OpenHCL: Enable VFIO cdev + IOMMUFD and implement new solution for VF Keep alive

.clang-format

@@ -415,6 +415,7 @@ ForEachMacros:
   - 'for_each_prop_dlc_cpus'
   - 'for_each_prop_dlc_platforms'
   - 'for_each_property_of_node'
+  - 'for_each_pt_level_entry'
   - 'for_each_rdt_resource'
   - 'for_each_reg'
   - 'for_each_reg_filtered'

Documentation/driver-api/vfio.rst

@@ -275,8 +275,6 @@ in a VFIO group.
 With CONFIG_VFIO_DEVICE_CDEV=y the user can now acquire a device fd
 by directly opening a character device /dev/vfio/devices/vfioX where
 "X" is the number allocated uniquely by VFIO for registered devices.
-cdev interface does not support noiommu devices, so user should use
-the legacy group interface if noiommu is wanted.
 
 The cdev only works with IOMMUFD.  Both VFIO drivers and applications
 must adapt to the new cdev security model which requires using
@@ -370,6 +368,93 @@ IOMMUFD IOAS/HWPT to enable userspace DMA::
 
 	/* Other device operations as stated in "VFIO Usage Example" */
 
+VFIO NOIOMMU mode
+-------------------------------------------------------------------------------
+VFIO also supports a no-IOMMU mode, intended for usages where unsafe DMA can
+be performed by userspace drivers w/o physical IOMMU protection. This mode
+is controlled by the parameter:
+
+/sys/module/vfio/parameters/enable_unsafe_noiommu_mode
+
+Upon enabling this mode, with an assigned device, the user will be presented
+with a VFIO group and device file, e.g.::
+
+  /dev/vfio/
+  |-- devices
+  |   `-- noiommu-vfioX	/* VFIO device cdev */
+  |-- noiommu-Y		/* VFIO group */
+  `-- vfio
+
+The capabilities vary depending on the device programming interface and kernel
+configuration used. The following table summarizes the differences ("Yes" means
+the UAPI is accessible and functional in noiommu mode, "No" means the UAPI is
+not supported):
+
++-------------------+---------------------+----------------------+
+| Feature           | VFIO group          | VFIO device cdev     |
++===================+=====================+======================+
+| VFIO device UAPI  | Yes                 | Yes                  |
++-------------------+---------------------+----------------------+
+| VFIO container    | No                  | No                   |
++-------------------+---------------------+----------------------+
+| IOMMUFD IOAS      | No                  | Yes*                 |
++-------------------+---------------------+----------------------+
+
+Note that the VFIO container case includes IOMMUFD provided VFIO compatibility
+interfaces when either CONFIG_VFIO_CONTAINER or CONFIG_IOMMUFD_VFIO_CONTAINER is
+enabled.
+
+* IOMMUFD UAPI is available for VFIO device cdev to pin and map user memory with
+  the ability to retrieve physical addresses for DMA command submission.
+
+Kconfig Support Matrix
+^^^^^^^^^^^^^^^^^^^^^^
+
+The visibility of CONFIG_VFIO_NOIOMMU depends on the combination of
+CONFIG_VFIO_GROUP, CONFIG_VFIO_DEVICE_CDEV, and whether a container backend
+(CONFIG_VFIO_CONTAINER or CONFIG_IOMMUFD_VFIO_CONTAINER) is configured.  The
+Kconfig dependencies enforce the following constraints:
+
+- At least one access path (group or cdev) must be available.
+- If VFIO_GROUP is enabled, a container backend is required; otherwise the
+  group node would be unusable in noiommu mode.
+- The cdev noiommu path requires CONFIG_GENERIC_ATOMIC64=n because it depends
+  on CONFIG_IOMMUFD_NOIOMMU.
+
+The resulting support matrix:
+
++------+-------+-----------+------+---------+---------------------------+
+| Case | GROUP | Container | CDEV | NOIOMMU | Notes                     |
++======+=======+===========+======+=========+===========================+
+|  1   |   y   |     y     |  n   |   yes   | Group noiommu works       |
++------+-------+-----------+------+---------+---------------------------+
+|  2   |   y   |     n     |  n   |   no    | Blocked - no container    |
++------+-------+-----------+------+---------+---------------------------+
+|  3   |   y   |     y     |  y   |   yes   | Both paths work [#cdev]_  |
++------+-------+-----------+------+---------+---------------------------+
+|  4   |   y   |     n     |  y   |   no    | Blocked - no container    |
++------+-------+-----------+------+---------+---------------------------+
+|  5   |   n   |     -     |  y   |   yes   | Cdev-only works [#cdev]_  |
++------+-------+-----------+------+---------+---------------------------+
+|  6   |   n   |     -     |  n   |   no    | No access path            |
++------+-------+-----------+------+---------+---------------------------+
+
+Container = CONFIG_VFIO_CONTAINER or CONFIG_IOMMUFD_VFIO_CONTAINER (either
+suffices).  Case 4 is intentionally blocked: allowing NOIOMMU with GROUP
+enabled but no container would create unusable group nodes.  Users who want
+cdev-only noiommu should set CONFIG_VFIO_GROUP=n (case 5).
+
+.. [#cdev] The cdev noiommu path requires CONFIG_GENERIC_ATOMIC64=n.  When
+   CONFIG_VFIO_GROUP=y, CONFIG_VFIO_DEVICE_CDEV=y, and
+   CONFIG_GENERIC_ATOMIC64=y, CONFIG_VFIO_NOIOMMU remains selectable for the
+   group path, but no noiommu device cdev is registered.  Cdev-only noiommu is
+   not selectable on those platforms.
+
+A new IOMMUFD ioctl IOMMU_IOAS_NOIOMMU_GET_PA is added to retrieve the physical
+address for a given IOVA. Although there is no physical DMA remapping hardware,
+IOMMU_IOAS_MAP_FIXED_IOVA is still used to establish IOVA-to-PA mappings in the
+software page table for later IOMMU_IOAS_NOIOMMU_GET_PA lookups.
+
 VFIO User API
 -------------------------------------------------------------------------------
 

