diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2026-06-17 10:21:00 +0100 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2026-06-17 10:21:00 +0100 |
| commit | 4b99990cdf9560e8a071640baf19f312e6ae02f4 (patch) | |
| tree | ba3c58e860666130caf5ae3bf386b6dbfbe59b04 /rust/kernel | |
| parent | 9c87e61e3c5797277407ba5eae4eac8a52be3fa3 (diff) | |
| parent | 52d4ab1ca790a668cc8f2c27017138b1c467168c (diff) | |
Merge tag 'drm-next-2026-06-17' of https://gitlab.freedesktop.org/drm/kernel
Pull drm updates from Dave Airlie:
"Highlights:
- xe: add initial CRI platform support
- amdgpu: initial HDMI 2.1 FRL support
- rust: add some new type concepts for device lifetimes
- scheduler: moves to a fair algorithm and lots of cleanups
But it's mostly the usual mountain of changes across the board.
core:
- add docbook for DRM_IOCTL_SYNCOBJ_EVENTFD
- change signature of drm_connector_attach_hdr_output_metadata_property
- dedup counter and timestamp retrieval in vblank code
- parse AMD VSDB v3 in CTA extension blocks
- add P230, Y7, XYYY2101010, T430, XVUY210101010 formats
- don't call drop master on file close if not master
- use drm_printf_indent in atomic / bridge
- fix 32b format descriptions
- docs: fix toctree
- hdmi: add common TMDS character rates
- fix drm_syncobj_find_fence leak
rust:
- introduce Higher-Ranked lifetime types
- replace drvdata with scoped registration data
- add GPUVM immediate mode abstraction for rust GPU drivers
- introduce DeviceContext type state for drm::Device
bridge:
- clarify drm_bridge_get/put
- create drm_get_bridge_by_endpoint and use it
- analogix_dp: add panel probing
- ite-it6211 - use drm audio hdmi helpers
buddy:
- add lockdep annotations
dp:
- add PR and VRR updates
- mst: fix buffer overflows
- add Adaptive Sync SDP decoding support
- fix OOB reads in dp-mst
ttm:
- bump fpfn/lpfn to 64-bit
scheduler:
- change default to fair scheduler
- map runqueue 1:1 with scheduler
dma-buf:
- port selftests to kunit
- convert dma-buf system/heap allocators to module
- add separate DMABUF_HEAPS_SYSTEM_CC_SHARED Kconfig
udmabuf:
- revert hugetlb support
- fix error with CONFIG_DMA_API_DEBUG
dma-fence:
- fix tracepoints lifetime
- remove unused signal on any support
ras:
- add clear error counter netlink command to drm ras
gpusvm:
- reject VMAs with VM_IO or VM_PFNMAP when creating SVM ranges
- use IOVA allocations
pagemap:
- use IOVA allocations
panels:
- update to use ref counts
- add support for CSW PNB601LS1-2, LGD LP116WHA-SPB1
- add support for waveshare panels
- CMN N116BCN-EA1, CMN N140HCA-EEK, IVO M140NWFQ R5,
- IVO, R140NWFW R0, BOE NT140*, BOE NV133FHM-N4F,
- AUO B140*, AUO B133HAN06.6 and AUO B116XTN02.3 eDP panels
- Surface Pro 12 Panel
xe:
- add CRI PCI-IDs
- debugfs add multi-lrc info
- engine init cleanup
- PF fair scheduling auto provisioning
- system controller support for CRI/Xe3p
- PXP state machine fixes
- Reset/wedge/unload corner case fixes
- Wedge path memory allocation fixes
- PAT type cleanups
- Reject unsafe PAT for CPU cached memory
- OA improvements for CRI device memory
- kernel doc syntax in xe headers
- xe_drm.h documentation fixes
- include guard cleanups
- VF CCS memory pool
- i915/xe step unification
- Xe3p GT tuning fixes
- forcewake cleanup in GT and GuC
- admin-only PF mode
- enable hwmon energy attributes for CRI
- enable GT_MI_USER_INTERRUPT
- refactor emit functions
- oa workarounds
- multi_queue: allow QUEUE_TIMESTAMP register
- convert stolen memory to ttm range manager
- use xe2 style blitter as a feature flag
- make drm_driver const
- add/use IRQ page to HW engine definition
- fix oops when display disabled
i915:
- enable PIPEDMC_ERROR interrupt
- more common display code refactoring
- restructure DP/HDMI sink format handling
- eliminate FB usage from lowlevel pinning code
- panel replay bw optimization
- integrate sharpness filter into the scaler
- new fb_pin abstraction for xe/i915 fb transparent handling
- skip inactive MST connectors on HDCP
- start switching to display specific registers
- use polling when irq unavailable
- Adaptive-sync SDP prep
amdgpu:
- use drm_display_info for AMD VSDB data
- Initial HDMI 2.1 FRL support
- Initial DCN 4.2.1 support
- GART fixes for non-4k pages
- GC 11.5.6/SDMA 6.4.0/and other new IPs
- GFX9/DCE6/Hawaii/SDMA4/GART/Userq fixes
- Finish support for using multiple SDMA queues for TTM operations
- SWSMU updates
- GC 12.1 updates
- SMU 15.0.8 updates
- DCN 4.2 updates
- DC type conversion fixes
- Enable DC power module
- Replay/PSR updates
- SMU 13.x updates
- Compute queue quantum MQD updates
- ASPM fix
- Align VKMS with common implementation
- DC analog support fixes
- UVD 3 fixes
- TCC harvesting fixes for SI
- GC 11 APU module reload fix
- NBIO 6.3.2 support
- IH 7.1 updates
- DC cursor fixes
- VCN/JPEG user fence fixes
- DC support for connectors without DDC
- Prefer ROM BAR for default VGA device
- DC bandwidth fixes
- Add PTL support for profiler
- Introduce dc_plane_cm and migrate surface update color path
- Add FRL registers for HDMI 2.1
- Restructure VM state machine
- Auxless ALPM support
- GEM_OP locking/warning fixes
- switch to system_dfl_wq
amdkfd:
- GPUVM TLB flush fix
- Hotplug fix
- Boundary check fixes
- SVM fixes
- CRIU fixes
- add profiler API
- MES 12.1 updates
msm:
- core:
- fix shrinker documentation
- IFPC enabled for gen8
- PERFCNTR_CONFIG ioctl support
- GPU:
- reworked UBWC handling
- a810 support
- MDSS:
- add support for Milos platform
- reworked UBWC handling
- DisplayPort:
- reworked HPD handling as prep for MST
- DPU:
- Milos platform support
- reworked UBWC handling
- DSI:
- Milos platform support
nova:
- Hopper/Blackwell enablement (GH100/GB100/GB202)
- FSP support
- 32-bit firmware support
- HAL functions
- refactor GSP boot/unload
- GA100 support
- VBIOS hardening/refactoring
- Adopt higher order lifetime types
tyr:
- define register blocks
- add shmem backed GEM objects
- adopt higher order lifetime types
- move clock cleanup into Drop
radeon:
- Hawaii SMU fixes
- CS parser fix
- use struct drm_edid instead of edid
amdxdna:
- export per-client BO memory via fdinfo
- AIE4 device support
- support medium/lower power modes
- expandable device heap support
- revert read-only user-pointer BO mappings
ivpu:
- support frequency limiting
panthor:
- enable GEM shrinker support
- add eviction and reclaim info to fdinfo
v3d:
- enable runtime PM
mgag200:
- support XRGB1555 + C8
ast:
- support XRGB1555 + C8
- use constants for lots of registers
- fix register handling
imagination:
- fence handling refactoring
nouveau:
- fix sched double call
- expose VBIOS on GSP-RM systems
- add GA100 support
virtio:
- add VIRTIO_GPU_F_BLOB_ALIGNMENT flag
- add deferred mapping support
gud:
- add RCade Display Adapter
hibmc:
- fix no connectors usage
mediatek:
- hdmi: convert error handling
- simplify mtk_crtc allocation
exynos:
- move fbdev emulation to drm client buffers
- use drm format helpers for geometry/size
- adopt core DMA tracking
- fix framebuffer offset handling
renesas:
- add RZ/T2H SOC support
versilicon:
- add cursor plane support
tegra:
- use drm client for framebuffer"
* tag 'drm-next-2026-06-17' of https://gitlab.freedesktop.org/drm/kernel: (1731 commits)
dma-buf: move system_cc_shared heap under separate Kconfig
accel/amdxdna: Clear sva pointer after unbind
agp/amd64: Fix broken error propagation in agp_amd64_probe()
accel/amdxdna: Require carveout when PASID and force_iova are disabled
drm/amdkfd: always resume_all after suspend_all
drm/amdgpu/gfx: move fault and EOP IRQ get/put to hw_init/hw_fini
drm/amd/display: Consult MCCS FreeSync cap only if requested & supported
drm/amd/pm: Use strscpy in profile mode parsing
drm/amdkfd: Fix infinite loop parsing CRAT with zero subtype length
drm/amdkfd: fix sysfs topology prop length on buffer truncation
drm/amdgpu: drop retry loop in amdgpu_hmm_range_get_pages
drm/amd/pm: bound OD parameter parsing to stack array size
drm/amd/pm: Stop pp_od_clk_voltage emit at PAGE_SIZE
drm/amdkfd: Unwind debug trap enable on copy_to_user failure
drm/amdgpu: validate the mes firmware version for gfx12.1
drm/amdgpu: validate the mes firmware version for gfx12
drm/amdgpu: compare MES firmware version ucode for gfx11
drm/amdkfd: Add bounds check for AMDKFD_IOC_WAIT_EVENTS
drm/amdgpu: restart the CS if some parts of the VM are still invalidated
drm/amd/display: use unsigned types for local pipe and REG_GET counters
...
