Merge tag 'for-joerg' of git://git.kernel.org/pub/scm/linux/kernel/git/jgg/iommufd into core

iommu shared branch with iommufd

The three dependent series on a shared branch:

- Change the iommufd fault handle into an always present hwpt handle in
  the domain

- Give iommufd its own SW_MSI implementation along with some IRQ layer
  rework

- Improvements to the handle attach API

Author: joergroedel

drivers/iommu/Kconfig

@@ -154,7 +154,6 @@ config IOMMU_DMA
 	select DMA_OPS_HELPERS
 	select IOMMU_API
 	select IOMMU_IOVA
-	select IRQ_MSI_IOMMU
 	select NEED_SG_DMA_LENGTH
 	select NEED_SG_DMA_FLAGS if SWIOTLB
 

drivers/iommu/dma-iommu.c

@@ -24,6 +24,7 @@
 #include <linux/memremap.h>
 #include <linux/mm.h>
 #include <linux/mutex.h>
+#include <linux/msi.h>
 #include <linux/of_iommu.h>
 #include <linux/pci.h>
 #include <linux/scatterlist.h>
@@ -102,6 +103,9 @@ static int __init iommu_dma_forcedac_setup(char *str)
 }
 early_param("iommu.forcedac", iommu_dma_forcedac_setup);
 
+static int iommu_dma_sw_msi(struct iommu_domain *domain, struct msi_desc *desc,
+			    phys_addr_t msi_addr);
+
 /* Number of entries per flush queue */
 #define IOVA_DEFAULT_FQ_SIZE	256
 #define IOVA_SINGLE_FQ_SIZE	32768
@@ -398,6 +402,7 @@ int iommu_get_dma_cookie(struct iommu_domain *domain)
 		return -ENOMEM;
 
 	mutex_init(&domain->iova_cookie->mutex);
+	iommu_domain_set_sw_msi(domain, iommu_dma_sw_msi);
 	return 0;
 }
 
@@ -429,6 +434,7 @@ int iommu_get_msi_cookie(struct iommu_domain *domain, dma_addr_t base)
 
 	cookie->msi_iova = base;
 	domain->iova_cookie = cookie;
+	iommu_domain_set_sw_msi(domain, iommu_dma_sw_msi);
 	return 0;
 }
 EXPORT_SYMBOL(iommu_get_msi_cookie);
@@ -443,6 +449,11 @@ void iommu_put_dma_cookie(struct iommu_domain *domain)
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iommu_dma_msi_page *msi, *tmp;
 
+#if IS_ENABLED(CONFIG_IRQ_MSI_IOMMU)
+	if (domain->sw_msi != iommu_dma_sw_msi)
+		return;
+#endif
+
 	if (!cookie)
 		return;
 
@@ -1800,60 +1811,26 @@ static struct iommu_dma_msi_page *iommu_dma_get_msi_page(struct device *dev,
 	return NULL;
 }
 
-/**
- * iommu_dma_prepare_msi() - Map the MSI page in the IOMMU domain
- * @desc: MSI descriptor, will store the MSI page
- * @msi_addr: MSI target address to be mapped
- *
- * Return: 0 on success or negative error code if the mapping failed.
- */
-int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr)
+static int iommu_dma_sw_msi(struct iommu_domain *domain, struct msi_desc *desc,
+			    phys_addr_t msi_addr)
 {
 	struct device *dev = msi_desc_to_dev(desc);
-	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
-	struct iommu_dma_msi_page *msi_page;
-	static DEFINE_MUTEX(msi_prepare_lock); /* see below */
+	const struct iommu_dma_msi_page *msi_page;
 
-	if (!domain || !domain->iova_cookie) {
-		desc->iommu_cookie = NULL;
+	if (!domain->iova_cookie) {
+		msi_desc_set_iommu_msi_iova(desc, 0, 0);
 		return 0;
 	}
 
