-mux.c
new file mode 100644
index 0000000..7b7243b
--- /dev/null
+++ b/drivers/clk/qcom/clk-regmap-phy-mux.c
@@ -0,0 +1,62 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2022, Linaro Ltd.
+ */
+
+#include <linux/clk-provider.h>
+#include <linux/bitfield.h>
+#include <linux/regmap.h>
+#include <linux/export.h>
+
+#include "clk-regmap.h"
+#include "clk-regmap-phy-mux.h"
+
+#define PHY_MUX_MASK		GENMASK(1, 0)
+#define PHY_MUX_PHY_SRC		0
+#define PHY_MUX_REF_SRC		2
+
+static inline struct clk_regmap_phy_mux *to_clk_regmap_phy_mux(struct clk_regmap *clkr)
+{
+	return container_of(clkr, struct clk_regmap_phy_mux, clkr);
+}
+
+static int phy_mux_is_enabled(struct clk_hw *hw)
+{
+	struct clk_regmap *clkr = to_clk_regmap(hw);
+	struct clk_regmap_phy_mux *phy_mux = to_clk_regmap_phy_mux(clkr);
+	unsigned int val;
+
+	regmap_read(clkr->regmap, phy_mux->reg, &val);
+	val = FIELD_GET(PHY_MUX_MASK, val);
+
+	WARN_ON(val != PHY_MUX_PHY_SRC && val != PHY_MUX_REF_SRC);
+
+	return val == PHY_MUX_PHY_SRC;
+}
+
+static int phy_mux_enable(struct clk_hw *hw)
+{
+	struct clk_regmap *clkr = to_clk_regmap(hw);
+	struct clk_regmap_phy_mux *phy_mux = to_clk_regmap_phy_mux(clkr);
+
+	return regmap_update_bits(clkr->regmap, phy_mux->reg,
+				  PHY_MUX_MASK,
+				  FIELD_PREP(PHY_MUX_MASK, PHY_MUX_PHY_SRC));
+}
+
+static void phy_mux_disable(struct clk_hw *hw)
+{
+	struct clk_regmap *clkr = to_clk_regmap(hw);
+	struct clk_regmap_phy_mux *phy_mux = to_clk_regmap_phy_mux(clkr);
+
+	regmap_update_bits(clkr->regmap, phy_mux->reg,
+			   PHY_MUX_MASK,
+			   FIELD_PREP(PHY_MUX_MASK, PHY_MUX_REF_SRC));
+}
+
+const struct clk_ops clk_regmap_phy_mux_ops = {
+	.enable = phy_mux_enable,
+	.disable = phy_mux_disable,
+	.is_enabled = phy_mux_is_enabled,
+};
+EXPORT_SYMBOL_GPL(clk_regmap_phy_mux_ops);
diff --git a/drivers/clk/qcom/clk-regmap-phy-mux.h b/drivers/clk/qcom/clk-regmap-phy-mux.h
new file mode 100644
index 0000000..614dd38
--- /dev/null
+++ b/drivers/clk/qcom/clk-regmap-phy-mux.h
@@ -0,0 +1,33 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2022, Linaro Ltd.
+ */
+
+#ifndef __QCOM_CLK_REGMAP_PHY_MUX_H__
+#define __QCOM_CLK_REGMAP_PHY_MUX_H__
+
+#include "clk-regmap.h"
+
+/*
+ * A clock implementation for PHY pipe and symbols clock muxes.
+ *
+ * If the clock is running off the from-PHY source, report it as enabled.
+ * Report it as disabled otherwise (if it uses reference source).
+ *
+ * This way the PHY will disable the pipe clock before turning off the GDSC,
+ * which in turn would lead to disabling corresponding pipe_clk_src (and thus
+ * it being parked to a safe, reference clock source). And vice versa, after
+ * enabling the GDSC the PHY will enable the pipe clock, which would cause
+ * pipe_clk_src to be switched from a safe source to the working one.
+ *
+ * For some platforms this should be used for the UFS symbol_clk_src clocks
+ * too.
+ */
+struct clk_regmap_phy_mux {
+	u32			reg;
+	struct clk_regmap	clkr;
+};
+
+extern const struct clk_ops clk_regmap_phy_mux_ops;
+
+#endif
diff --git a/drivers/clk/qcom/gcc-sc7280.c b/drivers/clk/qcom/gcc-sc7280.c
index 423627d..7ff64d4 100644
--- a/drivers/clk/qcom/gcc-sc7280.c
+++ b/drivers/clk/qcom/gcc-sc7280.c
@@ -17,6 +17,7 @@
 #include "clk-rcg.h"
 #include "clk-regmap-divider.h"
 #include "clk-regmap-mux.h"
+#include "clk-regmap-phy-mux.h"
 #include "common.h"
 #include "gdsc.h"
 #include "reset.h"
@@ -255,26 +256,6 @@
 	{ .hw = &gcc_gpll0_out_even.clkr.hw },
 };
 
-static const struct parent_map gcc_parent_map_6[] = {
-	{ P_PCIE_0_PIPE_CLK, 0 },
-	{ P_BI_TCXO, 2 },
-};
-
-static const struct clk_parent_data gcc_parent_data_6[] = {
-	{ .fw_name = "pcie_0_pipe_clk", .name = "pcie_0_pipe_clk" },
-	{ .fw_name = "bi_tcxo" },
-};
-
-static const struct parent_map gcc_parent_map_7[] = {
-	{ P_PCIE_1_PIPE_CLK, 0 },
-	{ P_BI_TCXO, 2 },
-};
-
-static const struct clk_parent_data gcc_parent_data_7[] = {
-	{ .fw_name = "pcie_1_pipe_clk", .name = "pcie_1_pipe_clk" },
-	{ .fw_name = "bi_tcxo" },
-};
-
 static const struct parent_map gcc_parent_map_8[] = {
 	{ P_BI_TCXO, 0 },
 	{ P_GCC_GPLL0_OUT_MAIN, 1 },
@@ -369,32 +350,32 @@
 	{ .hw = &gcc_mss_gpll0_main_div_clk_src.clkr.hw },
 };
 
-static struct clk_regmap_mux gcc_pcie_0_pipe_clk_src = {
+static struct clk_regmap_phy_mux gcc_pcie_0_pipe_clk_src = {
 	.reg = 0x6b054,
-	.shift = 0,
-	.width = 2,
-	.parent_map = gcc_parent_map_6,
 	.clkr = {
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_pcie_0_pipe_clk_src",
-			.parent_data = gcc_parent_data_6,
-			.num_parents = ARRAY_SIZE(gcc_parent_data_6),
-			.ops = &clk_regmap_mux_closest_ops,
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "pcie_0_pipe_clk",
+				.name = "pcie_0_pipe_clk",
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_phy_mux_ops,
 		},
 	},
 };
 
-static struct clk_regmap_mux gcc_pcie_1_pipe_clk_src = {
+static struct clk_regmap_phy_mux gcc_pcie_1_pipe_clk_src = {
 	.reg = 0x8d054,
-	.shift = 0,
-	.width = 2,
-	.parent_map = gcc_parent_map_7,
 	.clkr = {
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_pcie_1_pipe_clk_src",
-			.parent_data = gcc_parent_data_7,
-			.num_parents = ARRAY_SIZE(gcc_parent_data_7),
-			.ops = &clk_regmap_mux_closest_ops,
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "pcie_1_pipe_clk",
+				.name = "pcie_1_pipe_clk",
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_phy_mux_ops,
 		},
 	},
 };
diff --git a/drivers/clk/qcom/gcc-sm8450.c b/drivers/clk/qcom/gcc-sm8450.c
index 593a195..666efa5 100644
--- a/drivers/clk/qcom/gcc-sm8450.c
+++ b/drivers/clk/qcom/gcc-sm8450.c
@@ -17,6 +17,7 @@
 #include "clk-regmap.h"
 #include "clk-regmap-divider.h"
 #include "clk-regmap-mux.h"
+#include "clk-regmap-phy-mux.h"
 #include "gdsc.h"
 #include "reset.h"
 
@@ -26,9 +27,7 @@
 	P_GCC_GPLL0_OUT_MAIN,
 	P_GCC_GPLL4_OUT_MAIN,
 	P_GCC_GPLL9_OUT_MAIN,
-	P_PCIE_0_PIPE_CLK,
 	P_PCIE_1_PHY_AUX_CLK,
-	P_PCIE_1_PIPE_CLK,
 	P_SLEEP_CLK,
 	P_UFS_PHY_RX_SYMBOL_0_CLK,
 	P_UFS_PHY_RX_SYMBOL_1_CLK,
@@ -153,16 +152,6 @@
 	{ .fw_name = "bi_tcxo" },
 };
 
-static const struct parent_map gcc_parent_map_4[] = {
-	{ P_PCIE_0_PIPE_CLK, 0 },
-	{ P_BI_TCXO, 2 },
-};
-
-static const struct clk_parent_data gcc_parent_data_4[] = {
-	{ .fw_name = "pcie_0_pipe_clk", },
-	{ .fw_name = "bi_tcxo", },
-};
-
 static const struct parent_map gcc_parent_map_5[] = {
 	{ P_PCIE_1_PHY_AUX_CLK, 0 },
 	{ P_BI_TCXO, 2 },
@@ -173,16 +162,6 @@
 	{ .fw_name = "bi_tcxo" },
 };
 
-static const struct parent_map gcc_parent_map_6[] = {
-	{ P_PCIE_1_PIPE_CLK, 0 },
-	{ P_BI_TCXO, 2 },
-};
-
-static const struct clk_parent_data gcc_parent_data_6[] = {
-	{ .fw_name = "pcie_1_pipe_clk" },
-	{ .fw_name = "bi_tcxo" },
-};
-
 static const struct parent_map gcc_parent_map_7[] = {
 	{ P_BI_TCXO, 0 },
 	{ P_GCC_GPLL0_OUT_MAIN, 1 },
@@ -239,17 +218,16 @@
 	{ .fw_name = "bi_tcxo" },
 };
 
-static struct clk_regmap_mux gcc_pcie_0_pipe_clk_src = {
+static struct clk_regmap_phy_mux gcc_pcie_0_pipe_clk_src = {
 	.reg = 0x7b060,
-	.shift = 0,
-	.width = 2,
-	.parent_map = gcc_parent_map_4,
 	.clkr = {
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_pcie_0_pipe_clk_src",
-			.parent_data = gcc_parent_data_4,
-			.num_parents = ARRAY_SIZE(gcc_parent_data_4),
-			.ops = &clk_regmap_mux_closest_ops,
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "pcie_0_pipe_clk",
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_phy_mux_ops,
 		},
 	},
 };
@@ -269,17 +247,16 @@
 	},
 };
 
-static struct clk_regmap_mux gcc_pcie_1_pipe_clk_src = {
+static struct clk_regmap_phy_mux gcc_pcie_1_pipe_clk_src = {
 	.reg = 0x9d064,
-	.shift = 0,
-	.width = 2,
-	.parent_map = gcc_parent_map_6,
 	.clkr = {
 		.hw.init = &(struct clk_init_data){
 			.name = "gcc_pcie_1_pipe_clk_src",
-			.parent_data = gcc_parent_data_6,
-			.num_parents = ARRAY_SIZE(gcc_parent_data_6),
-			.ops = &clk_regmap_mux_closest_ops,
+			.parent_data = &(const struct clk_parent_data){
+				.fw_name = "pcie_1_pipe_clk",
+			},
+			.num_parents = 1,
+			.ops = &clk_regmap_phy_mux_ops,
 		},
 	},
 };
diff --git a/drivers/dma/dw-edma/dw-edma-core.c b/drivers/dma/dw-edma/dw-edma-core.c
index 468d109..07f7564 100644
--- a/drivers/dma/dw-edma/dw-edma-core.c
+++ b/drivers/dma/dw-edma/dw-edma-core.c
@@ -64,8 +64,8 @@
 
 static struct dw_edma_chunk *dw_edma_alloc_chunk(struct dw_edma_desc *desc)
 {
+	struct dw_edma_chip *chip = desc->chan->dw->chip;
 	struct dw_edma_chan *chan = desc->chan;
-	struct dw_edma *dw = chan->chip->dw;
 	struct dw_edma_chunk *chunk;
 
 	chunk = kzalloc(sizeof(*chunk), GFP_NOWAIT);
@@ -82,11 +82,11 @@
 	 */
 	chunk->cb = !(desc->chunks_alloc % 2);
 	if (chan->dir == EDMA_DIR_WRITE) {
-		chunk->ll_region.paddr = dw->ll_region_wr[chan->id].paddr;
-		chunk->ll_region.vaddr = dw->ll_region_wr[chan->id].vaddr;
+		chunk->ll_region.paddr = chip->ll_region_wr[chan->id].paddr;
+		chunk->ll_region.vaddr = chip->ll_region_wr[chan->id].vaddr;
 	} else {
-		chunk->ll_region.paddr = dw->ll_region_rd[chan->id].paddr;
-		chunk->ll_region.vaddr = dw->ll_region_rd[chan->id].vaddr;
+		chunk->ll_region.paddr = chip->ll_region_rd[chan->id].paddr;
+		chunk->ll_region.vaddr = chip->ll_region_rd[chan->id].vaddr;
 	}
 
 	if (desc->chunk) {
@@ -339,21 +339,40 @@
 	if (!chan->configured)
 		return NULL;
 
-	switch (chan->config.direction) {
-	case DMA_DEV_TO_MEM: /* local DMA */
-		if (dir == DMA_DEV_TO_MEM && chan->dir == EDMA_DIR_READ)
-			break;
-		return NULL;
-	case DMA_MEM_TO_DEV: /* local DMA */
-		if (dir == DMA_MEM_TO_DEV && chan->dir == EDMA_DIR_WRITE)
-			break;
-		return NULL;
-	default: /* remote DMA */
-		if (dir == DMA_MEM_TO_DEV && chan->dir == EDMA_DIR_READ)
-			break;
-		if (dir == DMA_DEV_TO_MEM && chan->dir == EDMA_DIR_WRITE)
-			break;
-		return NULL;
+	/*
+	 * Local Root Port/End-point              Remote End-point
+	 * +-----------------------+ PCIe bus +----------------------+
+	 * |                       |    +-+   |                      |
+	 * |    DEV_TO_MEM   Rx Ch <----+ +---+ Tx Ch  DEV_TO_MEM    |
+	 * |                       |    | |   |                      |
+	 * |    MEM_TO_DEV   Tx Ch +----+ +---> Rx Ch  MEM_TO_DEV    |
+	 * |                       |    +-+   |                      |
+	 * +-----------------------+          +----------------------+
+	 *
+	 * 1. Normal logic:
+	 * If eDMA is embedded into the DW PCIe RP/EP and controlled from the
+	 * CPU/Application side, the Rx channel (EDMA_DIR_READ) will be used
+	 * for the device read operations (DEV_TO_MEM) and the Tx channel
+	 * (EDMA_DIR_WRITE) - for the write operations (MEM_TO_DEV).
+	 *
+	 * 2. Inverted logic:
+	 * If eDMA is embedded into a Remote PCIe EP and is controlled by the
+	 * MWr/MRd TLPs sent from the CPU's PCIe host controller, the Tx
+	 * channel (EDMA_DIR_WRITE) will be used for the device read operations
+	 * (DEV_TO_MEM) and the Rx channel (EDMA_DIR_READ) - for the write
+	 * operations (MEM_TO_DEV).
+	 *
+	 * It is the client driver responsibility to choose a proper channel
+	 * for the DMA transfers.
+	 */
+	if (chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL) {
+		if ((chan->dir == EDMA_DIR_READ && dir != DMA_DEV_TO_MEM) ||
+		    (chan->dir == EDMA_DIR_WRITE && dir != DMA_MEM_TO_DEV))
+			return NULL;
+	} else {
+		if ((chan->dir == EDMA_DIR_WRITE && dir != DMA_DEV_TO_MEM) ||
+		    (chan->dir == EDMA_DIR_READ && dir != DMA_MEM_TO_DEV))
+			return NULL;
 	}
 
 	if (xfer->type == EDMA_XFER_CYCLIC) {
@@ -423,7 +442,7 @@
 		chunk->ll_region.sz += burst->sz;
 		desc->alloc_sz += burst->sz;
 
-		if (chan->dir == EDMA_DIR_WRITE) {
+		if (dir == DMA_DEV_TO_MEM) {
 			burst->sar = src_addr;
 			if (xfer->type == EDMA_XFER_CYCLIC) {
 				burst->dar = xfer->xfer.cyclic.paddr;
@@ -663,7 +682,7 @@
 	if (chan->status != EDMA_ST_IDLE)
 		return -EBUSY;
 
-	pm_runtime_get(chan->chip->dev);
+	pm_runtime_get(chan->dw->chip->dev);
 
 	return 0;
 }
@@ -685,15 +704,15 @@
 		cpu_relax();
 	}
 
-	pm_runtime_put(chan->chip->dev);
+	pm_runtime_put(chan->dw->chip->dev);
 }
 
-static int dw_edma_channel_setup(struct dw_edma_chip *chip, bool write,
+static int dw_edma_channel_setup(struct dw_edma *dw, bool write,
 				 u32 wr_alloc, u32 rd_alloc)
 {
+	struct dw_edma_chip *chip = dw->chip;
 	struct dw_edma_region *dt_region;
 	struct device *dev = chip->dev;
-	struct dw_edma *dw = chip->dw;
 	struct dw_edma_chan *chan;
 	struct dw_edma_irq *irq;
 	struct dma_device *dma;
@@ -726,7 +745,7 @@
 
 		chan->vc.chan.private = dt_region;
 
-		chan->chip = chip;
+		chan->dw = dw;
 		chan->id = j;
 		chan->dir = write ? EDMA_DIR_WRITE : EDMA_DIR_READ;
 		chan->configured = false;
@@ -734,9 +753,9 @@
 		chan->status = EDMA_ST_IDLE;
 
 		if (write)
-			chan->ll_max = (dw->ll_region_wr[j].sz / EDMA_LL_SZ);
+			chan->ll_max = (chip->ll_region_wr[j].sz / EDMA_LL_SZ);
 		else
-			chan->ll_max = (dw->ll_region_rd[j].sz / EDMA_LL_SZ);
+			chan->ll_max = (chip->ll_region_rd[j].sz / EDMA_LL_SZ);
 		chan->ll_max -= 1;
 
 		dev_vdbg(dev, "L. List:\tChannel %s[%u] max_cnt=%u\n",
@@ -766,13 +785,13 @@
 		vchan_init(&chan->vc, dma);
 
 		if (write) {
-			dt_region->paddr = dw->dt_region_wr[j].paddr;
-			dt_region->vaddr = dw->dt_region_wr[j].vaddr;
-			dt_region->sz = dw->dt_region_wr[j].sz;
+			dt_region->paddr = chip->dt_region_wr[j].paddr;
+			dt_region->vaddr = chip->dt_region_wr[j].vaddr;
+			dt_region->sz = chip->dt_region_wr[j].sz;
 		} else {
-			dt_region->paddr = dw->dt_region_rd[j].paddr;
-			dt_region->vaddr = dw->dt_region_rd[j].vaddr;
-			dt_region->sz = dw->dt_region_rd[j].sz;
+			dt_region->paddr = chip->dt_region_rd[j].paddr;
+			dt_region->vaddr = chip->dt_region_rd[j].vaddr;
+			dt_region->sz = chip->dt_region_rd[j].sz;
 		}
 
 		dw_edma_v0_core_device_config(chan);
@@ -826,11 +845,11 @@
 		(*mask)++;
 }
 
-static int dw_edma_irq_request(struct dw_edma_chip *chip,
+static int dw_edma_irq_request(struct dw_edma *dw,
 			       u32 *wr_alloc, u32 *rd_alloc)
 {
-	struct device *dev = chip->dev;
-	struct dw_edma *dw = chip->dw;
+	struct dw_edma_chip *chip = dw->chip;
+	struct device *dev = dw->chip->dev;
 	u32 wr_mask = 1;
 	u32 rd_mask = 1;
 	int i, err = 0;
@@ -839,12 +858,16 @@
 
 	ch_cnt = dw->wr_ch_cnt + dw->rd_ch_cnt;
 
-	if (dw->nr_irqs < 1)
+	if (chip->nr_irqs < 1 || !chip->ops->irq_vector)
 		return -EINVAL;
 
-	if (dw->nr_irqs == 1) {
+	dw->irq = devm_kcalloc(dev, chip->nr_irqs, sizeof(*dw->irq), GFP_KERNEL);
+	if (!dw->irq)
+		return -ENOMEM;
+
+	if (chip->nr_irqs == 1) {
 		/* Common IRQ shared among all channels */
-		irq = dw->ops->irq_vector(dev, 0);
+		irq = chip->ops->irq_vector(dev, 0);
 		err = request_irq(irq, dw_edma_interrupt_common,
 				  IRQF_SHARED, dw->name, &dw->irq[0]);
 		if (err) {
@@ -854,9 +877,11 @@
 
 		if (irq_get_msi_desc(irq))
 			get_cached_msi_msg(irq, &dw->irq[0].msi);
+
+		dw->nr_irqs = 1;
 	} else {
 		/* Distribute IRQs equally among all channels */
-		int tmp = dw->nr_irqs;
+		int tmp = chip->nr_irqs;
 
 		while (tmp && (*wr_alloc + *rd_alloc) < ch_cnt) {
 			dw_edma_dec_irq_alloc(&tmp, wr_alloc, dw->wr_ch_cnt);
@@ -867,7 +892,7 @@
 		dw_edma_add_irq_mask(&rd_mask, *rd_alloc, dw->rd_ch_cnt);
 
 		for (i = 0; i < (*wr_alloc + *rd_alloc); i++) {
-			irq = dw->ops->irq_vector(dev, i);
+			irq = chip->ops->irq_vector(dev, i);
 			err = request_irq(irq,
 					  i < *wr_alloc ?
 						dw_edma_interrupt_write :
@@ -901,20 +926,22 @@
 		return -EINVAL;
 
 	dev = chip->dev;
-	if (!dev)
+	if (!dev || !chip->ops)
 		return -EINVAL;
 
-	dw = chip->dw;
-	if (!dw || !dw->irq || !dw->ops || !dw->ops->irq_vector)
-		return -EINVAL;
+	dw = devm_kzalloc(dev, sizeof(*dw), GFP_KERNEL);
+	if (!dw)
+		return -ENOMEM;
+
+	dw->chip = chip;
 
 	raw_spin_lock_init(&dw->lock);
 
-	dw->wr_ch_cnt = min_t(u16, dw->wr_ch_cnt,
+	dw->wr_ch_cnt = min_t(u16, chip->ll_wr_cnt,
 			      dw_edma_v0_core_ch_count(dw, EDMA_DIR_WRITE));
 	dw->wr_ch_cnt = min_t(u16, dw->wr_ch_cnt, EDMA_MAX_WR_CH);
 
-	dw->rd_ch_cnt = min_t(u16, dw->rd_ch_cnt,
+	dw->rd_ch_cnt = min_t(u16, chip->ll_rd_cnt,
 			      dw_edma_v0_core_ch_count(dw, EDMA_DIR_READ));
 	dw->rd_ch_cnt = min_t(u16, dw->rd_ch_cnt, EDMA_MAX_RD_CH);
 
@@ -936,17 +963,17 @@
 	dw_edma_v0_core_off(dw);
 
 	/* Request IRQs */
-	err = dw_edma_irq_request(chip, &wr_alloc, &rd_alloc);
+	err = dw_edma_irq_request(dw, &wr_alloc, &rd_alloc);
 	if (err)
 		return err;
 
 	/* Setup write channels */
-	err = dw_edma_channel_setup(chip, true, wr_alloc, rd_alloc);
+	err = dw_edma_channel_setup(dw, true, wr_alloc, rd_alloc);
 	if (err)
 		goto err_irq_free;
 
 	/* Setup read channels */
-	err = dw_edma_channel_setup(chip, false, wr_alloc, rd_alloc);
+	err = dw_edma_channel_setup(dw, false, wr_alloc, rd_alloc);
 	if (err)
 		goto err_irq_free;
 
@@ -954,15 +981,15 @@
 	pm_runtime_enable(dev);
 
 	/* Turn debugfs on */
-	dw_edma_v0_core_debugfs_on(chip);
+	dw_edma_v0_core_debugfs_on(dw);
+
+	chip->dw = dw;
 
 	return 0;
 
 err_irq_free:
 	for (i = (dw->nr_irqs - 1); i >= 0; i--)
-		free_irq(dw->ops->irq_vector(dev, i), &dw->irq[i]);
-
-	dw->nr_irqs = 0;
+		free_irq(chip->ops->irq_vector(dev, i), &dw->irq[i]);
 
 	return err;
 }
@@ -980,7 +1007,7 @@
 
 	/* Free irqs */
 	for (i = (dw->nr_irqs - 1); i >= 0; i--)
-		free_irq(dw->ops->irq_vector(dev, i), &dw->irq[i]);
+		free_irq(chip->ops->irq_vector(dev, i), &dw->irq[i]);
 
 	/* Power management */
 	pm_runtime_disable(dev);
@@ -1001,7 +1028,7 @@
 	}
 
 	/* Turn debugfs off */
-	dw_edma_v0_core_debugfs_off(chip);
+	dw_edma_v0_core_debugfs_off(dw);
 
 	return 0;
 }
diff --git a/drivers/dma/dw-edma/dw-edma-core.h b/drivers/dma/dw-edma/dw-edma-core.h
index 60316d4..85df2d5 100644
--- a/drivers/dma/dw-edma/dw-edma-core.h
+++ b/drivers/dma/dw-edma/dw-edma-core.h
@@ -15,20 +15,12 @@
 #include "../virt-dma.h"
 
 #define EDMA_LL_SZ					24
-#define EDMA_MAX_WR_CH					8
-#define EDMA_MAX_RD_CH					8
 
 enum dw_edma_dir {
 	EDMA_DIR_WRITE = 0,
 	EDMA_DIR_READ
 };
 
-enum dw_edma_map_format {
-	EDMA_MF_EDMA_LEGACY = 0x0,
-	EDMA_MF_EDMA_UNROLL = 0x1,
-	EDMA_MF_HDMA_COMPAT = 0x5
-};
-
 enum dw_edma_request {
 	EDMA_REQ_NONE = 0,
 	EDMA_REQ_STOP,
@@ -57,12 +49,6 @@
 	u32				sz;
 };
 
-struct dw_edma_region {
-	phys_addr_t			paddr;
-	void				__iomem *vaddr;
-	size_t				sz;
-};
-
 struct dw_edma_chunk {
 	struct list_head		list;
 	struct dw_edma_chan		*chan;
@@ -87,7 +73,7 @@
 
 struct dw_edma_chan {
 	struct virt_dma_chan		vc;
-	struct dw_edma_chip		*chip;
+	struct dw_edma			*dw;
 	int				id;
 	enum dw_edma_dir		dir;
 
@@ -109,10 +95,6 @@
 	struct dw_edma			*dw;
 };
 
-struct dw_edma_core_ops {
-	int	(*irq_vector)(struct device *dev, unsigned int nr);
-};
-
 struct dw_edma {
 	char				name[20];
 
@@ -122,21 +104,14 @@
 	struct dma_device		rd_edma;
 	u16				rd_ch_cnt;
 
-	struct dw_edma_region		rg_region;	/* Registers */
-	struct dw_edma_region		ll_region_wr[EDMA_MAX_WR_CH];
-	struct dw_edma_region		ll_region_rd[EDMA_MAX_RD_CH];
-	struct dw_edma_region		dt_region_wr[EDMA_MAX_WR_CH];
-	struct dw_edma_region		dt_region_rd[EDMA_MAX_RD_CH];
-
 	struct dw_edma_irq		*irq;
 	int				nr_irqs;
 
-	enum dw_edma_map_format		mf;
-
 	struct dw_edma_chan		*chan;
-	const struct dw_edma_core_ops	*ops;
 
 	raw_spinlock_t			lock;		/* Only for legacy */
+
+	struct dw_edma_chip             *chip;
 #ifdef CONFIG_DEBUG_FS
 	struct dentry			*debugfs;
 #endif /* CONFIG_DEBUG_FS */
diff --git a/drivers/dma/dw-edma/dw-edma-pcie.c b/drivers/dma/dw-edma/dw-edma-pcie.c
index cee7aa2..d6b5e24 100644
--- a/drivers/dma/dw-edma/dw-edma-pcie.c
+++ b/drivers/dma/dw-edma/dw-edma-pcie.c
@@ -148,7 +148,6 @@
 	struct dw_edma_pcie_data vsec_data;
 	struct device *dev = &pdev->dev;
 	struct dw_edma_chip *chip;
-	struct dw_edma *dw;
 	int err, nr_irqs;
 	int i, mask;
 
@@ -197,10 +196,6 @@
 	if (!chip)
 		return -ENOMEM;
 
-	dw = devm_kzalloc(dev, sizeof(*dw), GFP_KERNEL);
-	if (!dw)
-		return -ENOMEM;
-
 	/* IRQs allocation */
 	nr_irqs = pci_alloc_irq_vectors(pdev, 1, vsec_data.irqs,
 					PCI_IRQ_MSI | PCI_IRQ_MSIX);
@@ -211,29 +206,23 @@
 	}
 
 	/* Data structure initialization */
-	chip->dw = dw;
 	chip->dev = dev;
 	chip->id = pdev->devfn;
-	chip->irq = pdev->irq;
 
-	dw->mf = vsec_data.mf;
-	dw->nr_irqs = nr_irqs;
-	dw->ops = &dw_edma_pcie_core_ops;
-	dw->wr_ch_cnt = vsec_data.wr_ch_cnt;
-	dw->rd_ch_cnt = vsec_data.rd_ch_cnt;
+	chip->mf = vsec_data.mf;
+	chip->nr_irqs = nr_irqs;
+	chip->ops = &dw_edma_pcie_core_ops;
 
-	dw->rg_region.vaddr = pcim_iomap_table(pdev)[vsec_data.rg.bar];
-	if (!dw->rg_region.vaddr)
+	chip->ll_wr_cnt = vsec_data.wr_ch_cnt;
+	chip->ll_rd_cnt = vsec_data.rd_ch_cnt;
+
+	chip->reg_base = pcim_iomap_table(pdev)[vsec_data.rg.bar];
+	if (!chip->reg_base)
 		return -ENOMEM;
 
-	dw->rg_region.vaddr += vsec_data.rg.off;
-	dw->rg_region.paddr = pdev->resource[vsec_data.rg.bar].start;
-	dw->rg_region.paddr += vsec_data.rg.off;
-	dw->rg_region.sz = vsec_data.rg.sz;
-
-	for (i = 0; i < dw->wr_ch_cnt; i++) {
-		struct dw_edma_region *ll_region = &dw->ll_region_wr[i];
-		struct dw_edma_region *dt_region = &dw->dt_region_wr[i];
+	for (i = 0; i < chip->ll_wr_cnt; i++) {
+		struct dw_edma_region *ll_region = &chip->ll_region_wr[i];
+		struct dw_edma_region *dt_region = &chip->dt_region_wr[i];
 		struct dw_edma_block *ll_block = &vsec_data.ll_wr[i];
 		struct dw_edma_block *dt_block = &vsec_data.dt_wr[i];
 
@@ -256,9 +245,9 @@
 		dt_region->sz = dt_block->sz;
 	}
 
-	for (i = 0; i < dw->rd_ch_cnt; i++) {
-		struct dw_edma_region *ll_region = &dw->ll_region_rd[i];
-		struct dw_edma_region *dt_region = &dw->dt_region_rd[i];
+	for (i = 0; i < chip->ll_rd_cnt; i++) {
+		struct dw_edma_region *ll_region = &chip->ll_region_rd[i];
+		struct dw_edma_region *dt_region = &chip->dt_region_rd[i];
 		struct dw_edma_block *ll_block = &vsec_data.ll_rd[i];
 		struct dw_edma_block *dt_block = &vsec_data.dt_rd[i];
 
@@ -282,45 +271,45 @@
 	}
 
 	/* Debug info */
-	if (dw->mf == EDMA_MF_EDMA_LEGACY)
-		pci_dbg(pdev, "Version:\teDMA Port Logic (0x%x)\n", dw->mf);
-	else if (dw->mf == EDMA_MF_EDMA_UNROLL)
-		pci_dbg(pdev, "Version:\teDMA Unroll (0x%x)\n", dw->mf);
-	else if (dw->mf == EDMA_MF_HDMA_COMPAT)
-		pci_dbg(pdev, "Version:\tHDMA Compatible (0x%x)\n", dw->mf);
+	if (chip->mf == EDMA_MF_EDMA_LEGACY)
+		pci_dbg(pdev, "Version:\teDMA Port Logic (0x%x)\n", chip->mf);
+	else if (chip->mf == EDMA_MF_EDMA_UNROLL)
+		pci_dbg(pdev, "Version:\teDMA Unroll (0x%x)\n", chip->mf);
+	else if (chip->mf == EDMA_MF_HDMA_COMPAT)
+		pci_dbg(pdev, "Version:\tHDMA Compatible (0x%x)\n", chip->mf);
 	else
-		pci_dbg(pdev, "Version:\tUnknown (0x%x)\n", dw->mf);
+		pci_dbg(pdev, "Version:\tUnknown (0x%x)\n", chip->mf);
 
-	pci_dbg(pdev, "Registers:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
+	pci_dbg(pdev, "Registers:\tBAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p)\n",
 		vsec_data.rg.bar, vsec_data.rg.off, vsec_data.rg.sz,
-		dw->rg_region.vaddr, &dw->rg_region.paddr);
+		chip->reg_base);
 
 
-	for (i = 0; i < dw->wr_ch_cnt; i++) {
+	for (i = 0; i < chip->ll_wr_cnt; i++) {
 		pci_dbg(pdev, "L. List:\tWRITE CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
 			i, vsec_data.ll_wr[i].bar,
-			vsec_data.ll_wr[i].off, dw->ll_region_wr[i].sz,
-			dw->ll_region_wr[i].vaddr, &dw->ll_region_wr[i].paddr);
+			vsec_data.ll_wr[i].off, chip->ll_region_wr[i].sz,
+			chip->ll_region_wr[i].vaddr, &chip->ll_region_wr[i].paddr);
 
 		pci_dbg(pdev, "Data:\tWRITE CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
 			i, vsec_data.dt_wr[i].bar,
-			vsec_data.dt_wr[i].off, dw->dt_region_wr[i].sz,
-			dw->dt_region_wr[i].vaddr, &dw->dt_region_wr[i].paddr);
+			vsec_data.dt_wr[i].off, chip->dt_region_wr[i].sz,
+			chip->dt_region_wr[i].vaddr, &chip->dt_region_wr[i].paddr);
 	}
 
-	for (i = 0; i < dw->rd_ch_cnt; i++) {
+	for (i = 0; i < chip->ll_rd_cnt; i++) {
 		pci_dbg(pdev, "L. List:\tREAD CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
 			i, vsec_data.ll_rd[i].bar,
-			vsec_data.ll_rd[i].off, dw->ll_region_rd[i].sz,
-			dw->ll_region_rd[i].vaddr, &dw->ll_region_rd[i].paddr);
+			vsec_data.ll_rd[i].off, chip->ll_region_rd[i].sz,
+			chip->ll_region_rd[i].vaddr, &chip->ll_region_rd[i].paddr);
 
 		pci_dbg(pdev, "Data:\tREAD CH%.2u, BAR=%u, off=0x%.8lx, sz=0x%zx bytes, addr(v=%p, p=%pa)\n",
 			i, vsec_data.dt_rd[i].bar,
-			vsec_data.dt_rd[i].off, dw->dt_region_rd[i].sz,
-			dw->dt_region_rd[i].vaddr, &dw->dt_region_rd[i].paddr);
+			vsec_data.dt_rd[i].off, chip->dt_region_rd[i].sz,
+			chip->dt_region_rd[i].vaddr, &chip->dt_region_rd[i].paddr);
 	}
 
-	pci_dbg(pdev, "Nr. IRQs:\t%u\n", dw->nr_irqs);
+	pci_dbg(pdev, "Nr. IRQs:\t%u\n", chip->nr_irqs);
 
 	/* Validating if PCI interrupts were enabled */
 	if (!pci_dev_msi_enabled(pdev)) {
@@ -328,10 +317,6 @@
 		return -EPERM;
 	}
 
-	dw->irq = devm_kcalloc(dev, nr_irqs, sizeof(*dw->irq), GFP_KERNEL);
-	if (!dw->irq)
-		return -ENOMEM;
-
 	/* Starting eDMA driver */
 	err = dw_edma_probe(chip);
 	if (err) {
diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.c b/drivers/dma/dw-edma/dw-edma-v0-core.c
index 33bc1e6..607647d 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-core.c
+++ b/drivers/dma/dw-edma/dw-edma-v0-core.c
@@ -25,7 +25,7 @@
 
 static inline struct dw_edma_v0_regs __iomem *__dw_regs(struct dw_edma *dw)
 {
-	return dw->rg_region.vaddr;
+	return dw->chip->reg_base;
 }
 
 #define SET_32(dw, name, value)				\
@@ -96,7 +96,7 @@
 static inline struct dw_edma_v0_ch_regs __iomem *
 __dw_ch_regs(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch)
 {
-	if (dw->mf == EDMA_MF_EDMA_LEGACY)
+	if (dw->chip->mf == EDMA_MF_EDMA_LEGACY)
 		return &(__dw_regs(dw)->type.legacy.ch);
 
 	if (dir == EDMA_DIR_WRITE)
@@ -108,7 +108,7 @@
 static inline void writel_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch,
 			     u32 value, void __iomem *addr)
 {
-	if (dw->mf == EDMA_MF_EDMA_LEGACY) {
+	if (dw->chip->mf == EDMA_MF_EDMA_LEGACY) {
 		u32 viewport_sel;
 		unsigned long flags;
 
@@ -133,7 +133,7 @@
 {
 	u32 value;
 
-	if (dw->mf == EDMA_MF_EDMA_LEGACY) {
+	if (dw->chip->mf == EDMA_MF_EDMA_LEGACY) {
 		u32 viewport_sel;
 		unsigned long flags;
 
@@ -169,7 +169,7 @@
 static inline void writeq_ch(struct dw_edma *dw, enum dw_edma_dir dir, u16 ch,
 			     u64 value, void __iomem *addr)
 {
-	if (dw->mf == EDMA_MF_EDMA_LEGACY) {
+	if (dw->chip->mf == EDMA_MF_EDMA_LEGACY) {
 		u32 viewport_sel;
 		unsigned long flags;
 
@@ -194,7 +194,7 @@
 {
 	u32 value;
 
-	if (dw->mf == EDMA_MF_EDMA_LEGACY) {
+	if (dw->chip->mf == EDMA_MF_EDMA_LEGACY) {
 		u32 viewport_sel;
 		unsigned long flags;
 
@@ -256,7 +256,7 @@
 
 enum dma_status dw_edma_v0_core_ch_status(struct dw_edma_chan *chan)
 {
-	struct dw_edma *dw = chan->chip->dw;
+	struct dw_edma *dw = chan->dw;
 	u32 tmp;
 
 	tmp = FIELD_GET(EDMA_V0_CH_STATUS_MASK,
@@ -272,7 +272,7 @@
 
 void dw_edma_v0_core_clear_done_int(struct dw_edma_chan *chan)
 {
-	struct dw_edma *dw = chan->chip->dw;
+	struct dw_edma *dw = chan->dw;
 
 	SET_RW_32(dw, chan->dir, int_clear,
 		  FIELD_PREP(EDMA_V0_DONE_INT_MASK, BIT(chan->id)));
@@ -280,7 +280,7 @@
 
 void dw_edma_v0_core_clear_abort_int(struct dw_edma_chan *chan)
 {
-	struct dw_edma *dw = chan->chip->dw;
+	struct dw_edma *dw = chan->dw;
 
 	SET_RW_32(dw, chan->dir, int_clear,
 		  FIELD_PREP(EDMA_V0_ABORT_INT_MASK, BIT(chan->id)));
@@ -301,6 +301,7 @@
 static void dw_edma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
 {
 	struct dw_edma_burst *child;
+	struct dw_edma_chan *chan = chunk->chan;
 	struct dw_edma_v0_lli __iomem *lli;
 	struct dw_edma_v0_llp __iomem *llp;
 	u32 control = 0, i = 0;
@@ -314,9 +315,11 @@
 	j = chunk->bursts_alloc;
 	list_for_each_entry(child, &chunk->burst->list, list) {
 		j--;
-		if (!j)
-			control |= (DW_EDMA_V0_LIE | DW_EDMA_V0_RIE);
-
+		if (!j) {
+			control |= DW_EDMA_V0_LIE;
+			if (!(chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL))
+				control |= DW_EDMA_V0_RIE;
+		}
 		/* Channel control */
 		SET_LL_32(&lli[i].control, control);
 		/* Transfer size */
@@ -357,7 +360,7 @@
 void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
 {
 	struct dw_edma_chan *chan = chunk->chan;
-	struct dw_edma *dw = chan->chip->dw;
+	struct dw_edma *dw = chan->dw;
 	u32 tmp;
 
 	dw_edma_v0_core_write_chunk(chunk);
@@ -365,7 +368,7 @@
 	if (first) {
 		/* Enable engine */
 		SET_RW_32(dw, chan->dir, engine_en, BIT(0));
-		if (dw->mf == EDMA_MF_HDMA_COMPAT) {
+		if (dw->chip->mf == EDMA_MF_HDMA_COMPAT) {
 			switch (chan->id) {
 			case 0:
 				SET_RW_COMPAT(dw, chan->dir, ch0_pwr_en,
@@ -435,7 +438,7 @@
 
 int dw_edma_v0_core_device_config(struct dw_edma_chan *chan)
 {
-	struct dw_edma *dw = chan->chip->dw;
+	struct dw_edma *dw = chan->dw;
 	u32 tmp = 0;
 
 	/* MSI done addr - low, high */
@@ -505,12 +508,12 @@
 }
 
 /* eDMA debugfs callbacks */
-void dw_edma_v0_core_debugfs_on(struct dw_edma_chip *chip)
+void dw_edma_v0_core_debugfs_on(struct dw_edma *dw)
 {
-	dw_edma_v0_debugfs_on(chip);
+	dw_edma_v0_debugfs_on(dw);
 }
 
-void dw_edma_v0_core_debugfs_off(struct dw_edma_chip *chip)
+void dw_edma_v0_core_debugfs_off(struct dw_edma *dw)
 {
-	dw_edma_v0_debugfs_off(chip);
+	dw_edma_v0_debugfs_off(dw);
 }
diff --git a/drivers/dma/dw-edma/dw-edma-v0-core.h b/drivers/dma/dw-edma/dw-edma-v0-core.h
index 2afa626..75aec6d 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-core.h
+++ b/drivers/dma/dw-edma/dw-edma-v0-core.h
@@ -22,7 +22,7 @@
 void dw_edma_v0_core_start(struct dw_edma_chunk *chunk, bool first);
 int dw_edma_v0_core_device_config(struct dw_edma_chan *chan);
 /* eDMA debug fs callbacks */
-void dw_edma_v0_core_debugfs_on(struct dw_edma_chip *chip);
-void dw_edma_v0_core_debugfs_off(struct dw_edma_chip *chip);
+void dw_edma_v0_core_debugfs_on(struct dw_edma *dw);
+void dw_edma_v0_core_debugfs_off(struct dw_edma *dw);
 
 #endif /* _DW_EDMA_V0_CORE_H */
diff --git a/drivers/dma/dw-edma/dw-edma-v0-debugfs.c b/drivers/dma/dw-edma/dw-edma-v0-debugfs.c
index 4b3bcff..5226c901 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-debugfs.c
+++ b/drivers/dma/dw-edma/dw-edma-v0-debugfs.c
@@ -54,7 +54,7 @@
 static int dw_edma_debugfs_u32_get(void *data, u64 *val)
 {
 	void __iomem *reg = (void __force __iomem *)data;
-	if (dw->mf == EDMA_MF_EDMA_LEGACY &&
+	if (dw->chip->mf == EDMA_MF_EDMA_LEGACY &&
 	    reg >= (void __iomem *)&regs->type.legacy.ch) {
 		void __iomem *ptr = &regs->type.legacy.ch;
 		u32 viewport_sel = 0;
@@ -173,7 +173,7 @@
 	nr_entries = ARRAY_SIZE(debugfs_regs);
 	dw_edma_debugfs_create_x32(debugfs_regs, nr_entries, regs_dir);
 
-	if (dw->mf == EDMA_MF_HDMA_COMPAT) {
+	if (dw->chip->mf == EDMA_MF_HDMA_COMPAT) {
 		nr_entries = ARRAY_SIZE(debugfs_unroll_regs);
 		dw_edma_debugfs_create_x32(debugfs_unroll_regs, nr_entries,
 					   regs_dir);
@@ -242,7 +242,7 @@
 	nr_entries = ARRAY_SIZE(debugfs_regs);
 	dw_edma_debugfs_create_x32(debugfs_regs, nr_entries, regs_dir);
 
-	if (dw->mf == EDMA_MF_HDMA_COMPAT) {
+	if (dw->chip->mf == EDMA_MF_HDMA_COMPAT) {
 		nr_entries = ARRAY_SIZE(debugfs_unroll_regs);
 		dw_edma_debugfs_create_x32(debugfs_unroll_regs, nr_entries,
 					   regs_dir);
@@ -282,13 +282,13 @@
 	dw_edma_debugfs_regs_rd(regs_dir);
 }
 
-void dw_edma_v0_debugfs_on(struct dw_edma_chip *chip)
+void dw_edma_v0_debugfs_on(struct dw_edma *_dw)
 {
-	dw = chip->dw;
+	dw = _dw;
 	if (!dw)
 		return;
 
-	regs = dw->rg_region.vaddr;
+	regs = dw->chip->reg_base;
 	if (!regs)
 		return;
 
@@ -296,16 +296,16 @@
 	if (!dw->debugfs)
 		return;
 
