diff options
| author | Dave Airlie <airlied@redhat.com> | 2025-09-17 16:09:24 +1000 |
|---|---|---|
| committer | Dave Airlie <airlied@redhat.com> | 2025-09-17 16:13:49 +1000 |
| commit | 6f17ab9a63e670bd62a287f95e3982f99eafd77e (patch) | |
| tree | 22a564695db44faa7428d309d2ae4570d613268f | |
| parent | 5770495279d79514989b00fe9ef0ff487bf2e54e (diff) | |
| parent | 299eb32863e584cfff7c6b667c3e92ae7d4d2bf9 (diff) | |
Merge tag 'drm-rust-next-2025-09-16' of https://gitlab.freedesktop.org/drm/rust/kernel into drm-next
DRM Rust changes for v6.18
Alloc
- Add BorrowedPage type and AsPageIter trait
- Implement Vmalloc::to_page() and VmallocPageIter
- Implement AsPageIter for VBox and VVec
DMA & Scatterlist
- Add dma::DataDirection and type alias for dma_addr_t
- Abstraction for struct scatterlist and struct sg_table
DRM
- In the DRM GEM module, simplify overall use of generics, add
DriverFile type alias and drop Object::SIZE.
Nova (Core)
- Various register!() macro improvements (paving the way for lifting
it to common driver infrastructure)
- Minor VBios fixes and refactoring
- Minor firmware request refactoring
- Advance firmware boot stages; process Booter and patch its
signature, process GSP and GSP bootloader
- Switch development fimrware version to r570.144
- Add basic firmware bindings for r570.144
- Move GSP boot code to its own module
- Clean up and take advantage of pin-init features to store most of
the driver's private data within a single allocation
- Update ARef import from sync::aref
- Add website to MAINTAINERS entry
Nova (DRM)
- Update ARef import from sync::aref
- Add website to MAINTAINERS entry
Pin-Init
- Merge pin-init PR from Benno
- `#[pin_data]` now generates a `*Projection` struct similar to the
`pin-project` crate.
- Add initializer code blocks to `[try_][pin_]init!` macros: make
initializer macros accept any number of `_: {/* arbitrary code
*/},` & make them run the code at that point.
- Make the `[try_][pin_]init!` macros expose initialized fields via
a `let` binding as `&mut T` or `Pin<&mut T>` for later fields.
Rust
- Various methods for AsBytes and FromBytes traits
Tyr
- Initial Rust driver skeleton for ARM Mali GPUs.
- It can power up the GPU, query for GPU metatdata through MMIO and
provide the metadata to userspace via DRM device IOCTL (struct
drm_panthor_dev_query).
Signed-off-by: Dave Airlie <airlied@redhat.com>
From: "Danilo Krummrich" <dakr@kernel.org>
Link: https://lore.kernel.org/r/DCUC4SY6SRBD.1ZLHAIQZOC6KG@kernel.org
62 files changed, 4001 insertions, 666 deletions
diff --git a/Documentation/gpu/nova/core/todo.rst b/Documentation/gpu/nova/core/todo.rst index 894a1e9c3741..091a2fb78c6b 100644 --- a/Documentation/gpu/nova/core/todo.rst +++ b/Documentation/gpu/nova/core/todo.rst @@ -131,8 +131,6 @@ crate so it can be used by other components as well. Features desired before this happens: -* Relative register with build-time base address validation, -* Arrays of registers with build-time index validation, * Make I/O optional I/O (for field values that are not registers), * Support other sizes than `u32`, * Allow visibility control for registers and individual fields, @@ -232,23 +230,6 @@ Rust abstraction for debugfs APIs. GPU (general) ============= -Parse firmware headers ----------------------- - -Parse ELF headers from the firmware files loaded from the filesystem. - -| Reference: ELF utils -| Complexity: Beginner -| Contact: Abdiel Janulgue - -Build radix3 page table ------------------------ - -Build the radix3 page table to map the firmware. - -| Complexity: Intermediate -| Contact: Abdiel Janulgue - Initial Devinit support ----------------------- diff --git a/MAINTAINERS b/MAINTAINERS index 5257d52679d6..838ae3c2b6fc 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2086,6 +2086,19 @@ F: Documentation/devicetree/bindings/gpu/arm,mali-valhall-csf.yaml F: drivers/gpu/drm/panthor/ F: include/uapi/drm/panthor_drm.h +ARM MALI TYR DRM DRIVER +M: Daniel Almeida <daniel.almeida@collabora.com> +M: Alice Ryhl <aliceryhl@google.com> +L: dri-devel@lists.freedesktop.org +S: Supported +W: https://rust-for-linux.com/tyr-gpu-driver +W https://drm.pages.freedesktop.org/maintainer-tools/drm-rust.html +B: https://gitlab.freedesktop.org/panfrost/linux/-/issues +T: git https://gitlab.freedesktop.org/drm/rust/kernel.git +F: Documentation/devicetree/bindings/gpu/arm,mali-valhall-csf.yaml +F: drivers/gpu/drm/tyr/ +F: include/uapi/drm/panthor_drm.h + ARM MALI-DP DRM DRIVER M: Liviu Dudau <liviu.dudau@arm.com> S: Supported @@ -7237,7 +7250,7 @@ F: include/linux/dma-mapping.h F: include/linux/swiotlb.h F: kernel/dma/ -DMA MAPPING HELPERS DEVICE DRIVER API [RUST] +DMA MAPPING & SCATTERLIST API [RUST] M: Danilo Krummrich <dakr@kernel.org> R: Abdiel Janulgue <abdiel.janulgue@gmail.com> R: Daniel Almeida <daniel.almeida@collabora.com> @@ -7248,7 +7261,9 @@ S: Supported W: https://rust-for-linux.com T: git git://git.kernel.org/pub/scm/linux/kernel/git/driver-core/driver-core.git F: rust/helpers/dma.c +F: rust/helpers/scatterlist.c F: rust/kernel/dma.rs +F: rust/kernel/scatterlist.rs F: samples/rust/rust_dma.rs DMA-BUF HEAPS FRAMEWORK @@ -7838,6 +7853,7 @@ M: Danilo Krummrich <dakr@kernel.org> M: Alexandre Courbot <acourbot@nvidia.com> L: nouveau@lists.freedesktop.org S: Supported +W: https://rust-for-linux.com/nova-gpu-driver Q: https://patchwork.freedesktop.org/project/nouveau/ B: https://gitlab.freedesktop.org/drm/nova/-/issues C: irc://irc.oftc.net/nouveau @@ -7849,6 +7865,7 @@ DRM DRIVER FOR NVIDIA GPUS [RUST] M: Danilo Krummrich <dakr@kernel.org> L: nouveau@lists.freedesktop.org S: Supported +W: https://rust-for-linux.com/nova-gpu-driver Q: https://patchwork.freedesktop.org/project/nouveau/ B: https://gitlab.freedesktop.org/drm/nova/-/issues C: irc://irc.oftc.net/nouveau diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig index f7ea8e895c0c..fda170730468 100644 --- a/drivers/gpu/drm/Kconfig +++ b/drivers/gpu/drm/Kconfig @@ -396,6 +396,8 @@ source "drivers/gpu/drm/sprd/Kconfig" source "drivers/gpu/drm/imagination/Kconfig" +source "drivers/gpu/drm/tyr/Kconfig" + config DRM_HYPERV tristate "DRM Support for Hyper-V synthetic video device" depends on DRM && PCI && HYPERV diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile index 4dafbdc8f86a..4b2f7d794275 100644 --- a/drivers/gpu/drm/Makefile +++ b/drivers/gpu/drm/Makefile @@ -220,6 +220,7 @@ obj-$(CONFIG_DRM_VBOXVIDEO) += vboxvideo/ obj-$(CONFIG_DRM_LIMA) += lima/ obj-$(CONFIG_DRM_PANFROST) += panfrost/ obj-$(CONFIG_DRM_PANTHOR) += panthor/ +obj-$(CONFIG_DRM_TYR) += tyr/ obj-$(CONFIG_DRM_ASPEED_GFX) += aspeed/ obj-$(CONFIG_DRM_MCDE) += mcde/ obj-$(CONFIG_DRM_TIDSS) += tidss/ diff --git a/drivers/gpu/drm/nova/driver.rs b/drivers/gpu/drm/nova/driver.rs index b28b2e05cc15..91b7380f83ab 100644 --- a/drivers/gpu/drm/nova/driver.rs +++ b/drivers/gpu/drm/nova/driver.rs @@ -1,6 +1,8 @@ // SPDX-License-Identifier: GPL-2.0 -use kernel::{auxiliary, c_str, device::Core, drm, drm::gem, drm::ioctl, prelude::*, types::ARef}; +use kernel::{ + auxiliary, c_str, device::Core, drm, drm::gem, drm::ioctl, prelude::*, sync::aref::ARef, +}; use crate::file::File; use crate::gem::NovaObject; diff --git a/drivers/gpu/drm/nova/gem.rs b/drivers/gpu/drm/nova/gem.rs index 33b62d21400c..2760ba4f3450 100644 --- a/drivers/gpu/drm/nova/gem.rs +++ b/drivers/gpu/drm/nova/gem.rs @@ -4,7 +4,7 @@ use kernel::{ drm, drm::{gem, gem::BaseObject}, prelude::*, - types::ARef, + sync::aref::ARef, }; use crate::{ @@ -16,16 +16,14 @@ use crate::{ #[pin_data] pub(crate) struct NovaObject {} -impl gem::BaseDriverObject<gem::Object<NovaObject>> for NovaObject { +impl gem::DriverObject for NovaObject { + type Driver = NovaDriver; + fn new(_dev: &NovaDevice, _size: usize) -> impl PinInit<Self, Error> { try_pin_init!(NovaObject {}) } } -impl gem::DriverObject for NovaObject { - type Driver = NovaDriver; -} - impl NovaObject { /// Create a new DRM GEM object. pub(crate) fn new(dev: &NovaDevice, size: usize) -> Result<ARef<gem::Object<Self>>> { diff --git a/drivers/gpu/drm/tyr/Kconfig b/drivers/gpu/drm/tyr/Kconfig new file mode 100644 index 000000000000..4b55308fd2eb --- /dev/null +++ b/drivers/gpu/drm/tyr/Kconfig @@ -0,0 +1,19 @@ +# SPDX-License-Identifier: GPL-2.0 or MIT + +config DRM_TYR + tristate "Tyr (Rust DRM support for ARM Mali CSF-based GPUs)" + depends on DRM=y + depends on RUST + depends on ARM || ARM64 || COMPILE_TEST + depends on !GENERIC_ATOMIC64 # for IOMMU_IO_PGTABLE_LPAE + default n + help + Rust DRM driver for ARM Mali CSF-based GPUs. + + This driver is for Mali (or Immortalis) Valhall Gxxx GPUs. + + Note that the Mali-G68 and Mali-G78, while Valhall architecture, will + be supported with the panfrost driver as they are not CSF GPUs. + + if M is selected, the module will be called tyr. This driver is work + in progress and may not be functional. diff --git a/drivers/gpu/drm/tyr/Makefile b/drivers/gpu/drm/tyr/Makefile new file mode 100644 index 000000000000..ba545f65f2c0 --- /dev/null +++ b/drivers/gpu/drm/tyr/Makefile @@ -0,0 +1,3 @@ +# SPDX-License-Identifier: GPL-2.0 or MIT + +obj-$(CONFIG_DRM_TYR) += tyr.o diff --git a/drivers/gpu/drm/tyr/driver.rs b/drivers/gpu/drm/tyr/driver.rs new file mode 100644 index 000000000000..d5625dd1e41c --- /dev/null +++ b/drivers/gpu/drm/tyr/driver.rs @@ -0,0 +1,205 @@ +// SPDX-License-Identifier: GPL-2.0 or MIT + +use kernel::c_str; +use