Danilo Krummrich
2023-Aug-03 16:52 UTC
[Nouveau] [PATCH drm-misc-next v9 00/11] Nouveau VM_BIND UAPI & DRM GPUVA Manager (merged)
This patch series provides a new UAPI for the Nouveau driver in order to support Vulkan features, such as sparse bindings and sparse residency. Furthermore, with the DRM GPUVA manager it provides a new DRM core feature to keep track of GPU virtual address (VA) mappings in a more generic way (merged into drm-misc/drm-misc-next since V8). The DRM GPUVA manager is indented to help drivers implement userspace-manageable GPU VA spaces in reference to the Vulkan API. In order to achieve this goal it serves the following purposes in this context. 1) Provide infrastructure to track GPU VA allocations and mappings, using an interval tree (RB-tree). 2) Generically connect GPU VA mappings to their backing buffers, in particular DRM GEM objects. 3) Provide a common implementation to perform more complex mapping operations on the GPU VA space. In particular splitting and merging of GPU VA mappings, e.g. for intersecting mapping requests or partial unmap requests. The new VM_BIND Nouveau UAPI build on top of the DRM GPUVA manager, itself providing the following new interfaces. 1) Initialize a GPU VA space via the new DRM_IOCTL_NOUVEAU_VM_INIT ioctl for UMDs to specify the portion of VA space managed by the kernel and userspace, respectively. 2) Allocate and free a VA space region as well as bind and unbind memory to the GPUs VA space via the new DRM_IOCTL_NOUVEAU_VM_BIND ioctl. 3) Execute push buffers with the new DRM_IOCTL_NOUVEAU_EXEC ioctl. Both, DRM_IOCTL_NOUVEAU_VM_BIND and DRM_IOCTL_NOUVEAU_EXEC, make use of the DRM scheduler to queue jobs and support asynchronous processing with DRM syncobjs as synchronization mechanism. By default DRM_IOCTL_NOUVEAU_VM_BIND does synchronous processing, DRM_IOCTL_NOUVEAU_EXEC supports asynchronous processing only. The new VM_BIND UAPI for Nouveau makes also use of drm_exec (execution context for GEM buffers) by Christian K?nig. Since the patch implementing drm_exec was not yet merged into drm-next it is part of this series, as well as a small fix for this patch, which was found while testing this series. This patch series is also available at [1]. There is a Mesa NVK merge request by Dave Airlie [2] implementing the corresponding userspace parts for this series. The Vulkan CTS test suite passes the sparse binding and sparse residency test cases for the new UAPI together with Dave's Mesa work. There are also some test cases in the igt-gpu-tools project [3] for the new UAPI and hence the DRM GPU VA manager. However, most of them are testing the DRM GPU VA manager's logic through Nouveau's new UAPI and should be considered just as helper for implementation. However, I absolutely intend to change those test cases to proper kunit test cases for the DRM GPUVA manager, once and if we agree on it's usefulness and design. [1] https://gitlab.freedesktop.org/nouvelles/kernel/-/tree/new-uapi-drm-next / https://gitlab.freedesktop.org/nouvelles/kernel/-/merge_requests/1 [2] https://gitlab.freedesktop.org/nouveau/mesa/-/merge_requests/150/ [3] https://gitlab.freedesktop.org/dakr/igt-gpu-tools/-/tree/wip_nouveau_vm_bind Changes in V2: ============= Nouveau: - Reworked the Nouveau VM_BIND UAPI to avoid memory allocations in fence signalling critical sections. Updates to the VA space are split up in three separate stages, where only the 2. stage executes in a fence signalling critical section: 1. update the VA space, allocate new structures and page tables 2. (un-)map the requested memory bindings 3. free structures and page tables - Separated generic job scheduler code from specific job implementations. - Separated the EXEC and VM_BIND implementation of the UAPI. - Reworked the locking parts of the nvkm/vmm RAW interface, such that (un-)map operations can be executed in fence signalling critical sections. GPUVA Manager: - made drm_gpuva_regions optional for users of the GPUVA manager - allow NULL GEMs for drm_gpuva entries - swichted from drm_mm to maple_tree for track drm_gpuva / drm_gpuva_region entries - provide callbacks for users to allocate custom drm_gpuva_op structures to allow inheritance - added user bits to drm_gpuva_flags - added a prefetch operation type in order to support generating prefetch operations in the same way other operations generated - hand the responsibility for mutual exclusion for a GEM's drm_gpuva list to the user; simplified corresponding (un-)link functions Maple Tree: - I added two maple tree patches to the series, one to support custom tree walk macros and one to hand the locking responsibility to the user of the GPUVA manager without pre-defined lockdep checks. Changes in V3: ============= Nouveau: - Reworked the Nouveau VM_BIND UAPI to do the job cleanup (including page table cleanup) within a workqueue rather than the job_free() callback of the scheduler itself. A job_free() callback can stall the execution (run() callback) of the next job in the queue. Since the page table cleanup requires to take the same locks as need to be taken for page table allocation, doing it directly in the job_free() callback would still violate the fence signalling critical path. - Separated Nouveau fence allocation and emit, such that we do not violate the fence signalling critical path in EXEC jobs. - Implement "regions" (for handling sparse mappings through PDEs and dual page tables) within Nouveau. - Drop the requirement for every mapping to be contained within a region. - Add necassary synchronization of VM_BIND job operation sequences in order to work around limitations in page table handling. This will be addressed in a future re-work of Nouveau's page table handling. - Fixed a couple of race conditions found through more testing. Thanks to Dave for consitently trying to break it. :-) GPUVA Manager: - Implement pre-allocation capabilities for tree modifications within fence signalling critical sections. - Implement accessors to to apply tree modification while walking the GPUVA tree in order to actually support processing of drm_gpuva_ops through callbacks in fence signalling critical sections rather than through pre-allocated operation lists. - Remove merging of GPUVAs; the kernel has limited to none knowlege about the semantics of mapping sequences. Hence, merging is purely speculative. It seems that gaining a significant (or at least a measurable) performance increase through merging is way more likely to happen when userspace is responsible for merging mappings up to the next larger page size if possible. - Since merging was removed, regions pretty much loose their right to exist. They might still be useful for handling dual page tables or similar mechanisms, but since Nouveau seems to be the only driver having a need for this for now, regions were removed from the GPUVA manager. - Fixed a couple of maple_tree related issues; thanks to Liam for helping me out. Changes in V4: ============= Nouveau: - Refactored how specific VM_BIND and EXEC jobs are created and how their arguments are passed to the generic job implementation. - Fixed a UAF race condition where bind job ops could have been freed already while still waiting for a job cleanup to finish. This is due to in certain cases we need to wait for mappings actually being unmapped before creating sparse regions in the same area. - Re-based the code onto drm_exec v4 patch. GPUVA Manager: - Fixed a maple tree related bug when pre-allocating MA states. (Boris Brezillion) - Made struct drm_gpuva_fn_ops a const object in all occurrences. (Boris Brezillion) Changes in V5: ============= Nouveau: - Link and unlink GPUVAs outside the fence signalling critical path in nouveau_uvmm_bind_job_submit() holding the dma-resv lock. Mutual exclusion of BO evicts causing mapping invalidation and regular mapping operations is ensured with dma-fences. GPUVA Manager: - Removed the separate GEMs GPUVA list lock. Link and unlink as well as iterating the GEM's GPUVA list should be protected with the GEM's dma-resv lock instead. - Renamed DRM_GPUVA_EVICTED flag to DRM_GPUVA_INVALIDATED. Mappings do not get eviced, they might get invalidated due to eviction. - Maple tree uses the 'unsinged long' type for node entries. While this works for GPU VA spaces larger than 32-bit on 64-bit kernel, the GPU VA space is limited to 32-bit on 32-bit kernels as well. As long as we do not have a 64-bit capable maple tree for 32-bit kernels, the GPU VA manager contains checks to throw warnings when GPU VA entries exceed the maple tree's storage capabilities. - Extended the Documentation and added example code as requested by Donald Robson. Changes in V6 ============ Nouveau: - Re-based the code onto drm_exec v5 patch. GPUVA Manager: - Switch from maple tree to RB-tree. It turned out that mas_preallocate() requires the maple tree not to change in between pre-allocating nodes with mas_preallocate() and inserting an entry with the help of the pre-allocated memory (mas_insert_prealloc()). However, considering that drivers typically implement interfaces where jobs to create GPU mappings can be submitted by userspace, are queued up by the kernel and are processed asynchronously in dma-fence signalling critical paths, this is a major issue. In the ioctl() used to submit a job we'd need to pre-allocated memory with mas_preallocate(), however, previously queued up jobs could concurrently alter the maple tree resulting in potentially insufficient pre-allocated memory for the currently submitted job on execution time. There is a detailed and still ongoing discussion about this topic one the -mm list [1]. So far the only solution seems to be to use GFP_ATOMIC and allocate memory directly in the fence signalling critical path, where we need it. However, I think that is not what we want to rely on. I think we should definitely continue in trying to find a solution on how to fit in the maple tree (or how to make the maple tree fit in). However, for now it seems to be more expedient to move on using a RB-tree. [1] https://lore.kernel.org/lkml/20230612203953.2093911-15-Liam.Howlett at oracle.com/ - Provide a flag to let driver optionally provide their own lock to lock linking and unlinking of GPUVAs to GEM objects. The DRM GPUVA manager still does not take the locks itself, but rather contains lockdep checks on either the GEMs dma-resv lock (default) or, if DRM_GPUVA_MANAGER_LOCK_EXTERN is set, the driver provided lock. (Boris Brezillon) Changes in V7 ============ Nouveau: - Rebase to drm_exec v7. - Move drm_gem_gpuva_init() before ttm_bo_init_validate(), but after initialization of the corresponding dma-resv. GPUVA Manager: - Fix drm_gpuva_find_first() range parameter in drm_gpuva_for_each_va* macros. (Boris) - Simplify drm_gpuva_for_each_va* macros using a __drm_gpuva_next() helper. (Boris) - Move lockdep checks for an optional external GEM gpuva list lock out of the GPUVA Manager to drm_gem.h. (Boris) - Fix code style issues pointed out by Thomas. - Switch to EXPORT_SYMBOL_GPL(). (Christoph) Changes in V8 ============ Nouveau: - n/a GPUVA Manager: - Fix documentation about locking the GEMs GPUVA list. (Donald) - Fix a few minor checkpatch warnings. Changes in V9 ============ Nouveau: - uAPI header (Faith, Dave): - documented preconditions to successfully initialize the VM_BIND uAPI - renamed drm_nouveau_vm_init unmanaged_{addr,size} to kernel_managed_{addr,size} - add NOUVEAU_GEM_DOMAIN_NO_SHARE flag - allow VM_BIND and EXEC jobs with op_count == 0 (Faith) - add a common dma-resv object for the VM and handle NOUVEAU_GEM_DOMAIN_NO_SHARE accordingly - add armed_submit() callback to nouveau_job - make use of drm_gpuva_map() rather than open code the GPUVA initialization GPUVA Manager : - n/a (merged into drm-misc/drm-misc-next since V8) DRM GEM: - added a patch to fix lockdep checks of GEM GPUVA locks Danilo Krummrich (11): drm/gem: fix lockdep check for dma-resv lock drm/nouveau: new VM_BIND uapi interfaces drm/nouveau: get vmm via nouveau_cli_vmm() drm/nouveau: bo: initialize GEM GPU VA interface drm/nouveau: move usercopy helpers to nouveau_drv.h drm/nouveau: fence: separate fence alloc and emit drm/nouveau: fence: fail to emit when fence context is killed drm/nouveau: chan: provide nouveau_channel_kill() drm/nouveau: nvkm/vmm: implement raw ops to manage uvmm drm/nouveau: implement new VM_BIND uAPI drm/nouveau: debugfs: implement DRM GPU VA debugfs Documentation/gpu/driver-uapi.rst | 11 + drivers/gpu/drm/nouveau/Kbuild | 3 + drivers/gpu/drm/nouveau/Kconfig | 2 + drivers/gpu/drm/nouveau/dispnv04/crtc.c | 9 +- drivers/gpu/drm/nouveau/include/nvif/if000c.h | 26 +- drivers/gpu/drm/nouveau/include/nvif/vmm.h | 19 +- .../gpu/drm/nouveau/include/nvkm/subdev/mmu.h | 20 +- drivers/gpu/drm/nouveau/nouveau_abi16.c | 24 + drivers/gpu/drm/nouveau/nouveau_abi16.h | 1 + drivers/gpu/drm/nouveau/nouveau_bo.c | 221 +- drivers/gpu/drm/nouveau/nouveau_bo.h | 3 +- drivers/gpu/drm/nouveau/nouveau_chan.c | 22 +- drivers/gpu/drm/nouveau/nouveau_chan.h | 1 + drivers/gpu/drm/nouveau/nouveau_debugfs.c | 39 + drivers/gpu/drm/nouveau/nouveau_dmem.c | 9 +- drivers/gpu/drm/nouveau/nouveau_drm.c | 27 +- drivers/gpu/drm/nouveau/nouveau_drv.h | 93 +- drivers/gpu/drm/nouveau/nouveau_exec.c | 436 ++++ drivers/gpu/drm/nouveau/nouveau_exec.h | 54 + drivers/gpu/drm/nouveau/nouveau_fence.c | 23 +- drivers/gpu/drm/nouveau/nouveau_fence.h | 5 +- drivers/gpu/drm/nouveau/nouveau_gem.c | 86 +- drivers/gpu/drm/nouveau/nouveau_gem.h | 3 +- drivers/gpu/drm/nouveau/nouveau_mem.h | 5 + drivers/gpu/drm/nouveau/nouveau_prime.c | 13 +- drivers/gpu/drm/nouveau/nouveau_sched.c | 444 ++++ drivers/gpu/drm/nouveau/nouveau_sched.h | 127 ++ drivers/gpu/drm/nouveau/nouveau_svm.c | 2 +- drivers/gpu/drm/nouveau/nouveau_uvmm.c | 1946 +++++++++++++++++ drivers/gpu/drm/nouveau/nouveau_uvmm.h | 108 + drivers/gpu/drm/nouveau/nouveau_vmm.c | 4 +- drivers/gpu/drm/nouveau/nvif/vmm.c | 100 +- .../gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.c | 213 +- drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c | 197 +- drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h | 25 + .../drm/nouveau/nvkm/subdev/mmu/vmmgf100.c | 16 +- .../drm/nouveau/nvkm/subdev/mmu/vmmgp100.c | 16 +- .../gpu/drm/nouveau/nvkm/subdev/mmu/vmmnv50.c | 27 +- include/drm/drm_gem.h | 15 +- include/uapi/drm/nouveau_drm.h | 217 ++ 40 files changed, 4362 insertions(+), 250 deletions(-) create mode 100644 drivers/gpu/drm/nouveau/nouveau_exec.c create mode 100644 drivers/gpu/drm/nouveau/nouveau_exec.h create mode 100644 drivers/gpu/drm/nouveau/nouveau_sched.c create mode 100644 drivers/gpu/drm/nouveau/nouveau_sched.h create mode 100644 drivers/gpu/drm/nouveau/nouveau_uvmm.c create mode 100644 drivers/gpu/drm/nouveau/nouveau_uvmm.h base-commit: e4774e9968b26dc5d225ce629af8081ddab0029a -- 2.41.0
Danilo Krummrich
2023-Aug-03 16:52 UTC
[Nouveau] [PATCH drm-misc-next v9 01/11] drm/gem: fix lockdep check for dma-resv lock
When no custom lock is set to protect a GEMs GPUVA list, lockdep checks should fall back to the GEM objects dma-resv lock. With the current implementation we're setting the lock_dep_map of the GEM objects 'resv' pointer (in case no custom lock_dep_map is set yet) on drm_gem_private_object_init(). However, the GEM objects 'resv' pointer might still change after drm_gem_private_object_init() is called, e.g. through ttm_bo_init_reserved(). This can result in the wrong lock being tracked. To fix this, call dma_resv_held() directly from drm_gem_gpuva_assert_lock_held() and fall back to the GEMs lock_dep_map pointer only if an actual custom lock is set. Fixes: e6303f323b1a ("drm: manager to keep track of GPUs VA mappings") Signed-off-by: Danilo Krummrich <dakr at redhat.com> --- include/drm/drm_gem.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-) diff --git a/include/drm/drm_gem.h b/include/drm/drm_gem.h index c0b13c43b459..bc9f6aa2f3fe 100644 --- a/include/drm/drm_gem.h +++ b/include/drm/drm_gem.h @@ -551,15 +551,17 @@ int drm_gem_evict(struct drm_gem_object *obj); * @lock: the lock used to protect the gpuva list. The locking primitive * must contain a dep_map field. * - * Call this if you're not proctecting access to the gpuva list - * with the dma-resv lock, otherwise, drm_gem_gpuva_init() takes care - * of initializing lock_dep_map for you. + * Call this if you're not proctecting access to the gpuva list with the + * dma-resv lock, but with a custom lock. */ #define drm_gem_gpuva_set_lock(obj, lock) \ - if (!(obj)->gpuva.lock_dep_map) \ + if (!WARN((obj)->gpuva.lock_dep_map, \ + "GEM GPUVA lock should be set only once.")) \ (obj)->gpuva.lock_dep_map = &(lock)->dep_map #define drm_gem_gpuva_assert_lock_held(obj) \ - lockdep_assert(lock_is_held((obj)->gpuva.lock_dep_map)) + lockdep_assert((obj)->gpuva.lock_dep_map ? \ + lock_is_held((obj)->gpuva.lock_dep_map) : \ + dma_resv_held((obj)->resv)) #else #define drm_gem_gpuva_set_lock(obj, lock) do {} while (0) #define drm_gem_gpuva_assert_lock_held(obj) do {} while (0) @@ -573,11 +575,12 @@ int drm_gem_evict(struct drm_gem_object *obj); * * Calling this function is only necessary for drivers intending to support the * &drm_driver_feature DRIVER_GEM_GPUVA. + * + * See also drm_gem_gpuva_set_lock(). */ static inline void drm_gem_gpuva_init(struct drm_gem_object *obj) { INIT_LIST_HEAD(&obj->gpuva.list); - drm_gem_gpuva_set_lock(obj, &obj->resv->lock.base); } /** -- 2.41.0
Danilo Krummrich
2023-Aug-03 16:52 UTC
[Nouveau] [PATCH drm-misc-next v9 02/11] drm/nouveau: new VM_BIND uapi interfaces
This commit provides the interfaces for the new UAPI motivated by the Vulkan API. It allows user mode drivers (UMDs) to: 1) Initialize a GPU virtual address (VA) space via the new DRM_IOCTL_NOUVEAU_VM_INIT ioctl. UMDs can provide a kernel reserved VA area. 2) Bind and unbind GPU VA space mappings via the new DRM_IOCTL_NOUVEAU_VM_BIND ioctl. 3) Execute push buffers with the new DRM_IOCTL_NOUVEAU_EXEC ioctl. Both, DRM_IOCTL_NOUVEAU_VM_BIND and DRM_IOCTL_NOUVEAU_EXEC support asynchronous processing with DRM syncobjs as synchronization mechanism. The default DRM_IOCTL_NOUVEAU_VM_BIND is synchronous processing, DRM_IOCTL_NOUVEAU_EXEC supports asynchronous processing only. Co-authored-by: Dave Airlie <airlied at redhat.com> Signed-off-by: Danilo Krummrich <dakr at redhat.com> --- Documentation/gpu/driver-uapi.rst | 8 ++ include/uapi/drm/nouveau_drm.h | 217 ++++++++++++++++++++++++++++++ 2 files changed, 225 insertions(+) diff --git a/Documentation/gpu/driver-uapi.rst b/Documentation/gpu/driver-uapi.rst index 4411e6919a3d..9c7ca6e33a68 100644 --- a/Documentation/gpu/driver-uapi.rst +++ b/Documentation/gpu/driver-uapi.rst @@ -6,3 +6,11 @@ drm/i915 uAPI ============ .. kernel-doc:: include/uapi/drm/i915_drm.h + +drm/nouveau uAPI +===============+ +VM_BIND / EXEC uAPI +------------------- + +.. kernel-doc:: include/uapi/drm/nouveau_drm.h diff --git a/include/uapi/drm/nouveau_drm.h b/include/uapi/drm/nouveau_drm.h index 853a327433d3..b567892c128d 100644 --- a/include/uapi/drm/nouveau_drm.h +++ b/include/uapi/drm/nouveau_drm.h @@ -38,6 +38,8 @@ extern "C" { #define NOUVEAU_GEM_DOMAIN_GART (1 << 2) #define NOUVEAU_GEM_DOMAIN_MAPPABLE (1 << 3) #define NOUVEAU_GEM_DOMAIN_COHERENT (1 << 4) +/* The BO will never be shared via import or export. */ +#define NOUVEAU_GEM_DOMAIN_NO_SHARE (1 << 5) #define NOUVEAU_GEM_TILE_COMP 0x00030000 /* nv50-only */ #define NOUVEAU_GEM_TILE_LAYOUT_MASK 0x0000ff00 @@ -126,6 +128,215 @@ struct drm_nouveau_gem_cpu_fini { __u32 handle; }; +/** + * struct drm_nouveau_sync - sync object + * + * This structure serves as synchronization mechanism for (potentially) + * asynchronous operations such as EXEC or VM_BIND. + */ +struct drm_nouveau_sync { + /** + * @flags: the flags for a sync object + * + * The first 8 bits are used to determine the type of the sync object. + */ + __u32 flags; +#define DRM_NOUVEAU_SYNC_SYNCOBJ 0x0 +#define DRM_NOUVEAU_SYNC_TIMELINE_SYNCOBJ 0x1 +#define DRM_NOUVEAU_SYNC_TYPE_MASK 0xf + /** + * @handle: the handle of the sync object + */ + __u32 handle; + /** + * @timeline_value: + * + * The timeline point of the sync object in case the syncobj is of + * type DRM_NOUVEAU_SYNC_TIMELINE_SYNCOBJ. + */ + __u64 timeline_value; +}; + +/** + * struct drm_nouveau_vm_init - GPU VA space init structure + * + * Used to initialize the GPU's VA space for a user client, telling the kernel + * which portion of the VA space is managed by the UMD and kernel respectively. + * + * For the UMD to use the VM_BIND uAPI, this must be called before any BOs or + * channels are created; if called afterwards DRM_IOCTL_NOUVEAU_VM_INIT fails + * with -ENOSYS. + */ +struct drm_nouveau_vm_init { + /** + * @kernel_managed_addr: start address of the kernel managed VA space + * region + */ + __u64 kernel_managed_addr; + /** + * @kernel_managed_size: size of the kernel managed VA space region in + * bytes + */ + __u64 kernel_managed_size; +}; + +/** + * struct drm_nouveau_vm_bind_op - VM_BIND operation + * + * This structure represents a single VM_BIND operation. UMDs should pass + * an array of this structure via struct drm_nouveau_vm_bind's &op_ptr field. + */ +struct drm_nouveau_vm_bind_op { + /** + * @op: the operation type + */ + __u32 op; +/** + * @DRM_NOUVEAU_VM_BIND_OP_MAP: + * + * Map a GEM object to the GPU's VA space. Optionally, the + * &DRM_NOUVEAU_VM_BIND_SPARSE flag can be passed to instruct the kernel to + * create sparse mappings for the given range. + */ +#define DRM_NOUVEAU_VM_BIND_OP_MAP 0x0 +/** + * @DRM_NOUVEAU_VM_BIND_OP_UNMAP: + * + * Unmap an existing mapping in the GPU's VA space. If the region the mapping + * is located in is a sparse region, new sparse mappings are created where the + * unmapped (memory backed) mapping was mapped previously. To remove a sparse + * region the &DRM_NOUVEAU_VM_BIND_SPARSE must be set. + */ +#define DRM_NOUVEAU_VM_BIND_OP_UNMAP 0x1 + /** + * @flags: the flags for a &drm_nouveau_vm_bind_op + */ + __u32 flags; +/** + * @DRM_NOUVEAU_VM_BIND_SPARSE: + * + * Indicates that an allocated VA space region should be sparse. + */ +#define DRM_NOUVEAU_VM_BIND_SPARSE (1 << 8) + /** + * @handle: the handle of the DRM GEM object to map + */ + __u32 