Merge tag 'irq-msi-2022-01-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull MSI irq updates from Thomas Gleixner:
"Rework of the MSI interrupt infrastructure.

This is a treewide cleanup and consolidation of MSI interrupt handling
in preparation for further changes in this area which are necessary
to:

- address existing shortcomings in the VFIO area

- support the upcoming Interrupt Message Store functionality which
decouples the message store from the PCI config/MMIO space"

* tag 'irq-msi-2022-01-13' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (94 commits)
genirq/msi: Populate sysfs entry only once
PCI/MSI: Unbreak pci_irq_get_affinity()
genirq/msi: Convert storage to xarray
genirq/msi: Simplify sysfs handling
genirq/msi: Add abuse prevention comment to msi header
genirq/msi: Mop up old interfaces
genirq/msi: Convert to new functions
genirq/msi: Make interrupt allocation less convoluted
platform-msi: Simplify platform device MSI code
platform-msi: Let core code handle MSI descriptors
bus: fsl-mc-msi: Simplify MSI descriptor handling
soc: ti: ti_sci_inta_msi: Remove ti_sci_inta_msi_domain_free_irqs()
soc: ti: ti_sci_inta_msi: Rework MSI descriptor allocation
NTB/msi: Convert to msi_on_each_desc()
PCI: hv: Rework MSI handling
powerpc/mpic_u3msi: Use msi_for_each-desc()
powerpc/fsl_msi: Use msi_for_each_desc()
powerpc/pasemi/msi: Convert to msi_on_each_dec()
powerpc/cell/axon_msi: Convert to msi_on_each_desc()
powerpc/4xx/hsta: Rework MSI handling
...

.clang-format

···
   - 'for_each_migratetype_order'
   - 'for_each_msi_entry'
   - 'for_each_msi_entry_safe'
-  - 'for_each_msi_vector'
   - 'for_each_net'
   - 'for_each_net_continue_reverse'
   - 'for_each_netdev'

Documentation/driver-api/pci/pci.rst

···
 .. kernel-doc:: drivers/pci/search.c
    :export:
 
-.. kernel-doc:: drivers/pci/msi.c
+.. kernel-doc:: drivers/pci/msi/msi.c
    :export:
 
 .. kernel-doc:: drivers/pci/bus.c

arch/mips/pci/msi-octeon.c

···
 	u64 search_mask;
 	int index;
 
+	if (desc->pci.msi_attrib.is_msix)
+		return -EINVAL;
+
 	/*
 	 * Read the MSI config to figure out how many IRQs this device
 	 * wants.  Most devices only want 1, which will give
···
 
 	irq_set_msi_desc(irq, desc);
 	pci_write_msi_msg(irq, &msg);
-	return 0;
-}
-
-int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
-{
-	struct msi_desc *entry;
-	int ret;
-
-	/*
-	 * MSI-X is not supported.
-	 */
-	if (type == PCI_CAP_ID_MSIX)
-		return -EINVAL;
-
-	/*
-	 * If an architecture wants to support multiple MSI, it needs to
-	 * override arch_setup_msi_irqs()
-	 */
-	if (type == PCI_CAP_ID_MSI && nvec > 1)
-		return 1;
-
-	for_each_pci_msi_entry(entry, dev) {
-		ret = arch_setup_msi_irq(dev, entry);
-		if (ret < 0)
-			return ret;
-		if (ret > 0)
-			return -ENOSPC;
-	}
-
 	return 0;
 }
 

arch/powerpc/boot/dts/bluestone.dts

···
 				0x0 0x0 0x0 0x3 &UIC3 0xe 0x4 /* swizzled int C */
 				0x0 0x0 0x0 0x4 &UIC3 0xf 0x4 /* swizzled int D */>;
 		};
-
-		MSI: ppc4xx-msi@C10000000 {
-			compatible = "amcc,ppc4xx-msi", "ppc4xx-msi";
-			reg = < 0xC 0x10000000 0x100
-				0xC 0x10000000 0x100>;
-			sdr-base = <0x36C>;
-			msi-data = <0x00004440>;
-			msi-mask = <0x0000ffe0>;
-			interrupts =<0 1 2 3 4 5 6 7>;
-			interrupt-parent = <&MSI>;
-			#interrupt-cells = <1>;
-			#address-cells = <0>;
-			#size-cells = <0>;
-			msi-available-ranges = <0x0 0x100>;
-			interrupt-map = <
-				0 &UIC3 0x18 1
-				1 &UIC3 0x19 1
-				2 &UIC3 0x1A 1
-				3 &UIC3 0x1B 1
-				4 &UIC3 0x1C 1
-				5 &UIC3 0x1D 1
-				6 &UIC3 0x1E 1
-				7 &UIC3 0x1F 1
-			>;
-		};
 	};
 };

arch/powerpc/boot/dts/canyonlands.dts

···
 				0x0 0x0 0x0 0x3 &UIC3 0x12 0x4 /* swizzled int C */
 				0x0 0x0 0x0 0x4 &UIC3 0x13 0x4 /* swizzled int D */>;
 		};
-
-		MSI: ppc4xx-msi@C10000000 {
-			compatible = "amcc,ppc4xx-msi", "ppc4xx-msi";
-			reg = < 0xC 0x10000000 0x100>;
-			sdr-base = <0x36C>;
-			msi-data = <0x00000000>;
-			msi-mask = <0x44440000>;
-			interrupt-count = <3>;
-			interrupts = <0 1 2 3>;
-			interrupt-parent = <&UIC3>;
-			#interrupt-cells = <1>;
-			#address-cells = <0>;
-			#size-cells = <0>;
-			interrupt-map = <0 &UIC3 0x18 1
-					1 &UIC3 0x19 1
-					2 &UIC3 0x1A 1
-					3 &UIC3 0x1B 1>;
-		};
 	};
 };

arch/powerpc/boot/dts/katmai.dts

···
 				0x0 0x0 0x0 0x4 &UIC3 0xb 0x4 /* swizzled int D */>;
 		};
 
-		MSI: ppc4xx-msi@400300000 {
-				compatible = "amcc,ppc4xx-msi", "ppc4xx-msi";
-				reg = < 0x4 0x00300000 0x100>;
-				sdr-base = <0x3B0>;
-				msi-data = <0x00000000>;
-				msi-mask = <0x44440000>;
-				interrupt-count = <3>;
-				interrupts =<0 1 2 3>;
-				interrupt-parent = <&UIC0>;
-				#interrupt-cells = <1>;
-				#address-cells = <0>;
-				#size-cells = <0>;
-				interrupt-map = <0 &UIC0 0xC 1
-					1 &UIC0 0x0D 1
-					2 &UIC0 0x0E 1
-					3 &UIC0 0x0F 1>;
-		};
-
 		I2O: i2o@400100000 {
 			compatible = "ibm,i2o-440spe";
 			reg = <0x00000004 0x00100000 0x100>;

arch/powerpc/boot/dts/kilauea.dts

···
 				0x0 0x0 0x0 0x3 &UIC2 0xd 0x4 /* swizzled int C */
 				0x0 0x0 0x0 0x4 &UIC2 0xe 0x4 /* swizzled int D */>;
 		};
-
-		MSI: ppc4xx-msi@C10000000 {
-			compatible = "amcc,ppc4xx-msi", "ppc4xx-msi";
-			reg = <0xEF620000 0x100>;
-			sdr-base = <0x4B0>;
-			msi-data = <0x00000000>;
-			msi-mask = <0x44440000>;
-			interrupt-count = <12>;
-			interrupts = <0 1 2 3 4 5 6 7 8 9 0xA 0xB 0xC 0xD>;
-			interrupt-parent = <&UIC2>;
-			#interrupt-cells = <1>;
-			#address-cells = <0>;
-			#size-cells = <0>;
-			interrupt-map = <0 &UIC2 0x10 1
-					1 &UIC2 0x11 1
-					2 &UIC2 0x12 1
-					2 &UIC2 0x13 1
-					2 &UIC2 0x14 1
-					2 &UIC2 0x15 1
-					2 &UIC2 0x16 1
-					2 &UIC2 0x17 1
-					2 &UIC2 0x18 1
-					2 &UIC2 0x19 1
-					2 &UIC2 0x1A 1
-					2 &UIC2 0x1B 1
-					2 &UIC2 0x1C 1
-					3 &UIC2 0x1D 1>;
-		};
 	};
 };

arch/powerpc/boot/dts/redwood.dts

···
 				0x0 0x0 0x0 0x4 &UIC3 0xb 0x4 /* swizzled int D */>;
 		};
 
-		MSI: ppc4xx-msi@400300000 {
-				compatible = "amcc,ppc4xx-msi", "ppc4xx-msi";
-				reg = < 0x4 0x00300000 0x100
-					0x4 0x00300000 0x100>;
-				sdr-base = <0x3B0>;
-				msi-data = <0x00000000>;
-				msi-mask = <0x44440000>;
-				interrupt-count = <3>;
-				interrupts =<0 1 2 3>;
-				interrupt-parent = <&UIC0>;
-				#interrupt-cells = <1>;
-				#address-cells = <0>;
-				#size-cells = <0>;
-				interrupt-map = <0 &UIC0 0xC 1
-					1 &UIC0 0x0D 1
-					2 &UIC0 0x0E 1
-					3 &UIC0 0x0F 1>;
-		};
-
 	};
 
 

arch/powerpc/platforms/40x/Kconfig

···
 	select PPC4xx_PCI_EXPRESS
 	select FORCE_PCI
 	select PCI_MSI
-	select PPC4xx_MSI
 	help
 	  This option enables support for the AMCC PPC405EX evaluation board.
 

arch/powerpc/platforms/44x/Kconfig

···
 	select APM821xx
 	select FORCE_PCI
 	select PCI_MSI
-	select PPC4xx_MSI
 	select PPC4xx_PCI_EXPRESS
 	select IBM_EMAC_RGMII if IBM_EMAC
 	help
···
 	select FORCE_PCI
 	select PPC4xx_PCI_EXPRESS
 	select PCI_MSI
-	select PPC4xx_MSI
 	help
 	  This option enables support for the AMCC PPC440SPe evaluation board.
 
···
 	select FORCE_PCI
 	select PPC4xx_PCI_EXPRESS
 	select PCI_MSI
-	select PPC4xx_MSI
 	select IBM_EMAC_RGMII if IBM_EMAC
 	select IBM_EMAC_ZMII if IBM_EMAC
 	help
···
 	select FORCE_PCI
 	select PPC4xx_PCI_EXPRESS
 	select PCI_MSI
-	select PPC4xx_MSI
 	help
 	  This option enables support for the AMCC PPC460SX Redwood board.
 

arch/powerpc/platforms/4xx/Makefile

···
 obj-$(CONFIG_4xx_SOC)		+= soc.o
 obj-$(CONFIG_PCI)		+= pci.o
 obj-$(CONFIG_PPC4xx_HSTA_MSI)	+= hsta_msi.o
-obj-$(CONFIG_PPC4xx_MSI)	+= msi.o
 obj-$(CONFIG_PPC4xx_CPM)	+= cpm.o
 obj-$(CONFIG_PPC4xx_GPIO)	+= gpio.o

arch/powerpc/platforms/4xx/hsta_msi.c

···
 		return -EINVAL;
 	}
 
-	for_each_pci_msi_entry(entry, dev) {
+	msi_for_each_desc(entry, &dev->dev, MSI_DESC_NOTASSOCIATED) {
 		irq = msi_bitmap_alloc_hwirqs(&ppc4xx_hsta_msi.bmp, 1);
 		if (irq < 0) {
 			pr_debug("%s: Failed to allocate msi interrupt\n",
···
 	struct msi_desc *entry;
 	int irq;
 
-	for_each_pci_msi_entry(entry, dev) {
-		if (!entry->irq)
-			continue;
-
+	msi_for_each_desc(entry, &dev->dev, MSI_DESC_ASSOCIATED) {
 		irq = hsta_find_hwirq_offset(entry->irq);
 
 		/* entry->irq should always be in irq_map */

arch/powerpc/platforms/4xx/msi.c

···
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Adding PCI-E MSI support for PPC4XX SoCs.
- *
- * Copyright (c) 2010, Applied Micro Circuits Corporation
- * Authors:	Tirumala R Marri <[e-mail]>
- *		Feng Kan <[e-mail]>
- */
-
-#include <linux/irq.h>
-#include <linux/pci.h>
-#include <linux/msi.h>
-#include <linux/of_platform.h>
-#include <linux/interrupt.h>
-#include <linux/export.h>
-#include <linux/kernel.h>
-#include <asm/prom.h>
-#include <asm/hw_irq.h>
-#include <asm/ppc-pci.h>
-#include <asm/dcr.h>
-#include <asm/dcr-regs.h>
-#include <asm/msi_bitmap.h>
-
-#define PEIH_TERMADH	0x00
-#define PEIH_TERMADL	0x08
-#define PEIH_MSIED	0x10
-#define PEIH_MSIMK	0x18
-#define PEIH_MSIASS	0x20
-#define PEIH_FLUSH0	0x30
-#define PEIH_FLUSH1	0x38
-#define PEIH_CNTRST	0x48
-
-static int msi_irqs;
-
-struct ppc4xx_msi {
-	u32 msi_addr_lo;
-	u32 msi_addr_hi;
-	void __iomem *msi_regs;
-	int *msi_virqs;
-	struct msi_bitmap bitmap;
-	struct device_node *msi_dev;
-};
-
-static struct ppc4xx_msi ppc4xx_msi;
-
-static int ppc4xx_msi_init_allocator(struct platform_device *dev,
-		struct ppc4xx_msi *msi_data)
-{
-	int err;
-
-	err = msi_bitmap_alloc(&msi_data->bitmap, msi_irqs,
-			      dev->dev.of_node);
-	if (err)
-		return err;
-
-	err = msi_bitmap_reserve_dt_hwirqs(&msi_data->bitmap);
-	if (err < 0) {
-		msi_bitmap_free(&msi_data->bitmap);
-		return err;
-	}
-
-	return 0;
-}
-
-static int ppc4xx_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
-{
-	int int_no = -ENOMEM;
-	unsigned int virq;
-	struct msi_msg msg;
-	struct msi_desc *entry;
-	struct ppc4xx_msi *msi_data = &ppc4xx_msi;
-
-	dev_dbg(&dev->dev, "PCIE-MSI:%s called. vec %x type %d\n",
-		__func__, nvec, type);
-	if (type == PCI_CAP_ID_MSIX)
-		pr_debug("ppc4xx msi: MSI-X untested, trying anyway.\n");
-
-	msi_data->msi_virqs = kmalloc_array(msi_irqs, sizeof(int), GFP_KERNEL);
-	if (!msi_data->msi_virqs)
-		return -ENOMEM;
-
-	for_each_pci_msi_entry(entry, dev) {
-		int_no = msi_bitmap_alloc_hwirqs(&msi_data->bitmap, 1);
-		if (int_no >= 0)
-			break;
-		if (int_no < 0) {
-			pr_debug("%s: fail allocating msi interrupt\n",
-					__func__);
-		}
-		virq = irq_of_parse_and_map(msi_data->msi_dev, int_no);
-		if (!virq) {
-			dev_err(&dev->dev, "%s: fail mapping irq\n", __func__);
-			msi_bitmap_free_hwirqs(&msi_data->bitmap, int_no, 1);
-			return -ENOSPC;
-		}
-		dev_dbg(&dev->dev, "%s: virq = %d\n", __func__, virq);
-
-		/* Setup msi address space */
-		msg.address_hi = msi_data->msi_addr_hi;
-		msg.address_lo = msi_data->msi_addr_lo;
-
-		irq_set_msi_desc(virq, entry);
-		msg.data = int_no;
-		pci_write_msi_msg(virq, &msg);
-	}
-	return 0;
-}
-
-void ppc4xx_teardown_msi_irqs(struct pci_dev *dev)
-{
-	struct msi_desc *entry;
-	struct ppc4xx_msi *msi_data = &ppc4xx_msi;
-	irq_hw_number_t hwirq;
-
-	dev_dbg(&dev->dev, "PCIE-MSI: tearing down msi irqs\n");
-
-	for_each_pci_msi_entry(entry, dev) {
-		if (!entry->irq)
-			continue;
-		hwirq = virq_to_hw(entry->irq);
-		irq_set_msi_desc(entry->irq, NULL);
-		irq_dispose_mapping(entry->irq);
-		msi_bitmap_free_hwirqs(&msi_data->bitmap, hwirq, 1);
-	}
-}
-
-static int ppc4xx_setup_pcieh_hw(struct platform_device *dev,
-				 struct resource res, struct ppc4xx_msi *msi)
-{
-	const u32 *msi_data;
-	const u32 *msi_mask;
-	const u32 *sdr_addr;
-	dma_addr_t msi_phys;
-	void *msi_virt;
-	int err;
-
-	sdr_addr = of_get_property(dev->dev.of_node, "sdr-base", NULL);
-	if (!sdr_addr)
-		return -EINVAL;
-
-	msi_data = of_get_property(dev->dev.of_node, "msi-data", NULL);
-	if (!msi_data)
-		return -EINVAL;
-
-	msi_mask = of_get_property(dev->dev.of_node, "msi-mask", NULL);
-	if (!msi_mask)
-		return -EINVAL;
-
-	msi->msi_dev = of_find_node_by_name(NULL, "ppc4xx-msi");
-	if (!msi->msi_dev)
-		return -ENODEV;
-
-	msi->msi_regs = of_iomap(msi->msi_dev, 0);
-	if (!msi->msi_regs) {
-		dev_err(&dev->dev, "of_iomap failed\n");
-		err = -ENOMEM;
-		goto node_put;
-	}
-	dev_dbg(&dev->dev, "PCIE-MSI: msi register mapped 0x%x 0x%x\n",
-		(u32) (msi->msi_regs + PEIH_TERMADH), (u32) (msi->msi_regs));
-
-	msi_virt = dma_alloc_coherent(&dev->dev, 64, &msi_phys, GFP_KERNEL);
-	if (!msi_virt) {
-		err = -ENOMEM;
-		goto iounmap;
-	}
-	msi->msi_addr_hi = upper_32_bits(msi_phys);
-	msi->msi_addr_lo = lower_32_bits(msi_phys & 0xffffffff);
-	dev_dbg(&dev->dev, "PCIE-MSI: msi address high 0x%x, low 0x%x\n",
-		msi->msi_addr_hi, msi->msi_addr_lo);
-
-	mtdcri(SDR0, *sdr_addr, upper_32_bits(res.start));	/*HIGH addr */
-	mtdcri(SDR0, *sdr_addr + 1, lower_32_bits(res.start));	/* Low addr */
-
-	/* Progam the Interrupt handler Termination addr registers */
-	out_be32(msi->msi_regs + PEIH_TERMADH, msi->msi_addr_hi);
-	out_be32(msi->msi_regs + PEIH_TERMADL, msi->msi_addr_lo);
-
-	/* Program MSI Expected data and Mask bits */
-	out_be32(msi->msi_regs + PEIH_MSIED, *msi_data);
-	out_be32(msi->msi_regs + PEIH_MSIMK, *msi_mask);
-
-	dma_free_coherent(&dev->dev, 64, msi_virt, msi_phys);
-
-	return 0;
-
-iounmap:
-	iounmap(msi->msi_regs);
-node_put:
-	of_node_put(msi->msi_dev);
-	return err;
-}
-
-static int ppc4xx_of_msi_remove(struct platform_device *dev)
-{
-	struct ppc4xx_msi *msi = dev->dev.platform_data;
-	int i;
-	int virq;
-
-	for (i = 0; i < msi_irqs; i++) {
-		virq = msi->msi_virqs[i];
-		if (virq)
-			irq_dispose_mapping(virq);
-	}
-
-	if (msi->bitmap.bitmap)
-		msi_bitmap_free(&msi->bitmap);
-	iounmap(msi->msi_regs);
-	of_node_put(msi->msi_dev);
-
-	return 0;
-}
-
-static int ppc4xx_msi_probe(struct platform_device *dev)
-{
-	struct ppc4xx_msi *msi;
-	struct resource res;
-	int err = 0;
-	struct pci_controller *phb;
-
-	dev_dbg(&dev->dev, "PCIE-MSI: Setting up MSI support...\n");
-
-	msi = devm_kzalloc(&dev->dev, sizeof(*msi), GFP_KERNEL);
-	if (!msi)
-		return -ENOMEM;
-	dev->dev.platform_data = msi;
-
-	/* Get MSI ranges */
-	err = of_address_to_resource(dev->dev.of_node, 0, &res);
-	if (err) {
-		dev_err(&dev->dev, "%pOF resource error!\n", dev->dev.of_node);
-		return err;
-	}
-
-	msi_irqs = of_irq_count(dev->dev.of_node);
-	if (!msi_irqs)
-		return -ENODEV;
-
-	err = ppc4xx_setup_pcieh_hw(dev, res, msi);
-	if (err)
-		return err;
-
-	err = ppc4xx_msi_init_allocator(dev, msi);
-	if (err) {
-		dev_err(&dev->dev, "Error allocating MSI bitmap\n");
-		goto error_out;
-	}
-	ppc4xx_msi = *msi;
-
-	list_for_each_entry(phb, &hose_list, list_node) {
-		phb->controller_ops.setup_msi_irqs = ppc4xx_setup_msi_irqs;
-		phb->controller_ops.teardown_msi_irqs = ppc4xx_teardown_msi_irqs;
-	}
-	return 0;
-
-error_out:
-	ppc4xx_of_msi_remove(dev);
-	return err;
-}
-static const struct of_device_id ppc4xx_msi_ids[] = {
-	{
-		.compatible = "amcc,ppc4xx-msi",
-	},
-	{}
-};
-static struct platform_driver ppc4xx_msi_driver = {
-	.probe = ppc4xx_msi_probe,
-	.remove = ppc4xx_of_msi_remove,
-	.driver = {
-		   .name = "ppc4xx-msi",
-		   .of_match_table = ppc4xx_msi_ids,
-		   },
-
-};
-
-static __init int ppc4xx_msi_init(void)
-{
-	return platform_driver_register(&ppc4xx_msi_driver);
-}
-
-subsys_initcall(ppc4xx_msi_init);

arch/powerpc/platforms/cell/axon_msi.c

···
 static int setup_msi_msg_address(struct pci_dev *dev, struct msi_msg *msg)
 {
 	struct device_node *dn;
-	struct msi_desc *entry;
 	int len;
 	const u32 *prop;
 
···
 		return -ENODEV;
 	}
 
-	entry = first_pci_msi_entry(dev);
-
 	for (; dn; dn = of_get_next_parent(dn)) {
-		if (entry->msi_attrib.is_64) {
+		if (!dev->no_64bit_msi) {
 			prop = of_get_property(dn, "msi-address-64", &len);
 			if (prop)
 				break;
···
 	if (rc)
 		return rc;
 
-	for_each_pci_msi_entry(entry, dev) {
+	msi_for_each_desc(entry, &dev->dev, MSI_DESC_NOTASSOCIATED) {
 		virq = irq_create_direct_mapping(msic->irq_domain);
 		if (!virq) {
 			dev_warn(&dev->dev,
···
 
 	dev_dbg(&dev->dev, "axon_msi: tearing down msi irqs\n");
 
-	for_each_pci_msi_entry(entry, dev) {
-		if (!entry->irq)
-			continue;
-
+	msi_for_each_desc(entry, &dev->dev, MSI_DESC_ASSOCIATED) {
 		irq_set_msi_desc(entry->irq, NULL);
 		irq_dispose_mapping(entry->irq);
 	}

arch/powerpc/platforms/pasemi/msi.c

···
 
 	pr_debug("pasemi_msi_teardown_msi_irqs, pdev %p\n", pdev);
 
-	for_each_pci_msi_entry(entry, pdev) {
-		if (!entry->irq)
-			continue;
-
+	msi_for_each_desc(entry, &pdev->dev, MSI_DESC_ASSOCIATED) {
 		hwirq = virq_to_hw(entry->irq);
 		irq_set_msi_desc(entry->irq, NULL);
 		irq_dispose_mapping(entry->irq);
 		msi_bitmap_free_hwirqs(&msi_mpic->msi_bitmap, hwirq, ALLOC_CHUNK);
 	}
-
-	return;
 }
 
 static int pasemi_msi_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
···
 	msg.address_hi = 0;
 	msg.address_lo = PASEMI_MSI_ADDR;
 
-	for_each_pci_msi_entry(entry, pdev) {
+	msi_for_each_desc(entry, &pdev->dev, MSI_DESC_NOTASSOCIATED) {
 		/* Allocate 16 interrupts for now, since that's the grouping for
 		 * affinity. This can be changed later if it turns out 32 is too
 		 * few MSIs for someone, but restrictions will apply to how the

arch/powerpc/platforms/powernv/pci-ioda.c

···
 	int rc;
 
 	rc = __pnv_pci_ioda_msi_setup(phb, pdev, d->hwirq,
-				      entry->msi_attrib.is_64, msg);
+				      entry->pci.msi_attrib.is_64, msg);
 	if (rc)
 		dev_err(&pdev->dev, "Failed to setup %s-bit MSI #%ld : %d\n",
-			entry->msi_attrib.is_64 ? "64" : "32", d->hwirq, rc);
+			entry->pci.msi_attrib.is_64 ? "64" : "32", d->hwirq, rc);
 }
 
 /*

arch/powerpc/platforms/pseries/msi.c

···
 	return request;
 }
 
-static int check_msix_entries(struct pci_dev *pdev)
-{
-	struct msi_desc *entry;
-	int expected;
-
-	/* There's no way for us to express to firmware that we want
-	 * a discontiguous, or non-zero based, range of MSI-X entries.
-	 * So we must reject such requests. */
-
-	expected = 0;
-	for_each_pci_msi_entry(entry, pdev) {
-		if (entry->msi_attrib.entry_nr != expected) {
-			pr_debug("rtas_msi: bad MSI-X entries.\n");
-			return -EINVAL;
-		}
-		expected++;
-	}
-
-	return 0;
-}
-
 static void rtas_hack_32bit_msi_gen2(struct pci_dev *pdev)
 {
 	u32 addr_hi, addr_lo;
···
 
 	if (quota && quota < nvec)
 		return quota;
-
-	if (type == PCI_CAP_ID_MSIX && check_msix_entries(pdev))
-		return -EINVAL;
 