-	/*
-	 * In fact the whole prepare operation should already be serialised by
-	 * irq_domain_mutex further up the callchain, but that's pretty subtle
-	 * on its own, so consider this locking as failsafe documentation...
-	 */
-	mutex_lock(&msi_prepare_lock);
+	iommu_group_mutex_assert(dev);
 	msi_page = iommu_dma_get_msi_page(dev, msi_addr, domain);
-	mutex_unlock(&msi_prepare_lock);
-
-	msi_desc_set_iommu_cookie(desc, msi_page);
-
 	if (!msi_page)
 		return -ENOMEM;
-	return 0;
-}
-
-/**
- * iommu_dma_compose_msi_msg() - Apply translation to an MSI message
- * @desc: MSI descriptor prepared by iommu_dma_prepare_msi()
- * @msg: MSI message containing target physical address
- */
-void iommu_dma_compose_msi_msg(struct msi_desc *desc, struct msi_msg *msg)
-{
-	struct device *dev = msi_desc_to_dev(desc);
-	const struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
-	const struct iommu_dma_msi_page *msi_page;
-
-	msi_page = msi_desc_get_iommu_cookie(desc);
 
-	if (!domain || !domain->iova_cookie || WARN_ON(!msi_page))
-		return;
-
-	msg->address_hi = upper_32_bits(msi_page->iova);
-	msg->address_lo &= cookie_msi_granule(domain->iova_cookie) - 1;
-	msg->address_lo += lower_32_bits(msi_page->iova);
+	msi_desc_set_iommu_msi_iova(
+		desc, msi_page->iova,
+		ilog2(cookie_msi_granule(domain->iova_cookie)));
+	return 0;
 }
 
 static int iommu_dma_init(void)

drivers/iommu/iommu-priv.h

@@ -24,9 +24,6 @@ static inline const struct iommu_ops *iommu_fwspec_ops(struct iommu_fwspec *fwsp
 	return iommu_ops_from_fwnode(fwspec ? fwspec->iommu_fwnode : NULL);
 }
 
-int iommu_group_replace_domain(struct iommu_group *group,
-			       struct iommu_domain *new_domain);
-
 int iommu_device_register_bus(struct iommu_device *iommu,
 			      const struct iommu_ops *ops,
 			      const struct bus_type *bus,

drivers/iommu/iommu.c

@@ -45,6 +45,9 @@ static unsigned int iommu_def_domain_type __read_mostly;
 static bool iommu_dma_strict __read_mostly = IS_ENABLED(CONFIG_IOMMU_DEFAULT_DMA_STRICT);
 static u32 iommu_cmd_line __read_mostly;
 
+/* Tags used with xa_tag_pointer() in group->pasid_array */
+enum { IOMMU_PASID_ARRAY_DOMAIN = 0, IOMMU_PASID_ARRAY_HANDLE = 1 };
+
 struct iommu_group {
 	struct kobject kobj;
 	struct kobject *devices_kobj;
@@ -2147,6 +2150,17 @@ struct iommu_domain *iommu_get_dma_domain(struct device *dev)
 	return dev->iommu_group->default_domain;
 }
 
+static void *iommu_make_pasid_array_entry(struct iommu_domain *domain,
+					  struct iommu_attach_handle *handle)
+{
+	if (handle) {
+		handle->domain = domain;
+		return xa_tag_pointer(handle, IOMMU_PASID_ARRAY_HANDLE);
+	}
+
+	return xa_tag_pointer(domain, IOMMU_PASID_ARRAY_DOMAIN);
+}
+
 static int __iommu_attach_group(struct iommu_domain *domain,
 				struct iommu_group *group)
 {
@@ -2187,32 +2201,6 @@ int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group)
 }
 EXPORT_SYMBOL_GPL(iommu_attach_group);
 
