pci-v5.18-changes

-----BEGIN PGP SIGNATURE-----
 
 iQJIBAABCgAyFiEEgMe7l+5h9hnxdsnuWYigwDrT+vwFAmI7iOwUHGJoZWxnYWFz
 QGdvb2dsZS5jb20ACgkQWYigwDrT+vxkuhAAtJkVwfeyUjZ8sms+qWdZaucJmFF1
 PDeKy8O8upLzRRykdWoAOjKKVcCB9ohxBjPMco2oYNTmSozxeau8jjMA9OTQvTOS
 ZhDDoi49/vHRHuq3WIeAMCuk7tH3H1L3f0UHJxJ3H/oObQ+eMsitPcGFK+QrISDX
 pYokOnXZvf7BT7NpVtogSe2mhniOD1zQSicAMiH6WKNHHZcxewrzV9LP3MFOoBAr
 VMhlhzJbOp9spvCt7M1DycJEQ2RNe+wGLBFDalhPuprwnkNchRV+0AwWfD90zc9u
 h/0J8jkXfqS6QfSd/lOlTvI6kGsV8UKZEt4h4X/hlHFebFM5ktD9X7GmcoYUDFd9
 aHV3I/Jf62uGJ31IrT0V/cSYNlMO+IVFwXLGir4B1cFPOkzyIG/i60iV/C6bnnCa
 TCMH6vxalFycYaHBFqw/K/Dlq+mrAX74nQDfbk8y6rprczM1BN220Z8BkpG13TBu
 MxgCEul2/BJmNcPS1IWb/mCfBy+rdrVn2DZuID3J9KTwKNOUTIuAF0FuxLP4Bk4o
 sti3vKIXOcHnAcJB9tEnpEfstPv2JT13eWDIMmp/qCwqcujOvsg/DSYrx+8ogmBF
 DJ/sbPy3BdIOAeTgepWHAxYcv9SlZTGJGl+oaR1zV0qLBogyQUWZ9Ijx5aAEAw3j
 AJicpdk3BkH3LC8=
 =5Q9H
 -----END PGP SIGNATURE-----

Merge tag 'pci-v5.18-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci

Pull pci updates from Bjorn Helgaas:
 "Enumeration:
   - Move the VGA arbiter from drivers/gpu to drivers/pci because it's
     PCI-specific, not GPU-specific (Bjorn Helgaas)
   - Select the default VGA device consistently whether it's enumerated
     before or after VGA arbiter init, which fixes arches that enumerate
     PCI devices late (Huacai Chen)

  Resource management:
   - Support BAR sizes up to 8TB (Dongdong Liu)

  PCIe native device hotplug:
   - Fix "Command Completed" tracking to avoid spurious timouts when
     powering off empty slots (Liguang Zhang)
   - Quirk Qualcomm devices that don't implement Command Completed
     correctly, again to avoid spurious timeouts (Manivannan Sadhasivam)

  Peer-to-peer DMA:
   - Add Intel 3rd Gen Intel Xeon Scalable Processors to whitelist
     (Michael J. Ruhl)

  APM X-Gene PCIe controller driver:
   - Revert generic DT parsing changes that broke some machines in the
     field (Marc Zyngier)

  Freescale i.MX6 PCIe controller driver:
   - Allow controller probe to succeed even when no devices currently
     present to allow hot-add later (Fabio Estevam)
   - Enable power management on i.MX6QP (Richard Zhu)
   - Assert CLKREQ# on i.MX8MM so enumeration doesn't hang when no
     device is connected (Richard Zhu)

  Marvell Aardvark PCIe controller driver:
   - Fix MSI and MSI-X support (Marek Behún, Pali Rohár)
   - Add support for ERR and PME interrupts (Pali Rohár)

  Marvell MVEBU PCIe controller driver:
   - Add DT binding and support for "num-lanes" (Pali Rohár)
   - Add support for INTx interrupts (Pali Rohár)

  Microsoft Hyper-V host bridge driver:
   - Avoid unnecessary hypercalls when unmasking IRQs on ARM64 (Boqun
     Feng)

  Qualcomm PCIe controller driver:
   - Add SM8450 DT binding and driver support (Dmitry Baryshkov)

  Renesas R-Car PCIe controller driver:
   - Help the controller get to the L1 state since the hardware can't do
     it on its own (Marek Vasut)
   - Return PCI_ERROR_RESPONSE (~0) for reads that fail on PCIe (Marek
     Vasut)

  SiFive FU740 PCIe controller driver:
   - Drop redundant '-gpios' from DT GPIO lookup (Ben Dooks)
   - Force 2.5GT/s for initial device probe (Ben Dooks)

  Socionext UniPhier Pro5 controller driver:
   - Add NX1 DT binding and driver support (Kunihiko Hayashi)

  Synopsys DesignWare PCIe controller driver:
   - Restore MSI configuration so MSI works after resume (Jisheng
     Zhang)"

* tag 'pci-v5.18-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/helgaas/pci: (94 commits)
  x86/PCI: Add #includes to asm/pci_x86.h
  PCI: ibmphp: Remove unused assignments
  PCI: cpqphp: Remove unused assignments
  PCI: fu740: Remove unused assignments
  PCI: kirin: Remove unused assignments
  PCI: Remove unused assignments
  PCI: Declare pci_filp_private only when HAVE_PCI_MMAP
  PCI: Avoid broken MSI on SB600 USB devices
  PCI: fu740: Force 2.5GT/s for initial device probe
  PCI: xgene: Revert "PCI: xgene: Fix IB window setup"
  PCI: xgene: Revert "PCI: xgene: Use inbound resources for setup"
  PCI: imx6: Assert i.MX8MM CLKREQ# even if no device present
  PCI: imx6: Invoke the PHY exit function after PHY power off
  PCI: rcar: Use PCI_SET_ERROR_RESPONSE after read which triggered an exception
  PCI: rcar: Finish transition to L1 state in rcar_pcie_config_access()
  PCI: dwc: Restore MSI Receiver mask during resume
  PCI: fu740: Drop redundant '-gpios' from DT GPIO lookup
  PCI/VGA: Replace full MIT license text with SPDX identifier
  PCI/VGA: Use unsigned format string to print lock counts
  PCI/VGA: Log bridge control messages when adding devices
  ...

Documentation/devicetree/bindings/pci/mvebu-pci.txt

@@ -77,9 +77,15 @@ and the following optional properties:
 - marvell,pcie-lane: the physical PCIe lane number, for ports having
   multiple lanes. If this property is not found, we assume that the
   value is 0.
+- num-lanes: number of SerDes PCIe lanes for this link (1 or 4)
 - reset-gpios: optional GPIO to PERST#
 - reset-delay-us: delay in us to wait after reset de-assertion, if not
   specified will default to 100ms, as required by the PCIe specification.
+- interrupt-names: list of interrupt names, supported are:
+   - "intx" - interrupt line triggered by one of the legacy interrupt
+- interrupts or interrupts-extended: List of the interrupt sources which
+  corresponding to the "interrupt-names". If non-empty then also additional
+  'interrupt-controller' subnode must be defined.
 
 Example:
 
@@ -141,6 +147,7 @@ pcie-controller {
 		interrupt-map = <0 0 0 0 &mpic 58>;
 		marvell,pcie-port = <0>;
 		marvell,pcie-lane = <0>;
+		num-lanes = <1>;
 		/* low-active PERST# reset on GPIO 25 */
 		reset-gpios = <&gpio0 25 1>;
 		/* wait 20ms for device settle after reset deassertion */
@@ -161,6 +168,7 @@ pcie-controller {
 		interrupt-map = <0 0 0 0 &mpic 59>;
 		marvell,pcie-port = <0>;
 		marvell,pcie-lane = <1>;
+		num-lanes = <1>;
 		clocks = <&gateclk 6>;
 	};
 
@@ -177,6 +185,7 @@ pcie-controller {
 		interrupt-map = <0 0 0 0 &mpic 60>;
 		marvell,pcie-port = <0>;
 		marvell,pcie-lane = <2>;
+		num-lanes = <1>;
 		clocks = <&gateclk 7>;
 	};
 
@@ -193,6 +202,7 @@ pcie-controller {
 		interrupt-map = <0 0 0 0 &mpic 61>;
 		marvell,pcie-port = <0>;
 		marvell,pcie-lane = <3>;
+		num-lanes = <1>;
 		clocks = <&gateclk 8>;
 	};
 
@@ -209,6 +219,7 @@ pcie-controller {
 		interrupt-map = <0 0 0 0 &mpic 62>;
 		marvell,pcie-port = <1>;
 		marvell,pcie-lane = <0>;
+		num-lanes = <1>;
 		clocks = <&gateclk 9>;
 	};
 
@@ -225,6 +236,7 @@ pcie-controller {
 		interrupt-map = <0 0 0 0 &mpic 63>;
 		marvell,pcie-port = <1>;
 		marvell,pcie-lane = <1>;
+		num-lanes = <1>;
 		clocks = <&gateclk 10>;
 	};
 
@@ -241,6 +253,7 @@ pcie-controller {
 		interrupt-map = <0 0 0 0 &mpic 64>;
 		marvell,pcie-port = <1>;
 		marvell,pcie-lane = <2>;
+		num-lanes = <1>;
 		clocks = <&gateclk 11>;
 	};
 
@@ -257,6 +270,7 @@ pcie-controller {
 		interrupt-map = <0 0 0 0 &mpic 65>;
 		marvell,pcie-port = <1>;
 		marvell,pcie-lane = <3>;
+		num-lanes = <1>;
 		clocks = <&gateclk 12>;
 	};
 
@@ -273,6 +287,7 @@ pcie-controller {
 		interrupt-map = <0 0 0 0 &mpic 99>;
 		marvell,pcie-port = <2>;
 		marvell,pcie-lane = <0>;
+		num-lanes = <1>;
 		clocks = <&gateclk 26>;
 	};
 
@@ -289,6 +304,7 @@ pcie-controller {
 		interrupt-map = <0 0 0 0 &mpic 103>;
 		marvell,pcie-port = <3>;
 		marvell,pcie-lane = <0>;
+		num-lanes = <1>;
 		clocks = <&gateclk 27>;
 	};
 };

Documentation/devicetree/bindings/pci/qcom,pcie.txt

@@ -15,6 +15,8 @@
 			- "qcom,pcie-sc8180x" for sc8180x
 			- "qcom,pcie-sdm845" for sdm845
 			- "qcom,pcie-sm8250" for sm8250
+			- "qcom,pcie-sm8450-pcie0" for PCIe0 on sm8450
+			- "qcom,pcie-sm8450-pcie1" for PCIe1 on sm8450
 			- "qcom,pcie-ipq6018" for ipq6018
 
 - reg:
@@ -169,6 +171,24 @@
 			- "ddrss_sf_tbu" PCIe SF TBU clock
 			- "pipe"	PIPE clock
 
+- clock-names:
+	Usage: required for sm8450-pcie0 and sm8450-pcie1
+	Value type: <stringlist>
+	Definition: Should contain the following entries
+			- "aux"         Auxiliary clock
+			- "cfg"         Configuration clock
+			- "bus_master"  Master AXI clock
+			- "bus_slave"   Slave AXI clock
+			- "slave_q2a"   Slave Q2A clock
+			- "tbu"         PCIe TBU clock
+			- "ddrss_sf_tbu" PCIe SF TBU clock
+			- "pipe"        PIPE clock
+			- "pipe_mux"    PIPE MUX
+			- "phy_pipe"    PIPE output clock
+			- "ref"         REFERENCE clock
+			- "aggre0"	Aggre NoC PCIe0 AXI clock, only for sm8450-pcie0
+			- "aggre1"	Aggre NoC PCIe1 AXI clock
+
 - resets:
 	Usage: required
 	Value type: <prop-encoded-array>
@@ -246,7 +266,7 @@
 			- "ahb"			AHB reset
 
 - reset-names:
-	Usage: required for sc8180x, sdm845 and sm8250
+	Usage: required for sc8180x, sdm845, sm8250 and sm8450
 	Value type: <stringlist>
 	Definition: Should contain the following entries
 			- "pci"			PCIe core reset

Documentation/devicetree/bindings/pci/socionext,uniphier-pcie-ep.yaml

@@ -20,7 +20,9 @@ allOf:
 
 properties:
   compatible:
-    const: socionext,uniphier-pro5-pcie-ep
+    enum:
+      - socionext,uniphier-pro5-pcie-ep
+      - socionext,uniphier-nx1-pcie-ep
 
   reg:
     minItems: 4
@@ -41,20 +43,26 @@ properties:
           - const: atu
 
   clocks:
+    minItems: 1
     maxItems: 2
 
   clock-names:
-    items:
+    oneOf:
-      - const: gio
+      - items:              # for Pro5
-      - const: link
+          - const: gio
+          - const: link
+      - const: link         # for NX1
 
   resets:
+    minItems: 1
     maxItems: 2
 
   reset-names:
-    items:
+    oneOf:
-      - const: gio
+      - items:              # for Pro5
-      - const: link
+          - const: gio
+          - const: link
+      - const: link         # for NX1
 
   num-ib-windows:
     const: 16

Documentation/gpu/vgaarbiter.rst

@@ -100,7 +100,7 @@ In-kernel interface
 .. kernel-doc:: include/linux/vgaarb.h
    :internal:
 
-.. kernel-doc:: drivers/gpu/vga/vgaarb.c
+.. kernel-doc:: drivers/pci/vgaarb.c
    :export:
 
 libpciaccess

MAINTAINERS

@@ -14938,6 +14938,7 @@ F:	drivers/pci/controller/mobiveil/pcie-mobiveil*
 
 PCI DRIVER FOR MVEBU (Marvell Armada 370 and Armada XP SOC support)
 M:	Thomas Petazzoni <thomas.petazzoni@bootlin.com>
+M:	Pali Rohár <pali@kernel.org>
 L:	linux-pci@vger.kernel.org
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained

arch/mips/include/asm/mach-bcm63xx/bcm63xx_regs.h

@@ -1380,8 +1380,6 @@
 
 #define PCIE_IDVAL3_REG			0x43c
 #define IDVAL3_CLASS_CODE_MASK		0xffffff
-#define IDVAL3_SUBCLASS_SHIFT		8
-#define IDVAL3_CLASS_SHIFT		16
 
 #define PCIE_DLSTATUS_REG		0x1048
 #define DLSTATUS_PHYLINKUP		(1 << 13)

arch/mips/pci/fixup-sb1250.c

@@ -75,7 +75,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_SIBYTE, PCI_DEVICE_ID_BCM1250_PCI,
  */
 static void quirk_sb1250_ht(struct pci_dev *dev)
 {
-	dev->class = PCI_CLASS_BRIDGE_PCI << 8;
+	dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL;
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_SIBYTE, PCI_DEVICE_ID_BCM1250_HT,
 			quirk_sb1250_ht);

arch/mips/pci/pci-bcm63xx.c

@@ -186,7 +186,7 @@ static int __init bcm63xx_register_pcie(void)
 	/* setup class code as bridge */
 	val = bcm_pcie_readl(PCIE_IDVAL3_REG);
 	val &= ~IDVAL3_CLASS_CODE_MASK;
-	val |= (PCI_CLASS_BRIDGE_PCI << IDVAL3_SUBCLASS_SHIFT);
+	val |= PCI_CLASS_BRIDGE_PCI_NORMAL;
 	bcm_pcie_writel(val, PCIE_IDVAL3_REG);
 
 	/* disable bar1 size */

arch/powerpc/platforms/powernv/pci.c

@@ -815,7 +815,7 @@ void pnv_pci_shutdown(void)
 /* Fixup wrong class code in p7ioc and p8 root complex */
 static void pnv_p7ioc_rc_quirk(struct pci_dev *dev)
 {
-	dev->class = PCI_CLASS_BRIDGE_PCI << 8;
+	dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL;
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_IBM, 0x3b9, pnv_p7ioc_rc_quirk);
 

arch/powerpc/sysdev/fsl_pci.c

@@ -55,7 +55,7 @@ static void quirk_fsl_pcie_early(struct pci_dev *dev)
 	if ((hdr_type & 0x7f) != PCI_HEADER_TYPE_BRIDGE)
 		return;
 
-	dev->class = PCI_CLASS_BRIDGE_PCI << 8;
+	dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL;
 	fsl_pcie_bus_fixup = 1;
 	return;
 }

arch/sh/drivers/pci/pcie-sh7786.c

@@ -314,7 +314,7 @@ static int __init pcie_init(struct sh7786_pcie_port *port)
 	 * class to match. Hardware takes care of propagating the IDSETR
 	 * settings, so there is no need to bother with a quirk.
 	 */
-	pci_write_reg(chan, PCI_CLASS_BRIDGE_PCI << 16, SH4A_PCIEIDSETR1);
+	pci_write_reg(chan, PCI_CLASS_BRIDGE_PCI_NORMAL << 8, SH4A_PCIEIDSETR1);
 
 	/* Initialize default capabilities. */
 	data = pci_read_reg(chan, SH4A_PCIEEXPCAP0);

arch/x86/include/asm/pci_x86.h

@@ -5,7 +5,10 @@
  *	(c) 1999 Martin Mares <mj@ucw.cz>
  */
 
+#include <linux/errno.h>
+#include <linux/init.h>
 #include <linux/ioport.h>
+#include <linux/spinlock.h>
 
 #undef DEBUG
 

drivers/gpu/vga/Kconfig

@@ -1,23 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-config VGA_ARB
-	bool "VGA Arbitration" if EXPERT
-	default y
-	depends on (PCI && !S390)
-	help
-	  Some "legacy" VGA devices implemented on PCI typically have the same
-	  hard-decoded addresses as they did on ISA. When multiple PCI devices
-	  are accessed at same time they need some kind of coordination. Please
-	  see Documentation/gpu/vgaarbiter.rst for more details. Select this to
-	  enable VGA arbiter.
-
-config VGA_ARB_MAX_GPUS
-	int "Maximum number of GPUs"
-	default 16
-	depends on VGA_ARB
-	help
-	  Reserves space in the kernel to maintain resource locking for
-	  multiple GPUS.  The overhead for each GPU is very small.
-
 config VGA_SWITCHEROO
 	bool "Laptop Hybrid Graphics - GPU switching support"
 	depends on X86

drivers/gpu/vga/Makefile

@@ -1,3 +1,2 @@
 # SPDX-License-Identifier: GPL-2.0-only
-obj-$(CONFIG_VGA_ARB)  += vgaarb.o
 obj-$(CONFIG_VGA_SWITCHEROO) += vga_switcheroo.o

drivers/pci/Kconfig

@@ -252,6 +252,25 @@ config PCIE_BUS_PEER2PEER
 
 endchoice
 
+config VGA_ARB
+	bool "VGA Arbitration" if EXPERT
+	default y
+	depends on (PCI && !S390)
+	help
+	  Some "legacy" VGA devices implemented on PCI typically have the same
+	  hard-decoded addresses as they did on ISA. When multiple PCI devices
+	  are accessed at same time they need some kind of coordination. Please
+	  see Documentation/gpu/vgaarbiter.rst for more details. Select this to
+	  enable VGA arbiter.
+
+config VGA_ARB_MAX_GPUS
+	int "Maximum number of GPUs"
+	default 16
+	depends on VGA_ARB
+	help
+	  Reserves space in the kernel to maintain resource locking for
+	  multiple GPUS.  The overhead for each GPU is very small.
+
 source "drivers/pci/hotplug/Kconfig"
 source "drivers/pci/controller/Kconfig"
 source "drivers/pci/endpoint/Kconfig"

drivers/pci/Makefile

@@ -30,6 +30,7 @@ obj-$(CONFIG_PCI_PF_STUB)	+= pci-pf-stub.o
 obj-$(CONFIG_PCI_ECAM)		+= ecam.o
 obj-$(CONFIG_PCI_P2PDMA)	+= p2pdma.o
 obj-$(CONFIG_XEN_PCIDEV_FRONTEND) += xen-pcifront.o
+obj-$(CONFIG_VGA_ARB)		+= vgaarb.o
 
 # Endpoint library must be initialized before its users
 obj-$(CONFIG_PCI_ENDPOINT)	+= endpoint/

drivers/pci/access.c

@@ -159,9 +159,12 @@ int pci_generic_config_write32(struct pci_bus *bus, unsigned int devfn,
 	 * write happen to have any RW1C (write-one-to-clear) bits set, we
 	 * just inadvertently cleared something we shouldn't have.
 	 */
-	dev_warn_ratelimited(&bus->dev, "%d-byte config write to %04x:%02x:%02x.%d offset %#x may corrupt adjacent RW1C bits\n",
+	if (!bus->unsafe_warn) {
-			     size, pci_domain_nr(bus), bus->number,
+		dev_warn(&bus->dev, "%d-byte config write to %04x:%02x:%02x.%d offset %#x may corrupt adjacent RW1C bits\n",
-			     PCI_SLOT(devfn), PCI_FUNC(devfn), where);
+			 size, pci_domain_nr(bus), bus->number,
+			 PCI_SLOT(devfn), PCI_FUNC(devfn), where);
+		bus->unsafe_warn = 1;
+	}
 
 	mask = ~(((1 << (size * 8)) - 1) << ((where & 0x3) * 8));
 	tmp = readl(addr) & mask;

drivers/pci/controller/Kconfig

@@ -10,6 +10,10 @@ config PCI_MVEBU
 	depends on ARM
 	depends on OF
 	select PCI_BRIDGE_EMUL
+	help
+	 Add support for Marvell EBU PCIe controller. This PCIe controller
+	 is used on 32-bit Marvell ARM SoCs: Dove, Kirkwood, Armada 370,
+	 Armada XP, Armada 375, Armada 38x and Armada 39x.
 
 config PCI_AARDVARK
 	tristate "Aardvark PCIe controller"

drivers/pci/controller/dwc/pci-imx6.c

@@ -453,10 +453,6 @@ static int imx6_pcie_enable_ref_clk(struct imx6_pcie *imx6_pcie)
 	case IMX7D:
 		break;
 	case IMX8MM:
-		ret = clk_prepare_enable(imx6_pcie->pcie_aux);
-		if (ret)
-			dev_err(dev, "unable to enable pcie_aux clock\n");
-		break;
 	case IMX8MQ:
 		ret = clk_prepare_enable(imx6_pcie->pcie_aux);
 		if (ret) {
@@ -809,9 +805,7 @@ static int imx6_pcie_start_link(struct dw_pcie *pci)
 	/* Start LTSSM. */
 	imx6_pcie_ltssm_enable(dev);
 
-	ret = dw_pcie_wait_for_link(pci);
+	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. */
@@ -847,11 +841,7 @@ static int imx6_pcie_start_link(struct dw_pcie *pci)
 		}
 
