Merge tag 'vfio-v6.6-rc1' of https://github.com/awilliam/linux-vfio

ec0e2dc8 · Linus Torvalds <[email protected]> · 2023-08-30 20:36:01 -07:00

Pull VFIO updates from Alex Williamson:

 - VFIO direct character device (cdev) interface support. This extracts
   the vfio device fd from the container and group model, and is
   intended to be the native uAPI for use with IOMMUFD (Yi Liu)

 - Enhancements to the PCI hot reset interface in support of cdev usage
   (Yi Liu)

 - Fix a potential race between registering and unregistering vfio files
   in the kvm-vfio interface and extend use of a lock to avoid extra
   drop and acquires (Dmitry Torokhov)

 - A new vfio-pci variant driver for the AMD/Pensando Distributed
   Services Card (PDS) Ethernet device, supporting live migration (Brett
   Creeley)

 - Cleanups to remove redundant owner setup in cdx and fsl bus drivers,
   and simplify driver init/exit in fsl code (Li Zetao)

 - Fix uninitialized hole in data structure and pad capability
   structures for alignment (Stefan Hajnoczi)

* tag 'vfio-v6.6-rc1' of https://github.com/awilliam/linux-vfio: (53 commits)
  vfio/pds: Send type for SUSPEND_STATUS command
  vfio/pds: fix return value in pds_vfio_get_lm_file()
  pds_core: Fix function header descriptions
  vfio: align capability structures
  vfio/type1: fix cap_migration information leak
  vfio/fsl-mc: Use module_fsl_mc_driver macro to simplify the code
  vfio/cdx: Remove redundant initialization owner in vfio_cdx_driver
  vfio/pds: Add Kconfig and documentation
  vfio/pds: Add support for firmware recovery
  vfio/pds: Add support for dirty page tracking
  vfio/pds: Add VFIO live migration support
  vfio/pds: register with the pds_core PF
  pds_core: Require callers of register/unregister to pass PF drvdata
  vfio/pds: Initial support for pds VFIO driver
  vfio: Commonize combine_ranges for use in other VFIO drivers
  kvm/vfio: avoid bouncing the mutex when adding and deleting groups
  kvm/vfio: ensure kvg instance stays around in kvm_vfio_group_add()
  docs: vfio: Add vfio device cdev description
  vfio: Compile vfio_group infrastructure optionally
  vfio: Move the IOMMU_CAP_CACHE_COHERENCY check in __vfio_register_dev()
  ...

Commit: ec0e2dc81072300acbda5deca2e02f98485eafa9
Parents: b6f6167e · 642265e2

Merge commit. Changes below are compared with the first parent: b6f6167e.