 	/*
 	 * Firmware currently refuse any non power of two allocation
···
 				   int nvec, msi_alloc_info_t *arg)
 {
 	struct pci_dev *pdev = to_pci_dev(dev);
-	struct msi_desc *desc = first_pci_msi_entry(pdev);
-	int type = desc->msi_attrib.is_msix ? PCI_CAP_ID_MSIX : PCI_CAP_ID_MSI;
+	int type = pdev->msix_enabled ? PCI_CAP_ID_MSIX : PCI_CAP_ID_MSI;
 
 	return rtas_prepare_msi_irqs(pdev, nvec, type, arg);
 }
···
 	.irq_write_msi_msg	= pseries_msi_write_msg,
 };
 
+
+/*
+ * Set MSI_FLAG_MSIX_CONTIGUOUS as there is no way to express to
+ * firmware to request a discontiguous or non-zero based range of
+ * MSI-X entries. Core code will reject such setup attempts.
+ */
 static struct msi_domain_info pseries_msi_domain_info = {
 	.flags = (MSI_FLAG_USE_DEF_DOM_OPS | MSI_FLAG_USE_DEF_CHIP_OPS |
-		  MSI_FLAG_MULTI_PCI_MSI  | MSI_FLAG_PCI_MSIX),
+		  MSI_FLAG_MULTI_PCI_MSI  | MSI_FLAG_PCI_MSIX |
+		  MSI_FLAG_MSIX_CONTIGUOUS),
 	.ops   = &pseries_pci_msi_domain_ops,
 	.chip  = &pseries_pci_msi_irq_chip,
 };
···
 	int hwirq;
 	int i, ret;
 
-	hwirq = rtas_query_irq_number(pci_get_pdn(pdev), desc->msi_attrib.entry_nr);
+	hwirq = rtas_query_irq_number(pci_get_pdn(pdev), desc->msi_index);
 	if (hwirq < 0) {
 		dev_err(&pdev->dev, "Failed to query HW IRQ: %d\n", hwirq);
 		return hwirq;

arch/powerpc/sysdev/Kconfig

···
 	depends on PCI_MSI
 	depends on PCI && 4xx
 
-config PPC4xx_MSI
-	bool
-	depends on PCI_MSI
-	depends on PCI && 4xx
-
 config PPC_MSI_BITMAP
 	bool
 	depends on PCI_MSI
 	default y if MPIC
 	default y if FSL_PCI
-	default y if PPC4xx_MSI
 	default y if PPC_POWERNV
 
 source "arch/powerpc/sysdev/xics/Kconfig"

arch/powerpc/sysdev/fsl_msi.c

···
 	struct fsl_msi *msi_data;
 	irq_hw_number_t hwirq;
 
-	for_each_pci_msi_entry(entry, pdev) {
-		if (!entry->irq)
-			continue;
+	msi_for_each_desc(entry, &pdev->dev, MSI_DESC_ASSOCIATED) {
 		hwirq = virq_to_hw(entry->irq);
 		msi_data = irq_get_chip_data(entry->irq);
 		irq_set_msi_desc(entry->irq, NULL);
 		irq_dispose_mapping(entry->irq);
 		msi_bitmap_free_hwirqs(&msi_data->bitmap, hwirq, 1);
 	}
-
-	return;
 }
 
 static void fsl_compose_msi_msg(struct pci_dev *pdev, int hwirq,
···
 		}
 	}
 
-	for_each_pci_msi_entry(entry, pdev) {
+	msi_for_each_desc(entry, &pdev->dev, MSI_DESC_NOTASSOCIATED) {
 		/*
 		 * Loop over all the MSI devices until we find one that has an
 		 * available interrupt.

arch/powerpc/sysdev/mpic_u3msi.c

···
 	struct msi_desc *entry;
 	irq_hw_number_t hwirq;
 
-	for_each_pci_msi_entry(entry, pdev) {
-		if (!entry->irq)
-			continue;
-
+	msi_for_each_desc(entry, &pdev->dev, MSI_DESC_ASSOCIATED) {
 		hwirq = virq_to_hw(entry->irq);
 		irq_set_msi_desc(entry->irq, NULL);
 		irq_dispose_mapping(entry->irq);
 		msi_bitmap_free_hwirqs(&msi_mpic->msi_bitmap, hwirq, 1);
 	}
-
-	return;
 }
 
 static int u3msi_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
···
 		return -ENXIO;
 	}
 
-	for_each_pci_msi_entry(entry, pdev) {
+	msi_for_each_desc(entry, &pdev->dev, MSI_DESC_NOTASSOCIATED) {
 		hwirq = msi_bitmap_alloc_hwirqs(&msi_mpic->msi_bitmap, 1);
 		if (hwirq < 0) {
 			pr_debug("u3msi: failed allocating hwirq\n");

arch/s390/pci/pci_irq.c

···
 
 	/* Request MSI interrupts */
 	hwirq = bit;
-	for_each_pci_msi_entry(msi, pdev) {
+	msi_for_each_desc(msi, &pdev->dev, MSI_DESC_NOTASSOCIATED) {
 		rc = -EIO;
 		if (hwirq - bit >= msi_vecs)
 			break;
···
 		return;
 
 	/* Release MSI interrupts */
-	for_each_pci_msi_entry(msi, pdev) {
-		if (!msi->irq)
-			continue;
+	msi_for_each_desc(msi, &pdev->dev, MSI_DESC_ASSOCIATED) {
 		irq_set_msi_desc(msi->irq, NULL);
 		irq_free_desc(msi->irq);
 		msi->msg.address_lo = 0;
···
 		airq_iv_free(zpci_ibv[0], zdev->msi_first_bit, zdev->msi_nr_irqs);
 }
 
-void arch_restore_msi_irqs(struct pci_dev *pdev)
+bool arch_restore_msi_irqs(struct pci_dev *pdev)
 {
 	struct zpci_dev *zdev = to_zpci(pdev);
 
 	if (!zdev->irqs_registered)
 		zpci_set_irq(zdev);
-	default_restore_msi_irqs(pdev);
+	return true;
 }
 
 static struct airq_struct zpci_airq = {

arch/sparc/kernel/pci_msi.c

···
 	msiqid = pick_msiq(pbm);
 
 	err = ops->msi_setup(pbm, msiqid, msi,
-			     (entry->msi_attrib.is_64 ? 1 : 0));
+			     (entry->pci.msi_attrib.is_64 ? 1 : 0));
 	if (err)
 		goto out_msi_free;
 
 	pbm->msi_irq_table[msi - pbm->msi_first] = *irq_p;
 
-	if (entry->msi_attrib.is_64) {
+	if (entry->pci.msi_attrib.is_64) {
 		msg.address_hi = pbm->msi64_start >> 32;
 		msg.address_lo = pbm->msi64_start & 0xffffffff;
 	} else {

arch/x86/hyperv/irqdomain.c

···
 	return hv_unmap_interrupt(hv_build_pci_dev_id(dev).as_uint64, old_entry);
 }
 
-static void hv_teardown_msi_irq_common(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
+static void hv_teardown_msi_irq(struct pci_dev *dev, struct irq_data *irqd)
 {
-	u64 status;
 	struct hv_interrupt_entry old_entry;
-	struct irq_desc *desc;
-	struct irq_data *data;
 	struct msi_msg msg;
+	u64 status;
 
-	desc = irq_to_desc(irq);
-	if (!desc) {
-		pr_debug("%s: no irq desc\n", __func__);
-		return;
-	}
-
-	data = &desc->irq_data;
-	if (!data) {
-		pr_debug("%s: no irq data\n", __func__);
-		return;
-	}
-
-	if (!data->chip_data) {
+	if (!irqd->chip_data) {
 		pr_debug("%s: no chip data\n!", __func__);
 		return;
 	}
 
-	old_entry = *(struct hv_interrupt_entry *)data->chip_data;
+	old_entry = *(struct hv_interrupt_entry *)irqd->chip_data;
 	entry_to_msi_msg(&old_entry, &msg);
 
-	kfree(data->chip_data);
-	data->chip_data = NULL;
+	kfree(irqd->chip_data);
+	irqd->chip_data = NULL;
 
 	status = hv_unmap_msi_interrupt(dev, &old_entry);
 
-	if (status != HV_STATUS_SUCCESS) {
+	if (status != HV_STATUS_SUCCESS)
 		pr_err("%s: hypercall failed, status %lld\n", __func__, status);
-		return;
-	}
 }
 
-static void hv_msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
+static void hv_msi_free_irq(struct irq_domain *domain,
+			    struct msi_domain_info *info, unsigned int virq)
 {
-	int i;
-	struct msi_desc *entry;
-	struct pci_dev *pdev;
+	struct irq_data *irqd = irq_get_irq_data(virq);
+	struct msi_desc *desc;
 
-	if (WARN_ON_ONCE(!dev_is_pci(dev)))
+	if (!irqd)
 		return;
 
-	pdev = to_pci_dev(dev);
+	desc = irq_data_get_msi_desc(irqd);
+	if (!desc || !desc->irq || WARN_ON_ONCE(!dev_is_pci(desc->dev)))
+		return;
 
-	for_each_pci_msi_entry(entry, pdev) {
-		if (entry->irq) {
-			for (i = 0; i < entry->nvec_used; i++) {
-				hv_teardown_msi_irq_common(pdev, entry, entry->irq + i);
-				irq_domain_free_irqs(entry->irq + i, 1);
-			}
-		}
-	}
+	hv_teardown_msi_irq(to_pci_dev(desc->dev), irqd);
 }
 
 /*
···
 };
 
 static struct msi_domain_ops pci_msi_domain_ops = {
-	.domain_free_irqs	= hv_msi_domain_free_irqs,
+	.msi_free		= hv_msi_free_irq,
 	.msi_prepare		= pci_msi_prepare,
 };
 

arch/x86/include/asm/x86_init.h

···
 	struct x86_hyper_runtime hyper;
 };
 
-struct pci_dev;
-
-struct x86_msi_ops {
-	void (*restore_msi_irqs)(struct pci_dev *dev);
-};
-
 struct x86_apic_ops {
 	unsigned int	(*io_apic_read)   (unsigned int apic, unsigned int reg);
 	void		(*restore)(void);

arch/x86/include/asm/xen/hypervisor.h

···
 }
 #endif
 
+struct pci_dev;
+
+#ifdef CONFIG_XEN_PV_DOM0
+bool xen_initdom_restore_msi(struct pci_dev *dev);
+#else
+static inline bool xen_initdom_restore_msi(struct pci_dev *dev) { return true; }
+#endif
+
 #ifdef CONFIG_HOTPLUG_CPU
 void xen_arch_register_cpu(int num);
 void xen_arch_unregister_cpu(int num);

arch/x86/kernel/apic/msi.c

···
 #include <asm/hw_irq.h>
 #include <asm/apic.h>
 #include <asm/irq_remapping.h>
+#include <asm/xen/hypervisor.h>
 
 struct irq_domain *x86_pci_msi_default_domain __ro_after_init;
 
···
 int pci_msi_prepare(struct irq_domain *domain, struct device *dev, int nvec,
 		    msi_alloc_info_t *arg)
 {
-	struct pci_dev *pdev = to_pci_dev(dev);
-	struct msi_desc *desc = first_pci_msi_entry(pdev);
-
 	init_irq_alloc_info(arg, NULL);
-	if (desc->msi_attrib.is_msix) {
+	if (to_pci_dev(dev)->msix_enabled) {
 		arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSIX;
 	} else {
 		arg->type = X86_IRQ_ALLOC_TYPE_PCI_MSI;
···
 	irq_domain_free_irqs(irq, 1);
 }
 #endif
+
+bool arch_restore_msi_irqs(struct pci_dev *dev)
+{
+	return xen_initdom_restore_msi(dev);
+}

arch/x86/kernel/x86_init.c

···
 
 EXPORT_SYMBOL_GPL(x86_platform);
 
-#if defined(CONFIG_PCI_MSI)
-struct x86_msi_ops x86_msi __ro_after_init = {
-	.restore_msi_irqs	= default_restore_msi_irqs,
-};
-
-/* MSI arch specific hooks */
-void arch_restore_msi_irqs(struct pci_dev *dev)
-{
-	x86_msi.restore_msi_irqs(dev);
-}
-#endif
-
 struct x86_apic_ops x86_apic_ops __ro_after_init = {
 	.io_apic_read	= native_io_apic_read,
 	.restore	= native_restore_boot_irq_mode,

arch/x86/pci/xen.c

···
 	if (ret)
 		goto error;
 	i = 0;
-	for_each_pci_msi_entry(msidesc, dev) {
+	msi_for_each_desc(msidesc, &dev->dev, MSI_DESC_NOTASSOCIATED) {
 		irq = xen_bind_pirq_msi_to_irq(dev, msidesc, v[i],
 					       (type == PCI_CAP_ID_MSI) ? nvec : 1,
 					       (type == PCI_CAP_ID_MSIX) ?
···
 	if (type == PCI_CAP_ID_MSI && nvec > 1)
 		return 1;
 
-	for_each_pci_msi_entry(msidesc, dev) {
+	msi_for_each_desc(msidesc, &dev->dev, MSI_DESC_NOTASSOCIATED) {
 		pirq = xen_allocate_pirq_msi(dev, msidesc);
 		if (pirq < 0) {
 			irq = -ENODEV;
···
 	int ret = 0;
 	struct msi_desc *msidesc;
 
-	for_each_pci_msi_entry(msidesc, dev) {
+	msi_for_each_desc(msidesc, &dev->dev, MSI_DESC_NOTASSOCIATED) {
 		struct physdev_map_pirq map_irq;
 		domid_t domid;
 
···
 				return -EINVAL;
 
 			map_irq.table_base = pci_resource_start(dev, bir);
-			map_irq.entry_nr = msidesc->msi_attrib.entry_nr;
+			map_irq.entry_nr = msidesc->msi_index;
 		}
 
 		ret = -EINVAL;
···
 	return ret;
 }
 
-static void xen_initdom_restore_msi_irqs(struct pci_dev *dev)
+bool xen_initdom_restore_msi(struct pci_dev *dev)
 {
 	int ret = 0;
+
+	if (!xen_initial_domain())
+		return true;
 
 	if (pci_seg_supported) {
 		struct physdev_pci_device restore_ext;
···
 		ret = HYPERVISOR_physdev_op(PHYSDEVOP_restore_msi, &restore);
 		WARN(ret && ret != -ENOSYS, "restore_msi -> %d\n", ret);
 	}
+	return false;
 }
 #else /* CONFIG_XEN_PV_DOM0 */
 #define xen_initdom_setup_msi_irqs	NULL
-#define xen_initdom_restore_msi_irqs	NULL
 #endif /* !CONFIG_XEN_PV_DOM0 */
 
 static void xen_teardown_msi_irqs(struct pci_dev *dev)
···
 	struct msi_desc *msidesc;
 	int i;
 
-	for_each_pci_msi_entry(msidesc, dev) {
-		if (msidesc->irq) {
-			for (i = 0; i < msidesc->nvec_used; i++)
-				xen_destroy_irq(msidesc->irq + i);
-		}
+	msi_for_each_desc(msidesc, &dev->dev, MSI_DESC_ASSOCIATED) {
+		for (i = 0; i < msidesc->nvec_used; i++)
+			xen_destroy_irq(msidesc->irq + i);
 	}
 }
 
 static void xen_pv_teardown_msi_irqs(struct pci_dev *dev)
 {
-	struct msi_desc *msidesc = first_pci_msi_entry(dev);
-
-	if (msidesc->msi_attrib.is_msix)
+	if (dev->msix_enabled)
 		xen_pci_frontend_disable_msix(dev);
 	else
 		xen_pci_frontend_disable_msi(dev);
···
 	if (WARN_ON_ONCE(!dev_is_pci(dev)))
 		return -EINVAL;
 
-	if (first_msi_entry(dev)->msi_attrib.is_msix)
-		type = PCI_CAP_ID_MSIX;
-	else
-		type = PCI_CAP_ID_MSI;
+	type = to_pci_dev(dev)->msix_enabled ? PCI_CAP_ID_MSIX : PCI_CAP_ID_MSI;
 
 	return xen_msi_ops.setup_msi_irqs(to_pci_dev(dev), nvec, type);
 }
···
 static __init void xen_setup_pci_msi(void)
 {
 	if (xen_pv_domain()) {
-		if (xen_initial_domain()) {
+		if (xen_initial_domain())
 			xen_msi_ops.setup_msi_irqs = xen_initdom_setup_msi_irqs;
-			x86_msi.restore_msi_irqs = xen_initdom_restore_msi_irqs;
-		} else {
+		else
 			xen_msi_ops.setup_msi_irqs = xen_setup_msi_irqs;
-		}
 		xen_msi_ops.teardown_msi_irqs = xen_pv_teardown_msi_irqs;
 		pci_msi_ignore_mask = 1;
 	} else if (xen_hvm_domain()) {

drivers/base/core.c

···
 	INIT_LIST_HEAD(&dev->devres_head);
 	device_pm_init(dev);
 	set_dev_node(dev, NUMA_NO_NODE);
-#ifdef CONFIG_GENERIC_MSI_IRQ
-	raw_spin_lock_init(&dev->msi_lock);
-	INIT_LIST_HEAD(&dev->msi_list);
-#endif
 	INIT_LIST_HEAD(&dev->links.consumers);
 	INIT_LIST_HEAD(&dev->links.suppliers);
 	INIT_LIST_HEAD(&dev->links.defer_sync);

drivers/base/platform-msi.c

···
 struct platform_msi_priv_data {
 	struct device			*dev;
 	void				*host_data;
-	const struct attribute_group    **msi_irq_groups;
 	msi_alloc_info_t		arg;
 	irq_write_msi_msg_t		write_msg;
 	int				devid;
···
  */
 static irq_hw_number_t platform_msi_calc_hwirq(struct msi_desc *desc)
 {
-	u32 devid;
+	u32 devid = desc->dev->msi.data->platform_data->devid;
 
-	devid = desc->platform.msi_priv_data->devid;
-
-	return (devid << (32 - DEV_ID_SHIFT)) | desc->platform.msi_index;
+	return (devid << (32 - DEV_ID_SHIFT)) | desc->msi_index;
 }
 
 static void platform_msi_set_desc(msi_alloc_info_t *arg, struct msi_desc *desc)
···
 static void platform_msi_write_msg(struct irq_data *data, struct msi_msg *msg)
 {
 	struct msi_desc *desc = irq_data_get_msi_desc(data);
-	struct platform_msi_priv_data *priv_data;
 
-	priv_data = desc->platform.msi_priv_data;
-
-	priv_data->write_msg(desc, msg);
+	desc->dev->msi.data->platform_data->write_msg(desc, msg);
 }
 
 static void platform_msi_update_chip_ops(struct msi_domain_info *info)
···
 	if (WARN_ON((info->flags & MSI_FLAG_LEVEL_CAPABLE) &&
 		    !(chip->flags & IRQCHIP_SUPPORTS_LEVEL_MSI)))
 		info->flags &= ~MSI_FLAG_LEVEL_CAPABLE;
-}
-
-static void platform_msi_free_descs(struct device *dev, int base, int nvec)
-{
-	struct msi_desc *desc, *tmp;
-
-	list_for_each_entry_safe(desc, tmp, dev_to_msi_list(dev), list) {
-		if (desc->platform.msi_index >= base &&
-		    desc->platform.msi_index < (base + nvec)) {
-			list_del(&desc->list);
-			free_msi_entry(desc);
-		}
-	}
-}
-
-static int platform_msi_alloc_descs_with_irq(struct device *dev, int virq,
-					     int nvec,
-					     struct platform_msi_priv_data *data)
-
-{
-	struct msi_desc *desc;
-	int i, base = 0;
-
-	if (!list_empty(dev_to_msi_list(dev))) {
-		desc = list_last_entry(dev_to_msi_list(dev),
-				       struct msi_desc, list);
-		base = desc->platform.msi_index + 1;
-	}
-
-	for (i = 0; i < nvec; i++) {
-		desc = alloc_msi_entry(dev, 1, NULL);
-		if (!desc)
-			break;
-
-		desc->platform.msi_priv_data = data;
-		desc->platform.msi_index = base + i;
-		desc->irq = virq ? virq + i : 0;
-
-		list_add_tail(&desc->list, dev_to_msi_list(dev));
-	}
-
-	if (i != nvec) {
-		/* Clean up the mess */
-		platform_msi_free_descs(dev, base, nvec);
-
-		return -ENOMEM;
-	}
-
-	return 0;
-}
-
-static int platform_msi_alloc_descs(struct device *dev, int nvec,
-				    struct platform_msi_priv_data *data)
-
-{
-	return platform_msi_alloc_descs_with_irq(dev, 0, nvec, data);
 }
 
 /**
···
 		platform_msi_update_dom_ops(info);
 	if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
 		platform_msi_update_chip_ops(info);
+	info->flags |= MSI_FLAG_DEV_SYSFS | MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS |
+		       MSI_FLAG_FREE_MSI_DESCS;
 
 	domain = msi_create_irq_domain(fwnode, info, parent);
 	if (domain)
···
 	return domain;
 }
 
-static struct platform_msi_priv_data *
-platform_msi_alloc_priv_data(struct device *dev, unsigned int nvec,
-			     irq_write_msi_msg_t write_msi_msg)
+static int platform_msi_alloc_priv_data(struct device *dev, unsigned int nvec,
+					irq_write_msi_msg_t write_msi_msg)
 {
 	struct platform_msi_priv_data *datap;
+	int err;
+
 	/*
 	 * Limit the number of interrupts to 2048 per device. Should we
 	 * need to bump this up, DEV_ID_SHIFT should be adjusted
 	 * accordingly (which would impact the max number of MSI
 	 * capable devices).
 	 */
-	if (!dev->msi_domain || !write_msi_msg || !nvec || nvec > MAX_DEV_MSIS)
-		return ERR_PTR(-EINVAL);
+	if (!dev->msi.domain || !write_msi_msg || !nvec || nvec > MAX_DEV_MSIS)
+		return -EINVAL;
 
-	if (dev->msi_domain->bus_token != DOMAIN_BUS_PLATFORM_MSI) {
+	if (dev->msi.domain->bus_token != DOMAIN_BUS_PLATFORM_MSI) {
 		dev_err(dev, "Incompatible msi_domain, giving up\n");
-		return ERR_PTR(-EINVAL);
+		return -EINVAL;
 	}
 
-	/* Already had a helping of MSI? Greed... */
-	if (!list_empty(dev_to_msi_list(dev)))
-		return ERR_PTR(-EBUSY);
+	err = msi_setup_device_data(dev);
+	if (err)
+		return err;
+
+	/* Already initialized? */
+	if (dev->msi.data->platform_data)
+		return -EBUSY;
 
 	datap = kzalloc(sizeof(*datap), GFP_KERNEL);
 	if (!datap)
-		return ERR_PTR(-ENOMEM);
+		return -ENOMEM;
 
 	datap->devid = ida_simple_get(&platform_msi_devid_ida,
 				      0, 1 << DEV_ID_SHIFT, GFP_KERNEL);
 	if (datap->devid < 0) {
-		int err = datap->devid;
+		err = datap->devid;
 		kfree(datap);
-		return ERR_PTR(err);
+		return err;
 	}
 
 	datap->write_msg = write_msi_msg;
 	datap->dev = dev;
-
-	return datap;
+	dev->msi.data->platform_data = datap;
+	return 0;
 }
 
-static void platform_msi_free_priv_data(struct platform_msi_priv_data *data)
+static void platform_msi_free_priv_data(struct device *dev)
 {
+	struct platform_msi_priv_data *data = dev->msi.data->platform_data;
+
+	dev->msi.data->platform_data = NULL;
 	ida_simple_remove(&platform_msi_devid_ida, data->devid);
 	kfree(data);
 }
···
 int platform_msi_domain_alloc_irqs(struct device *dev, unsigned int nvec,
 				   irq_write_msi_msg_t write_msi_msg)
 {
-	struct platform_msi_priv_data *priv_data;
 	int err;
 
-	priv_data = platform_msi_alloc_priv_data(dev, nvec, write_msi_msg);
-	if (IS_ERR(priv_data))
-		return PTR_ERR(priv_data);
-
-	err = platform_msi_alloc_descs(dev, nvec, priv_data);
+	err = platform_msi_alloc_priv_data(dev, nvec, write_msi_msg);
 	if (err)
-		goto out_free_priv_data;
+		return err;
 
-	err = msi_domain_alloc_irqs(dev->msi_domain, dev, nvec);
+	err = msi_domain_alloc_irqs(dev->msi.domain, dev, nvec);
 	if (err)
-		goto out_free_desc;
-
-	priv_data->msi_irq_groups = msi_populate_sysfs(dev);
-	if (IS_ERR(priv_data->msi_irq_groups)) {
-		err = PTR_ERR(priv_data->msi_irq_groups);
-		goto out_free_irqs;
-	}
-
-	return 0;
-
-out_free_irqs:
-	msi_domain_free_irqs(dev->msi_domain, dev);
-out_free_desc:
-	platform_msi_free_descs(dev, 0, nvec);
-out_free_priv_data:
-	platform_msi_free_priv_data(priv_data);
+		platform_msi_free_priv_data(dev);
 
 	return err;
 }
···
  */
 void platform_msi_domain_free_irqs(struct device *dev)
 {
-	if (!list_empty(dev_to_msi_list(dev))) {
-		struct msi_desc *desc;
-
-		desc = first_msi_entry(dev);
-		msi_destroy_sysfs(dev, desc->platform.msi_priv_data->msi_irq_groups);
-		platform_msi_free_priv_data(desc->platform.msi_priv_data);
-	}
-
-	msi_domain_free_irqs(dev->msi_domain, dev);
-	platform_msi_free_descs(dev, 0, MAX_DEV_MSIS);
+	msi_domain_free_irqs(dev->msi.domain, dev);
+	platform_msi_free_priv_data(dev);
 }
 EXPORT_SYMBOL_GPL(platform_msi_domain_free_irqs);
 
···
  *                              a platform-msi domain
  * @domain:	The platform-msi domain
  *
- * Returns the private data provided when calling
- * platform_msi_create_device_domain.
+ * Return: The private data provided when calling
+ * platform_msi_create_device_domain().
  */
 void *platform_msi_get_host_data(struct irq_domain *domain)
 {
 	struct platform_msi_priv_data *data = domain->host_data;
+
 	return data->host_data;
 }
 