Diffstat (limited to 'rust/kernel')
| -rw-r--r-- | rust/kernel/drm/device.rs | 252 | ||||
| -rw-r--r-- | rust/kernel/drm/driver.rs | 49 | ||||
| -rw-r--r-- | rust/kernel/drm/gem/mod.rs | 72 | ||||
| -rw-r--r-- | rust/kernel/drm/gem/shmem.rs | 61 | ||||
| -rw-r--r-- | rust/kernel/drm/gpuvm/mod.rs | 328 | ||||
| -rw-r--r-- | rust/kernel/drm/gpuvm/sm_ops.rs | 429 | ||||
| -rw-r--r-- | rust/kernel/drm/gpuvm/va.rs | 168 | ||||
| -rw-r--r-- | rust/kernel/drm/gpuvm/vm_bo.rs | 249 | ||||
| -rw-r--r-- | rust/kernel/drm/mod.rs | 5 |
9 files changed, 1501 insertions, 112 deletions
diff --git a/rust/kernel/drm/device.rs b/rust/kernel/drm/device.rs index 403fc35353c7..477cf771fb10 100644 --- a/rust/kernel/drm/device.rs +++ b/rust/kernel/drm/device.rs @@ -6,10 +6,12 @@ use crate::{ alloc::allocator::Kmalloc, - bindings, device, + bindings, + device, drm::{ self, - driver::AllocImpl, // + driver::AllocImpl, + private::Sealed, // }, error::from_err_ptr, prelude::*, @@ -17,16 +19,20 @@ use crate::{ ARef, AlwaysRefCounted, // }, - types::Opaque, + types::{ + NotThreadSafe, + Opaque, // + }, workqueue::{ HasDelayedWork, HasWork, Work, WorkItem, // - }, + }, // }; use core::{ alloc::Layout, + marker::PhantomData, mem, ops::Deref, ptr::{ @@ -66,36 +72,122 @@ macro_rules! drm_legacy_fields { } } -/// A typed DRM device with a specific `drm::Driver` implementation. +/// A trait implemented by all possible contexts a [`Device`] can be used in. +/// +/// Setting up a new [`Device`] is a multi-stage process. Each step of the process that a user +/// interacts with in Rust has a respective [`DeviceContext`] typestate. For example, +/// `Device<T, Registered>` would be a [`Device`] that reached the [`Registered`] [`DeviceContext`]. +/// +/// Each stage of this process is described below: +/// +/// ```text +/// 1 2 3 +/// +--------------+ +------------------+ +-----------------------+ +/// |Device created| → |Device initialized| → |Registered w/ userspace| +/// +--------------+ +------------------+ +-----------------------+ +/// (Uninit) (Registered) +/// ``` +/// +/// 1. The [`Device`] is in the [`Uninit`] context and is not guaranteed to be initialized or +/// registered with userspace. Only a limited subset of DRM core functionality is available. +/// 2. The [`Device`] is guaranteed to be fully initialized, but is not guaranteed to be registered +/// with userspace. All DRM core functionality which doesn't interact with userspace is +/// available. We currently don't have a context for representing this. +/// 3. The [`Device`] is guaranteed to be fully initialized, and is guaranteed to have been +/// registered with userspace at some point - thus putting it in the [`Registered`] context. +/// +/// An important caveat of [`DeviceContext`] which must be kept in mind: when used as a typestate +/// for a reference type, it can only guarantee that a [`Device`] reached a particular stage in the +/// initialization process _at the time the reference was taken_. No guarantee is made in regards to +/// what stage of the process the [`Device`] is currently in. This means for instance that a +/// `&Device<T, Uninit>` may actually be registered with userspace, it just wasn't known to be +/// registered at the time the reference was taken. +pub trait DeviceContext: Sealed + Send + Sync {} + +/// The [`DeviceContext`] of a [`Device`] that was registered with userspace at some point. /// -/// The device is always reference-counted. +/// This represents a [`Device`] which is guaranteed to have been registered with userspace at +/// some point in time. Such a DRM device is guaranteed to have been fully-initialized. +/// +/// Note: A device in this context is not guaranteed to remain registered with userspace for its +/// entire lifetime, as this is impossible to guarantee at compile-time. /// /// # Invariants /// -/// `self.dev` is a valid instance of a `struct device`. -#[repr(C)] -pub struct Device<T: drm::Driver> { - dev: Opaque<bindings::drm_device>, - data: T::Data, +/// A [`Device`] in this [`DeviceContext`] is guaranteed to have been registered with userspace +/// at some point in time. +pub struct Registered; + +impl Sealed for Registered {} +impl DeviceContext for Registered {} + +/// The [`DeviceContext`] of a [`Device`] that may be unregistered and partly uninitialized. +/// +/// A [`Device`] in this context is only guaranteed to be partly initialized, and may or may not +/// be registered with userspace. Thus operations which depend on the [`Device`] being fully +/// initialized, or which depend on the [`Device`] being registered with userspace are not +/// available through this [`DeviceContext`]. +/// +/// A [`Device`] in this context can be used to create a +/// [`Registration`](drm::driver::Registration). +pub struct Uninit; + +impl Sealed for Uninit {} +impl DeviceContext for Uninit {} + +/// A [`Device`] which is known at compile-time to be unregistered with userspace. +/// +/// This type allows performing operations which are only safe to do before userspace registration, +/// and can be used to create a [`Registration`](drm::driver::Registration) once the driver is ready +/// to register the device with userspace. +/// +/// Since DRM device initialization must be single-threaded, this object is not thread-safe. +/// +/// # Invariants +/// +/// The device in `self.0` is guaranteed to be a newly created [`Device`] that has not yet been +/// registered with userspace until this type is dropped. +pub struct UnregisteredDevice<T: drm::Driver>(ARef<Device<T, Uninit>>, NotThreadSafe); + +impl<T: drm::Driver> Deref for UnregisteredDevice<T> { + type Target = Device<T, Uninit>; + + fn deref(&self) -> &Self::Target { + &self.0 + } } -impl<T: drm::Driver> Device<T> { +impl<T: drm::Driver> UnregisteredDevice<T> { + const fn compute_features() -> u32 { + let mut features = drm::driver::FEAT_GEM; + + if T::FEAT_RENDER { + features |= drm::driver::FEAT_RENDER; + } + + features + } + const VTABLE: bindings::drm_driver = drm_legacy_fields! { load: None, open: Some(drm::File::<T::File>::open_callback), postclose: Some(drm::File::<T::File>::postclose_callback), unload: None, - release: Some(Self::release), + release: Some(Device::<T>::release), master_set: None, master_drop: None, debugfs_init: None, - gem_create_object: T::Object::ALLOC_OPS.gem_create_object, - prime_handle_to_fd: T::Object::ALLOC_OPS.prime_handle_to_fd, - prime_fd_to_handle: T::Object::ALLOC_OPS.prime_fd_to_handle, - gem_prime_import: T::Object::ALLOC_OPS.gem_prime_import, - gem_prime_import_sg_table: T::Object::ALLOC_OPS.gem_prime_import_sg_table, - dumb_create: T::Object::ALLOC_OPS.dumb_create, - dumb_map_offset: T::Object::ALLOC_OPS.dumb_map_offset, + + // Ignore the Uninit DeviceContext below. It is only provided because it is required by the + // compiler, and it is not actually used by these functions. + gem_create_object: T::Object::<Uninit>::ALLOC_OPS.gem_create_object, + prime_handle_to_fd: T::Object::<Uninit>::ALLOC_OPS.prime_handle_to_fd, + prime_fd_to_handle: T::Object::<Uninit>::ALLOC_OPS.prime_fd_to_handle, + gem_prime_import: T::Object::<Uninit>::ALLOC_OPS.gem_prime_import, + gem_prime_import_sg_table: T::Object::<Uninit>::ALLOC_OPS.gem_prime_import_sg_table, + dumb_create: T::Object::<Uninit>::ALLOC_OPS.dumb_create, + dumb_map_offset: T::Object::<Uninit>::ALLOC_OPS.dumb_map_offset, + show_fdinfo: None, fbdev_probe: None, @@ -105,7 +197,7 @@ impl<T: drm::Driver> Device<T> { name: crate::str::as_char_ptr_in_const_context(T::INFO.name).cast_mut(), desc: crate::str::as_char_ptr_in_const_context(T::INFO.desc).cast_mut(), - driver_features: drm::driver::FEAT_GEM, + driver_features: Self::compute_features(), ioctls: T::IOCTLS.as_ptr(), num_ioctls: T::IOCTLS.len() as i32, fops: &Self::GEM_FOPS, @@ -113,11 +205,13 @@ impl<T: drm::Driver> Device<T> { const GEM_FOPS: bindings::file_operations = drm::gem::create_fops(); - /// Create a new `drm::Device` for a `drm::Driver`. - pub fn new(dev: &device::Device, data: impl PinInit<T::Data, Error>) -> Result<ARef<Self>> { + /// Create a new `UnregisteredDevice` for a `drm::Driver`. + /// + /// This can be used to create a [`Registration`](kernel::drm::Registration). + pub fn new(dev: &device::Device, data: impl PinInit<T::Data, Error>) -> Result<Self> { // `__drm_dev_alloc` uses `kmalloc()` to allocate memory, hence ensure a `kmalloc()` // compatible `Layout`. - let layout = Kmalloc::aligned_layout(Layout::new::<Self>()); + let layout = Kmalloc::aligned_layout(Layout::new::<Device<T, Uninit>>()); // Use a temporary vtable without a `release` callback until `data` is initialized, so // init failure can release the DRM device without dropping uninitialized fields. @@ -129,12 +223,12 @@ impl<T: drm::Driver> Device<T> { // SAFETY: // - `alloc_vtable` reference remains valid until no longer used, // - `dev` is valid by its type invarants, - let raw_drm: *mut Self = unsafe { + let raw_drm: *mut Device<T, Uninit> = unsafe { bindings::__drm_dev_alloc( dev.as_raw(), &alloc_vtable, layout.size(), - mem::offset_of!(Self, dev), + mem::offset_of!(Device<T, Uninit>, dev), ) } .cast(); @@ -142,7 +236,7 @@ impl<T: drm::Driver> Device<T> { // SAFETY: `raw_drm` is a valid pointer to `Self`, given that `__drm_dev_alloc` was // successful. - let drm_dev = unsafe { Self::into_drm_device(raw_drm) }; + let drm_dev = unsafe { Device::into_drm_device(raw_drm) }; // SAFETY: `raw_drm` is a valid pointer to `Self`. let raw_data = unsafe { ptr::addr_of_mut!