Changes

55 files changed · +4350 −458

File	Status	Add	Del	Content
Documentation/driver-api/vfio.rst	modified	+144	−3	View file
Documentation/networking/device_drivers/ethernet/amd/pds_vfio_pci.rst	added	+79	−0	View file
Documentation/networking/device_drivers/ethernet/index.rst	modified	+1	−0	View file
Documentation/virt/kvm/devices/vfio.rst	modified	+31	−16	View file
MAINTAINERS	modified	+7	−0	View file
drivers/gpu/drm/i915/gvt/kvmgt.c	modified	+1	−0	View file
drivers/iommu/iommufd/Kconfig	modified	+2	−2	View file
drivers/iommu/iommufd/device.c	modified	+111	−5	View file
drivers/iommu/iommufd/iommufd_private.h	modified	+2	−0	View file
drivers/iommu/iommufd/main.c	modified	+25	−1	View file
drivers/iommu/iommufd/vfio_compat.c	modified	+2	−0	View file
drivers/net/ethernet/amd/pds_core/auxbus.c	modified	+7	−17	View file
drivers/s390/cio/vfio_ccw_ops.c	modified	+1	−0	View file
drivers/s390/crypto/vfio_ap_ops.c	modified	+1	−0	View file
drivers/vfio/Kconfig	modified	+27	−0	View file
drivers/vfio/Makefile	modified	+2	−1	View file
drivers/vfio/cdx/main.c	modified	+0	−1	View file
drivers/vfio/device_cdev.c	added	+228	−0	View file
drivers/vfio/fsl-mc/vfio_fsl_mc.c	modified	+2	−13	View file
drivers/vfio/group.c	modified	+111	−62	View file
drivers/vfio/iommufd.c	modified	+105	−33	View file
drivers/vfio/pci/Kconfig	modified	+2	−0	View file
drivers/vfio/pci/Makefile	modified	+2	−0	View file
drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c	modified	+2	−0	View file
drivers/vfio/pci/mlx5/cmd.c	modified	+1	−47	View file
drivers/vfio/pci/mlx5/main.c	modified	+1	−0	View file
drivers/vfio/pci/pds/Kconfig	added	+19	−0	View file
drivers/vfio/pci/pds/Makefile	added	+11	−0	View file
drivers/vfio/pci/pds/cmds.c	added	+510	−0	View file
drivers/vfio/pci/pds/cmds.h	added	+25	−0	View file
drivers/vfio/pci/pds/dirty.c	added	+564	−0	View file
drivers/vfio/pci/pds/dirty.h	added	+39	−0	View file
drivers/vfio/pci/pds/lm.c	added	+434	−0	View file
drivers/vfio/pci/pds/lm.h	added	+41	−0	View file
drivers/vfio/pci/pds/pci_drv.c	added	+209	−0	View file
drivers/vfio/pci/pds/pci_drv.h	added	+9	−0	View file
drivers/vfio/pci/pds/vfio_dev.c	added	+227	−0	View file
drivers/vfio/pci/pds/vfio_dev.h	added	+39	−0	View file
drivers/vfio/pci/vfio_pci.c	modified	+1	−0	View file
drivers/vfio/pci/vfio_pci_core.c	modified	+155	−106	View file
drivers/vfio/platform/vfio_amba.c	modified	+1	−0	View file
drivers/vfio/platform/vfio_platform.c	modified	+1	−0	View file
drivers/vfio/vfio.h	modified	+201	−17	View file
drivers/vfio/vfio_iommu_type1.c	modified	+3	−10	View file
drivers/vfio/vfio_main.c	modified	+279	−28	View file
include/linux/iommufd.h	modified	+7	−0	View file
include/linux/pds/pds_adminq.h	modified	+375	−0	View file
include/linux/pds/pds_common.h	modified	+6	−3	View file
include/linux/vfio.h	modified	+64	−5	View file
include/uapi/linux/kvm.h	modified	+10	−3	View file
include/uapi/linux/vfio.h	modified	+143	−1	View file
samples/vfio-mdev/mbochs.c	modified	+1	−0	View file
samples/vfio-mdev/mdpy.c	modified	+1	−0	View file
samples/vfio-mdev/mtty.c	modified	+1	−0	View file
virt/kvm/vfio.c	modified	+77	−84	View file

Only the first 600 diff lines are shown. Download the complete patch.

Documentation/driver-api/vfio.rst

View file

diff --git a/Documentation/driver-api/vfio.rst b/Documentation/driver-api/vfio.rst
index 68abc08..633d11c 100644
--- a/Documentation/driver-api/vfio.rst
+++ b/Documentation/driver-api/vfio.rst
@@ -239,6 +239,137 @@ group and can access them as follows::
 	/* Gratuitous device reset and go... */
 	ioctl(device, VFIO_DEVICE_RESET);
 
