Merge tag 'iommu-updates-v6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/iommu/linux

Pull iommu updates from Joerg Roedel:
 "Core iommufd dependencies from Jason:
   - 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

  Core fixes for probe-issues from Robin

  Intel VT-d changes:
   - Checking for SVA support in domain allocation and attach paths
   - Move PCI ATS and PRI configuration into probe paths
   - Fix a pentential hang on reboot -f
   - Miscellaneous cleanups

  AMD-Vi changes:
   - Support for up to 2k IRQs per PCI device function
   - Set of smaller fixes

  ARM-SMMU changes:
   - SMMUv2 devicetree binding updates for Qualcomm implementations
     (QCS8300 GPU and MSM8937)
   - Clean up SMMUv2 runtime PM implementation to help with wider rework
     of pm_runtime_put_autosuspend()

  Rockchip driver changes:
   - Driver adjustments for recent DT probing changes

  S390 IOMMU changes:
   - Support for IOMMU passthrough

  Apple Dart changes:
   - Driver adjustments to meet ISP device requirements
   - Null-ptr deref fix
   - Disable subpage protection for DART 1"

* tag 'iommu-updates-v6.15' of git://git.kernel.org/pub/scm/linux/kernel/git/iommu/linux: (54 commits)
  iommu/vt-d: Fix possible circular locking dependency
  iommu/vt-d: Don't clobber posted vCPU IRTE when host IRQ affinity changes
  iommu/vt-d: Put IRTE back into posted MSI mode if vCPU posting is disabled
  iommu: apple-dart: fix potential null pointer deref
  iommu/rockchip: Retire global dma_dev workaround
  iommu/rockchip: Register in a sensible order
  iommu/rockchip: Allocate per-device data sensibly
  iommu/mediatek-v1: Support COMPILE_TEST
  iommu/amd: Enable support for up to 2K interrupts per function
  iommu/amd: Rename DTE_INTTABLEN* and MAX_IRQS_PER_TABLE macro
  iommu/amd: Replace slab cache allocator with page allocator
  iommu/amd: Introduce generic function to set multibit feature value
  iommu: Don't warn prematurely about dodgy probes
  iommu/arm-smmu: Set rpm auto_suspend once during probe
  dt-bindings: arm-smmu: Document QCS8300 GPU SMMU
  iommu: Get DT/ACPI parsing into the proper probe path
  iommu: Keep dev->iommu state consistent
  iommu: Resolve ops in iommu_init_device()
  iommu: Handle race with default domain setup
  iommu: Unexport iommu_fwspec_free()
  ...

5 files changed, 288 insertions, 186 deletions

diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index dfd0898fb6c1..4e107f69f951 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -5,6 +5,7 @@
 #include <linux/iommufd.h>
 #include <linux/slab.h>
 #include <uapi/linux/iommufd.h>
+#include <linux/msi.h>
 
 #include "../iommu-priv.h"
 #include "io_pagetable.h"
@@ -293,36 +294,152 @@ u32 iommufd_device_to_id(struct iommufd_device *idev)
 }
 EXPORT_SYMBOL_NS_GPL(iommufd_device_to_id, "IOMMUFD");
 