handle; + /** + * @pad: 32 bit padding, should be 0 + */ + __u32 pad; + /** + * @addr: + * + * the address the VA space region or (memory backed) mapping should be mapped to + */ + __u64 addr; + /** + * @bo_offset: the offset within the BO backing the mapping + */ + __u64 bo_offset; + /** + * @range: the size of the requested mapping in bytes + */ + __u64 range; +}; + +/** + * struct drm_nouveau_vm_bind - structure for DRM_IOCTL_NOUVEAU_VM_BIND + */ +struct drm_nouveau_vm_bind { + /** + * @op_count: the number of &drm_nouveau_vm_bind_op + */ + __u32 op_count; + /** + * @flags: the flags for a &drm_nouveau_vm_bind ioctl + */ + __u32 flags; +/** + * @DRM_NOUVEAU_VM_BIND_RUN_ASYNC: + * + * Indicates that the given VM_BIND operation should be executed asynchronously + * by the kernel. + * + * If this flag is not supplied the kernel executes the associated operations + * synchronously and doesn't accept any &drm_nouveau_sync objects. + */ +#define DRM_NOUVEAU_VM_BIND_RUN_ASYNC 0x1 + /** + * @wait_count: the number of wait &drm_nouveau_syncs + */ + __u32 wait_count; + /** + * @sig_count: the number of &drm_nouveau_syncs to signal when finished + */ + __u32 sig_count; + /** + * @wait_ptr: pointer to &drm_nouveau_syncs to wait for + */ + __u64 wait_ptr; + /** + * @sig_ptr: pointer to &drm_nouveau_syncs to signal when finished + */ + __u64 sig_ptr; + /** + * @op_ptr: pointer to the &drm_nouveau_vm_bind_ops to execute + */ + __u64 op_ptr; +}; + +/** + * struct drm_nouveau_exec_push - EXEC push operation + * + * This structure represents a single EXEC push operation. UMDs should pass an + * array of this structure via struct drm_nouveau_exec's &push_ptr field. + */ +struct drm_nouveau_exec_push { + /** + * @va: the virtual address of the push buffer mapping + */ + __u64 va; + /** + * @va_len: the length of the push buffer mapping + */ + __u64 va_len; +}; + +/** + * struct drm_nouveau_exec - structure for DRM_IOCTL_NOUVEAU_EXEC + */ +struct drm_nouveau_exec { + /** + * @channel: the channel to execute the push buffer in + */ + __u32 channel; + /** + * @push_count: the number of &drm_nouveau_exec_push ops + */ + __u32 push_count; + /** + * @wait_count: the number of wait &drm_nouveau_syncs + */ + __u32 wait_count; + /** + * @sig_count: the number of &drm_nouveau_syncs to signal when finished + */ + __u32 sig_count; + /** + * @wait_ptr: pointer to &drm_nouveau_syncs to wait for + */ + __u64 wait_ptr; + /** + * @sig_ptr: pointer to &drm_nouveau_syncs to signal when finished + */ + __u64 sig_ptr; + /** + * @push_ptr: pointer to &drm_nouveau_exec_push ops + */ + __u64 push_ptr; +}; + #define DRM_NOUVEAU_GETPARAM 0x00 /* deprecated */ #define DRM_NOUVEAU_SETPARAM 0x01 /* deprecated */ #define DRM_NOUVEAU_CHANNEL_ALLOC 0x02 /* deprecated */ @@ -136,6 +347,9 @@ struct drm_nouveau_gem_cpu_fini { #define DRM_NOUVEAU_NVIF 0x07 #define DRM_NOUVEAU_SVM_INIT 0x08 #define DRM_NOUVEAU_SVM_BIND 0x09 +#define DRM_NOUVEAU_VM_INIT 0x10 +#define DRM_NOUVEAU_VM_BIND 0x11 +#define DRM_NOUVEAU_EXEC 0x12 #define DRM_NOUVEAU_GEM_NEW 0x40 #define DRM_NOUVEAU_GEM_PUSHBUF 0x41 #define DRM_NOUVEAU_GEM_CPU_PREP 0x42 @@ -197,6 +411,9 @@ struct drm_nouveau_svm_bind { #define DRM_IOCTL_NOUVEAU_GEM_CPU_FINI DRM_IOW (DRM_COMMAND_BASE + DRM_NOUVEAU_GEM_CPU_FINI, struct drm_nouveau_gem_cpu_fini) #define DRM_IOCTL_NOUVEAU_GEM_INFO DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_GEM_INFO, struct drm_nouveau_gem_info) +#define DRM_IOCTL_NOUVEAU_VM_INIT DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_VM_INIT, struct drm_nouveau_vm_init) +#define DRM_IOCTL_NOUVEAU_VM_BIND DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_VM_BIND, struct drm_nouveau_vm_bind) +#define DRM_IOCTL_NOUVEAU_EXEC DRM_IOWR(DRM_COMMAND_BASE + DRM_NOUVEAU_EXEC, struct drm_nouveau_exec) #if defined(__cplusplus) } #endif -- 2.41.0
Danilo Krummrich
2023-Aug-03 16:52 UTC
[Nouveau] [PATCH drm-misc-next v9 03/11] drm/nouveau: get vmm via nouveau_cli_vmm()
Provide a getter function for the client's current vmm context. Since we'll add a new (u)vmm context for UMD bindings in subsequent commits, this will keep the code clean. Signed-off-by: Danilo Krummrich <dakr at redhat.com> --- drivers/gpu/drm/nouveau/nouveau_bo.c | 2 +- drivers/gpu/drm/nouveau/nouveau_chan.c | 2 +- drivers/gpu/drm/nouveau/nouveau_drv.h | 9 +++++++++ drivers/gpu/drm/nouveau/nouveau_gem.c | 6 +++--- 4 files changed, 14 insertions(+), 5 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index c2ec91cc845d..7724fe63067d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -204,7 +204,7 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain, struct nouveau_drm *drm = cli->drm; struct nouveau_bo *nvbo; struct nvif_mmu *mmu = &cli->mmu; - struct nvif_vmm *vmm = cli->svm.cli ? &cli->svm.vmm : &cli->vmm.vmm; + struct nvif_vmm *vmm = &nouveau_cli_vmm(cli)->vmm; int i, pi = -1; if (!*size) { diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c index 3dfbc374478e..6d639314250a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_chan.c +++ b/drivers/gpu/drm/nouveau/nouveau_chan.c @@ -149,7 +149,7 @@ nouveau_channel_prep(struct nouveau_drm *drm, struct nvif_device *device, chan->device = device; chan->drm = drm; - chan->vmm = cli->svm.cli ? &cli->svm : &cli->vmm; + chan->vmm = nouveau_cli_vmm(cli); atomic_set(&chan->killed, 0); /* allocate memory for dma push buffer */ diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index b5de312a523f..81350e685b50 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -112,6 +112,15 @@ struct nouveau_cli_work { struct dma_fence_cb cb; }; +static inline struct nouveau_vmm * +nouveau_cli_vmm(struct nouveau_cli *cli) +{ + if (cli->svm.cli) + return &cli->svm; + + return &cli->vmm; +} + void nouveau_cli_work_queue(struct nouveau_cli *, struct dma_fence *, struct nouveau_cli_work *); diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index ab9062e50977..45ca4eb98f54 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -103,7 +103,7 @@ nouveau_gem_object_open(struct drm_gem_object *gem, struct drm_file *file_priv) struct nouveau_bo *nvbo = nouveau_gem_object(gem); struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev); struct device *dev = drm->dev->dev; - struct nouveau_vmm *vmm = cli->svm.cli ? &cli->svm : &cli->vmm; + struct nouveau_vmm *vmm = nouveau_cli_vmm(cli); struct nouveau_vma *vma; int ret; @@ -180,7 +180,7 @@ nouveau_gem_object_close(struct drm_gem_object *gem, struct drm_file *file_priv) struct nouveau_bo *nvbo = nouveau_gem_object(gem); struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev); struct device *dev = drm->dev->dev; - struct nouveau_vmm *vmm = cli->svm.cli ? &cli->svm : & cli->vmm; + struct nouveau_vmm *vmm = nouveau_cli_vmm(cli); struct nouveau_vma *vma; int ret; @@ -269,7 +269,7 @@ nouveau_gem_info(struct drm_file *file_priv, struct drm_gem_object *gem, { struct nouveau_cli *cli = nouveau_cli(file_priv); struct nouveau_bo *nvbo = nouveau_gem_object(gem); - struct nouveau_vmm *vmm = cli->svm.cli ? &cli->svm : &cli->vmm; + struct nouveau_vmm *vmm = nouveau_cli_vmm(cli); struct nouveau_vma *vma; if (is_power_of_2(nvbo->valid_domains)) -- 2.41.0
Danilo Krummrich
2023-Aug-03 16:52 UTC
[Nouveau] [PATCH drm-misc-next v9 04/11] drm/nouveau: bo: initialize GEM GPU VA interface
Initialize the GEM's DRM GPU VA manager interface in preparation for the (u)vmm implementation, provided by subsequent commits, to make use of it. Signed-off-by: Danilo Krummrich <dakr at redhat.com> --- drivers/gpu/drm/nouveau/nouveau_bo.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 7724fe63067d..057bc995f19b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -215,11 +215,14 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain, nvbo = kzalloc(sizeof(struct nouveau_bo), GFP_KERNEL); if (!nvbo) return ERR_PTR(-ENOMEM); + INIT_LIST_HEAD(&nvbo->head); INIT_LIST_HEAD(&nvbo->entry); INIT_LIST_HEAD(&nvbo->vma_list); nvbo->bo.bdev = &drm->ttm.bdev; + drm_gem_gpuva_init(&nvbo->bo.base); + /* This is confusing, and doesn't actually mean we want an uncached * mapping, but is what NOUVEAU_GEM_DOMAIN_COHERENT gets translated * into in nouveau_gem_new(). -- 2.41.0
Danilo Krummrich
2023-Aug-03 16:52 UTC
[Nouveau] [PATCH drm-misc-next v9 05/11] drm/nouveau: move usercopy helpers to nouveau_drv.h
Move the usercopy helpers to a common driver header file to make it usable for the new API added in subsequent commits. Signed-off-by: Danilo Krummrich <dakr at redhat.com> --- drivers/gpu/drm/nouveau/nouveau_drv.h | 26 ++++++++++++++++++++++++++ drivers/gpu/drm/nouveau/nouveau_gem.c | 26 -------------------------- 2 files changed, 26 insertions(+), 26 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index 81350e685b50..d28236021971 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -130,6 +130,32 @@ nouveau_cli(struct drm_file *fpriv) return fpriv ? fpriv->driver_priv : NULL; } +static inline void +u_free(void *addr) +{ + kvfree(addr); +} + +static inline void * +u_memcpya(uint64_t user, unsigned int nmemb, unsigned int size) +{ + void *mem; + void __user *userptr = (void __force __user *)(uintptr_t)user; + + size *= nmemb; + + mem = kvmalloc(size, GFP_KERNEL); + if (!mem) + return ERR_PTR(-ENOMEM); + + if (copy_from_user(mem, userptr, size)) { + u_free(mem); + return ERR_PTR(-EFAULT); + } + + return mem; +} + #include <nvif/object.h> #include <nvif/parent.h> diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index 45ca4eb98f54..a48f42aaeab9 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -613,32 +613,6 @@ nouveau_gem_pushbuf_validate(struct nouveau_channel *chan, return 0; } -static inline void -u_free(void *addr) -{ - kvfree(addr); -} - -static inline void * -u_memcpya(uint64_t user, unsigned nmemb, unsigned size) -{ - void *mem; - void __user *userptr = (void __force __user *)(uintptr_t)user; - - size *= nmemb; - - mem = kvmalloc(size, GFP_KERNEL); - if (!mem) - return ERR_PTR(-ENOMEM); - - if (copy_from_user(mem, userptr, size)) { - u_free(mem); - return ERR_PTR(-EFAULT); - } - - return mem; -} - static int nouveau_gem_pushbuf_reloc_apply(struct nouveau_cli *cli, struct drm_nouveau_gem_pushbuf *req, -- 2.41.0
Danilo Krummrich
2023-Aug-03 16:52 UTC
[Nouveau] [PATCH drm-misc-next v9 06/11] drm/nouveau: fence: separate fence alloc and emit
The new (VM_BIND) UAPI exports DMA fences through DRM syncobjs. Hence, in order to emit fences within DMA fence signalling critical sections (e.g. as typically done in the DRM GPU schedulers run_job() callback) we need to separate fence allocation and fence emitting. Signed-off-by: Danilo Krummrich <dakr at redhat.com> --- drivers/gpu/drm/nouveau/dispnv04/crtc.c | 9 ++++- drivers/gpu/drm/nouveau/nouveau_bo.c | 52 +++++++++++++++---------- drivers/gpu/drm/nouveau/nouveau_chan.c | 6 ++- drivers/gpu/drm/nouveau/nouveau_dmem.c | 9 +++-- drivers/gpu/drm/nouveau/nouveau_fence.c | 16 +++----- drivers/gpu/drm/nouveau/nouveau_fence.h | 3 +- drivers/gpu/drm/nouveau/nouveau_gem.c | 5 ++- 7 files changed, 59 insertions(+), 41 deletions(-) diff --git a/drivers/gpu/drm/nouveau/dispnv04/crtc.c b/drivers/gpu/drm/nouveau/dispnv04/crtc.c index a6f2e681bde9..a34924523133 100644 --- a/drivers/gpu/drm/nouveau/dispnv04/crtc.c +++ b/drivers/gpu/drm/nouveau/dispnv04/crtc.c @@ -1122,11 +1122,18 @@ nv04_page_flip_emit(struct nouveau_channel *chan, PUSH_NVSQ(push, NV_SW, NV_SW_PAGE_FLIP, 0x00000000); PUSH_KICK(push); - ret = nouveau_fence_new(chan, false, pfence); + ret = nouveau_fence_new(pfence); if (ret) goto fail; + ret = nouveau_fence_emit(*pfence, chan); + if (ret) + goto fail_fence_unref; + return 0; + +fail_fence_unref: + nouveau_fence_unref(pfence); fail: spin_lock_irqsave(&dev->event_lock, flags); list_del(&s->head); diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index 057bc995f19b..e9cbbf594e6f 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -820,29 +820,39 @@ nouveau_bo_move_m2mf(struct ttm_buffer_object *bo, int evict, mutex_lock(&cli->mutex); else mutex_lock_nested(&cli->mutex, SINGLE_DEPTH_NESTING); + ret = nouveau_fence_sync(nouveau_bo(bo), chan, true, ctx->interruptible); - if (ret == 0) { - ret = drm->ttm.move(chan, bo, bo->resource, new_reg); - if (ret == 0) { - ret = nouveau_fence_new(chan, false, &fence); - if (ret == 0) { - /* TODO: figure out a better solution here - * - * wait on the fence here explicitly as going through - * ttm_bo_move_accel_cleanup somehow doesn't seem to do it. - * - * Without this the operation can timeout and we'll fallback to a - * software copy, which might take several minutes to finish. - */ - nouveau_fence_wait(fence, false, false); - ret = ttm_bo_move_accel_cleanup(bo, - &fence->base, - evict, false, - new_reg); - nouveau_fence_unref(&fence); - } - } + if (ret) + goto out_unlock; + + ret = drm->ttm.move(chan, bo, bo->resource, new_reg); + if (ret) + goto out_unlock; + + ret = nouveau_fence_new(&fence); + if (ret) + goto out_unlock; + + ret = nouveau_fence_emit(fence, chan); + if (ret) { + nouveau_fence_unref(&fence); + goto out_unlock; } + + /* TODO: figure out a better solution here + * + * wait on the fence here explicitly as going through + * ttm_bo_move_accel_cleanup somehow doesn't seem to do it. + * + * Without this the operation can timeout and we'll fallback to a + * software copy, which might take several minutes to finish. + */ + nouveau_fence_wait(fence, false, false); + ret = ttm_bo_move_accel_cleanup(bo, &fence->base, evict, false, + new_reg); + nouveau_fence_unref(&fence); + +out_unlock: mutex_unlock(&cli->mutex); return ret; } diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c index 6d639314250a..f69be4c8f9f2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_chan.c +++ b/drivers/gpu/drm/nouveau/nouveau_chan.c @@ -62,9 +62,11 @@ nouveau_channel_idle(struct nouveau_channel *chan) struct nouveau_fence *fence = NULL; int ret; - ret = nouveau_fence_new(chan, false, &fence); + ret = nouveau_fence_new(&fence); if (!ret) { - ret = nouveau_fence_wait(fence, false, false); + ret = nouveau_fence_emit(fence, chan); + if (!ret) + ret = nouveau_fence_wait(fence, false, false); nouveau_fence_unref(&fence); } diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index 789857faa048..4ad40e42cae1 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -209,7 +209,8 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) goto done; } - nouveau_fence_new(dmem->migrate.chan, false, &fence); + if (!nouveau_fence_new(&fence)) + nouveau_fence_emit(fence, dmem->migrate.chan); migrate_vma_pages(&args); nouveau_dmem_fence_done(&fence); dma_unmap_page(drm->dev->dev, dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); @@ -402,7 +403,8 @@ nouveau_dmem_evict_chunk(struct nouveau_dmem_chunk *chunk) } } - nouveau_fence_new(chunk->drm->dmem->migrate.chan, false, &fence); + if (!nouveau_fence_new(&fence)) + nouveau_fence_emit(fence, chunk->drm->dmem->migrate.chan); migrate_device_pages(src_pfns, dst_pfns, npages); nouveau_dmem_fence_done(&fence); migrate_device_finalize(src_pfns, dst_pfns, npages); @@ -675,7 +677,8 @@ static void nouveau_dmem_migrate_chunk(struct nouveau_drm *drm, addr += PAGE_SIZE; } - nouveau_fence_new(drm->dmem->migrate.chan, false, &fence); + if (!nouveau_fence_new(&fence)) + nouveau_fence_emit(fence, chunk->drm->dmem->migrate.chan); migrate_vma_pages(args); nouveau_dmem_fence_done(&fence); nouveau_pfns_map(svmm, args->vma->vm_mm, args->start, pfns, i); diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index ee5e9d40c166..e946408f945b 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -210,6 +210,9 @@ nouveau_fence_emit(struct nouveau_fence *fence, struct nouveau_channel *chan) struct nouveau_fence_priv *priv = (void*)chan->drm->fence; int ret; + if (unlikely(!chan->fence)) + return -ENODEV; + fence->channel = chan; fence->timeout = jiffies + (15 * HZ); @@ -396,25 +399,16 @@ nouveau_fence_unref(struct nouveau_fence **pfence) } int -nouveau_fence_new(struct nouveau_channel *chan, bool sysmem, - struct nouveau_fence **pfence) +nouveau_fence_new(struct nouveau_fence **pfence) { struct nouveau_fence *fence; - int ret = 0; - - if (unlikely(!chan->fence)) - return -ENODEV; fence = kzalloc(sizeof(*fence), GFP_KERNEL); if (!fence) return -ENOMEM; - ret = nouveau_fence_emit(fence, chan); - if (ret) - nouveau_fence_unref(&fence); - *pfence = fence; - return ret; + return 0; } static const char *nouveau_fence_get_get_driver_name(struct dma_fence *fence) diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h index 0ca2bc85adf6..7c73c7c9834a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.h +++ b/drivers/gpu/drm/nouveau/nouveau_fence.h @@ -17,8 +17,7 @@ struct nouveau_fence { unsigned long timeout; }; -int nouveau_fence_new(struct nouveau_channel *, bool sysmem, - struct nouveau_fence **); +int nouveau_fence_new(struct nouveau_fence **); void nouveau_fence_unref(struct nouveau_fence **); int nouveau_fence_emit(struct nouveau_fence *, struct nouveau_channel *); diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index a48f42aaeab9..9c8d1b911a01 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -873,8 +873,11 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data, } } - ret = nouveau_fence_new(chan, false, &fence); + ret = nouveau_fence_new(&fence); + if (!ret) + ret = nouveau_fence_emit(fence, chan); if (ret) { + nouveau_fence_unref(&fence); NV_PRINTK(err, cli, "error fencing pushbuf: %d\n", ret); WIND_RING(chan); goto out; -- 2.41.0
Danilo Krummrich
2023-Aug-03 16:52 UTC
[Nouveau] [PATCH drm-misc-next v9 07/11] drm/nouveau: fence: fail to emit when fence context is killed
The new VM_BIND UAPI implementation introduced in subsequent commits will allow asynchronous jobs processing push buffers and emitting fences. If a fence context is killed, e.g. due to a channel fault, jobs which are already queued for execution might still emit new fences. In such a case a job would hang forever. To fix that, fail to emit a new fence on a killed fence context with -ENODEV to unblock the job. Signed-off-by: Danilo Krummrich <dakr at redhat.com> --- drivers/gpu/drm/nouveau/nouveau_fence.c | 7 +++++++ drivers/gpu/drm/nouveau/nouveau_fence.h | 2 +- 2 files changed, 8 insertions(+), 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.c b/drivers/gpu/drm/nouveau/nouveau_fence.c index e946408f945b..77c739a55b19 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.c +++ b/drivers/gpu/drm/nouveau/nouveau_fence.c @@ -96,6 +96,7 @@ nouveau_fence_context_kill(struct nouveau_fence_chan *fctx, int error) if (nouveau_fence_signal(fence)) nvif_event_block(&fctx->event); } + fctx->killed = 1; spin_unlock_irqrestore(&fctx->lock, flags); } @@ -229,6 +230,12 @@ nouveau_fence_emit(struct nouveau_fence *fence, struct nouveau_channel *chan) dma_fence_get(&fence->base); spin_lock_irq(&fctx->lock); + if (unlikely(fctx->killed)) { + spin_unlock_irq(&fctx->lock); + dma_fence_put(&fence->base); + return -ENODEV; + } + if (nouveau_fence_update(chan, fctx)) nvif_event_block(&fctx->event); diff --git a/drivers/gpu/drm/nouveau/nouveau_fence.h b/drivers/gpu/drm/nouveau/nouveau_fence.h index 7c73c7c9834a..2c72d96ef17d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fence.h +++ b/drivers/gpu/drm/nouveau/nouveau_fence.h @@ -44,7 +44,7 @@ struct nouveau_fence_chan { char name[32]; struct nvif_event event; - int notify_ref, dead; + int notify_ref, dead, killed; }; struct nouveau_fence_priv { -- 2.41.0
Danilo Krummrich
2023-Aug-03 16:52 UTC
[Nouveau] [PATCH drm-misc-next v9 08/11] drm/nouveau: chan: provide nouveau_channel_kill()
The new VM_BIND UAPI implementation introduced in subsequent commits will allow asynchronous jobs processing push buffers and emitting fences. If a job times out, we need a way to recover from this situation. For now, simply kill the channel to unblock all hung up jobs and signal userspace that the device is dead on the next EXEC or VM_BIND ioctl. Signed-off-by: Danilo Krummrich <dakr at redhat.com> --- drivers/gpu/drm/nouveau/nouveau_chan.c | 14 +++++++++++--- drivers/gpu/drm/nouveau/nouveau_chan.h | 1 + 2 files changed, 12 insertions(+), 3 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.c b/drivers/gpu/drm/nouveau/nouveau_chan.c index f69be4c8f9f2..1fd5ccf41128 100644 --- a/drivers/gpu/drm/nouveau/nouveau_chan.c +++ b/drivers/gpu/drm/nouveau/nouveau_chan.c @@ -40,6 +40,14 @@ MODULE_PARM_DESC(vram_pushbuf, "Create DMA push buffers in VRAM"); int nouveau_vram_pushbuf; module_param_named(vram_pushbuf, nouveau_vram_pushbuf, int, 0400); +void +nouveau_channel_kill(struct nouveau_channel *chan) +{ + atomic_set(&chan->killed, 1); + if (chan->fence) + nouveau_fence_context_kill(chan->fence, -ENODEV); +} + static int nouveau_channel_killed(struct nvif_event *event, void *repv, u32 repc) { @@ -47,9 +55,9 @@ nouveau_channel_killed(struct nvif_event *event, void *repv, u32 repc) struct nouveau_cli *cli = (void *)chan->user.client; NV_PRINTK(warn, cli, "channel %d killed!\n", chan->chid); - atomic_set(&chan->killed, 1); - if (chan->fence) - nouveau_fence_context_kill(chan->fence, -ENODEV); + + if (unlikely(!atomic_read(&chan->killed))) + nouveau_channel_kill(chan); return NVIF_EVENT_DROP; } diff --git a/drivers/gpu/drm/nouveau/nouveau_chan.h b/drivers/gpu/drm/nouveau/nouveau_chan.h index bad7466bd0d5..5de2ef4e98c2 100644 --- a/drivers/gpu/drm/nouveau/nouveau_chan.h +++ b/drivers/gpu/drm/nouveau/nouveau_chan.h @@ -66,6 +66,7 @@ int nouveau_channel_new(struct nouveau_drm *, struct nvif_device *, bool priv, u32 vram, u32 gart, struct nouveau_channel **); void nouveau_channel_del(struct nouveau_channel **); int nouveau_channel_idle(struct nouveau_channel *); +void nouveau_channel_kill(struct nouveau_channel *); extern int nouveau_vram_pushbuf; -- 2.41.0
Danilo Krummrich
2023-Aug-03 16:52 UTC
[Nouveau] [PATCH drm-misc-next v9 09/11] drm/nouveau: nvkm/vmm: implement raw ops to manage uvmm