+IOMMUFD and vfio_iommu_type1
+----------------------------
+
+IOMMUFD is the new user API to manage I/O page tables from userspace.
+It intends to be the portal of delivering advanced userspace DMA
+features (nested translation [5]_, PASID [6]_, etc.) while also providing
+a backwards compatibility interface for existing VFIO_TYPE1v2_IOMMU use
+cases.  Eventually the vfio_iommu_type1 driver, as well as the legacy
+vfio container and group model is intended to be deprecated.
+
+The IOMMUFD backwards compatibility interface can be enabled two ways.
+In the first method, the kernel can be configured with
+CONFIG_IOMMUFD_VFIO_CONTAINER, in which case the IOMMUFD subsystem
+transparently provides the entire infrastructure for the VFIO
+container and IOMMU backend interfaces.  The compatibility mode can
+also be accessed if the VFIO container interface, ie. /dev/vfio/vfio is
+simply symlink'd to /dev/iommu.  Note that at the time of writing, the
+compatibility mode is not entirely feature complete relative to
+VFIO_TYPE1v2_IOMMU (ex. DMA mapping MMIO) and does not attempt to
+provide compatibility to the VFIO_SPAPR_TCE_IOMMU interface.  Therefore
+it is not generally advisable at this time to switch from native VFIO
+implementations to the IOMMUFD compatibility interfaces.
+
+Long term, VFIO users should migrate to device access through the cdev
+interface described below, and native access through the IOMMUFD
+provided interfaces.
+
+VFIO Device cdev
+----------------
+
+Traditionally user acquires a device fd via VFIO_GROUP_GET_DEVICE_FD
+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
+VFIO_DEVICE_BIND_IOMMUFD to claim DMA ownership before starting to
+actually use the device.  Once BIND succeeds then a VFIO device can
+be fully accessed by the user.
+
+VFIO device cdev doesn't rely on VFIO group/container/iommu drivers.
+Hence those modules can be fully compiled out in an environment
+where no legacy VFIO application exists.
+
+So far SPAPR does not support IOMMUFD yet.  So it cannot support device
+cdev either.
+
+vfio device cdev access is still bound by IOMMU group semantics, ie. there
+can be only one DMA owner for the group.  Devices belonging to the same
+group can not be bound to multiple iommufd_ctx or shared between native
+kernel and vfio bus driver or other driver supporting the driver_managed_dma
+flag.  A violation of this ownership requirement will fail at the
+VFIO_DEVICE_BIND_IOMMUFD ioctl, which gates full device access.
+
+Device cdev Example
+-------------------
+
+Assume user wants to access PCI device 0000:6a:01.0::
+
+	$ ls /sys/bus/pci/devices/0000:6a:01.0/vfio-dev/
+	vfio0
+
+This device is therefore represented as vfio0.  The user can verify
+its existence::
+
+	$ ls -l /dev/vfio/devices/vfio0
+	crw------- 1 root root 511, 0 Feb 16 01:22 /dev/vfio/devices/vfio0
+	$ cat /sys/bus/pci/devices/0000:6a:01.0/vfio-dev/vfio0/dev
+	511:0
+	$ ls -l /dev/char/511\:0
+	lrwxrwxrwx 1 root root 21 Feb 16 01:22 /dev/char/511:0 -> ../vfio/devices/vfio0
+
+Then provide the user with access to the device if unprivileged
+operation is desired::
+
+	$ chown user:user /dev/vfio/devices/vfio0
+
+Finally the user could get cdev fd by::
+
+	cdev_fd = open("/dev/vfio/devices/vfio0", O_RDWR);
+
+An opened cdev_fd doesn't give the user any permission of accessing
+the device except binding the cdev_fd to an iommufd.  After that point
+then the device is fully accessible including attaching it to an
+IOMMUFD IOAS/HWPT to enable userspace DMA::
+
+	struct vfio_device_bind_iommufd bind = {
+		.argsz = sizeof(bind),
+		.flags = 0,
+	};
+	struct iommu_ioas_alloc alloc_data  = {
+		.size = sizeof(alloc_data),
+		.flags = 0,
+	};
+	struct vfio_device_attach_iommufd_pt attach_data = {
+		.argsz = sizeof(attach_data),
+		.flags = 0,
+	};
+	struct iommu_ioas_map map = {
+		.size = sizeof(map),
+		.flags = IOMMU_IOAS_MAP_READABLE |
+			 IOMMU_IOAS_MAP_WRITEABLE |
+			 IOMMU_IOAS_MAP_FIXED_IOVA,
+		.__reserved = 0,
+	};
+
+	iommufd = open("/dev/iommu", O_RDWR);
+
+	bind.iommufd = iommufd;
+	ioctl(cdev_fd, VFIO_DEVICE_BIND_IOMMUFD, &bind);
+
+	ioctl(iommufd, IOMMU_IOAS_ALLOC, &alloc_data);
+	attach_data.pt_id = alloc_data.out_ioas_id;
+	ioctl(cdev_fd, VFIO_DEVICE_ATTACH_IOMMUFD_PT, &attach_data);
+
+	/* Allocate some space and setup a DMA mapping */
+	map.user_va = (int64_t)mmap(0, 1024 * 1024, PROT_READ | PROT_WRITE,
+				    MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
+	map.iova = 0; /* 1MB starting at 0x0 from device view */
+	map.length = 1024 * 1024;
+	map.ioas_id = alloc_data.out_ioas_id;;
+
+	ioctl(iommufd, IOMMU_IOAS_MAP, &map);
+
+	/* Other device operations as stated in "VFIO Usage Example" */
+
 VFIO User API
 -------------------------------------------------------------------------------
 
