From: Lu Baolu baolu.lu@linux.intel.com

These complement the group interfaces used by VFIO and are for use by iommufd. The main difference is that multiple devices in the same group can all share the ownership by passing the same ownership pointer.

Move the common code into shared functions.

Tested-by: Nicolin Chen nicolinc@nvidia.com Signed-off-by: Lu Baolu baolu.lu@linux.intel.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com --- drivers/iommu/iommu.c | 124 +++++++++++++++++++++++++++++++++--------- include/linux/iommu.h | 12 ++++ 2 files changed, 110 insertions(+), 26 deletions(-)

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 6ca377f4fbf9e9..4cb14e44e40f83 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -3108,41 +3108,52 @@ static int __iommu_group_alloc_blocking_domain(struct iommu_group *group) return 0; }

+static int __iommu_take_dma_ownership(struct iommu_group *group, void *owner) +{ + int ret; + + if (WARN_ON(!owner)) + return -EINVAL; + + if ((group->domain && group->domain != group->default_domain) || + !xa_empty(&group->pasid_array)) + return -EBUSY; + + ret = __iommu_group_alloc_blocking_domain(group); + if (ret) + return ret; + ret = __iommu_group_set_domain(group, group->blocking_domain); + if (ret) + return ret; + + group->owner = owner; + group->owner_cnt++; + return 0; +} + /** * iommu_group_claim_dma_owner() - Set DMA ownership of a group * @group: The group. * @owner: Caller specified pointer. Used for exclusive ownership. * - * This is to support backward compatibility for vfio which manages - * the dma ownership in iommu_group level. New invocations on this - * interface should be prohibited. + * This is to support backward compatibility for vfio which manages the dma + * ownership in iommu_group level. New invocations on this interface should be + * prohibited. Only a single owner may exist for a group. */ int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner) { int ret = 0;

+ if (WARN_ON(!owner)) + return -EINVAL; + mutex_lock(&group->mutex); if (group->owner_cnt) { ret = -EPERM; goto unlock_out; - } else { - if ((group->domain && group->domain != group->default_domain) || - !xa_empty(&group->pasid_array)) { - ret = -EBUSY; - goto unlock_out; - } - - ret = __iommu_group_alloc_blocking_domain(group); - if (ret) - goto unlock_out; - - ret = __iommu_group_set_domain(group, group->blocking_domain); - if (ret) - goto unlock_out; - group->owner = owner; }

- group->owner_cnt++; + ret = __iommu_take_dma_ownership(group, owner); unlock_out: mutex_unlock(&group->mutex);

@@ -3151,30 +3162,91 @@ int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner) EXPORT_SYMBOL_GPL(iommu_group_claim_dma_owner);

/** - * iommu_group_release_dma_owner() - Release DMA ownership of a group - * @group: The group. + * iommu_device_claim_dma_owner() - Set DMA ownership of a device + * @dev: The device. + * @owner: Caller specified pointer. Used for exclusive ownership. * - * Release the DMA ownership claimed by iommu_group_claim_dma_owner(). + * Claim the DMA ownership of a device. Multiple devices in the same group may + * concurrently claim ownership if they present the same owner value. Returns 0 + * on success and error code on failure */ -void iommu_group_release_dma_owner(struct iommu_group *group) +int iommu_device_claim_dma_owner(struct device *dev, void *owner) { - int ret; + struct iommu_group *group = iommu_group_get(dev); + int ret = 0; + + if (!group) + return -ENODEV;

mutex_lock(&group->mutex); + if (group->owner_cnt) { + if (group->owner != owner) { + ret = -EPERM; + goto unlock_out; + } + group->owner_cnt++; + goto unlock_out; + } + + ret = __iommu_take_dma_ownership(group, owner); +unlock_out: + mutex_unlock(&group->mutex); + iommu_group_put(group); + + return ret; +} +EXPORT_SYMBOL_GPL(iommu_device_claim_dma_owner); + +static void __iommu_release_dma_ownership(struct iommu_group *group) +{ + int ret; + if (WARN_ON(!group->owner_cnt || !group->owner || !xa_empty(&group->pasid_array))) - goto unlock_out; + return;

group->owner_cnt = 0; group->owner = NULL; ret = __iommu_group_set_domain(group, group->default_domain); WARN(ret, "iommu driver failed to attach the default domain"); +}

-unlock_out: +/** + * iommu_group_release_dma_owner() - Release DMA ownership of a group + * @group: The group. + * + * Release the DMA ownership claimed by iommu_group_claim_dma_owner(). + */ +void iommu_group_release_dma_owner(struct iommu_group *group) +{ + mutex_lock(&group->mutex); + __iommu_release_dma_ownership(group); mutex_unlock(&group->mutex); } EXPORT_SYMBOL_GPL(iommu_group_release_dma_owner);

+/** + * iommu_device_release_dma_owner() - Release DMA ownership of a device + * @group: The device. + * + * Release the DMA ownership claimed by iommu_device_claim_dma_owner(). + */ +void iommu_device_release_dma_owner(struct device *dev) +{ + struct iommu_group *group = iommu_group_get(dev); + + mutex_lock(&group->mutex); + if (group->owner_cnt > 1) { + group->owner_cnt--; + goto unlock_out; + } + __iommu_release_dma_ownership(group); +unlock_out: + mutex_unlock(&group->mutex); + iommu_group_put(group); +} +EXPORT_SYMBOL_GPL(iommu_device_release_dma_owner); + /** * iommu_group_dma_owner_claimed() - Query group dma ownership status * @group: The group. diff --git a/include/linux/iommu.h b/include/linux/iommu.h index a09fd32d8cc273..1690c334e51631 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -707,6 +707,9 @@ int iommu_group_claim_dma_owner(struct iommu_group *group, void *owner); void iommu_group_release_dma_owner(struct iommu_group *group); bool iommu_group_dma_owner_claimed(struct iommu_group *group);

+int iommu_device_claim_dma_owner(struct device *dev, void *owner); +void iommu_device_release_dma_owner(struct device *dev); + struct iommu_domain *iommu_sva_domain_alloc(struct device *dev, struct mm_struct *mm); int iommu_attach_device_pasid(struct iommu_domain *domain, @@ -1064,6 +1067,15 @@ static inline bool iommu_group_dma_owner_claimed(struct iommu_group *group) return false; }

+static inline void iommu_device_release_dma_owner(struct device *dev) +{ +} + +static inline int iommu_device_claim_dma_owner(struct device *dev, void *owner) +{ + return -ENODEV; +} + static inline struct iommu_domain * iommu_sva_domain_alloc(struct device *dev, struct mm_struct *mm) {

From: Kevin Tian kevin.tian@intel.com

Add iommufd into the documentation tree, and supply initial documentation. Much of this is linked from code comments by kdoc.

Tested-by: Nicolin Chen nicolinc@nvidia.com Signed-off-by: Kevin Tian kevin.tian@intel.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com --- Documentation/userspace-api/index.rst | 1 + Documentation/userspace-api/iommufd.rst | 222 ++++++++++++++++++++++++ 2 files changed, 223 insertions(+) create mode 100644 Documentation/userspace-api/iommufd.rst

diff --git a/Documentation/userspace-api/index.rst b/Documentation/userspace-api/index.rst index c78da9ce0ec44e..f16337bdb8520f 100644 --- a/Documentation/userspace-api/index.rst +++ b/Documentation/userspace-api/index.rst @@ -25,6 +25,7 @@ place where this information is gathered. ebpf/index ioctl/index iommu + iommufd media/index netlink/index sysfs-platform_profile diff --git a/Documentation/userspace-api/iommufd.rst b/Documentation/userspace-api/iommufd.rst new file mode 100644 index 00000000000000..64a135f3055adc --- /dev/null +++ b/Documentation/userspace-api/iommufd.rst @@ -0,0 +1,222 @@ +.. SPDX-License-Identifier: GPL-2.0+ + +======= +IOMMUFD +======= + +:Author: Jason Gunthorpe +:Author: Kevin Tian + +Overview +======== + +IOMMUFD is the user API to control the IOMMU subsystem as it relates to managing +IO page tables from userspace using file descriptors. It intends to be general +and consumable by any driver that wants to expose DMA to userspace. These +drivers are eventually expected to deprecate any internal IOMMU logic if exists +(e.g. vfio_iommu_type1.c). + +At minimum iommufd provides universal support of managing I/O address spaces and +I/O page tables for all IOMMUs, with room in the design to add non-generic +features to cater to specific hardware functionality. + +In this context the capital letter (IOMMUFD) refers to the subsystem while the +small letter (iommufd) refers to the file descriptors created via /dev/iommu for +use by userspace. + +Key Concepts +============ + +User Visible Objects +-------------------- + +Following IOMMUFD objects are exposed to userspace: + +- IOMMUFD_OBJ_IOAS, representing an I/O address space (IOAS), allowing map/unmap + of user space memory into ranges of I/O Virtual Address (IOVA). + + The IOAS is a functional replacement for the VFIO container, and like the VFIO + container it copies an IOVA map to a list of iommu_domains held within it. + +- IOMMUFD_OBJ_DEVICE, representing a device that is bound to iommufd by an + external driver. + +- IOMMUFD_OBJ_HW_PAGETABLE, representing an actual hardware I/O page table + (i.e. a single struct iommu_domain) managed by the iommu driver. + + The IOAS has a list of HW_PAGETABLES that share the same IOVA mapping and + it will synchronize its mapping with each member HW_PAGETABLE. + +All user-visible objects are destroyed via the IOMMU_DESTROY uAPI. + +The diagram below shows relationship between user-visible objects and kernel +datastructures (external to iommufd), with numbers referred to operations +creating the objects and links:: + + _________________________________________________________ + | iommufd | + | [1] | + | _________________ | + | | | | + | | | | + | | | | + | | | | + | | | | + | | | | + | | | [3] [2] | + | | | ____________ __________ | + | | IOAS |<--| |<------| | | + | | | |HW_PAGETABLE| | DEVICE | | + | | | |____________| |__________| | + | | | | | | + | | | | | | + | | | | | | + | | | | | | + | | | | | | + | |_________________| | | | + | | | | | + |_________|___________________|___________________|_______| + | | | + | _____v______ _______v_____ + | PFN storage | | | | + |------------>|iommu_domain| |struct device| + |____________| |_____________| + +1. IOMMUFD_OBJ_IOAS is created via the IOMMU_IOAS_ALLOC uAPI. An iommufd can + hold multiple IOAS objects. IOAS is the most generic object and does not + expose interfaces that are specific to single IOMMU drivers. All operations + on the IOAS must operate equally on each of the iommu_domains inside of it. + +2. IOMMUFD_OBJ_DEVICE is created when an external driver calls the IOMMUFD kAPI + to bind a device to an iommufd. The driver is expected to implement proper a + set of ioctls to allow userspace to initiate the binding operation. + Successful completion of this operation establishes the desired DMA ownership + over the device. The driver must also set the driver_managed_dma flag and + must not touch the device until this operation succeeds. + +3. IOMMUFD_OBJ_HW_PAGETABLE is created when an external driver calls the IOMMUFD + kAPI to attach a bound device to an IOAS. Similarly the external driver uAPI + allows userspace to initiate the attaching operation. If a compatible + pagetable already exists then it is reused for the attachment. Otherwise a + new pagetable object and iommu_domain is created. Successful completion of + this operation sets up the linkages among IOAS, device and iommu_domain. Once + this completes the device could do DMA. + + Every iommu_domain inside the IOAS is also represented to userspace as a + HW_PAGETABLE object. + + .. note:: + + Future IOMMUFD updates will provide an API to create and manipulate the + HW_PAGETABLE directly. + +A device can only bind to an iommufd due to DMA ownership claim and attach to at +most one IOAS object (no support of PASID yet). + +Currently only PCI device is allowed to use IOMMUFD. + +Kernel Datastructure +-------------------- + +User visible objects are backed by following datastructures: + +- iommufd_ioas for IOMMUFD_OBJ_IOAS. +- iommufd_device for IOMMUFD_OBJ_DEVICE. +- iommufd_hw_pagetable for IOMMUFD_OBJ_HW_PAGETABLE. + +Several terminologies when looking at these datastructures: + +- Automatic domain - refers to an iommu domain created automatically when + attaching a device to an IOAS object. This is compatible to the semantics of + VFIO type1. + +- Manual domain - refers to an iommu domain designated by the user as the + target pagetable to be attached to by a device. Though currently there are + no uAPIs to directly create such domain, the datastructure and algorithms + are ready for handling that use case. + +- In-kernel user - refers to something like a VFIO mdev that is using the + IOMMUFD access interface to access the IOAS. This starts by creating an + iommufd_access object that is similar to the domain binding a physical device + would do. The access object will then allow converting IOVA ranges into struct + page * lists, or doing direct read/write to an IOVA. + +iommufd_ioas serves as the metadata datastructure to manage how IOVA ranges are +mapped to memory pages, composed of: + +- struct io_pagetable holding the IOVA map +- struct iopt_areas representing populated portions of IOVA +- struct iopt_pages representing the storage of PFNs +- struct iommu_domain representing the IO page table in the IOMMU +- struct iopt_pages_access representing in-kernel users of PFNs +- struct xarray pinned_pfns holding a list of pages pinned by in-kernel users + +Each iopt_pages represents a logical linear array of full PFNs. The PFNs are +ultimately derived from userspave VAs via an mm_struct. Once they have been +pinned the PFN is stored in IOPTEs of an iommu_domain or inside the pinned_pages +xarray if they have been pinned through an iommufd_access. + +PFN have to be copied between all combinations of storage locations, depending +on what domains are present and what kinds of in-kernel "software access" users +exists. The mechanism ensures that a page is pinned only once. + +An io_pagetable is composed of iopt_areas pointing at iopt_pages, along with a +list of iommu_domains that mirror the IOVA to PFN map. + +Multiple io_pagetable-s, through their iopt_area-s, can share a single +iopt_pages which avoids multi-pinning and double accounting of page +consumption. + +iommufd_ioas is sharable between subsystems, e.g. VFIO and VDPA, as long as +devices managed by different subsystems are bound to a same iommufd. + +IOMMUFD User API +================ + +.. kernel-doc:: include/uapi/linux/iommufd.h + +IOMMUFD Kernel API +================== + +The IOMMUFD kAPI is device-centric with group-related tricks managed behind the +scene. This allows the external drivers calling such kAPI to implement a simple +device-centric uAPI for connecting its device to an iommufd, instead of +explicitly imposing the group semantics in its uAPI as VFIO does. + +.. kernel-doc:: drivers/iommu/iommufd/device.c + :export: + +VFIO and IOMMUFD +---------------- + +Connecting a VFIO device to iommufd can be done in two ways. + +First is a VFIO compatible way by directly implementing the /dev/vfio/vfio +container IOCTLs by mapping them into io_pagetable operations. Doing so allows +the use of iommufd in legacy VFIO applications by symlinking /dev/vfio/vfio to +/dev/iommufd or extending VFIO to SET_CONTAINER using an iommufd instead of a +container fd. + +The second approach directly extends VFIO to support a new set of device-centric +user API based on aforementioned IOMMUFD kernel API. It requires userspace +change but better matches the IOMMUFD API semantics and easier to support new +iommufd features when comparing it to the first approach. + +Currently both approaches are still work-in-progress. + +There are still a few gaps to be resolved to catch up with VFIO type1, as +documented in iommufd_vfio_check_extension(). + +Future TODOs +============ + +Currently IOMMUFD supports only kernel-managed I/O page table, similar to VFIO +type1. New features on the radar include: + + - Binding iommu_domain's to PASID/SSID + - Userspace page tables, for ARM, x86 and S390 + - Kernel bypass'd invalidation of user page tables + - Re-use of the KVM page table in the IOMMU + - Dirty page tracking in the IOMMU + - Runtime Increase/Decrease of IOPTE size + - PRI support with faults resolved in userspace

The top of the data structure provides an IO Address Space (IOAS) that is similar to a VFIO container. The IOAS allows map/unmap of memory into ranges of IOVA called iopt_areas. Multiple IOMMU domains (IO page tables) and in-kernel accesses (like VFIO mdevs) can be attached to the IOAS to access the PFNs that those IOVA areas cover.

The IO Address Space (IOAS) datastructure is composed of: - struct io_pagetable holding the IOVA map - struct iopt_areas representing populated portions of IOVA - struct iopt_pages representing the storage of PFNs - struct iommu_domain representing each IO page table in the system IOMMU - struct iopt_pages_access representing in-kernel accesses of PFNs (ie VFIO mdevs) - struct xarray pinned_pfns holding a list of pages pinned by in-kernel accesses

This patch introduces the lowest part of the datastructure - the movement of PFNs in a tiered storage scheme: 1) iopt_pages::pinned_pfns xarray 2) Multiple iommu_domains 3) The origin of the PFNs, i.e. the userspace pointer

PFN have to be copied between all combinations of tiers, depending on the configuration.

The interface is an iterator called a 'pfn_reader' which determines which tier each PFN is stored and loads it into a list of PFNs held in a struct pfn_batch.

Each step of the iterator will fill up the pfn_batch, then the caller can use the pfn_batch to send the PFNs to the required destination. Repeating this loop will read all the PFNs in an IOVA range.

The pfn_reader and pfn_batch also keep track of the pinned page accounting.

While PFNs are always stored and accessed as full PAGE_SIZE units the iommu_domain tier can store with a sub-page offset/length to support IOMMUs with a smaller IOPTE size than PAGE_SIZE.

Tested-by: Nicolin Chen nicolinc@nvidia.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com --- .clang-format | 1 + drivers/iommu/iommufd/Makefile | 3 +- drivers/iommu/iommufd/double_span.h | 98 +++ drivers/iommu/iommufd/io_pagetable.h | 109 +++ drivers/iommu/iommufd/iommufd_private.h | 24 + drivers/iommu/iommufd/pages.c | 999 ++++++++++++++++++++++++ include/linux/iommufd.h | 7 + 7 files changed, 1240 insertions(+), 1 deletion(-) create mode 100644 drivers/iommu/iommufd/double_span.h create mode 100644 drivers/iommu/iommufd/io_pagetable.h create mode 100644 drivers/iommu/iommufd/pages.c

diff --git a/.clang-format b/.clang-format index 96d07786dcfb46..501241f8977664 100644 --- a/.clang-format +++ b/.clang-format @@ -440,6 +440,7 @@ ForEachMacros: - 'inet_lhash2_for_each_icsk' - 'inet_lhash2_for_each_icsk_continue' - 'inet_lhash2_for_each_icsk_rcu' + - 'interval_tree_for_each_double_span' - 'interval_tree_for_each_span' - 'intlist__for_each_entry' - 'intlist__for_each_entry_safe' diff --git a/drivers/iommu/iommufd/Makefile b/drivers/iommu/iommufd/Makefile index a07a8cffe937c6..05a0e91e30afad 100644 --- a/drivers/iommu/iommufd/Makefile +++ b/drivers/iommu/iommufd/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only iommufd-y := \ - main.o + main.o \ + pages.o

obj-$(CONFIG_IOMMUFD) += iommufd.o diff --git a/drivers/iommu/iommufd/double_span.h b/drivers/iommu/iommufd/double_span.h new file mode 100644 index 00000000000000..1d7fa31f9b6cc2 --- /dev/null +++ b/drivers/iommu/iommufd/double_span.h @@ -0,0 +1,98 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2022, NVIDIA CORPORATION & AFFILIATES. + */ +#ifndef __IOMMUFD_DOUBLE_SPAN_H +#define __IOMMUFD_DOUBLE_SPAN_H + +#include <linux/interval_tree.h> + +struct interval_tree_double_span_iter { + struct rb_root_cached *itrees[2]; + struct interval_tree_span_iter spans[2]; + union { + unsigned long start_hole; + unsigned long start_used; + }; + union { + unsigned long last_hole; + unsigned long last_used; + }; + /* 0 = hole, 1 = used span[0], 2 = used span[1], -1 done iteration */ + int is_used; +}; + +static void interval_tree_double_span_iter_update( + struct interval_tree_double_span_iter *iter) +{ + unsigned long last_hole = ULONG_MAX; + unsigned int i; + + for (i = 0; i != ARRAY_SIZE(iter->spans); i++) { + if (interval_tree_span_iter_done(&iter->spans[i])) { + iter->is_used = -1; + return; + } + + if (iter->spans[i].is_hole) { + last_hole = min(last_hole, iter->spans[i].last_hole); + continue; + } + + iter->is_used = i + 1; + iter->start_used = iter->spans[i].start_used; + iter->last_used = min(iter->spans[i].last_used, last_hole); + return; + } + + iter->is_used = 0; + iter->start_hole = iter->spans[0].start_hole; + iter->last_hole = + min(iter->spans[0].last_hole, iter->spans[1].last_hole); +} + +static void interval_tree_double_span_iter_first( + struct interval_tree_double_span_iter *iter, + struct rb_root_cached *itree1, struct rb_root_cached *itree2, + unsigned long first_index, unsigned long last_index) +{ + unsigned int i; + + iter->itrees[0] = itree1; + iter->itrees[1] = itree2; + for (i = 0; i != ARRAY_SIZE(iter->spans); i++) + interval_tree_span_iter_first(&iter->spans[i], iter->itrees[i], + first_index, last_index); + interval_tree_double_span_iter_update(iter); +} + +static void +interval_tree_double_span_iter_next(struct interval_tree_double_span_iter *iter) +{ + unsigned int i; + + if (iter->is_used == -1 || + iter->last_hole == iter->spans[0].last_index) { + iter->is_used = -1; + return; + } + + for (i = 0; i != ARRAY_SIZE(iter->spans); i++) + interval_tree_span_iter_advance( + &iter->spans[i], iter->itrees[i], iter->last_hole + 1); + interval_tree_double_span_iter_update(iter); +} + +static inline bool +interval_tree_double_span_iter_done(struct interval_tree_double_span_iter *state) +{ + return state->is_used == -1; +} + +#define interval_tree_for_each_double_span(span, itree1, itree2, first_index, \ + last_index) \ + for (interval_tree_double_span_iter_first(span, itree1, itree2, \ + first_index, last_index); \ + !interval_tree_double_span_iter_done(span); \ + interval_tree_double_span_iter_next(span)) + +#endif diff --git a/drivers/iommu/iommufd/io_pagetable.h b/drivers/iommu/iommufd/io_pagetable.h new file mode 100644 index 00000000000000..b74bf01ffc52c2 --- /dev/null +++ b/drivers/iommu/iommufd/io_pagetable.h @@ -0,0 +1,109 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES. + * + */ +#ifndef __IO_PAGETABLE_H +#define __IO_PAGETABLE_H + +#include <linux/interval_tree.h> +#include <linux/mutex.h> +#include <linux/kref.h> +#include <linux/xarray.h> + +#include "iommufd_private.h" + +struct iommu_domain; + +/* + * Each io_pagetable is composed of intervals of areas which cover regions of + * the iova that are backed by something. iova not covered by areas is not + * populated in the page table. Each area is fully populated with pages. + * + * iovas are in byte units, but must be iopt->iova_alignment aligned. + * + * pages can be NULL, this means some other thread is still working on setting + * up or tearing down the area. When observed under the write side of the + * domain_rwsem a NULL pages must mean the area is still being setup and no + * domains are filled. + * + * storage_domain points at an arbitrary iommu_domain that is holding the PFNs + * for this area. It is locked by the pages->mutex. This simplifies the locking + * as the pages code can rely on the storage_domain without having to get the + * iopt->domains_rwsem. + * + * The io_pagetable::iova_rwsem protects node + * The iopt_pages::mutex protects pages_node + * iopt and immu_prot are immutable + * The pages::mutex protects num_accesses + */ +struct iopt_area { + struct interval_tree_node node; + struct interval_tree_node pages_node; + struct io_pagetable *iopt; + struct iopt_pages *pages; + struct iommu_domain *storage_domain; + /* How many bytes into the first page the area starts */ + unsigned int page_offset; + /* IOMMU_READ, IOMMU_WRITE, etc */ + int iommu_prot; + unsigned int num_accesses; +}; + +static inline unsigned long iopt_area_index(struct iopt_area *area) +{ + return area->pages_node.start; +} + +static inline unsigned long iopt_area_last_index(struct iopt_area *area) +{ + return area->pages_node.last; +} + +static inline unsigned long iopt_area_iova(struct iopt_area *area) +{ + return area->node.start; +} + +static inline unsigned long iopt_area_last_iova(struct iopt_area *area) +{ + return area->node.last; +} + +enum { + IOPT_PAGES_ACCOUNT_NONE = 0, + IOPT_PAGES_ACCOUNT_USER = 1, + IOPT_PAGES_ACCOUNT_MM = 2, +}; + +/* + * This holds a pinned page list for multiple areas of IO address space. The + * pages always originate from a linear chunk of userspace VA. Multiple + * io_pagetable's, through their iopt_area's, can share a single iopt_pages + * which avoids multi-pinning and double accounting of page consumption. + * + * indexes in this structure are measured in PAGE_SIZE units, are 0 based from + * the start of the uptr and extend to npages. pages are pinned dynamically + * according to the intervals in the access_itree and domains_itree, npinned + * records the current number of pages pinned. + */ +struct iopt_pages { + struct kref kref; + struct mutex mutex; + size_t npages; + size_t npinned; + size_t last_npinned; + struct task_struct *source_task; + struct mm_struct *source_mm; + struct user_struct *source_user; + void __user *uptr; + bool writable:1; + u8 account_mode; + + struct xarray pinned_pfns; + /* Of iopt_pages_access::node */ + struct rb_root_cached access_itree; + /* Of iopt_area::pages_node */ + struct rb_root_cached domains_itree; +}; + +#endif diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index d523e7967b1440..6ed6f99ee439fa 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -14,6 +14,30 @@ struct iommufd_ctx { struct xarray objects; };