-	debugfs_create_u32("mf", 0444, dw->debugfs, &dw->mf);
+	debugfs_create_u32("mf", 0444, dw->debugfs, &dw->chip->mf);
 	debugfs_create_u16("wr_ch_cnt", 0444, dw->debugfs, &dw->wr_ch_cnt);
 	debugfs_create_u16("rd_ch_cnt", 0444, dw->debugfs, &dw->rd_ch_cnt);
 
 	dw_edma_debugfs_regs();
 }
 
-void dw_edma_v0_debugfs_off(struct dw_edma_chip *chip)
+void dw_edma_v0_debugfs_off(struct dw_edma *_dw)
 {
-	dw = chip->dw;
+	dw = _dw;
 	if (!dw)
 		return;
 
diff --git a/drivers/dma/dw-edma/dw-edma-v0-debugfs.h b/drivers/dma/dw-edma/dw-edma-v0-debugfs.h
index d0ff25a..3391b86 100644
--- a/drivers/dma/dw-edma/dw-edma-v0-debugfs.h
+++ b/drivers/dma/dw-edma/dw-edma-v0-debugfs.h
@@ -12,14 +12,14 @@
 #include <linux/dma/edma.h>
 
 #ifdef CONFIG_DEBUG_FS
-void dw_edma_v0_debugfs_on(struct dw_edma_chip *chip);
-void dw_edma_v0_debugfs_off(struct dw_edma_chip *chip);
+void dw_edma_v0_debugfs_on(struct dw_edma *dw);
+void dw_edma_v0_debugfs_off(struct dw_edma *dw);
 #else
-static inline void dw_edma_v0_debugfs_on(struct dw_edma_chip *chip)
+static inline void dw_edma_v0_debugfs_on(struct dw_edma *dw)
 {
 }
 
-static inline void dw_edma_v0_debugfs_off(struct dw_edma_chip *chip)
+static inline void dw_edma_v0_debugfs_off(struct dw_edma *dw)
 {
 }
 #endif /* CONFIG_DEBUG_FS */
diff --git a/drivers/pci/controller/Kconfig b/drivers/pci/controller/Kconfig
index b8d96d3..d1c5fcf 100644
--- a/drivers/pci/controller/Kconfig
+++ b/drivers/pci/controller/Kconfig
@@ -237,7 +237,7 @@
 
 config PCIE_MEDIATEK
 	tristate "MediaTek PCIe controller"
-	depends on ARCH_MEDIATEK || COMPILE_TEST
+	depends on ARCH_AIROHA || ARCH_MEDIATEK || COMPILE_TEST
 	depends on OF
 	depends on PCI_MSI_IRQ_DOMAIN
 	help
@@ -293,7 +293,7 @@
 config PCI_LOONGSON
 	bool "LOONGSON PCI Controller"
 	depends on MACH_LOONGSON64 || COMPILE_TEST
-	depends on OF
+	depends on OF || ACPI
 	depends on PCI_QUIRKS
 	default MACH_LOONGSON64
 	help
diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c
index dfcdeb4..e2a6e18 100644
--- a/drivers/pci/controller/dwc/pci-dra7xx.c
+++ b/drivers/pci/controller/dwc/pci-dra7xx.c
@@ -178,7 +178,7 @@
 	dra7xx_pcie_enable_msi_interrupts(dra7xx);
 }
 
-static int dra7xx_pcie_host_init(struct pcie_port *pp)
+static int dra7xx_pcie_host_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct dra7xx_pcie *dra7xx = to_dra7xx_pcie(pci);
@@ -202,7 +202,7 @@
 	.xlate = pci_irqd_intx_xlate,
 };
 
-static int dra7xx_pcie_handle_msi(struct pcie_port *pp, int index)
+static int dra7xx_pcie_handle_msi(struct dw_pcie_rp *pp, int index)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	unsigned long val;
@@ -224,7 +224,7 @@
 	return 1;
 }
 
-static void dra7xx_pcie_handle_msi_irq(struct pcie_port *pp)
+static void dra7xx_pcie_handle_msi_irq(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	int ret, i, count, num_ctrls;
@@ -255,8 +255,8 @@
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	struct dra7xx_pcie *dra7xx;
+	struct dw_pcie_rp *pp;
 	struct dw_pcie *pci;
-	struct pcie_port *pp;
 	unsigned long reg;
 	u32 bit;
 
@@ -344,7 +344,7 @@
 	return IRQ_HANDLED;
 }
 
-static int dra7xx_pcie_init_irq_domain(struct pcie_port *pp)
+static int dra7xx_pcie_init_irq_domain(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct device *dev = pci->dev;
@@ -475,7 +475,7 @@
 {
 	int ret;
 	struct dw_pcie *pci = dra7xx->pci;
-	struct pcie_port *pp = &pci->pp;
+	struct dw_pcie_rp *pp = &pci->pp;
 	struct device *dev = pci->dev;
 
 	pp->irq = platform_get_irq(pdev, 1);
@@ -483,7 +483,7 @@
 		return pp->irq;
 
 	/* MSI IRQ is muxed */
-	pp->msi_irq = -ENODEV;
+	pp->msi_irq[0] = -ENODEV;
 
 	ret = dra7xx_pcie_init_irq_domain(pp);
 	if (ret < 0)
diff --git a/drivers/pci/controller/dwc/pci-exynos.c b/drivers/pci/controller/dwc/pci-exynos.c
index 467c8d1..3786946 100644
--- a/drivers/pci/controller/dwc/pci-exynos.c
+++ b/drivers/pci/controller/dwc/pci-exynos.c
@@ -249,7 +249,7 @@
 	return (val & PCIE_ELBI_XMLH_LINKUP);
 }
 
-static int exynos_pcie_host_init(struct pcie_port *pp)
+static int exynos_pcie_host_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct exynos_pcie *ep = to_exynos_pcie(pci);
@@ -258,9 +258,8 @@
 
 	exynos_pcie_assert_core_reset(ep);
 
-	phy_reset(ep->phy);
-	phy_power_on(ep->phy);
 	phy_init(ep->phy);
+	phy_power_on(ep->phy);
 
 	exynos_pcie_deassert_core_reset(ep);
 	exynos_pcie_enable_irq_pulse(ep);
@@ -276,7 +275,7 @@
 				       struct platform_device *pdev)
 {
 	struct dw_pcie *pci = &ep->pci;
-	struct pcie_port *pp = &pci->pp;
+	struct dw_pcie_rp *pp = &pci->pp;
 	struct device *dev = &pdev->dev;
 	int ret;
 
@@ -292,7 +291,7 @@
 	}
 
 	pp->ops = &exynos_pcie_host_ops;
-	pp->msi_irq = -ENODEV;
+	pp->msi_irq[0] = -ENODEV;
 
 	ret = dw_pcie_host_init(pp);
 	if (ret) {
@@ -406,7 +405,7 @@
 {
 	struct exynos_pcie *ep = dev_get_drvdata(dev);
 	struct dw_pcie *pci = &ep->pci;
-	struct pcie_port *pp = &pci->pp;
+	struct dw_pcie_rp *pp = &pci->pp;
 	int ret;
 
 	ret = regulator_bulk_enable(ARRAY_SIZE(ep->supplies), ep->supplies);
diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
index 7a285fb..6e5debdb 100644
--- a/drivers/pci/controller/dwc/pci-imx6.c
+++ b/drivers/pci/controller/dwc/pci-imx6.c
@@ -67,6 +67,7 @@
 	struct dw_pcie		*pci;
 	int			reset_gpio;
 	bool			gpio_active_high;
+	bool			link_is_up;
 	struct clk		*pcie_bus;
 	struct clk		*pcie_phy;
 	struct clk		*pcie_inbound_axi;
@@ -146,6 +147,31 @@
 #define PHY_RX_OVRD_IN_LO_RX_DATA_EN		BIT(5)
 #define PHY_RX_OVRD_IN_LO_RX_PLL_EN		BIT(3)
 
+static unsigned int imx6_pcie_grp_offset(const struct imx6_pcie *imx6_pcie)
+{
+	WARN_ON(imx6_pcie->drvdata->variant != IMX8MQ &&
+		imx6_pcie->drvdata->variant != IMX8MM);
+	return imx6_pcie->controller_id == 1 ? IOMUXC_GPR16 : IOMUXC_GPR14;
+}
+
+static void imx6_pcie_configure_type(struct imx6_pcie *imx6_pcie)
+{
+	unsigned int mask, val;
+
+	if (imx6_pcie->drvdata->variant == IMX8MQ &&
+	    imx6_pcie->controller_id == 1) {
+		mask = IMX8MQ_GPR12_PCIE2_CTRL_DEVICE_TYPE;
+		val  = FIELD_PREP(IMX8MQ_GPR12_PCIE2_CTRL_DEVICE_TYPE,
+				  PCI_EXP_TYPE_ROOT_PORT);
+	} else {
+		mask = IMX6Q_GPR12_DEVICE_TYPE;
+		val  = FIELD_PREP(IMX6Q_GPR12_DEVICE_TYPE,
+				  PCI_EXP_TYPE_ROOT_PORT);
+	}
+
+	regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, mask, val);
+}
+
 static int pcie_phy_poll_ack(struct imx6_pcie *imx6_pcie, bool exp_val)
 {
 	struct dw_pcie *pci = imx6_pcie->pci;
@@ -271,6 +297,134 @@
 	return 0;
 }
 
+static void imx6_pcie_init_phy(struct imx6_pcie *imx6_pcie)
+{
+	switch (imx6_pcie->drvdata->variant) {
+	case IMX8MM:
+		/*
+		 * The PHY initialization had been done in the PHY
+		 * driver, break here directly.
+		 */
+		break;
+	case IMX8MQ:
+		/*
+		 * TODO: Currently this code assumes external
+		 * oscillator is being used
+		 */
+		regmap_update_bits(imx6_pcie->iomuxc_gpr,
+				   imx6_pcie_grp_offset(imx6_pcie),
+				   IMX8MQ_GPR_PCIE_REF_USE_PAD,
+				   IMX8MQ_GPR_PCIE_REF_USE_PAD);
+		/*
+		 * Regarding the datasheet, the PCIE_VPH is suggested
+		 * to be 1.8V. If the PCIE_VPH is supplied by 3.3V, the
+		 * VREG_BYPASS should be cleared to zero.
+		 */
+		if (imx6_pcie->vph &&
+		    regulator_get_voltage(imx6_pcie->vph) > 3000000)
+			regmap_update_bits(imx6_pcie->iomuxc_gpr,
+					   imx6_pcie_grp_offset(imx6_pcie),
+					   IMX8MQ_GPR_PCIE_VREG_BYPASS,
+					   0);
+		break;
+	case IMX7D:
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
+				   IMX7D_GPR12_PCIE_PHY_REFCLK_SEL, 0);
+		break;
+	case IMX6SX:
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
+				   IMX6SX_GPR12_PCIE_RX_EQ_MASK,
+				   IMX6SX_GPR12_PCIE_RX_EQ_2);
+		fallthrough;
+	default:
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
+				   IMX6Q_GPR12_PCIE_CTL_2, 0 << 10);
+
+		/* configure constant input signal to the pcie ctrl and phy */
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
+				   IMX6Q_GPR12_LOS_LEVEL, 9 << 4);
+
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8,
+				   IMX6Q_GPR8_TX_DEEMPH_GEN1,
+				   imx6_pcie->tx_deemph_gen1 << 0);
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8,
+				   IMX6Q_GPR8_TX_DEEMPH_GEN2_3P5DB,
+				   imx6_pcie->tx_deemph_gen2_3p5db << 6);
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8,
+				   IMX6Q_GPR8_TX_DEEMPH_GEN2_6DB,
+				   imx6_pcie->tx_deemph_gen2_6db << 12);
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8,
+				   IMX6Q_GPR8_TX_SWING_FULL,
+				   imx6_pcie->tx_swing_full << 18);
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8,
+				   IMX6Q_GPR8_TX_SWING_LOW,
+				   imx6_pcie->tx_swing_low << 25);
+		break;
+	}
+
+	imx6_pcie_configure_type(imx6_pcie);
+}
+
+static void imx7d_pcie_wait_for_phy_pll_lock(struct imx6_pcie *imx6_pcie)
+{
+	u32 val;
+	struct device *dev = imx6_pcie->pci->dev;
+
+	if (regmap_read_poll_timeout(imx6_pcie->iomuxc_gpr,
+				     IOMUXC_GPR22, val,
+				     val & IMX7D_GPR22_PCIE_PHY_PLL_LOCKED,
+				     PHY_PLL_LOCK_WAIT_USLEEP_MAX,
+				     PHY_PLL_LOCK_WAIT_TIMEOUT))
+		dev_err(dev, "PCIe PLL lock timeout\n");
+}
+
+static int imx6_setup_phy_mpll(struct imx6_pcie *imx6_pcie)
+{
+	unsigned long phy_rate = clk_get_rate(imx6_pcie->pcie_phy);
+	int mult, div;
+	u16 val;
+
+	if (!(imx6_pcie->drvdata->flags & IMX6_PCIE_FLAG_IMX6_PHY))
+		return 0;
+
+	switch (phy_rate) {
+	case 125000000:
+		/*
+		 * The default settings of the MPLL are for a 125MHz input
+		 * clock, so no need to reconfigure anything in that case.
+		 */
+		return 0;
+	case 100000000:
+		mult = 25;
+		div = 0;
+		break;
+	case 200000000:
+		mult = 25;
+		div = 1;
+		break;
+	default:
+		dev_err(imx6_pcie->pci->dev,
+			"Unsupported PHY reference clock rate %lu\n", phy_rate);
+		return -EINVAL;
+	}
+
+	pcie_phy_read(imx6_pcie, PCIE_PHY_MPLL_OVRD_IN_LO, &val);
+	val &= ~(PCIE_PHY_MPLL_MULTIPLIER_MASK <<
+		 PCIE_PHY_MPLL_MULTIPLIER_SHIFT);
+	val |= mult << PCIE_PHY_MPLL_MULTIPLIER_SHIFT;
+	val |= PCIE_PHY_MPLL_MULTIPLIER_OVRD;
+	pcie_phy_write(imx6_pcie, PCIE_PHY_MPLL_OVRD_IN_LO, val);
+
+	pcie_phy_read(imx6_pcie, PCIE_PHY_ATEOVRD, &val);
+	val &= ~(PCIE_PHY_ATEOVRD_REF_CLKDIV_MASK <<
+		 PCIE_PHY_ATEOVRD_REF_CLKDIV_SHIFT);
+	val |= div << PCIE_PHY_ATEOVRD_REF_CLKDIV_SHIFT;
+	val |= PCIE_PHY_ATEOVRD_EN;
+	pcie_phy_write(imx6_pcie, PCIE_PHY_ATEOVRD, val);
+
+	return 0;
+}
+
 static void imx6_pcie_reset_phy(struct imx6_pcie *imx6_pcie)
 {
 	u16 tmp;
@@ -367,61 +521,6 @@
 	return 0;
 }
 
-static void imx6_pcie_assert_core_reset(struct imx6_pcie *imx6_pcie)
-{
-	struct device *dev = imx6_pcie->pci->dev;
-
-	switch (imx6_pcie->drvdata->variant) {
-	case IMX7D:
-	case IMX8MQ:
-		reset_control_assert(imx6_pcie->pciephy_reset);
-		fallthrough;
-	case IMX8MM:
-		reset_control_assert(imx6_pcie->apps_reset);
-		break;
-	case IMX6SX:
-		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
-				   IMX6SX_GPR12_PCIE_TEST_POWERDOWN,
-				   IMX6SX_GPR12_PCIE_TEST_POWERDOWN);
-		/* Force PCIe PHY reset */
-		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR5,
-				   IMX6SX_GPR5_PCIE_BTNRST_RESET,
-				   IMX6SX_GPR5_PCIE_BTNRST_RESET);
-		break;
-	case IMX6QP:
-		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
-				   IMX6Q_GPR1_PCIE_SW_RST,
-				   IMX6Q_GPR1_PCIE_SW_RST);
-		break;
-	case IMX6Q:
-		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
-				   IMX6Q_GPR1_PCIE_TEST_PD, 1 << 18);
-		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
-				   IMX6Q_GPR1_PCIE_REF_CLK_EN, 0 << 16);
-		break;
-	}
-
-	if (imx6_pcie->vpcie && regulator_is_enabled(imx6_pcie->vpcie) > 0) {
-		int ret = regulator_disable(imx6_pcie->vpcie);
-
-		if (ret)
-			dev_err(dev, "failed to disable vpcie regulator: %d\n",
-				ret);
-	}
-
-	/* Some boards don't have PCIe reset GPIO. */
-	if (gpio_is_valid(imx6_pcie->reset_gpio))
-		gpio_set_value_cansleep(imx6_pcie->reset_gpio,
-					imx6_pcie->gpio_active_high);
-}
-
-static unsigned int imx6_pcie_grp_offset(const struct imx6_pcie *imx6_pcie)
-{
-	WARN_ON(imx6_pcie->drvdata->variant != IMX8MQ &&
-		imx6_pcie->drvdata->variant != IMX8MM);
-	return imx6_pcie->controller_id == 1 ? IOMUXC_GPR16 : IOMUXC_GPR14;
-}
-
 static int imx6_pcie_enable_ref_clk(struct imx6_pcie *imx6_pcie)
 {
 	struct dw_pcie *pci = imx6_pcie->pci;
@@ -482,38 +581,44 @@
 	return ret;
 }
 
-static void imx7d_pcie_wait_for_phy_pll_lock(struct imx6_pcie *imx6_pcie)
+static void imx6_pcie_disable_ref_clk(struct imx6_pcie *imx6_pcie)
 {
-	u32 val;
-	struct device *dev = imx6_pcie->pci->dev;
-
-	if (regmap_read_poll_timeout(imx6_pcie->iomuxc_gpr,
-				     IOMUXC_GPR22, val,
-				     val & IMX7D_GPR22_PCIE_PHY_PLL_LOCKED,
-				     PHY_PLL_LOCK_WAIT_USLEEP_MAX,
-				     PHY_PLL_LOCK_WAIT_TIMEOUT))
-		dev_err(dev, "PCIe PLL lock timeout\n");
+	switch (imx6_pcie->drvdata->variant) {
+	case IMX6SX:
+		clk_disable_unprepare(imx6_pcie->pcie_inbound_axi);
+		break;
+	case IMX6QP:
+	case IMX6Q:
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
+				IMX6Q_GPR1_PCIE_REF_CLK_EN, 0);
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
+				IMX6Q_GPR1_PCIE_TEST_PD,
+				IMX6Q_GPR1_PCIE_TEST_PD);
+		break;
+	case IMX7D:
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
+				   IMX7D_GPR12_PCIE_PHY_REFCLK_SEL,
+				   IMX7D_GPR12_PCIE_PHY_REFCLK_SEL);
+		break;
+	case IMX8MM:
+	case IMX8MQ:
+		clk_disable_unprepare(imx6_pcie->pcie_aux);
+		break;
+	default:
+		break;
+	}
 }
 
-static void imx6_pcie_deassert_core_reset(struct imx6_pcie *imx6_pcie)
+static int imx6_pcie_clk_enable(struct imx6_pcie *imx6_pcie)
 {
 	struct dw_pcie *pci = imx6_pcie->pci;
 	struct device *dev = pci->dev;
 	int ret;
 
-	if (imx6_pcie->vpcie && !regulator_is_enabled(imx6_pcie->vpcie)) {
-		ret = regulator_enable(imx6_pcie->vpcie);
-		if (ret) {
-			dev_err(dev, "failed to enable vpcie regulator: %d\n",
-				ret);
-			return;
-		}
-	}
-
 	ret = clk_prepare_enable(imx6_pcie->pcie_phy);
 	if (ret) {
 		dev_err(dev, "unable to enable pcie_phy clock\n");
-		goto err_pcie_phy;
+		return ret;
 	}
 
 	ret = clk_prepare_enable(imx6_pcie->pcie_bus);
@@ -534,25 +639,75 @@
 		goto err_ref_clk;
 	}
 
-	switch (imx6_pcie->drvdata->variant) {
-	case IMX8MM:
-		if (phy_power_on(imx6_pcie->phy))
-			dev_err(dev, "unable to power on PHY\n");
-		break;
-	default:
-		break;
-	}
 	/* allow the clocks to stabilize */
 	usleep_range(200, 500);
+	return 0;
+
+err_ref_clk:
+	clk_disable_unprepare(imx6_pcie->pcie);
+err_pcie:
+	clk_disable_unprepare(imx6_pcie->pcie_bus);
+err_pcie_bus:
+	clk_disable_unprepare(imx6_pcie->pcie_phy);
+
+	return ret;
+}
+
+static void imx6_pcie_clk_disable(struct imx6_pcie *imx6_pcie)
+{
+	imx6_pcie_disable_ref_clk(imx6_pcie);
+	clk_disable_unprepare(imx6_pcie->pcie);
+	clk_disable_unprepare(imx6_pcie->pcie_bus);
+	clk_disable_unprepare(imx6_pcie->pcie_phy);
+}
+
+static void imx6_pcie_assert_core_reset(struct imx6_pcie *imx6_pcie)
+{
+	switch (imx6_pcie->drvdata->variant) {
+	case IMX7D:
+	case IMX8MQ:
+		reset_control_assert(imx6_pcie->pciephy_reset);
+		fallthrough;
+	case IMX8MM:
+		reset_control_assert(imx6_pcie->apps_reset);
+		break;
+	case IMX6SX:
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
+				   IMX6SX_GPR12_PCIE_TEST_POWERDOWN,
+				   IMX6SX_GPR12_PCIE_TEST_POWERDOWN);
+		/* Force PCIe PHY reset */
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR5,
+				   IMX6SX_GPR5_PCIE_BTNRST_RESET,
+				   IMX6SX_GPR5_PCIE_BTNRST_RESET);
+		break;
+	case IMX6QP:
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
+				   IMX6Q_GPR1_PCIE_SW_RST,
+				   IMX6Q_GPR1_PCIE_SW_RST);
+		break;
+	case IMX6Q:
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
+				   IMX6Q_GPR1_PCIE_TEST_PD, 1 << 18);
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR1,
+				   IMX6Q_GPR1_PCIE_REF_CLK_EN, 0 << 16);
+		break;
+	}
+
+	/* Some boards don't have PCIe reset GPIO. */
+	if (gpio_is_valid(imx6_pcie->reset_gpio))
+		gpio_set_value_cansleep(imx6_pcie->reset_gpio,
+					imx6_pcie->gpio_active_high);
+}
+
+static int imx6_pcie_deassert_core_reset(struct imx6_pcie *imx6_pcie)
+{
+	struct dw_pcie *pci = imx6_pcie->pci;
+	struct device *dev = pci->dev;
 
 	switch (imx6_pcie->drvdata->variant) {
 	case IMX8MQ:
 		reset_control_deassert(imx6_pcie->pciephy_reset);
 		break;
-	case IMX8MM:
-		if (phy_init(imx6_pcie->phy))
-			dev_err(dev, "waiting for phy ready timeout!\n");
-		break;
 	case IMX7D:
 		reset_control_deassert(imx6_pcie->pciephy_reset);
 
@@ -588,6 +743,7 @@
 		usleep_range(200, 500);
 		break;
 	case IMX6Q:		/* Nothing to do */
+	case IMX8MM:
 		break;
 	}
 
@@ -600,153 +756,6 @@
 		msleep(100);
 	}
 
-	return;
-
-err_ref_clk:
-	clk_disable_unprepare(imx6_pcie->pcie);
-err_pcie:
-	clk_disable_unprepare(imx6_pcie->pcie_bus);
-err_pcie_bus:
-	clk_disable_unprepare(imx6_pcie->pcie_phy);
-err_pcie_phy:
-	if (imx6_pcie->vpcie && regulator_is_enabled(imx6_pcie->vpcie) > 0) {
-		ret = regulator_disable(imx6_pcie->vpcie);
-		if (ret)
-			dev_err(dev, "failed to disable vpcie regulator: %d\n",
-				ret);
-	}
-}
-
-static void imx6_pcie_configure_type(struct imx6_pcie *imx6_pcie)
-{
-	unsigned int mask, val;
-
-	if (imx6_pcie->drvdata->variant == IMX8MQ &&
-	    imx6_pcie->controller_id == 1) {
-		mask   = IMX8MQ_GPR12_PCIE2_CTRL_DEVICE_TYPE;
-		val    = FIELD_PREP(IMX8MQ_GPR12_PCIE2_CTRL_DEVICE_TYPE,
-				    PCI_EXP_TYPE_ROOT_PORT);
-	} else {
-		mask = IMX6Q_GPR12_DEVICE_TYPE;
-		val  = FIELD_PREP(IMX6Q_GPR12_DEVICE_TYPE,
-				  PCI_EXP_TYPE_ROOT_PORT);
-	}
-
-	regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12, mask, val);
-}
-
-static void imx6_pcie_init_phy(struct imx6_pcie *imx6_pcie)
-{
-	switch (imx6_pcie->drvdata->variant) {
-	case IMX8MM:
-		/*
-		 * The PHY initialization had been done in the PHY
-		 * driver, break here directly.
-		 */
-		break;
-	case IMX8MQ:
-		/*
-		 * TODO: Currently this code assumes external
-		 * oscillator is being used
-		 */
-		regmap_update_bits(imx6_pcie->iomuxc_gpr,
-				   imx6_pcie_grp_offset(imx6_pcie),
-				   IMX8MQ_GPR_PCIE_REF_USE_PAD,
-				   IMX8MQ_GPR_PCIE_REF_USE_PAD);
-		/*
-		 * Regarding the datasheet, the PCIE_VPH is suggested
-		 * to be 1.8V. If the PCIE_VPH is supplied by 3.3V, the
-		 * VREG_BYPASS should be cleared to zero.
-		 */
-		if (imx6_pcie->vph &&
-		    regulator_get_voltage(imx6_pcie->vph) > 3000000)
-			regmap_update_bits(imx6_pcie->iomuxc_gpr,
-					   imx6_pcie_grp_offset(imx6_pcie),
-					   IMX8MQ_GPR_PCIE_VREG_BYPASS,
-					   0);
-		break;
-	case IMX7D:
-		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
-				   IMX7D_GPR12_PCIE_PHY_REFCLK_SEL, 0);
-		break;
-	case IMX6SX:
-		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
-				   IMX6SX_GPR12_PCIE_RX_EQ_MASK,
-				   IMX6SX_GPR12_PCIE_RX_EQ_2);
-		fallthrough;
-	default:
-		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
-				   IMX6Q_GPR12_PCIE_CTL_2, 0 << 10);
-
-		/* configure constant input signal to the pcie ctrl and phy */
-		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
-				   IMX6Q_GPR12_LOS_LEVEL, 9 << 4);
-
-		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8,
-				   IMX6Q_GPR8_TX_DEEMPH_GEN1,
-				   imx6_pcie->tx_deemph_gen1 << 0);
-		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8,
-				   IMX6Q_GPR8_TX_DEEMPH_GEN2_3P5DB,
-				   imx6_pcie->tx_deemph_gen2_3p5db << 6);
-		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8,
-				   IMX6Q_GPR8_TX_DEEMPH_GEN2_6DB,
-				   imx6_pcie->tx_deemph_gen2_6db << 12);
-		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8,
-				   IMX6Q_GPR8_TX_SWING_FULL,
-				   imx6_pcie->tx_swing_full << 18);
-		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR8,
-				   IMX6Q_GPR8_TX_SWING_LOW,
-				   imx6_pcie->tx_swing_low << 25);
-		break;
-	}
-
-	imx6_pcie_configure_type(imx6_pcie);
-}
-
-static int imx6_setup_phy_mpll(struct imx6_pcie *imx6_pcie)
-{
-	unsigned long phy_rate = clk_get_rate(imx6_pcie->pcie_phy);
-	int mult, div;
-	u16 val;
-
-	if (!(imx6_pcie->drvdata->flags & IMX6_PCIE_FLAG_IMX6_PHY))
-		return 0;
-
-	switch (phy_rate) {
-	case 125000000:
-		/*
-		 * The default settings of the MPLL are for a 125MHz input
-		 * clock, so no need to reconfigure anything in that case.
-		 */
-		return 0;
-	case 100000000:
-		mult = 25;
-		div = 0;
-		break;
-	case 200000000:
-		mult = 25;
-		div = 1;
-		break;
-	default:
-		dev_err(imx6_pcie->pci->dev,
-			"Unsupported PHY reference clock rate %lu\n", phy_rate);
-		return -EINVAL;
-	}
-
-	pcie_phy_read(imx6_pcie, PCIE_PHY_MPLL_OVRD_IN_LO, &val);
-	val &= ~(PCIE_PHY_MPLL_MULTIPLIER_MASK <<
-		 PCIE_PHY_MPLL_MULTIPLIER_SHIFT);
-	val |= mult << PCIE_PHY_MPLL_MULTIPLIER_SHIFT;
-	val |= PCIE_PHY_MPLL_MULTIPLIER_OVRD;
-	pcie_phy_write(imx6_pcie, PCIE_PHY_MPLL_OVRD_IN_LO, val);
-
-	pcie_phy_read(imx6_pcie, PCIE_PHY_ATEOVRD, &val);
-	val &= ~(PCIE_PHY_ATEOVRD_REF_CLKDIV_MASK <<
-		 PCIE_PHY_ATEOVRD_REF_CLKDIV_SHIFT);
-	val |= div << PCIE_PHY_ATEOVRD_REF_CLKDIV_SHIFT;
-	val |= PCIE_PHY_ATEOVRD_EN;
-	pcie_phy_write(imx6_pcie, PCIE_PHY_ATEOVRD, val);
-
 	return 0;
 }
 
@@ -789,6 +798,25 @@
 	}
 }
 
+static void imx6_pcie_ltssm_disable(struct device *dev)
+{
+	struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev);
+
+	switch (imx6_pcie->drvdata->variant) {
+	case IMX6Q:
+	case IMX6SX:
+	case IMX6QP:
+		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
+				   IMX6Q_GPR12_PCIE_CTL_2, 0);
+		break;
+	case IMX7D:
+	case IMX8MQ:
+	case IMX8MM:
+		reset_control_assert(imx6_pcie->apps_reset);
+		break;
+	}
+}
+
 static int imx6_pcie_start_link(struct dw_pcie *pci)
 {
 	struct imx6_pcie *imx6_pcie = to_imx6_pcie(pci);
@@ -802,21 +830,26 @@
 	 * started in Gen2 mode, there is a possibility the devices on the
 	 * bus will not be detected at all.  This happens with PCIe switches.
 	 */
+	dw_pcie_dbi_ro_wr_en(pci);
 	tmp = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP);
 	tmp &= ~PCI_EXP_LNKCAP_SLS;
 	tmp |= PCI_EXP_LNKCAP_SLS_2_5GB;
 	dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCAP, tmp);
+	dw_pcie_dbi_ro_wr_dis(pci);
 
 	/* Start LTSSM. */
 	imx6_pcie_ltssm_enable(dev);
 
-	dw_pcie_wait_for_link(pci);
+	ret = dw_pcie_wait_for_link(pci);
+	if (ret)
+		goto err_reset_phy;
 
-	if (pci->link_gen == 2) {
-		/* Allow Gen2 mode after the link is up. */
+	if (pci->link_gen > 1) {
+		/* Allow faster modes after the link is up */
+		dw_pcie_dbi_ro_wr_en(pci);
 		tmp = dw_pcie_readl_dbi(pci, offset + PCI_EXP_LNKCAP);
 		tmp &= ~PCI_EXP_LNKCAP_SLS;
-		tmp |= PCI_EXP_LNKCAP_SLS_5_0GB;
+		tmp |= pci->link_gen;
 		dw_pcie_writel_dbi(pci, offset + PCI_EXP_LNKCAP, tmp);
 
 		/*
@@ -826,6 +859,7 @@
 		tmp = dw_pcie_readl_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL);
 		tmp |= PORT_LOGIC_SPEED_CHANGE;
 		dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, tmp);
+		dw_pcie_dbi_ro_wr_dis(pci);
 
 		if (imx6_pcie->drvdata->flags &
 		    IMX6_PCIE_FLAG_IMX6_SPEED_CHANGE) {
@@ -846,34 +880,110 @@
 		}
 
 		/* Make sure link training is finished as well! */
-		dw_pcie_wait_for_link(pci);
+		ret = dw_pcie_wait_for_link(pci);
+		if (ret)
+			goto err_reset_phy;
 	} else {
-		dev_info(dev, "Link: Gen2 disabled\n");
+		dev_info(dev, "Link: Only Gen1 is enabled\n");
 	}
 
+	imx6_pcie->link_is_up = true;
 	tmp = dw_pcie_readw_dbi(pci, offset + PCI_EXP_LNKSTA);
 	dev_info(dev, "Link up, Gen%i\n", tmp & PCI_EXP_LNKSTA_CLS);
 	return 0;
 
 err_reset_phy:
+	imx6_pcie->link_is_up = false;
 	dev_dbg(dev, "PHY DEBUG_R0=0x%08x DEBUG_R1=0x%08x\n",
 		dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG0),
 		dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG1));
 	imx6_pcie_reset_phy(imx6_pcie);
+	return 0;
+}
+
+static void imx6_pcie_stop_link(struct dw_pcie *pci)
+{
+	struct device *dev = pci->dev;
+
+	/* Turn off PCIe LTSSM */
+	imx6_pcie_ltssm_disable(dev);
+}
+
+static int imx6_pcie_host_init(struct dw_pcie_rp *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct device *dev = pci->dev;
+	struct imx6_pcie *imx6_pcie = to_imx6_pcie(pci);
+	int ret;
+
+	if (imx6_pcie->vpcie) {
+		ret = regulator_enable(imx6_pcie->vpcie);
+		if (ret) {
+			dev_err(dev, "failed to enable vpcie regulator: %d\n",
+				ret);
+			return ret;
+		}
+	}
+
+	imx6_pcie_assert_core_reset(imx6_pcie);
+	imx6_pcie_init_phy(imx6_pcie);
+
+	ret = imx6_pcie_clk_enable(imx6_pcie);
+	if (ret) {
+		dev_err(dev, "unable to enable pcie clocks: %d\n", ret);
+		goto err_reg_disable;
+	}
+
+	if (imx6_pcie->phy) {
+		ret = phy_power_on(imx6_pcie->phy);
+		if (ret) {
+			dev_err(dev, "pcie PHY power up failed\n");
+			goto err_clk_disable;
+		}
+	}
+
+	ret = imx6_pcie_deassert_core_reset(imx6_pcie);
+	if (ret < 0) {
+		dev_err(dev, "pcie deassert core reset failed: %d\n", ret);
+		goto err_phy_off;
+	}
+
+	if (imx6_pcie->phy) {
+		ret = phy_init(imx6_pcie->phy);
+		if (ret) {
+			dev_err(dev, "waiting for PHY ready timeout!\n");
+			goto err_phy_off;
+		}
+	}
+	imx6_setup_phy_mpll(imx6_pcie);
+
+	return 0;
+
+err_phy_off:
+	if (imx6_pcie->phy)
+		phy_power_off(imx6_pcie->phy);
+err_clk_disable:
+	imx6_pcie_clk_disable(imx6_pcie);
+err_reg_disable:
+	if (imx6_pcie->vpcie)
+		regulator_disable(imx6_pcie->vpcie);
 	return ret;
 }
 
-static int imx6_pcie_host_init(struct pcie_port *pp)
+static void imx6_pcie_host_exit(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct imx6_pcie *imx6_pcie = to_imx6_pcie(pci);
 
-	imx6_pcie_assert_core_reset(imx6_pcie);
-	imx6_pcie_init_phy(imx6_pcie);
-	imx6_pcie_deassert_core_reset(imx6_pcie);
-	imx6_setup_phy_mpll(imx6_pcie);
+	if (imx6_pcie->phy) {
+		if (phy_power_off(imx6_pcie->phy))
+			dev_err(pci->dev, "unable to power off PHY\n");
+		phy_exit(imx6_pcie->phy);
+	}
+	imx6_pcie_clk_disable(imx6_pcie);
 
-	return 0;
+	if (imx6_pcie->vpcie)
+		regulator_disable(imx6_pcie->vpcie);
 }
 
 static const struct dw_pcie_host_ops imx6_pcie_host_ops = {
@@ -884,26 +994,6 @@
 	.start_link = imx6_pcie_start_link,
 };
 
-#ifdef CONFIG_PM_SLEEP
-static void imx6_pcie_ltssm_disable(struct device *dev)
-{
-	struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev);
-
-	switch (imx6_pcie->drvdata->variant) {
-	case IMX6SX:
-	case IMX6QP:
-		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
-				   IMX6Q_GPR12_PCIE_CTL_2, 0);
-		break;
-	case IMX7D:
-	case IMX8MM:
-		reset_control_assert(imx6_pcie->apps_reset);
-		break;
-	default:
-		dev_err(dev, "ltssm_disable not supported\n");
-	}
-}
-
 static void imx6_pcie_pm_turnoff(struct imx6_pcie *imx6_pcie)
 {
 	struct device *dev = imx6_pcie->pci->dev;
@@ -941,49 +1031,17 @@
 	usleep_range(1000, 10000);
 }
 
-static void imx6_pcie_clk_disable(struct imx6_pcie *imx6_pcie)
-{
-	clk_disable_unprepare(imx6_pcie->pcie);
-	clk_disable_unprepare(imx6_pcie->pcie_phy);
-	clk_disable_unprepare(imx6_pcie->pcie_bus);
-
-	switch (imx6_pcie->drvdata->variant) {
-	case IMX6SX:
-		clk_disable_unprepare(imx6_pcie->pcie_inbound_axi);
-		break;
-	case IMX7D:
-		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
-				   IMX7D_GPR12_PCIE_PHY_REFCLK_SEL,
-				   IMX7D_GPR12_PCIE_PHY_REFCLK_SEL);
-		break;
-	case IMX8MQ:
-	case IMX8MM:
-		clk_disable_unprepare(imx6_pcie->pcie_aux);
-		break;
-	default:
-		break;
-	}
-}
-
 static int imx6_pcie_suspend_noirq(struct device *dev)
 {
 	struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev);
+	struct dw_pcie_rp *pp = &imx6_pcie->pci->pp;
 
 	if (!(imx6_pcie->drvdata->flags & IMX6_PCIE_FLAG_SUPPORTS_SUSPEND))
 		return 0;
 
 	imx6_pcie_pm_turnoff(imx6_pcie);
-	imx6_pcie_ltssm_disable(dev);
-	imx6_pcie_clk_disable(imx6_pcie);
-	switch (imx6_pcie->drvdata->variant) {
-	case IMX8MM:
-		if (phy_power_off(imx6_pcie->phy))
-			dev_err(dev, "unable to power off PHY\n");
-		phy_exit(imx6_pcie->phy);
-		break;
-	default:
-		break;
-	}
+	imx6_pcie_stop_link(imx6_pcie->pci);
+	imx6_pcie_host_exit(pp);
 
 	return 0;
 }
@@ -992,27 +1050,25 @@
 {
 	int ret;
 	struct imx6_pcie *imx6_pcie = dev_get_drvdata(dev);
-	struct pcie_port *pp = &imx6_pcie->pci->pp;
+	struct dw_pcie_rp *pp = &imx6_pcie->pci->pp;
 
 	if (!(imx6_pcie->drvdata->flags & IMX6_PCIE_FLAG_SUPPORTS_SUSPEND))
 		return 0;
 
-	imx6_pcie_assert_core_reset(imx6_pcie);
-	imx6_pcie_init_phy(imx6_pcie);
-	imx6_pcie_deassert_core_reset(imx6_pcie);
+	ret = imx6_pcie_host_init(pp);
+	if (ret)
+		return ret;
 	dw_pcie_setup_rc(pp);
 
-	ret = imx6_pcie_start_link(imx6_pcie->pci);
-	if (ret < 0)
-		dev_info(dev, "pcie link is down after resume.\n");
+	if (imx6_pcie->link_is_up)
+		imx6_pcie_start_link(imx6_pcie->pci);
 
 	return 0;
 }
-#endif
 
 static const struct dev_pm_ops imx6_pcie_pm_ops = {
-	SET_NOIRQ_SYSTEM_SLEEP_PM_OPS(imx6_pcie_suspend_noirq,
-				      imx6_pcie_resume_noirq)
+	NOIRQ_SYSTEM_SLEEP_PM_OPS(imx6_pcie_suspend_noirq,
+				  imx6_pcie_resume_noirq)
 };
 
 static int imx6_pcie_probe(struct platform_device *pdev)
@@ -1291,7 +1347,7 @@
 static void imx6_pcie_quirk(struct pci_dev *dev)
 {
 	struct pci_bus *bus = dev->bus;
-	struct pcie_port *pp = bus->sysdata;
+	struct dw_pcie_rp *pp = bus->sysdata;
 
 	/* Bus parent is the PCI bridge, its parent is this platform driver */
 	if (!bus->dev.parent || !bus->dev.parent->parent)
diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
index d10e5fd..2a9bbde 100644
--- a/drivers/pci/controller/dwc/pci-keystone.c
+++ b/drivers/pci/controller/dwc/pci-keystone.c
@@ -109,7 +109,7 @@
 	enum dw_pcie_device_mode mode;
 	const struct dw_pcie_host_ops *host_ops;
 	const struct dw_pcie_ep_ops *ep_ops;
-	unsigned int version;
+	u32 version;
 };
 
 struct keystone_pcie {
@@ -147,7 +147,7 @@
 
 static void ks_pcie_msi_irq_ack(struct irq_data *data)
 {
-	struct pcie_port *pp  = irq_data_get_irq_chip_data(data);
+	struct dw_pcie_rp *pp  = irq_data_get_irq_chip_data(data);
 	struct keystone_pcie *ks_pcie;
 	u32 irq = data->hwirq;
 	struct dw_pcie *pci;
@@ -167,7 +167,7 @@
 
 static void ks_pcie_compose_msi_msg(struct irq_data *data, struct msi_msg *msg)
 {
-	struct pcie_port *pp = irq_data_get_irq_chip_data(data);
+	struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(data);
 	struct keystone_pcie *ks_pcie;
 	struct dw_pcie *pci;
 	u64 msi_target;
@@ -192,7 +192,7 @@
 
 static void ks_pcie_msi_mask(struct irq_data *data)
 {
-	struct pcie_port *pp = irq_data_get_irq_chip_data(data);
+	struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(data);
 	struct keystone_pcie *ks_pcie;
 	u32 irq = data->hwirq;
 	struct dw_pcie *pci;
@@ -216,7 +216,7 @@
 
 static void ks_pcie_msi_unmask(struct irq_data *data)
 {
-	struct pcie_port *pp = irq_data_get_irq_chip_data(data);
+	struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(data);
 	struct keystone_pcie *ks_pcie;
 	u32 irq = data->hwirq;
 	struct dw_pcie *pci;
@@ -247,7 +247,7 @@
 	.irq_unmask = ks_pcie_msi_unmask,
 };
 
-static int ks_pcie_msi_host_init(struct pcie_port *pp)
+static int ks_pcie_msi_host_init(struct dw_pcie_rp *pp)
 {
 	pp->msi_irq_chip = &ks_pcie_msi_irq_chip;
 	return dw_pcie_allocate_domains(pp);
@@ -390,7 +390,7 @@
 	u32 val;
 	u32 num_viewport = ks_pcie->num_viewport;
 	struct dw_pcie *pci = ks_pcie->pci;
-	struct pcie_port *pp = &pci->pp;
+	struct dw_pcie_rp *pp = &pci->pp;
 	u64 start, end;
 	struct resource *mem;
 	int i;
@@ -428,7 +428,7 @@
 static void __iomem *ks_pcie_other_map_bus(struct pci_bus *bus,
 					   unsigned int devfn, int where)
 {
-	struct pcie_port *pp = bus->sysdata;
+	struct dw_pcie_rp *pp = bus->sysdata;
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
 	u32 reg;
@@ -456,7 +456,7 @@
  */
 static int ks_pcie_v3_65_add_bus(struct pci_bus *bus)
 {
-	struct pcie_port *pp = bus->sysdata;
+	struct dw_pcie_rp *pp = bus->sysdata;
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
 
@@ -574,7 +574,7 @@
 	struct keystone_pcie *ks_pcie = irq_desc_get_handler_data(desc);
 	u32 offset = irq - ks_pcie->msi_host_irq;
 	struct dw_pcie *pci = ks_pcie->pci;
-	struct pcie_port *pp = &pci->pp;
+	struct dw_pcie_rp *pp = &pci->pp;
 	struct device *dev = pci->dev;
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	u32 vector, reg, pos;
@@ -799,7 +799,7 @@
 	return 0;
 }
 
-static int __init ks_pcie_host_init(struct pcie_port *pp)
+static int __init ks_pcie_host_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
@@ -1069,19 +1069,19 @@
 
 static const struct ks_pcie_of_data ks_pcie_rc_of_data = {
 	.host_ops = &ks_pcie_host_ops,
-	.version = 0x365A,
+	.version = DW_PCIE_VER_365A,
 };
 
 static const struct ks_pcie_of_data ks_pcie_am654_rc_of_data = {
 	.host_ops = &ks_pcie_am654_host_ops,
 	.mode = DW_PCIE_RC_TYPE,
-	.version = 0x490A,
+	.version = DW_PCIE_VER_490A,
 };
 
 static const struct ks_pcie_of_data ks_pcie_am654_ep_of_data = {
 	.ep_ops = &ks_pcie_am654_ep_ops,
 	.mode = DW_PCIE_EP_TYPE,
-	.version = 0x490A,
+	.version = DW_PCIE_VER_490A,
 };
 
 static const struct of_device_id ks_pcie_of_match[] = {
@@ -1114,12 +1114,12 @@
 	struct device_link **link;
 	struct gpio_desc *gpiod;
 	struct resource *res;
-	unsigned int version;
 	void __iomem *base;
 	u32 num_viewport;
 	struct phy **phy;
 	u32 num_lanes;
 	char name[10];
+	u32 version;
 	int ret;
 	int irq;
 	int i;
@@ -1233,7 +1233,7 @@
 		goto err_get_sync;
 	}
 
-	if (pci->version >= 0x480A)
+	if (dw_pcie_ver_is_ge(pci, 480A))
 		ret = ks_pcie_am654_set_mode(dev, mode);
 	else
 		ret = ks_pcie_set_mode(dev);
diff --git a/drivers/pci/controller/dwc/pci-layerscape-ep.c b/drivers/pci/controller/dwc/pci-layerscape-ep.c
index 39f4664..ad99707 100644
--- a/drivers/pci/controller/dwc/pci-layerscape-ep.c
+++ b/drivers/pci/controller/dwc/pci-layerscape-ep.c
@@ -32,15 +32,6 @@
 	const struct ls_pcie_ep_drvdata *drvdata;
 };
 