@@ -279,6 +410,7 @@ similar to a file operations structure::
 					struct iommufd_ctx *ictx, u32 *out_device_id);
 		void	(*unbind_iommufd)(struct vfio_device *vdev);
 		int	(*attach_ioas)(struct vfio_device *vdev, u32 *pt_id);
+		void	(*detach_ioas)(struct vfio_device *vdev);
 		int	(*open_device)(struct vfio_device *vdev);
 		void	(*close_device)(struct vfio_device *vdev);
 		ssize_t	(*read)(struct vfio_device *vdev, char __user *buf,
@@ -315,9 +447,10 @@ container_of().
 	- The [un]bind_iommufd callbacks are issued when the device is bound to
 	  and unbound from iommufd.
 
-	- The attach_ioas callback is issued when the device is attached to an
-	  IOAS managed by the bound iommufd. The attached IOAS is automatically
-	  detached when the device is unbound from iommufd.
+	- The [de]attach_ioas callback is issued when the device is attached to
+	  and detached from an IOAS managed by the bound iommufd. However, the
+	  attached IOAS can also be automatically detached when the device is
+	  unbound from iommufd.
 
 	- The read/write/mmap callbacks implement the device region access defined
 	  by the device's own VFIO_DEVICE_GET_REGION_INFO ioctl.
@@ -564,3 +697,11 @@ This implementation has some specifics:
 				\-0d.1
 
 	00:1e.0 PCI bridge: Intel Corporation 82801 PCI Bridge (rev 90)
+
+.. [5] Nested translation is an IOMMU feature which supports two stage
+   address translations.  This improves the address translation efficiency
+   in IOMMU virtualization.
+
+.. [6] PASID stands for Process Address Space ID, introduced by PCI
+   Express.  It is a prerequisite for Shared Virtual Addressing (SVA)
+   and Scalable I/O Virtualization (Scalable IOV).

Documentation/networking/device_drivers/ethernet/amd/pds_vfio_pci.rst

View file

diff --git a/Documentation/networking/device_drivers/ethernet/amd/pds_vfio_pci.rst b/Documentation/networking/device_drivers/ethernet/amd/pds_vfio_pci.rst
new file mode 100644
index 0000000..7a6bc84
--- /dev/null
+++ b/Documentation/networking/device_drivers/ethernet/amd/pds_vfio_pci.rst
@@ -0,0 +1,79 @@
+.. SPDX-License-Identifier: GPL-2.0+
+.. note: can be edited and viewed with /usr/bin/formiko-vim
+
+==========================================================
+PCI VFIO driver for the AMD/Pensando(R) DSC adapter family
+==========================================================
+
+AMD/Pensando Linux VFIO PCI Device Driver
+Copyright(c) 2023 Advanced Micro Devices, Inc.
+
+Overview
+========
+
+The ``pds-vfio-pci`` module is a PCI driver that supports Live Migration
+capable Virtual Function (VF) devices in the DSC hardware.
+
+Using the device
+================
+
+The pds-vfio-pci device is enabled via multiple configuration steps and
+depends on the ``pds_core`` driver to create and enable SR-IOV Virtual
+Function devices.
+
+Shown below are the steps to bind the driver to a VF and also to the
+associated auxiliary device created by the ``pds_core`` driver. This
+example assumes the pds_core and pds-vfio-pci modules are already
+loaded.
+
+.. code-block:: bash
+  :name: example-setup-script
+
+  #!/bin/bash
+
+  PF_BUS="0000:60"
+  PF_BDF="0000:60:00.0"
+  VF_BDF="0000:60:00.1"
+
+  # Prevent non-vfio VF driver from probing the VF device
+  echo 0 > /sys/class/pci_bus/$PF_BUS/device/$PF_BDF/sriov_drivers_autoprobe
+
+  # Create single VF for Live Migration via pds_core
+  echo 1 > /sys/bus/pci/drivers/pds_core/$PF_BDF/sriov_numvfs
+
+  # Allow the VF to be bound to the pds-vfio-pci driver
+  echo "pds-vfio-pci" > /sys/class/pci_bus/$PF_BUS/device/$VF_BDF/driver_override
+
+  # Bind the VF to the pds-vfio-pci driver
+  echo "$VF_BDF" > /sys/bus/pci/drivers/pds-vfio-pci/bind
+
+After performing the steps above, a file in /dev/vfio/<iommu_group>
+should have been created.
+
+
+Enabling the driver
+===================
+
+The driver is enabled via the standard kernel configuration system,
+using the make command::
+
+  make oldconfig/menuconfig/etc.
+
+The driver is located in the menu structure at:
+
+  -> Device Drivers
+    -> VFIO Non-Privileged userspace driver framework
+      -> VFIO support for PDS PCI devices
+
+Support
+=======
+
+For general Linux networking support, please use the netdev mailing
+list, which is monitored by Pensando personnel::
+
+  [email protected]
+
+For more specific support needs, please use the Pensando driver support
+email::
+
+  [email protected]