+/* + * The IOVA to PFN map. The mapper automatically copies the PFNs into multiple + * domains and permits sharing of PFNs between io_pagetable instances. This + * supports both a design where IOAS's are 1:1 with a domain (eg because the + * domain is HW customized), or where the IOAS is 1:N with multiple generic + * domains. The io_pagetable holds an interval tree of iopt_areas which point + * to shared iopt_pages which hold the pfns mapped to the page table. + * + * The locking order is domains_rwsem -> iova_rwsem -> pages::mutex + */ +struct io_pagetable { + struct rw_semaphore domains_rwsem; + struct xarray domains; + unsigned int next_domain_id; + + struct rw_semaphore iova_rwsem; + struct rb_root_cached area_itree; + /* IOVA that cannot become reserved, struct iopt_allowed */ + struct rb_root_cached allowed_itree; + /* IOVA that cannot be allocated, struct iopt_reserved */ + struct rb_root_cached reserved_itree; + u8 disable_large_pages; +}; + struct iommufd_ucmd { struct iommufd_ctx *ictx; void __user *ubuffer; diff --git a/drivers/iommu/iommufd/pages.c b/drivers/iommu/iommufd/pages.c new file mode 100644 index 00000000000000..87e2bd78ae91e8 --- /dev/null +++ b/drivers/iommu/iommufd/pages.c @@ -0,0 +1,999 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES. + * + * The iopt_pages is the center of the storage and motion of PFNs. Each + * iopt_pages represents a logical linear array of full PFNs. The array is 0 + * based and has npages in it. Accessors use 'index' to refer to the entry in + * this logical array, regardless of its storage location. + * + * PFNs are stored in a tiered scheme: + * 1) iopt_pages::pinned_pfns xarray + * 2) An iommu_domain + * 3) The origin of the PFNs, i.e. the userspace pointer + * + * PFN have to be copied between all combinations of tiers, depending on the + * configuration. + * + * When a PFN is taken out of the userspace pointer it is pinned exactly once. + * The storage locations of the PFN's index are tracked in the two interval + * trees. If no interval includes the index then it is not pinned. + * + * If access_itree includes the PFN's index then an in-kernel access has + * requested the page. The PFN is stored in the xarray so other requestors can + * continue to find it. + * + * If the domains_itree includes the PFN's index then an iommu_domain is storing + * the PFN and it can be read back using iommu_iova_to_phys(). To avoid + * duplicating storage the xarray is not used if only iommu_domains are using + * the PFN's index. + * + * As a general principle this is designed so that destroy never fails. This + * means removing an iommu_domain or releasing a in-kernel access will not fail + * due to insufficient memory. In practice this means some cases have to hold + * PFNs in the xarray even though they are also being stored in an iommu_domain. + * + * While the iopt_pages can use an iommu_domain as storage, it does not have an + * IOVA itself. Instead the iopt_area represents a range of IOVA and uses the + * iopt_pages as the PFN provider. Multiple iopt_areas can share the iopt_pages + * and reference their own slice of the PFN array, with sub page granularity. + * + * In this file the term 'last' indicates an inclusive and closed interval, eg + * [0,0] refers to a single PFN. 'end' means an open range, eg [0,0) refers to + * no PFNs. + * + * Be cautious of overflow, an IOVA can go all the way up to U64_MAX, so + * last_iova + 1 can overflow. An iopt_pages index will always be much less than + * ULONG_MAX< so last_index + 1 cannot overflow. + */ +#include <linux/overflow.h> +#include <linux/slab.h> +#include <linux/iommu.h> +#include <linux/sched/mm.h> +#include <linux/highmem.h> +#include <linux/kthread.h> +#include <linux/iommufd.h> + +#include "io_pagetable.h" +#include "double_span.h" + +#define TEMP_MEMORY_LIMIT 65536 +#define BATCH_BACKUP_SIZE 32 + +/* + * More memory makes pin_user_pages() and the batching more efficient, but as + * this is only a performance optimization don't try too hard to get it. A 64k + * allocation can hold about 26M of 4k pages and 13G of 2M pages in an + * pfn_batch. Various destroy paths cannot fail and provide a small amount of + * stack memory as a backup contingency. If backup_len is given this cannot + * fail. + */ +static void *temp_kmalloc(size_t *size, void *backup, size_t backup_len) +{ + void *res; + + if (WARN_ON(*size == 0)) + return NULL; + + if (*size < backup_len) + return backup; + *size = min_t(size_t, *size, TEMP_MEMORY_LIMIT); + res = kmalloc(*size, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); + if (res) + return res; + *size = PAGE_SIZE; + if (backup_len) { + res = kmalloc(*size, GFP_KERNEL | __GFP_NOWARN | __GFP_NORETRY); + if (res) + return res; + *size = backup_len; + return backup; + } + return kmalloc(*size, GFP_KERNEL); +} + +static void iopt_pages_add_npinned(struct iopt_pages *pages, size_t npages) +{ + pages->npinned += npages; +} + +static void iopt_pages_sub_npinned(struct iopt_pages *pages, size_t npages) +{ + pages->npinned -= npages; +} + +static void iopt_pages_err_unpin(struct iopt_pages *pages, + unsigned long start_index, + unsigned long last_index, + struct page **page_list) +{ + unsigned long npages = last_index - start_index + 1; + + unpin_user_pages(page_list, npages); + iopt_pages_sub_npinned(pages, npages); +} + +/* + * index is the number of PAGE_SIZE units from the start of the area's + * iopt_pages. If the iova is sub page-size then the area has an iova that + * covers a portion of the first and last pages in the range. + */ +static unsigned long iopt_area_index_to_iova(struct iopt_area *area, + unsigned long index) +{ + index -= iopt_area_index(area); + if (index == 0) + return iopt_area_iova(area); + return iopt_area_iova(area) - area->page_offset + index * PAGE_SIZE; +} + +static unsigned long iopt_area_index_to_iova_last(struct iopt_area *area, + unsigned long index) +{ + if (index == iopt_area_last_index(area)) + return iopt_area_last_iova(area); + return iopt_area_iova(area) - area->page_offset + + (index - iopt_area_index(area) + 1) * PAGE_SIZE - 1; +} + +static void iommu_unmap_nofail(struct iommu_domain *domain, unsigned long iova, + size_t size) +{ + size_t ret; + + ret = iommu_unmap(domain, iova, size); + /* + * It is a logic error in this code or a driver bug if the IOMMU unmaps + * something other than exactly as requested. This implies that the + * iommu driver may not fail unmap for reasons beyond bad agruments. + * Particularly, the iommu driver may not do a memory allocation on the + * unmap path. + */ + WARN_ON(ret != size); +} + +static struct iopt_area *iopt_pages_find_domain_area(struct iopt_pages *pages, + unsigned long index) +{ + struct interval_tree_node *node; + + node = interval_tree_iter_first(&pages->domains_itree, index, index); + if (!node) + return NULL; + return container_of(node, struct iopt_area, pages_node); +} + +/* + * A simple datastructure to hold a vector of PFNs, optimized for contiguous + * PFNs. This is used as a temporary holding memory for shuttling pfns from one + * place to another. Generally everything is made more efficient if operations + * work on the largest possible grouping of pfns. eg fewer lock/unlock cycles, + * better cache locality, etc + */ +struct pfn_batch { + unsigned long *pfns; + u16 *npfns; + unsigned int array_size; + unsigned int end; + unsigned int total_pfns; +}; + +static void batch_clear(struct pfn_batch *batch) +{ + batch->total_pfns = 0; + batch->end = 0; + batch->pfns[0] = 0; + batch->npfns[0] = 0; +} + +/* + * Carry means we carry a portion of the final hugepage over to the front of the + * batch + */ +static void batch_clear_carry(struct pfn_batch *batch, unsigned int keep_pfns) +{ + if (!keep_pfns) + return batch_clear(batch); + + batch->total_pfns = keep_pfns; + batch->npfns[0] = keep_pfns; + batch->pfns[0] = batch->pfns[batch->end - 1] + + (batch->npfns[batch->end - 1] - keep_pfns); + batch->end = 0; +} + +static void batch_skip_carry(struct pfn_batch *batch, unsigned int skip_pfns) +{ + if (!batch->total_pfns) + return; + skip_pfns = min(batch->total_pfns, skip_pfns); + batch->pfns[0] += skip_pfns; + batch->npfns[0] -= skip_pfns; + batch->total_pfns -= skip_pfns; +} + +static int __batch_init(struct pfn_batch *batch, size_t max_pages, void *backup, + size_t backup_len) +{ + const size_t elmsz = sizeof(*batch->pfns) + sizeof(*batch->npfns); + size_t size = max_pages * elmsz; + + batch->pfns = temp_kmalloc(&size, backup, backup_len); + if (!batch->pfns) + return -ENOMEM; + batch->array_size = size / elmsz; + batch->npfns = (u16 *)(batch->pfns + batch->array_size); + batch_clear(batch); + return 0; +} + +static int batch_init(struct pfn_batch *batch, size_t max_pages) +{ + return __batch_init(batch, max_pages, NULL, 0); +} + +static void batch_init_backup(struct pfn_batch *batch, size_t max_pages, + void *backup, size_t backup_len) +{ + __batch_init(batch, max_pages, backup, backup_len); +} + +static void batch_destroy(struct pfn_batch *batch, void *backup) +{ + if (batch->pfns != backup) + kfree(batch->pfns); +} + +/* true if the pfn could be added, false otherwise */ +static bool batch_add_pfn(struct pfn_batch *batch, unsigned long pfn) +{ + /* FIXME: U16 is too small */ + if (batch->end && + pfn == batch->pfns[batch->end - 1] + batch->npfns[batch->end - 1] && + batch->npfns[batch->end - 1] != U16_MAX) { + batch->npfns[batch->end - 1]++; + batch->total_pfns++; + return true; + } + if (batch->end == batch->array_size) + return false; + batch->total_pfns++; + batch->pfns[batch->end] = pfn; + batch->npfns[batch->end] = 1; + batch->end++; + return true; +} + +/* + * Fill the batch with pfns from the domain. When the batch is full, or it + * reaches last_index, the function will return. The caller should use + * batch->total_pfns to determine the starting point for the next iteration. + */ +static void batch_from_domain(struct pfn_batch *batch, + struct iommu_domain *domain, + struct iopt_area *area, unsigned long start_index, + unsigned long last_index) +{ + unsigned int page_offset = 0; + unsigned long iova; + phys_addr_t phys; + + iova = iopt_area_index_to_iova(area, start_index); + if (start_index == iopt_area_index(area)) + page_offset = area->page_offset; + while (start_index <= last_index) { + /* + * This is pretty slow, it would be nice to get the page size + * back from the driver, or have the driver directly fill the + * batch. + */ + phys = iommu_iova_to_phys(domain, iova) - page_offset; + if (!batch_add_pfn(batch, PHYS_PFN(phys))) + return; + iova += PAGE_SIZE - page_offset; + page_offset = 0; + start_index++; + } +} + +static struct page **raw_pages_from_domain(struct iommu_domain *domain, + struct iopt_area *area, + unsigned long start_index, + unsigned long last_index, + struct page **out_pages) +{ + unsigned int page_offset = 0; + unsigned long iova; + phys_addr_t phys; + + iova = iopt_area_index_to_iova(area, start_index); + if (start_index == iopt_area_index(area)) + page_offset = area->page_offset; + while (start_index <= last_index) { + phys = iommu_iova_to_phys(domain, iova) - page_offset; + *(out_pages++) = pfn_to_page(PHYS_PFN(phys)); + iova += PAGE_SIZE - page_offset; + page_offset = 0; + start_index++; + } + return out_pages; +} + +/* Continues reading a domain until we reach a discontiguity in the pfns. */ +static void batch_from_domain_continue(struct pfn_batch *batch, + struct iommu_domain *domain, + struct iopt_area *area, + unsigned long start_index, + unsigned long last_index) +{ + unsigned int array_size = batch->array_size; + + batch->array_size = batch->end; + batch_from_domain(batch, domain, area, start_index, last_index); + batch->array_size = array_size; +} + +/* + * This is part of the VFIO compatibility support for VFIO_TYPE1_IOMMU. That + * mode permits splitting a mapped area up, and then one of the splits is + * unmapped. Doing this normally would cause us to violate our invariant of + * pairing map/unmap. Thus, to support old VFIO compatibility disable support + * for batching consecutive PFNs. + */ +static int batch_iommu_map_small(struct iommu_domain *domain, + unsigned long iova, phys_addr_t paddr, + size_t size, int prot) +{ + unsigned long start_iova = iova; + int rc; + + while (size) { + rc = iommu_map(domain, iova, paddr, PAGE_SIZE, prot); + if (rc) + goto err_unmap; + iova += PAGE_SIZE; + paddr += PAGE_SIZE; + size -= PAGE_SIZE; + } + return 0; + +err_unmap: + if (start_iova != iova) + iommu_unmap_nofail(domain, start_iova, iova - start_iova); + return rc; +} + +static int batch_to_domain(struct pfn_batch *batch, struct iommu_domain *domain, + struct iopt_area *area, unsigned long start_index) +{ + bool disable_large_pages = area->iopt->disable_large_pages; + unsigned long last_iova = iopt_area_last_iova(area); + unsigned int page_offset = 0; + unsigned long start_iova; + unsigned long next_iova; + unsigned int cur = 0; + unsigned long iova; + int rc; + + /* The first index might be a partial page */ + if (start_index == iopt_area_index(area)) + page_offset = area->page_offset; + next_iova = iova = start_iova = + iopt_area_index_to_iova(area, start_index); + while (cur < batch->end) { + next_iova = min(last_iova + 1, + next_iova + batch->npfns[cur] * PAGE_SIZE - + page_offset); + if (disable_large_pages) + rc = batch_iommu_map_small( + domain, iova, + PFN_PHYS(batch->pfns[cur]) + page_offset, + next_iova - iova, area->iommu_prot); + else + rc = iommu_map(domain, iova, + PFN_PHYS(batch->pfns[cur]) + page_offset, + next_iova - iova, area->iommu_prot); + if (rc) + goto err_unmap; + iova = next_iova; + page_offset = 0; + cur++; + } + return 0; +err_unmap: + if (start_iova != iova) + iommu_unmap_nofail(domain, start_iova, iova - start_iova); + return rc; +} + +static void batch_from_xarray(struct pfn_batch *batch, struct xarray *xa, + unsigned long start_index, + unsigned long last_index) +{ + XA_STATE(xas, xa, start_index); + void *entry; + + rcu_read_lock(); + while (true) { + entry = xas_next(&xas); + if (xas_retry(&xas, entry)) + continue; + WARN_ON(!xa_is_value(entry)); + if (!batch_add_pfn(batch, xa_to_value(entry)) || + start_index == last_index) + break; + start_index++; + } + rcu_read_unlock(); +} + +static void batch_from_xarray_clear(struct pfn_batch *batch, struct xarray *xa, + unsigned long start_index, + unsigned long last_index) +{ + XA_STATE(xas, xa, start_index); + void *entry; + + xas_lock(&xas); + while (true) { + entry = xas_next(&xas); + if (xas_retry(&xas, entry)) + continue; + WARN_ON(!xa_is_value(entry)); + if (!batch_add_pfn(batch, xa_to_value(entry))) + break; + xas_store(&xas, NULL); + if (start_index == last_index) + break; + start_index++; + } + xas_unlock(&xas); +} + +static void clear_xarray(struct xarray *xa, unsigned long start_index, + unsigned long last_index) +{ + XA_STATE(xas, xa, start_index); + void *entry; + + xas_lock(&xas); + xas_for_each(&xas, entry, last_index) + xas_store(&xas, NULL); + xas_unlock(&xas); +} + +static int pages_to_xarray(struct xarray *xa, unsigned long start_index, + unsigned long last_index, struct page **pages) +{ + struct page **end_pages = pages + (last_index - start_index) + 1; + XA_STATE(xas, xa, start_index); + + do { + void *old; + + xas_lock(&xas); + while (pages != end_pages) { + old = xas_store(&xas, xa_mk_value(page_to_pfn(*pages))); + if (xas_error(&xas)) + break; + WARN_ON(old); + pages++; + xas_next(&xas); + } + xas_unlock(&xas); + } while (xas_nomem(&xas, GFP_KERNEL)); + + if (xas_error(&xas)) { + if (xas.xa_index != start_index) + clear_xarray(xa, start_index, xas.xa_index - 1); + return xas_error(&xas); + } + return 0; +} + +static void batch_from_pages(struct pfn_batch *batch, struct page **pages, + size_t npages) +{ + struct page **end = pages + npages; + + for (; pages != end; pages++) + if (!batch_add_pfn(batch, page_to_pfn(*pages))) + break; +} + +static void batch_unpin(struct pfn_batch *batch, struct iopt_pages *pages, + unsigned int offset, size_t npages) +{ + unsigned int cur = 0; + + while (offset) { + if (batch->npfns[cur] > offset) + break; + offset -= batch->npfns[cur]; + cur++; + } + + while (npages) { + size_t to_unpin = + min_t(size_t, npages, batch->npfns[cur] - offset); + + unpin_user_page_range_dirty_lock( + pfn_to_page(batch->pfns[cur] + offset), to_unpin, + pages->writable); + iopt_pages_sub_npinned(pages, to_unpin); + cur++; + offset = 0; + npages -= to_unpin; + } +} + +static void copy_data_page(struct page *page, void *data, unsigned long offset, + size_t length, unsigned int flags) +{ + void *mem; + + mem = kmap_local_page(page); + if (flags & IOMMUFD_ACCESS_RW_WRITE) { + memcpy(mem + offset, data, length); + set_page_dirty_lock(page); + } else { + memcpy(data, mem + offset, length); + } + kunmap_local(mem); +} + +static unsigned long batch_rw(struct pfn_batch *batch, void *data, + unsigned long offset, unsigned long length, + unsigned int flags) +{ + unsigned long copied = 0; + unsigned int npage = 0; + unsigned int cur = 0; + + while (cur < batch->end) { + unsigned long bytes = min(length, PAGE_SIZE - offset); + + copy_data_page(pfn_to_page(batch->pfns[cur] + npage), data, + offset, bytes, flags); + offset = 0; + length -= bytes; + data += bytes; + copied += bytes; + npage++; + if (npage == batch->npfns[cur]) { + npage = 0; + cur++; + } + if (!length) + break; + } + return copied; +} + +/* pfn_reader_user is just the pin_user_pages() path */ +struct pfn_reader_user { + struct page **upages; + size_t upages_len; + unsigned long upages_start; + unsigned long upages_end; + unsigned int gup_flags; + int locked; +}; + +static void pfn_reader_user_init(struct pfn_reader_user *user, + struct iopt_pages *pages) +{ + user->upages = NULL; + user->upages_start = 0; + user->upages_end = 0; + user->locked = -1; + + if (pages->writable) { + user->gup_flags = FOLL_LONGTERM | FOLL_WRITE; + } else { + /* Still need to break COWs on read */ + user->gup_flags = FOLL_LONGTERM | FOLL_FORCE | FOLL_WRITE; + } +} + +static void pfn_reader_user_destroy(struct pfn_reader_user *user, + struct iopt_pages *pages) +{ + if (user->locked != -1) { + if (user->locked) + mmap_read_unlock(pages->source_mm); + if (pages->source_mm != current->mm) + mmput(pages->source_mm); + user->locked = 0; + } + + kfree(user->upages); + user->upages = NULL; +} + +static int pfn_reader_user_pin(struct pfn_reader_user *user, + struct iopt_pages *pages, + unsigned long start_index, + unsigned long last_index) +{ + bool remote_mm = pages->source_mm != current->mm; + unsigned long npages; + uintptr_t uptr; + long rc; + + if (!user->upages) { + /* All undone in pfn_reader_destroy() */ + user->upages_len = + (last_index - start_index + 1) * sizeof(*user->upages); + user->upages = temp_kmalloc(&user->upages_len, NULL, 0); + if (!user->upages) + return -ENOMEM; + } + + if (user->locked == -1) { + /* + * The majority of usages will run the map task within the mm + * providing the pages, so we can optimize into + * get_user_pages_fast() + */ + if (remote_mm) { + if (!mmget_not_zero(pages->source_mm)) + return -EFAULT; + } + user->locked = 0; + } + + npages = min_t(unsigned long, last_index - start_index + 1, + user->upages_len / sizeof(*user->upages)); + + uptr = (uintptr_t)(pages->uptr + start_index * PAGE_SIZE); + if (!remote_mm) + rc = pin_user_pages_fast(uptr, npages, user->gup_flags, + user->upages); + else { + if (!user->locked) { + mmap_read_lock(pages->source_mm); + user->locked = 1; + } + /* + * FIXME: last NULL can be &pfns->locked once the GUP patch + * is merged. + */ + rc = pin_user_pages_remote(pages->source_mm, uptr, npages, + user->gup_flags, user->upages, NULL, + NULL); + } + if (rc <= 0) { + if (WARN_ON(!rc)) + return -EFAULT; + return rc; + } + iopt_pages_add_npinned(pages, rc); + user->upages_start = start_index; + user->upages_end = start_index + rc; + return 0; +} + +/* This is the "modern" and faster accounting method used by io_uring */ +static int incr_user_locked_vm(struct iopt_pages *pages, unsigned long npages) +{ + unsigned long lock_limit; + unsigned long cur_pages; + unsigned long new_pages; + + lock_limit = task_rlimit(pages->source_task, RLIMIT_MEMLOCK) >> + PAGE_SHIFT; + npages = pages->npinned - pages->last_npinned; + do { + cur_pages = atomic_long_read(&pages->source_user->locked_vm); + new_pages = cur_pages + npages; + if (new_pages > lock_limit) + return -ENOMEM; + } while (atomic_long_cmpxchg(&pages->source_user->locked_vm, cur_pages, + new_pages) != cur_pages); + return 0; +} + +static void decr_user_locked_vm(struct iopt_pages *pages, unsigned long npages) +{ + if (WARN_ON(atomic_long_read(&pages->source_user->locked_vm) < npages)) + return; + atomic_long_sub(npages, &pages->source_user->locked_vm); +} + +/* This is the accounting method used for compatibility with VFIO */ +static int update_mm_locked_vm(struct iopt_pages *pages, unsigned long npages, + bool inc, struct pfn_reader_user *user) +{ + bool do_put = false; + int rc; + + if (user && user->locked) { + mmap_read_unlock(pages->source_mm); + user->locked = 0; + /* If we had the lock then we also have a get */ + } else if ((!user || !user->upages) && + pages->source_mm != current->mm) { + if (!mmget_not_zero(pages->source_mm)) + return -EINVAL; + do_put = true; + } + + mmap_write_lock(pages->source_mm); + rc = __account_locked_vm(pages->source_mm, npages, inc, + pages->source_task, false); + mmap_write_unlock(pages->source_mm); + + if (do_put) + mmput(pages->source_mm); + return rc; +} + +static int do_update_pinned(struct iopt_pages *pages, unsigned long npages, + bool inc, struct pfn_reader_user *user) +{ + int rc = 0; + + switch (pages->account_mode) { + case IOPT_PAGES_ACCOUNT_NONE: + break; + case IOPT_PAGES_ACCOUNT_USER: + if (inc) + rc = incr_user_locked_vm(pages, npages); + else + decr_user_locked_vm(pages, npages); + break; + case IOPT_PAGES_ACCOUNT_MM: + rc = update_mm_locked_vm(pages, npages, inc, user); + break; + } + if (rc) + return rc; + + pages->last_npinned = pages->npinned; + if (inc) + atomic64_add(npages, &pages->source_mm->pinned_vm); + else + atomic64_sub(npages, &pages->source_mm->pinned_vm); + return 0; +} + +static void update_unpinned(struct iopt_pages *pages) +{ + if (WARN_ON(pages->npinned > pages->last_npinned)) + return; + if (pages->npinned == pages->last_npinned) + return; + do_update_pinned(pages, pages->last_npinned - pages->npinned, false, + NULL); +} + +/* + * Changes in the number of pages pinned is done after the pages have been read + * and processed. If the user lacked the limit then the error unwind will unpin + * everything that was just pinned. This is because it is expensive to calculate + * how many pages we have already pinned within a range to generate an accurate + * prediction in advance of doing the work to actually pin them. + */ +static int pfn_reader_user_update_pinned(struct pfn_reader_user *user, + struct iopt_pages *pages) +{ + unsigned long npages; + bool inc; + + lockdep_assert_held(&pages->mutex); + + if (pages->npinned == pages->last_npinned) + return 0; + + if (pages->npinned < pages->last_npinned) { + npages = pages->last_npinned - pages->npinned; + inc = false; + } else { + npages = pages->npinned - pages->last_npinned; + inc = true; + } + return do_update_pinned(pages, npages, inc, user); +} + +/* + * PFNs are stored in three places, in order of preference: + * - The iopt_pages xarray. This is only populated if there is a + * iopt_pages_access + * - The iommu_domain under an area + * - The original PFN source, ie pages->source_mm + * + * This iterator reads the pfns optimizing to load according to the + * above order. + */ +struct pfn_reader { + struct iopt_pages *pages; + struct interval_tree_double_span_iter span; + struct pfn_batch batch; + unsigned long batch_start_index; + unsigned long batch_end_index; + unsigned long last_index; + + struct pfn_reader_user user; +}; + +static int pfn_reader_update_pinned(struct pfn_reader *pfns) +{ + return pfn_reader_user_update_pinned(&pfns->user, pfns->pages); +} + +/* + * The batch can contain a mixture of pages that are still in use and pages that + * need to be unpinned. Unpin only pages that are not held anywhere else. + */ +static void pfn_reader_unpin(struct pfn_reader *pfns) +{ + unsigned long last = pfns->batch_end_index - 1; + unsigned long start = pfns->batch_start_index; + struct interval_tree_double_span_iter span; + struct iopt_pages *pages = pfns->pages; + + lockdep_assert_held(&pages->mutex); + + interval_tree_for_each_double_span(&span, &pages->access_itree, + &pages->domains_itree, start, last) { + if (span.is_used) + continue; + + batch_unpin(&pfns->batch, pages, span.start_hole - start, + span.last_hole - span.start_hole + 1); + } +} + +/* Process a single span in the access_itree */ +static int pfn_reader_fill_span(struct pfn_reader *pfns) +{ + struct interval_tree_double_span_iter *span = &pfns->span; + unsigned long start_index = pfns->batch_end_index; + struct iopt_area *area; + int rc; + + if (span->is_used == 1) { + batch_from_xarray(&pfns->batch, &pfns->pages->pinned_pfns, + start_index, span->last_used); + return 0; + } + + if (span->is_used == 2) { + /* + * Pull as many pages from the first domain we find in the + * target span. If it is too small then we will be called again + * and we'll find another area. + */ + area = iopt_pages_find_domain_area(pfns->pages, start_index); + if (WARN_ON(!area)) + return -EINVAL; + + /* The storage_domain cannot change without the pages mutex */ + batch_from_domain( + &pfns->batch, area->storage_domain, area, start_index, + min(iopt_area_last_index(area), span->last_used)); + return 0; + } + + if (start_index >= pfns->user.upages_end) { + rc = pfn_reader_user_pin(&pfns->user, pfns->pages, start_index, + span->last_hole); + if (rc) + return rc; + } + + batch_from_pages(&pfns->batch, + pfns->user.upages + + (start_index - pfns->user.upages_start), + pfns->user.upages_end - start_index); + return 0; +} + +static bool pfn_reader_done(struct pfn_reader *pfns) +{ + return pfns->batch_start_index == pfns->last_index + 1; +} + +static int pfn_reader_next(struct pfn_reader *pfns) +{ + int rc; + + batch_clear(&pfns->batch); + pfns->batch_start_index = pfns->batch_end_index; + + while (pfns->batch_end_index != pfns->last_index + 1) { + unsigned int npfns = pfns->batch.total_pfns; + + rc = pfn_reader_fill_span(pfns); + if (rc) + return rc; + + if (WARN_ON(!pfns->batch.total_pfns)) + return -EINVAL; + + pfns->batch_end_index = + pfns->batch_start_index + pfns->batch.total_pfns; + if (pfns->batch_end_index == pfns->span.last_used + 1) + interval_tree_double_span_iter_next(&pfns->span); + + /* Batch is full */ + if (npfns == pfns->batch.total_pfns) + return 0; + } + return 0; +} + +static int pfn_reader_init(struct pfn_reader *pfns, struct iopt_pages *pages, + unsigned long start_index, unsigned long last_index) +{ + int rc; + + lockdep_assert_held(&pages->mutex); + + pfns->pages = pages; + pfns->batch_start_index = start_index; + pfns->batch_end_index = start_index; + pfns->last_index = last_index; + pfn_reader_user_init(&pfns->user, pages); + rc = batch_init(&pfns->batch, last_index - start_index + 1); + if (rc) + return rc; + interval_tree_double_span_iter_first(&pfns->span, &pages->access_itree, + &pages->domains_itree, start_index, + last_index); + return 0; +} + +/* + * There are many assertions regarding the state of pages->npinned vs + * pages->last_pinned, for instance something like unmapping a domain must only + * decrement the npinned, and pfn_reader_destroy() must be called only after all + * the pins are updated. This is fine for success flows, but error flows + * sometimes need to release the pins held inside the pfn_reader before going on + * to complete unmapping and releasing pins held in domains. + */ +static void pfn_reader_release_pins(struct pfn_reader *pfns) +{ + struct iopt_pages *pages = pfns->pages; + + if (pfns->user.upages_end > pfns->batch_end_index) { + size_t npages = pfns->user.upages_end - pfns->batch_end_index; + + /* Any pages not transferred to the batch are just unpinned */ + unpin_user_pages(pfns->user.upages + (pfns->batch_end_index - + pfns->user.upages_start), + npages); + iopt_pages_sub_npinned(pages, npages); + pfns->user.upages_end = pfns->batch_end_index; + } + if (pfns->batch_start_index != pfns->batch_end_index) { + pfn_reader_unpin(pfns); + pfns->batch_start_index = pfns->batch_end_index; + } +} + +static void pfn_reader_destroy(struct pfn_reader *pfns) +{ + struct iopt_pages *pages = pfns->pages; + + pfn_reader_release_pins(pfns); + pfn_reader_user_destroy(&pfns->user, pfns->pages); + batch_destroy(&pfns->batch, NULL); + WARN_ON(pages->last_npinned != pages->npinned); +} + +static int pfn_reader_first(struct pfn_reader *pfns, struct iopt_pages *pages, + unsigned long start_index, unsigned long last_index) +{ + int rc; + + rc = pfn_reader_init(pfns, pages, start_index, last_index); + if (rc) + return rc; + rc = pfn_reader_next(pfns); + if (rc) { + pfn_reader_destroy(pfns); + return rc; + } + return 0; +} diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index d1817472c27373..26e09d539737bb 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -13,6 +13,13 @@ struct iommufd_ctx; struct file;