-static int ls_pcie_establish_link(struct dw_pcie *pci)
-{
-	return 0;
-}
-
-static const struct dw_pcie_ops dw_ls_pcie_ep_ops = {
-	.start_link = ls_pcie_establish_link,
-};
-
 static const struct pci_epc_features*
 ls_pcie_ep_get_features(struct dw_pcie_ep *ep)
 {
@@ -106,19 +97,16 @@
 
 static const struct ls_pcie_ep_drvdata ls1_ep_drvdata = {
 	.ops = &ls_pcie_ep_ops,
-	.dw_pcie_ops = &dw_ls_pcie_ep_ops,
 };
 
 static const struct ls_pcie_ep_drvdata ls2_ep_drvdata = {
 	.func_offset = 0x20000,
 	.ops = &ls_pcie_ep_ops,
-	.dw_pcie_ops = &dw_ls_pcie_ep_ops,
 };
 
 static const struct ls_pcie_ep_drvdata lx2_ep_drvdata = {
 	.func_offset = 0x8000,
 	.ops = &ls_pcie_ep_ops,
-	.dw_pcie_ops = &dw_ls_pcie_ep_ops,
 };
 
 static const struct of_device_id ls_pcie_ep_of_match[] = {
diff --git a/drivers/pci/controller/dwc/pci-layerscape.c b/drivers/pci/controller/dwc/pci-layerscape.c
index 6a4f061..879b869 100644
--- a/drivers/pci/controller/dwc/pci-layerscape.c
+++ b/drivers/pci/controller/dwc/pci-layerscape.c
@@ -74,7 +74,7 @@
 	iowrite32(PCIE_ABSERR_SETTING, pci->dbi_base + PCIE_ABSERR);
 }
 
-static int ls_pcie_host_init(struct pcie_port *pp)
+static int ls_pcie_host_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct ls_pcie *pcie = to_ls_pcie(pci);
diff --git a/drivers/pci/controller/dwc/pci-meson.c b/drivers/pci/controller/dwc/pci-meson.c
index f44bf34..c152769 100644
--- a/drivers/pci/controller/dwc/pci-meson.c
+++ b/drivers/pci/controller/dwc/pci-meson.c
@@ -370,7 +370,7 @@
 	return 0;
 }
 
-static int meson_pcie_host_init(struct pcie_port *pp)
+static int meson_pcie_host_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct meson_pcie *mp = to_meson_pcie(pci);
diff --git a/drivers/pci/controller/dwc/pcie-al.c b/drivers/pci/controller/dwc/pcie-al.c
index e8afa50..b8cb77c 100644
--- a/drivers/pci/controller/dwc/pcie-al.c
+++ b/drivers/pci/controller/dwc/pcie-al.c
@@ -217,7 +217,7 @@
 static void __iomem *al_pcie_conf_addr_map_bus(struct pci_bus *bus,
 					       unsigned int devfn, int where)
 {
-	struct pcie_port *pp = bus->sysdata;
+	struct dw_pcie_rp *pp = bus->sysdata;
 	struct al_pcie *pcie = to_al_pcie(to_dw_pcie_from_pp(pp));
 	unsigned int busnr = bus->number;
 	struct al_pcie_target_bus_cfg *target_bus_cfg = &pcie->target_bus_cfg;
@@ -245,7 +245,7 @@
 static void al_pcie_config_prepare(struct al_pcie *pcie)
 {
 	struct al_pcie_target_bus_cfg *target_bus_cfg;
-	struct pcie_port *pp = &pcie->pci->pp;
+	struct dw_pcie_rp *pp = &pcie->pci->pp;
 	unsigned int ecam_bus_mask;
 	u32 cfg_control_offset;
 	u8 subordinate_bus;
@@ -289,7 +289,7 @@
 	al_pcie_controller_writel(pcie, cfg_control_offset, reg);
 }
 
-static int al_pcie_host_init(struct pcie_port *pp)
+static int al_pcie_host_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct al_pcie *pcie = to_al_pcie(pci);
diff --git a/drivers/pci/controller/dwc/pcie-armada8k.c b/drivers/pci/controller/dwc/pcie-armada8k.c
index 4e2552d..8b113d3 100644
--- a/drivers/pci/controller/dwc/pcie-armada8k.c
+++ b/drivers/pci/controller/dwc/pcie-armada8k.c
@@ -166,7 +166,7 @@
 	return 0;
 }
 
-static int armada8k_pcie_host_init(struct pcie_port *pp)
+static int armada8k_pcie_host_init(struct dw_pcie_rp *pp)
 {
 	u32 reg;
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
@@ -233,7 +233,7 @@
 				  struct platform_device *pdev)
 {
 	struct dw_pcie *pci = pcie->pci;
-	struct pcie_port *pp = &pci->pp;
+	struct dw_pcie_rp *pp = &pci->pp;
 	struct device *dev = &pdev->dev;
 	int ret;
 
diff --git a/drivers/pci/controller/dwc/pcie-artpec6.c b/drivers/pci/controller/dwc/pcie-artpec6.c
index 2f15441..9810207 100644
--- a/drivers/pci/controller/dwc/pcie-artpec6.c
+++ b/drivers/pci/controller/dwc/pcie-artpec6.c
@@ -97,7 +97,7 @@
 static u64 artpec6_pcie_cpu_addr_fixup(struct dw_pcie *pci, u64 pci_addr)
 {
 	struct artpec6_pcie *artpec6_pcie = to_artpec6_pcie(pci);
-	struct pcie_port *pp = &pci->pp;
+	struct dw_pcie_rp *pp = &pci->pp;
 	struct dw_pcie_ep *ep = &pci->ep;
 
 	switch (artpec6_pcie->mode) {
@@ -315,7 +315,7 @@
 	usleep_range(100, 200);
 }
 
-static int artpec6_pcie_host_init(struct pcie_port *pp)
+static int artpec6_pcie_host_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct artpec6_pcie *artpec6_pcie = to_artpec6_pcie(pci);
diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
index 0eda823..cf16276 100644
--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
+++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
@@ -154,9 +154,8 @@
 	return 0;
 }
 
-static int dw_pcie_ep_inbound_atu(struct dw_pcie_ep *ep, u8 func_no,
-				  enum pci_barno bar, dma_addr_t cpu_addr,
-				  enum dw_pcie_as_type as_type)
+static int dw_pcie_ep_inbound_atu(struct dw_pcie_ep *ep, u8 func_no, int type,
+				  dma_addr_t cpu_addr, enum pci_barno bar)
 {
 	int ret;
 	u32 free_win;
@@ -168,8 +167,8 @@
 		return -EINVAL;
 	}
 
-	ret = dw_pcie_prog_inbound_atu(pci, func_no, free_win, bar, cpu_addr,
-				       as_type);
+	ret = dw_pcie_prog_inbound_atu(pci, func_no, free_win, type,
+				       cpu_addr, bar);
 	if (ret < 0) {
 		dev_err(pci->dev, "Failed to program IB window\n");
 		return ret;
@@ -185,8 +184,9 @@
 				   phys_addr_t phys_addr,
 				   u64 pci_addr, size_t size)
 {
-	u32 free_win;
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+	u32 free_win;
+	int ret;
 
 	free_win = find_first_zero_bit(ep->ob_window_map, pci->num_ob_windows);
 	if (free_win >= pci->num_ob_windows) {
@@ -194,8 +194,10 @@
 		return -EINVAL;
 	}
 
-	dw_pcie_prog_ep_outbound_atu(pci, func_no, free_win, PCIE_ATU_TYPE_MEM,
-				     phys_addr, pci_addr, size);
+	ret = dw_pcie_prog_ep_outbound_atu(pci, func_no, free_win, PCIE_ATU_TYPE_MEM,
+					   phys_addr, pci_addr, size);
+	if (ret)
+		return ret;
 
 	set_bit(free_win, ep->ob_window_map);
 	ep->outbound_addr[free_win] = phys_addr;
@@ -213,7 +215,7 @@
 
 	__dw_pcie_ep_reset_bar(pci, func_no, bar, epf_bar->flags);
 
-	dw_pcie_disable_atu(pci, atu_index, DW_PCIE_REGION_INBOUND);
+	dw_pcie_disable_atu(pci, PCIE_ATU_REGION_DIR_IB, atu_index);
 	clear_bit(atu_index, ep->ib_window_map);
 	ep->epf_bar[bar] = NULL;
 }
@@ -221,27 +223,25 @@
 static int dw_pcie_ep_set_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
 			      struct pci_epf_bar *epf_bar)
 {
-	int ret;
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	enum pci_barno bar = epf_bar->barno;
 	size_t size = epf_bar->size;
 	int flags = epf_bar->flags;
-	enum dw_pcie_as_type as_type;
-	u32 reg;
 	unsigned int func_offset = 0;
+	int ret, type;
+	u32 reg;
 
 	func_offset = dw_pcie_ep_func_select(ep, func_no);
 
 	reg = PCI_BASE_ADDRESS_0 + (4 * bar) + func_offset;
 
 	if (!(flags & PCI_BASE_ADDRESS_SPACE))
-		as_type = DW_PCIE_AS_MEM;
+		type = PCIE_ATU_TYPE_MEM;
 	else
-		as_type = DW_PCIE_AS_IO;
+		type = PCIE_ATU_TYPE_IO;
 
-	ret = dw_pcie_ep_inbound_atu(ep, func_no, bar,
-				     epf_bar->phys_addr, as_type);
+	ret = dw_pcie_ep_inbound_atu(ep, func_no, type, epf_bar->phys_addr, bar);
 	if (ret)
 		return ret;
 
@@ -289,7 +289,7 @@
 	if (ret < 0)
 		return;
 
-	dw_pcie_disable_atu(pci, atu_index, DW_PCIE_REGION_OUTBOUND);
+	dw_pcie_disable_atu(pci, PCIE_ATU_REGION_DIR_OB, atu_index);
 	clear_bit(atu_index, ep->ob_window_map);
 }
 
@@ -435,8 +435,7 @@
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
-	if (pci->ops && pci->ops->stop_link)
-		pci->ops->stop_link(pci);
+	dw_pcie_stop_link(pci);
 }
 
 static int dw_pcie_ep_start(struct pci_epc *epc)
@@ -444,10 +443,7 @@
 	struct dw_pcie_ep *ep = epc_get_drvdata(epc);
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 
-	if (!pci->ops || !pci->ops->start_link)
-		return -EINVAL;
-
-	return pci->ops->start_link(pci);
+	return dw_pcie_start_link(pci);
 }
 
 static const struct pci_epc_features*
@@ -699,17 +695,15 @@
 
 	if (!pci->dbi_base2) {
 		res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi2");
-		if (!res)
+		if (!res) {
 			pci->dbi_base2 = pci->dbi_base + SZ_4K;
-		else {
+		} else {
 			pci->dbi_base2 = devm_pci_remap_cfg_resource(dev, res);
 			if (IS_ERR(pci->dbi_base2))
 				return PTR_ERR(pci->dbi_base2);
 		}
 	}
 
-	dw_pcie_iatu_detect(pci);
-
 	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "addr_space");
 	if (!res)
 		return -EINVAL;
@@ -717,17 +711,17 @@
 	ep->phys_base = res->start;
 	ep->addr_size = resource_size(res);
 
-	ep->ib_window_map = devm_kcalloc(dev,
-					 BITS_TO_LONGS(pci->num_ib_windows),
-					 sizeof(long),
-					 GFP_KERNEL);
+	dw_pcie_version_detect(pci);
+
+	dw_pcie_iatu_detect(pci);
+
+	ep->ib_window_map = devm_bitmap_zalloc(dev, pci->num_ib_windows,
+					       GFP_KERNEL);
 	if (!ep->ib_window_map)
 		return -ENOMEM;
 
-	ep->ob_window_map = devm_kcalloc(dev,
-					 BITS_TO_LONGS(pci->num_ob_windows),
-					 sizeof(long),
-					 GFP_KERNEL);
+	ep->ob_window_map = devm_bitmap_zalloc(dev, pci->num_ob_windows,
+					       GFP_KERNEL);
 	if (!ep->ob_window_map)
 		return -ENOMEM;
 
@@ -780,8 +774,9 @@
 	ep->msi_mem = pci_epc_mem_alloc_addr(epc, &ep->msi_mem_phys,
 					     epc->mem->window.page_size);
 	if (!ep->msi_mem) {
+		ret = -ENOMEM;
 		dev_err(dev, "Failed to reserve memory for MSI/MSI-X\n");
-		return -ENOMEM;
+		goto err_exit_epc_mem;
 	}
 
 	if (ep->ops->get_features) {
@@ -790,6 +785,19 @@
 			return 0;
 	}
 
-	return dw_pcie_ep_init_complete(ep);
+	ret = dw_pcie_ep_init_complete(ep);
+	if (ret)
+		goto err_free_epc_mem;
+
+	return 0;
+
+err_free_epc_mem:
+	pci_epc_mem_free_addr(epc, ep->msi_mem_phys, ep->msi_mem,
+			      epc->mem->window.page_size);
+
+err_exit_epc_mem:
+	pci_epc_mem_exit(epc);
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(dw_pcie_ep_init);
diff --git a/drivers/pci/controller/dwc/pcie-designware-host.c b/drivers/pci/controller/dwc/pcie-designware-host.c
index 99793025..7746f94 100644
--- a/drivers/pci/controller/dwc/pcie-designware-host.c
+++ b/drivers/pci/controller/dwc/pcie-designware-host.c
@@ -53,7 +53,7 @@
 };
 
 /* MSI int handler */
-irqreturn_t dw_handle_msi_irq(struct pcie_port *pp)
+irqreturn_t dw_handle_msi_irq(struct dw_pcie_rp *pp)
 {
 	int i, pos;
 	unsigned long val;
@@ -88,7 +88,7 @@
 static void dw_chained_msi_isr(struct irq_desc *desc)
 {
 	struct irq_chip *chip = irq_desc_get_chip(desc);
-	struct pcie_port *pp;
+	struct dw_pcie_rp *pp;
 
 	chained_irq_enter(chip, desc);
 
@@ -100,7 +100,7 @@
 
 static void dw_pci_setup_msi_msg(struct irq_data *d, struct msi_msg *msg)
 {
-	struct pcie_port *pp = irq_data_get_irq_chip_data(d);
+	struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(d);
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	u64 msi_target;
 
@@ -123,7 +123,7 @@
 
 static void dw_pci_bottom_mask(struct irq_data *d)
 {
-	struct pcie_port *pp = irq_data_get_irq_chip_data(d);
+	struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(d);
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	unsigned int res, bit, ctrl;
 	unsigned long flags;
@@ -142,7 +142,7 @@
 
 static void dw_pci_bottom_unmask(struct irq_data *d)
 {
-	struct pcie_port *pp = irq_data_get_irq_chip_data(d);
+	struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(d);
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	unsigned int res, bit, ctrl;
 	unsigned long flags;
@@ -161,7 +161,7 @@
 
 static void dw_pci_bottom_ack(struct irq_data *d)
 {
-	struct pcie_port *pp  = irq_data_get_irq_chip_data(d);
+	struct dw_pcie_rp *pp  = irq_data_get_irq_chip_data(d);
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	unsigned int res, bit, ctrl;
 
@@ -185,7 +185,7 @@
 				    unsigned int virq, unsigned int nr_irqs,
 				    void *args)
 {
-	struct pcie_port *pp = domain->host_data;
+	struct dw_pcie_rp *pp = domain->host_data;
 	unsigned long flags;
 	u32 i;
 	int bit;
@@ -213,7 +213,7 @@
 				    unsigned int virq, unsigned int nr_irqs)
 {
 	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
-	struct pcie_port *pp = domain->host_data;
+	struct dw_pcie_rp *pp = domain->host_data;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&pp->lock, flags);
@@ -229,7 +229,7 @@
 	.free	= dw_pcie_irq_domain_free,
 };
 
-int dw_pcie_allocate_domains(struct pcie_port *pp)
+int dw_pcie_allocate_domains(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct fwnode_handle *fwnode = of_node_to_fwnode(pci->dev->of_node);
@@ -255,10 +255,15 @@
 	return 0;
 }
 
-static void dw_pcie_free_msi(struct pcie_port *pp)
+static void dw_pcie_free_msi(struct dw_pcie_rp *pp)
 {
-	if (pp->msi_irq)
-		irq_set_chained_handler_and_data(pp->msi_irq, NULL, NULL);
+	u32 ctrl;
+
+	for (ctrl = 0; ctrl < MAX_MSI_CTRLS; ctrl++) {
+		if (pp->msi_irq[ctrl] > 0)
+			irq_set_chained_handler_and_data(pp->msi_irq[ctrl],
+							 NULL, NULL);
+	}
 
 	irq_domain_remove(pp->msi_domain);
 	irq_domain_remove(pp->irq_domain);
@@ -267,12 +272,13 @@
 		struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 		struct device *dev = pci->dev;
 
-		dma_unmap_single_attrs(dev, pp->msi_data, sizeof(pp->msi_msg),
-				       DMA_FROM_DEVICE, DMA_ATTR_SKIP_CPU_SYNC);
+		dma_unmap_page(dev, pp->msi_data, PAGE_SIZE, DMA_FROM_DEVICE);
+		if (pp->msi_page)
+			__free_page(pp->msi_page);
 	}
 }
 
-static void dw_pcie_msi_init(struct pcie_port *pp)
+static void dw_pcie_msi_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	u64 msi_target = (u64)pp->msi_data;
@@ -285,7 +291,112 @@
 	dw_pcie_writel_dbi(pci, PCIE_MSI_ADDR_HI, upper_32_bits(msi_target));
 }
 
-int dw_pcie_host_init(struct pcie_port *pp)
+static int dw_pcie_parse_split_msi_irq(struct dw_pcie_rp *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct device *dev = pci->dev;
+	struct platform_device *pdev = to_platform_device(dev);
+	u32 ctrl, max_vectors;
+	int irq;
+
+	/* Parse any "msiX" IRQs described in the devicetree */
+	for (ctrl = 0; ctrl < MAX_MSI_CTRLS; ctrl++) {
+		char msi_name[] = "msiX";
+
+		msi_name[3] = '0' + ctrl;
+		irq = platform_get_irq_byname_optional(pdev, msi_name);
+		if (irq == -ENXIO)
+			break;
+		if (irq < 0)
+			return dev_err_probe(dev, irq,
+					     "Failed to parse MSI IRQ '%s'\n",
+					     msi_name);
+
+		pp->msi_irq[ctrl] = irq;
+	}
+
+	/* If no "msiX" IRQs, caller should fallback to "msi" IRQ */
+	if (ctrl == 0)
+		return -ENXIO;
+
+	max_vectors = ctrl * MAX_MSI_IRQS_PER_CTRL;
+	if (pp->num_vectors > max_vectors) {
+		dev_warn(dev, "Exceeding number of MSI vectors, limiting to %u\n",
+			 max_vectors);
+		pp->num_vectors = max_vectors;
+	}
+	if (!pp->num_vectors)
+		pp->num_vectors = max_vectors;
+
+	return 0;
+}
+
+static int dw_pcie_msi_host_init(struct dw_pcie_rp *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct device *dev = pci->dev;
+	struct platform_device *pdev = to_platform_device(dev);
+	int ret;
+	u32 ctrl, num_ctrls;
+
+	for (ctrl = 0; ctrl < MAX_MSI_CTRLS; ctrl++)
+		pp->irq_mask[ctrl] = ~0;
+
+	if (!pp->msi_irq[0]) {
+		ret = dw_pcie_parse_split_msi_irq(pp);
+		if (ret < 0 && ret != -ENXIO)
+			return ret;
+	}
+
+	if (!pp->num_vectors)
+		pp->num_vectors = MSI_DEF_NUM_VECTORS;
+	num_ctrls = pp->num_vectors / MAX_MSI_IRQS_PER_CTRL;
+
+	if (!pp->msi_irq[0]) {
+		pp->msi_irq[0] = platform_get_irq_byname_optional(pdev, "msi");
+		if (pp->msi_irq[0] < 0) {
+			pp->msi_irq[0] = platform_get_irq(pdev, 0);
+			if (pp->msi_irq[0] < 0)
+				return pp->msi_irq[0];
+		}
+	}
+
+	dev_dbg(dev, "Using %d MSI vectors\n", pp->num_vectors);
+
+	pp->msi_irq_chip = &dw_pci_msi_bottom_irq_chip;
+
+	ret = dw_pcie_allocate_domains(pp);
+	if (ret)
+		return ret;
+
+	for (ctrl = 0; ctrl < num_ctrls; ctrl++) {
+		if (pp->msi_irq[ctrl] > 0)
+			irq_set_chained_handler_and_data(pp->msi_irq[ctrl],
+						    dw_chained_msi_isr, pp);
+	}
+
+	ret = dma_set_mask(dev, DMA_BIT_MASK(32));
+	if (ret)
+		dev_warn(dev, "Failed to set DMA mask to 32-bit. Devices with only 32-bit MSI support may not work properly\n");
+
+	pp->msi_page = alloc_page(GFP_DMA32);
+	pp->msi_data = dma_map_page(dev, pp->msi_page, 0,
+				    PAGE_SIZE, DMA_FROM_DEVICE);
+	ret = dma_mapping_error(dev, pp->msi_data);
+	if (ret) {
+		dev_err(pci->dev, "Failed to map MSI data\n");
+		__free_page(pp->msi_page);
+		pp->msi_page = NULL;
+		pp->msi_data = 0;
+		dw_pcie_free_msi(pp);
+
+		return ret;
+	}
+
+	return 0;
+}
+
+int dw_pcie_host_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct device *dev = pci->dev;
@@ -293,17 +404,17 @@
 	struct platform_device *pdev = to_platform_device(dev);
 	struct resource_entry *win;
 	struct pci_host_bridge *bridge;
-	struct resource *cfg_res;
+	struct resource *res;
 	int ret;
 
-	raw_spin_lock_init(&pci->pp.lock);
+	raw_spin_lock_init(&pp->lock);
 
-	cfg_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "config");
-	if (cfg_res) {
-		pp->cfg0_size = resource_size(cfg_res);
-		pp->cfg0_base = cfg_res->start;
+	res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "config");
+	if (res) {
+		pp->cfg0_size = resource_size(res);
+		pp->cfg0_base = res->start;
 
-		pp->va_cfg0_base = devm_pci_remap_cfg_resource(dev, cfg_res);
+		pp->va_cfg0_base = devm_pci_remap_cfg_resource(dev, res);
 		if (IS_ERR(pp->va_cfg0_base))
 			return PTR_ERR(pp->va_cfg0_base);
 	} else {
@@ -312,8 +423,8 @@
 	}
 
 	if (!pci->dbi_base) {
-		struct resource *dbi_res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi");
-		pci->dbi_base = devm_pci_remap_cfg_resource(dev, dbi_res);
+		res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dbi");
+		pci->dbi_base = devm_pci_remap_cfg_resource(dev, res);
 		if (IS_ERR(pci->dbi_base))
 			return PTR_ERR(pci->dbi_base);
 	}
@@ -350,67 +461,39 @@
 				     of_property_read_bool(np, "msi-parent") ||
 				     of_property_read_bool(np, "msi-map"));
 
-		if (!pp->num_vectors) {
+		/*
+		 * For the has_msi_ctrl case the default assignment is handled
+		 * in the dw_pcie_msi_host_init().
+		 */
+		if (!pp->has_msi_ctrl && !pp->num_vectors) {
 			pp->num_vectors = MSI_DEF_NUM_VECTORS;
 		} else if (pp->num_vectors > MAX_MSI_IRQS) {
 			dev_err(dev, "Invalid number of vectors\n");
-			return -EINVAL;
+			ret = -EINVAL;
+			goto err_deinit_host;
 		}
 
 		if (pp->ops->msi_host_init) {
 			ret = pp->ops->msi_host_init(pp);
 			if (ret < 0)
-				return ret;
+				goto err_deinit_host;
 		} else if (pp->has_msi_ctrl) {
-			u32 ctrl, num_ctrls;
-
-			num_ctrls = pp->num_vectors / MAX_MSI_IRQS_PER_CTRL;
-			for (ctrl = 0; ctrl < num_ctrls; ctrl++)
-				pp->irq_mask[ctrl] = ~0;
-
-			if (!pp->msi_irq) {
-				pp->msi_irq = platform_get_irq_byname_optional(pdev, "msi");
-				if (pp->msi_irq < 0) {
-					pp->msi_irq = platform_get_irq(pdev, 0);
-					if (pp->msi_irq < 0)
-						return pp->msi_irq;
-				}
-			}
-
-			pp->msi_irq_chip = &dw_pci_msi_bottom_irq_chip;
-
-			ret = dw_pcie_allocate_domains(pp);
-			if (ret)
-				return ret;
-
-			if (pp->msi_irq > 0)
-				irq_set_chained_handler_and_data(pp->msi_irq,
-							    dw_chained_msi_isr,
-							    pp);
-
-			ret = dma_set_mask(pci->dev, DMA_BIT_MASK(32));
-			if (ret)
-				dev_warn(pci->dev, "Failed to set DMA mask to 32-bit. Devices with only 32-bit MSI support may not work properly\n");
-
-			pp->msi_data = dma_map_single_attrs(pci->dev, &pp->msi_msg,
-						      sizeof(pp->msi_msg),
-						      DMA_FROM_DEVICE,
-						      DMA_ATTR_SKIP_CPU_SYNC);
-			ret = dma_mapping_error(pci->dev, pp->msi_data);
-			if (ret) {
-				dev_err(pci->dev, "Failed to map MSI data\n");
-				pp->msi_data = 0;
-				goto err_free_msi;
-			}
+			ret = dw_pcie_msi_host_init(pp);
+			if (ret < 0)
+				goto err_deinit_host;
 		}
 	}
 
+	dw_pcie_version_detect(pci);
+
 	dw_pcie_iatu_detect(pci);
 
-	dw_pcie_setup_rc(pp);
+	ret = dw_pcie_setup_rc(pp);
+	if (ret)
+		goto err_free_msi;
 
-	if (!dw_pcie_link_up(pci) && pci->ops && pci->ops->start_link) {
-		ret = pci->ops->start_link(pci);
+	if (!dw_pcie_link_up(pci)) {
+		ret = dw_pcie_start_link(pci);
 		if (ret)
 			goto err_free_msi;
 	}
@@ -421,32 +504,50 @@
 	bridge->sysdata = pp;
 
 	ret = pci_host_probe(bridge);
-	if (!ret)
-		return 0;
+	if (ret)
+		goto err_stop_link;
+
+	return 0;
+
+err_stop_link:
+	dw_pcie_stop_link(pci);
 
 err_free_msi:
 	if (pp->has_msi_ctrl)
 		dw_pcie_free_msi(pp);
+
+err_deinit_host:
+	if (pp->ops->host_deinit)
+		pp->ops->host_deinit(pp);
+
 	return ret;
 }
 EXPORT_SYMBOL_GPL(dw_pcie_host_init);
 
-void dw_pcie_host_deinit(struct pcie_port *pp)
+void dw_pcie_host_deinit(struct dw_pcie_rp *pp)
 {
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+
 	pci_stop_root_bus(pp->bridge->bus);
 	pci_remove_root_bus(pp->bridge->bus);
+
+	dw_pcie_stop_link(pci);
+
 	if (pp->has_msi_ctrl)
 		dw_pcie_free_msi(pp);
+
+	if (pp->ops->host_deinit)
+		pp->ops->host_deinit(pp);
 }
 EXPORT_SYMBOL_GPL(dw_pcie_host_deinit);
 
 static void __iomem *dw_pcie_other_conf_map_bus(struct pci_bus *bus,
 						unsigned int devfn, int where)
 {
-	int type;
-	u32 busdev;
-	struct pcie_port *pp = bus->sysdata;
+	struct dw_pcie_rp *pp = bus->sysdata;
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	int type, ret;
+	u32 busdev;
 
 	/*
 	 * Checking whether the link is up here is a last line of defense
@@ -467,8 +568,10 @@
 	else
 		type = PCIE_ATU_TYPE_CFG1;
 
-
-	dw_pcie_prog_outbound_atu(pci, 0, type, pp->cfg0_base, busdev, pp->cfg0_size);
+	ret = dw_pcie_prog_outbound_atu(pci, 0, type, pp->cfg0_base, busdev,
+					pp->cfg0_size);
+	if (ret)
+		return NULL;
 
 	return pp->va_cfg0_base + where;
 }
@@ -476,33 +579,45 @@
 static int dw_pcie_rd_other_conf(struct pci_bus *bus, unsigned int devfn,
 				 int where, int size, u32 *val)
 {
-	int ret;
-	struct pcie_port *pp = bus->sysdata;
+	struct dw_pcie_rp *pp = bus->sysdata;
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	int ret;
 
 	ret = pci_generic_config_read(bus, devfn, where, size, val);
+	if (ret != PCIBIOS_SUCCESSFUL)
+		return ret;
 
-	if (!ret && pci->io_cfg_atu_shared)
-		dw_pcie_prog_outbound_atu(pci, 0, PCIE_ATU_TYPE_IO, pp->io_base,
-					  pp->io_bus_addr, pp->io_size);
+	if (pp->cfg0_io_shared) {
+		ret = dw_pcie_prog_outbound_atu(pci, 0, PCIE_ATU_TYPE_IO,
+						pp->io_base, pp->io_bus_addr,
+						pp->io_size);
+		if (ret)
+			return PCIBIOS_SET_FAILED;
+	}
 
-	return ret;
+	return PCIBIOS_SUCCESSFUL;
 }
 
 static int dw_pcie_wr_other_conf(struct pci_bus *bus, unsigned int devfn,
 				 int where, int size, u32 val)
 {
-	int ret;
-	struct pcie_port *pp = bus->sysdata;
+	struct dw_pcie_rp *pp = bus->sysdata;
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	int ret;
 
 	ret = pci_generic_config_write(bus, devfn, where, size, val);
+	if (ret != PCIBIOS_SUCCESSFUL)
+		return ret;
 
-	if (!ret && pci->io_cfg_atu_shared)
-		dw_pcie_prog_outbound_atu(pci, 0, PCIE_ATU_TYPE_IO, pp->io_base,
-					  pp->io_bus_addr, pp->io_size);
+	if (pp->cfg0_io_shared) {
+		ret = dw_pcie_prog_outbound_atu(pci, 0, PCIE_ATU_TYPE_IO,
+						pp->io_base, pp->io_bus_addr,
+						pp->io_size);
+		if (ret)
+			return PCIBIOS_SET_FAILED;
+	}
 
-	return ret;
+	return PCIBIOS_SUCCESSFUL;
 }
 
 static struct pci_ops dw_child_pcie_ops = {
@@ -513,7 +628,7 @@
 
 void __iomem *dw_pcie_own_conf_map_bus(struct pci_bus *bus, unsigned int devfn, int where)
 {
-	struct pcie_port *pp = bus->sysdata;
+	struct dw_pcie_rp *pp = bus->sysdata;
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 
 	if (PCI_SLOT(devfn) > 0)
@@ -529,11 +644,72 @@
 	.write = pci_generic_config_write,
 };
 
-void dw_pcie_setup_rc(struct pcie_port *pp)
+static int dw_pcie_iatu_setup(struct dw_pcie_rp *pp)
 {
-	int i;
-	u32 val, ctrl, num_ctrls;
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct resource_entry *entry;
+	int i, ret;
+
+	/* Note the very first outbound ATU is used for CFG IOs */
+	if (!pci->num_ob_windows) {
+		dev_err(pci->dev, "No outbound iATU found\n");
+		return -EINVAL;
+	}
+
+	/*
+	 * Ensure all outbound windows are disabled before proceeding with
+	 * the MEM/IO ranges setups.
+	 */
+	for (i = 0; i < pci->num_ob_windows; i++)
+		dw_pcie_disable_atu(pci, PCIE_ATU_REGION_DIR_OB, i);
+
+	i = 0;
+	resource_list_for_each_entry(entry, &pp->bridge->windows) {
+		if (resource_type(entry->res) != IORESOURCE_MEM)
+			continue;
+
+		if (pci->num_ob_windows <= ++i)
+			break;
+
+		ret = dw_pcie_prog_outbound_atu(pci, i, PCIE_ATU_TYPE_MEM,
+						entry->res->start,
+						entry->res->start - entry->offset,
+						resource_size(entry->res));
+		if (ret) {
+			dev_err(pci->dev, "Failed to set MEM range %pr\n",
+				entry->res);
+			return ret;
+		}
+	}
+
+	if (pp->io_size) {
+		if (pci->num_ob_windows > ++i) {
+			ret = dw_pcie_prog_outbound_atu(pci, i, PCIE_ATU_TYPE_IO,
+							pp->io_base,
+							pp->io_bus_addr,
+							pp->io_size);
+			if (ret) {
+				dev_err(pci->dev, "Failed to set IO range %pr\n",
+					entry->res);
+				return ret;
+			}
+		} else {
+			pp->cfg0_io_shared = true;
+		}
+	}
+
+	if (pci->num_ob_windows <= i)
+		dev_warn(pci->dev, "Resources exceed number of ATU entries (%d)\n",
+			 pci->num_ob_windows);
+
+	return 0;
+}
+
+int dw_pcie_setup_rc(struct dw_pcie_rp *pp)
+{
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	u32 val, ctrl, num_ctrls;
+	int ret;
 
 	/*
 	 * Enable DBI read-only registers for writing/updating configuration.
@@ -582,45 +758,15 @@
 		PCI_COMMAND_MASTER | PCI_COMMAND_SERR;
 	dw_pcie_writel_dbi(pci, PCI_COMMAND, val);
 
-	/* Ensure all outbound windows are disabled so there are multiple matches */
-	for (i = 0; i < pci->num_ob_windows; i++)
-		dw_pcie_disable_atu(pci, i, DW_PCIE_REGION_OUTBOUND);
-
 	/*
 	 * If the platform provides its own child bus config accesses, it means
 	 * the platform uses its own address translation component rather than
 	 * ATU, so we should not program the ATU here.
 	 */
 	if (pp->bridge->child_ops == &dw_child_pcie_ops) {
-		int atu_idx = 0;
-		struct resource_entry *entry;
-
-		/* Get last memory resource entry */
-		resource_list_for_each_entry(entry, &pp->bridge->windows) {
-			if (resource_type(entry->res) != IORESOURCE_MEM)
-				continue;
-
-			if (pci->num_ob_windows <= ++atu_idx)
-				break;
-
-			dw_pcie_prog_outbound_atu(pci, atu_idx,
-						  PCIE_ATU_TYPE_MEM, entry->res->start,
-						  entry->res->start - entry->offset,
-						  resource_size(entry->res));
-		}
-
-		if (pp->io_size) {
-			if (pci->num_ob_windows > ++atu_idx)
-				dw_pcie_prog_outbound_atu(pci, atu_idx,
-							  PCIE_ATU_TYPE_IO, pp->io_base,
-							  pp->io_bus_addr, pp->io_size);
-			else
-				pci->io_cfg_atu_shared = true;
-		}
-
-		if (pci->num_ob_windows <= atu_idx)
-			dev_warn(pci->dev, "Resources exceed number of ATU entries (%d)",
-				 pci->num_ob_windows);
+		ret = dw_pcie_iatu_setup(pp);
+		if (ret)
+			return ret;
 	}
 
 	dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 0);
@@ -633,5 +779,7 @@
 	dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val);
 
 	dw_pcie_dbi_ro_wr_dis(pci);
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(dw_pcie_setup_rc);
diff --git a/drivers/pci/controller/dwc/pcie-designware-plat.c b/drivers/pci/controller/dwc/pcie-designware-plat.c
index 0c5de87d..1fcfb84 100644
--- a/drivers/pci/controller/dwc/pcie-designware-plat.c
+++ b/drivers/pci/controller/dwc/pcie-designware-plat.c
@@ -17,13 +17,11 @@
 #include <linux/platform_device.h>
 #include <linux/resource.h>
 #include <linux/types.h>
-#include <linux/regmap.h>
 
 #include "pcie-designware.h"
 
 struct dw_plat_pcie {
 	struct dw_pcie			*pci;
-	struct regmap			*regmap;
 	enum dw_pcie_device_mode	mode;
 };
 
@@ -31,20 +29,9 @@
 	enum dw_pcie_device_mode	mode;
 };
 
-static const struct of_device_id dw_plat_pcie_of_match[];
-
 static const struct dw_pcie_host_ops dw_plat_pcie_host_ops = {
 };
 
-static int dw_plat_pcie_establish_link(struct dw_pcie *pci)
-{
-	return 0;
-}
-
-static const struct dw_pcie_ops dw_pcie_ops = {
-	.start_link = dw_plat_pcie_establish_link,
-};
-
 static void dw_plat_pcie_ep_init(struct dw_pcie_ep *ep)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
@@ -96,7 +83,7 @@
 				 struct platform_device *pdev)
 {
 	struct dw_pcie *pci = dw_plat_pcie->pci;
-	struct pcie_port *pp = &pci->pp;
+	struct dw_pcie_rp *pp = &pci->pp;
 	struct device *dev = &pdev->dev;
 	int ret;
 
@@ -140,7 +127,6 @@
 		return -ENOMEM;
 
 	pci->dev = dev;
-	pci->ops = &dw_pcie_ops;
 
 	dw_plat_pcie->pci = pci;
 	dw_plat_pcie->mode = mode;
@@ -153,20 +139,21 @@
 			return -ENODEV;
 
 		ret = dw_plat_add_pcie_port(dw_plat_pcie, pdev);
-		if (ret < 0)
-			return ret;
 		break;
 	case DW_PCIE_EP_TYPE:
 		if (!IS_ENABLED(CONFIG_PCIE_DW_PLAT_EP))
 			return -ENODEV;
 
 		pci->ep.ops = &pcie_ep_ops;
-		return dw_pcie_ep_init(&pci->ep);
+		ret = dw_pcie_ep_init(&pci->ep);
+		break;
 	default:
 		dev_err(dev, "INVALID device type %d\n", dw_plat_pcie->mode);
+		ret = -EINVAL;
+		break;
 	}
 
-	return 0;
+	return ret;
 }
 
 static const struct dw_plat_pcie_of_data dw_plat_pcie_rc_of_data = {
diff --git a/drivers/pci/controller/dwc/pcie-designware.c b/drivers/pci/controller/dwc/pcie-designware.c
index d92c8a25..c6725c5 100644
--- a/drivers/pci/controller/dwc/pcie-designware.c
+++ b/drivers/pci/controller/dwc/pcie-designware.c
@@ -8,14 +8,41 @@
  * Author: Jingoo Han <jg1.han@samsung.com>
  */
 
+#include <linux/align.h>
+#include <linux/bitops.h>
 #include <linux/delay.h>
 #include <linux/of.h>
 #include <linux/of_platform.h>
+#include <linux/sizes.h>
 #include <linux/types.h>
 
 #include "../../pci.h"
 #include "pcie-designware.h"
 
+void dw_pcie_version_detect(struct dw_pcie *pci)
+{
+	u32 ver;
+
+	/* The content of the CSR is zero on DWC PCIe older than v4.70a */
+	ver = dw_pcie_readl_dbi(pci, PCIE_VERSION_NUMBER);
+	if (!ver)
+		return;
+
+	if (pci->version && pci->version != ver)
+		dev_warn(pci->dev, "Versions don't match (%08x != %08x)\n",
+			 pci->version, ver);
+	else
+		pci->version = ver;
+
+	ver = dw_pcie_readl_dbi(pci, PCIE_VERSION_TYPE);
+
+	if (pci->type && pci->type != ver)
+		dev_warn(pci->dev, "Types don't match (%08x != %08x)\n",
+			 pci->type, ver);
+	else
+		pci->type = ver;
+}
+
 /*
  * These interfaces resemble the pci_find_*capability() interfaces, but these
  * are for configuring host controllers, which are bridges *to* PCI devices but
@@ -181,48 +208,61 @@
 		dev_err(pci->dev, "write DBI address failed\n");
 }
 
-static u32 dw_pcie_readl_atu(struct dw_pcie *pci, u32 reg)
+static inline void __iomem *dw_pcie_select_atu(struct dw_pcie *pci, u32 dir,
+					       u32 index)
 {
+	if (pci->iatu_unroll_enabled)
+		return pci->atu_base + PCIE_ATU_UNROLL_BASE(dir, index);
+
+	dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT, dir | index);
+	return pci->atu_base;
+}
+
+static u32 dw_pcie_readl_atu(struct dw_pcie *pci, u32 dir, u32 index, u32 reg)
+{
+	void __iomem *base;
 	int ret;
 	u32 val;
 
-	if (pci->ops && pci->ops->read_dbi)
-		return pci->ops->read_dbi(pci, pci->atu_base, reg, 4);
+	base = dw_pcie_select_atu(pci, dir, index);
 
-	ret = dw_pcie_read(pci->atu_base + reg, 4, &val);
+	if (pci->ops && pci->ops->read_dbi)
+		return pci->ops->read_dbi(pci, base, reg, 4);
+
+	ret = dw_pcie_read(base + reg, 4, &val);
 	if (ret)
 		dev_err(pci->dev, "Read ATU address failed\n");
 
 	return val;
 }
 
-static void dw_pcie_writel_atu(struct dw_pcie *pci, u32 reg, u32 val)
+static void dw_pcie_writel_atu(struct dw_pcie *pci, u32 dir, u32 index,
+			       u32 reg, u32 val)
 {
+	void __iomem *base;
 	int ret;
 
+	base = dw_pcie_select_atu(pci, dir, index);
+
 	if (pci->ops && pci->ops->write_dbi) {
-		pci->ops->write_dbi(pci, pci->atu_base, reg, 4, val);
+		pci->ops->write_dbi(pci, base, reg, 4, val);
 		return;
 	}
 
-	ret = dw_pcie_write(pci->atu_base + reg, 4, val);
+	ret = dw_pcie_write(base + reg, 4, 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)
+static inline u32 dw_pcie_readl_atu_ob(struct dw_pcie *pci, u32 index, u32 reg)
 {
-	u32 offset = PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(index);
-
-	return dw_pcie_readl_atu(pci, offset + reg);
+	return dw_pcie_readl_atu(pci, PCIE_ATU_REGION_DIR_OB, index, reg);
 }
 
-static void dw_pcie_writel_ob_unroll(struct dw_pcie *pci, u32 index, u32 reg,
-				     u32 val)
+static inline void dw_pcie_writel_atu_ob(struct dw_pcie *pci, u32 index, u32 reg,
+					 u32 val)
 {
-	u32 offset = PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(index);
-
-	dw_pcie_writel_atu(pci, offset + reg, val);
+	dw_pcie_writel_atu(pci, PCIE_ATU_REGION_DIR_OB, index, reg, val);
 }
 
 static inline u32 dw_pcie_enable_ecrc(u32 val)
@@ -266,264 +306,160 @@
 	return val | PCIE_ATU_TD;
 }
 
-static void dw_pcie_prog_outbound_atu_unroll(struct dw_pcie *pci, u8 func_no,
-					     int index, int type,
-					     u64 cpu_addr, u64 pci_addr,
-					     u64 size)
+static int __dw_pcie_prog_outbound_atu(struct dw_pcie *pci, u8 func_no,
+				       int index, int type, u64 cpu_addr,
+				       u64 pci_addr, u64 size)
 {
 	u32 retries, val;
-	u64 limit_addr = cpu_addr + size - 1;
-
-	dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_LOWER_BASE,
-				 lower_32_bits(cpu_addr));
-	dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_UPPER_BASE,
-				 upper_32_bits(cpu_addr));
-	dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_LOWER_LIMIT,
-				 lower_32_bits(limit_addr));
-	dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_UPPER_LIMIT,
-				 upper_32_bits(limit_addr));
-	dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_LOWER_TARGET,
-				 lower_32_bits(pci_addr));
-	dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_UPPER_TARGET,
-				 upper_32_bits(pci_addr));
-	val = type | PCIE_ATU_FUNC_NUM(func_no);
-	val = upper_32_bits(size - 1) ?
-		val | PCIE_ATU_INCREASE_REGION_SIZE : val;
-	if (pci->version == 0x490A)
-		val = dw_pcie_enable_ecrc(val);
-	dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_REGION_CTRL1, val);
-	dw_pcie_writel_ob_unroll(pci, index, PCIE_ATU_UNR_REGION_CTRL2,
-				 PCIE_ATU_ENABLE);
-
-	/*
-	 * Make sure ATU enable takes effect before any subsequent config
-	 * and I/O accesses.
-	 */
-	for (retries = 0; retries < LINK_WAIT_MAX_IATU_RETRIES; retries++) {
-		val = dw_pcie_readl_ob_unroll(pci, index,
-					      PCIE_ATU_UNR_REGION_CTRL2);
-		if (val & PCIE_ATU_ENABLE)
-			return;
-
-		mdelay(LINK_WAIT_IATU);
-	}
-	dev_err(pci->dev, "Outbound iATU is not being enabled\n");
-}
-
-static void __dw_pcie_prog_outbound_atu(struct dw_pcie *pci, u8 func_no,
-					int index, int type, u64 cpu_addr,
-					u64 pci_addr, u64 size)
-{
-	u32 retries, val;
+	u64 limit_addr;
 
 	if (pci->ops && pci->ops->cpu_addr_fixup)
 		cpu_addr = pci->ops->cpu_addr_fixup(pci, cpu_addr);
 
-	if (pci->iatu_unroll_enabled) {
-		dw_pcie_prog_outbound_atu_unroll(pci, func_no, index, type,
-						 cpu_addr, pci_addr, size);
-		return;
-	}
+	limit_addr = cpu_addr + size - 1;
 