The new VM_BIND UAPI uses the DRM GPU VA manager to manage the VA space. Hence, we a need a way to manipulate the MMUs page tables without going through the internal range allocator implemented by nvkm/vmm. This patch adds a raw interface for nvkm/vmm to pass the resposibility for managing the address space and the corresponding map/unmap/sparse operations to the upper layers. Signed-off-by: Danilo Krummrich <dakr at redhat.com> --- drivers/gpu/drm/nouveau/include/nvif/if000c.h | 26 ++- drivers/gpu/drm/nouveau/include/nvif/vmm.h | 19 +- .../gpu/drm/nouveau/include/nvkm/subdev/mmu.h | 20 +- drivers/gpu/drm/nouveau/nouveau_svm.c | 2 +- drivers/gpu/drm/nouveau/nouveau_vmm.c | 4 +- drivers/gpu/drm/nouveau/nvif/vmm.c | 100 +++++++- .../gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.c | 213 ++++++++++++++++-- drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c | 197 ++++++++++++---- drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h | 25 ++ .../drm/nouveau/nvkm/subdev/mmu/vmmgf100.c | 16 +- .../drm/nouveau/nvkm/subdev/mmu/vmmgp100.c | 16 +- .../gpu/drm/nouveau/nvkm/subdev/mmu/vmmnv50.c | 27 ++- 12 files changed, 566 insertions(+), 99 deletions(-) diff --git a/drivers/gpu/drm/nouveau/include/nvif/if000c.h b/drivers/gpu/drm/nouveau/include/nvif/if000c.h index 9c7ff56831c5..a5a182b3c28d 100644 --- a/drivers/gpu/drm/nouveau/include/nvif/if000c.h +++ b/drivers/gpu/drm/nouveau/include/nvif/if000c.h @@ -3,7 +3,10 @@ struct nvif_vmm_v0 { __u8 version; __u8 page_nr; - __u8 managed; +#define NVIF_VMM_V0_TYPE_UNMANAGED 0x00 +#define NVIF_VMM_V0_TYPE_MANAGED 0x01 +#define NVIF_VMM_V0_TYPE_RAW 0x02 + __u8 type; __u8 pad03[5]; __u64 addr; __u64 size; @@ -17,6 +20,7 @@ struct nvif_vmm_v0 { #define NVIF_VMM_V0_UNMAP 0x04 #define NVIF_VMM_V0_PFNMAP 0x05 #define NVIF_VMM_V0_PFNCLR 0x06 +#define NVIF_VMM_V0_RAW 0x07 #define NVIF_VMM_V0_MTHD(i) ((i) + 0x80) struct nvif_vmm_page_v0 { @@ -66,6 +70,26 @@ struct nvif_vmm_unmap_v0 { __u64 addr; }; +struct nvif_vmm_raw_v0 { + __u8 version; +#define NVIF_VMM_RAW_V0_GET 0x0 +#define NVIF_VMM_RAW_V0_PUT 0x1 +#define NVIF_VMM_RAW_V0_MAP 0x2 +#define NVIF_VMM_RAW_V0_UNMAP 0x3 +#define NVIF_VMM_RAW_V0_SPARSE 0x4 + __u8 op; + __u8 sparse; + __u8 ref; + __u8 shift; + __u32 argc; + __u8 pad01[7]; + __u64 addr; + __u64 size; + __u64 offset; + __u64 memory; + __u64 argv; +}; + struct nvif_vmm_pfnmap_v0 { __u8 version; __u8 page; diff --git a/drivers/gpu/drm/nouveau/include/nvif/vmm.h b/drivers/gpu/drm/nouveau/include/nvif/vmm.h index a2ee92201ace..0ecedd0ee0a5 100644 --- a/drivers/gpu/drm/nouveau/include/nvif/vmm.h +++ b/drivers/gpu/drm/nouveau/include/nvif/vmm.h @@ -4,6 +4,12 @@ struct nvif_mem; struct nvif_mmu; +enum nvif_vmm_type { + UNMANAGED, + MANAGED, + RAW, +}; + enum nvif_vmm_get { ADDR, PTES, @@ -30,8 +36,9 @@ struct nvif_vmm { int page_nr; }; -int nvif_vmm_ctor(struct nvif_mmu *, const char *name, s32 oclass, bool managed, - u64 addr, u64 size, void *argv, u32 argc, struct nvif_vmm *); +int nvif_vmm_ctor(struct nvif_mmu *, const char *name, s32 oclass, + enum nvif_vmm_type, u64 addr, u64 size, void *argv, u32 argc, + struct nvif_vmm *); void nvif_vmm_dtor(struct nvif_vmm *); int nvif_vmm_get(struct nvif_vmm *, enum nvif_vmm_get, bool sparse, u8 page, u8 align, u64 size, struct nvif_vma *); @@ -39,4 +46,12 @@ void nvif_vmm_put(struct nvif_vmm *, struct nvif_vma *); int nvif_vmm_map(struct nvif_vmm *, u64 addr, u64 size, void *argv, u32 argc, struct nvif_mem *, u64 offset); int nvif_vmm_unmap(struct nvif_vmm *, u64); + +int nvif_vmm_raw_get(struct nvif_vmm *vmm, u64 addr, u64 size, u8 shift); +int nvif_vmm_raw_put(struct nvif_vmm *vmm, u64 addr, u64 size, u8 shift); +int nvif_vmm_raw_map(struct nvif_vmm *vmm, u64 addr, u64 size, u8 shift, + void *argv, u32 argc, struct nvif_mem *mem, u64 offset); +int nvif_vmm_raw_unmap(struct nvif_vmm *vmm, u64 addr, u64 size, + u8 shift, bool sparse); +int nvif_vmm_raw_sparse(struct nvif_vmm *vmm, u64 addr, u64 size, bool ref); #endif diff --git a/drivers/gpu/drm/nouveau/include/nvkm/subdev/mmu.h b/drivers/gpu/drm/nouveau/include/nvkm/subdev/mmu.h index 70e7887ef4b4..2fd2f2433fc7 100644 --- a/drivers/gpu/drm/nouveau/include/nvkm/subdev/mmu.h +++ b/drivers/gpu/drm/nouveau/include/nvkm/subdev/mmu.h @@ -17,6 +17,7 @@ struct nvkm_vma { bool part:1; /* Region was split from an allocated region by map(). */ bool busy:1; /* Region busy (for temporarily preventing user access). */ bool mapped:1; /* Region contains valid pages. */ + bool no_comp:1; /* Force no memory compression. */ struct nvkm_memory *memory; /* Memory currently mapped into VMA. */ struct nvkm_tags *tags; /* Compression tag reference. */ }; @@ -27,10 +28,26 @@ struct nvkm_vmm { const char *name; u32 debug; struct kref kref; - struct mutex mutex; + + struct { + struct mutex vmm; + struct mutex ref; + struct mutex map; + } mutex; u64 start; u64 limit; + struct { + struct { + u64 addr; + u64 size; + } p; + struct { + u64 addr; + u64 size; + } n; + bool raw; + } managed; struct nvkm_vmm_pt *pd; struct list_head join; @@ -70,6 +87,7 @@ struct nvkm_vmm_map { const struct nvkm_vmm_page *page; + bool no_comp; struct nvkm_tags *tags; u64 next; u64 type; diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index a74ba8d84ba7..186351ecf72f 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -350,7 +350,7 @@ nouveau_svmm_init(struct drm_device *dev, void *data, * VMM instead of the standard one. */ ret = nvif_vmm_ctor(&cli->mmu, "svmVmm", - cli->vmm.vmm.object.oclass, true, + cli->vmm.vmm.object.oclass, MANAGED, args->unmanaged_addr, args->unmanaged_size, &(struct gp100_vmm_v0) { .fault_replay = true, diff --git a/drivers/gpu/drm/nouveau/nouveau_vmm.c b/drivers/gpu/drm/nouveau/nouveau_vmm.c index 67d6619fcd5e..a6602c012671 100644 --- a/drivers/gpu/drm/nouveau/nouveau_vmm.c +++ b/drivers/gpu/drm/nouveau/nouveau_vmm.c @@ -128,8 +128,8 @@ nouveau_vmm_fini(struct nouveau_vmm *vmm) int nouveau_vmm_init(struct nouveau_cli *cli, s32 oclass, struct nouveau_vmm *vmm) { - int ret = nvif_vmm_ctor(&cli->mmu, "drmVmm", oclass, false, PAGE_SIZE, - 0, NULL, 0, &vmm->vmm); + int ret = nvif_vmm_ctor(&cli->mmu, "drmVmm", oclass, UNMANAGED, + PAGE_SIZE, 0, NULL, 0, &vmm->vmm); if (ret) return ret; diff --git a/drivers/gpu/drm/nouveau/nvif/vmm.c b/drivers/gpu/drm/nouveau/nvif/vmm.c index 6053d6dc2184..99296f03371a 100644 --- a/drivers/gpu/drm/nouveau/nvif/vmm.c +++ b/drivers/gpu/drm/nouveau/nvif/vmm.c @@ -104,6 +104,90 @@ nvif_vmm_get(struct nvif_vmm *vmm, enum nvif_vmm_get type, bool sparse, return ret; } +int +nvif_vmm_raw_get(struct nvif_vmm *vmm, u64 addr, u64 size, + u8 shift) +{ + struct nvif_vmm_raw_v0 args = { + .version = 0, + .op = NVIF_VMM_RAW_V0_GET, + .addr = addr, + .size = size, + .shift = shift, + }; + + return nvif_object_mthd(&vmm->object, NVIF_VMM_V0_RAW, + &args, sizeof(args)); +} + +int +nvif_vmm_raw_put(struct nvif_vmm *vmm, u64 addr, u64 size, u8 shift) +{ + struct nvif_vmm_raw_v0 args = { + .version = 0, + .op = NVIF_VMM_RAW_V0_PUT, + .addr = addr, + .size = size, + .shift = shift, + }; + + return nvif_object_mthd(&vmm->object, NVIF_VMM_V0_RAW, + &args, sizeof(args)); +} + +int +nvif_vmm_raw_map(struct nvif_vmm *vmm, u64 addr, u64 size, u8 shift, + void *argv, u32 argc, struct nvif_mem *mem, u64 offset) +{ + struct nvif_vmm_raw_v0 args = { + .version = 0, + .op = NVIF_VMM_RAW_V0_MAP, + .addr = addr, + .size = size, + .shift = shift, + .memory = nvif_handle(&mem->object), + .offset = offset, + .argv = (u64)(uintptr_t)argv, + .argc = argc, + }; + + + return nvif_object_mthd(&vmm->object, NVIF_VMM_V0_RAW, + &args, sizeof(args)); +} + +int +nvif_vmm_raw_unmap(struct nvif_vmm *vmm, u64 addr, u64 size, + u8 shift, bool sparse) +{ + struct nvif_vmm_raw_v0 args = { + .version = 0, + .op = NVIF_VMM_RAW_V0_UNMAP, + .addr = addr, + .size = size, + .shift = shift, + .sparse = sparse, + }; + + return nvif_object_mthd(&vmm->object, NVIF_VMM_V0_RAW, + &args, sizeof(args)); +} + +int +nvif_vmm_raw_sparse(struct nvif_vmm *vmm, u64 addr, u64 size, bool ref) +{ + struct nvif_vmm_raw_v0 args = { + .version = 0, + .op = NVIF_VMM_RAW_V0_SPARSE, + .addr = addr, + .size = size, + .ref = ref, + }; + + return nvif_object_mthd(&vmm->object, NVIF_VMM_V0_RAW, + &args, sizeof(args)); +} + void nvif_vmm_dtor(struct nvif_vmm *vmm) { @@ -112,8 +196,9 @@ nvif_vmm_dtor(struct nvif_vmm *vmm) } int -nvif_vmm_ctor(struct nvif_mmu *mmu, const char *name, s32 oclass, bool managed, - u64 addr, u64 size, void *argv, u32 argc, struct nvif_vmm *vmm) +nvif_vmm_ctor(struct nvif_mmu *mmu, const char *name, s32 oclass, + enum nvif_vmm_type type, u64 addr, u64 size, void *argv, u32 argc, + struct nvif_vmm *vmm) { struct nvif_vmm_v0 *args; u32 argn = sizeof(*args) + argc; @@ -125,9 +210,18 @@ nvif_vmm_ctor(struct nvif_mmu *mmu, const char *name, s32 oclass, bool managed, if (!(args = kmalloc(argn, GFP_KERNEL))) return -ENOMEM; args->version = 0; - args->managed = managed; args->addr = addr; args->size = size; + + switch (type) { + case UNMANAGED: args->type = NVIF_VMM_V0_TYPE_UNMANAGED; break; + case MANAGED: args->type = NVIF_VMM_V0_TYPE_MANAGED; break; + case RAW: args->type = NVIF_VMM_V0_TYPE_RAW; break; + default: + WARN_ON(1); + return -EINVAL; + } + memcpy(args->data, argv, argc); ret = nvif_object_ctor(&mmu->object, name ? name : "nvifVmm", 0, diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.c index 524cd3c0e3fe..38b7ced934b1 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.c @@ -58,10 +58,13 @@ nvkm_uvmm_mthd_pfnclr(struct nvkm_uvmm *uvmm, void *argv, u32 argc) } else return ret; + if (nvkm_vmm_in_managed_range(vmm, addr, size) && vmm->managed.raw) + return -EINVAL; + if (size) { - mutex_lock(&vmm->mutex); + mutex_lock(&vmm->mutex.vmm); ret = nvkm_vmm_pfn_unmap(vmm, addr, size); - mutex_unlock(&vmm->mutex); + mutex_unlock(&vmm->mutex.vmm); } return ret; @@ -88,10 +91,13 @@ nvkm_uvmm_mthd_pfnmap(struct nvkm_uvmm *uvmm, void *argv, u32 argc) } else return ret; + if (nvkm_vmm_in_managed_range(vmm, addr, size) && vmm->managed.raw) + return -EINVAL; + if (size) { - mutex_lock(&vmm->mutex); + mutex_lock(&vmm->mutex.vmm); ret = nvkm_vmm_pfn_map(vmm, page, addr, size, phys); - mutex_unlock(&vmm->mutex); + mutex_unlock(&vmm->mutex.vmm); } return ret; @@ -113,7 +119,10 @@ nvkm_uvmm_mthd_unmap(struct nvkm_uvmm *uvmm, void *argv, u32 argc) } else return ret; - mutex_lock(&vmm->mutex); + if (nvkm_vmm_in_managed_range(vmm, addr, 0) && vmm->managed.raw) + return -EINVAL; + + mutex_lock(&vmm->mutex.vmm); vma = nvkm_vmm_node_search(vmm, addr); if (ret = -ENOENT, !vma || vma->addr != addr) { VMM_DEBUG(vmm, "lookup %016llx: %016llx", @@ -134,7 +143,7 @@ nvkm_uvmm_mthd_unmap(struct nvkm_uvmm *uvmm, void *argv, u32 argc) nvkm_vmm_unmap_locked(vmm, vma, false); ret = 0; done: - mutex_unlock(&vmm->mutex); + mutex_unlock(&vmm->mutex.vmm); return ret; } @@ -159,13 +168,16 @@ nvkm_uvmm_mthd_map(struct nvkm_uvmm *uvmm, void *argv, u32 argc) } else return ret; + if (nvkm_vmm_in_managed_range(vmm, addr, size) && vmm->managed.raw) + return -EINVAL; + memory = nvkm_umem_search(client, handle); if (IS_ERR(memory)) { VMM_DEBUG(vmm, "memory %016llx %ld\n", handle, PTR_ERR(memory)); return PTR_ERR(memory); } - mutex_lock(&vmm->mutex); + mutex_lock(&vmm->mutex.vmm); if (ret = -ENOENT, !(vma = nvkm_vmm_node_search(vmm, addr))) { VMM_DEBUG(vmm, "lookup %016llx", addr); goto fail; @@ -198,7 +210,7 @@ nvkm_uvmm_mthd_map(struct nvkm_uvmm *uvmm, void *argv, u32 argc) } } vma->busy = true; - mutex_unlock(&vmm->mutex); + mutex_unlock(&vmm->mutex.vmm); ret = nvkm_memory_map(memory, offset, vmm, vma, argv, argc); if (ret == 0) { @@ -207,11 +219,11 @@ nvkm_uvmm_mthd_map(struct nvkm_uvmm *uvmm, void *argv, u32 argc) return 0; } - mutex_lock(&vmm->mutex); + mutex_lock(&vmm->mutex.vmm); vma->busy = false; nvkm_vmm_unmap_region(vmm, vma); fail: - mutex_unlock(&vmm->mutex); + mutex_unlock(&vmm->mutex.vmm); nvkm_memory_unref(&memory); return ret; } @@ -232,7 +244,7 @@ nvkm_uvmm_mthd_put(struct nvkm_uvmm *uvmm, void *argv, u32 argc) } else return ret; - mutex_lock(&vmm->mutex); + mutex_lock(&vmm->mutex.vmm); vma = nvkm_vmm_node_search(vmm, args->v0.addr); if (ret = -ENOENT, !vma || vma->addr != addr || vma->part) { VMM_DEBUG(vmm, "lookup %016llx: %016llx %d", addr, @@ -248,7 +260,7 @@ nvkm_uvmm_mthd_put(struct nvkm_uvmm *uvmm, void *argv, u32 argc) nvkm_vmm_put_locked(vmm, vma); ret = 0; done: - mutex_unlock(&vmm->mutex); + mutex_unlock(&vmm->mutex.vmm); return ret; } @@ -275,10 +287,10 @@ nvkm_uvmm_mthd_get(struct nvkm_uvmm *uvmm, void *argv, u32 argc) } else return ret; - mutex_lock(&vmm->mutex); + mutex_lock(&vmm->mutex.vmm); ret = nvkm_vmm_get_locked(vmm, getref, mapref, sparse, page, align, size, &vma); - mutex_unlock(&vmm->mutex); + mutex_unlock(&vmm->mutex.vmm); if (ret) return ret; @@ -314,6 +326,167 @@ nvkm_uvmm_mthd_page(struct nvkm_uvmm *uvmm, void *argv, u32 argc) return 0; } +static inline int +nvkm_uvmm_page_index(struct nvkm_uvmm *uvmm, u64 size, u8 shift, u8 *refd) +{ + struct nvkm_vmm *vmm = uvmm->vmm; + const struct nvkm_vmm_page *page; + + if (likely(shift)) { + for (page = vmm->func->page; page->shift; page++) { + if (shift == page->shift) + break; + } + + if (!page->shift || !IS_ALIGNED(size, 1ULL << page->shift)) { + VMM_DEBUG(vmm, "page %d %016llx", shift, size); + return -EINVAL; + } + } else { + return -EINVAL; + } + *refd = page - vmm->func->page; + + return 0; +} + +static int +nvkm_uvmm_mthd_raw_get(struct nvkm_uvmm *uvmm, struct nvif_vmm_raw_v0 *args) +{ + struct nvkm_vmm *vmm = uvmm->vmm; + u8 refd; + int ret; + + if (!nvkm_vmm_in_managed_range(vmm, args->addr, args->size)) + return -EINVAL; + + ret = nvkm_uvmm_page_index(uvmm, args->size, args->shift, &refd); + if (ret) + return ret; + + return nvkm_vmm_raw_get(vmm, args->addr, args->size, refd); +} + +static int +nvkm_uvmm_mthd_raw_put(struct nvkm_uvmm *uvmm, struct nvif_vmm_raw_v0 *args) +{ + struct nvkm_vmm *vmm = uvmm->vmm; + u8 refd; + int ret; + + if (!nvkm_vmm_in_managed_range(vmm, args->addr, args->size)) + return -EINVAL; + + ret = nvkm_uvmm_page_index(uvmm, args->size, args->shift, &refd); + if (ret) + return ret; + + nvkm_vmm_raw_put(vmm, args->addr, args->size, refd); + + return 0; +} + +static int +nvkm_uvmm_mthd_raw_map(struct nvkm_uvmm *uvmm, struct nvif_vmm_raw_v0 *args) +{ + struct nvkm_client *client = uvmm->object.client; + struct nvkm_vmm *vmm = uvmm->vmm; + struct nvkm_vma vma = { + .addr = args->addr, + .size = args->size, + .used = true, + .mapref = false, + .no_comp = true, + }; + struct nvkm_memory *memory; + u64 handle = args->memory; + u8 refd; + int ret; + + if (!nvkm_vmm_in_managed_range(vmm, args->addr, args->size)) + return -EINVAL; + + ret = nvkm_uvmm_page_index(uvmm, args->size, args->shift, &refd); + if (ret) + return ret; + + vma.page = vma.refd = refd; + + memory = nvkm_umem_search(client, args->memory); + if (IS_ERR(memory)) { + VMM_DEBUG(vmm, "memory %016llx %ld\n", handle, PTR_ERR(memory)); + return PTR_ERR(memory); + } + + ret = nvkm_memory_map(memory, args->offset, vmm, &vma, + (void *)args->argv, args->argc); + + nvkm_memory_unref(&vma.memory); + nvkm_memory_unref(&memory); + return ret; +} + +static int +nvkm_uvmm_mthd_raw_unmap(struct nvkm_uvmm *uvmm, struct nvif_vmm_raw_v0 *args) +{ + struct nvkm_vmm *vmm = uvmm->vmm; + u8 refd; + int ret; + + if (!nvkm_vmm_in_managed_range(vmm, args->addr, args->size)) + return -EINVAL; + + ret = nvkm_uvmm_page_index(uvmm, args->size, args->shift, &refd); + if (ret) + return ret; + + nvkm_vmm_raw_unmap(vmm, args->addr, args->size, + args->sparse, refd); + + return 0; +} + +static int +nvkm_uvmm_mthd_raw_sparse(struct nvkm_uvmm *uvmm, struct nvif_vmm_raw_v0 *args) +{ + struct nvkm_vmm *vmm = uvmm->vmm; + + if (!nvkm_vmm_in_managed_range(vmm, args->addr, args->size)) + return -EINVAL; + + return nvkm_vmm_raw_sparse(vmm, args->addr, args->size, args->ref); +} + +static int +nvkm_uvmm_mthd_raw(struct nvkm_uvmm *uvmm, void *argv, u32 argc) +{ + union { + struct nvif_vmm_raw_v0 v0; + } *args = argv; + int ret = -ENOSYS; + + if (!uvmm->vmm->managed.raw) + return -EINVAL; + + if ((ret = nvif_unpack(ret, &argv, &argc, args->v0, 0, 0, true))) + return ret; + + switch (args->v0.op) { + case NVIF_VMM_RAW_V0_GET: + return nvkm_uvmm_mthd_raw_get(uvmm, &args->v0); + case NVIF_VMM_RAW_V0_PUT: + return nvkm_uvmm_mthd_raw_put(uvmm, &args->v0); + case NVIF_VMM_RAW_V0_MAP: + return nvkm_uvmm_mthd_raw_map(uvmm, &args->v0); + case NVIF_VMM_RAW_V0_UNMAP: + return nvkm_uvmm_mthd_raw_unmap(uvmm, &args->v0); + case NVIF_VMM_RAW_V0_SPARSE: + return nvkm_uvmm_mthd_raw_sparse(uvmm, &args->v0); + default: + return -EINVAL; + }; +} + static int nvkm_uvmm_mthd(struct nvkm_object *object, u32 mthd, void *argv, u32 argc) { @@ -326,6 +499,7 @@ nvkm_uvmm_mthd(struct nvkm_object *object, u32 mthd, void *argv, u32 argc) case NVIF_VMM_V0_UNMAP : return nvkm_uvmm_mthd_unmap (uvmm, argv, argc); case NVIF_VMM_V0_PFNMAP: return nvkm_uvmm_mthd_pfnmap(uvmm, argv, argc); case NVIF_VMM_V0_PFNCLR: return nvkm_uvmm_mthd_pfnclr(uvmm, argv, argc); + case NVIF_VMM_V0_RAW : return nvkm_uvmm_mthd_raw (uvmm, argv, argc); case NVIF_VMM_V0_MTHD(0x00) ... NVIF_VMM_V0_MTHD(0x7f): if (uvmm->vmm->func->mthd) { return uvmm->vmm->func->mthd(uvmm->vmm, @@ -366,10 +540,11 @@ nvkm_uvmm_new(const struct nvkm_oclass *oclass, void *argv, u32 argc, struct nvkm_uvmm *uvmm; int ret = -ENOSYS; u64 addr, size; - bool managed; + bool managed, raw; if (!(ret = nvif_unpack(ret, &argv, &argc, args->v0, 0, 0, more))) { - managed = args->v0.managed != 0; + managed = args->v0.type == NVIF_VMM_V0_TYPE_MANAGED; + raw = args->v0.type == NVIF_VMM_V0_TYPE_RAW; addr = args->v0.addr; size = args->v0.size; } else @@ -377,12 +552,13 @@ nvkm_uvmm_new(const struct nvkm_oclass *oclass, void *argv, u32 argc, if (!(uvmm = kzalloc(sizeof(*uvmm), GFP_KERNEL))) return -ENOMEM; + nvkm_object_ctor(&nvkm_uvmm, oclass, &uvmm->object); *pobject = &uvmm->object; if (!mmu->vmm) { - ret = mmu->func->vmm.ctor(mmu, managed, addr, size, argv, argc, - NULL, "user", &uvmm->vmm); + ret = mmu->func->vmm.ctor(mmu, managed || raw, addr, size, + argv, argc, NULL, "user", &uvmm->vmm); if (ret) return ret; @@ -393,6 +569,7 @@ nvkm_uvmm_new(const struct nvkm_oclass *oclass, void *argv, u32 argc, uvmm->vmm = nvkm_vmm_ref(mmu->vmm); } + uvmm->vmm->managed.raw = raw; page = uvmm->vmm->func->page; args->v0.page_nr = 0; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c index ae793f400ba1..eb5fcadcb39a 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c @@ -676,41 +676,18 @@ nvkm_vmm_ptes_sparse(struct nvkm_vmm *vmm, u64 addr, u64 size, bool ref) return 0; } -static void -nvkm_vmm_ptes_unmap_put(struct nvkm_vmm *vmm, const struct nvkm_vmm_page *page, - u64 addr, u64 size, bool sparse, bool pfn) -{ - const struct nvkm_vmm_desc_func *func = page->desc->func; - nvkm_vmm_iter(vmm, page, addr, size, "unmap + unref", - false, pfn, nvkm_vmm_unref_ptes, NULL, NULL, - sparse ? func->sparse : func->invalid ? func->invalid : - func->unmap); -} - -static int -nvkm_vmm_ptes_get_map(struct nvkm_vmm *vmm, const struct nvkm_vmm_page *page, - u64 addr, u64 size, struct nvkm_vmm_map *map, - nvkm_vmm_pte_func func) -{ - u64 fail = nvkm_vmm_iter(vmm, page, addr, size, "ref + map", true, - false, nvkm_vmm_ref_ptes, func, map, NULL); - if (fail != ~0ULL) { - if ((size = fail - addr)) - nvkm_vmm_ptes_unmap_put(vmm, page, addr, size, false, false); - return -ENOMEM; - } - return 0; -} - static void nvkm_vmm_ptes_unmap(struct nvkm_vmm *vmm, const struct nvkm_vmm_page *page, u64 addr, u64 size, bool sparse, bool pfn) { const struct nvkm_vmm_desc_func *func = page->desc->func; + + mutex_lock(&vmm->mutex.map); nvkm_vmm_iter(vmm, page, addr, size, "unmap", false, pfn, NULL, NULL, NULL, sparse ? func->sparse : func->invalid ? func->invalid : func->unmap); + mutex_unlock(&vmm->mutex.map); } static void @@ -718,33 +695,108 @@ nvkm_vmm_ptes_map(struct nvkm_vmm *vmm, const struct nvkm_vmm_page *page, u64 addr, u64 size, struct nvkm_vmm_map *map, nvkm_vmm_pte_func func) { + mutex_lock(&vmm->mutex.map); nvkm_vmm_iter(vmm, page, addr, size, "map", false, false, NULL, func, map, NULL); + mutex_unlock(&vmm->mutex.map); } static void -nvkm_vmm_ptes_put(struct nvkm_vmm *vmm, const struct nvkm_vmm_page *page, - u64 addr, u64 size) +nvkm_vmm_ptes_put_locked(struct nvkm_vmm *vmm, const struct nvkm_vmm_page *page, + u64 addr, u64 size) { nvkm_vmm_iter(vmm, page, addr, size, "unref", false, false, nvkm_vmm_unref_ptes, NULL, NULL, NULL); } +static void +nvkm_vmm_ptes_put(struct nvkm_vmm *vmm, const struct nvkm_vmm_page *page, + u64 addr, u64 size) +{ + mutex_lock(&vmm->mutex.ref); + nvkm_vmm_ptes_put_locked(vmm, page, addr, size); + mutex_unlock(&vmm->mutex.ref); +} + static int nvkm_vmm_ptes_get(struct nvkm_vmm *vmm, const struct nvkm_vmm_page *page, u64 addr, u64 size) { - u64 fail = nvkm_vmm_iter(vmm, page, addr, size, "ref", true, false, - nvkm_vmm_ref_ptes, NULL, NULL, NULL); + u64 fail; + + mutex_lock(&vmm->mutex.ref); + fail = nvkm_vmm_iter(vmm, page, addr, size, "ref", true, false, + nvkm_vmm_ref_ptes, NULL, NULL, NULL); if (fail != ~0ULL) { if (fail != addr) - nvkm_vmm_ptes_put(vmm, page, addr, fail - addr); + nvkm_vmm_ptes_put_locked(vmm, page, addr, fail - addr); + mutex_unlock(&vmm->mutex.ref); + return -ENOMEM; + } + mutex_unlock(&vmm->mutex.ref); + return 0; +} + +static void +__nvkm_vmm_ptes_unmap_put(struct nvkm_vmm *vmm, const struct nvkm_vmm_page *page, + u64 addr, u64 size, bool sparse, bool pfn) +{ + const struct nvkm_vmm_desc_func *func = page->desc->func; + + nvkm_vmm_iter(vmm, page, addr, size, "unmap + unref", + false, pfn, nvkm_vmm_unref_ptes, NULL, NULL, + sparse ? func->sparse : func->invalid ? func->invalid : + func->unmap); +} + +static void +nvkm_vmm_ptes_unmap_put(struct nvkm_vmm *vmm, const struct nvkm_vmm_page *page, + u64 addr, u64 size, bool sparse, bool pfn) +{ + if (vmm->managed.raw) { + nvkm_vmm_ptes_unmap(vmm, page, addr, size, sparse, pfn); + nvkm_vmm_ptes_put(vmm, page, addr, size); + } else { + __nvkm_vmm_ptes_unmap_put(vmm, page, addr, size, sparse, pfn); + } +} + +static int +__nvkm_vmm_ptes_get_map(struct nvkm_vmm *vmm, const struct nvkm_vmm_page *page, + u64 addr, u64 size, struct nvkm_vmm_map *map, + nvkm_vmm_pte_func func) +{ + u64 fail = nvkm_vmm_iter(vmm, page, addr, size, "ref + map", true, + false, nvkm_vmm_ref_ptes, func, map, NULL); + if (fail != ~0ULL) { + if ((size = fail - addr)) + nvkm_vmm_ptes_unmap_put(vmm, page, addr, size, false, false); return -ENOMEM; } return 0; } -static inline struct nvkm_vma * +static int +nvkm_vmm_ptes_get_map(struct nvkm_vmm *vmm, const struct nvkm_vmm_page *page, + u64 addr, u64 size, struct nvkm_vmm_map *map, + nvkm_vmm_pte_func func) +{ + int ret; + + if (vmm->managed.raw) { + ret = nvkm_vmm_ptes_get(vmm, page, addr, size); + if (ret) + return ret; + + nvkm_vmm_ptes_map(vmm, page, addr, size, map, func); + + return 0; + } else { + return __nvkm_vmm_ptes_get_map(vmm, page, addr, size, map, func); + } +} + +struct nvkm_vma * nvkm_vma_new(u64 addr, u64 size) { struct nvkm_vma *vma = kzalloc(sizeof(*vma), GFP_KERNEL); @@ -1045,7 +1097,9 @@ nvkm_vmm_ctor(const struct nvkm_vmm_func *func, struct nvkm_mmu *mmu, vmm->debug = mmu->subdev.debug; kref_init(&vmm->kref); - __mutex_init(&vmm->mutex, "&vmm->mutex", key ? key : &_key); + __mutex_init(&vmm->mutex.vmm, "&vmm->mutex.vmm", key ? key : &_key); + mutex_init(&vmm->mutex.ref); + mutex_init(&vmm->mutex.map); /* Locate the smallest page size supported by the backend, it will * have the deepest nesting of page tables. @@ -1101,6 +1155,9 @@ nvkm_vmm_ctor(const struct nvkm_vmm_func *func, struct nvkm_mmu *mmu, if (addr && (ret = nvkm_vmm_ctor_managed(vmm, 0, addr))) return ret; + vmm->managed.p.addr = 0; + vmm->managed.p.size = addr; + /* NVKM-managed area. */ if (size) { if (!