+enum { + IOMMUFD_ACCESS_RW_READ = 0, + IOMMUFD_ACCESS_RW_WRITE = 1 << 0, + /* Set if the caller is in a kthread then rw will use kthread_use_mm() */ + IOMMUFD_ACCESS_RW_KTHREAD = 1 << 1, +}; + void iommufd_ctx_get(struct iommufd_ctx *ictx);

#if IS_ENABLED(CONFIG_IOMMUFD)

The iopt_pages which represents a logical linear list of full PFNs held in different storage tiers. Each area points to a slice of exactly one iopt_pages, and each iopt_pages can have multiple areas and accesses.

The three storage tiers are managed to meet these objectives:

- If no iommu_domain or in-kerenel access exists then minimal memory should be consumed by iomufd - If a page has been pinned then an iopt_pages will not pin it again - If an in-kernel access exists then the xarray must provide the backing storage to avoid allocations on domain removals - Otherwise any iommu_domain will be used for storage

In a common configuration with only an iommu_domain the iopt_pages does not allocate significant memory itself.

The external interface for pages has several logical operations:

iopt_area_fill_domain() will load the PFNs from storage into a single domain. This is used when attaching a new domain to an existing IOAS.

iopt_area_fill_domains() will load the PFNs from storage into multiple domains. This is used when creating a new IOVA map in an existing IOAS

iopt_pages_add_access() creates an iopt_pages_access that tracks an in-kernel access of PFNs. This is some external driver that might be accessing the IOVA using the CPU, or programming PFNs with the DMA API. ie a VFIO mdev.

iopt_pages_rw_access() directly perform a memcpy on the PFNs, without the overhead of iopt_pages_add_access()

iopt_pages_fill_xarray() will load PFNs into the xarray and return a 'struct page *' array. It is used by iopt_pages_access's to extract PFNs for in-kernel use. iopt_pages_fill_from_xarray() is a fast path when it is known the xarray is already filled.

As an iopt_pages can be referred to in slices by many areas and accesses it uses interval trees to keep track of which storage tiers currently hold the PFNs. On a page-by-page basis any request for a PFN will be satisfied from one of the storage tiers and the PFN copied to target domain/array.

Unfill actions are similar, on a page by page basis domains are unmapped, xarray entries freed or struct pages fully put back.

Significant complexity is required to fully optimize all of these data motions. The implementation calculates the largest consecutive range of same-storage indexes and operates in blocks. The accumulation of PFNs always generates the largest contiguous PFN range possible to optimize and this gathering can cross storage tier boundaries. For cases like 'fill domains' care is taken to avoid duplicated work and PFNs are read once and pushed into all domains.

The map/unmap interaction with the iommu_domain always works in contiguous PFN blocks. The implementation does not require or benefit from any split/merge optimization in the iommu_domain driver.

This design suggests several possible improvements in the IOMMU API that would greatly help performance, particularly a way for the driver to map and read the pfns lists instead of working with one driver call per page to read, and one driver call per contiguous range to store.

Tested-by: Nicolin Chen nicolinc@nvidia.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com --- drivers/iommu/iommufd/io_pagetable.h | 74 +++ drivers/iommu/iommufd/pages.c | 823 ++++++++++++++++++++++++++- 2 files changed, 893 insertions(+), 4 deletions(-)

diff --git a/drivers/iommu/iommufd/io_pagetable.h b/drivers/iommu/iommufd/io_pagetable.h index b74bf01ffc52c2..aebb9a496258ce 100644 --- a/drivers/iommu/iommufd/io_pagetable.h +++ b/drivers/iommu/iommufd/io_pagetable.h @@ -49,6 +49,15 @@ struct iopt_area { unsigned int num_accesses; };

+int iopt_area_fill_domains(struct iopt_area *area, struct iopt_pages *pages); +void iopt_area_unfill_domains(struct iopt_area *area, struct iopt_pages *pages); + +int iopt_area_fill_domain(struct iopt_area *area, struct iommu_domain *domain); +void iopt_area_unfill_domain(struct iopt_area *area, struct iopt_pages *pages, + struct iommu_domain *domain); +void iopt_area_unmap_domain(struct iopt_area *area, + struct iommu_domain *domain); + static inline unsigned long iopt_area_index(struct iopt_area *area) { return area->pages_node.start; @@ -69,6 +78,39 @@ static inline unsigned long iopt_area_last_iova(struct iopt_area *area) return area->node.last; }

+static inline size_t iopt_area_length(struct iopt_area *area) +{ + return (area->node.last - area->node.start) + 1; +} + +#define __make_iopt_iter(name) \ + static inline struct iopt_##name *iopt_##name##_iter_first( \ + struct io_pagetable *iopt, unsigned long start, \ + unsigned long last) \ + { \ + struct interval_tree_node *node; \ + \ + lockdep_assert_held(&iopt->iova_rwsem); \ + node = interval_tree_iter_first(&iopt->name##_itree, start, \ + last); \ + if (!node) \ + return NULL; \ + return container_of(node, struct iopt_##name, node); \ + } \ + static inline struct iopt_##name *iopt_##name##_iter_next( \ + struct iopt_##name *last_node, unsigned long start, \ + unsigned long last) \ + { \ + struct interval_tree_node *node; \ + \ + node = interval_tree_iter_next(&last_node->node, start, last); \ + if (!node) \ + return NULL; \ + return container_of(node, struct iopt_##name, node); \ + } + +__make_iopt_iter(area) + enum { IOPT_PAGES_ACCOUNT_NONE = 0, IOPT_PAGES_ACCOUNT_USER = 1, @@ -106,4 +148,36 @@ struct iopt_pages { struct rb_root_cached domains_itree; };

+struct iopt_pages *iopt_alloc_pages(void __user *uptr, unsigned long length, + bool writable); +void iopt_release_pages(struct kref *kref); +static inline void iopt_put_pages(struct iopt_pages *pages) +{ + kref_put(&pages->kref, iopt_release_pages); +} + +void iopt_pages_fill_from_xarray(struct iopt_pages *pages, unsigned long start, + unsigned long last, struct page **out_pages); +int iopt_pages_fill_xarray(struct iopt_pages *pages, unsigned long start, + unsigned long last, struct page **out_pages); +void iopt_pages_unfill_xarray(struct iopt_pages *pages, unsigned long start, + unsigned long last); + +int iopt_pages_add_access(struct iopt_pages *pages, unsigned long start, + unsigned long last, struct page **out_pages, + unsigned int flags); +void iopt_pages_remove_access(struct iopt_area *area, unsigned long start, + unsigned long last); +int iopt_pages_rw_access(struct iopt_pages *pages, unsigned long start_byte, + void *data, unsigned long length, unsigned int flags); + +/* + * Each interval represents an active iopt_access_pages(), it acts as an + * interval lock that keeps the PFNs pinned and stored in the xarray. + */ +struct iopt_pages_access { + struct interval_tree_node node; + refcount_t refcount; +}; + #endif diff --git a/drivers/iommu/iommufd/pages.c b/drivers/iommu/iommufd/pages.c index 87e2bd78ae91e8..d8f3f2a07e8378 100644 --- a/drivers/iommu/iommufd/pages.c +++ b/drivers/iommu/iommufd/pages.c @@ -151,6 +151,18 @@ static void iommu_unmap_nofail(struct iommu_domain *domain, unsigned long iova, WARN_ON(ret != size); }

+static void iopt_area_unmap_domain_range(struct iopt_area *area, + struct iommu_domain *domain, + unsigned long start_index, + unsigned long last_index) +{ + unsigned long start_iova = iopt_area_index_to_iova(area, start_index); + + iommu_unmap_nofail(domain, start_iova, + iopt_area_index_to_iova_last(area, last_index) - + start_iova + 1); +} + static struct iopt_area *iopt_pages_find_domain_area(struct iopt_pages *pages, unsigned long index) { @@ -171,7 +183,7 @@ static struct iopt_area *iopt_pages_find_domain_area(struct iopt_pages *pages, */ struct pfn_batch { unsigned long *pfns; - u16 *npfns; + u32 *npfns; unsigned int array_size; unsigned int end; unsigned int total_pfns; @@ -221,7 +233,7 @@ static int __batch_init(struct pfn_batch *batch, size_t max_pages, void *backup, if (!batch->pfns) return -ENOMEM; batch->array_size = size / elmsz; - batch->npfns = (u16 *)(batch->pfns + batch->array_size); + batch->npfns = (u32 *)(batch->pfns + batch->array_size); batch_clear(batch); return 0; } @@ -246,10 +258,11 @@ static void batch_destroy(struct pfn_batch *batch, void *backup) /* true if the pfn could be added, false otherwise */ static bool batch_add_pfn(struct pfn_batch *batch, unsigned long pfn) { - /* FIXME: U16 is too small */ + const unsigned int MAX_NPFNS = type_max(typeof(*batch->npfns)); + if (batch->end && pfn == batch->pfns[batch->end - 1] + batch->npfns[batch->end - 1] && - batch->npfns[batch->end - 1] != U16_MAX) { + batch->npfns[batch->end - 1] != MAX_NPFNS) { batch->npfns[batch->end - 1]++; batch->total_pfns++; return true; @@ -997,3 +1010,805 @@ static int pfn_reader_first(struct pfn_reader *pfns, struct iopt_pages *pages, } return 0; } + +struct iopt_pages *iopt_alloc_pages(void __user *uptr, unsigned long length, + bool writable) +{ + struct iopt_pages *pages; + + /* + * The iommu API uses size_t as the length, and protect the DIV_ROUND_UP + * below from overflow + */ + if (length > SIZE_MAX - PAGE_SIZE || length == 0) + return ERR_PTR(-EINVAL); + + pages = kzalloc(sizeof(*pages), GFP_KERNEL_ACCOUNT); + if (!pages) + return ERR_PTR(-ENOMEM); + + kref_init(&pages->kref); + xa_init_flags(&pages->pinned_pfns, XA_FLAGS_ACCOUNT); + mutex_init(&pages->mutex); + pages->source_mm = current->mm; + mmgrab(pages->source_mm); + pages->uptr = (void __user *)ALIGN_DOWN((uintptr_t)uptr, PAGE_SIZE); + pages->npages = DIV_ROUND_UP(length + (uptr - pages->uptr), PAGE_SIZE); + pages->access_itree = RB_ROOT_CACHED; + pages->domains_itree = RB_ROOT_CACHED; + pages->writable = writable; + if (capable(CAP_IPC_LOCK)) + pages->account_mode = IOPT_PAGES_ACCOUNT_NONE; + else + pages->account_mode = IOPT_PAGES_ACCOUNT_USER; + pages->source_task = current->group_leader; + get_task_struct(current->group_leader); + pages->source_user = get_uid(current_user()); + return pages; +} + +void iopt_release_pages(struct kref *kref) +{ + struct iopt_pages *pages = container_of(kref, struct iopt_pages, kref); + + WARN_ON(!RB_EMPTY_ROOT(&pages->access_itree.rb_root)); + WARN_ON(!RB_EMPTY_ROOT(&pages->domains_itree.rb_root)); + WARN_ON(pages->npinned); + WARN_ON(!xa_empty(&pages->pinned_pfns)); + mmdrop(pages->source_mm); + mutex_destroy(&pages->mutex); + put_task_struct(pages->source_task); + free_uid(pages->source_user); + kfree(pages); +} + +static void +iopt_area_unpin_domain(struct pfn_batch *batch, struct iopt_area *area, + struct iopt_pages *pages, struct iommu_domain *domain, + unsigned long start_index, unsigned long last_index, + unsigned long *unmapped_end_index, + unsigned long real_last_index) +{ + while (start_index <= last_index) { + unsigned long batch_last_index; + + if (*unmapped_end_index <= last_index) { + unsigned long start = + max(start_index, *unmapped_end_index); + + batch_from_domain(batch, domain, area, start, + last_index); + batch_last_index = start + batch->total_pfns - 1; + } else { + batch_last_index = last_index; + } + + /* + * unmaps must always 'cut' at a place where the pfns are not + * contiguous to pair with the maps that always install + * contiguous pages. Thus, if we have to stop unpinning in the + * middle of the domains we need to keep reading pfns until we + * find a cut point to do the unmap. The pfns we read are + * carried over and either skipped or integrated into the next + * batch. + */ + if (batch_last_index == last_index && + last_index != real_last_index) + batch_from_domain_continue(batch, domain, area, + last_index + 1, + real_last_index); + + if (*unmapped_end_index <= batch_last_index) { + iopt_area_unmap_domain_range( + area, domain, *unmapped_end_index, + start_index + batch->total_pfns - 1); + *unmapped_end_index = start_index + batch->total_pfns; + } + + /* unpin must follow unmap */ + batch_unpin(batch, pages, 0, + batch_last_index - start_index + 1); + start_index = batch_last_index + 1; + + batch_clear_carry(batch, + *unmapped_end_index - batch_last_index - 1); + } +} + +static void __iopt_area_unfill_domain(struct iopt_area *area, + struct iopt_pages *pages, + struct iommu_domain *domain, + unsigned long last_index) +{ + struct interval_tree_double_span_iter span; + unsigned long start_index = iopt_area_index(area); + unsigned long unmapped_end_index = start_index; + u64 backup[BATCH_BACKUP_SIZE]; + struct pfn_batch batch; + + lockdep_assert_held(&pages->mutex); + + batch_init_backup(&batch, last_index + 1, backup, sizeof(backup)); + interval_tree_for_each_double_span(&span, &pages->domains_itree, + &pages->access_itree, start_index, + last_index) { + if (span.is_used) { + batch_skip_carry(&batch, + span.last_used - span.start_used + 1); + continue; + } + iopt_area_unpin_domain(&batch, area, pages, domain, + span.start_hole, span.last_hole, + &unmapped_end_index, last_index); + } + if (unmapped_end_index != last_index + 1) + iopt_area_unmap_domain_range(area, domain, unmapped_end_index, + last_index); + WARN_ON(batch.total_pfns); + batch_destroy(&batch, backup); + update_unpinned(pages); +} + +static void iopt_area_unfill_partial_domain(struct iopt_area *area, + struct iopt_pages *pages, + struct iommu_domain *domain, + unsigned long end_index) +{ + if (end_index != iopt_area_index(area)) + __iopt_area_unfill_domain(area, pages, domain, end_index - 1); +} + +/** + * iopt_area_unmap_domain() - Unmap without unpinning PFNs in a domain + * @area: The IOVA range to unmap + * @domain: The domain to unmap + * + * The caller must know that unpinning is not required, usually because there + * are other domains in the iopt. + */ +void iopt_area_unmap_domain(struct iopt_area *area, struct iommu_domain *domain) +{ + iommu_unmap_nofail(domain, iopt_area_iova(area), + iopt_area_length(area)); +} + +/** + * iopt_area_unfill_domain() - Unmap and unpin PFNs in a domain + * @area: IOVA area to use + * @pages: page supplier for the area (area->pages is NULL) + * @domain: Domain to unmap from + * + * The domain should be removed from the domains_itree before calling. The + * domain will always be unmapped, but the PFNs may not be unpinned if there are + * still accesses. + */ +void iopt_area_unfill_domain(struct iopt_area *area, struct iopt_pages *pages, + struct iommu_domain *domain) +{ + __iopt_area_unfill_domain(area, pages, domain, + iopt_area_last_index(area)); +} + +/** + * iopt_area_fill_domain() - Map PFNs from the area into a domain + * @area: IOVA area to use + * @domain: Domain to load PFNs into + * + * Read the pfns from the area's underlying iopt_pages and map them into the + * given domain. Called when attaching a new domain to an io_pagetable. + */ +int iopt_area_fill_domain(struct iopt_area *area, struct iommu_domain *domain) +{ + unsigned long done_end_index; + struct pfn_reader pfns; + int rc; + + lockdep_assert_held(&area->pages->mutex); + + rc = pfn_reader_first(&pfns, area->pages, iopt_area_index(area), + iopt_area_last_index(area)); + if (rc) + return rc; + + while (!pfn_reader_done(&pfns)) { + done_end_index = pfns.batch_start_index; + rc = batch_to_domain(&pfns.batch, domain, area, + pfns.batch_start_index); + if (rc) + goto out_unmap; + done_end_index = pfns.batch_end_index; + + rc = pfn_reader_next(&pfns); + if (rc) + goto out_unmap; + } + + rc = pfn_reader_update_pinned(&pfns); + if (rc) + goto out_unmap; + goto out_destroy; + +out_unmap: + pfn_reader_release_pins(&pfns); + iopt_area_unfill_partial_domain(area, area->pages, domain, + done_end_index); +out_destroy: + pfn_reader_destroy(&pfns); + return rc; +} + +/** + * iopt_area_fill_domains() - Install PFNs into the area's domains + * @area: The area to act on + * @pages: The pages associated with the area (area->pages is NULL) + * + * Called during area creation. The area is freshly created and not inserted in + * the domains_itree yet. PFNs are read and loaded into every domain held in the + * area's io_pagetable and the area is installed in the domains_itree. + * + * On failure all domains are left unchanged. + */ +int iopt_area_fill_domains(struct iopt_area *area, struct iopt_pages *pages) +{ + unsigned long done_first_end_index; + unsigned long done_all_end_index; + struct iommu_domain *domain; + unsigned long unmap_index; + struct pfn_reader pfns; + unsigned long index; + int rc; + + lockdep_assert_held(&area->iopt->domains_rwsem); + + if (xa_empty(&area->iopt->domains)) + return 0; + + mutex_lock(&pages->mutex); + rc = pfn_reader_first(&pfns, pages, iopt_area_index(area), + iopt_area_last_index(area)); + if (rc) + goto out_unlock; + + while (!pfn_reader_done(&pfns)) { + done_first_end_index = pfns.batch_end_index; + done_all_end_index = pfns.batch_start_index; + xa_for_each(&area->iopt->domains, index, domain) { + rc = batch_to_domain(&pfns.batch, domain, area, + pfns.batch_start_index); + if (rc) + goto out_unmap; + } + done_all_end_index = done_first_end_index; + + rc = pfn_reader_next(&pfns); + if (rc) + goto out_unmap; + } + rc = pfn_reader_update_pinned(&pfns); + if (rc) + goto out_unmap; + + area->storage_domain = xa_load(&area->iopt->domains, 0); + interval_tree_insert(&area->pages_node, &pages->domains_itree); + goto out_destroy; + +out_unmap: + pfn_reader_release_pins(&pfns); + xa_for_each(&area->iopt->domains, unmap_index, domain) { + unsigned long end_index; + + if (unmap_index < index) + end_index = done_first_end_index; + else + end_index = done_all_end_index; + + /* + * The area is not yet part of the domains_itree so we have to + * manage the unpinning specially. The last domain does the + * unpin, every other domain is just unmapped. + */ + if (unmap_index != area->iopt->next_domain_id - 1) { + if (end_index != iopt_area_index(area)) + iopt_area_unmap_domain_range( + area, domain, iopt_area_index(area), + end_index - 1); + } else { + iopt_area_unfill_partial_domain(area, pages, domain, + end_index); + } + } +out_destroy: + pfn_reader_destroy(&pfns); +out_unlock: + mutex_unlock(&pages->mutex); + return rc; +} + +/** + * iopt_area_unfill_domains() - unmap PFNs from the area's domains + * @area: The area to act on + * @pages: The pages associated with the area (area->pages is NULL) + * + * Called during area destruction. This unmaps the iova's covered by all the + * area's domains and releases the PFNs. + */ +void iopt_area_unfill_domains(struct iopt_area *area, struct iopt_pages *pages) +{ + struct io_pagetable *iopt = area->iopt; + struct iommu_domain *domain; + unsigned long index; + + lockdep_assert_held(&iopt->domains_rwsem); + + mutex_lock(&pages->mutex); + if (!area->storage_domain) + goto out_unlock; + + xa_for_each(&iopt->domains, index, domain) + if (domain != area->storage_domain) + iopt_area_unmap_domain_range( + area, domain, iopt_area_index(area), + iopt_area_last_index(area)); + + interval_tree_remove(&area->pages_node, &pages->domains_itree); + iopt_area_unfill_domain(area, pages, area->storage_domain); + area->storage_domain = NULL; +out_unlock: + mutex_unlock(&pages->mutex); +} + +static void iopt_pages_unpin_xarray(struct pfn_batch *batch, + struct iopt_pages *pages, + unsigned long start_index, + unsigned long end_index) +{ + while (start_index <= end_index) { + batch_from_xarray_clear(batch, &pages->pinned_pfns, start_index, + end_index); + batch_unpin(batch, pages, 0, batch->total_pfns); + start_index += batch->total_pfns; + batch_clear(batch); + } +} + +/** + * iopt_pages_unfill_xarray() - Update the xarry after removing an access + * @pages: The pages to act on + * @start_index: Starting PFN index + * @last_index: Last PFN index + * + * Called when an iopt_pages_access is removed, removes pages from the itree. + * The access should already be removed from the access_itree. + */ +void iopt_pages_unfill_xarray(struct iopt_pages *pages, + unsigned long start_index, + unsigned long last_index) +{ + struct interval_tree_double_span_iter span; + u64 backup[BATCH_BACKUP_SIZE]; + struct pfn_batch batch; + bool batch_inited = false; + + lockdep_assert_held(&pages->mutex); + + interval_tree_for_each_double_span(&span, &pages->access_itree, + &pages->domains_itree, start_index, + last_index) { + if (!span.is_used) { + if (!batch_inited) { + batch_init_backup(&batch, + last_index - start_index + 1, + backup, sizeof(backup)); + batch_inited = true; + } + iopt_pages_unpin_xarray(&batch, pages, span.start_hole, + span.last_hole); + } else if (span.is_used == 2) { + /* Covered by a domain */ + clear_xarray(&pages->pinned_pfns, span.start_used, + span.last_used); + } + /* Otherwise covered by an existing access */ + } + if (batch_inited) + batch_destroy(&batch, backup); + update_unpinned(pages); +} + +/** + * iopt_pages_fill_from_xarray() - Fast path for reading PFNs + * @pages: The pages to act on + * @start_index: The first page index in the range + * @last_index: The last page index in the range + * @out_pages: The output array to return the pages + * + * This can be called if the caller is holding a refcount on an + * iopt_pages_access that is known to have already been filled. It quickly reads + * the pages directly from the xarray. + * + * This is part of the SW iommu interface to read pages for in-kernel use. + */ +void iopt_pages_fill_from_xarray(struct iopt_pages *pages, + unsigned long start_index, + unsigned long last_index, + struct page **out_pages) +{ + XA_STATE(xas, &pages->pinned_pfns, start_index); + void *entry; + + rcu_read_lock(); + while (start_index <= last_index) { + entry = xas_next(&xas); + if (xas_retry(&xas, entry)) + continue; + WARN_ON(!xa_is_value(entry)); + *(out_pages++) = pfn_to_page(xa_to_value(entry)); + start_index++; + } + rcu_read_unlock(); +} + +static int iopt_pages_fill_from_domain(struct iopt_pages *pages, + unsigned long start_index, + unsigned long last_index, + struct page **out_pages) +{ + while (start_index != last_index + 1) { + unsigned long domain_last; + struct iopt_area *area; + + area = iopt_pages_find_domain_area(pages, start_index); + if (WARN_ON(!area)) + return -EINVAL; + + domain_last = min(iopt_area_last_index(area), last_index); + out_pages = raw_pages_from_domain(area->storage_domain, area, + start_index, domain_last, + out_pages); + start_index = domain_last + 1; + } + return 0; +} + +static int iopt_pages_fill_from_mm(struct iopt_pages *pages, + struct pfn_reader_user *user, + unsigned long start_index, + unsigned long last_index, + struct page **out_pages) +{ + unsigned long cur_index = start_index; + int rc; + + while (cur_index != last_index + 1) { + user->upages = out_pages + (cur_index - start_index); + rc = pfn_reader_user_pin(user, pages, cur_index, last_index); + if (rc) + goto out_unpin; + cur_index = user->upages_end; + } + return 0; + +out_unpin: + if (start_index != cur_index) + iopt_pages_err_unpin(pages, start_index, cur_index - 1, + out_pages); + return rc; +} + +/** + * iopt_pages_fill_xarray() - Read PFNs + * @pages: The pages to act on + * @start_index: The first page index in the range + * @last_index: The last page index in the range + * @out_pages: The output array to return the pages, may be NULL + * + * This populates the xarray and returns the pages in out_pages. As the slow + * path this is able to copy pages from other storage tiers into the xarray. + * + * On failure the xarray is left unchanged. + * + * This is part of the SW iommu interface to read pages for in-kernel use. + */ +int iopt_pages_fill_xarray(struct iopt_pages *pages, unsigned long start_index, + unsigned long last_index, struct page **out_pages) +{ + struct interval_tree_double_span_iter span; + unsigned long xa_end = start_index; + struct pfn_reader_user user; + int rc; + + lockdep_assert_held(&pages->mutex); + + pfn_reader_user_init(&user, pages); + user.upages_len = (last_index - start_index + 1) * sizeof(*out_pages); + interval_tree_for_each_double_span(&span, &pages->access_itree, + &pages->domains_itree, start_index, + last_index) { + struct page **cur_pages; + + if (span.is_used == 1) { + cur_pages = out_pages + (span.start_used - start_index); + iopt_pages_fill_from_xarray(pages, span.start_used, + span.last_used, cur_pages); + continue; + } + + if (span.is_used == 2) { + cur_pages = out_pages + (span.start_used - start_index); + iopt_pages_fill_from_domain(pages, span.start_used, + span.last_used, cur_pages); + rc = pages_to_xarray(&pages->pinned_pfns, + span.start_used, span.last_used, + cur_pages); + if (rc) + goto out_clean_xa; + xa_end = span.last_used + 1; + continue; + } + + /* hole */ + cur_pages = out_pages + (span.start_hole - start_index); + rc = iopt_pages_fill_from_mm(pages, &user, span.start_hole, + span.last_hole, cur_pages); + if (rc) + goto out_clean_xa; + rc = pages_to_xarray(&pages->pinned_pfns, span.start_hole, + span.last_hole, cur_pages); + if (rc) { + iopt_pages_err_unpin(pages, span.start_hole, + span.last_hole, cur_pages); + goto out_clean_xa; + } + xa_end = span.last_hole + 1; + } + rc = pfn_reader_user_update_pinned(&user, pages); + if (rc) + goto out_clean_xa; + user.upages = NULL; + pfn_reader_user_destroy(&user, pages); + return 0; + +out_clean_xa: + if (start_index != xa_end) + iopt_pages_unfill_xarray(pages, start_index, xa_end - 1); + user.upages = NULL; + pfn_reader_user_destroy(&user, pages); + return rc; +} + +/* + * This can do everything and is fully coherent with what a iommu_domain would + * see. + */ +static int iopt_pages_rw_slow(struct iopt_pages *pages, + unsigned long start_index, + unsigned long last_index, unsigned long offset, + void *data, unsigned long length, + unsigned int flags) +{ + struct pfn_reader pfns; + int rc; + + mutex_lock(&pages->mutex); + + rc = pfn_reader_first(&pfns, pages, start_index, last_index); + if (rc) + goto out_unlock; + + while (!pfn_reader_done(&pfns)) { + unsigned long done; + + done = batch_rw(&pfns.batch, data, offset, length, flags); + data += done; + length -= done; + offset = 0; + pfn_reader_unpin(&pfns); + + rc = pfn_reader_next(&pfns); + if (rc) + goto out_destroy; + } + if (WARN_ON(length != 0)) + rc = -EINVAL; +out_destroy: + pfn_reader_destroy(&pfns); +out_unlock: + mutex_unlock(&pages->mutex); + return rc; +} + +/* + * A medium speed path that still allows DMA decoherence, but doesn't do any + * memory allocations or interval tree searches. + */ +static int iopt_pages_rw_page(struct iopt_pages *pages, unsigned long index, + unsigned long offset, void *data, + unsigned long length, unsigned int flags) +{ + struct page *page = NULL; + int rc; + + if (!mmget_not_zero(pages->source_mm)) + return iopt_pages_rw_slow(pages, index, index, offset, data, + length, flags); + + mmap_read_lock(pages->source_mm); + rc = pin_user_pages_remote( + pages->source_mm, (uintptr_t)(pages->uptr + index * PAGE_SIZE), + 1, (flags & IOMMUFD_ACCESS_RW_WRITE) ? FOLL_WRITE : 0, &page, + NULL, NULL); + mmap_read_unlock(pages->source_mm); + if (rc != 1) { + if (WARN_ON(rc >= 0)) + rc = -EINVAL; + goto out_mmput; + } + copy_data_page(page, data, offset, length, flags); + unpin_user_page(page); + rc = 0; + +out_mmput: + mmput(pages->source_mm); + return rc; +} + +/** + * iopt_pages_rw_access - Copy to/from a linear slice of the pages + * @pages: pages to act on + * @start_byte: First byte of pages to copy to/from + * @data: Kernel buffer to get/put the data + * @length: Number of bytes to copy + * @flags: IOMMUFD_ACCESS_RW_* flags + * + * This will find each page in the range, kmap it and then memcpy to/from + * the given kernel buffer. + */ +int iopt_pages_rw_access(struct iopt_pages *pages, unsigned long start_byte, + void *data, unsigned long length, unsigned int flags) +{ + unsigned long start_index = start_byte / PAGE_SIZE; + unsigned long last_index = (start_byte + length - 1) / PAGE_SIZE; + bool change_mm = current->mm != pages->source_mm; + int rc = 0; + + if ((flags & IOMMUFD_ACCESS_RW_WRITE) && !pages->writable) + return -EPERM; + + if (!(flags & IOMMUFD_ACCESS_RW_KTHREAD) && change_mm) { + if (start_index == last_index) + return iopt_pages_rw_page(pages, start_index, + start_byte % PAGE_SIZE, data, + length, flags); + return iopt_pages_rw_slow(pages, start_index, last_index, + start_byte % PAGE_SIZE, data, length, + flags); + } + + /* + * Try to copy using copy_to_user(). We do this as a fast path and + * ignore any pinning decoherence, unlike a real DMA path. + */ + if (change_mm) { + if (!mmget_not_zero(pages->source_mm)) + return iopt_pages_rw_slow(pages, start_index, + last_index, + start_byte % PAGE_SIZE, data, + length, flags); + kthread_use_mm(pages->source_mm); + } + + if (flags & IOMMUFD_ACCESS_RW_WRITE) { + if (copy_to_user(pages->uptr + start_byte, data, length)) + rc = -EFAULT; + } else { + if (copy_from_user(data, pages->uptr + start_byte, length)) + rc = -EFAULT; + } + + if (change_mm) { + kthread_unuse_mm(pages->source_mm); + mmput(pages->source_mm); + } + + return rc; +} + +static struct iopt_pages_access * +iopt_pages_get_exact_access(struct iopt_pages *pages, unsigned long index, + unsigned long last) +{ + struct interval_tree_node *node; + + lockdep_assert_held(&pages->mutex); + + /* There can be overlapping ranges in this interval tree */ + for (node = interval_tree_iter_first(&pages->access_itree, index, last); + node; node = interval_tree_iter_next(node, index, last)) + if (node->start == index && node->last == last) + return container_of(node, struct iopt_pages_access, + node); + return NULL; +} + +/** + * iopt_pages_add_access() - Record an in-knerel access for PFNs + * @pages: The source of PFNs + * @start_index: First page index + * @last_index: Inclusive last page index + * @out_pages: Output list of struct page's representing the PFNs + * @flags: IOMMUFD_ACCESS_RW_* flags + * + * Record that an in-kernel access will be accessing the pages, ensure they are + * pinned, and return the PFNs as a simple list of 'struct page *'. + * + * This should be undone through a matching call to iopt_pages_remove_access() + */ +int iopt_pages_add_access(struct iopt_pages *pages, unsigned long start_index, + unsigned long last_index, struct page **out_pages, + unsigned int flags) +{ + struct iopt_pages_access *access; + int rc; + + if ((flags & IOMMUFD_ACCESS_RW_WRITE) && !pages->writable) + return -EPERM; + + access = iopt_pages_get_exact_access(pages, start_index, last_index); + if (access) { + refcount_inc(&access->refcount); + iopt_pages_fill_from_xarray(pages, start_index, last_index, + out_pages); + return 0; + } + + access = kzalloc(sizeof(*access), GFP_KERNEL_ACCOUNT); + if (!access) + return -ENOMEM; + + rc = iopt_pages_fill_xarray(pages, start_index, last_index, out_pages); + if (rc) + goto out_free; + + access->node.start = start_index; + access->node.last = last_index; + refcount_set(&access->refcount, 1); + interval_tree_insert(&access->node, &pages->access_itree); + return 0; + +out_free: + kfree(access); + return rc; +} + +/** + * iopt_pages_remove_access() - Release an in-kernel access for PFNs + * @area: The source of PFNs + * @start_index: First page index + * @last_index: Inclusive last page index + * + * Undo iopt_pages_add_access() and unpin the pages if necessary. The caller + * must stop using the PFNs before calling this. + */ +void iopt_pages_remove_access(struct iopt_area *area, unsigned long start_index, + unsigned long last_index) +{ + struct iopt_pages_access *access; + struct iopt_pages *pages = area->pages; + + mutex_lock(&pages->mutex); + access = iopt_pages_get_exact_access(pages, start_index, last_index); + if (WARN_ON(!access)) + goto out_unlock; + + WARN_ON(area->num_accesses == 0); + area->num_accesses--; + + if (!refcount_dec_and_test(&access->refcount)) + goto out_unlock; + + interval_tree_remove(&access->node, &pages->access_itree); + iopt_pages_unfill_xarray(pages, start_index, last_index); + kfree(access); +out_unlock: + mutex_unlock(&pages->mutex); +}