+/*
+ * Get a iommufd_sw_msi_map for the msi physical address requested by the irq
+ * layer. The mapping to IOVA is global to the iommufd file descriptor, every
+ * domain that is attached to a device using the same MSI parameters will use
+ * the same IOVA.
+ */
+static __maybe_unused struct iommufd_sw_msi_map *
+iommufd_sw_msi_get_map(struct iommufd_ctx *ictx, phys_addr_t msi_addr,
+		       phys_addr_t sw_msi_start)
+{
+	struct iommufd_sw_msi_map *cur;
+	unsigned int max_pgoff = 0;
+
+	lockdep_assert_held(&ictx->sw_msi_lock);
+
+	list_for_each_entry(cur, &ictx->sw_msi_list, sw_msi_item) {
+		if (cur->sw_msi_start != sw_msi_start)
+			continue;
+		max_pgoff = max(max_pgoff, cur->pgoff + 1);
+		if (cur->msi_addr == msi_addr)
+			return cur;
+	}
+
+	if (ictx->sw_msi_id >=
+	    BITS_PER_BYTE * sizeof_field(struct iommufd_sw_msi_maps, bitmap))
+		return ERR_PTR(-EOVERFLOW);
+
+	cur = kzalloc(sizeof(*cur), GFP_KERNEL);
+	if (!cur)
+		return ERR_PTR(-ENOMEM);
+
+	cur->sw_msi_start = sw_msi_start;
+	cur->msi_addr = msi_addr;
+	cur->pgoff = max_pgoff;
+	cur->id = ictx->sw_msi_id++;
+	list_add_tail(&cur->sw_msi_item, &ictx->sw_msi_list);
+	return cur;
+}
+
+static int iommufd_sw_msi_install(struct iommufd_ctx *ictx,
+				  struct iommufd_hwpt_paging *hwpt_paging,
+				  struct iommufd_sw_msi_map *msi_map)
+{
+	unsigned long iova;
+
+	lockdep_assert_held(&ictx->sw_msi_lock);
+
+	iova = msi_map->sw_msi_start + msi_map->pgoff * PAGE_SIZE;
+	if (!test_bit(msi_map->id, hwpt_paging->present_sw_msi.bitmap)) {
+		int rc;
+
+		rc = iommu_map(hwpt_paging->common.domain, iova,
+			       msi_map->msi_addr, PAGE_SIZE,
+			       IOMMU_WRITE | IOMMU_READ | IOMMU_MMIO,
+			       GFP_KERNEL_ACCOUNT);
+		if (rc)
+			return rc;
+		__set_bit(msi_map->id, hwpt_paging->present_sw_msi.bitmap);
+	}
+	return 0;
+}
+
+/*
+ * Called by the irq code if the platform translates the MSI address through the
+ * IOMMU. msi_addr is the physical address of the MSI page. iommufd will
+ * allocate a fd global iova for the physical page that is the same on all
+ * domains and devices.
+ */
+#ifdef CONFIG_IRQ_MSI_IOMMU
+int iommufd_sw_msi(struct iommu_domain *domain, struct msi_desc *desc,
+		   phys_addr_t msi_addr)
+{
+	struct device *dev = msi_desc_to_dev(desc);
+	struct iommufd_hwpt_paging *hwpt_paging;
+	struct iommu_attach_handle *raw_handle;
+	struct iommufd_attach_handle *handle;
+	struct iommufd_sw_msi_map *msi_map;
+	struct iommufd_ctx *ictx;
+	unsigned long iova;
+	int rc;
+
+	/*
+	 * It is safe to call iommu_attach_handle_get() here because the iommu
+	 * core code invokes this under the group mutex which also prevents any
+	 * change of the attach handle for the duration of this function.
+	 */
+	iommu_group_mutex_assert(dev);
+
+	raw_handle =
+		iommu_attach_handle_get(dev->iommu_group, IOMMU_NO_PASID, 0);
+	if (IS_ERR(raw_handle))
+		return 0;
+	hwpt_paging = find_hwpt_paging(domain->iommufd_hwpt);
+
+	handle = to_iommufd_handle(raw_handle);
+	/* No IOMMU_RESV_SW_MSI means no change to the msi_msg */
+	if (handle->idev->igroup->sw_msi_start == PHYS_ADDR_MAX)
+		return 0;
+
+	ictx = handle->idev->ictx;
+	guard(mutex)(&ictx->sw_msi_lock);
+	/*
+	 * The input msi_addr is the exact byte offset of the MSI doorbell, we
+	 * assume the caller has checked that it is contained with a MMIO region
+	 * that is secure to map at PAGE_SIZE.
+	 */
+	msi_map = iommufd_sw_msi_get_map(handle->idev->ictx,
+					 msi_addr & PAGE_MASK,
+					 handle->idev->igroup->sw_msi_start);
+	if (IS_ERR(msi_map))
+		return PTR_ERR(msi_map);
+
+	rc = iommufd_sw_msi_install(ictx, hwpt_paging, msi_map);
+	if (rc)
+		return rc;
+	__set_bit(msi_map->id, handle->idev->igroup->required_sw_msi.bitmap);
+
+	iova = msi_map->sw_msi_start + msi_map->pgoff * PAGE_SIZE;
+	msi_desc_set_iommu_msi_iova(desc, iova, PAGE_SHIFT);
+	return 0;
+}
+#endif
+
 static int iommufd_group_setup_msi(struct iommufd_group *igroup,
 				   struct iommufd_hwpt_paging *hwpt_paging)
 {
-	phys_addr_t sw_msi_start = igroup->sw_msi_start;
-	int rc;
+	struct iommufd_ctx *ictx = igroup->ictx;
+	struct iommufd_sw_msi_map *cur;
+
+	if (igroup->sw_msi_start == PHYS_ADDR_MAX)
+		return 0;
 