 		/* Make sure link training is finished as well! */
-		ret = dw_pcie_wait_for_link(pci);
+		dw_pcie_wait_for_link(pci);
-		if (ret) {
-			dev_err(dev, "Failed to bring link up!\n");
-			goto err_reset_phy;
-		}
 	} else {
 		dev_info(dev, "Link: Gen2 disabled\n");
 	}
@@ -923,6 +913,7 @@ static void imx6_pcie_pm_turnoff(struct imx6_pcie *imx6_pcie)
 	/* Others poke directly at IOMUXC registers */
 	switch (imx6_pcie->drvdata->variant) {
 	case IMX6SX:
+	case IMX6QP:
 		regmap_update_bits(imx6_pcie->iomuxc_gpr, IOMUXC_GPR12,
 				IMX6SX_GPR12_PCIE_PM_TURN_OFF,
 				IMX6SX_GPR12_PCIE_PM_TURN_OFF);
@@ -983,6 +974,7 @@ static int imx6_pcie_suspend_noirq(struct device *dev)
 	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;
@@ -1252,7 +1244,8 @@ static const struct imx6_pcie_drvdata drvdata[] = {
 	[IMX6QP] = {
 		.variant = IMX6QP,
 		.flags = IMX6_PCIE_FLAG_IMX6_PHY |
-			 IMX6_PCIE_FLAG_IMX6_SPEED_CHANGE,
+			 IMX6_PCIE_FLAG_IMX6_SPEED_CHANGE |
+			 IMX6_PCIE_FLAG_SUPPORTS_SUSPEND,
 		.dbi_length = 0x200,
 	},
 	[IMX7D] = {

drivers/pci/controller/dwc/pci-keystone.c

@@ -531,13 +531,13 @@ static void ks_pcie_quirk(struct pci_dev *dev)
 	struct pci_dev *bridge;
 	static const struct pci_device_id rc_pci_devids[] = {
 		{ PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2HK),
-		 .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, },
+		 .class = PCI_CLASS_BRIDGE_PCI_NORMAL, .class_mask = ~0, },
 		{ PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2E),
-		 .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, },
+		 .class = PCI_CLASS_BRIDGE_PCI_NORMAL, .class_mask = ~0, },
 		{ PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2L),
-		 .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, },
+		 .class = PCI_CLASS_BRIDGE_PCI_NORMAL, .class_mask = ~0, },
 		{ PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2G),
-		 .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, },
+		 .class = PCI_CLASS_BRIDGE_PCI_NORMAL, .class_mask = ~0, },
 		{ 0, },
 	};
 

drivers/pci/controller/dwc/pci-meson.c

@@ -313,14 +313,14 @@ static int meson_pcie_rd_own_conf(struct pci_bus *bus, u32 devfn,
 	 * cannot program the PCI_CLASS_DEVICE register, so we must fabricate
 	 * the return value in the config accessors.
 	 */
-	if (where == PCI_CLASS_REVISION && size == 4)
+	if ((where & ~3) == PCI_CLASS_REVISION) {
-		*val = (PCI_CLASS_BRIDGE_PCI << 16) | (*val & 0xffff);
+		if (size <= 2)
-	else if (where == PCI_CLASS_DEVICE && size == 2)
+			*val = (*val & ((1 << (size * 8)) - 1)) << (8 * (where & 3));
-		*val = PCI_CLASS_BRIDGE_PCI;
+		*val &= ~0xffffff00;
-	else if (where == PCI_CLASS_DEVICE && size == 1)
+		*val |= PCI_CLASS_BRIDGE_PCI_NORMAL << 8;
-		*val = PCI_CLASS_BRIDGE_PCI & 0xff;
+		if (size <= 2)
-	else if (where == PCI_CLASS_DEVICE + 1 && size == 1)
+			*val = (*val >> (8 * (where & 3))) & ((1 << (size * 8)) - 1);
-		*val = (PCI_CLASS_BRIDGE_PCI >> 8) & 0xff;
+	}
 
 	return PCIBIOS_SUCCESSFUL;
 }

drivers/pci/controller/dwc/pcie-designware-host.c

@@ -362,6 +362,12 @@ int dw_pcie_host_init(struct pcie_port *pp)
 			if (ret < 0)
 				return ret;
 		} 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) {
@@ -541,7 +547,6 @@ void dw_pcie_setup_rc(struct pcie_port *pp)
 
 		/* Initialize IRQ Status array */
 		for (ctrl = 0; ctrl < num_ctrls; ctrl++) {
-			pp->irq_mask[ctrl] = ~0;
 			dw_pcie_writel_dbi(pci, PCIE_MSI_INTR0_MASK +
 					    (ctrl * MSI_REG_CTRL_BLOCK_SIZE),
 					    pp->irq_mask[ctrl]);

drivers/pci/controller/dwc/pcie-fu740.c

@@ -181,10 +181,59 @@ static int fu740_pcie_start_link(struct dw_pcie *pci)
 {
 	struct device *dev = pci->dev;
 	struct fu740_pcie *afp = dev_get_drvdata(dev);
+	u8 cap_exp = dw_pcie_find_capability(pci, PCI_CAP_ID_EXP);
+	int ret;
+	u32 orig, tmp;
+
+	/*
+	 * Force 2.5GT/s when starting the link, due to some devices not
+	 * probing at higher speeds. This happens with the PCIe switch
+	 * on the Unmatched board when U-Boot has not initialised the PCIe.
+	 * The fix in U-Boot is to force 2.5GT/s, which then gets cleared
+	 * by the soft reset done by this driver.
+	 */
+	dev_dbg(dev, "cap_exp at %x\n", cap_exp);
+	dw_pcie_dbi_ro_wr_en(pci);
+
+	tmp = dw_pcie_readl_dbi(pci, cap_exp + PCI_EXP_LNKCAP);
+	orig = tmp & PCI_EXP_LNKCAP_SLS;
+	tmp &= ~PCI_EXP_LNKCAP_SLS;
+	tmp |= PCI_EXP_LNKCAP_SLS_2_5GB;
+	dw_pcie_writel_dbi(pci, cap_exp + PCI_EXP_LNKCAP, tmp);
 
 	/* Enable LTSSM */
 	writel_relaxed(0x1, afp->mgmt_base + PCIEX8MGMT_APP_LTSSM_ENABLE);
-	return 0;
+
+	ret = dw_pcie_wait_for_link(pci);
+	if (ret) {
+		dev_err(dev, "error: link did not start\n");
+		goto err;
+	}
+
+	tmp = dw_pcie_readl_dbi(pci, cap_exp + PCI_EXP_LNKCAP);
+	if ((tmp & PCI_EXP_LNKCAP_SLS) != orig) {
+		dev_dbg(dev, "changing speed back to original\n");
+
+		tmp &= ~PCI_EXP_LNKCAP_SLS;
+		tmp |= orig;
+		dw_pcie_writel_dbi(pci, cap_exp + PCI_EXP_LNKCAP, tmp);
+
+		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);
+
+		ret = dw_pcie_wait_for_link(pci);
+		if (ret) {
+			dev_err(dev, "error: link did not start at new speed\n");
+			goto err;
+		}
+	}
+
+	ret = 0;
+err:
+	WARN_ON(ret);	/* we assume that errors will be very rare */
+	dw_pcie_dbi_ro_wr_dis(pci);
+	return ret;
 }
 
 static int fu740_pcie_host_init(struct pcie_port *pp)
@@ -224,7 +273,7 @@ static int fu740_pcie_host_init(struct pcie_port *pp)
 	/* Clear hold_phy_rst */
 	writel_relaxed(0x0, afp->mgmt_base + PCIEX8MGMT_APP_HOLD_PHY_RST);
 	/* Enable pcieauxclk */
-	ret = clk_prepare_enable(afp->pcie_aux);
+	clk_prepare_enable(afp->pcie_aux);
 	/* Set RC mode */
 	writel_relaxed(0x4, afp->mgmt_base + PCIEX8MGMT_DEVICE_TYPE);
 
@@ -259,11 +308,11 @@ static int fu740_pcie_probe(struct platform_device *pdev)
 		return PTR_ERR(afp->mgmt_base);
 
 	/* Fetch GPIOs */
-	afp->reset = devm_gpiod_get_optional(dev, "reset-gpios", GPIOD_OUT_LOW);
+	afp->reset = devm_gpiod_get_optional(dev, "reset", GPIOD_OUT_LOW);
 	if (IS_ERR(afp->reset))
 		return dev_err_probe(dev, PTR_ERR(afp->reset), "unable to get reset-gpios\n");
 
-	afp->pwren = devm_gpiod_get_optional(dev, "pwren-gpios", GPIOD_OUT_LOW);
+	afp->pwren = devm_gpiod_get_optional(dev, "pwren", GPIOD_OUT_LOW);
 	if (IS_ERR(afp->pwren))
 		return dev_err_probe(dev, PTR_ERR(afp->pwren), "unable to get pwren-gpios\n");
 

drivers/pci/controller/dwc/pcie-kirin.c

@@ -332,9 +332,6 @@ static int hi3660_pcie_phy_init(struct platform_device *pdev,
 	pcie->phy_priv = phy;
 	phy->dev = dev;
 
-	/* registers */
-	pdev = container_of(dev, struct platform_device, dev);
-
 	ret = hi3660_pcie_phy_get_clk(phy);
 	if (ret)
 		return ret;

drivers/pci/controller/dwc/pcie-qcom.c

@@ -161,7 +161,7 @@ struct qcom_pcie_resources_2_3_3 {
 
 /* 6 clocks typically, 7 for sm8250 */
 struct qcom_pcie_resources_2_7_0 {
-	struct clk_bulk_data clks[7];
+	struct clk_bulk_data clks[9];
 	int num_clks;
 	struct regulator_bulk_data supplies[2];
 	struct reset_control *pci_reset;
@@ -195,6 +195,10 @@ struct qcom_pcie_ops {
 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;
+	unsigned int has_aggre1_clk:1;
 };
 
 struct qcom_pcie {
@@ -204,8 +208,7 @@ struct qcom_pcie {
 	union qcom_pcie_resources res;
 	struct phy *phy;
 	struct gpio_desc *reset;
-	const struct qcom_pcie_ops *ops;
+	const struct qcom_pcie_cfg *cfg;
-	unsigned int pipe_clk_need_muxing:1;
 };
 
 #define to_qcom_pcie(x)		dev_get_drvdata((x)->dev)
@@ -229,8 +232,8 @@ static int qcom_pcie_start_link(struct dw_pcie *pci)
 	struct qcom_pcie *pcie = to_qcom_pcie(pci);
 
 	/* Enable Link Training state machine */
-	if (pcie->ops->ltssm_enable)
+	if (pcie->cfg->ops->ltssm_enable)
-		pcie->ops->ltssm_enable(pcie);
+		pcie->cfg->ops->ltssm_enable(pcie);
 
 	return 0;
 }
@@ -1146,6 +1149,7 @@ 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;
 	struct dw_pcie *pci = pcie->pci;
 	struct device *dev = pci->dev;
+	unsigned int idx;
 	int ret;
 
 	res->pci_reset = devm_reset_control_get_exclusive(dev, "pci");
@@ -1159,24 +1163,28 @@ static int qcom_pcie_get_resources_2_7_0(struct qcom_pcie *pcie)
 	if (ret)
 		return ret;
 
-	res->clks[0].id = "aux";
+	idx = 0;
-	res->clks[1].id = "cfg";
+	res->clks[idx++].id = "aux";
-	res->clks[2].id = "bus_master";
+	res->clks[idx++].id = "cfg";
-	res->clks[3].id = "bus_slave";
+	res->clks[idx++].id = "bus_master";
-	res->clks[4].id = "slave_q2a";
+	res->clks[idx++].id = "bus_slave";
-	res->clks[5].id = "tbu";
+	res->clks[idx++].id = "slave_q2a";
-	if (of_device_is_compatible(dev->of_node, "qcom,pcie-sm8250")) {
+	if (pcie->cfg->has_tbu_clk)
-		res->clks[6].id = "ddrss_sf_tbu";
+		res->clks[idx++].id = "tbu";
-		res->num_clks = 7;
+	if (pcie->cfg->has_ddrss_sf_tbu_clk)
-	} else {
+		res->clks[idx++].id = "ddrss_sf_tbu";
-		res->num_clks = 6;
+	if (pcie->cfg->has_aggre0_clk)
-	}
+		res->clks[idx++].id = "aggre0";
+	if (pcie->cfg->has_aggre1_clk)
+		res->clks[idx++].id = "aggre1";
+
+	res->num_clks = idx;
 
 	ret = devm_clk_bulk_get(dev, res->num_clks, res->clks);
 	if (ret < 0)
 		return ret;
 
-	if (pcie->pipe_clk_need_muxing) {
+	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);
@@ -1209,7 +1217,7 @@ static int qcom_pcie_init_2_7_0(struct qcom_pcie *pcie)
 	}
 
 	/* Set TCXO as clock source for pcie_pipe_clk_src */
-	if (pcie->pipe_clk_need_muxing)
+	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);
@@ -1236,6 +1244,9 @@ static int qcom_pcie_init_2_7_0(struct qcom_pcie *pcie)
 		goto err_disable_clocks;
 	}
 
+	/* Wait for reset to complete, required on SM8450 */
+	usleep_range(1000, 1500);
+
 	/* configure PCIe to RC mode */
 	writel(DEVICE_TYPE_RC, pcie->parf + PCIE20_PARF_DEVICE_TYPE);
 
@@ -1284,7 +1295,7 @@ static int qcom_pcie_post_init_2_7_0(struct qcom_pcie *pcie)
 	struct qcom_pcie_resources_2_7_0 *res = &pcie->res.v2_7_0;
 
 	/* Set pipe clock as clock source for pcie_pipe_clk_src */
-	if (pcie->pipe_clk_need_muxing)
+	if (pcie->cfg->pipe_clk_need_muxing)
 		clk_set_parent(res->pipe_clk_src, res->phy_pipe_clk);
 
 	return clk_prepare_enable(res->pipe_clk);
@@ -1384,7 +1395,7 @@ static int qcom_pcie_host_init(struct pcie_port *pp)
 
 	qcom_ep_reset_assert(pcie);
 
-	ret = pcie->ops->init(pcie);
+	ret = pcie->cfg->ops->init(pcie);
 	if (ret)
 		return ret;
 
@@ -1392,16 +1403,16 @@ static int qcom_pcie_host_init(struct pcie_port *pp)
 	if (ret)
 		goto err_deinit;
 
-	if (pcie->ops->post_init) {
+	if (pcie->cfg->ops->post_init) {
-		ret = pcie->ops->post_init(pcie);
+		ret = pcie->cfg->ops->post_init(pcie);
 		if (ret)
 			goto err_disable_phy;
 	}
 
 	qcom_ep_reset_deassert(pcie);
 
-	if (pcie->ops->config_sid) {
+	if (pcie->cfg->ops->config_sid) {
-		ret = pcie->ops->config_sid(pcie);
+		ret = pcie->cfg->ops->config_sid(pcie);
 		if (ret)
 			goto err;
 	}
@@ -1410,12 +1421,12 @@ static int qcom_pcie_host_init(struct pcie_port *pp)
 
 err:
 	qcom_ep_reset_assert(pcie);
-	if (pcie->ops->post_deinit)
+	if (pcie->cfg->ops->post_deinit)
-		pcie->ops->post_deinit(pcie);
+		pcie->cfg->ops->post_deinit(pcie);
 err_disable_phy:
 	phy_power_off(pcie->phy);
 err_deinit:
-	pcie->ops->deinit(pcie);
+	pcie->cfg->ops->deinit(pcie);
 
 	return ret;
 }
@@ -1509,14 +1520,33 @@ static const struct qcom_pcie_cfg ipq4019_cfg = {
 
 static const struct qcom_pcie_cfg sdm845_cfg = {
 	.ops = &ops_2_7_0,
+	.has_tbu_clk = true,
 };
 
 static const struct qcom_pcie_cfg sm8250_cfg = {
 	.ops = &ops_1_9_0,
+	.has_tbu_clk = true,
+	.has_ddrss_sf_tbu_clk = true,
+};
+
+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,
+};
+
+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,
 };
 
@@ -1559,8 +1589,7 @@ static int qcom_pcie_probe(struct platform_device *pdev)
 
 	pcie->pci = pci;
 
-	pcie->ops = pcie_cfg->ops;
+	pcie->cfg = pcie_cfg;
-	pcie->pipe_clk_need_muxing = pcie_cfg->pipe_clk_need_muxing;
 
 	pcie->reset = devm_gpiod_get_optional(dev, "perst", GPIOD_OUT_HIGH);
 	if (IS_ERR(pcie->reset)) {
@@ -1586,7 +1615,7 @@ static int qcom_pcie_probe(struct platform_device *pdev)
 		goto err_pm_runtime_put;
 	}
 
-	ret = pcie->ops->get_resources(pcie);
+	ret = pcie->cfg->ops->get_resources(pcie);
 	if (ret)
 		goto err_pm_runtime_put;
 
@@ -1628,13 +1657,15 @@ static const struct of_device_id qcom_pcie_match[] = {
 	{ .compatible = "qcom,pcie-sdm845", .data = &sdm845_cfg },
 	{ .compatible = "qcom,pcie-sm8250", .data = &sm8250_cfg },
 	{ .compatible = "qcom,pcie-sc8180x", .data = &sm8250_cfg },
+	{ .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 },
 	{ }
 };
 
 static void qcom_fixup_class(struct pci_dev *dev)
 {
-	dev->class = PCI_CLASS_BRIDGE_PCI << 8;
+	dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL;
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0101, qcom_fixup_class);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_QCOM, 0x0104, qcom_fixup_class);

drivers/pci/controller/dwc/pcie-uniphier-ep.c

@@ -10,6 +10,7 @@
 #include <linux/clk.h>
 #include <linux/delay.h>
 #include <linux/init.h>
+#include <linux/iopoll.h>
 #include <linux/of_device.h>
 #include <linux/pci.h>
 #include <linux/phy/phy.h>
@@ -31,6 +32,17 @@
 #define PCL_RSTCTRL2			0x0024
 #define PCL_RSTCTRL_PHY_RESET		BIT(0)
 
+#define PCL_PINCTRL0			0x002c
+#define PCL_PERST_PLDN_REGEN		BIT(12)
+#define PCL_PERST_NOE_REGEN		BIT(11)
+#define PCL_PERST_OUT_REGEN		BIT(8)
+#define PCL_PERST_PLDN_REGVAL		BIT(4)
+#define PCL_PERST_NOE_REGVAL		BIT(3)
+#define PCL_PERST_OUT_REGVAL		BIT(0)
+
+#define PCL_PIPEMON			0x0044
+#define PCL_PCLK_ALIVE			BIT(15)
+
 #define PCL_MODE			0x8000
 #define PCL_MODE_REGEN			BIT(8)
 #define PCL_MODE_REGVAL			BIT(0)
@@ -51,6 +63,9 @@
 #define PCL_APP_INTX			0x8074
 #define PCL_APP_INTX_SYS_INT		BIT(0)
 
+#define PCL_APP_PM0			0x8078
+#define PCL_SYS_AUX_PWR_DET		BIT(8)
+
 /* assertion time of INTx in usec */
 #define PCL_INTX_WIDTH_USEC		30
 
@@ -60,7 +75,14 @@ struct uniphier_pcie_ep_priv {
 	struct clk *clk, *clk_gio;
 	struct reset_control *rst, *rst_gio;
 	struct phy *phy;
-	const struct pci_epc_features *features;
+	const struct uniphier_pcie_ep_soc_data *data;
+};
+
+struct uniphier_pcie_ep_soc_data {
+	bool has_gio;
+	void (*init)(struct uniphier_pcie_ep_priv *priv);
+	int (*wait)(struct uniphier_pcie_ep_priv *priv);
+	const struct pci_epc_features features;
 };
 
 #define to_uniphier_pcie(x)	dev_get_drvdata((x)->dev)
@@ -91,7 +113,7 @@ static void uniphier_pcie_phy_reset(struct uniphier_pcie_ep_priv *priv,
 	writel(val, priv->base + PCL_RSTCTRL2);
 }
 
-static void uniphier_pcie_init_ep(struct uniphier_pcie_ep_priv *priv)
+static void uniphier_pcie_pro5_init_ep(struct uniphier_pcie_ep_priv *priv)
 {
 	u32 val;
 
@@ -116,6 +138,55 @@ static void uniphier_pcie_init_ep(struct uniphier_pcie_ep_priv *priv)
 	msleep(100);
 }
 
+static void uniphier_pcie_nx1_init_ep(struct uniphier_pcie_ep_priv *priv)
+{
+	u32 val;
+
+	/* set EP mode */
+	val = readl(priv->base + PCL_MODE);
+	val |= PCL_MODE_REGEN | PCL_MODE_REGVAL;
+	writel(val, priv->base + PCL_MODE);
+
+	/* use auxiliary power detection */
+	val = readl(priv->base + PCL_APP_PM0);
+	val |= PCL_SYS_AUX_PWR_DET;
+	writel(val, priv->base + PCL_APP_PM0);
+
+	/* assert PERST# */
+	val = readl(priv->base + PCL_PINCTRL0);
+	val &= ~(PCL_PERST_NOE_REGVAL | PCL_PERST_OUT_REGVAL
+		 | PCL_PERST_PLDN_REGVAL);
+	val |= PCL_PERST_NOE_REGEN | PCL_PERST_OUT_REGEN
+		| PCL_PERST_PLDN_REGEN;
+	writel(val, priv->base + PCL_PINCTRL0);
+
+	uniphier_pcie_ltssm_enable(priv, false);
+
+	usleep_range(100000, 200000);
+
+	/* deassert PERST# */
+	val = readl(priv->base + PCL_PINCTRL0);
+	val |= PCL_PERST_OUT_REGVAL | PCL_PERST_OUT_REGEN;
+	writel(val, priv->base + PCL_PINCTRL0);
+}
+
+static int uniphier_pcie_nx1_wait_ep(struct uniphier_pcie_ep_priv *priv)
+{
+	u32 status;
+	int ret;
+
+	/* wait PIPE clock */
+	ret = readl_poll_timeout(priv->base + PCL_PIPEMON, status,
+				 status & PCL_PCLK_ALIVE, 100000, 1000000);
+	if (ret) {
+		dev_err(priv->pci.dev,
+			"Failed to initialize controller in EP mode\n");
+		return ret;
+	}
+
+	return 0;
+}
+
 static int uniphier_pcie_start_link(struct dw_pcie *pci)
 {
 	struct uniphier_pcie_ep_priv *priv = to_uniphier_pcie(pci);
@@ -209,7 +280,7 @@ uniphier_pcie_get_features(struct dw_pcie_ep *ep)
 	struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
 	struct uniphier_pcie_ep_priv *priv = to_uniphier_pcie(pci);
 
-	return priv->features;
+	return &priv->data->features;
 }
 
 static const struct dw_pcie_ep_ops uniphier_pcie_ep_ops = {
@@ -238,7 +309,8 @@ static int uniphier_pcie_ep_enable(struct uniphier_pcie_ep_priv *priv)
 	if (ret)
 		goto out_rst_assert;
 
-	uniphier_pcie_init_ep(priv);
+	if (priv->data->init)
+		priv->data->init(priv);
 
 	uniphier_pcie_phy_reset(priv, true);
 
@@ -248,8 +320,16 @@ static int uniphier_pcie_ep_enable(struct uniphier_pcie_ep_priv *priv)
 
 	uniphier_pcie_phy_reset(priv, false);
 
+	if (priv->data->wait) {
+		ret = priv->data->wait(priv);
+		if (ret)
+			goto out_phy_exit;
+	}
+
 	return 0;
 
+out_phy_exit:
+	phy_exit(priv->phy);
 out_rst_gio_assert:
 	reset_control_assert(priv->rst_gio);
 out_rst_assert:
@@ -277,8 +357,8 @@ static int uniphier_pcie_ep_probe(struct platform_device *pdev)
 	if (!priv)
 		return -ENOMEM;
 
-	priv->features = of_device_get_match_data(dev);
+	priv->data = of_device_get_match_data(dev);
-	if (WARN_ON(!priv->features))
+	if (WARN_ON(!priv->data))
 		return -EINVAL;
 
 	priv->pci.dev = dev;
@@ -288,13 +368,15 @@ static int uniphier_pcie_ep_probe(struct platform_device *pdev)
 	if (IS_ERR(priv->base))
 		return PTR_ERR(priv->base);
 
-	priv->clk_gio = devm_clk_get(dev, "gio");
+	if (priv->data->has_gio) {
-	if (IS_ERR(priv->clk_gio))
+		priv->clk_gio = devm_clk_get(dev, "gio");
-		return PTR_ERR(priv->clk_gio);
+		if (IS_ERR(priv->clk_gio))
+			return PTR_ERR(priv->clk_gio);
 