This is the remainder of the IOAS data structure. Provide an object called an io_pagetable that is composed of iopt_areas pointing at iopt_pages, along with a list of iommu_domains that mirror the IOVA to PFN map.

At the top this is a simple interval tree of iopt_areas indicating the map of IOVA to iopt_pages. An xarray keeps track of a list of domains. Based on the attached domains there is a minimum alignment for areas (which may be smaller than PAGE_SIZE), an interval tree of reserved IOVA that can't be mapped and an IOVA of allowed IOVA that can always be mappable.

The concept of an 'access' refers to something like a VFIO mdev that is accessing the IOVA and using a 'struct page *' for CPU based access.

Externally an API is provided that matches the requirements of the IOCTL interface for map/unmap and domain attachment.

The API provides a 'copy' primitive to establish a new IOVA map in a different IOAS from an existing mapping by re-using the iopt_pages. This is the basic mechanism to provide single pinning.

This is designed to support a pre-registration flow where userspace would setup an dummy IOAS with no domains, map in memory and then establish an access to pin all PFNs into the xarray.

Copy can then be used to create new IOVA mappings in a different IOAS, with iommu_domains attached. Upon copy the PFNs will be read out of the xarray and mapped into the iommu_domains, avoiding any pin_user_pages() overheads.

Tested-by: Nicolin Chen nicolinc@nvidia.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Yi Liu yi.l.liu@intel.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- .clang-format | 1 + drivers/iommu/iommufd/Makefile | 1 + drivers/iommu/iommufd/io_pagetable.c | 1188 +++++++++++++++++++++++ drivers/iommu/iommufd/io_pagetable.h | 55 ++ drivers/iommu/iommufd/iommufd_private.h | 52 + 5 files changed, 1297 insertions(+) create mode 100644 drivers/iommu/iommufd/io_pagetable.c

diff --git a/.clang-format b/.clang-format index 501241f8977664..78aba4a10b1bbc 100644 --- a/.clang-format +++ b/.clang-format @@ -444,6 +444,7 @@ ForEachMacros: - 'interval_tree_for_each_span' - 'intlist__for_each_entry' - 'intlist__for_each_entry_safe' + - 'iopt_for_each_contig_area' - 'kcore_copy__for_each_phdr' - 'key_for_each' - 'key_for_each_safe' diff --git a/drivers/iommu/iommufd/Makefile b/drivers/iommu/iommufd/Makefile index 05a0e91e30afad..b66a8c47ff55ec 100644 --- a/drivers/iommu/iommufd/Makefile +++ b/drivers/iommu/iommufd/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only iommufd-y := \ + io_pagetable.o \ main.o \ pages.o

diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c new file mode 100644 index 00000000000000..86effe8ed1dce5 --- /dev/null +++ b/drivers/iommu/iommufd/io_pagetable.c @@ -0,0 +1,1188 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES. + * + * The io_pagetable is the top of datastructure that maps IOVA's to PFNs. The + * PFNs can be placed into an iommu_domain, or returned to the caller as a page + * list for access by an in-kernel user. + * + * The datastructure uses the iopt_pages to optimize the storage of the PFNs + * between the domains and xarray. + */ +#include <linux/iommufd.h> +#include <linux/lockdep.h> +#include <linux/iommu.h> +#include <linux/sched/mm.h> +#include <linux/err.h> +#include <linux/slab.h> +#include <linux/errno.h> + +#include "io_pagetable.h" + +struct iopt_pages_list { + struct iopt_pages *pages; + struct iopt_area *area; + struct list_head next; + unsigned long start_byte; + unsigned long length; +}; + +struct iopt_area *iopt_area_contig_init(struct iopt_area_contig_iter *iter, + struct io_pagetable *iopt, + unsigned long iova, + unsigned long last_iova) +{ + lockdep_assert_held(&iopt->iova_rwsem); + + iter->cur_iova = iova; + iter->last_iova = last_iova; + iter->area = iopt_area_iter_first(iopt, iova, iova); + if (!iter->area) + return NULL; + if (!iter->area->pages) { + iter->area = NULL; + return NULL; + } + return iter->area; +} + +struct iopt_area *iopt_area_contig_next(struct iopt_area_contig_iter *iter) +{ + unsigned long last_iova; + + if (!iter->area) + return NULL; + last_iova = iopt_area_last_iova(iter->area); + if (iter->last_iova <= last_iova) + return NULL; + + iter->cur_iova = last_iova + 1; + iter->area = iopt_area_iter_next(iter->area, iter->cur_iova, + iter->last_iova); + if (!iter->area) + return NULL; + if (iter->cur_iova != iopt_area_iova(iter->area) || + !iter->area->pages) { + iter->area = NULL; + return NULL; + } + return iter->area; +} + +static bool __alloc_iova_check_hole(struct interval_tree_span_iter *span, + unsigned long length, + unsigned long iova_alignment, + unsigned long page_offset) +{ + if (!span->is_hole || span->last_hole - span->start_hole < length - 1) + return false; + + span->start_hole = ALIGN(span->start_hole, iova_alignment) | + page_offset; + if (span->start_hole > span->last_hole || + span->last_hole - span->start_hole < length - 1) + return false; + return true; +} + +static bool __alloc_iova_check_used(struct interval_tree_span_iter *span, + unsigned long length, + unsigned long iova_alignment, + unsigned long page_offset) +{ + if (span->is_hole || span->last_used - span->start_used < length - 1) + return false; + + span->start_used = ALIGN(span->start_used, iova_alignment) | + page_offset; + if (span->start_used > span->last_used || + span->last_used - span->start_used < length - 1) + return false; + return true; +} + +/* + * Automatically find a block of IOVA that is not being used and not reserved. + * Does not return a 0 IOVA even if it is valid. + */ +static int iopt_alloc_iova(struct io_pagetable *iopt, unsigned long *iova, + unsigned long uptr, unsigned long length) +{ + struct interval_tree_span_iter reserved_span; + unsigned long page_offset = uptr % PAGE_SIZE; + struct interval_tree_span_iter allowed_span; + struct interval_tree_span_iter area_span; + unsigned long iova_alignment; + + lockdep_assert_held(&iopt->iova_rwsem); + + /* Protect roundup_pow-of_two() from overflow */ + if (length == 0 || length >= ULONG_MAX / 2) + return -EOVERFLOW; + + /* + * Keep alignment present in the uptr when building the IOVA, this + * increases the chance we can map a THP. + */ + if (!uptr) + iova_alignment = roundup_pow_of_two(length); + else + iova_alignment = min_t(unsigned long, + roundup_pow_of_two(length), + 1UL << __ffs64(uptr)); + + if (iova_alignment < iopt->iova_alignment) + return -EINVAL; + + interval_tree_for_each_span(&allowed_span, &iopt->allowed_itree, + PAGE_SIZE, ULONG_MAX - PAGE_SIZE) { + if (RB_EMPTY_ROOT(&iopt->allowed_itree.rb_root)) { + allowed_span.start_used = PAGE_SIZE; + allowed_span.last_used = ULONG_MAX - PAGE_SIZE; + allowed_span.is_hole = false; + } + + if (!__alloc_iova_check_used(&allowed_span, length, + iova_alignment, page_offset)) + continue; + + interval_tree_for_each_span(&area_span, &iopt->area_itree, + allowed_span.start_used, + allowed_span.last_used) { + if (!__alloc_iova_check_hole(&area_span, length, + iova_alignment, + page_offset)) + continue; + + interval_tree_for_each_span(&reserved_span, + &iopt->reserved_itree, + area_span.start_used, + area_span.last_used) { + if (!__alloc_iova_check_hole( + &reserved_span, length, + iova_alignment, page_offset)) + continue; + + *iova = reserved_span.start_hole; + return 0; + } + } + } + return -ENOSPC; +} + +static int iopt_check_iova(struct io_pagetable *iopt, unsigned long iova, + unsigned long length) +{ + unsigned long last; + + lockdep_assert_held(&iopt->iova_rwsem); + + if ((iova & (iopt->iova_alignment - 1))) + return -EINVAL; + + if (check_add_overflow(iova, length - 1, &last)) + return -EOVERFLOW; + + /* No reserved IOVA intersects the range */ + if (iopt_reserved_iter_first(iopt, iova, last)) + return -ENOENT; + + /* Check that there is not already a mapping in the range */ + if (iopt_area_iter_first(iopt, iova, last)) + return -EADDRINUSE; + return 0; +} + +/* + * The area takes a slice of the pages from start_bytes to start_byte + length + */ +static int iopt_insert_area(struct io_pagetable *iopt, struct iopt_area *area, + struct iopt_pages *pages, unsigned long iova, + unsigned long start_byte, unsigned long length, + int iommu_prot) +{ + lockdep_assert_held_write(&iopt->iova_rwsem); + + if ((iommu_prot & IOMMU_WRITE) && !pages->writable) + return -EPERM; + + area->iommu_prot = iommu_prot; + area->page_offset = start_byte % PAGE_SIZE; + if (area->page_offset & (iopt->iova_alignment - 1)) + return -EINVAL; + + area->node.start = iova; + if (check_add_overflow(iova, length - 1, &area->node.last)) + return -EOVERFLOW; + + area->pages_node.start = start_byte / PAGE_SIZE; + if (check_add_overflow(start_byte, length - 1, &area->pages_node.last)) + return -EOVERFLOW; + area->pages_node.last = area->pages_node.last / PAGE_SIZE; + if (WARN_ON(area->pages_node.last >= pages->npages)) + return -EOVERFLOW; + + /* + * The area is inserted with a NULL pages indicating it is not fully + * initialized yet. + */ + area->iopt = iopt; + interval_tree_insert(&area->node, &iopt->area_itree); + return 0; +} + +static int iopt_alloc_area_pages(struct io_pagetable *iopt, + struct list_head *pages_list, + unsigned long length, unsigned long *dst_iova, + int iommu_prot, unsigned int flags) +{ + struct iopt_pages_list *elm; + unsigned long iova; + int rc = 0; + + list_for_each_entry(elm, pages_list, next) { + elm->area = kzalloc(sizeof(*elm->area), GFP_KERNEL_ACCOUNT); + if (!elm->area) + return -ENOMEM; + } + + down_write(&iopt->iova_rwsem); + if ((length & (iopt->iova_alignment - 1)) || !length) { + rc = -EINVAL; + goto out_unlock; + } + + if (flags & IOPT_ALLOC_IOVA) { + /* Use the first entry to guess the ideal IOVA alignment */ + elm = list_first_entry(pages_list, struct iopt_pages_list, + next); + rc = iopt_alloc_iova( + iopt, dst_iova, + (uintptr_t)elm->pages->uptr + elm->start_byte, length); + if (rc) + goto out_unlock; + } else { + rc = iopt_check_iova(iopt, *dst_iova, length); + if (rc) + goto out_unlock; + } + + /* + * Areas are created with a NULL pages so that the IOVA space is + * reserved and we can unlock the iova_rwsem. + */ + iova = *dst_iova; + list_for_each_entry(elm, pages_list, next) { + rc = iopt_insert_area(iopt, elm->area, elm->pages, iova, + elm->start_byte, elm->length, iommu_prot); + if (rc) + goto out_unlock; + iova += elm->length; + } + +out_unlock: + up_write(&iopt->iova_rwsem); + return rc; +} + +static void iopt_abort_area(struct iopt_area *area) +{ + if (area->iopt) { + down_write(&area->iopt->iova_rwsem); + interval_tree_remove(&area->node, &area->iopt->area_itree); + up_write(&area->iopt->iova_rwsem); + } + kfree(area); +} + +void iopt_free_pages_list(struct list_head *pages_list) +{ + struct iopt_pages_list *elm; + + while ((elm = list_first_entry_or_null(pages_list, + struct iopt_pages_list, next))) { + if (elm->area) + iopt_abort_area(elm->area); + if (elm->pages) + iopt_put_pages(elm->pages); + list_del(&elm->next); + kfree(elm); + } +} + +static int iopt_fill_domains_pages(struct list_head *pages_list) +{ + struct iopt_pages_list *undo_elm; + struct iopt_pages_list *elm; + int rc; + + list_for_each_entry(elm, pages_list, next) { + rc = iopt_area_fill_domains(elm->area, elm->pages); + if (rc) + goto err_undo; + } + return 0; + +err_undo: + list_for_each_entry(undo_elm, pages_list, next) { + if (undo_elm == elm) + break; + iopt_area_unfill_domains(undo_elm->area, undo_elm->pages); + } + return rc; +} + +int iopt_map_pages(struct io_pagetable *iopt, struct list_head *pages_list, + unsigned long length, unsigned long *dst_iova, + int iommu_prot, unsigned int flags) +{ + struct iopt_pages_list *elm; + int rc; + + rc = iopt_alloc_area_pages(iopt, pages_list, length, dst_iova, + iommu_prot, flags); + if (rc) + return rc; + + down_read(&iopt->domains_rwsem); + rc = iopt_fill_domains_pages(pages_list); + if (rc) + goto out_unlock_domains; + + down_write(&iopt->iova_rwsem); + list_for_each_entry(elm, pages_list, next) { + /* + * area->pages must be set inside the domains_rwsem to ensure + * any newly added domains will get filled. Moves the reference + * in from the list. + */ + elm->area->pages = elm->pages; + elm->pages = NULL; + elm->area = NULL; + } + up_write(&iopt->iova_rwsem); +out_unlock_domains: + up_read(&iopt->domains_rwsem); + return rc; +} + +/** + * iopt_map_user_pages() - Map a user VA to an iova in the io page table + * @ictx: iommufd_ctx the iopt is part of + * @iopt: io_pagetable to act on + * @iova: If IOPT_ALLOC_IOVA is set this is unused on input and contains + * the chosen iova on output. Otherwise is the iova to map to on input + * @uptr: User VA to map + * @length: Number of bytes to map + * @iommu_prot: Combination of IOMMU_READ/WRITE/etc bits for the mapping + * @flags: IOPT_ALLOC_IOVA or zero + * + * iova, uptr, and length must be aligned to iova_alignment. For domain backed + * page tables this will pin the pages and load them into the domain at iova. + * For non-domain page tables this will only setup a lazy reference and the + * caller must use iopt_access_pages() to touch them. + * + * iopt_unmap_iova() must be called to undo this before the io_pagetable can be + * destroyed. + */ +int iopt_map_user_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt, + unsigned long *iova, void __user *uptr, + unsigned long length, int iommu_prot, + unsigned int flags) +{ + struct iopt_pages_list elm = {}; + LIST_HEAD(pages_list); + int rc; + + elm.pages = iopt_alloc_pages(uptr, length, iommu_prot & IOMMU_WRITE); + if (IS_ERR(elm.pages)) + return PTR_ERR(elm.pages); + if (ictx->account_mode == IOPT_PAGES_ACCOUNT_MM && + elm.pages->account_mode == IOPT_PAGES_ACCOUNT_USER) + elm.pages->account_mode = IOPT_PAGES_ACCOUNT_MM; + elm.start_byte = uptr - elm.pages->uptr; + elm.length = length; + list_add(&elm.next, &pages_list); + + rc = iopt_map_pages(iopt, &pages_list, length, iova, iommu_prot, flags); + if (rc) { + if (elm.area) + iopt_abort_area(elm.area); + if (elm.pages) + iopt_put_pages(elm.pages); + return rc; + } + return 0; +} + +int iopt_get_pages(struct io_pagetable *iopt, unsigned long iova, + unsigned long length, struct list_head *pages_list) +{ + struct iopt_area_contig_iter iter; + unsigned long last_iova; + struct iopt_area *area; + int rc; + + if (!length) + return -EINVAL; + if (check_add_overflow(iova, length - 1, &last_iova)) + return -EOVERFLOW; + + down_read(&iopt->iova_rwsem); + iopt_for_each_contig_area(&iter, area, iopt, iova, last_iova) { + struct iopt_pages_list *elm; + unsigned long last = min(last_iova, iopt_area_last_iova(area)); + + elm = kzalloc(sizeof(*elm), GFP_KERNEL_ACCOUNT); + if (!elm) { + rc = -ENOMEM; + goto err_free; + } + elm->start_byte = iopt_area_start_byte(area, iter.cur_iova); + elm->pages = area->pages; + elm->length = (last - iter.cur_iova) + 1; + kref_get(&elm->pages->kref); + list_add_tail(&elm->next, pages_list); + } + if (!iopt_area_contig_done(&iter)) { + rc = -ENOENT; + goto err_free; + } + up_read(&iopt->iova_rwsem); + return 0; +err_free: + up_read(&iopt->iova_rwsem); + iopt_free_pages_list(pages_list); + return rc; +} + +static int iopt_unmap_iova_range(struct io_pagetable *iopt, unsigned long start, + unsigned long end, unsigned long *unmapped) +{ + struct iopt_area *area; + unsigned long unmapped_bytes = 0; + int rc = -ENOENT; + + /* + * The domains_rwsem must be held in read mode any time any area->pages + * is NULL. This prevents domain attach/detatch from running + * concurrently with cleaning up the area. + */ + down_read(&iopt->domains_rwsem); + down_write(&iopt->iova_rwsem); + while ((area = iopt_area_iter_first(iopt, start, end))) { + unsigned long area_last = iopt_area_last_iova(area); + unsigned long area_first = iopt_area_iova(area); + struct iopt_pages *pages; + + /* Userspace should not race map/unmap's of the same area */ + if (!area->pages) { + rc = -EBUSY; + goto out_unlock_iova; + } + + if (area_first < start || area_last > end) { + rc = -ENOENT; + goto out_unlock_iova; + } + + /* + * num_accesses writers must hold the iova_rwsem too, so we can + * safely read it under the write side of the iovam_rwsem + * without the pages->mutex. + */ + if (area->num_accesses) { + start = area_first; + area->prevent_access = true; + up_write(&iopt->iova_rwsem); + up_read(&iopt->domains_rwsem); + /* Later patch calls back to drivers to unmap */ + return -EBUSY; + } + + pages = area->pages; + area->pages = NULL; + up_write(&iopt->iova_rwsem); + + iopt_area_unfill_domains(area, pages); + iopt_abort_area(area); + iopt_put_pages(pages); + + unmapped_bytes += area_last - area_first + 1; + + down_write(&iopt->iova_rwsem); + } + if (unmapped_bytes) + rc = 0; + +out_unlock_iova: + up_write(&iopt->iova_rwsem); + up_read(&iopt->domains_rwsem); + if (unmapped) + *unmapped = unmapped_bytes; + return rc; +} + +/** + * iopt_unmap_iova() - Remove a range of iova + * @iopt: io_pagetable to act on + * @iova: Starting iova to unmap + * @length: Number of bytes to unmap + * @unmapped: Return number of bytes unmapped + * + * The requested range must be a superset of existing ranges. + * Splitting/truncating IOVA mappings is not allowed. + */ +int iopt_unmap_iova(struct io_pagetable *iopt, unsigned long iova, + unsigned long length, unsigned long *unmapped) +{ + unsigned long iova_end; + + if (!length) + return -EINVAL; + + if (check_add_overflow(iova, length - 1, &iova_end)) + return -EOVERFLOW; + + return iopt_unmap_iova_range(iopt, iova, iova_end, unmapped); +} + +int iopt_unmap_all(struct io_pagetable *iopt, unsigned long *unmapped) +{ + int rc; + + rc = iopt_unmap_iova_range(iopt, 0, ULONG_MAX, unmapped); + /* If the IOVAs are empty then unmap all succeeds */ + if (rc == -ENOENT) + return 0; + return rc; +} + +/* The caller must always free all the nodes in the allowed_iova rb_root. */ +int iopt_set_allow_iova(struct io_pagetable *iopt, + struct rb_root_cached *allowed_iova) +{ + struct iopt_allowed *allowed; + + down_write(&iopt->iova_rwsem); + swap(*allowed_iova, iopt->allowed_itree); + + for (allowed = iopt_allowed_iter_first(iopt, 0, ULONG_MAX); allowed; + allowed = iopt_allowed_iter_next(allowed, 0, ULONG_MAX)) { + if (iopt_reserved_iter_first(iopt, allowed->node.start, + allowed->node.last)) { + swap(*allowed_iova, iopt->allowed_itree); + up_write(&iopt->iova_rwsem); + return -EADDRINUSE; + } + } + up_write(&iopt->iova_rwsem); + return 0; +} + +int iopt_reserve_iova(struct io_pagetable *iopt, unsigned long start, + unsigned long last, void *owner) +{ + struct iopt_reserved *reserved; + + lockdep_assert_held_write(&iopt->iova_rwsem); + + if (iopt_area_iter_first(iopt, start, last) || + iopt_allowed_iter_first(iopt, start, last)) + return -EADDRINUSE; + + reserved = kzalloc(sizeof(*reserved), GFP_KERNEL_ACCOUNT); + if (!reserved) + return -ENOMEM; + reserved->node.start = start; + reserved->node.last = last; + reserved->owner = owner; + interval_tree_insert(&reserved->node, &iopt->reserved_itree); + return 0; +} + +static void __iopt_remove_reserved_iova(struct io_pagetable *iopt, void *owner) +{ + struct iopt_reserved *reserved, *next; + + lockdep_assert_held_write(&iopt->iova_rwsem); + + for (reserved = iopt_reserved_iter_first(iopt, 0, ULONG_MAX); reserved; + reserved = next) { + next = iopt_reserved_iter_next(reserved, 0, ULONG_MAX); + + if (reserved->owner == owner) { + interval_tree_remove(&reserved->node, + &iopt->reserved_itree); + kfree(reserved); + } + } +} + +void iopt_remove_reserved_iova(struct io_pagetable *iopt, void *owner) +{ + down_write(&iopt->iova_rwsem); + __iopt_remove_reserved_iova(iopt, owner); + up_write(&iopt->iova_rwsem); +} + +void iopt_init_table(struct io_pagetable *iopt) +{ + init_rwsem(&iopt->iova_rwsem); + init_rwsem(&iopt->domains_rwsem); + iopt->area_itree = RB_ROOT_CACHED; + iopt->allowed_itree = RB_ROOT_CACHED; + iopt->reserved_itree = RB_ROOT_CACHED; + xa_init_flags(&iopt->domains, XA_FLAGS_ACCOUNT); + xa_init_flags(&iopt->access_list, XA_FLAGS_ALLOC); + + /* + * iopt's start as SW tables that can use the entire size_t IOVA space + * due to the use of size_t in the APIs. They have no alignment + * restriction. + */ + iopt->iova_alignment = 1; +} + +void iopt_destroy_table(struct io_pagetable *iopt) +{ + struct interval_tree_node *node; + + while ((node = interval_tree_iter_first(&iopt->allowed_itree, 0, + ULONG_MAX))) { + interval_tree_remove(node, &iopt->allowed_itree); + kfree(container_of(node, struct iopt_allowed, node)); + } + + WARN_ON(!RB_EMPTY_ROOT(&iopt->reserved_itree.rb_root)); + WARN_ON(!xa_empty(&iopt->domains)); + WARN_ON(!xa_empty(&iopt->access_list)); + WARN_ON(!RB_EMPTY_ROOT(&iopt->area_itree.rb_root)); +} + +/** + * iopt_unfill_domain() - Unfill a domain with PFNs + * @iopt: io_pagetable to act on + * @domain: domain to unfill + * + * This is used when removing a domain from the iopt. Every area in the iopt + * will be unmapped from the domain. The domain must already be removed from the + * domains xarray. + */ +static void iopt_unfill_domain(struct io_pagetable *iopt, + struct iommu_domain *domain) +{ + struct iopt_area *area; + + lockdep_assert_held(&iopt->iova_rwsem); + lockdep_assert_held_write(&iopt->domains_rwsem); + + /* + * Some other domain is holding all the pfns still, rapidly unmap this + * domain. + */ + if (iopt->next_domain_id != 0) { + /* Pick an arbitrary remaining domain to act as storage */ + struct iommu_domain *storage_domain = + xa_load(&iopt->domains, 0); + + for (area = iopt_area_iter_first(iopt, 0, ULONG_MAX); area; + area = iopt_area_iter_next(area, 0, ULONG_MAX)) { + struct iopt_pages *pages = area->pages; + + if (!pages) + continue; + + mutex_lock(&pages->mutex); + if (area->storage_domain == domain) + area->storage_domain = storage_domain; + mutex_unlock(&pages->mutex); + + iopt_area_unmap_domain(area, domain); + } + return; + } + + for (area = iopt_area_iter_first(iopt, 0, ULONG_MAX); area; + area = iopt_area_iter_next(area, 0, ULONG_MAX)) { + struct iopt_pages *pages = area->pages; + + if (!pages) + continue; + + mutex_lock(&pages->mutex); + interval_tree_remove(&area->pages_node, &pages->domains_itree); + WARN_ON(area->storage_domain != domain); + area->storage_domain = NULL; + iopt_area_unfill_domain(area, pages, domain); + mutex_unlock(&pages->mutex); + } +} + +/** + * iopt_fill_domain() - Fill a domain with PFNs + * @iopt: io_pagetable to act on + * @domain: domain to fill + * + * Fill the domain with PFNs from every area in the iopt. On failure the domain + * is left unchanged. + */ +static int iopt_fill_domain(struct io_pagetable *iopt, + struct iommu_domain *domain) +{ + struct iopt_area *end_area; + struct iopt_area *area; + int rc; + + lockdep_assert_held(&iopt->iova_rwsem); + lockdep_assert_held_write(&iopt->domains_rwsem); + + for (area = iopt_area_iter_first(iopt, 0, ULONG_MAX); area; + area = iopt_area_iter_next(area, 0, ULONG_MAX)) { + struct iopt_pages *pages = area->pages; + + if (!pages) + continue; + + mutex_lock(&pages->mutex); + rc = iopt_area_fill_domain(area, domain); + if (rc) { + mutex_unlock(&pages->mutex); + goto out_unfill; + } + if (!area->storage_domain) { + WARN_ON(iopt->next_domain_id != 0); + area->storage_domain = domain; + interval_tree_insert(&area->pages_node, + &pages->domains_itree); + } + mutex_unlock(&pages->mutex); + } + return 0; + +out_unfill: + end_area = area; + for (area = iopt_area_iter_first(iopt, 0, ULONG_MAX); area; + area = iopt_area_iter_next(area, 0, ULONG_MAX)) { + struct iopt_pages *pages = area->pages; + + if (area == end_area) + break; + if (!pages) + continue; + mutex_lock(&pages->mutex); + if (iopt->next_domain_id == 0) { + interval_tree_remove(&area->pages_node, + &pages->domains_itree); + area->storage_domain = NULL; + } + iopt_area_unfill_domain(area, pages, domain); + mutex_unlock(&pages->mutex); + } + return rc; +} + +/* All existing area's conform to an increased page size */ +static int iopt_check_iova_alignment(struct io_pagetable *iopt, + unsigned long new_iova_alignment) +{ + unsigned long align_mask = new_iova_alignment - 1; + struct iopt_area *area; + + lockdep_assert_held(&iopt->iova_rwsem); + lockdep_assert_held(&iopt->domains_rwsem); + + for (area = iopt_area_iter_first(iopt, 0, ULONG_MAX); area; + area = iopt_area_iter_next(area, 0, ULONG_MAX)) + if ((iopt_area_iova(area) & align_mask) || + (iopt_area_length(area) & align_mask) || + (area->page_offset & align_mask)) + return -EADDRINUSE; + return 0; +} + +int iopt_table_add_domain(struct io_pagetable *iopt, + struct iommu_domain *domain) +{ + const struct iommu_domain_geometry *geometry = &domain->geometry; + struct iommu_domain *iter_domain; + unsigned int new_iova_alignment; + unsigned long index; + int rc; + + down_write(&iopt->domains_rwsem); + down_write(&iopt->iova_rwsem); + + xa_for_each(&iopt->domains, index, iter_domain) { + if (WARN_ON(iter_domain == domain)) { + rc = -EEXIST; + goto out_unlock; + } + } + + /* + * The io page size drives the iova_alignment. Internally the iopt_pages + * works in PAGE_SIZE units and we adjust when mapping sub-PAGE_SIZE + * objects into the iommu_domain. + * + * A iommu_domain must always be able to accept PAGE_SIZE to be + * compatible as we can't guarantee higher contiguity. + */ + new_iova_alignment = max_t(unsigned long, + 1UL << __ffs(domain->pgsize_bitmap), + iopt->iova_alignment); + if (new_iova_alignment > PAGE_SIZE) { + rc = -EINVAL; + goto out_unlock; + } + if (new_iova_alignment != iopt->iova_alignment) { + rc = iopt_check_iova_alignment(iopt, new_iova_alignment); + if (rc) + goto out_unlock; + } + + /* No area exists that is outside the allowed domain aperture */ + if (geometry->aperture_start != 0) { + rc = iopt_reserve_iova(iopt, 0, geometry->aperture_start - 1, + domain); + if (rc) + goto out_reserved; + } + if (geometry->aperture_end != ULONG_MAX) { + rc = iopt_reserve_iova(iopt, geometry->aperture_end + 1, + ULONG_MAX, domain); + if (rc) + goto out_reserved; + } + + rc = xa_reserve(&iopt->domains, iopt->next_domain_id, GFP_KERNEL); + if (rc) + goto out_reserved; + + rc = iopt_fill_domain(iopt, domain); + if (rc) + goto out_release; + + iopt->iova_alignment = new_iova_alignment; + xa_store(&iopt->domains, iopt->next_domain_id, domain, GFP_KERNEL); + iopt->next_domain_id++; + up_write(&iopt->iova_rwsem); + up_write(&iopt->domains_rwsem); + return 0; +out_release: + xa_release(&iopt->domains, iopt->next_domain_id); +out_reserved: + __iopt_remove_reserved_iova(iopt, domain); +out_unlock: + up_write(&iopt->iova_rwsem); + up_write(&iopt->domains_rwsem); + return rc; +} + +static int iopt_calculate_iova_alignment(struct io_pagetable *iopt) +{ + unsigned long new_iova_alignment; + struct iommufd_access *access; + struct iommu_domain *domain; + unsigned long index; + + lockdep_assert_held_write(&iopt->iova_rwsem); + lockdep_assert_held(&iopt->domains_rwsem); + + if (iopt->disable_large_pages) + new_iova_alignment = PAGE_SIZE; + else + new_iova_alignment = 1; + + xa_for_each(&iopt->domains, index, domain) + new_iova_alignment = max_t(unsigned long, + 1UL << __ffs(domain->pgsize_bitmap), + new_iova_alignment); + xa_for_each(&iopt->access_list, index, access) + new_iova_alignment = max_t(unsigned long, + access->iova_alignment, + new_iova_alignment); + + if (new_iova_alignment > iopt->iova_alignment) { + int rc; + + rc = iopt_check_iova_alignment(iopt, new_iova_alignment); + if (rc) + return rc; + } + iopt->iova_alignment = new_iova_alignment; + return 0; +} + +void iopt_table_remove_domain(struct io_pagetable *iopt, + struct iommu_domain *domain) +{ + struct iommu_domain *iter_domain = NULL; + unsigned long index; + + down_write(&iopt->domains_rwsem); + down_write(&iopt->iova_rwsem); + + xa_for_each(&iopt->domains, index, iter_domain) + if (iter_domain == domain) + break; + if (WARN_ON(iter_domain != domain) || index >= iopt->next_domain_id) + goto out_unlock; + + /* + * Compress the xarray to keep it linear by swapping the entry to erase + * with the tail entry and shrinking the tail. + */ + iopt->next_domain_id--; + iter_domain = xa_erase(&iopt->domains, iopt->next_domain_id); + if (index != iopt->next_domain_id) + xa_store(&iopt->domains, index, iter_domain, GFP_KERNEL); + + iopt_unfill_domain(iopt, domain); + __iopt_remove_reserved_iova(iopt, domain); + + WARN_ON(iopt_calculate_iova_alignment(iopt)); +out_unlock: + up_write(&iopt->iova_rwsem); + up_write(&iopt->domains_rwsem); +} + +/** + * iopt_area_split - Split an area into two parts at iova + * @area: The area to split + * @iova: Becomes the last of a new area + * + * This splits an area into two. It is part of the VFIO compatibility to allow + * poking a hole in the mapping. The two areas continue to point at the same + * iopt_pages, just with different starting bytes. + */ +static int iopt_area_split(struct iopt_area *area, unsigned long iova) +{ + unsigned long alignment = area->iopt->iova_alignment; + unsigned long last_iova = iopt_area_last_iova(area); + unsigned long start_iova = iopt_area_iova(area); + unsigned long new_start = iova + 1; + struct io_pagetable *iopt = area->iopt; + struct iopt_pages *pages = area->pages; + struct iopt_area *lhs; + struct iopt_area *rhs; + int rc; + + lockdep_assert_held_write(&iopt->iova_rwsem); + + if (iova == start_iova || iova == last_iova) + return 0; + + if (!pages || area->prevent_access) + return -EBUSY; + + if (new_start & (alignment - 1) || + iopt_area_start_byte(area, new_start) & (alignment - 1)) + return -EINVAL; + + lhs = kzalloc(sizeof(*area), GFP_KERNEL_ACCOUNT); + if (!lhs) + return -ENOMEM; + + rhs = kzalloc(sizeof(*area), GFP_KERNEL_ACCOUNT); + if (!rhs) { + rc = -ENOMEM; + goto err_free_lhs; + } + + mutex_lock(&pages->mutex); + /* + * Splitting is not permitted if a domain could have been mapped with + * huge pages. + */ + if (area->storage_domain && !iopt->disable_large_pages) { + rc = -EINVAL; + goto err_unlock; + } + + interval_tree_remove(&area->node, &iopt->area_itree); + rc = iopt_insert_area(iopt, lhs, area->pages, start_iova, + iopt_area_start_byte(area, start_iova), + (new_start - 1) - start_iova + 1, + area->iommu_prot); + if (WARN_ON(rc)) + goto err_insert; + + rc = iopt_insert_area(iopt, rhs, area->pages, new_start, + iopt_area_start_byte(area, new_start), + last_iova - new_start + 1, area->iommu_prot); + if (WARN_ON(rc)) + goto err_remove_lhs; + + lhs->storage_domain = area->storage_domain; + lhs->num_accesses = area->num_accesses; + lhs->pages = area->pages; + rhs->storage_domain = area->storage_domain; + rhs->num_accesses = area->num_accesses; + rhs->pages = area->pages; + kref_get(&rhs->pages->kref); + kfree(area); + mutex_unlock(&pages->mutex); + + /* + * No change to domains or accesses because the pages hasn't been + * changed + */ + return 0; + +err_remove_lhs: + interval_tree_remove(&lhs->node, &iopt->area_itree); +err_insert: + interval_tree_insert(&area->node, &iopt->area_itree); +err_unlock: + mutex_unlock(&pages->mutex); + kfree(rhs); +err_free_lhs: + kfree(lhs); + return rc; +} + +int iopt_cut_iova(struct io_pagetable *iopt, unsigned long *iovas, + size_t num_iovas) +{ + int rc = 0; + int i; + + down_write(&iopt->iova_rwsem); + for (i = 0; i < num_iovas; i++) { + struct iopt_area *area; + + area = iopt_area_iter_first(iopt, iovas[i], iovas[i]); + if (!area) + continue; + rc = iopt_area_split(area, iovas[i]); + if (rc) + break; + } + up_write(&iopt->iova_rwsem); + return rc; +} + +void iopt_enable_large_pages(struct io_pagetable *iopt) +{ + int rc; + + down_write(&iopt->domains_rwsem); + down_write(&iopt->iova_rwsem); + WRITE_ONCE(iopt->disable_large_pages, false); + rc = iopt_calculate_iova_alignment(iopt); + WARN_ON(rc); + up_write(&iopt->iova_rwsem); + up_write(&iopt->domains_rwsem); +} + +int iopt_disable_large_pages(struct io_pagetable *iopt) +{ + int rc = 0; + + down_write(&iopt->domains_rwsem); + down_write(&iopt->iova_rwsem); + if (iopt->disable_large_pages) + goto out_unlock; + + /* Won't do it if domains already have pages mapped in them */ + if (!xa_empty(&iopt->domains) && + !RB_EMPTY_ROOT(&iopt->area_itree.rb_root)) { + rc = -EINVAL; + goto out_unlock; + } + + WRITE_ONCE(iopt->disable_large_pages, true); + rc = iopt_calculate_iova_alignment(iopt); + if (rc) + WRITE_ONCE(iopt->disable_large_pages, false); +out_unlock: + up_write(&iopt->iova_rwsem); + up_write(&iopt->domains_rwsem); + return rc; +} + +int iopt_add_access(struct io_pagetable *iopt, struct iommufd_access *access) +{ + int rc; + + down_write(&iopt->domains_rwsem); + down_write(&iopt->iova_rwsem); + rc = xa_alloc(&iopt->access_list, &access->iopt_access_list_id, access, + xa_limit_16b, GFP_KERNEL_ACCOUNT); + if (rc) + goto out_unlock; + + rc = iopt_calculate_iova_alignment(iopt); + if (rc) { + xa_erase(&iopt->access_list, access->iopt_access_list_id); + goto out_unlock; + } + +out_unlock: + up_write(&iopt->iova_rwsem); + up_write(&iopt->domains_rwsem); + return rc; +} + +void iopt_remove_access(struct io_pagetable *iopt, + struct iommufd_access *access) +{ + down_write(&iopt->domains_rwsem); + down_write(&iopt->iova_rwsem); + WARN_ON(xa_erase(&iopt->access_list, access->iopt_access_list_id) != + access); + WARN_ON(iopt_calculate_iova_alignment(iopt)); + up_write(&iopt->iova_rwsem); + up_write(&iopt->domains_rwsem); +} + +/* Narrow the valid_iova_itree to include reserved ranges from a group. */ +int iopt_table_enforce_group_resv_regions(struct io_pagetable *iopt, + struct device *device, + struct iommu_group *group, + phys_addr_t *sw_msi_start) +{ + struct iommu_resv_region *resv; + struct iommu_resv_region *tmp; + LIST_HEAD(group_resv_regions); + int rc; + + down_write(&iopt->iova_rwsem); + rc = iommu_get_group_resv_regions(group, &group_resv_regions); + if (rc) + goto out_unlock; + + list_for_each_entry(resv, &group_resv_regions, list) { + if (resv->type == IOMMU_RESV_DIRECT_RELAXABLE) + continue; + + /* + * The presence of any 'real' MSI regions should take precedence + * over the software-managed one if the IOMMU driver happens to + * advertise both types. + */ + if (sw_msi_start && resv->type == IOMMU_RESV_MSI) { + *sw_msi_start = 0; + sw_msi_start = NULL; + } + if (sw_msi_start && resv->type == IOMMU_RESV_SW_MSI) + *sw_msi_start = resv->start; + + rc = iopt_reserve_iova(iopt, resv->start, + resv->length - 1 + resv->start, device); + if (rc) + goto out_reserved; + } + rc = 0; + goto out_free_resv; + +out_reserved: + __iopt_remove_reserved_iova(iopt, device); +out_free_resv: + list_for_each_entry_safe(resv, tmp, &group_resv_regions, list) + kfree(resv); +out_unlock: + up_write(&iopt->iova_rwsem); + return rc; +} diff --git a/drivers/iommu/iommufd/io_pagetable.h b/drivers/iommu/iommufd/io_pagetable.h index aebb9a496258ce..9a1c8a5ae3c883 100644 --- a/drivers/iommu/iommufd/io_pagetable.h +++ b/drivers/iommu/iommufd/io_pagetable.h @@ -46,9 +46,19 @@ struct iopt_area { unsigned int page_offset; /* IOMMU_READ, IOMMU_WRITE, etc */ int iommu_prot; + bool prevent_access : 1; unsigned int num_accesses; };

