Merge tag 'irq-msi-2025-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull MSI updates from Thomas Gleixner:
 "Updates for the MSI subsystem (core code and PCI):

   - Switch the MSI descriptor locking to lock guards

   - Replace a broken and naive implementation of PCI/MSI-X control word
     updates in the PCI/TPH driver with a properly serialized variant in
     the PCI/MSI core code.

   - Remove the MSI descriptor abuse in the SCCI/UFS/QCOM driver by
     replacing the direct access to the MSI descriptors with the proper
     API function calls. People will never understand that APIs exist
     for a reason...

   - Provide core infrastructre for the upcoming PCI endpoint library
     extensions. Currently limited to ARM GICv3+, but in theory
     extensible to other architectures.

   - Provide a MSI domain::teardown() callback, which allows drivers to
     undo the effects of the prepare() callback.

   - Move the MSI domain::prepare() callback invocation to domain
     creation time to avoid redundant (and in case of ARM/GIC-V3-ITS
     confusing) invocations on every allocation.

     In combination with the new teardown callback this removes some
     ugly hacks in the GIC-V3-ITS driver, which pretended to work around
     the short comings of the core code so far. With this update the
     code is correct by design and implementation.

   - Make the irqchip MSI library globally available, provide a MSI
     parent domain creation helper and convert a bunch of (PCI/)MSI
     drivers over to the modern MSI parent mechanism. This is the first
     step to get rid of at least one incarnation of the three PCI/MSI
     management schemes.

   - The usual small cleanups and improvements"

* tag 'irq-msi-2025-05-25' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (33 commits)
  PCI/MSI: Use bool for MSI enable state tracking
  PCI: tegra: Convert to MSI parent infrastructure
  PCI: xgene: Convert to MSI parent infrastructure
  PCI: apple: Convert to MSI parent infrastructure
  irqchip/msi-lib: Honour the MSI_FLAG_NO_AFFINITY flag
  irqchip/mvebu: Convert to msi_create_parent_irq_domain() helper
  irqchip/gic: Convert to msi_create_parent_irq_domain() helper
  genirq/msi: Add helper for creating MSI-parent irq domains
  irqchip: Make irq-msi-lib.h globally available
  irqchip/gic-v3-its: Use allocation size from the prepare call
  genirq/msi: Engage the .msi_teardown() callback on domain removal
  genirq/msi: Move prepare() call to per-device allocation
  irqchip/gic-v3-its: Implement .msi_teardown() callback
  genirq/msi: Add .msi_teardown() callback as the reverse of .msi_prepare()
  irqchip/gic-v3-its: Add support for device tree msi-map and msi-mask
  dt-bindings: PCI: pci-ep: Add support for iommu-map and msi-map
  irqchip/gic-v3-its: Set IRQ_DOMAIN_FLAG_MSI_IMMUTABLE for ITS
  irqdomain: Add IRQ_DOMAIN_FLAG_MSI_IMMUTABLE and irq_domain_is_msi_immutable()
  platform-msi: Add msi_remove_device_irq_domain() in platform_device_msi_free_irqs_all()
  genirq/msi: Rename msi_[un]lock_descs()
  ...

Author: torvalds

Documentation/devicetree/bindings/pci/pci-ep.yaml

@@ -17,6 +17,24 @@ properties:
   $nodename:
     pattern: "^pcie-ep@"
 
+  iommu-map:
+    $ref: /schemas/types.yaml#/definitions/uint32-matrix
+    items:
+      items:
+        - description: Device ID (see msi-map) base
+          maximum: 0x7ffff
+        - description: phandle to IOMMU
+        - description: IOMMU specifier base (currently always 1 cell)
+        - description: Number of Device IDs
+          maximum: 0x80000
+
+  iommu-map-mask:
+    description:
+      A mask to be applied to each Device ID prior to being mapped to an
+      IOMMU specifier per the iommu-map property.
+    $ref: /schemas/types.yaml#/definitions/uint32
+    maximum: 0x7ffff
+
   max-functions:
     description: Maximum number of functions that can be configured
     $ref: /schemas/types.yaml#/definitions/uint8
@@ -35,6 +53,56 @@ properties:
     $ref: /schemas/types.yaml#/definitions/uint32
     enum: [ 1, 2, 3, 4 ]
 