kernel::clk::Clk; +use kernel::clk::OptionalClk; +use kernel::device::Bound; +use kernel::device::Core; +use kernel::device::Device; +use kernel::devres::Devres; +use kernel::drm; +use kernel::drm::ioctl; +use kernel::new_mutex; +use kernel::of; +use kernel::platform; +use kernel::prelude::*; +use kernel::regulator; +use kernel::regulator::Regulator; +use kernel::sizes::SZ_2M; +use kernel::sync::Arc; +use kernel::sync::Mutex; +use kernel::time; +use kernel::types::ARef; + +use crate::file::File; +use crate::gem::TyrObject; +use crate::gpu; +use crate::gpu::GpuInfo; +use crate::regs; + +pub(crate) type IoMem = kernel::io::mem::IoMem<SZ_2M>; + +/// Convenience type alias for the DRM device type for this driver. +pub(crate) type TyrDevice = drm::Device<TyrDriver>; + +#[pin_data(PinnedDrop)] +pub(crate) struct TyrDriver { + device: ARef<TyrDevice>, +} + +#[pin_data(PinnedDrop)] +pub(crate) struct TyrData { + pub(crate) pdev: ARef<platform::Device>, + + #[pin] + clks: Mutex<Clocks>, + + #[pin] + regulators: Mutex<Regulators>, + + /// Some information on the GPU. + /// + /// This is mainly queried by userspace, i.e.: Mesa. + pub(crate) gpu_info: GpuInfo, +} + +// Both `Clk` and `Regulator` do not implement `Send` or `Sync`, but they +// should. There are patches on the mailing list to address this, but they have +// not landed yet. +// +// For now, add this workaround so that this patch compiles with the promise +// that it will be removed in a future patch. +// +// SAFETY: This will be removed in a future patch. +unsafe impl Send for TyrData {} +// SAFETY: This will be removed in a future patch. +unsafe impl Sync for TyrData {} + +fn issue_soft_reset(dev: &Device<Bound>, iomem: &Devres<IoMem>) -> Result { + regs::GPU_CMD.write(dev, iomem, regs::GPU_CMD_SOFT_RESET)?; + + // TODO: We cannot poll, as there is no support in Rust currently, so we + // sleep. Change this when read_poll_timeout() is implemented in Rust. + kernel::time::delay::fsleep(time::Delta::from_millis(100)); + + if regs::GPU_IRQ_RAWSTAT.read(dev, iomem)? & regs::GPU_IRQ_RAWSTAT_RESET_COMPLETED == 0 { + dev_err!(dev, "GPU reset failed with errno\n"); + dev_err!( + dev, + "GPU_INT_RAWSTAT is {}\n", + regs::GPU_IRQ_RAWSTAT.read(dev, iomem)? + ); + + return Err(EIO); + } + + Ok(()) +} + +kernel::of_device_table!( + OF_TABLE, + MODULE_OF_TABLE, + <TyrDriver as platform::Driver>::IdInfo, + [ + (of::DeviceId::new(c_str!("rockchip,rk3588-mali")), ()), + (of::DeviceId::new(c_str!("arm,mali-valhall-csf")), ()) + ] +); + +impl platform::Driver for TyrDriver { + type IdInfo = (); + const OF_ID_TABLE: Option<of::IdTable<Self::IdInfo>> = Some(&OF_TABLE); + + fn probe( + pdev: &platform::Device<Core>, + _info: Option<&Self::IdInfo>, + ) -> Result<Pin<KBox<Self>>> { + let core_clk = Clk::get(pdev.as_ref(), Some(c_str!("core")))?; + let stacks_clk = OptionalClk::get(pdev.as_ref(), Some(c_str!("stacks")))?; + let coregroup_clk = OptionalClk::get(pdev.as_ref(), Some(c_str!("coregroup")))?; + + core_clk.prepare_enable()?; + stacks_clk.prepare_enable()?; + coregroup_clk.prepare_enable()?; + + let mali_regulator = Regulator::<regulator::Enabled>::get(pdev.as_ref(), c_str!("mali"))?; + let sram_regulator = Regulator::<regulator::Enabled>::get(pdev.as_ref(), c_str!("sram"))?; + + let request = pdev.io_request_by_index(0).ok_or(ENODEV)?; + let iomem = Arc::pin_init(request.iomap_sized::<SZ_2M>(), GFP_KERNEL)?; + + issue_soft_reset(pdev.as_ref(), &iomem)?; + gpu::l2_power_on(pdev.as_ref(), &iomem)?; + + let gpu_info = GpuInfo::new(pdev.as_ref(), &iomem)?; + gpu_info.log(pdev); + + let platform: ARef<platform::Device> = pdev.into(); + + let data = try_pin_init!(TyrData { + pdev: platform.clone(), + clks <- new_mutex!(Clocks { + core: core_clk, + stacks: stacks_clk, + coregroup: coregroup_clk, + }), + regulators <- new_mutex!(Regulators { + mali: mali_regulator, + sram: sram_regulator, + }), + gpu_info, + }); + + let tdev: ARef<TyrDevice> = drm::Device::new(pdev.as_ref(), data)?; + drm::driver::Registration::new_foreign_owned(&tdev, pdev.as_ref(), 0)?; + + let driver = KBox::pin_init(try_pin_init!(TyrDriver { device: tdev }), GFP_KERNEL)?; + + // We need this to be dev_info!() because dev_dbg!() does not work at + // all in Rust for now, and we need to see whether probe succeeded. + dev_info!(pdev.as_ref(), "Tyr initialized correctly.\n"); + Ok(driver) + } +} + +#[pinned_drop] +impl PinnedDrop for TyrDriver { + fn drop(self: Pin<&mut Self>) {} +} + +#[pinned_drop] +impl PinnedDrop for TyrData { + fn drop(self: Pin<&mut Self>) { + // TODO: the type-state pattern for Clks will fix this. + let clks = self.clks.lock(); + clks.core.disable_unprepare(); + clks.stacks.disable_unprepare(); + clks.coregroup.disable_unprepare(); + } +} + +// We need to retain the name "panthor" to achieve drop-in compatibility with +// the C driver in the userspace stack. +const INFO: drm::DriverInfo = drm::DriverInfo { + major: 1, + minor: 5, + patchlevel: 0, + name: c_str!