mirror of
https://github.com/torvalds/linux.git
synced 2026-10-07 11:06:03 +02:00
perf: - export perf_allow_ APIs for xe udmabuf: - remove default size limit of 64MB rust: - i/o rework (signed tag from driver-core tree) - add registration guard and registration data - fix unbounded lifetimes in ioctl handler args - fix a drm_dev_register race - gem_shmem: add DmaResvGuard helper - gpuvm: require send/sync for driver data - implement send/sync for GpuVaAlloc and GpuVmBo - add SmContext lifetime - rename dma_handle to dma_address - change pci_sriov_get_totalvfs return to unsigned int core: - create drm_of_get_panel_orientation - send per-connector hotplug events - add thunderbolt UBHR tunneling support connector: - add color format property dmem: - introduce a peak file - accept one region per limit - add dmemcg support for eviction gpusvm: - reorg code to give drivers more flexibility atomic: - add create_state callback and helper - add documentation on atomic commit lifetime buddy: - add per-order free - add used block scoreboard - fix UAF - test buffer clearance on resume - add phys_addr->block helper gem: - drop DRIVER_GEM_GPUVA flag ttm: - be more aggressive allocating below protection limit sched: - add test suite for concurrent job submissions hdmi: - hook the color format property in helpers mipi-dsi: - add MIPI_DSI_MODE_DSC_ALL_SLICES_IN_PKT bridge: - add atomic create callbacks - drop atomic reset - display-connector: don't autoenable HPD IRQ - trigger initial HPD for DP - ti-sn65dsi83: remove NO_HFP and NO_HBP mode flags - analogix_dp: switch to DP link training helpers dp: - add support for DSC max delta BPP edid: - parse panel type from DisplayID 2.x Display Parameters sysfb: - improve panel, stride, framebuffer size validation panel: - implement ref counting for struct drm_panel - himax-hx83121a: add backlight regulator support - novatek-nt36672a: Inline panel init sequences - visionox-vtdr6130: enable DSC - novatek-nt37801: Use mipi_dsi_*_multi() functions - samsung-s6d16d0: Fix prepare error handling - support Novatek NT36536 plus DT bindings - sofef00: fix backlight updates - osd101t2587: use mipi_dsi_*_multi interface - panel-edp: adjust timing for AUO displays - panel-lvds: support Opto Logic SCX1001511GGC49 - panel-simple: support Kyocera tcg070wvlq - panel-edp: quirks - AUO B116XAT04.3, CMN N116BCP-EA2, CSW MNB601LS1-8 - BOE NV116WH2-M30, BOE NT116WHM-N21, BOE NV116FH1-M31 - BOE NV116FH1-M30, NV140FHM-N5B, TM156VDXP25 - BOE NE160QDM-NY1, MB116AS01 - new: - Samsung ATNA40HQ08-0, Anbernic TD4310 - Chipone ICNA35XX, Ilitek ILI9488 - Ilitek ILI7807S, Renesas R63419 - MNE001BS6-2, MNF601BS4-1, Sharp LQ120P1JX51 virtio: - add support for save/restore virtio_gpu_objects - abort vq wait on device removal amdgpu: - add color format DRM property - initial compute pipe reset support - add GFX 6-8 modifier support - initial DCN 6.0.0 support - dmemcg eviction support - improved boundary checking for bios parsing - RAS updates and rework - VCN secure submission fixes - 8K panel fix - Display KUNIT tests - parse panel type from DisplayID - Align IP discovery to pci device lifetime - SOC15 register macro cleanups - UVD memory placement fixes - GFX9 mode2 reset fixes - drop unnecessary BUG/BUG_ON - GFX8 soft reset rework - enable soft reset on GFX8 - PSP/SMU 15.0.9 update - VI ASPM fix - userq fixes - amdgpu_vm_get_task_info_pasid lifetime fix - DC CACP support - change system_unbound_wq with system_dfl_wq - Loosen VFCT bios parsing to deal with pci=realloc - SI/SMU7 AC/DC switch fix - VM fence handling fix - GEM close optimisation - Apple Studio Display fixes - DC FRL fixes amdkfd: - initial compute pipe reset support - allow applications to opt out of sigbus on fatal errors - improve CRIU boundary checks - MQD handling rework - move TBA/TMA from system to device memory - avoid topology-lock in kfd_mmap - SVM eviction fixes radeon: - fix unset CONFIG_ACPI build i915: - Novalake (NVL display version 35) timing generator enabling - NVL DC3CO enabling - enable UBHR link rates on thunderbolt tunnels - Reduce Xe3+ PM demand peak bandwidth - enable pipe DMC error interrupts for display 30+ - add kunit tests for DP link config selection - refactor and document DP link