+  msi-map:
+    description: |
+      Maps a Device ID to an MSI and associated MSI specifier data.
+
+      A PCI Endpoint (EP) can use MSI as a doorbell function. This is achieved by
+      mapping the MSI controller's address into PCI BAR<n>. The PCI Root Complex
+      can write to this BAR<n>, triggering the EP to generate IRQ. This notifies
+      the EP-side driver of an event, eliminating the need for the driver to
+      continuously poll for status changes.
+
+      However, the EP cannot rely on Requester ID (RID) because the RID is
+      determined by the PCI topology of the host system. Since the EP may be
+      connected to different PCI hosts, the RID can vary between systems and is
+      therefore not a reliable identifier.
+
+      Each EP can support up to 8 physical functions and up to 65,536 virtual
+      functions. To uniquely identify each child device, a device ID is defined
+      as
+         - Bits [2:0] for the function number (func)
+         - Bits [18:3] for the virtual function index (vfunc)
+
+      The resulting device ID is computed as:
+
+        (func & 0x7) | (vfunc << 3)
+
+      The property is an arbitrary number of tuples of
+      (device-id-base, msi, msi-base,length).
+
+      Any Device ID id in the interval [id-base, id-base + length) is
+      associated with the listed MSI, with the MSI specifier
+      (id - id-base + msi-base).
+    $ref: /schemas/types.yaml#/definitions/uint32-matrix
+    items:
+      items:
+        - description: The Device ID base matched by the entry
+          maximum: 0x7ffff
+        - description: phandle to msi-controller node
+        - description: (optional) The msi-specifier produced for the first
+            Device ID matched by the entry. Currently, msi-specifier is 0 or
+            1 cells.
+        - description: The length of consecutive Device IDs following the
+            Device ID base
+          maximum: 0x80000
+
+  msi-map-mask:
+    description: A mask to be applied to each Device ID prior to being
+      mapped to an msi-specifier per the msi-map property.
+    $ref: /schemas/types.yaml#/definitions/uint32
+    maximum: 0x7ffff
+
   num-lanes:
     description: maximum number of lanes
     $ref: /schemas/types.yaml#/definitions/uint32

drivers/base/platform-msi.c

@@ -95,5 +95,6 @@ EXPORT_SYMBOL_GPL(platform_device_msi_init_and_alloc_irqs);
 void platform_device_msi_free_irqs_all(struct device *dev)
 {
 	msi_domain_free_irqs_all(dev, MSI_DEFAULT_DOMAIN);
+	msi_remove_device_irq_domain(dev, MSI_DEFAULT_DOMAIN);
 }
 EXPORT_SYMBOL_GPL(platform_device_msi_free_irqs_all);

drivers/irqchip/irq-bcm2712-mip.c

@@ -11,7 +11,7 @@
 #include <linux/of_address.h>
 #include <linux/of_platform.h>
 
-#include "irq-msi-lib.h"
+#include <linux/irqchip/irq-msi-lib.h>
 
 #define MIP_INT_RAISE		0x00
 #define MIP_INT_CLEAR		0x10

drivers/irqchip/irq-gic-v2m.c

@@ -26,7 +26,7 @@
 #include <linux/irqchip/arm-gic.h>
 #include <linux/irqchip/arm-gic-common.h>
 