(vma = nvkm_vma_new(addr, size))) @@ -1114,6 +1171,9 @@ nvkm_vmm_ctor(const struct nvkm_vmm_func *func, struct nvkm_mmu *mmu, size = vmm->limit - addr; if (size && (ret = nvkm_vmm_ctor_managed(vmm, addr, size))) return ret; + + vmm->managed.n.addr = addr; + vmm->managed.n.size = size; } else { /* Address-space fully managed by NVKM, requiring calls to * nvkm_vmm_get()/nvkm_vmm_put() to allocate address-space. @@ -1362,9 +1422,9 @@ void nvkm_vmm_unmap(struct nvkm_vmm *vmm, struct nvkm_vma *vma) { if (vma->memory) { - mutex_lock(&vmm->mutex); + mutex_lock(&vmm->mutex.vmm); nvkm_vmm_unmap_locked(vmm, vma, false); - mutex_unlock(&vmm->mutex); + mutex_unlock(&vmm->mutex.vmm); } } @@ -1423,6 +1483,8 @@ nvkm_vmm_map_locked(struct nvkm_vmm *vmm, struct nvkm_vma *vma, nvkm_vmm_pte_func func; int ret; + map->no_comp = vma->no_comp; + /* Make sure we won't overrun the end of the memory object. */ if (unlikely(nvkm_memory_size(map->memory) < map->offset + vma->size)) { VMM_DEBUG(vmm, "overrun %016llx %016llx %016llx", @@ -1507,10 +1569,15 @@ nvkm_vmm_map(struct nvkm_vmm *vmm, struct nvkm_vma *vma, void *argv, u32 argc, struct nvkm_vmm_map *map) { int ret; - mutex_lock(&vmm->mutex); + + if (nvkm_vmm_in_managed_range(vmm, vma->addr, vma->size) && + vmm->managed.raw) + return nvkm_vmm_map_locked(vmm, vma, argv, argc, map); + + mutex_lock(&vmm->mutex.vmm); ret = nvkm_vmm_map_locked(vmm, vma, argv, argc, map); vma->busy = false; - mutex_unlock(&vmm->mutex); + mutex_unlock(&vmm->mutex.vmm); return ret; } @@ -1620,9 +1687,9 @@ nvkm_vmm_put(struct nvkm_vmm *vmm, struct nvkm_vma **pvma) { struct nvkm_vma *vma = *pvma; if (vma) { - mutex_lock(&vmm->mutex); + mutex_lock(&vmm->mutex.vmm); nvkm_vmm_put_locked(vmm, vma); - mutex_unlock(&vmm->mutex); + mutex_unlock(&vmm->mutex.vmm); *pvma = NULL; } } @@ -1769,9 +1836,49 @@ int nvkm_vmm_get(struct nvkm_vmm *vmm, u8 page, u64 size, struct nvkm_vma **pvma) { int ret; - mutex_lock(&vmm->mutex); + mutex_lock(&vmm->mutex.vmm); ret = nvkm_vmm_get_locked(vmm, false, true, false, page, 0, size, pvma); - mutex_unlock(&vmm->mutex); + mutex_unlock(&vmm->mutex.vmm); + return ret; +} + +void +nvkm_vmm_raw_unmap(struct nvkm_vmm *vmm, u64 addr, u64 size, + bool sparse, u8 refd) +{ + const struct nvkm_vmm_page *page = &vmm->func->page[refd]; + + nvkm_vmm_ptes_unmap(vmm, page, addr, size, sparse, false); +} + +void +nvkm_vmm_raw_put(struct nvkm_vmm *vmm, u64 addr, u64 size, u8 refd) +{ + const struct nvkm_vmm_page *page = vmm->func->page; + + nvkm_vmm_ptes_put(vmm, &page[refd], addr, size); +} + +int +nvkm_vmm_raw_get(struct nvkm_vmm *vmm, u64 addr, u64 size, u8 refd) +{ + const struct nvkm_vmm_page *page = vmm->func->page; + + if (unlikely(!size)) + return -EINVAL; + + return nvkm_vmm_ptes_get(vmm, &page[refd], addr, size); +} + +int +nvkm_vmm_raw_sparse(struct nvkm_vmm *vmm, u64 addr, u64 size, bool ref) +{ + int ret; + + mutex_lock(&vmm->mutex.ref); + ret = nvkm_vmm_ptes_sparse(vmm, addr, size, ref); + mutex_unlock(&vmm->mutex.ref); + return ret; } @@ -1779,9 +1886,9 @@ void nvkm_vmm_part(struct nvkm_vmm *vmm, struct nvkm_memory *inst) { if (inst && vmm && vmm->func->part) { - mutex_lock(&vmm->mutex); + mutex_lock(&vmm->mutex.vmm); vmm->func->part(vmm, inst); - mutex_unlock(&vmm->mutex); + mutex_unlock(&vmm->mutex.vmm); } } @@ -1790,9 +1897,9 @@ nvkm_vmm_join(struct nvkm_vmm *vmm, struct nvkm_memory *inst) { int ret = 0; if (vmm->func->join) { - mutex_lock(&vmm->mutex); + mutex_lock(&vmm->mutex.vmm); ret = vmm->func->join(vmm, inst); - mutex_unlock(&vmm->mutex); + mutex_unlock(&vmm->mutex.vmm); } return ret; } diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h index f6188aa9171c..f9bc30cdb2b3 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h @@ -163,6 +163,7 @@ int nvkm_vmm_new_(const struct nvkm_vmm_func *, struct nvkm_mmu *, u32 pd_header, bool managed, u64 addr, u64 size, struct lock_class_key *, const char *name, struct nvkm_vmm **); +struct nvkm_vma *nvkm_vma_new(u64 addr, u64 size); struct nvkm_vma *nvkm_vmm_node_search(struct nvkm_vmm *, u64 addr); struct nvkm_vma *nvkm_vmm_node_split(struct nvkm_vmm *, struct nvkm_vma *, u64 addr, u64 size); @@ -173,6 +174,30 @@ void nvkm_vmm_put_locked(struct nvkm_vmm *, struct nvkm_vma *); void nvkm_vmm_unmap_locked(struct nvkm_vmm *, struct nvkm_vma *, bool pfn); void nvkm_vmm_unmap_region(struct nvkm_vmm *, struct nvkm_vma *); +int nvkm_vmm_raw_get(struct nvkm_vmm *vmm, u64 addr, u64 size, u8 refd); +void nvkm_vmm_raw_put(struct nvkm_vmm *vmm, u64 addr, u64 size, u8 refd); +void nvkm_vmm_raw_unmap(struct nvkm_vmm *vmm, u64 addr, u64 size, + bool sparse, u8 refd); +int nvkm_vmm_raw_sparse(struct nvkm_vmm *, u64 addr, u64 size, bool ref); + +static inline bool +nvkm_vmm_in_managed_range(struct nvkm_vmm *vmm, u64 start, u64 size) +{ + u64 p_start = vmm->managed.p.addr; + u64 p_end = p_start + vmm->managed.p.size; + u64 n_start = vmm->managed.n.addr; + u64 n_end = n_start + vmm->managed.n.size; + u64 end = start + size; + + if (start >= p_start && end <= p_end) + return true; + + if (start >= n_start && end <= n_end) + return true; + + return false; +} + #define NVKM_VMM_PFN_ADDR 0xfffffffffffff000ULL #define NVKM_VMM_PFN_ADDR_SHIFT 12 #define NVKM_VMM_PFN_APER 0x00000000000000f0ULL diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgf100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgf100.c index 5438384d9a67..5e857c02e9aa 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgf100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgf100.c @@ -287,15 +287,17 @@ gf100_vmm_valid(struct nvkm_vmm *vmm, void *argv, u32 argc, return -EINVAL; } - ret = nvkm_memory_tags_get(memory, device, tags, - nvkm_ltc_tags_clear, - &map->tags); - if (ret) { - VMM_DEBUG(vmm, "comp %d", ret); - return ret; + if (!map->no_comp) { + ret = nvkm_memory_tags_get(memory, device, tags, + nvkm_ltc_tags_clear, + &map->tags); + if (ret) { + VMM_DEBUG(vmm, "comp %d", ret); + return ret; + } } - if (map->tags->mn) { + if (!map->no_comp && map->tags->mn) { u64 tags = map->tags->mn->offset + (map->offset >> 17); if (page->shift == 17 || !gm20x) { map->type |= tags << 44; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c index 17899fc95b2d..f3630d0e0d55 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c @@ -453,15 +453,17 @@ gp100_vmm_valid(struct nvkm_vmm *vmm, void *argv, u32 argc, return -EINVAL; } - ret = nvkm_memory_tags_get(memory, device, tags, - nvkm_ltc_tags_clear, - &map->tags); - if (ret) { - VMM_DEBUG(vmm, "comp %d", ret); - return ret; + if (!map->no_comp) { + ret = nvkm_memory_tags_get(memory, device, tags, + nvkm_ltc_tags_clear, + &map->tags); + if (ret) { + VMM_DEBUG(vmm, "comp %d", ret); + return ret; + } } - if (map->tags->mn) { + if (!map->no_comp && map->tags->mn) { tags = map->tags->mn->offset + (map->offset >> 16); map->ctag |= ((1ULL << page->shift) >> 16) << 36; map->type |= tags << 36; diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmnv50.c b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmnv50.c index b7548dcd72c7..ff08ad5005a9 100644 --- a/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmnv50.c +++ b/drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmnv50.c @@ -296,19 +296,22 @@ nv50_vmm_valid(struct nvkm_vmm *vmm, void *argv, u32 argc, return -EINVAL; } - ret = nvkm_memory_tags_get(memory, device, tags, NULL, - &map->tags); - if (ret) { - VMM_DEBUG(vmm, "comp %d", ret); - return ret; - } + if (!map->no_comp) { + ret = nvkm_memory_tags_get(memory, device, tags, NULL, + &map->tags); + if (ret) { + VMM_DEBUG(vmm, "comp %d", ret); + return ret; + } - if (map->tags->mn) { - u32 tags = map->tags->mn->offset + (map->offset >> 16); - map->ctag |= (u64)comp << 49; - map->type |= (u64)comp << 47; - map->type |= (u64)tags << 49; - map->next |= map->ctag; + if (map->tags->mn) { + u32 tags = map->tags->mn->offset + + (map->offset >> 16); + map->ctag |= (u64)comp << 49; + map->type |= (u64)comp << 47; + map->type |= (u64)tags << 49; + map->next |= map->ctag; + } } } -- 2.41.0
Danilo Krummrich
2023-Aug-03 16:52 UTC
[Nouveau] [PATCH drm-misc-next v9 10/11] drm/nouveau: implement new VM_BIND uAPI
This commit provides the implementation for the new uapi motivated by the Vulkan API. It allows user mode drivers (UMDs) to: 1) Initialize a GPU virtual address (VA) space via the new DRM_IOCTL_NOUVEAU_VM_INIT ioctl for UMDs to specify the portion of VA space managed by the kernel and userspace, respectively. 2) Allocate and free a VA space region as well as bind and unbind memory to the GPUs VA space via the new DRM_IOCTL_NOUVEAU_VM_BIND ioctl. UMDs can request the named operations to be processed either synchronously or asynchronously. It supports DRM syncobjs (incl. timelines) as synchronization mechanism. The management of the GPU VA mappings is implemented with the DRM GPU VA manager. 3) Execute push buffers with the new DRM_IOCTL_NOUVEAU_EXEC ioctl. The execution happens asynchronously. It supports DRM syncobj (incl. timelines) as synchronization mechanism. DRM GEM object locking is handled with drm_exec. Both, DRM_IOCTL_NOUVEAU_VM_BIND and DRM_IOCTL_NOUVEAU_EXEC, use the DRM GPU scheduler for the asynchronous paths. Signed-off-by: Danilo Krummrich <dakr at redhat.com> --- Documentation/gpu/driver-uapi.rst | 3 + drivers/gpu/drm/nouveau/Kbuild | 3 + drivers/gpu/drm/nouveau/Kconfig | 2 + drivers/gpu/drm/nouveau/nouveau_abi16.c | 24 + drivers/gpu/drm/nouveau/nouveau_abi16.h | 1 + drivers/gpu/drm/nouveau/nouveau_bo.c | 168 +- drivers/gpu/drm/nouveau/nouveau_bo.h | 3 +- drivers/gpu/drm/nouveau/nouveau_drm.c | 27 +- drivers/gpu/drm/nouveau/nouveau_drv.h | 58 +- drivers/gpu/drm/nouveau/nouveau_exec.c | 436 +++++ drivers/gpu/drm/nouveau/nouveau_exec.h | 54 + drivers/gpu/drm/nouveau/nouveau_gem.c | 49 +- drivers/gpu/drm/nouveau/nouveau_gem.h | 3 +- drivers/gpu/drm/nouveau/nouveau_mem.h | 5 + drivers/gpu/drm/nouveau/nouveau_prime.c | 13 +- drivers/gpu/drm/nouveau/nouveau_sched.c | 444 ++++++ drivers/gpu/drm/nouveau/nouveau_sched.h | 127 ++ drivers/gpu/drm/nouveau/nouveau_uvmm.c | 1946 +++++++++++++++++++++++ drivers/gpu/drm/nouveau/nouveau_uvmm.h | 108 ++ 19 files changed, 3403 insertions(+), 71 deletions(-) create mode 100644 drivers/gpu/drm/nouveau/nouveau_exec.c create mode 100644 drivers/gpu/drm/nouveau/nouveau_exec.h create mode 100644 drivers/gpu/drm/nouveau/nouveau_sched.c create mode 100644 drivers/gpu/drm/nouveau/nouveau_sched.h create mode 100644 drivers/gpu/drm/nouveau/nouveau_uvmm.c create mode 100644 drivers/gpu/drm/nouveau/nouveau_uvmm.h diff --git a/Documentation/gpu/driver-uapi.rst b/Documentation/gpu/driver-uapi.rst index 9c7ca6e33a68..c08bcbb95fb3 100644 --- a/Documentation/gpu/driver-uapi.rst +++ b/Documentation/gpu/driver-uapi.rst @@ -13,4 +13,7 @@ drm/nouveau uAPI VM_BIND / EXEC uAPI ------------------- +.. kernel-doc:: drivers/gpu/drm/nouveau/nouveau_exec.c + :doc: Overview + .. kernel-doc:: include/uapi/drm/nouveau_drm.h diff --git a/drivers/gpu/drm/nouveau/Kbuild b/drivers/gpu/drm/nouveau/Kbuild index 5e5617006da5..cf6b3a80c0c8 100644 --- a/drivers/gpu/drm/nouveau/Kbuild +++ b/drivers/gpu/drm/nouveau/Kbuild @@ -47,6 +47,9 @@ nouveau-y += nouveau_prime.o nouveau-y += nouveau_sgdma.o nouveau-y += nouveau_ttm.o nouveau-y += nouveau_vmm.o +nouveau-y += nouveau_exec.o +nouveau-y += nouveau_sched.o +nouveau-y += nouveau_uvmm.o # DRM - modesetting nouveau-$(CONFIG_DRM_NOUVEAU_BACKLIGHT) += nouveau_backlight.o diff --git a/drivers/gpu/drm/nouveau/Kconfig b/drivers/gpu/drm/nouveau/Kconfig index a70bd65e1400..c52e8096cca4 100644 --- a/drivers/gpu/drm/nouveau/Kconfig +++ b/drivers/gpu/drm/nouveau/Kconfig @@ -10,6 +10,8 @@ config DRM_NOUVEAU select DRM_KMS_HELPER select DRM_TTM select DRM_TTM_HELPER + select DRM_EXEC + select DRM_SCHED select I2C select I2C_ALGOBIT select BACKLIGHT_CLASS_DEVICE if DRM_NOUVEAU_BACKLIGHT diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.c b/drivers/gpu/drm/nouveau/nouveau_abi16.c index 82dab51d8aeb..30afbec9e3b1 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.c +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.c @@ -35,6 +35,7 @@ #include "nouveau_chan.h" #include "nouveau_abi16.h" #include "nouveau_vmm.h" +#include "nouveau_sched.h" static struct nouveau_abi16 * nouveau_abi16(struct drm_file *file_priv) @@ -125,6 +126,17 @@ nouveau_abi16_chan_fini(struct nouveau_abi16 *abi16, { struct nouveau_abi16_ntfy *ntfy, *temp; + /* When a client exits without waiting for it's queued up jobs to + * finish it might happen that we fault the channel. This is due to + * drm_file_free() calling drm_gem_release() before the postclose() + * callback. Hence, we can't tear down this scheduler entity before + * uvmm mappings are unmapped. Currently, we can't detect this case. + * + * However, this should be rare and harmless, since the channel isn't + * needed anymore. + */ + nouveau_sched_entity_fini(&chan->sched_entity); + /* wait for all activity to stop before cleaning up */ if (chan->chan) nouveau_channel_idle(chan->chan); @@ -261,6 +273,13 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS) if (!drm->channel) return nouveau_abi16_put(abi16, -ENODEV); + /* If uvmm wasn't initialized until now disable it completely to prevent + * userspace from mixing up UAPIs. + * + * The client lock is already acquired by nouveau_abi16_get(). + */ + __nouveau_cli_disable_uvmm_noinit(cli); + device = &abi16->device; engine = NV_DEVICE_HOST_RUNLIST_ENGINES_GR; @@ -304,6 +323,11 @@ nouveau_abi16_ioctl_channel_alloc(ABI16_IOCTL_ARGS) if (ret) goto done; + ret = nouveau_sched_entity_init(&chan->sched_entity, &drm->sched, + drm->sched_wq); + if (ret) + goto done; + init->channel = chan->chan->chid; if (device->info.family >= NV_DEVICE_INFO_V0_TESLA) diff --git a/drivers/gpu/drm/nouveau/nouveau_abi16.h b/drivers/gpu/drm/nouveau/nouveau_abi16.h index 27eae85f33e6..8209eb28feaf 100644 --- a/drivers/gpu/drm/nouveau/nouveau_abi16.h +++ b/drivers/gpu/drm/nouveau/nouveau_abi16.h @@ -26,6 +26,7 @@ struct nouveau_abi16_chan { struct nouveau_bo *ntfy; struct nouveau_vma *ntfy_vma; struct nvkm_mm heap; + struct nouveau_sched_entity sched_entity; }; struct nouveau_abi16 { diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.c b/drivers/gpu/drm/nouveau/nouveau_bo.c index e9cbbf594e6f..949195d5d782 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.c +++ b/drivers/gpu/drm/nouveau/nouveau_bo.c @@ -199,7 +199,7 @@ nouveau_bo_fixup_align(struct nouveau_bo *nvbo, int *align, u64 *size) struct nouveau_bo * nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain, - u32 tile_mode, u32 tile_flags) + u32 tile_mode, u32 tile_flags, bool internal) { struct nouveau_drm *drm = cli->drm; struct nouveau_bo *nvbo; @@ -221,8 +221,6 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain, INIT_LIST_HEAD(&nvbo->vma_list); nvbo->bo.bdev = &drm->ttm.bdev; - drm_gem_gpuva_init(&nvbo->bo.base); - /* This is confusing, and doesn't actually mean we want an uncached * mapping, but is what NOUVEAU_GEM_DOMAIN_COHERENT gets translated * into in nouveau_gem_new(). @@ -235,68 +233,103 @@ nouveau_bo_alloc(struct nouveau_cli *cli, u64 *size, int *align, u32 domain, nvbo->force_coherent = true; } - if (cli->device.info.family >= NV_DEVICE_INFO_V0_FERMI) { - nvbo->kind = (tile_flags & 0x0000ff00) >> 8; - if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) { - kfree(nvbo); - return ERR_PTR(-EINVAL); + nvbo->contig = !(tile_flags & NOUVEAU_GEM_TILE_NONCONTIG); + if (!nouveau_cli_uvmm(cli) || internal) { + /* for BO noVM allocs, don't assign kinds */ + if (cli->device.info.family >= NV_DEVICE_INFO_V0_FERMI) { + nvbo->kind = (tile_flags & 0x0000ff00) >> 8; + if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) { + kfree(nvbo); + return ERR_PTR(-EINVAL); + } + + nvbo->comp = mmu->kind[nvbo->kind] != nvbo->kind; + } else if (cli->device.info.family >= NV_DEVICE_INFO_V0_TESLA) { + nvbo->kind = (tile_flags & 0x00007f00) >> 8; + nvbo->comp = (tile_flags & 0x00030000) >> 16; + if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) { + kfree(nvbo); + return ERR_PTR(-EINVAL); + } + } else { + nvbo->zeta = (tile_flags & 0x00000007); } + nvbo->mode = tile_mode; + + /* Determine the desirable target GPU page size for the buffer. */ + for (i = 0; i < vmm->page_nr; i++) { + /* Because we cannot currently allow VMM maps to fail + * during buffer migration, we need to determine page + * size for the buffer up-front, and pre-allocate its + * page tables. + * + * Skip page sizes that can't support needed domains. + */ + if (cli->device.info.family > NV_DEVICE_INFO_V0_CURIE && + (domain & NOUVEAU_GEM_DOMAIN_VRAM) && !vmm->page[i].vram) + continue; + if ((domain & NOUVEAU_GEM_DOMAIN_GART) && + (!vmm->page[i].host || vmm->page[i].shift > PAGE_SHIFT)) + continue; - nvbo->comp = mmu->kind[nvbo->kind] != nvbo->kind; - } else - if (cli->device.info.family >= NV_DEVICE_INFO_V0_TESLA) { - nvbo->kind = (tile_flags & 0x00007f00) >> 8; - nvbo->comp = (tile_flags & 0x00030000) >> 16; - if (!nvif_mmu_kind_valid(mmu, nvbo->kind)) { + /* Select this page size if it's the first that supports + * the potential memory domains, or when it's compatible + * with the requested compression settings. + */ + if (pi < 0 || !nvbo->comp || vmm->page[i].comp) + pi = i; + + /* Stop once the buffer is larger than the current page size. */ + if (*size >= 1ULL << vmm->page[i].shift) + break; + } + + if (WARN_ON(pi < 0)) { kfree(nvbo); return ERR_PTR(-EINVAL); } - } else { - nvbo->zeta = (tile_flags & 0x00000007); - } - nvbo->mode = tile_mode; - nvbo->contig = !(tile_flags & NOUVEAU_GEM_TILE_NONCONTIG); - - /* Determine the desirable target GPU page size for the buffer. */ - for (i = 0; i < vmm->page_nr; i++) { - /* Because we cannot currently allow VMM maps to fail - * during buffer migration, we need to determine page - * size for the buffer up-front, and pre-allocate its - * page tables. - * - * Skip page sizes that can't support needed domains. - */ - if (cli->device.info.family > NV_DEVICE_INFO_V0_CURIE && - (domain & NOUVEAU_GEM_DOMAIN_VRAM) && !vmm->page[i].vram) - continue; - if ((domain & NOUVEAU_GEM_DOMAIN_GART) && - (!vmm->page[i].host || vmm->page[i].shift > PAGE_SHIFT)) - continue; - /* Select this page size if it's the first that supports - * the potential memory domains, or when it's compatible - * with the requested compression settings. - */ - if (pi < 0 || !nvbo->comp || vmm->page[i].comp) - pi = i; - - /* Stop once the buffer is larger than the current page size. */ - if (*size >= 1ULL << vmm->page[i].shift) - break; - } + /* Disable compression if suitable settings couldn't be found. */ + if (nvbo->comp && !vmm->page[pi].comp) { + if (mmu->object.oclass >= NVIF_CLASS_MMU_GF100) + nvbo->kind = mmu->kind[nvbo->kind]; + nvbo->comp = 0; + } + nvbo->page = vmm->page[pi].shift; + } else { + /* reject other tile flags when in VM mode. */ + if (tile_mode) + return ERR_PTR(-EINVAL); + if (tile_flags & ~NOUVEAU_GEM_TILE_NONCONTIG) + return ERR_PTR(-EINVAL); - if (WARN_ON(pi < 0)) { - kfree(nvbo); - return ERR_PTR(-EINVAL); - } + /* Determine the desirable target GPU page size for the buffer. */ + for (i = 0; i < vmm->page_nr; i++) { + /* Because we cannot currently allow VMM maps to fail + * during buffer migration, we need to determine page + * size for the buffer up-front, and pre-allocate its + * page tables. + * + * Skip page sizes that can't support needed domains. + */ + if ((domain & NOUVEAU_GEM_DOMAIN_VRAM) && !vmm->page[i].vram) + continue; + if ((domain & NOUVEAU_GEM_DOMAIN_GART) && + (!vmm->page[i].host || vmm->page[i].shift > PAGE_SHIFT)) + continue; - /* Disable compression if suitable settings couldn't be found. */ - if (nvbo->comp && !vmm->page[pi].comp) { - if (mmu->object.oclass >= NVIF_CLASS_MMU_GF100) - nvbo->kind = mmu->kind[nvbo->kind]; - nvbo->comp = 0; + if (pi < 0) + pi = i; + /* Stop once the buffer is larger than the current page size. */ + if (*size >= 1ULL << vmm->page[i].shift) + break; + } + if (WARN_ON(pi < 0)) { + kfree(nvbo); + return ERR_PTR(-EINVAL); + } + nvbo->page = vmm->page[pi].shift; } - nvbo->page = vmm->page[pi].shift; nouveau_bo_fixup_align(nvbo, align, size); @@ -309,18 +342,33 @@ nouveau_bo_init(struct nouveau_bo *nvbo, u64 size, int align, u32 domain, { int type = sg ? ttm_bo_type_sg : ttm_bo_type_device; int ret; + struct ttm_operation_ctx ctx = { + .interruptible = false, + .no_wait_gpu = false, + .resv = robj, + }; nouveau_bo_placement_set(nvbo, domain, 0); INIT_LIST_HEAD(&nvbo->io_reserve_lru); - ret = ttm_bo_init_validate(nvbo->bo.bdev, &nvbo->bo, type, - &nvbo->placement, align >> PAGE_SHIFT, false, + /* At this point we're guaranteed the dma-resv of the drm_gem_object is + * initialized. We also can't do it after ttm_bo_init_validate(), + * because during validation we might receive a bo_move() callback where + * we already need to iterate the GEMs GPUVA list. + */ + drm_gem_gpuva_init(&nvbo->bo.base); + + ret = ttm_bo_init_reserved(nvbo->bo.bdev, &nvbo->bo, type, + &nvbo->placement, align >> PAGE_SHIFT, &ctx, sg, robj, nouveau_bo_del_ttm); if (ret) { /* ttm will call nouveau_bo_del_ttm if it fails.. */ return ret; } + if (!robj) + ttm_bo_unreserve(&nvbo->bo); + return 0; } @@ -334,7 +382,7 @@ nouveau_bo_new(struct nouveau_cli *cli, u64 size, int align, int ret; nvbo = nouveau_bo_alloc(cli, &size, &align, domain, tile_mode, - tile_flags); + tile_flags, true); if (IS_ERR(nvbo)) return PTR_ERR(nvbo); @@ -948,6 +996,7 @@ static void nouveau_bo_move_ntfy(struct ttm_buffer_object *bo, list_for_each_entry(vma, &nvbo->vma_list, head) { nouveau_vma_map(vma, mem); } + nouveau_uvmm_bo_map_all(nvbo, mem); } else { list_for_each_entry(vma, &nvbo->vma_list, head) { ret = dma_resv_wait_timeout(bo->base.resv, @@ -956,6 +1005,7 @@ static void nouveau_bo_move_ntfy(struct ttm_buffer_object *bo, WARN_ON(ret <= 0); nouveau_vma_unmap(vma); } + nouveau_uvmm_bo_unmap_all(nvbo); } if (new_reg) diff --git a/drivers/gpu/drm/nouveau/nouveau_bo.h b/drivers/gpu/drm/nouveau/nouveau_bo.h index 774dd93ca76b..07f671cf895e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_bo.h +++ b/drivers/gpu/drm/nouveau/nouveau_bo.h @@ -26,6 +26,7 @@ struct nouveau_bo { struct list_head entry; int pbbo_index; bool validate_mapped; + bool no_share; /* GPU address space is independent of CPU word size */ uint64_t offset; @@ -73,7 +74,7 @@ extern struct ttm_device_funcs nouveau_bo_driver; void nouveau_bo_move_init(struct nouveau_drm *); struct nouveau_bo *nouveau_bo_alloc(struct nouveau_cli *, u64 *size, int *align, - u32 domain, u32 tile_mode, u32 tile_flags); + u32 domain, u32 tile_mode, u32 tile_flags, bool internal); int nouveau_bo_init(struct nouveau_bo *, u64 size, int align, u32 domain, struct sg_table *sg, struct dma_resv *robj); int nouveau_bo_new(struct nouveau_cli *, u64 size, int align, u32 domain, diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index 8325fcf35c5e..4396f501b16a 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -68,6 +68,9 @@ #include "nouveau_platform.h" #include "nouveau_svm.h" #include "nouveau_dmem.h" +#include "nouveau_exec.h" +#include "nouveau_uvmm.h" +#include "nouveau_sched.h" DECLARE_DYNDBG_CLASSMAP(drm_debug_classes, DD_CLASS_TYPE_DISJOINT_BITS, 0, "DRM_UT_CORE", @@ -196,6 +199,8 @@ nouveau_cli_fini(struct nouveau_cli *cli) WARN_ON(!list_empty(&cli->worker)); usif_client_fini(cli); + nouveau_uvmm_fini(&cli->uvmm); + nouveau_sched_entity_fini(&cli->sched_entity); nouveau_vmm_fini(&cli->svm); nouveau_vmm_fini(&cli->vmm); nvif_mmu_dtor(&cli->mmu); @@ -301,6 +306,12 @@ nouveau_cli_init(struct nouveau_drm *drm, const char *sname, } cli->mem = &mems[ret]; + + ret = nouveau_sched_entity_init(&cli->sched_entity, &drm->sched, + drm->sched_wq); + if (ret) + goto done; + return 0; done: if (ret) @@ -568,10 +579,14 @@ nouveau_drm_device_init(struct drm_device *dev) nvif_parent_ctor(&nouveau_parent, &drm->parent); drm->master.base.object.parent = &drm->parent; - ret = nouveau_cli_init(drm, "DRM-master", &drm->master); + ret = nouveau_sched_init(drm); if (ret) goto fail_alloc; + ret = nouveau_cli_init(drm, "DRM-master", &drm->master); + if (ret) + goto fail_sched; + ret = nouveau_cli_init(drm, "DRM", &drm->client); if (ret) goto fail_master; @@ -628,7 +643,6 @@ nouveau_drm_device_init(struct drm_device *dev) } return 0; - fail_dispinit: nouveau_display_destroy(dev); fail_dispctor: @@ -641,6 +655,8 @@ nouveau_drm_device_init(struct drm_device *dev) nouveau_cli_fini(&drm->client); fail_master: nouveau_cli_fini(&drm->master); +fail_sched: + nouveau_sched_fini(drm); fail_alloc: nvif_parent_dtor(&drm->parent); kfree(drm); @@ -692,6 +708,8 @@ nouveau_drm_device_fini(struct drm_device *dev) } mutex_unlock(&drm->clients_lock); + nouveau_sched_fini(drm); + nouveau_cli_fini(&drm->client); nouveau_cli_fini(&drm->master); nvif_parent_dtor(&drm->parent); @@ -1193,6 +1211,9 @@ nouveau_ioctls[] = { DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_CPU_PREP, nouveau_gem_ioctl_cpu_prep, DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_CPU_FINI, nouveau_gem_ioctl_cpu_fini, DRM_RENDER_ALLOW), DRM_IOCTL_DEF_DRV(NOUVEAU_GEM_INFO, nouveau_gem_ioctl_info, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(NOUVEAU_VM_INIT, nouveau_uvmm_ioctl_vm_init, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(NOUVEAU_VM_BIND, nouveau_uvmm_ioctl_vm_bind, DRM_RENDER_ALLOW), + DRM_IOCTL_DEF_DRV(NOUVEAU_EXEC, nouveau_exec_ioctl_exec, DRM_RENDER_ALLOW), }; long @@ -1240,6 +1261,8 @@ nouveau_driver_fops = { static struct drm_driver driver_stub = { .driver_features = DRIVER_GEM | + DRIVER_SYNCOBJ | DRIVER_SYNCOBJ_TIMELINE | + DRIVER_GEM_GPUVA | DRIVER_MODESET | DRIVER_RENDER, .open = nouveau_drm_open, diff --git a/drivers/gpu/drm/nouveau/nouveau_drv.h b/drivers/gpu/drm/nouveau/nouveau_drv.h index d28236021971..1fe17ff95f5e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drv.h +++ b/drivers/gpu/drm/nouveau/nouveau_drv.h @@ -10,8 +10,8 @@ #define DRIVER_DATE "20120801" #define DRIVER_MAJOR 1 -#define DRIVER_MINOR 3 -#define DRIVER_PATCHLEVEL 1 +#define DRIVER_MINOR 4 +#define DRIVER_PATCHLEVEL 0 /* * 1.1.1: @@ -63,7 +63,9 @@ struct platform_device; #include "nouveau_fence.h" #include "nouveau_bios.h" +#include "nouveau_sched.h" #include "nouveau_vmm.h" +#include "nouveau_uvmm.h" struct nouveau_drm_tile { struct nouveau_fence *fence; @@ -91,6 +93,10 @@ struct nouveau_cli { struct nvif_mmu mmu; struct nouveau_vmm vmm; struct nouveau_vmm svm; + struct nouveau_uvmm uvmm; + + struct nouveau_sched_entity sched_entity; + const struct nvif_mclass *mem; struct list_head head; @@ -112,15 +118,59 @@ struct nouveau_cli_work { struct dma_fence_cb cb; }; +static inline struct nouveau_uvmm * +nouveau_cli_uvmm(struct nouveau_cli *cli) +{ + if (!cli || !cli->uvmm.vmm.cli) + return NULL; + + return &cli->uvmm; +} + +static inline struct nouveau_uvmm * +nouveau_cli_uvmm_locked(struct nouveau_cli *cli) +{ + struct nouveau_uvmm *uvmm; + + mutex_lock(&cli->mutex); + uvmm = nouveau_cli_uvmm(cli); + mutex_unlock(&cli->mutex); + + return uvmm; +} + static inline struct nouveau_vmm * nouveau_cli_vmm(struct nouveau_cli *cli) { + struct nouveau_uvmm *uvmm; + + uvmm = nouveau_cli_uvmm(cli); + if (uvmm) + return &uvmm->vmm; + if (cli->svm.cli) return &cli->svm; return &cli->vmm; } +static inline void +__nouveau_cli_disable_uvmm_noinit(struct nouveau_cli *cli) +{ + struct nouveau_uvmm *uvmm = nouveau_cli_uvmm(cli); + + if (!uvmm) + cli->uvmm.disabled = true; +} + +static inline void +nouveau_cli_disable_uvmm_noinit(struct nouveau_cli *cli) +{ + mutex_lock(&cli->mutex); + __nouveau_cli_disable_uvmm_noinit(cli); + mutex_unlock(&cli->mutex); +} + void nouveau_cli_work_queue(struct nouveau_cli *, struct dma_fence *, struct nouveau_cli_work *); @@ -257,6 +307,10 @@ struct nouveau_drm { struct mutex lock; bool component_registered; } audio; + + struct drm_gpu_scheduler sched; + struct workqueue_struct *sched_wq; + }; static inline struct nouveau_drm * diff --git a/drivers/gpu/drm/nouveau/nouveau_exec.c b/drivers/gpu/drm/nouveau/nouveau_exec.c new file mode 100644 index 000000000000..64a542566be7 --- /dev/null +++ b/drivers/gpu/drm/nouveau/nouveau_exec.c @@ -0,0 +1,436 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright (c) 2022 Red Hat. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: + * Danilo Krummrich <dakr at redhat.com> + * + */ + +#include <drm/drm_exec.h> + +#include "nouveau_drv.h" +#include "nouveau_gem.h" +#include "nouveau_mem.h" +#include "nouveau_dma.h" +#include "nouveau_exec.h" +#include "nouveau_abi16.h" +#include "nouveau_chan.h" +#include "nouveau_sched.h" +#include "nouveau_uvmm.h" + +/** + * DOC: Overview + * + * Nouveau's VM_BIND / EXEC UAPI consists of three ioctls: DRM_NOUVEAU_VM_INIT, + * DRM_NOUVEAU_VM_BIND and DRM_NOUVEAU_EXEC. + * + * In order to use the UAPI firstly a user client must initialize the VA space + * using the DRM_NOUVEAU_VM_INIT ioctl specifying which region of the VA space + * should be managed by the kernel and which by the UMD. + * + * The DRM_NOUVEAU_VM_BIND ioctl provides clients an interface to manage the + * userspace-managable portion of the VA space. It provides operations to map + * and unmap memory. Mappings may be flagged as sparse. Sparse mappings are not + * backed by a GEM object and the kernel will ignore GEM handles provided + * alongside a sparse mapping. + * + * Userspace may request memory backed mappings either within or outside of the + * bounds (but not crossing those bounds) of a previously mapped sparse + * mapping. Subsequently requested memory backed mappings within a sparse + * mapping will take precedence over the corresponding range of the sparse + * mapping. If such memory backed mappings are unmapped the kernel will make + * sure that the corresponding sparse mapping will take their place again. + * Requests to unmap a sparse mapping that still contains memory backed mappings + * will result in those memory backed mappings being unmapped first. + * + * Unmap requests are not bound to the range of existing mappings and can even + * overlap the bounds of sparse mappings. For such a request the kernel will + * make sure to unmap all memory backed mappings within the given range, + * splitting up memory backed mappings which are only partially contained + * within the given range. Unmap requests with the sparse flag set must match + * the range of a previously mapped sparse mapping exactly though. + * + * While the kernel generally permits arbitrary sequences and ranges of memory + * backed mappings being mapped and unmapped, either within a single or multiple + * VM_BIND ioctl calls, there are some restrictions for sparse mappings. + * + * The kernel does not permit to: + * - unmap non-existent sparse mappings + * - unmap a sparse mapping and map a new sparse mapping overlapping the range + * of the previously unmapped sparse mapping within the same VM_BIND ioctl + * - unmap a sparse mapping and map new memory backed mappings overlapping the + * range of the previously unmapped sparse mapping within the same VM_BIND + * ioctl + * + * When using the VM_BIND ioctl to request the kernel to map memory to a given + * virtual address in the GPU's VA space there is no guarantee that the actual + * mappings are created in the GPU's MMU. If the given memory is swapped out + * at the time the bind operation is executed the kernel will stash the mapping + * details into it's internal alloctor and create the actual MMU mappings once + * the memory is swapped back in. While this is transparent for userspace, it is + * guaranteed that all the backing memory is swapped back in and all the memory + * mappings, as requested by userspace previously, are actually mapped once the + * DRM_NOUVEAU_EXEC ioctl is called to submit an exec job. + * + * A VM_BIND job can be executed either synchronously or asynchronously. If + * exectued asynchronously, userspace may provide a list of syncobjs this job + * will wait for and/or a list of syncobj the kernel will signal once the + * VM_BIND job finished execution. If executed synchronously the ioctl will + * block until the bind job is finished. For synchronous jobs the kernel will + * not permit any syncobjs submitted to the kernel. + * + * To execute a push buffer the UAPI provides the DRM_NOUVEAU_EXEC ioctl. EXEC + * jobs are always executed asynchronously, and, equal to VM_BIND jobs, provide + * the option to synchronize them with syncobjs. + * + * Besides that, EXEC jobs can be scheduled for a specified channel to execute on. + * + * Since VM_BIND jobs update the GPU's VA space on job submit, EXEC jobs do have + * an up to date view of the VA space. However, the actual mappings might still + * be pending. Hence, EXEC jobs require to have the particular fences - of + * the corresponding VM_BIND jobs they depent on - attached to them. + */ + +static int +nouveau_exec_job_submit(struct nouveau_job *job) +{ + struct nouveau_exec_job *exec_job = to_nouveau_exec_job(job); + struct nouveau_cli *cli = job->cli; + struct nouveau_uvmm *uvmm = nouveau_cli_uvmm(cli); + struct drm_exec *exec = &job->exec; + struct drm_gem_object *obj; + unsigned long index; + int ret; + + ret = nouveau_fence_new(&exec_job->fence); + if (ret) + return ret; + + nouveau_uvmm_lock(uvmm); + drm_exec_init(exec, DRM_EXEC_INTERRUPTIBLE_WAIT | + DRM_EXEC_IGNORE_DUPLICATES); + drm_exec_until_all_locked(exec) { + struct drm_gpuva *va; + + drm_gpuva_for_each_va(va, &uvmm->umgr) { + if (unlikely(va == &uvmm->umgr.kernel_alloc_node)) + continue; + + ret = drm_exec_prepare_obj(exec, va->gem.obj, 1); + drm_exec_retry_on_contention(exec); + if (ret) + goto err_uvmm_unlock; + } + } + nouveau_uvmm_unlock(uvmm); + + drm_exec_for_each_locked_object(exec, index, obj) { + struct nouveau_bo *nvbo = nouveau_gem_object(obj); + + ret = nouveau_bo_validate(nvbo, true, false); + if (ret) + goto err_exec_fini; + } + + return 0; + +err_uvmm_unlock: + nouveau_uvmm_unlock(uvmm); +err_exec_fini: + drm_exec_fini(exec); + return ret; + +} + +static void +nouveau_exec_job_armed_submit(struct nouveau_job *job) +{ + struct drm_exec *exec = &job->exec; + struct drm_gem_object *obj; + unsigned long index; + + drm_exec_for_each_locked_object(exec, index, obj) + dma_resv_add_fence(obj->resv, job->done_fence, job->resv_usage); + + drm_exec_fini(exec); +} + +static struct dma_fence * +nouveau_exec_job_run(struct nouveau_job *job) +{ + struct nouveau_exec_job *exec_job = to_nouveau_exec_job(job); + struct nouveau_channel *chan = exec_job->chan; + struct nouveau_fence *fence = exec_job->fence; + int i, ret; + + ret = nouveau_dma_wait(chan, exec_job->push.count + 1, 16); + if (ret) { + NV_PRINTK(err, job->cli, "nv50cal_space: %d\n", ret); + return ERR_PTR(ret); + } + + for (i = 0; i < exec_job->push.count; i++) { + nv50_dma_push(chan, exec_job->push.s[i].va, + exec_job->push.s[i].va_len); + } + + ret = nouveau_fence_emit(fence, chan); + if (ret) { + NV_PRINTK(err, job->cli, "error fencing pushbuf: %d\n", ret); + WIND_RING(chan); + return ERR_PTR(ret); + } + + exec_job->fence = NULL; + + return &fence->base; +} + +static void +nouveau_exec_job_free(struct nouveau_job *job) +{ + struct nouveau_exec_job *exec_job = to_nouveau_exec_job(job); + + nouveau_job_free(job); + + nouveau_fence_unref(&exec_job->fence); + kfree(exec_job->push.s); + kfree(exec_job); +} + +static enum drm_gpu_sched_stat +nouveau_exec_job_timeout(struct nouveau_job *job) +{ + struct nouveau_exec_job *exec_job = to_nouveau_exec_job(job); + struct nouveau_channel *chan = exec_job->chan; + + if (unlikely(!atomic_read(&chan->killed))) + nouveau_channel_kill(chan); + + NV_PRINTK(warn, job->cli, "job timeout, channel %d killed!\n", + chan->chid); + + nouveau_sched_entity_fini(job->entity); + + return DRM_GPU_SCHED_STAT_ENODEV; +} + +static struct nouveau_job_ops nouveau_exec_job_ops = { + .submit = nouveau_exec_job_submit, + .armed_submit = nouveau_exec_job_armed_submit, + .run = nouveau_exec_job_run, + .free = nouveau_exec_job_free, + .timeout = nouveau_exec_job_timeout, +}; + +int +nouveau_exec_job_init(struct nouveau_exec_job **pjob, + struct nouveau_exec_job_args *__args) +{ + struct nouveau_exec_job *job; + struct nouveau_job_args args = {}; + int ret; + + job = *pjob = kzalloc(sizeof(*job), GFP_KERNEL); + if (!job) + return -ENOMEM; + + job->push.count = __args->push.count; + if (__args->push.count) { + job->push.s = kmemdup(__args->push.s, + sizeof(*__args->push.s) * + __args->push.count, + GFP_KERNEL); + if (!job->push.s) { + ret = -ENOMEM; + goto err_free_job; + } + } + + job->chan = __args->chan; + + args.sched_entity = __args->sched_entity; + args.file_priv = __args->file_priv; + + args.in_sync.count = __args->in_sync.count; + args.in_sync.s = __args->in_sync.s; + + args.out_sync.count = __args->out_sync.count; + args.out_sync.s = __args->out_sync.s; + + args.ops = &nouveau_exec_job_ops; + args.resv_usage = DMA_RESV_USAGE_WRITE; + + ret = nouveau_job_init(&job->base, &args); + if (ret) + goto err_free_pushs; + + return 0; + +err_free_pushs: + kfree(job->push.s); +err_free_job: + kfree(job); + *pjob = NULL; + + return ret; +} + +static int +nouveau_exec(struct nouveau_exec_job_args *args) +{ + struct nouveau_exec_job *job; + int ret; + + ret = nouveau_exec_job_init(&job, args); + if (ret) + return ret; + + ret = nouveau_job_submit(&job->base); + if (ret) + goto err_job_fini; + + return 0; + +err_job_fini: + nouveau_job_fini(&job->base); + return ret; +} + +static int +nouveau_exec_ucopy(struct nouveau_exec_job_args *args, + struct drm_nouveau_exec __user *req) +{ + struct drm_nouveau_sync **s; + u32 inc = req->wait_count; + u64 ins = req->wait_ptr; + u32 outc = req->sig_count; + u64 outs = req->sig_ptr; + u32 pushc = req->push_count; + u64 pushs = req->push_ptr; + int ret; + + if (pushc) { + args->push.count = pushc; + args->push.s = u_memcpya(pushs, pushc, sizeof(*args->push.s)); + if (IS_ERR(args->push.s)) + return PTR_ERR(args->push.s); + } + + if (inc) { + s = &args->in_sync.s; + + args->in_sync.count = inc; + *s = u_memcpya(ins, inc, sizeof(**s)); + if (IS_ERR(*s)) { + ret = PTR_ERR(*s); + goto err_free_pushs; + } + } + + if (outc) { + s = &args->out_sync.s; + + args->out_sync.count = outc; + *s = u_memcpya(outs, outc, sizeof(**s)); + if (IS_ERR(*s)) { + ret = PTR_ERR(*s); + goto err_free_ins; + } + } + + return 0; + +err_free_pushs: + u_free(args->push.s); +err_free_ins: + u_free(args->in_sync.s); + return ret; +} + +static void +nouveau_exec_ufree(struct nouveau_exec_job_args *args) +{ + u_free(args->push.s); + u_free(args->in_sync.s); + u_free(args->out_sync.s); +} + +int +nouveau_exec_ioctl_exec(struct drm_device *dev, + void __user *data, + struct drm_file *file_priv) +{ + struct nouveau_abi16 *abi16 = nouveau_abi16_get(file_priv); + struct nouveau_cli *cli = nouveau_cli(file_priv); + struct nouveau_abi16_chan *chan16; + struct nouveau_channel *chan = NULL; + struct nouveau_exec_job_args args = {}; + struct drm_nouveau_exec __user *req = data; + int ret = 0; + + if (unlikely(!abi16)) + return -ENOMEM; + + /* abi16 locks already */ + if (unlikely(!nouveau_cli_uvmm(cli))) + return nouveau_abi16_put(abi16, -ENOSYS); + + list_for_each_entry(chan16, &abi16->channels, head) { + if (chan16->chan->chid == req->channel) { + chan = chan16->chan; + break; + } + } + + if (!chan) + return nouveau_abi16_put(abi16, -ENOENT); + + if (unlikely(atomic_read(&chan->killed))) + return nouveau_abi16_put(abi16, -ENODEV); + + if (!chan->dma.ib_max) + return nouveau_abi16_put(abi16, -ENOSYS); + + if (unlikely(req->push_count > NOUVEAU_GEM_MAX_PUSH)) { + NV_PRINTK(err, cli, "pushbuf push count exceeds limit: %d max %d\n", + req->push_count, NOUVEAU_GEM_MAX_PUSH); + return nouveau_abi16_put(abi16, -EINVAL); + } + + ret = nouveau_exec_ucopy(&args, req); + if (ret) + goto out; + + args.sched_entity = &chan16->sched_entity; + args.file_priv = file_priv; + args.chan = chan; + + ret = nouveau_exec(&args); + if (ret) + goto out_free_args; + +out_free_args: + nouveau_exec_ufree(&args); +out: + return nouveau_abi16_put(abi16, ret); +} diff --git a/drivers/gpu/drm/nouveau/nouveau_exec.h b/drivers/gpu/drm/nouveau/nouveau_exec.h new file mode 100644 index 000000000000..3032db27b8d7 --- /dev/null +++ b/drivers/gpu/drm/nouveau/nouveau_exec.h @@ -0,0 +1,54 @@ +/* SPDX-License-Identifier: MIT */ + +#ifndef __NOUVEAU_EXEC_H__ +#define __NOUVEAU_EXEC_H__ + +#include <drm/drm_exec.h> + +#include "nouveau_drv.h" +#include "nouveau_sched.h" + +struct nouveau_exec_job_args { + struct drm_file *file_priv; + struct nouveau_sched_entity *sched_entity; + + struct drm_exec exec; + struct nouveau_channel *chan; + + struct { + struct drm_nouveau_sync *s; + u32 count; + } in_sync; + + struct { + struct drm_nouveau_sync *s; + u32 count; + } out_sync; + + struct { + struct drm_nouveau_exec_push *s; + u32 count; + } push; +}; + +struct nouveau_exec_job { + struct nouveau_job base; + struct nouveau_fence *fence; + struct nouveau_channel *chan; + + struct { + struct drm_nouveau_exec_push *s; + u32 count; + } push; +}; + +#define to_nouveau_exec_job(job) \ + container_of((job), struct nouveau_exec_job, base) + +int nouveau_exec_job_init(struct nouveau_exec_job **job, + struct nouveau_exec_job_args *args); + +int nouveau_exec_ioctl_exec(struct drm_device *dev, void __user *data, + struct drm_file *file_priv); + +#endif diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.c b/drivers/gpu/drm/nouveau/nouveau_gem.c index 9c8d1b911a01..f39360870c70 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.c +++ b/drivers/gpu/drm/nouveau/nouveau_gem.c @@ -103,6 +103,7 @@ nouveau_gem_object_open(struct drm_gem_object *gem, struct drm_file *file_priv) struct nouveau_bo *nvbo = nouveau_gem_object(gem); struct nouveau_drm *drm = nouveau_bdev(nvbo->bo.bdev); struct device *dev = drm->dev->dev; + struct nouveau_uvmm *uvmm = nouveau_cli_uvmm(cli); struct nouveau_vmm *vmm = nouveau_cli_vmm(cli); struct nouveau_vma *vma; int ret; @@ -110,6 +111,9 @@ nouveau_gem_object_open(struct drm_gem_object *gem, struct drm_file *file_priv) if (vmm->vmm.object.oclass < NVIF_CLASS_VMM_NV50) return 0; + if (nvbo->no_share && uvmm && &uvmm->resv != nvbo->bo.base.resv) + return -EPERM; + ret = ttm_bo_reserve(&nvbo->bo, false, false, NULL); if (ret) return ret; @@ -120,7 +124,11 @@ nouveau_gem_object_open(struct drm_gem_object *gem, struct drm_file *file_priv) goto out; } - ret = nouveau_vma_new(nvbo, vmm, &vma); + /* only create a VMA on binding */ + if (!nouveau_cli_uvmm(cli)) + ret = nouveau_vma_new(nvbo, vmm, &vma); + else + ret = 0; pm_runtime_mark_last_busy(dev); pm_runtime_put_autosuspend(dev); out: @@ -187,6 +195,9 @@ nouveau_gem_object_close(struct drm_gem_object *gem, struct drm_file *file_priv) if (vmm->vmm.object.oclass < NVIF_CLASS_VMM_NV50) return; + if (nouveau_cli_uvmm(cli)) + return; + ret = ttm_bo_reserve(&nvbo->bo, false, false, NULL); if (ret) return; @@ -209,6 +220,7 @@ const struct drm_gem_object_funcs nouveau_gem_object_funcs = { .free = nouveau_gem_object_del, .open = nouveau_gem_object_open, .close = nouveau_gem_object_close, + .export = nouveau_gem_prime_export, .pin = nouveau_gem_prime_pin, .unpin = nouveau_gem_prime_unpin, .get_sg_table = nouveau_gem_prime_get_sg_table, @@ -224,18 +236,28 @@ nouveau_gem_new(struct nouveau_cli *cli, u64 size, int align, uint32_t domain, struct nouveau_bo **pnvbo) { struct nouveau_drm *drm = cli->drm; + struct nouveau_uvmm *uvmm = nouveau_cli_uvmm(cli); + struct dma_resv *resv = NULL; struct nouveau_bo *nvbo; int ret; + if (domain & NOUVEAU_GEM_DOMAIN_NO_SHARE) { + if (unlikely(!uvmm)) + return -EINVAL; + + resv = &uvmm->resv; + } + if (!