("panthor"), + desc: c_str!("ARM Mali Tyr DRM driver"), +}; + +#[vtable] +impl drm::Driver for TyrDriver { + type Data = TyrData; + type File = File; + type Object = drm::gem::Object<TyrObject>; + + const INFO: drm::DriverInfo = INFO; + + kernel::declare_drm_ioctls! { + (PANTHOR_DEV_QUERY, drm_panthor_dev_query, ioctl::RENDER_ALLOW, File::dev_query), + } +} + +#[pin_data] +struct Clocks { + core: Clk, + stacks: OptionalClk, + coregroup: OptionalClk, +} + +#[pin_data] +struct Regulators { + mali: Regulator<regulator::Enabled>, + sram: Regulator<regulator::Enabled>, +} diff --git a/drivers/gpu/drm/tyr/file.rs b/drivers/gpu/drm/tyr/file.rs new file mode 100644 index 000000000000..0ef432947b73 --- /dev/null +++ b/drivers/gpu/drm/tyr/file.rs @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 or MIT + +use kernel::drm; +use kernel::prelude::*; +use kernel::uaccess::UserSlice; +use kernel::uapi; + +use crate::driver::TyrDevice; +use crate::TyrDriver; + +#[pin_data] +pub(crate) struct File {} + +/// Convenience type alias for our DRM `File` type +pub(crate) type DrmFile = drm::file::File<File>; + +impl drm::file::DriverFile for File { + type Driver = TyrDriver; + + fn open(_dev: &drm::Device<Self::Driver>) -> Result<Pin<KBox<Self>>> { + KBox::try_pin_init(try_pin_init!(Self {}), GFP_KERNEL) + } +} + +impl File { + pub(crate) fn dev_query( + tdev: &TyrDevice, + devquery: &mut uapi::drm_panthor_dev_query, + _file: &DrmFile, + ) -> Result<u32> { + if devquery.pointer == 0 { + match devquery.type_ { + uapi::drm_panthor_dev_query_type_DRM_PANTHOR_DEV_QUERY_GPU_INFO => { + devquery.size = core::mem::size_of_val(&tdev.gpu_info) as u32; + Ok(0) + } + _ => Err(EINVAL), + } + } else { + match devquery.type_ { + uapi::drm_panthor_dev_query_type_DRM_PANTHOR_DEV_QUERY_GPU_INFO => { + let mut writer = UserSlice::new( + UserPtr::from_addr(devquery.pointer as usize), + devquery.size as usize, + ) + .writer(); + + writer.write(&tdev.gpu_info)?; + + Ok(0) + } + _ => Err(EINVAL), + } + } + } +} diff --git a/drivers/gpu/drm/tyr/gem.rs b/drivers/gpu/drm/tyr/gem.rs new file mode 100644 index 000000000000..1273bf89dbd5 --- /dev/null +++ b/drivers/gpu/drm/tyr/gem.rs @@ -0,0 +1,18 @@ +// SPDX-License-Identifier: GPL-2.0 or MIT + +use crate::driver::TyrDevice; +use crate::driver::TyrDriver; +use kernel::drm::gem; +use kernel::prelude::*; + +/// GEM Object inner driver data +#[pin_data] +pub(crate) struct TyrObject {} + +impl gem::DriverObject for TyrObject { + type Driver = TyrDriver; + + fn new(_dev: &TyrDevice, _size: usize) -> impl PinInit<Self, Error> { + try_pin_init!(TyrObject {}) + } +} diff --git a/drivers/gpu/drm/tyr/gpu.rs b/drivers/gpu/drm/tyr/gpu.rs new file mode 100644 index 000000000000..6c582910dd5d --- /dev/null +++ b/drivers/gpu/drm/tyr/gpu.rs @@ -0,0 +1,219 @@ +// SPDX-License-Identifier: GPL-2.0 or MIT + +use kernel::bits::genmask_u32; +use kernel::device::Bound; +use kernel::device::Device; +use kernel::devres::Devres; +use kernel::platform; +use kernel::prelude::*; +use kernel::time; +use kernel::transmute::AsBytes; + +use crate::driver::IoMem; +use crate::regs; + +/// Struct containing information that can be queried by userspace. This is read from +/// the GPU's registers. +/// +/// # Invariants +/// +/// - The layout of this struct identical to the C `struct drm_panthor_gpu_info`. +#[repr(C)] +pub(crate) struct GpuInfo { + pub(crate) gpu_id: u32, + pub(crate) gpu_rev: u32, + pub(crate) csf_id: u32, + pub(crate) l2_features: u32, + pub(crate) tiler_features: u32, + pub(crate) mem_features: u32, + pub(crate) mmu_features: u32, + pub(crate) thread_features: u32, + pub(crate) max_threads: u32, + pub(crate) thread_max_workgroup_size: u32, + pub(crate) thread_max_barrier_size: u32, + pub(crate) coherency_features: u32, + pub(crate) texture_features: [u32; 4], + pub(crate) as_present: u32, + pub(crate) pad0: u32, + pub(crate) shader_present: u64, + pub(crate) l2_present: u64, + pub(crate) tiler_present: u64, + pub(crate) core_features: u32, + pub(crate) pad: u32, +} + +impl GpuInfo { + pub(crate) fn new(dev: &Device<Bound>, iomem: &Devres<IoMem>) -> Result<Self> { + let gpu_id = regs::GPU_ID.read(dev, iomem)?; + let csf_id = regs::GPU_CSF_ID.read(dev, iomem)?; + let gpu_rev = regs::GPU_REVID.read(dev, iomem)?; + let core_features = regs::GPU_CORE_FEATURES.read(dev, iomem)?; + let l2_features = regs::GPU_L2_FEATURES.read(dev, iomem)?; + let tiler_features = regs::GPU_TILER_FEATURES.read(dev, iomem)?; + let mem_features = regs::GPU_MEM_FEATURES.read(dev, iomem)?; + let mmu_features = regs::GPU_MMU_FEATURES.read(dev, iomem)?; + let thread_features = regs::GPU_THREAD_FEATURES.read(dev, iomem)?; + let max_threads = regs::GPU_THREAD_MAX_THREADS.read(dev, iomem)?; + let thread_max_workgroup_size = regs::GPU_THREAD_MAX_WORKGROUP_SIZE.read(dev, iomem)?; + let thread_max_barrier_size = regs::GPU_THREAD_MAX_BARRIER_SIZE.read(dev, iomem)?; + let coherency_features = regs::GPU_COHERENCY_FEATURES.read(dev, iomem)?; + + let texture_features = regs::GPU_TEXTURE_FEATURES0.read(dev, iomem)?; + + let as_present = regs::GPU_AS_PRESENT.read(dev, iomem)?; + + let shader_present = u64::from(regs::GPU_SHADER_PRESENT_LO.read(dev, iomem)?); + let shader_present = + shader_present | u64::from(regs::GPU_SHADER_PRESENT_HI.read(dev, iomem)?) << 32; + + let tiler_present = u64::from(regs::GPU_TILER_PRESENT_LO.read(dev, iomem)?); + let tiler_present = + tiler_present | u64::from(regs::GPU_TILER_PRESENT_HI.read(dev, iomem)?) << 32; + + let l2_present = u64::from(regs::GPU_L2_PRESENT_LO.read(dev, iomem)?); + let l2_present = l2_present | u64::from(regs::GPU_L2_PRESENT_HI.read(dev, iomem)?) << 32; + + Ok(Self { + gpu_id, + gpu_rev, + csf_id, + l2_features, + tiler_features, + mem_features, + mmu_features, + thread_features, + max_threads, + thread_max_workgroup_size, + thread_max_barrier_size, + coherency_features, + // TODO: Add texture_features_{1,2,3}. + texture_features: [texture_features, 0, 0, 0], + as_present, + pad0: 0, + shader_present, + l2_present, + tiler_present, + core_features, + pad: 0, + }) + } + + pub(crate) fn log(&self, pdev: &platform::Device) { + let major = (self.gpu_id >> 16) & 0xff; + let minor = (self.gpu_id >> 8) & 0xff; + let status = self.gpu_id & 0xff; + + let model_name = if let Some(model) = GPU_MODELS + .iter() + .find(|&f| f.major == major && f.minor == minor) + { + model.name + } else { + "unknown" + }; + + dev_info!( + pdev.as_ref(), + "mali-{} id 0x{:x} major 0x{:x} minor 0x{:x} status 0x{:x}", + model_name, + self.gpu_id >> 16, + major, + minor, + status + ); + + dev_info!( + pdev.as_ref(), + "Features: L2:{:#x} Tiler:{:#x} Mem:{:#x} MMU:{:#x} AS:{:#x}", + self.l2_features, + self.tiler_features, + self.mem_features, + self.mmu_features, + self.as_present + ); + + dev_info!( + pdev.as_ref(), + "shader_present=0x{:016x} l2_present=0x{:016x} tiler_present=0x{:016x}", + self.shader_present, + self.l2_present, + self.tiler_present + ); + } + + /// Returns the number of virtual address bits supported by the GPU. + #[expect(dead_code)] + pub(crate) fn va_bits(&self) -> u32 { + self.mmu_features & genmask_u32(0..=7) + } + + /// Returns the number of physical address bits supported by the GPU. + #[expect(dead_code)] + pub(crate) fn pa_bits(&self) -> u32 { + (self.mmu_features >> 8) & genmask_u32(0..=7) + } +} + +// SAFETY: `GpuInfo`'s invariant guarantees that it is the same type that is +// already exposed to userspace by the C driver. This implies that it fulfills +// the requirements for `AsBytes`. +// +// This means: +// +// - No implicit padding, +// - No kernel pointers, +// - No interior mutability. +unsafe impl AsBytes for GpuInfo {} + +struct GpuModels { + name: &'static str, + major: u32, + minor: u32, +} + +const GPU_MODELS: [GpuModels; 1] = [GpuModels { + name: "g610", + major: 10, + minor: 7, +}]; + +#[allow(dead_code)] +pub(crate) struct GpuId { + pub(crate) arch_major: u32, + pub(crate) arch_minor: u32, + pub(crate) arch_rev: u32, + pub(crate) prod_major: u32, + pub(crate) ver_major: u32, + pub(crate) ver_minor: u32, + pub(crate) ver_status: u32, +} + +impl From<u32> for GpuId { + fn from(value: u32) -> Self { + GpuId { + arch_major: (value & genmask_u32(28..=31)) >> 28, + arch_minor: (value & genmask_u32(24..=27)) >> 24, + arch_rev: (value & genmask_u32(20..=23)) >> 20, + prod_major: (value & genmask_u32(16..=19)) >> 16, + ver_major: (value & genmask_u32(12..=15)) >> 12, + ver_minor: (value & genmask_u32(4..=11)) >> 4, + ver_status: value & genmask_u32(0..=3), + } + } +} + +/// Powers on the l2 block. +pub(crate) fn l2_power_on(dev: &Device<Bound>, iomem: &Devres<IoMem>) -> Result { + regs::L2_PWRON_LO.write(dev, iomem, 1)?; + + // TODO: We cannot poll, as there is no support in Rust currently, so we + // sleep. Change this when read_poll_timeout() is implemented in Rust. + kernel::time::delay::fsleep(time::Delta::from_millis(100)); + + if regs::L2_READY_LO.read(dev, iomem)? != 1 { + dev_err!