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
  ...

2 files changed, 77 insertions, 161 deletions

diff --git a/drivers/base/core.c b/drivers/base/core.c
index 8b17cb80420c..7bb957b11861 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -2872,10 +2872,6 @@ void device_initialize(struct device *dev)
 	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);
diff --git a/drivers/base/platform-msi.c b/drivers/base/platform-msi.c
index 3d6c8f9caf43..296ea673d661 100644
--- a/drivers/base/platform-msi.c
+++ b/drivers/base/platform-msi.c
@@ -23,7 +23,6 @@
 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;
@@ -39,11 +38,9 @@ static DEFINE_IDA(platform_msi_devid_ida);
  */
 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)
@@ -86,11 +83,8 @@ static void platform_msi_update_dom_ops(struct msi_domain_info *info)
 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)
@@ -113,62 +107,6 @@ static void platform_msi_update_chip_ops(struct msi_domain_info *info)
 		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_create_irq_domain - Create a platform MSI interrupt domain
  * @fwnode:		Optional fwnode of the interrupt controller
@@ -191,6 +129,8 @@ struct irq_domain *platform_msi_create_irq_domain(struct fwnode_handle *fwnode,
 		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)
@@ -199,49 +139,57 @@ struct irq_domain *platform_msi_create_irq_domain(struct fwnode_handle *fwnode,
 	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);
 }
@@ -258,35 +206,15 @@ static void platform_msi_free_priv_data(struct platform_msi_priv_data *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;
 }
@@ -298,16 +226,8 @@ EXPORT_SYMBOL_GPL(platform_msi_domain_alloc_irqs);
  */
 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);
 
@@ -316,17 +236,20 @@ 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
@@ -335,7 +258,11 @@ void *platform_msi_get_host_data(struct irq_domain *domain)
  * @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,
@@ -349,12 +276,20 @@ __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)
@@ -370,61 +305,46 @@ __platform_msi_create_device_domain(struct device *dev,
 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;
-
-	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);
+	struct device *dev = data->dev;
 
-	return err;
+	return msi_domain_populate_irqs(domain->parent, dev, virq, nr_irqs, &data->arg);
 }