-	priv->rst_gio = devm_reset_control_get_shared(dev, "gio");
+		priv->rst_gio = devm_reset_control_get_shared(dev, "gio");
-	if (IS_ERR(priv->rst_gio))
+		if (IS_ERR(priv->rst_gio))
-		return PTR_ERR(priv->rst_gio);
+			return PTR_ERR(priv->rst_gio);
+	}
 
 	priv->clk = devm_clk_get(dev, "link");
 	if (IS_ERR(priv->clk))
@@ -321,13 +403,31 @@ static int uniphier_pcie_ep_probe(struct platform_device *pdev)
 	return dw_pcie_ep_init(&priv->pci.ep);
 }
 
-static const struct pci_epc_features uniphier_pro5_data = {
+static const struct uniphier_pcie_ep_soc_data uniphier_pro5_data = {
-	.linkup_notifier = false,
+	.has_gio = true,
-	.msi_capable = true,
+	.init = uniphier_pcie_pro5_init_ep,
-	.msix_capable = false,
+	.wait = NULL,
-	.align = 1 << 16,
+	.features = {
-	.bar_fixed_64bit = BIT(BAR_0) | BIT(BAR_2) | BIT(BAR_4),
+		.linkup_notifier = false,
-	.reserved_bar =  BIT(BAR_4),
+		.msi_capable = true,
+		.msix_capable = false,
+		.align = 1 << 16,
+		.bar_fixed_64bit = BIT(BAR_0) | BIT(BAR_2) | BIT(BAR_4),
+		.reserved_bar =  BIT(BAR_4),
+	},
+};
+
+static const struct uniphier_pcie_ep_soc_data uniphier_nx1_data = {
+	.has_gio = false,
+	.init = uniphier_pcie_nx1_init_ep,
+	.wait = uniphier_pcie_nx1_wait_ep,
+	.features = {
+		.linkup_notifier = false,
+		.msi_capable = true,
+		.msix_capable = false,
+		.align = 1 << 12,
+		.bar_fixed_64bit = BIT(BAR_0) | BIT(BAR_2) | BIT(BAR_4),
+	},
 };
 
 static const struct of_device_id uniphier_pcie_ep_match[] = {
@@ -335,6 +435,10 @@ static const struct of_device_id uniphier_pcie_ep_match[] = {
 		.compatible = "socionext,uniphier-pro5-pcie-ep",
 		.data = &uniphier_pro5_data,
 	},
+	{
+		.compatible = "socionext,uniphier-nx1-pcie-ep",
+		.data = &uniphier_nx1_data,
+	},
 	{ /* sentinel */ },
 };
 

drivers/pci/controller/mobiveil/pcie-mobiveil-host.c

@@ -295,7 +295,7 @@ int mobiveil_host_init(struct mobiveil_pcie *pcie, bool reinit)
 	/* fixup for PCIe class register */
 	value = mobiveil_csr_readl(pcie, PAB_INTP_AXI_PIO_CLASS);
 	value &= 0xff;
-	value |= (PCI_CLASS_BRIDGE_PCI << 16);
+	value |= PCI_CLASS_BRIDGE_PCI_NORMAL << 8;
 	mobiveil_csr_writel(pcie, value, PAB_INTP_AXI_PIO_CLASS);
 
 	return 0;

drivers/pci/controller/pci-aardvark.c

@@ -38,10 +38,6 @@
 #define     PCIE_CORE_ERR_CAPCTL_ECRC_CHK_TX_EN			BIT(6)
 #define     PCIE_CORE_ERR_CAPCTL_ECRC_CHCK			BIT(7)
 #define     PCIE_CORE_ERR_CAPCTL_ECRC_CHCK_RCV			BIT(8)
-#define     PCIE_CORE_INT_A_ASSERT_ENABLE			1
-#define     PCIE_CORE_INT_B_ASSERT_ENABLE			2
-#define     PCIE_CORE_INT_C_ASSERT_ENABLE			3
-#define     PCIE_CORE_INT_D_ASSERT_ENABLE			4
 /* PIO registers base address and register offsets */
 #define PIO_BASE_ADDR				0x4000
 #define PIO_CTRL				(PIO_BASE_ADDR + 0x0)
@@ -102,6 +98,10 @@
 #define PCIE_MSG_PM_PME_MASK			BIT(7)
 #define PCIE_ISR0_MASK_REG			(CONTROL_BASE_ADDR + 0x44)
 #define     PCIE_ISR0_MSI_INT_PENDING		BIT(24)
+#define     PCIE_ISR0_CORR_ERR			BIT(11)
+#define     PCIE_ISR0_NFAT_ERR			BIT(12)
+#define     PCIE_ISR0_FAT_ERR			BIT(13)
+#define     PCIE_ISR0_ERR_MASK			GENMASK(13, 11)
 #define     PCIE_ISR0_INTX_ASSERT(val)		BIT(16 + (val))
 #define     PCIE_ISR0_INTX_DEASSERT(val)	BIT(20 + (val))
 #define     PCIE_ISR0_ALL_MASK			GENMASK(31, 0)
@@ -272,17 +272,16 @@ struct advk_pcie {
 		u32 actions;
 	} wins[OB_WIN_COUNT];
 	u8 wins_count;
+	int irq;
+	struct irq_domain *rp_irq_domain;
 	struct irq_domain *irq_domain;
 	struct irq_chip irq_chip;
 	raw_spinlock_t irq_lock;
 	struct irq_domain *msi_domain;
 	struct irq_domain *msi_inner_domain;
-	struct irq_chip msi_bottom_irq_chip;
+	raw_spinlock_t msi_irq_lock;
-	struct irq_chip msi_irq_chip;
-	struct msi_domain_info msi_domain_info;
 	DECLARE_BITMAP(msi_used, MSI_IRQ_NUM);
 	struct mutex msi_used_lock;
-	u16 msi_msg;
 	int link_gen;
 	struct pci_bridge_emul bridge;
 	struct gpio_desc *reset_gpio;
@@ -477,6 +476,7 @@ static void advk_pcie_disable_ob_win(struct advk_pcie *pcie, u8 win_num)
 
 static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 {
+	phys_addr_t msi_addr;
 	u32 reg;
 	int i;
 
@@ -529,7 +529,7 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 	 */
 	reg = advk_readl(pcie, PCIE_CORE_DEV_REV_REG);
 	reg &= ~0xffffff00;
-	reg |= (PCI_CLASS_BRIDGE_PCI << 8) << 8;
+	reg |= PCI_CLASS_BRIDGE_PCI_NORMAL << 8;
 	advk_writel(pcie, reg, PCIE_CORE_DEV_REV_REG);
 
 	/* Disable Root Bridge I/O space, memory space and bus mastering */
@@ -565,6 +565,11 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 	reg |= LANE_COUNT_1;
 	advk_writel(pcie, reg, PCIE_CORE_CTRL0_REG);
 
+	/* Set MSI address */
+	msi_addr = virt_to_phys(pcie);
+	advk_writel(pcie, lower_32_bits(msi_addr), PCIE_MSI_ADDR_LOW_REG);
+	advk_writel(pcie, upper_32_bits(msi_addr), PCIE_MSI_ADDR_HIGH_REG);
+
 	/* Enable MSI */
 	reg = advk_readl(pcie, PCIE_CORE_CTRL2_REG);
 	reg |= PCIE_CORE_CTRL2_MSI_ENABLE;
@@ -576,15 +581,20 @@ static void advk_pcie_setup_hw(struct advk_pcie *pcie)
 	advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_REG);
 	advk_writel(pcie, PCIE_IRQ_ALL_MASK, HOST_CTRL_INT_STATUS_REG);
 
-	/* Disable All ISR0/1 Sources */
+	/* Disable All ISR0/1 and MSI Sources */
-	reg = PCIE_ISR0_ALL_MASK;
+	advk_writel(pcie, PCIE_ISR0_ALL_MASK, PCIE_ISR0_MASK_REG);
+	advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_MASK_REG);
+	advk_writel(pcie, PCIE_MSI_ALL_MASK, PCIE_MSI_MASK_REG);
+
+	/* Unmask summary MSI interrupt */
+	reg = advk_readl(pcie, PCIE_ISR0_MASK_REG);
 	reg &= ~PCIE_ISR0_MSI_INT_PENDING;
 	advk_writel(pcie, reg, PCIE_ISR0_MASK_REG);
 
-	advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_MASK_REG);
+	/* Unmask PME interrupt for processing of PME requester */
-
+	reg = advk_readl(pcie, PCIE_ISR0_MASK_REG);
-	/* Unmask all MSIs */
+	reg &= ~PCIE_MSG_PM_PME_MASK;
-	advk_writel(pcie, ~(u32)PCIE_MSI_ALL_MASK, PCIE_MSI_MASK_REG);
+	advk_writel(pcie, reg, PCIE_ISR0_MASK_REG);
 
 	/* Enable summary interrupt for GIC SPI source */
 	reg = PCIE_IRQ_ALL_MASK & (~PCIE_IRQ_ENABLE_INTS_MASK);
@@ -778,11 +788,15 @@ advk_pci_bridge_emul_base_conf_read(struct pci_bridge_emul *bridge,
 	case PCI_INTERRUPT_LINE: {
 		/*
 		 * From the whole 32bit register we support reading from HW only
-		 * one bit: PCI_BRIDGE_CTL_BUS_RESET.
+		 * two bits: PCI_BRIDGE_CTL_BUS_RESET and PCI_BRIDGE_CTL_SERR.
 		 * Other bits are retrieved only from emulated config buffer.
 		 */
 		__le32 *cfgspace = (__le32 *)&bridge->conf;
 		u32 val = le32_to_cpu(cfgspace[PCI_INTERRUPT_LINE / 4]);
+		if (advk_readl(pcie, PCIE_ISR0_MASK_REG) & PCIE_ISR0_ERR_MASK)
+			val &= ~(PCI_BRIDGE_CTL_SERR << 16);
+		else
+			val |= PCI_BRIDGE_CTL_SERR << 16;
 		if (advk_readl(pcie, PCIE_CORE_CTRL1_REG) & HOT_RESET_GEN)
 			val |= PCI_BRIDGE_CTL_BUS_RESET << 16;
 		else
@@ -808,6 +822,19 @@ advk_pci_bridge_emul_base_conf_write(struct pci_bridge_emul *bridge,
 		break;
 
 	case PCI_INTERRUPT_LINE:
+		/*
+		 * According to Figure 6-3: Pseudo Logic Diagram for Error
+		 * Message Controls in PCIe base specification, SERR# Enable bit
+		 * in Bridge Control register enable receiving of ERR_* messages
+		 */
+		if (mask & (PCI_BRIDGE_CTL_SERR << 16)) {
+			u32 val = advk_readl(pcie, PCIE_ISR0_MASK_REG);
+			if (new & (PCI_BRIDGE_CTL_SERR << 16))
+				val &= ~PCIE_ISR0_ERR_MASK;
+			else
+				val |= PCIE_ISR0_ERR_MASK;
+			advk_writel(pcie, val, PCIE_ISR0_MASK_REG);
+		}
 		if (mask & (PCI_BRIDGE_CTL_BUS_RESET << 16)) {
 			u32 val = advk_readl(pcie, PCIE_CORE_CTRL1_REG);
 			if (new & (PCI_BRIDGE_CTL_BUS_RESET << 16))
@@ -835,20 +862,11 @@ advk_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge,
 		*value = PCI_EXP_SLTSTA_PDS << 16;
 		return PCI_BRIDGE_EMUL_HANDLED;
 
-	case PCI_EXP_RTCTL: {
+	/*
-		u32 val = advk_readl(pcie, PCIE_ISR0_MASK_REG);
+	 * PCI_EXP_RTCTL and PCI_EXP_RTSTA are also supported, but do not need
-		*value = (val & PCIE_MSG_PM_PME_MASK) ? 0 : PCI_EXP_RTCTL_PMEIE;
+	 * to be handled here, because their values are stored in emulated
-		*value |= le16_to_cpu(bridge->pcie_conf.rootctl) & PCI_EXP_RTCTL_CRSSVE;
+	 * config space buffer, and we read them from there when needed.
-		*value |= PCI_EXP_RTCAP_CRSVIS << 16;
+	 */
-		return PCI_BRIDGE_EMUL_HANDLED;
-	}
-
-	case PCI_EXP_RTSTA: {
-		u32 isr0 = advk_readl(pcie, PCIE_ISR0_REG);
-		u32 msglog = advk_readl(pcie, PCIE_MSG_LOG_REG);
-		*value = (isr0 & PCIE_MSG_PM_PME_MASK) << 16 | (msglog >> 16);
-		return PCI_BRIDGE_EMUL_HANDLED;
-	}
 
 	case PCI_EXP_LNKCAP: {
 		u32 val = advk_readl(pcie, PCIE_CORE_PCIEXP_CAP + reg);
@@ -903,19 +921,18 @@ advk_pci_bridge_emul_pcie_conf_write(struct pci_bridge_emul *bridge,
 		break;
 
 	case PCI_EXP_RTCTL: {
-		/* Only mask/unmask PME interrupt */
+		u16 rootctl = le16_to_cpu(bridge->pcie_conf.rootctl);
-		u32 val = advk_readl(pcie, PCIE_ISR0_MASK_REG) &
+		/* Only emulation of PMEIE and CRSSVE bits is provided */
-			~PCIE_MSG_PM_PME_MASK;
+		rootctl &= PCI_EXP_RTCTL_PMEIE | PCI_EXP_RTCTL_CRSSVE;
-		if ((new & PCI_EXP_RTCTL_PMEIE) == 0)
+		bridge->pcie_conf.rootctl = cpu_to_le16(rootctl);
-			val |= PCIE_MSG_PM_PME_MASK;
-		advk_writel(pcie, val, PCIE_ISR0_MASK_REG);
 		break;
 	}
 
-	case PCI_EXP_RTSTA:
+	/*
-		new = (new & PCI_EXP_RTSTA_PME) >> 9;
+	 * PCI_EXP_RTSTA is also supported, but does not need to be handled
-		advk_writel(pcie, new, PCIE_ISR0_REG);
+	 * here, because its value is stored in emulated config space buffer,
-		break;
+	 * and we write it there when needed.
+	 */
 
 	case PCI_EXP_DEVCTL:
 	case PCI_EXP_DEVCTL2:
@@ -928,7 +945,7 @@ advk_pci_bridge_emul_pcie_conf_write(struct pci_bridge_emul *bridge,
 	}
 }
 
-static struct pci_bridge_emul_ops advk_pci_bridge_emul_ops = {
+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,
@@ -959,7 +976,7 @@ static int advk_sw_pci_bridge_init(struct advk_pcie *pcie)
 	bridge->conf.pref_mem_limit = cpu_to_le16(PCI_PREF_RANGE_TYPE_64);
 
 	/* Support interrupt A for MSI feature */
-	bridge->conf.intpin = PCIE_CORE_INT_A_ASSERT_ENABLE;
+	bridge->conf.intpin = PCI_INTERRUPT_INTA;
 
 	/* Aardvark HW provides PCIe Capability structure in version 2 */
 	bridge->pcie_conf.cap = cpu_to_le16(2);
@@ -981,8 +998,12 @@ static bool advk_pcie_valid_device(struct advk_pcie *pcie, struct pci_bus *bus,
 		return false;
 
 	/*
-	 * If the link goes down after we check for link-up, nothing bad
+	 * If the link goes down after we check for link-up, we have a problem:
-	 * happens but the config access times out.
+	 * if a PIO request is executed while link-down, the whole controller
+	 * gets stuck in a non-functional state, and even after link comes up
+	 * again, PIO requests won't work anymore, and a reset of the whole PCIe
+	 * controller is needed. Therefore we need to prevent sending PIO
+	 * requests while the link is down.
 	 */
 	if (!pci_is_root_bus(bus) && !advk_pcie_link_up(pcie))
 		return false;
@@ -1180,11 +1201,11 @@ static void advk_msi_irq_compose_msi_msg(struct irq_data *data,
 					 struct msi_msg *msg)
 {
 	struct advk_pcie *pcie = irq_data_get_irq_chip_data(data);
-	phys_addr_t msi_msg = virt_to_phys(&pcie->msi_msg);
+	phys_addr_t msi_addr = virt_to_phys(pcie);
 
-	msg->address_lo = lower_32_bits(msi_msg);
+	msg->address_lo = lower_32_bits(msi_addr);
-	msg->address_hi = upper_32_bits(msi_msg);
+	msg->address_hi = upper_32_bits(msi_addr);
-	msg->data = data->irq;
+	msg->data = data->hwirq;
 }
 
 static int advk_msi_set_affinity(struct irq_data *irq_data,
@@ -1193,6 +1214,54 @@ static int advk_msi_set_affinity(struct irq_data *irq_data,
 	return -EINVAL;
 }
 
+static void advk_msi_irq_mask(struct irq_data *d)
+{
+	struct advk_pcie *pcie = d->domain->host_data;
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
+	unsigned long flags;
+	u32 mask;
+
+	raw_spin_lock_irqsave(&pcie->msi_irq_lock, flags);
+	mask = advk_readl(pcie, PCIE_MSI_MASK_REG);
+	mask |= BIT(hwirq);
+	advk_writel(pcie, mask, PCIE_MSI_MASK_REG);
+	raw_spin_unlock_irqrestore(&pcie->msi_irq_lock, flags);
+}
+
+static void advk_msi_irq_unmask(struct irq_data *d)
+{
+	struct advk_pcie *pcie = d->domain->host_data;
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
+	unsigned long flags;
+	u32 mask;
+
+	raw_spin_lock_irqsave(&pcie->msi_irq_lock, flags);
+	mask = advk_readl(pcie, PCIE_MSI_MASK_REG);
+	mask &= ~BIT(hwirq);
+	advk_writel(pcie, mask, PCIE_MSI_MASK_REG);
+	raw_spin_unlock_irqrestore(&pcie->msi_irq_lock, flags);
+}
+
+static void advk_msi_top_irq_mask(struct irq_data *d)
+{
+	pci_msi_mask_irq(d);
+	irq_chip_mask_parent(d);
+}
+
+static void advk_msi_top_irq_unmask(struct irq_data *d)
+{
+	pci_msi_unmask_irq(d);
+	irq_chip_unmask_parent(d);
+}
+
+static struct irq_chip advk_msi_bottom_irq_chip = {
+	.name			= "MSI",
+	.irq_compose_msi_msg	= advk_msi_irq_compose_msi_msg,
+	.irq_set_affinity	= advk_msi_set_affinity,
+	.irq_mask		= advk_msi_irq_mask,
+	.irq_unmask		= advk_msi_irq_unmask,
+};
+
 static int advk_msi_irq_domain_alloc(struct irq_domain *domain,
 				     unsigned int virq,
 				     unsigned int nr_irqs, void *args)
@@ -1201,19 +1270,15 @@ static int advk_msi_irq_domain_alloc(struct irq_domain *domain,
 	int hwirq, i;
 
 	mutex_lock(&pcie->msi_used_lock);
-	hwirq = bitmap_find_next_zero_area(pcie->msi_used, MSI_IRQ_NUM,
+	hwirq = bitmap_find_free_region(pcie->msi_used, MSI_IRQ_NUM,
-					   0, nr_irqs, 0);
+					order_base_2(nr_irqs));
-	if (hwirq >= MSI_IRQ_NUM) {
-		mutex_unlock(&pcie->msi_used_lock);
-		return -ENOSPC;
-	}
-
-	bitmap_set(pcie->msi_used, hwirq, nr_irqs);
 	mutex_unlock(&pcie->msi_used_lock);
+	if (hwirq < 0)
+		return -ENOSPC;
 
 	for (i = 0; i < nr_irqs; i++)
 		irq_domain_set_info(domain, virq + i, hwirq + i,
-				    &pcie->msi_bottom_irq_chip,
+				    &advk_msi_bottom_irq_chip,
 				    domain->host_data, handle_simple_irq,
 				    NULL, NULL);
 
@@ -1227,7 +1292,7 @@ static void advk_msi_irq_domain_free(struct irq_domain *domain,
 	struct advk_pcie *pcie = domain->host_data;
 
 	mutex_lock(&pcie->msi_used_lock);
-	bitmap_clear(pcie->msi_used, d->hwirq, nr_irqs);
+	bitmap_release_region(pcie->msi_used, d->hwirq, order_base_2(nr_irqs));
 	mutex_unlock(&pcie->msi_used_lock);
 }
 
@@ -1269,7 +1334,6 @@ static int advk_pcie_irq_map(struct irq_domain *h,
 {
 	struct advk_pcie *pcie = h->host_data;
 
-	advk_pcie_irq_mask(irq_get_irq_data(virq));
 	irq_set_status_flags(virq, IRQ_LEVEL);
 	irq_set_chip_and_handler(virq, &pcie->irq_chip,
 				 handle_level_irq);
@@ -1283,37 +1347,25 @@ static const struct irq_domain_ops advk_pcie_irq_domain_ops = {
 	.xlate = irq_domain_xlate_onecell,
 };
 
+static struct irq_chip advk_msi_irq_chip = {
+	.name		= "advk-MSI",
+	.irq_mask	= advk_msi_top_irq_mask,
+	.irq_unmask	= advk_msi_top_irq_unmask,
+};
+
+static struct msi_domain_info advk_msi_domain_info = {
+	.flags	= MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
+		  MSI_FLAG_MULTI_PCI_MSI | MSI_FLAG_PCI_MSIX,
+	.chip	= &advk_msi_irq_chip,
+};
+
 static int advk_pcie_init_msi_irq_domain(struct advk_pcie *pcie)
 {
 	struct device *dev = &pcie->pdev->dev;
-	struct device_node *node = dev->of_node;
-	struct irq_chip *bottom_ic, *msi_ic;
-	struct msi_domain_info *msi_di;
-	phys_addr_t msi_msg_phys;
 
+	raw_spin_lock_init(&pcie->msi_irq_lock);
 	mutex_init(&pcie->msi_used_lock);
 
-	bottom_ic = &pcie->msi_bottom_irq_chip;
-
-	bottom_ic->name = "MSI";
-	bottom_ic->irq_compose_msi_msg = advk_msi_irq_compose_msi_msg;
-	bottom_ic->irq_set_affinity = advk_msi_set_affinity;
-
-	msi_ic = &pcie->msi_irq_chip;
-	msi_ic->name = "advk-MSI";
-
-	msi_di = &pcie->msi_domain_info;
-	msi_di->flags = MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
-		MSI_FLAG_MULTI_PCI_MSI;
-	msi_di->chip = msi_ic;
-
-	msi_msg_phys = virt_to_phys(&pcie->msi_msg);
-
-	advk_writel(pcie, lower_32_bits(msi_msg_phys),
-		    PCIE_MSI_ADDR_LOW_REG);
-	advk_writel(pcie, upper_32_bits(msi_msg_phys),
-		    PCIE_MSI_ADDR_HIGH_REG);
-
 	pcie->msi_inner_domain =
 		irq_domain_add_linear(NULL, MSI_IRQ_NUM,
 				      &advk_msi_domain_ops, pcie);
@@ -1321,8 +1373,9 @@ static int advk_pcie_init_msi_irq_domain(struct advk_pcie *pcie)
 		return -ENOMEM;
 
 	pcie->msi_domain =
-		pci_msi_create_irq_domain(of_node_to_fwnode(node),
+		pci_msi_create_irq_domain(dev_fwnode(dev),
-					  msi_di, pcie->msi_inner_domain);
+					  &advk_msi_domain_info,
+					  pcie->msi_inner_domain);
 	if (!pcie->msi_domain) {
 		irq_domain_remove(pcie->msi_inner_domain);
 		return -ENOMEM;
@@ -1363,7 +1416,6 @@ static int advk_pcie_init_irq_domain(struct advk_pcie *pcie)
 	}
 
 	irq_chip->irq_mask = advk_pcie_irq_mask;
-	irq_chip->irq_mask_ack = advk_pcie_irq_mask;
 	irq_chip->irq_unmask = advk_pcie_irq_unmask;
 
 	pcie->irq_domain =
@@ -1385,10 +1437,73 @@ static void advk_pcie_remove_irq_domain(struct advk_pcie *pcie)
 	irq_domain_remove(pcie->irq_domain);
 }
 