(domain & (NOUVEAU_GEM_DOMAIN_VRAM | NOUVEAU_GEM_DOMAIN_GART))) domain |= NOUVEAU_GEM_DOMAIN_CPU; nvbo = nouveau_bo_alloc(cli, &size, &align, domain, tile_mode, - tile_flags); + tile_flags, false); if (IS_ERR(nvbo)) return PTR_ERR(nvbo); nvbo->bo.base.funcs = &nouveau_gem_object_funcs; + nvbo->no_share = domain & NOUVEAU_GEM_DOMAIN_NO_SHARE; /* Initialize the embedded gem-object. We return a single gem-reference * to the caller, instead of a normal nouveau_bo ttm reference. */ @@ -246,7 +268,14 @@ nouveau_gem_new(struct nouveau_cli *cli, u64 size, int align, uint32_t domain, return ret; } - ret = nouveau_bo_init(nvbo, size, align, domain, NULL, NULL); + if (resv) + dma_resv_lock(resv, NULL); + + ret = nouveau_bo_init(nvbo, size, align, domain, NULL, resv); + + if (resv) + dma_resv_unlock(resv); + if (ret) return ret; @@ -279,13 +308,15 @@ nouveau_gem_info(struct drm_file *file_priv, struct drm_gem_object *gem, else rep->domain = NOUVEAU_GEM_DOMAIN_VRAM; rep->offset = nvbo->offset; - if (vmm->vmm.object.oclass >= NVIF_CLASS_VMM_NV50) { + if (vmm->vmm.object.oclass >= NVIF_CLASS_VMM_NV50 && + !nouveau_cli_uvmm(cli)) { vma = nouveau_vma_find(nvbo, vmm); if (!vma) return -EINVAL; rep->offset = vma->addr; - } + } else + rep->offset = 0; rep->size = nvbo->bo.base.size; rep->map_handle = drm_vma_node_offset_addr(&nvbo->bo.base.vma_node); @@ -310,6 +341,11 @@ nouveau_gem_ioctl_new(struct drm_device *dev, void *data, struct nouveau_bo *nvbo = NULL; int ret = 0; + /* If uvmm wasn't initialized until now disable it completely to prevent + * userspace from mixing up UAPIs. + */ + nouveau_cli_disable_uvmm_noinit(cli); + ret = nouveau_gem_new(cli, req->info.size, req->align, req->info.domain, req->info.tile_mode, req->info.tile_flags, &nvbo); @@ -721,6 +757,9 @@ nouveau_gem_ioctl_pushbuf(struct drm_device *dev, void *data, if (unlikely(!abi16)) return -ENOMEM; + if (unlikely(nouveau_cli_uvmm(cli))) + return -ENOSYS; + list_for_each_entry(temp, &abi16->channels, head) { if (temp->chan->chid == req->channel) { chan = temp->chan; diff --git a/drivers/gpu/drm/nouveau/nouveau_gem.h b/drivers/gpu/drm/nouveau/nouveau_gem.h index 3b919c7c931c..10814d446435 100644 --- a/drivers/gpu/drm/nouveau/nouveau_gem.h +++ b/drivers/gpu/drm/nouveau/nouveau_gem.h @@ -37,5 +37,6 @@ extern void nouveau_gem_prime_unpin(struct drm_gem_object *); extern struct sg_table *nouveau_gem_prime_get_sg_table(struct drm_gem_object *); extern struct drm_gem_object *nouveau_gem_prime_import_sg_table( struct drm_device *, struct dma_buf_attachment *, struct sg_table *); - +struct dma_buf *nouveau_gem_prime_export(struct drm_gem_object *gobj, + int flags); #endif diff --git a/drivers/gpu/drm/nouveau/nouveau_mem.h b/drivers/gpu/drm/nouveau/nouveau_mem.h index 76c86d8bb01e..5365a3d3a17f 100644 --- a/drivers/gpu/drm/nouveau/nouveau_mem.h +++ b/drivers/gpu/drm/nouveau/nouveau_mem.h @@ -35,4 +35,9 @@ int nouveau_mem_vram(struct ttm_resource *, bool contig, u8 page); int nouveau_mem_host(struct ttm_resource *, struct ttm_tt *); void nouveau_mem_fini(struct nouveau_mem *); int nouveau_mem_map(struct nouveau_mem *, struct nvif_vmm *, struct nvif_vma *); +int +nouveau_mem_map_fixed(struct nouveau_mem *mem, + struct nvif_vmm *vmm, + u8 kind, u64 addr, + u64 offset, u64 range); #endif diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c index f42c2b1b0363..1b2ff0c40fc1 100644 --- a/drivers/gpu/drm/nouveau/nouveau_prime.c +++ b/drivers/gpu/drm/nouveau/nouveau_prime.c @@ -50,7 +50,7 @@ struct drm_gem_object *nouveau_gem_prime_import_sg_table(struct drm_device *dev, dma_resv_lock(robj, NULL); nvbo = nouveau_bo_alloc(&drm->client, &size, &align, - NOUVEAU_GEM_DOMAIN_GART, 0, 0); + NOUVEAU_GEM_DOMAIN_GART, 0, 0, true); if (IS_ERR(nvbo)) { obj = ERR_CAST(nvbo); goto unlock; @@ -102,3 +102,14 @@ void nouveau_gem_prime_unpin(struct drm_gem_object *obj) nouveau_bo_unpin(nvbo); } + +struct dma_buf *nouveau_gem_prime_export(struct drm_gem_object *gobj, + int flags) +{ + struct nouveau_bo *nvbo = nouveau_gem_object(gobj); + + if (nvbo->no_share) + return ERR_PTR(-EPERM); + + return drm_gem_prime_export(gobj, flags); +} diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.c b/drivers/gpu/drm/nouveau/nouveau_sched.c new file mode 100644 index 000000000000..0539ee2eaa15 --- /dev/null +++ b/drivers/gpu/drm/nouveau/nouveau_sched.c @@ -0,0 +1,444 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright (c) 2022 Red Hat. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: + * Danilo Krummrich <dakr at redhat.com> + * + */ + +#include <linux/slab.h> +#include <drm/gpu_scheduler.h> +#include <drm/drm_syncobj.h> + +#include "nouveau_drv.h" +#include "nouveau_gem.h" +#include "nouveau_mem.h" +#include "nouveau_dma.h" +#include "nouveau_exec.h" +#include "nouveau_abi16.h" +#include "nouveau_sched.h" + +/* FIXME + * + * We want to make sure that jobs currently executing can't be deferred by + * other jobs competing for the hardware. Otherwise we might end up with job + * timeouts just because of too many clients submitting too many jobs. We don't + * want jobs to time out because of system load, but because of the job being + * too bulky. + * + * For now allow for up to 16 concurrent jobs in flight until we know how many + * rings the hardware can process in parallel. + */ +#define NOUVEAU_SCHED_HW_SUBMISSIONS 16 +#define NOUVEAU_SCHED_JOB_TIMEOUT_MS 10000 + +int +nouveau_job_init(struct nouveau_job *job, + struct nouveau_job_args *args) +{ + struct nouveau_sched_entity *entity = args->sched_entity; + int ret; + + job->file_priv = args->file_priv; + job->cli = nouveau_cli(args->file_priv); + job->entity = entity; + + job->sync = args->sync; + job->resv_usage = args->resv_usage; + + job->ops = args->ops; + + job->in_sync.count = args->in_sync.count; + if (job->in_sync.count) { + if (job->sync) + return -EINVAL; + + job->in_sync.data = kmemdup(args->in_sync.s, + sizeof(*args->in_sync.s) * + args->in_sync.count, + GFP_KERNEL); + if (!job->in_sync.data) + return -ENOMEM; + } + + job->out_sync.count = args->out_sync.count; + if (job->out_sync.count) { + if (job->sync) { + ret = -EINVAL; + goto err_free_in_sync; + } + + job->out_sync.data = kmemdup(args->out_sync.s, + sizeof(*args->out_sync.s) * + args->out_sync.count, + GFP_KERNEL); + if (!job->out_sync.data) { + ret = -ENOMEM; + goto err_free_in_sync; + } + + job->out_sync.objs = kcalloc(job->out_sync.count, + sizeof(*job->out_sync.objs), + GFP_KERNEL); + if (!job->out_sync.objs) { + ret = -ENOMEM; + goto err_free_out_sync; + } + + job->out_sync.chains = kcalloc(job->out_sync.count, + sizeof(*job->out_sync.chains), + GFP_KERNEL); + if (!job->out_sync.chains) { + ret = -ENOMEM; + goto err_free_objs; + } + + } + + ret = drm_sched_job_init(&job->base, &entity->base, NULL); + if (ret) + goto err_free_chains; + + job->state = NOUVEAU_JOB_INITIALIZED; + + return 0; + +err_free_chains: + kfree(job->out_sync.chains); +err_free_objs: + kfree(job->out_sync.objs); +err_free_out_sync: + kfree(job->out_sync.data); +err_free_in_sync: + kfree(job->in_sync.data); +return ret; +} + +void +nouveau_job_free(struct nouveau_job *job) +{ + kfree(job->in_sync.data); + kfree(job->out_sync.data); + kfree(job->out_sync.objs); + kfree(job->out_sync.chains); +} + +void nouveau_job_fini(struct nouveau_job *job) +{ + dma_fence_put(job->done_fence); + drm_sched_job_cleanup(&job->base); + job->ops->free(job); +} + +static int +sync_find_fence(struct nouveau_job *job, + struct drm_nouveau_sync *sync, + struct dma_fence **fence) +{ + u32 stype = sync->flags & DRM_NOUVEAU_SYNC_TYPE_MASK; + u64 point = 0; + int ret; + + if (stype != DRM_NOUVEAU_SYNC_SYNCOBJ && + stype != DRM_NOUVEAU_SYNC_TIMELINE_SYNCOBJ) + return -EOPNOTSUPP; + + if (stype == DRM_NOUVEAU_SYNC_TIMELINE_SYNCOBJ) + point = sync->timeline_value; + + ret = drm_syncobj_find_fence(job->file_priv, + sync->handle, point, + sync->flags, fence); + if (ret) + return ret; + + return 0; +} + +static int +nouveau_job_add_deps(struct nouveau_job *job) +{ + struct dma_fence *in_fence = NULL; + int ret, i; + + for (i = 0; i < job->in_sync.count; i++) { + struct drm_nouveau_sync *sync = &job->in_sync.data[i]; + + ret = sync_find_fence(job, sync, &in_fence); + if (ret) { + NV_PRINTK(warn, job->cli, + "Failed to find syncobj (-> in): handle=%d\n", + sync->handle); + return ret; + } + + ret = drm_sched_job_add_dependency(&job->base, in_fence); + if (ret) + return ret; + } + + return 0; +} + +static void +nouveau_job_fence_attach_cleanup(struct nouveau_job *job) +{ + int i; + + for (i = 0; i < job->out_sync.count; i++) { + struct drm_syncobj *obj = job->out_sync.objs[i]; + struct dma_fence_chain *chain = job->out_sync.chains[i]; + + if (obj) + drm_syncobj_put(obj); + + if (chain) + dma_fence_chain_free(chain); + } +} + +static int +nouveau_job_fence_attach_prepare(struct nouveau_job *job) +{ + int i, ret; + + for (i = 0; i < job->out_sync.count; i++) { + struct drm_nouveau_sync *sync = &job->out_sync.data[i]; + struct drm_syncobj **pobj = &job->out_sync.objs[i]; + struct dma_fence_chain **pchain = &job->out_sync.chains[i]; + u32 stype = sync->flags & DRM_NOUVEAU_SYNC_TYPE_MASK; + + if (stype != DRM_NOUVEAU_SYNC_SYNCOBJ && + stype != DRM_NOUVEAU_SYNC_TIMELINE_SYNCOBJ) { + ret = -EINVAL; + goto err_sync_cleanup; + } + + *pobj = drm_syncobj_find(job->file_priv, sync->handle); + if (!*pobj) { + NV_PRINTK(warn, job->cli, + "Failed to find syncobj (-> out): handle=%d\n", + sync->handle); + ret = -ENOENT; + goto err_sync_cleanup; + } + + if (stype == DRM_NOUVEAU_SYNC_TIMELINE_SYNCOBJ) { + *pchain = dma_fence_chain_alloc(); + if (!*pchain) { + ret = -ENOMEM; + goto err_sync_cleanup; + } + } + } + + return 0; + +err_sync_cleanup: + nouveau_job_fence_attach_cleanup(job); + return ret; +} + +static void +nouveau_job_fence_attach(struct nouveau_job *job) +{ + struct dma_fence *fence = job->done_fence; + int i; + + for (i = 0; i < job->out_sync.count; i++) { + struct drm_nouveau_sync *sync = &job->out_sync.data[i]; + struct drm_syncobj **pobj = &job->out_sync.objs[i]; + struct dma_fence_chain **pchain = &job->out_sync.chains[i]; + u32 stype = sync->flags & DRM_NOUVEAU_SYNC_TYPE_MASK; + + if (stype == DRM_NOUVEAU_SYNC_TIMELINE_SYNCOBJ) { + drm_syncobj_add_point(*pobj, *pchain, fence, + sync->timeline_value); + } else { + drm_syncobj_replace_fence(*pobj, fence); + } + + drm_syncobj_put(*pobj); + *pobj = NULL; + *pchain = NULL; + } +} + +int +nouveau_job_submit(struct nouveau_job *job) +{ + struct nouveau_sched_entity *entity = to_nouveau_sched_entity(job->base.entity); + struct dma_fence *done_fence = NULL; + int ret; + + ret = nouveau_job_add_deps(job); + if (ret) + goto err; + + ret = nouveau_job_fence_attach_prepare(job); + if (ret) + goto err; + + /* Make sure the job appears on the sched_entity's queue in the same + * order as it was submitted. + */ + mutex_lock(&entity->mutex); + + /* Guarantee we won't fail after the submit() callback returned + * successfully. + */ + if (job->ops->submit) { + ret = job->ops->submit(job); + if (ret) + goto err_cleanup; + } + + drm_sched_job_arm(&job->base); + job->done_fence = dma_fence_get(&job->base.s_fence->finished); + if (job->sync) + done_fence = dma_fence_get(job->done_fence); + + if (job->ops->armed_submit) + job->ops->armed_submit(job); + + nouveau_job_fence_attach(job); + + /* Set job state before pushing the job to the scheduler, + * such that we do not overwrite the job state set in run(). + */ + job->state = NOUVEAU_JOB_SUBMIT_SUCCESS; + + drm_sched_entity_push_job(&job->base); + + mutex_unlock(&entity->mutex); + + if (done_fence) { + dma_fence_wait(done_fence, true); + dma_fence_put(done_fence); + } + + return 0; + +err_cleanup: + mutex_unlock(&entity->mutex); + nouveau_job_fence_attach_cleanup(job); +err: + job->state = NOUVEAU_JOB_SUBMIT_FAILED; + return ret; +} + +bool +nouveau_sched_entity_qwork(struct nouveau_sched_entity *entity, + struct work_struct *work) +{ + return queue_work(entity->sched_wq, work); +} + +static struct dma_fence * +nouveau_job_run(struct nouveau_job *job) +{ + struct dma_fence *fence; + + fence = job->ops->run(job); + if (IS_ERR(fence)) + job->state = NOUVEAU_JOB_RUN_FAILED; + else + job->state = NOUVEAU_JOB_RUN_SUCCESS; + + return fence; +} + +static struct dma_fence * +nouveau_sched_run_job(struct drm_sched_job *sched_job) +{ + struct nouveau_job *job = to_nouveau_job(sched_job); + + return nouveau_job_run(job); +} + +static enum drm_gpu_sched_stat +nouveau_sched_timedout_job(struct drm_sched_job *sched_job) +{ + struct nouveau_job *job = to_nouveau_job(sched_job); + + NV_PRINTK(warn, job->cli, "Job timed out.\n"); + + if (job->ops->timeout) + return job->ops->timeout(job); + + return DRM_GPU_SCHED_STAT_ENODEV; +} + +static void +nouveau_sched_free_job(struct drm_sched_job *sched_job) +{ + struct nouveau_job *job = to_nouveau_job(sched_job); + + nouveau_job_fini(job); +} + +int nouveau_sched_entity_init(struct nouveau_sched_entity *entity, + struct drm_gpu_scheduler *sched, + struct workqueue_struct *sched_wq) +{ + mutex_init(&entity->mutex); + spin_lock_init(&entity->job.list.lock); + INIT_LIST_HEAD(&entity->job.list.head); + init_waitqueue_head(&entity->job.wq); + + entity->sched_wq = sched_wq; + return drm_sched_entity_init(&entity->base, + DRM_SCHED_PRIORITY_NORMAL, + &sched, 1, NULL); +} + +void +nouveau_sched_entity_fini(struct nouveau_sched_entity *entity) +{ + drm_sched_entity_destroy(&entity->base); +} + +static const struct drm_sched_backend_ops nouveau_sched_ops = { + .run_job = nouveau_sched_run_job, + .timedout_job = nouveau_sched_timedout_job, + .free_job = nouveau_sched_free_job, +}; + +int nouveau_sched_init(struct nouveau_drm *drm) +{ + struct drm_gpu_scheduler *sched = &drm->sched; + long job_hang_limit = msecs_to_jiffies(NOUVEAU_SCHED_JOB_TIMEOUT_MS); + + drm->sched_wq = create_singlethread_workqueue("nouveau_sched_wq"); + if (!drm->sched_wq) + return -ENOMEM; + + return drm_sched_init(sched, &nouveau_sched_ops, + NOUVEAU_SCHED_HW_SUBMISSIONS, 0, job_hang_limit, + NULL, NULL, "nouveau_sched", drm->dev->dev); +} + +void nouveau_sched_fini(struct nouveau_drm *drm) +{ + destroy_workqueue(drm->sched_wq); + drm_sched_fini(&drm->sched); +} diff --git a/drivers/gpu/drm/nouveau/nouveau_sched.h b/drivers/gpu/drm/nouveau/nouveau_sched.h new file mode 100644 index 000000000000..27ac19792597 --- /dev/null +++ b/drivers/gpu/drm/nouveau/nouveau_sched.h @@ -0,0 +1,127 @@ +/* SPDX-License-Identifier: MIT */ + +#ifndef NOUVEAU_SCHED_H +#define NOUVEAU_SCHED_H + +#include <linux/types.h> + +#include <drm/drm_exec.h> +#include <drm/gpu_scheduler.h> + +#include "nouveau_drv.h" + +#define to_nouveau_job(sched_job) \ + container_of((sched_job), struct nouveau_job, base) + +struct nouveau_job_ops; + +enum nouveau_job_state { + NOUVEAU_JOB_UNINITIALIZED = 0, + NOUVEAU_JOB_INITIALIZED, + NOUVEAU_JOB_SUBMIT_SUCCESS, + NOUVEAU_JOB_SUBMIT_FAILED, + NOUVEAU_JOB_RUN_SUCCESS, + NOUVEAU_JOB_RUN_FAILED, +}; + +struct nouveau_job_args { + struct drm_file *file_priv; + struct nouveau_sched_entity *sched_entity; + + enum dma_resv_usage resv_usage; + bool sync; + + struct { + struct drm_nouveau_sync *s; + u32 count; + } in_sync; + + struct { + struct drm_nouveau_sync *s; + u32 count; + } out_sync; + + struct nouveau_job_ops *ops; +}; + +struct nouveau_job { + struct drm_sched_job base; + + enum nouveau_job_state state; + + struct nouveau_sched_entity *entity; + + struct drm_file *file_priv; + struct nouveau_cli *cli; + + struct drm_exec exec; + enum dma_resv_usage resv_usage; + struct dma_fence *done_fence; + + bool sync; + + struct { + struct drm_nouveau_sync *data; + u32 count; + } in_sync; + + struct { + struct drm_nouveau_sync *data; + struct drm_syncobj **objs; + struct dma_fence_chain **chains; + u32 count; + } out_sync; + + struct nouveau_job_ops { + /* If .submit() returns without any error, it is guaranteed that + * armed_submit() is called. + */ + int (*submit)(struct nouveau_job *); + void (*armed_submit)(struct nouveau_job *); + struct dma_fence *(*run)(struct nouveau_job *); + void (*free)(struct nouveau_job *); + enum drm_gpu_sched_stat (*timeout)(struct nouveau_job *); + } *ops; +}; + +int nouveau_job_ucopy_syncs(struct nouveau_job_args *args, + u32 inc, u64 ins, + u32 outc, u64 outs); + +int nouveau_job_init(struct nouveau_job *job, + struct nouveau_job_args *args); +void nouveau_job_free(struct nouveau_job *job); + +int nouveau_job_submit(struct nouveau_job *job); +void nouveau_job_fini(struct nouveau_job *job); + +#define to_nouveau_sched_entity(entity) \ + container_of((entity), struct nouveau_sched_entity, base) + +struct nouveau_sched_entity { + struct drm_sched_entity base; + struct mutex mutex; + + struct workqueue_struct *sched_wq; + + struct { + struct { + struct list_head head; + spinlock_t lock; + } list; + struct wait_queue_head wq; + } job; +}; + +int nouveau_sched_entity_init(struct nouveau_sched_entity *entity, + struct drm_gpu_scheduler *sched, + struct workqueue_struct *sched_wq); +void nouveau_sched_entity_fini(struct nouveau_sched_entity *entity); + +bool nouveau_sched_entity_qwork(struct nouveau_sched_entity *entity, + struct work_struct *work); + +int nouveau_sched_init(struct nouveau_drm *drm); +void nouveau_sched_fini(struct nouveau_drm *drm); + +#endif diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c new file mode 100644 index 000000000000..5c43b77dc797 --- /dev/null +++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c @@ -0,0 +1,1946 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright (c) 2022 Red Hat. + * + * Permission is hereby granted, free of charge, to any person obtaining a + * copy of this software and associated documentation files (the "Software"), + * to deal in the Software without restriction, including without limitation + * the rights to use, copy, modify, merge, publish, distribute, sublicense, + * and/or sell copies of the Software, and to permit persons to whom the + * Software is furnished to do so, subject to the following conditions: + * + * The above copyright notice and this permission notice shall be included in + * all copies or substantial portions of the Software. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR + * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, + * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL + * THE COPYRIGHT HOLDER(S) OR AUTHOR(S) BE LIABLE FOR ANY CLAIM, DAMAGES OR + * OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, + * ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR + * OTHER DEALINGS IN THE SOFTWARE. + * + * Authors: + * Danilo Krummrich <dakr at redhat.com> + * + */ + +/* + * Locking: + * + * The uvmm mutex protects any operations on the GPU VA space provided by the + * DRM GPU VA manager. + * + * The GEMs dma_resv lock protects the GEMs GPUVA list, hence link/unlink of a + * mapping to it's backing GEM must be performed under this lock. + * + * Actual map/unmap operations within the fence signalling critical path are + * protected by installing DMA fences to the corresponding GEMs DMA + * reservations, such that concurrent BO moves, which itself walk the GEMs GPUVA + * list in order to map/unmap it's entries, can't occur concurrently. + * + * Accessing the DRM_GPUVA_INVALIDATED flag doesn't need any separate + * protection, since there are no accesses other than from BO move callbacks + * and from the fence signalling critical path, which are already protected by + * the corresponding GEMs DMA reservation fence. + */ + +#include "nouveau_drv.h" +#include "nouveau_gem.h" +#include "nouveau_mem.h" +#include "nouveau_uvmm.h" + +#include <nvif/vmm.h> +#include <nvif/mem.h> + +#include <nvif/class.h> +#include <nvif/if000c.h> +#include <nvif/if900d.h> + +#define NOUVEAU_VA_SPACE_BITS 47 /* FIXME */ +#define NOUVEAU_VA_SPACE_START 0x0 +#define NOUVEAU_VA_SPACE_END (1ULL << NOUVEAU_VA_SPACE_BITS) + +#define list_last_op(_ops) list_last_entry(_ops, struct bind_job_op, entry) +#define list_prev_op(_op) list_prev_entry(_op, entry) +#define list_for_each_op(_op, _ops) list_for_each_entry(_op, _ops, entry) +#define list_for_each_op_from_reverse(_op, _ops) \ + list_for_each_entry_from_reverse(_op, _ops, entry) +#define list_for_each_op_safe(_op, _n, _ops) list_for_each_entry_safe(_op, _n, _ops, entry) + +enum vm_bind_op { + OP_MAP = DRM_NOUVEAU_VM_BIND_OP_MAP, + OP_UNMAP = DRM_NOUVEAU_VM_BIND_OP_UNMAP, + OP_MAP_SPARSE, + OP_UNMAP_SPARSE, +}; + +struct nouveau_uvma_prealloc { + struct nouveau_uvma *map; + struct nouveau_uvma *prev; + struct nouveau_uvma *next; +}; + +struct bind_job_op { + struct list_head entry; + + enum vm_bind_op op; + u32 flags; + + struct { + u64 addr; + u64 range; + } va; + + struct { + u32 handle; + u64 offset; + struct drm_gem_object *obj; + } gem; + + struct nouveau_uvma_region *reg; + struct nouveau_uvma_prealloc new; + struct drm_gpuva_ops *ops; +}; + +struct uvmm_map_args { + struct nouveau_uvma_region *region; + u64 addr; + u64 range; + u8 kind; +}; + +static int +nouveau_uvmm_vmm_sparse_ref(struct nouveau_uvmm *uvmm, + u64 addr, u64 range) +{ + struct nvif_vmm *vmm = &uvmm->vmm.vmm; + + return nvif_vmm_raw_sparse(vmm, addr, range, true); +} + +static int +nouveau_uvmm_vmm_sparse_unref(struct nouveau_uvmm *uvmm, + u64 addr, u64 range) +{ + struct nvif_vmm *vmm = &uvmm->vmm.vmm; + + return nvif_vmm_raw_sparse(vmm, addr, range, false); +} + +static int +nouveau_uvmm_vmm_get(struct nouveau_uvmm *uvmm, + u64 addr, u64 range) +{ + struct nvif_vmm *vmm = &uvmm->vmm.vmm; + + return nvif_vmm_raw_get(vmm, addr, range, PAGE_SHIFT); +} + +static int +nouveau_uvmm_vmm_put(struct nouveau_uvmm *uvmm, + u64 addr, u64 range) +{ + struct nvif_vmm *vmm = &uvmm->vmm.vmm; + + return nvif_vmm_raw_put(vmm, addr, range, PAGE_SHIFT); +} + +static int +nouveau_uvmm_vmm_unmap(struct nouveau_uvmm *uvmm, + u64 addr, u64 range, bool sparse) +{ + struct nvif_vmm *vmm = &uvmm->vmm.vmm; + + return nvif_vmm_raw_unmap(vmm, addr, range, PAGE_SHIFT, sparse); +} + +static int +nouveau_uvmm_vmm_map(struct nouveau_uvmm *uvmm, + u64 addr, u64 range, + u64 bo_offset, u8 kind, + struct nouveau_mem *mem) +{ + struct nvif_vmm *vmm = &uvmm->vmm.vmm; + union { + struct gf100_vmm_map_v0 gf100; + } args; + u32 argc = 0; + + switch (vmm->object.oclass) { + case NVIF_CLASS_VMM_GF100: + case NVIF_CLASS_VMM_GM200: + case NVIF_CLASS_VMM_GP100: + args.gf100.version = 0; + if (mem->mem.type & NVIF_MEM_VRAM) + args.gf100.vol = 0; + else + args.gf100.vol = 1; + args.gf100.ro = 0; + args.gf100.priv = 0; + args.gf100.kind = kind; + argc = sizeof(args.gf100); + break; + default: + WARN_ON(1); + return -ENOSYS; + } + + return nvif_vmm_raw_map(vmm, addr, range, PAGE_SHIFT, + &args, argc, + &mem->mem, bo_offset); +} + +static int +nouveau_uvma_region_sparse_unref(struct nouveau_uvma_region *reg) +{ + u64 addr = reg->va.addr; + u64 range = reg->va.range; + + return nouveau_uvmm_vmm_sparse_unref(reg->uvmm, addr, range); +} + +static int +nouveau_uvma_vmm_put(struct nouveau_uvma *uvma) +{ + u64 addr = uvma->va.va.addr; + u64 range = uvma->va.va.range; + + return nouveau_uvmm_vmm_put(uvma->uvmm, addr, range); +} + +static int +nouveau_uvma_map(struct nouveau_uvma *uvma, + struct nouveau_mem *mem) +{ + u64 addr = uvma->va.va.addr; + u64 offset = uvma->va.gem.offset; + u64 range = uvma->va.va.range; + + return nouveau_uvmm_vmm_map(uvma->uvmm, addr, range, + offset, uvma->kind, mem); +} + +static int +nouveau_uvma_unmap(struct nouveau_uvma *uvma) +{ + u64 addr = uvma->va.va.addr; + u64 range = uvma->va.va.range; + bool sparse = !!uvma->region; + + if (drm_gpuva_invalidated(&uvma->va)) + return 0; + + return nouveau_uvmm_vmm_unmap(uvma->uvmm, addr, range, sparse); +} + +static int +nouveau_uvma_alloc(struct nouveau_uvma **puvma) +{ + *puvma = kzalloc(sizeof(**puvma), GFP_KERNEL); + if (!