Documentation/networking/device_drivers/ethernet/index.rst

View file

diff --git a/Documentation/networking/device_drivers/ethernet/index.rst b/Documentation/networking/device_drivers/ethernet/index.rst
index 94ecb67..9827e81 100644
--- a/Documentation/networking/device_drivers/ethernet/index.rst
+++ b/Documentation/networking/device_drivers/ethernet/index.rst
@@ -16,6 +16,7 @@ Contents:
    altera/altera_tse
    amd/pds_core
    amd/pds_vdpa
+   amd/pds_vfio_pci
    aquantia/atlantic
    chelsio/cxgb
    cirrus/cs89x0

Documentation/virt/kvm/devices/vfio.rst

View file

diff --git a/Documentation/virt/kvm/devices/vfio.rst b/Documentation/virt/kvm/devices/vfio.rst
index 08b5442..c549143 100644
--- a/Documentation/virt/kvm/devices/vfio.rst
+++ b/Documentation/virt/kvm/devices/vfio.rst
@@ -9,22 +9,34 @@ Device types supported:
   - KVM_DEV_TYPE_VFIO
 
 Only one VFIO instance may be created per VM.  The created device
-tracks VFIO groups in use by the VM and features of those groups
-important to the correctness and acceleration of the VM.  As groups
-are enabled and disabled for use by the VM, KVM should be updated
-about their presence.  When registered with KVM, a reference to the
-VFIO-group is held by KVM.
+tracks VFIO files (group or device) in use by the VM and features
+of those groups/devices important to the correctness and acceleration
+of the VM.  As groups/devices are enabled and disabled for use by the
+VM, KVM should be updated about their presence.  When registered with
+KVM, a reference to the VFIO file is held by KVM.
 
 Groups:
-  KVM_DEV_VFIO_GROUP
-
-KVM_DEV_VFIO_GROUP attributes:
-  KVM_DEV_VFIO_GROUP_ADD: Add a VFIO group to VFIO-KVM device tracking
-	kvm_device_attr.addr points to an int32_t file descriptor
-	for the VFIO group.
-  KVM_DEV_VFIO_GROUP_DEL: Remove a VFIO group from VFIO-KVM device tracking
-	kvm_device_attr.addr points to an int32_t file descriptor
-	for the VFIO group.
+  KVM_DEV_VFIO_FILE
+	alias: KVM_DEV_VFIO_GROUP
+
+KVM_DEV_VFIO_FILE attributes:
+  KVM_DEV_VFIO_FILE_ADD: Add a VFIO file (group/device) to VFIO-KVM device
+	tracking
+
+	kvm_device_attr.addr points to an int32_t file descriptor for the
+	VFIO file.
+
+  KVM_DEV_VFIO_FILE_DEL: Remove a VFIO file (group/device) from VFIO-KVM
+	device tracking
+
+	kvm_device_attr.addr points to an int32_t file descriptor for the
+	VFIO file.
+
+KVM_DEV_VFIO_GROUP (legacy kvm device group restricted to the handling of VFIO group fd):
+  KVM_DEV_VFIO_GROUP_ADD: same as KVM_DEV_VFIO_FILE_ADD for group fd only
+
+  KVM_DEV_VFIO_GROUP_DEL: same as KVM_DEV_VFIO_FILE_DEL for group fd only
+
   KVM_DEV_VFIO_GROUP_SET_SPAPR_TCE: attaches a guest visible TCE table
 	allocated by sPAPR KVM.
 	kvm_device_attr.addr points to a struct::
@@ -40,7 +52,10 @@ KVM_DEV_VFIO_GROUP attributes:
 	- @tablefd is a file descriptor for a TCE table allocated via
 	  KVM_CREATE_SPAPR_TCE.
 
