Nouveau VM_BIND UAPI & DRM GPUVA Manager (merged)
Subsystems (4)
v9 cover 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 König. 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/[email protected]/
- 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
Signature · 1 line
2.41.0
PATCH v9 1/11 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.
--- include/drm/drm_gem.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-)
include/drm/drm_gem.h +9 -6
@@ -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); }/**
Signature · 1 line
2.41.0
Re: [PATCH drm-misc-next v9 01/11] drm/gem: fix lockdep check for dma-resv lock
Quoted 10 lines · On Thu, 3 Aug 2023 18:52:20 +0200 Danilo Krummrich <[email protected]> wrote:
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_mapof the GEM objects 'resv' pointer (in case no customlock_dep_mapis set yet) ondrm_gem_private_object_init().However, the GEM objects 'resv' pointer might still change after
drm_gem_private_object_init()is called, e.g. throughttm_bo_init_reserved(). This can result in the wrong lock being tracked.
Quoted 6 lines
To fix this, call
dma_resv_held()directly fromdrm_gem_gpuva_assert_lock_held()and fall back to the GEMslock_dep_mappointer only if an actual custom lock is set.Fixes e6303f323b1a ("drm: manager to keep track of GPUs VA mappings")Signed-off-by Danilo Krummrich <[email protected]>
but I'm wondering if it wouldn't be a good thing to add a drm_gem_set_resv() helper, so the core can control drm_gem_object::resv re-assignments (block them if it's happening after the GEM has been exposed to the outside world or update auxiliary data if it's happening before that).
Quoted 45 lines
--- include/drm/drm_gem.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-)include/drm/drm_gem.h +9
-6@@ -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); }/**
Re: [PATCH drm-misc-next v9 01/11] drm/gem: fix lockdep check for dma-resv lock
Quoted 20 lines · Boris Brezillon
Quoted 10 lines · On Thu, 3 Aug 2023 18:52:20 +0200 Danilo Krummrich <[email protected]> wrote:
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_mapof the GEM objects 'resv' pointer (in case no customlock_dep_mapis set yet) ondrm_gem_private_object_init().However, the GEM objects 'resv' pointer might still change after
drm_gem_private_object_init()is called, e.g. throughttm_bo_init_reserved(). This can result in the wrong lock being tracked.Quoted 6 lines
To fix this, call
dma_resv_held()directly fromdrm_gem_gpuva_assert_lock_held()and fall back to the GEMslock_dep_mappointer only if an actual custom lock is set.Fixes e6303f323b1a ("drm: manager to keep track of GPUs VA mappings")Signed-off-by Danilo Krummrich <[email protected]>
Quoted 7 lines
Reviewed-by Boris Brezillon <[email protected]>but I'm wondering if it wouldn't be a good thing to add a
drm_gem_set_resv()helper, so the core can controldrm_gem_object::resvre-assignments (block them if it's happening after the GEM has been exposed to the outside world or update auxiliary data if it's happening before that).
I agree, this might be a good idea. There are quite a few places where drm_gem_object::resv is set from external code.
Quoted 47 lines
Quoted 46 lines
--- include/drm/drm_gem.h | 15 +++++++++------ 1 file changed, 9 insertions(+), 6 deletions(-)include/drm/drm_gem.h +9
-6@@ -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); }/**
PATCH v9 2/11 drm/nouveau: new VM_BIND uapi interfaces
In reply to Danilo KrummrichThis 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.
--- Documentation/gpu/driver-uapi.rst | 8 ++ include/uapi/drm/nouveau_drm.h | 217 ++++++++++++++++++++++++++++++ 2 files changed, 225 insertions(+)
Documentation/gpu/driver-uapi.rst +8 -0
@@ -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
include/uapi/drm/nouveau_drm.h +217 -0
241 lines not on this page · raw message
Signature · 1 line
2.41.0
Re: [PATCH drm-misc-next v9 02/11] drm/nouveau: new VM_BIND uapi interfaces
Quoted 12 lines · Danilo Krummrich
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_INITioctl. UMDs can provide a kernel reserved VA area.2) Bind and unbind GPU VA space mappings via the new
DRM_IOCTL_NOUVEAU_VM_BINDioctl.3) Execute push buffers with the new
DRM_IOCTL_NOUVEAU_EXECioctl.