-#include "irq-msi-lib.h"
+#include <linux/irqchip/irq-msi-lib.h>
 
 /*
 * MSI_TYPER:
@@ -261,23 +261,23 @@ static struct msi_parent_ops gicv2m_msi_parent_ops = {
 
 static __init int gicv2m_allocate_domains(struct irq_domain *parent)
 {
-	struct irq_domain *inner_domain;
+	struct irq_domain_info info = {
+		.ops		= &gicv2m_domain_ops,
+		.parent		= parent,
+	};
 	struct v2m_data *v2m;
 
 	v2m = list_first_entry_or_null(&v2m_nodes, struct v2m_data, entry);
 	if (!v2m)
 		return 0;
 
-	inner_domain = irq_domain_create_hierarchy(parent, 0, 0, v2m->fwnode,
-						   &gicv2m_domain_ops, v2m);
-	if (!inner_domain) {
+	info.host_data = v2m;
+	info.fwnode = v2m->fwnode;
+
+	if (!msi_create_parent_irq_domain(&info, &gicv2m_msi_parent_ops)) {
 		pr_err("Failed to create GICv2m domain\n");
 		return -ENOMEM;
 	}
-
-	irq_domain_update_bus_token(inner_domain, DOMAIN_BUS_NEXUS);
-	inner_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT;
-	inner_domain->msi_parent_ops = &gicv2m_msi_parent_ops;
 	return 0;
 }
 

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

@@ -8,7 +8,7 @@
 #include <linux/pci.h>
 
 #include "irq-gic-common.h"
-#include "irq-msi-lib.h"
+#include <linux/irqchip/irq-msi-lib.h>
 
 #define ITS_MSI_FLAGS_REQUIRED  (MSI_FLAG_USE_DEF_DOM_OPS |	\
 				 MSI_FLAG_USE_DEF_CHIP_OPS |	\
@@ -67,17 +67,6 @@ static int its_pci_msi_prepare(struct irq_domain *domain, struct device *dev,
 	/* ITS specific DeviceID, as the core ITS ignores dev. */
 	info->scratchpad[0].ul = pci_msi_domain_get_msi_rid(domain->parent, pdev);
 
-	/*
-	 * @domain->msi_domain_info->hwsize contains the size of the
-	 * MSI[-X] domain, but vector allocation happens one by one. This
-	 * needs some thought when MSI comes into play as the size of MSI
-	 * might be unknown at domain creation time and therefore set to
-	 * MSI_MAX_INDEX.
-	 */
-	msi_info = msi_get_domain_info(domain);
-	if (msi_info->hwsize > nvec)
-		nvec = msi_info->hwsize;
-
 	/*
 	 * Always allocate a power of 2, and special case device 0 for
 	 * broken systems where the DevID is not wired (and all devices
@@ -118,6 +107,14 @@ static int of_pmsi_get_dev_id(struct irq_domain *domain, struct device *dev,
 		index++;
 	} while (!ret);
 
+	if (ret) {
+		struct device_node *np = NULL;
+
+		ret = of_map_id(dev->of_node, dev->id, "msi-map", "msi-map-mask", &np, dev_id);
+		if (np)
+			of_node_put(np);
+	}
+
 	return ret;
 }
 
@@ -143,14 +140,6 @@ static int its_pmsi_prepare(struct irq_domain *domain, struct device *dev,
 	/* ITS specific DeviceID, as the core ITS ignores dev. */
 	info->scratchpad[0].ul = dev_id;
 
-	/*
-	 * @domain->msi_domain_info->hwsize contains the size of the device
-	 * domain, but vector allocation happens one by one.
-	 */
-	msi_info = msi_get_domain_info(domain);
-	if (msi_info->hwsize > nvec)
-		nvec = msi_info->hwsize;
-
 	/* Allocate at least 32 MSIs, and always as a power of 2 */
 	nvec = max_t(int, 32, roundup_pow_of_two(nvec));
 
@@ -159,6 +148,14 @@ static int its_pmsi_prepare(struct irq_domain *domain, struct device *dev,
 					  dev, nvec, info);
 }
 