+static struct lock_class_key platform_device_msi_lock_class;
+
 /**
- * __platform_msi_create_device_domain - Create a platform-msi domain
+ * __platform_msi_create_device_domain - Create a platform-msi device domain
  *
  * @dev:		The device generating the MSIs
  * @nvec:		The number of MSIs that need to be allocated
···
  * @ops:		The hierarchy domain operations to use
  * @host_data:		Private data associated to this domain
  *
- * Returns an irqdomain for @nvec interrupts
+ * Return: An irqdomain for @nvec interrupts on success, NULL in case of error.
+ *
+ * This is for interrupt domains which stack on a platform-msi domain
+ * created by platform_msi_create_irq_domain(). @dev->msi.domain points to
+ * that platform-msi domain which is the parent for the new domain.
  */
 struct irq_domain *
 __platform_msi_create_device_domain(struct device *dev,
···
 	struct irq_domain *domain;
 	int err;
 
-	data = platform_msi_alloc_priv_data(dev, nvec, write_msi_msg);
-	if (IS_ERR(data))
+	err = platform_msi_alloc_priv_data(dev, nvec, write_msi_msg);
+	if (err)
 		return NULL;
 
+	/*
+	 * Use a separate lock class for the MSI descriptor mutex on
+	 * platform MSI device domains because the descriptor mutex nests
+	 * into the domain mutex. See alloc/free below.
+	 */
+	lockdep_set_class(&dev->msi.data->mutex, &platform_device_msi_lock_class);
+
+	data = dev->msi.data->platform_data;
 	data->host_data = host_data;
-	domain = irq_domain_create_hierarchy(dev->msi_domain, 0,
+	domain = irq_domain_create_hierarchy(dev->msi.domain, 0,
 					     is_tree ? 0 : nvec,
 					     dev->fwnode, ops, data);
 	if (!domain)
···
 free_domain:
 	irq_domain_remove(domain);
 free_priv:
-	platform_msi_free_priv_data(data);
+	platform_msi_free_priv_data(dev);
 	return NULL;
 }
 
 /**
- * platform_msi_domain_free - Free interrupts associated with a platform-msi
- *                            domain
+ * platform_msi_device_domain_free - Free interrupts associated with a platform-msi
+ *				     device domain
  *
- * @domain:	The platform-msi domain
+ * @domain:	The platform-msi device domain
  * @virq:	The base irq from which to perform the free operation
- * @nvec:	How many interrupts to free from @virq
+ * @nr_irqs:	How many interrupts to free from @virq
  */
-void platform_msi_domain_free(struct irq_domain *domain, unsigned int virq,
-			      unsigned int nvec)
+void platform_msi_device_domain_free(struct irq_domain *domain, unsigned int virq,
+				     unsigned int nr_irqs)
 {
 	struct platform_msi_priv_data *data = domain->host_data;
-	struct msi_desc *desc, *tmp;
-	for_each_msi_entry_safe(desc, tmp, data->dev) {
-		if (WARN_ON(!desc->irq || desc->nvec_used != 1))
-			return;
-		if (!(desc->irq >= virq && desc->irq < (virq + nvec)))
-			continue;
 
-		irq_domain_free_irqs_common(domain, desc->irq, 1);
-		list_del(&desc->list);
-		free_msi_entry(desc);
-	}
+	msi_lock_descs(data->dev);
+	irq_domain_free_irqs_common(domain, virq, nr_irqs);
+	msi_free_msi_descs_range(data->dev, MSI_DESC_ALL, virq, virq + nr_irqs - 1);
+	msi_unlock_descs(data->dev);
 }
 
 /**
- * platform_msi_domain_alloc - Allocate interrupts associated with
- *			       a platform-msi domain
+ * platform_msi_device_domain_alloc - Allocate interrupts associated with
+ *				      a platform-msi device domain
  *
- * @domain:	The platform-msi domain
+ * @domain:	The platform-msi device domain
  * @virq:	The base irq from which to perform the allocate operation
- * @nr_irqs:	How many interrupts to free from @virq
+ * @nr_irqs:	How many interrupts to allocate from @virq
  *
  * Return 0 on success, or an error code on failure. Must be called
  * with irq_domain_mutex held (which can only be done as part of a
  * top-level interrupt allocation).
  */
-int platform_msi_domain_alloc(struct irq_domain *domain, unsigned int virq,
-			      unsigned int nr_irqs)
+int platform_msi_device_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				     unsigned int nr_irqs)
 {
 	struct platform_msi_priv_data *data = domain->host_data;
-	int err;
+	struct device *dev = data->dev;
 
-	err = platform_msi_alloc_descs_with_irq(data->dev, virq, nr_irqs, data);
-	if (err)
-		return err;
-
-	err = msi_domain_populate_irqs(domain->parent, data->dev,
-				       virq, nr_irqs, &data->arg);
-	if (err)
-		platform_msi_domain_free(domain, virq, nr_irqs);
-
-	return err;
+	return msi_domain_populate_irqs(domain->parent, dev, virq, nr_irqs, &data->arg);
 }

drivers/bus/fsl-mc/dprc-driver.c

···
 	struct fsl_mc_device *mc_dev = to_fsl_mc_device(dev);
 	struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_dev);
 	struct fsl_mc_io *mc_io = mc_dev->mc_io;
-	struct msi_desc *msi_desc = mc_dev->irqs[0]->msi_desc;
+	int irq = mc_dev->irqs[0]->virq;
 
 	dev_dbg(dev, "DPRC IRQ %d triggered on CPU %u\n",
 		irq_num, smp_processor_id());
···
 		return IRQ_HANDLED;
 
 	mutex_lock(&mc_bus->scan_mutex);
-	if (!msi_desc || msi_desc->irq != (u32)irq_num)
+	if (irq != (u32)irq_num)
 		goto out;
 
 	status = 0;
···
 	 * function that programs the MSI physically in the device
 	 */
 	error = devm_request_threaded_irq(&mc_dev->dev,
-					  irq->msi_desc->irq,
+					  irq->virq,
 					  dprc_irq0_handler,
 					  dprc_irq0_handler_thread,
 					  IRQF_NO_SUSPEND | IRQF_ONESHOT,
···
 
 	(void)disable_dprc_irq(mc_dev);
 
-	devm_free_irq(&mc_dev->dev, irq->msi_desc->irq, &mc_dev->dev);
+	devm_free_irq(&mc_dev->dev, irq->virq, &mc_dev->dev);
 
 	fsl_mc_free_irqs(mc_dev);
 }

drivers/bus/fsl-mc/fsl-mc-allocator.c

···
 			     unsigned int irq_count)
 {
 	unsigned int i;
-	struct msi_desc *msi_desc;
 	struct fsl_mc_device_irq *irq_resources;
 	struct fsl_mc_device_irq *mc_dev_irq;
 	int error;
···
 		mc_dev_irq->resource.type = res_pool->type;
 		mc_dev_irq->resource.data = mc_dev_irq;
 		mc_dev_irq->resource.parent_pool = res_pool;
+		mc_dev_irq->virq = msi_get_virq(&mc_bus_dev->dev, i);
+		mc_dev_irq->resource.id = mc_dev_irq->virq;
 		INIT_LIST_HEAD(&mc_dev_irq->resource.node);
 		list_add_tail(&mc_dev_irq->resource.node, &res_pool->free_list);
-	}
-
-	for_each_msi_entry(msi_desc, &mc_bus_dev->dev) {
-		mc_dev_irq = &irq_resources[msi_desc->fsl_mc.msi_index];
-		mc_dev_irq->msi_desc = msi_desc;
-		mc_dev_irq->resource.id = msi_desc->irq;
 	}
 
 	res_pool->max_count = irq_count;

drivers/bus/fsl-mc/fsl-mc-msi.c

···
 	 * Make the base hwirq value for ICID*10000 so it is readable
 	 * as a decimal value in /proc/interrupts.
 	 */
-	return (irq_hw_number_t)(desc->fsl_mc.msi_index + (dev->icid * 10000));
+	return (irq_hw_number_t)(desc->msi_index + (dev->icid * 10000));
 }
 
 static void fsl_mc_msi_set_desc(msi_alloc_info_t *arg,
···
 }
 
 static void __fsl_mc_msi_write_msg(struct fsl_mc_device *mc_bus_dev,
-				   struct fsl_mc_device_irq *mc_dev_irq)
+				   struct fsl_mc_device_irq *mc_dev_irq,
+				   struct msi_desc *msi_desc)
 {
 	int error;
 	struct fsl_mc_device *owner_mc_dev = mc_dev_irq->mc_dev;
-	struct msi_desc *msi_desc = mc_dev_irq->msi_desc;
 	struct dprc_irq_cfg irq_cfg;
 
 	/*
···
 	struct fsl_mc_device *mc_bus_dev = to_fsl_mc_device(msi_desc->dev);
 	struct fsl_mc_bus *mc_bus = to_fsl_mc_bus(mc_bus_dev);
 	struct fsl_mc_device_irq *mc_dev_irq =
-		&mc_bus->irq_resources[msi_desc->fsl_mc.msi_index];
+		&mc_bus->irq_resources[msi_desc->msi_index];
 
 	msi_desc->msg = *msg;
 
 	/*
 	 * Program the MSI (paddr, value) pair in the device:
 	 */
-	__fsl_mc_msi_write_msg(mc_bus_dev, mc_dev_irq);
+	__fsl_mc_msi_write_msg(mc_bus_dev, mc_dev_irq, msi_desc);
 }
 
 static void fsl_mc_msi_update_chip_ops(struct msi_domain_info *info)
···
 		fsl_mc_msi_update_dom_ops(info);
 	if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
 		fsl_mc_msi_update_chip_ops(info);
+	info->flags |= MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS | MSI_FLAG_FREE_MSI_DESCS;
 
 	domain = msi_create_irq_domain(fwnode, info, parent);
 	if (domain)
···
 	return msi_domain;
 }
 
-static void fsl_mc_msi_free_descs(struct device *dev)
-{
-	struct msi_desc *desc, *tmp;
-
-	list_for_each_entry_safe(desc, tmp, dev_to_msi_list(dev), list) {
-		list_del(&desc->list);
-		free_msi_entry(desc);
-	}
-}
-
-static int fsl_mc_msi_alloc_descs(struct device *dev, unsigned int irq_count)
-
-{
-	unsigned int i;
-	int error;
-	struct msi_desc *msi_desc;
-
-	for (i = 0; i < irq_count; i++) {
-		msi_desc = alloc_msi_entry(dev, 1, NULL);
-		if (!msi_desc) {
-			dev_err(dev, "Failed to allocate msi entry\n");
-			error = -ENOMEM;
-			goto cleanup_msi_descs;
-		}
-
-		msi_desc->fsl_mc.msi_index = i;
-		INIT_LIST_HEAD(&msi_desc->list);
-		list_add_tail(&msi_desc->list, dev_to_msi_list(dev));
-	}
-
-	return 0;
-
-cleanup_msi_descs:
-	fsl_mc_msi_free_descs(dev);
-	return error;
-}
-
-int fsl_mc_msi_domain_alloc_irqs(struct device *dev,
-				 unsigned int irq_count)
+int fsl_mc_msi_domain_alloc_irqs(struct device *dev,  unsigned int irq_count)
 {
 	struct irq_domain *msi_domain;
 	int error;
 
-	if (!list_empty(dev_to_msi_list(dev)))
+	msi_domain = dev_get_msi_domain(dev);
+	if (!msi_domain)
 		return -EINVAL;
 
-	error = fsl_mc_msi_alloc_descs(dev, irq_count);
-	if (error < 0)
+	error = msi_setup_device_data(dev);
+	if (error)
 		return error;
 
-	msi_domain = dev_get_msi_domain(dev);
-	if (!msi_domain) {
-		error = -EINVAL;
-		goto cleanup_msi_descs;
-	}
+	if (msi_first_desc(dev, MSI_DESC_ALL))
+		return -EINVAL;
 
 	/*
 	 * NOTE: Calling this function will trigger the invocation of the
···
 	 */
 	error = msi_domain_alloc_irqs(msi_domain, dev, irq_count);
 
-	if (error) {
+	if (error)
 		dev_err(dev, "Failed to allocate IRQs\n");
-		goto cleanup_msi_descs;
-	}
-
-	return 0;
-
-cleanup_msi_descs:
-	fsl_mc_msi_free_descs(dev);
 	return error;
 }
 
···
 		return;
 
 	msi_domain_free_irqs(msi_domain, dev);
-
-	if (list_empty(dev_to_msi_list(dev)))
-		return;
-
-	fsl_mc_msi_free_descs(dev);
 }

drivers/dma/mv_xor_v2.c

···
  * @desc_size: HW descriptor size
  * @npendings: number of pending descriptors (for which tx_submit has
  * @hw_queue_idx: HW queue index
- * @msi_desc: local interrupt descriptor information
+ * @irq: The Linux interrupt number
  * been called, but not yet issue_pending)
  */
 struct mv_xor_v2_device {
···
 	int desc_size;
 	unsigned int npendings;
 	unsigned int hw_queue_idx;
-	struct msi_desc *msi_desc;
+	unsigned int irq;
 };
 
 /**
···
 	int i, ret = 0;
 	struct dma_device *dma_dev;
 	struct mv_xor_v2_sw_desc *sw_desc;
-	struct msi_desc *msi_desc;
 
 	BUILD_BUG_ON(sizeof(struct mv_xor_v2_descriptor) !=
 		     MV_XOR_V2_EXT_DESC_SIZE);
···
 	if (ret)
 		goto disable_clk;
 
-	msi_desc = first_msi_entry(&pdev->dev);
-	if (!msi_desc) {
-		ret = -ENODEV;
-		goto free_msi_irqs;
-	}
-	xor_dev->msi_desc = msi_desc;
+	xor_dev->irq = msi_get_virq(&pdev->dev, 0);
 
-	ret = devm_request_irq(&pdev->dev, msi_desc->irq,
+	ret = devm_request_irq(&pdev->dev, xor_dev->irq,
 			       mv_xor_v2_interrupt_handler, 0,
 			       dev_name(&pdev->dev), xor_dev);
 	if (ret)
···
 			  xor_dev->desc_size * MV_XOR_V2_DESC_NUM,
 			  xor_dev->hw_desq_virt, xor_dev->hw_desq);
 
-	devm_free_irq(&pdev->dev, xor_dev->msi_desc->irq, xor_dev);
+	devm_free_irq(&pdev->dev, xor_dev->irq, xor_dev);
 
 	platform_msi_domain_free_irqs(&pdev->dev);
 

drivers/dma/qcom/hidma.c

···
 	struct device *dev = msi_desc_to_dev(desc);
 	struct hidma_dev *dmadev = dev_get_drvdata(dev);
 
-	if (!desc->platform.msi_index) {
+	if (!desc->msi_index) {
 		writel(msg->address_lo, dmadev->dev_evca + 0x118);
 		writel(msg->address_hi, dmadev->dev_evca + 0x11C);
 		writel(msg->data, dmadev->dev_evca + 0x120);
···
 {
 #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
 	struct device *dev = dmadev->ddev.dev;
-	struct msi_desc *desc;
+	int i, virq;
 
-	/* free allocated MSI interrupts above */
-	for_each_msi_entry(desc, dev)
-		devm_free_irq(dev, desc->irq, &dmadev->lldev);
+	for (i = 0; i < HIDMA_MSI_INTS; i++) {
+		virq = msi_get_virq(dev, i);
+		if (virq)
+			devm_free_irq(dev, virq, &dmadev->lldev);
+	}
 
 	platform_msi_domain_free_irqs(dev);
 #endif
···
 			     struct platform_device *pdev)
 {
 #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
-	int rc;
-	struct msi_desc *desc;
-	struct msi_desc *failed_desc = NULL;
+	int rc, i, virq;
 
 	rc = platform_msi_domain_alloc_irqs(&pdev->dev, HIDMA_MSI_INTS,
 					    hidma_write_msi_msg);
 	if (rc)
 		return rc;
 
-	for_each_msi_entry(desc, &pdev->dev) {
-		if (!desc->platform.msi_index)
-			dmadev->msi_virqbase = desc->irq;
-
-		rc = devm_request_irq(&pdev->dev, desc->irq,
+	for (i = 0; i < HIDMA_MSI_INTS; i++) {
+		virq = msi_get_virq(&pdev->dev, i);
+		rc = devm_request_irq(&pdev->dev, virq,
 				       hidma_chirq_handler_msi,
 				       0, "qcom-hidma-msi",
 				       &dmadev->lldev);
-		if (rc) {
-			failed_desc = desc;
+		if (rc)
 			break;
-		}
+		if (!i)
+			dmadev->msi_virqbase = virq;
 	}
 
 	if (rc) {
 		/* free allocated MSI interrupts above */
-		for_each_msi_entry(desc, &pdev->dev) {
-			if (desc == failed_desc)
-				break;
-			devm_free_irq(&pdev->dev, desc->irq,
-				      &dmadev->lldev);
+		for (--i; i >= 0; i--) {
+			virq = msi_get_virq(&pdev->dev, i);
+			devm_free_irq(&pdev->dev, virq, &dmadev->lldev);
 		}
+		dev_warn(&pdev->dev,
+			 "failed to request MSI irq, falling back to wired IRQ\n");
 	} else {
 		/* Add callback to free MSIs on teardown */
 		hidma_ll_setup_irq(dmadev->lldev, true);
-
 	}
-	if (rc)
-		dev_warn(&pdev->dev,
-			 "failed to request MSI irq, falling back to wired IRQ\n");
 	return rc;
 #else
 	return -EINVAL;

drivers/dma/ti/k3-udma-private.c

···
 {
 	const struct udma_oes_offsets *oes = &ud->soc_data->oes;
 
-	return ti_sci_inta_msi_get_virq(ud->dev, udma_tflow_id +
-					oes->pktdma_tchan_flow);
+	return msi_get_virq(ud->dev, udma_tflow_id + oes->pktdma_tchan_flow);
 }
 EXPORT_SYMBOL(xudma_pktdma_tflow_get_irq);
 
···
 {
 	const struct udma_oes_offsets *oes = &ud->soc_data->oes;
 
-	return ti_sci_inta_msi_get_virq(ud->dev, udma_rflow_id +
-					oes->pktdma_rchan_flow);
+	return msi_get_virq(ud->dev, udma_rflow_id + oes->pktdma_rchan_flow);
 }
 EXPORT_SYMBOL(xudma_pktdma_rflow_get_irq);

drivers/dma/ti/k3-udma.c

···
 
 	/* Event from UDMA (TR events) only needed for slave TR mode channels */
 	if (is_slave_direction(uc->config.dir) && !uc->config.pkt_mode) {
-		uc->irq_num_udma = ti_sci_inta_msi_get_virq(ud->dev,
-							    irq_udma_idx);
+		uc->irq_num_udma = msi_get_virq(ud->dev, irq_udma_idx);
 		if (uc->irq_num_udma <= 0) {
 			dev_err(ud->dev, "Failed to get udma irq (index: %u)\n",
 				irq_udma_idx);
···
 		uc->psil_paired = true;
 	}
 
-	uc->irq_num_ring = ti_sci_inta_msi_get_virq(ud->dev, irq_ring_idx);
+	uc->irq_num_ring = msi_get_virq(ud->dev, irq_ring_idx);
 	if (uc->irq_num_ring <= 0) {
 		dev_err(ud->dev, "Failed to get ring irq (index: %u)\n",
 			irq_ring_idx);
···
 
 	/* Event from BCDMA (TR events) only needed for slave channels */
 	if (is_slave_direction(uc->config.dir)) {
-		uc->irq_num_udma = ti_sci_inta_msi_get_virq(ud->dev,
-							    irq_udma_idx);
+		uc->irq_num_udma = msi_get_virq(ud->dev, irq_udma_idx);
 		if (uc->irq_num_udma <= 0) {
 			dev_err(ud->dev, "Failed to get bcdma irq (index: %u)\n",
 				irq_udma_idx);
···
 
 	uc->psil_paired = true;
 
-	uc->irq_num_ring = ti_sci_inta_msi_get_virq(ud->dev, irq_ring_idx);
+	uc->irq_num_ring = msi_get_virq(ud->dev, irq_ring_idx);
 	if (uc->irq_num_ring <= 0) {
 		dev_err(ud->dev, "Failed to get ring irq (index: %u)\n",
 			irq_ring_idx);
···
 	if (IS_ERR(ud->ringacc))
 		return PTR_ERR(ud->ringacc);
 
-	dev->msi_domain = of_msi_get_domain(dev, dev->of_node,
+	dev->msi.domain = of_msi_get_domain(dev, dev->of_node,
 					    DOMAIN_BUS_TI_SCI_INTA_MSI);
-	if (!dev->msi_domain) {
+	if (!dev->msi.domain) {
 		dev_err(dev, "Failed to get MSI domain\n");
 		return -EPROBE_DEFER;
 	}

drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c

···
 	phys_addr_t doorbell;
 	struct device *dev = msi_desc_to_dev(desc);
 	struct arm_smmu_device *smmu = dev_get_drvdata(dev);
-	phys_addr_t *cfg = arm_smmu_msi_cfg[desc->platform.msi_index];
+	phys_addr_t *cfg = arm_smmu_msi_cfg[desc->msi_index];
 
 	doorbell = (((u64)msg->address_hi) << 32) | msg->address_lo;
 	doorbell &= MSI_CFG0_ADDR_MASK;
···
 
 static void arm_smmu_setup_msis(struct arm_smmu_device *smmu)
 {
-	struct msi_desc *desc;
 	int ret, nvec = ARM_SMMU_MAX_MSIS;
 	struct device *dev = smmu->dev;
 
···
 	if (!(smmu->features & ARM_SMMU_FEAT_MSI))
 		return;
 
-	if (!dev->msi_domain) {
+	if (!dev->msi.domain) {
 		dev_info(smmu->dev, "msi_domain absent - falling back to wired irqs\n");
 		return;
 	}
···
 		return;
 	}
 
-	for_each_msi_entry(desc, dev) {
-		switch (desc->platform.msi_index) {
-		case EVTQ_MSI_INDEX:
-			smmu->evtq.q.irq = desc->irq;
-			break;
-		case GERROR_MSI_INDEX:
-			smmu->gerr_irq = desc->irq;
-			break;
-		case PRIQ_MSI_INDEX:
-			smmu->priq.q.irq = desc->irq;
-			break;
-		default:	/* Unknown */
-			continue;
-		}
-	}
+	smmu->evtq.q.irq = msi_get_virq(dev, EVTQ_MSI_INDEX);
+	smmu->gerr_irq = msi_get_virq(dev, GERROR_MSI_INDEX);
+	smmu->priq.q.irq = msi_get_virq(dev, PRIQ_MSI_INDEX);
 
 	/* Add callback to free MSIs on teardown */
 	devm_add_action(dev, arm_smmu_free_msis, dev);

drivers/irqchip/irq-gic-v2m.c

···
 	.irq_mask		= gicv2m_mask_msi_irq,
 	.irq_unmask		= gicv2m_unmask_msi_irq,
 	.irq_eoi		= irq_chip_eoi_parent,
-	.irq_write_msi_msg	= pci_msi_domain_write_msg,
 };
 
 static struct msi_domain_info gicv2m_msi_domain_info = {

drivers/irqchip/irq-gic-v3-its-pci-msi.c

···
 	.irq_unmask		= its_unmask_msi_irq,
 	.irq_mask		= its_mask_msi_irq,
 	.irq_eoi		= irq_chip_eoi_parent,
-	.irq_write_msi_msg	= pci_msi_domain_write_msg,
 };
 
 static int its_pci_msi_vec_count(struct pci_dev *pdev, void *data)

drivers/irqchip/irq-gic-v3-mbi.c

···
 	.irq_unmask		= mbi_unmask_msi_irq,
 	.irq_eoi		= irq_chip_eoi_parent,
 	.irq_compose_msi_msg	= mbi_compose_msi_msg,
-	.irq_write_msi_msg	= pci_msi_domain_write_msg,
 };
 
 static struct msi_domain_info mbi_msi_domain_info = {

drivers/irqchip/irq-mbigen.c

···
 	if (err)
 		return err;
 
-	err = platform_msi_domain_alloc(domain, virq, nr_irqs);
+	err = platform_msi_device_domain_alloc(domain, virq, nr_irqs);
 	if (err)
 		return err;
 
···
 static void mbigen_irq_domain_free(struct irq_domain *domain, unsigned int virq,
 				   unsigned int nr_irqs)
 {
-	platform_msi_domain_free(domain, virq, nr_irqs);
+	platform_msi_device_domain_free(domain, virq, nr_irqs);
 }
 
 static const struct irq_domain_ops mbigen_domain_ops = {

drivers/irqchip/irq-mvebu-icu.c

···
 		icu_irqd->icu_group = msi_data->subset_data->icu_group;
 	icu_irqd->icu = icu;
 
-	err = platform_msi_domain_alloc(domain, virq, nr_irqs);
+	err = platform_msi_device_domain_alloc(domain, virq, nr_irqs);
 	if (err) {
 		dev_err(icu->dev, "failed to allocate ICU interrupt in parent domain\n");
 		goto free_irqd;
···
 	return 0;
 
 free_msi:
-	platform_msi_domain_free(domain, virq, nr_irqs);
+	platform_msi_device_domain_free(domain, virq, nr_irqs);
 free_irqd:
 	kfree(icu_irqd);
 	return err;
···
 
 	kfree(icu_irqd);
 
-	platform_msi_domain_free(domain, virq, nr_irqs);
+	platform_msi_device_domain_free(domain, virq, nr_irqs);
 }
 
 static const struct irq_domain_ops mvebu_icu_domain_ops = {
···
 		msi_data->subset_data = of_device_get_match_data(dev);
 	}
 
-	dev->msi_domain = of_msi_get_domain(dev, dev->of_node,
+	dev->msi.domain = of_msi_get_domain(dev, dev->of_node,
 					    DOMAIN_BUS_PLATFORM_MSI);
-	if (!dev->msi_domain)
+	if (!dev->msi.domain)
 		return -EPROBE_DEFER;
 
-	msi_parent_dn = irq_domain_get_of_node(dev->msi_domain);
+	msi_parent_dn = irq_domain_get_of_node(dev->msi.domain);
 	if (!msi_parent_dn)
 		return -ENODEV;
 

drivers/irqchip/irq-ti-sci-inta.c

···
 	struct platform_device *pdev = to_platform_device(desc->dev);
 
 	arg->desc = desc;
-	arg->hwirq = TO_HWIRQ(pdev->id, desc->inta.dev_index);
+	arg->hwirq = TO_HWIRQ(pdev->id, desc->msi_index);
 }
 
 static struct msi_domain_ops ti_sci_inta_msi_ops = {

drivers/mailbox/bcm-flexrm-mailbox.c

···
 {
 	struct device *dev = msi_desc_to_dev(desc);
 	struct flexrm_mbox *mbox = dev_get_drvdata(dev);
-	struct flexrm_ring *ring = &mbox->rings[desc->platform.msi_index];
+	struct flexrm_ring *ring = &mbox->rings[desc->msi_index];
 