-The GROUP_ADD operation above should be invoked prior to accessing the
+The FILE/GROUP_ADD operation above should be invoked prior to accessing the
 device file descriptor via VFIO_GROUP_GET_DEVICE_FD in order to support
 drivers which require a kvm pointer to be set in their .open_device()
-callback.
+callback.  It is the same for device file descriptor via character device
+open which gets device access via VFIO_DEVICE_BIND_IOMMUFD.  For such file
+descriptors, FILE_ADD should be invoked before VFIO_DEVICE_BIND_IOMMUFD
+to support the drivers mentioned in prior sentence as well.

MAINTAINERS

View file

diff --git a/MAINTAINERS b/MAINTAINERS
index 43050d8..4e3419c 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -22482,6 +22482,13 @@ S:	Maintained
 P:	Documentation/driver-api/vfio-pci-device-specific-driver-acceptance.rst
 F:	drivers/vfio/pci/*/
 
+VFIO PDS PCI DRIVER
+M:	Brett Creeley <[email protected]>
+L:	[email protected]
+S:	Maintained
+F:	Documentation/networking/device_drivers/ethernet/amd/pds_vfio_pci.rst
+F:	drivers/vfio/pci/pds/
+
 VFIO PLATFORM DRIVER
 M:	Eric Auger <[email protected]>
 L:	[email protected]

drivers/gpu/drm/i915/gvt/kvmgt.c

View file

diff --git a/drivers/gpu/drm/i915/gvt/kvmgt.c b/drivers/gpu/drm/i915/gvt/kvmgt.c
index de675d7..9cd9e9d 100644
--- a/drivers/gpu/drm/i915/gvt/kvmgt.c
+++ b/drivers/gpu/drm/i915/gvt/kvmgt.c
@@ -1474,6 +1474,7 @@ static const struct vfio_device_ops intel_vgpu_dev_ops = {
 	.bind_iommufd	= vfio_iommufd_emulated_bind,
 	.unbind_iommufd = vfio_iommufd_emulated_unbind,
 	.attach_ioas	= vfio_iommufd_emulated_attach_ioas,
+	.detach_ioas	= vfio_iommufd_emulated_detach_ioas,
 };
 
 static int intel_vgpu_probe(struct mdev_device *mdev)

drivers/iommu/iommufd/Kconfig

View file

diff --git a/drivers/iommu/iommufd/Kconfig b/drivers/iommu/iommufd/Kconfig
index ada693e..99d4b07 100644
--- a/drivers/iommu/iommufd/Kconfig
+++ b/drivers/iommu/iommufd/Kconfig
@@ -14,8 +14,8 @@ config IOMMUFD
 if IOMMUFD
 config IOMMUFD_VFIO_CONTAINER
 	bool "IOMMUFD provides the VFIO container /dev/vfio/vfio"
-	depends on VFIO && !VFIO_CONTAINER
-	default VFIO && !VFIO_CONTAINER
+	depends on VFIO_GROUP && !VFIO_CONTAINER
+	default VFIO_GROUP && !VFIO_CONTAINER
 	help
 	  IOMMUFD will provide /dev/vfio/vfio instead of VFIO. This relies on
 	  IOMMUFD providing compatibility emulation to give the same ioctls.

drivers/iommu/iommufd/device.c

View file

diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index ed2937a..1d49aad 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -99,6 +99,36 @@ out_group_put:
 EXPORT_SYMBOL_NS_GPL(iommufd_device_bind, IOMMUFD);
 