recovery - i915/xe driver display probe/remove/suspend/resume/shutdown cleanup and unification - i915/xe display runtime PM unified - Break i915 and xe panic dependency on struct intel_framebuffer - Streamline Pre/Post-CSC LUT loops - drop TGL DC3DO support - CDCLK santization - fix HDMI scrambling enable - fix phys bo pread/pwrite with offset - add missing nospec on parallel submit slot - fix some NULL derefs xe: - drop force_execlist module param - gate observation streams with perf_allow_cpu - skip FORCE_WC and vm_bound check for external dma-bufs - dmemcg eviction support - remove unused NVL-S GuC - TLB invalidation improvements - NVL-S updated PCI-IDs and w/a - madvise: optimise invalidation path - fix infinite gt-reset loop in timeout recovery - update TTM device benefical_order - wait on external BO kernel fences in exec ioctl - add/use more KLV helpers - sriov: disable display in admin only PF mode - add RAS GPU health indicator - optimise TTM populate for DONTNEED BO - drop force_probe for NVL-s - add debugfs for pcode info amdxdna: - disable device buffer export nova: - build nova-core/nova-drm from drivers/gpu - export nova-core rust symbols (workaround) - GSP boot process consolidation - Boot GSP with vGPU enabled - TLV firmware image format support - Hopper/Blackwell fixes and cleanups - I/O projection adoption tyr: - firmware loading and MCU boot - add generic slot manager + MMU - GPU VM support ARM64 LPAE page tables - add kernel buffer object for internal allocations - add parser for Mali CSF - add MCU booting nouveau: - race fixes - check instmem iomapping at first use - add dmemcg support - expose NVDEC channels - add scanline position/head state support for GSP qxl: - convert simple encoder to regular ethosu: - add perf counter support etnaviv: - force flush on power register ops msm: - support DSC configuration with slice_per_pkt > 1 mxsfb: - fix disable sequence panthor: - support sparse mappings rockchip: - switch away from simple helpers - support YUV background color - fix layer config timeout - add edp support for rk3576 - add batch command submission function rocket: - error handling and NULL ptr deref fixes sun4i: - switch away from simple helpers imagination: - mark BXM-4-64 MC1 as support host1x: - support tegra264 tegra: - add DSI for tegra 20/30 v3d: - reduce PM runtime autosuspend delay - scheduler fixes and refactoring - deprecate v3d 3.3 and 4.1 - validate CPU job query boundaries hibmc: - improve plane format handling - switch to gem shmem mediatek: - cec: correct compat for mt7623-8167? exynos: - remove simple dependency - add error handling to encoder paths - take i2c adapter module reference -----BEGIN PGP SIGNATURE----- iQIzBAABCgAdFiEEEKbZHaGwW9KfbeusDHTzWXnEhr4FAmqGlb0ACgkQDHTzWXnE hr7l9A//TnfntEghigEEFobfJX+p9FzaOTPPia8paooAj52OBK8Z86WpbYwEo4K9 X+vPXPYpqgKSiGkkC33swAlylWs2v3JoZQ+CESERBk176Ql3ZKhicBINH+k8jIcX uaFoDgpgMoV1JCcvF/m48de8YRcejSN43rIucS0aIH5/r/YEyRsE4d4dzCXw/qD8 92tjbmH20mChfeo8MUNatZx+t8ssSOrVdqouLmmFB8tYTcca6qwN60uA+9VESVtd nZLCEiZD0FUI73oT7fmK/zL2rTb2pZRPFNdz0mb6f7UUpu7f8RYnroHrNsGa/FHl K5RD1/gSVpfc6CbrhPnePaRKvIGeEC4ief8YRRyeoNVT3cmkf+citpOoKN2JajF1 bub/ni2z1FGA3y1ckJb4Z6HmGHt5gki/KoAKCmZkJ7bb7WJq/JHMWEFfq4LuNjTA FSSxPozM4pb69DL02wwRJIEe8cYcc/gVTgrSkzR/tsVUoE6XI4AwZJ/Exa43+jVe hjNkAOMrl/+ma/WGQ4BPUVeTRPZP6RlNM4cSWvG1YA2Pf6+O+XLjukac6t+Ozj0X Fz1ePqYxELKSOYkZKxdpxRDyzY6SxvtyDHfHblo4p+BUvaXKP4wfNRexXETD6Qow P7rqYN6riDMRPI9CoPd25V7cbfYbvoV0iJzv3EQwU3pvB9Vu1ho= =TGZ1 -----END PGP SIGNATURE----- Merge tag 'drm-next-2026-08-20' of https://gitlab.freedesktop.org/drm/kernel Pull drm updates from Dave Airlie: "Highlights: - dmemcg eviction support is good for low VRAM things like Steam Machine - AMD adds gfx6-8 modifier support for older GPUs that enables a bunch of wayland stuff - i915/xe has some new hw support but also a lot of display refactoring Everything: perf: - export perf_allow_ APIs for xe udmabuf: - remove default size limit of 64MB rust: - i/o rework (signed tag from driver-core tree) - add registration guard and registration data - fix unbounded lifetimes in ioctl handler args - fix a drm_dev_register race - gem_shmem: add DmaResvGuard helper - gpuvm: require send/sync for driver data - implement send/sync for