Quoted 9 lines
Both,
DRM_IOCTL_NOUVEAU_VM_BINDandDRM_IOCTL_NOUVEAU_EXECsupport asynchronous processing with DRM syncobjs as synchronization mechanism.The default
DRM_IOCTL_NOUVEAU_VM_BINDis synchronous processing,DRM_IOCTL_NOUVEAU_EXECsupports asynchronous processing only.Co-authored-by Dave Airlie <[email protected]>Signed-off-by Danilo Krummrich <[email protected]>
Userspace is also reviewed and sitting here:
https://gitlab.freedesktop.org/nouveau/mesa/-/merge_requests/150
I'll rev it all on top of the latest header here in a few minutes but I think the only header change was the rename for VM_INIT which shouldn't be a real problem.
~Faith
Quoted 299 lines
--- Documentation/gpu/driver-uapi.rst | 8 ++ include/uapi/drm/nouveau_drm.h | 217 ++++++++++++++++++++++++++++++ 2 files changed, 225 insertions(+)Documentation/gpu/driver-uapi.rst +8
-0@@ -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.hinclude/uapi/drm/nouveau_drm.h +13
-0@@ -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.
include/uapi/drm/nouveau_drm.h +22
-0+*/ +__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 theVM_BINDuAPI, this must be called before any BOs or
+ * channels are created; if called afterwardsDRM_IOCTL_NOUVEAU_VM_INITfails
+ * with-ENOSYS.
+ */include/uapi/drm/nouveau_drm.h +3
-0+struct drm_nouveau_vm_init { +/** +* @kernel_managed_addr: start address of the kernel managed VA space
include/uapi/drm/nouveau_drm.h +5
-0+* region +*/ +__u64 kernel_managed_addr; +/** +* @kernel_managed_size: size of the kernel managed VA space region in
include/uapi/drm/nouveau_drm.h +10
-0+* 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.
+ */include/uapi/drm/nouveau_drm.h +10
-0+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.
+ */include/uapi/drm/nouveau_drm.h +5
-0+#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_SPARSEmust be set.
+ */include/uapi/drm/nouveau_drm.h +23
-0+#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
include/uapi/drm/nouveau_drm.h +28
-0+*/ +__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_syncobjects.
+ */include/uapi/drm/nouveau_drm.h +7
-0+#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
include/uapi/drm/nouveau_drm.h +20
-0+*/ +__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_ptrfield.
+ */include/uapi/drm/nouveau_drm.h +29
-0+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
include/uapi/drm/nouveau_drm.h +21
-0+*/ +__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, structdrm_nouveau_vm_bind)
+#defineDRM_IOCTL_NOUVEAU_EXECDRM_IOWR(DRM_COMMAND_BASE +DRM_NOUVEAU_EXEC, structdrm_nouveau_exec)
#ifdefined(__cplusplus)
}
#endif
--
2.41.0
PATCH v9 3/11 drm/nouveau: get vmm via nouveau_cli_vmm()
In reply to Danilo KrummrichProvide 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.
--- 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(-)
drivers/gpu/drm/nouveau/nouveau_bo.c +1 -1
@@ -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) {
drivers/gpu/drm/nouveau/nouveau_chan.c +1 -1
@@ -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 */
drivers/gpu/drm/nouveau/nouveau_drv.h +9 -0
@@ -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 *);
drivers/gpu/drm/nouveau/nouveau_gem.c +3 -3
@@ -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))
Signature · 1 line
2.41.0
PATCH v9 4/11 drm/nouveau: bo: initialize GEM GPU VA interface
In reply to Danilo KrummrichInitialize the GEM's DRM GPU VA manager interface in preparation for the (u)vmm implementation, provided by subsequent commits, to make use of it.
--- drivers/gpu/drm/nouveau/nouveau_bo.c | 3 +++ 1 file changed, 3 insertions(+)
drivers/gpu/drm/nouveau/nouveau_bo.c +3 -0
@@ -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().
Signature · 1 line
2.41.0
PATCH v9 5/11 drm/nouveau: move usercopy helpers to nouveau_drv.h
In reply to Danilo KrummrichMove the usercopy helpers to a common driver header file to make it usable for the new API added in subsequent commits.