((*raw_drm.as_ptr()).data) }; @@ -161,9 +255,39 @@ impl<T: drm::Driver> Device<T> { // SAFETY: The reference count is one, and now we take ownership of that reference as a // `drm::Device`. - Ok(unsafe { ARef::from_raw(raw_drm) }) + // INVARIANT: We just created the device above, but have yet to call `drm_dev_register`. + // `Self` cannot be copied or sent to another thread - ensuring that `drm_dev_register` + // won't be called during its lifetime and that the device is unregistered. + Ok(Self(unsafe { ARef::from_raw(raw_drm) }, NotThreadSafe)) } +} +/// A typed DRM device with a specific [`drm::Driver`] implementation and [`DeviceContext`]. +/// +/// Since DRM devices can be used before being fully initialized and registered with userspace, `C` +/// represents the furthest [`DeviceContext`] we can guarantee that this [`Device`] has reached. +/// +/// Keep in mind: this means that an unregistered device can still have the registration state +/// [`Registered`] as long as it was registered with userspace once in the past, and that the +/// behavior of such a device is still well-defined. Additionally, a device with the registration +/// state [`Uninit`] simply does not have a guaranteed registration state at compile time, and could +/// be either registered or unregistered. Since there is no way to guarantee a long-lived reference +/// to an unregistered device would remain unregistered, we do not provide a [`DeviceContext`] for +/// this. +/// +/// # Invariants +/// +/// * `self.dev` is a valid instance of a `struct device`. +/// * The data layout of `Self` remains the same across all implementations of `C`. +/// * Any invariants for `C` also apply. +#[repr(C)] +pub struct Device<T: drm::Driver, C: DeviceContext = Registered> { + dev: Opaque<bindings::drm_device>, + data: T::Data, + _ctx: PhantomData<C>, +} + +impl<T: drm::Driver, C: DeviceContext> Device<T, C> { pub(crate) fn as_raw(&self) -> *mut bindings::drm_device { self.dev.get() } @@ -189,13 +313,13 @@ impl<T: drm::Driver> Device<T> { /// /// # Safety /// - /// Callers must ensure that `ptr` is valid, non-null, and has a non-zero reference count, - /// i.e. it must be ensured that the reference count of the C `struct drm_device` `ptr` points - /// to can't drop to zero, for the duration of this function call and the entire duration when - /// the returned reference exists. - /// - /// Additionally, callers must ensure that the `struct device`, `ptr` is pointing to, is - /// embedded in `Self`. + /// * Callers must ensure that `ptr` is valid, non-null, and has a non-zero reference count, + /// i.e. it must be ensured that the reference count of the C `struct drm_device` `ptr` points + /// to can't drop to zero, for the duration of this function call and the entire duration when + /// the returned reference exists. + /// * Additionally, callers must ensure that the `struct device`, `ptr` is pointing to, is + /// embedded in `Self`. + /// * Callers promise that any type invariants of `C` will be upheld. #[doc(hidden)] pub unsafe fn from_raw<'a>(ptr: *const bindings::drm_device) -> &'a Self { // SAFETY: By the safety requirements of this function `ptr` is a valid pointer to a @@ -215,9 +339,20 @@ impl<T: drm::Driver> Device<T> { // - `this` is valid for dropping. unsafe { core::ptr::drop_in_place(this) }; } + + /// Change the [`DeviceContext`] for a [`Device`]. + /// + /// # Safety + /// + /// The caller promises that `self` fulfills all of the guarantees provided by the given + /// [`DeviceContext`]. + pub(crate) unsafe fn assume_ctx<NewCtx: DeviceContext>(&self) -> &Device<T, NewCtx> { + // SAFETY: The data layout is identical via our type invariants. + unsafe { mem::transmute(self) } + } } -impl<T: drm::Driver> Deref for Device<T> { +impl<T: drm::Driver, C: DeviceContext> Deref for Device<T, C> { type Target = T::Data; fn deref(&self) -> &Self::Target { @@ -227,7 +362,7 @@ impl<T: drm::Driver> Deref for Device<T> { // SAFETY: DRM device objects are always reference counted and the get/put functions // satisfy the requirements. -unsafe impl<T: drm::Driver> AlwaysRefCounted for Device<T> { +unsafe impl<T: drm::Driver, C: DeviceContext> AlwaysRefCounted for Device<T, C> { fn inc_ref(&self) { // SAFETY: The existence of a shared reference guarantees that the refcount is non-zero. unsafe { bindings::drm_dev_get(self.as_raw()) }; @@ -242,7 +377,7 @@ unsafe impl<T: drm::Driver> AlwaysRefCounted for Device<T> { } } -impl<T: drm::Driver> AsRef<device::Device> for Device<T> { +impl<T: drm::Driver, C: DeviceContext> AsRef<device::Device> for Device<T, C> { fn as_ref(&self) -> &device::Device { // SAFETY: `bindings::drm_device::dev` is valid as long as the DRM device itself is valid, // which is guaranteed by the type invariant. @@ -251,21 +386,22 @@ impl<T: drm::Driver> AsRef<device::Device> for Device<T> { } // SAFETY: A `drm::Device` can be released from any thread. -unsafe impl<T: drm::Driver> Send for Device<T> {} +unsafe impl<T: drm::Driver, C: DeviceContext> Send for Device<T, C> {} // SAFETY: A `drm::Device` can be shared among threads because all immutable methods are protected // by the synchronization in `struct drm_device`. -unsafe impl<T: drm::Driver> Sync for Device<T> {} +unsafe impl<T: drm::Driver, C: DeviceContext> Sync for Device<T, C> {} -impl<T, const ID: u64> WorkItem<ID> for Device<T> +impl<T, C, const ID: u64> WorkItem<ID> for Device<T, C> where T: drm::Driver, - T::Data: WorkItem<ID, Pointer = ARef<Device<T>>>, - T::Data: HasWork<Device<T>, ID>, + T::Data: WorkItem<ID, Pointer = ARef<Self>>, + T::Data: HasWork<Self, ID>, + C: DeviceContext, { - type Pointer = ARef<Device<T>>; + type Pointer = ARef<Self>; - fn run(ptr: ARef<Device<T>>) { + fn run(ptr: ARef<Self>) { T::Data::run(ptr); } } @@ -277,40 +413,42 @@ where // stored inline in `drm::Device`, so the `container_of` call is valid. // // - The two methods are true inverses of each other: given `ptr: *mut -// Device<T>`, `raw_get_work` will return a `*mut Work<Device<T>, ID>` through -// `T::Data::raw_get_work` and given a `ptr: *mut Work<Device<T>, ID>`, -// `work_container_of` will return a `*mut Device<T>` through `container_of`. -unsafe impl<T, const ID: u64> HasWork<Device<T>, ID> for Device<T> +// Device<T, C>`, `raw_get_work` will return a `*mut Work<Device<T, C>, ID>` through +// `T::Data::raw_get_work` and given a `ptr: *mut Work<Device<T, C>, ID>`, +// `work_container_of` will return a `*mut Device<T, C>` through `container_of`. +unsafe impl<T, C, const ID: u64> HasWork<Self, ID> for Device<T, C> where T: drm::Driver, - T::Data: HasWork<Device<T>, ID>, + T::Data: HasWork<Self, ID>, + C: DeviceContext, { - unsafe fn raw_get_work(ptr: *mut Self) -> *mut Work<Device<T>, ID> { - // SAFETY: The caller promises that `ptr` points to a valid `Device<T>`. + unsafe fn raw_get_work(ptr: *mut Self) -> *mut Work<Self, ID> { + // SAFETY: The caller promises that `ptr` points to a valid `Device<T, C>`. let data_ptr = unsafe { &raw mut (*ptr).data }; // SAFETY: `data_ptr` is a valid pointer to `T::Data`. unsafe { T::Data::raw_get_work(data_ptr) } } - unsafe fn work_container_of(ptr: *mut Work<Device<T>, ID>) -> *mut Self { + unsafe fn work_container_of(ptr: *mut Work<Self, ID>) -> *mut Self { // SAFETY: The caller promises that `ptr` points at a `Work` field in // `T::Data`. let data_ptr = unsafe { T::Data::work_container_of(ptr) }; - // SAFETY: `T::Data` is stored as the `data` field in `Device<T>`. + // SAFETY: `T::Data` is stored as the `data` field in `Device<T, C>`. unsafe { crate::container_of!(data_ptr, Self, data) } } } // SAFETY: Our `HasWork<T, ID>` implementation returns a `work_struct` that is // stored in the `work` field of a `delayed_work` with the same access rules as -// the `work_struct` owing to the bound on `T::Data: HasDelayedWork<Device<T>, +// the `work_struct` owing to the bound on `T::Data: HasDelayedWork<Device<T, C>, // ID>`, which requires that `T::Data::raw_get_work` return a `work_struct` that // is inside a `delayed_work`. -unsafe impl<T, const ID: u64> HasDelayedWork<Device<T>, ID> for Device<T> +unsafe impl<T, C, const ID: u64> HasDelayedWork<Self, ID> for Device<T, C> where T: drm::Driver, - T::Data: HasDelayedWork<Device<T>, ID>, + T::Data: HasDelayedWork<Self, ID>, + C: DeviceContext, { } diff --git a/rust/kernel/drm/driver.rs b/rust/kernel/drm/driver.rs index 5233bdebc9fc..25f7e233884d 100644 --- a/rust/kernel/drm/driver.rs +++ b/rust/kernel/drm/driver.rs @@ -13,9 +13,15 @@ use crate::{ prelude::*, sync::aref::ARef, // }; +use core::{ + mem, + ptr::NonNull, // +}; /// Driver use the GEM memory manager. This should be set for all modern drivers. pub(crate) const FEAT_GEM: u32 = bindings::drm_driver_feature_DRIVER_GEM; +/// Driver supports render nodes, i.e.: /dev/dri/renderDXX devices. +pub(crate) const FEAT_RENDER: u32 = bindings::drm_driver_feature_DRIVER_RENDER; /// Information data for a DRM Driver. pub struct DriverInfo { @@ -105,7 +111,7 @@ pub trait Driver { type Data: Sync + Send; /// The type used to manage memory for this driver. - type Object: AllocImpl; + type Object<Ctx: drm::DeviceContext>: AllocImpl; /// The type used to represent a DRM File (client) type File: drm::file::DriverFile; @@ -115,6 +121,16 @@ pub trait Driver { /// IOCTL list. See `kernel::drm::ioctl::declare_drm_ioctls!{}`. const IOCTLS: &'static [drm::ioctl::DrmIoctlDescriptor]; + + /// Sets the `DRIVER_RENDER` feature for this driver. + /// + /// When enabled, the driver exposes `/dev/dri/renderDXX` render nodes to + /// userspace. The render node is an alternate low-priviledge way to access + /// the driver, which is enforced on a per-ioctl level. Userspace processes + /// that open the render node can only invoke ioctls explicitly listed as + /// usable from the render node (i.e. marked DRM_RENDER_ALLOW), whereas + /// userspace processes using the master node can invoke any ioctl. + const FEAT_RENDER: bool = false; } /// The registration type of a `drm::Device`. @@ -123,21 +139,31 @@ pub trait Driver { pub struct Registration<T: Driver>(ARef<drm::Device<T>>); impl<T: Driver> Registration<T> { - fn new(drm: &drm::Device<T>, flags: usize) -> Result<Self> { + fn new(drm: drm::UnregisteredDevice<T>, flags: usize) -> Result<Self> { // SAFETY: `drm.as_raw()` is valid by the invariants of `drm::Device`. to_result(unsafe { bindings::drm_dev_register(drm.as_raw(), flags) })?; - Ok(Self(drm.into())) + // SAFETY: We just called `drm_dev_register` above + let new = NonNull::from(unsafe { drm.assume_ctx() }); + + // Leak the ARef from UnregisteredDevice in preparation for transferring its ownership. + mem::forget(drm); + + // SAFETY: `drm`'s `Drop` constructor was never called, ensuring that there remains at least + // one reference to the device - which we take ownership over here. + let new = unsafe { ARef::from_raw(new) }; + + Ok(Self(new)) } - /// Registers a new [`Device`](drm::Device) with userspace. + /// Registers a new [`UnregisteredDevice`](drm::UnregisteredDevice) with userspace. /// /// Ownership of the [`Registration`] object is passed to [`devres::register`]. - pub fn new_foreign_owned( - drm: &drm::Device<T>, - dev: &device::Device<device::Bound>, + pub fn new_foreign_owned<'a>( + drm: drm::UnregisteredDevice<T>, + dev: &'a device::Device<device::Bound>, flags: usize, - ) -> Result + ) -> Result<&'a drm::Device<T>> where T: 'static, { @@ -146,8 +172,13 @@ impl<T: Driver> Registration<T> { } let reg = Registration::<T>::new(drm, flags)?; + let