 	/*
-	 * If the IOMMU driver gives a IOMMU_RESV_SW_MSI then it is asking us to
-	 * call iommu_get_msi_cookie() on its behalf. This is necessary to setup
-	 * the MSI window so iommu_dma_prepare_msi() can install pages into our
-	 * domain after request_irq(). If it is not done interrupts will not
-	 * work on this domain.
-	 *
-	 * FIXME: This is conceptually broken for iommufd since we want to allow
-	 * userspace to change the domains, eg switch from an identity IOAS to a
-	 * DMA IOAS. There is currently no way to create a MSI window that
-	 * matches what the IRQ layer actually expects in a newly created
-	 * domain.
+	 * Install all the MSI pages the device has been using into the domain
 	 */
-	if (sw_msi_start != PHYS_ADDR_MAX && !hwpt_paging->msi_cookie) {
-		rc = iommu_get_msi_cookie(hwpt_paging->common.domain,
-					  sw_msi_start);
+	guard(mutex)(&ictx->sw_msi_lock);
+	list_for_each_entry(cur, &ictx->sw_msi_list, sw_msi_item) {
+		int rc;
+
+		if (cur->sw_msi_start != igroup->sw_msi_start ||
+		    !test_bit(cur->id, igroup->required_sw_msi.bitmap))
+			continue;
+
+		rc = iommufd_sw_msi_install(ictx, hwpt_paging, cur);
 		if (rc)
 			return rc;
-
-		/*
-		 * iommu_get_msi_cookie() can only be called once per domain,
-		 * it returns -EBUSY on later calls.
-		 */
-		hwpt_paging->msi_cookie = true;
 	}
 	return 0;
 }
@@ -352,6 +469,111 @@ iommufd_device_attach_reserved_iova(struct iommufd_device *idev,
 	return 0;
 }
 