--- drivers/gpu/drm/nouveau/nouveau_drv.h | 26 ++++++++++++++++++++++++++ drivers/gpu/drm/nouveau/nouveau_gem.c | 26 -------------------------- 2 files changed, 26 insertions(+), 26 deletions(-)
drivers/gpu/drm/nouveau/nouveau_drv.h +26 -0
@@ -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>
drivers/gpu/drm/nouveau/nouveau_gem.c +0 -26
@@ -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,
Signature · 1 line
2.41.0
PATCH v9 6/11 drm/nouveau: fence: separate fence alloc and emit
In reply to Danilo KrummrichThe 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.
--- 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(-)
drivers/gpu/drm/nouveau/dispnv04/crtc.c +8 -1
@@ -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);
drivers/gpu/drm/nouveau/nouveau_bo.c +31 -21
60 lines not on this page · raw message
drivers/gpu/drm/nouveau/nouveau_chan.c +4 -2
@@ -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); }
drivers/gpu/drm/nouveau/nouveau_dmem.c +6 -3
@@ -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);
drivers/gpu/drm/nouveau/nouveau_fence.c +5 -11
@@ -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)
drivers/gpu/drm/nouveau/nouveau_fence.h +1 -2
@@ -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 *);
drivers/gpu/drm/nouveau/nouveau_gem.c +4 -1
@@ -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;
Signature · 1 line
2.41.0
Re: [PATCH drm-misc-next v9 06/11] drm/nouveau: fence: separate fence alloc and emit
Am 03.08.23 um 18:52 schrieb Danilo Krummrich:
Quoted 4 lines
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 schedulersrun_job()callback) we need to separate fence allocation and fence emitting.
At least from the description that sounds like it might be illegal. Daniel can you take a look as well.
What exactly are you doing here?
Regards,
Christian.
Quoted 226 lines
Signed-off-by Danilo Krummrich <[email protected]>--- 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(-)drivers/gpu/drm/nouveau/dispnv04/crtc.c +8
-1@@ -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);drivers/gpu/drm/nouveau/nouveau_bo.c +31
-21@@ -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; }drivers/gpu/drm/nouveau/nouveau_chan.c +4
-2@@ -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); }drivers/gpu/drm/nouveau/nouveau_dmem.c +6
-3@@ -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);drivers/gpu/drm/nouveau/nouveau_fence.c +5
-11@@ -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)drivers/gpu/drm/nouveau/nouveau_fence.h +1
-2@@ -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 *);drivers/gpu/drm/nouveau/nouveau_gem.c +4
-1@@ -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;
Re: [PATCH drm-misc-next v9 06/11] drm/nouveau: fence: separate fence alloc and emit
Hi Christian,
Quoted 9 lines · Christian König
Am 03.08.23 um 18:52 schrieb Danilo Krummrich:
Quoted 4 lines
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 schedulersrun_job()callback) we need to separate fence allocation and fence emitting.At least from the description that sounds like it might be illegal. Daniel can you take a look as well.
What exactly are you doing here?
I'm basically doing exactly the same as amdgpu_fence_emit() does in amdgpu_ib_schedule() called by amdgpu_job_run().
The difference - and this is what this patch is for - is that I separate the fence allocation from emitting the fence, such that the fence structure is allocated before the job is submitted to the GPU scheduler. amdgpu solves this with GFP_ATOMIC within amdgpu_fence_emit() to allocate the fence structure in this case.
- Danilo
Quoted 224 lines
Regards,
Christian.Quoted 219 lines
Signed-off-by Danilo Krummrich <[email protected]>---
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(-)drivers/gpu/drm/nouveau/dispnv04/crtc.c +8
-1@@ -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);drivers/gpu/drm/nouveau/nouveau_bo.c +0
-0@@ -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_cleanupsomehow 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)
+ gotoout_unlock;drivers/gpu/drm/nouveau/nouveau_bo.c +13
-0+ + 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;}
drivers/gpu/drm/nouveau/nouveau_bo.c +15
-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); + +out_unlock:
mutex_unlock(&cli->mutex);
return ret;
}drivers/gpu/drm/nouveau/nouveau_chan.c +4
-2@@ -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); }drivers/gpu/drm/nouveau/nouveau_dmem.c +6
-3@@ -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(structnouveau_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);drivers/gpu/drm/nouveau/nouveau_fence.c +3
-0@@ -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
drivers/gpu/drm/nouveau/nouveau_fence.c +1
-2-nouveau_fence_new(struct nouveau_channel *chan, bool sysmem, - struct nouveau_fence **pfence) +nouveau_fence_new(struct nouveau_fence **pfence){
structnouveau_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(structdma_fence*fence)drivers/gpu/drm/nouveau/nouveau_fence.h +1
-2@@ -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 *);drivers/gpu/drm/nouveau/nouveau_gem.c +4
-1@@ -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;
Re: [PATCH drm-misc-next v9 06/11] drm/nouveau: fence: separate fence alloc and emit
Am 07.08.23 um 20:54 schrieb Danilo Krummrich:
Quoted 9 lines
Hi Christian,
Quoted 6 lines · Christian König
Am 03.08.23 um 18:52 schrieb Danilo Krummrich:
Quoted 4 lines
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 schedulersrun_job()callback) we need to separate fence allocation and fence emitting.