 	/* Configure per-Ring MSI registers */
 	writel_relaxed(msg->address_lo, ring->regs + RING_MSI_ADDR_LS);
···
 	int index, ret = 0;
 	void __iomem *regs;
 	void __iomem *regs_end;
-	struct msi_desc *desc;
 	struct resource *iomem;
 	struct flexrm_ring *ring;
 	struct flexrm_mbox *mbox;
···
 		goto fail_destroy_cmpl_pool;
 
 	/* Save alloced IRQ numbers for each ring */
-	for_each_msi_entry(desc, dev) {
-		ring = &mbox->rings[desc->platform.msi_index];
-		ring->irq = desc->irq;
-	}
+	for (index = 0; index < mbox->num_rings; index++)
+		mbox->rings[index].irq = msi_get_virq(dev, index);
 
 	/* Check availability of debugfs */
 	if (!debugfs_initialized())

drivers/net/ethernet/freescale/dpaa2/dpaa2-eth.c

···
 	}
 
 	irq = ls_dev->irqs[0];
-	err = devm_request_threaded_irq(&ls_dev->dev, irq->msi_desc->irq,
+	err = devm_request_threaded_irq(&ls_dev->dev, irq->virq,
 					NULL, dpni_irq0_handler_thread,
 					IRQF_NO_SUSPEND | IRQF_ONESHOT,
 					dev_name(&ls_dev->dev), &ls_dev->dev);
···
 	return 0;
 
 free_irq:
-	devm_free_irq(&ls_dev->dev, irq->msi_desc->irq, &ls_dev->dev);
+	devm_free_irq(&ls_dev->dev, irq->virq, &ls_dev->dev);
 free_mc_irq:
 	fsl_mc_free_irqs(ls_dev);
 

drivers/net/ethernet/freescale/dpaa2/dpaa2-ptp.c

···
 static int dpaa2_ptp_probe(struct fsl_mc_device *mc_dev)
 {
 	struct device *dev = &mc_dev->dev;
-	struct fsl_mc_device_irq *irq;
 	struct ptp_qoriq *ptp_qoriq;
 	struct device_node *node;
 	void __iomem *base;
···
 		goto err_unmap;
 	}
 
-	irq = mc_dev->irqs[0];
-	ptp_qoriq->irq = irq->msi_desc->irq;
+	ptp_qoriq->irq = mc_dev->irqs[0]->virq;
 
 	err = request_threaded_irq(ptp_qoriq->irq, NULL,
 				   dpaa2_ptp_irq_handler_thread,

drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c

···
 
 	irq = sw_dev->irqs[DPSW_IRQ_INDEX_IF];
 
-	err = devm_request_threaded_irq(dev, irq->msi_desc->irq,
-					NULL,
+	err = devm_request_threaded_irq(dev, irq->virq, NULL,
 					dpaa2_switch_irq0_handler_thread,
 					IRQF_NO_SUSPEND | IRQF_ONESHOT,
 					dev_name(dev), dev);
···
 	return 0;
 
 free_devm_irq:
-	devm_free_irq(dev, irq->msi_desc->irq, dev);
+	devm_free_irq(dev, irq->virq, dev);
 free_irq:
 	fsl_mc_free_irqs(sw_dev);
 	return err;

drivers/net/wireless/ath/ath11k/pci.c

···
 	}
 
 	ab_pci->msi_ep_base_data = msi_desc->msg.data;
-	if (msi_desc->msi_attrib.is_64)
+	if (msi_desc->pci.msi_attrib.is_64)
 		set_bit(ATH11K_PCI_FLAG_IS_MSI_64, &ab_pci->flags);
 
 	ath11k_dbg(ab, ATH11K_DBG_PCI, "msi base data is %d\n", ab_pci->msi_ep_base_data);

drivers/ntb/msi.c

···
 	if (!ntb->msi)
 		return -EINVAL;
 
-	desc = first_msi_entry(&ntb->pdev->dev);
+	msi_lock_descs(&ntb->pdev->dev);
+	desc = msi_first_desc(&ntb->pdev->dev, MSI_DESC_ASSOCIATED);
 	addr = desc->msg.address_lo + ((uint64_t)desc->msg.address_hi << 32);
+	msi_unlock_descs(&ntb->pdev->dev);
 
 	for (peer = 0; peer < ntb_peer_port_count(ntb); peer++) {
 		peer_widx = ntb_peer_highest_mw_idx(ntb, peer);
···
 				  const char *name, void *dev_id,
 				  struct ntb_msi_desc *msi_desc)
 {
+	struct device *dev = &ntb->pdev->dev;
 	struct msi_desc *entry;
 	int ret;
 
 	if (!ntb->msi)
 		return -EINVAL;
 
-	for_each_pci_msi_entry(entry, ntb->pdev) {
+	msi_lock_descs(dev);
+	msi_for_each_desc(entry, dev, MSI_DESC_ASSOCIATED) {
 		if (irq_has_action(entry->irq))
 			continue;
 
···
 		ret = ntbm_msi_setup_callback(ntb, entry, msi_desc);
 		if (ret) {
 			devm_free_irq(&ntb->dev, entry->irq, dev_id);
-			return ret;
+			goto unlock;
 		}
 
-
-		return entry->irq;
+		ret = entry->irq;
+		goto unlock;
 	}
+	ret = -ENODEV;
 
-	return -ENODEV;
+unlock:
+	msi_unlock_descs(dev);
+	return ret;
 }
 EXPORT_SYMBOL(ntbm_msi_request_threaded_irq);
 

drivers/pci/Makefile

···
 obj-$(CONFIG_PCI)		+= access.o bus.o probe.o host-bridge.o \
 				   remove.o pci.o pci-driver.o search.o \
 				   pci-sysfs.o rom.o setup-res.o irq.o vpd.o \
-				   setup-bus.o vc.o mmap.o setup-irq.o msi.o
+				   setup-bus.o vc.o mmap.o setup-irq.o
 
+obj-$(CONFIG_PCI)		+= msi/
 obj-$(CONFIG_PCI)		+= pcie/
 
 ifdef CONFIG_PCI

drivers/pci/controller/pci-hyperv.c

···
 
 static int hv_pci_restore_msi_msg(struct pci_dev *pdev, void *arg)
 {
-	struct msi_desc *entry;
 	struct irq_data *irq_data;
+	struct msi_desc *entry;
+	int ret = 0;
 
-	for_each_pci_msi_entry(entry, pdev) {
+	msi_lock_descs(&pdev->dev);
+	msi_for_each_desc(entry, &pdev->dev, MSI_DESC_ASSOCIATED) {
 		irq_data = irq_get_irq_data(entry->irq);
-		if (WARN_ON_ONCE(!irq_data))
-			return -EINVAL;
+		if (WARN_ON_ONCE(!irq_data)) {
+			ret = -EINVAL;
+			break;
+		}
 
 		hv_compose_msi_msg(irq_data, &entry->msg);
 	}
+	msi_unlock_descs(&pdev->dev);
 
-	return 0;
+	return ret;
 }
 
 /*

drivers/pci/msi.c drivers/pci/msi/msi.c

···
  * Copyright (C) Tom Long Nguyen ([e-mail])
  * Copyright (C) 2016 Christoph Hellwig.
  */
-
 #include <linux/err.h>
-#include <linux/mm.h>
-#include <linux/irq.h>
-#include <linux/interrupt.h>
 #include <linux/export.h>
-#include <linux/ioport.h>
-#include <linux/pci.h>
-#include <linux/proc_fs.h>
-#include <linux/msi.h>
-#include <linux/smp.h>
-#include <linux/errno.h>
-#include <linux/io.h>
-#include <linux/acpi_iort.h>
-#include <linux/slab.h>
-#include <linux/irqdomain.h>
-#include <linux/of_irq.h>
+#include <linux/irq.h>
 
-#include "pci.h"
-
-#ifdef CONFIG_PCI_MSI
+#include "../pci.h"
+#include "msi.h"
 
 static int pci_msi_enable = 1;
 int pci_msi_ignore_mask;
 
-#define msix_table_size(flags)	((flags & PCI_MSIX_FLAGS_QSIZE) + 1)
-
-#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
-static int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
-{
-	struct irq_domain *domain;
-
-	domain = dev_get_msi_domain(&dev->dev);
-	if (domain && irq_domain_is_hierarchy(domain))
-		return msi_domain_alloc_irqs(domain, &dev->dev, nvec);
-
-	return arch_setup_msi_irqs(dev, nvec, type);
-}
-
-static void pci_msi_teardown_msi_irqs(struct pci_dev *dev)
-{
-	struct irq_domain *domain;
-
-	domain = dev_get_msi_domain(&dev->dev);
-	if (domain && irq_domain_is_hierarchy(domain))
-		msi_domain_free_irqs(domain, &dev->dev);
-	else
-		arch_teardown_msi_irqs(dev);
-}
-#else
-#define pci_msi_setup_msi_irqs		arch_setup_msi_irqs
-#define pci_msi_teardown_msi_irqs	arch_teardown_msi_irqs
-#endif
-
-#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS
-/* Arch hooks */
-int __weak arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
-{
-	return -EINVAL;
-}
-
-void __weak arch_teardown_msi_irq(unsigned int irq)
-{
-}
-
-int __weak arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
-{
-	struct msi_desc *entry;
-	int ret;
-
-	/*
-	 * If an architecture wants to support multiple MSI, it needs to
-	 * override arch_setup_msi_irqs()
-	 */
-	if (type == PCI_CAP_ID_MSI && nvec > 1)
-		return 1;
-
-	for_each_pci_msi_entry(entry, dev) {
-		ret = arch_setup_msi_irq(dev, entry);
-		if (ret < 0)
-			return ret;
-		if (ret > 0)
-			return -ENOSPC;
-	}
-
-	return 0;
-}
-
-void __weak arch_teardown_msi_irqs(struct pci_dev *dev)
-{
-	int i;
-	struct msi_desc *entry;
-
-	for_each_pci_msi_entry(entry, dev)
-		if (entry->irq)
-			for (i = 0; i < entry->nvec_used; i++)
-				arch_teardown_msi_irq(entry->irq + i);
-}
-#endif /* CONFIG_PCI_MSI_ARCH_FALLBACKS */
-
-static void default_restore_msi_irq(struct pci_dev *dev, int irq)
-{
-	struct msi_desc *entry;
-
-	entry = NULL;
-	if (dev->msix_enabled) {
-		for_each_pci_msi_entry(entry, dev) {
-			if (irq == entry->irq)
-				break;
-		}
-	} else if (dev->msi_enabled)  {
-		entry = irq_get_msi_desc(irq);
-	}
-
-	if (entry)
-		__pci_write_msi_msg(entry, &entry->msg);
-}
-
-void __weak arch_restore_msi_irqs(struct pci_dev *dev)
-{
-	return default_restore_msi_irqs(dev);
-}
-
-/*
- * PCI 2.3 does not specify mask bits for each MSI interrupt.  Attempting to
- * mask all MSI interrupts by clearing the MSI enable bit does not work
- * reliably as devices without an INTx disable bit will then generate a
- * level IRQ which will never be cleared.
- */
-static inline __attribute_const__ u32 msi_multi_mask(struct msi_desc *desc)
-{
-	/* Don't shift by >= width of type */
-	if (desc->msi_attrib.multi_cap >= 5)
-		return 0xffffffff;
-	return (1 << (1 << desc->msi_attrib.multi_cap)) - 1;
-}
-
 static noinline void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 set)
 {
-	raw_spinlock_t *lock = &desc->dev->msi_lock;
+	raw_spinlock_t *lock = &to_pci_dev(desc->dev)->msi_lock;
 	unsigned long flags;
 
-	if (!desc->msi_attrib.can_mask)
+	if (!desc->pci.msi_attrib.can_mask)
 		return;
 
 	raw_spin_lock_irqsave(lock, flags);
-	desc->msi_mask &= ~clear;
-	desc->msi_mask |= set;
-	pci_write_config_dword(msi_desc_to_pci_dev(desc), desc->mask_pos,
-			       desc->msi_mask);
+	desc->pci.msi_mask &= ~clear;
+	desc->pci.msi_mask |= set;
+	pci_write_config_dword(msi_desc_to_pci_dev(desc), desc->pci.mask_pos,
+			       desc->pci.msi_mask);
 	raw_spin_unlock_irqrestore(lock, flags);
 }
 
···
 
 static inline void __iomem *pci_msix_desc_addr(struct msi_desc *desc)
 {
-	return desc->mask_base + desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
+	return desc->pci.mask_base + desc->msi_index * PCI_MSIX_ENTRY_SIZE;
 }
 
 /*
···
 {
 	void __iomem *desc_addr = pci_msix_desc_addr(desc);
 
-	if (desc->msi_attrib.can_mask)
+	if (desc->pci.msi_attrib.can_mask)
 		writel(ctrl, desc_addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
 }
 
 static inline void pci_msix_mask(struct msi_desc *desc)
 {
-	desc->msix_ctrl |= PCI_MSIX_ENTRY_CTRL_MASKBIT;
-	pci_msix_write_vector_ctrl(desc, desc->msix_ctrl);
+	desc->pci.msix_ctrl |= PCI_MSIX_ENTRY_CTRL_MASKBIT;
+	pci_msix_write_vector_ctrl(desc, desc->pci.msix_ctrl);
 	/* Flush write to device */
-	readl(desc->mask_base);
+	readl(desc->pci.mask_base);
 }
 
 static inline void pci_msix_unmask(struct msi_desc *desc)
 {
-	desc->msix_ctrl &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT;
-	pci_msix_write_vector_ctrl(desc, desc->msix_ctrl);
+	desc->pci.msix_ctrl &= ~PCI_MSIX_ENTRY_CTRL_MASKBIT;
+	pci_msix_write_vector_ctrl(desc, desc->pci.msix_ctrl);
 }
 
 static void __pci_msi_mask_desc(struct msi_desc *desc, u32 mask)
 {
-	if (desc->msi_attrib.is_msix)
+	if (desc->pci.msi_attrib.is_msix)
 		pci_msix_mask(desc);
 	else
 		pci_msi_mask(desc, mask);
···
 
 static void __pci_msi_unmask_desc(struct msi_desc *desc, u32 mask)
 {
-	if (desc->msi_attrib.is_msix)
+	if (desc->pci.msi_attrib.is_msix)
 		pci_msix_unmask(desc);
 	else
 		pci_msi_unmask(desc, mask);
···
 }
 EXPORT_SYMBOL_GPL(pci_msi_unmask_irq);
 
-void default_restore_msi_irqs(struct pci_dev *dev)
-{
-	struct msi_desc *entry;
-
-	for_each_pci_msi_entry(entry, dev)
-		default_restore_msi_irq(dev, entry->irq);
-}
-
 void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 {
 	struct pci_dev *dev = msi_desc_to_pci_dev(entry);
 
 	BUG_ON(dev->current_state != PCI_D0);
 
-	if (entry->msi_attrib.is_msix) {
+	if (entry->pci.msi_attrib.is_msix) {
 		void __iomem *base = pci_msix_desc_addr(entry);
 
-		if (WARN_ON_ONCE(entry->msi_attrib.is_virtual))
+		if (WARN_ON_ONCE(entry->pci.msi_attrib.is_virtual))
 			return;
 
 		msg->address_lo = readl(base + PCI_MSIX_ENTRY_LOWER_ADDR);
···
 
 		pci_read_config_dword(dev, pos + PCI_MSI_ADDRESS_LO,
 				      &msg->address_lo);
-		if (entry->msi_attrib.is_64) {
+		if (entry->pci.msi_attrib.is_64) {
 			pci_read_config_dword(dev, pos + PCI_MSI_ADDRESS_HI,
 					      &msg->address_hi);
 			pci_read_config_word(dev, pos + PCI_MSI_DATA_64, &data);
···
 
 	if (dev->current_state != PCI_D0 || pci_dev_is_disconnected(dev)) {
 		/* Don't touch the hardware now */
-	} else if (entry->msi_attrib.is_msix) {
+	} else if (entry->pci.msi_attrib.is_msix) {
 		void __iomem *base = pci_msix_desc_addr(entry);
-		u32 ctrl = entry->msix_ctrl;
+		u32 ctrl = entry->pci.msix_ctrl;
 		bool unmasked = !(ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT);
 
-		if (entry->msi_attrib.is_virtual)
+		if (entry->pci.msi_attrib.is_virtual)
 			goto skip;
 
 		/*
···
 
 		pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl);
 		msgctl &= ~PCI_MSI_FLAGS_QSIZE;
-		msgctl |= entry->msi_attrib.multiple << 4;
+		msgctl |= entry->pci.msi_attrib.multiple << 4;
 		pci_write_config_word(dev, pos + PCI_MSI_FLAGS, msgctl);
 
 		pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_LO,
 				       msg->address_lo);
-		if (entry->msi_attrib.is_64) {
+		if (entry->pci.msi_attrib.is_64) {
 			pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_HI,
 					       msg->address_hi);
 			pci_write_config_word(dev, pos + PCI_MSI_DATA_64,
···
 
 static void free_msi_irqs(struct pci_dev *dev)
 {
-	struct list_head *msi_list = dev_to_msi_list(&dev->dev);
-	struct msi_desc *entry, *tmp;
-	int i;
-
-	for_each_pci_msi_entry(entry, dev)
-		if (entry->irq)
-			for (i = 0; i < entry->nvec_used; i++)
-				BUG_ON(irq_has_action(entry->irq + i));
-
-	if (dev->msi_irq_groups) {
-		msi_destroy_sysfs(&dev->dev, dev->msi_irq_groups);
-		dev->msi_irq_groups = NULL;
-	}
-
 	pci_msi_teardown_msi_irqs(dev);
 
-	list_for_each_entry_safe(entry, tmp, msi_list, list) {
-		if (entry->msi_attrib.is_msix) {
-			if (list_is_last(&entry->list, msi_list))
-				iounmap(entry->mask_base);
-		}
-
-		list_del(&entry->list);
-		free_msi_entry(entry);
+	if (dev->msix_base) {
+		iounmap(dev->msix_base);
+		dev->msix_base = NULL;
 	}
 }
 
···
 	pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control);
 }
 
+/*
+ * Architecture override returns true when the PCI MSI message should be
+ * written by the generic restore function.
+ */
+bool __weak arch_restore_msi_irqs(struct pci_dev *dev)
+{
+	return true;
+}
+
 static void __pci_restore_msi_state(struct pci_dev *dev)
 {
-	u16 control;
 	struct msi_desc *entry;
+	u16 control;
 
 	if (!dev->msi_enabled)
 		return;
···
 
 	pci_intx_for_msi(dev, 0);
 	pci_msi_set_enable(dev, 0);
-	arch_restore_msi_irqs(dev);
+	if (arch_restore_msi_irqs(dev))
+		__pci_write_msi_msg(entry, &entry->msg);
 
 	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
 	pci_msi_update_mask(entry, 0, 0);
 	control &= ~PCI_MSI_FLAGS_QSIZE;
-	control |= (entry->msi_attrib.multiple << 4) | PCI_MSI_FLAGS_ENABLE;
+	control |= (entry->pci.msi_attrib.multiple << 4) | PCI_MSI_FLAGS_ENABLE;
 	pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control);
 }
 
···
 static void __pci_restore_msix_state(struct pci_dev *dev)
 {
 	struct msi_desc *entry;
+	bool write_msg;
 
 	if (!dev->msix_enabled)
 		return;
-	BUG_ON(list_empty(dev_to_msi_list(&dev->dev)));
 
 	/* route the table */
 	pci_intx_for_msi(dev, 0);
 	pci_msix_clear_and_set_ctrl(dev, 0,
 				PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL);
 
-	arch_restore_msi_irqs(dev);
-	for_each_pci_msi_entry(entry, dev)
-		pci_msix_write_vector_ctrl(entry, entry->msix_ctrl);
+	write_msg = arch_restore_msi_irqs(dev);
+
+	msi_lock_descs(&dev->dev);
+	msi_for_each_desc(entry, &dev->dev, MSI_DESC_ALL) {
+		if (write_msg)
+			__pci_write_msi_msg(entry, &entry->msg);
+		pci_msix_write_vector_ctrl(entry, entry->pci.msix_ctrl);
+	}
+	msi_unlock_descs(&dev->dev);
 
 	pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
 }
···
 }
 EXPORT_SYMBOL_GPL(pci_restore_msi_state);
 
-static struct msi_desc *
-msi_setup_entry(struct pci_dev *dev, int nvec, struct irq_affinity *affd)
+static void pcim_msi_release(void *pcidev)
 {
-	struct irq_affinity_desc *masks = NULL;
-	struct msi_desc *entry;
+	struct pci_dev *dev = pcidev;
+
+	dev->is_msi_managed = false;
+	pci_free_irq_vectors(dev);
+}
+
+/*
+ * Needs to be separate from pcim_release to prevent an ordering problem
+ * vs. msi_device_data_release() in the MSI core code.
+ */
+static int pcim_setup_msi_release(struct pci_dev *dev)
+{
+	int ret;
+
+	if (!pci_is_managed(dev) || dev->is_msi_managed)
+		return 0;
+
+	ret = devm_add_action(&dev->dev, pcim_msi_release, dev);
+	if (!ret)
+		dev->is_msi_managed = true;
+	return ret;
+}
+
+/*
+ * Ordering vs. devres: msi device data has to be installed first so that
+ * pcim_msi_release() is invoked before it on device release.
+ */
+static int pci_setup_msi_context(struct pci_dev *dev)
+{
+	int ret = msi_setup_device_data(&dev->dev);
+
+	if (!ret)
+		ret = pcim_setup_msi_release(dev);
+	return ret;
+}
+
+static int msi_setup_msi_desc(struct pci_dev *dev, int nvec,
+			      struct irq_affinity_desc *masks)
+{
+	struct msi_desc desc;
 	u16 control;
 
-	if (affd)
-		masks = irq_create_affinity_masks(nvec, affd);
-
 	/* MSI Entry Initialization */
-	entry = alloc_msi_entry(&dev->dev, nvec, masks);
-	if (!entry)
-		goto out;
+	memset(&desc, 0, sizeof(desc));
 
 	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
 	/* Lies, damned lies, and MSIs */
 	if (dev->dev_flags & PCI_DEV_FLAGS_HAS_MSI_MASKING)
 		control |= PCI_MSI_FLAGS_MASKBIT;
+	/* Respect XEN's mask disabling */
+	if (pci_msi_ignore_mask)
+		control &= ~PCI_MSI_FLAGS_MASKBIT;
 
-	entry->msi_attrib.is_msix	= 0;
-	entry->msi_attrib.is_64		= !!(control & PCI_MSI_FLAGS_64BIT);
-	entry->msi_attrib.is_virtual    = 0;
-	entry->msi_attrib.entry_nr	= 0;
-	entry->msi_attrib.can_mask	= !pci_msi_ignore_mask &&
-					  !!(control & PCI_MSI_FLAGS_MASKBIT);
-	entry->msi_attrib.default_irq	= dev->irq;	/* Save IOAPIC IRQ */
-	entry->msi_attrib.multi_cap	= (control & PCI_MSI_FLAGS_QMASK) >> 1;
-	entry->msi_attrib.multiple	= ilog2(__roundup_pow_of_two(nvec));
+	desc.nvec_used			= nvec;
+	desc.pci.msi_attrib.is_64	= !!(control & PCI_MSI_FLAGS_64BIT);
+	desc.pci.msi_attrib.can_mask	= !!(control & PCI_MSI_FLAGS_MASKBIT);
+	desc.pci.msi_attrib.default_irq	= dev->irq;
+	desc.pci.msi_attrib.multi_cap	= (control & PCI_MSI_FLAGS_QMASK) >> 1;
+	desc.pci.msi_attrib.multiple	= ilog2(__roundup_pow_of_two(nvec));
+	desc.affinity			= masks;
 
 	if (control & PCI_MSI_FLAGS_64BIT)
-		entry->mask_pos = dev->msi_cap + PCI_MSI_MASK_64;
+		desc.pci.mask_pos = dev->msi_cap + PCI_MSI_MASK_64;
 	else
-		entry->mask_pos = dev->msi_cap + PCI_MSI_MASK_32;
+		desc.pci.mask_pos = dev->msi_cap + PCI_MSI_MASK_32;
 
 	/* Save the initial mask status */
-	if (entry->msi_attrib.can_mask)
-		pci_read_config_dword(dev, entry->mask_pos, &entry->msi_mask);
+	if (desc.pci.msi_attrib.can_mask)
+		pci_read_config_dword(dev, desc.pci.mask_pos, &desc.pci.msi_mask);
 
-out:
-	kfree(masks);
-	return entry;
+	return msi_add_msi_desc(&dev->dev, &desc);
 }
 
 static int msi_verify_entries(struct pci_dev *dev)
···
 	if (!dev->no_64bit_msi)
 		return 0;
 
-	for_each_pci_msi_entry(entry, dev) {
+	msi_for_each_desc(entry, &dev->dev, MSI_DESC_ALL) {
 		if (entry->msg.address_hi) {
 			pci_err(dev, "arch assigned 64-bit MSI address %#x%08x but device only supports 32 bits\n",
 				entry->msg.address_hi, entry->msg.address_lo);
-			return -EIO;
+			break;
 		}
 	}
-	return 0;
+	return !entry ? 0 : -EIO;
 }
 
 /**
···
 static int msi_capability_init(struct pci_dev *dev, int nvec,
 			       struct irq_affinity *affd)
 {
-	const struct attribute_group **groups;
+	struct irq_affinity_desc *masks = NULL;
 	struct msi_desc *entry;
 	int ret;
 
-	pci_msi_set_enable(dev, 0);	/* Disable MSI during set up */
+	/*
+	 * Disable MSI during setup in the hardware, but mark it enabled
+	 * so that setup code can evaluate it.
+	 */
+	pci_msi_set_enable(dev, 0);
+	dev->msi_enabled = 1;
 
-	entry = msi_setup_entry(dev, nvec, affd);
-	if (!entry)
-		return -ENOMEM;
+	if (affd)
+		masks = irq_create_affinity_masks(nvec, affd);
+
+	msi_lock_descs(&dev->dev);
+	ret = msi_setup_msi_desc(dev, nvec, masks);
+	if (ret)
+		goto fail;
 