Microsoft/hcl-arm64.config

@@ -1521,6 +1521,7 @@ CONFIG_UIO=y
 # CONFIG_UIO_MF624 is not set
 CONFIG_UIO_HV_GENERIC=y
 CONFIG_VFIO=y
+CONFIG_VFIO_DEVICE_CDEV=y
 CONFIG_VFIO_GROUP=y
 CONFIG_VFIO_CONTAINER=y
 CONFIG_VFIO_IOMMU_TYPE1=y
@@ -1612,8 +1613,33 @@ CONFIG_ARM_ARCH_TIMER=y
 # end of Clock Source drivers
 
 # CONFIG_MAILBOX is not set
+CONFIG_IOMMU_IOVA=y
 CONFIG_IOMMU_API=y
-# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_IOMMU_SUPPORT=y
+
+#
+# Generic IOMMU Pagetable Support
+#
+# CONFIG_IOMMU_IO_PGTABLE_LPAE is not set
+# CONFIG_IOMMU_IO_PGTABLE_ARMV7S is not set
+# CONFIG_IOMMU_IO_PGTABLE_DART is not set
+# end of Generic IOMMU Pagetable Support
+
+CONFIG_IOMMU_DEFAULT_DMA_STRICT=y
+# CONFIG_IOMMU_DEFAULT_DMA_LAZY is not set
+# CONFIG_IOMMU_DEFAULT_PASSTHROUGH is not set
+CONFIG_OF_IOMMU=y
+CONFIG_IOMMU_DMA=y
+# CONFIG_ARM_SMMU is not set
+# CONFIG_ARM_SMMU_V3 is not set
+CONFIG_IOMMUFD_DRIVER_CORE=y
+CONFIG_IOMMUFD=y
+CONFIG_IOMMUFD_NOIOMMU=y
+# CONFIG_VIRTIO_IOMMU is not set
+CONFIG_GENERIC_PT=y
+# CONFIG_DEBUG_GENERIC_PT is not set
+CONFIG_IOMMU_PT=y
+CONFIG_IOMMU_PT_AMDV1=y
 
