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
  ...

12 files changed, 739 insertions, 703 deletions

diff --git a/drivers/pci/Makefile b/drivers/pci/Makefile
index d62c4ac4ae1b..37be95adf169 100644
--- a/drivers/pci/Makefile
+++ b/drivers/pci/Makefile
@@ -5,8 +5,9 @@
 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
diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
index 6733cb14e775..45b6ff8dc665 100644
--- a/drivers/pci/controller/pci-hyperv.c
+++ b/drivers/pci/controller/pci-hyperv.c
@@ -3445,18 +3445,23 @@ static int hv_pci_suspend(struct hv_device *hdev)
 
 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;
 }
 
 /*
diff --git a/drivers/pci/msi/Makefile b/drivers/pci/msi/Makefile
new file mode 100644
index 000000000000..93ef7b9e404d
--- /dev/null
+++ b/drivers/pci/msi/Makefile
@@ -0,0 +1,7 @@
+# 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
diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c
new file mode 100644
index 000000000000..0d63541c4052
--- /dev/null
+++ b/drivers/pci/msi/irqdomain.c
@@ -0,0 +1,280 @@
+// 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;
+}
diff --git a/drivers/pci/msi/legacy.c b/drivers/pci/msi/legacy.c
new file mode 100644
index 000000000000..cdbb4689db78
--- /dev/null
+++ b/drivers/pci/msi/legacy.c
@@ -0,0 +1,81 @@
+// 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);
+}
diff --git a/drivers/pci/msi.c b/drivers/pci/msi/msi.c
index d84cf30bb279..c19c7ca58186 100644
--- a/drivers/pci/msi.c
+++ b/drivers/pci/msi/msi.c
@@ -6,156 +6,29 @@
  * Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
  * 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 "pci.h"
-
-#ifdef CONFIG_PCI_MSI
+#include <linux/irq.h>
+
+#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);
 }
 
@@ -171,7 +44,7 @@ static inline void pci_msi_unmask(struct msi_desc *desc, u32 mask)
 
 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;
 }
 
 /*
@@ -184,27 +57,27 @@ static void pci_msix_write_vector_ctrl(struct msi_desc *desc, u32 ctrl)
 {
 	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);
@@ -212,7 +85,7 @@ static void __pci_msi_mask_desc(struct msi_desc *desc, u32 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);
@@ -242,24 +115,16 @@ void pci_msi_unmask_irq(struct irq_data *data)
 }
 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);
@@ -271,7 +136,7 @@ void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 
 		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);
@@ -289,12 +154,12 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 
 	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;
 
 		/*
@@ -323,12 +188,12 @@ void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 
 		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,
@@ -359,30 +224,11 @@ EXPORT_SYMBOL_GPL(pci_write_msi_msg);
 
 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;
 	}
 }
 
@@ -403,10 +249,19 @@ static void pci_msi_set_enable(struct pci_dev *dev, int enable)
 	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;
@@ -415,12 +270,13 @@ static void __pci_restore_msi_state(struct pci_dev *dev)
 
 	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);
 }
 
@@ -437,19 +293,25 @@ static void pci_msix_clear_and_set_ctrl(struct pci_dev *dev, u16 clear, u16 set)
 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);
 }
@@ -461,48 +323,79 @@ void pci_restore_msi_state(struct pci_dev *dev)
 }
 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;
-	u16 control;
+	struct pci_dev *dev = pcidev;
 
-	if (affd)
-		masks = irq_create_affinity_masks(nvec, affd);
+	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;
 
 	/* 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)
@@ -512,14 +405,14 @@ 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;
 }
 
 /**
@@ -537,21 +430,29 @@ static int msi_verify_entries(struct pci_dev *dev)
 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)
@@ -561,26 +462,22 @@ static int msi_capability_init(struct pci_dev *dev, int nvec,
 	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;
 }
 
@@ -605,70 +502,49 @@ static void __iomem *msix_map_region(struct pci_dev *dev,
 	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);
 
-	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;
-		}
+	memset(&desc, 0, sizeof(desc));
 
-		entry->msi_attrib.is_msix	= 1;
-		entry->msi_attrib.is_64		= 1;
+	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;
 
-		if (entries)
-			entry->msi_attrib.entry_nr = entries[i].entry;
-		else
-			entry->msi_attrib.entry_nr = i;
+	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;
 
-		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);
+		if (!desc.pci.msi_attrib.can_mask) {
+			addr = pci_msix_desc_addr(&desc);
+			desc.pci.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++;
 		}
 	}
@@ -686,6 +562,41 @@ static void msix_mask_all(void __iomem *base, int tsize)
 		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
@@ -700,7 +611,6 @@ static void msix_mask_all(void __iomem *base, int tsize)
 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;
@@ -713,6 +623,9 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
 	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);
@@ -722,32 +635,14 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
 		goto out_disable;
 	}
 
-	ret = msix_setup_entries(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;
+	dev->msix_base = base;
 
-	/* Check if all MSI entries honor device restrictions */
-	ret = msi_verify_entries(dev);
+	ret = msix_setup_interrupts(dev, base, entries, nvec, affd);
 	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;
+		goto out_disable;
 
-	/* 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
@@ -763,27 +658,8 @@ static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
 	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;
@@ -870,18 +746,17 @@ static void pci_msi_shutdown(struct pci_dev *dev)
 	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);
 }
 