-/**
- * iommu_group_replace_domain - replace the domain that a group is attached to
- * @group: IOMMU group that will be attached to the new domain
- * @new_domain: new IOMMU domain to replace with
- *
- * This API allows the group to switch domains without being forced to go to
- * the blocking domain in-between.
- *
- * If the currently attached domain is a core domain (e.g. a default_domain),
- * it will act just like the iommu_attach_group().
- */
-int iommu_group_replace_domain(struct iommu_group *group,
-			       struct iommu_domain *new_domain)
-{
-	int ret;
-
-	if (!new_domain)
-		return -EINVAL;
-
-	mutex_lock(&group->mutex);
-	ret = __iommu_group_set_domain(group, new_domain);
-	mutex_unlock(&group->mutex);
-	return ret;
-}
-EXPORT_SYMBOL_NS_GPL(iommu_group_replace_domain, "IOMMUFD_INTERNAL");
-
 static int __iommu_device_set_domain(struct iommu_group *group,
 				     struct device *dev,
 				     struct iommu_domain *new_domain,
@@ -3374,6 +3362,7 @@ int iommu_attach_device_pasid(struct iommu_domain *domain,
 	struct iommu_group *group = dev->iommu_group;
 	struct group_device *device;
 	const struct iommu_ops *ops;
+	void *entry;
 	int ret;
 
 	if (!group)
@@ -3397,16 +3386,31 @@ int iommu_attach_device_pasid(struct iommu_domain *domain,
 		}
 	}
 
-	if (handle)
-		handle->domain = domain;
+	entry = iommu_make_pasid_array_entry(domain, handle);
 
-	ret = xa_insert(&group->pasid_array, pasid, handle, GFP_KERNEL);
+	/*
+	 * Entry present is a failure case. Use xa_insert() instead of
+	 * xa_reserve().
+	 */
+	ret = xa_insert(&group->pasid_array, pasid, XA_ZERO_ENTRY, GFP_KERNEL);
 	if (ret)
 		goto out_unlock;
 
 	ret = __iommu_set_group_pasid(domain, group, pasid);
-	if (ret)
-		xa_erase(&group->pasid_array, pasid);
+	if (ret) {
+		xa_release(&group->pasid_array, pasid);
+		goto out_unlock;
+	}
+
+	/*
+	 * The xa_insert() above reserved the memory, and the group->mutex is
+	 * held, this cannot fail. The new domain cannot be visible until the
+	 * operation succeeds as we cannot tolerate PRIs becoming concurrently
+	 * queued and then failing attach.
+	 */
+	WARN_ON(xa_is_err(xa_store(&group->pasid_array,
+				   pasid, entry, GFP_KERNEL)));
+
 out_unlock:
 	mutex_unlock(&group->mutex);
 	return ret;
@@ -3480,13 +3484,17 @@ struct iommu_attach_handle *
 iommu_attach_handle_get(struct iommu_group *group, ioasid_t pasid, unsigned int type)
 {
 	struct iommu_attach_handle *handle;
+	void *entry;
 
 	xa_lock(&group->pasid_array);
-	handle = xa_load(&group->pasid_array, pasid);
-	if (!handle)
+	entry = xa_load(&group->pasid_array, pasid);
+	if (!entry || xa_pointer_tag(entry) != IOMMU_PASID_ARRAY_HANDLE) {
 		handle = ERR_PTR(-ENOENT);
-	else if (type && handle->domain->type != type)
-		handle = ERR_PTR(-EBUSY);
+	} else {
+		handle = xa_untag_pointer(entry);
+		if (type && handle->domain->type != type)
+			handle = ERR_PTR(-EBUSY);
+	}
 	xa_unlock(&group->pasid_array);
 
 	return handle;
@@ -3509,25 +3517,35 @@ int iommu_attach_group_handle(struct iommu_domain *domain,
 			      struct iommu_group *group,
 			      struct iommu_attach_handle *handle)
 {
+	void *entry;
 	int ret;
 
-	if (handle)
-		handle->domain = domain;
+	if (!handle)
+		return -EINVAL;
 
 	mutex_lock(&group->mutex);
-	ret = xa_insert(&group->pasid_array, IOMMU_NO_PASID, handle, GFP_KERNEL);
+	entry = iommu_make_pasid_array_entry(domain, handle);
+	ret = xa_insert(&group->pasid_array,
+			IOMMU_NO_PASID, XA_ZERO_ENTRY, GFP_KERNEL);
 	if (ret)
-		goto err_unlock;
+		goto out_unlock;
 
 	ret = __iommu_attach_group(domain, group);
-	if (ret)
-		goto err_erase;
-	mutex_unlock(&group->mutex);
+	if (ret) {
+		xa_release(&group->pasid_array, IOMMU_NO_PASID);
+		goto out_unlock;
+	}
 