+static void its_msi_teardown(struct irq_domain *domain, msi_alloc_info_t *info)
+{
+	struct msi_domain_info *msi_info;
+
+	msi_info = msi_get_domain_info(domain->parent);
+	msi_info->ops->msi_teardown(domain->parent, info);
+}
+
 static bool its_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
 				  struct irq_domain *real_parent, struct msi_domain_info *info)
 {
@@ -182,6 +179,7 @@ static bool its_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
 		 * %MSI_MAX_INDEX.
 		 */
 		info->ops->msi_prepare = its_pci_msi_prepare;
+		info->ops->msi_teardown = its_msi_teardown;
 		break;
 	case DOMAIN_BUS_DEVICE_MSI:
 	case DOMAIN_BUS_WIRED_TO_MSI:
@@ -190,6 +188,7 @@ static bool its_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
 		 * size is also known at domain creation time.
 		 */
 		info->ops->msi_prepare = its_pmsi_prepare;
+		info->ops->msi_teardown = its_msi_teardown;
 		break;
 	default:
 		/* Confused. How did the lib return true? */

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

@@ -41,7 +41,7 @@
 #include <asm/exception.h>
 
 #include "irq-gic-common.h"
-#include "irq-msi-lib.h"
+#include <linux/irqchip/irq-msi-lib.h>
 
 #define ITS_FLAGS_CMDQ_NEEDS_FLUSHING		(1ULL << 0)
 #define ITS_FLAGS_WORKAROUND_CAVIUM_22375	(1ULL << 1)
@@ -3624,8 +3624,33 @@ static int its_msi_prepare(struct irq_domain *domain, struct device *dev,
 	return err;
 }
 
+static void its_msi_teardown(struct irq_domain *domain, msi_alloc_info_t *info)
+{
+	struct its_device *its_dev = info->scratchpad[0].ptr;
+
+	guard(mutex)(&its_dev->its->dev_alloc_lock);
+
+	/* If the device is shared, keep everything around */
+	if (its_dev->shared)
+		return;
+
+	/* LPIs should have been already unmapped at this stage */
+	if (WARN_ON_ONCE(!bitmap_empty(its_dev->event_map.lpi_map,
+				       its_dev->event_map.nr_lpis)))
+		return;
+
+	its_lpi_free(its_dev->event_map.lpi_map,
+		     its_dev->event_map.lpi_base,
+		     its_dev->event_map.nr_lpis);
+
+	/* Unmap device/itt, and get rid of the tracking */
+	its_send_mapd(its_dev, 0);
+	its_free_device(its_dev);
+}
+
 static struct msi_domain_ops its_msi_domain_ops = {
 	.msi_prepare	= its_msi_prepare,
+	.msi_teardown	= its_msi_teardown,
 };
 
 static int its_irq_gic_domain_alloc(struct irq_domain *domain,
@@ -3726,7 +3751,6 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq,
 {
 	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
 	struct its_device *its_dev = irq_data_get_irq_chip_data(d);
-	struct its_node *its = its_dev->its;
 	int i;
 
 	bitmap_release_region(its_dev->event_map.lpi_map,
@@ -3740,26 +3764,6 @@ static void its_irq_domain_free(struct irq_domain *domain, unsigned int virq,
 		irq_domain_reset_irq_data(data);
 	}
 
-	mutex_lock(&its->dev_alloc_lock);
-
-	/*
-	 * If all interrupts have been freed, start mopping the
-	 * floor. This is conditioned on the device not being shared.
-	 */
-	if (!its_dev->shared &&
-	    bitmap_empty(its_dev->event_map.lpi_map,
-			 its_dev->event_map.nr_lpis)) {
-		its_lpi_free(its_dev->event_map.lpi_map,
-			     its_dev->event_map.lpi_base,
-			     its_dev->event_map.nr_lpis);
-
-		/* Unmap device/itt */
-		its_send_mapd(its_dev, 0);
-		its_free_device(its_dev);
-	}
-
-	mutex_unlock(&its->dev_alloc_lock);
-
 	irq_domain_free_irqs_parent(domain, virq, nr_irqs);
 }
 