+/* The device attach/detach/replace helpers for attach_handle */
+
+static int iommufd_hwpt_attach_device(struct iommufd_hw_pagetable *hwpt,
+				      struct iommufd_device *idev)
+{
+	struct iommufd_attach_handle *handle;
+	int rc;
+
+	lockdep_assert_held(&idev->igroup->lock);
+
+	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+	if (!handle)
+		return -ENOMEM;
+
+	if (hwpt->fault) {
+		rc = iommufd_fault_iopf_enable(idev);
+		if (rc)
+			goto out_free_handle;
+	}
+
+	handle->idev = idev;
+	rc = iommu_attach_group_handle(hwpt->domain, idev->igroup->group,
+				       &handle->handle);
+	if (rc)
+		goto out_disable_iopf;
+
+	return 0;
+
+out_disable_iopf:
+	if (hwpt->fault)
+		iommufd_fault_iopf_disable(idev);
+out_free_handle:
+	kfree(handle);
+	return rc;
+}
+
+static struct iommufd_attach_handle *
+iommufd_device_get_attach_handle(struct iommufd_device *idev)
+{
+	struct iommu_attach_handle *handle;
+
+	lockdep_assert_held(&idev->igroup->lock);
+
+	handle =
+		iommu_attach_handle_get(idev->igroup->group, IOMMU_NO_PASID, 0);
+	if (IS_ERR(handle))
+		return NULL;
+	return to_iommufd_handle(handle);
+}
+
+static void iommufd_hwpt_detach_device(struct iommufd_hw_pagetable *hwpt,
+				       struct iommufd_device *idev)
+{
+	struct iommufd_attach_handle *handle;
+
+	handle = iommufd_device_get_attach_handle(idev);
+	iommu_detach_group_handle(hwpt->domain, idev->igroup->group);
+	if (hwpt->fault) {
+		iommufd_auto_response_faults(hwpt, handle);
+		iommufd_fault_iopf_disable(idev);
+	}
+	kfree(handle);
+}
+
+static int iommufd_hwpt_replace_device(struct iommufd_device *idev,
+				       struct iommufd_hw_pagetable *hwpt,
+				       struct iommufd_hw_pagetable *old)
+{
+	struct iommufd_attach_handle *handle, *old_handle =
+		iommufd_device_get_attach_handle(idev);
+	int rc;
+
+	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
+	if (!handle)
+		return -ENOMEM;
+
+	if (hwpt->fault && !old->fault) {
+		rc = iommufd_fault_iopf_enable(idev);
+		if (rc)
+			goto out_free_handle;
+	}
+
+	handle->idev = idev;
+	rc = iommu_replace_group_handle(idev->igroup->group, hwpt->domain,
+					&handle->handle);
+	if (rc)
+		goto out_disable_iopf;
+
+	if (old->fault) {
+		iommufd_auto_response_faults(hwpt, old_handle);
+		if (!hwpt->fault)
+			iommufd_fault_iopf_disable(idev);
+	}
+	kfree(old_handle);
+
+	return 0;
+
+out_disable_iopf:
+	if (hwpt->fault && !old->fault)
+		iommufd_fault_iopf_disable(idev);
+out_free_handle:
+	kfree(handle);
+	return rc;
+}
+
 int iommufd_hw_pagetable_attach(struct iommufd_hw_pagetable *hwpt,
 				struct iommufd_device *idev)
 {
diff --git a/drivers/iommu/iommufd/fault.c b/drivers/iommu/iommufd/fault.c
index d9a937450e55..c48d72c9668c 100644
--- a/drivers/iommu/iommufd/fault.c
+++ b/drivers/iommu/iommufd/fault.c
@@ -17,7 +17,7 @@
 #include "../iommu-priv.h"
 #include "iommufd_private.h"
 
-static int iommufd_fault_iopf_enable(struct iommufd_device *idev)
+int iommufd_fault_iopf_enable(struct iommufd_device *idev)
 {
 	struct device *dev = idev->dev;
 	int ret;
@@ -50,7 +50,7 @@ static int iommufd_fault_iopf_enable(struct iommufd_device *idev)
 	return ret;
 }
 
-static void iommufd_fault_iopf_disable(struct iommufd_device *idev)
+void iommufd_fault_iopf_disable(struct iommufd_device *idev)
 {
 	mutex_lock(&idev->iopf_lock);
 	if (!WARN_ON(idev->iopf_enabled == 0)) {
@@ -60,46 +60,8 @@ static void iommufd_fault_iopf_disable(struct iommufd_device *idev)
 	mutex_unlock(&idev->iopf_lock);
 }
 