 	/* All MSIs are unmasked by default; mask them all */
+	entry = msi_first_desc(&dev->dev, MSI_DESC_ALL);
 	pci_msi_mask(entry, msi_multi_mask(entry));
-
-	list_add_tail(&entry->list, dev_to_msi_list(&dev->dev));
 
 	/* Configure MSI capability structure */
 	ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI);
···
 	if (ret)
 		goto err;
 
-	groups = msi_populate_sysfs(&dev->dev);
-	if (IS_ERR(groups)) {
-		ret = PTR_ERR(groups);
-		goto err;
-	}
-
-	dev->msi_irq_groups = groups;
-
 	/* Set MSI enabled bits	*/
 	pci_intx_for_msi(dev, 0);
 	pci_msi_set_enable(dev, 1);
-	dev->msi_enabled = 1;
 
 	pcibios_free_irq(dev);
 	dev->irq = entry->irq;
-	return 0;
+	goto unlock;
 
 err:
 	pci_msi_unmask(entry, msi_multi_mask(entry));
 	free_msi_irqs(dev);
+fail:
+	dev->msi_enabled = 0;
+unlock:
+	msi_unlock_descs(&dev->dev);
+	kfree(masks);
 	return ret;
 }
 
···
 	return ioremap(phys_addr, nr_entries * PCI_MSIX_ENTRY_SIZE);
 }
 
-static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
-			      struct msix_entry *entries, int nvec,
-			      struct irq_affinity *affd)
+static int msix_setup_msi_descs(struct pci_dev *dev, void __iomem *base,
+				struct msix_entry *entries, int nvec,
+				struct irq_affinity_desc *masks)
 {
-	struct irq_affinity_desc *curmsk, *masks = NULL;
-	struct msi_desc *entry;
+	int ret = 0, i, vec_count = pci_msix_vec_count(dev);
+	struct irq_affinity_desc *curmsk;
+	struct msi_desc desc;
 	void __iomem *addr;
-	int ret, i;
-	int vec_count = pci_msix_vec_count(dev);
 
-	if (affd)
-		masks = irq_create_affinity_masks(nvec, affd);
+	memset(&desc, 0, sizeof(desc));
 
-	for (i = 0, curmsk = masks; i < nvec; i++) {
-		entry = alloc_msi_entry(&dev->dev, 1, curmsk);
-		if (!entry) {
-			if (!i)
-				iounmap(base);
-			else
-				free_msi_irqs(dev);
-			/* No enough memory. Don't try again */
-			ret = -ENOMEM;
-			goto out;
+	desc.nvec_used			= 1;
+	desc.pci.msi_attrib.is_msix	= 1;
+	desc.pci.msi_attrib.is_64	= 1;
+	desc.pci.msi_attrib.default_irq	= dev->irq;
+	desc.pci.mask_base		= base;
+
+	for (i = 0, curmsk = masks; i < nvec; i++, curmsk++) {
+		desc.msi_index = entries ? entries[i].entry : i;
+		desc.affinity = masks ? curmsk : NULL;
+		desc.pci.msi_attrib.is_virtual = desc.msi_index >= vec_count;
+		desc.pci.msi_attrib.can_mask = !pci_msi_ignore_mask &&
+					       !desc.pci.msi_attrib.is_virtual;
+
+		if (!desc.pci.msi_attrib.can_mask) {
+			addr = pci_msix_desc_addr(&desc);
+			desc.pci.msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
 		}
 
-		entry->msi_attrib.is_msix	= 1;
-		entry->msi_attrib.is_64		= 1;
-
-		if (entries)
-			entry->msi_attrib.entry_nr = entries[i].entry;
-		else
-			entry->msi_attrib.entry_nr = i;
-
-		entry->msi_attrib.is_virtual =
-			entry->msi_attrib.entry_nr >= vec_count;
-
-		entry->msi_attrib.can_mask	= !pci_msi_ignore_mask &&
-						  !entry->msi_attrib.is_virtual;
-
-		entry->msi_attrib.default_irq	= dev->irq;
-		entry->mask_base		= base;
-
-		if (entry->msi_attrib.can_mask) {
-			addr = pci_msix_desc_addr(entry);
-			entry->msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
-		}
-
-		list_add_tail(&entry->list, dev_to_msi_list(&dev->dev));
-		if (masks)
-			curmsk++;
+		ret = msi_add_msi_desc(&dev->dev, &desc);
+		if (ret)
+			break;
 	}
-	ret = 0;
-out:
-	kfree(masks);
 	return ret;
 }
 
 static void msix_update_entries(struct pci_dev *dev, struct msix_entry *entries)
 {
-	struct msi_desc *entry;
+	struct msi_desc *desc;
 
-	for_each_pci_msi_entry(entry, dev) {
-		if (entries) {
-			entries->vector = entry->irq;
+	if (entries) {
+		msi_for_each_desc(desc, &dev->dev, MSI_DESC_ALL) {
+			entries->vector = desc->irq;
 			entries++;
 		}
 	}
···
 		writel(ctrl, base + PCI_MSIX_ENTRY_VECTOR_CTRL);
 }
 
+static int msix_setup_interrupts(struct pci_dev *dev, void __iomem *base,
+				 struct msix_entry *entries, int nvec,
+				 struct irq_affinity *affd)
+{
+	struct irq_affinity_desc *masks = NULL;
+	int ret;
+
+	if (affd)
+		masks = irq_create_affinity_masks(nvec, affd);
+
+	msi_lock_descs(&dev->dev);
+	ret = msix_setup_msi_descs(dev, base, entries, nvec, masks);
+	if (ret)
+		goto out_free;
+
+	ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX);
+	if (ret)
+		goto out_free;
+
+	/* Check if all MSI entries honor device restrictions */
+	ret = msi_verify_entries(dev);
+	if (ret)
+		goto out_free;
+
+	msix_update_entries(dev, entries);
+	goto out_unlock;
+
+out_free:
+	free_msi_irqs(dev);
+out_unlock:
+	msi_unlock_descs(&dev->dev);
+	kfree(masks);
+	return ret;
+}
+
 /**
  * msix_capability_init - configure device's MSI-X capability
  * @dev: pointer to the pci_dev data structure of MSI-X device function
···
 static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
 				int nvec, struct irq_affinity *affd)
 {
-	const struct attribute_group **groups;
 	void __iomem *base;
 	int ret, tsize;
 	u16 control;
···
 	pci_msix_clear_and_set_ctrl(dev, 0, PCI_MSIX_FLAGS_MASKALL |
 				    PCI_MSIX_FLAGS_ENABLE);
 
+	/* Mark it enabled so setup functions can query it */
+	dev->msix_enabled = 1;
+
 	pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control);
 	/* Request & Map MSI-X table region */
 	tsize = msix_table_size(control);
···
 		goto out_disable;
 	}
 
-	ret = msix_setup_entries(dev, base, entries, nvec, affd);
+	dev->msix_base = base;
+
+	ret = msix_setup_interrupts(dev, base, entries, nvec, affd);
 	if (ret)
 		goto out_disable;
 
-	ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX);
-	if (ret)
-		goto out_avail;
-
-	/* Check if all MSI entries honor device restrictions */
-	ret = msi_verify_entries(dev);
-	if (ret)
-		goto out_free;
-
-	msix_update_entries(dev, entries);
-
-	groups = msi_populate_sysfs(&dev->dev);
-	if (IS_ERR(groups)) {
-		ret = PTR_ERR(groups);
-		goto out_free;
-	}
-
-	dev->msi_irq_groups = groups;
-
-	/* Set MSI-X enabled bits and unmask the function */
+	/* Disable INTX */
 	pci_intx_for_msi(dev, 0);
-	dev->msix_enabled = 1;
 
 	/*
 	 * Ensure that all table entries are masked to prevent
···
 	pcibios_free_irq(dev);
 	return 0;
 
-out_avail:
-	if (ret < 0) {
-		/*
-		 * If we had some success, report the number of IRQs
-		 * we succeeded in setting up.
-		 */
-		struct msi_desc *entry;
-		int avail = 0;
-
-		for_each_pci_msi_entry(entry, dev) {
-			if (entry->irq != 0)
-				avail++;
-		}
-		if (avail != 0)
-			ret = avail;
-	}
-
-out_free:
-	free_msi_irqs(dev);
-
 out_disable:
+	dev->msix_enabled = 0;
 	pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE, 0);
 
 	return ret;
···
 	if (!pci_msi_enable || !dev || !dev->msi_enabled)
 		return;
 
-	BUG_ON(list_empty(dev_to_msi_list(&dev->dev)));
-	desc = first_pci_msi_entry(dev);
-
 	pci_msi_set_enable(dev, 0);
 	pci_intx_for_msi(dev, 1);
 	dev->msi_enabled = 0;
 
 	/* Return the device with MSI unmasked as initial states */
-	pci_msi_unmask(desc, msi_multi_mask(desc));
+	desc = msi_first_desc(&dev->dev, MSI_DESC_ALL);
+	if (!WARN_ON_ONCE(!desc))
+		pci_msi_unmask(desc, msi_multi_mask(desc));
 
 	/* Restore dev->irq to its default pin-assertion IRQ */
-	dev->irq = desc->msi_attrib.default_irq;
+	dev->irq = desc->pci.msi_attrib.default_irq;
 	pcibios_alloc_irq(dev);
 }
 
···
 	if (!pci_msi_enable || !dev || !dev->msi_enabled)
 		return;
 
+	msi_lock_descs(&dev->dev);
 	pci_msi_shutdown(dev);
 	free_msi_irqs(dev);
+	msi_unlock_descs(&dev->dev);
 }
 EXPORT_SYMBOL(pci_disable_msi);
 
···
 
 static void pci_msix_shutdown(struct pci_dev *dev)
 {
-	struct msi_desc *entry;
+	struct msi_desc *desc;
 
 	if (!pci_msi_enable || !dev || !dev->msix_enabled)
 		return;
···
 	}
 
 	/* Return the device with MSI-X masked as initial states */
-	for_each_pci_msi_entry(entry, dev)
-		pci_msix_mask(entry);
+	msi_for_each_desc(desc, &dev->dev, MSI_DESC_ALL)
+		pci_msix_mask(desc);
 
 	pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
 	pci_intx_for_msi(dev, 1);
···
 	if (!pci_msi_enable || !dev || !dev->msix_enabled)
 		return;
 
+	msi_lock_descs(&dev->dev);
 	pci_msix_shutdown(dev);
 	free_msi_irqs(dev);
+	msi_unlock_descs(&dev->dev);
 }
 EXPORT_SYMBOL(pci_disable_msix);
-
-void pci_no_msi(void)
-{
-	pci_msi_enable = 0;
-}
-
-/**
- * pci_msi_enabled - is MSI enabled?
- *
- * Returns true if MSI has not been disabled by the command-line option
- * pci=nomsi.
- **/
-int pci_msi_enabled(void)
-{
-	return pci_msi_enable;
-}
-EXPORT_SYMBOL(pci_msi_enabled);
 
 static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec,
 				  struct irq_affinity *affd)
···
 
 	if (nvec > maxvec)
 		nvec = maxvec;
+
+	rc = pci_setup_msi_context(dev);
+	if (rc)
+		return rc;
 
 	for (;;) {
 		if (affd) {
···
 
 	if (WARN_ON_ONCE(dev->msix_enabled))
 		return -EINVAL;
+
+	rc = pci_setup_msi_context(dev);
+	if (rc)
+		return rc;
 
 	for (;;) {
 		if (affd) {
···
 
 /**
  * pci_irq_vector - return Linux IRQ number of a device vector
- * @dev: PCI device to operate on
- * @nr: device-relative interrupt vector index (0-based).
+ * @dev:	PCI device to operate on
+ * @nr:		Interrupt vector index (0-based)
+ *
+ * @nr has the following meanings depending on the interrupt mode:
+ *   MSI-X:	The index in the MSI-X vector table
+ *   MSI:	The index of the enabled MSI vectors
+ *   INTx:	Must be 0
+ *
+ * Return: The Linux interrupt number or -EINVAl if @nr is out of range.
  */
 int pci_irq_vector(struct pci_dev *dev, unsigned int nr)
 {
-	if (dev->msix_enabled) {
-		struct msi_desc *entry;
-		int i = 0;
+	unsigned int irq;
 
-		for_each_pci_msi_entry(entry, dev) {
-			if (i == nr)
-				return entry->irq;
-			i++;
-		}
-		WARN_ON_ONCE(1);
-		return -EINVAL;
-	}
+	if (!dev->msi_enabled && !dev->msix_enabled)
+		return !nr ? dev->irq : -EINVAL;
 
-	if (dev->msi_enabled) {
-		struct msi_desc *entry = first_pci_msi_entry(dev);
-
-		if (WARN_ON_ONCE(nr >= entry->nvec_used))
-			return -EINVAL;
-	} else {
-		if (WARN_ON_ONCE(nr > 0))
-			return -EINVAL;
-	}
-
-	return dev->irq + nr;
+	irq = msi_get_virq(&dev->dev, nr);
+	return irq ? irq : -EINVAL;
 }
 EXPORT_SYMBOL(pci_irq_vector);
 
···
  * pci_irq_get_affinity - return the affinity of a particular MSI vector
  * @dev:	PCI device to operate on
  * @nr:		device-relative interrupt vector index (0-based).
+ *
+ * @nr has the following meanings depending on the interrupt mode:
+ *   MSI-X:	The index in the MSI-X vector table
+ *   MSI:	The index of the enabled MSI vectors
+ *   INTx:	Must be 0
+ *
+ * Return: A cpumask pointer or NULL if @nr is out of range
  */
 const struct cpumask *pci_irq_get_affinity(struct pci_dev *dev, int nr)
 {
-	if (dev->msix_enabled) {
-		struct msi_desc *entry;
-		int i = 0;
+	int idx, irq = pci_irq_vector(dev, nr);
+	struct msi_desc *desc;
 
-		for_each_pci_msi_entry(entry, dev) {
-			if (i == nr)
-				return &entry->affinity->mask;
-			i++;
-		}
-		WARN_ON_ONCE(1);
+	if (WARN_ON_ONCE(irq <= 0))
 		return NULL;
-	} else if (dev->msi_enabled) {
-		struct msi_desc *entry = first_pci_msi_entry(dev);
 
-		if (WARN_ON_ONCE(!entry || !entry->affinity ||
-				 nr >= entry->nvec_used))
-			return NULL;
-
-		return &entry->affinity[nr].mask;
-	} else {
+	desc = irq_get_msi_desc(irq);
+	/* Non-MSI does not have the information handy */
+	if (!desc)
 		return cpu_possible_mask;
-	}
+
+	if (WARN_ON_ONCE(!desc->affinity))
+		return NULL;
+
+	/*
+	 * MSI has a mask array in the descriptor.
+	 * MSI-X has a single mask.
+	 */
+	idx = dev->msi_enabled ? nr : 0;
+	return &desc->affinity[idx].mask;
 }
 EXPORT_SYMBOL(pci_irq_get_affinity);
 
···
 }
 EXPORT_SYMBOL(msi_desc_to_pci_dev);
 
-void *msi_desc_to_pci_sysdata(struct msi_desc *desc)
+void pci_no_msi(void)
 {
-	struct pci_dev *dev = msi_desc_to_pci_dev(desc);
-
-	return dev->bus->sysdata;
-}
-EXPORT_SYMBOL_GPL(msi_desc_to_pci_sysdata);
-
-#ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
-/**
- * pci_msi_domain_write_msg - Helper to write MSI message to PCI config space
- * @irq_data:	Pointer to interrupt data of the MSI interrupt
- * @msg:	Pointer to the message
- */
-void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg)
-{
-	struct msi_desc *desc = irq_data_get_msi_desc(irq_data);
-
-	/*
-	 * For MSI-X desc->irq is always equal to irq_data->irq. For
-	 * MSI only the first interrupt of MULTI MSI passes the test.
-	 */
-	if (desc->irq == irq_data->irq)
-		__pci_write_msi_msg(desc, msg);
+	pci_msi_enable = 0;
 }
 
 /**
- * pci_msi_domain_calc_hwirq - Generate a unique ID for an MSI source
- * @desc:	Pointer to the MSI descriptor
+ * pci_msi_enabled - is MSI enabled?
  *
- * The ID number is only used within the irqdomain.
- */
-static irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc)
+ * Returns true if MSI has not been disabled by the command-line option
+ * pci=nomsi.
+ **/
+int pci_msi_enabled(void)
 {
-	struct pci_dev *dev = msi_desc_to_pci_dev(desc);
-
-	return (irq_hw_number_t)desc->msi_attrib.entry_nr |
-		pci_dev_id(dev) << 11 |
-		(pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 27;
+	return pci_msi_enable;
 }
-
-static inline bool pci_msi_desc_is_multi_msi(struct msi_desc *desc)
-{
-	return !desc->msi_attrib.is_msix && desc->nvec_used > 1;
-}
-
-/**
- * pci_msi_domain_check_cap - Verify that @domain supports the capabilities
- * 			      for @dev
- * @domain:	The interrupt domain to check
- * @info:	The domain info for verification
- * @dev:	The device to check
- *
- * Returns:
- *  0 if the functionality is supported
- *  1 if Multi MSI is requested, but the domain does not support it
- *  -ENOTSUPP otherwise
- */
-int pci_msi_domain_check_cap(struct irq_domain *domain,
-			     struct msi_domain_info *info, struct device *dev)
-{
-	struct msi_desc *desc = first_pci_msi_entry(to_pci_dev(dev));
-
-	/* Special handling to support __pci_enable_msi_range() */
-	if (pci_msi_desc_is_multi_msi(desc) &&
-	    !(info->flags & MSI_FLAG_MULTI_PCI_MSI))
-		return 1;
-	else if (desc->msi_attrib.is_msix && !(info->flags & MSI_FLAG_PCI_MSIX))
-		return -ENOTSUPP;
-
-	return 0;
-}
-
-static int pci_msi_domain_handle_error(struct irq_domain *domain,
-				       struct msi_desc *desc, int error)
-{
-	/* Special handling to support __pci_enable_msi_range() */
-	if (pci_msi_desc_is_multi_msi(desc) && error == -ENOSPC)
-		return 1;
-
-	return error;
-}
-
-static void pci_msi_domain_set_desc(msi_alloc_info_t *arg,
-				    struct msi_desc *desc)
-{
-	arg->desc = desc;
-	arg->hwirq = pci_msi_domain_calc_hwirq(desc);
-}
-
-static struct msi_domain_ops pci_msi_domain_ops_default = {
-	.set_desc	= pci_msi_domain_set_desc,
-	.msi_check	= pci_msi_domain_check_cap,
-	.handle_error	= pci_msi_domain_handle_error,
-};
-
-static void pci_msi_domain_update_dom_ops(struct msi_domain_info *info)
-{
-	struct msi_domain_ops *ops = info->ops;
-
-	if (ops == NULL) {
-		info->ops = &pci_msi_domain_ops_default;
-	} else {
-		if (ops->set_desc == NULL)
-			ops->set_desc = pci_msi_domain_set_desc;
-		if (ops->msi_check == NULL)
-			ops->msi_check = pci_msi_domain_check_cap;
-		if (ops->handle_error == NULL)
-			ops->handle_error = pci_msi_domain_handle_error;
-	}
-}
-
-static void pci_msi_domain_update_chip_ops(struct msi_domain_info *info)
-{
-	struct irq_chip *chip = info->chip;
-
-	BUG_ON(!chip);
-	if (!chip->irq_write_msi_msg)
-		chip->irq_write_msi_msg = pci_msi_domain_write_msg;
-	if (!chip->irq_mask)
-		chip->irq_mask = pci_msi_mask_irq;
-	if (!chip->irq_unmask)
-		chip->irq_unmask = pci_msi_unmask_irq;
-}
-
-/**
- * pci_msi_create_irq_domain - Create a MSI interrupt domain
- * @fwnode:	Optional fwnode of the interrupt controller
- * @info:	MSI domain info
- * @parent:	Parent irq domain
- *
- * Updates the domain and chip ops and creates a MSI interrupt domain.
- *
- * Returns:
- * A domain pointer or NULL in case of failure.
- */
-struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
-					     struct msi_domain_info *info,
-					     struct irq_domain *parent)
-{
-	struct irq_domain *domain;
-
-	if (WARN_ON(info->flags & MSI_FLAG_LEVEL_CAPABLE))
-		info->flags &= ~MSI_FLAG_LEVEL_CAPABLE;
-
-	if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS)
-		pci_msi_domain_update_dom_ops(info);
-	if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
-		pci_msi_domain_update_chip_ops(info);
-
-	info->flags |= MSI_FLAG_ACTIVATE_EARLY;
-	if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE))
-		info->flags |= MSI_FLAG_MUST_REACTIVATE;
-
-	/* PCI-MSI is oneshot-safe */
-	info->chip->flags |= IRQCHIP_ONESHOT_SAFE;
-
-	domain = msi_create_irq_domain(fwnode, info, parent);
-	if (!domain)
-		return NULL;
-
-	irq_domain_update_bus_token(domain, DOMAIN_BUS_PCI_MSI);
-	return domain;
-}
-EXPORT_SYMBOL_GPL(pci_msi_create_irq_domain);
-
-/*
- * Users of the generic MSI infrastructure expect a device to have a single ID,
- * so with DMA aliases we have to pick the least-worst compromise. Devices with
- * DMA phantom functions tend to still emit MSIs from the real function number,
- * so we ignore those and only consider topological aliases where either the
- * alias device or RID appears on a different bus number. We also make the
- * reasonable assumption that bridges are walked in an upstream direction (so
- * the last one seen wins), and the much braver assumption that the most likely
- * case is that of PCI->PCIe so we should always use the alias RID. This echoes
- * the logic from intel_irq_remapping's set_msi_sid(), which presumably works
- * well enough in practice; in the face of the horrible PCIe<->PCI-X conditions
- * for taking ownership all we can really do is close our eyes and hope...
- */
-static int get_msi_id_cb(struct pci_dev *pdev, u16 alias, void *data)
-{
-	u32 *pa = data;
-	u8 bus = PCI_BUS_NUM(*pa);
-
-	if (pdev->bus->number != bus || PCI_BUS_NUM(alias) != bus)
-		*pa = alias;
-
-	return 0;
-}
-
-/**
- * pci_msi_domain_get_msi_rid - Get the MSI requester id (RID)
- * @domain:	The interrupt domain
- * @pdev:	The PCI device.
- *
- * The RID for a device is formed from the alias, with a firmware
- * supplied mapping applied
- *
- * Returns: The RID.
- */
-u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev)
-{
-	struct device_node *of_node;
-	u32 rid = pci_dev_id(pdev);
-
-	pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid);
-
-	of_node = irq_domain_get_of_node(domain);
-	rid = of_node ? of_msi_map_id(&pdev->dev, of_node, rid) :
-			iort_msi_map_id(&pdev->dev, rid);
-
-	return rid;
-}
-
-/**
- * pci_msi_get_device_domain - Get the MSI domain for a given PCI device
- * @pdev:	The PCI device
- *
- * Use the firmware data to find a device-specific MSI domain
- * (i.e. not one that is set as a default).
- *
- * Returns: The corresponding MSI domain or NULL if none has been found.
- */
-struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev)
-{
-	struct irq_domain *dom;
-	u32 rid = pci_dev_id(pdev);
-
-	pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid);
-	dom = of_msi_map_get_device_domain(&pdev->dev, rid, DOMAIN_BUS_PCI_MSI);
-	if (!dom)
-		dom = iort_get_device_domain(&pdev->dev, rid,
-					     DOMAIN_BUS_PCI_MSI);
-	return dom;
-}
-
-/**
- * pci_dev_has_special_msi_domain - Check whether the device is handled by
- *				    a non-standard PCI-MSI domain
- * @pdev:	The PCI device to check.
- *
- * Returns: True if the device irqdomain or the bus irqdomain is
- * non-standard PCI/MSI.
- */
-bool pci_dev_has_special_msi_domain(struct pci_dev *pdev)
-{
-	struct irq_domain *dom = dev_get_msi_domain(&pdev->dev);
-
-	if (!dom)
-		dom = dev_get_msi_domain(&pdev->bus->dev);
-
-	if (!dom)
-		return true;
-
-	return dom->bus_token != DOMAIN_BUS_PCI_MSI;
-}
-
-#endif /* CONFIG_PCI_MSI_IRQ_DOMAIN */
-#endif /* CONFIG_PCI_MSI */
-
-void pci_msi_init(struct pci_dev *dev)
-{
-	u16 ctrl;
-
-	/*
-	 * Disable the MSI hardware to avoid screaming interrupts
-	 * during boot.  This is the power on reset default so
-	 * usually this should be a noop.
-	 */
-	dev->msi_cap = pci_find_capability(dev, PCI_CAP_ID_MSI);
-	if (!dev->msi_cap)
-		return;
-
-	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &ctrl);
-	if (ctrl & PCI_MSI_FLAGS_ENABLE)
-		pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS,
-				      ctrl & ~PCI_MSI_FLAGS_ENABLE);
-
-	if (!(ctrl & PCI_MSI_FLAGS_64BIT))
-		dev->no_64bit_msi = 1;
-}
-
-void pci_msix_init(struct pci_dev *dev)
-{
-	u16 ctrl;
-
-	dev->msix_cap = pci_find_capability(dev, PCI_CAP_ID_MSIX);
-	if (!dev->msix_cap)
-		return;
-
-	pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &ctrl);
-	if (ctrl & PCI_MSIX_FLAGS_ENABLE)
-		pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS,
-				      ctrl & ~PCI_MSIX_FLAGS_ENABLE);
-}
+EXPORT_SYMBOL(pci_msi_enabled);

drivers/pci/msi/Makefile

···
+# SPDX-License-Identifier: GPL-2.0
+#
+# Makefile for the PCI/MSI
+obj-$(CONFIG_PCI)			+= pcidev_msi.o
+obj-$(CONFIG_PCI_MSI)			+= msi.o
+obj-$(CONFIG_PCI_MSI_IRQ_DOMAIN)	+= irqdomain.o
+obj-$(CONFIG_PCI_MSI_ARCH_FALLBACKS)	+= legacy.o