@@ -890,8 +765,10 @@ void pci_disable_msi(struct pci_dev *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);
 
@@ -952,7 +829,7 @@ static int __pci_enable_msix(struct pci_dev *dev, struct msix_entry *entries,
 
 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;
@@ -963,8 +840,8 @@ static void pci_msix_shutdown(struct pci_dev *dev)
 	}
 
 	/* 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);
@@ -977,28 +854,13 @@ void pci_disable_msix(struct pci_dev *dev)
 	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)
 {
@@ -1029,6 +891,10 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec,
 	if (nvec > maxvec)
 		nvec = maxvec;
 
+	rc = pci_setup_msi_context(dev);
+	if (rc)
+		return rc;
+
 	for (;;) {
 		if (affd) {
 			nvec = irq_calc_affinity_vectors(minvec, nvec, affd);
@@ -1072,6 +938,10 @@ static int __pci_enable_msix_range(struct pci_dev *dev,
 	if (WARN_ON_ONCE(dev->msix_enabled))
 		return -EINVAL;
 
+	rc = pci_setup_msi_context(dev);
+	if (rc)
+		return rc;
+
 	for (;;) {
 		if (affd) {
 			nvec = irq_calc_affinity_vectors(minvec, nvec, affd);
@@ -1194,35 +1064,25 @@ EXPORT_SYMBOL(pci_free_irq_vectors);
 
 /**
  * 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;
-
-		for_each_pci_msi_entry(entry, dev) {
-			if (i == nr)
-				return entry->irq;
-			i++;
-		}
-		WARN_ON_ONCE(1);
-		return -EINVAL;
-	}
+	unsigned int irq;
 
-	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;
-	}
+	if (!dev->msi_enabled && !dev->msix_enabled)
+		return !nr ? dev->irq : -EINVAL;
 
-	return dev->irq + nr;
+	irq = msi_get_virq(&dev->dev, nr);
+	return irq ? irq : -EINVAL;
 }
 EXPORT_SYMBOL(pci_irq_vector);
 
@@ -1230,332 +1090,58 @@ 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;
-	}
-}
-EXPORT_SYMBOL(pci_irq_get_affinity);
 
-struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc)
-{
-	return to_pci_dev(desc->dev);
-}
-EXPORT_SYMBOL(msi_desc_to_pci_dev);
-
-void *msi_desc_to_pci_sysdata(struct msi_desc *desc)
-{
-	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);
+	if (WARN_ON_ONCE(!desc->affinity))
+		return NULL;
 
 	/*
-	 * For MSI-X desc->irq is always equal to irq_data->irq. For
-	 * MSI only the first interrupt of MULTI MSI passes the test.
+	 * MSI has a mask array in the descriptor.
+	 * MSI-X has a single mask.
 	 */
-	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_attrib.entry_nr |
-		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->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;
+	idx = dev->msi_enabled ? nr : 0;
+	return &desc->affinity[idx].mask;
 }
+EXPORT_SYMBOL(pci_irq_get_affinity);
 
-/**
- * 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 pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc)
 {
-	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;
+	return to_pci_dev(desc->dev);
 }
+EXPORT_SYMBOL(msi_desc_to_pci_dev);
 
-/**
- * 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)
+void pci_no_msi(void)
 {
-	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_msi_enable = 0;
 }
 
 /**
- * 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.
+ * pci_msi_enabled - is MSI enabled?
  *
- * 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)
+ * Returns true if MSI has not been disabled by the command-line option
+ * pci=nomsi.
+ **/
+int pci_msi_enabled(void)
 {
-	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);
+	return pci_msi_enable;
 }
+EXPORT_SYMBOL(pci_msi_enabled);
diff --git a/drivers/pci/msi/msi.h b/drivers/pci/msi/msi.h
new file mode 100644
index 000000000000..dbeff066bedd
--- /dev/null
+++ b/drivers/pci/msi/msi.h
@@ -0,0 +1,39 @@
+/* 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;
+}
diff --git a/drivers/pci/msi/pcidev_msi.c b/drivers/pci/msi/pcidev_msi.c
new file mode 100644
index 000000000000..5520aff53b56
--- /dev/null
+++ b/drivers/pci/msi/pcidev_msi.c
@@ -0,0 +1,43 @@
+// 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);
+	}
+}
diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c
index cfe2f85af09e..602f0fb0b007 100644
--- a/drivers/pci/pci-sysfs.c
+++ b/drivers/pci/pci-sysfs.c
@@ -62,11 +62,8 @@ static ssize_t irq_show(struct device *dev,
 	 * 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);
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 3d2fb394986a..f3f606c232a8 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -2024,11 +2024,6 @@ static void pcim_release(struct device *gendev, void *res)
 	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);
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 087d3658f75c..443efb00e219 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -2311,7 +2311,9 @@ struct pci_dev *pci_alloc_dev(struct pci_bus *bus)
 	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);
diff --git a/drivers/pci/xen-pcifront.c b/drivers/pci/xen-pcifront.c
index d858d25b6cab..d2a7b9fd678b 100644
--- a/drivers/pci/xen-pcifront.c
+++ b/drivers/pci/xen-pcifront.c
@@ -262,8 +262,8 @@ static int pci_frontend_enable_msix(struct pci_dev *dev,
 	}
 
 	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++;