-static int __fault_domain_attach_dev(struct iommufd_hw_pagetable *hwpt,
-				     struct iommufd_device *idev)
-{
-	struct iommufd_attach_handle *handle;
-	int ret;
-
-	handle = kzalloc(sizeof(*handle), GFP_KERNEL);
-	if (!handle)
-		return -ENOMEM;
-
-	handle->idev = idev;
-	ret = iommu_attach_group_handle(hwpt->domain, idev->igroup->group,
-					&handle->handle);
-	if (ret)
-		kfree(handle);
-
-	return ret;
-}
-
-int iommufd_fault_domain_attach_dev(struct iommufd_hw_pagetable *hwpt,
-				    struct iommufd_device *idev)
-{
-	int ret;
-
-	if (!hwpt->fault)
-		return -EINVAL;
-
-	ret = iommufd_fault_iopf_enable(idev);
-	if (ret)
-		return ret;
-
-	ret = __fault_domain_attach_dev(hwpt, idev);
-	if (ret)
-		iommufd_fault_iopf_disable(idev);
-
-	return ret;
-}
-
-static void iommufd_auto_response_faults(struct iommufd_hw_pagetable *hwpt,
-					 struct iommufd_attach_handle *handle)
+void iommufd_auto_response_faults(struct iommufd_hw_pagetable *hwpt,
+				  struct iommufd_attach_handle *handle)
 {
 	struct iommufd_fault *fault = hwpt->fault;
 	struct iopf_group *group, *next;
@@ -135,88 +97,6 @@ static void iommufd_auto_response_faults(struct iommufd_hw_pagetable *hwpt,
 	mutex_unlock(&fault->mutex);
 }
 
-static struct iommufd_attach_handle *
-iommufd_device_get_attach_handle(struct iommufd_device *idev)
-{
-	struct iommu_attach_handle *handle;
-
-	handle = iommu_attach_handle_get(idev->igroup->group, IOMMU_NO_PASID, 0);
-	if (IS_ERR(handle))
-		return NULL;
-
-	return to_iommufd_handle(handle);
-}
-
-void iommufd_fault_domain_detach_dev(struct iommufd_hw_pagetable *hwpt,
-				     struct iommufd_device *idev)
-{
-	struct iommufd_attach_handle *handle;
-
-	handle = iommufd_device_get_attach_handle(idev);
-	iommu_detach_group_handle(hwpt->domain, idev->igroup->group);
-	iommufd_auto_response_faults(hwpt, handle);
-	iommufd_fault_iopf_disable(idev);
-	kfree(handle);
-}
-
-static int __fault_domain_replace_dev(struct iommufd_device *idev,
-				      struct iommufd_hw_pagetable *hwpt,
-				      struct iommufd_hw_pagetable *old)
-{
-	struct iommufd_attach_handle *handle, *curr = NULL;
-	int ret;
-
-	if (old->fault)
-		curr = iommufd_device_get_attach_handle(idev);
-
-	if (hwpt->fault) {
-		handle = kzalloc(sizeof(*handle), GFP_KERNEL);
-		if (!handle)
-			return -ENOMEM;
-
-		handle->idev = idev;
-		ret = iommu_replace_group_handle(idev->igroup->group,
-						 hwpt->domain, &handle->handle);
-	} else {
-		ret = iommu_replace_group_handle(idev->igroup->group,
-						 hwpt->domain, NULL);
-	}
-
-	if (!ret && curr) {
-		iommufd_auto_response_faults(old, curr);
-		kfree(curr);
-	}
-
-	return ret;
-}
-
-int iommufd_fault_domain_replace_dev(struct iommufd_device *idev,
-				     struct iommufd_hw_pagetable *hwpt,
-				     struct iommufd_hw_pagetable *old)
-{
-	bool iopf_off = !hwpt->fault && old->fault;
-	bool iopf_on = hwpt->fault && !old->fault;
-	int ret;
-
-	if (iopf_on) {
-		ret = iommufd_fault_iopf_enable(idev);
-		if (ret)
-			return ret;
-	}
-
-	ret = __fault_domain_replace_dev(idev, hwpt, old);
-	if (ret) {
-		if (iopf_on)
-			iommufd_fault_iopf_disable(idev);
-		return ret;
-	}
-
-	if (iopf_off)
-		iommufd_fault_iopf_disable(idev);
-
-	return 0;
-}
-
 void iommufd_fault_destroy(struct iommufd_object *obj)
 {
 	struct iommufd_fault *fault = container_of(obj, struct iommufd_fault, obj);
@@ -449,7 +329,7 @@ int iommufd_fault_iopf_handler(struct iopf_group *group)
 	struct iommufd_hw_pagetable *hwpt;
 	struct iommufd_fault *fault;
 