-	dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT,
-			   PCIE_ATU_REGION_OUTBOUND | index);
-	dw_pcie_writel_dbi(pci, PCIE_ATU_LOWER_BASE,
-			   lower_32_bits(cpu_addr));
-	dw_pcie_writel_dbi(pci, PCIE_ATU_UPPER_BASE,
-			   upper_32_bits(cpu_addr));
-	dw_pcie_writel_dbi(pci, PCIE_ATU_LIMIT,
-			   lower_32_bits(cpu_addr + size - 1));
-	if (pci->version >= 0x460A)
-		dw_pcie_writel_dbi(pci, PCIE_ATU_UPPER_LIMIT,
-				   upper_32_bits(cpu_addr + size - 1));
-	dw_pcie_writel_dbi(pci, PCIE_ATU_LOWER_TARGET,
-			   lower_32_bits(pci_addr));
-	dw_pcie_writel_dbi(pci, PCIE_ATU_UPPER_TARGET,
-			   upper_32_bits(pci_addr));
-	val = type | PCIE_ATU_FUNC_NUM(func_no);
-	val = ((upper_32_bits(size - 1)) && (pci->version >= 0x460A)) ?
-		val | PCIE_ATU_INCREASE_REGION_SIZE : val;
-	if (pci->version == 0x490A)
-		val = dw_pcie_enable_ecrc(val);
-	dw_pcie_writel_dbi(pci, PCIE_ATU_CR1, val);
-	dw_pcie_writel_dbi(pci, PCIE_ATU_CR2, PCIE_ATU_ENABLE);
-
-	/*
-	 * Make sure ATU enable takes effect before any subsequent config
-	 * and I/O accesses.
-	 */
-	for (retries = 0; retries < LINK_WAIT_MAX_IATU_RETRIES; retries++) {
-		val = dw_pcie_readl_dbi(pci, PCIE_ATU_CR2);
-		if (val & PCIE_ATU_ENABLE)
-			return;
-
-		mdelay(LINK_WAIT_IATU);
-	}
-	dev_err(pci->dev, "Outbound iATU is not being enabled\n");
-}
-
-void dw_pcie_prog_outbound_atu(struct dw_pcie *pci, int index, int type,
-			       u64 cpu_addr, u64 pci_addr, u64 size)
-{
-	__dw_pcie_prog_outbound_atu(pci, 0, index, type,
-				    cpu_addr, pci_addr, size);
-}
-
-void dw_pcie_prog_ep_outbound_atu(struct dw_pcie *pci, u8 func_no, int index,
-				  int type, u64 cpu_addr, u64 pci_addr,
-				  u64 size)
-{
-	__dw_pcie_prog_outbound_atu(pci, func_no, index, type,
-				    cpu_addr, pci_addr, size);
-}
-
-static u32 dw_pcie_readl_ib_unroll(struct dw_pcie *pci, u32 index, u32 reg)
-{
-	u32 offset = PCIE_GET_ATU_INB_UNR_REG_OFFSET(index);
-
-	return dw_pcie_readl_atu(pci, offset + reg);
-}
-
-static void dw_pcie_writel_ib_unroll(struct dw_pcie *pci, u32 index, u32 reg,
-				     u32 val)
-{
-	u32 offset = PCIE_GET_ATU_INB_UNR_REG_OFFSET(index);
-
-	dw_pcie_writel_atu(pci, offset + reg, val);
-}
-
-static int dw_pcie_prog_inbound_atu_unroll(struct dw_pcie *pci, u8 func_no,
-					   int index, int bar, u64 cpu_addr,
-					   enum dw_pcie_as_type as_type)
-{
-	int type;
-	u32 retries, val;
-
-	dw_pcie_writel_ib_unroll(pci, index, PCIE_ATU_UNR_LOWER_TARGET,
-				 lower_32_bits(cpu_addr));
-	dw_pcie_writel_ib_unroll(pci, index, PCIE_ATU_UNR_UPPER_TARGET,
-				 upper_32_bits(cpu_addr));
-
-	switch (as_type) {
-	case DW_PCIE_AS_MEM:
-		type = PCIE_ATU_TYPE_MEM;
-		break;
-	case DW_PCIE_AS_IO:
-		type = PCIE_ATU_TYPE_IO;
-		break;
-	default:
+	if ((limit_addr & ~pci->region_limit) != (cpu_addr & ~pci->region_limit) ||
+	    !IS_ALIGNED(cpu_addr, pci->region_align) ||
+	    !IS_ALIGNED(pci_addr, pci->region_align) || !size) {
 		return -EINVAL;
 	}
 
-	dw_pcie_writel_ib_unroll(pci, index, PCIE_ATU_UNR_REGION_CTRL1, type |
-				 PCIE_ATU_FUNC_NUM(func_no));
-	dw_pcie_writel_ib_unroll(pci, index, PCIE_ATU_UNR_REGION_CTRL2,
-				 PCIE_ATU_FUNC_NUM_MATCH_EN |
-				 PCIE_ATU_ENABLE |
-				 PCIE_ATU_BAR_MODE_ENABLE | (bar << 8));
+	dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_LOWER_BASE,
+			      lower_32_bits(cpu_addr));
+	dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_UPPER_BASE,
+			      upper_32_bits(cpu_addr));
+
+	dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_LIMIT,
+			      lower_32_bits(limit_addr));
+	if (dw_pcie_ver_is_ge(pci, 460A))
+		dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_UPPER_LIMIT,
+				      upper_32_bits(limit_addr));
+
+	dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_LOWER_TARGET,
+			      lower_32_bits(pci_addr));
+	dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_UPPER_TARGET,
+			      upper_32_bits(pci_addr));
+
+	val = type | PCIE_ATU_FUNC_NUM(func_no);
+	if (upper_32_bits(limit_addr) > upper_32_bits(cpu_addr) &&
+	    dw_pcie_ver_is_ge(pci, 460A))
+		val |= PCIE_ATU_INCREASE_REGION_SIZE;
+	if (dw_pcie_ver_is(pci, 490A))
+		val = dw_pcie_enable_ecrc(val);
+	dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_REGION_CTRL1, val);
+
+	dw_pcie_writel_atu_ob(pci, index, PCIE_ATU_REGION_CTRL2, PCIE_ATU_ENABLE);
 
 	/*
 	 * Make sure ATU enable takes effect before any subsequent config
 	 * and I/O accesses.
 	 */
 	for (retries = 0; retries < LINK_WAIT_MAX_IATU_RETRIES; retries++) {
-		val = dw_pcie_readl_ib_unroll(pci, index,
-					      PCIE_ATU_UNR_REGION_CTRL2);
+		val = dw_pcie_readl_atu_ob(pci, index, PCIE_ATU_REGION_CTRL2);
 		if (val & PCIE_ATU_ENABLE)
 			return 0;
 
 		mdelay(LINK_WAIT_IATU);
 	}
-	dev_err(pci->dev, "Inbound iATU is not being enabled\n");
 
-	return -EBUSY;
+	dev_err(pci->dev, "Outbound iATU is not being enabled\n");
+
+	return -ETIMEDOUT;
+}
+
+int dw_pcie_prog_outbound_atu(struct dw_pcie *pci, int index, int type,
+			      u64 cpu_addr, u64 pci_addr, u64 size)
+{
+	return __dw_pcie_prog_outbound_atu(pci, 0, index, type,
+					   cpu_addr, pci_addr, size);
+}
+
+int dw_pcie_prog_ep_outbound_atu(struct dw_pcie *pci, u8 func_no, int index,
+				 int type, u64 cpu_addr, u64 pci_addr,
+				 u64 size)
+{
+	return __dw_pcie_prog_outbound_atu(pci, func_no, index, type,
+					   cpu_addr, pci_addr, size);
+}
+
+static inline u32 dw_pcie_readl_atu_ib(struct dw_pcie *pci, u32 index, u32 reg)
+{
+	return dw_pcie_readl_atu(pci, PCIE_ATU_REGION_DIR_IB, index, reg);
+}
+
+static inline void dw_pcie_writel_atu_ib(struct dw_pcie *pci, u32 index, u32 reg,
+					 u32 val)
+{
+	dw_pcie_writel_atu(pci, PCIE_ATU_REGION_DIR_IB, index, reg, val);
 }
 
 int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, u8 func_no, int index,
-			     int bar, u64 cpu_addr,
-			     enum dw_pcie_as_type as_type)
+			     int type, u64 cpu_addr, u8 bar)
 {
-	int type;
 	u32 retries, val;
 
-	if (pci->iatu_unroll_enabled)
-		return dw_pcie_prog_inbound_atu_unroll(pci, func_no, index, bar,
-						       cpu_addr, as_type);
-
-	dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT, PCIE_ATU_REGION_INBOUND |
-			   index);
-	dw_pcie_writel_dbi(pci, PCIE_ATU_LOWER_TARGET, lower_32_bits(cpu_addr));
-	dw_pcie_writel_dbi(pci, PCIE_ATU_UPPER_TARGET, upper_32_bits(cpu_addr));
-
-	switch (as_type) {
-	case DW_PCIE_AS_MEM:
-		type = PCIE_ATU_TYPE_MEM;
-		break;
-	case DW_PCIE_AS_IO:
-		type = PCIE_ATU_TYPE_IO;
-		break;
-	default:
+	if (!IS_ALIGNED(cpu_addr, pci->region_align))
 		return -EINVAL;
-	}
 
-	dw_pcie_writel_dbi(pci, PCIE_ATU_CR1, type |
-			   PCIE_ATU_FUNC_NUM(func_no));
-	dw_pcie_writel_dbi(pci, PCIE_ATU_CR2, PCIE_ATU_ENABLE |
-			   PCIE_ATU_FUNC_NUM_MATCH_EN |
-			   PCIE_ATU_BAR_MODE_ENABLE | (bar << 8));
+	dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_LOWER_TARGET,
+			      lower_32_bits(cpu_addr));
+	dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_UPPER_TARGET,
+			      upper_32_bits(cpu_addr));
+
+	dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_REGION_CTRL1, type |
+			      PCIE_ATU_FUNC_NUM(func_no));
+	dw_pcie_writel_atu_ib(pci, index, PCIE_ATU_REGION_CTRL2,
+			      PCIE_ATU_ENABLE | PCIE_ATU_FUNC_NUM_MATCH_EN |
+			      PCIE_ATU_BAR_MODE_ENABLE | (bar << 8));
 
 	/*
 	 * Make sure ATU enable takes effect before any subsequent config
 	 * and I/O accesses.
 	 */
 	for (retries = 0; retries < LINK_WAIT_MAX_IATU_RETRIES; retries++) {
-		val = dw_pcie_readl_dbi(pci, PCIE_ATU_CR2);
+		val = dw_pcie_readl_atu_ib(pci, index, PCIE_ATU_REGION_CTRL2);
 		if (val & PCIE_ATU_ENABLE)
 			return 0;
 
 		mdelay(LINK_WAIT_IATU);
 	}
+
 	dev_err(pci->dev, "Inbound iATU is not being enabled\n");
 
-	return -EBUSY;
+	return -ETIMEDOUT;
 }
 
-void dw_pcie_disable_atu(struct dw_pcie *pci, int index,
-			 enum dw_pcie_region_type type)
+void dw_pcie_disable_atu(struct dw_pcie *pci, u32 dir, int index)
 {
-	int region;
-
-	switch (type) {
-	case DW_PCIE_REGION_INBOUND:
-		region = PCIE_ATU_REGION_INBOUND;
-		break;
-	case DW_PCIE_REGION_OUTBOUND:
-		region = PCIE_ATU_REGION_OUTBOUND;
-		break;
-	default:
-		return;
-	}
-
-	dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT, region | index);
-	dw_pcie_writel_dbi(pci, PCIE_ATU_CR2, ~(u32)PCIE_ATU_ENABLE);
+	dw_pcie_writel_atu(pci, dir, index, PCIE_ATU_REGION_CTRL2, 0);
 }
 
 int dw_pcie_wait_for_link(struct dw_pcie *pci)
 {
+	u32 offset, val;
 	int retries;
 
 	/* Check if the link is up or not */
 	for (retries = 0; retries < LINK_WAIT_MAX_RETRIES; retries++) {
-		if (dw_pcie_link_up(pci)) {
-			dev_info(pci->dev, "Link up\n");
-			return 0;
-		}
+		if (dw_pcie_link_up(pci))
+			break;
+
 		usleep_range(LINK_WAIT_USLEEP_MIN, LINK_WAIT_USLEEP_MAX);
 	}
 
-	dev_info(pci->dev, "Phy link never came up\n");
+	if (retries >= LINK_WAIT_MAX_RETRIES) {
+		dev_err(pci->dev, "Phy link never came up\n");
+		return -ETIMEDOUT;
+	}
 
-	return -ETIMEDOUT;
+	offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
+	val = dw_pcie_readw_dbi(pci, offset + PCI_EXP_LNKSTA);
+
+	dev_info(pci->dev, "PCIe Gen.%u x%u link up\n",
+		 FIELD_GET(PCI_EXP_LNKSTA_CLS, val),
+		 FIELD_GET(PCI_EXP_LNKSTA_NLW, val));
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(dw_pcie_wait_for_link);
 
@@ -534,7 +470,7 @@
 	if (pci->ops && pci->ops->link_up)
 		return pci->ops->link_up(pci);
 
-	val = readl(pci->dbi_base + PCIE_PORT_DEBUG1);
+	val = dw_pcie_readl_dbi(pci, PCIE_PORT_DEBUG1);
 	return ((val & PCIE_PORT_DEBUG1_LINK_UP) &&
 		(!(val & PCIE_PORT_DEBUG1_LINK_IN_TRAINING)));
 }
@@ -586,95 +522,81 @@
 
 }
 
-static u8 dw_pcie_iatu_unroll_enabled(struct dw_pcie *pci)
+static bool dw_pcie_iatu_unroll_enabled(struct dw_pcie *pci)
 {
 	u32 val;
 
 	val = dw_pcie_readl_dbi(pci, PCIE_ATU_VIEWPORT);
 	if (val == 0xffffffff)
-		return 1;
+		return true;
 
-	return 0;
-}
-
-static void dw_pcie_iatu_detect_regions_unroll(struct dw_pcie *pci)
-{
-	int max_region, i, ob = 0, ib = 0;
-	u32 val;
-
-	max_region = min((int)pci->atu_size / 512, 256);
-
-	for (i = 0; i < max_region; i++) {
-		dw_pcie_writel_ob_unroll(pci, i, PCIE_ATU_UNR_LOWER_TARGET,
-					0x11110000);
-
-		val = dw_pcie_readl_ob_unroll(pci, i, PCIE_ATU_UNR_LOWER_TARGET);
-		if (val == 0x11110000)
-			ob++;
-		else
-			break;
-	}
-
-	for (i = 0; i < max_region; i++) {
-		dw_pcie_writel_ib_unroll(pci, i, PCIE_ATU_UNR_LOWER_TARGET,
-					0x11110000);
-
-		val = dw_pcie_readl_ib_unroll(pci, i, PCIE_ATU_UNR_LOWER_TARGET);
-		if (val == 0x11110000)
-			ib++;
-		else
-			break;
-	}
-	pci->num_ib_windows = ib;
-	pci->num_ob_windows = ob;
+	return false;
 }
 
 static void dw_pcie_iatu_detect_regions(struct dw_pcie *pci)
 {
-	int max_region, i, ob = 0, ib = 0;
-	u32 val;
+	int max_region, ob, ib;
+	u32 val, min, dir;
+	u64 max;
 
-	dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT, 0xFF);
-	max_region = dw_pcie_readl_dbi(pci, PCIE_ATU_VIEWPORT) + 1;
+	if (pci->iatu_unroll_enabled) {
+		max_region = min((int)pci->atu_size / 512, 256);
+	} else {
+		dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT, 0xFF);
+		max_region = dw_pcie_readl_dbi(pci, PCIE_ATU_VIEWPORT) + 1;
+	}
 
-	for (i = 0; i < max_region; i++) {
-		dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT, PCIE_ATU_REGION_OUTBOUND | i);
-		dw_pcie_writel_dbi(pci, PCIE_ATU_LOWER_TARGET, 0x11110000);
-		val = dw_pcie_readl_dbi(pci, PCIE_ATU_LOWER_TARGET);
-		if (val == 0x11110000)
-			ob++;
-		else
+	for (ob = 0; ob < max_region; ob++) {
+		dw_pcie_writel_atu_ob(pci, ob, PCIE_ATU_LOWER_TARGET, 0x11110000);
+		val = dw_pcie_readl_atu_ob(pci, ob, PCIE_ATU_LOWER_TARGET);
+		if (val != 0x11110000)
 			break;
 	}
 
-	for (i = 0; i < max_region; i++) {
-		dw_pcie_writel_dbi(pci, PCIE_ATU_VIEWPORT, PCIE_ATU_REGION_INBOUND | i);
-		dw_pcie_writel_dbi(pci, PCIE_ATU_LOWER_TARGET, 0x11110000);
-		val = dw_pcie_readl_dbi(pci, PCIE_ATU_LOWER_TARGET);
-		if (val == 0x11110000)
-			ib++;
-		else
+	for (ib = 0; ib < max_region; ib++) {
+		dw_pcie_writel_atu_ib(pci, ib, PCIE_ATU_LOWER_TARGET, 0x11110000);
+		val = dw_pcie_readl_atu_ib(pci, ib, PCIE_ATU_LOWER_TARGET);
+		if (val != 0x11110000)
 			break;
 	}
 
-	pci->num_ib_windows = ib;
+	if (ob) {
+		dir = PCIE_ATU_REGION_DIR_OB;
+	} else if (ib) {
+		dir = PCIE_ATU_REGION_DIR_IB;
+	} else {
+		dev_err(pci->dev, "No iATU regions found\n");
+		return;
+	}
+
+	dw_pcie_writel_atu(pci, dir, 0, PCIE_ATU_LIMIT, 0x0);
+	min = dw_pcie_readl_atu(pci, dir, 0, PCIE_ATU_LIMIT);
+
+	if (dw_pcie_ver_is_ge(pci, 460A)) {
+		dw_pcie_writel_atu(pci, dir, 0, PCIE_ATU_UPPER_LIMIT, 0xFFFFFFFF);
+		max = dw_pcie_readl_atu(pci, dir, 0, PCIE_ATU_UPPER_LIMIT);
+	} else {
+		max = 0;
+	}
+
 	pci->num_ob_windows = ob;
+	pci->num_ib_windows = ib;
+	pci->region_align = 1 << fls(min);
+	pci->region_limit = (max << 32) | (SZ_4G - 1);
 }
 
 void dw_pcie_iatu_detect(struct dw_pcie *pci)
 {
-	struct device *dev = pci->dev;
-	struct platform_device *pdev = to_platform_device(dev);
+	struct platform_device *pdev = to_platform_device(pci->dev);
 
-	if (pci->version >= 0x480A || (!pci->version &&
-				       dw_pcie_iatu_unroll_enabled(pci))) {
-		pci->iatu_unroll_enabled = true;
+	pci->iatu_unroll_enabled = dw_pcie_iatu_unroll_enabled(pci);
+	if (pci->iatu_unroll_enabled) {
 		if (!pci->atu_base) {
 			struct resource *res =
 				platform_get_resource_byname(pdev, IORESOURCE_MEM, "atu");
 			if (res) {
 				pci->atu_size = resource_size(res);
-				pci->atu_base = devm_ioremap_resource(dev, res);
+				pci->atu_base = devm_ioremap_resource(pci->dev, res);
 			}
 			if (!pci->atu_base || IS_ERR(pci->atu_base))
 				pci->atu_base = pci->dbi_base + DEFAULT_DBI_ATU_OFFSET;
@@ -683,23 +605,25 @@
 		if (!pci->atu_size)
 			/* Pick a minimal default, enough for 8 in and 8 out windows */
 			pci->atu_size = SZ_4K;
+	} else {
+		pci->atu_base = pci->dbi_base + PCIE_ATU_VIEWPORT_BASE;
+		pci->atu_size = PCIE_ATU_VIEWPORT_SIZE;
+	}
 
-		dw_pcie_iatu_detect_regions_unroll(pci);
-	} else
-		dw_pcie_iatu_detect_regions(pci);
+	dw_pcie_iatu_detect_regions(pci);
 
 	dev_info(pci->dev, "iATU unroll: %s\n", pci->iatu_unroll_enabled ?
 		"enabled" : "disabled");
 
-	dev_info(pci->dev, "Detected iATU regions: %u outbound, %u inbound",
-		 pci->num_ob_windows, pci->num_ib_windows);
+	dev_info(pci->dev, "iATU regions: %u ob, %u ib, align %uK, limit %lluG\n",
+		 pci->num_ob_windows, pci->num_ib_windows,
+		 pci->region_align / SZ_1K, (pci->region_limit + 1) / SZ_1G);
 }
 
 void dw_pcie_setup(struct dw_pcie *pci)
 {
+	struct device_node *np = pci->dev->of_node;
 	u32 val;
-	struct device *dev = pci->dev;
-	struct device_node *np = dev->of_node;
 
 	if (pci->link_gen > 0)
 		dw_pcie_link_set_max_speed(pci, pci->link_gen);
@@ -726,6 +650,13 @@
 	val |= PORT_LINK_DLL_LINK_EN;
 	dw_pcie_writel_dbi(pci, PCIE_PORT_LINK_CONTROL, val);
 
+	if (of_property_read_bool(np, "snps,enable-cdm-check")) {
+		val = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS);
+		val |= PCIE_PL_CHK_REG_CHK_REG_CONTINUOUS |
+		       PCIE_PL_CHK_REG_CHK_REG_START;
+		dw_pcie_writel_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS, val);
+	}
+
 	of_property_read_u32(np, "num-lanes", &pci->num_lanes);
 	if (!pci->num_lanes) {
 		dev_dbg(pci->dev, "Using h/w default number of lanes\n");
@@ -772,11 +703,4 @@
 		break;
 	}
 	dw_pcie_writel_dbi(pci, PCIE_LINK_WIDTH_SPEED_CONTROL, val);
-
-	if (of_property_read_bool(np, "snps,enable-cdm-check")) {
-		val = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS);
-		val |= PCIE_PL_CHK_REG_CHK_REG_CONTINUOUS |
-		       PCIE_PL_CHK_REG_CHK_REG_START;
-		dw_pcie_writel_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS, val);
-	}
 }
diff --git a/drivers/pci/controller/dwc/pcie-designware.h b/drivers/pci/controller/dwc/pcie-designware.h
index 7d6e9b75..09b8870 100644
--- a/drivers/pci/controller/dwc/pcie-designware.h
+++ b/drivers/pci/controller/dwc/pcie-designware.h
@@ -20,6 +20,29 @@
 #include <linux/pci-epc.h>
 #include <linux/pci-epf.h>
 
+/* DWC PCIe IP-core versions (native support since v4.70a) */
+#define DW_PCIE_VER_365A		0x3336352a
+#define DW_PCIE_VER_460A		0x3436302a
+#define DW_PCIE_VER_470A		0x3437302a
+#define DW_PCIE_VER_480A		0x3438302a
+#define DW_PCIE_VER_490A		0x3439302a
+#define DW_PCIE_VER_520A		0x3532302a
+
+#define __dw_pcie_ver_cmp(_pci, _ver, _op) \
+	((_pci)->version _op DW_PCIE_VER_ ## _ver)
+
+#define dw_pcie_ver_is(_pci, _ver) __dw_pcie_ver_cmp(_pci, _ver, ==)
+
+#define dw_pcie_ver_is_ge(_pci, _ver) __dw_pcie_ver_cmp(_pci, _ver, >=)
+
+#define dw_pcie_ver_type_is(_pci, _ver, _type) \
+	(__dw_pcie_ver_cmp(_pci, _ver, ==) && \
+	 __dw_pcie_ver_cmp(_pci, TYPE_ ## _type, ==))
+
+#define dw_pcie_ver_type_is_ge(_pci, _ver, _type) \
+	(__dw_pcie_ver_cmp(_pci, _ver, ==) && \
+	 __dw_pcie_ver_cmp(_pci, TYPE_ ## _type, >=))
+
 /* Parameters for the waiting for link up routine */
 #define LINK_WAIT_MAX_RETRIES		10
 #define LINK_WAIT_USLEEP_MIN		90000
@@ -74,13 +97,34 @@
 #define PCIE_MSI_INTR0_MASK		0x82C
 #define PCIE_MSI_INTR0_STATUS		0x830
 
+#define GEN3_RELATED_OFF			0x890
+#define GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL	BIT(0)
+#define GEN3_RELATED_OFF_RXEQ_RGRDLESS_RXTS	BIT(13)
+#define GEN3_RELATED_OFF_GEN3_EQ_DISABLE	BIT(16)
+#define GEN3_RELATED_OFF_RATE_SHADOW_SEL_SHIFT	24
+#define GEN3_RELATED_OFF_RATE_SHADOW_SEL_MASK	GENMASK(25, 24)
+
 #define PCIE_PORT_MULTI_LANE_CTRL	0x8C0
 #define PORT_MLTI_UPCFG_SUPPORT		BIT(7)
 
+#define PCIE_VERSION_NUMBER		0x8F8
+#define PCIE_VERSION_TYPE		0x8FC
+
+/*
+ * iATU inbound and outbound windows CSRs. Before the IP-core v4.80a each
+ * iATU region CSRs had been indirectly accessible by means of the dedicated
+ * viewport selector. The iATU/eDMA CSRs space was re-designed in DWC PCIe
+ * v4.80a in a way so the viewport was unrolled into the directly accessible
+ * iATU/eDMA CSRs space.
+ */
 #define PCIE_ATU_VIEWPORT		0x900
-#define PCIE_ATU_REGION_INBOUND		BIT(31)
-#define PCIE_ATU_REGION_OUTBOUND	0
-#define PCIE_ATU_CR1			0x904
+#define PCIE_ATU_REGION_DIR_IB		BIT(31)
+#define PCIE_ATU_REGION_DIR_OB		0
+#define PCIE_ATU_VIEWPORT_BASE		0x904
+#define PCIE_ATU_UNROLL_BASE(dir, index) \
+	(((index) << 9) | ((dir == PCIE_ATU_REGION_DIR_IB) ? BIT(8) : 0))
+#define PCIE_ATU_VIEWPORT_SIZE		0x2C
+#define PCIE_ATU_REGION_CTRL1		0x000
 #define PCIE_ATU_INCREASE_REGION_SIZE	BIT(13)
 #define PCIE_ATU_TYPE_MEM		0x0
 #define PCIE_ATU_TYPE_IO		0x2
@@ -88,19 +132,19 @@
 #define PCIE_ATU_TYPE_CFG1		0x5
 #define PCIE_ATU_TD			BIT(8)
 #define PCIE_ATU_FUNC_NUM(pf)           ((pf) << 20)
-#define PCIE_ATU_CR2			0x908
+#define PCIE_ATU_REGION_CTRL2		0x004
 #define PCIE_ATU_ENABLE			BIT(31)
 #define PCIE_ATU_BAR_MODE_ENABLE	BIT(30)
 #define PCIE_ATU_FUNC_NUM_MATCH_EN      BIT(19)
-#define PCIE_ATU_LOWER_BASE		0x90C
-#define PCIE_ATU_UPPER_BASE		0x910
-#define PCIE_ATU_LIMIT			0x914
-#define PCIE_ATU_LOWER_TARGET		0x918
+#define PCIE_ATU_LOWER_BASE		0x008
+#define PCIE_ATU_UPPER_BASE		0x00C
+#define PCIE_ATU_LIMIT			0x010
+#define PCIE_ATU_LOWER_TARGET		0x014
 #define PCIE_ATU_BUS(x)			FIELD_PREP(GENMASK(31, 24), x)
 #define PCIE_ATU_DEV(x)			FIELD_PREP(GENMASK(23, 19), x)
 #define PCIE_ATU_FUNC(x)		FIELD_PREP(GENMASK(18, 16), x)
-#define PCIE_ATU_UPPER_TARGET		0x91C
-#define PCIE_ATU_UPPER_LIMIT		0x924
+#define PCIE_ATU_UPPER_TARGET		0x018
+#define PCIE_ATU_UPPER_LIMIT		0x020
 
 #define PCIE_MISC_CONTROL_1_OFF		0x8BC
 #define PCIE_DBI_RO_WR_EN		BIT(0)
@@ -131,6 +175,25 @@
 #define PCIE_ATU_UNR_UPPER_LIMIT	0x20
 
 /*
+ * RAS-DES register definitions
+ */
+#define PCIE_RAS_DES_EVENT_COUNTER_CONTROL	0x8
+#define EVENT_COUNTER_ALL_CLEAR		0x3
+#define EVENT_COUNTER_ENABLE_ALL	0x7
+#define EVENT_COUNTER_ENABLE_SHIFT	2
+#define EVENT_COUNTER_EVENT_SEL_MASK	GENMASK(7, 0)
+#define EVENT_COUNTER_EVENT_SEL_SHIFT	16
+#define EVENT_COUNTER_EVENT_Tx_L0S	0x2
+#define EVENT_COUNTER_EVENT_Rx_L0S	0x3
+#define EVENT_COUNTER_EVENT_L1		0x5
+#define EVENT_COUNTER_EVENT_L1_1	0x7
+#define EVENT_COUNTER_EVENT_L1_2	0x8
+#define EVENT_COUNTER_GROUP_SEL_SHIFT	24
+#define EVENT_COUNTER_GROUP_5		0x5
+
+#define PCIE_RAS_DES_EVENT_COUNTER_DATA		0xc
+
+/*
  * The default address offset between dbi_base and atu_base. Root controller
  * drivers are not required to initialize atu_base if the offset matches this
  * default; the driver core automatically derives atu_base from dbi_base using
@@ -138,13 +201,6 @@
  */
 #define DEFAULT_DBI_ATU_OFFSET (0x3 << 20)
 
-/* Register address builder */
-#define PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(region) \
-		((region) << 9)
-
-#define PCIE_GET_ATU_INB_UNR_REG_OFFSET(region) \
-		(((region) << 9) | BIT(8))
-
 #define MAX_MSI_IRQS			256
 #define MAX_MSI_IRQS_PER_CTRL		32
 #define MAX_MSI_CTRLS			(MAX_MSI_IRQS / MAX_MSI_IRQS_PER_CTRL)
@@ -155,16 +211,10 @@
 #define MAX_IATU_IN			256
 #define MAX_IATU_OUT			256
 
-struct pcie_port;
 struct dw_pcie;
+struct dw_pcie_rp;
 struct dw_pcie_ep;
 
-enum dw_pcie_region_type {
-	DW_PCIE_REGION_UNKNOWN,
-	DW_PCIE_REGION_INBOUND,
-	DW_PCIE_REGION_OUTBOUND,
-};
-
 enum dw_pcie_device_mode {
 	DW_PCIE_UNKNOWN_TYPE,
 	DW_PCIE_EP_TYPE,
@@ -173,12 +223,14 @@
 };
 
 struct dw_pcie_host_ops {
-	int (*host_init)(struct pcie_port *pp);
-	int (*msi_host_init)(struct pcie_port *pp);
+	int (*host_init)(struct dw_pcie_rp *pp);
+	void (*host_deinit)(struct dw_pcie_rp *pp);
+	int (*msi_host_init)(struct dw_pcie_rp *pp);
 };
 
-struct pcie_port {
+struct dw_pcie_rp {
 	bool			has_msi_ctrl:1;
+	bool			cfg0_io_shared:1;
 	u64			cfg0_base;
 	void __iomem		*va_cfg0_base;
 	u32			cfg0_size;
@@ -187,11 +239,11 @@
 	u32			io_size;
 	int			irq;
 	const struct dw_pcie_host_ops *ops;
-	int			msi_irq;
+	int			msi_irq[MAX_MSI_CTRLS];
 	struct irq_domain	*irq_domain;
 	struct irq_domain	*msi_domain;
-	u16			msi_msg;
 	dma_addr_t		msi_data;
+	struct page		*msi_page;
 	struct irq_chip		*msi_irq_chip;
 	u32			num_vectors;
 	u32			irq_mask[MAX_MSI_CTRLS];
@@ -200,12 +252,6 @@
 	DECLARE_BITMAP(msi_irq_in_use, MAX_MSI_IRQS);
 };
 
-enum dw_pcie_as_type {
-	DW_PCIE_AS_UNKNOWN,
-	DW_PCIE_AS_MEM,
-	DW_PCIE_AS_IO,
-};
-
 struct dw_pcie_ep_ops {
 	void	(*ep_init)(struct dw_pcie_ep *ep);
 	int	(*raise_irq)(struct dw_pcie_ep *ep, u8 func_no,
@@ -261,20 +307,21 @@
 	struct device		*dev;
 	void __iomem		*dbi_base;
 	void __iomem		*dbi_base2;
-	/* Used when iatu_unroll_enabled is true */
 	void __iomem		*atu_base;
 	size_t			atu_size;
 	u32			num_ib_windows;
 	u32			num_ob_windows;
-	struct pcie_port	pp;
+	u32			region_align;
+	u64			region_limit;
+	struct dw_pcie_rp	pp;
 	struct dw_pcie_ep	ep;
 	const struct dw_pcie_ops *ops;
-	unsigned int		version;
+	u32			version;
+	u32			type;
 	int			num_lanes;
 	int			link_gen;
 	u8			n_fts[2];
 	bool			iatu_unroll_enabled: 1;
-	bool			io_cfg_atu_shared: 1;
 };
 
 #define to_dw_pcie_from_pp(port) container_of((port), struct dw_pcie, pp)
@@ -282,6 +329,8 @@
 #define to_dw_pcie_from_ep(endpoint)   \
 		container_of((endpoint), struct dw_pcie, ep)
 
+void dw_pcie_version_detect(struct dw_pcie *pci);
+
 u8 dw_pcie_find_capability(struct dw_pcie *pci, u8 cap);
 u16 dw_pcie_find_ext_capability(struct dw_pcie *pci, u8 cap);
 
@@ -294,17 +343,13 @@
 int dw_pcie_link_up(struct dw_pcie *pci);
 void dw_pcie_upconfig_setup(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,
-			       int type, u64 cpu_addr, u64 pci_addr,
-			       u64 size);
-void dw_pcie_prog_ep_outbound_atu(struct dw_pcie *pci, u8 func_no, int index,
-				  int type, u64 cpu_addr, u64 pci_addr,
-				  u64 size);
+int dw_pcie_prog_outbound_atu(struct dw_pcie *pci, int index, int type,
+			      u64 cpu_addr, u64 pci_addr, u64 size);
+int dw_pcie_prog_ep_outbound_atu(struct dw_pcie *pci, u8 func_no, int index,
+				 int type, u64 cpu_addr, u64 pci_addr, u64 size);
 int dw_pcie_prog_inbound_atu(struct dw_pcie *pci, u8 func_no, int index,
-			     int bar, u64 cpu_addr,
-			     enum dw_pcie_as_type as_type);
-void dw_pcie_disable_atu(struct dw_pcie *pci, int index,
-			 enum dw_pcie_region_type type);
+			     int type, u64 cpu_addr, u8 bar);
+void dw_pcie_disable_atu(struct dw_pcie *pci, u32 dir, int index);
 void dw_pcie_setup(struct dw_pcie *pci);
 void dw_pcie_iatu_detect(struct dw_pcie *pci);
 
@@ -365,34 +410,49 @@
 	dw_pcie_writel_dbi(pci, reg, val);
 }
 
+static inline int dw_pcie_start_link(struct dw_pcie *pci)
+{
+	if (pci->ops && pci->ops->start_link)
+		return pci->ops->start_link(pci);
+
+	return 0;
+}
+
+static inline void dw_pcie_stop_link(struct dw_pcie *pci)
+{
+	if (pci->ops && pci->ops->stop_link)
+		pci->ops->stop_link(pci);
+}
+
 #ifdef CONFIG_PCIE_DW_HOST
-irqreturn_t dw_handle_msi_irq(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);
+irqreturn_t dw_handle_msi_irq(struct dw_pcie_rp *pp);
+int dw_pcie_setup_rc(struct dw_pcie_rp *pp);
+int dw_pcie_host_init(struct dw_pcie_rp *pp);
+void dw_pcie_host_deinit(struct dw_pcie_rp *pp);
+int dw_pcie_allocate_domains(struct dw_pcie_rp *pp);
 void __iomem *dw_pcie_own_conf_map_bus(struct pci_bus *bus, unsigned int devfn,
 				       int where);
 #else
-static inline irqreturn_t dw_handle_msi_irq(struct pcie_port *pp)
+static inline irqreturn_t dw_handle_msi_irq(struct dw_pcie_rp *pp)
 {
 	return IRQ_NONE;
 }
 
-static inline void dw_pcie_setup_rc(struct pcie_port *pp)
-{
-}
-
-static inline int dw_pcie_host_init(struct pcie_port *pp)
+static inline int dw_pcie_setup_rc(struct dw_pcie_rp *pp)
 {
 	return 0;
 }
 
-static inline void dw_pcie_host_deinit(struct pcie_port *pp)
+static inline int dw_pcie_host_init(struct dw_pcie_rp *pp)
+{
+	return 0;
+}
+
+static inline void dw_pcie_host_deinit(struct dw_pcie_rp *pp)
 {
 }
 
-static inline int dw_pcie_allocate_domains(struct pcie_port *pp)
+static inline int dw_pcie_allocate_domains(struct dw_pcie_rp *pp)
 {
 	return 0;
 }
diff --git a/drivers/pci/controller/dwc/pcie-dw-rockchip.c b/drivers/pci/controller/dwc/pcie-dw-rockchip.c
index 8c5bb9d..c1e7653 100644
--- a/drivers/pci/controller/dwc/pcie-dw-rockchip.c
+++ b/drivers/pci/controller/dwc/pcie-dw-rockchip.c
@@ -186,7 +186,7 @@
 	return 0;
 }
 
-static int rockchip_pcie_host_init(struct pcie_port *pp)
+static int rockchip_pcie_host_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct rockchip_pcie *rockchip = to_rockchip_pcie(pci);
@@ -288,7 +288,7 @@
 {
 	struct device *dev = &pdev->dev;
 	struct rockchip_pcie *rockchip;
-	struct pcie_port *pp;
+	struct dw_pcie_rp *pp;
 	int ret;
 
 	rockchip = devm_kzalloc(dev, sizeof(*rockchip), GFP_KERNEL);
diff --git a/drivers/pci/controller/dwc/pcie-fu740.c b/drivers/pci/controller/dwc/pcie-fu740.c
index 02cc70d..0c90583c 100644
--- a/drivers/pci/controller/dwc/pcie-fu740.c
+++ b/drivers/pci/controller/dwc/pcie-fu740.c
@@ -16,11 +16,9 @@
 #include <linux/gpio.h>
 #include <linux/gpio/consumer.h>
 #include <linux/kernel.h>
-#include <linux/mfd/syscon.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/platform_device.h>
-#include <linux/regulator/consumer.h>
 #include <linux/resource.h>
 #include <linux/types.h>
 #include <linux/interrupt.h>
@@ -236,7 +234,7 @@
 	return ret;
 }
 
-static int fu740_pcie_host_init(struct pcie_port *pp)
+static int fu740_pcie_host_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct fu740_pcie *afp = to_fu740_pcie(pci);
diff --git a/drivers/pci/controller/dwc/pcie-histb.c b/drivers/pci/controller/dwc/pcie-histb.c
index 410555d..e2b80f1 100644
--- a/drivers/pci/controller/dwc/pcie-histb.c
+++ b/drivers/pci/controller/dwc/pcie-histb.c
@@ -74,7 +74,7 @@
 	writel(val, histb_pcie->ctrl + reg);
 }
 
-static void histb_pcie_dbi_w_mode(struct pcie_port *pp, bool enable)
+static void histb_pcie_dbi_w_mode(struct dw_pcie_rp *pp, bool enable)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct histb_pcie *hipcie = to_histb_pcie(pci);
@@ -88,7 +88,7 @@
 	histb_pcie_writel(hipcie, PCIE_SYS_CTRL0, val);
 }
 
-static void histb_pcie_dbi_r_mode(struct pcie_port *pp, bool enable)
+static void histb_pcie_dbi_r_mode(struct dw_pcie_rp *pp, bool enable)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct histb_pcie *hipcie = to_histb_pcie(pci);
@@ -180,7 +180,7 @@
 	return 0;
 }
 
-static int histb_pcie_host_init(struct pcie_port *pp)
+static int histb_pcie_host_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct histb_pcie *hipcie = to_histb_pcie(pci);
@@ -219,7 +219,7 @@
 		regulator_disable(hipcie->vpcie);
 }
 
-static int histb_pcie_host_enable(struct pcie_port *pp)
+static int histb_pcie_host_enable(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct histb_pcie *hipcie = to_histb_pcie(pci);
@@ -297,7 +297,7 @@
 {
 	struct histb_pcie *hipcie;
 	struct dw_pcie *pci;
-	struct pcie_port *pp;
+	struct dw_pcie_rp *pp;
 	struct device_node *np = pdev->dev.of_node;
 	struct device *dev = &pdev->dev;
 	enum of_gpio_flags of_flags;
diff --git a/drivers/pci/controller/dwc/pcie-intel-gw.c b/drivers/pci/controller/dwc/pcie-intel-gw.c
index 5ba1449..c348120 100644
--- a/drivers/pci/controller/dwc/pcie-intel-gw.c
+++ b/drivers/pci/controller/dwc/pcie-intel-gw.c
@@ -58,10 +58,6 @@
 #define BUS_IATU_OFFSET			SZ_256M
 #define RESET_INTERVAL_MS		100
 
-struct intel_pcie_soc {
-	unsigned int	pcie_ver;
-};
-
 struct intel_pcie {
 	struct dw_pcie		pci;
 	void __iomem		*app_base;
@@ -306,7 +302,11 @@
 	intel_pcie_ltssm_disable(pcie);
 	intel_pcie_link_setup(pcie);
 	intel_pcie_init_n_fts(pci);
-	dw_pcie_setup_rc(&pci->pp);
+
+	ret = dw_pcie_setup_rc(&pci->pp);
+	if (ret)
+		goto app_init_err;
+
 	dw_pcie_upconfig_setup(pci);
 
 	intel_pcie_device_rst_deassert(pcie);
@@ -343,7 +343,7 @@
 static int intel_pcie_remove(struct platform_device *pdev)
 {
 	struct intel_pcie *pcie = platform_get_drvdata(pdev);
-	struct pcie_port *pp = &pcie->pci.pp;
+	struct dw_pcie_rp *pp = &pcie->pci.pp;
 
 	dw_pcie_host_deinit(pp);
 	__intel_pcie_remove(pcie);
@@ -373,7 +373,7 @@
 	return intel_pcie_host_setup(pcie);
 }
 
-static int intel_pcie_rc_init(struct pcie_port *pp)
+static int intel_pcie_rc_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct intel_pcie *pcie = dev_get_drvdata(pci->dev);
@@ -394,16 +394,11 @@
 	.host_init =		intel_pcie_rc_init,
 };
 
-static const struct intel_pcie_soc pcie_data = {
-	.pcie_ver =		0x520A,
-};
-
 static int intel_pcie_probe(struct platform_device *pdev)
 {
-	const struct intel_pcie_soc *data;
 	struct device *dev = &pdev->dev;
 	struct intel_pcie *pcie;
-	struct pcie_port *pp;
+	struct dw_pcie_rp *pp;
 	struct dw_pcie *pci;
 	int ret;
 
@@ -424,12 +419,7 @@
 	if (ret)
 		return ret;
 
-	data = device_get_match_data(dev);
-	if (!data)
-		return -ENODEV;
-
 	pci->ops = &intel_pcie_ops;
-	pci->version = data->pcie_ver;
 	pp->ops = &intel_pcie_dw_ops;
 
 	ret = dw_pcie_host_init(pp);
@@ -447,7 +437,7 @@
 };
 
 static const struct of_device_id of_intel_pcie_match[] = {
-	{ .compatible = "intel,lgm-pcie", .data = &pcie_data },
+	{ .compatible = "intel,lgm-pcie" },
 	{}
 };
 
diff --git a/drivers/pci/controller/dwc/pcie-keembay.c b/drivers/pci/controller/dwc/pcie-keembay.c
index 1ac29a6..f90f36b 100644
--- a/drivers/pci/controller/dwc/pcie-keembay.c
+++ b/drivers/pci/controller/dwc/pcie-keembay.c
@@ -231,7 +231,7 @@
 	struct keembay_pcie *pcie = irq_desc_get_handler_data(desc);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
 	u32 val, mask, status;
-	struct pcie_port *pp;
+	struct dw_pcie_rp *pp;
 
 	/*
 	 * Keem Bay PCIe Controller provides an additional IP logic on top of
@@ -332,13 +332,13 @@
 				      struct platform_device *pdev)
 {
 	struct dw_pcie *pci = &pcie->pci;
-	struct pcie_port *pp = &pci->pp;
+	struct dw_pcie_rp *pp = &pci->pp;
 	struct device *dev = &pdev->dev;
 	u32 val;
 	int ret;
 
 	pp->ops = &keembay_pcie_host_ops;
-	pp->msi_irq = -ENODEV;
+	pp->msi_irq[0] = -ENODEV;
 
 	ret = keembay_pcie_setup_msi_irq(pcie);
 	if (ret)
diff --git a/drivers/pci/controller/dwc/pcie-kirin.c b/drivers/pci/controller/dwc/pcie-kirin.c
index a52cad2..7f67aad 100644
--- a/drivers/pci/controller/dwc/pcie-kirin.c
+++ b/drivers/pci/controller/dwc/pcie-kirin.c
@@ -620,7 +620,7 @@
 	return 0;
 }
 
-static int kirin_pcie_host_init(struct pcie_port *pp)
+static int kirin_pcie_host_init(struct dw_pcie_rp *pp)
 {
 	pp->bridge->ops = &kirin_pci_ops;
 
diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
index 2ea1375..66886dc 100644
--- a/drivers/pci/controller/dwc/pcie-qcom.c
+++ b/drivers/pci/controller/dwc/pcie-qcom.c
@@ -41,6 +41,9 @@
 #define L23_CLK_RMV_DIS				BIT(2)
 #define L1_CLK_RMV_DIS				BIT(1)
 
+#define PCIE20_PARF_PM_CTRL			0x20
+#define REQ_NOT_ENTR_L1				BIT(5)
+
 #define PCIE20_PARF_PHY_CTRL			0x40
 #define PHY_CTRL_PHY_TX0_TERM_OFFSET_MASK	GENMASK(20, 16)
 #define PHY_CTRL_PHY_TX0_TERM_OFFSET(x)		((x) << 16)
@@ -52,6 +55,10 @@
 #define PCIE20_PARF_DBI_BASE_ADDR		0x168
 #define PCIE20_PARF_SLV_ADDR_SPACE_SIZE		0x16C
 #define PCIE20_PARF_MHI_CLOCK_RESET_CTRL	0x174
+#define AHB_CLK_EN				BIT(0)
+#define MSTR_AXI_CLK_EN				BIT(1)
+#define BYPASS					BIT(4)
+
 #define PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT	0x178
 #define PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT_V2	0x1A8
 #define PCIE20_PARF_LTSSM			0x1B0
@@ -69,7 +76,20 @@
 #define PCIE20_AXI_MSTR_RESP_COMP_CTRL1		0x81c
 #define CFG_BRIDGE_SB_INIT			BIT(0)
 