+struct iopt_allowed { + struct interval_tree_node node; +}; + +struct iopt_reserved { + struct interval_tree_node node; + void *owner; +}; + int iopt_area_fill_domains(struct iopt_area *area, struct iopt_pages *pages); void iopt_area_unfill_domains(struct iopt_area *area, struct iopt_pages *pages);

@@ -83,6 +93,24 @@ static inline size_t iopt_area_length(struct iopt_area *area) return (area->node.last - area->node.start) + 1; }

+/* + * Number of bytes from the start of the iopt_pages that the iova begins. + * iopt_area_start_byte() / PAGE_SIZE encodes the starting page index + * iopt_area_start_byte() % PAGE_SIZE encodes the offset within that page + */ +static inline unsigned long iopt_area_start_byte(struct iopt_area *area, + unsigned long iova) +{ + return (iova - iopt_area_iova(area)) + area->page_offset + + iopt_area_index(area) * PAGE_SIZE; +} + +static inline unsigned long iopt_area_iova_to_index(struct iopt_area *area, + unsigned long iova) +{ + return iopt_area_start_byte(area, iova) / PAGE_SIZE; +} + #define __make_iopt_iter(name) \ static inline struct iopt_##name *iopt_##name##_iter_first( \ struct io_pagetable *iopt, unsigned long start, \ @@ -110,6 +138,33 @@ static inline size_t iopt_area_length(struct iopt_area *area) }

__make_iopt_iter(area) +__make_iopt_iter(allowed) +__make_iopt_iter(reserved) + +struct iopt_area_contig_iter { + unsigned long cur_iova; + unsigned long last_iova; + struct iopt_area *area; +}; +struct iopt_area *iopt_area_contig_init(struct iopt_area_contig_iter *iter, + struct io_pagetable *iopt, + unsigned long iova, + unsigned long last_iova); +struct iopt_area *iopt_area_contig_next(struct iopt_area_contig_iter *iter); + +static inline bool iopt_area_contig_done(struct iopt_area_contig_iter *iter) +{ + return iter->area && iter->last_iova <= iopt_area_last_iova(iter->area); +} + +/* + * Iterate over a contiguous list of areas that span the iova,last_iova range. + * The caller must check iopt_area_contig_done() after the loop to see if + * contiguous areas existed. + */ +#define iopt_for_each_contig_area(iter, area, iopt, iova, last_iova) \ + for (area = iopt_area_contig_init(iter, iopt, iova, last_iova); area; \ + area = iopt_area_contig_next(iter))

enum { IOPT_PAGES_ACCOUNT_NONE = 0, diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 6ed6f99ee439fa..6b7e0982b8c802 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -9,9 +9,14 @@ #include <linux/refcount.h> #include <linux/uaccess.h>

+struct iommu_domain; +struct iommu_group; + struct iommufd_ctx { struct file *file; struct xarray objects; + + u8 account_mode; };

/* @@ -27,6 +32,7 @@ struct iommufd_ctx { struct io_pagetable { struct rw_semaphore domains_rwsem; struct xarray domains; + struct xarray access_list; unsigned int next_domain_id;

struct rw_semaphore iova_rwsem; @@ -36,7 +42,45 @@ struct io_pagetable { /* IOVA that cannot be allocated, struct iopt_reserved */ struct rb_root_cached reserved_itree; u8 disable_large_pages; + unsigned long iova_alignment; +}; + +void iopt_init_table(struct io_pagetable *iopt); +void iopt_destroy_table(struct io_pagetable *iopt); +int iopt_get_pages(struct io_pagetable *iopt, unsigned long iova, + unsigned long length, struct list_head *pages_list); +void iopt_free_pages_list(struct list_head *pages_list); +enum { + IOPT_ALLOC_IOVA = 1 << 0, }; +int iopt_map_user_pages(struct iommufd_ctx *ictx, struct io_pagetable *iopt, + unsigned long *iova, void __user *uptr, + unsigned long length, int iommu_prot, + unsigned int flags); +int iopt_map_pages(struct io_pagetable *iopt, struct list_head *pages_list, + unsigned long length, unsigned long *dst_iova, + int iommu_prot, unsigned int flags); +int iopt_unmap_iova(struct io_pagetable *iopt, unsigned long iova, + unsigned long length, unsigned long *unmapped); +int iopt_unmap_all(struct io_pagetable *iopt, unsigned long *unmapped); + +int iopt_table_add_domain(struct io_pagetable *iopt, + struct iommu_domain *domain); +void iopt_table_remove_domain(struct io_pagetable *iopt, + struct iommu_domain *domain); +int iopt_table_enforce_group_resv_regions(struct io_pagetable *iopt, + struct device *device, + struct iommu_group *group, + phys_addr_t *sw_msi_start); +int iopt_set_allow_iova(struct io_pagetable *iopt, + struct rb_root_cached *allowed_iova); +int iopt_reserve_iova(struct io_pagetable *iopt, unsigned long start, + unsigned long last, void *owner); +void iopt_remove_reserved_iova(struct io_pagetable *iopt, void *owner); +int iopt_cut_iova(struct io_pagetable *iopt, unsigned long *iovas, + size_t num_iovas); +void iopt_enable_large_pages(struct io_pagetable *iopt); +int iopt_disable_large_pages(struct io_pagetable *iopt);

struct iommufd_ucmd { struct iommufd_ctx *ictx; @@ -130,4 +174,12 @@ struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx, type), \ typeof(*(ptr)), obj)

+struct iommufd_access { + unsigned long iova_alignment; + u32 iopt_access_list_id; +}; + +int iopt_add_access(struct io_pagetable *iopt, struct iommufd_access *access); +void iopt_remove_access(struct io_pagetable *iopt, + struct iommufd_access *access); #endif

Connect the IOAS to its IOCTL interface. This exposes most of the functionality in the io_pagetable to userspace.

This is intended to be the core of the generic interface that IOMMUFD will provide. Every IOMMU driver should be able to implement an iommu_domain that is compatible with this generic mechanism.

It is also designed to be easy to use for simple non virtual machine monitor users, like DPDK: - Universal simple support for all IOMMUs (no PPC special path) - An IOVA allocator that considers the aperture and the allowed/reserved ranges - io_pagetable allows any number of iommu_domains to be connected to the IOAS - Automatic allocation and re-use of iommu_domains

Along with room in the design to add non-generic features to cater to specific HW functionality.

Tested-by: Nicolin Chen nicolinc@nvidia.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com --- drivers/iommu/iommufd/Makefile | 1 + drivers/iommu/iommufd/ioas.c | 384 ++++++++++++++++++++++++ drivers/iommu/iommufd/iommufd_private.h | 33 ++ drivers/iommu/iommufd/main.c | 45 +++ include/uapi/linux/iommufd.h | 241 +++++++++++++++ 5 files changed, 704 insertions(+) create mode 100644 drivers/iommu/iommufd/ioas.c

diff --git a/drivers/iommu/iommufd/Makefile b/drivers/iommu/iommufd/Makefile index b66a8c47ff55ec..2b4f36f1b72f9d 100644 --- a/drivers/iommu/iommufd/Makefile +++ b/drivers/iommu/iommufd/Makefile @@ -1,6 +1,7 @@ # SPDX-License-Identifier: GPL-2.0-only iommufd-y := \ io_pagetable.o \ + ioas.o \ main.o \ pages.o

diff --git a/drivers/iommu/iommufd/ioas.c b/drivers/iommu/iommufd/ioas.c new file mode 100644 index 00000000000000..7671456e86413a --- /dev/null +++ b/drivers/iommu/iommufd/ioas.c @@ -0,0 +1,384 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES + */ +#include <linux/interval_tree.h> +#include <linux/iommufd.h> +#include <linux/iommu.h> +#include <uapi/linux/iommufd.h> + +#include "io_pagetable.h" + +void iommufd_ioas_destroy(struct iommufd_object *obj) +{ + struct iommufd_ioas *ioas = container_of(obj, struct iommufd_ioas, obj); + int rc; + + rc = iopt_unmap_all(&ioas->iopt, NULL); + WARN_ON(rc && rc != -ENOENT); + iopt_destroy_table(&ioas->iopt); +} + +struct iommufd_ioas *iommufd_ioas_alloc(struct iommufd_ctx *ictx) +{ + struct iommufd_ioas *ioas; + + ioas = iommufd_object_alloc(ictx, ioas, IOMMUFD_OBJ_IOAS); + if (IS_ERR(ioas)) + return ioas; + + iopt_init_table(&ioas->iopt); + return ioas; +} + +int iommufd_ioas_alloc_ioctl(struct iommufd_ucmd *ucmd) +{ + struct iommu_ioas_alloc *cmd = ucmd->cmd; + struct iommufd_ioas *ioas; + int rc; + + if (cmd->flags) + return -EOPNOTSUPP; + + ioas = iommufd_ioas_alloc(ucmd->ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + cmd->out_ioas_id = ioas->obj.id; + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); + if (rc) + goto out_table; + iommufd_object_finalize(ucmd->ictx, &ioas->obj); + return 0; + +out_table: + iommufd_object_abort_and_destroy(ucmd->ictx, &ioas->obj); + return rc; +} + +int iommufd_ioas_iova_ranges(struct iommufd_ucmd *ucmd) +{ + struct iommu_iova_range __user *ranges; + struct iommu_ioas_iova_ranges *cmd = ucmd->cmd; + struct iommufd_ioas *ioas; + struct interval_tree_span_iter span; + u32 max_iovas; + int rc; + + if (cmd->__reserved) + return -EOPNOTSUPP; + + ioas = iommufd_get_ioas(ucmd, cmd->ioas_id); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + down_read(&ioas->iopt.iova_rwsem); + max_iovas = cmd->num_iovas; + ranges = u64_to_user_ptr(cmd->allowed_iovas); + cmd->num_iovas = 0; + cmd->out_iova_alignment = ioas->iopt.iova_alignment; + interval_tree_for_each_span(&span, &ioas->iopt.reserved_itree, 0, + ULONG_MAX) { + if (!span.is_hole) + continue; + if (cmd->num_iovas < max_iovas) { + struct iommu_iova_range elm = { + .start = span.start_hole, + .last = span.last_hole, + }; + + if (copy_to_user(&ranges[cmd->num_iovas], &elm, + sizeof(elm))) { + rc = -EFAULT; + goto out_put; + } + } + cmd->num_iovas++; + } + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); + if (rc) + goto out_put; + if (cmd->num_iovas > max_iovas) + rc = -EMSGSIZE; +out_put: + up_read(&ioas->iopt.iova_rwsem); + iommufd_put_object(&ioas->obj); + return rc; +} + +static int iommufd_ioas_load_iovas(struct rb_root_cached *itree, + struct iommu_iova_range __user *ranges, + u32 num) +{ + u32 i; + + for (i = 0; i != num; i++) { + struct iommu_iova_range range; + struct iopt_allowed *allowed; + + if (copy_from_user(&range, ranges + i, sizeof(range))) + return -EFAULT; + + if (range.start >= range.last) + return -EINVAL; + + if (interval_tree_iter_first(itree, range.start, range.last)) + return -EINVAL; + + allowed = kzalloc(sizeof(*allowed), GFP_KERNEL_ACCOUNT); + if (!allowed) + return -ENOMEM; + allowed->node.start = range.start; + allowed->node.last = range.last; + + interval_tree_insert(&allowed->node, itree); + } + return 0; +} + +int iommufd_ioas_allow_iovas(struct iommufd_ucmd *ucmd) +{ + struct iommu_ioas_allow_iovas *cmd = ucmd->cmd; + struct rb_root_cached allowed_iova = RB_ROOT_CACHED; + struct interval_tree_node *node; + struct iommufd_ioas *ioas; + struct io_pagetable *iopt; + int rc = 0; + + if (cmd->__reserved) + return -EOPNOTSUPP; + + ioas = iommufd_get_ioas(ucmd, cmd->ioas_id); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + iopt = &ioas->iopt; + + rc = iommufd_ioas_load_iovas(&allowed_iova, + u64_to_user_ptr(cmd->allowed_iovas), + cmd->num_iovas); + if (rc) + goto out_free; + + rc = iopt_set_allow_iova(iopt, &allowed_iova); +out_free: + while ((node = interval_tree_iter_first(&allowed_iova, 0, ULONG_MAX))) { + interval_tree_remove(node, &allowed_iova); + kfree(container_of(node, struct iopt_allowed, node)); + } + iommufd_put_object(&ioas->obj); + return rc; +} + +static int conv_iommu_prot(u32 map_flags) +{ + int iommu_prot; + + /* + * We provide no manual cache coherency ioctls to userspace and most + * architectures make the CPU ops for cache flushing privileged. + * Therefore we require the underlying IOMMU to support CPU coherent + * operation. Support for IOMMU_CACHE is enforced by the + * IOMMU_CAP_CACHE_COHERENCY test during bind. + */ + iommu_prot = IOMMU_CACHE; + if (map_flags & IOMMU_IOAS_MAP_WRITEABLE) + iommu_prot |= IOMMU_WRITE; + if (map_flags & IOMMU_IOAS_MAP_READABLE) + iommu_prot |= IOMMU_READ; + return iommu_prot; +} + +int iommufd_ioas_map(struct iommufd_ucmd *ucmd) +{ + struct iommu_ioas_map *cmd = ucmd->cmd; + struct iommufd_ioas *ioas; + unsigned int flags = 0; + unsigned long iova; + int rc; + + if ((cmd->flags & + ~(IOMMU_IOAS_MAP_FIXED_IOVA | IOMMU_IOAS_MAP_WRITEABLE | + IOMMU_IOAS_MAP_READABLE)) || + cmd->__reserved) + return -EOPNOTSUPP; + if (cmd->iova >= ULONG_MAX || cmd->length >= ULONG_MAX) + return -EOVERFLOW; + + ioas = iommufd_get_ioas(ucmd, cmd->ioas_id); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + if (!(cmd->flags & IOMMU_IOAS_MAP_FIXED_IOVA)) + flags = IOPT_ALLOC_IOVA; + iova = cmd->iova; + rc = iopt_map_user_pages(ucmd->ictx, &ioas->iopt, &iova, + u64_to_user_ptr(cmd->user_va), cmd->length, + conv_iommu_prot(cmd->flags), flags); + if (rc) + goto out_put; + + cmd->iova = iova; + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); +out_put: + iommufd_put_object(&ioas->obj); + return rc; +} + +int iommufd_ioas_copy(struct iommufd_ucmd *ucmd) +{ + struct iommu_ioas_copy *cmd = ucmd->cmd; + struct iommufd_ioas *src_ioas; + struct iommufd_ioas *dst_ioas; + unsigned int flags = 0; + LIST_HEAD(pages_list); + unsigned long iova; + int rc; + + if ((cmd->flags & + ~(IOMMU_IOAS_MAP_FIXED_IOVA | IOMMU_IOAS_MAP_WRITEABLE | + IOMMU_IOAS_MAP_READABLE))) + return -EOPNOTSUPP; + if (cmd->length >= ULONG_MAX || cmd->src_iova >= ULONG_MAX || + cmd->dst_iova >= ULONG_MAX) + return -EOVERFLOW; + + src_ioas = iommufd_get_ioas(ucmd, cmd->src_ioas_id); + if (IS_ERR(src_ioas)) + return PTR_ERR(src_ioas); + rc = iopt_get_pages(&src_ioas->iopt, cmd->src_iova, cmd->length, + &pages_list); + iommufd_put_object(&src_ioas->obj); + if (rc) + return rc; + + dst_ioas = iommufd_get_ioas(ucmd, cmd->dst_ioas_id); + if (IS_ERR(dst_ioas)) { + rc = PTR_ERR(dst_ioas); + goto out_pages; + } + + if (!(cmd->flags & IOMMU_IOAS_MAP_FIXED_IOVA)) + flags = IOPT_ALLOC_IOVA; + iova = cmd->dst_iova; + rc = iopt_map_pages(&dst_ioas->iopt, &pages_list, cmd->length, &iova, + conv_iommu_prot(cmd->flags), flags); + if (rc) + goto out_put_dst; + + cmd->dst_iova = iova; + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); +out_put_dst: + iommufd_put_object(&dst_ioas->obj); +out_pages: + iopt_free_pages_list(&pages_list); + return rc; +} + +int iommufd_ioas_unmap(struct iommufd_ucmd *ucmd) +{ + struct iommu_ioas_unmap *cmd = ucmd->cmd; + struct iommufd_ioas *ioas; + unsigned long unmapped = 0; + int rc; + + ioas = iommufd_get_ioas(ucmd, cmd->ioas_id); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + if (cmd->iova == 0 && cmd->length == U64_MAX) { + rc = iopt_unmap_all(&ioas->iopt, &unmapped); + if (rc) + goto out_put; + } else { + if (cmd->iova >= ULONG_MAX || cmd->length >= ULONG_MAX) { + rc = -EOVERFLOW; + goto out_put; + } + rc = iopt_unmap_iova(&ioas->iopt, cmd->iova, cmd->length, + &unmapped); + if (rc) + goto out_put; + } + + cmd->length = unmapped; + rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd)); + +out_put: + iommufd_put_object(&ioas->obj); + return rc; +} + +int iommufd_option_rlimit_mode(struct iommu_option *cmd, + struct iommufd_ctx *ictx) +{ + if (cmd->op == IOMMU_OPTION_OP_GET) { + cmd->val64 = ictx->account_mode == IOPT_PAGES_ACCOUNT_MM; + return 0; + } + if (cmd->op == IOMMU_OPTION_OP_SET) { + int rc = 0; + + if (!capable(CAP_SYS_RESOURCE)) + return -EPERM; + + xa_lock(&ictx->objects); + if (!xa_empty(&ictx->objects)) { + rc = -EBUSY; + } else { + if (cmd->val64 == 0) + ictx->account_mode = IOPT_PAGES_ACCOUNT_USER; + else if (cmd->val64 == 1) + ictx->account_mode = IOPT_PAGES_ACCOUNT_MM; + else + rc = -EINVAL; + } + xa_unlock(&ictx->objects); + + return rc; + } + return -EOPNOTSUPP; +} + +static int iommufd_ioas_option_huge_pages(struct iommu_option *cmd, + struct iommufd_ioas *ioas) +{ + if (cmd->op == IOMMU_OPTION_OP_GET) { + cmd->val64 = !ioas->iopt.disable_large_pages; + return 0; + } + if (cmd->op == IOMMU_OPTION_OP_SET) { + if (cmd->val64 == 0) + return iopt_disable_large_pages(&ioas->iopt); + if (cmd->val64 == 1) { + iopt_enable_large_pages(&ioas->iopt); + return 0; + } + return -EINVAL; + } + return -EOPNOTSUPP; +} + +int iommufd_ioas_option(struct iommufd_ucmd *ucmd) +{ + struct iommu_option *cmd = ucmd->cmd; + struct iommufd_ioas *ioas; + int rc = 0; + + if (cmd->__reserved) + return -EOPNOTSUPP; + + ioas = iommufd_get_ioas(ucmd, cmd->object_id); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + switch (cmd->option_id) { + case IOMMU_OPTION_HUGE_PAGES: + rc = iommufd_ioas_option_huge_pages(cmd, ioas); + break; + default: + rc = -EOPNOTSUPP; + } + + iommufd_put_object(&ioas->obj); + return rc; +} diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 6b7e0982b8c802..68c12115400285 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -11,6 +11,7 @@

struct iommu_domain; struct iommu_group; +struct iommu_option;

struct iommufd_ctx { struct file *file; @@ -102,6 +103,7 @@ static inline int iommufd_ucmd_respond(struct iommufd_ucmd *ucmd, enum iommufd_object_type { IOMMUFD_OBJ_NONE, IOMMUFD_OBJ_ANY = IOMMUFD_OBJ_NONE, + IOMMUFD_OBJ_IOAS, };

/* Base struct for all objects with a userspace ID handle. */ @@ -174,6 +176,37 @@ struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx, type), \ typeof(*(ptr)), obj)

+/* + * The IO Address Space (IOAS) pagetable is a virtual page table backed by the + * io_pagetable object. It is a user controlled mapping of IOVA -> PFNs. The + * mapping is copied into all of the associated domains and made available to + * in-kernel users. + */ +struct iommufd_ioas { + struct iommufd_object obj; + struct io_pagetable iopt; +}; + +static inline struct iommufd_ioas *iommufd_get_ioas(struct iommufd_ucmd *ucmd, + u32 id) +{ + return container_of(iommufd_get_object(ucmd->ictx, id, + IOMMUFD_OBJ_IOAS), + struct iommufd_ioas, obj); +} + +struct iommufd_ioas *iommufd_ioas_alloc(struct iommufd_ctx *ictx); +int iommufd_ioas_alloc_ioctl(struct iommufd_ucmd *ucmd); +void iommufd_ioas_destroy(struct iommufd_object *obj); +int iommufd_ioas_iova_ranges(struct iommufd_ucmd *ucmd); +int iommufd_ioas_allow_iovas(struct iommufd_ucmd *ucmd); +int iommufd_ioas_map(struct iommufd_ucmd *ucmd); +int iommufd_ioas_copy(struct iommufd_ucmd *ucmd); +int iommufd_ioas_unmap(struct iommufd_ucmd *ucmd); +int iommufd_ioas_option(struct iommufd_ucmd *ucmd); +int iommufd_option_rlimit_mode(struct iommu_option *cmd, + struct iommufd_ctx *ictx); + struct iommufd_access { unsigned long iova_alignment; u32 iopt_access_list_id; diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index 3a705cadb85020..266109045537ed 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -202,8 +202,36 @@ static int iommufd_fops_release(struct inode *inode, struct file *filp) return 0; }

+static int iommufd_option(struct iommufd_ucmd *ucmd) +{ + struct iommu_option *cmd = ucmd->cmd; + int rc; + + switch (cmd->option_id) { + case IOMMU_OPTION_RLIMIT_MODE: + rc = iommufd_option_rlimit_mode(cmd, ucmd->ictx); + break; + case IOMMU_OPTION_HUGE_PAGES: + rc = iommufd_ioas_option(ucmd); + break; + default: + return -EOPNOTSUPP; + } + if (rc) + return rc; + if (copy_to_user(&((struct iommu_option __user *)ucmd->ubuffer)->val64, + &cmd->val64, sizeof(cmd->val64))) + return -EFAULT; + return 0; +} + union ucmd_buffer { struct iommu_destroy destroy; + struct iommu_ioas_alloc alloc; + struct iommu_ioas_allow_iovas allow_iovas; + struct iommu_ioas_iova_ranges iova_ranges; + struct iommu_ioas_map map; + struct iommu_ioas_unmap unmap; };

struct iommufd_ioctl_op { @@ -224,6 +252,20 @@ struct iommufd_ioctl_op { } static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = { IOCTL_OP(IOMMU_DESTROY, iommufd_destroy, struct iommu_destroy, id), + IOCTL_OP(IOMMU_IOAS_ALLOC, iommufd_ioas_alloc_ioctl, + struct iommu_ioas_alloc, out_ioas_id), + IOCTL_OP(IOMMU_IOAS_ALLOW_IOVAS, iommufd_ioas_allow_iovas, + struct iommu_ioas_allow_iovas, allowed_iovas), + IOCTL_OP(IOMMU_IOAS_COPY, iommufd_ioas_copy, struct iommu_ioas_copy, + src_iova), + IOCTL_OP(IOMMU_IOAS_IOVA_RANGES, iommufd_ioas_iova_ranges, + struct iommu_ioas_iova_ranges, out_iova_alignment), + IOCTL_OP(IOMMU_IOAS_MAP, iommufd_ioas_map, struct iommu_ioas_map, + iova), + IOCTL_OP(IOMMU_IOAS_UNMAP, iommufd_ioas_unmap, struct iommu_ioas_unmap, + length), + IOCTL_OP(IOMMU_OPTION, iommufd_option, struct iommu_option, + val64), };

static long iommufd_fops_ioctl(struct file *filp, unsigned int cmd, @@ -310,6 +352,9 @@ void iommufd_ctx_put(struct iommufd_ctx *ictx) EXPORT_SYMBOL_NS_GPL(iommufd_ctx_put, IOMMUFD);

static const struct iommufd_object_ops iommufd_object_ops[] = { + [IOMMUFD_OBJ_IOAS] = { + .destroy = iommufd_ioas_destroy, + }, };

static struct miscdevice iommu_misc_dev = { diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index 2ad06b27a35fe5..a872a50d800a41 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -37,6 +37,13 @@ enum { IOMMUFD_CMD_BASE = 0x80, IOMMUFD_CMD_DESTROY = IOMMUFD_CMD_BASE, + IOMMUFD_CMD_IOAS_ALLOC, + IOMMUFD_CMD_IOAS_ALLOW_IOVAS, + IOMMUFD_CMD_IOAS_COPY, + IOMMUFD_CMD_IOAS_IOVA_RANGES, + IOMMUFD_CMD_IOAS_MAP, + IOMMUFD_CMD_IOAS_UNMAP, + IOMMUFD_CMD_OPTION, };