-	hwpt = group->attach_handle->domain->fault_data;
+	hwpt = group->attach_handle->domain->iommufd_hwpt;
 	fault = hwpt->fault;
 
 	spin_lock(&fault->lock);
diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index 598be26a14e2..7de6e914232e 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -156,6 +156,7 @@ iommufd_hwpt_paging_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas,
 			goto out_abort;
 		}
 	}
+	iommu_domain_set_sw_msi(hwpt->domain, iommufd_sw_msi);
 
 	/*
 	 * Set the coherency mode before we do iopt_table_add_domain() as some
@@ -251,6 +252,7 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx,
 		goto out_abort;
 	}
 	hwpt->domain->owner = ops;
+	iommu_domain_set_sw_msi(hwpt->domain, iommufd_sw_msi);
 
 	if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED)) {
 		rc = -EINVAL;
@@ -307,6 +309,7 @@ iommufd_viommu_alloc_hwpt_nested(struct iommufd_viommu *viommu, u32 flags,
 		goto out_abort;
 	}
 	hwpt->domain->owner = viommu->iommu_dev->ops;
+	iommu_domain_set_sw_msi(hwpt->domain, iommufd_sw_msi);
 
 	if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED)) {
 		rc = -EINVAL;
@@ -406,10 +409,10 @@ int iommufd_hwpt_alloc(struct iommufd_ucmd *ucmd)
 		}
 		hwpt->fault = fault;
 		hwpt->domain->iopf_handler = iommufd_fault_iopf_handler;
-		hwpt->domain->fault_data = hwpt;
 		refcount_inc(&fault->obj.users);
 		iommufd_put_object(ucmd->ictx, &fault->obj);
 	}
+	hwpt->domain->iommufd_hwpt = hwpt;
 
 	cmd->out_hwpt_id = hwpt->obj.id;
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index 0b1bafc7fd99..246297452a44 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -19,6 +19,22 @@ struct iommu_group;
 struct iommu_option;
 struct iommufd_device;
 
+struct iommufd_sw_msi_map {
+	struct list_head sw_msi_item;
+	phys_addr_t sw_msi_start;
+	phys_addr_t msi_addr;
+	unsigned int pgoff;
+	unsigned int id;
+};
+
+/* Bitmap of struct iommufd_sw_msi_map::id */
+struct iommufd_sw_msi_maps {
+	DECLARE_BITMAP(bitmap, 64);
+};
+
+int iommufd_sw_msi(struct iommu_domain *domain, struct msi_desc *desc,
+		   phys_addr_t msi_addr);
+
 struct iommufd_ctx {
 	struct file *file;
 	struct xarray objects;
@@ -26,6 +42,10 @@ struct iommufd_ctx {
 	wait_queue_head_t destroy_wait;
 	struct rw_semaphore ioas_creation_lock;
 
+	struct mutex sw_msi_lock;
+	struct list_head sw_msi_list;
+	unsigned int sw_msi_id;
+
 	u8 account_mode;
 	/* Compatibility with VFIO no iommu */
 	u8 no_iommu_mode;
@@ -283,10 +303,10 @@ struct iommufd_hwpt_paging {
 	struct iommufd_ioas *ioas;
 	bool auto_domain : 1;
 	bool enforce_cache_coherency : 1;
-	bool msi_cookie : 1;
 	bool nest_parent : 1;
 	/* Head at iommufd_ioas::hwpt_list */
 	struct list_head hwpt_item;
+	struct iommufd_sw_msi_maps present_sw_msi;
 };
 
 struct iommufd_hwpt_nested {
@@ -383,6 +403,7 @@ struct iommufd_group {
 	struct iommu_group *group;
 	struct iommufd_hw_pagetable *hwpt;
 	struct list_head device_list;
+	struct iommufd_sw_msi_maps required_sw_msi;
 	phys_addr_t sw_msi_start;
 };
 