-#define PCIE_CAP_LINK1_VAL			0x2FD7F
+#define PCIE_CAP_SLOT_POWER_LIMIT_VAL		FIELD_PREP(PCI_EXP_SLTCAP_SPLV, \
+						250)
+#define PCIE_CAP_SLOT_POWER_LIMIT_SCALE		FIELD_PREP(PCI_EXP_SLTCAP_SPLS, \
+						1)
+#define PCIE_CAP_SLOT_VAL			(PCI_EXP_SLTCAP_ABP | \
+						PCI_EXP_SLTCAP_PCP | \
+						PCI_EXP_SLTCAP_MRLSP | \
+						PCI_EXP_SLTCAP_AIP | \
+						PCI_EXP_SLTCAP_PIP | \
+						PCI_EXP_SLTCAP_HPS | \
+						PCI_EXP_SLTCAP_HPC | \
+						PCI_EXP_SLTCAP_EIP | \
+						PCIE_CAP_SLOT_POWER_LIMIT_VAL | \
+						PCIE_CAP_SLOT_POWER_LIMIT_SCALE)
 
 #define PCIE20_PARF_Q2A_FLUSH			0x1AC
 
@@ -128,7 +148,6 @@
 	struct clk *master_clk;
 	struct clk *slave_clk;
 	struct clk *cfg_clk;
-	struct clk *pipe_clk;
 	struct regulator_bulk_data supplies[QCOM_PCIE_2_3_2_MAX_SUPPLY];
 };
 
@@ -165,10 +184,11 @@
 	int num_clks;
 	struct regulator_bulk_data supplies[2];
 	struct reset_control *pci_reset;
-	struct clk *pipe_clk;
-	struct clk *pipe_clk_src;
-	struct clk *phy_pipe_clk;
-	struct clk *ref_clk_src;
+};
+
+struct qcom_pcie_resources_2_9_0 {
+	struct clk_bulk_data clks[5];
+	struct reset_control *rst;
 };
 
 union qcom_pcie_resources {
@@ -178,6 +198,7 @@
 	struct qcom_pcie_resources_2_3_3 v2_3_3;
 	struct qcom_pcie_resources_2_4_0 v2_4_0;
 	struct qcom_pcie_resources_2_7_0 v2_7_0;
+	struct qcom_pcie_resources_2_9_0 v2_9_0;
 };
 
 struct qcom_pcie;
@@ -194,7 +215,6 @@
 
 struct qcom_pcie_cfg {
 	const struct qcom_pcie_ops *ops;
-	unsigned int pipe_clk_need_muxing:1;
 	unsigned int has_tbu_clk:1;
 	unsigned int has_ddrss_sf_tbu_clk:1;
 	unsigned int has_aggre0_clk:1;
@@ -325,8 +345,6 @@
 	struct qcom_pcie_resources_2_1_0 *res = &pcie->res.v2_1_0;
 	struct dw_pcie *pci = pcie->pci;
 	struct device *dev = pci->dev;
-	struct device_node *node = dev->of_node;
-	u32 val;
 	int ret;
 
 	/* reset the PCIe interface as uboot can leave it undefined state */
@@ -337,8 +355,6 @@
 	reset_control_assert(res->ext_reset);
 	reset_control_assert(res->phy_reset);
 
-	writel(1, pcie->parf + PCIE20_PARF_PHY_CTRL);
-
 	ret = regulator_bulk_enable(ARRAY_SIZE(res->supplies), res->supplies);
 	if (ret < 0) {
 		dev_err(dev, "cannot enable regulators\n");
@@ -381,15 +397,42 @@
 		goto err_deassert_axi;
 	}
 
-	ret = clk_bulk_prepare_enable(ARRAY_SIZE(res->clks), res->clks);
-	if (ret)
-		goto err_clks;
+	return 0;
+
+err_deassert_axi:
+	reset_control_assert(res->por_reset);
+err_deassert_por:
+	reset_control_assert(res->pci_reset);
+err_deassert_pci:
+	reset_control_assert(res->phy_reset);
+err_deassert_phy:
+	reset_control_assert(res->ext_reset);
+err_deassert_ext:
+	reset_control_assert(res->ahb_reset);
+err_deassert_ahb:
+	regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies);
+
+	return ret;
+}
+
+static int qcom_pcie_post_init_2_1_0(struct qcom_pcie *pcie)
+{
+	struct qcom_pcie_resources_2_1_0 *res = &pcie->res.v2_1_0;
+	struct dw_pcie *pci = pcie->pci;
+	struct device *dev = pci->dev;
+	struct device_node *node = dev->of_node;
+	u32 val;
+	int ret;
 
 	/* enable PCIe clocks and resets */
 	val = readl(pcie->parf + PCIE20_PARF_PHY_CTRL);
 	val &= ~BIT(0);
 	writel(val, pcie->parf + PCIE20_PARF_PHY_CTRL);
 
+	ret = clk_bulk_prepare_enable(ARRAY_SIZE(res->clks), res->clks);
+	if (ret)
+		return ret;
+
 	if (of_device_is_compatible(node, "qcom,pcie-ipq8064") ||
 	    of_device_is_compatible(node, "qcom,pcie-ipq8064-v2")) {
 		writel(PCS_DEEMPH_TX_DEEMPH_GEN1(24) |
@@ -428,23 +471,6 @@
 	       pci->dbi_base + PCIE20_AXI_MSTR_RESP_COMP_CTRL1);
 
 	return 0;
-
-err_clks:
-	reset_control_assert(res->axi_reset);
-err_deassert_axi:
-	reset_control_assert(res->por_reset);
-err_deassert_por:
-	reset_control_assert(res->pci_reset);
-err_deassert_pci:
-	reset_control_assert(res->phy_reset);
-err_deassert_phy:
-	reset_control_assert(res->ext_reset);
-err_deassert_ext:
-	reset_control_assert(res->ahb_reset);
-err_deassert_ahb:
-	regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies);
-
-	return ret;
 }
 
 static int qcom_pcie_get_resources_1_0_0(struct qcom_pcie *pcie)
@@ -532,16 +558,6 @@
 		goto err_slave;
 	}
 
-	/* change DBI base address */
-	writel(0, pcie->parf + PCIE20_PARF_DBI_BASE_ADDR);
-
-	if (IS_ENABLED(CONFIG_PCI_MSI)) {
-		u32 val = readl(pcie->parf + PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT);
-
-		val |= BIT(31);
-		writel(val, pcie->parf + PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT);
-	}
-
 	return 0;
 err_slave:
 	clk_disable_unprepare(res->slave_bus);
@@ -557,6 +573,21 @@
 	return ret;
 }
 
+static int qcom_pcie_post_init_1_0_0(struct qcom_pcie *pcie)
+{
+	/* change DBI base address */
+	writel(0, pcie->parf + PCIE20_PARF_DBI_BASE_ADDR);
+
+	if (IS_ENABLED(CONFIG_PCI_MSI)) {
+		u32 val = readl(pcie->parf + PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT);
+
+		val |= BIT(31);
+		writel(val, pcie->parf + PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT);
+	}
+
+	return 0;
+}
+
 static void qcom_pcie_2_3_2_ltssm_enable(struct qcom_pcie *pcie)
 {
 	u32 val;
@@ -597,8 +628,7 @@
 	if (IS_ERR(res->slave_clk))
 		return PTR_ERR(res->slave_clk);
 
-	res->pipe_clk = devm_clk_get(dev, "pipe");
-	return PTR_ERR_OR_ZERO(res->pipe_clk);
+	return 0;
 }
 
 static void qcom_pcie_deinit_2_3_2(struct qcom_pcie *pcie)
@@ -613,19 +643,11 @@
 	regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies);
 }
 
-static void qcom_pcie_post_deinit_2_3_2(struct qcom_pcie *pcie)
-{
-	struct qcom_pcie_resources_2_3_2 *res = &pcie->res.v2_3_2;
-
-	clk_disable_unprepare(res->pipe_clk);
-}
-
 static int qcom_pcie_init_2_3_2(struct qcom_pcie *pcie)
 {
 	struct qcom_pcie_resources_2_3_2 *res = &pcie->res.v2_3_2;
 	struct dw_pcie *pci = pcie->pci;
 	struct device *dev = pci->dev;
-	u32 val;
 	int ret;
 
 	ret = regulator_bulk_enable(ARRAY_SIZE(res->supplies), res->supplies);
@@ -658,6 +680,25 @@
 		goto err_slave_clk;
 	}
 
+	return 0;
+
+err_slave_clk:
+	clk_disable_unprepare(res->master_clk);
+err_master_clk:
+	clk_disable_unprepare(res->cfg_clk);
+err_cfg_clk:
+	clk_disable_unprepare(res->aux_clk);
+
+err_aux_clk:
+	regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies);
+
+	return ret;
+}
+
+static int qcom_pcie_post_init_2_3_2(struct qcom_pcie *pcie)
+{
+	u32 val;
+
 	/* enable PCIe clocks and resets */
 	val = readl(pcie->parf + PCIE20_PARF_PHY_CTRL);
 	val &= ~BIT(0);
@@ -680,34 +721,6 @@
 	writel(val, pcie->parf + PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT_V2);
 
 	return 0;
-
-err_slave_clk:
-	clk_disable_unprepare(res->master_clk);
-err_master_clk:
-	clk_disable_unprepare(res->cfg_clk);
-err_cfg_clk:
-	clk_disable_unprepare(res->aux_clk);
-
-err_aux_clk:
-	regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies);
-
-	return ret;
-}
-
-static int qcom_pcie_post_init_2_3_2(struct qcom_pcie *pcie)
-{
-	struct qcom_pcie_resources_2_3_2 *res = &pcie->res.v2_3_2;
-	struct dw_pcie *pci = pcie->pci;
-	struct device *dev = pci->dev;
-	int ret;
-
-	ret = clk_prepare_enable(res->pipe_clk);
-	if (ret) {
-		dev_err(dev, "cannot prepare/enable pipe clock\n");
-		return ret;
-	}
-
-	return 0;
 }
 
 static int qcom_pcie_get_resources_2_4_0(struct qcom_pcie *pcie)
@@ -814,7 +827,6 @@
 	struct qcom_pcie_resources_2_4_0 *res = &pcie->res.v2_4_0;
 	struct dw_pcie *pci = pcie->pci;
 	struct device *dev = pci->dev;
-	u32 val;
 	int ret;
 
 	ret = reset_control_assert(res->axi_m_reset);
@@ -939,6 +951,33 @@
 	if (ret)
 		goto err_clks;
 
+	return 0;
+
+err_clks:
+	reset_control_assert(res->ahb_reset);
+err_rst_ahb:
+	reset_control_assert(res->pwr_reset);
+err_rst_pwr:
+	reset_control_assert(res->axi_s_reset);
+err_rst_axi_s:
+	reset_control_assert(res->axi_m_sticky_reset);
+err_rst_axi_m_sticky:
+	reset_control_assert(res->axi_m_reset);
+err_rst_axi_m:
+	reset_control_assert(res->pipe_sticky_reset);
+err_rst_pipe_sticky:
+	reset_control_assert(res->pipe_reset);
+err_rst_pipe:
+	reset_control_assert(res->phy_reset);
+err_rst_phy:
+	reset_control_assert(res->phy_ahb_reset);
+	return ret;
+}
+
+static int qcom_pcie_post_init_2_4_0(struct qcom_pcie *pcie)
+{
+	u32 val;
+
 	/* enable PCIe clocks and resets */
 	val = readl(pcie->parf + PCIE20_PARF_PHY_CTRL);
 	val &= ~BIT(0);
@@ -961,26 +1000,6 @@
 	writel(val, pcie->parf + PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT_V2);
 
 	return 0;
-
-err_clks:
-	reset_control_assert(res->ahb_reset);
-err_rst_ahb:
-	reset_control_assert(res->pwr_reset);
-err_rst_pwr:
-	reset_control_assert(res->axi_s_reset);
-err_rst_axi_s:
-	reset_control_assert(res->axi_m_sticky_reset);
-err_rst_axi_m_sticky:
-	reset_control_assert(res->axi_m_reset);
-err_rst_axi_m:
-	reset_control_assert(res->pipe_sticky_reset);
-err_rst_pipe_sticky:
-	reset_control_assert(res->pipe_reset);
-err_rst_pipe:
-	reset_control_assert(res->phy_reset);
-err_rst_phy:
-	reset_control_assert(res->phy_ahb_reset);
-	return ret;
 }
 
 static int qcom_pcie_get_resources_2_3_3(struct qcom_pcie *pcie)
@@ -1038,9 +1057,7 @@
 	struct qcom_pcie_resources_2_3_3 *res = &pcie->res.v2_3_3;
 	struct dw_pcie *pci = pcie->pci;
 	struct device *dev = pci->dev;
-	u16 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
 	int i, ret;
-	u32 val;
 
 	for (i = 0; i < ARRAY_SIZE(res->rst); i++) {
 		ret = reset_control_assert(res->rst[i]);
@@ -1097,32 +1114,6 @@
 		goto err_clk_aux;
 	}
 
-	writel(SLV_ADDR_SPACE_SZ,
-		pcie->parf + PCIE20_v3_PARF_SLV_ADDR_SPACE_SIZE);
-
-	val = readl(pcie->parf + PCIE20_PARF_PHY_CTRL);
-	val &= ~BIT(0);
-	writel(val, pcie->parf + PCIE20_PARF_PHY_CTRL);
-
-	writel(0, pcie->parf + PCIE20_PARF_DBI_BASE_ADDR);
-
-	writel(MST_WAKEUP_EN | SLV_WAKEUP_EN | MSTR_ACLK_CGC_DIS
-		| SLV_ACLK_CGC_DIS | CORE_CLK_CGC_DIS |
-		AUX_PWR_DET | L23_CLK_RMV_DIS | L1_CLK_RMV_DIS,
-		pcie->parf + PCIE20_PARF_SYS_CTRL);
-	writel(0, pcie->parf + PCIE20_PARF_Q2A_FLUSH);
-
-	writel(PCI_COMMAND_MASTER, pci->dbi_base + PCI_COMMAND);
-	writel(DBI_RO_WR_EN, pci->dbi_base + PCIE20_MISC_CONTROL_1_REG);
-	writel(PCIE_CAP_LINK1_VAL, pci->dbi_base + offset + PCI_EXP_SLTCAP);
-
-	val = readl(pci->dbi_base + offset + PCI_EXP_LNKCAP);
-	val &= ~PCI_EXP_LNKCAP_ASPMS;
-	writel(val, pci->dbi_base + offset + PCI_EXP_LNKCAP);
-
-	writel(PCI_EXP_DEVCTL2_COMP_TMOUT_DIS, pci->dbi_base + offset +
-		PCI_EXP_DEVCTL2);
-
 	return 0;
 
 err_clk_aux:
@@ -1144,6 +1135,41 @@
 	return ret;
 }
 
+static int qcom_pcie_post_init_2_3_3(struct qcom_pcie *pcie)
+{
+	struct dw_pcie *pci = pcie->pci;
+	u16 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
+	u32 val;
+
+	writel(SLV_ADDR_SPACE_SZ,
+		pcie->parf + PCIE20_v3_PARF_SLV_ADDR_SPACE_SIZE);
+
+	val = readl(pcie->parf + PCIE20_PARF_PHY_CTRL);
+	val &= ~BIT(0);
+	writel(val, pcie->parf + PCIE20_PARF_PHY_CTRL);
+
+	writel(0, pcie->parf + PCIE20_PARF_DBI_BASE_ADDR);
+
+	writel(MST_WAKEUP_EN | SLV_WAKEUP_EN | MSTR_ACLK_CGC_DIS
+		| SLV_ACLK_CGC_DIS | CORE_CLK_CGC_DIS |
+		AUX_PWR_DET | L23_CLK_RMV_DIS | L1_CLK_RMV_DIS,
+		pcie->parf + PCIE20_PARF_SYS_CTRL);
+	writel(0, pcie->parf + PCIE20_PARF_Q2A_FLUSH);
+
+	writel(PCI_COMMAND_MASTER, pci->dbi_base + PCI_COMMAND);
+	writel(DBI_RO_WR_EN, pci->dbi_base + PCIE20_MISC_CONTROL_1_REG);
+	writel(PCIE_CAP_SLOT_VAL, pci->dbi_base + offset + PCI_EXP_SLTCAP);
+
+	val = readl(pci->dbi_base + offset + PCI_EXP_LNKCAP);
+	val &= ~PCI_EXP_LNKCAP_ASPMS;
+	writel(val, pci->dbi_base + offset + PCI_EXP_LNKCAP);
+
+	writel(PCI_EXP_DEVCTL2_COMP_TMOUT_DIS, pci->dbi_base + offset +
+		PCI_EXP_DEVCTL2);
+
+	return 0;
+}
+
 static int qcom_pcie_get_resources_2_7_0(struct qcom_pcie *pcie)
 {
 	struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0;
@@ -1184,22 +1210,7 @@
 	if (ret < 0)
 		return ret;
 
-	if (pcie->cfg->pipe_clk_need_muxing) {
-		res->pipe_clk_src = devm_clk_get(dev, "pipe_mux");
-		if (IS_ERR(res->pipe_clk_src))
-			return PTR_ERR(res->pipe_clk_src);
-
-		res->phy_pipe_clk = devm_clk_get(dev, "phy_pipe");
-		if (IS_ERR(res->phy_pipe_clk))
-			return PTR_ERR(res->phy_pipe_clk);
-
-		res->ref_clk_src = devm_clk_get(dev, "ref");
-		if (IS_ERR(res->ref_clk_src))
-			return PTR_ERR(res->ref_clk_src);
-	}
-
-	res->pipe_clk = devm_clk_get(dev, "pipe");
-	return PTR_ERR_OR_ZERO(res->pipe_clk);
+	return 0;
 }
 
 static int qcom_pcie_init_2_7_0(struct qcom_pcie *pcie)
@@ -1216,10 +1227,6 @@
 		return ret;
 	}
 
-	/* Set TCXO as clock source for pcie_pipe_clk_src */
-	if (pcie->cfg->pipe_clk_need_muxing)
-		clk_set_parent(res->pipe_clk_src, res->ref_clk_src);
-
 	ret = clk_bulk_prepare_enable(res->num_clks, res->clks);
 	if (ret < 0)
 		goto err_disable_regulators;
@@ -1261,6 +1268,11 @@
 	val |= BIT(4);
 	writel(val, pcie->parf + PCIE20_PARF_MHI_CLOCK_RESET_CTRL);
 
+	/* Enable L1 and L1SS */
+	val = readl(pcie->parf + PCIE20_PARF_PM_CTRL);
+	val &= ~REQ_NOT_ENTR_L1;
+	writel(val, pcie->parf + PCIE20_PARF_PM_CTRL);
+
 	if (IS_ENABLED(CONFIG_PCI_MSI)) {
 		val = readl(pcie->parf + PCIE20_PARF_AXI_MSTR_WR_ADDR_HALT);
 		val |= BIT(31);
@@ -1281,25 +1293,114 @@
 	struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0;
 
 	clk_bulk_disable_unprepare(res->num_clks, res->clks);
+
 	regulator_bulk_disable(ARRAY_SIZE(res->supplies), res->supplies);
 }
 
-static int qcom_pcie_post_init_2_7_0(struct qcom_pcie *pcie)
+static int qcom_pcie_get_resources_2_9_0(struct qcom_pcie *pcie)
 {
-	struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0;
+	struct qcom_pcie_resources_2_9_0 *res = &pcie->res.v2_9_0;
+	struct dw_pcie *pci = pcie->pci;
+	struct device *dev = pci->dev;
+	int ret;
 
-	/* Set pipe clock as clock source for pcie_pipe_clk_src */
-	if (pcie->cfg->pipe_clk_need_muxing)
-		clk_set_parent(res->pipe_clk_src, res->phy_pipe_clk);
+	res->clks[0].id = "iface";
+	res->clks[1].id = "axi_m";
+	res->clks[2].id = "axi_s";
+	res->clks[3].id = "axi_bridge";
+	res->clks[4].id = "rchng";
 
-	return clk_prepare_enable(res->pipe_clk);
+	ret = devm_clk_bulk_get(dev, ARRAY_SIZE(res->clks), res->clks);
+	if (ret < 0)
+		return ret;
+
+	res->rst = devm_reset_control_array_get_exclusive(dev);
+	if (IS_ERR(res->rst))
+		return PTR_ERR(res->rst);
+
+	return 0;
 }
 
-static void qcom_pcie_post_deinit_2_7_0(struct qcom_pcie *pcie)
+static void qcom_pcie_deinit_2_9_0(struct qcom_pcie *pcie)
 {
-	struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0;
+	struct qcom_pcie_resources_2_9_0 *res = &pcie->res.v2_9_0;
 
-	clk_disable_unprepare(res->pipe_clk);
+	clk_bulk_disable_unprepare(ARRAY_SIZE(res->clks), res->clks);
+}
+
+static int qcom_pcie_init_2_9_0(struct qcom_pcie *pcie)
+{
+	struct qcom_pcie_resources_2_9_0 *res = &pcie->res.v2_9_0;
+	struct device *dev = pcie->pci->dev;
+	int ret;
+
+	ret = reset_control_assert(res->rst);
+	if (ret) {
+		dev_err(dev, "reset assert failed (%d)\n", ret);
+		return ret;
+	}
+
+	/*
+	 * Delay periods before and after reset deassert are working values
+	 * from downstream Codeaurora kernel
+	 */
+	usleep_range(2000, 2500);
+
+	ret = reset_control_deassert(res->rst);
+	if (ret) {
+		dev_err(dev, "reset deassert failed (%d)\n", ret);
+		return ret;
+	}
+
+	usleep_range(2000, 2500);
+
+	return clk_bulk_prepare_enable(ARRAY_SIZE(res->clks), res->clks);
+}
+
+static int qcom_pcie_post_init_2_9_0(struct qcom_pcie *pcie)
+{
+	struct dw_pcie *pci = pcie->pci;
+	u16 offset = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
+	u32 val;
+	int i;
+
+	writel(SLV_ADDR_SPACE_SZ,
+		pcie->parf + PCIE20_v3_PARF_SLV_ADDR_SPACE_SIZE);
+
+	val = readl(pcie->parf + PCIE20_PARF_PHY_CTRL);
+	val &= ~BIT(0);
+	writel(val, pcie->parf + PCIE20_PARF_PHY_CTRL);
+
+	writel(0, pcie->parf + PCIE20_PARF_DBI_BASE_ADDR);
+
+	writel(DEVICE_TYPE_RC, pcie->parf + PCIE20_PARF_DEVICE_TYPE);
+	writel(BYPASS | MSTR_AXI_CLK_EN | AHB_CLK_EN,
+		pcie->parf + PCIE20_PARF_MHI_CLOCK_RESET_CTRL);
+	writel(GEN3_RELATED_OFF_RXEQ_RGRDLESS_RXTS |
+		GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL,
+		pci->dbi_base + GEN3_RELATED_OFF);
+
+	writel(MST_WAKEUP_EN | SLV_WAKEUP_EN | MSTR_ACLK_CGC_DIS |
+		SLV_ACLK_CGC_DIS | CORE_CLK_CGC_DIS |
+		AUX_PWR_DET | L23_CLK_RMV_DIS | L1_CLK_RMV_DIS,
+		pcie->parf + PCIE20_PARF_SYS_CTRL);
+
+	writel(0, pcie->parf + PCIE20_PARF_Q2A_FLUSH);
+
+	dw_pcie_dbi_ro_wr_en(pci);
+	writel(PCIE_CAP_SLOT_VAL, pci->dbi_base + offset + PCI_EXP_SLTCAP);
+
+	val = readl(pci->dbi_base + offset + PCI_EXP_LNKCAP);
+	val &= ~PCI_EXP_LNKCAP_ASPMS;
+	writel(val, pci->dbi_base + offset + PCI_EXP_LNKCAP);
+
+	writel(PCI_EXP_DEVCTL2_COMP_TMOUT_DIS, pci->dbi_base + offset +
+			PCI_EXP_DEVCTL2);
+
+	for (i = 0; i < 256; i++)
+		writel(0, pcie->parf + PCIE20_PARF_BDF_TO_SID_TABLE_N + (4 * i));
+
+	return 0;
 }
 
 static int qcom_pcie_link_up(struct dw_pcie *pci)
@@ -1381,7 +1482,7 @@
 	return 0;
 }
 
-static int qcom_pcie_host_init(struct pcie_port *pp)
+static int qcom_pcie_host_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct qcom_pcie *pcie = to_qcom_pcie(pci);
@@ -1433,6 +1534,7 @@
 static const struct qcom_pcie_ops ops_2_1_0 = {
 	.get_resources = qcom_pcie_get_resources_2_1_0,
 	.init = qcom_pcie_init_2_1_0,
+	.post_init = qcom_pcie_post_init_2_1_0,
 	.deinit = qcom_pcie_deinit_2_1_0,
 	.ltssm_enable = qcom_pcie_2_1_0_ltssm_enable,
 };
@@ -1441,6 +1543,7 @@
 static const struct qcom_pcie_ops ops_1_0_0 = {
 	.get_resources = qcom_pcie_get_resources_1_0_0,
 	.init = qcom_pcie_init_1_0_0,
+	.post_init = qcom_pcie_post_init_1_0_0,
 	.deinit = qcom_pcie_deinit_1_0_0,
 	.ltssm_enable = qcom_pcie_2_1_0_ltssm_enable,
 };
@@ -1451,7 +1554,6 @@
 	.init = qcom_pcie_init_2_3_2,
 	.post_init = qcom_pcie_post_init_2_3_2,
 	.deinit = qcom_pcie_deinit_2_3_2,
-	.post_deinit = qcom_pcie_post_deinit_2_3_2,
 	.ltssm_enable = qcom_pcie_2_3_2_ltssm_enable,
 };
 
@@ -1459,6 +1561,7 @@
 static const struct qcom_pcie_ops ops_2_4_0 = {
 	.get_resources = qcom_pcie_get_resources_2_4_0,
 	.init = qcom_pcie_init_2_4_0,
+	.post_init = qcom_pcie_post_init_2_4_0,
 	.deinit = qcom_pcie_deinit_2_4_0,
 	.ltssm_enable = qcom_pcie_2_3_2_ltssm_enable,
 };
@@ -1467,6 +1570,7 @@
 static const struct qcom_pcie_ops ops_2_3_3 = {
 	.get_resources = qcom_pcie_get_resources_2_3_3,
 	.init = qcom_pcie_init_2_3_3,
+	.post_init = qcom_pcie_post_init_2_3_3,
 	.deinit = qcom_pcie_deinit_2_3_3,
 	.ltssm_enable = qcom_pcie_2_3_2_ltssm_enable,
 };
@@ -1477,8 +1581,6 @@
 	.init = qcom_pcie_init_2_7_0,
 	.deinit = qcom_pcie_deinit_2_7_0,
 	.ltssm_enable = qcom_pcie_2_3_2_ltssm_enable,
-	.post_init = qcom_pcie_post_init_2_7_0,
-	.post_deinit = qcom_pcie_post_deinit_2_7_0,
 };
 
 /* Qcom IP rev.: 1.9.0 */
@@ -1487,11 +1589,18 @@
 	.init = qcom_pcie_init_2_7_0,
 	.deinit = qcom_pcie_deinit_2_7_0,
 	.ltssm_enable = qcom_pcie_2_3_2_ltssm_enable,
-	.post_init = qcom_pcie_post_init_2_7_0,
-	.post_deinit = qcom_pcie_post_deinit_2_7_0,
 	.config_sid = qcom_pcie_config_sid_sm8250,
 };
 
+/* Qcom IP rev.: 2.9.0  Synopsys IP rev.: 5.00a */
+static const struct qcom_pcie_ops ops_2_9_0 = {
+	.get_resources = qcom_pcie_get_resources_2_9_0,
+	.init = qcom_pcie_init_2_9_0,
+	.post_init = qcom_pcie_post_init_2_9_0,
+	.deinit = qcom_pcie_deinit_2_9_0,
+	.ltssm_enable = qcom_pcie_2_3_2_ltssm_enable,
+};
+
 static const struct qcom_pcie_cfg apq8084_cfg = {
 	.ops = &ops_1_0_0,
 };
@@ -1533,7 +1642,6 @@
 static const struct qcom_pcie_cfg sm8450_pcie0_cfg = {
 	.ops = &ops_1_9_0,
 	.has_ddrss_sf_tbu_clk = true,
-	.pipe_clk_need_muxing = true,
 	.has_aggre0_clk = true,
 	.has_aggre1_clk = true,
 };
@@ -1541,14 +1649,12 @@
 static const struct qcom_pcie_cfg sm8450_pcie1_cfg = {
 	.ops = &ops_1_9_0,
 	.has_ddrss_sf_tbu_clk = true,
-	.pipe_clk_need_muxing = true,
 	.has_aggre1_clk = true,
 };
 
 static const struct qcom_pcie_cfg sc7280_cfg = {
 	.ops = &ops_1_9_0,
 	.has_tbu_clk = true,
-	.pipe_clk_need_muxing = true,
 };
 
 static const struct qcom_pcie_cfg sc8180x_cfg = {
@@ -1556,6 +1662,10 @@
 	.has_tbu_clk = true,
 };
 
+static const struct qcom_pcie_cfg ipq6018_cfg = {
+	.ops = &ops_2_9_0,
+};
+
 static const struct dw_pcie_ops dw_pcie_ops = {
 	.link_up = qcom_pcie_link_up,
 	.start_link = qcom_pcie_start_link,
@@ -1564,7 +1674,7 @@
 static int qcom_pcie_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
-	struct pcie_port *pp;
+	struct dw_pcie_rp *pp;
 	struct dw_pcie *pci;
 	struct qcom_pcie *pcie;
 	const struct qcom_pcie_cfg *pcie_cfg;
@@ -1666,6 +1776,7 @@
 	{ .compatible = "qcom,pcie-sm8450-pcie0", .data = &sm8450_pcie0_cfg },
 	{ .compatible = "qcom,pcie-sm8450-pcie1", .data = &sm8450_pcie1_cfg },
 	{ .compatible = "qcom,pcie-sc7280", .data = &sc7280_cfg },
+	{ .compatible = "qcom,pcie-ipq6018", .data = &ipq6018_cfg },
 	{ }
 };
 
diff --git a/drivers/pci/controller/dwc/pcie-spear13xx.c b/drivers/pci/controller/dwc/pcie-spear13xx.c
index 1569e82..9d933e0 100644
--- a/drivers/pci/controller/dwc/pcie-spear13xx.c
+++ b/drivers/pci/controller/dwc/pcie-spear13xx.c
@@ -85,7 +85,7 @@
 	struct spear13xx_pcie *spear13xx_pcie = arg;
 	struct pcie_app_reg __iomem *app_reg = spear13xx_pcie->app_base;
 	struct dw_pcie *pci = spear13xx_pcie->pci;
-	struct pcie_port *pp = &pci->pp;
+	struct dw_pcie_rp *pp = &pci->pp;
 	unsigned int status;
 
 	status = readl(&app_reg->int_sts);
@@ -121,7 +121,7 @@
 	return 0;
 }
 
-static int spear13xx_pcie_host_init(struct pcie_port *pp)
+static int spear13xx_pcie_host_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct spear13xx_pcie *spear13xx_pcie = to_spear13xx_pcie(pci);
@@ -155,7 +155,7 @@
 				   struct platform_device *pdev)
 {
 	struct dw_pcie *pci = spear13xx_pcie->pci;
-	struct pcie_port *pp = &pci->pp;
+	struct dw_pcie_rp *pp = &pci->pp;
 	struct device *dev = &pdev->dev;
 	int ret;
 
@@ -172,7 +172,7 @@
 	}
 
 	pp->ops = &spear13xx_pcie_host_ops;
-	pp->msi_irq = -ENODEV;
+	pp->msi_irq[0] = -ENODEV;
 
 	ret = dw_pcie_host_init(pp);
 	if (ret) {
diff --git a/drivers/pci/controller/dwc/pcie-tegra194-acpi.c b/drivers/pci/controller/dwc/pcie-tegra194-acpi.c
index c2de6ed..55f6191 100644
--- a/drivers/pci/controller/dwc/pcie-tegra194-acpi.c
+++ b/drivers/pci/controller/dwc/pcie-tegra194-acpi.c
@@ -39,7 +39,8 @@
 static void atu_reg_write(struct tegra194_pcie_ecam *pcie_ecam, int index,
 			  u32 val, u32 reg)
 {
-	u32 offset = PCIE_GET_ATU_OUTB_UNR_REG_OFFSET(index);
+	u32 offset = PCIE_ATU_UNROLL_BASE(PCIE_ATU_REGION_DIR_OB, index) +
+		     PCIE_ATU_VIEWPORT_BASE;
 
 	writel(val, pcie_ecam->iatu_base + offset + reg);
 }
@@ -58,8 +59,8 @@
 		      PCIE_ATU_LIMIT);
 	atu_reg_write(pcie_ecam, index, upper_32_bits(pci_addr),
 		      PCIE_ATU_UPPER_TARGET);
-	atu_reg_write(pcie_ecam, index, type, PCIE_ATU_CR1);
-	atu_reg_write(pcie_ecam, index, PCIE_ATU_ENABLE, PCIE_ATU_CR2);
+	atu_reg_write(pcie_ecam, index, type, PCIE_ATU_REGION_CTRL1);
+	atu_reg_write(pcie_ecam, index, PCIE_ATU_ENABLE, PCIE_ATU_REGION_CTRL2);
 }
 
 static void __iomem *tegra194_map_bus(struct pci_bus *bus,
diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c
index cc26784..1b6b437 100644
--- a/drivers/pci/controller/dwc/pcie-tegra194.c
+++ b/drivers/pci/controller/dwc/pcie-tegra194.c
@@ -1,8 +1,10 @@
 // SPDX-License-Identifier: GPL-2.0+
 /*
- * PCIe host controller driver for Tegra194 SoC
+ * PCIe host controller driver for the following SoCs
+ * Tegra194
+ * Tegra234
  *
- * Copyright (C) 2019 NVIDIA Corporation.
+ * Copyright (C) 2019-2022 NVIDIA Corporation.
  *
  * Author: Vidya Sagar <vidyas@nvidia.com>
  */
@@ -35,6 +37,9 @@
 #include <soc/tegra/bpmp-abi.h>
 #include "../../pci.h"
 
+#define TEGRA194_DWC_IP_VER			0x490A
+#define TEGRA234_DWC_IP_VER			0x562A
+
 #define APPL_PINMUX				0x0
 #define APPL_PINMUX_PEX_RST			BIT(0)
 #define APPL_PINMUX_CLKREQ_OVERRIDE_EN		BIT(2)
@@ -49,6 +54,7 @@
 #define APPL_CTRL_HW_HOT_RST_MODE_MASK		GENMASK(1, 0)
 #define APPL_CTRL_HW_HOT_RST_MODE_SHIFT		22
 #define APPL_CTRL_HW_HOT_RST_MODE_IMDT_RST	0x1
+#define APPL_CTRL_HW_HOT_RST_MODE_IMDT_RST_LTSSM_EN	0x2
 
 #define APPL_INTR_EN_L0_0			0x8
 #define APPL_INTR_EN_L0_0_LINK_STATE_INT_EN	BIT(0)
@@ -170,19 +176,6 @@
 #define CFG_TIMER_CTRL_MAX_FUNC_NUM_OFF	0x718
 #define CFG_TIMER_CTRL_ACK_NAK_SHIFT	(19)
 
-#define EVENT_COUNTER_ALL_CLEAR		0x3
-#define EVENT_COUNTER_ENABLE_ALL	0x7
-#define EVENT_COUNTER_ENABLE_SHIFT	2
-#define EVENT_COUNTER_EVENT_SEL_MASK	GENMASK(7, 0)
-#define EVENT_COUNTER_EVENT_SEL_SHIFT	16
-#define EVENT_COUNTER_EVENT_Tx_L0S	0x2
-#define EVENT_COUNTER_EVENT_Rx_L0S	0x3
-#define EVENT_COUNTER_EVENT_L1		0x5
-#define EVENT_COUNTER_EVENT_L1_1	0x7
-#define EVENT_COUNTER_EVENT_L1_2	0x8
-#define EVENT_COUNTER_GROUP_SEL_SHIFT	24
-#define EVENT_COUNTER_GROUP_5		0x5
-
 #define N_FTS_VAL					52
 #define FTS_VAL						52
 
@@ -191,12 +184,6 @@
 #define GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC_MASK	GENMASK(23, 8)
 #define GEN3_EQ_CONTROL_OFF_FB_MODE_MASK	GENMASK(3, 0)
 
-#define GEN3_RELATED_OFF			0x890
-#define GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL	BIT(0)
-#define GEN3_RELATED_OFF_GEN3_EQ_DISABLE	BIT(16)
-#define GEN3_RELATED_OFF_RATE_SHADOW_SEL_SHIFT	24
-#define GEN3_RELATED_OFF_RATE_SHADOW_SEL_MASK	GENMASK(25, 24)
-
 #define PORT_LOGIC_AMBA_ERROR_RESPONSE_DEFAULT	0x8D0
 #define AMBA_ERROR_RESPONSE_CRS_SHIFT		3
 #define AMBA_ERROR_RESPONSE_CRS_MASK		GENMASK(1, 0)
@@ -243,7 +230,19 @@
 	GEN4_CORE_CLK_FREQ
 };
 
-struct tegra194_pcie {
+struct tegra_pcie_dw_of_data {
+	u32 version;
+	enum dw_pcie_device_mode mode;
+	bool has_msix_doorbell_access_fix;
+	bool has_sbr_reset_fix;
+	bool has_l1ss_exit_fix;
+	bool has_ltr_req_fix;
+	u32 cdm_chk_int_en_bit;
+	u32 gen4_preset_vec;
+	u8 n_fts[2];
+};
+
+struct tegra_pcie_dw {
 	struct device *dev;
 	struct resource *appl_res;
 	struct resource *dbi_res;
@@ -255,17 +254,20 @@
 	struct dw_pcie pci;
 	struct tegra_bpmp *bpmp;
 
-	enum dw_pcie_device_mode mode;
+	struct tegra_pcie_dw_of_data *of_data;
 
 	bool supports_clkreq;
 	bool enable_cdm_check;
+	bool enable_srns;
 	bool link_state;
 	bool update_fc_fixup;
+	bool enable_ext_refclk;
 	u8 init_link_width;
 	u32 msi_ctrl_int;
 	u32 num_lanes;
 	u32 cid;
 	u32 cfg_link_cap_l1sub;
+	u32 ras_des_cap;
 	u32 pcie_cap_base;
 	u32 aspm_cmrt;
 	u32 aspm_pwr_on_t;
@@ -287,22 +289,18 @@
 	int ep_state;
 };
 
-struct tegra194_pcie_of_data {
-	enum dw_pcie_device_mode mode;
-};
-
-static inline struct tegra194_pcie *to_tegra_pcie(struct dw_pcie *pci)
+static inline struct tegra_pcie_dw *to_tegra_pcie(struct dw_pcie *pci)
 {
-	return container_of(pci, struct tegra194_pcie, pci);
+	return container_of(pci, struct tegra_pcie_dw, pci);
 }
 
-static inline void appl_writel(struct tegra194_pcie *pcie, const u32 value,
+static inline void appl_writel(struct tegra_pcie_dw *pcie, const u32 value,
 			       const u32 reg)
 {
 	writel_relaxed(value, pcie->appl_base + reg);
 }
 
-static inline u32 appl_readl(struct tegra194_pcie *pcie, const u32 reg)
+static inline u32 appl_readl(struct tegra_pcie_dw *pcie, const u32 reg)
 {
 	return readl_relaxed(pcie->appl_base + reg);
 }
@@ -311,10 +309,10 @@
 	enum dw_pcie_device_mode mode;
 };
 
-static void apply_bad_link_workaround(struct pcie_port *pp)
+static void apply_bad_link_workaround(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
-	struct tegra194_pcie *pcie = to_tegra_pcie(pci);
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
 	u32 current_link_width;
 	u16 val;
 
@@ -347,18 +345,18 @@
 
 static irqreturn_t tegra_pcie_rp_irq_handler(int irq, void *arg)
 {
-	struct tegra194_pcie *pcie = arg;
+	struct tegra_pcie_dw *pcie = arg;
 	struct dw_pcie *pci = &pcie->pci;
-	struct pcie_port *pp = &pci->pp;
-	u32 val, tmp;
+	struct dw_pcie_rp *pp = &pci->pp;
+	u32 val, status_l0, status_l1;
 	u16 val_w;
 
-	val = appl_readl(pcie, APPL_INTR_STATUS_L0);
-	if (val & APPL_INTR_STATUS_L0_LINK_STATE_INT) {
-		val = appl_readl(pcie, APPL_INTR_STATUS_L1_0_0);
-		if (val & APPL_INTR_STATUS_L1_0_0_LINK_REQ_RST_NOT_CHGED) {
-			appl_writel(pcie, val, APPL_INTR_STATUS_L1_0_0);
-
+	status_l0 = appl_readl(pcie, APPL_INTR_STATUS_L0);
+	if (status_l0 & APPL_INTR_STATUS_L0_LINK_STATE_INT) {
+		status_l1 = appl_readl(pcie, APPL_INTR_STATUS_L1_0_0);
+		appl_writel(pcie, status_l1, APPL_INTR_STATUS_L1_0_0);
+		if (!pcie->of_data->has_sbr_reset_fix &&
+		    status_l1 & APPL_INTR_STATUS_L1_0_0_LINK_REQ_RST_NOT_CHGED) {
 			/* SBR & Surprise Link Down WAR */
 			val = appl_readl(pcie, APPL_CAR_RESET_OVRD);
 			val &= ~APPL_CAR_RESET_OVRD_CYA_OVERRIDE_CORE_RST_N;
@@ -374,15 +372,21 @@
 		}
 	}
 
-	if (val & APPL_INTR_STATUS_L0_INT_INT) {
-		val = appl_readl(pcie, APPL_INTR_STATUS_L1_8_0);
-		if (val & APPL_INTR_STATUS_L1_8_0_AUTO_BW_INT_STS) {
+	if (status_l0 & APPL_INTR_STATUS_L0_INT_INT) {
+		status_l1 = appl_readl(pcie, APPL_INTR_STATUS_L1_8_0);
+		if (status_l1 & APPL_INTR_STATUS_L1_8_0_AUTO_BW_INT_STS) {
 			appl_writel(pcie,
 				    APPL_INTR_STATUS_L1_8_0_AUTO_BW_INT_STS,
 				    APPL_INTR_STATUS_L1_8_0);
 			apply_bad_link_workaround(pp);
 		}
-		if (val & APPL_INTR_STATUS_L1_8_0_BW_MGT_INT_STS) {
+		if (status_l1 & APPL_INTR_STATUS_L1_8_0_BW_MGT_INT_STS) {
+			val_w = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base +
+						  PCI_EXP_LNKSTA);
+			val_w |= PCI_EXP_LNKSTA_LBMS;
+			dw_pcie_writew_dbi(pci, pcie->pcie_cap_base +
+					   PCI_EXP_LNKSTA, val_w);
+
 			appl_writel(pcie,
 				    APPL_INTR_STATUS_L1_8_0_BW_MGT_INT_STS,
 				    APPL_INTR_STATUS_L1_8_0);
@@ -394,31 +398,30 @@
 		}
 	}
 
-	val = appl_readl(pcie, APPL_INTR_STATUS_L0);
-	if (val & APPL_INTR_STATUS_L0_CDM_REG_CHK_INT) {
-		val = appl_readl(pcie, APPL_INTR_STATUS_L1_18);
-		tmp = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS);
-		if (val & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMPLT) {
+	if (status_l0 & APPL_INTR_STATUS_L0_CDM_REG_CHK_INT) {
+		status_l1 = appl_readl(pcie, APPL_INTR_STATUS_L1_18);
+		val = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS);
+		if (status_l1 & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMPLT) {
 			dev_info(pci->dev, "CDM check complete\n");
-			tmp |= PCIE_PL_CHK_REG_CHK_REG_COMPLETE;
+			val |= PCIE_PL_CHK_REG_CHK_REG_COMPLETE;
 		}
-		if (val & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMP_ERR) {
+		if (status_l1 & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_CMP_ERR) {
 			dev_err(pci->dev, "CDM comparison mismatch\n");
-			tmp |= PCIE_PL_CHK_REG_CHK_REG_COMPARISON_ERROR;
+			val |= PCIE_PL_CHK_REG_CHK_REG_COMPARISON_ERROR;
 		}
-		if (val & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_LOGIC_ERR) {
+		if (status_l1 & APPL_INTR_STATUS_L1_18_CDM_REG_CHK_LOGIC_ERR) {
 			dev_err(pci->dev, "CDM Logic error\n");
-			tmp |= PCIE_PL_CHK_REG_CHK_REG_LOGIC_ERROR;
+			val |= PCIE_PL_CHK_REG_CHK_REG_LOGIC_ERROR;
 		}
-		dw_pcie_writel_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS, tmp);
-		tmp = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_ERR_ADDR);
-		dev_err(pci->dev, "CDM Error Address Offset = 0x%08X\n", tmp);
+		dw_pcie_writel_dbi(pci, PCIE_PL_CHK_REG_CONTROL_STATUS, val);
+		val = dw_pcie_readl_dbi(pci, PCIE_PL_CHK_REG_ERR_ADDR);
+		dev_err(pci->dev, "CDM Error Address Offset = 0x%08X\n", val);
 	}
 
 	return IRQ_HANDLED;
 }
 
-static void pex_ep_event_hot_rst_done(struct tegra194_pcie *pcie)
+static void pex_ep_event_hot_rst_done(struct tegra_pcie_dw *pcie)
 {
 	u32 val;
 
@@ -446,7 +449,7 @@
 
 static irqreturn_t tegra_pcie_ep_irq_thread(int irq, void *arg)
 {
-	struct tegra194_pcie *pcie = arg;
+	struct tegra_pcie_dw *pcie = arg;
 	struct dw_pcie *pci = &pcie->pci;
 	u32 val, speed;
 
@@ -454,6 +457,9 @@
 		PCI_EXP_LNKSTA_CLS;
 	clk_set_rate(pcie->core_clk, pcie_gen_freq[speed - 1]);
 