 #
 # Remoteproc drivers
@@ -2195,11 +2221,13 @@ CONFIG_ZLIB_INFLATE=y
 CONFIG_DECOMPRESS_GZIP=y
 CONFIG_GENERIC_ALLOCATOR=y
 CONFIG_INTERVAL_TREE=y
+CONFIG_INTERVAL_TREE_SPAN_ITER=y
 CONFIG_XARRAY_MULTI=y
 CONFIG_HAS_IOMEM=y
 CONFIG_HAS_IOPORT=y
 CONFIG_HAS_IOPORT_MAP=y
 CONFIG_HAS_DMA=y
+CONFIG_DMA_OPS_HELPERS=y
 CONFIG_NEED_SG_DMA_FLAGS=y
 CONFIG_NEED_SG_DMA_LENGTH=y
 CONFIG_NEED_DMA_MAP_STATE=y

Microsoft/hcl-x64.config

@@ -2,7 +2,7 @@
 # Automatically generated file; DO NOT EDIT.
 # Linux/x86_64 6.18.37 Kernel Configuration
 #
-CONFIG_CC_VERSION_TEXT="gcc (Ubuntu 13.3.0-6ubuntu2~24.04) 13.3.0"
+CONFIG_CC_VERSION_TEXT="gcc (Ubuntu 13.3.0-6ubuntu2~24.04.1) 13.3.0"
 CONFIG_CC_IS_GCC=y
 CONFIG_GCC_VERSION=130300
 CONFIG_CLANG_VERSION=0
@@ -1501,6 +1501,7 @@ CONFIG_UIO=y
 # CONFIG_UIO_MF624 is not set
 CONFIG_UIO_HV_GENERIC=y
 CONFIG_VFIO=y
+CONFIG_VFIO_DEVICE_CDEV=y
 CONFIG_VFIO_GROUP=y
 CONFIG_VFIO_CONTAINER=y
 CONFIG_VFIO_IOMMU_TYPE1=y
@@ -1574,8 +1575,29 @@ CONFIG_CLKBLD_I8253=y
 # end of Clock Source drivers
 
 # CONFIG_MAILBOX is not set
+CONFIG_IOMMU_IOVA=y
 CONFIG_IOMMU_API=y
-# CONFIG_IOMMU_SUPPORT is not set
+CONFIG_IOMMU_SUPPORT=y
+
+#
+# Generic IOMMU Pagetable Support
+#
+# end of Generic IOMMU Pagetable Support
+
+# CONFIG_IOMMU_DEFAULT_DMA_STRICT is not set
+CONFIG_IOMMU_DEFAULT_DMA_LAZY=y
+# CONFIG_IOMMU_DEFAULT_PASSTHROUGH is not set
+CONFIG_OF_IOMMU=y
+CONFIG_IOMMU_DMA=y
+CONFIG_IOMMUFD_DRIVER_CORE=y
+CONFIG_IOMMUFD=y
+CONFIG_IOMMUFD_NOIOMMU=y
+CONFIG_HYPERV_IOMMU=y
+# CONFIG_VIRTIO_IOMMU is not set
+CONFIG_GENERIC_PT=y
+# CONFIG_DEBUG_GENERIC_PT is not set
+CONFIG_IOMMU_PT=y
+CONFIG_IOMMU_PT_AMDV1=y
 