(dev, "Failed to power on the GPU\n"); + return Err(EIO); + } + + Ok(()) +} diff --git a/drivers/gpu/drm/tyr/regs.rs b/drivers/gpu/drm/tyr/regs.rs new file mode 100644 index 000000000000..f46933aaa221 --- /dev/null +++ b/drivers/gpu/drm/tyr/regs.rs @@ -0,0 +1,108 @@ +// SPDX-License-Identifier: GPL-2.0 or MIT + +// We don't expect that all the registers and fields will be used, even in the +// future. +// +// Nevertheless, it is useful to have most of them defined, like the C driver +// does. +#![allow(dead_code)] + +use kernel::bits::bit_u32; +use kernel::device::Bound; +use kernel::device::Device; +use kernel::devres::Devres; +use kernel::prelude::*; + +use crate::driver::IoMem; + +/// Represents a register in the Register Set +/// +/// TODO: Replace this with the Nova `register!()` macro when it is available. +/// In particular, this will automatically give us 64bit register reads and +/// writes. +pub(crate) struct Register<const OFFSET: usize>; + +impl<const OFFSET: usize> Register<OFFSET> { + #[inline] + pub(crate) fn read(&self, dev: &Device<Bound>, iomem: &Devres<IoMem>) -> Result<u32> { + let value = (*iomem).access(dev)?.read32(OFFSET); + Ok(value) + } + + #[inline] + pub(crate) fn write(&self, dev: &Device<Bound>, iomem: &Devres<IoMem>, value: u32) -> Result { + (*iomem).access(dev)?.write32(value, OFFSET); + Ok(()) + } +} + +pub(crate) const GPU_ID: Register<0x0> = Register; +pub(crate) const GPU_L2_FEATURES: Register<0x4> = Register; +pub(crate) const GPU_CORE_FEATURES: Register<0x8> = Register; +pub(crate) const GPU_CSF_ID: Register<0x1c> = Register; +pub(crate) const GPU_REVID: Register<0x280> = Register; +pub(crate) const GPU_TILER_FEATURES: Register<0xc> = Register; +pub(crate) const GPU_MEM_FEATURES: Register<0x10> = Register; +pub(crate) const GPU_MMU_FEATURES: Register<0x14> = Register; +pub(crate) const GPU_AS_PRESENT: Register<0x18> = Register; +pub(crate) const GPU_IRQ_RAWSTAT: Register<0x20> = Register; + +pub(crate) const GPU_IRQ_RAWSTAT_FAULT: u32 = bit_u32(0); +pub(crate) const GPU_IRQ_RAWSTAT_PROTECTED_FAULT: u32 = bit_u32(1); +pub(crate) const GPU_IRQ_RAWSTAT_RESET_COMPLETED: u32 = bit_u32(8); +pub(crate) const GPU_IRQ_RAWSTAT_POWER_CHANGED_SINGLE: u32 = bit_u32(9); +pub(crate) const GPU_IRQ_RAWSTAT_POWER_CHANGED_ALL: u32 = bit_u32(10); +pub(crate) const GPU_IRQ_RAWSTAT_CLEAN_CACHES_COMPLETED: u32 = bit_u32(17); +pub(crate) const GPU_IRQ_RAWSTAT_DOORBELL_STATUS: u32 = bit_u32(18); +pub(crate) const GPU_IRQ_RAWSTAT_MCU_STATUS: u32 = bit_u32(19); + +pub(crate) const GPU_IRQ_CLEAR: Register<0x24> = Register; +pub(crate) const GPU_IRQ_MASK: Register<0x28> = Register; +pub(crate) const GPU_IRQ_STAT: Register<0x2c> = Register; +pub(crate) const GPU_CMD: Register<0x30> = Register; +pub(crate) const GPU_CMD_SOFT_RESET: u32 = 1 | (1 << 8); +pub(crate) const GPU_CMD_HARD_RESET: u32 = 1 | (2 << 8); +pub(crate) const GPU_THREAD_FEATURES: Register<0xac> = Register; +pub(crate) const GPU_THREAD_MAX_THREADS: Register<0xa0> = Register; +pub(crate) const GPU_THREAD_MAX_WORKGROUP_SIZE: Register<0xa4> = Register; +pub(crate) const GPU_THREAD_MAX_BARRIER_SIZE: Register<0xa8> = Register; +pub(crate) const GPU_TEXTURE_FEATURES0: Register<0xb0> = Register; +pub(crate) const GPU_SHADER_PRESENT_LO: Register<0x100> = Register; +pub(crate) const GPU_SHADER_PRESENT_HI: Register<0x104> = Register; +pub(crate) const GPU_TILER_PRESENT_LO: Register<0x110> = Register; +pub(crate) const GPU_TILER_PRESENT_HI: Register<0x114> = Register; +pub(crate) const GPU_L2_PRESENT_LO: Register<0x120> = Register; +pub(crate) const GPU_L2_PRESENT_HI: Register<0x124> = Register; +pub(crate) const L2_READY_LO: Register<0x160> = Register; +pub(crate) const L2_READY_HI: Register<0x164> = Register; +pub(crate) const L2_PWRON_LO: Register<0x1a0> = Register; +pub(crate) const L2_PWRON_HI: Register<0x1a4> = Register; +pub(crate) const L2_PWRTRANS_LO: Register<0x220> = Register; +pub(crate) const L2_PWRTRANS_HI: Register<0x204> = Register; +pub(crate) const L2_PWRACTIVE_LO: Register<0x260> = Register; +pub(crate) const L2_PWRACTIVE_HI: Register<0x264> = Register; + +pub(crate) const MCU_CONTROL: Register<0x700> = Register; +pub(crate) const MCU_CONTROL_ENABLE: u32 = 1; +pub(crate) const MCU_CONTROL_AUTO: u32 = 2; +pub(crate) const MCU_CONTROL_DISABLE: u32 = 0; + +pub(crate) const MCU_STATUS: Register<0x704> = Register; +pub(crate) const MCU_STATUS_DISABLED: u32 = 0; +pub(crate) const MCU_STATUS_ENABLED: u32 = 1; +pub(crate) const MCU_STATUS_HALT: u32 = 2; +pub(crate) const MCU_STATUS_FATAL: u32 = 3; + +pub(crate) const GPU_COHERENCY_FEATURES: Register<0x300> = Register; + +pub(crate) const JOB_IRQ_RAWSTAT: Register<0x1000> = Register; +pub(crate) const JOB_IRQ_CLEAR: Register<0x1004> = Register; +pub(crate) const JOB_IRQ_MASK: Register<0x1008> = Register; +pub(crate) const JOB_IRQ_STAT: Register<0x100c> = Register; + +pub(crate) const JOB_IRQ_GLOBAL_IF: u32 = bit_u32(31); + +pub(crate) const MMU_IRQ_RAWSTAT: Register<0x2000> = Register; +pub(crate) const MMU_IRQ_CLEAR: Register<0x2004> = Register; +pub(crate) const MMU_IRQ_MASK: Register<0x2008> = Register; +pub(crate) const MMU_IRQ_STAT: Register<0x200c> = Register; diff --git a/drivers/gpu/drm/tyr/tyr.rs b/drivers/gpu/drm/tyr/tyr.rs new file mode 100644 index 000000000000..861d1db43072 --- /dev/null +++ b/drivers/gpu/drm/tyr/tyr.rs @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 or MIT + +//! Arm Mali Tyr DRM driver. +//! +//! The name "Tyr" is inspired by Norse mythology, reflecting Arm's tradition of +//! naming their GPUs after Nordic mythological figures and places. + +use crate::driver::TyrDriver; + +mod driver; +mod file; +mod gem; +mod gpu; +mod regs; + +kernel::module_platform_driver! { + type: TyrDriver, + name: "tyr", + authors: ["The Tyr driver authors"], + description: "Arm Mali Tyr DRM driver", + license: "Dual MIT/GPL", +} diff --git a/drivers/gpu/nova-core/driver.rs b/drivers/gpu/nova-core/driver.rs index 274989ea1fb4..1380b47617f7 100644 --- a/drivers/gpu/nova-core/driver.rs +++ b/drivers/gpu/nova-core/driver.rs @@ -34,14 +34,19 @@ impl pci::Driver for NovaCore { pdev.enable_device_mem()?; pdev.set_master(); - let bar = Arc::pin_init( + let devres_bar = Arc::pin_init( pdev.iomap_region_sized::<BAR0_SIZE>(0, c_str!("nova-core/bar0")), GFP_KERNEL, )?; + // Used to provided a `&Bar0` to `Gpu::new` without tying it to the lifetime of + // `devres_bar`. + let bar_clone = Arc::clone(&devres_bar); + let bar = bar_clone.access(pdev.as_ref())?; + let this = KBox::pin_init( try_pin_init!(Self { - gpu <- Gpu::new(pdev, bar)?, + gpu <- Gpu::new(pdev, devres_bar, bar), _reg: auxiliary::Registration::new( pdev.as_ref(), c_str!("nova-drm"), @@ -54,4 +59,8 @@ impl pci::Driver for NovaCore { Ok(this) } + + fn unbind(pdev: &pci::Device<Core>, this: Pin<&Self>) { + this.gpu.unbind(pdev.as_ref()); + } } diff --git a/drivers/gpu/nova-core/falcon.rs b/drivers/gpu/nova-core/falcon.rs index 50437c67c14a..37e6298195e4 100644 --- a/drivers/gpu/nova-core/falcon.rs +++ b/drivers/gpu/nova-core/falcon.rs @@ -4,16 +4,17 @@ use core::ops::Deref; use hal::FalconHal; -use kernel::bindings; use kernel::device; +use kernel::dma::DmaAddress; use kernel::prelude::*; +use kernel::sync::aref::ARef; use kernel::time::Delta; -use kernel::types::ARef; use crate::dma::DmaObject; use crate::driver::Bar0; use crate::gpu::Chipset; use crate::regs; +use crate::regs::macros::RegisterBase; use crate::util; pub(crate) mod gsp; @@ -274,14 +275,25 @@ impl From<bool> for FalconFbifMemType { } } -/// Trait defining the parameters of a given Falcon instance. -pub(crate) trait FalconEngine: Sync { - /// Base I/O address for the falcon, relative from which its registers are accessed. - const BASE: usize; +/// Type used to represent the `PFALCON` registers address base for a given falcon engine. +pub(crate) struct PFalconBase(()); + +/// Type used to represent the `PFALCON2` registers address base for a given falcon engine. +pub(crate) struct PFalcon2Base(()); + +/// Trait defining the parameters of a given Falcon engine. +/// +/// Each engine provides one base for `PFALCON` and `PFALCON2` registers. The `ID` constant is used +/// to identify a given Falcon instance with register I/O methods. +pub(crate) trait FalconEngine: + Send + Sync + RegisterBase<PFalconBase> + RegisterBase<PFalcon2Base> + Sized +{ + /// Singleton of the engine, used to identify it with register I/O methods. + const ID: Self; } /// Represents a portion of the firmware to be loaded into a particular memory (e.g. IMEM or DMEM). -#[derive(Debug)] +#[derive(Debug, Clone)] pub(crate) struct FalconLoadTarget { /// Offset from the start of the source object to copy from. pub(crate) src_start: u32, @@ -292,7 +304,7 @@ pub(crate) struct FalconLoadTarget { } /// Parameters for the falcon boot ROM. -#[derive(Debug)] +#[derive(Debug, Clone)] pub(crate) struct FalconBromParams { /// Offset in `DMEM`` of the firmware's signature. pub(crate) pkc_data_offset: u32, @@ -343,13 +355,13 @@ impl<E: FalconEngine + 'static> Falcon<E> { bar: &Bar0, need_riscv: bool, ) -> Result<Self> { - let hwcfg1 = regs::NV_PFALCON_FALCON_HWCFG1::read(bar, E::BASE); + let hwcfg1 = regs::NV_PFALCON_FALCON_HWCFG1::read(bar, &E::ID); // Check that the revision and security model contain valid values. let _ = hwcfg1.core_rev()?; let _ = hwcfg1.security_model()?; if need_riscv { - let hwcfg2 = regs::NV_PFALCON_FALCON_HWCFG2::read(bar, E::BASE); + let hwcfg2 = regs::NV_PFALCON_FALCON_HWCFG2::read(bar, &E::ID); if !hwcfg2.riscv() { dev_err!