+	if (pcie->of_data->has_ltr_req_fix)
+		return IRQ_HANDLED;
+
 	/* If EP doesn't advertise L1SS, just return */
 	val = dw_pcie_readl_dbi(pci, pcie->cfg_link_cap_l1sub);
 	if (!(val & (PCI_L1SS_CAP_ASPM_L1_1 | PCI_L1SS_CAP_ASPM_L1_2)))
@@ -492,7 +498,7 @@
 
 static irqreturn_t tegra_pcie_ep_hard_irq(int irq, void *arg)
 {
-	struct tegra194_pcie *pcie = arg;
+	struct tegra_pcie_dw *pcie = arg;
 	struct dw_pcie_ep *ep = &pcie->pci.ep;
 	int spurious = 1;
 	u32 status_l0, status_l1, link_status;
@@ -535,16 +541,21 @@
 	return IRQ_HANDLED;
 }
 
-static int tegra194_pcie_rd_own_conf(struct pci_bus *bus, u32 devfn, int where,
+static int tegra_pcie_dw_rd_own_conf(struct pci_bus *bus, u32 devfn, int where,
 				     int size, u32 *val)
 {
+	struct dw_pcie_rp *pp = bus->sysdata;
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
+
 	/*
 	 * This is an endpoint mode specific register happen to appear even
 	 * when controller is operating in root port mode and system hangs
 	 * when it is accessed with link being in ASPM-L1 state.
 	 * So skip accessing it altogether
 	 */
-	if (!PCI_SLOT(devfn) && where == PORT_LOGIC_MSIX_DOORBELL) {
+	if (!pcie->of_data->has_msix_doorbell_access_fix &&
+	    !PCI_SLOT(devfn) && where == PORT_LOGIC_MSIX_DOORBELL) {
 		*val = 0x00000000;
 		return PCIBIOS_SUCCESSFUL;
 	}
@@ -552,16 +563,21 @@
 	return pci_generic_config_read(bus, devfn, where, size, val);
 }
 
-static int tegra194_pcie_wr_own_conf(struct pci_bus *bus, u32 devfn, int where,
+static int tegra_pcie_dw_wr_own_conf(struct pci_bus *bus, u32 devfn, int where,
 				     int size, u32 val)
 {
+	struct dw_pcie_rp *pp = bus->sysdata;
+	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
+
 	/*
 	 * This is an endpoint mode specific register happen to appear even
 	 * when controller is operating in root port mode and system hangs
 	 * when it is accessed with link being in ASPM-L1 state.
 	 * So skip accessing it altogether
 	 */
-	if (!PCI_SLOT(devfn) && where == PORT_LOGIC_MSIX_DOORBELL)
+	if (!pcie->of_data->has_msix_doorbell_access_fix &&
+	    !PCI_SLOT(devfn) && where == PORT_LOGIC_MSIX_DOORBELL)
 		return PCIBIOS_SUCCESSFUL;
 
 	return pci_generic_config_write(bus, devfn, where, size, val);
@@ -569,30 +585,12 @@
 
 static struct pci_ops tegra_pci_ops = {
 	.map_bus = dw_pcie_own_conf_map_bus,
-	.read = tegra194_pcie_rd_own_conf,
-	.write = tegra194_pcie_wr_own_conf,
+	.read = tegra_pcie_dw_rd_own_conf,
+	.write = tegra_pcie_dw_wr_own_conf,
 };
 
 #if defined(CONFIG_PCIEASPM)
-static const u32 event_cntr_ctrl_offset[] = {
-	0x1d8,
-	0x1a8,
-	0x1a8,
-	0x1a8,
-	0x1c4,
-	0x1d8
-};
-
-static const u32 event_cntr_data_offset[] = {
-	0x1dc,
-	0x1ac,
-	0x1ac,
-	0x1ac,
-	0x1c8,
-	0x1dc
-};
-
-static void disable_aspm_l11(struct tegra194_pcie *pcie)
+static void disable_aspm_l11(struct tegra_pcie_dw *pcie)
 {
 	u32 val;
 
@@ -601,7 +599,7 @@
 	dw_pcie_writel_dbi(&pcie->pci, pcie->cfg_link_cap_l1sub, val);
 }
 
-static void disable_aspm_l12(struct tegra194_pcie *pcie)
+static void disable_aspm_l12(struct tegra_pcie_dw *pcie)
 {
 	u32 val;
 
@@ -610,24 +608,27 @@
 	dw_pcie_writel_dbi(&pcie->pci, pcie->cfg_link_cap_l1sub, val);
 }
 
-static inline u32 event_counter_prog(struct tegra194_pcie *pcie, u32 event)
+static inline u32 event_counter_prog(struct tegra_pcie_dw *pcie, u32 event)
 {
 	u32 val;
 
-	val = dw_pcie_readl_dbi(&pcie->pci, event_cntr_ctrl_offset[pcie->cid]);
+	val = dw_pcie_readl_dbi(&pcie->pci, pcie->ras_des_cap +
+				PCIE_RAS_DES_EVENT_COUNTER_CONTROL);
 	val &= ~(EVENT_COUNTER_EVENT_SEL_MASK << EVENT_COUNTER_EVENT_SEL_SHIFT);
 	val |= EVENT_COUNTER_GROUP_5 << EVENT_COUNTER_GROUP_SEL_SHIFT;
 	val |= event << EVENT_COUNTER_EVENT_SEL_SHIFT;
 	val |= EVENT_COUNTER_ENABLE_ALL << EVENT_COUNTER_ENABLE_SHIFT;
-	dw_pcie_writel_dbi(&pcie->pci, event_cntr_ctrl_offset[pcie->cid], val);
-	val = dw_pcie_readl_dbi(&pcie->pci, event_cntr_data_offset[pcie->cid]);
+	dw_pcie_writel_dbi(&pcie->pci, pcie->ras_des_cap +
+			   PCIE_RAS_DES_EVENT_COUNTER_CONTROL, val);
+	val = dw_pcie_readl_dbi(&pcie->pci, pcie->ras_des_cap +
+				PCIE_RAS_DES_EVENT_COUNTER_DATA);
 
 	return val;
 }
 
 static int aspm_state_cnt(struct seq_file *s, void *data)
 {
-	struct tegra194_pcie *pcie = (struct tegra194_pcie *)
+	struct tegra_pcie_dw *pcie = (struct tegra_pcie_dw *)
 				     dev_get_drvdata(s->private);
 	u32 val;
 
@@ -647,18 +648,20 @@
 		   event_counter_prog(pcie, EVENT_COUNTER_EVENT_L1_2));
 
 	/* Clear all counters */
-	dw_pcie_writel_dbi(&pcie->pci, event_cntr_ctrl_offset[pcie->cid],
+	dw_pcie_writel_dbi(&pcie->pci, pcie->ras_des_cap +
+			   PCIE_RAS_DES_EVENT_COUNTER_CONTROL,
 			   EVENT_COUNTER_ALL_CLEAR);
 
 	/* Re-enable counting */
 	val = EVENT_COUNTER_ENABLE_ALL << EVENT_COUNTER_ENABLE_SHIFT;
 	val |= EVENT_COUNTER_GROUP_5 << EVENT_COUNTER_GROUP_SEL_SHIFT;
-	dw_pcie_writel_dbi(&pcie->pci, event_cntr_ctrl_offset[pcie->cid], val);
+	dw_pcie_writel_dbi(&pcie->pci, pcie->ras_des_cap +
+			   PCIE_RAS_DES_EVENT_COUNTER_CONTROL, val);
 
 	return 0;
 }
 
-static void init_host_aspm(struct tegra194_pcie *pcie)
+static void init_host_aspm(struct tegra_pcie_dw *pcie)
 {
 	struct dw_pcie *pci = &pcie->pci;
 	u32 val;
@@ -666,10 +669,14 @@
 	val = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_L1SS);
 	pcie->cfg_link_cap_l1sub = val + PCI_L1SS_CAP;
 
+	pcie->ras_des_cap = dw_pcie_find_ext_capability(&pcie->pci,
+							PCI_EXT_CAP_ID_VNDR);
+
 	/* Enable ASPM counters */
 	val = EVENT_COUNTER_ENABLE_ALL << EVENT_COUNTER_ENABLE_SHIFT;
 	val |= EVENT_COUNTER_GROUP_5 << EVENT_COUNTER_GROUP_SEL_SHIFT;
-	dw_pcie_writel_dbi(pci, event_cntr_ctrl_offset[pcie->cid], val);
+	dw_pcie_writel_dbi(pci, pcie->ras_des_cap +
+			   PCIE_RAS_DES_EVENT_COUNTER_CONTROL, val);
 
 	/* Program T_cmrt and T_pwr_on values */
 	val = dw_pcie_readl_dbi(pci, pcie->cfg_link_cap_l1sub);
@@ -686,22 +693,22 @@
 	dw_pcie_writel_dbi(pci, PCIE_PORT_AFR, val);
 }
 
-static void init_debugfs(struct tegra194_pcie *pcie)
+static void init_debugfs(struct tegra_pcie_dw *pcie)
 {
 	debugfs_create_devm_seqfile(pcie->dev, "aspm_state_cnt", pcie->debugfs,
 				    aspm_state_cnt);
 }
 #else
-static inline void disable_aspm_l12(struct tegra194_pcie *pcie) { return; }
-static inline void disable_aspm_l11(struct tegra194_pcie *pcie) { return; }
-static inline void init_host_aspm(struct tegra194_pcie *pcie) { return; }
-static inline void init_debugfs(struct tegra194_pcie *pcie) { return; }
+static inline void disable_aspm_l12(struct tegra_pcie_dw *pcie) { return; }
+static inline void disable_aspm_l11(struct tegra_pcie_dw *pcie) { return; }
+static inline void init_host_aspm(struct tegra_pcie_dw *pcie) { return; }
+static inline void init_debugfs(struct tegra_pcie_dw *pcie) { return; }
 #endif
 
-static void tegra_pcie_enable_system_interrupts(struct pcie_port *pp)
+static void tegra_pcie_enable_system_interrupts(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
-	struct tegra194_pcie *pcie = to_tegra_pcie(pci);
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
 	u32 val;
 	u16 val_w;
 
@@ -709,13 +716,15 @@
 	val |= APPL_INTR_EN_L0_0_LINK_STATE_INT_EN;
 	appl_writel(pcie, val, APPL_INTR_EN_L0_0);
 
-	val = appl_readl(pcie, APPL_INTR_EN_L1_0_0);
-	val |= APPL_INTR_EN_L1_0_0_LINK_REQ_RST_NOT_INT_EN;
-	appl_writel(pcie, val, APPL_INTR_EN_L1_0_0);
+	if (!pcie->of_data->has_sbr_reset_fix) {
+		val = appl_readl(pcie, APPL_INTR_EN_L1_0_0);
+		val |= APPL_INTR_EN_L1_0_0_LINK_REQ_RST_NOT_INT_EN;
+		appl_writel(pcie, val, APPL_INTR_EN_L1_0_0);
+	}
 
 	if (pcie->enable_cdm_check) {
 		val = appl_readl(pcie, APPL_INTR_EN_L0_0);
-		val |= APPL_INTR_EN_L0_0_CDM_REG_CHK_INT_EN;
+		val |= pcie->of_data->cdm_chk_int_en_bit;
 		appl_writel(pcie, val, APPL_INTR_EN_L0_0);
 
 		val = appl_readl(pcie, APPL_INTR_EN_L1_18);
@@ -736,10 +745,10 @@
 			   val_w);
 }
 
-static void tegra_pcie_enable_legacy_interrupts(struct pcie_port *pp)
+static void tegra_pcie_enable_legacy_interrupts(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
-	struct tegra194_pcie *pcie = to_tegra_pcie(pci);
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
 	u32 val;
 
 	/* Enable legacy interrupt generation */
@@ -757,10 +766,10 @@
 	appl_writel(pcie, val, APPL_INTR_EN_L1_8_0);
 }
 
-static void tegra_pcie_enable_msi_interrupts(struct pcie_port *pp)
+static void tegra_pcie_enable_msi_interrupts(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
-	struct tegra194_pcie *pcie = to_tegra_pcie(pci);
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
 	u32 val;
 
 	/* Enable MSI interrupt generation */
@@ -770,10 +779,10 @@
 	appl_writel(pcie, val, APPL_INTR_EN_L0_0);
 }
 
-static void tegra_pcie_enable_interrupts(struct pcie_port *pp)
+static void tegra_pcie_enable_interrupts(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
-	struct tegra194_pcie *pcie = to_tegra_pcie(pci);
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
 
 	/* Clear interrupt statuses before enabling interrupts */
 	appl_writel(pcie, 0xFFFFFFFF, APPL_INTR_STATUS_L0);
@@ -798,7 +807,7 @@
 		tegra_pcie_enable_msi_interrupts(pp);
 }
 
-static void config_gen3_gen4_eq_presets(struct tegra194_pcie *pcie)
+static void config_gen3_gen4_eq_presets(struct tegra_pcie_dw *pcie)
 {
 	struct dw_pcie *pci = &pcie->pci;
 	u32 val, offset, i;
@@ -842,7 +851,8 @@
 
 	val = dw_pcie_readl_dbi(pci, GEN3_EQ_CONTROL_OFF);
 	val &= ~GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC_MASK;
-	val |= (0x360 << GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC_SHIFT);
+	val |= (pcie->of_data->gen4_preset_vec <<
+		GEN3_EQ_CONTROL_OFF_PSET_REQ_VEC_SHIFT);
 	val &= ~GEN3_EQ_CONTROL_OFF_FB_MODE_MASK;
 	dw_pcie_writel_dbi(pci, GEN3_EQ_CONTROL_OFF, val);
 
@@ -851,11 +861,12 @@
 	dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val);
 }
 
-static int tegra194_pcie_host_init(struct pcie_port *pp)
+static int tegra_pcie_dw_host_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
-	struct tegra194_pcie *pcie = to_tegra_pcie(pci);
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
 	u32 val;
+	u16 val_16;
 
 	pp->bridge->ops = &tegra_pci_ops;
 
@@ -863,6 +874,11 @@
 		pcie->pcie_cap_base = dw_pcie_find_capability(&pcie->pci,
 							      PCI_CAP_ID_EXP);
 
+	val_16 = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_DEVCTL);
+	val_16 &= ~PCI_EXP_DEVCTL_PAYLOAD;
+	val_16 |= PCI_EXP_DEVCTL_PAYLOAD_256B;
+	dw_pcie_writew_dbi(pci, pcie->pcie_cap_base + PCI_EXP_DEVCTL, val_16);
+
 	val = dw_pcie_readl_dbi(pci, PCI_IO_BASE);
 	val &= ~(IO_BASE_IO_DECODE | IO_BASE_IO_DECODE_BIT8);
 	dw_pcie_writel_dbi(pci, PCI_IO_BASE, val);
@@ -887,6 +903,15 @@
 	val |= (pcie->num_lanes << PCI_EXP_LNKSTA_NLW_SHIFT);
 	dw_pcie_writel_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKCAP, val);
 
+	/* Clear Slot Clock Configuration bit if SRNS configuration */
+	if (pcie->enable_srns) {
+		val_16 = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base +
+					   PCI_EXP_LNKSTA);
+		val_16 &= ~PCI_EXP_LNKSTA_SLC;
+		dw_pcie_writew_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA,
+				   val_16);
+	}
+
 	config_gen3_gen4_eq_presets(pcie);
 
 	init_host_aspm(pcie);
@@ -897,9 +922,11 @@
 		disable_aspm_l12(pcie);
 	}
 
-	val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF);
-	val &= ~GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL;
-	dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val);
+	if (!pcie->of_data->has_l1ss_exit_fix) {
+		val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF);
+		val &= ~GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL;
+		dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val);
+	}
 
 	if (pcie->update_fc_fixup) {
 		val = dw_pcie_readl_dbi(pci, CFG_TIMER_CTRL_MAX_FUNC_NUM_OFF);
@@ -912,14 +939,14 @@
 	return 0;
 }
 
-static int tegra194_pcie_start_link(struct dw_pcie *pci)
+static int tegra_pcie_dw_start_link(struct dw_pcie *pci)
 {
 	u32 val, offset, speed, tmp;
-	struct tegra194_pcie *pcie = to_tegra_pcie(pci);
-	struct pcie_port *pp = &pci->pp;
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
+	struct dw_pcie_rp *pp = &pci->pp;
 	bool retry = true;
 
-	if (pcie->mode == DW_PCIE_EP_TYPE) {
+	if (pcie->of_data->mode == DW_PCIE_EP_TYPE) {
 		enable_irq(pcie->pex_rst_irq);
 		return 0;
 	}
@@ -978,9 +1005,9 @@
 		offset = dw_pcie_find_ext_capability(pci, PCI_EXT_CAP_ID_DLF);
 		val = dw_pcie_readl_dbi(pci, offset + PCI_DLF_CAP);
 		val &= ~PCI_DLF_EXCHANGE_ENABLE;
-		dw_pcie_writel_dbi(pci, offset, val);
+		dw_pcie_writel_dbi(pci, offset + PCI_DLF_CAP, val);
 
-		tegra194_pcie_host_init(pp);
+		tegra_pcie_dw_host_init(pp);
 		dw_pcie_setup_rc(pp);
 
 		retry = false;
@@ -996,32 +1023,32 @@
 	return 0;
 }
 
-static int tegra194_pcie_link_up(struct dw_pcie *pci)
+static int tegra_pcie_dw_link_up(struct dw_pcie *pci)
 {
-	struct tegra194_pcie *pcie = to_tegra_pcie(pci);
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
 	u32 val = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA);
 
 	return !!(val & PCI_EXP_LNKSTA_DLLLA);
 }
 
-static void tegra194_pcie_stop_link(struct dw_pcie *pci)
+static void tegra_pcie_dw_stop_link(struct dw_pcie *pci)
 {
-	struct tegra194_pcie *pcie = to_tegra_pcie(pci);
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
 
 	disable_irq(pcie->pex_rst_irq);
 }
 
 static const struct dw_pcie_ops tegra_dw_pcie_ops = {
-	.link_up = tegra194_pcie_link_up,
-	.start_link = tegra194_pcie_start_link,
-	.stop_link = tegra194_pcie_stop_link,
+	.link_up = tegra_pcie_dw_link_up,
+	.start_link = tegra_pcie_dw_start_link,
+	.stop_link = tegra_pcie_dw_stop_link,
 };
 
-static const struct dw_pcie_host_ops tegra194_pcie_host_ops = {
-	.host_init = tegra194_pcie_host_init,
+static const struct dw_pcie_host_ops tegra_pcie_dw_host_ops = {
+	.host_init = tegra_pcie_dw_host_init,
 };
 
-static void tegra_pcie_disable_phy(struct tegra194_pcie *pcie)
+static void tegra_pcie_disable_phy(struct tegra_pcie_dw *pcie)
 {
 	unsigned int phy_count = pcie->phy_count;
 
@@ -1031,7 +1058,7 @@
 	}
 }
 
-static int tegra_pcie_enable_phy(struct tegra194_pcie *pcie)
+static int tegra_pcie_enable_phy(struct tegra_pcie_dw *pcie)
 {
 	unsigned int i;
 	int ret;
@@ -1058,7 +1085,7 @@
 	return ret;
 }
 
-static int tegra194_pcie_parse_dt(struct tegra194_pcie *pcie)
+static int tegra_pcie_dw_parse_dt(struct tegra_pcie_dw *pcie)
 {
 	struct platform_device *pdev = to_platform_device(pcie->dev);
 	struct device_node *np = pcie->dev->of_node;
@@ -1111,13 +1138,27 @@
 	if (of_property_read_bool(np, "nvidia,update-fc-fixup"))
 		pcie->update_fc_fixup = true;
 
+	/* RP using an external REFCLK is supported only in Tegra234 */
+	if (pcie->of_data->version == TEGRA194_DWC_IP_VER) {
+		if (pcie->of_data->mode == DW_PCIE_EP_TYPE)
+			pcie->enable_ext_refclk = true;
+	} else {
+		pcie->enable_ext_refclk =
+			of_property_read_bool(pcie->dev->of_node,
+					      "nvidia,enable-ext-refclk");
+	}
+
 	pcie->supports_clkreq =
 		of_property_read_bool(pcie->dev->of_node, "supports-clkreq");
 
 	pcie->enable_cdm_check =
 		of_property_read_bool(np, "snps,enable-cdm-check");
 
-	if (pcie->mode == DW_PCIE_RC_TYPE)
+	if (pcie->of_data->version == TEGRA234_DWC_IP_VER)
+		pcie->enable_srns =
+			of_property_read_bool(np, "nvidia,enable-srns");
+
+	if (pcie->of_data->mode == DW_PCIE_RC_TYPE)
 		return 0;
 
 	/* Endpoint mode specific DT entries */
@@ -1154,15 +1195,18 @@
 	return 0;
 }
 
-static int tegra_pcie_bpmp_set_ctrl_state(struct tegra194_pcie *pcie,
+static int tegra_pcie_bpmp_set_ctrl_state(struct tegra_pcie_dw *pcie,
 					  bool enable)
 {
 	struct mrq_uphy_response resp;
 	struct tegra_bpmp_message msg;
 	struct mrq_uphy_request req;
 
-	/* Controller-5 doesn't need to have its state set by BPMP-FW */
-	if (pcie->cid == 5)
+	/*
+	 * Controller-5 doesn't need to have its state set by BPMP-FW in
+	 * Tegra194
+	 */
+	if (pcie->of_data->version == TEGRA194_DWC_IP_VER && pcie->cid == 5)
 		return 0;
 
 	memset(&req, 0, sizeof(req));
@@ -1182,7 +1226,7 @@
 	return tegra_bpmp_transfer(pcie->bpmp, &msg);
 }
 
-static int tegra_pcie_bpmp_set_pll_state(struct tegra194_pcie *pcie,
+static int tegra_pcie_bpmp_set_pll_state(struct tegra_pcie_dw *pcie,
 					 bool enable)
 {
 	struct mrq_uphy_response resp;
@@ -1210,9 +1254,9 @@
 	return tegra_bpmp_transfer(pcie->bpmp, &msg);
 }
 
-static void tegra_pcie_downstream_dev_to_D0(struct tegra194_pcie *pcie)
+static void tegra_pcie_downstream_dev_to_D0(struct tegra_pcie_dw *pcie)
 {
-	struct pcie_port *pp = &pcie->pci.pp;
+	struct dw_pcie_rp *pp = &pcie->pci.pp;
 	struct pci_bus *child, *root_bus = NULL;
 	struct pci_dev *pdev;
 
@@ -1248,7 +1292,7 @@
 	}
 }
 
-static int tegra_pcie_get_slot_regulators(struct tegra194_pcie *pcie)
+static int tegra_pcie_get_slot_regulators(struct tegra_pcie_dw *pcie)
 {
 	pcie->slot_ctl_3v3 = devm_regulator_get_optional(pcie->dev, "vpcie3v3");
 	if (IS_ERR(pcie->slot_ctl_3v3)) {
@@ -1269,7 +1313,7 @@
 	return 0;
 }
 
-static int tegra_pcie_enable_slot_regulators(struct tegra194_pcie *pcie)
+static int tegra_pcie_enable_slot_regulators(struct tegra_pcie_dw *pcie)
 {
 	int ret;
 
@@ -1307,7 +1351,7 @@
 	return ret;
 }
 
-static void tegra_pcie_disable_slot_regulators(struct tegra194_pcie *pcie)
+static void tegra_pcie_disable_slot_regulators(struct tegra_pcie_dw *pcie)
 {
 	if (pcie->slot_ctl_12v)
 		regulator_disable(pcie->slot_ctl_12v);
@@ -1315,7 +1359,7 @@
 		regulator_disable(pcie->slot_ctl_3v3);
 }
 
-static int tegra_pcie_config_controller(struct tegra194_pcie *pcie,
+static int tegra_pcie_config_controller(struct tegra_pcie_dw *pcie,
 					bool en_hw_hot_rst)
 {
 	int ret;
@@ -1328,6 +1372,14 @@
 		return ret;
 	}
 
+	if (pcie->enable_ext_refclk) {
+		ret = tegra_pcie_bpmp_set_pll_state(pcie, true);
+		if (ret) {
+			dev_err(pcie->dev, "Failed to init UPHY: %d\n", ret);
+			goto fail_pll_init;
+		}
+	}
+
 	ret = tegra_pcie_enable_slot_regulators(pcie);
 	if (ret < 0)
 		goto fail_slot_reg_en;
@@ -1351,11 +1403,13 @@
 		goto fail_core_apb_rst;
 	}
 
-	if (en_hw_hot_rst) {
+	if (en_hw_hot_rst || pcie->of_data->has_sbr_reset_fix) {
 		/* Enable HW_HOT_RST mode */
 		val = appl_readl(pcie, APPL_CTRL);
 		val &= ~(APPL_CTRL_HW_HOT_RST_MODE_MASK <<
 			 APPL_CTRL_HW_HOT_RST_MODE_SHIFT);
+		val |= (APPL_CTRL_HW_HOT_RST_MODE_IMDT_RST_LTSSM_EN <<
+			APPL_CTRL_HW_HOT_RST_MODE_SHIFT);
 		val |= APPL_CTRL_HW_HOT_RST_EN;
 		appl_writel(pcie, val, APPL_CTRL);
 	}
@@ -1382,6 +1436,19 @@
 	val |= (APPL_CFG_MISC_ARCACHE_VAL << APPL_CFG_MISC_ARCACHE_SHIFT);
 	appl_writel(pcie, val, APPL_CFG_MISC);
 
+	if (pcie->enable_srns || pcie->enable_ext_refclk) {
+		/*
+		 * When Tegra PCIe RP is using external clock, it cannot supply
+		 * same clock to its downstream hierarchy. Hence, gate PCIe RP
+		 * REFCLK out pads when RP & EP are using separate clocks or RP
+		 * is using an external REFCLK.
+		 */
+		val = appl_readl(pcie, APPL_PINMUX);
+		val |= APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE_EN;
+		val &= ~APPL_PINMUX_CLK_OUTPUT_IN_OVERRIDE;
+		appl_writel(pcie, val, APPL_PINMUX);
+	}
+
 	if (!pcie->supports_clkreq) {
 		val = appl_readl(pcie, APPL_PINMUX);
 		val |= APPL_PINMUX_CLKREQ_OVERRIDE_EN;
@@ -1407,12 +1474,15 @@
 fail_reg_en:
 	tegra_pcie_disable_slot_regulators(pcie);
 fail_slot_reg_en:
+	if (pcie->enable_ext_refclk)
+		tegra_pcie_bpmp_set_pll_state(pcie, false);
+fail_pll_init:
 	tegra_pcie_bpmp_set_ctrl_state(pcie, false);
 
 	return ret;
 }
 
-static void tegra_pcie_unconfig_controller(struct tegra194_pcie *pcie)
+static void tegra_pcie_unconfig_controller(struct tegra_pcie_dw *pcie)
 {
 	int ret;
 
@@ -1434,23 +1504,29 @@
 
 	tegra_pcie_disable_slot_regulators(pcie);
 
+	if (pcie->enable_ext_refclk) {
+		ret = tegra_pcie_bpmp_set_pll_state(pcie, false);
+		if (ret)
+			dev_err(pcie->dev, "Failed to deinit UPHY: %d\n", ret);
+	}
+
 	ret = tegra_pcie_bpmp_set_ctrl_state(pcie, false);
 	if (ret)
 		dev_err(pcie->dev, "Failed to disable controller %d: %d\n",
 			pcie->cid, ret);
 }
 
-static int tegra_pcie_init_controller(struct tegra194_pcie *pcie)
+static int tegra_pcie_init_controller(struct tegra_pcie_dw *pcie)
 {
 	struct dw_pcie *pci = &pcie->pci;
-	struct pcie_port *pp = &pci->pp;
+	struct dw_pcie_rp *pp = &pci->pp;
 	int ret;
 
 	ret = tegra_pcie_config_controller(pcie, false);
 	if (ret < 0)
 		return ret;
 
-	pp->ops = &tegra194_pcie_host_ops;
+	pp->ops = &tegra_pcie_dw_host_ops;
 
 	ret = dw_pcie_host_init(pp);
 	if (ret < 0) {
@@ -1465,11 +1541,11 @@
 	return ret;
 }
 
-static int tegra_pcie_try_link_l2(struct tegra194_pcie *pcie)
+static int tegra_pcie_try_link_l2(struct tegra_pcie_dw *pcie)
 {
 	u32 val;
 
-	if (!tegra194_pcie_link_up(&pcie->pci))
+	if (!tegra_pcie_dw_link_up(&pcie->pci))
 		return 0;
 
 	val = appl_readl(pcie, APPL_RADM_STATUS);
@@ -1481,12 +1557,12 @@
 				 1, PME_ACK_TIMEOUT);
 }
 
-static void tegra194_pcie_pme_turnoff(struct tegra194_pcie *pcie)
+static void tegra_pcie_dw_pme_turnoff(struct tegra_pcie_dw *pcie)
 {
 	u32 data;
 	int err;
 
-	if (!tegra194_pcie_link_up(&pcie->pci)) {
+	if (!tegra_pcie_dw_link_up(&pcie->pci)) {
 		dev_dbg(pcie->dev, "PCIe link is not up...!\n");
 		return;
 	}
@@ -1543,15 +1619,15 @@
 	appl_writel(pcie, data, APPL_PINMUX);
 }
 
-static void tegra_pcie_deinit_controller(struct tegra194_pcie *pcie)
+static void tegra_pcie_deinit_controller(struct tegra_pcie_dw *pcie)
 {
 	tegra_pcie_downstream_dev_to_D0(pcie);
 	dw_pcie_host_deinit(&pcie->pci.pp);
-	tegra194_pcie_pme_turnoff(pcie);
+	tegra_pcie_dw_pme_turnoff(pcie);
 	tegra_pcie_unconfig_controller(pcie);
 }
 
-static int tegra_pcie_config_rp(struct tegra194_pcie *pcie)
+static int tegra_pcie_config_rp(struct tegra_pcie_dw *pcie)
 {
 	struct device *dev = pcie->dev;
 	char *name;
@@ -1578,7 +1654,7 @@
 		goto fail_pm_get_sync;
 	}
 
-	pcie->link_state = tegra194_pcie_link_up(&pcie->pci);
+	pcie->link_state = tegra_pcie_dw_link_up(&pcie->pci);
 	if (!pcie->link_state) {
 		ret = -ENOMEDIUM;
 		goto fail_host_init;
@@ -1603,7 +1679,7 @@
 	return ret;
 }
 
-static void pex_ep_event_pex_rst_assert(struct tegra194_pcie *pcie)
+static void pex_ep_event_pex_rst_assert(struct tegra_pcie_dw *pcie)
 {
 	u32 val;
 	int ret;
@@ -1634,6 +1710,13 @@
 
 	pm_runtime_put_sync(pcie->dev);
 
+	if (pcie->enable_ext_refclk) {
+		ret = tegra_pcie_bpmp_set_pll_state(pcie, false);
+		if (ret)
+			dev_err(pcie->dev, "Failed to turn off UPHY: %d\n",
+				ret);
+	}
+
 	ret = tegra_pcie_bpmp_set_pll_state(pcie, false);
 	if (ret)
 		dev_err(pcie->dev, "Failed to turn off UPHY: %d\n", ret);
@@ -1642,13 +1725,14 @@
 	dev_dbg(pcie->dev, "Uninitialization of endpoint is completed\n");
 }
 
-static void pex_ep_event_pex_rst_deassert(struct tegra194_pcie *pcie)
+static void pex_ep_event_pex_rst_deassert(struct tegra_pcie_dw *pcie)
 {
 	struct dw_pcie *pci = &pcie->pci;
 	struct dw_pcie_ep *ep = &pci->ep;
 	struct device *dev = pcie->dev;
 	u32 val;
 	int ret;
+	u16 val_16;
 
 	if (pcie->ep_state == EP_STATE_ENABLED)
 		return;
@@ -1660,10 +1744,20 @@
 		return;
 	}
 
-	ret = tegra_pcie_bpmp_set_pll_state(pcie, true);
+	ret = tegra_pcie_bpmp_set_ctrl_state(pcie, true);
 	if (ret) {
-		dev_err(dev, "Failed to init UPHY for PCIe EP: %d\n", ret);
-		goto fail_pll_init;
+		dev_err(pcie->dev, "Failed to enable controller %u: %d\n",
+			pcie->cid, ret);
+		goto fail_set_ctrl_state;
+	}
+
+	if (pcie->enable_ext_refclk) {
+		ret = tegra_pcie_bpmp_set_pll_state(pcie, true);
+		if (ret) {
+			dev_err(dev, "Failed to init UPHY for PCIe EP: %d\n",
+				ret);
+			goto fail_pll_init;
+		}
 	}
 
 	ret = clk_prepare_enable(pcie->core_clk);
@@ -1760,12 +1854,29 @@
 		disable_aspm_l12(pcie);
 	}
 
-	val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF);
-	val &= ~GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL;
-	dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val);
+	if (!pcie->of_data->has_l1ss_exit_fix) {
+		val = dw_pcie_readl_dbi(pci, GEN3_RELATED_OFF);
+		val &= ~GEN3_RELATED_OFF_GEN3_ZRXDC_NONCOMPL;
+		dw_pcie_writel_dbi(pci, GEN3_RELATED_OFF, val);
+	}
 
 	pcie->pcie_cap_base = dw_pcie_find_capability(&pcie->pci,
 						      PCI_CAP_ID_EXP);
+
+	val_16 = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base + PCI_EXP_DEVCTL);
+	val_16 &= ~PCI_EXP_DEVCTL_PAYLOAD;
+	val_16 |= PCI_EXP_DEVCTL_PAYLOAD_256B;
+	dw_pcie_writew_dbi(pci, pcie->pcie_cap_base + PCI_EXP_DEVCTL, val_16);
+
+	/* Clear Slot Clock Configuration bit if SRNS configuration */
+	if (pcie->enable_srns) {
+		val_16 = dw_pcie_readw_dbi(pci, pcie->pcie_cap_base +
+					   PCI_EXP_LNKSTA);
+		val_16 &= ~PCI_EXP_LNKSTA_SLC;
+		dw_pcie_writew_dbi(pci, pcie->pcie_cap_base + PCI_EXP_LNKSTA,
+				   val_16);
+	}
+
 	clk_set_rate(pcie->core_clk, GEN4_CORE_CLK_FREQ);
 
 	val = (ep->msi_mem_phys & MSIX_ADDR_MATCH_LOW_OFF_MASK);
@@ -1782,6 +1893,13 @@
 
 	dw_pcie_ep_init_notify(ep);
 
+	/* Program the private control to allow sending LTR upstream */
+	if (pcie->of_data->has_ltr_req_fix) {
+		val = appl_readl(pcie, APPL_LTR_MSG_2);
+		val |= APPL_LTR_MSG_2_LTR_MSG_REQ_STATE;
+		appl_writel(pcie, val, APPL_LTR_MSG_2);
+	}
+
 	/* Enable LTSSM */
 	val = appl_readl(pcie, APPL_CTRL);
 	val |= APPL_CTRL_LTSSM_EN;
@@ -1802,12 +1920,14 @@
 fail_core_clk_enable:
 	tegra_pcie_bpmp_set_pll_state(pcie, false);
 fail_pll_init:
+	tegra_pcie_bpmp_set_ctrl_state(pcie, false);
+fail_set_ctrl_state:
 	pm_runtime_put_sync(dev);
 }
 
 static irqreturn_t tegra_pcie_ep_pex_rst_irq(int irq, void *arg)
 {
-	struct tegra194_pcie *pcie = arg;
+	struct tegra_pcie_dw *pcie = arg;
 
 	if (gpiod_get_value(pcie->pex_rst_gpiod))
 		pex_ep_event_pex_rst_assert(pcie);
@@ -1817,7 +1937,7 @@
 	return IRQ_HANDLED;
 }
 
-static int tegra_pcie_ep_raise_legacy_irq(struct tegra194_pcie *pcie, u16 irq)
+static int tegra_pcie_ep_raise_legacy_irq(struct tegra_pcie_dw *pcie, u16 irq)
 {
 	/* Tegra194 supports only INTA */
 	if (irq > 1)
@@ -1829,7 +1949,7 @@
 	return 0;
 }
 
-static int tegra_pcie_ep_raise_msi_irq(struct tegra194_pcie *pcie, u16 irq)
+static int tegra_pcie_ep_raise_msi_irq(struct tegra_pcie_dw *pcie, u16 irq)
 {
 	if (unlikely(irq > 31))
 		return -EINVAL;
@@ -1839,7 +1959,7 @@
 	return 0;
 }
 
-static int tegra_pcie_ep_raise_msix_irq(struct tegra194_pcie *pcie, u16 irq)
+static int tegra_pcie_ep_raise_msix_irq(struct tegra_pcie_dw *pcie, u16 irq)
 {
 	struct dw_pcie_ep *ep = &pcie->pci.ep;
 
@@ -1853,7 +1973,7 @@
 				   u16 interrupt_num)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
-	struct tegra194_pcie *pcie = to_tegra_pcie(pci);
+	struct tegra_pcie_dw *pcie = to_tegra_pcie(pci);
 
 	switch (type) {
 	case PCI_EPC_IRQ_LEGACY:
@@ -1894,7 +2014,7 @@
 	.get_features = tegra_pcie_ep_get_features,
 };
 
-static int tegra_pcie_config_ep(struct tegra194_pcie *pcie,
+static int tegra_pcie_config_ep(struct tegra_pcie_dw *pcie,
 				struct platform_device *pdev)
 {
 	struct dw_pcie *pci = &pcie->pci;
@@ -1949,19 +2069,20 @@
 	if (ret) {
 		dev_err(dev, "Failed to initialize DWC Endpoint subsystem: %d\n",
 			ret);
+		pm_runtime_disable(dev);
 		return ret;
 	}
 
 	return 0;
 }
 
-static int tegra194_pcie_probe(struct platform_device *pdev)
+static int tegra_pcie_dw_probe(struct platform_device *pdev)
 {
-	const struct tegra194_pcie_of_data *data;
+	const struct tegra_pcie_dw_of_data *data;
 	struct device *dev = &pdev->dev;
 	struct resource *atu_dma_res;
-	struct tegra194_pcie *pcie;
-	struct pcie_port *pp;
+	struct tegra_pcie_dw *pcie;
+	struct dw_pcie_rp *pp;
 	struct dw_pcie *pci;
 	struct phy **phys;
 	char *name;
@@ -1977,16 +2098,14 @@
 	pci = &pcie->pci;
 	pci->dev = &pdev->dev;
 	pci->ops = &tegra_dw_pcie_ops;
-	pci->n_fts[0] = N_FTS_VAL;
-	pci->n_fts[1] = FTS_VAL;
-	pci->version = 0x490A;
-
+	pcie->dev = &pdev->dev;
+	pcie->of_data = (struct tegra_pcie_dw_of_data *)data;
+	pci->n_fts[0] = pcie->of_data->n_fts[0];
+	pci->n_fts[1] = pcie->of_data->n_fts[1];
 	pp = &pci->pp;
 	pp->num_vectors = MAX_MSI_IRQS;
-	pcie->dev = &pdev->dev;
-	pcie->mode = (enum dw_pcie_device_mode)data->mode;
 
-	ret = tegra194_pcie_parse_dt(pcie);
+	ret = tegra_pcie_dw_parse_dt(pcie);
 	if (ret < 0) {
 		const char *level = KERN_ERR;
 
@@ -2101,7 +2220,7 @@
 
 	platform_set_drvdata(pdev, pcie);
 
-	switch (pcie->mode) {
+	switch (pcie->of_data->mode) {
 	case DW_PCIE_RC_TYPE:
 		ret = devm_request_irq(dev, pp->irq, tegra_pcie_rp_irq_handler,
 				       IRQF_SHARED, "tegra-pcie-intr", pcie);
@@ -2136,7 +2255,8 @@
 		break;
 
 	default:
-		dev_err(dev, "Invalid PCIe device type %d\n", pcie->mode);
+		dev_err(dev, "Invalid PCIe device type %d\n",
+			pcie->of_data->mode);
 	}
 
 fail:
@@ -2144,16 +2264,22 @@
 	return ret;
 }
 
-static int tegra194_pcie_remove(struct platform_device *pdev)
+static int tegra_pcie_dw_remove(struct platform_device *pdev)
 {
-	struct tegra194_pcie *pcie = platform_get_drvdata(pdev);
+	struct tegra_pcie_dw *pcie = platform_get_drvdata(pdev);
 
-	if (!pcie->link_state)
-		return 0;
+	if (pcie->of_data->mode == DW_PCIE_RC_TYPE) {
+		if (!pcie->link_state)
+			return 0;
 
-	debugfs_remove_recursive(pcie->debugfs);
-	tegra_pcie_deinit_controller(pcie);
-	pm_runtime_put_sync(pcie->dev);
+		debugfs_remove_recursive(pcie->debugfs);
+		tegra_pcie_deinit_controller(pcie);
+		pm_runtime_put_sync(pcie->dev);
+	} else {
+		disable_irq(pcie->pex_rst_irq);
+		pex_ep_event_pex_rst_assert(pcie);
+	}
+
 	pm_runtime_disable(pcie->dev);
 	tegra_bpmp_put(pcie->bpmp);
 	if (pcie->pex_refclk_sel_gpiod)
@@ -2162,41 +2288,48 @@
 	return 0;
 }
 
-static int tegra194_pcie_suspend_late(struct device *dev)
+static int tegra_pcie_dw_suspend_late(struct device *dev)
 {
-	struct tegra194_pcie *pcie = dev_get_drvdata(dev);
+	struct tegra_pcie_dw *pcie = dev_get_drvdata(dev);
 	u32 val;
 
+	if (pcie->of_data->mode == DW_PCIE_EP_TYPE) {
+		dev_err(dev, "Failed to Suspend as Tegra PCIe is in EP mode\n");
+		return -EPERM;
+	}
+
 	if (!pcie->link_state)
 		return 0;
 
 	/* Enable HW_HOT_RST mode */
-	val = appl_readl(pcie, APPL_CTRL);
-	val &= ~(APPL_CTRL_HW_HOT_RST_MODE_MASK <<
-		 APPL_CTRL_HW_HOT_RST_MODE_SHIFT);
-	val |= APPL_CTRL_HW_HOT_RST_EN;
-	appl_writel(pcie, val, APPL_CTRL);
+	if (!pcie->of_data->has_sbr_reset_fix) {
+		val = appl_readl(pcie, APPL_CTRL);
+		val &= ~(APPL_CTRL_HW_HOT_RST_MODE_MASK <<
+			 APPL_CTRL_HW_HOT_RST_MODE_SHIFT);
+		val |= APPL_CTRL_HW_HOT_RST_EN;
+		appl_writel(pcie, val, APPL_CTRL);
+	}
 
 	return 0;
 }
 
-static int tegra194_pcie_suspend_noirq(struct device *dev)
+static int tegra_pcie_dw_suspend_noirq(struct device *dev)
 {
-	struct tegra194_pcie *pcie = dev_get_drvdata(dev);
+	struct tegra_pcie_dw *pcie = dev_get_drvdata(dev);
 
 	if (!pcie->link_state)
 		return 0;
 
 	tegra_pcie_downstream_dev_to_D0(pcie);
-	tegra194_pcie_pme_turnoff(pcie);
+	tegra_pcie_dw_pme_turnoff(pcie);
 	tegra_pcie_unconfig_controller(pcie);
 
 	return 0;
 }
 
-static int tegra194_pcie_resume_noirq(struct device *dev)
+static int tegra_pcie_dw_resume_noirq(struct device *dev)
 {
-	struct tegra194_pcie *pcie = dev_get_drvdata(dev);
+	struct tegra_pcie_dw *pcie = dev_get_drvdata(dev);
 	int ret;
 
 	if (!pcie->link_state)
@@ -2206,7 +2339,7 @@
 	if (ret < 0)
 		return ret;
 
-	ret = tegra194_pcie_host_init(&pcie->pci.pp);
+	ret = tegra_pcie_dw_host_init(&pcie->pci.pp);
 	if (ret < 0) {
 		dev_err(dev, "Failed to init host: %d\n", ret);
 		goto fail_host_init;
@@ -2214,7 +2347,7 @@
 
 	dw_pcie_setup_rc(&pcie->pci.pp);
 
-	ret = tegra194_pcie_start_link(&pcie->pci);
+	ret = tegra_pcie_dw_start_link(&pcie->pci);
 	if (ret < 0)
 		goto fail_host_init;
 
@@ -2225,12 +2358,12 @@
 	return ret;
 }
 
-static int tegra194_pcie_resume_early(struct device *dev)
+static int tegra_pcie_dw_resume_early(struct device *dev)
 {
-	struct tegra194_pcie *pcie = dev_get_drvdata(dev);
+	struct tegra_pcie_dw *pcie = dev_get_drvdata(dev);
 	u32 val;
 
-	if (pcie->mode == DW_PCIE_EP_TYPE) {
+	if (pcie->of_data->mode == DW_PCIE_EP_TYPE) {
 		dev_err(dev, "Suspend is not supported in EP mode");
 		return -ENOTSUPP;
 	}
@@ -2239,75 +2372,124 @@
 		return 0;
 
 	/* Disable HW_HOT_RST mode */
-	val = appl_readl(pcie, APPL_CTRL);
-	val &= ~(APPL_CTRL_HW_HOT_RST_MODE_MASK <<
-		 APPL_CTRL_HW_HOT_RST_MODE_SHIFT);
-	val |= APPL_CTRL_HW_HOT_RST_MODE_IMDT_RST <<
-	       APPL_CTRL_HW_HOT_RST_MODE_SHIFT;
-	val &= ~APPL_CTRL_HW_HOT_RST_EN;
-	appl_writel(pcie, val, APPL_CTRL);
+	if (!pcie->of_data->has_sbr_reset_fix) {
+		val = appl_readl(pcie, APPL_CTRL);
+		val &= ~(APPL_CTRL_HW_HOT_RST_MODE_MASK <<
+			 APPL_CTRL_HW_HOT_RST_MODE_SHIFT);
+		val |= APPL_CTRL_HW_HOT_RST_MODE_IMDT_RST <<
+		       APPL_CTRL_HW_HOT_RST_MODE_SHIFT;
+		val &= ~APPL_CTRL_HW_HOT_RST_EN;
+		appl_writel(pcie, val, APPL_CTRL);
+	}
 
 	return 0;
 }
 
-static void tegra194_pcie_shutdown(struct platform_device *pdev)
+static void tegra_pcie_dw_shutdown(struct platform_device *pdev)
 {
-	struct tegra194_pcie *pcie = platform_get_drvdata(pdev);
+	struct tegra_pcie_dw *pcie = platform_get_drvdata(pdev);
 
-	if (!pcie->link_state)
-		return;
+	if (pcie->of_data->mode == DW_PCIE_RC_TYPE) {
+		if (!pcie->link_state)
+			return;
 