Quoted 7 lines
Quoted 3 lines
At least from the description that sounds like it might be illegal. Daniel can you take a look as well.
What exactly are you doing here?
I'm basically doing exactly the same as
amdgpu_fence_emit()does inamdgpu_ib_schedule()called byamdgpu_job_run().The difference - and this is what this patch is for - is that I separate the fence allocation from emitting the fence, such that the fence structure is allocated before the job is submitted to the GPU scheduler. amdgpu solves this with
GFP_ATOMICwithinamdgpu_fence_emit()to allocate the fence structure in this case.
Yeah, that use case is perfectly valid. Maybe update the commit message a bit to better describe that.
Something like "Separate fence allocation and emitting to avoid allocation within DMA fence signalling critical sections inside the DRM scheduler. This helps implementing the new UAPI....".
Regards,
Christian.
Quoted 231 lines
- Danilo
Quoted 227 lines
Regards,
Christian.Quoted 222 lines
Signed-off-by Danilo Krummrich <[email protected]>---
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(-)drivers/gpu/drm/nouveau/dispnv04/crtc.c +8
-1@@ -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);drivers/gpu/drm/nouveau/nouveau_bo.c +0
-0@@ -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_cleanupsomehow 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)
+ gotoout_unlock;drivers/gpu/drm/nouveau/nouveau_bo.c +13
-0+ + 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;}
drivers/gpu/drm/nouveau/nouveau_bo.c +15
-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); + +out_unlock:
mutex_unlock(&cli->mutex);
return ret;
}drivers/gpu/drm/nouveau/nouveau_chan.c +4
-2@@ -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); }drivers/gpu/drm/nouveau/nouveau_dmem.c +6
-3@@ -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(structnouveau_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);drivers/gpu/drm/nouveau/nouveau_fence.c +3
-0@@ -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
drivers/gpu/drm/nouveau/nouveau_fence.c +1
-2-nouveau_fence_new(struct nouveau_channel *chan, bool sysmem, - struct nouveau_fence **pfence) +nouveau_fence_new(struct nouveau_fence **pfence){
structnouveau_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(structdma_fence*fence)drivers/gpu/drm/nouveau/nouveau_fence.h +1
-2@@ -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 *);drivers/gpu/drm/nouveau/nouveau_gem.c +4
-1@@ -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;
PATCH v9 7/11 drm/nouveau: fence: fail to emit when fence context is killed
In reply to Danilo KrummrichThe 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.
--- drivers/gpu/drm/nouveau/nouveau_fence.c | 7 +++++++ drivers/gpu/drm/nouveau/nouveau_fence.h | 2 +- 2 files changed, 8 insertions(+), 1 deletion(-)
drivers/gpu/drm/nouveau/nouveau_fence.c +7 -0
@@ -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);
drivers/gpu/drm/nouveau/nouveau_fence.h +1 -1
@@ -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 {
Signature · 1 line
2.41.0
PATCH v9 8/11 drm/nouveau: chan: provide nouveau_channel_kill()
In reply to Danilo KrummrichThe 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.
--- drivers/gpu/drm/nouveau/nouveau_chan.c | 14 +++++++++++--- drivers/gpu/drm/nouveau/nouveau_chan.h | 1 + 2 files changed, 12 insertions(+), 3 deletions(-)
drivers/gpu/drm/nouveau/nouveau_chan.c +11 -3
@@ -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 ; }
drivers/gpu/drm/nouveau/nouveau_chan.h +1 -0
@@ -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;
Signature · 1 line
2.41.0
PATCH v9 9/11 drm/nouveau: nvkm/vmm: implement raw ops to manage uvmm
In reply to Danilo KrummrichThe 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.