drivers/pci/msi/irqdomain.c

···
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PCI Message Signaled Interrupt (MSI) - irqdomain support
+ */
+#include <linux/acpi_iort.h>
+#include <linux/irqdomain.h>
+#include <linux/of_irq.h>
+
+#include "msi.h"
+
+int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	struct irq_domain *domain;
+
+	domain = dev_get_msi_domain(&dev->dev);
+	if (domain && irq_domain_is_hierarchy(domain))
+		return msi_domain_alloc_irqs_descs_locked(domain, &dev->dev, nvec);
+
+	return pci_msi_legacy_setup_msi_irqs(dev, nvec, type);
+}
+
+void pci_msi_teardown_msi_irqs(struct pci_dev *dev)
+{
+	struct irq_domain *domain;
+
+	domain = dev_get_msi_domain(&dev->dev);
+	if (domain && irq_domain_is_hierarchy(domain))
+		msi_domain_free_irqs_descs_locked(domain, &dev->dev);
+	else
+		pci_msi_legacy_teardown_msi_irqs(dev);
+}
+
+/**
+ * pci_msi_domain_write_msg - Helper to write MSI message to PCI config space
+ * @irq_data:	Pointer to interrupt data of the MSI interrupt
+ * @msg:	Pointer to the message
+ */
+static void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg)
+{
+	struct msi_desc *desc = irq_data_get_msi_desc(irq_data);
+
+	/*
+	 * For MSI-X desc->irq is always equal to irq_data->irq. For
+	 * MSI only the first interrupt of MULTI MSI passes the test.
+	 */
+	if (desc->irq == irq_data->irq)
+		__pci_write_msi_msg(desc, msg);
+}
+
+/**
+ * pci_msi_domain_calc_hwirq - Generate a unique ID for an MSI source
+ * @desc:	Pointer to the MSI descriptor
+ *
+ * The ID number is only used within the irqdomain.
+ */
+static irq_hw_number_t pci_msi_domain_calc_hwirq(struct msi_desc *desc)
+{
+	struct pci_dev *dev = msi_desc_to_pci_dev(desc);
+
+	return (irq_hw_number_t)desc->msi_index |
+		pci_dev_id(dev) << 11 |
+		(pci_domain_nr(dev->bus) & 0xFFFFFFFF) << 27;
+}
+
+static inline bool pci_msi_desc_is_multi_msi(struct msi_desc *desc)
+{
+	return !desc->pci.msi_attrib.is_msix && desc->nvec_used > 1;
+}
+
+/**
+ * pci_msi_domain_check_cap - Verify that @domain supports the capabilities
+ *			      for @dev
+ * @domain:	The interrupt domain to check
+ * @info:	The domain info for verification
+ * @dev:	The device to check
+ *
+ * Returns:
+ *  0 if the functionality is supported
+ *  1 if Multi MSI is requested, but the domain does not support it
+ *  -ENOTSUPP otherwise
+ */
+static int pci_msi_domain_check_cap(struct irq_domain *domain,
+				    struct msi_domain_info *info,
+				    struct device *dev)
+{
+	struct msi_desc *desc = msi_first_desc(dev, MSI_DESC_ALL);
+
+	/* Special handling to support __pci_enable_msi_range() */
+	if (pci_msi_desc_is_multi_msi(desc) &&
+	    !(info->flags & MSI_FLAG_MULTI_PCI_MSI))
+		return 1;
+
+	if (desc->pci.msi_attrib.is_msix) {
+		if (!(info->flags & MSI_FLAG_PCI_MSIX))
+			return -ENOTSUPP;
+
+		if (info->flags & MSI_FLAG_MSIX_CONTIGUOUS) {
+			unsigned int idx = 0;
+
+			/* Check for gaps in the entry indices */
+			msi_for_each_desc(desc, dev, MSI_DESC_ALL) {
+				if (desc->msi_index != idx++)
+					return -ENOTSUPP;
+			}
+		}
+	}
+	return 0;
+}
+
+static void pci_msi_domain_set_desc(msi_alloc_info_t *arg,
+				    struct msi_desc *desc)
+{
+	arg->desc = desc;
+	arg->hwirq = pci_msi_domain_calc_hwirq(desc);
+}
+
+static struct msi_domain_ops pci_msi_domain_ops_default = {
+	.set_desc	= pci_msi_domain_set_desc,
+	.msi_check	= pci_msi_domain_check_cap,
+};
+
+static void pci_msi_domain_update_dom_ops(struct msi_domain_info *info)
+{
+	struct msi_domain_ops *ops = info->ops;
+
+	if (ops == NULL) {
+		info->ops = &pci_msi_domain_ops_default;
+	} else {
+		if (ops->set_desc == NULL)
+			ops->set_desc = pci_msi_domain_set_desc;
+		if (ops->msi_check == NULL)
+			ops->msi_check = pci_msi_domain_check_cap;
+	}
+}
+
+static void pci_msi_domain_update_chip_ops(struct msi_domain_info *info)
+{
+	struct irq_chip *chip = info->chip;
+
+	BUG_ON(!chip);
+	if (!chip->irq_write_msi_msg)
+		chip->irq_write_msi_msg = pci_msi_domain_write_msg;
+	if (!chip->irq_mask)
+		chip->irq_mask = pci_msi_mask_irq;
+	if (!chip->irq_unmask)
+		chip->irq_unmask = pci_msi_unmask_irq;
+}
+
+/**
+ * pci_msi_create_irq_domain - Create a MSI interrupt domain
+ * @fwnode:	Optional fwnode of the interrupt controller
+ * @info:	MSI domain info
+ * @parent:	Parent irq domain
+ *
+ * Updates the domain and chip ops and creates a MSI interrupt domain.
+ *
+ * Returns:
+ * A domain pointer or NULL in case of failure.
+ */
+struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
+					     struct msi_domain_info *info,
+					     struct irq_domain *parent)
+{
+	struct irq_domain *domain;
+
+	if (WARN_ON(info->flags & MSI_FLAG_LEVEL_CAPABLE))
+		info->flags &= ~MSI_FLAG_LEVEL_CAPABLE;
+
+	if (info->flags & MSI_FLAG_USE_DEF_DOM_OPS)
+		pci_msi_domain_update_dom_ops(info);
+	if (info->flags & MSI_FLAG_USE_DEF_CHIP_OPS)
+		pci_msi_domain_update_chip_ops(info);
+
+	info->flags |= MSI_FLAG_ACTIVATE_EARLY | MSI_FLAG_DEV_SYSFS |
+		       MSI_FLAG_FREE_MSI_DESCS;
+	if (IS_ENABLED(CONFIG_GENERIC_IRQ_RESERVATION_MODE))
+		info->flags |= MSI_FLAG_MUST_REACTIVATE;
+
+	/* PCI-MSI is oneshot-safe */
+	info->chip->flags |= IRQCHIP_ONESHOT_SAFE;
+
+	domain = msi_create_irq_domain(fwnode, info, parent);
+	if (!domain)
+		return NULL;
+
+	irq_domain_update_bus_token(domain, DOMAIN_BUS_PCI_MSI);
+	return domain;
+}
+EXPORT_SYMBOL_GPL(pci_msi_create_irq_domain);
+
+/*
+ * Users of the generic MSI infrastructure expect a device to have a single ID,
+ * so with DMA aliases we have to pick the least-worst compromise. Devices with
+ * DMA phantom functions tend to still emit MSIs from the real function number,
+ * so we ignore those and only consider topological aliases where either the
+ * alias device or RID appears on a different bus number. We also make the
+ * reasonable assumption that bridges are walked in an upstream direction (so
+ * the last one seen wins), and the much braver assumption that the most likely
+ * case is that of PCI->PCIe so we should always use the alias RID. This echoes
+ * the logic from intel_irq_remapping's set_msi_sid(), which presumably works
+ * well enough in practice; in the face of the horrible PCIe<->PCI-X conditions
+ * for taking ownership all we can really do is close our eyes and hope...
+ */
+static int get_msi_id_cb(struct pci_dev *pdev, u16 alias, void *data)
+{
+	u32 *pa = data;
+	u8 bus = PCI_BUS_NUM(*pa);
+
+	if (pdev->bus->number != bus || PCI_BUS_NUM(alias) != bus)
+		*pa = alias;
+
+	return 0;
+}
+
+/**
+ * pci_msi_domain_get_msi_rid - Get the MSI requester id (RID)
+ * @domain:	The interrupt domain
+ * @pdev:	The PCI device.
+ *
+ * The RID for a device is formed from the alias, with a firmware
+ * supplied mapping applied
+ *
+ * Returns: The RID.
+ */
+u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev)
+{
+	struct device_node *of_node;
+	u32 rid = pci_dev_id(pdev);
+
+	pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid);
+
+	of_node = irq_domain_get_of_node(domain);
+	rid = of_node ? of_msi_map_id(&pdev->dev, of_node, rid) :
+			iort_msi_map_id(&pdev->dev, rid);
+
+	return rid;
+}
+
+/**
+ * pci_msi_get_device_domain - Get the MSI domain for a given PCI device
+ * @pdev:	The PCI device
+ *
+ * Use the firmware data to find a device-specific MSI domain
+ * (i.e. not one that is set as a default).
+ *
+ * Returns: The corresponding MSI domain or NULL if none has been found.
+ */
+struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev)
+{
+	struct irq_domain *dom;
+	u32 rid = pci_dev_id(pdev);
+
+	pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid);
+	dom = of_msi_map_get_device_domain(&pdev->dev, rid, DOMAIN_BUS_PCI_MSI);
+	if (!dom)
+		dom = iort_get_device_domain(&pdev->dev, rid,
+					     DOMAIN_BUS_PCI_MSI);
+	return dom;
+}
+
+/**
+ * pci_dev_has_special_msi_domain - Check whether the device is handled by
+ *				    a non-standard PCI-MSI domain
+ * @pdev:	The PCI device to check.
+ *
+ * Returns: True if the device irqdomain or the bus irqdomain is
+ * non-standard PCI/MSI.
+ */
+bool pci_dev_has_special_msi_domain(struct pci_dev *pdev)
+{
+	struct irq_domain *dom = dev_get_msi_domain(&pdev->dev);
+
+	if (!dom)
+		dom = dev_get_msi_domain(&pdev->bus->dev);
+
+	if (!dom)
+		return true;
+
+	return dom->bus_token != DOMAIN_BUS_PCI_MSI;
+}

drivers/pci/msi/legacy.c

···
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PCI Message Signaled Interrupt (MSI).
+ *
+ * Legacy architecture specific setup and teardown mechanism.
+ */
+#include "msi.h"
+
+/* Arch hooks */
+int __weak arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
+{
+	return -EINVAL;
+}
+
+void __weak arch_teardown_msi_irq(unsigned int irq)
+{
+}
+
+int __weak arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	struct msi_desc *desc;
+	int ret;
+
+	/*
+	 * If an architecture wants to support multiple MSI, it needs to
+	 * override arch_setup_msi_irqs()
+	 */
+	if (type == PCI_CAP_ID_MSI && nvec > 1)
+		return 1;
+
+	msi_for_each_desc(desc, &dev->dev, MSI_DESC_NOTASSOCIATED) {
+		ret = arch_setup_msi_irq(dev, desc);
+		if (ret)
+			return ret < 0 ? ret : -ENOSPC;
+	}
+
+	return 0;
+}
+
+void __weak arch_teardown_msi_irqs(struct pci_dev *dev)
+{
+	struct msi_desc *desc;
+	int i;
+
+	msi_for_each_desc(desc, &dev->dev, MSI_DESC_ASSOCIATED) {
+		for (i = 0; i < desc->nvec_used; i++)
+			arch_teardown_msi_irq(desc->irq + i);
+	}
+}
+
+static int pci_msi_setup_check_result(struct pci_dev *dev, int type, int ret)
+{
+	struct msi_desc *desc;
+	int avail = 0;
+
+	if (type != PCI_CAP_ID_MSIX || ret >= 0)
+		return ret;
+
+	/* Scan the MSI descriptors for successfully allocated ones. */
+	msi_for_each_desc(desc, &dev->dev, MSI_DESC_ASSOCIATED)
+		avail++;
+
+	return avail ? avail : ret;
+}
+
+int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	int ret = arch_setup_msi_irqs(dev, nvec, type);
+
+	ret = pci_msi_setup_check_result(dev, type, ret);
+	if (!ret)
+		ret = msi_device_populate_sysfs(&dev->dev);
+	return ret;
+}
+
+void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev)
+{
+	msi_device_destroy_sysfs(&dev->dev);
+	arch_teardown_msi_irqs(dev);
+	msi_free_msi_descs(&dev->dev);
+}

drivers/pci/msi/msi.h

···
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#include <linux/pci.h>
+#include <linux/msi.h>
+
+#define msix_table_size(flags)	((flags & PCI_MSIX_FLAGS_QSIZE) + 1)
+
+extern int pci_msi_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
+extern void pci_msi_teardown_msi_irqs(struct pci_dev *dev);
+
+#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS
+extern int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
+extern void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev);
+#else
+static inline int pci_msi_legacy_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	WARN_ON_ONCE(1);
+	return -ENODEV;
+}
+
+static inline void pci_msi_legacy_teardown_msi_irqs(struct pci_dev *dev)
+{
+	WARN_ON_ONCE(1);
+}
+#endif
+
+/*
+ * PCI 2.3 does not specify mask bits for each MSI interrupt.  Attempting to
+ * mask all MSI interrupts by clearing the MSI enable bit does not work
+ * reliably as devices without an INTx disable bit will then generate a
+ * level IRQ which will never be cleared.
+ */
+static inline __attribute_const__ u32 msi_multi_mask(struct msi_desc *desc)
+{
+	/* Don't shift by >= width of type */
+	if (desc->pci.msi_attrib.multi_cap >= 5)
+		return 0xffffffff;
+	return (1 << (1 << desc->pci.msi_attrib.multi_cap)) - 1;
+}

drivers/pci/msi/pcidev_msi.c

···
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * MSI[X} related functions which are available unconditionally.
+ */
+#include "../pci.h"
+
+/*
+ * Disable the MSI[X] hardware to avoid screaming interrupts during boot.
+ * This is the power on reset default so usually this should be a noop.
+ */
+
+void pci_msi_init(struct pci_dev *dev)
+{
+	u16 ctrl;
+
+	dev->msi_cap = pci_find_capability(dev, PCI_CAP_ID_MSI);
+	if (!dev->msi_cap)
+		return;
+
+	pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &ctrl);
+	if (ctrl & PCI_MSI_FLAGS_ENABLE) {
+		pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS,
+				      ctrl & ~PCI_MSI_FLAGS_ENABLE);
+	}
+
+	if (!(ctrl & PCI_MSI_FLAGS_64BIT))
+		dev->no_64bit_msi = 1;
+}
+
+void pci_msix_init(struct pci_dev *dev)
+{
+	u16 ctrl;
+
+	dev->msix_cap = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+	if (!dev->msix_cap)
+		return;
+
+	pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &ctrl);
+	if (ctrl & PCI_MSIX_FLAGS_ENABLE) {
+		pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS,
+				      ctrl & ~PCI_MSIX_FLAGS_ENABLE);
+	}
+}

drivers/pci/pci-sysfs.c

···
 	 * For MSI, show the first MSI IRQ; for all other cases including
 	 * MSI-X, show the legacy INTx IRQ.
 	 */
-	if (pdev->msi_enabled) {
-		struct msi_desc *desc = first_pci_msi_entry(pdev);
-
-		return sysfs_emit(buf, "%u\n", desc->irq);
-	}
+	if (pdev->msi_enabled)
+		return sysfs_emit(buf, "%u\n", pci_irq_vector(pdev, 0));
 #endif
 
 	return sysfs_emit(buf, "%u\n", pdev->irq);

drivers/pci/pci.c

···
 	struct pci_devres *this = res;
 	int i;
 
-	if (dev->msi_enabled)
-		pci_disable_msi(dev);
-	if (dev->msix_enabled)
-		pci_disable_msix(dev);
-
 	for (i = 0; i < DEVICE_COUNT_RESOURCE; i++)
 		if (this->region_mask & (1 << i))
 			pci_release_region(dev, i);

drivers/pci/probe.c

···
 	INIT_LIST_HEAD(&dev->bus_list);
 	dev->dev.type = &pci_dev_type;
 	dev->bus = pci_bus_get(bus);
-
+#ifdef CONFIG_PCI_MSI
+	raw_spin_lock_init(&dev->msi_lock);
+#endif
 	return dev;
 }
 EXPORT_SYMBOL(pci_alloc_dev);

drivers/pci/xen-pcifront.c

···
 	}
 
 	i = 0;
-	for_each_pci_msi_entry(entry, dev) {
-		op.msix_entries[i].entry = entry->msi_attrib.entry_nr;
+	msi_for_each_desc(entry, &dev->dev, MSI_DESC_NOTASSOCIATED) {
+		op.msix_entries[i].entry = entry->msi_index;
 		/* Vector is useless at this point. */
 		op.msix_entries[i].vector = -1;
 		i++;

drivers/perf/arm_smmuv3_pmu.c

···
 
 static void smmu_pmu_setup_msi(struct smmu_pmu *pmu)
 {
-	struct msi_desc *desc;
 	struct device *dev = pmu->dev;
 	int ret;
 
···
 		return;
 	}
 
-	desc = first_msi_entry(dev);
-	if (desc)
-		pmu->irq = desc->irq;
+	pmu->irq = msi_get_virq(dev, 0);
 
 	/* Add callback to free MSIs on teardown */
 	devm_add_action(dev, smmu_pmu_free_msis, dev);

drivers/soc/fsl/dpio/dpio-driver.c

···
 	irq = dpio_dev->irqs[0];
 
 	/* clear the affinity hint */
-	irq_set_affinity_hint(irq->msi_desc->irq, NULL);
+	irq_set_affinity_hint(irq->virq, NULL);
 }
 
 static int register_dpio_irq_handlers(struct fsl_mc_device *dpio_dev, int cpu)
···
 
 	irq = dpio_dev->irqs[0];
 	error = devm_request_irq(&dpio_dev->dev,
-				 irq->msi_desc->irq,
+				 irq->virq,
 				 dpio_irq_handler,
 				 0,
 				 dev_name(&dpio_dev->dev),
···
 	}
 
 	/* set the affinity hint */
-	if (irq_set_affinity_hint(irq->msi_desc->irq, cpumask_of(cpu)))
+	if (irq_set_affinity_hint(irq->virq, cpumask_of(cpu)))
 		dev_err(&dpio_dev->dev,
 			"irq_set_affinity failed irq %d cpu %d\n",
-			irq->msi_desc->irq, cpu);
+			irq->virq, cpu);
 
 	return 0;
 }

drivers/soc/ti/k3-ringacc.c

···
 	if (!ring)
 		return -EINVAL;
 
-	irq_num = ti_sci_inta_msi_get_virq(ring->parent->dev, ring->ring_id);
+	irq_num = msi_get_virq(ring->parent->dev, ring->ring_id);
 	if (irq_num <= 0)
 		irq_num = -EINVAL;
 	return irq_num;
···
 	struct resource *res;
 	int ret, i;
 
-	dev->msi_domain = of_msi_get_domain(dev, dev->of_node,
+	dev->msi.domain = of_msi_get_domain(dev, dev->of_node,
 					    DOMAIN_BUS_TI_SCI_INTA_MSI);
-	if (!dev->msi_domain) {
+	if (!dev->msi.domain) {
 		dev_err(dev, "Failed to get MSI domain\n");
 		return -EPROBE_DEFER;
 	}

drivers/soc/ti/ti_sci_inta_msi.c

···
 	struct irq_domain *domain;
 
 	ti_sci_inta_msi_update_chip_ops(info);
+	info->flags |= MSI_FLAG_FREE_MSI_DESCS;
 
 	domain = msi_create_irq_domain(fwnode, info, parent);
 	if (domain)
···
 }
 EXPORT_SYMBOL_GPL(ti_sci_inta_msi_create_irq_domain);
 
-static void ti_sci_inta_msi_free_descs(struct device *dev)
-{
-	struct msi_desc *desc, *tmp;
-
-	list_for_each_entry_safe(desc, tmp, dev_to_msi_list(dev), list) {
-		list_del(&desc->list);
-		free_msi_entry(desc);
-	}
-}
-
 static int ti_sci_inta_msi_alloc_descs(struct device *dev,
 				       struct ti_sci_resource *res)
 {
-	struct msi_desc *msi_desc;
+	struct msi_desc msi_desc;
 	int set, i, count = 0;
 
+	memset(&msi_desc, 0, sizeof(msi_desc));
+	msi_desc.nvec_used = 1;
+
 	for (set = 0; set < res->sets; set++) {
-		for (i = 0; i < res->desc[set].num; i++) {
-			msi_desc = alloc_msi_entry(dev, 1, NULL);
-			if (!msi_desc) {
-				ti_sci_inta_msi_free_descs(dev);
-				return -ENOMEM;
-			}
-
-			msi_desc->inta.dev_index = res->desc[set].start + i;
-			INIT_LIST_HEAD(&msi_desc->list);
-			list_add_tail(&msi_desc->list, dev_to_msi_list(dev));
-			count++;
+		for (i = 0; i < res->desc[set].num; i++, count++) {
+			msi_desc.msi_index = res->desc[set].start + i;
+			if (msi_add_msi_desc(dev, &msi_desc))
+				goto fail;
 		}
-		for (i = 0; i < res->desc[set].num_sec; i++) {
-			msi_desc = alloc_msi_entry(dev, 1, NULL);
-			if (!msi_desc) {
-				ti_sci_inta_msi_free_descs(dev);
-				return -ENOMEM;
-			}
 
-			msi_desc->inta.dev_index = res->desc[set].start_sec + i;
-			INIT_LIST_HEAD(&msi_desc->list);
-			list_add_tail(&msi_desc->list, dev_to_msi_list(dev));
-			count++;
+		for (i = 0; i < res->desc[set].num_sec; i++, count++) {
+			msi_desc.msi_index = res->desc[set].start_sec + i;
+			if (msi_add_msi_desc(dev, &msi_desc))
+				goto fail;
 		}
 	}
-
 	return count;
+fail:
+	msi_free_msi_descs(dev);
+	return -ENOMEM;
 }
 
 int ti_sci_inta_msi_domain_alloc_irqs(struct device *dev,
···
 	if (pdev->id < 0)
 		return -ENODEV;
 
-	nvec = ti_sci_inta_msi_alloc_descs(dev, res);
-	if (nvec <= 0)
-		return nvec;
+	ret = msi_setup_device_data(dev);
+	if (ret)
+		return ret;
 
-	ret = msi_domain_alloc_irqs(msi_domain, dev, nvec);
-	if (ret) {
-		dev_err(dev, "Failed to allocate IRQs %d\n", ret);
-		goto cleanup;
+	msi_lock_descs(dev);
+	nvec = ti_sci_inta_msi_alloc_descs(dev, res);
+	if (nvec <= 0) {
+		ret = nvec;
+		goto unlock;
 	}
 
-	return 0;
-
-cleanup:
-	ti_sci_inta_msi_free_descs(&pdev->dev);
+	ret = msi_domain_alloc_irqs_descs_locked(msi_domain, dev, nvec);
+	if (ret)
+		dev_err(dev, "Failed to allocate IRQs %d\n", ret);
+unlock:
+	msi_unlock_descs(dev);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(ti_sci_inta_msi_domain_alloc_irqs);
-
-void ti_sci_inta_msi_domain_free_irqs(struct device *dev)
-{
-	msi_domain_free_irqs(dev->msi_domain, dev);
-	ti_sci_inta_msi_free_descs(dev);
-}
-EXPORT_SYMBOL_GPL(ti_sci_inta_msi_domain_free_irqs);
-
-unsigned int ti_sci_inta_msi_get_virq(struct device *dev, u32 dev_index)
-{
-	struct msi_desc *desc;
-
-	for_each_msi_entry(desc, dev)
-		if (desc->inta.dev_index == dev_index)
-			return desc->irq;
-
-	return -ENODEV;
-}
-EXPORT_SYMBOL_GPL(ti_sci_inta_msi_get_virq);

drivers/vfio/fsl-mc/vfio_fsl_mc_intr.c

···
 	int hwirq;
 	int ret;
 
-	hwirq = vdev->mc_dev->irqs[index]->msi_desc->irq;
+	hwirq = vdev->mc_dev->irqs[index]->virq;
 	if (irq->trigger) {
 		free_irq(hwirq, irq);
 		kfree(irq->name);
···
 		return vfio_set_trigger(vdev, index, fd);
 	}
 
-	hwirq = vdev->mc_dev->irqs[index]->msi_desc->irq;
+	hwirq = vdev->mc_dev->irqs[index]->virq;
 
 	irq = &vdev->mc_irqs[index];
 

include/linux/device.h

···
 struct iommu_group;
 struct dev_pin_info;
 struct dev_iommu;
+struct msi_device_data;
 
 /**
  * struct subsys_interface - interfaces to device functions
···
 };
 
 /**
+ * struct dev_msi_info - Device data related to MSI
+ * @domain:	The MSI interrupt domain associated to the device
+ * @data:	Pointer to MSI device data
+ */
+struct dev_msi_info {
+#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
+	struct irq_domain	*domain;
+#endif
+#ifdef CONFIG_GENERIC_MSI_IRQ
+	struct msi_device_data	*data;
+#endif
+};
+
+/**
  * struct device - The basic device structure
  * @parent:	The device's "parent" device, the device to which it is attached.
  * 		In most cases, a parent device is some sort of bus or host
···
  * @em_pd:	device's energy model performance domain
  * @pins:	For device pin management.
  *		See Documentation/driver-api/pin-control.rst for details.
- * @msi_lock:	Lock to protect MSI mask cache and mask register
- * @msi_list:	Hosts MSI descriptors
- * @msi_domain: The generic MSI domain this device is using.
+ * @msi:	MSI related data
  * @numa_node:	NUMA node this device is close to.
  * @dma_ops:    DMA mapping operations for this device.
  * @dma_mask:	Dma mask (if dma'ble device).
···
 	struct em_perf_domain	*em_pd;
 #endif
 