/** @@ -52,4 +59,238 @@ struct iommu_destroy { }; #define IOMMU_DESTROY _IO(IOMMUFD_TYPE, IOMMUFD_CMD_DESTROY)

+/** + * struct iommu_ioas_alloc - ioctl(IOMMU_IOAS_ALLOC) + * @size: sizeof(struct iommu_ioas_alloc) + * @flags: Must be 0 + * @out_ioas_id: Output IOAS ID for the allocated object + * + * Allocate an IO Address Space (IOAS) which holds an IO Virtual Address (IOVA) + * to memory mapping. + */ +struct iommu_ioas_alloc { + __u32 size; + __u32 flags; + __u32 out_ioas_id; +}; +#define IOMMU_IOAS_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_ALLOC) + +/** + * struct iommu_iova_range + * @start: First IOVA + * @last: Inclusive last IOVA + * + * An interval in IOVA space. + */ +struct iommu_iova_range { + __aligned_u64 start; + __aligned_u64 last; +}; + +/** + * struct iommu_ioas_iova_ranges - ioctl(IOMMU_IOAS_IOVA_RANGES) + * @size: sizeof(struct iommu_ioas_iova_ranges) + * @ioas_id: IOAS ID to read ranges from + * @num_iovas: Input/Output total number of ranges in the IOAS + * @__reserved: Must be 0 + * @allowed_iovas: Pointer to the output array of struct iommu_iova_range + * @out_iova_alignment: Minimum alignment required for mapping IOVA + * + * Query an IOAS for ranges of allowed IOVAs. Mapping IOVA outside these ranges + * is not allowed. num_iovas will be set to the total number of iovas and + * the allowed_iovas[] will be filled in as space permits. + * + * The allowed ranges are dependent on the HW path the DMA operation takes, and + * can change during the lifetime of the IOAS. A fresh empty IOAS will have a + * full range, and each attached device will narrow the ranges based on that + * device's HW restrictions. Detatching a device can widen the ranges. Userspace + * should query ranges after every attach/detatch to know what IOVAs are valid + * for mapping. + * + * On input num_iovas is the length of the allowed_iovas array. On output it is + * the total number of iovas filled in. The ioctl will return -EMSGSIZE and set + * num_iovas to the required value if num_iovas is too small. In this case the + * caller should allocate a larger output array and re-issue the ioctl. + */ +struct iommu_ioas_iova_ranges { + __u32 size; + __u32 ioas_id; + __u32 num_iovas; + __u32 __reserved; + __aligned_u64 allowed_iovas; + __aligned_u64 out_iova_alignment; +}; +#define IOMMU_IOAS_IOVA_RANGES _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_IOVA_RANGES) + +/** + * struct iommu_ioas_allow_iovas - ioctl(IOMMU_IOAS_ALLOW_IOVAS) + * @size: sizeof(struct iommu_ioas_allow_iovas) + * @ioas_id: IOAS ID to allow IOVAs from + * @num_iovas: Input/Output total number of ranges in the IOAS + * @__reserved: Must be 0 + * @allowed_iovas: Pointer to array of struct iommu_iova_range + * + * Ensure a range of IOVAs are always available for allocation. If this call + * succeeds then IOMMU_IOAS_IOVA_RANGES will never return a list of IOVA ranges + * that are narrower than the ranges provided here. This call will fail if + * IOMMU_IOAS_IOVA_RANGES is currently narrower than the given ranges. + * + * When an IOAS is first created the IOVA_RANGES will be maximally sized, and as + * devices are attached the IOVA will narrow based on the device restrictions. + * When an allowed range is specified any narrowing will be refused, ie device + * attachment can fail if the device requires limiting within the allowed range. + * + * Automatic IOVA allocation is also impacted by this call. MAP will only + * allocate within the allowed IOVAs if they are present. + * + * This call replaces the entire allowed list with the given list. + */ +struct iommu_ioas_allow_iovas { + __u32 size; + __u32 ioas_id; + __u32 num_iovas; + __u32 __reserved; + __aligned_u64 allowed_iovas; +}; +#define IOMMU_IOAS_ALLOW_IOVAS _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_ALLOW_IOVAS) + +/** + * enum iommufd_ioas_map_flags - Flags for map and copy + * @IOMMU_IOAS_MAP_FIXED_IOVA: If clear the kernel will compute an appropriate + * IOVA to place the mapping at + * @IOMMU_IOAS_MAP_WRITEABLE: DMA is allowed to write to this mapping + * @IOMMU_IOAS_MAP_READABLE: DMA is allowed to read from this mapping + */ +enum iommufd_ioas_map_flags { + IOMMU_IOAS_MAP_FIXED_IOVA = 1 << 0, + IOMMU_IOAS_MAP_WRITEABLE = 1 << 1, + IOMMU_IOAS_MAP_READABLE = 1 << 2, +}; + +/** + * struct iommu_ioas_map - ioctl(IOMMU_IOAS_MAP) + * @size: sizeof(struct iommu_ioas_map) + * @flags: Combination of enum iommufd_ioas_map_flags + * @ioas_id: IOAS ID to change the mapping of + * @__reserved: Must be 0 + * @user_va: Userspace pointer to start mapping from + * @length: Number of bytes to map + * @iova: IOVA the mapping was placed at. If IOMMU_IOAS_MAP_FIXED_IOVA is set + * then this must be provided as input. + * + * Set an IOVA mapping from a user pointer. If FIXED_IOVA is specified then the + * mapping will be established at iova, otherwise a suitable location based on + * the reserved and allowed lists will be automatically selected and returned in + * iova. + */ +struct iommu_ioas_map { + __u32 size; + __u32 flags; + __u32 ioas_id; + __u32 __reserved; + __aligned_u64 user_va; + __aligned_u64 length; + __aligned_u64 iova; +}; +#define IOMMU_IOAS_MAP _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_MAP) + +/** + * struct iommu_ioas_copy - ioctl(IOMMU_IOAS_COPY) + * @size: sizeof(struct iommu_ioas_copy) + * @flags: Combination of enum iommufd_ioas_map_flags + * @dst_ioas_id: IOAS ID to change the mapping of + * @src_ioas_id: IOAS ID to copy from + * @length: Number of bytes to copy and map + * @dst_iova: IOVA the mapping was placed at. If IOMMU_IOAS_MAP_FIXED_IOVA is + * set then this must be provided as input. + * @src_iova: IOVA to start the copy + * + * Copy an already existing mapping from src_ioas_id and establish it in + * dst_ioas_id. The src iova/length must exactly match a range used with + * IOMMU_IOAS_MAP. + * + * This may be used to efficiently clone a subset of an IOAS to another, or as a + * kind of 'cache' to speed up mapping. Copy has an effciency advantage over + * establishing equivalent new mappings, as internal resources are shared, and + * the kernel will pin the user memory only once. + */ +struct iommu_ioas_copy { + __u32 size; + __u32 flags; + __u32 dst_ioas_id; + __u32 src_ioas_id; + __aligned_u64 length; + __aligned_u64 dst_iova; + __aligned_u64 src_iova; +}; +#define IOMMU_IOAS_COPY _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_COPY) + +/** + * struct iommu_ioas_unmap - ioctl(IOMMU_IOAS_UNMAP) + * @size: sizeof(struct iommu_ioas_unmap) + * @ioas_id: IOAS ID to change the mapping of + * @iova: IOVA to start the unmapping at + * @length: Number of bytes to unmap, and return back the bytes unmapped + * + * Unmap an IOVA range. The iova/length must be a superset of a previously + * mapped range used with IOMMU_IOAS_MAP or IOMMU_IOAS_COPY. Splitting or + * truncating ranges is not allowed. The values 0 to U64_MAX will unmap + * everything. + */ +struct iommu_ioas_unmap { + __u32 size; + __u32 ioas_id; + __aligned_u64 iova; + __aligned_u64 length; +}; +#define IOMMU_IOAS_UNMAP _IO(IOMMUFD_TYPE, IOMMUFD_CMD_IOAS_UNMAP) + +/** + * enum iommufd_option + * @IOMMU_OPTION_RLIMIT_MODE: + * Change how RLIMIT_MEMLOCK accounting works. The caller must have privilege + * to invoke this. Value 0 (default) is user based accouting, 1 uses process + * based accounting. Global option, object_id must be 0 + * @IOMMU_OPTION_HUGE_PAGES: + * Value 1 (default) allows contiguous pages to be combined when generating + * iommu mappings. Value 0 disables combining, everything is mapped to + * PAGE_SIZE. This can be useful for benchmarking. This is a per-IOAS + * option, the object_id must be the IOAS ID. + */ +enum iommufd_option { + IOMMU_OPTION_RLIMIT_MODE = 0, + IOMMU_OPTION_HUGE_PAGES = 1, +}; + +/** + * enum iommufd_option_ops + * @IOMMU_OPTION_OP_SET: Set the option's value + * @IOMMU_OPTION_OP_GET: Get the option's value + */ +enum iommufd_option_ops { + IOMMU_OPTION_OP_SET = 0, + IOMMU_OPTION_OP_GET = 1, +}; + +/** + * @size: sizeof(struct iommu_option) + * @option_id: One of enum iommufd_option + * @op: One of enum iommufd_option_ops + * @__reserved: Must be 0 + * @object_id: ID of the object if required + * @val64: Option value to set or value returned on get + * + * Change a simple option value. This multiplexor allows controlling a options + * on objects. IOMMU_OPTION_OP_SET will load an option and IOMMU_OPTION_OP_GET + * will return the current value. + */ +struct iommu_option { + __u32 size; + __u32 option_id; + __u16 op; + __u16 __reserved; + __u32 object_id; + __aligned_u64 val64; +}; +#define IOMMU_OPTION _IO(IOMMUFD_TYPE, IOMMUFD_CMD_OPTION) #endif

The hw_pagetable object exposes the internal struct iommu_domain's to userspace. An iommu_domain is required when any DMA device attaches to an IOAS to control the io page table through the iommu driver.

For compatibility with VFIO the hw_pagetable is automatically created when a DMA device is attached to the IOAS. If a compatible iommu_domain already exists then the hw_pagetable associated with it is used for the attachment.

In the initial series there is no iommufd uAPI for the hw_pagetable object. The next patch provides driver facing APIs for IO page table attachment that allows drivers to accept either an IOAS or a hw_pagetable ID and for the driver to return the hw_pagetable ID that was auto-selected from an IOAS. The expectation is the driver will provide uAPI through its own FD for attaching its device to iommufd. This allows userspace to learn the mapping of devices to iommu_domains and to override the automatic attachment.

The future HW specific interface will allow userspace to create hw_pagetable objects using iommu_domains with IOMMU driver specific parameters. This infrastructure will allow linking those domains to IOAS's and devices.

Tested-by: Nicolin Chen nicolinc@nvidia.com Reviewed-by: Kevin Tian kevin.tian@intel.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com --- drivers/iommu/iommufd/Makefile | 1 + drivers/iommu/iommufd/hw_pagetable.c | 57 +++++++++++++++++++++++++ drivers/iommu/iommufd/ioas.c | 3 ++ drivers/iommu/iommufd/iommufd_private.h | 33 ++++++++++++++ drivers/iommu/iommufd/main.c | 3 ++ 5 files changed, 97 insertions(+) create mode 100644 drivers/iommu/iommufd/hw_pagetable.c

diff --git a/drivers/iommu/iommufd/Makefile b/drivers/iommu/iommufd/Makefile index 2b4f36f1b72f9d..e13e971aa28c60 100644 --- a/drivers/iommu/iommufd/Makefile +++ b/drivers/iommu/iommufd/Makefile @@ -1,5 +1,6 @@ # SPDX-License-Identifier: GPL-2.0-only iommufd-y := \ + hw_pagetable.o \ io_pagetable.o \ ioas.o \ main.o \ diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c new file mode 100644 index 00000000000000..43d473989a0667 --- /dev/null +++ b/drivers/iommu/iommufd/hw_pagetable.c @@ -0,0 +1,57 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES + */ +#include <linux/iommu.h> + +#include "iommufd_private.h" + +void iommufd_hw_pagetable_destroy(struct iommufd_object *obj) +{ + struct iommufd_hw_pagetable *hwpt = + container_of(obj, struct iommufd_hw_pagetable, obj); + + WARN_ON(!list_empty(&hwpt->devices)); + + iommu_domain_free(hwpt->domain); + refcount_dec(&hwpt->ioas->obj.users); + mutex_destroy(&hwpt->devices_lock); +} + +/** + * iommufd_hw_pagetable_alloc() - Get an iommu_domain for a device + * @ictx: iommufd context + * @ioas: IOAS to associate the domain with + * @dev: Device to get an iommu_domain for + * + * Allocate a new iommu_domain and return it as a hw_pagetable. + */ +struct iommufd_hw_pagetable * +iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, + struct device *dev) +{ + struct iommufd_hw_pagetable *hwpt; + int rc; + + hwpt = iommufd_object_alloc(ictx, hwpt, IOMMUFD_OBJ_HW_PAGETABLE); + if (IS_ERR(hwpt)) + return hwpt; + + hwpt->domain = iommu_domain_alloc(dev->bus); + if (!hwpt->domain) { + rc = -ENOMEM; + goto out_abort; + } + + INIT_LIST_HEAD(&hwpt->devices); + INIT_LIST_HEAD(&hwpt->hwpt_item); + mutex_init(&hwpt->devices_lock); + /* Pairs with iommufd_hw_pagetable_destroy() */ + refcount_inc(&ioas->obj.users); + hwpt->ioas = ioas; + return hwpt; + +out_abort: + iommufd_object_abort(ictx, &hwpt->obj); + return ERR_PTR(rc); +} diff --git a/drivers/iommu/iommufd/ioas.c b/drivers/iommu/iommufd/ioas.c index 7671456e86413a..64e6d0f73e39aa 100644 --- a/drivers/iommu/iommufd/ioas.c +++ b/drivers/iommu/iommufd/ioas.c @@ -17,6 +17,7 @@ void iommufd_ioas_destroy(struct iommufd_object *obj) rc = iopt_unmap_all(&ioas->iopt, NULL); WARN_ON(rc && rc != -ENOENT); iopt_destroy_table(&ioas->iopt); + mutex_destroy(&ioas->mutex); }

struct iommufd_ioas *iommufd_ioas_alloc(struct iommufd_ctx *ictx) @@ -28,6 +29,8 @@ struct iommufd_ioas *iommufd_ioas_alloc(struct iommufd_ctx *ictx) return ioas;

iopt_init_table(&ioas->iopt); + INIT_LIST_HEAD(&ioas->hwpt_list); + mutex_init(&ioas->mutex); return ioas; }

diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index 68c12115400285..d0272efcd8038e 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -103,6 +103,7 @@ static inline int iommufd_ucmd_respond(struct iommufd_ucmd *ucmd, enum iommufd_object_type { IOMMUFD_OBJ_NONE, IOMMUFD_OBJ_ANY = IOMMUFD_OBJ_NONE, + IOMMUFD_OBJ_HW_PAGETABLE, IOMMUFD_OBJ_IOAS, };

@@ -181,10 +182,20 @@ struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx, * io_pagetable object. It is a user controlled mapping of IOVA -> PFNs. The * mapping is copied into all of the associated domains and made available to * in-kernel users. + * + * Every iommu_domain that is created is wrapped in a iommufd_hw_pagetable + * object. When we go to attach a device to an IOAS we need to get an + * iommu_domain and wrapping iommufd_hw_pagetable for it. + * + * An iommu_domain & iommfd_hw_pagetable will be automatically selected + * for a device based on the hwpt_list. If no suitable iommu_domain + * is found a new iommu_domain will be created. */ struct iommufd_ioas { struct iommufd_object obj; struct io_pagetable iopt; + struct mutex mutex; + struct list_head hwpt_list; };

static inline struct iommufd_ioas *iommufd_get_ioas(struct iommufd_ucmd *ucmd, @@ -207,6 +218,28 @@ int iommufd_ioas_option(struct iommufd_ucmd *ucmd); int iommufd_option_rlimit_mode(struct iommu_option *cmd, struct iommufd_ctx *ictx);

+/* + * A HW pagetable is called an iommu_domain inside the kernel. This user object + * allows directly creating and inspecting the domains. Domains that have kernel + * owned page tables will be associated with an iommufd_ioas that provides the + * IOVA to PFN map. + */ +struct iommufd_hw_pagetable { + struct iommufd_object obj; + struct iommufd_ioas *ioas; + struct iommu_domain *domain; + bool auto_domain : 1; + /* Head at iommufd_ioas::hwpt_list */ + struct list_head hwpt_item; + struct mutex devices_lock; + struct list_head devices; +}; + +struct iommufd_hw_pagetable * +iommufd_hw_pagetable_alloc(struct iommufd_ctx *ictx, struct iommufd_ioas *ioas, + struct device *dev); +void iommufd_hw_pagetable_destroy(struct iommufd_object *obj); + struct iommufd_access { unsigned long iova_alignment; u32 iopt_access_list_id; diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index 266109045537ed..3eab714b8e12a3 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -355,6 +355,9 @@ static const struct iommufd_object_ops iommufd_object_ops[] = { [IOMMUFD_OBJ_IOAS] = { .destroy = iommufd_ioas_destroy, }, + [IOMMUFD_OBJ_HW_PAGETABLE] = { + .destroy = iommufd_hw_pagetable_destroy, + }, };

static struct miscdevice iommu_misc_dev = {

iommufd can directly implement the /dev/vfio/vfio container IOCTLs by mapping them into io_pagetable operations.

A userspace application can test against iommufd and confirm compatibility then simply make a small change to open /dev/iommu instead of /dev/vfio/vfio.

For testing purposes /dev/vfio/vfio can be symlinked to /dev/iommu and then all applications will use the compatibility path with no code changes. A later series allows /dev/vfio/vfio to be directly provided by iommufd, which allows the rlimit mode to work the same as well.

This series just provides the iommufd side of compatibility. Actually linking this to VFIO_SET_CONTAINER is a followup series, with a link in the cover letter.

Internally the compatibility API uses a normal IOAS object that, like vfio, is automatically allocated when the first device is attached.

Userspace can also query or set this IOAS object directly using the IOMMU_VFIO_IOAS ioctl. This allows mixing and matching new iommufd only features while still using the VFIO style map/unmap ioctls.

While this is enough to operate qemu, it has a few differences:

- Resource limits rely on memory cgroups to bound what userspace can do instead of the module parameter dma_entry_limit.

- VFIO P2P is not implemented. The DMABUF patches for vfio are a start at a solution where iommufd would import a special DMABUF. This is to avoid further propogating the follow_pfn() security problem.

- A full audit for pedantic compatibility details (eg errnos, etc) has not yet been done

- powerpc SPAPR is left out, as it is not connected to the iommu_domain framework. It seems interest in SPAPR is minimal as it is currently non-working in v6.1-rc1. They will have to convert to the iommu subsystem framework to enjoy iommfd.

The following are not going to be implemented and we expect to remove them from VFIO type1:

- SW access 'dirty tracking'. As discussed in the cover letter this will be done in VFIO.

- VFIO_TYPE1_NESTING_IOMMU https://lore.kernel.org/all/0-v1-0093c9b0e345+19-vfio_no_nesting_jgg@nvidia....

- VFIO_DMA_MAP_FLAG_VADDR https://lore.kernel.org/all/Yz777bJZjTyLrHEQ@nvidia.com/

Tested-by: Nicolin Chen nicolinc@nvidia.com Signed-off-by: Nicolin Chen nicolinc@nvidia.com Signed-off-by: Jason Gunthorpe jgg@nvidia.com --- drivers/iommu/iommufd/Makefile | 3 +- drivers/iommu/iommufd/iommufd_private.h | 6 + drivers/iommu/iommufd/main.c | 16 +- drivers/iommu/iommufd/vfio_compat.c | 452 ++++++++++++++++++++++++ include/linux/iommufd.h | 7 + include/uapi/linux/iommufd.h | 36 ++ 6 files changed, 514 insertions(+), 6 deletions(-) create mode 100644 drivers/iommu/iommufd/vfio_compat.c

diff --git a/drivers/iommu/iommufd/Makefile b/drivers/iommu/iommufd/Makefile index ca28a135b9675f..2fdff04000b326 100644 --- a/drivers/iommu/iommufd/Makefile +++ b/drivers/iommu/iommufd/Makefile @@ -5,6 +5,7 @@ iommufd-y := \ io_pagetable.o \ ioas.o \ main.o \ - pages.o + pages.o \ + vfio_compat.o

obj-$(CONFIG_IOMMUFD) += iommufd.o diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h index d7d606d459d4c8..5bb9788fc5aef1 100644 --- a/drivers/iommu/iommufd/iommufd_private.h +++ b/drivers/iommu/iommufd/iommufd_private.h @@ -18,6 +18,7 @@ struct iommufd_ctx { struct xarray objects;

u8 account_mode; + struct iommufd_ioas *vfio_ioas; };

/* @@ -92,6 +93,9 @@ struct iommufd_ucmd { void *cmd; };

+int iommufd_vfio_ioctl(struct iommufd_ctx *ictx, unsigned int cmd, + unsigned long arg); + /* Copy the response in ucmd->cmd back to userspace. */ static inline int iommufd_ucmd_respond(struct iommufd_ucmd *ucmd, size_t cmd_len) @@ -222,6 +226,8 @@ int iommufd_ioas_option(struct iommufd_ucmd *ucmd); int iommufd_option_rlimit_mode(struct iommu_option *cmd, struct iommufd_ctx *ictx);

+int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd); + /* * A HW pagetable is called an iommu_domain inside the kernel. This user object * allows directly creating and inspecting the domains. Domains that have kernel diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c index c8cc0953dea13a..f76b2c8dcde8e5 100644 --- a/drivers/iommu/iommufd/main.c +++ b/drivers/iommu/iommufd/main.c @@ -133,6 +133,8 @@ bool iommufd_object_destroy_user(struct iommufd_ctx *ictx, return false; } __xa_erase(&ictx->objects, obj->id); + if (ictx->vfio_ioas && &ictx->vfio_ioas->obj == obj) + ictx->vfio_ioas = NULL; xa_unlock(&ictx->objects); up_write(&obj->destroy_rwsem);

@@ -266,27 +268,31 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = { length), IOCTL_OP(IOMMU_OPTION, iommufd_option, struct iommu_option, val64), + IOCTL_OP(IOMMU_VFIO_IOAS, iommufd_vfio_ioas, struct iommu_vfio_ioas, + __reserved), };

static long iommufd_fops_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { + struct iommufd_ctx *ictx = filp->private_data; const struct iommufd_ioctl_op *op; struct iommufd_ucmd ucmd = {}; union ucmd_buffer buf; unsigned int nr; int ret;

- ucmd.ictx = filp->private_data; + nr = _IOC_NR(cmd); + if (nr < IOMMUFD_CMD_BASE || + (nr - IOMMUFD_CMD_BASE) >= ARRAY_SIZE(iommufd_ioctl_ops)) + return iommufd_vfio_ioctl(ictx, cmd, arg); + + ucmd.ictx = ictx; ucmd.ubuffer = (void __user *)arg; ret = get_user(ucmd.user_size, (u32 __user *)ucmd.ubuffer); if (ret) return ret;