@@ -5122,7 +5126,12 @@ static void __init __iomem *its_map_one(struct resource *res, int *err)
 
 static int its_init_domain(struct its_node *its)
 {
-	struct irq_domain *inner_domain;
+	struct irq_domain_info dom_info = {
+		.fwnode		= its->fwnode_handle,
+		.ops		= &its_domain_ops,
+		.domain_flags	= its->msi_domain_flags,
+		.parent		= its_parent,
+	};
 	struct msi_domain_info *info;
 
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
@@ -5131,21 +5140,12 @@ static int its_init_domain(struct its_node *its)
 
 	info->ops = &its_msi_domain_ops;
 	info->data = its;
+	dom_info.host_data = info;
 
-	inner_domain = irq_domain_create_hierarchy(its_parent,
-						   its->msi_domain_flags, 0,
-						   its->fwnode_handle, &its_domain_ops,
-						   info);
-	if (!inner_domain) {
+	if (!msi_create_parent_irq_domain(&dom_info, &gic_v3_its_msi_parent_ops)) {
 		kfree(info);
 		return -ENOMEM;
 	}
-
-	irq_domain_update_bus_token(inner_domain, DOMAIN_BUS_NEXUS);
-
-	inner_domain->msi_parent_ops = &gic_v3_its_msi_parent_ops;
-	inner_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT;
-
 	return 0;
 }
 
@@ -5522,7 +5522,7 @@ static struct its_node __init *its_node_init(struct resource *res,
 	its->base = its_base;
 	its->phys_base = res->start;
 	its->get_msi_base = its_irq_get_msi_base;
-	its->msi_domain_flags = IRQ_DOMAIN_FLAG_ISOLATED_MSI;
+	its->msi_domain_flags = IRQ_DOMAIN_FLAG_ISOLATED_MSI | IRQ_DOMAIN_FLAG_MSI_IMMUTABLE;
 
 	its->numa_node = numa_node;
 	its->fwnode_handle = handle;

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

@@ -18,7 +18,7 @@
 
 #include <linux/irqchip/arm-gic-v3.h>
 
-#include "irq-msi-lib.h"
+#include <linux/irqchip/irq-msi-lib.h>
 
 struct mbi_range {
 	u32			spi_start;
@@ -206,17 +206,13 @@ static const struct msi_parent_ops gic_v3_mbi_msi_parent_ops = {
 
 static int mbi_allocate_domain(struct irq_domain *parent)
 {
-	struct irq_domain *nexus_domain;
+	struct irq_domain_info info = {
+		.fwnode		= parent->fwnode,
+		.ops		= &mbi_domain_ops,
+		.parent		= parent,
+	};
 
-	nexus_domain = irq_domain_create_hierarchy(parent, 0, 0, parent->fwnode,
-						   &mbi_domain_ops, NULL);
-	if (!nexus_domain)
-		return -ENOMEM;
-
-	irq_domain_update_bus_token(nexus_domain, DOMAIN_BUS_NEXUS);
-	nexus_domain->flags |= IRQ_DOMAIN_FLAG_MSI_PARENT;
-	nexus_domain->msi_parent_ops = &gic_v3_mbi_msi_parent_ops;
-	return 0;
+	return msi_create_parent_irq_domain(&info, &gic_v3_mbi_msi_parent_ops) ? 0 : -ENOMEM;
 }
 
 int __init mbi_init(struct fwnode_handle *fwnode, struct irq_domain *parent)

drivers/irqchip/irq-imx-mu-msi.c

@@ -24,7 +24,7 @@
 #include <linux/pm_domain.h>
 #include <linux/spinlock.h>
 
-#include "irq-msi-lib.h"
+#include <linux/irqchip/irq-msi-lib.h>
 
 #define IMX_MU_CHANS            4