+static struct irq_chip advk_rp_irq_chip = {
+	.name = "advk-RP",
+};
+
+static int advk_pcie_rp_irq_map(struct irq_domain *h,
+				unsigned int virq, irq_hw_number_t hwirq)
+{
+	struct advk_pcie *pcie = h->host_data;
+
+	irq_set_chip_and_handler(virq, &advk_rp_irq_chip, handle_simple_irq);
+	irq_set_chip_data(virq, pcie);
+
+	return 0;
+}
+
+static const struct irq_domain_ops advk_pcie_rp_irq_domain_ops = {
+	.map = advk_pcie_rp_irq_map,
+	.xlate = irq_domain_xlate_onecell,
+};
+
+static int advk_pcie_init_rp_irq_domain(struct advk_pcie *pcie)
+{
+	pcie->rp_irq_domain = irq_domain_add_linear(NULL, 1,
+						    &advk_pcie_rp_irq_domain_ops,
+						    pcie);
+	if (!pcie->rp_irq_domain) {
+		dev_err(&pcie->pdev->dev, "Failed to add Root Port IRQ domain\n");
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void advk_pcie_remove_rp_irq_domain(struct advk_pcie *pcie)
+{
+	irq_domain_remove(pcie->rp_irq_domain);
+}
+
+static void advk_pcie_handle_pme(struct advk_pcie *pcie)
+{
+	u32 requester = advk_readl(pcie, PCIE_MSG_LOG_REG) >> 16;
+
+	advk_writel(pcie, PCIE_MSG_PM_PME_MASK, PCIE_ISR0_REG);
+
+	/*
+	 * PCIE_MSG_LOG_REG contains the last inbound message, so store
+	 * the requester ID only when PME was not asserted yet.
+	 * Also do not trigger PME interrupt when PME is still asserted.
+	 */
+	if (!(le32_to_cpu(pcie->bridge.pcie_conf.rootsta) & PCI_EXP_RTSTA_PME)) {
+		pcie->bridge.pcie_conf.rootsta = cpu_to_le32(requester | PCI_EXP_RTSTA_PME);
+
+		/*
+		 * Trigger PME interrupt only if PMEIE bit in Root Control is set.
+		 * Aardvark HW returns zero for PCI_EXP_FLAGS_IRQ, so use PCIe interrupt 0.
+		 */
+		if (!(le16_to_cpu(pcie->bridge.pcie_conf.rootctl) & PCI_EXP_RTCTL_PMEIE))
+			return;
+
+		if (generic_handle_domain_irq(pcie->rp_irq_domain, 0) == -EINVAL)
+			dev_err_ratelimited(&pcie->pdev->dev, "unhandled PME IRQ\n");
+	}
+}
+
 static void advk_pcie_handle_msi(struct advk_pcie *pcie)
 {
 	u32 msi_val, msi_mask, msi_status, msi_idx;
-	u16 msi_data;
 
 	msi_mask = advk_readl(pcie, PCIE_MSI_MASK_REG);
 	msi_val = advk_readl(pcie, PCIE_MSI_STATUS_REG);
@@ -1398,13 +1513,9 @@ static void advk_pcie_handle_msi(struct advk_pcie *pcie)
 		if (!(BIT(msi_idx) & msi_status))
 			continue;
 
-		/*
-		 * msi_idx contains bits [4:0] of the msi_data and msi_data
-		 * contains 16bit MSI interrupt number
-		 */
 		advk_writel(pcie, BIT(msi_idx), PCIE_MSI_STATUS_REG);
-		msi_data = advk_readl(pcie, PCIE_MSI_PAYLOAD_REG) & PCIE_MSI_DATA_MASK;
+		if (generic_handle_domain_irq(pcie->msi_inner_domain, msi_idx) == -EINVAL)
-		generic_handle_irq(msi_data);
+			dev_err_ratelimited(&pcie->pdev->dev, "unexpected MSI 0x%02x\n", msi_idx);
 	}
 
 	advk_writel(pcie, PCIE_ISR0_MSI_INT_PENDING,
@@ -1425,6 +1536,22 @@ static void advk_pcie_handle_int(struct advk_pcie *pcie)
 	isr1_mask = advk_readl(pcie, PCIE_ISR1_MASK_REG);
 	isr1_status = isr1_val & ((~isr1_mask) & PCIE_ISR1_ALL_MASK);
 
+	/* Process PME interrupt as the first one to do not miss PME requester id */
+	if (isr0_status & PCIE_MSG_PM_PME_MASK)
+		advk_pcie_handle_pme(pcie);
+
+	/* Process ERR interrupt */
+	if (isr0_status & PCIE_ISR0_ERR_MASK) {
+		advk_writel(pcie, PCIE_ISR0_ERR_MASK, PCIE_ISR0_REG);
+
+		/*
+		 * Aardvark HW returns zero for PCI_ERR_ROOT_AER_IRQ, so use
+		 * PCIe interrupt 0
+		 */
+		if (generic_handle_domain_irq(pcie->rp_irq_domain, 0) == -EINVAL)
+			dev_err_ratelimited(&pcie->pdev->dev, "unhandled ERR IRQ\n");
+	}
+
 	/* Process MSI interrupts */
 	if (isr0_status & PCIE_ISR0_MSI_INT_PENDING)
 		advk_pcie_handle_msi(pcie);
@@ -1437,28 +1564,50 @@ static void advk_pcie_handle_int(struct advk_pcie *pcie)
 		advk_writel(pcie, PCIE_ISR1_INTX_ASSERT(i),
 			    PCIE_ISR1_REG);
 
-		generic_handle_domain_irq(pcie->irq_domain, i);
+		if (generic_handle_domain_irq(pcie->irq_domain, i) == -EINVAL)
+			dev_err_ratelimited(&pcie->pdev->dev, "unexpected INT%c IRQ\n",
+					    (char)i + 'A');
 	}
 }
 
-static irqreturn_t advk_pcie_irq_handler(int irq, void *arg)
+static void advk_pcie_irq_handler(struct irq_desc *desc)
 {
-	struct advk_pcie *pcie = arg;
+	struct advk_pcie *pcie = irq_desc_get_handler_data(desc);
-	u32 status;
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	u32 val, mask, status;
 
-	status = advk_readl(pcie, HOST_CTRL_INT_STATUS_REG);
+	chained_irq_enter(chip, desc);
-	if (!(status & PCIE_IRQ_CORE_INT))
-		return IRQ_NONE;
 
-	advk_pcie_handle_int(pcie);
+	val = advk_readl(pcie, HOST_CTRL_INT_STATUS_REG);
+	mask = advk_readl(pcie, HOST_CTRL_INT_MASK_REG);
+	status = val & ((~mask) & PCIE_IRQ_ALL_MASK);
 
-	/* Clear interrupt */
+	if (status & PCIE_IRQ_CORE_INT) {
-	advk_writel(pcie, PCIE_IRQ_CORE_INT, HOST_CTRL_INT_STATUS_REG);
+		advk_pcie_handle_int(pcie);
 
-	return IRQ_HANDLED;
+		/* Clear interrupt */
+		advk_writel(pcie, PCIE_IRQ_CORE_INT, HOST_CTRL_INT_STATUS_REG);
+	}
+
+	chained_irq_exit(chip, desc);
 }
 
-static void __maybe_unused advk_pcie_disable_phy(struct advk_pcie *pcie)
+static int advk_pcie_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
+{
+	struct advk_pcie *pcie = dev->bus->sysdata;
+
+	/*
+	 * Emulated root bridge has its own emulated irq chip and irq domain.
+	 * Argument pin is the INTx pin (1=INTA, 2=INTB, 3=INTC, 4=INTD) and
+	 * hwirq for irq_create_mapping() is indexed from zero.
+	 */
+	if (pci_is_root_bus(dev->bus))
+		return irq_create_mapping(pcie->rp_irq_domain, pin - 1);
+	else
+		return of_irq_parse_and_map_pci(dev, slot, pin);
+}
+
+static void advk_pcie_disable_phy(struct advk_pcie *pcie)
 {
 	phy_power_off(pcie->phy);
 	phy_exit(pcie->phy);
@@ -1522,7 +1671,7 @@ static int advk_pcie_probe(struct platform_device *pdev)
 	struct advk_pcie *pcie;
 	struct pci_host_bridge *bridge;
 	struct resource_entry *entry;
-	int ret, irq;
+	int ret;
 
 	bridge = devm_pci_alloc_host_bridge(dev, sizeof(struct advk_pcie));
 	if (!bridge)
@@ -1608,17 +1757,9 @@ static int advk_pcie_probe(struct platform_device *pdev)
 	if (IS_ERR(pcie->base))
 		return PTR_ERR(pcie->base);
 
-	irq = platform_get_irq(pdev, 0);
+	pcie->irq = platform_get_irq(pdev, 0);
-	if (irq < 0)
+	if (pcie->irq < 0)
-		return irq;
+		return pcie->irq;
-
-	ret = devm_request_irq(dev, irq, advk_pcie_irq_handler,
-			       IRQF_SHARED | IRQF_NO_THREAD, "advk-pcie",
-			       pcie);
-	if (ret) {
-		dev_err(dev, "Failed to register interrupt\n");
-		return ret;
-	}
 
 	pcie->reset_gpio = devm_gpiod_get_from_of_node(dev, dev->of_node,
 						       "reset-gpios", 0,
@@ -1667,11 +1808,24 @@ static int advk_pcie_probe(struct platform_device *pdev)
 		return ret;
 	}
 
+	ret = advk_pcie_init_rp_irq_domain(pcie);
+	if (ret) {
+		dev_err(dev, "Failed to initialize irq\n");
+		advk_pcie_remove_msi_irq_domain(pcie);
+		advk_pcie_remove_irq_domain(pcie);
+		return ret;
+	}
+
+	irq_set_chained_handler_and_data(pcie->irq, advk_pcie_irq_handler, pcie);
+
 	bridge->sysdata = pcie;
 	bridge->ops = &advk_pcie_ops;
+	bridge->map_irq = advk_pcie_map_irq;
 
 	ret = pci_host_probe(bridge);
 	if (ret < 0) {
+		irq_set_chained_handler_and_data(pcie->irq, NULL, NULL);
+		advk_pcie_remove_rp_irq_domain(pcie);
 		advk_pcie_remove_msi_irq_domain(pcie);
 		advk_pcie_remove_irq_domain(pcie);
 		return ret;
@@ -1719,7 +1873,11 @@ static int advk_pcie_remove(struct platform_device *pdev)
 	advk_writel(pcie, PCIE_ISR1_ALL_MASK, PCIE_ISR1_REG);
 	advk_writel(pcie, PCIE_IRQ_ALL_MASK, HOST_CTRL_INT_STATUS_REG);
 
+	/* Remove IRQ handler */
+	irq_set_chained_handler_and_data(pcie->irq, NULL, NULL);
+
 	/* Remove IRQ domains */
+	advk_pcie_remove_rp_irq_domain(pcie);
 	advk_pcie_remove_msi_irq_domain(pcie);
 	advk_pcie_remove_irq_domain(pcie);
 

drivers/pci/controller/pci-hyperv.c

@@ -616,6 +616,121 @@ static int hv_msi_prepare(struct irq_domain *domain, struct device *dev,
 {
 	return pci_msi_prepare(domain, dev, nvec, info);
 }
+
+/**
+ * hv_arch_irq_unmask() - "Unmask" the IRQ by setting its current
+ * affinity.
+ * @data:	Describes the IRQ
+ *
+ * Build new a destination for the MSI and make a hypercall to
+ * update the Interrupt Redirection Table. "Device Logical ID"
+ * is built out of this PCI bus's instance GUID and the function
+ * number of the device.
+ */
+static void hv_arch_irq_unmask(struct irq_data *data)
+{
+	struct msi_desc *msi_desc = irq_data_get_msi_desc(data);
+	struct hv_retarget_device_interrupt *params;
+	struct hv_pcibus_device *hbus;
+	struct cpumask *dest;
+	cpumask_var_t tmp;
+	struct pci_bus *pbus;
+	struct pci_dev *pdev;
+	unsigned long flags;
+	u32 var_size = 0;
+	int cpu, nr_bank;
+	u64 res;
+
+	dest = irq_data_get_effective_affinity_mask(data);
+	pdev = msi_desc_to_pci_dev(msi_desc);
+	pbus = pdev->bus;
+	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
+
+	spin_lock_irqsave(&hbus->retarget_msi_interrupt_lock, flags);
+
+	params = &hbus->retarget_msi_interrupt_params;
+	memset(params, 0, sizeof(*params));
+	params->partition_id = HV_PARTITION_ID_SELF;
+	params->int_entry.source = HV_INTERRUPT_SOURCE_MSI;
+	hv_set_msi_entry_from_desc(&params->int_entry.msi_entry, msi_desc);
+	params->device_id = (hbus->hdev->dev_instance.b[5] << 24) |
+			   (hbus->hdev->dev_instance.b[4] << 16) |
+			   (hbus->hdev->dev_instance.b[7] << 8) |
+			   (hbus->hdev->dev_instance.b[6] & 0xf8) |
+			   PCI_FUNC(pdev->devfn);
+	params->int_target.vector = hv_msi_get_int_vector(data);
+
+	/*
+	 * Honoring apic->delivery_mode set to APIC_DELIVERY_MODE_FIXED by
+	 * setting the HV_DEVICE_INTERRUPT_TARGET_MULTICAST flag results in a
+	 * spurious interrupt storm. Not doing so does not seem to have a
+	 * negative effect (yet?).
+	 */
+
+	if (hbus->protocol_version >= PCI_PROTOCOL_VERSION_1_2) {
+		/*
+		 * PCI_PROTOCOL_VERSION_1_2 supports the VP_SET version of the
+		 * HVCALL_RETARGET_INTERRUPT hypercall, which also coincides
+		 * with >64 VP support.
+		 * ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED
+		 * is not sufficient for this hypercall.
+		 */
+		params->int_target.flags |=
+			HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET;
+
+		if (!alloc_cpumask_var(&tmp, GFP_ATOMIC)) {
+			res = 1;
+			goto exit_unlock;
+		}
+
+		cpumask_and(tmp, dest, cpu_online_mask);
+		nr_bank = cpumask_to_vpset(&params->int_target.vp_set, tmp);
+		free_cpumask_var(tmp);
+
+		if (nr_bank <= 0) {
+			res = 1;
+			goto exit_unlock;
+		}
+
+		/*
+		 * var-sized hypercall, var-size starts after vp_mask (thus
+		 * vp_set.format does not count, but vp_set.valid_bank_mask
+		 * does).
+		 */
+		var_size = 1 + nr_bank;
+	} else {
+		for_each_cpu_and(cpu, dest, cpu_online_mask) {
+			params->int_target.vp_mask |=
+				(1ULL << hv_cpu_number_to_vp_number(cpu));
+		}
+	}
+
+	res = hv_do_hypercall(HVCALL_RETARGET_INTERRUPT | (var_size << 17),
+			      params, NULL);
+
+exit_unlock:
+	spin_unlock_irqrestore(&hbus->retarget_msi_interrupt_lock, flags);
+
+	/*
+	 * During hibernation, when a CPU is offlined, the kernel tries
+	 * to move the interrupt to the remaining CPUs that haven't
+	 * been offlined yet. In this case, the below hv_do_hypercall()
+	 * always fails since the vmbus channel has been closed:
+	 * refer to cpu_disable_common() -> fixup_irqs() ->
+	 * irq_migrate_all_off_this_cpu() -> migrate_one_irq().
+	 *
+	 * Suppress the error message for hibernation because the failure
+	 * during hibernation does not matter (at this time all the devices
+	 * have been frozen). Note: the correct affinity info is still updated
+	 * into the irqdata data structure in migrate_one_irq() ->
+	 * irq_do_set_affinity() -> hv_set_affinity(), so later when the VM
+	 * resumes, hv_pci_restore_msi_state() is able to correctly restore
+	 * the interrupt with the correct affinity.
+	 */
+	if (!hv_result_success(res) && hbus->state != hv_pcibus_removing)
+		dev_err(&hbus->hdev->device,
+			"%s() failed: %#llx", __func__, res);
+}
 #elif defined(CONFIG_ARM64)
 /*
  * SPI vectors to use for vPCI; arch SPIs range is [32, 1019], but leaving a bit
@@ -839,6 +954,12 @@ static struct irq_domain *hv_pci_get_root_domain(void)
 {
 	return hv_msi_gic_irq_domain;
 }
+
+/*
+ * SPIs are used for interrupts of PCI devices and SPIs is managed via GICD
+ * registers which Hyper-V already supports, so no hypercall needed.
+ */
+static void hv_arch_irq_unmask(struct irq_data *data) { }
 #endif /* CONFIG_ARM64 */
 
 /**
@@ -1456,119 +1577,9 @@ static void hv_irq_mask(struct irq_data *data)
 		irq_chip_mask_parent(data);
 }
 
-/**
- * hv_irq_unmask() - "Unmask" the IRQ by setting its current
- * affinity.
- * @data:	Describes the IRQ
- *
- * Build new a destination for the MSI and make a hypercall to
- * update the Interrupt Redirection Table. "Device Logical ID"
- * is built out of this PCI bus's instance GUID and the function
- * number of the device.
- */
 static void hv_irq_unmask(struct irq_data *data)
 {
-	struct msi_desc *msi_desc = irq_data_get_msi_desc(data);
+	hv_arch_irq_unmask(data);
-	struct hv_retarget_device_interrupt *params;
-	struct hv_pcibus_device *hbus;
-	struct cpumask *dest;
-	cpumask_var_t tmp;
-	struct pci_bus *pbus;
-	struct pci_dev *pdev;
-	unsigned long flags;
-	u32 var_size = 0;
-	int cpu, nr_bank;
-	u64 res;
-
-	dest = irq_data_get_effective_affinity_mask(data);
-	pdev = msi_desc_to_pci_dev(msi_desc);
-	pbus = pdev->bus;
-	hbus = container_of(pbus->sysdata, struct hv_pcibus_device, sysdata);
-
-	spin_lock_irqsave(&hbus->retarget_msi_interrupt_lock, flags);
-
-	params = &hbus->retarget_msi_interrupt_params;
-	memset(params, 0, sizeof(*params));
-	params->partition_id = HV_PARTITION_ID_SELF;
-	params->int_entry.source = HV_INTERRUPT_SOURCE_MSI;
-	hv_set_msi_entry_from_desc(&params->int_entry.msi_entry, msi_desc);
-	params->device_id = (hbus->hdev->dev_instance.b[5] << 24) |
-			   (hbus->hdev->dev_instance.b[4] << 16) |
-			   (hbus->hdev->dev_instance.b[7] << 8) |
-			   (hbus->hdev->dev_instance.b[6] & 0xf8) |
-			   PCI_FUNC(pdev->devfn);
-	params->int_target.vector = hv_msi_get_int_vector(data);
-
-	/*
-	 * Honoring apic->delivery_mode set to APIC_DELIVERY_MODE_FIXED by
-	 * setting the HV_DEVICE_INTERRUPT_TARGET_MULTICAST flag results in a
-	 * spurious interrupt storm. Not doing so does not seem to have a
-	 * negative effect (yet?).
-	 */
-
-	if (hbus->protocol_version >= PCI_PROTOCOL_VERSION_1_2) {
-		/*
-		 * PCI_PROTOCOL_VERSION_1_2 supports the VP_SET version of the
-		 * HVCALL_RETARGET_INTERRUPT hypercall, which also coincides
-		 * with >64 VP support.
-		 * ms_hyperv.hints & HV_X64_EX_PROCESSOR_MASKS_RECOMMENDED
-		 * is not sufficient for this hypercall.
-		 */
-		params->int_target.flags |=
-			HV_DEVICE_INTERRUPT_TARGET_PROCESSOR_SET;
-
-		if (!alloc_cpumask_var(&tmp, GFP_ATOMIC)) {
-			res = 1;
-			goto exit_unlock;
-		}
-
-		cpumask_and(tmp, dest, cpu_online_mask);
-		nr_bank = cpumask_to_vpset(&params->int_target.vp_set, tmp);
-		free_cpumask_var(tmp);
-
-		if (nr_bank <= 0) {
-			res = 1;
-			goto exit_unlock;
-		}
-
-		/*
-		 * var-sized hypercall, var-size starts after vp_mask (thus
-		 * vp_set.format does not count, but vp_set.valid_bank_mask
-		 * does).
-		 */
-		var_size = 1 + nr_bank;
-	} else {
-		for_each_cpu_and(cpu, dest, cpu_online_mask) {
-			params->int_target.vp_mask |=
-				(1ULL << hv_cpu_number_to_vp_number(cpu));
-		}
-	}
-
-	res = hv_do_hypercall(HVCALL_RETARGET_INTERRUPT | (var_size << 17),
-			      params, NULL);
-
-exit_unlock:
-	spin_unlock_irqrestore(&hbus->retarget_msi_interrupt_lock, flags);
-
-	/*
-	 * During hibernation, when a CPU is offlined, the kernel tries
-	 * to move the interrupt to the remaining CPUs that haven't
-	 * been offlined yet. In this case, the below hv_do_hypercall()
-	 * always fails since the vmbus channel has been closed:
-	 * refer to cpu_disable_common() -> fixup_irqs() ->
-	 * irq_migrate_all_off_this_cpu() -> migrate_one_irq().
-	 *
-	 * Suppress the error message for hibernation because the failure
-	 * during hibernation does not matter (at this time all the devices
-	 * have been frozen). Note: the correct affinity info is still updated
-	 * into the irqdata data structure in migrate_one_irq() ->
-	 * irq_do_set_affinity() -> hv_set_affinity(), so later when the VM
-	 * resumes, hv_pci_restore_msi_state() is able to correctly restore
-	 * the interrupt with the correct affinity.
-	 */
-	if (!hv_result_success(res) && hbus->state != hv_pcibus_removing)
-		dev_err(&hbus->hdev->device,
-			"%s() failed: %#llx", __func__, res);
 
 	if (data->parent_data->chip->irq_unmask)
 		irq_chip_unmask_parent(data);

drivers/pci/controller/pci-loongson.c

@@ -35,7 +35,7 @@ struct loongson_pci {
 /* Fixup wrong class code in PCIe bridges */
 static void bridge_class_quirk(struct pci_dev *dev)
 {
-	dev->class = PCI_CLASS_BRIDGE_PCI << 8;
+	dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL;
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_LOONGSON,
 			DEV_PCIE_PORT_0, bridge_class_quirk);

drivers/pci/controller/pci-mvebu.c

@@ -32,8 +32,9 @@
 #define PCIE_DEV_REV_OFF	0x0008
 #define PCIE_BAR_LO_OFF(n)	(0x0010 + ((n) << 3))
 #define PCIE_BAR_HI_OFF(n)	(0x0014 + ((n) << 3))
+#define PCIE_SSDEV_ID_OFF	0x002c
 #define PCIE_CAP_PCIEXP		0x0060
-#define PCIE_HEADER_LOG_4_OFF	0x0128
+#define PCIE_CAP_PCIERR_OFF	0x0100
 #define PCIE_BAR_CTRL_OFF(n)	(0x1804 + (((n) - 1) * 4))
 #define PCIE_WIN04_CTRL_OFF(n)	(0x1820 + ((n) << 4))
 #define PCIE_WIN04_BASE_OFF(n)	(0x1824 + ((n) << 4))
@@ -53,9 +54,10 @@
 	 PCIE_CONF_ADDR_EN)
 #define PCIE_CONF_DATA_OFF	0x18fc
 #define PCIE_INT_CAUSE_OFF	0x1900
+#define PCIE_INT_UNMASK_OFF	0x1910
+#define  PCIE_INT_INTX(i)		BIT(24+i)
 #define  PCIE_INT_PM_PME		BIT(28)
-#define PCIE_MASK_OFF		0x1910
+#define  PCIE_INT_ALL_MASK		GENMASK(31, 0)
-#define  PCIE_MASK_ENABLE_INTS          0x0f000000
 #define PCIE_CTRL_OFF		0x1a00
 #define  PCIE_CTRL_X1_MODE		0x0001
 #define  PCIE_CTRL_RC_MODE		BIT(1)
@@ -93,6 +95,7 @@ struct mvebu_pcie_port {
 	void __iomem *base;
 	u32 port;
 	u32 lane;
+	bool is_x4;
 	int devfn;
 	unsigned int mem_target;
 	unsigned int mem_attr;
@@ -108,6 +111,9 @@ struct mvebu_pcie_port {
 	struct mvebu_pcie_window iowin;
 	u32 saved_pcie_stat;
 	struct resource regs;
+	struct irq_domain *intx_irq_domain;
+	raw_spinlock_t irq_lock;
+	int intx_irq;
 };
 
 static inline void mvebu_writel(struct mvebu_pcie_port *port, u32 val, u32 reg)
@@ -233,13 +239,25 @@ static void mvebu_pcie_setup_wins(struct mvebu_pcie_port *port)
 
 static void mvebu_pcie_setup_hw(struct mvebu_pcie_port *port)
 {
-	u32 ctrl, cmd, dev_rev, mask;
+	u32 ctrl, lnkcap, cmd, dev_rev, unmask;
 
