ctrliq
diff --git a/‎Documentation/ABI/testing/debugfs-amd-iommu‎
Lines changed: 131 additions & 0 deletions b/‎Documentation/ABI/testing/debugfs-amd-iommu‎
Lines changed: 131 additions & 0 deletions
diff --git a/‎Documentation/userspace-api/iommufd.rst‎
Lines changed: 14 additions & 2 deletions b/‎Documentation/userspace-api/iommufd.rst‎
Lines changed: 14 additions & 2 deletions
diff --git a/‎arch/powerpc/kvm/powerpc.c‎
Lines changed: 1 addition & 4 deletions b/‎arch/powerpc/kvm/powerpc.c‎
Lines changed: 1 addition & 4 deletions
diff --git a/‎drivers/dma/idxd/init.c‎
Lines changed: 6 additions & 35 deletions b/‎drivers/dma/idxd/init.c‎
Lines changed: 6 additions & 35 deletions
diff --git a/‎drivers/gpu/host1x/dev.c‎
Lines changed: 6 additions & 0 deletions b/‎drivers/gpu/host1x/dev.c‎
Lines changed: 6 additions & 0 deletions
@@ -0,0 +1,131 @@
+What:		/sys/kernel/debug/iommu/amd/iommu<x>/mmio
+Date:		January 2025
+Contact:	Dheeraj Kumar Srivastava <dheerajkumar.srivastava@amd.com>
+Description:
+		This file provides read/write access for user input. Users specify the
+		MMIO register offset for iommu<x>, and the file outputs the corresponding
+		MMIO register value of iommu<x>
+
+		Example::
+
+		  $ echo "0x18" > /sys/kernel/debug/iommu/amd/iommu00/mmio
+		  $ cat /sys/kernel/debug/iommu/amd/iommu00/mmio
+
+		Output::
+
+		  Offset:0x18 Value:0x000c22000003f48d
+
+What:		/sys/kernel/debug/iommu/amd/iommu<x>/capability
+Date:		January 2025
+Contact:	Dheeraj Kumar Srivastava <dheerajkumar.srivastava@amd.com>
+Description:
+		This file provides read/write access for user input. Users specify the
+		capability register offset for iommu<x>, and the file outputs the
+		corresponding capability register value of iommu<x>.
+
+		Example::
+
+		  $ echo "0x10" > /sys/kernel/debug/iommu/amd/iommu00/capability
+		  $ cat /sys/kernel/debug/iommu/amd/iommu00/capability
+
+		Output::
+
+		  Offset:0x10 Value:0x00203040
+
+What:		/sys/kernel/debug/iommu/amd/iommu<x>/cmdbuf
+Date:		January 2025
+Contact:	Dheeraj Kumar Srivastava <dheerajkumar.srivastava@amd.com>
+Description:
+		This file is a read-only output file containing iommu<x> command
+		buffer entries.
+
+		Examples::
+
+		  $ cat /sys/kernel/debug/iommu/amd/iommu<x>/cmdbuf
+
+		Output::
+
+		  CMD Buffer Head Offset:339 Tail Offset:339
+		    0: 00835001 10000001 00003c00 00000000
+		    1: 00000000 30000005 fffff003 7fffffff
+		    2: 00835001 10000001 00003c01 00000000
+		    3: 00000000 30000005 fffff003 7fffffff
+		    4: 00835001 10000001 00003c02 00000000
+		    5: 00000000 30000005 fffff003 7fffffff
+		    6: 00835001 10000001 00003c03 00000000
+		    7: 00000000 30000005 fffff003 7fffffff
+		    8: 00835001 10000001 00003c04 00000000
+		    9: 00000000 30000005 fffff003 7fffffff
+		   10: 00835001 10000001 00003c05 00000000
+		   11: 00000000 30000005 fffff003 7fffffff
+		  [...]
+
+What:		/sys/kernel/debug/iommu/amd/devid
+Date:		January 2025
+Contact:	Dheeraj Kumar Srivastava <dheerajkumar.srivastava@amd.com>
+Description:
+		This file provides read/write access for user input. Users specify the
+		device ID, which can be used to dump IOMMU data structures such as the
+		interrupt remapping table and device table.
+
+		Example:
+
+		1.
+		  ::
+
+		    $ echo 0000:01:00.0 > /sys/kernel/debug/iommu/amd/devid
+		    $ cat /sys/kernel/debug/iommu/amd/devid
+
+		  Output::
+
+		    0000:01:00.0
+
+		2.
+		  ::
+
+		    $ echo 01:00.0 > /sys/kernel/debug/iommu/amd/devid
+		    $ cat /sys/kernel/debug/iommu/amd/devid
+
+		  Output::
+
+		    0000:01:00.0
+
+What:		/sys/kernel/debug/iommu/amd/devtbl
+Date:		January 2025
+Contact:	Dheeraj Kumar Srivastava <dheerajkumar.srivastava@amd.com>
+Description:
+		This file is a read-only output file containing the device table entry
+		for the device ID provided in /sys/kernel/debug/iommu/amd/devid.
+
+		Example::
+
+		  $ cat /sys/kernel/debug/iommu/amd/devtbl
+
+		Output::
+
+		  DeviceId             QWORD[3]         QWORD[2]         QWORD[1]         QWORD[0] iommu
+		  0000:01:00.0 0000000000000000 20000001373b8013 0000000000000038 6000000114d7b603 iommu3
+
+What:		/sys/kernel/debug/iommu/amd/irqtbl
+Date:		January 2025
+Contact:	Dheeraj Kumar Srivastava <dheerajkumar.srivastava@amd.com>
+Description:
+		This file is a read-only output file containing valid IRT table entries
+		for the device ID provided in /sys/kernel/debug/iommu/amd/devid.
+
+		Example::
+
+		  $ cat /sys/kernel/debug/iommu/amd/irqtbl
+
+		Output::
+
+		  DeviceId 0000:01:00.0
+		  IRT[0000] 0000000000000020 0000000000000241
+		  IRT[0001] 0000000000000020 0000000000000841
+		  IRT[0002] 0000000000000020 0000000000002041
+		  IRT[0003] 0000000000000020 0000000000008041
+		  IRT[0004] 0000000000000020 0000000000020041
+		  IRT[0005] 0000000000000020 0000000000080041
+		  IRT[0006] 0000000000000020 0000000000200041
+		  IRT[0007] 0000000000000020 0000000000800041
+		  [...]
@@ -43,7 +43,7 @@ Following IOMMUFD objects are exposed to userspace:
 