-	debugfs_remove_recursive(pcie->debugfs);
-	tegra_pcie_downstream_dev_to_D0(pcie);
+		debugfs_remove_recursive(pcie->debugfs);
+		tegra_pcie_downstream_dev_to_D0(pcie);
 
-	disable_irq(pcie->pci.pp.irq);
-	if (IS_ENABLED(CONFIG_PCI_MSI))
-		disable_irq(pcie->pci.pp.msi_irq);
+		disable_irq(pcie->pci.pp.irq);
+		if (IS_ENABLED(CONFIG_PCI_MSI))
+			disable_irq(pcie->pci.pp.msi_irq[0]);
 
-	tegra194_pcie_pme_turnoff(pcie);
-	tegra_pcie_unconfig_controller(pcie);
+		tegra_pcie_dw_pme_turnoff(pcie);
+		tegra_pcie_unconfig_controller(pcie);
+		pm_runtime_put_sync(pcie->dev);
+	} else {
+		disable_irq(pcie->pex_rst_irq);
+		pex_ep_event_pex_rst_assert(pcie);
+	}
 }
 
-static const struct tegra194_pcie_of_data tegra194_pcie_rc_of_data = {
+static const struct tegra_pcie_dw_of_data tegra194_pcie_dw_rc_of_data = {
+	.version = TEGRA194_DWC_IP_VER,
 	.mode = DW_PCIE_RC_TYPE,
+	.cdm_chk_int_en_bit = BIT(19),
+	/* Gen4 - 5, 6, 8 and 9 presets enabled */
+	.gen4_preset_vec = 0x360,
+	.n_fts = { 52, 52 },
 };
 
-static const struct tegra194_pcie_of_data tegra194_pcie_ep_of_data = {
+static const struct tegra_pcie_dw_of_data tegra194_pcie_dw_ep_of_data = {
+	.version = TEGRA194_DWC_IP_VER,
 	.mode = DW_PCIE_EP_TYPE,
+	.cdm_chk_int_en_bit = BIT(19),
+	/* Gen4 - 5, 6, 8 and 9 presets enabled */
+	.gen4_preset_vec = 0x360,
+	.n_fts = { 52, 52 },
 };
 
-static const struct of_device_id tegra194_pcie_of_match[] = {
+static const struct tegra_pcie_dw_of_data tegra234_pcie_dw_rc_of_data = {
+	.version = TEGRA234_DWC_IP_VER,
+	.mode = DW_PCIE_RC_TYPE,
+	.has_msix_doorbell_access_fix = true,
+	.has_sbr_reset_fix = true,
+	.has_l1ss_exit_fix = true,
+	.cdm_chk_int_en_bit = BIT(18),
+	/* Gen4 - 6, 8 and 9 presets enabled */
+	.gen4_preset_vec = 0x340,
+	.n_fts = { 52, 80 },
+};
+
+static const struct tegra_pcie_dw_of_data tegra234_pcie_dw_ep_of_data = {
+	.version = TEGRA234_DWC_IP_VER,
+	.mode = DW_PCIE_EP_TYPE,
+	.has_l1ss_exit_fix = true,
+	.has_ltr_req_fix = true,
+	.cdm_chk_int_en_bit = BIT(18),
+	/* Gen4 - 6, 8 and 9 presets enabled */
+	.gen4_preset_vec = 0x340,
+	.n_fts = { 52, 80 },
+};
+
+static const struct of_device_id tegra_pcie_dw_of_match[] = {
 	{
 		.compatible = "nvidia,tegra194-pcie",
-		.data = &tegra194_pcie_rc_of_data,
+		.data = &tegra194_pcie_dw_rc_of_data,
 	},
 	{
 		.compatible = "nvidia,tegra194-pcie-ep",
-		.data = &tegra194_pcie_ep_of_data,
+		.data = &tegra194_pcie_dw_ep_of_data,
 	},
-	{},
+	{
+		.compatible = "nvidia,tegra234-pcie",
+		.data = &tegra234_pcie_dw_rc_of_data,
+	},
+	{
+		.compatible = "nvidia,tegra234-pcie-ep",
+		.data = &tegra234_pcie_dw_ep_of_data,
+	},
+	{}
 };
 
-static const struct dev_pm_ops tegra194_pcie_pm_ops = {
-	.suspend_late = tegra194_pcie_suspend_late,
-	.suspend_noirq = tegra194_pcie_suspend_noirq,
-	.resume_noirq = tegra194_pcie_resume_noirq,
-	.resume_early = tegra194_pcie_resume_early,
+static const struct dev_pm_ops tegra_pcie_dw_pm_ops = {
+	.suspend_late = tegra_pcie_dw_suspend_late,
+	.suspend_noirq = tegra_pcie_dw_suspend_noirq,
+	.resume_noirq = tegra_pcie_dw_resume_noirq,
+	.resume_early = tegra_pcie_dw_resume_early,
 };
 
-static struct platform_driver tegra194_pcie_driver = {
-	.probe = tegra194_pcie_probe,
-	.remove = tegra194_pcie_remove,
-	.shutdown = tegra194_pcie_shutdown,
+static struct platform_driver tegra_pcie_dw_driver = {
+	.probe = tegra_pcie_dw_probe,
+	.remove = tegra_pcie_dw_remove,
+	.shutdown = tegra_pcie_dw_shutdown,
 	.driver = {
 		.name	= "tegra194-pcie",
-		.pm = &tegra194_pcie_pm_ops,
-		.of_match_table = tegra194_pcie_of_match,
+		.pm = &tegra_pcie_dw_pm_ops,
+		.of_match_table = tegra_pcie_dw_of_match,
 	},
 };
-module_platform_driver(tegra194_pcie_driver);
+module_platform_driver(tegra_pcie_dw_driver);
 
-MODULE_DEVICE_TABLE(of, tegra194_pcie_of_match);
+MODULE_DEVICE_TABLE(of, tegra_pcie_dw_of_match);
 
 MODULE_AUTHOR("Vidya Sagar <vidyas@nvidia.com>");
 MODULE_DESCRIPTION("NVIDIA PCIe host controller driver");
diff --git a/drivers/pci/controller/dwc/pcie-uniphier.c b/drivers/pci/controller/dwc/pcie-uniphier.c
index b45ac37..48c3eba 100644
--- a/drivers/pci/controller/dwc/pcie-uniphier.c
+++ b/drivers/pci/controller/dwc/pcie-uniphier.c
@@ -171,7 +171,7 @@
 
 static void uniphier_pcie_irq_mask(struct irq_data *d)
 {
-	struct pcie_port *pp = irq_data_get_irq_chip_data(d);
+	struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(d);
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct uniphier_pcie *pcie = to_uniphier_pcie(pci);
 	unsigned long flags;
@@ -188,7 +188,7 @@
 
 static void uniphier_pcie_irq_unmask(struct irq_data *d)
 {
-	struct pcie_port *pp = irq_data_get_irq_chip_data(d);
+	struct dw_pcie_rp *pp = irq_data_get_irq_chip_data(d);
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct uniphier_pcie *pcie = to_uniphier_pcie(pci);
 	unsigned long flags;
@@ -225,7 +225,7 @@
 
 static void uniphier_pcie_irq_handler(struct irq_desc *desc)
 {
-	struct pcie_port *pp = irq_desc_get_handler_data(desc);
+	struct dw_pcie_rp *pp = irq_desc_get_handler_data(desc);
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct uniphier_pcie *pcie = to_uniphier_pcie(pci);
 	struct irq_chip *chip = irq_desc_get_chip(desc);
@@ -258,7 +258,7 @@
 	chained_irq_exit(chip, desc);
 }
 
-static int uniphier_pcie_config_legacy_irq(struct pcie_port *pp)
+static int uniphier_pcie_config_legacy_irq(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct uniphier_pcie *pcie = to_uniphier_pcie(pci);
@@ -295,7 +295,7 @@
 	return ret;
 }
 
-static int uniphier_pcie_host_init(struct pcie_port *pp)
+static int uniphier_pcie_host_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct uniphier_pcie *pcie = to_uniphier_pcie(pci);
diff --git a/drivers/pci/controller/dwc/pcie-visconti.c b/drivers/pci/controller/dwc/pcie-visconti.c
index 50f80f0..71026fe 100644
--- a/drivers/pci/controller/dwc/pcie-visconti.c
+++ b/drivers/pci/controller/dwc/pcie-visconti.c
@@ -178,7 +178,7 @@
  */
 static u64 visconti_pcie_cpu_addr_fixup(struct dw_pcie *pci, u64 cpu_addr)
 {
-	struct pcie_port *pp = &pci->pp;
+	struct dw_pcie_rp *pp = &pci->pp;
 
 	return cpu_addr & ~pp->io_base;
 }
@@ -190,7 +190,7 @@
 	.stop_link = visconti_pcie_stop_link,
 };
 
-static int visconti_pcie_host_init(struct pcie_port *pp)
+static int visconti_pcie_host_init(struct dw_pcie_rp *pp)
 {
 	struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
 	struct visconti_pcie *pcie = dev_get_drvdata(pci->dev);
@@ -278,7 +278,7 @@
 				  struct platform_device *pdev)
 {
 	struct dw_pcie *pci = &pcie->pci;
-	struct pcie_port *pp = &pci->pp;
+	struct dw_pcie_rp *pp = &pci->pp;
 
 	pp->irq = platform_get_irq_byname(pdev, "intr");
 	if (pp->irq < 0)
diff --git a/drivers/pci/controller/pci-aardvark.c b/drivers/pci/controller/pci-aardvark.c
index ffec82c..966c8b4 100644
--- a/drivers/pci/controller/pci-aardvark.c
+++ b/drivers/pci/controller/pci-aardvark.c
@@ -8,6 +8,7 @@
  * Author: Hezi Shahmoon <hezi.shahmoon@marvell.com>
  */
 
+#include <linux/bitfield.h>
 #include <linux/delay.h>
 #include <linux/gpio/consumer.h>
 #include <linux/interrupt.h>
@@ -33,6 +34,7 @@
 #define PCIE_CORE_CMD_STATUS_REG				0x4
 #define PCIE_CORE_DEV_REV_REG					0x8
 #define PCIE_CORE_PCIEXP_CAP					0xc0
+#define PCIE_CORE_PCIERR_CAP					0x100
 #define PCIE_CORE_ERR_CAPCTL_REG				0x118
 #define     PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX			BIT(5)
 #define     PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX_EN			BIT(6)
@@ -857,14 +859,11 @@
 
 
 	switch (reg) {
-	case PCI_EXP_SLTCTL:
-		*value = PCI_EXP_SLTSTA_PDS << 16;
-		return PCI_BRIDGE_EMUL_HANDLED;
-
 	/*
-	 * PCI_EXP_RTCTL and PCI_EXP_RTSTA are also supported, but do not need
-	 * to be handled here, because their values are stored in emulated
-	 * config space buffer, and we read them from there when needed.
+	 * PCI_EXP_SLTCAP, PCI_EXP_SLTCTL, PCI_EXP_RTCTL and PCI_EXP_RTSTA are
+	 * also supported, but do not need to be handled here, because their
+	 * values are stored in emulated config space buffer, and we read them
+	 * from there when needed.
 	 */
 
 	case PCI_EXP_LNKCAP: {
@@ -944,11 +943,89 @@
 	}
 }
 
+static pci_bridge_emul_read_status_t
+advk_pci_bridge_emul_ext_conf_read(struct pci_bridge_emul *bridge,
+				   int reg, u32 *value)
+{
+	struct advk_pcie *pcie = bridge->data;
+
+	switch (reg) {
+	case 0:
+		*value = advk_readl(pcie, PCIE_CORE_PCIERR_CAP + reg);
+
+		/*
+		 * PCI_EXT_CAP_NEXT bits are set to offset 0x150, but Armada
+		 * 3700 Functional Specification does not document registers
+		 * at those addresses.
+		 *
+		 * Thus we clear PCI_EXT_CAP_NEXT bits to make Advanced Error
+		 * Reporting Capability header the last Extended Capability.
+		 * If we obtain documentation for those registers in the
+		 * future, this can be changed.
+		 */
+		*value &= 0x000fffff;
+		return PCI_BRIDGE_EMUL_HANDLED;
+
+	case PCI_ERR_UNCOR_STATUS:
+	case PCI_ERR_UNCOR_MASK:
+	case PCI_ERR_UNCOR_SEVER:
+	case PCI_ERR_COR_STATUS:
+	case PCI_ERR_COR_MASK:
+	case PCI_ERR_CAP:
+	case PCI_ERR_HEADER_LOG + 0:
+	case PCI_ERR_HEADER_LOG + 4:
+	case PCI_ERR_HEADER_LOG + 8:
+	case PCI_ERR_HEADER_LOG + 12:
+	case PCI_ERR_ROOT_COMMAND:
+	case PCI_ERR_ROOT_STATUS:
+	case PCI_ERR_ROOT_ERR_SRC:
+		*value = advk_readl(pcie, PCIE_CORE_PCIERR_CAP + reg);
+		return PCI_BRIDGE_EMUL_HANDLED;
+
+	default:
+		return PCI_BRIDGE_EMUL_NOT_HANDLED;
+	}
+}
+
+static void
+advk_pci_bridge_emul_ext_conf_write(struct pci_bridge_emul *bridge,
+				    int reg, u32 old, u32 new, u32 mask)
+{
+	struct advk_pcie *pcie = bridge->data;
+
+	switch (reg) {
+	/* These are W1C registers, so clear other bits */
+	case PCI_ERR_UNCOR_STATUS:
+	case PCI_ERR_COR_STATUS:
+	case PCI_ERR_ROOT_STATUS:
+		new &= mask;
+		fallthrough;
+
+	case PCI_ERR_UNCOR_MASK:
+	case PCI_ERR_UNCOR_SEVER:
+	case PCI_ERR_COR_MASK:
+	case PCI_ERR_CAP:
+	case PCI_ERR_HEADER_LOG + 0:
+	case PCI_ERR_HEADER_LOG + 4:
+	case PCI_ERR_HEADER_LOG + 8:
+	case PCI_ERR_HEADER_LOG + 12:
+	case PCI_ERR_ROOT_COMMAND:
+	case PCI_ERR_ROOT_ERR_SRC:
+		advk_writel(pcie, new, PCIE_CORE_PCIERR_CAP + reg);
+		break;
+
+	default:
+		break;
+	}
+}
+
 static const struct pci_bridge_emul_ops advk_pci_bridge_emul_ops = {
 	.read_base = advk_pci_bridge_emul_base_conf_read,
 	.write_base = advk_pci_bridge_emul_base_conf_write,
 	.read_pcie = advk_pci_bridge_emul_pcie_conf_read,
 	.write_pcie = advk_pci_bridge_emul_pcie_conf_write,
+	.read_ext = advk_pci_bridge_emul_ext_conf_read,
+	.write_ext = advk_pci_bridge_emul_ext_conf_write,
 };
 
 /*
@@ -977,8 +1054,25 @@
 	/* Support interrupt A for MSI feature */
 	bridge->conf.intpin = PCI_INTERRUPT_INTA;
 
-	/* Aardvark HW provides PCIe Capability structure in version 2 */
-	bridge->pcie_conf.cap = cpu_to_le16(2);
+	/*
+	 * Aardvark HW provides PCIe Capability structure in version 2 and
+	 * indicate slot support, which is emulated.
+	 */
+	bridge->pcie_conf.cap = cpu_to_le16(2 | PCI_EXP_FLAGS_SLOT);
+
+	/*
+	 * Set Presence Detect State bit permanently since there is no support
+	 * for unplugging the card nor detecting whether it is plugged. (If a
+	 * platform exists in the future that supports it, via a GPIO for
+	 * example, it should be implemented via this bit.)
+	 *
+	 * Set physical slot number to 1 since there is only one port and zero
+	 * value is reserved for ports within the same silicon as Root Port
+	 * which is not our case.
+	 */
+	bridge->pcie_conf.slotcap = cpu_to_le32(FIELD_PREP(PCI_EXP_SLTCAP_PSN,
+							   1));
+	bridge->pcie_conf.slotsta = cpu_to_le16(PCI_EXP_SLTSTA_PDS);
 
 	/* Indicates supports for Completion Retry Status */
 	bridge->pcie_conf.rootcap = cpu_to_le16(PCI_EXP_RTCAP_CRSVIS);
diff --git a/drivers/pci/controller/pci-loongson.c b/drivers/pci/controller/pci-loongson.c
index 50a8e1d..05c5040 100644
--- a/drivers/pci/controller/pci-loongson.c
+++ b/drivers/pci/controller/pci-loongson.c
@@ -9,6 +9,8 @@
 #include <linux/of_pci.h>
 #include <linux/pci.h>
 #include <linux/pci_ids.h>
+#include <linux/pci-acpi.h>
+#include <linux/pci-ecam.h>
 
 #include "../pci.h"
 
@@ -18,18 +20,31 @@
 #define DEV_PCIE_PORT_2	0x7a29
 
 #define DEV_LS2K_APB	0x7a02
-#define DEV_LS7A_CONF	0x7a10
+#define DEV_LS7A_GMAC	0x7a03
+#define DEV_LS7A_DC1	0x7a06
 #define DEV_LS7A_LPC	0x7a0c
+#define DEV_LS7A_AHCI	0x7a08
+#define DEV_LS7A_CONF	0x7a10
+#define DEV_LS7A_GNET	0x7a13
+#define DEV_LS7A_EHCI	0x7a14
+#define DEV_LS7A_DC2	0x7a36
+#define DEV_LS7A_HDMI	0x7a37
 
 #define FLAG_CFG0	BIT(0)
 #define FLAG_CFG1	BIT(1)
 #define FLAG_DEV_FIX	BIT(2)
+#define FLAG_DEV_HIDDEN	BIT(3)
+
+struct loongson_pci_data {
+	u32 flags;
+	struct pci_ops *ops;
+};
 
 struct loongson_pci {
 	void __iomem *cfg0_base;
 	void __iomem *cfg1_base;
 	struct platform_device *pdev;
-	u32 flags;
+	const struct loongson_pci_data *data;
 };
 
 /* Fixup wrong class code in PCIe bridges */
@@ -92,55 +107,106 @@
 }
 DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, loongson_mrrs_quirk);
 
-static void __iomem *cfg1_map(struct loongson_pci *priv, int bus,
-				unsigned int devfn, int where)
+static void loongson_pci_pin_quirk(struct pci_dev *pdev)
 {
-	unsigned long addroff = 0x0;
+	pdev->pin = 1 + (PCI_FUNC(pdev->devfn) & 3);
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON,
+			DEV_LS7A_DC1, loongson_pci_pin_quirk);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON,
+			DEV_LS7A_DC2, loongson_pci_pin_quirk);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON,
+			DEV_LS7A_GMAC, loongson_pci_pin_quirk);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON,
+			DEV_LS7A_AHCI, loongson_pci_pin_quirk);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON,
+			DEV_LS7A_EHCI, loongson_pci_pin_quirk);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON,
+			DEV_LS7A_GNET, loongson_pci_pin_quirk);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON,
+			DEV_LS7A_HDMI, loongson_pci_pin_quirk);
 
-	if (bus != 0)
-		addroff |= BIT(28); /* Type 1 Access */
-	addroff |= (where & 0xff) | ((where & 0xf00) << 16);
-	addroff |= (bus << 16) | (devfn << 8);
-	return priv->cfg1_base + addroff;
+static struct loongson_pci *pci_bus_to_loongson_pci(struct pci_bus *bus)
+{
+	struct pci_config_window *cfg;
+
+	if (acpi_disabled)
+		return (struct loongson_pci *)(bus->sysdata);
+
+	cfg = bus->sysdata;
+	return (struct loongson_pci *)(cfg->priv);
 }
 
-static void __iomem *cfg0_map(struct loongson_pci *priv, int bus,
-				unsigned int devfn, int where)
+static void __iomem *cfg0_map(struct loongson_pci *priv, struct pci_bus *bus,
+			      unsigned int devfn, int where)
 {
 	unsigned long addroff = 0x0;
+	unsigned char busnum = bus->number;
 
-	if (bus != 0)
+	if (!pci_is_root_bus(bus)) {
 		addroff |= BIT(24); /* Type 1 Access */
-	addroff |= (bus << 16) | (devfn << 8) | where;
+		addroff |= (busnum << 16);
+	}
+	addroff |= (devfn << 8) | where;
 	return priv->cfg0_base + addroff;
 }
 
-static void __iomem *pci_loongson_map_bus(struct pci_bus *bus, unsigned int devfn,
-			       int where)
+static void __iomem *cfg1_map(struct loongson_pci *priv, struct pci_bus *bus,
+			      unsigned int devfn, int where)
 {
+	unsigned long addroff = 0x0;
 	unsigned char busnum = bus->number;
-	struct pci_host_bridge *bridge = pci_find_host_bridge(bus);
-	struct loongson_pci *priv =  pci_host_bridge_priv(bridge);
+
+	if (!pci_is_root_bus(bus)) {
+		addroff |= BIT(28); /* Type 1 Access */
+		addroff |= (busnum << 16);
+	}
+	addroff |= (devfn << 8) | (where & 0xff) | ((where & 0xf00) << 16);
+	return priv->cfg1_base + addroff;
+}
+
+static bool pdev_may_exist(struct pci_bus *bus, unsigned int device,
+			   unsigned int function)
+{
+	return !(pci_is_root_bus(bus) &&
+		(device >= 9 && device <= 20) && (function > 0));
+}
+
+static void __iomem *pci_loongson_map_bus(struct pci_bus *bus,
+					  unsigned int devfn, int where)
+{
+	unsigned int device = PCI_SLOT(devfn);
+	unsigned int function = PCI_FUNC(devfn);
+	struct loongson_pci *priv = pci_bus_to_loongson_pci(bus);
 
 	/*
 	 * Do not read more than one device on the bus other than
-	 * the host bus. For our hardware the root bus is always bus 0.
+	 * the host bus.
 	 */
-	if (priv->flags & FLAG_DEV_FIX && busnum != 0 &&
-		PCI_SLOT(devfn) > 0)
-		return NULL;
+	if ((priv->data->flags & FLAG_DEV_FIX) && bus->self) {
+		if (!pci_is_root_bus(bus) && (device > 0))
+			return NULL;
+	}
+
+	/* Don't access non-existent devices */
+	if (priv->data->flags & FLAG_DEV_HIDDEN) {
+		if (!pdev_may_exist(bus, device, function))
+			return NULL;
+	}
 
 	/* CFG0 can only access standard space */
 	if (where < PCI_CFG_SPACE_SIZE && priv->cfg0_base)
-		return cfg0_map(priv, busnum, devfn, where);
+		return cfg0_map(priv, bus, devfn, where);
 
 	/* CFG1 can access extended space */
 	if (where < PCI_CFG_SPACE_EXP_SIZE && priv->cfg1_base)
-		return cfg1_map(priv, busnum, devfn, where);
+		return cfg1_map(priv, bus, devfn, where);
 
 	return NULL;
 }
 
+#ifdef CONFIG_OF
+
 static int loongson_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	int irq;
@@ -159,20 +225,42 @@
 	return val;
 }
 
-/* H/w only accept 32-bit PCI operations */
+/* LS2K/LS7A accept 8/16/32-bit PCI config operations */
 static struct pci_ops loongson_pci_ops = {
 	.map_bus = pci_loongson_map_bus,
+	.read	= pci_generic_config_read,
+	.write	= pci_generic_config_write,
+};
+
+/* RS780/SR5690 only accept 32-bit PCI config operations */
+static struct pci_ops loongson_pci_ops32 = {
+	.map_bus = pci_loongson_map_bus,
 	.read	= pci_generic_config_read32,
 	.write	= pci_generic_config_write32,
 };
 
+static const struct loongson_pci_data ls2k_pci_data = {
+	.flags = FLAG_CFG1 | FLAG_DEV_FIX | FLAG_DEV_HIDDEN,
+	.ops = &loongson_pci_ops,
+};
+
+static const struct loongson_pci_data ls7a_pci_data = {
+	.flags = FLAG_CFG1 | FLAG_DEV_FIX | FLAG_DEV_HIDDEN,
+	.ops = &loongson_pci_ops,
+};
+
+static const struct loongson_pci_data rs780e_pci_data = {
+	.flags = FLAG_CFG0,
+	.ops = &loongson_pci_ops32,
+};
+
 static const struct of_device_id loongson_pci_of_match[] = {
 	{ .compatible = "loongson,ls2k-pci",
-		.data = (void *)(FLAG_CFG0 | FLAG_CFG1 | FLAG_DEV_FIX), },
+		.data = &ls2k_pci_data, },
 	{ .compatible = "loongson,ls7a-pci",
-		.data = (void *)(FLAG_CFG0 | FLAG_CFG1 | FLAG_DEV_FIX), },
+		.data = &ls7a_pci_data, },
 	{ .compatible = "loongson,rs780e-pci",
-		.data = (void *)(FLAG_CFG0), },
+		.data = &rs780e_pci_data, },
 	{}
 };
 
@@ -193,20 +281,20 @@
 
 	priv = pci_host_bridge_priv(bridge);
 	priv->pdev = pdev;
-	priv->flags = (unsigned long)of_device_get_match_data(dev);
+	priv->data = of_device_get_match_data(dev);
 
-	regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	if (!regs) {
-		dev_err(dev, "missing mem resources for cfg0\n");
-		return -EINVAL;
+	if (priv->data->flags & FLAG_CFG0) {
+		regs = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+		if (!regs)
+			dev_err(dev, "missing mem resources for cfg0\n");
+		else {
+			priv->cfg0_base = devm_pci_remap_cfg_resource(dev, regs);
+			if (IS_ERR(priv->cfg0_base))
+				return PTR_ERR(priv->cfg0_base);
+		}
 	}
 
-	priv->cfg0_base = devm_pci_remap_cfg_resource(dev, regs);
-	if (IS_ERR(priv->cfg0_base))
-		return PTR_ERR(priv->cfg0_base);
-
-	/* CFG1 is optional */
-	if (priv->flags & FLAG_CFG1) {
+	if (priv->data->flags & FLAG_CFG1) {
 		regs = platform_get_resource(pdev, IORESOURCE_MEM, 1);
 		if (!regs)
 			dev_info(dev, "missing mem resource for cfg1\n");
@@ -218,7 +306,7 @@
 	}
 
 	bridge->sysdata = priv;
-	bridge->ops = &loongson_pci_ops;
+	bridge->ops = priv->data->ops;
 	bridge->map_irq = loongson_map_irq;
 
 	return pci_host_probe(bridge);
@@ -232,3 +320,41 @@
 	.probe = loongson_pci_probe,
 };
 builtin_platform_driver(loongson_pci_driver);
+
+#endif
+
+#ifdef CONFIG_ACPI
+
+static int loongson_pci_ecam_init(struct pci_config_window *cfg)
+{
+	struct device *dev = cfg->parent;
+	struct loongson_pci *priv;
+	struct loongson_pci_data *data;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	data = devm_kzalloc(dev, sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	cfg->priv = priv;
+	data->flags = FLAG_CFG1 | FLAG_DEV_HIDDEN;
+	priv->data = data;
+	priv->cfg1_base = cfg->win - (cfg->busr.start << 16);
+
+	return 0;
+}
+
+const struct pci_ecam_ops loongson_pci_ecam_ops = {
+	.bus_shift = 16,
+	.init	   = loongson_pci_ecam_init,
+	.pci_ops   = {
+		.map_bus = pci_loongson_map_bus,
+		.read	 = pci_generic_config_read,
+		.write	 = pci_generic_config_write,
+	}
+};
+
+#endif
diff --git a/drivers/pci/controller/pci-rcar-gen2.c b/drivers/pci/controller/pci-rcar-gen2.c
index 35804ea..8396957 100644
--- a/drivers/pci/controller/pci-rcar-gen2.c
+++ b/drivers/pci/controller/pci-rcar-gen2.c
@@ -328,6 +328,7 @@
 	{ .compatible = "renesas,pci-r8a7791", },
 	{ .compatible = "renesas,pci-r8a7794", },
 	{ .compatible = "renesas,pci-rcar-gen2", },
+	{ .compatible = "renesas,pci-rzn1", },
 	{ },
 };
 
diff --git a/drivers/pci/controller/pcie-brcmstb.c b/drivers/pci/controller/pcie-brcmstb.c
index e61058e..521acd6 100644
--- a/drivers/pci/controller/pcie-brcmstb.c
+++ b/drivers/pci/controller/pcie-brcmstb.c
@@ -24,6 +24,7 @@
 #include <linux/pci.h>
 #include <linux/pci-ecam.h>
 #include <linux/printk.h>
+#include <linux/regulator/consumer.h>
 #include <linux/reset.h>
 #include <linux/sizes.h>
 #include <linux/slab.h>
@@ -190,11 +191,6 @@
 
 /* Forward declarations */
 struct brcm_pcie;
-static inline void brcm_pcie_bridge_sw_init_set_7278(struct brcm_pcie *pcie, u32 val);
-static inline void brcm_pcie_bridge_sw_init_set_generic(struct brcm_pcie *pcie, u32 val);
-static inline void brcm_pcie_perst_set_4908(struct brcm_pcie *pcie, u32 val);
-static inline void brcm_pcie_perst_set_7278(struct brcm_pcie *pcie, u32 val);
-static inline void brcm_pcie_perst_set_generic(struct brcm_pcie *pcie, u32 val);
 
 enum {
 	RGR1_SW_INIT_1,
@@ -223,64 +219,9 @@
 	void (*bridge_sw_init_set)(struct brcm_pcie *pcie, u32 val);
 };
 
-static const int pcie_offsets[] = {
-	[RGR1_SW_INIT_1] = 0x9210,
-	[EXT_CFG_INDEX]  = 0x9000,
-	[EXT_CFG_DATA]   = 0x9004,
-};
-
-static const int pcie_offsets_bmips_7425[] = {
-	[RGR1_SW_INIT_1] = 0x8010,
-	[EXT_CFG_INDEX]  = 0x8300,
-	[EXT_CFG_DATA]   = 0x8304,
-};
-
-static const struct pcie_cfg_data generic_cfg = {
-	.offsets	= pcie_offsets,
-	.type		= GENERIC,
-	.perst_set	= brcm_pcie_perst_set_generic,
-	.bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic,
-};
-
-static const struct pcie_cfg_data bcm7425_cfg = {
-	.offsets	= pcie_offsets_bmips_7425,
-	.type		= BCM7425,
-	.perst_set	= brcm_pcie_perst_set_generic,
-	.bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic,
-};
-
-static const struct pcie_cfg_data bcm7435_cfg = {
-	.offsets	= pcie_offsets,
-	.type		= BCM7435,
-	.perst_set	= brcm_pcie_perst_set_generic,
-	.bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic,
-};
-
-static const struct pcie_cfg_data bcm4908_cfg = {
-	.offsets	= pcie_offsets,
-	.type		= BCM4908,
-	.perst_set	= brcm_pcie_perst_set_4908,
-	.bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic,
-};
-
-static const int pcie_offset_bcm7278[] = {
-	[RGR1_SW_INIT_1] = 0xc010,
-	[EXT_CFG_INDEX] = 0x9000,
-	[EXT_CFG_DATA] = 0x9004,
-};
-
-static const struct pcie_cfg_data bcm7278_cfg = {
-	.offsets	= pcie_offset_bcm7278,
-	.type		= BCM7278,
-	.perst_set	= brcm_pcie_perst_set_7278,
-	.bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_7278,
-};
-
-static const struct pcie_cfg_data bcm2711_cfg = {
-	.offsets	= pcie_offsets,
-	.type		= BCM2711,
-	.perst_set	= brcm_pcie_perst_set_generic,
-	.bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic,
+struct subdev_regulators {
+	unsigned int num_supplies;
+	struct regulator_bulk_data supplies[];
 };
 
 struct brcm_msi {
@@ -320,6 +261,8 @@
 	u32			hw_rev;
 	void			(*perst_set)(struct brcm_pcie *pcie, u32 val);
 	void			(*bridge_sw_init_set)(struct brcm_pcie *pcie, u32 val);
+	struct subdev_regulators *sr;
+	bool			ep_wakeup_capable;
 };
 
 static inline bool is_bmips(const struct brcm_pcie *pcie)
@@ -741,52 +684,48 @@
 	return dla && plu;
 }
 
-static void __iomem *brcm_pcie_map_conf(struct pci_bus *bus, unsigned int devfn,
-					int where)
+static void __iomem *brcm_pcie_map_bus(struct pci_bus *bus,
+				       unsigned int devfn, int where)
 {
 	struct brcm_pcie *pcie = bus->sysdata;
 	void __iomem *base = pcie->base;
 	int idx;
 
-	/* Accesses to the RC go right to the RC registers if slot==0 */
+	/* Accesses to the RC go right to the RC registers if !devfn */
 	if (pci_is_root_bus(bus))
-		return PCI_SLOT(devfn) ? NULL : base + where;
+		return devfn ? NULL : base + PCIE_ECAM_REG(where);
+
+	/* An access to our HW w/o link-up will cause a CPU Abort */
+	if (!brcm_pcie_link_up(pcie))
+		return NULL;
 
 	/* For devices, write to the config space index register */
 	idx = PCIE_ECAM_OFFSET(bus->number, devfn, 0);
 	writel(idx, pcie->base + PCIE_EXT_CFG_INDEX);
-	return base + PCIE_EXT_CFG_DATA + where;
+	return base + PCIE_EXT_CFG_DATA + PCIE_ECAM_REG(where);
 }
 
-static void __iomem *brcm_pcie_map_conf32(struct pci_bus *bus, unsigned int devfn,
-					 int where)
+static void __iomem *brcm7425_pcie_map_bus(struct pci_bus *bus,
+					   unsigned int devfn, int where)
 {
 	struct brcm_pcie *pcie = bus->sysdata;
 	void __iomem *base = pcie->base;
 	int idx;
 
-	/* Accesses to the RC go right to the RC registers if slot==0 */
+	/* Accesses to the RC go right to the RC registers if !devfn */
 	if (pci_is_root_bus(bus))
-		return PCI_SLOT(devfn) ? NULL : base + (where & ~0x3);
+		return devfn ? NULL : base + PCIE_ECAM_REG(where);
+
+	/* An access to our HW w/o link-up will cause a CPU Abort */
+	if (!brcm_pcie_link_up(pcie))
+		return NULL;
 
 	/* For devices, write to the config space index register */
-	idx = PCIE_ECAM_OFFSET(bus->number, devfn, (where & ~3));
+	idx = PCIE_ECAM_OFFSET(bus->number, devfn, where);
 	writel(idx, base + IDX_ADDR(pcie));
 	return base + DATA_ADDR(pcie);
 }
 
-static struct pci_ops brcm_pcie_ops = {
-	.map_bus = brcm_pcie_map_conf,
-	.read = pci_generic_config_read,
-	.write = pci_generic_config_write,
-};
-
-static struct pci_ops brcm_pcie_ops32 = {
-	.map_bus = brcm_pcie_map_conf32,
-	.read = pci_generic_config_read32,
-	.write = pci_generic_config_write32,
-};
-
 static inline void brcm_pcie_bridge_sw_init_set_generic(struct brcm_pcie *pcie, u32 val)
 {
 	u32 tmp, mask =  RGR1_SW_INIT_1_INIT_GENERIC_MASK;
@@ -926,17 +865,13 @@
 
 static int brcm_pcie_setup(struct brcm_pcie *pcie)
 {
-	struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie);
 	u64 rc_bar2_offset, rc_bar2_size;
 	void __iomem *base = pcie->base;
-	struct device *dev = pcie->dev;
+	struct pci_host_bridge *bridge;
 	struct resource_entry *entry;
-	bool ssc_good = false;
-	struct resource *res;
-	int num_out_wins = 0;
-	u16 nlw, cls, lnksta;
-	int i, ret, memc;
 	u32 tmp, burst, aspm_support;
+	int num_out_wins = 0;
+	int ret, memc;
 
 	/* Reset the bridge */
 	pcie->bridge_sw_init_set(pcie, 1);
@@ -1012,6 +947,11 @@
 	else
 		pcie->msi_target_addr = BRCM_MSI_TARGET_ADDR_GT_4GB;
 
+	if (!brcm_pcie_rc_mode(pcie)) {
+		dev_err(pcie->dev, "PCIe RC controller misconfigured as Endpoint\n");
+		return -EINVAL;
+	}
+
 	/* disable the PCIe->GISB memory window (RC_BAR1) */
 	tmp = readl(base + PCIE_MISC_RC_BAR1_CONFIG_LO);
 	tmp &= ~PCIE_MISC_RC_BAR1_CONFIG_LO_SIZE_MASK;
@@ -1022,31 +962,27 @@
 	tmp &= ~PCIE_MISC_RC_BAR3_CONFIG_LO_SIZE_MASK;
 	writel(tmp, base + PCIE_MISC_RC_BAR3_CONFIG_LO);
 
-	if (pcie->gen)
-		brcm_pcie_set_gen(pcie, pcie->gen);
-
-	/* Unassert the fundamental reset */
-	pcie->perst_set(pcie, 0);
+	/* Don't advertise L0s capability if 'aspm-no-l0s' */
+	aspm_support = PCIE_LINK_STATE_L1;
+	if (!of_property_read_bool(pcie->np, "aspm-no-l0s"))
+		aspm_support |= PCIE_LINK_STATE_L0S;
+	tmp = readl(base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY);
+	u32p_replace_bits(&tmp, aspm_support,
+		PCIE_RC_CFG_PRIV1_LINK_CAPABILITY_ASPM_SUPPORT_MASK);
+	writel(tmp, base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY);
 
 	/*
-	 * Give the RC/EP time to wake up, before trying to configure RC.
-	 * Intermittently check status for link-up, up to a total of 100ms.
+	 * For config space accesses on the RC, show the right class for
+	 * a PCIe-PCIe bridge (the default setting is to be EP mode).
 	 */
-	for (i = 0; i < 100 && !brcm_pcie_link_up(pcie); i += 5)
-		msleep(5);
+	tmp = readl(base + PCIE_RC_CFG_PRIV1_ID_VAL3);
+	u32p_replace_bits(&tmp, 0x060400,
+			  PCIE_RC_CFG_PRIV1_ID_VAL3_CLASS_CODE_MASK);
+	writel(tmp, base + PCIE_RC_CFG_PRIV1_ID_VAL3);
 
-	if (!brcm_pcie_link_up(pcie)) {
-		dev_err(dev, "link down\n");
-		return -ENODEV;
-	}
-
-	if (!brcm_pcie_rc_mode(pcie)) {
-		dev_err(dev, "PCIe misconfigured; is in EP mode\n");
-		return -EINVAL;
-	}
-
+	bridge = pci_host_bridge_from_priv(pcie);
 	resource_list_for_each_entry(entry, &bridge->windows) {
-		res = entry->res;
+		struct resource *res = entry->res;
 
 		if (resource_type(res) != IORESOURCE_MEM)
 			continue;
@@ -1075,23 +1011,41 @@
 		num_out_wins++;
 	}
 
-	/* Don't advertise L0s capability if 'aspm-no-l0s' */
-	aspm_support = PCIE_LINK_STATE_L1;
-	if (!of_property_read_bool(pcie->np, "aspm-no-l0s"))
-		aspm_support |= PCIE_LINK_STATE_L0S;
-	tmp = readl(base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY);
-	u32p_replace_bits(&tmp, aspm_support,
-		PCIE_RC_CFG_PRIV1_LINK_CAPABILITY_ASPM_SUPPORT_MASK);
-	writel(tmp, base + PCIE_RC_CFG_PRIV1_LINK_CAPABILITY);
+	/* PCIe->SCB endian mode for BAR */
+	tmp = readl(base + PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1);
+	u32p_replace_bits(&tmp, PCIE_RC_CFG_VENDOR_SPCIFIC_REG1_LITTLE_ENDIAN,
+		PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1_ENDIAN_MODE_BAR2_MASK);
+	writel(tmp, base + PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1);
+
+	return 0;
+}
+
+static int brcm_pcie_start_link(struct brcm_pcie *pcie)
+{
+	struct device *dev = pcie->dev;
+	void __iomem *base = pcie->base;
+	u16 nlw, cls, lnksta;
+	bool ssc_good = false;
+	u32 tmp;
+	int ret, i;
+
+	/* Unassert the fundamental reset */
+	pcie->perst_set(pcie, 0);
 
 	/*
-	 * For config space accesses on the RC, show the right class for
-	 * a PCIe-PCIe bridge (the default setting is to be EP mode).
+	 * Give the RC/EP time to wake up, before trying to configure RC.
+	 * Intermittently check status for link-up, up to a total of 100ms.
 	 */
-	tmp = readl(base + PCIE_RC_CFG_PRIV1_ID_VAL3);
-	u32p_replace_bits(&tmp, 0x060400,
-			  PCIE_RC_CFG_PRIV1_ID_VAL3_CLASS_CODE_MASK);
-	writel(tmp, base + PCIE_RC_CFG_PRIV1_ID_VAL3);
+	for (i = 0; i < 100 && !brcm_pcie_link_up(pcie); i += 5)
+		msleep(5);
+
+	if (!brcm_pcie_link_up(pcie)) {
+		dev_err(dev, "link down\n");
+		return -ENODEV;
+	}
+
+	if (pcie->gen)
+		brcm_pcie_set_gen(pcie, pcie->gen);
 
 	if (pcie->ssc) {
 		ret = brcm_pcie_set_ssc(pcie);
@@ -1108,12 +1062,6 @@
 		 pci_speed_string(pcie_link_speed[cls]), nlw,
 		 ssc_good ? "(SSC)" : "(!SSC)");
 
-	/* PCIe->SCB endian mode for BAR */
-	tmp = readl(base + PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1);
-	u32p_replace_bits(&tmp, PCIE_RC_CFG_VENDOR_SPCIFIC_REG1_LITTLE_ENDIAN,
-		PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1_ENDIAN_MODE_BAR2_MASK);
-	writel(tmp, base + PCIE_RC_CFG_VENDOR_VENDOR_SPECIFIC_REG1);
-
 	/*
 	 * Refclk from RC should be gated with CLKREQ# input when ASPM L0s,L1
 	 * is enabled => setting the CLKREQ_DEBUG_ENABLE field to 1.
@@ -1125,6 +1073,82 @@
 	return 0;
 }
 
+static const char * const supplies[] = {
+	"vpcie3v3",
+	"vpcie3v3aux",
+	"vpcie12v",
+};
+
+static void *alloc_subdev_regulators(struct device *dev)
+{
+	const size_t size = sizeof(struct subdev_regulators) +
+		sizeof(struct regulator_bulk_data) * ARRAY_SIZE(supplies);
+	struct subdev_regulators *sr;
+	int i;
+
+	sr = devm_kzalloc(dev, size, GFP_KERNEL);
+	if (sr) {
+		sr->num_supplies = ARRAY_SIZE(supplies);
+		for (i = 0; i < ARRAY_SIZE(supplies); i++)
+			sr->supplies[i].supply = supplies[i];
+	}
+
+	return sr;
+}
+
+static int brcm_pcie_add_bus(struct pci_bus *bus)
+{
+	struct brcm_pcie *pcie = bus->sysdata;
+	struct device *dev = &bus->dev;
+	struct subdev_regulators *sr;
+	int ret;
+
+	if (!bus->parent || !pci_is_root_bus(bus->parent))
+		return 0;
+
+	if (dev->of_node) {
+		sr = alloc_subdev_regulators(dev);
+		if (!sr) {
+			dev_info(dev, "Can't allocate regulators for downstream device\n");
+			goto no_regulators;
+		}
+
+		pcie->sr = sr;
+
+		ret = regulator_bulk_get(dev, sr->num_supplies, sr->supplies);
+		if (ret) {
+			dev_info(dev, "No regulators for downstream device\n");
+			goto no_regulators;
+		}
+
+		ret = regulator_bulk_enable(sr->num_supplies, sr->supplies);
+		if (ret) {
+			dev_err(dev, "Can't enable regulators for downstream device\n");
+			regulator_bulk_free(sr->num_supplies, sr->supplies);
+			pcie->sr = NULL;
+		}
+	}
+
+no_regulators:
+	brcm_pcie_start_link(pcie);
+	return 0;
+}
+
+static void brcm_pcie_remove_bus(struct pci_bus *bus)
+{
+	struct brcm_pcie *pcie = bus->sysdata;
+	struct subdev_regulators *sr = pcie->sr;
+	struct device *dev = &bus->dev;
+
+	if (!sr)
+		return;
+
+	if (regulator_bulk_disable(sr->num_supplies, sr->supplies))
+		dev_err(dev, "Failed to disable regulators for downstream device\n");
+	regulator_bulk_free(sr->num_supplies, sr->supplies);
+	pcie->sr = NULL;
+}
+
 /* L23 is a low-power PCIe link state */
 static void brcm_pcie_enter_l23(struct brcm_pcie *pcie)
 {
@@ -1221,9 +1245,21 @@
 	pcie->bridge_sw_init_set(pcie, 1);
 }
 
-static int brcm_pcie_suspend(struct device *dev)
+static int pci_dev_may_wakeup(struct pci_dev *dev, void *data)
+{
+	bool *ret = data;
+
+	if (device_may_wakeup(&dev->dev)) {
+		*ret = true;
+		dev_info(&dev->dev, "Possible wake-up device; regulators will not be disabled\n");
+	}
+	return (int) *ret;
+}
+
+static int brcm_pcie_suspend_noirq(struct device *dev)
 {
 	struct brcm_pcie *pcie = dev_get_drvdata(dev);
+	struct pci_host_bridge *bridge = pci_host_bridge_from_priv(pcie);
 	int ret;
 
 	brcm_pcie_turn_off(pcie);
@@ -1241,12 +1277,31 @@
 		return ret;
 	}
 
+	if (pcie->sr) {
+		/*
+		 * Now turn off the regulators, but if at least one
+		 * downstream device is enabled as a wake-up source, do not
+		 * turn off regulators.
+		 */
+		pcie->ep_wakeup_capable = false;
+		pci_walk_bus(bridge->bus, pci_dev_may_wakeup,
+			     &pcie->ep_wakeup_capable);
+		if (!pcie->ep_wakeup_capable) {
+			ret = regulator_bulk_disable(pcie->sr->num_supplies,
+						     pcie->sr->supplies);
+			if (ret) {
+				dev_err(dev, "Could not turn off regulators\n");
+				reset_control_reset(pcie->rescal);
+				return ret;
+			}
+		}
+	}
 	clk_disable_unprepare(pcie->clk);
 
 	return 0;
 }
 
-static int brcm_pcie_resume(struct device *dev)
+static int brcm_pcie_resume_noirq(struct device *dev)
 {
 	struct brcm_pcie *pcie = dev_get_drvdata(dev);
 	void __iomem *base;
@@ -1281,11 +1336,37 @@
 	if (ret)
 		goto err_reset;
 