 	/* Setup PCIe controller to Root Complex mode. */
 	ctrl = mvebu_readl(port, PCIE_CTRL_OFF);
 	ctrl |= PCIE_CTRL_RC_MODE;
 	mvebu_writel(port, ctrl, PCIE_CTRL_OFF);
 
+	/*
+	 * Set Maximum Link Width to X1 or X4 in Root Port's PCIe Link
+	 * Capability register. This register is defined by PCIe specification
+	 * as read-only but this mvebu controller has it as read-write and must
+	 * be set to number of SerDes PCIe lanes (1 or 4). If this register is
+	 * not set correctly then link with endpoint card is not established.
+	 */
+	lnkcap = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCAP);
+	lnkcap &= ~PCI_EXP_LNKCAP_MLW;
+	lnkcap |= (port->is_x4 ? 4 : 1) << 4;
+	mvebu_writel(port, lnkcap, PCIE_CAP_PCIEXP + PCI_EXP_LNKCAP);
+
 	/* Disable Root Bridge I/O space, memory space and bus mastering. */
 	cmd = mvebu_readl(port, PCIE_CMD_OFF);
 	cmd &= ~(PCI_COMMAND_IO | PCI_COMMAND_MEMORY | PCI_COMMAND_MASTER);
@@ -268,23 +286,57 @@ static void mvebu_pcie_setup_hw(struct mvebu_pcie_port *port)
 	 */
 	dev_rev = mvebu_readl(port, PCIE_DEV_REV_OFF);
 	dev_rev &= ~0xffffff00;
-	dev_rev |= (PCI_CLASS_BRIDGE_PCI << 8) << 8;
+	dev_rev |= PCI_CLASS_BRIDGE_PCI_NORMAL << 8;
 	mvebu_writel(port, dev_rev, PCIE_DEV_REV_OFF);
 
 	/* Point PCIe unit MBUS decode windows to DRAM space. */
 	mvebu_pcie_setup_wins(port);
 
-	/* Enable interrupt lines A-D. */
+	/* Mask all interrupt sources. */
-	mask = mvebu_readl(port, PCIE_MASK_OFF);
+	mvebu_writel(port, ~PCIE_INT_ALL_MASK, PCIE_INT_UNMASK_OFF);
-	mask |= PCIE_MASK_ENABLE_INTS;
+
-	mvebu_writel(port, mask, PCIE_MASK_OFF);
+	/* Clear all interrupt causes. */
+	mvebu_writel(port, ~PCIE_INT_ALL_MASK, PCIE_INT_CAUSE_OFF);
+
+	/* Check if "intx" interrupt was specified in DT. */
+	if (port->intx_irq > 0)
+		return;
+
+	/*
+	 * Fallback code when "intx" interrupt was not specified in DT:
+	 * Unmask all legacy INTx interrupts as driver does not provide a way
+	 * for masking and unmasking of individual legacy INTx interrupts.
+	 * Legacy INTx are reported via one shared GIC source and therefore
+	 * kernel cannot distinguish which individual legacy INTx was triggered.
+	 * These interrupts are shared, so it should not cause any issue. Just
+	 * performance penalty as every PCIe interrupt handler needs to be
+	 * called when some interrupt is triggered.
+	 */
+	unmask = mvebu_readl(port, PCIE_INT_UNMASK_OFF);
+	unmask |= PCIE_INT_INTX(0) | PCIE_INT_INTX(1) |
+		  PCIE_INT_INTX(2) | PCIE_INT_INTX(3);
+	mvebu_writel(port, unmask, PCIE_INT_UNMASK_OFF);
 }
 
-static int mvebu_pcie_hw_rd_conf(struct mvebu_pcie_port *port,
+static struct mvebu_pcie_port *mvebu_pcie_find_port(struct mvebu_pcie *pcie,
-				 struct pci_bus *bus,
+						    struct pci_bus *bus,
-				 u32 devfn, int where, int size, u32 *val)
+						    int devfn);
+
+static int mvebu_pcie_child_rd_conf(struct pci_bus *bus, u32 devfn, int where,
+				    int size, u32 *val)
 {
-	void __iomem *conf_data = port->base + PCIE_CONF_DATA_OFF;
+	struct mvebu_pcie *pcie = bus->sysdata;
+	struct mvebu_pcie_port *port;
+	void __iomem *conf_data;
+
+	port = mvebu_pcie_find_port(pcie, bus, devfn);
+	if (!port)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	if (!mvebu_pcie_link_up(port))
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	conf_data = port->base + PCIE_CONF_DATA_OFF;
 
 	mvebu_writel(port, PCIE_CONF_ADDR(bus->number, devfn, where),
 		     PCIE_CONF_ADDR_OFF);
@@ -300,18 +352,27 @@ static int mvebu_pcie_hw_rd_conf(struct mvebu_pcie_port *port,
 		*val = readl_relaxed(conf_data);
 		break;
 	default:
-		*val = 0xffffffff;
 		return PCIBIOS_BAD_REGISTER_NUMBER;
 	}
 
 	return PCIBIOS_SUCCESSFUL;
 }
 
-static int mvebu_pcie_hw_wr_conf(struct mvebu_pcie_port *port,
+static int mvebu_pcie_child_wr_conf(struct pci_bus *bus, u32 devfn,
-				 struct pci_bus *bus,
+				    int where, int size, u32 val)
-				 u32 devfn, int where, int size, u32 val)
 {
-	void __iomem *conf_data = port->base + PCIE_CONF_DATA_OFF;
+	struct mvebu_pcie *pcie = bus->sysdata;
+	struct mvebu_pcie_port *port;
+	void __iomem *conf_data;
+
+	port = mvebu_pcie_find_port(pcie, bus, devfn);
+	if (!port)
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	if (!mvebu_pcie_link_up(port))
+		return PCIBIOS_DEVICE_NOT_FOUND;
+
+	conf_data = port->base + PCIE_CONF_DATA_OFF;
 
 	mvebu_writel(port, PCIE_CONF_ADDR(bus->number, devfn, where),
 		     PCIE_CONF_ADDR_OFF);
@@ -333,6 +394,11 @@ static int mvebu_pcie_hw_wr_conf(struct mvebu_pcie_port *port,
 	return PCIBIOS_SUCCESSFUL;
 }
 
+static struct pci_ops mvebu_pcie_child_ops = {
+	.read = mvebu_pcie_child_rd_conf,
+	.write = mvebu_pcie_child_wr_conf,
+};
+
 /*
  * Remove windows, starting from the largest ones to the smallest
  * ones.
@@ -438,12 +504,6 @@ static int mvebu_pcie_handle_iobase_change(struct mvebu_pcie_port *port)
 		return mvebu_pcie_set_window(port, port->io_target, port->io_attr,
 					     &desired, &port->iowin);
 
-	if (!mvebu_has_ioport(port)) {
-		dev_WARN(&port->pcie->pdev->dev,
-			 "Attempt to set IO when IO is disabled\n");
-		return -EOPNOTSUPP;
-	}
-
 	/*
 	 * We read the PCI-to-PCI bridge emulated registers, and
 	 * calculate the base address and size of the address decoding
@@ -552,15 +612,20 @@ mvebu_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge,
 
 	case PCI_EXP_LNKCAP:
 		/*
-		 * PCIe requires the clock power management capability to be
+		 * PCIe requires that the Clock Power Management capability bit
-		 * hard-wired to zero for downstream ports
+		 * is hard-wired to zero for downstream ports but HW returns 1.
+		 * Additionally enable Data Link Layer Link Active Reporting
+		 * Capable bit as DL_Active indication is provided too.
 		 */
-		*value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCAP) &
+		*value = (mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCAP) &
-			 ~PCI_EXP_LNKCAP_CLKPM;
+			  ~PCI_EXP_LNKCAP_CLKPM) | PCI_EXP_LNKCAP_DLLLARC;
 		break;
 
 	case PCI_EXP_LNKCTL:
-		*value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCTL);
+		/* DL_Active indication is provided via PCIE_STAT_OFF */
+		*value = mvebu_readl(port, PCIE_CAP_PCIEXP + PCI_EXP_LNKCTL) |
+			 (mvebu_pcie_link_up(port) ?
+			  (PCI_EXP_LNKSTA_DLLLA << 16) : 0);
 		break;
 
 	case PCI_EXP_SLTCTL:
@@ -590,6 +655,37 @@ mvebu_pci_bridge_emul_pcie_conf_read(struct pci_bridge_emul *bridge,
 	return PCI_BRIDGE_EMUL_HANDLED;
 }
 
+static pci_bridge_emul_read_status_t
+mvebu_pci_bridge_emul_ext_conf_read(struct pci_bridge_emul *bridge,
+				    int reg, u32 *value)
+{
+	struct mvebu_pcie_port *port = bridge->data;
+
+	switch (reg) {
+	case 0:
+	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 = mvebu_readl(port, PCIE_CAP_PCIERR_OFF + reg);
+		break;
+
+	default:
+		return PCI_BRIDGE_EMUL_NOT_HANDLED;
+	}
+
+	return PCI_BRIDGE_EMUL_HANDLED;
+}
+
 static void
 mvebu_pci_bridge_emul_base_conf_write(struct pci_bridge_emul *bridge,
 				      int reg, u32 old, u32 new, u32 mask)
@@ -599,24 +695,18 @@ mvebu_pci_bridge_emul_base_conf_write(struct pci_bridge_emul *bridge,
 
 	switch (reg) {
 	case PCI_COMMAND:
-		if (!mvebu_has_ioport(port)) {
-			conf->command = cpu_to_le16(
-				le16_to_cpu(conf->command) & ~PCI_COMMAND_IO);
-			new &= ~PCI_COMMAND_IO;
-		}
-
 		mvebu_writel(port, new, PCIE_CMD_OFF);
 		break;
 
 	case PCI_IO_BASE:
-		if ((mask & 0xffff) && mvebu_pcie_handle_iobase_change(port)) {
+		if ((mask & 0xffff) && mvebu_has_ioport(port) &&
+		    mvebu_pcie_handle_iobase_change(port)) {
 			/* On error disable IO range */
 			conf->iobase &= ~0xf0;
 			conf->iolimit &= ~0xf0;
+			conf->iobase |= 0xf0;
 			conf->iobaseupper = cpu_to_le16(0x0000);
 			conf->iolimitupper = cpu_to_le16(0x0000);
-			if (mvebu_has_ioport(port))
-				conf->iobase |= 0xf0;
 		}
 		break;
 
@@ -630,14 +720,14 @@ mvebu_pci_bridge_emul_base_conf_write(struct pci_bridge_emul *bridge,
 		break;
 
 	case PCI_IO_BASE_UPPER16:
-		if (mvebu_pcie_handle_iobase_change(port)) {
+		if (mvebu_has_ioport(port) &&
+		    mvebu_pcie_handle_iobase_change(port)) {
 			/* On error disable IO range */
 			conf->iobase &= ~0xf0;
 			conf->iolimit &= ~0xf0;
+			conf->iobase |= 0xf0;
 			conf->iobaseupper = cpu_to_le16(0x0000);
 			conf->iolimitupper = cpu_to_le16(0x0000);
-			if (mvebu_has_ioport(port))
-				conf->iobase |= 0xf0;
 		}
 		break;
 
@@ -675,10 +765,9 @@ mvebu_pci_bridge_emul_pcie_conf_write(struct pci_bridge_emul *bridge,
 
 	case PCI_EXP_LNKCTL:
 		/*
-		 * If we don't support CLKREQ, we must ensure that the
+		 * PCIe requires that the Enable Clock Power Management bit
-		 * CLKREQ enable bit always reads zero.  Since we haven't
+		 * is hard-wired to zero for downstream ports but HW allows
-		 * had this capability, and it's dependent on board wiring,
+		 * to change it.
-		 * disable it for the time being.
 		 */
 		new &= ~PCI_EXP_LNKCTL_CLKREQ_EN;
 
@@ -709,11 +798,45 @@ mvebu_pci_bridge_emul_pcie_conf_write(struct pci_bridge_emul *bridge,
 	}
 }
 
-static struct pci_bridge_emul_ops mvebu_pci_bridge_emul_ops = {
+static void
+mvebu_pci_bridge_emul_ext_conf_write(struct pci_bridge_emul *bridge,
+				     int reg, u32 old, u32 new, u32 mask)
+{
+	struct mvebu_pcie_port *port = 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:
+		mvebu_writel(port, new, PCIE_CAP_PCIERR_OFF + reg);
+		break;
+
+	default:
+		break;
+	}
+}
+
+static const struct pci_bridge_emul_ops mvebu_pci_bridge_emul_ops = {
 	.read_base = mvebu_pci_bridge_emul_base_conf_read,
 	.write_base = mvebu_pci_bridge_emul_base_conf_write,
 	.read_pcie = mvebu_pci_bridge_emul_pcie_conf_read,
 	.write_pcie = mvebu_pci_bridge_emul_pcie_conf_write,
+	.read_ext = mvebu_pci_bridge_emul_ext_conf_read,
+	.write_ext = mvebu_pci_bridge_emul_ext_conf_write,
 };
 
 /*
@@ -722,19 +845,24 @@ static struct pci_bridge_emul_ops mvebu_pci_bridge_emul_ops = {
  */
 static int mvebu_pci_bridge_emul_init(struct mvebu_pcie_port *port)
 {
+	unsigned int bridge_flags = PCI_BRIDGE_EMUL_NO_PREFMEM_FORWARD;
 	struct pci_bridge_emul *bridge = &port->bridge;
+	u32 dev_id = mvebu_readl(port, PCIE_DEV_ID_OFF);
+	u32 dev_rev = mvebu_readl(port, PCIE_DEV_REV_OFF);
+	u32 ssdev_id = mvebu_readl(port, PCIE_SSDEV_ID_OFF);
 	u32 pcie_cap = mvebu_readl(port, PCIE_CAP_PCIEXP);
 	u8 pcie_cap_ver = ((pcie_cap >> 16) & PCI_EXP_FLAGS_VERS);
 
-	bridge->conf.vendor = PCI_VENDOR_ID_MARVELL;
+	bridge->conf.vendor = cpu_to_le16(dev_id & 0xffff);
-	bridge->conf.device = mvebu_readl(port, PCIE_DEV_ID_OFF) >> 16;
+	bridge->conf.device = cpu_to_le16(dev_id >> 16);
-	bridge->conf.class_revision =
+	bridge->conf.class_revision = cpu_to_le32(dev_rev & 0xff);
-		mvebu_readl(port, PCIE_DEV_REV_OFF) & 0xff;
 
 	if (mvebu_has_ioport(port)) {
 		/* We support 32 bits I/O addressing */
 		bridge->conf.iobase = PCI_IO_RANGE_TYPE_32;
 		bridge->conf.iolimit = PCI_IO_RANGE_TYPE_32;
+	} else {
+		bridge_flags |= PCI_BRIDGE_EMUL_NO_IO_FORWARD;
 	}
 
 	/*
@@ -743,11 +871,13 @@ static int mvebu_pci_bridge_emul_init(struct mvebu_pcie_port *port)
 	 */
 	bridge->pcie_conf.cap = cpu_to_le16(pcie_cap_ver);
 
+	bridge->subsystem_vendor_id = ssdev_id & 0xffff;
+	bridge->subsystem_id = ssdev_id >> 16;
 	bridge->has_pcie = true;
 	bridge->data = port;
 	bridge->ops = &mvebu_pci_bridge_emul_ops;
 
-	return pci_bridge_emul_init(bridge, PCI_BRIDGE_EMUL_NO_PREFETCHABLE_BAR);
+	return pci_bridge_emul_init(bridge, bridge_flags);
 }
 
 static inline struct mvebu_pcie *sys_to_pcie(struct pci_sys_data *sys)
@@ -784,25 +914,12 @@ static int mvebu_pcie_wr_conf(struct pci_bus *bus, u32 devfn,
 {
 	struct mvebu_pcie *pcie = bus->sysdata;
 	struct mvebu_pcie_port *port;
-	int ret;
 
 	port = mvebu_pcie_find_port(pcie, bus, devfn);
 	if (!port)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
-	/* Access the emulated PCI-to-PCI bridge */
+	return pci_bridge_emul_conf_write(&port->bridge, where, size, val);
-	if (bus->number == 0)
-		return pci_bridge_emul_conf_write(&port->bridge, where,
-						  size, val);
-
-	if (!mvebu_pcie_link_up(port))
-		return PCIBIOS_DEVICE_NOT_FOUND;
-
-	/* Access the real PCIe interface */
-	ret = mvebu_pcie_hw_wr_conf(port, bus, devfn,
-				    where, size, val);
-
-	return ret;
 }
 
 /* PCI configuration space read function */
@@ -811,25 +928,12 @@ static int mvebu_pcie_rd_conf(struct pci_bus *bus, u32 devfn, int where,
 {
 	struct mvebu_pcie *pcie = bus->sysdata;
 	struct mvebu_pcie_port *port;
-	int ret;
 
 	port = mvebu_pcie_find_port(pcie, bus, devfn);
 	if (!port)
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
-	/* Access the emulated PCI-to-PCI bridge */
+	return pci_bridge_emul_conf_read(&port->bridge, where, size, val);
-	if (bus->number == 0)
-		return pci_bridge_emul_conf_read(&port->bridge, where,
-						 size, val);
-
-	if (!mvebu_pcie_link_up(port))
-		return PCIBIOS_DEVICE_NOT_FOUND;
-
-	/* Access the real PCIe interface */
-	ret = mvebu_pcie_hw_rd_conf(port, bus, devfn,
-				    where, size, val);
-
-	return ret;
 }
 
 static struct pci_ops mvebu_pcie_ops = {
@@ -837,6 +941,108 @@ static struct pci_ops mvebu_pcie_ops = {
 	.write = mvebu_pcie_wr_conf,
 };
 
+static void mvebu_pcie_intx_irq_mask(struct irq_data *d)
+{
+	struct mvebu_pcie_port *port = d->domain->host_data;
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
+	unsigned long flags;
+	u32 unmask;
+
+	raw_spin_lock_irqsave(&port->irq_lock, flags);
+	unmask = mvebu_readl(port, PCIE_INT_UNMASK_OFF);
+	unmask &= ~PCIE_INT_INTX(hwirq);
+	mvebu_writel(port, unmask, PCIE_INT_UNMASK_OFF);
+	raw_spin_unlock_irqrestore(&port->irq_lock, flags);
+}
+
+static void mvebu_pcie_intx_irq_unmask(struct irq_data *d)
+{
+	struct mvebu_pcie_port *port = d->domain->host_data;
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
+	unsigned long flags;
+	u32 unmask;
+
+	raw_spin_lock_irqsave(&port->irq_lock, flags);
+	unmask = mvebu_readl(port, PCIE_INT_UNMASK_OFF);
+	unmask |= PCIE_INT_INTX(hwirq);
+	mvebu_writel(port, unmask, PCIE_INT_UNMASK_OFF);
+	raw_spin_unlock_irqrestore(&port->irq_lock, flags);
+}
+
+static struct irq_chip intx_irq_chip = {
+	.name = "mvebu-INTx",
+	.irq_mask = mvebu_pcie_intx_irq_mask,
+	.irq_unmask = mvebu_pcie_intx_irq_unmask,
+};
+
+static int mvebu_pcie_intx_irq_map(struct irq_domain *h,
+				   unsigned int virq, irq_hw_number_t hwirq)
+{
+	struct mvebu_pcie_port *port = h->host_data;
+
+	irq_set_status_flags(virq, IRQ_LEVEL);
+	irq_set_chip_and_handler(virq, &intx_irq_chip, handle_level_irq);
+	irq_set_chip_data(virq, port);
+
+	return 0;
+}
+
+static const struct irq_domain_ops mvebu_pcie_intx_irq_domain_ops = {
+	.map = mvebu_pcie_intx_irq_map,
+	.xlate = irq_domain_xlate_onecell,
+};
+
+static int mvebu_pcie_init_irq_domain(struct mvebu_pcie_port *port)
+{
+	struct device *dev = &port->pcie->pdev->dev;
+	struct device_node *pcie_intc_node;
+
+	raw_spin_lock_init(&port->irq_lock);
+
+	pcie_intc_node = of_get_next_child(port->dn, NULL);
+	if (!pcie_intc_node) {
+		dev_err(dev, "No PCIe Intc node found for %s\n", port->name);
+		return -ENODEV;
+	}
+
+	port->intx_irq_domain = irq_domain_add_linear(pcie_intc_node, PCI_NUM_INTX,
+						      &mvebu_pcie_intx_irq_domain_ops,
+						      port);
+	of_node_put(pcie_intc_node);
+	if (!port->intx_irq_domain) {
+		dev_err(dev, "Failed to get INTx IRQ domain for %s\n", port->name);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static void mvebu_pcie_irq_handler(struct irq_desc *desc)
+{
+	struct mvebu_pcie_port *port = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	struct device *dev = &port->pcie->pdev->dev;
+	u32 cause, unmask, status;
+	int i;
+
+	chained_irq_enter(chip, desc);
+
+	cause = mvebu_readl(port, PCIE_INT_CAUSE_OFF);
+	unmask = mvebu_readl(port, PCIE_INT_UNMASK_OFF);
+	status = cause & unmask;
+
+	/* Process legacy INTx interrupts */
+	for (i = 0; i < PCI_NUM_INTX; i++) {
+		if (!(status & PCIE_INT_INTX(i)))
+			continue;
+
+		if (generic_handle_domain_irq(port->intx_irq_domain, i) == -EINVAL)
+			dev_err_ratelimited(dev, "unexpected INT%c IRQ\n", (char)i+'A');
+	}
+
+	chained_irq_exit(chip, desc);
+}
+
 static int mvebu_pcie_map_irq(const struct pci_dev *dev, u8 slot, u8 pin)
 {
 	/* Interrupt support on mvebu emulated bridges is not implemented yet */
@@ -986,6 +1192,7 @@ static int mvebu_pcie_parse_port(struct mvebu_pcie *pcie,
 	struct device *dev = &pcie->pdev->dev;
 	enum of_gpio_flags flags;
 	int reset_gpio, ret;
+	u32 num_lanes;
 
 	port->pcie = pcie;
 
@@ -998,6 +1205,9 @@ static int mvebu_pcie_parse_port(struct mvebu_pcie *pcie,
 	if (of_property_read_u32(child, "marvell,pcie-lane", &port->lane))
 		port->lane = 0;
 
+	if (!of_property_read_u32(child, "num-lanes", &num_lanes) && num_lanes == 4)
+		port->is_x4 = true;
+
 	port->name = devm_kasprintf(dev, GFP_KERNEL, "pcie%d.%d", port->port,
 				    port->lane);
 	if (!port->name) {
@@ -1030,6 +1240,21 @@ static int mvebu_pcie_parse_port(struct mvebu_pcie *pcie,
 		port->io_attr = -1;
 	}
 