@@ -496,43 +517,10 @@ int iommufd_fault_alloc(struct iommufd_ucmd *ucmd);
 void iommufd_fault_destroy(struct iommufd_object *obj);
 int iommufd_fault_iopf_handler(struct iopf_group *group);
 
-int iommufd_fault_domain_attach_dev(struct iommufd_hw_pagetable *hwpt,
-				    struct iommufd_device *idev);
-void iommufd_fault_domain_detach_dev(struct iommufd_hw_pagetable *hwpt,
-				     struct iommufd_device *idev);
-int iommufd_fault_domain_replace_dev(struct iommufd_device *idev,
-				     struct iommufd_hw_pagetable *hwpt,
-				     struct iommufd_hw_pagetable *old);
-
-static inline int iommufd_hwpt_attach_device(struct iommufd_hw_pagetable *hwpt,
-					     struct iommufd_device *idev)
-{
-	if (hwpt->fault)
-		return iommufd_fault_domain_attach_dev(hwpt, idev);
-
-	return iommu_attach_group(hwpt->domain, idev->igroup->group);
-}
-
-static inline void iommufd_hwpt_detach_device(struct iommufd_hw_pagetable *hwpt,
-					      struct iommufd_device *idev)
-{
-	if (hwpt->fault) {
-		iommufd_fault_domain_detach_dev(hwpt, idev);
-		return;
-	}
-
-	iommu_detach_group(hwpt->domain, idev->igroup->group);
-}
-
-static inline int iommufd_hwpt_replace_device(struct iommufd_device *idev,
-					      struct iommufd_hw_pagetable *hwpt,
-					      struct iommufd_hw_pagetable *old)
-{
-	if (old->fault || hwpt->fault)
-		return iommufd_fault_domain_replace_dev(idev, hwpt, old);
-
-	return iommu_group_replace_domain(idev->igroup->group, hwpt->domain);
-}
+int iommufd_fault_iopf_enable(struct iommufd_device *idev);
+void iommufd_fault_iopf_disable(struct iommufd_device *idev);
+void iommufd_auto_response_faults(struct iommufd_hw_pagetable *hwpt,
+				  struct iommufd_attach_handle *handle);
 
 static inline struct iommufd_viommu *
 iommufd_get_viommu(struct iommufd_ucmd *ucmd, u32 id)
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index ccf616462a1c..b6fa9fd11bc1 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -227,6 +227,8 @@ static int iommufd_fops_open(struct inode *inode, struct file *filp)
 	xa_init(&ictx->groups);
 	ictx->file = filp;
 	init_waitqueue_head(&ictx->destroy_wait);
+	mutex_init(&ictx->sw_msi_lock);
+	INIT_LIST_HEAD(&ictx->sw_msi_list);
 	filp->private_data = ictx;
 	return 0;
 }
@@ -234,6 +236,8 @@ static int iommufd_fops_open(struct inode *inode, struct file *filp)
 static int iommufd_fops_release(struct inode *inode, struct file *filp)
 {
 	struct iommufd_ctx *ictx = filp->private_data;
+	struct iommufd_sw_msi_map *next;
+	struct iommufd_sw_msi_map *cur;
 	struct iommufd_object *obj;
 
 	/*
@@ -262,6 +266,11 @@ static int iommufd_fops_release(struct inode *inode, struct file *filp)
 			break;
 	}
 	WARN_ON(!xa_empty(&ictx->groups));
+
+	mutex_destroy(&ictx->sw_msi_lock);
+	list_for_each_entry_safe(cur, next, &ictx->sw_msi_list, sw_msi_item)
+		kfree(cur);
+
 	kfree(ictx);
 	return 0;
 }