 /**
+ * iommufd_ctx_has_group - True if any device within the group is bound
+ *                         to the ictx
+ * @ictx: iommufd file descriptor
+ * @group: Pointer to a physical iommu_group struct
+ *
+ * True if any device within the group has been bound to this ictx, ex. via
+ * iommufd_device_bind(), therefore implying ictx ownership of the group.
+ */
+bool iommufd_ctx_has_group(struct iommufd_ctx *ictx, struct iommu_group *group)
+{
+	struct iommufd_object *obj;
+	unsigned long index;
+
+	if (!ictx || !group)
+		return false;
+
+	xa_lock(&ictx->objects);
+	xa_for_each(&ictx->objects, index, obj) {
+		if (obj->type == IOMMUFD_OBJ_DEVICE &&
+		    container_of(obj, struct iommufd_device, obj)->group == group) {
+			xa_unlock(&ictx->objects);
+			return true;
+		}
+	}
+	xa_unlock(&ictx->objects);
+	return false;
+}
+EXPORT_SYMBOL_NS_GPL(iommufd_ctx_has_group, IOMMUFD);
+
+/**
  * iommufd_device_unbind - Undo iommufd_device_bind()
  * @idev: Device returned by iommufd_device_bind()
  *
@@ -113,6 +143,18 @@ void iommufd_device_unbind(struct iommufd_device *idev)
 }
 EXPORT_SYMBOL_NS_GPL(iommufd_device_unbind, IOMMUFD);
 
+struct iommufd_ctx *iommufd_device_to_ictx(struct iommufd_device *idev)
+{
+	return idev->ictx;
+}
+EXPORT_SYMBOL_NS_GPL(iommufd_device_to_ictx, IOMMUFD);
+
+u32 iommufd_device_to_id(struct iommufd_device *idev)
+{
+	return idev->obj.id;
+}
+EXPORT_SYMBOL_NS_GPL(iommufd_device_to_id, IOMMUFD);
+
 static int iommufd_device_setup_msi(struct iommufd_device *idev,
 				    struct iommufd_hw_pagetable *hwpt,
 				    phys_addr_t sw_msi_start)
@@ -441,6 +483,7 @@ iommufd_access_create(struct iommufd_ctx *ictx,
 	iommufd_ctx_get(ictx);
 	iommufd_object_finalize(ictx, &access->obj);
 	*id = access->obj.id;
+	mutex_init(&access->ioas_lock);
 	return access;
 }
 EXPORT_SYMBOL_NS_GPL(iommufd_access_create, IOMMUFD);
@@ -457,26 +500,60 @@ void iommufd_access_destroy(struct iommufd_access *access)
 }
 EXPORT_SYMBOL_NS_GPL(iommufd_access_destroy, IOMMUFD);
 
+void iommufd_access_detach(struct iommufd_access *access)
+{
+	struct iommufd_ioas *cur_ioas = access->ioas;
+
+	mutex_lock(&access->ioas_lock);
+	if (WARN_ON(!access->ioas))
+		goto out;
+	/*
+	 * Set ioas to NULL to block any further iommufd_access_pin_pages().
+	 * iommufd_access_unpin_pages() can continue using access->ioas_unpin.
+	 */
+	access->ioas = NULL;
+
+	if (access->ops->unmap) {
+		mutex_unlock(&access->ioas_lock);
+		access->ops->unmap(access->data, 0, ULONG_MAX);
+		mutex_lock(&access->ioas_lock);
+	}
+	iopt_remove_access(&cur_ioas->iopt, access);
+	refcount_dec(&cur_ioas->obj.users);
+out:
+	access->ioas_unpin = NULL;
+	mutex_unlock(&access->ioas_lock);
+}
+EXPORT_SYMBOL_NS_GPL(iommufd_access_detach, IOMMUFD);
+
 int iommufd_access_attach(struct iommufd_access *access, u32 ioas_id)
 {
 	struct iommufd_ioas *new_ioas;
 	int rc = 0;
 
-	if (access->ioas)
+	mutex_lock(&access->ioas_lock);
+	if (WARN_ON(access->ioas || access->ioas_unpin)) {
+		mutex_unlock(&access->ioas_lock);
 		return -EINVAL;
+	}
 
 	new_ioas = iommufd_get_ioas(access->ictx, ioas_id);
-	if (IS_ERR(new_ioas))
+	if (IS_ERR(new_ioas)) {
+		mutex_unlock(&access->ioas_lock);
 		return PTR_ERR(new_ioas);
+	}
 
 	rc = iopt_add_access(&new_ioas->iopt, access);
 	if (rc) {
+		mutex_unlock(&access->ioas_lock);
 		iommufd_put_object(&new_ioas->obj);
 		return rc;
 	}
 	iommufd_ref_to_users(&new_ioas->obj);
 