+	/*
+	 * Old DT bindings do not contain "intx" interrupt
+	 * so do not fail probing driver when interrupt does not exist.
+	 */
+	port->intx_irq = of_irq_get_byname(child, "intx");
+	if (port->intx_irq == -EPROBE_DEFER) {
+		ret = port->intx_irq;
+		goto err;
+	}
+	if (port->intx_irq <= 0) {
+		dev_warn(dev, "%s: legacy INTx interrupts cannot be masked individually, "
+			      "%pOF does not contain intx interrupt\n",
+			 port->name, child);
+	}
+
 	reset_gpio = of_get_named_gpio_flags(child, "reset-gpios", 0, &flags);
 	if (reset_gpio == -EPROBE_DEFER) {
 		ret = reset_gpio;
@@ -1226,6 +1451,7 @@ static int mvebu_pcie_probe(struct platform_device *pdev)
 
 	for (i = 0; i < pcie->nports; i++) {
 		struct mvebu_pcie_port *port = &pcie->ports[i];
+		int irq = port->intx_irq;
 
 		child = port->dn;
 		if (!child)
@@ -1253,6 +1479,22 @@ static int mvebu_pcie_probe(struct platform_device *pdev)
 			continue;
 		}
 
+		if (irq > 0) {
+			ret = mvebu_pcie_init_irq_domain(port);
+			if (ret) {
+				dev_err(dev, "%s: cannot init irq domain\n",
+					port->name);
+				pci_bridge_emul_cleanup(&port->bridge);
+				devm_iounmap(dev, port->base);
+				port->base = NULL;
+				mvebu_pcie_powerdown(port);
+				continue;
+			}
+			irq_set_chained_handler_and_data(irq,
+							 mvebu_pcie_irq_handler,
+							 port);
+		}
+
 		/*
 		 * PCIe topology exported by mvebu hw is quite complicated. In
 		 * reality has something like N fully independent host bridges
@@ -1333,10 +1575,9 @@ static int mvebu_pcie_probe(struct platform_device *pdev)
 		mvebu_pcie_set_local_bus_nr(port, 0);
 	}
 
-	pcie->nports = i;
-
 	bridge->sysdata = pcie;
 	bridge->ops = &mvebu_pcie_ops;
+	bridge->child_ops = &mvebu_pcie_child_ops;
 	bridge->align_resource = mvebu_pcie_align_resource;
 	bridge->map_irq = mvebu_pcie_map_irq;
 
@@ -1358,6 +1599,7 @@ static int mvebu_pcie_remove(struct platform_device *pdev)
 
 	for (i = 0; i < pcie->nports; i++) {
 		struct mvebu_pcie_port *port = &pcie->ports[i];
+		int irq = port->intx_irq;
 
 		if (!port->base)
 			continue;
@@ -1368,7 +1610,17 @@ static int mvebu_pcie_remove(struct platform_device *pdev)
 		mvebu_writel(port, cmd, PCIE_CMD_OFF);
 
 		/* Mask all interrupt sources. */
-		mvebu_writel(port, 0, PCIE_MASK_OFF);
+		mvebu_writel(port, ~PCIE_INT_ALL_MASK, PCIE_INT_UNMASK_OFF);
+
+		/* Clear all interrupt causes. */
+		mvebu_writel(port, ~PCIE_INT_ALL_MASK, PCIE_INT_CAUSE_OFF);
+
+		if (irq > 0)
+			irq_set_chained_handler_and_data(irq, NULL, NULL);
+
+		/* Remove IRQ domains. */
+		if (port->intx_irq_domain)
+			irq_domain_remove(port->intx_irq_domain);
 
 		/* Free config space for emulated root bridge. */
 		pci_bridge_emul_cleanup(&port->bridge);

drivers/pci/controller/pci-tegra.c

@@ -726,7 +726,7 @@ static void tegra_pcie_port_free(struct tegra_pcie_port *port)
 /* Tegra PCIE root complex wrongly reports device class */
 static void tegra_pcie_fixup_class(struct pci_dev *dev)
 {
-	dev->class = PCI_CLASS_BRIDGE_PCI << 8;
+	dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL;
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0bf0, tegra_pcie_fixup_class);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_NVIDIA, 0x0bf1, tegra_pcie_fixup_class);

drivers/pci/controller/pci-xgene.c

@@ -49,7 +49,6 @@
 #define EN_REG				0x00000001
 #define OB_LO_IO			0x00000002
 #define XGENE_PCIE_DEVICEID		0xE004
-#define SZ_1T				(SZ_1G*1024ULL)
 #define PIPE_PHY_RATE_RD(src)		((0xc000 & (u32)(src)) >> 0xe)
 
 #define XGENE_V1_PCI_EXP_CAP		0x40
@@ -465,7 +464,7 @@ static int xgene_pcie_select_ib_reg(u8 *ib_reg_mask, u64 size)
 		return 1;
 	}
 
-	if ((size > SZ_1K) && (size < SZ_4G) && !(*ib_reg_mask & (1 << 0))) {
+	if ((size > SZ_1K) && (size < SZ_1T) && !(*ib_reg_mask & (1 << 0))) {
 		*ib_reg_mask |= (1 << 0);
 		return 0;
 	}
@@ -479,28 +478,27 @@ static int xgene_pcie_select_ib_reg(u8 *ib_reg_mask, u64 size)
 }
 
 static void xgene_pcie_setup_ib_reg(struct xgene_pcie *port,
-				    struct resource_entry *entry,
+				    struct of_pci_range *range, u8 *ib_reg_mask)
-				    u8 *ib_reg_mask)
 {
 	void __iomem *cfg_base = port->cfg_base;
 	struct device *dev = port->dev;
 	void __iomem *bar_addr;
 	u32 pim_reg;
-	u64 cpu_addr = entry->res->start;
+	u64 cpu_addr = range->cpu_addr;
-	u64 pci_addr = cpu_addr - entry->offset;
+	u64 pci_addr = range->pci_addr;
-	u64 size = resource_size(entry->res);
+	u64 size = range->size;
 	u64 mask = ~(size - 1) | EN_REG;
 	u32 flags = PCI_BASE_ADDRESS_MEM_TYPE_64;
 	u32 bar_low;
 	int region;
 
-	region = xgene_pcie_select_ib_reg(ib_reg_mask, size);
+	region = xgene_pcie_select_ib_reg(ib_reg_mask, range->size);
 	if (region < 0) {
 		dev_warn(dev, "invalid pcie dma-range config\n");
 		return;
 	}
 
-	if (entry->res->flags & IORESOURCE_PREFETCH)
+	if (range->flags & IORESOURCE_PREFETCH)
 		flags |= PCI_BASE_ADDRESS_MEM_PREFETCH;
 
 	bar_low = pcie_bar_low_val((u32)cpu_addr, flags);
@@ -531,13 +529,25 @@ static void xgene_pcie_setup_ib_reg(struct xgene_pcie *port,
 
 static int xgene_pcie_parse_map_dma_ranges(struct xgene_pcie *port)
 {
-	struct pci_host_bridge *bridge = pci_host_bridge_from_priv(port);
+	struct device_node *np = port->node;
-	struct resource_entry *entry;
+	struct of_pci_range range;
+	struct of_pci_range_parser parser;
+	struct device *dev = port->dev;
 	u8 ib_reg_mask = 0;
 
-	resource_list_for_each_entry(entry, &bridge->dma_ranges)
+	if (of_pci_dma_range_parser_init(&parser, np)) {
-		xgene_pcie_setup_ib_reg(port, entry, &ib_reg_mask);
+		dev_err(dev, "missing dma-ranges property\n");
+		return -EINVAL;
+	}
 
+	/* Get the dma-ranges from DT */
+	for_each_of_pci_range(&parser, &range) {
+		u64 end = range.cpu_addr + range.size - 1;
+
+		dev_dbg(dev, "0x%08x 0x%016llx..0x%016llx -> 0x%016llx\n",
+			range.flags, range.cpu_addr, end, range.pci_addr);
+		xgene_pcie_setup_ib_reg(port, &range, &ib_reg_mask);
+	}
 	return 0;
 }
 

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

@@ -18,7 +18,7 @@
 /* NS: CLASS field is R/O, and set to wrong 0x200 value */
 static void bcma_pcie2_fixup_class(struct pci_dev *dev)
 {
-	dev->class = PCI_CLASS_BRIDGE_PCI << 8;
+	dev->class = PCI_CLASS_BRIDGE_PCI_NORMAL;
 }
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x8011, bcma_pcie2_fixup_class);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_BROADCOM, 0x8012, bcma_pcie2_fixup_class);

drivers/pci/controller/pcie-iproc.c

@@ -789,14 +789,13 @@ static int iproc_pcie_check_link(struct iproc_pcie *pcie)
 		return -EFAULT;
 	}
 
-	/* force class to PCI_CLASS_BRIDGE_PCI (0x0604) */
+	/* force class to PCI_CLASS_BRIDGE_PCI_NORMAL (0x060400) */
 #define PCI_BRIDGE_CTRL_REG_OFFSET	0x43c
-#define PCI_CLASS_BRIDGE_MASK		0xffff00
+#define PCI_BRIDGE_CTRL_REG_CLASS_MASK	0xffffff
-#define PCI_CLASS_BRIDGE_SHIFT		8
 	iproc_pci_raw_config_read32(pcie, 0, PCI_BRIDGE_CTRL_REG_OFFSET,
 				    4, &class);
-	class &= ~PCI_CLASS_BRIDGE_MASK;
+	class &= ~PCI_BRIDGE_CTRL_REG_CLASS_MASK;
-	class |= (PCI_CLASS_BRIDGE_PCI << PCI_CLASS_BRIDGE_SHIFT);
+	class |= PCI_CLASS_BRIDGE_PCI_NORMAL;
 	iproc_pci_raw_config_write32(pcie, 0, PCI_BRIDGE_CTRL_REG_OFFSET,
 				     4, class);
 
@@ -1581,7 +1580,7 @@ static void quirk_paxc_bridge(struct pci_dev *pdev)
 	 * code that the bridge is not an Ethernet device.
 	 */
 	if (pdev->hdr_type == PCI_HEADER_TYPE_BRIDGE)
-		pdev->class = PCI_CLASS_BRIDGE_PCI << 8;
+		pdev->class = PCI_CLASS_BRIDGE_PCI_NORMAL;
 
 	/*
 	 * MPSS is not being set properly (as it is currently 0).  This is

drivers/pci/controller/pcie-mediatek-gen3.c

@@ -292,7 +292,7 @@ static int mtk_pcie_startup_port(struct mtk_gen3_pcie *pcie)
 	/* Set class code */
 	val = readl_relaxed(pcie->base + PCIE_PCI_IDS_1);
 	val &= ~GENMASK(31, 8);
-	val |= PCI_CLASS(PCI_CLASS_BRIDGE_PCI << 8);
+	val |= PCI_CLASS(PCI_CLASS_BRIDGE_PCI_NORMAL);
 	writel_relaxed(val, pcie->base + PCIE_PCI_IDS_1);
 
 	/* Mask all INTx interrupts */

drivers/pci/controller/pcie-rcar-host.c

@@ -65,6 +65,42 @@ struct rcar_pcie_host {
 	int			(*phy_init_fn)(struct rcar_pcie_host *host);
 };
 
+static DEFINE_SPINLOCK(pmsr_lock);
+
+static int rcar_pcie_wakeup(struct device *pcie_dev, void __iomem *pcie_base)
+{
+	unsigned long flags;
+	u32 pmsr, val;
+	int ret = 0;
+
+	spin_lock_irqsave(&pmsr_lock, flags);
+
+	if (!pcie_base || pm_runtime_suspended(pcie_dev)) {
+		ret = -EINVAL;
+		goto unlock_exit;
+	}
+
+	pmsr = readl(pcie_base + PMSR);
+
+	/*
+	 * Test if the PCIe controller received PM_ENTER_L1 DLLP and
+	 * the PCIe controller is not in L1 link state. If true, apply
+	 * fix, which will put the controller into L1 link state, from
+	 * which it can return to L0s/L0 on its own.
+	 */
+	if ((pmsr & PMEL1RX) && ((pmsr & PMSTATE) != PMSTATE_L1)) {
+		writel(L1IATN, pcie_base + PMCTLR);
+		ret = readl_poll_timeout_atomic(pcie_base + PMSR, val,
+						val & L1FAEG, 10, 1000);
+		WARN(ret, "Timeout waiting for L1 link state, ret=%d\n", ret);
+		writel(L1FAEG | PMEL1RX, pcie_base + PMSR);
+	}
+
+unlock_exit:
+	spin_unlock_irqrestore(&pmsr_lock, flags);
+	return ret;
+}
+
 static struct rcar_pcie_host *msi_to_host(struct rcar_msi *msi)
 {
 	return container_of(msi, struct rcar_pcie_host, msi);
@@ -78,6 +114,54 @@ static u32 rcar_read_conf(struct rcar_pcie *pcie, int where)
 	return val >> shift;
 }
 
+#ifdef CONFIG_ARM
+#define __rcar_pci_rw_reg_workaround(instr)				\
+		"	.arch armv7-a\n"				\
+		"1:	" instr " %1, [%2]\n"				\
+		"2:	isb\n"						\
+		"3:	.pushsection .text.fixup,\"ax\"\n"		\
+		"	.align	2\n"					\
+		"4:	mov	%0, #" __stringify(PCIBIOS_SET_FAILED) "\n" \
+		"	b	3b\n"					\
+		"	.popsection\n"					\
+		"	.pushsection __ex_table,\"a\"\n"		\
+		"	.align	3\n"					\
+		"	.long	1b, 4b\n"				\
+		"	.long	2b, 4b\n"				\
+		"	.popsection\n"
+#endif
+
+static int rcar_pci_write_reg_workaround(struct rcar_pcie *pcie, u32 val,
+					 unsigned int reg)
+{
+	int error = PCIBIOS_SUCCESSFUL;
+#ifdef CONFIG_ARM
+	asm volatile(
+		__rcar_pci_rw_reg_workaround("str")
+	: "+r"(error):"r"(val), "r"(pcie->base + reg) : "memory");
+#else
+	rcar_pci_write_reg(pcie, val, reg);
+#endif
+	return error;
+}
+
+static int rcar_pci_read_reg_workaround(struct rcar_pcie *pcie, u32 *val,
+					unsigned int reg)
+{
+	int error = PCIBIOS_SUCCESSFUL;
+#ifdef CONFIG_ARM
+	asm volatile(
+		__rcar_pci_rw_reg_workaround("ldr")
+	: "+r"(error), "=r"(*val) : "r"(pcie->base + reg) : "memory");
+
+	if (error != PCIBIOS_SUCCESSFUL)
+		PCI_SET_ERROR_RESPONSE(val);
+#else
+	*val = rcar_pci_read_reg(pcie, reg);
+#endif
+	return error;
+}
+
 /* Serialization is provided by 'pci_lock' in drivers/pci/access.c */
 static int rcar_pcie_config_access(struct rcar_pcie_host *host,
 		unsigned char access_type, struct pci_bus *bus,
@@ -85,6 +169,14 @@ static int rcar_pcie_config_access(struct rcar_pcie_host *host,
 {
 	struct rcar_pcie *pcie = &host->pcie;
 	unsigned int dev, func, reg, index;
+	int ret;
+
+	/* Wake the bus up in case it is in L1 state. */
+	ret = rcar_pcie_wakeup(pcie->dev, pcie->base);
+	if (ret) {
+		PCI_SET_ERROR_RESPONSE(data);
+		return PCIBIOS_SET_FAILED;
+	}
 
 	dev = PCI_SLOT(devfn);
 	func = PCI_FUNC(devfn);
@@ -141,14 +233,14 @@ static int rcar_pcie_config_access(struct rcar_pcie_host *host,
 		return PCIBIOS_DEVICE_NOT_FOUND;
 
 	if (access_type == RCAR_PCI_ACCESS_READ)
-		*data = rcar_pci_read_reg(pcie, PCIECDR);
+		ret = rcar_pci_read_reg_workaround(pcie, data, PCIECDR);
 	else
-		rcar_pci_write_reg(pcie, *data, PCIECDR);
+		ret = rcar_pci_write_reg_workaround(pcie, *data, PCIECDR);
 
 	/* Disable the configuration access */
 	rcar_pci_write_reg(pcie, 0, PCIECCTLR);
 
-	return PCIBIOS_SUCCESSFUL;
+	return ret;
 }
 
 static int rcar_pcie_read_conf(struct pci_bus *bus, unsigned int devfn,
@@ -370,7 +462,7 @@ static int rcar_pcie_hw_init(struct rcar_pcie *pcie)
 	 * class to match. Hardware takes care of propagating the IDSETR
 	 * settings, so there is no need to bother with a quirk.
 	 */
-	rcar_pci_write_reg(pcie, PCI_CLASS_BRIDGE_PCI << 16, IDSETR1);
+	rcar_pci_write_reg(pcie, PCI_CLASS_BRIDGE_PCI_NORMAL << 8, IDSETR1);
 
 	/*
 	 * Setup Secondary Bus Number & Subordinate Bus Number, even though
@@ -1050,40 +1142,10 @@ static struct platform_driver rcar_pcie_driver = {
 };
 
 #ifdef CONFIG_ARM
-static DEFINE_SPINLOCK(pmsr_lock);
 static int rcar_pcie_aarch32_abort_handler(unsigned long addr,
 		unsigned int fsr, struct pt_regs *regs)
 {
-	unsigned long flags;
+	return !fixup_exception(regs);
-	u32 pmsr, val;
-	int ret = 0;
-
-	spin_lock_irqsave(&pmsr_lock, flags);
-
-	if (!pcie_base || pm_runtime_suspended(pcie_dev)) {
-		ret = 1;
-		goto unlock_exit;
-	}
-
-	pmsr = readl(pcie_base + PMSR);
-
-	/*
-	 * Test if the PCIe controller received PM_ENTER_L1 DLLP and
-	 * the PCIe controller is not in L1 link state. If true, apply
-	 * fix, which will put the controller into L1 link state, from
-	 * which it can return to L0s/L0 on its own.
-	 */
-	if ((pmsr & PMEL1RX) && ((pmsr & PMSTATE) != PMSTATE_L1)) {
-		writel(L1IATN, pcie_base + PMCTLR);
-		ret = readl_poll_timeout_atomic(pcie_base + PMSR, val,
-						val & L1FAEG, 10, 1000);
-		WARN(ret, "Timeout waiting for L1 link state, ret=%d\n", ret);
-		writel(L1FAEG | PMEL1RX, pcie_base + PMSR);
-	}
-
-unlock_exit:
-	spin_unlock_irqrestore(&pmsr_lock, flags);
-	return ret;
 }
 
 static const struct of_device_id rcar_pcie_abort_handler_of_match[] __initconst = {

drivers/pci/controller/pcie-rockchip-host.c

@@ -370,7 +370,7 @@ static int rockchip_pcie_host_init_port(struct rockchip_pcie *rockchip)
 	rockchip_pcie_write(rockchip, ROCKCHIP_VENDOR_ID,
 			    PCIE_CORE_CONFIG_VENDOR);
 	rockchip_pcie_write(rockchip,
-			    PCI_CLASS_BRIDGE_PCI << PCIE_RC_CONFIG_SCC_SHIFT,
+			    PCI_CLASS_BRIDGE_PCI_NORMAL << 8,
 			    PCIE_RC_CONFIG_RID_CCR);
 
 	/* Clear THP cap's next cap pointer to remove L1 substate cap */

drivers/pci/controller/pcie-rockchip.h

@@ -134,7 +134,6 @@
 #define PCIE_RC_CONFIG_NORMAL_BASE	0x800000
 #define PCIE_RC_CONFIG_BASE		0xa00000
 #define PCIE_RC_CONFIG_RID_CCR		(PCIE_RC_CONFIG_BASE + 0x08)
-#define   PCIE_RC_CONFIG_SCC_SHIFT		16
 #define PCIE_RC_CONFIG_DCR		(PCIE_RC_CONFIG_BASE + 0xc4)
 #define   PCIE_RC_CONFIG_DCR_CSPL_SHIFT		18
 #define   PCIE_RC_CONFIG_DCR_CSPL_LIMIT		0xff

drivers/pci/endpoint/functions/pci-epf-test.c

@@ -285,7 +285,17 @@ static int pci_epf_test_copy(struct pci_epf_test *epf_test)
 		if (ret)
 			dev_err(dev, "Data transfer failed\n");
 	} else {
-		memcpy(dst_addr, src_addr, reg->size);
+		void *buf;
+
+		buf = kzalloc(reg->size, GFP_KERNEL);
+		if (!buf) {
+			ret = -ENOMEM;
+			goto err_map_addr;
+		}
+
+		memcpy_fromio(buf, src_addr, reg->size);
+		memcpy_toio(dst_addr, buf, reg->size);
+		kfree(buf);
 	}
 	ktime_get_ts64(&end);
 	pci_epf_test_print_rate("COPY", reg->size, &start, &end, use_dma);
@@ -441,7 +451,7 @@ static int pci_epf_test_write(struct pci_epf_test *epf_test)
 		if (!epf_test->dma_supported) {
 			dev_err(dev, "Cannot transfer data using DMA\n");
 			ret = -EINVAL;
-			goto err_map_addr;
+			goto err_dma_map;
 		}
 
 		src_phys_addr = dma_map_single(dma_dev, buf, reg->size,

drivers/pci/hotplug/acpiphp_glue.c

@@ -226,9 +226,9 @@ static void acpiphp_post_dock_fixup(struct acpi_device *adev)
 static acpi_status acpiphp_add_context(acpi_handle handle, u32 lvl, void *data,
 				       void **rv)
 {
+	struct acpi_device *adev = acpi_fetch_acpi_dev(handle);
 	struct acpiphp_bridge *bridge = data;
 	struct acpiphp_context *context;
-	struct acpi_device *adev;
 	struct acpiphp_slot *slot;
 	struct acpiphp_func *newfunc;
 	acpi_status status = AE_OK;
@@ -238,6 +238,9 @@ static acpi_status acpiphp_add_context(acpi_handle handle, u32 lvl, void *data,
 	struct pci_dev *pdev = bridge->pci_dev;
 	u32 val;
 
+	if (!adev)
+		return AE_OK;
+
 	status = acpi_evaluate_integer(handle, "_ADR", NULL, &adr);
 	if (ACPI_FAILURE(status)) {
 		if (status != AE_NOT_FOUND)
@@ -245,8 +248,6 @@ static acpi_status acpiphp_add_context(acpi_handle handle, u32 lvl, void *data,
 				"can't evaluate _ADR (%#x)\n", status);
 		return AE_OK;
 	}
-	if (acpi_bus_get_device(handle, &adev))
-		return AE_OK;
 
 	device = (adr >> 16) & 0xffff;
 	function = adr & 0xffff;

drivers/pci/hotplug/acpiphp_ibm.c

@@ -433,8 +433,9 @@ static int __init ibm_acpiphp_init(void)
 		goto init_return;
 	}
 	pr_debug("%s: found IBM aPCI device\n", __func__);
-	if (acpi_bus_get_device(ibm_acpi_handle, &device)) {
+	device = acpi_fetch_acpi_dev(ibm_acpi_handle);
-		pr_err("%s: acpi_bus_get_device failed\n", __func__);
+	if (!device) {
+		pr_err("%s: acpi_fetch_acpi_dev failed\n", __func__);
 		retval = -ENODEV;
 		goto init_return;
 	}

drivers/pci/hotplug/cpqphp_core.c

@@ -1254,7 +1254,7 @@ static void __exit unload_cpqphpd(void)
 	struct pci_resource *res;
 	struct pci_resource *tres;
 