+	if (pcie->sr) {
+		if (pcie->ep_wakeup_capable) {
+			/*
+			 * We are resuming from a suspend.  In the suspend we
+			 * did not disable the power supplies, so there is
+			 * no need to enable them (and falsely increase their
+			 * usage count).
+			 */
+			pcie->ep_wakeup_capable = false;
+		} else {
+			ret = regulator_bulk_enable(pcie->sr->num_supplies,
+						    pcie->sr->supplies);
+			if (ret) {
+				dev_err(dev, "Could not turn on regulators\n");
+				goto err_reset;
+			}
+		}
+	}
+
+	ret = brcm_pcie_start_link(pcie);
+	if (ret)
+		goto err_regulator;
+
 	if (pcie->msi)
 		brcm_msi_set_regs(pcie->msi);
 
 	return 0;
 
+err_regulator:
+	if (pcie->sr)
+		regulator_bulk_disable(pcie->sr->num_supplies, pcie->sr->supplies);
 err_reset:
 	reset_control_rearm(pcie->rescal);
 err_disable_clk:
@@ -1316,6 +1397,66 @@
 	return 0;
 }
 
+static const int pcie_offsets[] = {
+	[RGR1_SW_INIT_1] = 0x9210,
+	[EXT_CFG_INDEX]  = 0x9000,
+	[EXT_CFG_DATA]   = 0x9004,
+};
+
+static const int pcie_offsets_bmips_7425[] = {
+	[RGR1_SW_INIT_1] = 0x8010,
+	[EXT_CFG_INDEX]  = 0x8300,
+	[EXT_CFG_DATA]   = 0x8304,
+};
+
+static const struct pcie_cfg_data generic_cfg = {
+	.offsets	= pcie_offsets,
+	.type		= GENERIC,
+	.perst_set	= brcm_pcie_perst_set_generic,
+	.bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic,
+};
+
+static const struct pcie_cfg_data bcm7425_cfg = {
+	.offsets	= pcie_offsets_bmips_7425,
+	.type		= BCM7425,
+	.perst_set	= brcm_pcie_perst_set_generic,
+	.bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic,
+};
+
+static const struct pcie_cfg_data bcm7435_cfg = {
+	.offsets	= pcie_offsets,
+	.type		= BCM7435,
+	.perst_set	= brcm_pcie_perst_set_generic,
+	.bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic,
+};
+
+static const struct pcie_cfg_data bcm4908_cfg = {
+	.offsets	= pcie_offsets,
+	.type		= BCM4908,
+	.perst_set	= brcm_pcie_perst_set_4908,
+	.bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic,
+};
+
+static const int pcie_offset_bcm7278[] = {
+	[RGR1_SW_INIT_1] = 0xc010,
+	[EXT_CFG_INDEX] = 0x9000,
+	[EXT_CFG_DATA] = 0x9004,
+};
+
+static const struct pcie_cfg_data bcm7278_cfg = {
+	.offsets	= pcie_offset_bcm7278,
+	.type		= BCM7278,
+	.perst_set	= brcm_pcie_perst_set_7278,
+	.bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_7278,
+};
+
+static const struct pcie_cfg_data bcm2711_cfg = {
+	.offsets	= pcie_offsets,
+	.type		= BCM2711,
+	.perst_set	= brcm_pcie_perst_set_generic,
+	.bridge_sw_init_set = brcm_pcie_bridge_sw_init_set_generic,
+};
+
 static const struct of_device_id brcm_pcie_match[] = {
 	{ .compatible = "brcm,bcm2711-pcie", .data = &bcm2711_cfg },
 	{ .compatible = "brcm,bcm4908-pcie", .data = &bcm4908_cfg },
@@ -1328,6 +1469,22 @@
 	{},
 };
 
+static struct pci_ops brcm_pcie_ops = {
+	.map_bus = brcm_pcie_map_bus,
+	.read = pci_generic_config_read,
+	.write = pci_generic_config_write,
+	.add_bus = brcm_pcie_add_bus,
+	.remove_bus = brcm_pcie_remove_bus,
+};
+
+static struct pci_ops brcm7425_pcie_ops = {
+	.map_bus = brcm7425_pcie_map_bus,
+	.read = pci_generic_config_read32,
+	.write = pci_generic_config_write32,
+	.add_bus = brcm_pcie_add_bus,
+	.remove_bus = brcm_pcie_remove_bus,
+};
+
 static int brcm_pcie_probe(struct platform_device *pdev)
 {
 	struct device_node *np = pdev->dev.of_node, *msi_np;
@@ -1414,12 +1571,22 @@
 		}
 	}
 
-	bridge->ops = pcie->type == BCM7425 ? &brcm_pcie_ops32 : &brcm_pcie_ops;
+	bridge->ops = pcie->type == BCM7425 ? &brcm7425_pcie_ops : &brcm_pcie_ops;
 	bridge->sysdata = pcie;
 
 	platform_set_drvdata(pdev, pcie);
 
-	return pci_host_probe(bridge);
+	ret = pci_host_probe(bridge);
+	if (!ret && !brcm_pcie_link_up(pcie))
+		ret = -ENODEV;
+
+	if (ret) {
+		brcm_pcie_remove(pdev);
+		return ret;
+	}
+
+	return 0;
+
 fail:
 	__brcm_pcie_remove(pcie);
 	return ret;
@@ -1428,8 +1595,8 @@
 MODULE_DEVICE_TABLE(of, brcm_pcie_match);
 
 static const struct dev_pm_ops brcm_pcie_pm_ops = {
-	.suspend = brcm_pcie_suspend,
-	.resume = brcm_pcie_resume,
+	.suspend_noirq = brcm_pcie_suspend_noirq,
+	.resume_noirq = brcm_pcie_resume_noirq,
 };
 
 static struct platform_driver brcm_pcie_driver = {
diff --git a/drivers/pci/controller/pcie-iproc-msi.c b/drivers/pci/controller/pcie-iproc-msi.c
index 757b7fb..fee036b 100644
--- a/drivers/pci/controller/pcie-iproc-msi.c
+++ b/drivers/pci/controller/pcie-iproc-msi.c
@@ -589,8 +589,8 @@
 		msi->has_inten_reg = true;
 
 	msi->nr_msi_vecs = msi->nr_irqs * EQ_LEN;
-	msi->bitmap = devm_kcalloc(pcie->dev, BITS_TO_LONGS(msi->nr_msi_vecs),
-				   sizeof(*msi->bitmap), GFP_KERNEL);
+	msi->bitmap = devm_bitmap_zalloc(pcie->dev, msi->nr_msi_vecs,
+					 GFP_KERNEL);
 	if (!msi->bitmap)
 		return -ENOMEM;
 
diff --git a/drivers/pci/controller/pcie-mediatek-gen3.c b/drivers/pci/controller/pcie-mediatek-gen3.c
index 5d9fd36..6577c71 100644
--- a/drivers/pci/controller/pcie-mediatek-gen3.c
+++ b/drivers/pci/controller/pcie-mediatek-gen3.c
@@ -153,6 +153,37 @@
 	DECLARE_BITMAP(msi_irq_in_use, PCIE_MSI_IRQS_NUM);
 };
 
+/* LTSSM state in PCIE_LTSSM_STATUS_REG bit[28:24] */
+static const char *const ltssm_str[] = {
+	"detect.quiet",			/* 0x00 */
+	"detect.active",		/* 0x01 */
+	"polling.active",		/* 0x02 */
+	"polling.compliance",		/* 0x03 */
+	"polling.configuration",	/* 0x04 */
+	"config.linkwidthstart",	/* 0x05 */
+	"config.linkwidthaccept",	/* 0x06 */
+	"config.lanenumwait",		/* 0x07 */
+	"config.lanenumaccept",		/* 0x08 */
+	"config.complete",		/* 0x09 */
+	"config.idle",			/* 0x0A */
+	"recovery.receiverlock",	/* 0x0B */
+	"recovery.equalization",	/* 0x0C */
+	"recovery.speed",		/* 0x0D */
+	"recovery.receiverconfig",	/* 0x0E */
+	"recovery.idle",		/* 0x0F */
+	"L0",				/* 0x10 */
+	"L0s",				/* 0x11 */
+	"L1.entry",			/* 0x12 */
+	"L1.idle",			/* 0x13 */
+	"L2.idle",			/* 0x14 */
+	"L2.transmitwake",		/* 0x15 */
+	"disable",			/* 0x16 */
+	"loopback.entry",		/* 0x17 */
+	"loopback.active",		/* 0x18 */
+	"loopback.exit",		/* 0x19 */
+	"hotreset",			/* 0x1A */
+};
+
 /**
  * mtk_pcie_config_tlp_header() - Configure a configuration TLP header
  * @bus: PCI bus to query
@@ -327,8 +358,16 @@
 				 !!(val & PCIE_PORT_LINKUP), 20,
 				 PCI_PM_D3COLD_WAIT * USEC_PER_MSEC);
 	if (err) {
+		const char *ltssm_state;
+		int ltssm_index;
+
 		val = readl_relaxed(pcie->base + PCIE_LTSSM_STATUS_REG);
-		dev_err(pcie->dev, "PCIe link down, ltssm reg val: %#x\n", val);
+		ltssm_index = PCIE_LTSSM_STATE(val);
+		ltssm_state = ltssm_index >= ARRAY_SIZE(ltssm_str) ?
+			      "Unknown state" : ltssm_str[ltssm_index];
+		dev_err(pcie->dev,
+			"PCIe link down, current LTSSM state: %s (%#x)\n",
+			ltssm_state, val);
 		return err;
 	}
 
@@ -600,7 +639,8 @@
 						  &intx_domain_ops, pcie);
 	if (!pcie->intx_domain) {
 		dev_err(dev, "failed to create INTx IRQ domain\n");
-		return -ENODEV;
+		ret = -ENODEV;
+		goto out_put_node;
 	}
 
 	/* Setup MSI */
@@ -623,13 +663,15 @@
 		goto err_msi_domain;
 	}
 
+	of_node_put(intc_node);
 	return 0;
 
 err_msi_domain:
 	irq_domain_remove(pcie->msi_bottom_domain);
 err_msi_bottom_domain:
 	irq_domain_remove(pcie->intx_domain);
-
+out_put_node:
+	of_node_put(intc_node);
 	return ret;
 }
 
diff --git a/drivers/pci/controller/pcie-microchip-host.c b/drivers/pci/controller/pcie-microchip-host.c
index dd5dba4..7263d17 100644
--- a/drivers/pci/controller/pcie-microchip-host.c
+++ b/drivers/pci/controller/pcie-microchip-host.c
@@ -904,6 +904,7 @@
 						   &event_domain_ops, port);
 	if (!port->event_domain) {
 		dev_err(dev, "failed to get event domain\n");
+		of_node_put(pcie_intc_node);
 		return -ENOMEM;
 	}
 
@@ -913,6 +914,7 @@
 						  &intx_domain_ops, port);
 	if (!port->intx_domain) {
 		dev_err(dev, "failed to get an INTx IRQ domain\n");
+		of_node_put(pcie_intc_node);
 		return -ENOMEM;
 	}
 
diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
index 5b833f0..36b1801 100644
--- a/drivers/pci/endpoint/functions/pci-epf-test.c
+++ b/drivers/pci/endpoint/functions/pci-epf-test.c
@@ -52,9 +52,11 @@
 	enum pci_barno		test_reg_bar;
 	size_t			msix_table_offset;
 	struct delayed_work	cmd_handler;
-	struct dma_chan		*dma_chan;
+	struct dma_chan		*dma_chan_tx;
+	struct dma_chan		*dma_chan_rx;
 	struct completion	transfer_complete;
 	bool			dma_supported;
+	bool			dma_private;
 	const struct pci_epc_features *epc_features;
 };
 
@@ -96,6 +98,8 @@
  * @dma_src: The source address of the data transfer. It can be a physical
  *	     address given by pci_epc_mem_alloc_addr or DMA mapping APIs.
  * @len: The size of the data transfer
+ * @dma_remote: remote RC physical address
+ * @dir: DMA transfer direction
  *
  * Function that uses dmaengine API to transfer data between PCIe EP and remote
  * PCIe RC. The source and destination address can be a physical address given
@@ -105,12 +109,16 @@
  */
 static int pci_epf_test_data_transfer(struct pci_epf_test *epf_test,
 				      dma_addr_t dma_dst, dma_addr_t dma_src,
-				      size_t len)
+				      size_t len, dma_addr_t dma_remote,
+				      enum dma_transfer_direction dir)
 {
+	struct dma_chan *chan = (dir == DMA_DEV_TO_MEM) ?
+				 epf_test->dma_chan_tx : epf_test->dma_chan_rx;
+	dma_addr_t dma_local = (dir == DMA_MEM_TO_DEV) ? dma_src : dma_dst;
 	enum dma_ctrl_flags flags = DMA_CTRL_ACK | DMA_PREP_INTERRUPT;
-	struct dma_chan *chan = epf_test->dma_chan;
 	struct pci_epf *epf = epf_test->epf;
 	struct dma_async_tx_descriptor *tx;
+	struct dma_slave_config sconf = {};
 	struct device *dev = &epf->dev;
 	dma_cookie_t cookie;
 	int ret;
@@ -120,7 +128,24 @@
 		return -EINVAL;
 	}
 
-	tx = dmaengine_prep_dma_memcpy(chan, dma_dst, dma_src, len, flags);
+	if (epf_test->dma_private) {
+		sconf.direction = dir;
+		if (dir == DMA_MEM_TO_DEV)
+			sconf.dst_addr = dma_remote;
+		else
+			sconf.src_addr = dma_remote;
+
+		if (dmaengine_slave_config(chan, &sconf)) {
+			dev_err(dev, "DMA slave config fail\n");
+			return -EIO;
+		}
+		tx = dmaengine_prep_slave_single(chan, dma_local, len, dir,
+						 flags);
+	} else {
+		tx = dmaengine_prep_dma_memcpy(chan, dma_dst, dma_src, len,
+					       flags);
+	}
+
 	if (!tx) {
 		dev_err(dev, "Failed to prepare DMA memcpy\n");
 		return -EIO;
@@ -148,6 +173,23 @@
 	return 0;
 }
 
+struct epf_dma_filter {
+	struct device *dev;
+	u32 dma_mask;
+};
+
+static bool epf_dma_filter_fn(struct dma_chan *chan, void *node)
+{
+	struct epf_dma_filter *filter = node;
+	struct dma_slave_caps caps;
+
+	memset(&caps, 0, sizeof(caps));
+	dma_get_slave_caps(chan, &caps);
+
+	return chan->device->dev == filter->dev
+		&& (filter->dma_mask & caps.directions);
+}
+
 /**
  * pci_epf_test_init_dma_chan() - Function to initialize EPF test DMA channel
  * @epf_test: the EPF test device that performs data transfer operation
@@ -158,10 +200,44 @@
 {
 	struct pci_epf *epf = epf_test->epf;
 	struct device *dev = &epf->dev;
+	struct epf_dma_filter filter;
 	struct dma_chan *dma_chan;
 	dma_cap_mask_t mask;
 	int ret;
 
+	filter.dev = epf->epc->dev.parent;
+	filter.dma_mask = BIT(DMA_DEV_TO_MEM);
+
+	dma_cap_zero(mask);
+	dma_cap_set(DMA_SLAVE, mask);
+	dma_chan = dma_request_channel(mask, epf_dma_filter_fn, &filter);
+	if (!dma_chan) {
+		dev_info(dev, "Failed to get private DMA rx channel. Falling back to generic one\n");
+		goto fail_back_tx;
+	}
+
+	epf_test->dma_chan_rx = dma_chan;
+
+	filter.dma_mask = BIT(DMA_MEM_TO_DEV);
+	dma_chan = dma_request_channel(mask, epf_dma_filter_fn, &filter);
+
+	if (!dma_chan) {
+		dev_info(dev, "Failed to get private DMA tx channel. Falling back to generic one\n");
+		goto fail_back_rx;
+	}
+
+	epf_test->dma_chan_tx = dma_chan;
+	epf_test->dma_private = true;
+
+	init_completion(&epf_test->transfer_complete);
+
+	return 0;
+
+fail_back_rx:
+	dma_release_channel(epf_test->dma_chan_rx);
+	epf_test->dma_chan_tx = NULL;
+
+fail_back_tx:
 	dma_cap_zero(mask);
 	dma_cap_set(DMA_MEMCPY, mask);
 
@@ -174,7 +250,7 @@
 	}
 	init_completion(&epf_test->transfer_complete);
 
-	epf_test->dma_chan = dma_chan;
+	epf_test->dma_chan_tx = epf_test->dma_chan_rx = dma_chan;
 
 	return 0;
 }
@@ -190,8 +266,17 @@
 	if (!epf_test->dma_supported)
 		return;
 
-	dma_release_channel(epf_test->dma_chan);
-	epf_test->dma_chan = NULL;
+	dma_release_channel(epf_test->dma_chan_tx);
+	if (epf_test->dma_chan_tx == epf_test->dma_chan_rx) {
+		epf_test->dma_chan_tx = NULL;
+		epf_test->dma_chan_rx = NULL;
+		return;
+	}
+
+	dma_release_channel(epf_test->dma_chan_rx);
+	epf_test->dma_chan_rx = NULL;
+
+	return;
 }
 
 static void pci_epf_test_print_rate(const char *ops, u64 size,
@@ -280,8 +365,15 @@
 			goto err_map_addr;
 		}
 
+		if (epf_test->dma_private) {
+			dev_err(dev, "Cannot transfer data using DMA\n");
+			ret = -EINVAL;
+			goto err_map_addr;
+		}
+
 		ret = pci_epf_test_data_transfer(epf_test, dst_phys_addr,
-						 src_phys_addr, reg->size);
+						 src_phys_addr, reg->size, 0,
+						 DMA_MEM_TO_MEM);
 		if (ret)
 			dev_err(dev, "Data transfer failed\n");
 	} else {
@@ -373,7 +465,8 @@
 
 		ktime_get_ts64(&start);
 		ret = pci_epf_test_data_transfer(epf_test, dst_phys_addr,
-						 phys_addr, reg->size);
+						 phys_addr, reg->size,
+						 reg->src_addr, DMA_DEV_TO_MEM);
 		if (ret)
 			dev_err(dev, "Data transfer failed\n");
 		ktime_get_ts64(&end);
@@ -463,8 +556,11 @@
 		}
 
 		ktime_get_ts64(&start);
+
 		ret = pci_epf_test_data_transfer(epf_test, phys_addr,
-						 src_phys_addr, reg->size);
+						 src_phys_addr, reg->size,
+						 reg->dst_addr,
+						 DMA_MEM_TO_DEV);
 		if (ret)
 			dev_err(dev, "Data transfer failed\n");
 		ktime_get_ts64(&end);
@@ -627,7 +723,6 @@
 
 	cancel_delayed_work(&epf_test->cmd_handler);
 	pci_epf_test_clean_dma_chan(epf_test);
-	pci_epc_stop(epc);
 	for (bar = 0; bar < PCI_STD_NUM_BARS; bar++) {
 		epf_bar = &epf->bar[bar];
 
diff --git a/drivers/pci/mmap.c b/drivers/pci/mmap.c
index b8c9011..4504039 100644
--- a/drivers/pci/mmap.c
+++ b/drivers/pci/mmap.c
@@ -13,27 +13,6 @@
 
 #ifdef ARCH_GENERIC_PCI_MMAP_RESOURCE
 
-/*
- * Modern setup: generic pci_mmap_resource_range(), and implement the legacy
- * pci_mmap_page_range() (if needed) as a wrapper round it.
- */
-
-#ifdef HAVE_PCI_MMAP
-int pci_mmap_page_range(struct pci_dev *pdev, int bar,
-			struct vm_area_struct *vma,
-			enum pci_mmap_state mmap_state, int write_combine)
-{
-	resource_size_t start, end;
-
-	pci_resource_to_user(pdev, bar, &pdev->resource[bar], &start, &end);
-
-	/* Adjust vm_pgoff to be the offset within the resource */
-	vma->vm_pgoff -= start >> PAGE_SHIFT;
-	return pci_mmap_resource_range(pdev, bar, vma, mmap_state,
-				       write_combine);
-}
-#endif
-
 static const struct vm_operations_struct pci_phys_vm_ops = {
 #ifdef CONFIG_HAVE_IOREMAP_PROT
 	.access = generic_access_phys,
@@ -70,27 +49,4 @@
 				  vma->vm_page_prot);
 }
 
-#elif defined(HAVE_PCI_MMAP) /* && !ARCH_GENERIC_PCI_MMAP_RESOURCE */
-
-/*
- * 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.
- */
-
-int pci_mmap_resource_range(struct pci_dev *pdev, int bar,
-			    struct vm_area_struct *vma,
-			    enum pci_mmap_state mmap_state, int write_combine)
-{
-	resource_size_t start, end;
-
-	/*
-	 * pci_mmap_page_range() expects the same kind of entry as coming
-	 * from /proc/bus/pci/ which is a "user visible" value. If this is
-	 * different from the resource itself, arch will do necessary fixup.
-	 */
-	pci_resource_to_user(pdev, bar, &pdev->resource[bar], &start, &end);
-	vma->vm_pgoff += start >> PAGE_SHIFT;
-	return pci_mmap_page_range(pdev, bar, vma, mmap_state, write_combine);
-}
 #endif
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index cfaf40a..093303c 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -1293,9 +1293,6 @@
 		pci_restore_bars(dev);
 	}
 
-	if (dev->bus->self)
-		pcie_aspm_pm_state_change(dev->bus->self);
-
 	return 0;
 }
 
@@ -1390,9 +1387,6 @@
 				     pci_power_name(dev->current_state),
 				     pci_power_name(state));
 
-	if (dev->bus->self)
-		pcie_aspm_pm_state_change(dev->bus->self);
-
 	return 0;
 }
 
diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
index e10cdec..785f310 100644
--- a/drivers/pci/pci.h
+++ b/drivers/pci/pci.h
@@ -560,12 +560,10 @@
 #ifdef CONFIG_PCIEASPM
 void pcie_aspm_init_link_state(struct pci_dev *pdev);
 void pcie_aspm_exit_link_state(struct pci_dev *pdev);
-void pcie_aspm_pm_state_change(struct pci_dev *pdev);
 void pcie_aspm_powersave_config_link(struct pci_dev *pdev);
 #else
 static inline void pcie_aspm_init_link_state(struct pci_dev *pdev) { }
 static inline void pcie_aspm_exit_link_state(struct pci_dev *pdev) { }
-static inline void pcie_aspm_pm_state_change(struct pci_dev *pdev) { }
 static inline void pcie_aspm_powersave_config_link(struct pci_dev *pdev) { }
 #endif
 
diff --git a/drivers/pci/pcie/aer.c b/drivers/pci/pcie/aer.c
index 7952e5e..e2d8a74 100644
--- a/drivers/pci/pcie/aer.c
+++ b/drivers/pci/pcie/aer.c
@@ -392,6 +392,11 @@
 	pci_add_ext_cap_save_buffer(dev, PCI_EXT_CAP_ID_ERR, sizeof(u32) * n);
 
 	pci_aer_clear_status(dev);
+
+	if (pci_aer_available())
+		pci_enable_pcie_error_reporting(dev);
+
+	pcie_set_ecrc_checking(dev);
 }
 
 void pci_aer_exit(struct pci_dev *dev)
@@ -538,7 +543,7 @@
 	u64 *stats = pdev->aer_stats->stats_array;			\
 	size_t len = 0;							\
 									\
-	for (i = 0; i < ARRAY_SIZE(strings_array); i++) {		\
+	for (i = 0; i < ARRAY_SIZE(pdev->aer_stats->stats_array); i++) {\
 		if (strings_array[i])					\
 			len += sysfs_emit_at(buf, len, "%s %llu\n",	\
 					     strings_array[i],		\
@@ -1228,9 +1233,6 @@
 			pci_disable_pcie_error_reporting(dev);
 	}
 
-	if (enable)
-		pcie_set_ecrc_checking(dev);
-
 	return 0;
 }
 
@@ -1347,6 +1349,11 @@
 	struct device *device = &dev->device;
 	struct pci_dev *port = dev->port;
 
+	BUILD_BUG_ON(ARRAY_SIZE(aer_correctable_error_string) <
+		     AER_MAX_TYPEOF_COR_ERRS);
+	BUILD_BUG_ON(ARRAY_SIZE(aer_uncorrectable_error_string) <
+		     AER_MAX_TYPEOF_UNCOR_ERRS);
+
 	/* Limit to Root Ports or Root Complex Event Collectors */
 	if ((pci_pcie_type(port) != PCI_EXP_TYPE_RC_EC) &&
 	    (pci_pcie_type(port) != PCI_EXP_TYPE_ROOT_PORT))
diff --git a/drivers/pci/pcie/aspm.c b/drivers/pci/pcie/aspm.c
index a96b742..a8aec19 100644
--- a/drivers/pci/pcie/aspm.c
+++ b/drivers/pci/pcie/aspm.c
@@ -1012,25 +1012,6 @@
 	up_read(&pci_bus_sem);
 }
 
-/* @pdev: the root port or switch downstream port */
-void pcie_aspm_pm_state_change(struct pci_dev *pdev)
-{
-	struct pcie_link_state *link = pdev->link_state;
-
-	if (aspm_disabled || !link)
-		return;
-	/*
-	 * Devices changed PM state, we should recheck if latency
-	 * meets all functions' requirement
-	 */
-	down_read(&pci_bus_sem);
-	mutex_lock(&aspm_lock);
-	pcie_update_aspm_capable(link->root);
-	pcie_config_aspm_path(link);
-	mutex_unlock(&aspm_lock);
-	up_read(&pci_bus_sem);
-}
-
 void pcie_aspm_powersave_config_link(struct pci_dev *pdev)
 {
 	struct pcie_link_state *link = pdev->link_state;
@@ -1366,4 +1347,3 @@
 {
 	return aspm_support_enabled;
 }
-EXPORT_SYMBOL(pcie_aspm_support_enabled);
diff --git a/drivers/pci/pcie/err.c b/drivers/pci/pcie/err.c
index 0c5a143..59c90d0 100644
--- a/drivers/pci/pcie/err.c
+++ b/drivers/pci/pcie/err.c
@@ -55,10 +55,14 @@
 
 	device_lock(&dev->dev);
 	pdrv = dev->driver;
-	if (!pci_dev_set_io_state(dev, state) ||
-		!pdrv ||
-		!pdrv->err_handler ||
-		!pdrv->err_handler->error_detected) {
+	if (pci_dev_is_disconnected(dev)) {
+		vote = PCI_ERS_RESULT_DISCONNECT;
+	} else if (!pci_dev_set_io_state(dev, state)) {
+		pci_info(dev, "can't recover (state transition %u -> %u invalid)\n",
+			dev->error_state, state);
+		vote = PCI_ERS_RESULT_NONE;
+	} else if (!pdrv || !pdrv->err_handler ||
+		   !pdrv->err_handler->error_detected) {
 		/*
 		 * If any device in the subtree does not have an error_detected
 		 * callback, PCI_ERS_RESULT_NO_AER_DRIVER prevents subsequent
diff --git a/drivers/pci/pcie/portdrv_core.c b/drivers/pci/pcie/portdrv_core.c
index 604feeb..1ac7fec 100644
--- a/drivers/pci/pcie/portdrv_core.c
+++ b/drivers/pci/pcie/portdrv_core.c
@@ -222,15 +222,8 @@
 
 #ifdef CONFIG_PCIEAER
 	if (dev->aer_cap && pci_aer_available() &&
-	    (pcie_ports_native || host->native_aer)) {
+	    (pcie_ports_native || host->native_aer))
 		services |= PCIE_PORT_SERVICE_AER;
-
-		/*
-		 * Disable AER on this port in case it's been enabled by the
-		 * BIOS (the AER service driver will enable it when necessary).
-		 */
-		pci_disable_pcie_error_reporting(dev);
-	}
 #endif
 
 	/* Root Ports and Root Complex Event Collectors may generate PMEs */
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 17a9699..9884d8b 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1890,6 +1890,9 @@
 
 	dev->broken_intx_masking = pci_intx_mask_broken(dev);
 
+	/* Clear errors left from system firmware */
+	pci_write_config_word(dev, PCI_STATUS, 0xffff);
+
 	switch (dev->hdr_type) {		    /* header type */
 	case PCI_HEADER_TYPE_NORMAL:		    /* standard header */
 		if (class == PCI_CLASS_BRIDGE_PCI)
@@ -2579,33 +2582,39 @@
 }
 EXPORT_SYMBOL(pci_scan_single_device);
 
-static unsigned int next_fn(struct pci_bus *bus, struct pci_dev *dev,
-			    unsigned int fn)
+static int next_ari_fn(struct pci_bus *bus, struct pci_dev *dev, int fn)
 {
 	int pos;
 	u16 cap = 0;
 	unsigned int next_fn;
 
-	if (pci_ari_enabled(bus)) {
-		if (!dev)
-			return 0;
-		pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ARI);
-		if (!pos)
-			return 0;
+	if (!dev)
+		return -ENODEV;
 
-		pci_read_config_word(dev, pos + PCI_ARI_CAP, &cap);
-		next_fn = PCI_ARI_CAP_NFN(cap);
-		if (next_fn <= fn)
-			return 0;	/* protect against malformed list */
+	pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ARI);
+	if (!pos)
+		return -ENODEV;
 
-		return next_fn;
-	}
+	pci_read_config_word(dev, pos + PCI_ARI_CAP, &cap);
+	next_fn = PCI_ARI_CAP_NFN(cap);
+	if (next_fn <= fn)
+		return -ENODEV;	/* protect against malformed list */
 
-	/* dev may be NULL for non-contiguous multifunction devices */
-	if (!dev || dev->multifunction)
-		return (fn + 1) % 8;
+	return next_fn;
+}
 
-	return 0;
+static int next_fn(struct pci_bus *bus, struct pci_dev *dev, int fn)
+{
+	if (pci_ari_enabled(bus))
+		return next_ari_fn(bus, dev, fn);
+
+	if (fn >= 7)
+		return -ENODEV;
+	/* only multifunction devices may have more functions */
+	if (dev && !dev->multifunction)
+		return -ENODEV;
+
+	return fn + 1;
 }
 
 static int only_one_child(struct pci_bus *bus)
@@ -2643,26 +2652,30 @@
  */
 int pci_scan_slot(struct pci_bus *bus, int devfn)
 {
-	unsigned int fn, nr = 0;
 	struct pci_dev *dev;
+	int fn = 0, nr = 0;
 
 	if (only_one_child(bus) && (devfn > 0))
 		return 0; /* Already scanned the entire slot */
 
-	dev = pci_scan_single_device(bus, devfn);
-	if (!dev)
-		return 0;
-	if (!pci_dev_is_added(dev))
-		nr++;
-
-	for (fn = next_fn(bus, dev, 0); fn > 0; fn = next_fn(bus, dev, fn)) {
+	do {
 		dev = pci_scan_single_device(bus, devfn + fn);
 		if (dev) {
 			if (!pci_dev_is_added(dev))
 				nr++;
-			dev->multifunction = 1;
+			if (fn > 0)
+				dev->multifunction = 1;
+		} else if (fn == 0) {
+			/*
+			 * Function 0 is required unless we are running on
+			 * a hypervisor that passes through individual PCI
+			 * functions.
+			 */
+			if (!hypervisor_isolated_pci_functions())
+				break;
 		}
-	}
+		fn = next_fn(bus, dev, fn);
+	} while (fn >= 0);
 
 	/* Only one slot has PCIe device */
 	if (bus->self && nr)
@@ -2858,29 +2871,14 @@
 {
 	unsigned int used_buses, normal_bridges = 0, hotplug_bridges = 0;
 	unsigned int start = bus->busn_res.start;
-	unsigned int devfn, fn, cmax, max = start;
+	unsigned int devfn, cmax, max = start;
 	struct pci_dev *dev;
-	int nr_devs;
 
 	dev_dbg(&bus->dev, "scanning bus\n");
 
 	/* Go find them, Rover! */
-	for (devfn = 0; devfn < 256; devfn += 8) {
-		nr_devs = pci_scan_slot(bus, devfn);
-
-		/*
-		 * The Jailhouse hypervisor may pass individual functions of a
-		 * multi-function device to a guest without passing function 0.
-		 * Look for them as well.
-		 */
-		if (jailhouse_paravirt() && nr_devs == 0) {
-			for (fn = 1; fn < 8; fn++) {
-				dev = pci_scan_single_device(bus, devfn + fn);
-				if (dev)
-					dev->multifunction = 1;
-			}
-		}
-	}
+	for (devfn = 0; devfn < 256; devfn += 8)
+		pci_scan_slot(bus, devfn);
 
 	/* Reserve buses for SR-IOV capability */
 	used_buses = pci_iov_bus_range(bus);
diff --git a/drivers/pci/proc.c b/drivers/pci/proc.c
index 31b26d8..f967709 100644
--- a/drivers/pci/proc.c
+++ b/drivers/pci/proc.c
@@ -244,6 +244,7 @@
 {
 	struct pci_dev *dev = pde_data(file_inode(file));
 	struct pci_filp_private *fpriv = file->private_data;
+	resource_size_t start, end;
 	int i, ret, write_combine = 0, res_bit = IORESOURCE_MEM;
 
 	if (!capable(CAP_SYS_RAWIO) ||
@@ -278,7 +279,11 @@
 	    iomem_is_exclusive(dev->resource[i].start))
 		return -EINVAL;
 
-	ret = pci_mmap_page_range(dev, i, vma,
+	pci_resource_to_user(dev, i, &dev->resource[i], &start, &end);
+
+	/* Adjust vm_pgoff to be the offset within the resource */
+	vma->vm_pgoff -= start >> PAGE_SHIFT;
+	ret = pci_mmap_resource_range(dev, i, vma,
 				  fpriv->mmap_state, write_combine);
 	if (ret < 0)
 		return ret;
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index 41aeaa23..d35e631 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -2709,10 +2709,10 @@
 			nvenet_msi_disable);
 
 /*
- * PCIe spec r4.0 sec 7.7.1.2 and sec 7.7.2.2 say that if MSI/MSI-X is enabled,
- * then the device can't use INTx interrupts. Tegra's PCIe root ports don't
- * generate MSI interrupts for PME and AER events instead only INTx interrupts
- * are generated. Though Tegra's PCIe root ports can generate MSI interrupts
+ * PCIe spec r6.0 sec 6.1.4.3 says that if MSI/MSI-X is enabled, the device
+ * can't use INTx interrupts. Tegra's PCIe Root Ports don't generate MSI
+ * interrupts for PME and AER events; instead only INTx interrupts are
+ * generated. Though Tegra's PCIe Root Ports can generate MSI interrupts
  * for other events, since PCIe specification doesn't support using a mix of
  * INTx and MSI/MSI-X, it is required to disable MSI interrupts to avoid port
  * service drivers registering their respective ISRs for MSIs.
@@ -2760,6 +2760,15 @@
 DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_NVIDIA, 0x10e6,
 			      PCI_CLASS_BRIDGE_PCI, 8,
 			      pci_quirk_nvidia_tegra_disable_rp_msi);
+DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_NVIDIA, 0x229a,
+			      PCI_CLASS_BRIDGE_PCI, 8,
+			      pci_quirk_nvidia_tegra_disable_rp_msi);
+DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_NVIDIA, 0x229c,
+			      PCI_CLASS_BRIDGE_PCI, 8,
+			      pci_quirk_nvidia_tegra_disable_rp_msi);
+DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_NVIDIA, 0x229e,
+			      PCI_CLASS_BRIDGE_PCI, 8,
+			      pci_quirk_nvidia_tegra_disable_rp_msi);
 
 /*
  * Some versions of the MCP55 bridge from Nvidia have a legacy IRQ routing
@@ -4924,6 +4933,9 @@
 	{ PCI_VENDOR_ID_AMPERE, 0xE00C, pci_quirk_xgene_acs },
 	/* Broadcom multi-function device */
 	{ PCI_VENDOR_ID_BROADCOM, 0x16D7, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_BROADCOM, 0x1750, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_BROADCOM, 0x1751, pci_quirk_mf_endpoint_acs },
+	{ PCI_VENDOR_ID_BROADCOM, 0x1752, pci_quirk_mf_endpoint_acs },
 	{ PCI_VENDOR_ID_BROADCOM, 0xD714, pci_quirk_brcm_acs },
 	/* Amazon Annapurna Labs */
 	{ PCI_VENDOR_ID_AMAZON_ANNAPURNA_LABS, 0x0031, pci_quirk_al_acs },
diff --git a/drivers/pci/switch/switchtec.c b/drivers/pci/switch/switchtec.c
index c36c123..75be4fe 100644
--- a/drivers/pci/switch/switchtec.c
+++ b/drivers/pci/switch/switchtec.c
@@ -1376,8 +1376,7 @@
 	dev->groups = switchtec_device_groups;
 	dev->release = stdev_release;
 
-	minor = ida_simple_get(&switchtec_minor_ida, 0, 0,
-			       GFP_KERNEL);
+	minor = ida_alloc(&switchtec_minor_ida, GFP_KERNEL);
 	if (minor < 0) {
 		rc = minor;
 		goto err_put;
@@ -1692,7 +1691,7 @@
 err_devadd:
 	stdev_kill(stdev);
 err_put:
-	ida_simple_remove(&switchtec_minor_ida, MINOR(stdev->dev.devt));
+	ida_free(&switchtec_minor_ida, MINOR(stdev->dev.devt));
 	put_device(&stdev->dev);
 	return rc;
 }
@@ -1704,7 +1703,7 @@
 	pci_set_drvdata(pdev, NULL);
 
 	cdev_device_del(&stdev->cdev, &stdev->dev);
-	ida_simple_remove(&switchtec_minor_ida, MINOR(stdev->dev.devt));
+	ida_free(&switchtec_minor_ida, MINOR(stdev->dev.devt));
 	dev_info(&stdev->dev, "unregistered.\n");
 	stdev_kill(stdev);
 	put_device(&stdev->dev);
diff --git a/drivers/phy/samsung/phy-exynos-pcie.c b/drivers/phy/samsung/phy-exynos-pcie.c
index 578cfe0..53c9230 100644
--- a/drivers/phy/samsung/phy-exynos-pcie.c
+++ b/drivers/phy/samsung/phy-exynos-pcie.c
@@ -51,6 +51,13 @@
 {
 	struct exynos_pcie_phy *ep = phy_get_drvdata(phy);
 
+	regmap_update_bits(ep->pmureg, EXYNOS5433_PMU_PCIE_PHY_OFFSET,
+			   BIT(0), 1);
+	regmap_update_bits(ep->fsysreg, PCIE_EXYNOS5433_PHY_GLOBAL_RESET,
+			   PCIE_APP_REQ_EXIT_L1_MODE, 0);
+	regmap_update_bits(ep->fsysreg, PCIE_EXYNOS5433_PHY_L1SUB_CM_CON,
+			   PCIE_REFCLK_GATING_EN, 0);
+
 	regmap_update_bits(ep->fsysreg,	PCIE_EXYNOS5433_PHY_COMMON_RESET,
 			   PCIE_PHY_RESET, 1);
 	regmap_update_bits(ep->fsysreg, PCIE_EXYNOS5433_PHY_MAC_RESET,
@@ -109,20 +116,7 @@
 	return 0;
 }
 
-static int exynos5433_pcie_phy_power_on(struct phy *phy)
-{
-	struct exynos_pcie_phy *ep = phy_get_drvdata(phy);
-
-	regmap_update_bits(ep->pmureg, EXYNOS5433_PMU_PCIE_PHY_OFFSET,
-			   BIT(0), 1);
-	regmap_update_bits(ep->fsysreg, PCIE_EXYNOS5433_PHY_GLOBAL_RESET,
-			   PCIE_APP_REQ_EXIT_L1_MODE, 0);
-	regmap_update_bits(ep->fsysreg, PCIE_EXYNOS5433_PHY_L1SUB_CM_CON,
-			   PCIE_REFCLK_GATING_EN, 0);
-	return 0;
-}
-
-static int exynos5433_pcie_phy_power_off(struct phy *phy)
+static int exynos5433_pcie_phy_exit(struct phy *phy)
 {
 	struct exynos_pcie_phy *ep = phy_get_drvdata(phy);
 
@@ -135,8 +129,7 @@
 
 static const struct phy_ops exynos5433_phy_ops = {
 	.init		= exynos5433_pcie_phy_init,
-	.power_on	= exynos5433_pcie_phy_power_on,
-	.power_off	= exynos5433_pcie_phy_power_off,
+	.exit		= exynos5433_pcie_phy_exit,
 	.owner		= THIS_MODULE,
 };
 
diff --git a/include/linux/dma/edma.h b/include/linux/dma/edma.h
index cab6e18..7d8062e 100644
--- a/include/linux/dma/edma.h
+++ b/include/linux/dma/edma.h
@@ -12,19 +12,74 @@
 #include <linux/device.h>
 #include <linux/dmaengine.h>
 
+#define EDMA_MAX_WR_CH                                  8
+#define EDMA_MAX_RD_CH                                  8
+
 struct dw_edma;
 
+struct dw_edma_region {
+	phys_addr_t	paddr;
+	void __iomem	*vaddr;
+	size_t		sz;
+};
+
+struct dw_edma_core_ops {
+	int (*irq_vector)(struct device *dev, unsigned int nr);
+};
+
+enum dw_edma_map_format {
+	EDMA_MF_EDMA_LEGACY = 0x0,
+	EDMA_MF_EDMA_UNROLL = 0x1,
+	EDMA_MF_HDMA_COMPAT = 0x5
+};
+
+/**
+ * enum dw_edma_chip_flags - Flags specific to an eDMA chip
+ * @DW_EDMA_CHIP_LOCAL:		eDMA is used locally by an endpoint
+ */
+enum dw_edma_chip_flags {
+	DW_EDMA_CHIP_LOCAL	= BIT(0),
+};
+
 /**
  * struct dw_edma_chip - representation of DesignWare eDMA controller hardware
  * @dev:		 struct device of the eDMA controller
  * @id:			 instance ID
- * @irq:		 irq line
- * @dw:			 struct dw_edma that is filed by dw_edma_probe()
+ * @nr_irqs:		 total number of DMA IRQs
+ * @ops			 DMA channel to IRQ number mapping
+ * @flags		 dw_edma_chip_flags
+ * @reg_base		 DMA register base address
+ * @ll_wr_cnt		 DMA write link list count
+ * @ll_rd_cnt		 DMA read link list count
+ * @rg_region		 DMA register region
+ * @ll_region_wr	 DMA descriptor link list memory for write channel
+ * @ll_region_rd	 DMA descriptor link list memory for read channel
+ * @dt_region_wr	 DMA data memory for write channel
+ * @dt_region_rd	 DMA data memory for read channel
+ * @mf			 DMA register map format
+ * @dw:			 struct dw_edma that is filled by dw_edma_probe()
  */
 struct dw_edma_chip {
 	struct device		*dev;
 	int			id;
-	int			irq;
+	int			nr_irqs;
+	const struct dw_edma_core_ops   *ops;
+	u32			flags;
+
+	void __iomem		*reg_base;
+
+	u16			ll_wr_cnt;
+	u16			ll_rd_cnt;
+	/* link list address */
+	struct dw_edma_region	ll_region_wr[EDMA_MAX_WR_CH];
+	struct dw_edma_region	ll_region_rd[EDMA_MAX_RD_CH];
+
+	/* data region */
+	struct dw_edma_region	dt_region_wr[EDMA_MAX_WR_CH];
+	struct dw_edma_region	dt_region_rd[EDMA_MAX_RD_CH];
+
+	enum dw_edma_map_format	mf;
+
 	struct dw_edma		*dw;
 };
 
diff --git a/include/linux/hypervisor.h b/include/linux/hypervisor.h
index fc08b43..9efbc54 100644
--- a/include/linux/hypervisor.h
+++ b/include/linux/hypervisor.h
@@ -32,4 +32,12 @@
 
 #endif /* !CONFIG_X86 */
 
+static inline bool hypervisor_isolated_pci_functions(void)
+{
+	if (IS_ENABLED(CONFIG_S390))
+		return true;
+
+	return jailhouse_paravirt();
+}
+
 #endif /* __LINUX_HYPEVISOR_H */
diff --git a/include/linux/pci-ecam.h b/include/linux/pci-ecam.h
index adea5a4..6b1301e 100644
--- a/include/linux/pci-ecam.h
+++ b/include/linux/pci-ecam.h
@@ -87,6 +87,7 @@
 extern const struct pci_ecam_ops xgene_v2_pcie_ecam_ops; /* APM X-Gene PCIe v2.x */
 extern const struct pci_ecam_ops al_pcie_ops;	/* Amazon Annapurna Labs PCIe */
 extern const struct pci_ecam_ops tegra194_pcie_ops; /* Tegra194 PCIe */
+extern const struct pci_ecam_ops loongson_pci_ecam_ops; /* Loongson PCIe */
 #endif
 
 #if IS_ENABLED(CONFIG_PCI_HOST_COMMON)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 81a57b4..060af91 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -1909,24 +1909,14 @@
 
 #include <asm/pci.h>
 
-/* These two functions provide almost identical functionality. Depending
- * on the architecture, one will be implemented as a wrapper around the
- * other (in drivers/pci/mmap.c).
- *
+/*
  * pci_mmap_resource_range() maps a specific BAR, and vm->vm_pgoff
  * is expected to be an offset within that region.
  *
- * pci_mmap_page_range() is the legacy architecture-specific interface,
- * which accepts a "user visible" resource address converted by
- * pci_resource_to_user(), as used in the legacy mmap() interface in
- * /proc/bus/pci/.
  */
 int pci_mmap_resource_range(struct pci_dev *dev, int bar,
 			    struct vm_area_struct *vma,
 			    enum pci_mmap_state mmap_state, int write_combine);
-int pci_mmap_page_range(struct pci_dev *pdev, int bar,
-			struct vm_area_struct *vma,
-			enum pci_mmap_state mmap_state, int write_combine);
 
 #ifndef arch_can_pci_mmap_wc
 #define arch_can_pci_mmap_wc()		0