 - IOMMUFD_OBJ_HWPT_PAGING, representing an actual hardware I/O page table
   (i.e. a single struct iommu_domain) managed by the iommu driver. "PAGING"
-  primarly indicates this type of HWPT should be linked to an IOAS. It also
+  primarily indicates this type of HWPT should be linked to an IOAS. It also
   indicates that it is backed by an iommu_domain with __IOMMU_DOMAIN_PAGING
   feature flag. This can be either an UNMANAGED stage-1 domain for a device
   running in the user space, or a nesting parent stage-2 domain for mappings
@@ -76,7 +76,7 @@ Following IOMMUFD objects are exposed to userspace:
 
   * Security namespace for guest owned ID, e.g. guest-controlled cache tags
   * Non-device-affiliated event reporting, e.g. invalidation queue errors
-  * Access to a sharable nesting parent pagetable across physical IOMMUs
+  * Access to a shareable nesting parent pagetable across physical IOMMUs
   * Virtualization of various platforms IDs, e.g. RIDs and others
   * Delivery of paravirtualized invalidation
   * Direct assigned invalidation queues
@@ -124,6 +124,17 @@ Following IOMMUFD objects are exposed to userspace:
   used to allocate a vEVENTQ. Each vIOMMU can support multiple types of vEVENTS,
   but is confined to one vEVENTQ per vEVENTQ type.
 
+- IOMMUFD_OBJ_HW_QUEUE, representing a hardware accelerated queue, as a subset
+  of IOMMU's virtualization features, for the IOMMU HW to directly read or write
+  the virtual queue memory owned by a guest OS. This HW-acceleration feature can
+  allow VM to work with the IOMMU HW directly without a VM Exit, so as to reduce
+  overhead from the hypercalls. Along with the HW QUEUE object, iommufd provides
+  user space an mmap interface for VMM to mmap a physical MMIO region from the
+  host physical address space to the guest physical address space, allowing the
+  guest OS to directly control the allocated HW QUEUE. Thus, when allocating a
+  HW QUEUE, the VMM must request a pair of mmap info (offset/length) and pass in
+  exactly to an mmap syscall via its offset and length arguments.
+
 All user-visible objects are destroyed via the IOMMU_DESTROY uAPI.
 
 The diagrams below show relationships between user-visible objects and kernel
@@ -270,6 +281,7 @@ User visible objects are backed by following datastructures:
 - iommufd_viommu for IOMMUFD_OBJ_VIOMMU.
 - iommufd_vdevice for IOMMUFD_OBJ_VDEVICE.
 - iommufd_veventq for IOMMUFD_OBJ_VEVENTQ.
+- iommufd_hw_queue for IOMMUFD_OBJ_HW_QUEUE.
 