*puvma) + return -ENOMEM; + + return 0; +} + +static void +nouveau_uvma_free(struct nouveau_uvma *uvma) +{ + kfree(uvma); +} + +static void +nouveau_uvma_gem_get(struct nouveau_uvma *uvma) +{ + drm_gem_object_get(uvma->va.gem.obj); +} + +static void +nouveau_uvma_gem_put(struct nouveau_uvma *uvma) +{ + drm_gem_object_put(uvma->va.gem.obj); +} + +static int +nouveau_uvma_region_alloc(struct nouveau_uvma_region **preg) +{ + *preg = kzalloc(sizeof(**preg), GFP_KERNEL); + if (!*preg) + return -ENOMEM; + + kref_init(&(*preg)->kref); + + return 0; +} + +static void +nouveau_uvma_region_free(struct kref *kref) +{ + struct nouveau_uvma_region *reg + container_of(kref, struct nouveau_uvma_region, kref); + + kfree(reg); +} + +static void +nouveau_uvma_region_get(struct nouveau_uvma_region *reg) +{ + kref_get(®->kref); +} + +static void +nouveau_uvma_region_put(struct nouveau_uvma_region *reg) +{ + kref_put(®->kref, nouveau_uvma_region_free); +} + +static int +__nouveau_uvma_region_insert(struct nouveau_uvmm *uvmm, + struct nouveau_uvma_region *reg) +{ + u64 addr = reg->va.addr; + u64 range = reg->va.range; + u64 last = addr + range - 1; + MA_STATE(mas, &uvmm->region_mt, addr, addr); + + if (unlikely(mas_walk(&mas))) { + mas_unlock(&mas); + return -EEXIST; + } + + if (unlikely(mas.last < last)) { + mas_unlock(&mas); + return -EEXIST; + } + + mas.index = addr; + mas.last = last; + + mas_store_gfp(&mas, reg, GFP_KERNEL); + + reg->uvmm = uvmm; + + return 0; +} + +static int +nouveau_uvma_region_insert(struct nouveau_uvmm *uvmm, + struct nouveau_uvma_region *reg, + u64 addr, u64 range) +{ + int ret; + + reg->uvmm = uvmm; + reg->va.addr = addr; + reg->va.range = range; + + ret = __nouveau_uvma_region_insert(uvmm, reg); + if (ret) + return ret; + + return 0; +} + +static void +nouveau_uvma_region_remove(struct nouveau_uvma_region *reg) +{ + struct nouveau_uvmm *uvmm = reg->uvmm; + MA_STATE(mas, &uvmm->region_mt, reg->va.addr, 0); + + mas_erase(&mas); +} + +static int +nouveau_uvma_region_create(struct nouveau_uvmm *uvmm, + u64 addr, u64 range) +{ + struct nouveau_uvma_region *reg; + int ret; + + if (!drm_gpuva_interval_empty(&uvmm->umgr, addr, range)) + return -ENOSPC; + + ret = nouveau_uvma_region_alloc(®); + if (ret) + return ret; + + ret = nouveau_uvma_region_insert(uvmm, reg, addr, range); + if (ret) + goto err_free_region; + + ret = nouveau_uvmm_vmm_sparse_ref(uvmm, addr, range); + if (ret) + goto err_region_remove; + + return 0; + +err_region_remove: + nouveau_uvma_region_remove(reg); +err_free_region: + nouveau_uvma_region_put(reg); + return ret; +} + +static struct nouveau_uvma_region * +nouveau_uvma_region_find_first(struct nouveau_uvmm *uvmm, + u64 addr, u64 range) +{ + MA_STATE(mas, &uvmm->region_mt, addr, 0); + + return mas_find(&mas, addr + range - 1); +} + +static struct nouveau_uvma_region * +nouveau_uvma_region_find(struct nouveau_uvmm *uvmm, + u64 addr, u64 range) +{ + struct nouveau_uvma_region *reg; + + reg = nouveau_uvma_region_find_first(uvmm, addr, range); + if (!reg) + return NULL; + + if (reg->va.addr != addr || + reg->va.range != range) + return NULL; + + return reg; +} + +static bool +nouveau_uvma_region_empty(struct nouveau_uvma_region *reg) +{ + struct nouveau_uvmm *uvmm = reg->uvmm; + + return drm_gpuva_interval_empty(&uvmm->umgr, + reg->va.addr, + reg->va.range); +} + +static int +__nouveau_uvma_region_destroy(struct nouveau_uvma_region *reg) +{ + struct nouveau_uvmm *uvmm = reg->uvmm; + u64 addr = reg->va.addr; + u64 range = reg->va.range; + + if (!nouveau_uvma_region_empty(reg)) + return -EBUSY; + + nouveau_uvma_region_remove(reg); + nouveau_uvmm_vmm_sparse_unref(uvmm, addr, range); + nouveau_uvma_region_put(reg); + + return 0; +} + +static int +nouveau_uvma_region_destroy(struct nouveau_uvmm *uvmm, + u64 addr, u64 range) +{ + struct nouveau_uvma_region *reg; + + reg = nouveau_uvma_region_find(uvmm, addr, range); + if (!reg) + return -ENOENT; + + return __nouveau_uvma_region_destroy(reg); +} + +static void +nouveau_uvma_region_dirty(struct nouveau_uvma_region *reg) +{ + + init_completion(®->complete); + reg->dirty = true; +} + +static void +nouveau_uvma_region_complete(struct nouveau_uvma_region *reg) +{ + complete_all(®->complete); +} + +static void +op_map_prepare_unwind(struct nouveau_uvma *uvma) +{ + nouveau_uvma_gem_put(uvma); + drm_gpuva_remove(&uvma->va); + nouveau_uvma_free(uvma); +} + +static void +op_unmap_prepare_unwind(struct drm_gpuva *va) +{ + drm_gpuva_insert(va->mgr, va); +} + +static void +nouveau_uvmm_sm_prepare_unwind(struct nouveau_uvmm *uvmm, + struct nouveau_uvma_prealloc *new, + struct drm_gpuva_ops *ops, + struct drm_gpuva_op *last, + struct uvmm_map_args *args) +{ + struct drm_gpuva_op *op = last; + u64 vmm_get_start = args ? args->addr : 0; + u64 vmm_get_end = args ? args->addr + args->range : 0; + + /* Unwind GPUVA space. */ + drm_gpuva_for_each_op_from_reverse(op, ops) { + switch (op->op) { + case DRM_GPUVA_OP_MAP: + op_map_prepare_unwind(new->map); + break; + case DRM_GPUVA_OP_REMAP: { + struct drm_gpuva_op_remap *r = &op->remap; + + if (r->next) + op_map_prepare_unwind(new->next); + + if (r->prev) + op_map_prepare_unwind(new->prev); + + op_unmap_prepare_unwind(r->unmap->va); + break; + } + case DRM_GPUVA_OP_UNMAP: + op_unmap_prepare_unwind(op->unmap.va); + break; + default: + break; + } + } + + /* Unmap operation don't allocate page tables, hence skip the following + * page table unwind. + */ + if (!args) + return; + + drm_gpuva_for_each_op(op, ops) { + switch (op->op) { + case DRM_GPUVA_OP_MAP: { + u64 vmm_get_range = vmm_get_end - vmm_get_start; + + if (vmm_get_range) + nouveau_uvmm_vmm_put(uvmm, vmm_get_start, + vmm_get_range); + break; + } + case DRM_GPUVA_OP_REMAP: { + struct drm_gpuva_op_remap *r = &op->remap; + struct drm_gpuva *va = r->unmap->va; + u64 ustart = va->va.addr; + u64 urange = va->va.range; + u64 uend = ustart + urange; + + if (r->prev) + vmm_get_start = uend; + + if (r->next) + vmm_get_end = ustart; + + if (r->prev && r->next) + vmm_get_start = vmm_get_end = 0; + + break; + } + case DRM_GPUVA_OP_UNMAP: { + struct drm_gpuva_op_unmap *u = &op->unmap; + struct drm_gpuva *va = u->va; + u64 ustart = va->va.addr; + u64 urange = va->va.range; + u64 uend = ustart + urange; + + /* Nothing to do for mappings we merge with. */ + if (uend == vmm_get_start || + ustart == vmm_get_end) + break; + + if (ustart > vmm_get_start) { + u64 vmm_get_range = ustart - vmm_get_start; + + nouveau_uvmm_vmm_put(uvmm, vmm_get_start, + vmm_get_range); + } + vmm_get_start = uend; + break; + } + default: + break; + } + + if (op == last) + break; + } +} + +static void +nouveau_uvmm_sm_map_prepare_unwind(struct nouveau_uvmm *uvmm, + struct nouveau_uvma_prealloc *new, + struct drm_gpuva_ops *ops, + u64 addr, u64 range) +{ + struct drm_gpuva_op *last = drm_gpuva_last_op(ops); + struct uvmm_map_args args = { + .addr = addr, + .range = range, + }; + + nouveau_uvmm_sm_prepare_unwind(uvmm, new, ops, last, &args); +} + +static void +nouveau_uvmm_sm_unmap_prepare_unwind(struct nouveau_uvmm *uvmm, + struct nouveau_uvma_prealloc *new, + struct drm_gpuva_ops *ops) +{ + struct drm_gpuva_op *last = drm_gpuva_last_op(ops); + + nouveau_uvmm_sm_prepare_unwind(uvmm, new, ops, last, NULL); +} + +static int +op_map_prepare(struct nouveau_uvmm *uvmm, + struct nouveau_uvma **puvma, + struct drm_gpuva_op_map *op, + struct uvmm_map_args *args) +{ + struct nouveau_uvma *uvma; + int ret; + + ret = nouveau_uvma_alloc(&uvma); + if (ret) + return ret; + + uvma->uvmm = uvmm; + uvma->region = args->region; + uvma->kind = args->kind; + + drm_gpuva_map(&uvmm->umgr, &uvma->va, op); + + /* Keep a reference until this uvma is destroyed. */ + nouveau_uvma_gem_get(uvma); + + *puvma = uvma; + return 0; +} + +static void +op_unmap_prepare(struct drm_gpuva_op_unmap *u) +{ + drm_gpuva_unmap(u); +} + +static int +nouveau_uvmm_sm_prepare(struct nouveau_uvmm *uvmm, + struct nouveau_uvma_prealloc *new, + struct drm_gpuva_ops *ops, + struct uvmm_map_args *args) +{ + struct drm_gpuva_op *op; + u64 vmm_get_start = args ? args->addr : 0; + u64 vmm_get_end = args ? args->addr + args->range : 0; + int ret; + + drm_gpuva_for_each_op(op, ops) { + switch (op->op) { + case DRM_GPUVA_OP_MAP: { + u64 vmm_get_range = vmm_get_end - vmm_get_start; + + ret = op_map_prepare(uvmm, &new->map, &op->map, args); + if (ret) + goto unwind; + + if (args && vmm_get_range) { + ret = nouveau_uvmm_vmm_get(uvmm, vmm_get_start, + vmm_get_range); + if (ret) { + op_map_prepare_unwind(new->map); + goto unwind; + } + } + break; + } + case DRM_GPUVA_OP_REMAP: { + struct drm_gpuva_op_remap *r = &op->remap; + struct drm_gpuva *va = r->unmap->va; + struct uvmm_map_args remap_args = { + .kind = uvma_from_va(va)->kind, + }; + u64 ustart = va->va.addr; + u64 urange = va->va.range; + u64 uend = ustart + urange; + + op_unmap_prepare(r->unmap); + + if (r->prev) { + ret = op_map_prepare(uvmm, &new->prev, r->prev, + &remap_args); + if (ret) + goto unwind; + + if (args) + vmm_get_start = uend; + } + + if (r->next) { + ret = op_map_prepare(uvmm, &new->next, r->next, + &remap_args); + if (ret) { + if (r->prev) + op_map_prepare_unwind(new->prev); + goto unwind; + } + + if (args) + vmm_get_end = ustart; + } + + if (args && (r->prev && r->next)) + vmm_get_start = vmm_get_end = 0; + + break; + } + case DRM_GPUVA_OP_UNMAP: { + struct drm_gpuva_op_unmap *u = &op->unmap; + struct drm_gpuva *va = u->va; + u64 ustart = va->va.addr; + u64 urange = va->va.range; + u64 uend = ustart + urange; + + op_unmap_prepare(u); + + if (!args) + break; + + /* Nothing to do for mappings we merge with. */ + if (uend == vmm_get_start || + ustart == vmm_get_end) + break; + + if (ustart > vmm_get_start) { + u64 vmm_get_range = ustart - vmm_get_start; + + ret = nouveau_uvmm_vmm_get(uvmm, vmm_get_start, + vmm_get_range); + if (ret) { + op_unmap_prepare_unwind(va); + goto unwind; + } + } + vmm_get_start = uend; + + break; + } + default: + ret = -EINVAL; + goto unwind; + } + } + + return 0; + +unwind: + if (op != drm_gpuva_first_op(ops)) + nouveau_uvmm_sm_prepare_unwind(uvmm, new, ops, + drm_gpuva_prev_op(op), + args); + return ret; +} + +static int +nouveau_uvmm_sm_map_prepare(struct nouveau_uvmm *uvmm, + struct nouveau_uvma_prealloc *new, + struct nouveau_uvma_region *region, + struct drm_gpuva_ops *ops, + u64 addr, u64 range, u8 kind) +{ + struct uvmm_map_args args = { + .region = region, + .addr = addr, + .range = range, + .kind = kind, + }; + + return nouveau_uvmm_sm_prepare(uvmm, new, ops, &args); +} + +static int +nouveau_uvmm_sm_unmap_prepare(struct nouveau_uvmm *uvmm, + struct nouveau_uvma_prealloc *new, + struct drm_gpuva_ops *ops) +{ + return nouveau_uvmm_sm_prepare(uvmm, new, ops, NULL); +} + +static struct drm_gem_object * +op_gem_obj(struct drm_gpuva_op *op) +{ + switch (op->op) { + case DRM_GPUVA_OP_MAP: + return op->map.gem.obj; + case DRM_GPUVA_OP_REMAP: + /* Actually, we're looking for the GEMs backing remap.prev and + * remap.next, but since this is a remap they're identical to + * the GEM backing the unmapped GPUVA. + */ + return op->remap.unmap->va->gem.obj; + case DRM_GPUVA_OP_UNMAP: + return op->unmap.va->gem.obj; + default: + WARN(1, "Unknown operation.\n"); + return NULL; + } +} + +static void +op_map(struct nouveau_uvma *uvma) +{ + struct nouveau_bo *nvbo = nouveau_gem_object(uvma->va.gem.obj); + + nouveau_uvma_map(uvma, nouveau_mem(nvbo->bo.resource)); +} + +static void +op_unmap(struct drm_gpuva_op_unmap *u) +{ + struct drm_gpuva *va = u->va; + struct nouveau_uvma *uvma = uvma_from_va(va); + + /* nouveau_uvma_unmap() does not unmap if backing BO is evicted. */ + if (!u->keep) + nouveau_uvma_unmap(uvma); +} + +static void +op_unmap_range(struct drm_gpuva_op_unmap *u, + u64 addr, u64 range) +{ + struct nouveau_uvma *uvma = uvma_from_va(u->va); + bool sparse = !!uvma->region; + + if (!drm_gpuva_invalidated(u->va)) + nouveau_uvmm_vmm_unmap(uvma->uvmm, addr, range, sparse); +} + +static void +op_remap(struct drm_gpuva_op_remap *r, + struct nouveau_uvma_prealloc *new) +{ + struct drm_gpuva_op_unmap *u = r->unmap; + struct nouveau_uvma *uvma = uvma_from_va(u->va); + u64 addr = uvma->va.va.addr; + u64 range = uvma->va.va.range; + + if (r->prev) + addr = r->prev->va.addr + r->prev->va.range; + + if (r->next) + range = r->next->va.addr - addr; + + op_unmap_range(u, addr, range); +} + +static int +nouveau_uvmm_sm(struct nouveau_uvmm *uvmm, + struct nouveau_uvma_prealloc *new, + struct drm_gpuva_ops *ops) +{ + struct drm_gpuva_op *op; + + drm_gpuva_for_each_op(op, ops) { + switch (op->op) { + case DRM_GPUVA_OP_MAP: + op_map(new->map); + break; + case DRM_GPUVA_OP_REMAP: + op_remap(&op->remap, new); + break; + case DRM_GPUVA_OP_UNMAP: + op_unmap(&op->unmap); + break; + default: + break; + } + } + + return 0; +} + +static int +nouveau_uvmm_sm_map(struct nouveau_uvmm *uvmm, + struct nouveau_uvma_prealloc *new, + struct drm_gpuva_ops *ops) +{ + return nouveau_uvmm_sm(uvmm, new, ops); +} + +static int +nouveau_uvmm_sm_unmap(struct nouveau_uvmm *uvmm, + struct nouveau_uvma_prealloc *new, + struct drm_gpuva_ops *ops) +{ + return nouveau_uvmm_sm(uvmm, new, ops); +} + +static void +nouveau_uvmm_sm_cleanup(struct nouveau_uvmm *uvmm, + struct nouveau_uvma_prealloc *new, + struct drm_gpuva_ops *ops, bool unmap) +{ + struct drm_gpuva_op *op; + + drm_gpuva_for_each_op(op, ops) { + switch (op->op) { + case DRM_GPUVA_OP_MAP: + break; + case DRM_GPUVA_OP_REMAP: { + struct drm_gpuva_op_remap *r = &op->remap; + struct drm_gpuva_op_map *p = r->prev; + struct drm_gpuva_op_map *n = r->next; + struct drm_gpuva *va = r->unmap->va; + struct nouveau_uvma *uvma = uvma_from_va(va); + + if (unmap) { + u64 addr = va->va.addr; + u64 end = addr + va->va.range; + + if (p) + addr = p->va.addr + p->va.range; + + if (n) + end = n->va.addr; + + nouveau_uvmm_vmm_put(uvmm, addr, end - addr); + } + + nouveau_uvma_gem_put(uvma); + nouveau_uvma_free(uvma); + break; + } + case DRM_GPUVA_OP_UNMAP: { + struct drm_gpuva_op_unmap *u = &op->unmap; + struct drm_gpuva *va = u->va; + struct nouveau_uvma *uvma = uvma_from_va(va); + + if (unmap) + nouveau_uvma_vmm_put(uvma); + + nouveau_uvma_gem_put(uvma); + nouveau_uvma_free(uvma); + break; + } + default: + break; + } + } +} + +static void +nouveau_uvmm_sm_map_cleanup(struct nouveau_uvmm *uvmm, + struct nouveau_uvma_prealloc *new, + struct drm_gpuva_ops *ops) +{ + nouveau_uvmm_sm_cleanup(uvmm, new, ops, false); +} + +static void +nouveau_uvmm_sm_unmap_cleanup(struct nouveau_uvmm *uvmm, + struct nouveau_uvma_prealloc *new, + struct drm_gpuva_ops *ops) +{ + nouveau_uvmm_sm_cleanup(uvmm, new, ops, true); +} + +static int +nouveau_uvmm_validate_range(struct nouveau_uvmm *uvmm, u64 addr, u64 range) +{ + u64 end = addr + range; + u64 kernel_managed_end = uvmm->kernel_managed_addr + + uvmm->kernel_managed_size; + + if (addr & ~PAGE_MASK) + return -EINVAL; + + if (range & ~PAGE_MASK) + return -EINVAL; + + if (end <= addr) + return -EINVAL; + + if (addr < NOUVEAU_VA_SPACE_START || + end > NOUVEAU_VA_SPACE_END) + return -EINVAL; + + if (addr < kernel_managed_end && + end > uvmm->kernel_managed_addr) + return -EINVAL; + + return 0; +} + +static int +nouveau_uvmm_bind_job_alloc(struct nouveau_uvmm_bind_job **pjob) +{ + *pjob = kzalloc(sizeof(**pjob), GFP_KERNEL); + if (!*pjob) + return -ENOMEM; + + kref_init(&(*pjob)->kref); + + return 0; +} + +static void +nouveau_uvmm_bind_job_free(struct kref *kref) +{ + struct nouveau_uvmm_bind_job *job + container_of(kref, struct nouveau_uvmm_bind_job, kref); + + nouveau_job_free(&job->base); + kfree(job); +} + +static void +nouveau_uvmm_bind_job_get(struct nouveau_uvmm_bind_job *job) +{ + kref_get(&job->kref); +} + +static void +nouveau_uvmm_bind_job_put(struct nouveau_uvmm_bind_job *job) +{ + kref_put(&job->kref, nouveau_uvmm_bind_job_free); +} + +static int +bind_validate_op(struct nouveau_job *job, + struct bind_job_op *op) +{ + struct nouveau_uvmm *uvmm = nouveau_cli_uvmm(job->cli); + struct drm_gem_object *obj = op->gem.obj; + + if (op->op == OP_MAP) { + if (op->gem.offset & ~PAGE_MASK) + return -EINVAL; + + if (obj->size <= op->gem.offset) + return -EINVAL; + + if (op->va.range > (obj->size - op->gem.offset)) + return -EINVAL; + } + + return nouveau_uvmm_validate_range(uvmm, op->va.addr, op->va.range); +} + +static void +bind_validate_map_sparse(struct nouveau_job *job, u64 addr, u64 range) +{ + struct nouveau_uvmm_bind_job *bind_job; + struct nouveau_sched_entity *entity = job->entity; + struct bind_job_op *op; + u64 end = addr + range; + +again: + spin_lock(&entity->job.list.lock); + list_for_each_entry(bind_job, &entity->job.list.head, entry) { + list_for_each_op(op, &bind_job->ops) { + if (op->op == OP_UNMAP) { + u64 op_addr = op->va.addr; + u64 op_end = op_addr + op->va.range; + + if (!(end <= op_addr || addr >= op_end)) { + nouveau_uvmm_bind_job_get(bind_job); + spin_unlock(&entity->job.list.lock); + wait_for_completion(&bind_job->complete); + nouveau_uvmm_bind_job_put(bind_job); + goto again; + } + } + } + } + spin_unlock(&entity->job.list.lock); +} + +static int +bind_validate_map_common(struct nouveau_job *job, u64 addr, u64 range, + bool sparse) +{ + struct nouveau_uvmm *uvmm = nouveau_cli_uvmm(job->cli); + struct nouveau_uvma_region *reg; + u64 reg_addr, reg_end; + u64 end = addr + range; + +again: + nouveau_uvmm_lock(uvmm); + reg = nouveau_uvma_region_find_first(uvmm, addr, range); + if (!reg) { + nouveau_uvmm_unlock(uvmm); + return 0; + } + + /* Generally, job submits are serialized, hence only + * dirty regions can be modified concurrently. + */ + if (reg->dirty) { + nouveau_uvma_region_get(reg); + nouveau_uvmm_unlock(uvmm); + wait_for_completion(®->complete); + nouveau_uvma_region_put(reg); + goto again; + } + nouveau_uvmm_unlock(uvmm); + + if (sparse) + return -ENOSPC; + + reg_addr = reg->va.addr; + reg_end = reg_addr + reg->va.range; + + /* Make sure the mapping is either outside of a + * region or fully enclosed by a region. + */ + if (reg_addr > addr || reg_end < end) + return -ENOSPC; + + return 0; +} + +static int +bind_validate_region(struct nouveau_job *job) +{ + struct nouveau_uvmm_bind_job *bind_job = to_uvmm_bind_job(job); + struct bind_job_op *op; + int ret; + + list_for_each_op(op, &bind_job->ops) { + u64 op_addr = op->va.addr; + u64 op_range = op->va.range; + bool sparse = false; + + switch (op->op) { + case OP_MAP_SPARSE: + sparse = true; + bind_validate_map_sparse(job, op_addr, op_range); + fallthrough; + case OP_MAP: + ret = bind_validate_map_common(job, op_addr, op_range, + sparse); + if (ret) + return ret; + break; + default: + break; + } + } + + return 0; +} + +static void +bind_link_gpuvas(struct drm_gpuva_ops *ops, struct nouveau_uvma_prealloc *new) +{ + struct drm_gpuva_op *op; + + drm_gpuva_for_each_op(op, ops) { + switch (op->op) { + case DRM_GPUVA_OP_MAP: + drm_gpuva_link(&new->map->va); + break; + case DRM_GPUVA_OP_REMAP: + if (op->remap.prev) + drm_gpuva_link(&new->prev->va); + if (op->remap.next) + drm_gpuva_link(&new->next->va); + drm_gpuva_unlink(op->remap.unmap->va); + break; + case DRM_GPUVA_OP_UNMAP: + drm_gpuva_unlink(op->unmap.va); + break; + default: + break; + } + } +} + +static int +nouveau_uvmm_bind_job_submit(struct nouveau_job *job) +{ + struct nouveau_uvmm *uvmm = nouveau_cli_uvmm(job->cli); + struct nouveau_uvmm_bind_job *bind_job = to_uvmm_bind_job(job); + struct nouveau_sched_entity *entity = job->entity; + struct drm_exec *exec = &job->exec; + struct bind_job_op *op; + int ret; + + list_for_each_op(op, &bind_job->ops) { + if (op->op == OP_MAP) { + op->gem.obj = drm_gem_object_lookup(job->file_priv, + op->gem.handle); + if (!op->gem.obj) + return -ENOENT; + } + + ret = bind_validate_op(job, op); + if (ret) + return ret; + } + + /* If a sparse region or mapping overlaps a dirty region, we need to + * wait for the region to complete the unbind process. This is due to + * how page table management is currently implemented. A future + * implementation might change this. + */ + ret = bind_validate_region(job); + if (ret) + return ret; + + /* Once we start modifying the GPU VA space we need to keep holding the + * uvmm lock until we can't fail anymore. This is due to the set of GPU + * VA space changes must appear atomically and we need to be able to + * unwind all GPU VA space changes on failure. + */ + nouveau_uvmm_lock(uvmm); + list_for_each_op(op, &bind_job->ops) { + switch (op->op) { + case OP_MAP_SPARSE: + ret = nouveau_uvma_region_create(uvmm, + op->va.addr, + op->va.range); + if (ret) + goto unwind_continue; + + break; + case OP_UNMAP_SPARSE: + op->reg = nouveau_uvma_region_find(uvmm, op->va.addr, + op->va.range); + if (!op->reg || op->reg->dirty) { + ret = -ENOENT; + goto unwind_continue; + } + + op->ops = drm_gpuva_sm_unmap_ops_create(&uvmm->umgr, + op->va.addr, + op->va.range); + if (IS_ERR(op->ops)) { + ret = PTR_ERR(op->ops); + goto unwind_continue; + } + + ret = nouveau_uvmm_sm_unmap_prepare(uvmm, &op->new, + op->ops); + if (ret) { + drm_gpuva_ops_free(&uvmm->umgr, op->ops); + op->ops = NULL; + op->reg = NULL; + goto unwind_continue; + } + + nouveau_uvma_region_dirty(op->reg); + + break; + case OP_MAP: { + struct nouveau_uvma_region *reg; + + reg = nouveau_uvma_region_find_first(uvmm, + op->va.addr, + op->va.range); + if (reg) { + u64 reg_addr = reg->va.addr; + u64 reg_end = reg_addr + reg->va.range; + u64 op_addr = op->va.addr; + u64 op_end = op_addr + op->va.range; + + if (unlikely(reg->dirty)) { + ret = -EINVAL; + goto unwind_continue; + } + + /* Make sure the mapping is either outside of a + * region or fully enclosed by a region. + */ + if (reg_addr > op_addr || reg_end < op_end) { + ret = -ENOSPC; + goto unwind_continue; + } + } + + op->ops = drm_gpuva_sm_map_ops_create(&uvmm->umgr, + op->va.addr, + op->va.range, + op->gem.obj, + op->gem.offset); + if (IS_ERR(op->ops)) { + ret = PTR_ERR(op->ops); + goto unwind_continue; + } + + ret = nouveau_uvmm_sm_map_prepare(uvmm, &op->new, + reg, op->ops, + op->va.addr, + op->va.range, + op->flags & 0xff); + if (ret) { + drm_gpuva_ops_free(&uvmm->umgr, op->ops); + op->ops = NULL; + goto unwind_continue; + } + + break; + } + case OP_UNMAP: + op->ops = drm_gpuva_sm_unmap_ops_create(&uvmm->umgr, + op->va.addr, + op->va.range); + if (IS_ERR(op->ops)) { + ret = PTR_ERR(op->ops); + goto unwind_continue; + } + + ret = nouveau_uvmm_sm_unmap_prepare(uvmm, &op->new, + op->ops); + if (ret) { + drm_gpuva_ops_free(&uvmm->umgr, op->ops); + op->ops = NULL; + goto unwind_continue; + } + + break; + default: + ret = -EINVAL; + goto unwind_continue; + } + } + + drm_exec_init(exec, DRM_EXEC_INTERRUPTIBLE_WAIT | + DRM_EXEC_IGNORE_DUPLICATES); + drm_exec_until_all_locked(exec) { + list_for_each_op(op, &bind_job->ops) { + struct drm_gpuva_op *va_op; + + if (IS_ERR_OR_NULL(op->ops)) + continue; + + drm_gpuva_for_each_op(va_op, op->ops) { + struct drm_gem_object *obj = op_gem_obj(va_op); + + if (unlikely(!obj)) + continue; + + ret = drm_exec_prepare_obj(exec, obj, 1); + drm_exec_retry_on_contention(exec); + if (ret) { + op = list_last_op(&bind_job->ops); + goto unwind; + } + } + } + } + + list_for_each_op(op, &bind_job->ops) { + struct drm_gpuva_op *va_op; + + if (IS_ERR_OR_NULL(op->ops)) + continue; + + drm_gpuva_for_each_op(va_op, op->ops) { + struct drm_gem_object *obj = op_gem_obj(va_op); + + if (unlikely(!obj)) + continue; + + /* Don't validate GEMs backing mappings we're about to + * unmap, it's not worth the effort. + */ + if (unlikely(va_op->op == DRM_GPUVA_OP_UNMAP)) + continue; + + ret = nouveau_bo_validate(nouveau_gem_object(obj), + true, false); + if (ret) { + op = list_last_op(&bind_job->ops); + goto unwind; + } + } + } + + /* Link and unlink GPUVAs while holding the dma_resv lock. + * + * As long as we validate() all GEMs and add fences to all GEMs DMA + * reservations backing map and remap operations we can be sure there + * won't be any concurrent (in)validations during job execution, hence + * we're safe to check drm_gpuva_invalidated() within the fence + * signalling critical path without holding a separate lock. + * + * GPUVAs about to be unmapped are safe as well, since they're unlinked + * already. + * + * GEMs from map and remap operations must be validated before linking + * their corresponding mappings to prevent the actual PT update to + * happen right away in validate() rather than asynchronously as + * intended. + * + * Note that after linking and unlinking the GPUVAs in this loop this + * function cannot fail anymore, hence there is no need for an unwind + * path. + */ + list_for_each_op(op, &bind_job->ops) { + switch (op->op) { + case OP_UNMAP_SPARSE: + case OP_MAP: + case OP_UNMAP: + bind_link_gpuvas(op->ops, &op->new); + break; + default: + break; + } + } + nouveau_uvmm_unlock(uvmm); + + spin_lock(&entity->job.list.lock); + list_add(&bind_job->entry, &entity->job.list.head); + spin_unlock(&entity->job.list.lock); + + return 0; + +unwind_continue: + op = list_prev_op(op); +unwind: + list_for_each_op_from_reverse(op, &bind_job->ops) { + switch (op->op) { + case OP_MAP_SPARSE: + nouveau_uvma_region_destroy(uvmm, op->va.addr, + op->va.range); + break; + case OP_UNMAP_SPARSE: + __nouveau_uvma_region_insert(uvmm, op->reg); + nouveau_uvmm_sm_unmap_prepare_unwind(uvmm, &op->new, + op->ops); + break; + case OP_MAP: + nouveau_uvmm_sm_map_prepare_unwind(uvmm, &op->new, + op->ops, + op->va.addr, + op->va.range); + break; + case OP_UNMAP: + nouveau_uvmm_sm_unmap_prepare_unwind(uvmm, &op->new, + op->ops); + break; + } + + drm_gpuva_ops_free(&uvmm->umgr, op->ops); + op->ops = NULL; + op->reg = NULL; + } + + nouveau_uvmm_unlock(uvmm); + drm_exec_fini(exec); + return ret; +} + +static void +nouveau_uvmm_bind_job_armed_submit(struct nouveau_job *job) +{ + struct drm_exec *exec = &job->exec; + struct drm_gem_object *obj; + unsigned long index; + + drm_exec_for_each_locked_object(exec, index, obj) + dma_resv_add_fence(obj->resv, job->done_fence, job->resv_usage); + + drm_exec_fini(exec); +} + +static struct dma_fence * +nouveau_uvmm_bind_job_run(struct nouveau_job *job) +{ + struct nouveau_uvmm_bind_job *bind_job = to_uvmm_bind_job(job); + struct nouveau_uvmm *uvmm = nouveau_cli_uvmm(job->cli); + struct bind_job_op *op; + int ret = 0; + + list_for_each_op(op, &bind_job->ops) { + switch (op->op) { + case OP_MAP_SPARSE: + /* noop */ + break; + case OP_MAP: + ret = nouveau_uvmm_sm_map(uvmm, &op->new, op->ops); + if (ret) + goto out; + break; + case OP_UNMAP_SPARSE: + fallthrough; + case OP_UNMAP: + ret = nouveau_uvmm_sm_unmap(uvmm, &op->new, op->ops); + if (ret) + goto out; + break; + } + } + +out: + if (ret) + NV_PRINTK(err, job->cli, "bind job failed: %d\n", ret); + return ERR_PTR(ret); +} + +static void +nouveau_uvmm_bind_job_free_work_fn(struct work_struct *work) +{ + struct nouveau_uvmm_bind_job *bind_job + container_of(work, struct nouveau_uvmm_bind_job, work); + struct nouveau_job *job = &bind_job->base; + struct nouveau_uvmm *uvmm = nouveau_cli_uvmm(job->cli); + struct nouveau_sched_entity *entity = job->entity; + struct bind_job_op *op, *next; + + list_for_each_op(op, &bind_job->ops) { + struct drm_gem_object *obj = op->gem.obj; + + /* When nouveau_uvmm_bind_job_submit() fails op->ops and op->reg + * will be NULL, hence skip the cleanup. + */ + switch (op->op) { + case OP_MAP_SPARSE: + /* noop */ + break; + case OP_UNMAP_SPARSE: + if (!IS_ERR_OR_NULL(op->ops)) + nouveau_uvmm_sm_unmap_cleanup(uvmm, &op->new, + op->ops); + + if (op->reg) { + nouveau_uvma_region_sparse_unref(op->reg); + nouveau_uvmm_lock(uvmm); + nouveau_uvma_region_remove(op->reg); + nouveau_uvmm_unlock(uvmm); + nouveau_uvma_region_complete(op->reg); + nouveau_uvma_region_put(op->reg); + } + + break; + case OP_MAP: + if (!IS_ERR_OR_NULL(op->ops)) + nouveau_uvmm_sm_map_cleanup(uvmm, &op->new, + op->ops); + break; + case OP_UNMAP: + if (!IS_ERR_OR_NULL(op->ops)) + nouveau_uvmm_sm_unmap_cleanup(uvmm, &op->new, + op->ops); + break; + } + + if (!IS_ERR_OR_NULL(op->ops)) + drm_gpuva_ops_free(&uvmm->umgr, op->ops); + + if (obj) + drm_gem_object_put(obj); + } + + spin_lock(&entity->job.list.lock); + list_del(&bind_job->entry); + spin_unlock(&entity->job.list.lock); + + complete_all(&bind_job->complete); + wake_up(&entity->job.wq); + + /* Remove and free ops after removing the bind job from the job list to + * avoid races against bind_validate_map_sparse(). + */ + list_for_each_op_safe(op, next, &bind_job->ops) { + list_del(&op->entry); + kfree(op); + } + + nouveau_uvmm_bind_job_put(bind_job); +} + +static void +nouveau_uvmm_bind_job_free_qwork(struct nouveau_job *job) +{ + struct nouveau_uvmm_bind_job *bind_job = to_uvmm_bind_job(job); + struct nouveau_sched_entity *entity = job->entity; + + nouveau_sched_entity_qwork(entity, &bind_job->work); +} + +static struct nouveau_job_ops nouveau_bind_job_ops = { + .submit = nouveau_uvmm_bind_job_submit, + .armed_submit = nouveau_uvmm_bind_job_armed_submit, + .run = nouveau_uvmm_bind_job_run, + .free = nouveau_uvmm_bind_job_free_qwork, +}; + +static int +bind_job_op_from_uop(struct bind_job_op **pop, + struct drm_nouveau_vm_bind_op *uop) +{ + struct bind_job_op *op; + + op = *pop = kzalloc(sizeof(*op), GFP_KERNEL); + if (!op) + return -ENOMEM; + + switch (uop->op) { + case OP_MAP: + op->op = uop->flags & DRM_NOUVEAU_VM_BIND_SPARSE ? + OP_MAP_SPARSE : OP_MAP; + break; + case OP_UNMAP: + op->op = uop->flags & DRM_NOUVEAU_VM_BIND_SPARSE ? + OP_UNMAP_SPARSE : OP_UNMAP; + break; + default: + op->op = uop->op; + break; + } + + op->flags = uop->flags; + op->va.addr = uop->addr; + op->va.range = uop->range; + op->gem.handle = uop->handle; + op->gem.offset = uop->bo_offset; + + return 0; +} + +static void +bind_job_ops_free(struct list_head *ops) +{ + struct bind_job_op *op, *next; + + list_for_each_op_safe(op, next, ops) { + list_del(&op->entry); + kfree(op); + } +} + +static int +nouveau_uvmm_bind_job_init(struct nouveau_uvmm_bind_job **pjob, + struct nouveau_uvmm_bind_job_args *__args) +{ + struct nouveau_uvmm_bind_job *job; + struct nouveau_job_args args = {}; + struct bind_job_op *op; + int i, ret; + + ret = nouveau_uvmm_bind_job_alloc(&job); + if (ret) + return ret; + + INIT_LIST_HEAD(&job->ops); + INIT_LIST_HEAD(&job->entry); + + for (i = 0; i < __args->op.count; i++) { + ret = bind_job_op_from_uop(&op, &__args->op.s[i]); + if (ret) + goto err_free; + + list_add_tail(&op->entry, &job->ops); + } + + init_completion(&job->complete); + INIT_WORK(&job->work, nouveau_uvmm_bind_job_free_work_fn); + + args.sched_entity = __args->sched_entity; + args.file_priv = __args->file_priv; + + args.in_sync.count = __args->in_sync.count; + args.in_sync.s = __args->in_sync.s; + + args.out_sync.count = __args->out_sync.count; + args.out_sync.s = __args->out_sync.s; + + args.sync = !(__args->flags & DRM_NOUVEAU_VM_BIND_RUN_ASYNC); + args.ops = &nouveau_bind_job_ops; + args.resv_usage = DMA_RESV_USAGE_BOOKKEEP; + + ret = nouveau_job_init(&job->base, &args); + if (ret) + goto err_free; + + *pjob = job; + return 0; + +err_free: + bind_job_ops_free(&job->ops); + kfree(job); + *pjob = NULL; + + return ret; +} + +int +nouveau_uvmm_ioctl_vm_init(struct drm_device *dev, + void *data, + struct drm_file *file_priv) +{ + struct nouveau_cli *cli = nouveau_cli(file_priv); + struct drm_nouveau_vm_init *init = data; + + return nouveau_uvmm_init(&cli->uvmm, cli, init->kernel_managed_addr, + init->kernel_managed_size); +} + +static int +nouveau_uvmm_vm_bind(struct nouveau_uvmm_bind_job_args *args) +{ + struct nouveau_uvmm_bind_job *job; + int ret; + + ret = nouveau_uvmm_bind_job_init(&job, args); + if (ret) + return ret; + + ret = nouveau_job_submit(&job->base); + if (ret) + goto err_job_fini; + + return 0; + +err_job_fini: + nouveau_job_fini(&job->base); + return ret; +} + +static int +nouveau_uvmm_vm_bind_ucopy(struct nouveau_uvmm_bind_job_args *args, + struct drm_nouveau_vm_bind __user *req) +{ + struct drm_nouveau_sync **s; + u32 inc = req->wait_count; + u64 ins = req->wait_ptr; + u32 outc = req->sig_count; + u64 outs = req->sig_ptr; + u32 opc = req->op_count; + u64 ops = req->op_ptr; + int ret; + + args->flags = req->flags; + + if (opc) { + args->op.count = opc; + args->op.s = u_memcpya(ops, opc, + sizeof(*args->op.s)); + if (IS_ERR(args->op.s)) + return PTR_ERR(args->op.s); + } + + if (inc) { + s = &args->in_sync.s; + + args->in_sync.count = inc; + *s = u_memcpya(ins, inc, sizeof(**s)); + if (IS_ERR(*s)) { + ret = PTR_ERR(*s); + goto err_free_ops; + } + } + + if (outc) { + s = &args->out_sync.s; + + args->out_sync.count = outc; + *s = u_memcpya(outs, outc, sizeof(**s)); + if (IS_ERR(*s)) { + ret = PTR_ERR(*s); + goto err_free_ins; + } + } + + return 0; + +err_free_ops: + u_free(args->op.s); +err_free_ins: + u_free(args->in_sync.s); + return ret; +} + +static void +nouveau_uvmm_vm_bind_ufree(struct nouveau_uvmm_bind_job_args *args) +{ + u_free(args->op.s); + u_free(args->in_sync.s); + u_free(args->out_sync.s); +} + +int +nouveau_uvmm_ioctl_vm_bind(struct drm_device *dev, + void __user *data, + struct drm_file *file_priv) +{ + struct nouveau_cli *cli = nouveau_cli(file_priv); + struct nouveau_uvmm_bind_job_args args = {}; + struct drm_nouveau_vm_bind __user *req = data; + int ret = 0; + + if (unlikely(!nouveau_cli_uvmm_locked(cli))) + return -ENOSYS; + + ret = nouveau_uvmm_vm_bind_ucopy(&args, req); + if (ret) + return ret; + + args.sched_entity = &cli->sched_entity; + args.file_priv = file_priv; + + ret = nouveau_uvmm_vm_bind(&args); + if (ret) + goto out_free_args; + +out_free_args: + nouveau_uvmm_vm_bind_ufree(&args); + return ret; +} + +void +nouveau_uvmm_bo_map_all(struct nouveau_bo *nvbo, struct nouveau_mem *mem) +{ + struct drm_gem_object *obj = &nvbo->bo.base; + struct drm_gpuva *va; + + dma_resv_assert_held(obj->resv); + + drm_gem_for_each_gpuva(va, obj) { + struct nouveau_uvma *uvma = uvma_from_va(va); + + nouveau_uvma_map(uvma, mem); + drm_gpuva_invalidate(va, false); + } +} + +void +nouveau_uvmm_bo_unmap_all(struct nouveau_bo *nvbo) +{ + struct drm_gem_object *obj = &nvbo->bo.base; + struct drm_gpuva *va; + + dma_resv_assert_held(obj->resv); + + drm_gem_for_each_gpuva(va, obj) { + struct nouveau_uvma *uvma = uvma_from_va(va); + + nouveau_uvma_unmap(uvma); + drm_gpuva_invalidate(va, true); + } +} + +int +nouveau_uvmm_init(struct nouveau_uvmm *uvmm, struct nouveau_cli *cli, + u64 kernel_managed_addr, u64 kernel_managed_size) +{ + int ret; + u64 kernel_managed_end = kernel_managed_addr + kernel_managed_size; + + mutex_init(&uvmm->mutex); + dma_resv_init(&uvmm->resv); + mt_init_flags(&uvmm->region_mt, MT_FLAGS_LOCK_EXTERN); + mt_set_external_lock(&uvmm->region_mt, &uvmm->mutex); + + mutex_lock(&cli->mutex); + + if (unlikely(cli->uvmm.disabled)) { + ret = -ENOSYS; + goto out_unlock; + } + + if (kernel_managed_end <= kernel_managed_addr) { + ret = -EINVAL; + goto out_unlock; + } + + if (kernel_managed_end > NOUVEAU_VA_SPACE_END) { + ret = -EINVAL; + goto out_unlock; + } + + uvmm->kernel_managed_addr = kernel_managed_addr; + uvmm->kernel_managed_size = kernel_managed_size; + + drm_gpuva_manager_init(&uvmm->umgr, cli->name, + NOUVEAU_VA_SPACE_START, + NOUVEAU_VA_SPACE_END, + kernel_managed_addr, kernel_managed_size, + NULL); + + ret = nvif_vmm_ctor(&cli->mmu, "uvmm", + cli->vmm.vmm.object.oclass, RAW, + kernel_managed_addr, kernel_managed_size, + NULL, 0, &cli->uvmm.vmm.vmm); + if (ret) + goto out_free_gpuva_mgr; + + cli->uvmm.vmm.cli = cli; + mutex_unlock(&cli->mutex); + + return 0; + +out_free_gpuva_mgr: + drm_gpuva_manager_destroy(&uvmm->umgr); +out_unlock: + mutex_unlock(&cli->mutex); + return ret; +} + +void +nouveau_uvmm_fini(struct nouveau_uvmm *uvmm) +{ + MA_STATE(mas, &uvmm->region_mt, 0, 0); + struct nouveau_uvma_region *reg; + struct nouveau_cli *cli = uvmm->vmm.cli; + struct nouveau_sched_entity *entity = &cli->sched_entity; + struct drm_gpuva *va, *next; + + if (!cli) + return; + + rmb(); /* for list_empty to work without lock */ + wait_event(entity->job.wq, list_empty(&entity->job.list.head)); + + nouveau_uvmm_lock(uvmm); + drm_gpuva_for_each_va_safe(va, next, &uvmm->umgr) { + struct nouveau_uvma *uvma = uvma_from_va(va); + struct drm_gem_object *obj = va->gem.obj; + + if (unlikely(va == &uvmm->umgr.kernel_alloc_node)) + continue; + + drm_gpuva_remove(va); + + dma_resv_lock(obj->resv, NULL); + drm_gpuva_unlink(va); + dma_resv_unlock(obj->resv); + + nouveau_uvma_unmap(uvma); + nouveau_uvma_vmm_put(uvma); + + nouveau_uvma_gem_put(uvma); + nouveau_uvma_free(uvma); + } + + mas_for_each(&mas, reg, ULONG_MAX) { + mas_erase(&mas); + nouveau_uvma_region_sparse_unref(reg); + nouveau_uvma_region_put(reg); + } + + WARN(!mtree_empty(&uvmm->region_mt), + "nouveau_uvma_region tree not empty, potentially leaking memory."); + __mt_destroy(&uvmm->region_mt); + nouveau_uvmm_unlock(uvmm); + + mutex_lock(&cli->mutex); + nouveau_vmm_fini(&uvmm->vmm); + drm_gpuva_manager_destroy(&uvmm->umgr); + mutex_unlock(&cli->mutex); + + dma_resv_fini(&uvmm->resv); +} diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.h b/drivers/gpu/drm/nouveau/nouveau_uvmm.h new file mode 100644 index 000000000000..3923c03012f9 --- /dev/null +++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.h @@ -0,0 +1,108 @@ +/* SPDX-License-Identifier: MIT */ + +#ifndef __NOUVEAU_UVMM_H__ +#define __NOUVEAU_UVMM_H__ + +#include <drm/drm_gpuva_mgr.h> + +#include "nouveau_drv.h" + +struct nouveau_uvmm { + struct nouveau_vmm vmm; + struct drm_gpuva_manager umgr; + struct maple_tree region_mt; + struct mutex mutex; + struct dma_resv resv; + + u64 kernel_managed_addr; + u64 kernel_managed_size; + + bool disabled; +}; + +struct nouveau_uvma_region { + struct nouveau_uvmm *uvmm; + + struct { + u64 addr; + u64 range; + } va; + + struct kref kref; + + struct completion complete; + bool dirty; +}; + +struct nouveau_uvma { + struct drm_gpuva va; + + struct nouveau_uvmm *uvmm; + struct nouveau_uvma_region *region; + + u8 kind; +}; + +struct nouveau_uvmm_bind_job { + struct nouveau_job base; + + struct kref kref; + struct list_head entry; + struct work_struct work; + struct completion complete; + + /* struct bind_job_op */ + struct list_head ops; +}; + +struct nouveau_uvmm_bind_job_args { + struct drm_file *file_priv; + struct nouveau_sched_entity *sched_entity; + + unsigned int flags; + + struct { + struct drm_nouveau_sync *s; + u32 count; + } in_sync; + + struct { + struct drm_nouveau_sync *s; + u32 count; + } out_sync; + + struct { + struct drm_nouveau_vm_bind_op *s; + u32 count; + } op; +}; + +#define to_uvmm_bind_job(job) container_of((job), struct nouveau_uvmm_bind_job, base) + +#define uvmm_from_mgr(x) container_of((x), struct nouveau_uvmm, umgr) +#define uvma_from_va(x) container_of((x), struct nouveau_uvma, va) + +int nouveau_uvmm_init(struct nouveau_uvmm *uvmm, struct nouveau_cli *cli, + u64 kernel_managed_addr, u64 kernel_managed_size); +void nouveau_uvmm_fini(struct nouveau_uvmm *uvmm); + +void nouveau_uvmm_bo_map_all(struct nouveau_bo *nvbov, struct nouveau_mem *mem); +void nouveau_uvmm_bo_unmap_all(struct nouveau_bo *nvbo); + +int nouveau_uvmm_ioctl_vm_init(struct drm_device *dev, void __user *data, + struct drm_file *file_priv); + +int nouveau_uvmm_ioctl_vm_bind(struct drm_device *dev, void __user *data, + struct drm_file *file_priv); + +static inline void nouveau_uvmm_lock(struct nouveau_uvmm *uvmm) +{ + mutex_lock(&uvmm->mutex); +} + +static inline void nouveau_uvmm_unlock(struct nouveau_uvmm *uvmm) +{ + mutex_unlock(&uvmm->mutex); +} + +#endif -- 2.41.0
Danilo Krummrich
2023-Aug-03 16:52 UTC
[Nouveau] [PATCH drm-misc-next v9 11/11] drm/nouveau: debugfs: implement DRM GPU VA debugfs
Provide the driver indirection iterating over all DRM GPU VA spaces to enable the common 'gpuvas' debugfs file for dumping DRM GPU VA spaces. Signed-off-by: Danilo Krummrich <dakr at redhat.com> --- drivers/gpu/drm/nouveau/nouveau_debugfs.c | 39 +++++++++++++++++++++++ 1 file changed, 39 insertions(+) diff --git a/drivers/gpu/drm/nouveau/nouveau_debugfs.c b/drivers/gpu/drm/nouveau/nouveau_debugfs.c index 99d022a91afc..053f703f2f68 100644 --- a/drivers/gpu/drm/nouveau/nouveau_debugfs.c +++ b/drivers/gpu/drm/nouveau/nouveau_debugfs.c @@ -203,6 +203,44 @@ nouveau_debugfs_pstate_open(struct inode *inode, struct file *file) return single_open(file, nouveau_debugfs_pstate_get, inode->i_private); } +static void +nouveau_debugfs_gpuva_regions(struct seq_file *m, struct nouveau_uvmm *uvmm) +{ + MA_STATE(mas, &uvmm->region_mt, 0, 0); + struct nouveau_uvma_region *reg; + + seq_puts (m, " VA regions | start | range | end \n"); + seq_puts (m, "----------------------------------------------------------------------------\n"); + mas_for_each(&mas, reg, ULONG_MAX) + seq_printf(m, " | 0x%016llx | 0x%016llx | 0x%016llx\n", + reg->va.addr, reg->va.range, reg->va.addr + reg->va.range); +} + +static int +nouveau_debugfs_gpuva(struct seq_file *m, void *data) +{ + struct drm_info_node *node = (struct drm_info_node *) m->private; + struct nouveau_drm *drm = nouveau_drm(node->minor->dev); + struct nouveau_cli *cli; + + mutex_lock(&drm->clients_lock); + list_for_each_entry(cli, &drm->clients, head) { + struct nouveau_uvmm *uvmm = nouveau_cli_uvmm(cli); + + if (!uvmm) + continue; + + nouveau_uvmm_lock(uvmm); + drm_debugfs_gpuva_info(m, &uvmm->umgr); + seq_puts(m, "\n"); + nouveau_debugfs_gpuva_regions(m, uvmm); + nouveau_uvmm_unlock(uvmm); + } + mutex_unlock(&drm->clients_lock); + + return 0; +} + static const struct file_operations nouveau_pstate_fops = { .owner = THIS_MODULE, .open = nouveau_debugfs_pstate_open, @@ -214,6 +252,7 @@ static const struct file_operations nouveau_pstate_fops = { static struct drm_info_list nouveau_debugfs_list[] = { { "vbios.rom", nouveau_debugfs_vbios_image, 0, NULL }, { "strap_peek", nouveau_debugfs_strap_peek, 0, NULL }, + DRM_DEBUGFS_GPUVA_INFO(nouveau_debugfs_gpuva, NULL), }; #define NOUVEAU_DEBUGFS_ENTRIES ARRAY_SIZE(nouveau_debugfs_list) -- 2.41.0
Dave Airlie
2023-Aug-03 21:44 UTC
[Nouveau] [PATCH drm-misc-next v9 00/11] Nouveau VM_BIND UAPI & DRM GPUVA Manager (merged)
On Fri, 4 Aug 2023 at 02:52, Danilo Krummrich <dakr at redhat.com> wrote:> > This patch series provides a new UAPI for the Nouveau driver in order to > support Vulkan features, such as sparse bindings and sparse residency. >Now that Faith has reviewed the uAPI and userspace work, I think we should try and steer this in. I think the only thing I see is the SPDX + MIT header in some places, I think we can drop the MIT bits where SPDX is there, and leave copyright and authorship (if you like), personally I've been leaving authorship up to git, as it saves trouble with people randomly emailing you about things you wrote 10 years ago. Otherwise for the series: Reviewed-by: Dave Airlie <airlied at redhat.com> Dave.