-#ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
-	struct irq_domain	*msi_domain;
-#endif
 #ifdef CONFIG_PINCTRL
 	struct dev_pin_info	*pins;
 #endif
-#ifdef CONFIG_GENERIC_MSI_IRQ
-	raw_spinlock_t		msi_lock;
-	struct list_head	msi_list;
-#endif
+	struct dev_msi_info	msi;
 #ifdef CONFIG_DMA_OPS
 	const struct dma_map_ops *dma_ops;
 #endif
···
 static inline struct irq_domain *dev_get_msi_domain(const struct device *dev)
 {
 #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
-	return dev->msi_domain;
+	return dev->msi.domain;
 #else
 	return NULL;
 #endif
···
 static inline void dev_set_msi_domain(struct device *dev, struct irq_domain *d)
 {
 #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
-	dev->msi_domain = d;
+	dev->msi.domain = d;
 #endif
 }
 

include/linux/fsl/mc.h

···
 
 /**
  * struct fsl_mc_device_irq - MC object device message-based interrupt
- * @msi_desc: pointer to MSI descriptor allocated by fsl_mc_msi_alloc_descs()
+ * @virq: Linux virtual interrupt number
  * @mc_dev: MC object device that owns this interrupt
  * @dev_irq_index: device-relative IRQ index
  * @resource: MC generic resource associated with the interrupt
  */
 struct fsl_mc_device_irq {
-	struct msi_desc *msi_desc;
+	unsigned int virq;
 	struct fsl_mc_device *mc_dev;
 	u8 dev_irq_index;
 	struct fsl_mc_resource resource;

include/linux/msi.h

···
 #ifndef LINUX_MSI_H
 #define LINUX_MSI_H
 
-#include <linux/kobject.h>
+/*
+ * This header file contains MSI data structures and functions which are
+ * only relevant for:
+ *	- Interrupt core code
+ *	- PCI/MSI core code
+ *	- MSI interrupt domain implementations
+ *	- IOMMU, low level VFIO, NTB and other justified exceptions
+ *	  dealing with low level MSI details.
+ *
+ * Regular device drivers have no business with any of these functions and
+ * especially storing MSI descriptor pointers in random code is considered
+ * abuse. The only function which is relevant for drivers is msi_get_virq().
+ */
+
+#include <linux/cpumask.h>
+#include <linux/xarray.h>
+#include <linux/mutex.h>
 #include <linux/list.h>
 #include <asm/msi.h>
 
···
 struct msi_desc;
 struct pci_dev;
 struct platform_msi_priv_data;
+struct device_attribute;
+
 void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
 #ifdef CONFIG_GENERIC_MSI_IRQ
 void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg);
···
 				    struct msi_msg *msg);
 
 /**
- * platform_msi_desc - Platform device specific msi descriptor data
- * @msi_priv_data:	Pointer to platform private data
- * @msi_index:		The index of the MSI descriptor for multi MSI
- */
-struct platform_msi_desc {
-	struct platform_msi_priv_data	*msi_priv_data;
-	u16				msi_index;
-};
-
-/**
- * fsl_mc_msi_desc - FSL-MC device specific msi descriptor data
- * @msi_index:		The index of the MSI descriptor
- */
-struct fsl_mc_msi_desc {
-	u16				msi_index;
-};
-
-/**
- * ti_sci_inta_msi_desc - TISCI based INTA specific msi descriptor data
- * @dev_index: TISCI device index
- */
-struct ti_sci_inta_msi_desc {
-	u16	dev_index;
-};
-
-/**
- * struct msi_desc - Descriptor structure for MSI based interrupts
- * @list:	List head for management
- * @irq:	The base interrupt number
- * @nvec_used:	The number of vectors used
- * @dev:	Pointer to the device which uses this descriptor
- * @msg:	The last set MSI message cached for reuse
- * @affinity:	Optional pointer to a cpu affinity mask for this descriptor
- *
- * @write_msi_msg:	Callback that may be called when the MSI message
- *			address or data changes
- * @write_msi_msg_data:	Data parameter for the callback.
+ * pci_msi_desc - PCI/MSI specific MSI descriptor data
  *
  * @msi_mask:	[PCI MSI]   MSI cached mask bits
  * @msix_ctrl:	[PCI MSI-X] MSI-X cached per vector control bits
  * @is_msix:	[PCI MSI/X] True if MSI-X
  * @multiple:	[PCI MSI/X] log2 num of messages allocated
  * @multi_cap:	[PCI MSI/X] log2 num of messages supported
- * @maskbit:	[PCI MSI/X] Mask-Pending bit supported?
+ * @can_mask:	[PCI MSI/X] Masking supported?
  * @is_64:	[PCI MSI/X] Address size: 0=32bit 1=64bit
- * @entry_nr:	[PCI MSI/X] Entry which is described by this descriptor
  * @default_irq:[PCI MSI/X] The default pre-assigned non-MSI irq
  * @mask_pos:	[PCI MSI]   Mask register position
  * @mask_base:	[PCI MSI-X] Mask register base address
- * @platform:	[platform]  Platform device specific msi descriptor data
- * @fsl_mc:	[fsl-mc]    FSL MC device specific msi descriptor data
- * @inta:	[INTA]	    TISCI based INTA specific msi descriptor data
+ */
+struct pci_msi_desc {
+	union {
+		u32 msi_mask;
+		u32 msix_ctrl;
+	};
+	struct {
+		u8	is_msix		: 1;
+		u8	multiple	: 3;
+		u8	multi_cap	: 3;
+		u8	can_mask	: 1;
+		u8	is_64		: 1;
+		u8	is_virtual	: 1;
+		unsigned default_irq;
+	} msi_attrib;
+	union {
+		u8	mask_pos;
+		void __iomem *mask_base;
+	};
+};
+
+#define MSI_MAX_INDEX		((unsigned int)USHRT_MAX)
+
+/**
+ * struct msi_desc - Descriptor structure for MSI based interrupts
+ * @irq:	The base interrupt number
+ * @nvec_used:	The number of vectors used
+ * @dev:	Pointer to the device which uses this descriptor
+ * @msg:	The last set MSI message cached for reuse
+ * @affinity:	Optional pointer to a cpu affinity mask for this descriptor
+ * @sysfs_attr:	Pointer to sysfs device attribute
+ *
+ * @write_msi_msg:	Callback that may be called when the MSI message
+ *			address or data changes
+ * @write_msi_msg_data:	Data parameter for the callback.
+ *
+ * @msi_index:	Index of the msi descriptor
+ * @pci:	PCI specific msi descriptor data
  */
 struct msi_desc {
 	/* Shared device/bus type independent data */
-	struct list_head		list;
 	unsigned int			irq;
 	unsigned int			nvec_used;
 	struct device			*dev;
···
 #ifdef CONFIG_IRQ_MSI_IOMMU
 	const void			*iommu_cookie;
 #endif
+#ifdef CONFIG_SYSFS
+	struct device_attribute		*sysfs_attrs;
+#endif
 
 	void (*write_msi_msg)(struct msi_desc *entry, void *data);
 	void *write_msi_msg_data;
 
-	union {
-		/* PCI MSI/X specific data */
-		struct {
-			union {
-				u32 msi_mask;
-				u32 msix_ctrl;
-			};
-			struct {
-				u8	is_msix		: 1;
-				u8	multiple	: 3;
-				u8	multi_cap	: 3;
-				u8	can_mask	: 1;
-				u8	is_64		: 1;
-				u8	is_virtual	: 1;
-				u16	entry_nr;
-				unsigned default_irq;
-			} msi_attrib;
-			union {
-				u8	mask_pos;
-				void __iomem *mask_base;
-			};
-		};
-
-		/*
-		 * Non PCI variants add their data structure here. New
-		 * entries need to use a named structure. We want
-		 * proper name spaces for this. The PCI part is
-		 * anonymous for now as it would require an immediate
-		 * tree wide cleanup.
-		 */
-		struct platform_msi_desc platform;
-		struct fsl_mc_msi_desc fsl_mc;
-		struct ti_sci_inta_msi_desc inta;
-	};
+	u16				msi_index;
+	struct pci_msi_desc		pci;
 };
 
-/* Helpers to hide struct msi_desc implementation details */
+/*
+ * Filter values for the MSI descriptor iterators and accessor functions.
+ */
+enum msi_desc_filter {
+	/* All descriptors */
+	MSI_DESC_ALL,
+	/* Descriptors which have no interrupt associated */
+	MSI_DESC_NOTASSOCIATED,
+	/* Descriptors which have an interrupt associated */
+	MSI_DESC_ASSOCIATED,
+};
+
+/**
+ * msi_device_data - MSI per device data
+ * @properties:		MSI properties which are interesting to drivers
+ * @platform_data:	Platform-MSI specific data
+ * @mutex:		Mutex protecting the MSI descriptor store
+ * @__store:		Xarray for storing MSI descriptor pointers
+ * @__iter_idx:		Index to search the next entry for iterators
+ */
+struct msi_device_data {
+	unsigned long			properties;
+	struct platform_msi_priv_data	*platform_data;
+	struct mutex			mutex;
+	struct xarray			__store;
+	unsigned long			__iter_idx;
+};
+
+int msi_setup_device_data(struct device *dev);
+
+unsigned int msi_get_virq(struct device *dev, unsigned int index);
+void msi_lock_descs(struct device *dev);
+void msi_unlock_descs(struct device *dev);
+
+struct msi_desc *msi_first_desc(struct device *dev, enum msi_desc_filter filter);
+struct msi_desc *msi_next_desc(struct device *dev, enum msi_desc_filter filter);
+
+/**
+ * msi_for_each_desc - Iterate the MSI descriptors
+ *
+ * @desc:	struct msi_desc pointer used as iterator
+ * @dev:	struct device pointer - device to iterate
+ * @filter:	Filter for descriptor selection
+ *
+ * Notes:
+ *  - The loop must be protected with a msi_lock_descs()/msi_unlock_descs()
+ *    pair.
+ *  - It is safe to remove a retrieved MSI descriptor in the loop.
+ */
+#define msi_for_each_desc(desc, dev, filter)			\
+	for ((desc) = msi_first_desc((dev), (filter)); (desc);	\
+	     (desc) = msi_next_desc((dev), (filter)))
+
 #define msi_desc_to_dev(desc)		((desc)->dev)
-#define dev_to_msi_list(dev)		(&(dev)->msi_list)
-#define first_msi_entry(dev)		\
-	list_first_entry(dev_to_msi_list((dev)), struct msi_desc, list)
-#define for_each_msi_entry(desc, dev)	\
-	list_for_each_entry((desc), dev_to_msi_list((dev)), list)
-#define for_each_msi_entry_safe(desc, tmp, dev)	\
-	list_for_each_entry_safe((desc), (tmp), dev_to_msi_list((dev)), list)
-#define for_each_msi_vector(desc, __irq, dev)				\
-	for_each_msi_entry((desc), (dev))				\
-		if ((desc)->irq)					\
-			for (__irq = (desc)->irq;			\
-			     __irq < ((desc)->irq + (desc)->nvec_used);	\
-			     __irq++)
 
 #ifdef CONFIG_IRQ_MSI_IOMMU
 static inline const void *msi_desc_get_iommu_cookie(struct msi_desc *desc)
···
 #endif
 
 #ifdef CONFIG_PCI_MSI
-#define first_pci_msi_entry(pdev)	first_msi_entry(&(pdev)->dev)
-#define for_each_pci_msi_entry(desc, pdev)	\
-	for_each_msi_entry((desc), &(pdev)->dev)
-
 struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc);
-void *msi_desc_to_pci_sysdata(struct msi_desc *desc);
 void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg);
 #else /* CONFIG_PCI_MSI */
-static inline void *msi_desc_to_pci_sysdata(struct msi_desc *desc)
-{
-	return NULL;
-}
 static inline void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg)
 {
 }
 #endif /* CONFIG_PCI_MSI */
 
-struct msi_desc *alloc_msi_entry(struct device *dev, int nvec,
-				 const struct irq_affinity_desc *affinity);
-void free_msi_entry(struct msi_desc *entry);
+int msi_add_msi_desc(struct device *dev, struct msi_desc *init_desc);
+void msi_free_msi_descs_range(struct device *dev, enum msi_desc_filter filter,
+			      unsigned int first_index, unsigned int last_index);
+
+/**
+ * msi_free_msi_descs - Free MSI descriptors of a device
+ * @dev:	Device to free the descriptors
+ */
+static inline void msi_free_msi_descs(struct device *dev)
+{
+	msi_free_msi_descs_range(dev, MSI_DESC_ALL, 0, MSI_MAX_INDEX);
+}
+
 void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
 void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
 
 void pci_msi_mask_irq(struct irq_data *data);
 void pci_msi_unmask_irq(struct irq_data *data);
-
-const struct attribute_group **msi_populate_sysfs(struct device *dev);
-void msi_destroy_sysfs(struct device *dev,
-		       const struct attribute_group **msi_irq_groups);
 
 /*
  * The arch hooks to setup up msi irqs. Default functions are implemented
···
 void arch_teardown_msi_irq(unsigned int irq);
 int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
 void arch_teardown_msi_irqs(struct pci_dev *dev);
-#else
-static inline int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
-{
-	WARN_ON_ONCE(1);
-	return -ENODEV;
-}
-
-static inline void arch_teardown_msi_irqs(struct pci_dev *dev)
-{
-	WARN_ON_ONCE(1);
-}
-#endif
+#ifdef CONFIG_SYSFS
+int msi_device_populate_sysfs(struct device *dev);
+void msi_device_destroy_sysfs(struct device *dev);
+#else /* CONFIG_SYSFS */
+static inline int msi_device_populate_sysfs(struct device *dev) { return 0; }
+static inline void msi_device_destroy_sysfs(struct device *dev) { }
+#endif /* !CONFIG_SYSFS */
+#endif /* CONFIG_PCI_MSI_ARCH_FALLBACKS */
 
 /*
- * The restore hooks are still available as they are useful even
- * for fully irq domain based setups. Courtesy to XEN/X86.
+ * The restore hook is still available even for fully irq domain based
+ * setups. Courtesy to XEN/X86.
  */
-void arch_restore_msi_irqs(struct pci_dev *dev);
-void default_restore_msi_irqs(struct pci_dev *dev);
+bool arch_restore_msi_irqs(struct pci_dev *dev);
 
 #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
 
···
  * @msi_free:		Domain specific function to free a MSI interrupts
  * @msi_check:		Callback for verification of the domain/info/dev data
  * @msi_prepare:	Prepare the allocation of the interrupts in the domain
- * @msi_finish:		Optional callback to finalize the allocation
  * @set_desc:		Set the msi descriptor for an interrupt
- * @handle_error:	Optional error handler if the allocation fails
  * @domain_alloc_irqs:	Optional function to override the default allocation
  *			function.
  * @domain_free_irqs:	Optional function to override the default free
  *			function.
  *
- * @get_hwirq, @msi_init and @msi_free are callbacks used by
- * msi_create_irq_domain() and related interfaces
+ * @get_hwirq, @msi_init and @msi_free are callbacks used by the underlying
+ * irqdomain.
  *
- * @msi_check, @msi_prepare, @msi_finish, @set_desc and @handle_error
- * are callbacks used by msi_domain_alloc_irqs() and related
- * interfaces which are based on msi_desc.
+ * @msi_check, @msi_prepare and @set_desc are callbacks used by
+ * msi_domain_alloc/free_irqs().
  *
  * @domain_alloc_irqs, @domain_free_irqs can be used to override the
  * default allocation/free functions (__msi_domain_alloc/free_irqs). This
···
 	int		(*msi_prepare)(struct irq_domain *domain,
 				       struct device *dev, int nvec,
 				       msi_alloc_info_t *arg);
-	void		(*msi_finish)(msi_alloc_info_t *arg, int retval);
 	void		(*set_desc)(msi_alloc_info_t *arg,
 				    struct msi_desc *desc);
-	int		(*handle_error)(struct irq_domain *domain,
-					struct msi_desc *desc, int error);
 	int		(*domain_alloc_irqs)(struct irq_domain *domain,
 					     struct device *dev, int nvec);
 	void		(*domain_free_irqs)(struct irq_domain *domain,
···
 	MSI_FLAG_MUST_REACTIVATE	= (1 << 5),
 	/* Is level-triggered capable, using two messages */
 	MSI_FLAG_LEVEL_CAPABLE		= (1 << 6),
+	/* Populate sysfs on alloc() and destroy it on free() */
+	MSI_FLAG_DEV_SYSFS		= (1 << 7),
+	/* MSI-X entries must be contiguous */
+	MSI_FLAG_MSIX_CONTIGUOUS	= (1 << 8),
+	/* Allocate simple MSI descriptors */
+	MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS	= (1 << 9),
+	/* Free MSI descriptors */
+	MSI_FLAG_FREE_MSI_DESCS		= (1 << 10),
 };
 
 int msi_domain_set_affinity(struct irq_data *data, const struct cpumask *mask,
···
 					 struct irq_domain *parent);
 int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 			    int nvec);
+int msi_domain_alloc_irqs_descs_locked(struct irq_domain *domain, struct device *dev,
+				       int nvec);
 int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
 			  int nvec);
 void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev);
+void msi_domain_free_irqs_descs_locked(struct irq_domain *domain, struct device *dev);
 void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev);
 struct msi_domain_info *msi_get_domain_info(struct irq_domain *domain);
 
···
 #define platform_msi_create_device_tree_domain(dev, nvec, write, ops, data) \
 	__platform_msi_create_device_domain(dev, nvec, true, write, ops, data)
 
-int platform_msi_domain_alloc(struct irq_domain *domain, unsigned int virq,
-			      unsigned int nr_irqs);
-void platform_msi_domain_free(struct irq_domain *domain, unsigned int virq,
-			      unsigned int nvec);
+int platform_msi_device_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				     unsigned int nr_irqs);
+void platform_msi_device_domain_free(struct irq_domain *domain, unsigned int virq,
+				     unsigned int nvec);
 void *platform_msi_get_host_data(struct irq_domain *domain);
 #endif /* CONFIG_GENERIC_MSI_IRQ_DOMAIN */
 
 #ifdef CONFIG_PCI_MSI_IRQ_DOMAIN
-void pci_msi_domain_write_msg(struct irq_data *irq_data, struct msi_msg *msg);
 struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
 					     struct msi_domain_info *info,
 					     struct irq_domain *parent);
-int pci_msi_domain_check_cap(struct irq_domain *domain,
-			     struct msi_domain_info *info, struct device *dev);
 u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev);
 struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev);
 bool pci_dev_has_special_msi_domain(struct pci_dev *pdev);

include/linux/pci.h

···
 	unsigned int	ats_enabled:1;		/* Address Translation Svc */
 	unsigned int	pasid_enabled:1;	/* Process Address Space ID */
 	unsigned int	pri_enabled:1;		/* Page Request Interface */
-	unsigned int	is_managed:1;
+	unsigned int	is_managed:1;		/* Managed via devres */
+	unsigned int	is_msi_managed:1;	/* MSI release via devres installed */
 	unsigned int	needs_freset:1;		/* Requires fundamental reset */
 	unsigned int	state_saved:1;
 	unsigned int	is_physfn:1;
···
 	u8		ptm_granularity;
 #endif
 #ifdef CONFIG_PCI_MSI
-	const struct attribute_group **msi_irq_groups;
+	void __iomem	*msix_base;
+	raw_spinlock_t	msi_lock;
 #endif
 	struct pci_vpd	vpd;
 #ifdef CONFIG_PCIE_DPC

include/linux/soc/ti/ti_sci_inta_msi.h

···
 				   struct irq_domain *parent);
 int ti_sci_inta_msi_domain_alloc_irqs(struct device *dev,
 				      struct ti_sci_resource *res);
-unsigned int ti_sci_inta_msi_get_virq(struct device *dev, u32 index);
-void ti_sci_inta_msi_domain_free_irqs(struct device *dev);
 #endif /* __INCLUDE_LINUX_IRQCHIP_TI_SCI_INTA_H */

kernel/irq/msi.c

···
 #include <linux/irqdomain.h>
 #include <linux/msi.h>
 #include <linux/slab.h>
+#include <linux/sysfs.h>
 #include <linux/pci.h>
 
 #include "internals.h"
 
+static inline int msi_sysfs_create_group(struct device *dev);
+
 /**
- * alloc_msi_entry - Allocate an initialized msi_desc
+ * msi_alloc_desc - Allocate an initialized msi_desc
  * @dev:	Pointer to the device for which this is allocated
  * @nvec:	The number of vectors used in this entry
  * @affinity:	Optional pointer to an affinity mask array size of @nvec
···
  *
  * Return: pointer to allocated &msi_desc on success or %NULL on failure
  */
-struct msi_desc *alloc_msi_entry(struct device *dev, int nvec,
-				 const struct irq_affinity_desc *affinity)
+static struct msi_desc *msi_alloc_desc(struct device *dev, int nvec,
+					const struct irq_affinity_desc *affinity)
 {
-	struct msi_desc *desc;
+	struct msi_desc *desc = kzalloc(sizeof(*desc), GFP_KERNEL);
 
-	desc = kzalloc(sizeof(*desc), GFP_KERNEL);
 	if (!desc)
 		return NULL;
 
-	INIT_LIST_HEAD(&desc->list);
 	desc->dev = dev;
 	desc->nvec_used = nvec;
 	if (affinity) {
-		desc->affinity = kmemdup(affinity,
-			nvec * sizeof(*desc->affinity), GFP_KERNEL);
+		desc->affinity = kmemdup(affinity, nvec * sizeof(*desc->affinity), GFP_KERNEL);
 		if (!desc->affinity) {
 			kfree(desc);
 			return NULL;
 		}
 	}
-
 	return desc;
 }
 
-void free_msi_entry(struct msi_desc *entry)
+static void msi_free_desc(struct msi_desc *desc)
 {
-	kfree(entry->affinity);
-	kfree(entry);
+	kfree(desc->affinity);
+	kfree(desc);
+}
+
+static int msi_insert_desc(struct msi_device_data *md, struct msi_desc *desc, unsigned int index)
+{
+	int ret;
+
+	desc->msi_index = index;
+	ret = xa_insert(&md->__store, index, desc, GFP_KERNEL);
+	if (ret)
+		msi_free_desc(desc);
+	return ret;
+}
+
+/**
+ * msi_add_msi_desc - Allocate and initialize a MSI descriptor
+ * @dev:	Pointer to the device for which the descriptor is allocated
+ * @init_desc:	Pointer to an MSI descriptor to initialize the new descriptor
+ *
+ * Return: 0 on success or an appropriate failure code.
+ */
+int msi_add_msi_desc(struct device *dev, struct msi_desc *init_desc)
+{
+	struct msi_desc *desc;
+
+	lockdep_assert_held(&dev->msi.data->mutex);
+
+	desc = msi_alloc_desc(dev, init_desc->nvec_used, init_desc->affinity);
+	if (!desc)
+		return -ENOMEM;
+
+	/* Copy type specific data to the new descriptor. */
+	desc->pci = init_desc->pci;
+	return msi_insert_desc(dev->msi.data, desc, init_desc->msi_index);
+}
+
+/**
+ * msi_add_simple_msi_descs - Allocate and initialize MSI descriptors
+ * @dev:	Pointer to the device for which the descriptors are allocated
+ * @index:	Index for the first MSI descriptor
+ * @ndesc:	Number of descriptors to allocate
+ *
+ * Return: 0 on success or an appropriate failure code.
+ */
+static int msi_add_simple_msi_descs(struct device *dev, unsigned int index, unsigned int ndesc)
+{
+	unsigned int idx, last = index + ndesc - 1;
+	struct msi_desc *desc;
+	int ret;
+
+	lockdep_assert_held(&dev->msi.data->mutex);
+
+	for (idx = index; idx <= last; idx++) {
+		desc = msi_alloc_desc(dev, 1, NULL);
+		if (!desc)
+			goto fail_mem;
+		ret = msi_insert_desc(dev->msi.data, desc, idx);
+		if (ret)
+			goto fail;
+	}
+	return 0;
+
+fail_mem:
+	ret = -ENOMEM;
+fail:
+	msi_free_msi_descs_range(dev, MSI_DESC_NOTASSOCIATED, index, last);
+	return ret;
+}
+
+static bool msi_desc_match(struct msi_desc *desc, enum msi_desc_filter filter)
+{
+	switch (filter) {
+	case MSI_DESC_ALL:
+		return true;
+	case MSI_DESC_NOTASSOCIATED:
+		return !desc->irq;
+	case MSI_DESC_ASSOCIATED:
+		return !!desc->irq;
+	}
+	WARN_ON_ONCE(1);
+	return false;
+}
+
+/**
+ * msi_free_msi_descs_range - Free MSI descriptors of a device
+ * @dev:		Device to free the descriptors
+ * @filter:		Descriptor state filter
+ * @first_index:	Index to start freeing from
+ * @last_index:		Last index to be freed
+ */
+void msi_free_msi_descs_range(struct device *dev, enum msi_desc_filter filter,
+			      unsigned int first_index, unsigned int last_index)
+{
+	struct xarray *xa = &dev->msi.data->__store;
+	struct msi_desc *desc;
+	unsigned long idx;
+
+	lockdep_assert_held(&dev->msi.data->mutex);
+
+	xa_for_each_range(xa, idx, desc, first_index, last_index) {
+		if (msi_desc_match(desc, filter)) {
+			xa_erase(xa, idx);
+			msi_free_desc(desc);
+		}
+	}
 }
 
 void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
···
 }
 EXPORT_SYMBOL_GPL(get_cached_msi_msg);
 