-	rc = compaq_nvram_store(cpqhp_rom_start);
+	compaq_nvram_store(cpqhp_rom_start);
 
 	ctrl = cpqhp_ctrl_list;
 

drivers/pci/hotplug/cpqphp_ctrl.c

@@ -881,7 +881,6 @@ irqreturn_t cpqhp_ctrl_intr(int IRQ, void *data)
 	u8 reset;
 	u16 misc;
 	u32 Diff;
-	u32 temp_dword;
 
 
 	misc = readw(ctrl->hpc_reg + MISC);
@@ -917,7 +916,7 @@ irqreturn_t cpqhp_ctrl_intr(int IRQ, void *data)
 		writel(Diff, ctrl->hpc_reg + INT_INPUT_CLEAR);
 
 		/* Read it back to clear any posted writes */
-		temp_dword = readl(ctrl->hpc_reg + INT_INPUT_CLEAR);
+		readl(ctrl->hpc_reg + INT_INPUT_CLEAR);
 
 		if (!Diff)
 			/* Clear all interrupts */
@@ -1412,7 +1411,6 @@ static u32 board_added(struct pci_func *func, struct controller *ctrl)
 	u32 rc = 0;
 	struct pci_func *new_slot = NULL;
 	struct pci_bus *bus = ctrl->pci_bus;
-	struct slot *p_slot;
 	struct resource_lists res_lists;
 
 	hp_slot = func->device - ctrl->slot_device_offset;
@@ -1459,7 +1457,7 @@ static u32 board_added(struct pci_func *func, struct controller *ctrl)
 	if (rc)
 		return rc;
 
-	p_slot = cpqhp_find_slot(ctrl, hp_slot + ctrl->slot_device_offset);
+	cpqhp_find_slot(ctrl, hp_slot + ctrl->slot_device_offset);
 
 	/* turn on board and blink green LED */
 
@@ -1614,7 +1612,6 @@ static u32 remove_board(struct pci_func *func, u32 replace_flag, struct controll
 	u8 device;
 	u8 hp_slot;
 	u8 temp_byte;
-	u32 rc;
 	struct resource_lists res_lists;
 	struct pci_func *temp_func;
 
@@ -1629,7 +1626,7 @@ static u32 remove_board(struct pci_func *func, u32 replace_flag, struct controll
 	/* When we get here, it is safe to change base address registers.
 	 * We will attempt to save the base address register lengths */
 	if (replace_flag || !ctrl->add_support)
-		rc = cpqhp_save_base_addr_length(ctrl, func);
+		cpqhp_save_base_addr_length(ctrl, func);
 	else if (!func->bus_head && !func->mem_head &&
 		 !func->p_mem_head && !func->io_head) {
 		/* Here we check to see if we've saved any of the board's
@@ -1647,7 +1644,7 @@ static u32 remove_board(struct pci_func *func, u32 replace_flag, struct controll
 		}
 
 		if (!skip)
-			rc = cpqhp_save_used_resources(ctrl, func);
+			cpqhp_save_used_resources(ctrl, func);
 	}
 	/* Change status to shutdown */
 	if (func->is_a_board)
@@ -1767,7 +1764,7 @@ void cpqhp_event_stop_thread(void)
 
 static void interrupt_event_handler(struct controller *ctrl)
 {
-	int loop = 0;
+	int loop;
 	int change = 1;
 	struct pci_func *func;
 	u8 hp_slot;
@@ -1885,7 +1882,6 @@ static void interrupt_event_handler(struct controller *ctrl)
 void cpqhp_pushbutton_thread(struct timer_list *t)
 {
 	u8 hp_slot;
-	u8 device;
 	struct pci_func *func;
 	struct slot *p_slot = from_timer(p_slot, t, task_event);
 	struct controller *ctrl = (struct controller *) p_slot->ctrl;
@@ -1893,8 +1889,6 @@ void cpqhp_pushbutton_thread(struct timer_list *t)
 	pushbutton_pending = NULL;
 	hp_slot = p_slot->hp_slot;
 
-	device = p_slot->device;
-
 	if (is_slot_enabled(ctrl, hp_slot)) {
 		p_slot->state = POWEROFF_STATE;
 		/* power Down board */
@@ -1951,15 +1945,12 @@ int cpqhp_process_SI(struct controller *ctrl, struct pci_func *func)
 	u32 tempdword;
 	int rc;
 	struct slot *p_slot;
-	int physical_slot = 0;
 
 	tempdword = 0;
 
 	device = func->device;
 	hp_slot = device - ctrl->slot_device_offset;
 	p_slot = cpqhp_find_slot(ctrl, device);
-	if (p_slot)
-		physical_slot = p_slot->number;
 
 	/* Check to see if the interlock is closed */
 	tempdword = readl(ctrl->hpc_reg + INT_INPUT_CLEAR);
@@ -2043,13 +2034,10 @@ int cpqhp_process_SS(struct controller *ctrl, struct pci_func *func)
 	unsigned int devfn;
 	struct slot *p_slot;
 	struct pci_bus *pci_bus = ctrl->pci_bus;
-	int physical_slot = 0;
 
 	device = func->device;
 	func = cpqhp_slot_find(ctrl->bus, device, index++);
 	p_slot = cpqhp_find_slot(ctrl, device);
-	if (p_slot)
-		physical_slot = p_slot->number;
 
 	/* Make sure there are no video controllers here */
 	while (func && !rc) {

drivers/pci/hotplug/cpqphp_pci.c

@@ -473,7 +473,7 @@ int cpqhp_save_slot_config(struct controller *ctrl, struct pci_func *new_slot)
 	int sub_bus;
 	int max_functions;
 	int function = 0;
-	int cloop = 0;
+	int cloop;
 	int stop_it;
 
 	ID = 0xFFFFFFFF;

drivers/pci/hotplug/ibmphp_hpc.c

@@ -325,11 +325,9 @@ static u8 i2c_ctrl_write(struct controller *ctlr_ptr, void __iomem *WPGBbar, u8
 static u8 isa_ctrl_read(struct controller *ctlr_ptr, u8 offset)
 {
 	u16 start_address;
-	u16 end_address;
 	u8 data;
 
 	start_address = ctlr_ptr->u.isa_ctlr.io_start;
-	end_address = ctlr_ptr->u.isa_ctlr.io_end;
 	data = inb(start_address + offset);
 	return data;
 }

drivers/pci/hotplug/ibmphp_res.c

@@ -1955,7 +1955,7 @@ static int __init update_bridge_ranges(struct bus_node **bus)
 						bus_sec = find_bus_wprev(sec_busno, NULL, 0);
 						/* this bus structure doesn't exist yet, PPB was configured during previous loading of ibmphp */
 						if (!bus_sec) {
-							bus_sec = alloc_error_bus(NULL, sec_busno, 1);
+							alloc_error_bus(NULL, sec_busno, 1);
 							/* the rest will be populated during NVRAM call */
 							return 0;
 						}
@@ -2114,6 +2114,5 @@ static int __init update_bridge_ranges(struct bus_node **bus)
 		}	/* end for function */
 	}	/* end for device */
 
-	bus = &bus_cur;
 	return 0;
 }

drivers/pci/hotplug/pciehp_hpc.c

@@ -98,6 +98,8 @@ static int pcie_poll_cmd(struct controller *ctrl, int timeout)
 		if (slot_status & PCI_EXP_SLTSTA_CC) {
 			pcie_capability_write_word(pdev, PCI_EXP_SLTSTA,
 						   PCI_EXP_SLTSTA_CC);
+			ctrl->cmd_busy = 0;
+			smp_mb();
 			return 1;
 		}
 		msleep(10);
@@ -1084,6 +1086,8 @@ static void quirk_cmd_compl(struct pci_dev *pdev)
 }
 DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_INTEL, PCI_ANY_ID,
 			      PCI_CLASS_BRIDGE_PCI, 8, quirk_cmd_compl);
+DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_QCOM, 0x0110,
+			      PCI_CLASS_BRIDGE_PCI, 8, quirk_cmd_compl);
 DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_QCOM, 0x0400,
 			      PCI_CLASS_BRIDGE_PCI, 8, quirk_cmd_compl);
 DECLARE_PCI_FIXUP_CLASS_EARLY(PCI_VENDOR_ID_QCOM, 0x0401,

drivers/pci/hotplug/shpchp_core.c

@@ -312,7 +312,7 @@ static void shpc_remove(struct pci_dev *dev)
 }
 
 static const struct pci_device_id shpcd_pci_tbl[] = {
-	{PCI_DEVICE_CLASS(((PCI_CLASS_BRIDGE_PCI << 8) | 0x00), ~0)},
+	{PCI_DEVICE_CLASS(PCI_CLASS_BRIDGE_PCI_NORMAL, ~0)},
 	{ /* end: all zeroes */ }
 };
 MODULE_DEVICE_TABLE(pci, shpcd_pci_tbl);

drivers/pci/p2pdma.c

@@ -321,6 +321,7 @@ static const struct pci_p2pdma_whitelist_entry {
 	{PCI_VENDOR_ID_INTEL,	0x2032, 0},
 	{PCI_VENDOR_ID_INTEL,	0x2033, 0},
 	{PCI_VENDOR_ID_INTEL,	0x2020, 0},
+	{PCI_VENDOR_ID_INTEL,	0x09a2, 0},
 	{}
 };
 

drivers/pci/pci-acpi.c

@@ -89,9 +89,9 @@ int acpi_get_rc_resources(struct device *dev, const char *hid, u16 segment,
 		return -ENODEV;
 	}
 
-	ret = acpi_bus_get_device(handle, &adev);
+	adev = acpi_fetch_acpi_dev(handle);
-	if (ret)
+	if (!adev)
-		return ret;
+		return -ENODEV;
 
 	ret = acpi_get_rc_addr(adev, res);
 	if (ret) {

drivers/pci/pci-bridge-emul.c

@@ -21,8 +21,11 @@
 #include "pci-bridge-emul.h"
 
 #define PCI_BRIDGE_CONF_END	PCI_STD_HEADER_SIZEOF
+#define PCI_CAP_SSID_SIZEOF	(PCI_SSVID_DEVICE_ID + 2)
+#define PCI_CAP_SSID_START	PCI_BRIDGE_CONF_END
+#define PCI_CAP_SSID_END	(PCI_CAP_SSID_START + PCI_CAP_SSID_SIZEOF)
 #define PCI_CAP_PCIE_SIZEOF	(PCI_EXP_SLTSTA2 + 2)
-#define PCI_CAP_PCIE_START	PCI_BRIDGE_CONF_END
+#define PCI_CAP_PCIE_START	PCI_CAP_SSID_END
 #define PCI_CAP_PCIE_END	(PCI_CAP_PCIE_START + PCI_CAP_PCIE_SIZEOF)
 
 /**
@@ -315,6 +318,25 @@ struct pci_bridge_reg_behavior pcie_cap_regs_behavior[PCI_CAP_PCIE_SIZEOF / 4] =
 	},
 };
 
+static pci_bridge_emul_read_status_t
+pci_bridge_emul_read_ssid(struct pci_bridge_emul *bridge, int reg, u32 *value)
+{
+	switch (reg) {
+	case PCI_CAP_LIST_ID:
+		*value = PCI_CAP_ID_SSVID |
+			(bridge->has_pcie ? (PCI_CAP_PCIE_START << 8) : 0);
+		return PCI_BRIDGE_EMUL_HANDLED;
+
+	case PCI_SSVID_VENDOR_ID:
+		*value = bridge->subsystem_vendor_id |
+			(bridge->subsystem_id << 16);
+		return PCI_BRIDGE_EMUL_HANDLED;
+
+	default:
+		return PCI_BRIDGE_EMUL_NOT_HANDLED;
+	}
+}
+
 /*
  * Initialize a pci_bridge_emul structure to represent a fake PCI
  * bridge configuration space. The caller needs to have initialized
@@ -328,10 +350,12 @@ int pci_bridge_emul_init(struct pci_bridge_emul *bridge,
 	BUILD_BUG_ON(sizeof(bridge->conf) != PCI_BRIDGE_CONF_END);
 
 	/*
-	 * class_revision: Class is high 24 bits and revision is low 8 bit of this member,
+	 * class_revision: Class is high 24 bits and revision is low 8 bit
-	 * while class for PCI Bridge Normal Decode has the 24-bit value: PCI_CLASS_BRIDGE_PCI << 8
+	 * of this member, while class for PCI Bridge Normal Decode has the
+	 * 24-bit value: PCI_CLASS_BRIDGE_PCI_NORMAL
 	 */
-	bridge->conf.class_revision |= cpu_to_le32((PCI_CLASS_BRIDGE_PCI << 8) << 8);
+	bridge->conf.class_revision |=
+		cpu_to_le32(PCI_CLASS_BRIDGE_PCI_NORMAL << 8);
 	bridge->conf.header_type = PCI_HEADER_TYPE_BRIDGE;
 	bridge->conf.cache_line_size = 0x10;
 	bridge->conf.status = cpu_to_le16(PCI_STATUS_CAP_LIST);
@@ -341,9 +365,17 @@ int pci_bridge_emul_init(struct pci_bridge_emul *bridge,
 	if (!bridge->pci_regs_behavior)
 		return -ENOMEM;
 
-	if (bridge->has_pcie) {
+	if (bridge->subsystem_vendor_id)
+		bridge->conf.capabilities_pointer = PCI_CAP_SSID_START;
+	else if (bridge->has_pcie)
 		bridge->conf.capabilities_pointer = PCI_CAP_PCIE_START;
+	else
+		bridge->conf.capabilities_pointer = 0;
+
+	if (bridge->conf.capabilities_pointer)
 		bridge->conf.status |= cpu_to_le16(PCI_STATUS_CAP_LIST);
+
+	if (bridge->has_pcie) {
 		bridge->pcie_conf.cap_id = PCI_CAP_ID_EXP;
 		bridge->pcie_conf.cap |= cpu_to_le16(PCI_EXP_TYPE_ROOT_PORT << 4);
 		bridge->pcie_cap_regs_behavior =
@@ -377,11 +409,20 @@ int pci_bridge_emul_init(struct pci_bridge_emul *bridge,
 			~(BIT(10) << 16);
 	}
 
-	if (flags & PCI_BRIDGE_EMUL_NO_PREFETCHABLE_BAR) {
+	if (flags & PCI_BRIDGE_EMUL_NO_PREFMEM_FORWARD) {
 		bridge->pci_regs_behavior[PCI_PREF_MEMORY_BASE / 4].ro = ~0;
 		bridge->pci_regs_behavior[PCI_PREF_MEMORY_BASE / 4].rw = 0;
 	}
 
+	if (flags & PCI_BRIDGE_EMUL_NO_IO_FORWARD) {
+		bridge->pci_regs_behavior[PCI_COMMAND / 4].ro |= PCI_COMMAND_IO;
+		bridge->pci_regs_behavior[PCI_COMMAND / 4].rw &= ~PCI_COMMAND_IO;
+		bridge->pci_regs_behavior[PCI_IO_BASE / 4].ro |= GENMASK(15, 0);
+		bridge->pci_regs_behavior[PCI_IO_BASE / 4].rw &= ~GENMASK(15, 0);
+		bridge->pci_regs_behavior[PCI_IO_BASE_UPPER16 / 4].ro = ~0;
+		bridge->pci_regs_behavior[PCI_IO_BASE_UPPER16 / 4].rw = 0;
+	}
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(pci_bridge_emul_init);
@@ -413,25 +454,33 @@ int pci_bridge_emul_conf_read(struct pci_bridge_emul *bridge, int where,
 	__le32 *cfgspace;
 	const struct pci_bridge_reg_behavior *behavior;
 
-	if (bridge->has_pcie && reg >= PCI_CAP_PCIE_END) {
+	if (reg < PCI_BRIDGE_CONF_END) {
-		*value = 0;
+		/* Emulated PCI space */
-		return PCIBIOS_SUCCESSFUL;
+		read_op = bridge->ops->read_base;
-	}
+		cfgspace = (__le32 *) &bridge->conf;
-
+		behavior = bridge->pci_regs_behavior;
-	if (!bridge->has_pcie && reg >= PCI_BRIDGE_CONF_END) {
+	} else if (reg >= PCI_CAP_SSID_START && reg < PCI_CAP_SSID_END && bridge->subsystem_vendor_id) {
-		*value = 0;
+		/* Emulated PCI Bridge Subsystem Vendor ID capability */
-		return PCIBIOS_SUCCESSFUL;
+		reg -= PCI_CAP_SSID_START;
-	}
+		read_op = pci_bridge_emul_read_ssid;
-
+		cfgspace = NULL;
-	if (bridge->has_pcie && reg >= PCI_CAP_PCIE_START) {
+		behavior = NULL;
+	} else if (reg >= PCI_CAP_PCIE_START && reg < PCI_CAP_PCIE_END && bridge->has_pcie) {
+		/* Our emulated PCIe capability */
 		reg -= PCI_CAP_PCIE_START;
 		read_op = bridge->ops->read_pcie;
 		cfgspace = (__le32 *) &bridge->pcie_conf;
 		behavior = bridge->pcie_cap_regs_behavior;
+	} else if (reg >= PCI_CFG_SPACE_SIZE && bridge->has_pcie) {
+		/* PCIe extended capability space */
+		reg -= PCI_CFG_SPACE_SIZE;
+		read_op = bridge->ops->read_ext;
+		cfgspace = NULL;
+		behavior = NULL;
 	} else {
-		read_op = bridge->ops->read_base;
+		/* Not implemented */
-		cfgspace = (__le32 *) &bridge->conf;
+		*value = 0;
-		behavior = bridge->pci_regs_behavior;
+		return PCIBIOS_SUCCESSFUL;
 	}
 
 	if (read_op)
@@ -439,15 +488,20 @@ int pci_bridge_emul_conf_read(struct pci_bridge_emul *bridge, int where,
 	else
 		ret = PCI_BRIDGE_EMUL_NOT_HANDLED;
 
-	if (ret == PCI_BRIDGE_EMUL_NOT_HANDLED)
+	if (ret == PCI_BRIDGE_EMUL_NOT_HANDLED) {
-		*value = le32_to_cpu(cfgspace[reg / 4]);
+		if (cfgspace)
+			*value = le32_to_cpu(cfgspace[reg / 4]);
+		else
+			*value = 0;
+	}
 
 	/*
 	 * Make sure we never return any reserved bit with a value
 	 * different from 0.
 	 */
-	*value &= behavior[reg / 4].ro | behavior[reg / 4].rw |
+	if (behavior)
-		  behavior[reg / 4].w1c;
+		*value &= behavior[reg / 4].ro | behavior[reg / 4].rw |
+			  behavior[reg / 4].w1c;
 
 	if (size == 1)
 		*value = (*value >> (8 * (where & 3))) & 0xff;
@@ -475,11 +529,31 @@ int pci_bridge_emul_conf_write(struct pci_bridge_emul *bridge, int where,
 	__le32 *cfgspace;
 	const struct pci_bridge_reg_behavior *behavior;
 
-	if (bridge->has_pcie && reg >= PCI_CAP_PCIE_END)
+	ret = pci_bridge_emul_conf_read(bridge, reg, 4, &old);
-		return PCIBIOS_SUCCESSFUL;
+	if (ret != PCIBIOS_SUCCESSFUL)
+		return ret;
 
-	if (!bridge->has_pcie && reg >= PCI_BRIDGE_CONF_END)
+	if (reg < PCI_BRIDGE_CONF_END) {
+		/* Emulated PCI space */
+		write_op = bridge->ops->write_base;
+		cfgspace = (__le32 *) &bridge->conf;
+		behavior = bridge->pci_regs_behavior;
+	} else if (reg >= PCI_CAP_PCIE_START && reg < PCI_CAP_PCIE_END && bridge->has_pcie) {
+		/* Our emulated PCIe capability */
+		reg -= PCI_CAP_PCIE_START;
+		write_op = bridge->ops->write_pcie;
+		cfgspace = (__le32 *) &bridge->pcie_conf;
+		behavior = bridge->pcie_cap_regs_behavior;
+	} else if (reg >= PCI_CFG_SPACE_SIZE && bridge->has_pcie) {
+		/* PCIe extended capability space */
+		reg -= PCI_CFG_SPACE_SIZE;
+		write_op = bridge->ops->write_ext;
+		cfgspace = NULL;
+		behavior = NULL;
+	} else {
+		/* Not implemented */
 		return PCIBIOS_SUCCESSFUL;
+	}
 
 	shift = (where & 0x3) * 8;
 
@@ -492,44 +566,38 @@ int pci_bridge_emul_conf_write(struct pci_bridge_emul *bridge, int where,
 	else
 		return PCIBIOS_BAD_REGISTER_NUMBER;
 
-	ret = pci_bridge_emul_conf_read(bridge, reg, 4, &old);
+	if (behavior) {
-	if (ret != PCIBIOS_SUCCESSFUL)
+		/* Keep all bits, except the RW bits */
-		return ret;
+		new = old & (~mask | ~behavior[reg / 4].rw);
 
-	if (bridge->has_pcie && reg >= PCI_CAP_PCIE_START) {
+		/* Update the value of the RW bits */
-		reg -= PCI_CAP_PCIE_START;
+		new |= (value << shift) & (behavior[reg / 4].rw & mask);
-		write_op = bridge->ops->write_pcie;
+
-		cfgspace = (__le32 *) &bridge->pcie_conf;
+		/* Clear the W1C bits */
-		behavior = bridge->pcie_cap_regs_behavior;
+		new &= ~((value << shift) & (behavior[reg / 4].w1c & mask));
 	} else {
-		write_op = bridge->ops->write_base;
+		new = old & ~mask;
-		cfgspace = (__le32 *) &bridge->conf;
+		new |= (value << shift) & mask;
-		behavior = bridge->pci_regs_behavior;
 	}
 
-	/* Keep all bits, except the RW bits */
+	if (cfgspace) {
-	new = old & (~mask | ~behavior[reg / 4].rw);
+		/* Save the new value with the cleared W1C bits into the cfgspace */
+		cfgspace[reg / 4] = cpu_to_le32(new);
+	}
 
-	/* Update the value of the RW bits */
+	if (behavior) {
-	new |= (value << shift) & (behavior[reg / 4].rw & mask);
+		/*
+		 * Clear the W1C bits not specified by the write mask, so that the
+		 * write_op() does not clear them.
+		 */
+		new &= ~(behavior[reg / 4].w1c & ~mask);
 