-	return 0;
-err_erase:
-	xa_erase(&group->pasid_array, IOMMU_NO_PASID);
-err_unlock:
+	/*
+	 * The xa_insert() above reserved the memory, and the group->mutex is
+	 * held, this cannot fail. The new domain cannot be visible until the
+	 * operation succeeds as we cannot tolerate PRIs becoming concurrently
+	 * queued and then failing attach.
+	 */
+	WARN_ON(xa_is_err(xa_store(&group->pasid_array,
+				   IOMMU_NO_PASID, entry, GFP_KERNEL)));
+
+out_unlock:
 	mutex_unlock(&group->mutex);
 	return ret;
 }
@@ -3557,33 +3575,34 @@ EXPORT_SYMBOL_NS_GPL(iommu_detach_group_handle, "IOMMUFD_INTERNAL");
  * @new_domain: new IOMMU domain to replace with
  * @handle: attach handle
  *
- * This is a variant of iommu_group_replace_domain(). It allows the caller to
- * provide an attach handle for the new domain and use it when the domain is
- * attached.
+ * This API allows the group to switch domains without being forced to go to
+ * the blocking domain in-between. It allows the caller to provide an attach
+ * handle for the new domain and use it when the domain is attached.
+ *
+ * If the currently attached domain is a core domain (e.g. a default_domain),
+ * it will act just like the iommu_attach_group_handle().
  */
 int iommu_replace_group_handle(struct iommu_group *group,
 			       struct iommu_domain *new_domain,
 			       struct iommu_attach_handle *handle)
 {
-	void *curr;
+	void *curr, *entry;
 	int ret;
 
-	if (!new_domain)
+	if (!new_domain || !handle)
 		return -EINVAL;
 
 	mutex_lock(&group->mutex);
-	if (handle) {
-		ret = xa_reserve(&group->pasid_array, IOMMU_NO_PASID, GFP_KERNEL);
-		if (ret)
-			goto err_unlock;
-		handle->domain = new_domain;
-	}
+	entry = iommu_make_pasid_array_entry(new_domain, handle);
+	ret = xa_reserve(&group->pasid_array, IOMMU_NO_PASID, GFP_KERNEL);
+	if (ret)
+		goto err_unlock;
 
 	ret = __iommu_group_set_domain(group, new_domain);
 	if (ret)
 		goto err_release;
 
-	curr = xa_store(&group->pasid_array, IOMMU_NO_PASID, handle, GFP_KERNEL);
+	curr = xa_store(&group->pasid_array, IOMMU_NO_PASID, entry, GFP_KERNEL);
 	WARN_ON(xa_is_err(curr));
 
 	mutex_unlock(&group->mutex);
@@ -3596,3 +3615,32 @@ int iommu_replace_group_handle(struct iommu_group *group,
 	return ret;
 }
 EXPORT_SYMBOL_NS_GPL(iommu_replace_group_handle, "IOMMUFD_INTERNAL");
+
+#if IS_ENABLED(CONFIG_IRQ_MSI_IOMMU)
+/**
+ * iommu_dma_prepare_msi() - Map the MSI page in the IOMMU domain
+ * @desc: MSI descriptor, will store the MSI page
+ * @msi_addr: MSI target address to be mapped
+ *
+ * The implementation of sw_msi() should take msi_addr and map it to
+ * an IOVA in the domain and call msi_desc_set_iommu_msi_iova() with the
+ * mapping information.
+ *
+ * Return: 0 on success or negative error code if the mapping failed.
+ */
+int iommu_dma_prepare_msi(struct msi_desc *desc, phys_addr_t msi_addr)
+{
+	struct device *dev = msi_desc_to_dev(desc);
+	struct iommu_group *group = dev->iommu_group;
+	int ret = 0;
+
+	if (!group)
+		return 0;
+
+	mutex_lock(&group->mutex);
+	if (group->domain && group->domain->sw_msi)
+		ret = group->domain->sw_msi(group->domain, desc, msi_addr);
+	mutex_unlock(&group->mutex);
+	return ret;
+}
+#endif /* CONFIG_IRQ_MSI_IOMMU */