 #
 # Remoteproc drivers
@@ -2142,11 +2164,14 @@ CONFIG_ZLIB_INFLATE=y
 # CONFIG_XZ_DEC is not set
 CONFIG_DECOMPRESS_GZIP=y
 CONFIG_INTERVAL_TREE=y
+CONFIG_INTERVAL_TREE_SPAN_ITER=y
 CONFIG_XARRAY_MULTI=y
 CONFIG_HAS_IOMEM=y
 CONFIG_HAS_IOPORT=y
 CONFIG_HAS_IOPORT_MAP=y
 CONFIG_HAS_DMA=y
+CONFIG_DMA_OPS_HELPERS=y
+CONFIG_NEED_SG_DMA_FLAGS=y
 CONFIG_NEED_SG_DMA_LENGTH=y
 CONFIG_NEED_DMA_MAP_STATE=y
 CONFIG_ARCH_DMA_ADDR_T_64BIT=y

drivers/iommu/Kconfig

@@ -384,3 +384,5 @@ config SPRD_IOMMU
 	  Say Y here if you want to use the multimedia devices listed above.
 
 endif # IOMMU_SUPPORT
+
+source "drivers/iommu/generic_pt/Kconfig"

drivers/iommu/Makefile

@@ -3,6 +3,7 @@ obj-y += arm/ iommufd/
 obj-$(CONFIG_AMD_IOMMU) += amd/
 obj-$(CONFIG_INTEL_IOMMU) += intel/
 obj-$(CONFIG_RISCV_IOMMU) += riscv/
+obj-$(CONFIG_GENERIC_PT) += generic_pt/fmt/
 obj-$(CONFIG_IOMMU_API) += iommu.o
 obj-$(CONFIG_IOMMU_SUPPORT) += iommu-pages.o
 obj-$(CONFIG_IOMMU_API) += iommu-traces.o

drivers/iommu/generic_pt/Kconfig

@@ -0,0 +1,45 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+menuconfig GENERIC_PT
+	bool "Generic Radix Page Table"
+	help
+	  Generic library for building radix tree page tables.
+
+	  Generic PT provides a set of HW page table formats and a common
+	  set of APIs to work with them.
+
+if GENERIC_PT
+config DEBUG_GENERIC_PT
+	bool "Extra debugging checks for GENERIC_PT"
+	help
+	  Enable extra run time debugging checks for GENERIC_PT code. This
+	  incurs a runtime cost and should not be enabled for production
+	  kernels.
+
+	  The kunit tests require this to be enabled to get full coverage.
+
+config IOMMU_PT
+	tristate "IOMMU Page Tables"
+	select IOMMU_API
+	depends on IOMMU_SUPPORT
+	depends on GENERIC_PT
+	help
+	  Generic library for building IOMMU page tables
+
+	  IOMMU_PT provides an implementation of the page table operations
+	  related to struct iommu_domain using GENERIC_PT. It provides a single
+	  implementation of the page table operations that can be shared by
+	  multiple drivers.
+
+if IOMMU_PT
+config IOMMU_PT_AMDV1
+	tristate "IOMMU page table for 64-bit AMD IOMMU v1"
+	depends on !GENERIC_ATOMIC64 # for cmpxchg64
+	help
+	  iommu_domain implementation for the AMD v1 page table. AMDv1 is the
+	  "host" page table. It supports granular page sizes of almost every
+	  power of 2 and decodes an full 64-bit IOVA space.
+
+	  Selected automatically by an IOMMU driver that uses this format.
+endif
+endif

drivers/iommu/generic_pt/fmt/Makefile

@@ -0,0 +1,11 @@
+# SPDX-License-Identifier: GPL-2.0
+
+iommu_pt_fmt-$(CONFIG_IOMMU_PT_AMDV1) += amdv1
+
+define create_format
+obj-$(2) += iommu_$(1).o
+
+endef
+
+$(eval $(foreach fmt,$(iommu_pt_fmt-y),$(call create_format,$(fmt),y)))
+$(eval $(foreach fmt,$(iommu_pt_fmt-m),$(call create_format,$(fmt),m)))