drm = NonNull::from(reg.device()); + + devres::register(dev, reg, GFP_KERNEL)?; - devres::register(dev, reg, GFP_KERNEL) + // SAFETY: Since `reg` was passed to devres::register(), the device now owns the lifetime + // of the DRM registration - ensuring that this references lives for at least as long as 'a. + Ok(unsafe { drm.as_ref() }) } /// Returns a reference to the `Device` instance for this registration. diff --git a/rust/kernel/drm/gem/mod.rs b/rust/kernel/drm/gem/mod.rs index 01b5bd47a333..c8b66d816871 100644 --- a/rust/kernel/drm/gem/mod.rs +++ b/rust/kernel/drm/gem/mod.rs @@ -8,6 +8,10 @@ use crate::{ bindings, drm::{ self, + device::{ + DeviceContext, + Registered, // + }, driver::{ AllocImpl, AllocOps, // @@ -22,6 +26,7 @@ use crate::{ types::Opaque, }; use core::{ + marker::PhantomData, ops::Deref, ptr::NonNull, // }; @@ -73,6 +78,12 @@ pub(crate) use impl_aref_for_gem_obj; /// [`DriverFile`]: drm::file::DriverFile pub type DriverFile<T> = drm::File<<<T as DriverObject>::Driver as drm::Driver>::File>; +/// A type alias for retrieving the current [`AllocImpl`] for a given [`DriverObject`]. +/// +/// [`Driver`]: drm::Driver +pub type DriverAllocImpl<T, Ctx = Registered> = + <<T as DriverObject>::Driver as drm::Driver>::Object<Ctx>; + /// GEM object functions, which must be implemented by drivers. pub trait DriverObject: Sync + Send + Sized { /// Parent `Driver` for this object. @@ -82,19 +93,19 @@ pub trait DriverObject: Sync + Send + Sized { type Args; /// Create a new driver data object for a GEM object of a given size. - fn new( - dev: &drm::Device<Self::Driver>, + fn new<Ctx: DeviceContext>( + dev: &drm::Device<Self::Driver, Ctx>, size: usize, args: Self::Args, ) -> impl PinInit<Self, Error>; /// Open a new handle to an existing object, associated with a File. - fn open(_obj: &<Self::Driver as drm::Driver>::Object, _file: &DriverFile<Self>) -> Result { + fn open(_obj: &DriverAllocImpl<Self>, _file: &DriverFile<Self>) -> Result { Ok(()) } /// Close a handle to an existing object, associated with a File. - fn close(_obj: &<Self::Driver as drm::Driver>::Object, _file: &DriverFile<Self>) {} + fn close(_obj: &DriverAllocImpl<Self>, _file: &DriverFile<Self>) {} } /// Trait that represents a GEM object subtype @@ -120,9 +131,12 @@ extern "C" fn open_callback<T: DriverObject>( // SAFETY: `open_callback` is only ever called with a valid pointer to a `struct drm_file`. let file = unsafe { DriverFile::<T>::from_raw(raw_file) }; - // SAFETY: `open_callback` is specified in the AllocOps structure for `DriverObject<T>`, - // ensuring that `raw_obj` is contained within a `DriverObject<T>` - let obj = unsafe { <<T::Driver as drm::Driver>::Object as IntoGEMObject>::from_raw(raw_obj) }; + // SAFETY: + // * `open_callback` is specified in the AllocOps structure for `DriverObject`, ensuring that + // `raw_obj` is contained within a `DriverAllocImpl<T>` + // * It is only possible for `open_callback` to be called after device registration, ensuring + // that the object's device is in the `Registered` state. + let obj: &DriverAllocImpl<T> = unsafe { IntoGEMObject::from_raw(raw_obj) }; match T::open(obj, file) { Err(e) => e.to_errno(), @@ -139,12 +153,12 @@ extern "C" fn close_callback<T: DriverObject>( // SAFETY: `close_callback` is specified in the AllocOps structure for `Object<T>`, ensuring // that `raw_obj` is indeed contained within a `Object<T>`. - let obj = unsafe { <<T::Driver as drm::Driver>::Object as IntoGEMObject>::from_raw(raw_obj) }; + let obj: &DriverAllocImpl<T> = unsafe { IntoGEMObject::from_raw(raw_obj) }; T::close(obj, file); } -impl<T: DriverObject> IntoGEMObject for Object<T> { +impl<T: DriverObject, Ctx: DeviceContext> IntoGEMObject for Object<T, Ctx> { fn as_raw(&self) -> *mut bindings::drm_gem_object { self.obj.get() } @@ -152,7 +166,7 @@ impl<T: DriverObject> IntoGEMObject for Object<T> { unsafe fn from_raw<'a>(self_ptr: *mut bindings::drm_gem_object) -> &'a Self { // SAFETY: `obj` is guaranteed to be in an `Object<T>` via the safety contract of this // function - unsafe { &*crate::container_of!(Opaque::cast_from(self_ptr), Object<T>, obj) } + unsafe { &*crate::container_of!(Opaque::cast_from(self_ptr), Object<T, Ctx>, obj) } } } @@ -169,7 +183,7 @@ pub trait BaseObject: IntoGEMObject { fn create_handle<D, F>(&self, file: &drm::File<F>) -> Result<u32> where Self: AllocImpl<Driver = D>, - D: drm::Driver<Object = Self, File = F>, + D: drm::Driver<Object<Registered> = Self, File = F>, F: drm::file::DriverFile<Driver = D>, { let mut handle: u32 = 0; @@ -184,7 +198,7 @@ pub trait BaseObject: IntoGEMObject { fn lookup_handle<D, F>(file: &drm::File<F>, handle: u32) -> Result<ARef<Self>> where Self: AllocImpl<Driver = D>, - D: drm::Driver<Object = Self, File = F>, + D: drm::Driver<Object<Registered> = Self, File = F>, F: drm::file::DriverFile<Driver = D>, { // SAFETY: The arguments are all valid per the type invariants. @@ -236,16 +250,18 @@ impl<T: IntoGEMObject> BaseObjectPrivate for T {} /// /// # Invariants /// -/// - `self.obj` is a valid instance of a `struct drm_gem_object`. +/// * `self.obj` is a valid instance of a `struct drm_gem_object`. +/// * Any type invariants of `Ctx` apply to the parent DRM device for this GEM object. #[repr(C)] #[pin_data] -pub struct Object<T: DriverObject + Send + Sync> { +pub struct Object<T: DriverObject + Send + Sync, Ctx: DeviceContext = Registered> { obj: Opaque<bindings::drm_gem_object>, #[pin] data: T, + _ctx: PhantomData<Ctx>, } -impl<T: DriverObject> Object<T> { +impl<T: DriverObject, Ctx: DeviceContext> Object<T, Ctx> { const OBJECT_FUNCS: bindings::drm_gem_object_funcs = bindings::drm_gem_object_funcs { free: Some(Self::free_callback), open: Some(open_callback::<T>), @@ -265,11 +281,16 @@ impl<T: DriverObject> Object<T> { }; /// Create a new GEM object. - pub fn new(dev: &drm::Device<T::Driver>, size: usize, args: T::Args) -> Result<ARef<Self>> { + pub fn new( + dev: &drm::Device<T::Driver, Ctx>, + size: usize, + args: T::Args, + ) -> Result<ARef<Self>> { let obj: Pin<KBox<Self>> = KBox::pin_init( try_pin_init!(Self { obj: Opaque::new(bindings::drm_gem_object::default()), data <- T::new(dev, size, args), + _ctx: PhantomData, }), GFP_KERNEL, )?; @@ -277,6 +298,8 @@ impl<T: DriverObject> Object<T> { // SAFETY: `obj.as_raw()` is guaranteed to be valid by the initialization above. unsafe { (*obj.as_raw()).funcs = &Self::OBJECT_FUNCS }; + // INVARIANT: `dev` and the GEM object are in the same state at the moment, and upgrading + // the typestate in `dev` will not carry over to the GEM object. if let Err(err) = // SAFETY: The arguments are all valid per the type invariants. to_result(unsafe { @@ -300,13 +323,15 @@ impl<T: DriverObject> Object<T> { } /// Returns the `Device` that owns this GEM object. - pub fn dev(&self) -> &drm::Device<T::Driver> { + pub fn dev(&self) -> &drm::Device<T::Driver, Ctx> { // SAFETY: // - `struct drm_gem_object.dev` is initialized and valid for as long as the GEM // object lives. // - The device we used for creating the gem object is passed as &drm::Device<T::Driver> to // Object::<T>::new(), so we know that `T::Driver` is the right generic parameter to use // here. + // - Any type invariants of `Ctx` are upheld by using the same `Ctx` for the `Device` we + // return. unsafe { drm::Device::from_raw((*self.as_raw()).dev) } } @@ -331,11 +356,16 @@ impl<T: DriverObject> Object<T> { } } -impl_aref_for_gem_obj!(impl<T> for Object<T> where T: DriverObject); +impl_aref_for_gem_obj! { + impl<T, C> for Object<T, C> + where + T: DriverObject, + C: DeviceContext +} -impl<T: DriverObject> super::private::Sealed for Object<T> {} +impl<T: DriverObject, Ctx: DeviceContext> super::private::Sealed for Object<T, Ctx> {} -impl<T: DriverObject> Deref for Object<T> { +impl<T: DriverObject, Ctx: DeviceContext> Deref for Object<T, Ctx> { type Target = T; fn deref(&self) -> &Self::Target { @@ -343,7 +373,7 @@ impl<T: DriverObject> Deref for Object<T> { } } -impl<T: DriverObject> AllocImpl for Object<T> { +impl<T: DriverObject, Ctx: DeviceContext> AllocImpl for Object<T, Ctx> { type Driver = T::Driver; const ALLOC_OPS: AllocOps = AllocOps { diff --git a/rust/kernel/drm/gem/shmem.rs b/rust/kernel/drm/gem/shmem.rs index e1b648920d2f..34af402899a0 100644 --- a/rust/kernel/drm/gem/shmem.rs +++ b/rust/kernel/drm/gem/shmem.rs @@ -12,10 +12,12 @@ use crate::{ container_of, drm::{ - device, driver, gem, - private::Sealed, // + private::Sealed, + Device, + DeviceContext, + Registered, // }, error::to_result, prelude::*, @@ -23,11 +25,12 @@ use crate::{ types::Opaque, // }; use core::{ + marker::PhantomData, ops::{ Deref, DerefMut, // }, - ptr::NonNull, + ptr::NonNull, // }; use gem::{ BaseObjectPrivate, @@ -40,42 +43,49 @@ use gem::{ /// This is used with [`Object::new()`] to control various properties that can only be set when /// initially creating a shmem-backed GEM object. #[derive(Default)] -pub struct ObjectConfig<'a, T: DriverObject> { +pub struct ObjectConfig<'a, T: DriverObject, C: DeviceContext = Registered> { /// Whether to set the write-combine map flag. pub map_wc: bool, /// Reuse the DMA reservation from another GEM object. /// /// The newly created [`Object`] will hold an owned refcount to `parent_resv_obj` if specified. - pub parent_resv_obj: Option<&'a Object<T>>, + pub parent_resv_obj: Option<&'a Object<T, C>>, } /// A shmem-backed GEM object. /// /// # Invariants /// -/// `obj` contains a valid initialized `struct drm_gem_shmem_object` for the lifetime of this -/// object. +/// - `obj` contains a valid initialized `struct drm_gem_shmem_object` for the lifetime of this +/// object. +/// - Any type invariants of `C` apply to the parent DRM device for this GEM object. #[repr(C)] #[pin_data] -pub struct Object<T: DriverObject> { +pub struct Object<T: DriverObject, C: DeviceContext = Registered> { #[pin] obj: Opaque<bindings::drm_gem_shmem_object>, /// Parent object that owns this object's DMA reservation object. - parent_resv_obj: Option<ARef<Object<T>>>, + parent_resv_obj: Option<ARef<Object<T, C>>>, #[pin] inner: T, + _ctx: PhantomData<C>, } -super::impl_aref_for_gem_obj!