 	access->ioas = new_ioas;
+	access->ioas_unpin = new_ioas;
+	mutex_unlock(&access->ioas_lock);
 	return 0;
 }
 EXPORT_SYMBOL_NS_GPL(iommufd_access_attach, IOMMUFD);
@@ -531,8 +608,8 @@ void iommufd_access_notify_unmap(struct io_pagetable *iopt, unsigned long iova,
 void iommufd_access_unpin_pages(struct iommufd_access *access,
 				unsigned long iova, unsigned long length)
 {
-	struct io_pagetable *iopt = &access->ioas->iopt;
 	struct iopt_area_contig_iter iter;
+	struct io_pagetable *iopt;
 	unsigned long last_iova;
 	struct iopt_area *area;
 
@@ -540,6 +617,17 @@ void iommufd_access_unpin_pages(struct iommufd_access *access,
 	    WARN_ON(check_add_overflow(iova, length - 1, &last_iova)))
 		return;
 
+	mutex_lock(&access->ioas_lock);
+	/*
+	 * The driver must be doing something wrong if it calls this before an
+	 * iommufd_access_attach() or after an iommufd_access_detach().
+	 */
+	if (WARN_ON(!access->ioas_unpin)) {
+		mutex_unlock(&access->ioas_lock);
+		return;
+	}
+	iopt = &access->ioas_unpin->iopt;
+
 	down_read(&iopt->iova_rwsem);
 	iopt_for_each_contig_area(&iter, area, iopt, iova, last_iova)
 		iopt_area_remove_access(
@@ -549,6 +637,7 @@ void iommufd_access_unpin_pages(struct iommufd_access *access,
 				min(last_iova, iopt_area_last_iova(area))));
 	WARN_ON(!iopt_area_contig_done(&iter));
 	up_read(&iopt->iova_rwsem);
+	mutex_unlock(&access->ioas_lock);
 }
 EXPORT_SYMBOL_NS_GPL(iommufd_access_unpin_pages, IOMMUFD);
 
@@ -594,8 +683,8 @@ int iommufd_access_pin_pages(struct iommufd_access *access, unsigned long iova,
 			     unsigned long length, struct page **out_pages,
 			     unsigned int flags)
 {
-	struct io_pagetable *iopt = &access->ioas->iopt;
 	struct iopt_area_contig_iter iter;
+	struct io_pagetable *iopt;
 	unsigned long last_iova;
 	struct iopt_area *area;
 	int rc;
@@ -610,6 +699,13 @@ int iommufd_access_pin_pages(struct iommufd_access *access, unsigned long iova,
 	if (check_add_overflow(iova, length - 1, &last_iova))
 		return -EOVERFLOW;
 
+	mutex_lock(&access->ioas_lock);
+	if (!access->ioas) {
+		mutex_unlock(&access->ioas_lock);
+		return -ENOENT;
+	}
+	iopt = &access->ioas->iopt;
+
 	down_read(&iopt->iova_rwsem);
 	iopt_for_each_contig_area(&iter, area, iopt, iova, last_iova) {
 		unsigned long last = min(last_iova, iopt_area_last_iova(area));
@@ -640,6 +736,7 @@ int iommufd_access_pin_pages(struct iommufd_access *access, unsigned long iova,
 	}
 
 	up_read(&iopt->iova_rwsem);
+	mutex_unlock(&access->ioas_lock);
 	return 0;
 
 err_remove:
@@ -654,6 +751,7 @@ err_remove:
 						  iopt_area_last_iova(area))));
 	}
 	up_read(&iopt->iova_rwsem);
+	mutex_unlock(&access->ioas_lock);
 	return rc;
 }
 EXPORT_SYMBOL_NS_GPL(iommufd_access_pin_pages, IOMMUFD);
@@ -673,8 +771,8 @@ EXPORT_SYMBOL_NS_GPL(iommufd_access_pin_pages, IOMMUFD);
 int iommufd_access_rw(struct iommufd_access *access, unsigned long iova,
 		      void *data, size_t length, unsigned int flags)
 {
-	struct io_pagetable *iopt = &access->ioas->iopt;
 	struct iopt_area_contig_iter iter;
+	struct io_pagetable *iopt;
 	struct iopt_area *area;
 	unsigned long last_iova;