-	/* Clear the W1C bits */
+		/*
-	new &= ~((value << shift) & (behavior[reg / 4].w1c & mask));
+		 * Set the W1C bits specified by the write mask, so that write_op()
-
+		 * knows about that they are to be cleared.
-	/* Save the new value with the cleared W1C bits into the cfgspace */
+		 */
-	cfgspace[reg / 4] = cpu_to_le32(new);
+		new |= (value << shift) & (behavior[reg / 4].w1c & mask);
-
+	}
-	/*
-	 * Clear the W1C bits not specified by the write mask, so that the
-	 * write_op() does not clear them.
-	 */
-	new &= ~(behavior[reg / 4].w1c & ~mask);
-
-	/*
-	 * Set the W1C bits specified by the write mask, so that write_op()
-	 * knows about that they are to be cleared.
-	 */
-	new |= (value << shift) & (behavior[reg / 4].w1c & mask);
 
 	if (write_op)
 		write_op(bridge, reg, old, new, mask);

drivers/pci/pci-bridge-emul.h

@@ -90,6 +90,14 @@ struct pci_bridge_emul_ops {
 	 */
 	pci_bridge_emul_read_status_t (*read_pcie)(struct pci_bridge_emul *bridge,
 						   int reg, u32 *value);
+
+	/*
+	 * Same as ->read_base(), except it is for reading from the
+	 * PCIe extended capability configuration space.
+	 */
+	pci_bridge_emul_read_status_t (*read_ext)(struct pci_bridge_emul *bridge,
+						  int reg, u32 *value);
+
 	/*
 	 * Called when writing to the regular PCI bridge configuration
 	 * space. old is the current value, new is the new value being
@@ -105,6 +113,13 @@ struct pci_bridge_emul_ops {
 	 */
 	void (*write_pcie)(struct pci_bridge_emul *bridge, int reg,
 			   u32 old, u32 new, u32 mask);
+
+	/*
+	 * Same as ->write_base(), except it is for writing from the
+	 * PCIe extended capability configuration space.
+	 */
+	void (*write_ext)(struct pci_bridge_emul *bridge, int reg,
+			  u32 old, u32 new, u32 mask);
 };
 
 struct pci_bridge_reg_behavior;
@@ -112,15 +127,27 @@ struct pci_bridge_reg_behavior;
 struct pci_bridge_emul {
 	struct pci_bridge_emul_conf conf;
 	struct pci_bridge_emul_pcie_conf pcie_conf;
-	struct pci_bridge_emul_ops *ops;
+	const struct pci_bridge_emul_ops *ops;
 	struct pci_bridge_reg_behavior *pci_regs_behavior;
 	struct pci_bridge_reg_behavior *pcie_cap_regs_behavior;
 	void *data;
 	bool has_pcie;
+	u16 subsystem_vendor_id;
+	u16 subsystem_id;
 };
 
 enum {
-	PCI_BRIDGE_EMUL_NO_PREFETCHABLE_BAR = BIT(0),
+	/*
+	 * PCI bridge does not support forwarding of prefetchable memory
+	 * requests between primary and secondary buses.
+	 */
+	PCI_BRIDGE_EMUL_NO_PREFMEM_FORWARD = BIT(0),
+
+	/*
+	 * PCI bridge does not support forwarding of IO requests between
+	 * primary and secondary buses.
+	 */
+	PCI_BRIDGE_EMUL_NO_IO_FORWARD = BIT(1),
 };
 
 int pci_bridge_emul_init(struct pci_bridge_emul *bridge,

drivers/pci/pci-sysfs.c

@@ -754,8 +754,6 @@ static ssize_t pci_read_config(struct file *filp, struct kobject *kobj,
 		u8 val;
 		pci_user_read_config_byte(dev, off, &val);
 		data[off - init_off] = val;
-		off++;
-		--size;
 	}
 
 	pci_config_pm_runtime_put(dev);
@@ -818,11 +816,8 @@ static ssize_t pci_write_config(struct file *filp, struct kobject *kobj,
 		size -= 2;
 	}
 
-	if (size) {
+	if (size)
 		pci_user_write_config_byte(dev, off, data[off - init_off]);
-		off++;
-		--size;
-	}
 
 	pci_config_pm_runtime_put(dev);
 

drivers/pci/pcie/Kconfig

@@ -43,7 +43,7 @@ config PCIEAER_INJECT
 	  error injection can fake almost all kinds of errors with the
 	  help of a user space helper tool aer-inject, which can be
 	  gotten from:
-	     https://www.kernel.org/pub/linux/utils/pci/aer-inject/
+	     https://git.kernel.org/cgit/linux/kernel/git/gong.chen/aer-inject.git/
 
 #
 # PCI Express ECRC

drivers/pci/pcie/aer_inject.c

@@ -6,7 +6,7 @@
  * trigger various real hardware errors. Software based error
  * injection can fake almost all kinds of errors with the help of a
  * user space helper tool aer-inject, which can be gotten from:
- *   https://www.kernel.org/pub/linux/utils/pci/aer-inject/
+ *   https://git.kernel.org/cgit/linux/kernel/git/gong.chen/aer-inject.git/
  *
  * Copyright 2009 Intel Corporation.
  *     Huang Ying <ying.huang@intel.com>

drivers/pci/pcie/portdrv_pci.c

@@ -178,9 +178,9 @@ static pci_ers_result_t pcie_portdrv_mmio_enabled(struct pci_dev *dev)
  */
 static const struct pci_device_id port_pci_ids[] = {
 	/* handle any PCI-Express port */
-	{ PCI_DEVICE_CLASS(((PCI_CLASS_BRIDGE_PCI << 8) | 0x00), ~0) },
+	{ PCI_DEVICE_CLASS(PCI_CLASS_BRIDGE_PCI_NORMAL, ~0) },
 	/* subtractive decode PCI-to-PCI bridge, class type is 060401h */
-	{ PCI_DEVICE_CLASS(((PCI_CLASS_BRIDGE_PCI << 8) | 0x01), ~0) },
+	{ PCI_DEVICE_CLASS(PCI_CLASS_BRIDGE_PCI_SUBTRACTIVE, ~0) },
 	/* handle any Root Complex Event Collector */
 	{ PCI_DEVICE_CLASS(((PCI_CLASS_SYSTEM_RCEC << 8) | 0x00), ~0) },
 	{ },

drivers/pci/proc.c

@@ -99,9 +99,7 @@ static ssize_t proc_bus_pci_read(struct file *file, char __user *buf,
 		unsigned char val;
 		pci_user_read_config_byte(dev, pos, &val);
 		__put_user(val, buf);
-		buf++;
 		pos++;
-		cnt--;
 	}
 
 	pci_config_pm_runtime_put(dev);
@@ -176,9 +174,7 @@ static ssize_t proc_bus_pci_write(struct file *file, const char __user *buf,
 		unsigned char val;
 		__get_user(val, buf);
 		pci_user_write_config_byte(dev, pos, val);
-		buf++;
 		pos++;
-		cnt--;
 	}
 
 	pci_config_pm_runtime_put(dev);
@@ -188,10 +184,12 @@ static ssize_t proc_bus_pci_write(struct file *file, const char __user *buf,
 	return nbytes;
 }
 
+#ifdef HAVE_PCI_MMAP
 struct pci_filp_private {
 	enum pci_mmap_state mmap_state;
 	int write_combine;
 };
+#endif /* HAVE_PCI_MMAP */
 
 static long proc_bus_pci_ioctl(struct file *file, unsigned int cmd,
 			       unsigned long arg)

drivers/pci/quirks.c

@@ -1811,6 +1811,18 @@ static void quirk_alder_ioapic(struct pci_dev *pdev)
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL,	PCI_DEVICE_ID_INTEL_EESSC,	quirk_alder_ioapic);
 #endif
 
+static void quirk_no_msi(struct pci_dev *dev)
+{
+	pci_info(dev, "avoiding MSI to work around a hardware defect\n");
+	dev->no_msi = 1;
+}
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x4386, quirk_no_msi);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x4387, quirk_no_msi);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x4388, quirk_no_msi);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x4389, quirk_no_msi);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x438a, quirk_no_msi);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_ATI, 0x438b, quirk_no_msi);
+
 static void quirk_pcie_mch(struct pci_dev *pdev)
 {
 	pdev->no_msi = 1;

drivers/pci/setup-bus.c

@@ -994,7 +994,7 @@ static int pbus_size_mem(struct pci_bus *bus, unsigned long mask,
 {
 	struct pci_dev *dev;
 	resource_size_t min_align, align, size, size0, size1;
-	resource_size_t aligns[18]; /* Alignments from 1MB to 128GB */
+	resource_size_t aligns[24]; /* Alignments from 1MB to 8TB */
 	int order, max_order;
 	struct resource *b_res = find_bus_resource_of_type(bus,
 					mask | IORESOURCE_PREFETCH, type);
@@ -1525,7 +1525,7 @@ static void pci_bridge_release_resources(struct pci_bus *bus,
 {
 	struct pci_dev *dev = bus->self;
 	struct resource *r;
-	unsigned int old_flags = 0;
+	unsigned int old_flags;
 	struct resource *b_res;
 	int idx = 1;
 

drivers/pci/vgaarb.c

@@ -1,32 +1,11 @@
+// SPDX-License-Identifier: MIT
 /*
  * vgaarb.c: Implements the VGA arbitration. For details refer to
  * Documentation/gpu/vgaarbiter.rst
  *
- *
  * (C) Copyright 2005 Benjamin Herrenschmidt <benh@kernel.crashing.org>
  * (C) Copyright 2007 Paulo R. Zanoni <przanoni@gmail.com>
  * (C) Copyright 2007, 2009 Tiago Vignatti <vignatti@freedesktop.org>
- *
- * Permission is hereby granted, free of charge, to any person obtaining a
- * copy of this software and associated documentation files (the "Software"),
- * to deal in the Software without restriction, including without limitation
- * the rights to use, copy, modify, merge, publish, distribute, sublicense,
- * and/or sell copies of the Software, and to permit persons to whom the
- * Software is furnished to do so, subject to the following conditions:
- *
- * The above copyright notice and this permission notice (including the next
- * paragraph) shall be included in all copies or substantial portions of the
- * Software.
- *
- * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
- * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
- * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT.  IN NO EVENT SHALL
- * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
- * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
- * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
- * DEALINGS
- * IN THE SOFTWARE.
- *
  */
 
 #define pr_fmt(fmt) "vgaarb: " fmt
@@ -72,6 +51,7 @@ struct vga_device {
 	unsigned int io_norm_cnt;	/* normal IO count */
 	unsigned int mem_norm_cnt;	/* normal MEM count */
 	bool bridge_has_one_vga;
+	bool is_firmware_default;	/* device selected by firmware */
 	unsigned int (*set_decode)(struct pci_dev *pdev, bool decode);
 };
 
@@ -122,8 +102,6 @@ both:
 /* this is only used a cookie - it should not be dereferenced */
 static struct pci_dev *vga_default;
 
-static void vga_arb_device_card_gone(struct pci_dev *pdev);
-
 /* Find somebody in our list */
 static struct vga_device *vgadev_find(struct pci_dev *pdev)
 {
@@ -565,6 +543,144 @@ bail:
 }
 EXPORT_SYMBOL(vga_put);
 
+static bool vga_is_firmware_default(struct pci_dev *pdev)
+{
+#if defined(CONFIG_X86) || defined(CONFIG_IA64)
+	u64 base = screen_info.lfb_base;
+	u64 size = screen_info.lfb_size;
+	u64 limit;
+	resource_size_t start, end;
+	unsigned long flags;
+	int i;
+
+	/* Select the device owning the boot framebuffer if there is one */
+
+	if (screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE)
+		base |= (u64)screen_info.ext_lfb_base << 32;
+
+	limit = base + size;
+
+	/* Does firmware framebuffer belong to us? */
+	for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
+		flags = pci_resource_flags(pdev, i);
+
+		if ((flags & IORESOURCE_MEM) == 0)
+			continue;
+
+		start = pci_resource_start(pdev, i);
+		end  = pci_resource_end(pdev, i);
+
+		if (!start || !end)
+			continue;
+
+		if (base < start || limit >= end)
+			continue;
+
+		return true;
+	}
+#endif
+	return false;
+}
+
+static bool vga_arb_integrated_gpu(struct device *dev)
+{
+#if defined(CONFIG_ACPI)
+	struct acpi_device *adev = ACPI_COMPANION(dev);
+
+	return adev && !strcmp(acpi_device_hid(adev), ACPI_VIDEO_HID);
+#else
+	return false;
+#endif
+}
+
+/*
+ * Return true if vgadev is a better default VGA device than the best one
+ * we've seen so far.
+ */
+static bool vga_is_boot_device(struct vga_device *vgadev)
+{
+	struct vga_device *boot_vga = vgadev_find(vga_default_device());
+	struct pci_dev *pdev = vgadev->pdev;
+	u16 cmd, boot_cmd;
+
+	/*
+	 * We select the default VGA device in this order:
+	 *   Firmware framebuffer (see vga_arb_select_default_device())
+	 *   Legacy VGA device (owns VGA_RSRC_LEGACY_MASK)
+	 *   Non-legacy integrated device (see vga_arb_select_default_device())
+	 *   Non-legacy discrete device (see vga_arb_select_default_device())
+	 *   Other device (see vga_arb_select_default_device())
+	 */
+
+	/*
+	 * We always prefer a firmware default device, so if we've already
+	 * found one, there's no need to consider vgadev.
+	 */
+	if (boot_vga && boot_vga->is_firmware_default)
+		return false;
+
+	if (vga_is_firmware_default(pdev)) {
+		vgadev->is_firmware_default = true;
+		return true;
+	}
+
+	/*
+	 * A legacy VGA device has MEM and IO enabled and any bridges
+	 * leading to it have PCI_BRIDGE_CTL_VGA enabled so the legacy
+	 * resources ([mem 0xa0000-0xbffff], [io 0x3b0-0x3bb], etc) are
+	 * routed to it.
+	 *
+	 * We use the first one we find, so if we've already found one,
+	 * vgadev is no better.
+	 */
+	if (boot_vga &&
+	    (boot_vga->owns & VGA_RSRC_LEGACY_MASK) == VGA_RSRC_LEGACY_MASK)
+		return false;
+
+	if ((vgadev->owns & VGA_RSRC_LEGACY_MASK) == VGA_RSRC_LEGACY_MASK)
+		return true;
+
+	/*
+	 * If we haven't found a legacy VGA device, accept a non-legacy
+	 * device.  It may have either IO or MEM enabled, and bridges may
+	 * not have PCI_BRIDGE_CTL_VGA enabled, so it may not be able to
+	 * use legacy VGA resources.  Prefer an integrated GPU over others.
+	 */
+	pci_read_config_word(pdev, PCI_COMMAND, &cmd);
+	if (cmd & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) {
+
+		/*
+		 * An integrated GPU overrides a previous non-legacy
+		 * device.  We expect only a single integrated GPU, but if
+		 * there are more, we use the *last* because that was the
+		 * previous behavior.
+		 */
+		if (vga_arb_integrated_gpu(&pdev->dev))
+			return true;
+
+		/*
+		 * We prefer the first non-legacy discrete device we find.
+		 * If we already found one, vgadev is no better.
+		 */
+		if (boot_vga) {
+			pci_read_config_word(boot_vga->pdev, PCI_COMMAND,
+					     &boot_cmd);
+			if (boot_cmd & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY))
+				return false;
+		}
+		return true;
+	}
+
+	/*
+	 * vgadev has neither IO nor MEM enabled.  If we haven't found any
+	 * other VGA devices, it is the best candidate so far.
+	 */
+	if (!boot_vga)
+		return true;
+
+	return false;
+}
+
 /*
  * Rules for using a bridge to control a VGA descendant decoding: if a bridge
  * has only one VGA descendant then it can be used to control the VGA routing
@@ -582,8 +698,10 @@ static void vga_arbiter_check_bridge_sharing(struct vga_device *vgadev)
 
 	vgadev->bridge_has_one_vga = true;
 
-	if (list_empty(&vga_list))
+	if (list_empty(&vga_list)) {
+		vgaarb_info(&vgadev->pdev->dev, "bridge control possible\n");
 		return;
+	}
 
 	/* okay iterate the new devices bridge hierarachy */
 	new_bus = vgadev->pdev->bus;
@@ -622,6 +740,11 @@ static void vga_arbiter_check_bridge_sharing(struct vga_device *vgadev)
 		}
 		new_bus = new_bus->parent;
 	}
+
+	if (vgadev->bridge_has_one_vga)
+		vgaarb_info(&vgadev->pdev->dev, "bridge control possible\n");
+	else
+		vgaarb_info(&vgadev->pdev->dev, "no bridge control possible\n");
 }
 
 /*
@@ -692,12 +815,10 @@ static bool vga_arbiter_add_pci_device(struct pci_dev *pdev)
 		bus = bus->parent;
 	}
 
-	/* Deal with VGA default device. Use first enabled one
+	if (vga_is_boot_device(vgadev)) {
-	 * by default if arch doesn't have it's own hook
+		vgaarb_info(&pdev->dev, "setting as boot VGA device%s\n",
-	 */
+			    vga_default_device() ?
-	if (vga_default == NULL &&
+			    " (overriding previous)" : "");
-	    ((vgadev->owns & VGA_RSRC_LEGACY_MASK) == VGA_RSRC_LEGACY_MASK)) {
-		vgaarb_info(&pdev->dev, "setting as boot VGA device\n");
 		vga_set_default_device(pdev);
 	}
 
@@ -741,10 +862,6 @@ static bool vga_arbiter_del_pci_device(struct pci_dev *pdev)
 	/* Remove entry from list */
 	list_del(&vgadev->list);
 	vga_count--;
-	/* Notify userland driver that the device is gone so it discards
-	 * it's copies of the pci_dev pointer
-	 */
-	vga_arb_device_card_gone(pdev);
 
 	/* Wake up all possible waiters */
 	wake_up_all(&vga_wait_queue);
@@ -994,9 +1111,7 @@ static ssize_t vga_arb_read(struct file *file, char __user *buf,
 	if (lbuf == NULL)
 		return -ENOMEM;
 
-	/* Shields against vga_arb_device_card_gone (pci_dev going
+	/* Protects vga_list */
-	 * away), and allows access to vga list
-	 */
 	spin_lock_irqsave(&vga_lock, flags);
 
 	/* If we are targeting the default, use it */
@@ -1013,8 +1128,6 @@ static ssize_t vga_arb_read(struct file *file, char __user *buf,
 		/* Wow, it's not in the list, that shouldn't happen,
 		 * let's fix us up and return invalid card
 		 */
-		if (pdev == priv->target)
-			vga_arb_device_card_gone(pdev);
 		spin_unlock_irqrestore(&vga_lock, flags);
 		len = sprintf(lbuf, "invalid");
 		goto done;
@@ -1022,7 +1135,7 @@ static ssize_t vga_arb_read(struct file *file, char __user *buf,
 
 	/* Fill the buffer with infos */
 	len = snprintf(lbuf, 1024,
-		       "count:%d,PCI:%s,decodes=%s,owns=%s,locks=%s(%d:%d)\n",
+		       "count:%d,PCI:%s,decodes=%s,owns=%s,locks=%s(%u:%u)\n",
 		       vga_decode_count, pci_name(pdev),
 		       vga_iostate_to_str(vgadev->decodes),
 		       vga_iostate_to_str(vgadev->owns),
@@ -1358,10 +1471,6 @@ static int vga_arb_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
-static void vga_arb_device_card_gone(struct pci_dev *pdev)
-{
-}
-
 /*
  * callback any registered clients to let them know we have a
  * change in VGA cards
@@ -1430,111 +1539,10 @@ static struct miscdevice vga_arb_device = {
 	MISC_DYNAMIC_MINOR, "vga_arbiter", &vga_arb_device_fops
 };
 
-#if defined(CONFIG_ACPI)
-static bool vga_arb_integrated_gpu(struct device *dev)
-{
-	struct acpi_device *adev = ACPI_COMPANION(dev);
-
-	return adev && !strcmp(acpi_device_hid(adev), ACPI_VIDEO_HID);
-}
-#else
-static bool vga_arb_integrated_gpu(struct device *dev)
-{
-	return false;
-}
-#endif
-
-static void __init vga_arb_select_default_device(void)
-{
-	struct pci_dev *pdev, *found = NULL;
-	struct vga_device *vgadev;
-
-#if defined(CONFIG_X86) || defined(CONFIG_IA64)
-	u64 base = screen_info.lfb_base;
-	u64 size = screen_info.lfb_size;
-	u64 limit;
-	resource_size_t start, end;
-	unsigned long flags;
-	int i;
-
-	if (screen_info.capabilities & VIDEO_CAPABILITY_64BIT_BASE)
-		base |= (u64)screen_info.ext_lfb_base << 32;
-
-	limit = base + size;
-
-	list_for_each_entry(vgadev, &vga_list, list) {
-		struct device *dev = &vgadev->pdev->dev;
-		/*
-		 * Override vga_arbiter_add_pci_device()'s I/O based detection
-		 * as it may take the wrong device (e.g. on Apple system under
-		 * EFI).
-		 *
-		 * Select the device owning the boot framebuffer if there is
-		 * one.
-		 */
-
-		/* Does firmware framebuffer belong to us? */
-		for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
-			flags = pci_resource_flags(vgadev->pdev, i);
-
-			if ((flags & IORESOURCE_MEM) == 0)
-				continue;
-
-			start = pci_resource_start(vgadev->pdev, i);
-			end  = pci_resource_end(vgadev->pdev, i);
-
-			if (!start || !end)
-				continue;
-
-			if (base < start || limit >= end)
-				continue;
-
-			if (!vga_default_device())
-				vgaarb_info(dev, "setting as boot device\n");
-			else if (vgadev->pdev != vga_default_device())
-				vgaarb_info(dev, "overriding boot device\n");
-			vga_set_default_device(vgadev->pdev);
-		}
-	}
-#endif
-
-	if (!vga_default_device()) {
-		list_for_each_entry_reverse(vgadev, &vga_list, list) {
-			struct device *dev = &vgadev->pdev->dev;
-			u16 cmd;
-
-			pdev = vgadev->pdev;
-			pci_read_config_word(pdev, PCI_COMMAND, &cmd);
-			if (cmd & (PCI_COMMAND_IO | PCI_COMMAND_MEMORY)) {
-				found = pdev;
-				if (vga_arb_integrated_gpu(dev))
-					break;
-			}
-		}
-	}
-
-	if (found) {
-		vgaarb_info(&found->dev, "setting as boot device (VGA legacy resources not available)\n");
-		vga_set_default_device(found);
-		return;
-	}
-
-	if (!vga_default_device()) {
-		vgadev = list_first_entry_or_null(&vga_list,
-						  struct vga_device, list);
-		if (vgadev) {
-			struct device *dev = &vgadev->pdev->dev;
-			vgaarb_info(dev, "setting as boot device (VGA legacy resources not available)\n");
-			vga_set_default_device(vgadev->pdev);
-		}
-	}
-}
-
 static int __init vga_arb_device_init(void)
 {
 	int rc;
 	struct pci_dev *pdev;
-	struct vga_device *vgadev;
 
 	rc = misc_register(&vga_arb_device);
 	if (rc < 0)
@@ -1550,18 +1558,7 @@ static int __init vga_arb_device_init(void)
 			       PCI_ANY_ID, pdev)) != NULL)
 		vga_arbiter_add_pci_device(pdev);
 
-	list_for_each_entry(vgadev, &vga_list, list) {
-		struct device *dev = &vgadev->pdev->dev;
-
-		if (vgadev->bridge_has_one_vga)
-			vgaarb_info(dev, "bridge control possible\n");
-		else
-			vgaarb_info(dev, "no bridge control possible\n");
-	}
-
-	vga_arb_select_default_device();
-
 	pr_info("loaded\n");
 	return rc;
 }
-subsys_initcall(vga_arb_device_init);
+subsys_initcall_sync(vga_arb_device_init);

include/linux/pci.h

@@ -668,6 +668,7 @@ struct pci_bus {
 	struct bin_attribute	*legacy_io;	/* Legacy I/O for this bus */
 	struct bin_attribute	*legacy_mem;	/* Legacy mem */
 	unsigned int		is_added:1;
+	unsigned int		unsafe_warn:1;	/* warned about RW1C config write */
 };
 
 #define to_pci_bus(n)	container_of(n, struct pci_bus, dev)

include/linux/pci_ids.h

@@ -60,6 +60,8 @@
 #define PCI_CLASS_BRIDGE_EISA		0x0602
 #define PCI_CLASS_BRIDGE_MC		0x0603
 #define PCI_CLASS_BRIDGE_PCI		0x0604
+#define PCI_CLASS_BRIDGE_PCI_NORMAL		0x060400
+#define PCI_CLASS_BRIDGE_PCI_SUBTRACTIVE	0x060401
 #define PCI_CLASS_BRIDGE_PCMCIA		0x0605
 #define PCI_CLASS_BRIDGE_NUBUS		0x0606
 #define PCI_CLASS_BRIDGE_CARDBUS	0x0607

include/linux/sizes.h

@@ -47,6 +47,8 @@
 #define SZ_8G				_AC(0x200000000, ULL)
 #define SZ_16G				_AC(0x400000000, ULL)
 #define SZ_32G				_AC(0x800000000, ULL)
+
+#define SZ_1T				_AC(0x10000000000, ULL)
 #define SZ_64T				_AC(0x400000000000, ULL)
 
 #endif /* __LINUX_SIZES_H__ */