+static void msi_device_data_release(struct device *dev, void *res)
+{
+	struct msi_device_data *md = res;
+
+	WARN_ON_ONCE(!xa_empty(&md->__store));
+	xa_destroy(&md->__store);
+	dev->msi.data = NULL;
+}
+
+/**
+ * msi_setup_device_data - Setup MSI device data
+ * @dev:	Device for which MSI device data should be set up
+ *
+ * Return: 0 on success, appropriate error code otherwise
+ *
+ * This can be called more than once for @dev. If the MSI device data is
+ * already allocated the call succeeds. The allocated memory is
+ * automatically released when the device is destroyed.
+ */
+int msi_setup_device_data(struct device *dev)
+{
+	struct msi_device_data *md;
+	int ret;
+
+	if (dev->msi.data)
+		return 0;
+
+	md = devres_alloc(msi_device_data_release, sizeof(*md), GFP_KERNEL);
+	if (!md)
+		return -ENOMEM;
+
+	ret = msi_sysfs_create_group(dev);
+	if (ret) {
+		devres_free(md);
+		return ret;
+	}
+
+	xa_init(&md->__store);
+	mutex_init(&md->mutex);
+	dev->msi.data = md;
+	devres_add(dev, md);
+	return 0;
+}
+
+/**
+ * msi_lock_descs - Lock the MSI descriptor storage of a device
+ * @dev:	Device to operate on
+ */
+void msi_lock_descs(struct device *dev)
+{
+	mutex_lock(&dev->msi.data->mutex);
+}
+EXPORT_SYMBOL_GPL(msi_lock_descs);
+
+/**
+ * msi_unlock_descs - Unlock the MSI descriptor storage of a device
+ * @dev:	Device to operate on
+ */
+void msi_unlock_descs(struct device *dev)
+{
+	/* Invalidate the index wich was cached by the iterator */
+	dev->msi.data->__iter_idx = MSI_MAX_INDEX;
+	mutex_unlock(&dev->msi.data->mutex);
+}
+EXPORT_SYMBOL_GPL(msi_unlock_descs);
+
+static struct msi_desc *msi_find_desc(struct msi_device_data *md, enum msi_desc_filter filter)
+{
+	struct msi_desc *desc;
+
+	xa_for_each_start(&md->__store, md->__iter_idx, desc, md->__iter_idx) {
+		if (msi_desc_match(desc, filter))
+			return desc;
+	}
+	md->__iter_idx = MSI_MAX_INDEX;
+	return NULL;
+}
+
+/**
+ * msi_first_desc - Get the first MSI descriptor of a device
+ * @dev:	Device to operate on
+ * @filter:	Descriptor state filter
+ *
+ * Must be called with the MSI descriptor mutex held, i.e. msi_lock_descs()
+ * must be invoked before the call.
+ *
+ * Return: Pointer to the first MSI descriptor matching the search
+ *	   criteria, NULL if none found.
+ */
+struct msi_desc *msi_first_desc(struct device *dev, enum msi_desc_filter filter)
+{
+	struct msi_device_data *md = dev->msi.data;
+
+	if (WARN_ON_ONCE(!md))
+		return NULL;
+
+	lockdep_assert_held(&md->mutex);
+
+	md->__iter_idx = 0;
+	return msi_find_desc(md, filter);
+}
+EXPORT_SYMBOL_GPL(msi_first_desc);
+
+/**
+ * msi_next_desc - Get the next MSI descriptor of a device
+ * @dev:	Device to operate on
+ *
+ * The first invocation of msi_next_desc() has to be preceeded by a
+ * successful invocation of __msi_first_desc(). Consecutive invocations are
+ * only valid if the previous one was successful. All these operations have
+ * to be done within the same MSI mutex held region.
+ *
+ * Return: Pointer to the next MSI descriptor matching the search
+ *	   criteria, NULL if none found.
+ */
+struct msi_desc *msi_next_desc(struct device *dev, enum msi_desc_filter filter)
+{
+	struct msi_device_data *md = dev->msi.data;
+
+	if (WARN_ON_ONCE(!md))
+		return NULL;
+
+	lockdep_assert_held(&md->mutex);
+
+	if (md->__iter_idx >= (unsigned long)MSI_MAX_INDEX)
+		return NULL;
+
+	md->__iter_idx++;
+	return msi_find_desc(md, filter);
+}
+EXPORT_SYMBOL_GPL(msi_next_desc);
+
+/**
+ * msi_get_virq - Return Linux interrupt number of a MSI interrupt
+ * @dev:	Device to operate on
+ * @index:	MSI interrupt index to look for (0-based)
+ *
+ * Return: The Linux interrupt number on success (> 0), 0 if not found
+ */
+unsigned int msi_get_virq(struct device *dev, unsigned int index)
+{
+	struct msi_desc *desc;
+	unsigned int ret = 0;
+	bool pcimsi;
+
+	if (!dev->msi.data)
+		return 0;
+
+	pcimsi = dev_is_pci(dev) ? to_pci_dev(dev)->msi_enabled : false;
+
+	msi_lock_descs(dev);
+	desc = xa_load(&dev->msi.data->__store, pcimsi ? 0 : index);
+	if (desc && desc->irq) {
+		/*
+		 * PCI-MSI has only one descriptor for multiple interrupts.
+		 * PCI-MSIX and platform MSI use a descriptor per
+		 * interrupt.
+		 */
+		if (pcimsi) {
+			if (index < desc->nvec_used)
+				ret = desc->irq + index;
+		} else {
+			ret = desc->irq;
+		}
+	}
+	msi_unlock_descs(dev);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(msi_get_virq);
+
+#ifdef CONFIG_SYSFS
+static struct attribute *msi_dev_attrs[] = {
+	NULL
+};
+
+static const struct attribute_group msi_irqs_group = {
+	.name	= "msi_irqs",
+	.attrs	= msi_dev_attrs,
+};
+
+static inline int msi_sysfs_create_group(struct device *dev)
+{
+	return devm_device_add_group(dev, &msi_irqs_group);
+}
+
 static ssize_t msi_mode_show(struct device *dev, struct device_attribute *attr,
 			     char *buf)
 {
-	struct msi_desc *entry;
-	bool is_msix = false;
-	unsigned long irq;
-	int retval;
-
-	retval = kstrtoul(attr->attr.name, 10, &irq);
-	if (retval)
-		return retval;
-
-	entry = irq_get_msi_desc(irq);
-	if (!entry)
-		return -ENODEV;
-
-	if (dev_is_pci(dev))
-		is_msix = entry->msi_attrib.is_msix;
+	/* MSI vs. MSIX is per device not per interrupt */
+	bool is_msix = dev_is_pci(dev) ? to_pci_dev(dev)->msix_enabled : false;
 
 	return sysfs_emit(buf, "%s\n", is_msix ? "msix" : "msi");
 }
 
-/**
- * msi_populate_sysfs - Populate msi_irqs sysfs entries for devices
- * @dev:	The device(PCI, platform etc) who will get sysfs entries
- *
- * Return attribute_group ** so that specific bus MSI can save it to
- * somewhere during initilizing msi irqs. If devices has no MSI irq,
- * return NULL; if it fails to populate sysfs, return ERR_PTR
- */
-const struct attribute_group **msi_populate_sysfs(struct device *dev)
+static void msi_sysfs_remove_desc(struct device *dev, struct msi_desc *desc)
 {
-	const struct attribute_group **msi_irq_groups;
-	struct attribute **msi_attrs, *msi_attr;
-	struct device_attribute *msi_dev_attr;
-	struct attribute_group *msi_irq_group;
-	struct msi_desc *entry;
-	int ret = -ENOMEM;
-	int num_msi = 0;
-	int count = 0;
+	struct device_attribute *attrs = desc->sysfs_attrs;
 	int i;
 
-	/* Determine how many msi entries we have */
-	for_each_msi_entry(entry, dev)
-		num_msi += entry->nvec_used;
-	if (!num_msi)
-		return NULL;
+	if (!attrs)
+		return;
 
-	/* Dynamically create the MSI attributes for the device */
-	msi_attrs = kcalloc(num_msi + 1, sizeof(void *), GFP_KERNEL);
-	if (!msi_attrs)
-		return ERR_PTR(-ENOMEM);
+	desc->sysfs_attrs = NULL;
+	for (i = 0; i < desc->nvec_used; i++) {
+		if (attrs[i].show)
+			sysfs_remove_file_from_group(&dev->kobj, &attrs[i].attr, msi_irqs_group.name);
+		kfree(attrs[i].attr.name);
+	}
+	kfree(attrs);
+}
 
-	for_each_msi_entry(entry, dev) {
-		for (i = 0; i < entry->nvec_used; i++) {
-			msi_dev_attr = kzalloc(sizeof(*msi_dev_attr), GFP_KERNEL);
-			if (!msi_dev_attr)
-				goto error_attrs;
-			msi_attrs[count] = &msi_dev_attr->attr;
+static int msi_sysfs_populate_desc(struct device *dev, struct msi_desc *desc)
+{
+	struct device_attribute *attrs;
+	int ret, i;
 
-			sysfs_attr_init(&msi_dev_attr->attr);
-			msi_dev_attr->attr.name = kasprintf(GFP_KERNEL, "%d",
-							    entry->irq + i);
-			if (!msi_dev_attr->attr.name)
-				goto error_attrs;
-			msi_dev_attr->attr.mode = 0444;
-			msi_dev_attr->show = msi_mode_show;
-			++count;
+	attrs = kcalloc(desc->nvec_used, sizeof(*attrs), GFP_KERNEL);
+	if (!attrs)
+		return -ENOMEM;
+
+	desc->sysfs_attrs = attrs;
+	for (i = 0; i < desc->nvec_used; i++) {
+		sysfs_attr_init(&attrs[i].attr);
+		attrs[i].attr.name = kasprintf(GFP_KERNEL, "%d", desc->irq + i);
+		if (!attrs[i].attr.name) {
+			ret = -ENOMEM;
+			goto fail;
+		}
+
+		attrs[i].attr.mode = 0444;
+		attrs[i].show = msi_mode_show;
+
+		ret = sysfs_add_file_to_group(&dev->kobj, &attrs[i].attr, msi_irqs_group.name);
+		if (ret) {
+			attrs[i].show = NULL;
+			goto fail;
 		}
 	}
+	return 0;
 
-	msi_irq_group = kzalloc(sizeof(*msi_irq_group), GFP_KERNEL);
-	if (!msi_irq_group)
-		goto error_attrs;
-	msi_irq_group->name = "msi_irqs";
-	msi_irq_group->attrs = msi_attrs;
+fail:
+	msi_sysfs_remove_desc(dev, desc);
+	return ret;
+}
 
-	msi_irq_groups = kcalloc(2, sizeof(void *), GFP_KERNEL);
-	if (!msi_irq_groups)
-		goto error_irq_group;
-	msi_irq_groups[0] = msi_irq_group;
+#ifdef CONFIG_PCI_MSI_ARCH_FALLBACKS
+/**
+ * msi_device_populate_sysfs - Populate msi_irqs sysfs entries for a device
+ * @dev:	The device (PCI, platform etc) which will get sysfs entries
+ */
+int msi_device_populate_sysfs(struct device *dev)
+{
+	struct msi_desc *desc;
+	int ret;
 
-	ret = sysfs_create_groups(&dev->kobj, msi_irq_groups);
-	if (ret)
-		goto error_irq_groups;
-
-	return msi_irq_groups;
-
-error_irq_groups:
-	kfree(msi_irq_groups);
-error_irq_group:
-	kfree(msi_irq_group);
-error_attrs:
-	count = 0;
-	msi_attr = msi_attrs[count];
-	while (msi_attr) {
-		msi_dev_attr = container_of(msi_attr, struct device_attribute, attr);
-		kfree(msi_attr->name);
-		kfree(msi_dev_attr);
-		++count;
-		msi_attr = msi_attrs[count];
+	msi_for_each_desc(desc, dev, MSI_DESC_ASSOCIATED) {
+		if (desc->sysfs_attrs)
+			continue;
+		ret = msi_sysfs_populate_desc(dev, desc);
+		if (ret)
+			return ret;
 	}
-	kfree(msi_attrs);
-	return ERR_PTR(ret);
+	return 0;
 }
 
 /**
- * msi_destroy_sysfs - Destroy msi_irqs sysfs entries for devices
- * @dev:		The device(PCI, platform etc) who will remove sysfs entries
- * @msi_irq_groups:	attribute_group for device msi_irqs entries
+ * msi_device_destroy_sysfs - Destroy msi_irqs sysfs entries for a device
+ * @dev:		The device (PCI, platform etc) for which to remove
+ *			sysfs entries
  */
-void msi_destroy_sysfs(struct device *dev, const struct attribute_group **msi_irq_groups)
+void msi_device_destroy_sysfs(struct device *dev)
 {
-	struct device_attribute *dev_attr;
-	struct attribute **msi_attrs;
-	int count = 0;
+	struct msi_desc *desc;
 
-	if (msi_irq_groups) {
-		sysfs_remove_groups(&dev->kobj, msi_irq_groups);
-		msi_attrs = msi_irq_groups[0]->attrs;
-		while (msi_attrs[count]) {
-			dev_attr = container_of(msi_attrs[count],
-					struct device_attribute, attr);
-			kfree(dev_attr->attr.name);
-			kfree(dev_attr);
-			++count;
-		}
-		kfree(msi_attrs);
-		kfree(msi_irq_groups[0]);
-		kfree(msi_irq_groups);
-	}
+	msi_for_each_desc(desc, dev, MSI_DESC_ALL)
+		msi_sysfs_remove_desc(dev, desc);
 }
+#endif /* CONFIG_PCI_MSI_ARCH_FALLBACK */
+#else /* CONFIG_SYSFS */
+static inline int msi_sysfs_create_group(struct device *dev) { return 0; }
+static inline int msi_sysfs_populate_desc(struct device *dev, struct msi_desc *desc) { return 0; }
+static inline void msi_sysfs_remove_desc(struct device *dev, struct msi_desc *desc) { }
+#endif /* !CONFIG_SYSFS */
 
 #ifdef CONFIG_GENERIC_MSI_IRQ_DOMAIN
 static inline void irq_chip_write_msi_msg(struct irq_data *data,
···
 }
 
 int msi_domain_populate_irqs(struct irq_domain *domain, struct device *dev,
-			     int virq, int nvec, msi_alloc_info_t *arg)
+			     int virq_base, int nvec, msi_alloc_info_t *arg)
 {
 	struct msi_domain_info *info = domain->host_data;
 	struct msi_domain_ops *ops = info->ops;
 	struct msi_desc *desc;
-	int ret = 0;
+	int ret, virq;
 
-	for_each_msi_entry(desc, dev) {
-		/* Don't even try the multi-MSI brain damage. */
-		if (WARN_ON(!desc->irq || desc->nvec_used != 1)) {
-			ret = -EINVAL;
-			break;
-		}
+	msi_lock_descs(dev);
+	ret = msi_add_simple_msi_descs(dev, virq_base, nvec);
+	if (ret)
+		goto unlock;
 
-		if (!(desc->irq >= virq && desc->irq < (virq + nvec)))
-			continue;
+	for (virq = virq_base; virq < virq_base + nvec; virq++) {
+		desc = xa_load(&dev->msi.data->__store, virq);
+		desc->irq = virq;
 
 		ops->set_desc(arg, desc);
-		/* Assumes the domain mutex is held! */
-		ret = irq_domain_alloc_irqs_hierarchy(domain, desc->irq, 1,
-						      arg);
+		ret = irq_domain_alloc_irqs_hierarchy(domain, virq, 1, arg);
 		if (ret)
-			break;
+			goto fail;
 
-		irq_set_msi_desc_off(desc->irq, 0, desc);
+		irq_set_msi_desc(virq, desc);
 	}
+	msi_unlock_descs(dev);
+	return 0;
 
-	if (ret) {
-		/* Mop up the damage */
-		for_each_msi_entry(desc, dev) {
-			if (!(desc->irq >= virq && desc->irq < (virq + nvec)))
-				continue;
-
-			irq_domain_free_irqs_common(domain, desc->irq, 1);
-		}
-	}
-
+fail:
+	for (--virq; virq >= virq_base; virq--)
+		irq_domain_free_irqs_common(domain, virq, 1);
+	msi_free_msi_descs_range(dev, MSI_DESC_ALL, virq_base, virq_base + nvec - 1);
+unlock:
+	msi_unlock_descs(dev);
 	return ret;
 }
 
···
 	 * Checking the first MSI descriptor is sufficient. MSIX supports
 	 * masking and MSI does so when the can_mask attribute is set.
 	 */
-	desc = first_msi_entry(dev);
-	return desc->msi_attrib.is_msix || desc->msi_attrib.can_mask;
+	desc = msi_first_desc(dev, MSI_DESC_ALL);
+	return desc->pci.msi_attrib.is_msix || desc->pci.msi_attrib.can_mask;
+}
+
+static int msi_handle_pci_fail(struct irq_domain *domain, struct msi_desc *desc,
+			       int allocated)
+{
+	switch(domain->bus_token) {
+	case DOMAIN_BUS_PCI_MSI:
+	case DOMAIN_BUS_VMD_MSI:
+		if (IS_ENABLED(CONFIG_PCI_MSI))
+			break;
+		fallthrough;
+	default:
+		return -ENOSPC;
+	}
+
+	/* Let a failed PCI multi MSI allocation retry */
+	if (desc->nvec_used > 1)
+		return 1;
+
+	/* If there was a successful allocation let the caller know */
+	return allocated ? allocated : -ENOSPC;
+}
+
+#define VIRQ_CAN_RESERVE	0x01
+#define VIRQ_ACTIVATE		0x02
+#define VIRQ_NOMASK_QUIRK	0x04
+
+static int msi_init_virq(struct irq_domain *domain, int virq, unsigned int vflags)
+{
+	struct irq_data *irqd = irq_domain_get_irq_data(domain, virq);
+	int ret;
+
+	if (!(vflags & VIRQ_CAN_RESERVE)) {
+		irqd_clr_can_reserve(irqd);
+		if (vflags & VIRQ_NOMASK_QUIRK)
+			irqd_set_msi_nomask_quirk(irqd);
+	}
+
+	if (!(vflags & VIRQ_ACTIVATE))
+		return 0;
+
+	ret = irq_domain_activate_irq(irqd, vflags & VIRQ_CAN_RESERVE);
+	if (ret)
+		return ret;
+	/*
+	 * If the interrupt uses reservation mode, clear the activated bit
+	 * so request_irq() will assign the final vector.
+	 */
+	if (vflags & VIRQ_CAN_RESERVE)
+		irqd_clr_activated(irqd);
+	return 0;
 }
 
 int __msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
···
 {
 	struct msi_domain_info *info = domain->host_data;
 	struct msi_domain_ops *ops = info->ops;
-	struct irq_data *irq_data;
-	struct msi_desc *desc;
 	msi_alloc_info_t arg = { };
+	unsigned int vflags = 0;
+	struct msi_desc *desc;
+	int allocated = 0;
 	int i, ret, virq;
-	bool can_reserve;
 
 	ret = msi_domain_prepare_irqs(domain, dev, nvec, &arg);
 	if (ret)
 		return ret;
-
-	for_each_msi_entry(desc, dev) {
-		ops->set_desc(&arg, desc);
-
-		virq = __irq_domain_alloc_irqs(domain, -1, desc->nvec_used,
-					       dev_to_node(dev), &arg, false,
-					       desc->affinity);
-		if (virq < 0) {
-			ret = -ENOSPC;
-			if (ops->handle_error)
-				ret = ops->handle_error(domain, desc, ret);
-			if (ops->msi_finish)
-				ops->msi_finish(&arg, ret);
-			return ret;
-		}
-
-		for (i = 0; i < desc->nvec_used; i++) {
-			irq_set_msi_desc_off(virq, i, desc);
-			irq_debugfs_copy_devname(virq + i, dev);
-		}
-	}
-
-	if (ops->msi_finish)
-		ops->msi_finish(&arg, 0);
-
-	can_reserve = msi_check_reservation_mode(domain, info, dev);
 
 	/*
 	 * This flag is set by the PCI layer as we need to activate
 	 * the MSI entries before the PCI layer enables MSI in the
 	 * card. Otherwise the card latches a random msi message.
 	 */
-	if (!(info->flags & MSI_FLAG_ACTIVATE_EARLY))
-		goto skip_activate;
+	if (info->flags & MSI_FLAG_ACTIVATE_EARLY)
+		vflags |= VIRQ_ACTIVATE;
 
-	for_each_msi_vector(desc, i, dev) {
-		if (desc->irq == i) {
-			virq = desc->irq;
-			dev_dbg(dev, "irq [%d-%d] for MSI\n",
-				virq, virq + desc->nvec_used - 1);
-		}
-
-		irq_data = irq_domain_get_irq_data(domain, i);
-		if (!can_reserve) {
-			irqd_clr_can_reserve(irq_data);
-			if (domain->flags & IRQ_DOMAIN_MSI_NOMASK_QUIRK)
-				irqd_set_msi_nomask_quirk(irq_data);
-		}
-		ret = irq_domain_activate_irq(irq_data, can_reserve);
-		if (ret)
-			goto cleanup;
+	/*
+	 * Interrupt can use a reserved vector and will not occupy
+	 * a real device vector until the interrupt is requested.
+	 */
+	if (msi_check_reservation_mode(domain, info, dev)) {
+		vflags |= VIRQ_CAN_RESERVE;
+		/*
+		 * MSI affinity setting requires a special quirk (X86) when
+		 * reservation mode is active.
+		 */
+		if (domain->flags & IRQ_DOMAIN_MSI_NOMASK_QUIRK)
+			vflags |= VIRQ_NOMASK_QUIRK;
 	}
 
-skip_activate:
-	/*
-	 * If these interrupts use reservation mode, clear the activated bit
-	 * so request_irq() will assign the final vector.
-	 */
-	if (can_reserve) {
-		for_each_msi_vector(desc, i, dev) {
-			irq_data = irq_domain_get_irq_data(domain, i);
-			irqd_clr_activated(irq_data);
+	msi_for_each_desc(desc, dev, MSI_DESC_NOTASSOCIATED) {
+		ops->set_desc(&arg, desc);
+
+		virq = __irq_domain_alloc_irqs(domain, -1, desc->nvec_used,
+					       dev_to_node(dev), &arg, false,
+					       desc->affinity);
+		if (virq < 0)
+			return msi_handle_pci_fail(domain, desc, allocated);
+
+		for (i = 0; i < desc->nvec_used; i++) {
+			irq_set_msi_desc_off(virq, i, desc);
+			irq_debugfs_copy_devname(virq + i, dev);
+			ret = msi_init_virq(domain, virq + i, vflags);
+			if (ret)
+				return ret;
 		}
+		if (info->flags & MSI_FLAG_DEV_SYSFS) {
+			ret = msi_sysfs_populate_desc(dev, desc);
+			if (ret)
+				return ret;
+		}
+		allocated++;
 	}
 	return 0;
+}
 
-cleanup:
-	msi_domain_free_irqs(domain, dev);
+static int msi_domain_add_simple_msi_descs(struct msi_domain_info *info,
+					   struct device *dev,
+					   unsigned int num_descs)
+{
+	if (!(info->flags & MSI_FLAG_ALLOC_SIMPLE_MSI_DESCS))
+		return 0;
+
+	return msi_add_simple_msi_descs(dev, 0, num_descs);
+}
+
+/**
+ * msi_domain_alloc_irqs_descs_locked - Allocate interrupts from a MSI interrupt domain
+ * @domain:	The domain to allocate from
+ * @dev:	Pointer to device struct of the device for which the interrupts
+ *		are allocated
+ * @nvec:	The number of interrupts to allocate
+ *
+ * Must be invoked from within a msi_lock_descs() / msi_unlock_descs()
+ * pair. Use this for MSI irqdomains which implement their own vector
+ * allocation/free.
+ *
+ * Return: %0 on success or an error code.
+ */
+int msi_domain_alloc_irqs_descs_locked(struct irq_domain *domain, struct device *dev,
+				       int nvec)
+{
+	struct msi_domain_info *info = domain->host_data;
+	struct msi_domain_ops *ops = info->ops;
+	int ret;
+
+	lockdep_assert_held(&dev->msi.data->mutex);
+
+	ret = msi_domain_add_simple_msi_descs(info, dev, nvec);
+	if (ret)
+		return ret;
+
+	ret = ops->domain_alloc_irqs(domain, dev, nvec);
+	if (ret)
+		msi_domain_free_irqs_descs_locked(domain, dev);
 	return ret;
 }
 
···
  *
  * Return: %0 on success or an error code.
  */
-int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
-			  int nvec)
+int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev, int nvec)
 {
-	struct msi_domain_info *info = domain->host_data;
-	struct msi_domain_ops *ops = info->ops;
+	int ret;
 
-	return ops->domain_alloc_irqs(domain, dev, nvec);
+	msi_lock_descs(dev);
+	ret = msi_domain_alloc_irqs_descs_locked(domain, dev, nvec);
+	msi_unlock_descs(dev);
+	return ret;
 }
 
 void __msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
 {
-	struct irq_data *irq_data;
+	struct msi_domain_info *info = domain->host_data;
+	struct irq_data *irqd;
 	struct msi_desc *desc;
 	int i;
 
-	for_each_msi_vector(desc, i, dev) {
-		irq_data = irq_domain_get_irq_data(domain, i);
-		if (irqd_is_activated(irq_data))
-			irq_domain_deactivate_irq(irq_data);
-	}
-
-	for_each_msi_entry(desc, dev) {
-		/*
-		 * We might have failed to allocate an MSI early
-		 * enough that there is no IRQ associated to this
-		 * entry. If that's the case, don't do anything.
-		 */
-		if (desc->irq) {
-			irq_domain_free_irqs(desc->irq, desc->nvec_used);
-			desc->irq = 0;
+	/* Only handle MSI entries which have an interrupt associated */
+	msi_for_each_desc(desc, dev, MSI_DESC_ASSOCIATED) {
+		/* Make sure all interrupts are deactivated */
+		for (i = 0; i < desc->nvec_used; i++) {
+			irqd = irq_domain_get_irq_data(domain, desc->irq + i);
+			if (irqd && irqd_is_activated(irqd))
+				irq_domain_deactivate_irq(irqd);
 		}
+
+		irq_domain_free_irqs(desc->irq, desc->nvec_used);
+		if (info->flags & MSI_FLAG_DEV_SYSFS)
+			msi_sysfs_remove_desc(dev, desc);
+		desc->irq = 0;
 	}
+}
+
+static void msi_domain_free_msi_descs(struct msi_domain_info *info,
+				      struct device *dev)
+{
+	if (info->flags & MSI_FLAG_FREE_MSI_DESCS)
+		msi_free_msi_descs(dev);
+}
+
+/**
+ * msi_domain_free_irqs_descs_locked - Free interrupts from a MSI interrupt @domain associated to @dev
+ * @domain:	The domain to managing the interrupts
+ * @dev:	Pointer to device struct of the device for which the interrupts
+ *		are free
+ *
+ * Must be invoked from within a msi_lock_descs() / msi_unlock_descs()
+ * pair. Use this for MSI irqdomains which implement their own vector
+ * allocation.
+ */
+void msi_domain_free_irqs_descs_locked(struct irq_domain *domain, struct device *dev)
+{
+	struct msi_domain_info *info = domain->host_data;
+	struct msi_domain_ops *ops = info->ops;
+
+	lockdep_assert_held(&dev->msi.data->mutex);
+
+	ops->domain_free_irqs(domain, dev);
+	msi_domain_free_msi_descs(info, dev);
 }
 
 /**
···
  */
 void msi_domain_free_irqs(struct irq_domain *domain, struct device *dev)
 {
-	struct msi_domain_info *info = domain->host_data;
-	struct msi_domain_ops *ops = info->ops;
-
-	return ops->domain_free_irqs(domain, dev);
+	msi_lock_descs(dev);
+	msi_domain_free_irqs_descs_locked(domain, dev);
+	msi_unlock_descs(dev);
 }
 
 /**