(impl<T> for Object<T> where T: DriverObject); +super::impl_aref_for_gem_obj! { + impl<T, C> for Object<T, C> + where + T: DriverObject, + C: DeviceContext +} // SAFETY: All GEM objects are thread-safe. -unsafe impl<T: DriverObject> Send for Object<T> {} +unsafe impl<T: DriverObject, C: DeviceContext> Send for Object<T, C> {} // SAFETY: All GEM objects are thread-safe. -unsafe impl<T: DriverObject> Sync for Object<T> {} +unsafe impl<T: DriverObject, C: DeviceContext> Sync for Object<T, C> {} -impl<T: DriverObject> Object<T> { +impl<T: DriverObject, C: DeviceContext> Object<T, C> { /// `drm_gem_object_funcs` vtable suitable for GEM shmem objects. const VTABLE: bindings::drm_gem_object_funcs = bindings::drm_gem_object_funcs { free: Some(Self::free_callback), @@ -106,9 +116,9 @@ impl<T: DriverObject> Object<T> { /// /// Additional config options can be specified using `config`. pub fn new( - dev: &device::Device<T::Driver>, + dev: &Device<T::Driver, C>, size: usize, - config: ObjectConfig<'_, T>, + config: ObjectConfig<'_, T, C>, args: T::Args, ) -> Result<ARef<Self>> { let new: Pin<KBox<Self>> = KBox::try_pin_init( @@ -116,6 +126,7 @@ impl<T: DriverObject> Object<T> { obj <- Opaque::init_zeroed(), parent_resv_obj: config.parent_resv_obj.map(|p| p.into()), inner <- T::new(dev, size, args), + _ctx: PhantomData::<C>, }), GFP_KERNEL, )?; @@ -148,9 +159,9 @@ impl<T: DriverObject> Object<T> { } /// Returns the `Device` that owns this GEM object. - pub fn dev(&self) -> &device::Device<T::Driver> { + pub fn dev(&self) -> &Device<T::Driver, C> { // SAFETY: `dev` will have been initialized in `Self::new()` by `drm_gem_shmem_init()`. - unsafe { device::Device::from_raw((*self.as_raw()).dev) } + unsafe { Device::from_raw((*self.as_raw()).dev) } } extern "C" fn free_callback(obj: *mut bindings::drm_gem_object) { @@ -168,7 +179,7 @@ impl<T: DriverObject> Object<T> { // SAFETY: // - We verified above that `obj` is valid, which makes `this` valid // - This function is set in AllocOps, so we know that `this` is contained within a - // `Object<T>` + // `Object<T, C>` let this = unsafe { container_of!(Opaque::cast_from(this), Self, obj) }.cast_mut(); // SAFETY: We're recovering the Kbox<> we created in gem_create_object() @@ -176,7 +187,7 @@ impl<T: DriverObject> Object<T> { } } -impl<T: DriverObject> Deref for Object<T> { +impl<T: DriverObject, C: DeviceContext> Deref for Object<T, C> { type Target = T; fn deref(&self) -> &Self::Target { @@ -184,15 +195,15 @@ impl<T: DriverObject> Deref for Object<T> { } } -impl<T: DriverObject> DerefMut for Object<T> { +impl<T: DriverObject, C: DeviceContext> DerefMut for Object<T, C> { fn deref_mut(&mut self) -> &mut Self::Target { &mut self.inner } } -impl<T: DriverObject> Sealed for Object<T> {} +impl<T: DriverObject, C: DeviceContext> Sealed for Object<T, C> {} -impl<T: DriverObject> gem::IntoGEMObject for Object<T> { +impl<T: DriverObject, C: DeviceContext> gem::IntoGEMObject for Object<T, C> { fn as_raw(&self) -> *mut bindings::drm_gem_object { // SAFETY: // - Our immutable reference is proof that this is safe to dereference. @@ -200,18 +211,18 @@ impl<T: DriverObject> gem::IntoGEMObject for Object<T> { unsafe { &raw mut (*self.obj.get()).base } } - unsafe fn from_raw<'a>(obj: *mut bindings::drm_gem_object) -> &'a Object<T> { + unsafe fn from_raw<'a>(obj: *mut bindings::drm_gem_object) -> &'a Self { // SAFETY: The safety contract of from_gem_obj() guarantees that `obj` is contained within // `Self` unsafe { let obj = Opaque::cast_from(container_of!(obj, bindings::drm_gem_shmem_object, base)); - &*container_of!(obj, Object<T>, obj) + &*container_of!(obj, Self, obj) } } } -impl<T: DriverObject> driver::AllocImpl for Object<T> { +impl<T: DriverObject, C: DeviceContext> driver::AllocImpl for Object<T, C> { type Driver = T::Driver; const ALLOC_OPS: driver::AllocOps = driver::AllocOps { diff --git a/rust/kernel/drm/gpuvm/mod.rs b/rust/kernel/drm/gpuvm/mod.rs new file mode 100644 index 000000000000..ae58f6f667c1 --- /dev/null +++ b/rust/kernel/drm/gpuvm/mod.rs @@ -0,0 +1,328 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT + +#![cfg(CONFIG_RUST_DRM_GPUVM)] + +//! DRM GPUVM in immediate mode +//! +//! Rust abstractions for using GPUVM in immediate mode. This is when the GPUVM state is updated +//! during `run_job()`, i.e., in the DMA fence signalling critical path, to ensure that the GPUVM +//! and the GPU's virtual address space has the same state at all times. +//! +//! C header: [`include/drm/drm_gpuvm.h`](srctree/include/drm/drm_gpuvm.h) + +use kernel::{ + alloc::{ + AllocError, + Flags as AllocFlags, // + }, + bindings, + drm, + drm::gem::IntoGEMObject, + error::to_result, + prelude::*, + sync::aref::{ + ARef, + AlwaysRefCounted, // + }, + types::Opaque, // +}; + +use core::{ + cell::UnsafeCell, + marker::PhantomData, + mem::{ + ManuallyDrop, + MaybeUninit, // + }, + ops::{ + Deref, + DerefMut, + Range, // + }, + ptr::{ + self, + NonNull, // + }, // +}; + +mod sm_ops; +pub use self::sm_ops::*; + +mod vm_bo; +pub use self::vm_bo::*; + +mod va; +pub use self::va::*; + +/// A DRM GPU VA manager. +/// +/// This object is refcounted, but the locations of mapped ranges may only be accessed or changed +/// via the special unique handle [`UniqueRefGpuVm`]. +/// +/// # Invariants +/// +/// * Stored in an allocation managed by the refcount in `self.vm`. +/// * Access to `data` and the gpuvm interval tree is controlled via the [`UniqueRefGpuVm`] type. +/// * Does not contain any sparse [`GpuVa<T>`] instances. +#[pin_data] +pub struct GpuVm<T: DriverGpuVm> { + #[pin] + vm: Opaque<bindings::drm_gpuvm>, + /// Accessed only through the [`UniqueRefGpuVm`] reference. + data: UnsafeCell<T>, +} + +// SAFETY: The GPUVM api does not assume that it is tied to a specific thread. The destructor will +// drop the `data` field, which is okay because it is guaranteed `Send` by the `DriverGpuVm` trait. +unsafe impl<T: DriverGpuVm> Send for GpuVm<T> {} +// SAFETY: The GPUVM api is designed to allow &self methods to be called in parallel. +unsafe impl<T: DriverGpuVm> Sync for GpuVm<T> {} + +// SAFETY: By type invariants, the allocation is managed by the refcount in `self.vm`. +unsafe impl<T: DriverGpuVm> AlwaysRefCounted for GpuVm<T> { + fn inc_ref(&self) { + // SAFETY: By type invariants, the allocation is managed by the refcount in `self.vm`. + unsafe { bindings::drm_gpuvm_get(self.vm.get()) }; + } + + unsafe fn dec_ref(obj: NonNull<Self>) { + // SAFETY: By type invariants, the allocation is managed by the refcount in `self.vm`. + unsafe { bindings::drm_gpuvm_put((*obj.as_ptr()).vm.get()) }; + } +} + +impl<T: DriverGpuVm> PartialEq for GpuVm<T> { + #[inline] + fn eq(&self, other: &Self) -> bool { + core::ptr::eq(self.as_raw(), other.as_raw()) + } +} +impl<T: DriverGpuVm> Eq for GpuVm<T> {} + +impl<T: DriverGpuVm> GpuVm<T> { + const fn vtable() -> &'static bindings::drm_gpuvm_ops { + &bindings::drm_gpuvm_ops { + vm_free: Some(Self::vm_free), + op_alloc: None, + op_free: None, + vm_bo_alloc: GpuVmBo::<T>::ALLOC_FN, + vm_bo_free: GpuVmBo::<T>::FREE_FN, + vm_bo_validate: None, + sm_step_map: Some(Self::sm_step_map), + sm_step_unmap: Some(Self::sm_step_unmap), + sm_step_remap: Some(Self::sm_step_remap), + } + } + + /// Creates a GPUVM instance. + #[expect(clippy::new_ret_no_self)] + pub fn new<E>( + name: &'static CStr, + dev: &drm::Device<T::Driver>, + r_obj: &T::Object, + range: Range<u64>, + reserve_range: Range<u64>, + data: T, + ) -> Result<UniqueRefGpuVm<T>, E> + where + E: From<AllocError>, + E: From<core::convert::Infallible>, + { + let obj = KBox::try_pin_init::<E>( + try_pin_init!(Self { + data: UnsafeCell::new(data), + vm <- Opaque::ffi_init(|vm| { + // SAFETY: These arguments are valid. `vm` is valid until refcount drops to + // zero. The `vm` is zeroed before calling this method by `__GFP_ZERO` flag + // below. + unsafe { + bindings::drm_gpuvm_init( + vm, + name.as_char_ptr(), + bindings::drm_gpuvm_flags_DRM_GPUVM_IMMEDIATE_MODE + | bindings::drm_gpuvm_flags_DRM_GPUVM_RESV_PROTECTED, + dev.as_raw(), + r_obj.as_raw(), + range.start, + range.end - range.start, + reserve_range.start, + reserve_range.end - reserve_range.start, + const { Self::vtable() }, + ) + } + }), + }? E), + GFP_KERNEL | __GFP_ZERO, + )?; + // SAFETY: This transfers the initial refcount to the ARef. + let aref = unsafe { + ARef::from_raw(NonNull::new_unchecked(KBox::into_raw( + Pin::into_inner_unchecked(obj), + ))) + }; + // INVARIANT: This reference is unique. + Ok(UniqueRefGpuVm(aref)) + } + + /// Access this [`GpuVm`] from a raw pointer. + /// + /// # Safety + /// + /// The pointer must reference the `struct drm_gpuvm` in a valid [`GpuVm<T>`] that remains + /// valid for at least `'a`. + #[inline] + pub unsafe fn from_raw<'a>(ptr: *mut bindings::drm_gpuvm) -> &'a Self { + // SAFETY: Caller passes a pointer to the `drm_gpuvm` in a `GpuVm<T>`. Caller ensures the + // pointer is valid for 'a. + unsafe { &*kernel::container_of!(Opaque::cast_from(ptr), Self, vm) } + } + + /// Returns a raw pointer to the embedded `struct drm_gpuvm`. + #[inline] + pub fn as_raw(&self) -> *mut bindings::drm_gpuvm { + self.vm.get() + } + + /// The start of the VA space. + #[inline] + pub fn va_start(&self) -> u64 { + // SAFETY: The `mm_start` field is immutable. + unsafe { (*self.as_raw()).mm_start } + } + + /// The length of the GPU's virtual address space. + #[inline] + pub fn va_length(&self) -> u64 { + // SAFETY: The `mm_range` field is immutable. + unsafe { (*self.as_raw()).mm_range } + } + + /// Returns the range of the GPU virtual address space. + #[inline] + pub fn va_range(&self) -> Range<u64> { + let start = self.va_start(); + // OVERFLOW: This reconstructs the Range<u64> passed to the constructor, so it won't fail. + let end = start + self.va_length(); + Range { start, end } + } + + /// Get or create the [`GpuVmBo`] for this gem object. + #[inline] + pub fn obtain( + &self, + obj: &T::Object, + data: impl PinInit<T::VmBoData>, + ) -> Result<ARef<GpuVmBo<T>>, AllocError> { + Ok(GpuVmBoAlloc::new(self, obj, data)?.obtain()) + } + + /// Clean up buffer objects that are no longer used. + #[inline] + pub fn deferred_cleanup(&self) { + // SAFETY: This GPUVM uses immediate mode. + unsafe { bindings::drm_gpuvm_bo_deferred_cleanup(self.as_raw()) } + } + + /// Check if this GEM object is an external object for this GPUVM. + #[inline] + pub fn is_extobj(&self, obj: &T::Object) -> bool { + // SAFETY: We may call this with any GPUVM and GEM object. + unsafe { bindings::drm_gpuvm_is_extobj(self.as_raw(), obj.as_raw()) } + } + + /// Free this GPUVM. + /// + /// # Safety + /// + /// Called when refcount hits zero. + unsafe extern "C" fn vm_free(me: *mut bindings::drm_gpuvm) { + // SAFETY: Caller passes a pointer to the `drm_gpuvm` in a `GpuVm<T>`. + let me = unsafe { kernel::container_of!