GpuVaAlloc and GpuVmBo - add SmContext lifetime - rename dma_handle to dma_address - change pci_sriov_get_totalvfs return to unsigned int core: - create drm_of_get_panel_orientation - send per-connector hotplug events - add thunderbolt UBHR tunneling support connector: - add color format property dmem: - introduce a peak file - accept one region per limit - add dmemcg support for eviction gpusvm: - reorg code to give drivers more flexibility atomic: - add create_state callback and helper - add documentation on atomic commit lifetime buddy: - add per-order free - add used block scoreboard - fix UAF - test buffer clearance on resume - add phys_addr->block helper gem: - drop DRIVER_GEM_GPUVA flag ttm: - be more aggressive allocating below protection limit sched: - add test suite for concurrent job submissions hdmi: - hook the color format property in helpers mipi-dsi: - add MIPI_DSI_MODE_DSC_ALL_SLICES_IN_PKT bridge: - add atomic create callbacks - drop atomic reset - display-connector: don't autoenable HPD IRQ - trigger initial HPD for DP - ti-sn65dsi83: remove NO_HFP and NO_HBP mode flags - analogix_dp: switch to DP link training helpers dp: - add support for DSC max delta BPP edid: - parse panel type from DisplayID 2.x Display Parameters sysfb: - improve panel, stride, framebuffer size validation panel: - implement ref counting for struct drm_panel - himax-hx83121a: add backlight regulator support - novatek-nt36672a: Inline panel init sequences - visionox-vtdr6130: enable DSC - novatek-nt37801: Use mipi_dsi_*_multi() functions - samsung-s6d16d0: Fix prepare error handling - support Novatek NT36536 plus DT bindings - sofef00: fix backlight updates - osd101t2587: use mipi_dsi_*_multi interface - panel-edp: adjust timing for AUO displays - panel-lvds: support Opto Logic SCX1001511GGC49 - panel-simple: support Kyocera tcg070wvlq - panel-edp: quirks - AUO B116XAT04.3, CMN N116BCP-EA2, CSW MNB601LS1-8 - BOE NV116WH2-M30, BOE NT116WHM-N21, BOE NV116FH1-M31 - BOE NV116FH1-M30, NV140FHM-N5B, TM156VDXP25 - BOE NE160QDM-NY1, MB116AS01 - new: - Samsung ATNA40HQ08-0, Anbernic TD4310 - Chipone ICNA35XX, Ilitek ILI9488 - Ilitek ILI7807S, Renesas R63419 - MNE001BS6-2, MNF601BS4-1, Sharp LQ120P1JX51 virtio: - add support for save/restore virtio_gpu_objects - abort vq wait on device removal amdgpu: - add color format DRM property - initial compute pipe reset support - add GFX 6-8 modifier support - initial DCN 6.0.0 support - dmemcg eviction support - improved boundary checking for bios parsing - RAS updates and rework - VCN secure submission fixes - 8K panel fix - Display KUNIT tests - parse panel type from DisplayID - Align IP discovery to pci device lifetime - SOC15 register macro cleanups - UVD memory placement fixes - GFX9 mode2 reset fixes - drop unnecessary BUG/BUG_ON - GFX8 soft reset rework - enable soft reset on GFX8 - PSP/SMU 15.0.9 update - VI ASPM fix - userq fixes - amdgpu_vm_get_task_info_pasid lifetime fix - DC CACP support - change system_unbound_wq with system_dfl_wq - Loosen VFCT bios parsing to deal with pci=realloc - SI/SMU7 AC/DC switch fix - VM fence handling fix - GEM close optimisation - Apple Studio Display fixes - DC FRL fixes amdkfd: - initial compute pipe reset support - allow applications to opt out of sigbus on fatal errors - improve CRIU boundary checks - MQD handling rework - move TBA/TMA from system to device memory - avoid topology-lock in kfd_mmap - SVM eviction fixes radeon: - fix unset CONFIG_ACPI build i915: - Novalake (NVL display version 35) timing generator enabling - NVL DC3CO enabling - enable UBHR link rates on thunderbolt tunnels - Reduce Xe3+ PM demand peak bandwidth - enable pipe DMC error interrupts for display 30+ - add kunit tests for DP link config selection - refactor and document DP link recovery - i915/xe driver display probe/remove/suspend/resume/shutdown cleanup and unification - i915/xe display runtime PM unified - Break i915 and xe panic dependency on struct intel_framebuffer - Streamline Pre/Post-CSC LUT loops - drop TGL DC3DO support - CDCLK santization - fix HDMI scrambling enable - fix phys bo pread/pwrite with offset - add missing nospec on parallel submit slot - fix some NULL derefs xe: - drop force_execlist module param - gate