--- 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(-)
drivers/gpu/drm/nouveau/include/nvif/if000c.h +25 -1
@@ -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;
drivers/gpu/drm/nouveau/include/nvif/vmm.h +17 -2
@@ -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
drivers/gpu/drm/nouveau/include/nvkm/subdev/mmu.h +19 -1
@@ -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;
drivers/gpu/drm/nouveau/nouveau_svm.c +1 -1
@@ -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,
drivers/gpu/drm/nouveau/nouveau_vmm.c +2 -2
@@ -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;
drivers/gpu/drm/nouveau/nvif/vmm.c +97 -3
120 lines not on this page · raw message
drivers/gpu/drm/nouveau/nvkm/subdev/mmu/uvmm.c +195 -18
324 lines not on this page · raw message
drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.c +152 -45
306 lines not on this page · raw message
drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmm.h +25 -0
@@ -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
drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgf100.c +9 -7
@@ -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 ;
drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmgp100.c +9 -7
@@ -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 ;
drivers/gpu/drm/nouveau/nvkm/subdev/mmu/vmmnv50.c +15 -12
@@ -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; + } } }
Signature · 1 line
2.41.0
PATCH v9 10/11 drm/nouveau: implement new VM_BIND uAPI
In reply to Danilo KrummrichThis 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.
--- 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
Documentation/gpu/driver-uapi.rst +3 -0
@@ -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
drivers/gpu/drm/nouveau/Kbuild +3 -0
@@ -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
drivers/gpu/drm/nouveau/Kconfig +2 -0
@@ -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
drivers/gpu/drm/nouveau/nouveau_abi16.c +24 -0
@@ -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 )
drivers/gpu/drm/nouveau/nouveau_abi16.h +1 -0
@@ -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 {
drivers/gpu/drm/nouveau/nouveau_bo.c +109 -59
229 lines not on this page · raw message
drivers/gpu/drm/nouveau/nouveau_bo.h +2 -1
@@ -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,
drivers/gpu/drm/nouveau/nouveau_drm.c +25 -2
@@ -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,
drivers/gpu/drm/nouveau/nouveau_drv.h +56 -2
98 lines not on this page · raw message
drivers/gpu/drm/nouveau/nouveau_exec.c new file +436 -0
436 lines not on this page · raw message
drivers/gpu/drm/nouveau/nouveau_exec.h new file +54 -0
54 lines not on this page · raw message
drivers/gpu/drm/nouveau/nouveau_gem.c +44 -5
125 lines not on this page · raw message
drivers/gpu/drm/nouveau/nouveau_gem.h +2 -1
@@ -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
drivers/gpu/drm/nouveau/nouveau_mem.h +5 -0
@@ -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
drivers/gpu/drm/nouveau/nouveau_prime.c +12 -1
@@ -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); +}
drivers/gpu/drm/nouveau/nouveau_sched.c new file +444 -0
444 lines not on this page · raw message
drivers/gpu/drm/nouveau/nouveau_sched.h new file +127 -0
127 lines not on this page · raw message
drivers/gpu/drm/nouveau/nouveau_uvmm.c new file +1946 -0
1,271 lines not on this page · raw message
drivers/gpu/drm/nouveau/nouveau_uvmm.h new file +108 -0
108 lines not on this page · raw message
The rest of this diff is not shown. View the raw message.
Signature · 1 line
2.41.0
Part of the diff is not shown here. View the raw message.
PATCH v9 11/11 drm/nouveau: debugfs: implement DRM GPU VA debugfs
In reply to Danilo KrummrichProvide the driver indirection iterating over all DRM GPU VA spaces to enable the common 'gpuvas' debugfs file for dumping DRM GPU VA spaces.
--- drivers/gpu/drm/nouveau/nouveau_debugfs.c | 39 +++++++++++++++++++++++ 1 file changed, 39 insertions(+)
drivers/gpu/drm/nouveau/nouveau_debugfs.c +39 -0
@@ -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)
Signature · 1 line
2.41.0
Quoted 4 lines · Danilo Krummrich
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:
Dave.
Quoted 9 lines · Dave Airlie
Quoted 4 lines · Danilo Krummrich
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.
Quoted 9 lines
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 <[email protected]>
FYI: There's a small, easily resolved conflict with the uapi fixup patch. I don't care too much which goes in first but I'd like both to land before I merge NVK so I don't have to deal with a nouveau_deprecated.h.
~Faith
Quoted 2 lines
Dave.