(Opaque::cast_from(me), Self, vm).cast_mut() }; + // SAFETY: By type invariants we can free it when refcount hits zero. + drop(unsafe { KBox::from_raw(me) }) + } + + #[inline] + fn raw_resv(&self) -> *mut bindings::dma_resv { + // SAFETY: `r_obj` is immutable and valid for duration of GPUVM. + unsafe { (*(*self.as_raw()).r_obj).resv } + } +} + +/// The manager for a GPUVM. +pub trait DriverGpuVm: Sized + Send { + /// Parent `Driver` for this object. + type Driver: drm::Driver<Object = Self::Object>; + + /// The kind of GEM object stored in this GPUVM. + type Object: IntoGEMObject; + + /// Data stored with each [`struct drm_gpuva`](struct@GpuVa). + type VaData; + + /// Data stored with each [`struct drm_gpuvm_bo`](struct@GpuVmBo). + type VmBoData; + + /// The private data passed to callbacks. + type SmContext<'ctx>; + + /// Indicates that a new mapping should be created. + fn sm_step_map<'op, 'ctx>( + &mut self, + op: OpMap<'op, Self>, + context: &mut Self::SmContext<'ctx>, + ) -> Result<OpMapped<'op, Self>, Error>; + + /// Indicates that an existing mapping should be removed. + fn sm_step_unmap<'op, 'ctx>( + &mut self, + op: OpUnmap<'op, Self>, + context: &mut Self::SmContext<'ctx>, + ) -> Result<OpUnmapped<'op, Self>, Error>; + + /// Indicates that an existing mapping should be split up. + fn sm_step_remap<'op, 'ctx>( + &mut self, + op: OpRemap<'op, Self>, + context: &mut Self::SmContext<'ctx>, + ) -> Result<OpRemapped<'op, Self>, Error>; +} + +/// The core of the DRM GPU VA manager. +/// +/// This object is a unique reference to the VM that can access the interval tree and the Rust +/// `data` field. +/// +/// # Invariants +/// +/// Each `GpuVm` instance has at most one `UniqueRefGpuVm` reference. +pub struct UniqueRefGpuVm<T: DriverGpuVm>(ARef<GpuVm<T>>); + +// SAFETY: The GPUVM api is designed to allow &self methods to be called in parallel, and +// concurrent access to `data` is safe due to the `T: Sync` requirement. +unsafe impl<T: DriverGpuVm + Sync> Sync for UniqueRefGpuVm<T> {} + +impl<T: DriverGpuVm> UniqueRefGpuVm<T> { + /// Access the data owned by this `UniqueRefGpuVm` immutably. + #[inline] + pub fn data_ref(&self) -> &T { + // SAFETY: By the type invariants we may access `data`. + unsafe { &*self.0.data.get() } + } + + /// Access the data owned by this `UniqueRefGpuVm` mutably. + #[inline] + pub fn data(&mut self) -> &mut T { + // SAFETY: By the type invariants we may access `data`. + unsafe { &mut *self.0.data.get() } + } +} + +impl<T: DriverGpuVm> Deref for UniqueRefGpuVm<T> { + type Target = GpuVm<T>; + + #[inline] + fn deref(&self) -> &GpuVm<T> { + &self.0 + } +} diff --git a/rust/kernel/drm/gpuvm/sm_ops.rs b/rust/kernel/drm/gpuvm/sm_ops.rs new file mode 100644 index 000000000000..69a8e5ab2821 --- /dev/null +++ b/rust/kernel/drm/gpuvm/sm_ops.rs @@ -0,0 +1,429 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT + +use super::*; + +/// The actual data that gets threaded through the callbacks. +struct SmData<'a, 'ctx, T: DriverGpuVm> { + gpuvm: &'a mut UniqueRefGpuVm<T>, + user_context: &'a mut T::SmContext<'ctx>, +} + +/// Adds an extra field to `SmData` for `sm_map()` callbacks. +/// +/// # Invariants +/// +/// `self.vm_bo.gpuvm() == self.sm_data.gpuvm`. +#[repr(C)] +struct SmMapData<'a, 'ctx, T: DriverGpuVm> { + sm_data: SmData<'a, 'ctx, T>, + vm_bo: &'a GpuVmBo<T>, +} + +/// The argument for [`UniqueRefGpuVm::sm_map`]. +pub struct OpMapRequest<'a, 'ctx, T: DriverGpuVm> { + /// Address in GPU virtual address space. + pub addr: u64, + /// Length of mapping to create. + pub range: u64, + /// Offset in GEM object. + pub gem_offset: u64, + /// The GEM object to map. + pub vm_bo: &'a GpuVmBo<T>, + /// The user-provided context type. + pub context: &'a mut T::SmContext<'ctx>, +} + +impl<'a, 'ctx, T: DriverGpuVm> OpMapRequest<'a, 'ctx, T> { + fn raw_request(&self) -> bindings::drm_gpuvm_map_req { + bindings::drm_gpuvm_map_req { + map: bindings::drm_gpuva_op_map { + va: bindings::drm_gpuva_op_map__bindgen_ty_1 { + addr: self.addr, + range: self.range, + }, + gem: bindings::drm_gpuva_op_map__bindgen_ty_2 { + offset: self.gem_offset, + obj: self.vm_bo.obj().as_raw(), + }, + }, + } + } +} + +/// Represents an `sm_step_map` operation that has not yet been completed. +pub struct OpMap<'op, T: DriverGpuVm> { + op: &'op bindings::drm_gpuva_op_map, + // Since these abstractions are designed for immediate mode, the VM BO needs to be + // pre-allocated, so we always have it available when we reach this point. + vm_bo: &'op GpuVmBo<T>, + // This ensures that 'op is invariant, so that `OpMap<'long, T>` does not + // coerce to `OpMap<'short, T>`. This ensures that the user can't return + // the wrong `OpMapped` value. + _invariant: PhantomData<*mut &'op mut T>, +} + +impl<'op, T: DriverGpuVm> OpMap<'op, T> { + /// The base address of the new mapping. + pub fn addr(&self) -> u64 { + self.op.va.addr + } + + /// The length of the new mapping. + pub fn length(&self) -> u64 { + self.op.va.range + } + + /// The offset within the [`drm_gem_object`](DriverGpuVm::Object). + pub fn gem_offset(&self) -> u64 { + self.op.gem.offset + } + + /// The [`drm_gem_object`](DriverGpuVm::Object) to map. + pub fn obj(&self) -> &T::Object { + // SAFETY: The `obj` pointer is guaranteed to be valid. + unsafe { <T::Object as IntoGEMObject>::from_raw(self.op.gem.obj) } + } + + /// The [`GpuVmBo`] that the new VA will be associated with. + pub fn vm_bo(&self) -> &GpuVmBo<T> { + self.vm_bo + } + + /// Use the pre-allocated VA to carry out this map operation. + pub fn insert(self, va: GpuVaAlloc<T>, va_data: impl PinInit<T::VaData>) -> OpMapped<'op, T> { + let va = va.prepare(va_data); + // SAFETY: By the type invariants we may access the interval tree. + unsafe { bindings::drm_gpuva_map(self.vm_bo.gpuvm().as_raw(), va, self.op) }; + + let _gpuva_guard = self.vm_bo().lock_gpuva(); + // SAFETY: The va is prepared for insertion, and we hold the GEM lock. + unsafe { bindings::drm_gpuva_link(va, self.vm_bo.as_raw()) }; + + OpMapped { + _invariant: self._invariant, + } + } +} + +/// Represents a completed [`OpMap`] operation. +pub struct OpMapped<'op, T> { + _invariant: PhantomData<*mut &'op mut T>, +} + +/// Represents an `sm_step_unmap` operation that has not yet been completed. +pub struct OpUnmap<'op, T: DriverGpuVm> { + op: &'op bindings::drm_gpuva_op_unmap, + // This ensures that 'op is invariant, so that `OpUnmap<'long, T>` does not + // coerce to `OpUnmap<'short, T>`. This ensures that the user can't return the + // wrong`OpUnmapped` value. + _invariant: PhantomData<*mut &'op mut T>, +} + +impl<'op, T: DriverGpuVm> OpUnmap<'op, T> { + /// Indicates whether this [`GpuVa`] is physically contiguous with the + /// original mapping request. + /// + /// Optionally, if `keep` is set, drivers may keep the actual page table + /// mappings for this `drm_gpuva`, adding the missing page table entries + /// only and update the `drm_gpuvm` accordingly. + pub fn keep(&self) -> bool { + self.op.keep + } + + /// The range being unmapped. + pub fn va(&self) -> &GpuVa<T> { + // SAFETY: This is a valid va. It's not the `kernel_alloc_node` because you can't unmap it, + // and it's not sparse by the `GpuVm<T>` type invariants. + unsafe { GpuVa::<T>::from_raw(self.op.va) } + } + + /// Remove the VA. + pub fn remove(self) -> (OpUnmapped<'op, T>, GpuVaRemoved<T>) { + // SAFETY: The op references a valid drm_gpuva in the GPUVM. + unsafe { bindings::drm_gpuva_unmap(self.op) }; + // SAFETY: The va is no longer in the interval tree so we may unlink it. + unsafe { bindings::drm_gpuva_unlink_defer(self.op.va) }; + + // SAFETY: We just removed this va from the `GpuVm<T>`. + let va = unsafe { GpuVaRemoved::from_raw(self.op.va) }; + + ( + OpUnmapped { + _invariant: self._invariant, + }, + va, + ) + } +} + +/// Represents a completed [`OpUnmap`] operation. +pub struct OpUnmapped<'op, T> { + _invariant: PhantomData<*mut &'op mut T>, +} + +/// Represents an `sm_step_remap` operation that has not yet been completed. +pub struct OpRemap<'op, T: DriverGpuVm> { + op: &'op bindings::drm_gpuva_op_remap, + // This ensures that 'op is invariant, so that `OpRemap<'long, T>` does not + // coerce to `OpRemap<'short, T>`. This ensures that the user can't return the + // wrong`OpRemapped` value. + _invariant: PhantomData<*mut &'op mut T>, +} + +impl<'op, T: DriverGpuVm> OpRemap<'op, T> { + /// The preceding part of a split mapping. + #[inline] + pub fn prev(&self) -> Option<&OpRemapMapData> { + // SAFETY: We checked for null, so the pointer must be valid. + NonNull::new(self.op.prev).map(|ptr| unsafe { OpRemapMapData::from_raw(ptr) }) + } + + /// The subsequent part of a split mapping. + #[inline] + pub fn next(&self) -> Option<&OpRemapMapData> { + // SAFETY: We checked for null, so the pointer must be valid. + NonNull::new(self.op.next).map(|ptr| unsafe { OpRemapMapData::from_raw(ptr) }) + } + + /// Indicates whether the `drm_gpuva` being removed is physically contiguous with the original + /// mapping request. + /// + /// Optionally, if `keep` is set, drivers may keep the actual page table mappings for this + /// `drm_gpuva`, adding the missing page table entries only and update the `drm_gpuvm` + /// accordingly. + #[inline] + pub fn keep(&self) -> bool { + // SAFETY: The unmap pointer is always valid. + unsafe { (*self.op.unmap).keep } + } + + /// The range being unmapped. + #[inline] + pub fn va_to_unmap(&self) -> &GpuVa<T> { + // SAFETY: This is a valid va. It's not the `kernel_alloc_node` because you can't unmap it, + // and it's not sparse by the `GpuVm<T>` type invariants. + unsafe { GpuVa::<T>::from_raw((*self.op.unmap).va) } + } + + /// The [`drm_gem_object`](DriverGpuVm::Object) whose VA is being remapped. + #[inline] + pub fn obj(&self) -> &T::Object { + self.va_to_unmap().obj() + } + + /// The [`GpuVmBo`] that is being remapped. + #[inline] + pub fn vm_bo(&self) -> &GpuVmBo<T> { + self.va_to_unmap().vm_bo() + } + + /// Update the GPUVM to perform the remapping. + pub fn remap( + self, + va_alloc: [GpuVaAlloc<T>; 2], + prev_data: impl PinInit<T::VaData>, + next_data: impl PinInit<T::VaData>, + ) -> (OpRemapped<'op, T>, OpRemapRet<T>) { + let [va1, va2] = va_alloc; + + let mut unused_va = None; + let mut prev_ptr = ptr::null_mut(); + let mut next_ptr = ptr::null_mut(); + if self.prev().is_some() { + prev_ptr = va1.prepare(prev_data); + } else { + unused_va = Some(va1); + } + if self.next().is_some() { + next_ptr = va2.prepare(next_data); + } else { + unused_va = Some(va2); + } + + // SAFETY: the pointers are non-null when required + unsafe { bindings::drm_gpuva_remap(prev_ptr, next_ptr, self.op) }; + + let gpuva_guard = self.vm_bo().lock_gpuva(); + if !prev_ptr.is_null() { + // SAFETY: The prev_ptr is a valid drm_gpuva prepared for insertion. The vm_bo is still + // valid as the not-yet-unlinked gpuva holds a refcount on the vm_bo. + unsafe { bindings::drm_gpuva_link(prev_ptr, self.vm_bo().as_raw()) }; + } + if !next_ptr.is_null() { + // SAFETY: The next_ptr is a valid drm_gpuva prepared for insertion. The vm_bo is still + // valid as the not-yet-unlinked gpuva holds a refcount on the vm_bo. + unsafe { bindings::drm_gpuva_link(next_ptr, self.vm_bo().as_raw()) }; + } + drop(gpuva_guard); + + // SAFETY: The va is no longer in the interval tree so we may unlink it. + unsafe { bindings::drm_gpuva_unlink_defer((*self.op.unmap).va) }; + + ( + OpRemapped { + _invariant: self._invariant, + }, + OpRemapRet { + // SAFETY: We just removed this va from the `GpuVm<T>`. + unmapped_va: unsafe { GpuVaRemoved::from_raw((*self.op.unmap).va) }, + unused_va, + }, + ) + } +} + +/// Part of an [`OpRemap`] that represents a new mapping. +#[repr(transparent)] +pub struct OpRemapMapData(bindings::drm_gpuva_op_map); + +impl OpRemapMapData { + /// # Safety + /// Must reference a valid `drm_gpuva_op_map` for duration of `'a`. + unsafe fn from_raw<'a>(ptr: NonNull<bindings::drm_gpuva_op_map>) -> &'a Self { + // SAFETY: ok per safety requirements + unsafe { ptr.cast().as_ref() } + } + + /// The base address of the new mapping. + pub fn addr(&self) -> u64 { + self.0.va.addr + } + + /// The length of the new mapping. + pub fn length(&self) -> u64 { + self.0.va.range + } + + /// The offset within the [`drm_gem_object`](DriverGpuVm::Object). + pub fn gem_offset(&self) -> u64 { + self.0.gem.offset + } +} + +/// Struct containing objects removed or not used by [`OpRemap::remap`]. +pub struct OpRemapRet<T: DriverGpuVm> { + /// The `drm_gpuva` that was removed. + pub unmapped_va: GpuVaRemoved<T>, + /// If the remap did not split the region into two pieces, then the unused `drm_gpuva` is + /// returned here. + pub unused_va: Option<GpuVaAlloc<T>>, +} + +/// Represents a completed [`OpRemap`] operation. +pub struct OpRemapped<'op, T> { + _invariant: PhantomData<*mut &'op mut T>, +} + +impl<T: DriverGpuVm> UniqueRefGpuVm<T> { + /// Create a mapping, removing or remapping anything that overlaps. + /// + /// Internally calls the [`DriverGpuVm`] callbacks similar to [`Self::sm_unmap`], except that + /// the [`DriverGpuVm::sm_step_map`] is called once to create the requested mapping. + #[inline] + pub fn sm_map(&mut self, req: OpMapRequest<'_, '_, T>) -> Result { + if req.vm_bo.gpuvm() != &**self { + return Err(EINVAL); + } + + let gpuvm = self.as_raw(); + let raw_req = req.raw_request(); + // INVARIANT: Checked above that `vm_bo.gpuvm() == self`. + let mut p = SmMapData { + sm_data: SmData { + gpuvm: self, + user_context: req.context, + }, + vm_bo: req.vm_bo, + }; + // SAFETY: + // * raw_request() creates a valid request. + // * The private data is valid to be interpreted as both SmData and SmMapData since the + // first field of SmMapData is SmData. + to_result(unsafe { + bindings::drm_gpuvm_sm_map(gpuvm, (&raw mut p).cast(), &raw const raw_req) + }) + } + + /// Remove any mappings in the given region. + /// + /// Internally calls [`DriverGpuVm::sm_step_unmap`] for ranges entirely contained within the + /// given range, and [`DriverGpuVm::sm_step_remap`] for ranges that overlap with the range. + #[inline] + pub fn sm_unmap(&mut self, addr: u64, length: u64, context: &mut T::SmContext<'_>) -> Result { + let gpuvm = self.as_raw(); + let mut p = SmData { + gpuvm: self, + user_context: context, + }; + // SAFETY: + // * raw_request() creates a valid request. + // * The private data is a valid SmData. + to_result(unsafe { bindings::drm_gpuvm_sm_unmap(gpuvm, (&raw mut p).cast(), addr, length) }) + } +} + +impl<T: DriverGpuVm> GpuVm<T> { + /// # Safety + /// Must be called from `sm_map` with a pointer to `SmMapData`. + pub(super) unsafe extern "C" fn sm_step_map( + op: *mut bindings::drm_gpuva_op, + p: *mut c_void, + ) -> c_int { + // SAFETY: If we reach `sm_step_map` then we were called from `sm_map` which always passes + // an `SmMapData` as private data. + let p = unsafe { &mut *p.cast::<SmMapData<'_, '_, T>>() }; + let op = OpMap { + // SAFETY: sm_step_map is called with a map operation. + op: unsafe { &(*op).__bindgen_anon_1.map }, + vm_bo: p.vm_bo, + _invariant: PhantomData, + }; + match p + .sm_data + .gpuvm + .data() + .sm_step_map(op, p.sm_data.user_context) + { + Ok(OpMapped { .. }) => 0, + Err(err) => err.to_errno(), + } + } + + /// # Safety + /// Must be called from `sm_map` or `sm_unmap` with a pointer to `SmMapData` or `SmData`. + pub(super) unsafe extern "C" fn sm_step_unmap( + op: *mut bindings::drm_gpuva_op, + p: *mut c_void, + ) -> c_int { + // SAFETY: The caller provides a pointer that can be treated as `SmData`. + let p = unsafe { &mut *p.cast::<SmData<'_, '_, T>>() }; + let op = OpUnmap { + // SAFETY: sm_step_unmap is called with an unmap operation. + op: unsafe { &(*op).__bindgen_anon_1.unmap }, + _invariant: PhantomData, + }; + match p.gpuvm.data().sm_step_unmap(op, p.user_context) { + Ok(OpUnmapped { .. }) => 0, + Err(err) => err.to_errno(), + } + } + + /// # Safety + /// Must be called from `sm_map` or `sm_unmap` with a pointer to `SmMapData` or `SmData`. + pub(super) unsafe extern "C" fn sm_step_remap( + op: *mut bindings::drm_gpuva_op, + p: *mut c_void, + ) -> c_int { + // SAFETY: The caller provides a pointer that can be treated as `SmData`. + let p = unsafe { &mut *p.cast::<SmData<'_, '_, T>>() }; + let op = OpRemap { + // SAFETY: sm_step_remap is called with a remap operation. + op: unsafe { &(*op).__bindgen_anon_1.remap }, + _invariant: PhantomData, + }; + match p.gpuvm.data().sm_step_remap(op, p.user_context) { + Ok(OpRemapped { .. }) => 0, + Err(err) => err.to_errno(), + } + } +} diff --git a/rust/kernel/drm/gpuvm/va.rs b/rust/kernel/drm/gpuvm/va.rs new file mode 100644 index 000000000000..0b09fe44ab39 --- /dev/null +++ b/rust/kernel/drm/gpuvm/va.rs @@ -0,0 +1,168 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT + +use super::*; + +/// Represents that a range of a GEM object is mapped in this [`GpuVm`] instance. +/// +/// Does not assume that GEM lock is held. +/// +/// # Invariants +/// +/// * This is a valid `drm_gpuva` object that is resident in a [`GpuVm<T>`] instance. +/// * It is associated with a [`GpuVmBo<T>`]. Or in other words, it's not an +/// `gpuvm->kernel_alloc_node` and `DRM_GPUVA_SPARSE` is not set. +/// * The associated [`GpuVmBo<T>`] is part of the GEM list. +#[repr(C)] +#[pin_data] +pub struct GpuVa<T: DriverGpuVm> { + #[pin] + inner: Opaque<bindings::drm_gpuva>, + #[pin] + data: T::VaData, +} + +impl<T: DriverGpuVm> PartialEq for GpuVa<T> { + #[inline] + fn eq(&self, other: &Self) -> bool { + core::ptr::eq(self.as_raw(), other.as_raw()) + } +} +impl<T: DriverGpuVm> Eq for GpuVa<T> {} + +impl<T: DriverGpuVm> GpuVa<T> { + /// Access this [`GpuVa`] from a raw pointer. + /// + /// # Safety + /// + /// * For the duration of `'a`, the pointer must reference a valid `drm_gpuva` associated with + /// a [`GpuVm<T>`]. + /// * It must be associated with a [`GpuVmBo<T>`]. + /// * The associated [`GpuVmBo<T>`] is part of the GEM list. + #[inline] + pub unsafe fn from_raw<'a>(ptr: *mut bindings::drm_gpuva) -> &'a Self { + // CAST: `drm_gpuva` is first field and `repr(C)`. + // SAFETY: The safety requirements match the invariants of `GpuVa`. + unsafe { &*ptr.cast() } + } + + /// Returns a raw pointer to underlying C value. + #[inline] + pub fn as_raw(&self) -> *mut bindings::drm_gpuva { + self.inner.get() + } + + /// Returns the address of this mapping in the GPU virtual address space. + #[inline] + pub fn addr(&self) -> u64 { + // SAFETY: The `va.addr` field of `drm_gpuva` is immutable. + unsafe { (*self.as_raw()).va.addr } + } + + /// Returns the length of this mapping. + #[inline] + pub fn length(&self) -> u64 { + // SAFETY: The `va.range` field of `drm_gpuva` is immutable. + unsafe { (*self.as_raw()).va.range } + } + + /// Returns `addr..addr+length`. + #[inline] + pub fn range(&self) -> Range<u64> { + let addr = self.addr(); + addr..addr + self.length() + } + + /// Returns the offset within the GEM object. + #[inline] + pub fn gem_offset(&self) -> u64 { + // SAFETY: The `gem.offset` field of `drm_gpuva` is immutable. + unsafe { (*self.as_raw()).gem.offset } + } + + /// Returns the GEM object. + #[inline] + pub fn obj(&self) -> &T::Object { + // SAFETY: The `gem.obj` field of `drm_gpuva` is immutable. We know that it's not null + // because this VA is associated with a `GpuVmBo<T>`. + unsafe { <T::Object as IntoGEMObject>::from_raw((*self.as_raw()).gem.obj) } + } + + /// Returns the underlying [`GpuVmBo`] object that backs this [`GpuVa`]. + #[inline] + pub fn vm_bo(&self) -> &GpuVmBo<T> { + // SAFETY: The `vm_bo` field of `drm_gpuva` is immutable. We know that it's not null + // because this VA is associated with a `GpuVmBo<T>`. The BO is in the GEM list by the type + // invariants. + unsafe { GpuVmBo::from_raw((*self.as_raw()).vm_bo) } + } +} + +/// A pre-allocated [`GpuVa`] object. +/// +/// # Invariants +/// +/// The memory is zeroed. +pub struct GpuVaAlloc<T: DriverGpuVm>(KBox<MaybeUninit<GpuVa<T>>>); + +impl<T: DriverGpuVm> GpuVaAlloc<T> { + /// Pre-allocate a [`GpuVa`] object. + pub fn new(flags: AllocFlags) -> Result<GpuVaAlloc<T>, AllocError> { + // INVARIANTS: Memory allocated with __GFP_ZERO. + Ok(GpuVaAlloc(KBox::new_uninit(flags | __GFP_ZERO)?)) + } + + /// Prepare this `drm_gpuva` for insertion into the GPUVM. + #[must_use] + pub(super) fn prepare(mut self, va_data: impl PinInit<T::VaData>) -> *mut bindings::drm_gpuva { + let va_ptr = MaybeUninit::as_mut_ptr(&mut self.0); + // SAFETY: The `data` field is pinned. + let Ok(()) = unsafe { va_data.