 Several terminologies when looking at these datastructures:
 
 
@@ -550,12 +550,9 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 
 #ifdef CONFIG_PPC_BOOK3S_64
 	case KVM_CAP_SPAPR_TCE:
+		fallthrough;
 	case KVM_CAP_SPAPR_TCE_64:
-		r = 1;
-		break;
 	case KVM_CAP_SPAPR_TCE_VFIO:
-		r = !!cpu_has_feature(CPU_FTR_HVMODE);
-		break;
 	case KVM_CAP_PPC_RTAS:
 	case KVM_CAP_PPC_FIXUP_HCALL:
 	case KVM_CAP_PPC_ENABLE_HCALL:
 
@@ -705,27 +705,6 @@ static void idxd_disable_system_pasid(struct idxd_device *idxd)
 	idxd->pasid = IOMMU_PASID_INVALID;
 }
 
-static int idxd_enable_sva(struct pci_dev *pdev)
-{
-	int ret;
-
-	ret = iommu_dev_enable_feature(&pdev->dev, IOMMU_DEV_FEAT_IOPF);
-	if (ret)
-		return ret;
-
-	ret = iommu_dev_enable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA);
-	if (ret)
-		iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_IOPF);
-
-	return ret;
-}
-
-static void idxd_disable_sva(struct pci_dev *pdev)
-{
-	iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_SVA);
-	iommu_dev_disable_feature(&pdev->dev, IOMMU_DEV_FEAT_IOPF);
-}
-
 static int idxd_probe(struct idxd_device *idxd)
 {
 	struct pci_dev *pdev = idxd->pdev;
@@ -740,17 +719,13 @@ static int idxd_probe(struct idxd_device *idxd)
 	dev_dbg(dev, "IDXD reset complete\n");
 
 	if (IS_ENABLED(CONFIG_INTEL_IDXD_SVM) && sva) {
-		if (idxd_enable_sva(pdev)) {
-			dev_warn(dev, "Unable to turn on user SVA feature.\n");
-		} else {
-			set_bit(IDXD_FLAG_USER_PASID_ENABLED, &idxd->flags);
+		set_bit(IDXD_FLAG_USER_PASID_ENABLED, &idxd->flags);
 
-			rc = idxd_enable_system_pasid(idxd);
-			if (rc)
-				dev_warn(dev, "No in-kernel DMA with PASID. %d\n", rc);
-			else
-				set_bit(IDXD_FLAG_PASID_ENABLED, &idxd->flags);
-		}
+		rc = idxd_enable_system_pasid(idxd);
+		if (rc)
+			dev_warn(dev, "No in-kernel DMA with PASID. %d\n", rc);
+		else
+			set_bit(IDXD_FLAG_PASID_ENABLED, &idxd->flags);
 	} else if (!sva) {
 		dev_warn(dev, "User forced SVA off via module param.\n");
 	}
@@ -788,8 +763,6 @@ static int idxd_probe(struct idxd_device *idxd)
  err:
 	if (device_pasid_enabled(idxd))
 		idxd_disable_system_pasid(idxd);
-	if (device_user_pasid_enabled(idxd))
-		idxd_disable_sva(pdev);
 	return rc;
 }
 
@@ -800,8 +773,6 @@ static void idxd_cleanup(struct idxd_device *idxd)
 	idxd_cleanup_internals(idxd);
 	if (device_pasid_enabled(idxd))
 		idxd_disable_system_pasid(idxd);
-	if (device_user_pasid_enabled(idxd))
-		idxd_disable_sva(idxd->pdev);
 }
 
 /*
 
@@ -367,6 +367,10 @@ static bool host1x_wants_iommu(struct host1x *host1x)
 	return true;
 }
 
+/*
+ * Returns ERR_PTR on failure, NULL if the translation is IDENTITY, otherwise a
+ * valid paging domain.
+ */
 static struct iommu_domain *host1x_iommu_attach(struct host1x *host)
 {
 	struct iommu_domain *domain = iommu_get_domain_for_dev(host->dev);
@@ -391,6 +395,8 @@ static struct iommu_domain *host1x_iommu_attach(struct host1x *host)
 	 * Similarly, if host1x is already attached to an IOMMU (via the DMA
 	 * API), don't try to attach again.
 	 */
+	if (domain && domain->type == IOMMU_DOMAIN_IDENTITY)
+		domain = NULL;
 	if (!host1x_wants_iommu(host) || domain)
 		return domain;