- nr = _IOC_NR(cmd); - if (nr < IOMMUFD_CMD_BASE || - (nr - IOMMUFD_CMD_BASE) >= ARRAY_SIZE(iommufd_ioctl_ops)) - return -ENOIOCTLCMD; op = &iommufd_ioctl_ops[nr - IOMMUFD_CMD_BASE]; if (op->ioctl_num != cmd) return -ENOIOCTLCMD; diff --git a/drivers/iommu/iommufd/vfio_compat.c b/drivers/iommu/iommufd/vfio_compat.c new file mode 100644 index 00000000000000..dbef3274803336 --- /dev/null +++ b/drivers/iommu/iommufd/vfio_compat.c @@ -0,0 +1,452 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (c) 2021-2022, NVIDIA CORPORATION & AFFILIATES + */ +#include <linux/file.h> +#include <linux/interval_tree.h> +#include <linux/iommu.h> +#include <linux/iommufd.h> +#include <linux/slab.h> +#include <linux/vfio.h> +#include <uapi/linux/vfio.h> +#include <uapi/linux/iommufd.h> + +#include "iommufd_private.h" + +static struct iommufd_ioas *get_compat_ioas(struct iommufd_ctx *ictx) +{ + struct iommufd_ioas *ioas = ERR_PTR(-ENODEV); + + xa_lock(&ictx->objects); + if (!ictx->vfio_ioas || !iommufd_lock_obj(&ictx->vfio_ioas->obj)) + goto out_unlock; + ioas = ictx->vfio_ioas; +out_unlock: + xa_unlock(&ictx->objects); + return ioas; +} + +/** + * iommufd_vfio_compat_ioas_id - Return the IOAS ID that vfio should use + * @ictx: Context to operate on + * @out_ioas_id: The ioas_id the caller should use + * + * The compatibility IOAS is the IOAS that the vfio compatibility ioctls operate + * on since they do not have an IOAS ID input in their ABI. Only attaching a + * group should cause a default creation of the internal ioas, this returns the + * existing ioas if it has already been assigned somehow. + */ +int iommufd_vfio_compat_ioas_id(struct iommufd_ctx *ictx, u32 *out_ioas_id) +{ + struct iommufd_ioas *ioas = NULL; + struct iommufd_ioas *out_ioas; + + ioas = iommufd_ioas_alloc(ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + xa_lock(&ictx->objects); + if (ictx->vfio_ioas && iommufd_lock_obj(&ictx->vfio_ioas->obj)) + out_ioas = ictx->vfio_ioas; + else { + out_ioas = ioas; + ictx->vfio_ioas = ioas; + } + xa_unlock(&ictx->objects); + + *out_ioas_id = out_ioas->obj.id; + if (out_ioas != ioas) { + iommufd_put_object(&out_ioas->obj); + iommufd_object_abort(ictx, &ioas->obj); + return 0; + } + /* + * An automatically created compat IOAS is treated as a userspace + * created object. Userspace can learn the ID via IOMMU_VFIO_IOAS_GET, + * and if not manually destroyed it will be destroyed automatically + * at iommufd release. + */ + iommufd_object_finalize(ictx, &ioas->obj); + return 0; +} +EXPORT_SYMBOL_NS_GPL(iommufd_vfio_compat_ioas_id, IOMMUFD_VFIO); + +int iommufd_vfio_ioas(struct iommufd_ucmd *ucmd) +{ + struct iommu_vfio_ioas *cmd = ucmd->cmd; + struct iommufd_ioas *ioas; + + if (cmd->__reserved) + return -EOPNOTSUPP; + switch (cmd->op) { + case IOMMU_VFIO_IOAS_GET: + ioas = get_compat_ioas(ucmd->ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + cmd->ioas_id = ioas->obj.id; + iommufd_put_object(&ioas->obj); + return iommufd_ucmd_respond(ucmd, sizeof(*cmd)); + + case IOMMU_VFIO_IOAS_SET: + ioas = iommufd_get_ioas(ucmd, cmd->ioas_id); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + xa_lock(&ucmd->ictx->objects); + ucmd->ictx->vfio_ioas = ioas; + xa_unlock(&ucmd->ictx->objects); + iommufd_put_object(&ioas->obj); + return 0; + + case IOMMU_VFIO_IOAS_CLEAR: + xa_lock(&ucmd->ictx->objects); + ucmd->ictx->vfio_ioas = NULL; + xa_unlock(&ucmd->ictx->objects); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int iommufd_vfio_map_dma(struct iommufd_ctx *ictx, unsigned int cmd, + void __user *arg) +{ + u32 supported_flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE; + size_t minsz = offsetofend(struct vfio_iommu_type1_dma_map, size); + struct vfio_iommu_type1_dma_map map; + int iommu_prot = IOMMU_CACHE; + struct iommufd_ioas *ioas; + unsigned long iova; + int rc; + + if (copy_from_user(&map, arg, minsz)) + return -EFAULT; + + if (map.argsz < minsz || map.flags & ~supported_flags) + return -EINVAL; + + if (map.flags & VFIO_DMA_MAP_FLAG_READ) + iommu_prot |= IOMMU_READ; + if (map.flags & VFIO_DMA_MAP_FLAG_WRITE) + iommu_prot |= IOMMU_WRITE; + + ioas = get_compat_ioas(ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + /* + * Maps created through the legacy interface always use VFIO compatible + * rlimit accounting. If the user wishes to use the faster user based + * rlimit accounting then they must use the new interface. + */ + iova = map.iova; + rc = iopt_map_user_pages(ictx, &ioas->iopt, &iova, u64_to_user_ptr(map.vaddr), + map.size, iommu_prot, 0); + iommufd_put_object(&ioas->obj); + return rc; +} + +static int iommufd_vfio_unmap_dma(struct iommufd_ctx *ictx, unsigned int cmd, + void __user *arg) +{ + size_t minsz = offsetofend(struct vfio_iommu_type1_dma_unmap, size); + /* + * VFIO_DMA_UNMAP_FLAG_GET_DIRTY_BITMAP is obsoleted by the new + * dirty tracking direction: + * https://lore.kernel.org/kvm/20220731125503.142683-1-yishaih@nvidia.com/ + * https://lore.kernel.org/kvm/20220428210933.3583-1-joao.m.martins@oracle.com/ + */ + u32 supported_flags = VFIO_DMA_UNMAP_FLAG_ALL; + struct vfio_iommu_type1_dma_unmap unmap; + struct iommufd_ioas *ioas; + unsigned long unmapped; + int rc; + + if (copy_from_user(&unmap, arg, minsz)) + return -EFAULT; + + if (unmap.argsz < minsz || unmap.flags & ~supported_flags) + return -EINVAL; + + ioas = get_compat_ioas(ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + if (unmap.flags & VFIO_DMA_UNMAP_FLAG_ALL) { + if (unmap.iova != 0 || unmap.size != 0) { + rc = -EINVAL; + goto err_put; + } + rc = iopt_unmap_all(&ioas->iopt, &unmapped); + } else { + if (READ_ONCE(ioas->iopt.disable_large_pages)) { + unsigned long iovas[] = { unmap.iova + unmap.size - 1, + unmap.iova - 1 }; + + rc = iopt_cut_iova(&ioas->iopt, iovas, + unmap.iova ? 2 : 1); + if (rc) + goto err_put; + } + rc = iopt_unmap_iova(&ioas->iopt, unmap.iova, unmap.size, + &unmapped); + } + unmap.size = unmapped; + if (copy_to_user(arg, &unmap, minsz)) + rc = -EFAULT; + +err_put: + iommufd_put_object(&ioas->obj); + return rc; +} + +static int iommufd_vfio_cc_iommu(struct iommufd_ctx *ictx) +{ + struct iommufd_hw_pagetable *hwpt; + struct iommufd_ioas *ioas; + int rc = 1; + + ioas = get_compat_ioas(ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + mutex_lock(&ioas->mutex); + list_for_each_entry(hwpt, &ioas->hwpt_list, hwpt_item) { + if (!hwpt->enforce_cache_coherency) { + rc = 0; + break; + } + } + mutex_unlock(&ioas->mutex); + + iommufd_put_object(&ioas->obj); + return rc; +} + +static int iommufd_vfio_check_extension(struct iommufd_ctx *ictx, + unsigned long type) +{ + switch (type) { + case VFIO_TYPE1_IOMMU: + case VFIO_TYPE1v2_IOMMU: + case VFIO_UNMAP_ALL: + return 1; + + case VFIO_DMA_CC_IOMMU: + return iommufd_vfio_cc_iommu(ictx); + + /* + * This is obsolete, and to be removed from VFIO. It was an incomplete + * idea that got merged. + * https://lore.kernel.org/kvm/0-v1-0093c9b0e345+19-vfio_no_nesting_jgg@nvidia.... + */ + case VFIO_TYPE1_NESTING_IOMMU: + return 0; + + /* + * VFIO_DMA_MAP_FLAG_VADDR + * https://lore.kernel.org/kvm/1611939252-7240-1-git-send-email-steven.sistare@... + * https://lore.kernel.org/all/Yz777bJZjTyLrHEQ@nvidia.com/ + * + * It is hard to see how this could be implemented safely. + */ + case VFIO_UPDATE_VADDR: + default: + return 0; + } +} + +static int iommufd_vfio_set_iommu(struct iommufd_ctx *ictx, unsigned long type) +{ + struct iommufd_ioas *ioas = NULL; + int rc = 0; + + if (type != VFIO_TYPE1_IOMMU && type != VFIO_TYPE1v2_IOMMU) + return -EINVAL; + + /* VFIO fails the set_iommu if there is no group */ + ioas = get_compat_ioas(ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + if (type == VFIO_TYPE1_IOMMU) + rc = iopt_disable_large_pages(&ioas->iopt); + iommufd_put_object(&ioas->obj); + return rc; +} + +static unsigned long iommufd_get_pagesizes(struct iommufd_ioas *ioas) +{ + struct io_pagetable *iopt = &ioas->iopt; + unsigned long pgsize_bitmap = ULONG_MAX; + struct iommu_domain *domain; + unsigned long index; + + down_read(&iopt->domains_rwsem); + xa_for_each(&iopt->domains, index, domain) + pgsize_bitmap &= domain->pgsize_bitmap; + + /* See vfio_update_pgsize_bitmap() */ + if (pgsize_bitmap & ~PAGE_MASK) { + pgsize_bitmap &= PAGE_MASK; + pgsize_bitmap |= PAGE_SIZE; + } + pgsize_bitmap = max(pgsize_bitmap, ioas->iopt.iova_alignment); + up_read(&iopt->domains_rwsem); + return pgsize_bitmap; +} + +static int iommufd_fill_cap_iova(struct iommufd_ioas *ioas, + struct vfio_info_cap_header __user *cur, + size_t avail) +{ + struct vfio_iommu_type1_info_cap_iova_range __user *ucap_iovas = + container_of(cur, + struct vfio_iommu_type1_info_cap_iova_range __user, + header); + struct vfio_iommu_type1_info_cap_iova_range cap_iovas = { + .header = { + .id = VFIO_IOMMU_TYPE1_INFO_CAP_IOVA_RANGE, + .version = 1, + }, + }; + struct interval_tree_span_iter span; + + interval_tree_for_each_span(&span, &ioas->iopt.reserved_itree, 0, + ULONG_MAX) { + struct vfio_iova_range range; + + if (!span.is_hole) + continue; + range.start = span.start_hole; + range.end = span.last_hole; + if (avail >= struct_size(&cap_iovas, iova_ranges, + cap_iovas.nr_iovas + 1) && + copy_to_user(&ucap_iovas->iova_ranges[cap_iovas.nr_iovas], + &range, sizeof(range))) + return -EFAULT; + cap_iovas.nr_iovas++; + } + if (avail >= struct_size(&cap_iovas, iova_ranges, cap_iovas.nr_iovas) && + copy_to_user(ucap_iovas, &cap_iovas, sizeof(cap_iovas))) + return -EFAULT; + return struct_size(&cap_iovas, iova_ranges, cap_iovas.nr_iovas); +} + +static int iommufd_fill_cap_dma_avail(struct iommufd_ioas *ioas, + struct vfio_info_cap_header __user *cur, + size_t avail) +{ + struct vfio_iommu_type1_info_dma_avail cap_dma = { + .header = { + .id = VFIO_IOMMU_TYPE1_INFO_DMA_AVAIL, + .version = 1, + }, + /* iommufd has no limit, return the same value as VFIO. */ + .avail = U16_MAX, + }; + + if (avail >= sizeof(cap_dma) && + copy_to_user(cur, &cap_dma, sizeof(cap_dma))) + return -EFAULT; + return sizeof(cap_dma); +} + +static int iommufd_vfio_iommu_get_info(struct iommufd_ctx *ictx, + void __user *arg) +{ + typedef int (*fill_cap_fn)(struct iommufd_ioas *ioas, + struct vfio_info_cap_header __user *cur, + size_t avail); + static const fill_cap_fn fill_fns[] = { + iommufd_fill_cap_dma_avail, + iommufd_fill_cap_iova, + }; + size_t minsz = offsetofend(struct vfio_iommu_type1_info, iova_pgsizes); + struct vfio_info_cap_header __user *last_cap = NULL; + struct vfio_iommu_type1_info info; + struct iommufd_ioas *ioas; + size_t total_cap_size; + int rc; + int i; + + if (copy_from_user(&info, arg, minsz)) + return -EFAULT; + + if (info.argsz < minsz) + return -EINVAL; + minsz = min_t(size_t, info.argsz, sizeof(info)); + + ioas = get_compat_ioas(ictx); + if (IS_ERR(ioas)) + return PTR_ERR(ioas); + + info.flags = VFIO_IOMMU_INFO_PGSIZES; + info.iova_pgsizes = iommufd_get_pagesizes(ioas); + info.cap_offset = 0; + + down_read(&ioas->iopt.iova_rwsem); + total_cap_size = sizeof(info); + for (i = 0; i != ARRAY_SIZE(fill_fns); i++) { + int cap_size; + + if (info.argsz > total_cap_size) + cap_size = fill_fns[i](ioas, arg + total_cap_size, + info.argsz - total_cap_size); + else + cap_size = fill_fns[i](ioas, NULL, 0); + if (cap_size < 0) { + rc = cap_size; + goto out_put; + } + if (last_cap && info.argsz >= total_cap_size && + put_user(total_cap_size, &last_cap->next)) { + rc = -EFAULT; + goto out_put; + } + last_cap = arg + total_cap_size; + total_cap_size += cap_size; + } + + /* + * If the user did not provide enough space then only some caps are + * returned and the argsz will be updated to the correct amount to get + * all caps. + */ + if (info.argsz >= total_cap_size) + info.cap_offset = sizeof(info); + info.argsz = total_cap_size; + info.flags |= VFIO_IOMMU_INFO_CAPS; + if (copy_to_user(arg, &info, minsz)) { + rc = -EFAULT; + goto out_put; + } + rc = 0; + +out_put: + up_read(&ioas->iopt.iova_rwsem); + iommufd_put_object(&ioas->obj); + return rc; +} + +int iommufd_vfio_ioctl(struct iommufd_ctx *ictx, unsigned int cmd, + unsigned long arg) +{ + void __user *uarg = (void __user *)arg; + + switch (cmd) { + case VFIO_GET_API_VERSION: + return VFIO_API_VERSION; + case VFIO_SET_IOMMU: + return iommufd_vfio_set_iommu(ictx, arg); + case VFIO_CHECK_EXTENSION: + return iommufd_vfio_check_extension(ictx, arg); + case VFIO_IOMMU_GET_INFO: + return iommufd_vfio_iommu_get_info(ictx, uarg); + case VFIO_IOMMU_MAP_DMA: + return iommufd_vfio_map_dma(ictx, cmd, uarg); + case VFIO_IOMMU_UNMAP_DMA: + return iommufd_vfio_unmap_dma(ictx, cmd, uarg); + case VFIO_IOMMU_DIRTY_PAGES: + default: + return -ENOIOCTLCMD; + } + return -ENOIOCTLCMD; +} diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h index fb9a4c275cca86..d57b044acca4cb 100644 --- a/include/linux/iommufd.h +++ b/include/linux/iommufd.h @@ -58,6 +58,7 @@ void iommufd_access_unpin_pages(struct iommufd_access *access, unsigned long iova, unsigned long length); int iommufd_access_rw(struct iommufd_access *access, unsigned long iova, void *data, size_t len, unsigned int flags); +int iommufd_vfio_compat_ioas_id(struct iommufd_ctx *ictx, u32 *out_ioas_id); #else /* !CONFIG_IOMMUFD */ static inline struct iommufd_ctx *iommufd_ctx_from_file(struct file *file) { @@ -88,5 +89,11 @@ static inline int iommufd_access_rw(struct iommufd_access *access, unsigned long { return -EOPNOTSUPP; } + +static inline int iommufd_vfio_compat_ioas_id(struct iommufd_ctx *ictx, + u32 *out_ioas_id) +{ + return -EOPNOTSUPP; +} #endif /* CONFIG_IOMMUFD */ #endif diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h index a872a50d800a41..c7109d7e5e09a9 100644 --- a/include/uapi/linux/iommufd.h +++ b/include/uapi/linux/iommufd.h @@ -44,6 +44,7 @@ enum { IOMMUFD_CMD_IOAS_MAP, IOMMUFD_CMD_IOAS_UNMAP, IOMMUFD_CMD_OPTION, + IOMMUFD_CMD_VFIO_IOAS, };

/** @@ -293,4 +294,39 @@ struct iommu_option { __aligned_u64 val64; }; #define IOMMU_OPTION _IO(IOMMUFD_TYPE, IOMMUFD_CMD_OPTION) + +/** + * enum iommufd_vfio_ioas_op + * @IOMMU_VFIO_IOAS_GET: Get the current compatibility IOAS + * @IOMMU_VFIO_IOAS_SET: Change the current compatibility IOAS + * @IOMMU_VFIO_IOAS_CLEAR: Disable VFIO compatibility + */ +enum iommufd_vfio_ioas_op { + IOMMU_VFIO_IOAS_GET = 0, + IOMMU_VFIO_IOAS_SET = 1, + IOMMU_VFIO_IOAS_CLEAR = 2, +}; + +/** + * struct iommu_vfio_ioas - ioctl(IOMMU_VFIO_IOAS) + * @size: sizeof(struct iommu_vfio_ioas) + * @ioas_id: For IOMMU_VFIO_IOAS_SET the input IOAS ID to set + * For IOMMU_VFIO_IOAS_GET will output the IOAS ID + * @op: One of enum iommufd_vfio_ioas_op + * @__reserved: Must be 0 + * + * The VFIO compatibility support uses a single ioas because VFIO APIs do not + * support the ID field. Set or Get the IOAS that VFIO compatibility will use. + * When VFIO_GROUP_SET_CONTAINER is used on an iommufd it will get the + * compatibility ioas, either by taking what is already set, or auto creating + * one. From then on VFIO will continue to use that ioas and is not effected by + * this ioctl. SET or CLEAR does not destroy any auto-created IOAS. + */ +struct iommu_vfio_ioas { + __u32 size; + __u32 ioas_id; + __u16 op; + __u16 __reserved; +}; +#define IOMMU_VFIO_IOAS _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VFIO_IOAS) #endif

These are on performance paths so we protect them using the CONFIG_IOMMUFD_TEST to not hit during normal operation.

These are useful when running the test suite and syzkaller to find data structure inconsistencies early.

Signed-off-by: Jason Gunthorpe jgg@nvidia.com --- drivers/iommu/iommufd/device.c | 5 ++++ drivers/iommu/iommufd/io_pagetable.c | 22 +++++++++++++++ drivers/iommu/iommufd/io_pagetable.h | 3 +++ drivers/iommu/iommufd/pages.c | 40 ++++++++++++++++++++++++++-- 4 files changed, 68 insertions(+), 2 deletions(-)

diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c index 8ca5a38b2a79b8..536a34d099968d 100644 --- a/drivers/iommu/iommufd/device.c +++ b/drivers/iommu/iommufd/device.c @@ -589,6 +589,11 @@ int iommufd_access_pin_pages(struct iommufd_access *access, unsigned long iova, bool first = true; int rc;

+ /* Driver didn't specify needs_pin_pages in its ops */ + if (IS_ENABLED(CONFIG_IOMMUFD_TEST) && + WARN_ON(access->iova_alignment != PAGE_SIZE)) + return -EINVAL; + if (!length) return -EINVAL; if (check_add_overflow(iova, length - 1, &last_iova)) diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c index a7d16cd14ea200..432592fc026f4e 100644 --- a/drivers/iommu/iommufd/io_pagetable.c +++ b/drivers/iommu/iommufd/io_pagetable.c @@ -261,6 +261,11 @@ static int iopt_alloc_area_pages(struct io_pagetable *iopt, (uintptr_t)elm->pages->uptr + elm->start_byte, length); if (rc) goto out_unlock; + if (IS_ENABLED(CONFIG_IOMMUFD_TEST) && + WARN_ON(iopt_check_iova(iopt, *dst_iova, length))) { + rc = -EINVAL; + goto out_unlock; + } } else { rc = iopt_check_iova(iopt, *dst_iova, length); if (rc) @@ -287,6 +292,8 @@ static int iopt_alloc_area_pages(struct io_pagetable *iopt,

static void iopt_abort_area(struct iopt_area *area) { + if (IS_ENABLED(CONFIG_IOMMUFD_TEST)) + WARN_ON(area->pages); if (area->iopt) { down_write(&area->iopt->iova_rwsem); interval_tree_remove(&area->node, &area->iopt->area_itree); @@ -652,6 +659,9 @@ void iopt_destroy_table(struct io_pagetable *iopt) { struct interval_tree_node *node;

+ if (IS_ENABLED(CONFIG_IOMMUFD_TEST)) + iopt_remove_reserved_iova(iopt, NULL); + while ((node = interval_tree_iter_first(&iopt->allowed_itree, 0, ULONG_MAX))) { interval_tree_remove(node, &iopt->allowed_itree); @@ -698,6 +708,8 @@ static void iopt_unfill_domain(struct io_pagetable *iopt, continue;

mutex_lock(&pages->mutex); + if (IS_ENABLED(CONFIG_IOMMUFD_TEST)) + WARN_ON(!area->storage_domain); if (area->storage_domain == domain) area->storage_domain = storage_domain; mutex_unlock(&pages->mutex); @@ -802,6 +814,16 @@ static int iopt_check_iova_alignment(struct io_pagetable *iopt, (iopt_area_length(area) & align_mask) || (area->page_offset & align_mask)) return -EADDRINUSE; + + if (IS_ENABLED(CONFIG_IOMMUFD_TEST)) { + struct iommufd_access *access; + unsigned long index; + + xa_for_each(&iopt->access_list, index, access) + if (WARN_ON(access->iova_alignment > + new_iova_alignment)) + return -EADDRINUSE; + } return 0; }

diff --git a/drivers/iommu/iommufd/io_pagetable.h b/drivers/iommu/iommufd/io_pagetable.h index 9a1c8a5ae3c883..3b85fa344f6be3 100644 --- a/drivers/iommu/iommufd/io_pagetable.h +++ b/drivers/iommu/iommufd/io_pagetable.h @@ -101,6 +101,9 @@ static inline size_t iopt_area_length(struct iopt_area *area) static inline unsigned long iopt_area_start_byte(struct iopt_area *area, unsigned long iova) { + if (IS_ENABLED(CONFIG_IOMMUFD_TEST)) + WARN_ON(iova < iopt_area_iova(area) || + iova > iopt_area_last_iova(area)); return (iova - iopt_area_iova(area)) + area->page_offset + iopt_area_index(area) * PAGE_SIZE; } diff --git a/drivers/iommu/iommufd/pages.c b/drivers/iommu/iommufd/pages.c index 2ddcb0d4f71e04..c535be1bedb9ba 100644 --- a/drivers/iommu/iommufd/pages.c +++ b/drivers/iommu/iommufd/pages.c @@ -101,12 +101,20 @@ static void *temp_kmalloc(size_t *size, void *backup, size_t backup_len)

static void iopt_pages_add_npinned(struct iopt_pages *pages, size_t npages) { - pages->npinned += npages; + int rc; + + rc = check_add_overflow(pages->npinned, npages, &pages->npinned); + if (IS_ENABLED(CONFIG_IOMMUFD_TEST)) + WARN_ON(rc || pages->npinned > pages->npages); }

static void iopt_pages_sub_npinned(struct iopt_pages *pages, size_t npages) { - pages->npinned -= npages; + int rc; + + rc = check_sub_overflow(pages->npinned, npages, &pages->npinned); + if (IS_ENABLED(CONFIG_IOMMUFD_TEST)) + WARN_ON(rc || pages->npinned > pages->npages); }

static void iopt_pages_err_unpin(struct iopt_pages *pages, @@ -128,6 +136,9 @@ static void iopt_pages_err_unpin(struct iopt_pages *pages, static unsigned long iopt_area_index_to_iova(struct iopt_area *area, unsigned long index) { + if (IS_ENABLED(CONFIG_IOMMUFD_TEST)) + WARN_ON(index < iopt_area_index(area) || + index > iopt_area_last_index(area)); index -= iopt_area_index(area); if (index == 0) return iopt_area_iova(area); @@ -137,6 +148,9 @@ static unsigned long iopt_area_index_to_iova(struct iopt_area *area, static unsigned long iopt_area_index_to_iova_last(struct iopt_area *area, unsigned long index) { + if (IS_ENABLED(CONFIG_IOMMUFD_TEST)) + WARN_ON(index < iopt_area_index(area) || + index > iopt_area_last_index(area)); if (index == iopt_area_last_index(area)) return iopt_area_last_iova(area); return iopt_area_iova(area) - area->page_offset + @@ -240,6 +254,8 @@ static int __batch_init(struct pfn_batch *batch, size_t max_pages, void *backup, batch->pfns = temp_kmalloc(&size, backup, backup_len); if (!batch->pfns) return -ENOMEM; + if (IS_ENABLED(CONFIG_IOMMUFD_TEST) && WARN_ON(size < elmsz)) + return -EINVAL; batch->array_size = size / elmsz; batch->npfns = (u32 *)(batch->pfns + batch->array_size); batch_clear(batch); @@ -367,6 +383,10 @@ static int batch_iommu_map_small(struct iommu_domain *domain, unsigned long start_iova = iova; int rc;

+ if (IS_ENABLED(CONFIG_IOMMUFD_TEST)) + WARN_ON(paddr % PAGE_SIZE || iova % PAGE_SIZE || + size % PAGE_SIZE); + while (size) { rc = iommu_map(domain, iova, paddr, PAGE_SIZE, prot); if (rc) @@ -652,6 +672,10 @@ static int pfn_reader_user_pin(struct pfn_reader_user *user, uintptr_t uptr; long rc;

+ if (IS_ENABLED(CONFIG_IOMMUFD_TEST) && + WARN_ON(last_index < start_index)) + return -EINVAL; + if (!user->upages) { /* All undone in pfn_reader_destroy() */ user->upages_len = @@ -890,6 +914,10 @@ static int pfn_reader_fill_span(struct pfn_reader *pfns) struct iopt_area *area; int rc;

+ if (IS_ENABLED(CONFIG_IOMMUFD_TEST) && + WARN_ON(span->last_used < start_index)) + return -EINVAL; + if (span->is_used == 1) { batch_from_xarray(&pfns->batch, &pfns->pages->pinned_pfns, start_index, span->last_used); @@ -942,6 +970,10 @@ static int pfn_reader_next(struct pfn_reader *pfns) while (pfns->batch_end_index != pfns->last_index + 1) { unsigned int npfns = pfns->batch.total_pfns;

+ if (IS_ENABLED(CONFIG_IOMMUFD_TEST) && + WARN_ON(interval_tree_double_span_iter_done(&pfns->span))) + return -EINVAL; + rc = pfn_reader_fill_span(pfns); if (rc) return rc; @@ -1025,6 +1057,10 @@ static int pfn_reader_first(struct pfn_reader *pfns, struct iopt_pages *pages, { int rc;

+ if (IS_ENABLED(CONFIG_IOMMUFD_TEST) && + WARN_ON(last_index < start_index)) + return -EINVAL; + rc = pfn_reader_init(pfns, pages, start_index, last_index); if (rc) return rc;