__pinned_init(&raw mut (*va_ptr).data) }; + KBox::into_raw(self.0).cast() + } +} + +/// A [`GpuVa`] object that has been removed. +/// +/// # Invariants +/// +/// The `drm_gpuva` is not resident in the [`GpuVm`]. +pub struct GpuVaRemoved<T: DriverGpuVm>(KBox<GpuVa<T>>); + +impl<T: DriverGpuVm> GpuVaRemoved<T> { + /// Convert a raw pointer into a [`GpuVaRemoved`]. + /// + /// # Safety + /// + /// * Must have been removed from a [`GpuVm<T>`]. + /// * It must not be a `gpuvm->kernel_alloc_node` va. + pub(super) unsafe fn from_raw(ptr: *mut bindings::drm_gpuva) -> Self { + // SAFETY: Since it used to be a VA in a `GpuVm<T>` and it's not a kernel_alloc_node, this + // pointer references a `GpuVa<T>` with a valid `T::VaData`. Since it has been removed, we + // can take ownership of the allocation. + GpuVaRemoved(unsafe { KBox::from_raw(ptr.cast()) }) + } + + /// Take ownership of the VA data. + pub fn into_inner(self) -> T::VaData + where + T::VaData: Unpin, + { + KBox::into_inner(self.0).data + } +} + +impl<T: DriverGpuVm> Deref for GpuVaRemoved<T> { + type Target = T::VaData; + fn deref(&self) -> &T::VaData { + &self.0.data + } +} + +impl<T: DriverGpuVm> DerefMut for GpuVaRemoved<T> +where + T::VaData: Unpin, +{ + fn deref_mut(&mut self) -> &mut T::VaData { + &mut self.0.data + } +} diff --git a/rust/kernel/drm/gpuvm/vm_bo.rs b/rust/kernel/drm/gpuvm/vm_bo.rs new file mode 100644 index 000000000000..c064ac63897b --- /dev/null +++ b/rust/kernel/drm/gpuvm/vm_bo.rs @@ -0,0 +1,249 @@ +// SPDX-License-Identifier: GPL-2.0 OR MIT + +use super::*; + +/// Represents that a given GEM object has at least one mapping on this [`GpuVm`] instance. +/// +/// Does not assume that GEM lock is held. +/// +/// # Invariants +/// +/// * Allocated with `kmalloc` and refcounted via `inner`. +/// * Is present in the gem list. +#[repr(C)] +#[pin_data] +pub struct GpuVmBo<T: DriverGpuVm> { + #[pin] + inner: Opaque<bindings::drm_gpuvm_bo>, + #[pin] + data: T::VmBoData, +} + +// SAFETY: By type invariants, the allocation is managed by the refcount in `self.inner`. +unsafe impl<T: DriverGpuVm> AlwaysRefCounted for GpuVmBo<T> { + fn inc_ref(&self) { + // SAFETY: By type invariants, the allocation is managed by the refcount in `self.inner`. + unsafe { bindings::drm_gpuvm_bo_get(self.inner.get()) }; + } + + unsafe fn dec_ref(obj: NonNull<Self>) { + // CAST: `drm_gpuvm_bo` is first field of repr(C) struct. + // SAFETY: By type invariants, the allocation is managed by the refcount in `self.inner`. + // This GPUVM instance uses immediate mode, so we may put the refcount using the deferred + // mechanism. + unsafe { bindings::drm_gpuvm_bo_put_deferred(obj.as_ptr().cast()) }; + } +} + +impl<T: DriverGpuVm> PartialEq for GpuVmBo<T> { + #[inline] + fn eq(&self, other: &Self) -> bool { + core::ptr::eq(self.as_raw(), other.as_raw()) + } +} +impl<T: DriverGpuVm> Eq for GpuVmBo<T> {} + +impl<T: DriverGpuVm> GpuVmBo<T> { + /// The function pointer for allocating a GpuVmBo stored in the gpuvm vtable. + /// + /// Allocation is always implemented according to [`Self::vm_bo_alloc`], but it is set to + /// `None` if the default gpuvm behavior is the same as `vm_bo_alloc`. + /// + /// This may be `Some` even if `FREE_FN` is `None`, or vice-versa. + pub(super) const ALLOC_FN: Option<unsafe extern "C" fn() -> *mut bindings::drm_gpuvm_bo> = { + use core::alloc::Layout; + let base = Layout::new::<bindings::drm_gpuvm_bo>(); + let rust = Layout::new::<Self>(); + assert!(base.size() <= rust.size()); + if base.size() != rust.size() || base.align() != rust.align() { + Some(Self::vm_bo_alloc) + } else { + // This causes GPUVM to allocate a `GpuVmBo<T>` with `kzalloc(sizeof(drm_gpuvm_bo))`. + None + } + }; + + /// The function pointer for freeing a GpuVmBo stored in the gpuvm vtable. + /// + /// Freeing is always implemented according to [`Self::vm_bo_free`], but it is set to `None` if + /// the default gpuvm behavior is the same as `vm_bo_free`. + /// + /// This may be `Some` even if `ALLOC_FN` is `None`, or vice-versa. + pub(super) const FREE_FN: Option<unsafe extern "C" fn(*mut bindings::drm_gpuvm_bo)> = { + if core::mem::needs_drop::<Self>() { + Some(Self::vm_bo_free) + } else { + // This causes GPUVM to free a `GpuVmBo<T>` with `kfree`. + None + } + }; + + /// Custom function for allocating a `drm_gpuvm_bo`. + /// + /// # Safety + /// + /// Always safe to call. + unsafe extern "C" fn vm_bo_alloc() -> *mut bindings::drm_gpuvm_bo { + let raw_ptr = KBox::<Self>::new_uninit(GFP_KERNEL | __GFP_ZERO) + .map(KBox::into_raw) + .unwrap_or(ptr::null_mut()); + + // CAST: `drm_gpuvm_bo` is first field of `Self`. + raw_ptr.cast() + } + + /// Custom function for freeing a `drm_gpuvm_bo`. + /// + /// # Safety + /// + /// The pointer must have been allocated with [`GpuVmBo::ALLOC_FN`], and must not be used after + /// this call. + unsafe extern "C" fn vm_bo_free(ptr: *mut bindings::drm_gpuvm_bo) { + // CAST: `drm_gpuvm_bo` is first field of `Self`. + // SAFETY: + // * The ptr was allocated from kmalloc with the layout of `GpuVmBo<T>`. + // * `ptr->inner` has no destructor. + // * `ptr->data` contains a valid `T::VmBoData` that we can drop. + drop(unsafe { KBox::<Self>::from_raw(ptr.cast()) }); + } + + /// Access this [`GpuVmBo`] from a raw pointer. + /// + /// # Safety + /// + /// For the duration of `'a`, the pointer must reference a valid `drm_gpuvm_bo` associated with + /// a [`GpuVm<T>`]. The BO must also be present in the GEM list. + #[inline] + pub(crate) unsafe fn from_raw<'a>(ptr: *mut bindings::drm_gpuvm_bo) -> &'a Self { + // SAFETY: `drm_gpuvm_bo` is first field and `repr(C)`. + unsafe { &*ptr.cast() } + } + + /// Returns a raw pointer to underlying C value. + #[inline] + pub fn as_raw(&self) -> *mut bindings::drm_gpuvm_bo { + self.inner.get() + } + + /// The [`GpuVm`] that this GEM object is mapped in. + #[inline] + pub fn gpuvm(&self) -> &GpuVm<T> { + // SAFETY: The `obj` pointer is guaranteed to be valid. + unsafe { GpuVm::<T>::from_raw((*self.inner.get()).vm) } + } + + /// The [`drm_gem_object`](DriverGpuVm::Object) for these mappings. + #[inline] + pub fn obj(&self) -> &T::Object { + // SAFETY: The `obj` pointer is guaranteed to be valid. + unsafe { <T::Object as IntoGEMObject>::from_raw((*self.inner.get()).obj) } + } + + /// The driver data with this buffer object. + #[inline] + pub fn data(&self) -> &T::VmBoData { + &self.data + } + + pub(super) fn lock_gpuva(&self) -> crate::sync::MutexGuard<'_, ()> { + // SAFETY: The GEM object is valid. + let ptr = unsafe { &raw mut (*self.obj().as_raw()).gpuva.lock }; + // SAFETY: The GEM object is valid, so the mutex is properly initialized. + let mutex = unsafe { crate::sync::Mutex::from_raw(ptr) }; + mutex.lock() + } +} + +/// A pre-allocated [`GpuVmBo`] object. +/// +/// # Invariants +/// +/// Points at a `drm_gpuvm_bo` that contains a valid `T::VmBoData`, has a refcount of one, and is +/// absent from any gem, extobj, or evict lists. +pub(super) struct GpuVmBoAlloc<T: DriverGpuVm>(NonNull<GpuVmBo<T>>); + +impl<T: DriverGpuVm> GpuVmBoAlloc<T> { + /// Create a new pre-allocated [`GpuVmBo`]. + /// + /// It's intentional that the initializer is infallible because `drm_gpuvm_bo_put` will call + /// drop on the data, so we don't have a way to free it when the data is missing. + #[inline] + pub(super) fn new( + gpuvm: &GpuVm<T>, + gem: &T::Object, + value: impl PinInit<T::VmBoData>, + ) -> Result<GpuVmBoAlloc<T>, AllocError> { + // CAST: `GpuVmBoAlloc::vm_bo_alloc` ensures that this memory was allocated with the layout + // of `GpuVmBo<T>`. The type is repr(C), so `container_of` is not required. + // SAFETY: The provided gpuvm and gem ptrs are valid for the duration of this call. + let raw_ptr = unsafe { + bindings::drm_gpuvm_bo_create(gpuvm.as_raw(), gem.as_raw()).cast::<GpuVmBo<T>>() + }; + let ptr = NonNull::new(raw_ptr).ok_or(AllocError)?; + // SAFETY: `ptr->data` is a valid pinned location. + let Ok(()) = unsafe { value.__pinned_init(&raw mut (*raw_ptr).data) }; + // INVARIANTS: We just created the vm_bo so it's absent from lists, and the data is valid + // as we just initialized it. + Ok(GpuVmBoAlloc(ptr)) + } + + /// Returns a raw pointer to underlying C value. + #[inline] + pub(super) fn as_raw(&self) -> *mut bindings::drm_gpuvm_bo { + // SAFETY: The pointer references a valid `drm_gpuvm_bo`. + unsafe { (*self.0.as_ptr()).inner.get() } + } + + /// Look up whether there is an existing [`GpuVmBo`] for this gem object. + /// + /// The caller should not hold the GEM mutex or DMA resv lock. + #[inline] + pub(super) fn obtain(self) -> ARef<GpuVmBo<T>> { + let me = ManuallyDrop::new(self); + // SAFETY: Valid `drm_gpuvm_bo` not already in the lists. We do not access `me` after this + // call. + let ptr = unsafe { bindings::drm_gpuvm_bo_obtain_prealloc(me.as_raw()) }; + + // SAFETY: `drm_gpuvm_bo_obtain_prealloc` always returns a non-null ptr + let nonnull = unsafe { NonNull::new_unchecked(ptr.cast()) }; + + // INVARIANTS: `drm_gpuvm_bo_obtain_prealloc` ensures that the bo is in the GEM list. + // SAFETY: We received one refcount from `drm_gpuvm_bo_obtain_prealloc`. + let ret = unsafe { ARef::<GpuVmBo<T>>::from_raw(nonnull) }; + + // Ensure that external objects are in the extobj list. + // + // Note that we must call `extobj_add` even if `ptr != me` to avoid a race condition where + // we could end up using the extobj before the thread with `ptr == me` calls extobj_add. + if ret.gpuvm().is_extobj(ret.obj()) { + let resv_lock = ret.gpuvm().raw_resv(); + // TODO: Use a proper lock guard here once a dma_resv lock abstraction exists. + // SAFETY: The GPUVM is still alive, so its resv lock is too. + unsafe { bindings::dma_resv_lock(resv_lock, ptr::null_mut()) }; + // SAFETY: We hold the GPUVMs resv lock. + unsafe { bindings::drm_gpuvm_bo_extobj_add(ptr) }; + // SAFETY: We took the lock, so we can unlock it. + unsafe { bindings::dma_resv_unlock(resv_lock) }; + } + + ret + } +} + +impl<T: DriverGpuVm> Deref for GpuVmBoAlloc<T> { + type Target = GpuVmBo<T>; + #[inline] + fn deref(&self) -> &GpuVmBo<T> { + // SAFETY: By the type invariants we may deref while `Self` exists. + unsafe { self.0.as_ref() } + } +} + +impl<T: DriverGpuVm> Drop for GpuVmBoAlloc<T> { + #[inline] + fn drop(&mut self) { + // TODO: Call drm_gpuvm_bo_destroy_not_in_lists() directly. + // SAFETY: It's safe to perform a deferred put in any context. + unsafe { bindings::drm_gpuvm_bo_put_deferred(self.as_raw()) }; + } +} diff --git a/rust/kernel/drm/mod.rs b/rust/kernel/drm/mod.rs index 1b82b6945edf..a66e7166f66b 100644 --- a/rust/kernel/drm/mod.rs +++ b/rust/kernel/drm/mod.rs @@ -6,9 +6,14 @@ pub mod device; pub mod driver; pub mod file; pub mod gem; +pub mod gpuvm; pub mod ioctl; pub use self::device::Device; +pub use self::device::DeviceContext; +pub use self::device::Registered; +pub use self::device::Uninit; +pub use self::device::UnregisteredDevice; pub use self::driver::Driver; pub use self::driver::DriverInfo; pub use self::driver::Registration; |