observation streams with perf_allow_cpu - skip FORCE_WC and vm_bound check for external dma-bufs - dmemcg eviction support - remove unused NVL-S GuC - TLB invalidation improvements - NVL-S updated PCI-IDs and w/a - madvise: optimise invalidation path - fix infinite gt-reset loop in timeout recovery - update TTM device benefical_order - wait on external BO kernel fences in exec ioctl - add/use more KLV helpers - sriov: disable display in admin only PF mode - add RAS GPU health indicator - optimise TTM populate for DONTNEED BO - drop force_probe for NVL-s - add debugfs for pcode info amdxdna: - disable device buffer export nova: - build nova-core/nova-drm from drivers/gpu - export nova-core rust symbols (workaround) - GSP boot process consolidation - Boot GSP with vGPU enabled - TLV firmware image format support - Hopper/Blackwell fixes and cleanups - I/O projection adoption tyr: - firmware loading and MCU boot - add generic slot manager + MMU - GPU VM support ARM64 LPAE page tables - add kernel buffer object for internal allocations - add parser for Mali CSF - add MCU booting nouveau: - race fixes - check instmem iomapping at first use - add dmemcg support - expose NVDEC channels - add scanline position/head state support for GSP qxl: - convert simple encoder to regular ethosu: - add perf counter support etnaviv: - force flush on power register ops msm: - support DSC configuration with slice_per_pkt > 1 mxsfb: - fix disable sequence panthor: - support sparse mappings rockchip: - switch away from simple helpers - support YUV background color - fix layer config timeout - add edp support for rk3576 - add batch command submission function rocket: - error handling and NULL ptr deref fixes sun4i: - switch away from simple helpers imagination: - mark BXM-4-64 MC1 as support host1x: - support tegra264 tegra: - add DSI for tegra 20/30 v3d: - reduce PM runtime autosuspend delay - scheduler fixes and refactoring - deprecate v3d 3.3 and 4.1 - validate CPU job query boundaries hibmc: - improve plane format handling - switch to gem shmem mediatek: - cec: correct compat for mt7623-8167? exynos: - remove simple dependency - add error handling to encoder paths - take i2c adapter module reference" * tag 'drm-next-2026-08-20' of https://gitlab.freedesktop.org/drm/kernel: (2074 commits) drm/xe/mcr: Take vcs1/vecs1 into account for first media slice drm/xe: Fix a bug in pc_adjust_freq_bounds() drm/xe: Fix xe_device_probe() failure drm/xe/drm_ras: Move has_drm_ras check to drm_ras layer drm/xe/ras: Fix boot-time ras error processing drm/amd/display: make DC_RUN_WITH_PREEMPTION_ENABLED misuse a build error drm/amd/pm: silence uninitialized variable warnings drm/amdgpu: skip BOs being torn down during GTT recovery drm/amdgpu: Reject UVD message with invalid number of h265 refs drm/amdgpu: keep PRT mappings off the vm_bo state lists drm/amdgpu: fix nbif 6.3.1 l1 low power not functional drm/amd/display: fix BT.2020 YCbCr output CSC matrices for DCE drm/amd/display: fix BT.2020 YCbCr limited output CSC matrix drm/amdgpu: Implement insert_end for VCE 3 drm/amdgpu: Fix UVD min buffer sizes drm/amdgpu: Fix UVD decode image min size calculation drm/amdgpu: Fix UVD dpb min size calculation for H264 drm/amdgpu: Reject UVD message with dimensions above 4096 drm/amdgpu: check ASPM on the dGPU host link drm/radeon: fix autosuspend cleanup during teardown ...
259 lines
10 KiB
Rust
259 lines
10 KiB
Rust
// 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: It is safe to send a `GpuVmBo<T>` to another thread: dropping it there drops
|
|
// `T::VmBoData` and the GEM `T::Object`, both `Send` by the `DriverGpuVm` bounds.
|
|
unsafe impl<T: DriverGpuVm> Send for GpuVmBo<T> {}
|
|
|
|
// SAFETY: It is safe to share a `&GpuVmBo<T>` between threads: it effectively shares
|
|
// `&T::VmBoData` and the GEM `&T::Object` (both `Sync`), and any thread may upgrade to an
|
|
// `ARef` and ultimately drop them (both `Send`), per the `DriverGpuVm` bounds.
|
|
unsafe impl<T: DriverGpuVm> Sync for GpuVmBo<T> {}
|
|
|
|
// 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.
|
|
unsafe { pin_init::raw_init(&raw mut (*raw_ptr).data, value) };
|
|
// 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()) };
|
|
}
|
|
}
|