( dev, @@ -369,7 +381,7 @@ impl<E: FalconEngine + 'static> Falcon<E> { fn reset_wait_mem_scrubbing(&self, bar: &Bar0) -> Result { // TIMEOUT: memory scrubbing should complete in less than 20ms. util::wait_on(Delta::from_millis(20), || { - if regs::NV_PFALCON_FALCON_HWCFG2::read(bar, E::BASE).mem_scrubbing_done() { + if regs::NV_PFALCON_FALCON_HWCFG2::read(bar, &E::ID).mem_scrubbing_done() { Some(()) } else { None @@ -379,12 +391,12 @@ impl<E: FalconEngine + 'static> Falcon<E> { /// Reset the falcon engine. fn reset_eng(&self, bar: &Bar0) -> Result { - let _ = regs::NV_PFALCON_FALCON_HWCFG2::read(bar, E::BASE); + let _ = regs::NV_PFALCON_FALCON_HWCFG2::read(bar, &E::ID); // According to OpenRM's `kflcnPreResetWait_GA102` documentation, HW sometimes does not set // RESET_READY so a non-failing timeout is used. let _ = util::wait_on(Delta::from_micros(150), || { - let r = regs::NV_PFALCON_FALCON_HWCFG2::read(bar, E::BASE); + let r = regs::NV_PFALCON_FALCON_HWCFG2::read(bar, &E::ID); if r.reset_ready() { Some(()) } else { @@ -392,13 +404,13 @@ impl<E: FalconEngine + 'static> Falcon<E> { } }); - regs::NV_PFALCON_FALCON_ENGINE::alter(bar, E::BASE, |v| v.set_reset(true)); + regs::NV_PFALCON_FALCON_ENGINE::alter(bar, &E::ID, |v| v.set_reset(true)); // TODO[DLAY]: replace with udelay() or equivalent once available. // TIMEOUT: falcon engine should not take more than 10us to reset. let _: Result = util::wait_on(Delta::from_micros(10), || None); - regs::NV_PFALCON_FALCON_ENGINE::alter(bar, E::BASE, |v| v.set_reset(false)); + regs::NV_PFALCON_FALCON_ENGINE::alter(bar, &E::ID, |v| v.set_reset(false)); self.reset_wait_mem_scrubbing(bar)?; @@ -413,7 +425,7 @@ impl<E: FalconEngine + 'static> Falcon<E> { regs::NV_PFALCON_FALCON_RM::default() .set_value(regs::NV_PMC_BOOT_0::read(bar).into()) - .write(bar, E::BASE); + .write(bar, &E::ID); Ok(()) } @@ -443,7 +455,7 @@ impl<E: FalconEngine + 'static> Falcon<E> { fw.dma_handle_with_offset(load_offsets.src_start as usize)?, ), }; - if dma_start % bindings::dma_addr_t::from(DMA_LEN) > 0 { + if dma_start % DmaAddress::from(DMA_LEN) > 0 { dev_err!( self.dev, "DMA transfer start addresses must be a multiple of {}", @@ -451,44 +463,57 @@ impl<E: FalconEngine + 'static> Falcon<E> { ); return Err(EINVAL); } - if load_offsets.len % DMA_LEN > 0 { - dev_err!( - self.dev, - "DMA transfer length must be a multiple of {}", - DMA_LEN - ); - return Err(EINVAL); - } + + // DMA transfers can only be done in units of 256 bytes. Compute how many such transfers we + // need to perform. + let num_transfers = load_offsets.len.div_ceil(DMA_LEN); + + // Check that the area we are about to transfer is within the bounds of the DMA object. + // Upper limit of transfer is `(num_transfers * DMA_LEN) + load_offsets.src_start`. + match num_transfers + .checked_mul(DMA_LEN) + .and_then(|size| size.checked_add(load_offsets.src_start)) + { + None => { + dev_err!(self.dev, "DMA transfer length overflow"); + return Err(EOVERFLOW); + } + Some(upper_bound) if upper_bound as usize > fw.size() => { + dev_err!(self.dev, "DMA transfer goes beyond range of DMA object"); + return Err(EINVAL); + } + Some(_) => (), + }; // Set up the base source DMA address. regs::NV_PFALCON_FALCON_DMATRFBASE::default() .set_base((dma_start >> 8) as u32) - .write(bar, E::BASE); + .write(bar, &E::ID); regs::NV_PFALCON_FALCON_DMATRFBASE1::default() .set_base((dma_start >> 40) as u16) - .write(bar, E::BASE); + .write(bar, &E::ID); let cmd = regs::NV_PFALCON_FALCON_DMATRFCMD::default() .set_size(DmaTrfCmdSize::Size256B) .set_imem(target_mem == FalconMem::Imem) .set_sec(if sec { 1 } else { 0 }); - for pos in (0..load_offsets.len).step_by(DMA_LEN as usize) { + for pos in (0..num_transfers).map(|i| i * DMA_LEN) { // Perform a transfer of size `DMA_LEN`. regs::NV_PFALCON_FALCON_DMATRFMOFFS::default() .set_offs(load_offsets.dst_start + pos) - .write(bar, E::BASE); + .write(bar, &E::ID); regs::NV_PFALCON_FALCON_DMATRFFBOFFS::default() .set_offs(src_start + pos) - .write(bar, E::BASE); - cmd.write(bar, E::BASE); + .write(bar, &E::ID); + cmd.write(bar, &E::ID); // Wait for the transfer to complete. // TIMEOUT: arbitrarily large value, no DMA transfer to the falcon's small memories // should ever take that long. util::wait_on(Delta::from_secs(2), || { - let r = regs::NV_PFALCON_FALCON_DMATRFCMD::read(bar, E::BASE); + let r = regs::NV_PFALCON_FALCON_DMATRFCMD::read(bar, &E::ID); if r.idle() { Some(()) } else { @@ -502,9 +527,9 @@ impl<E: FalconEngine + 'static> Falcon<E> { /// Perform a DMA load into `IMEM` and `DMEM` of `fw`, and prepare the falcon to run it. pub(crate) fn dma_load<F: FalconFirmware<Target = E>>(&self, bar: &Bar0, fw: &F) -> Result { - regs::NV_PFALCON_FBIF_CTL::alter(bar, E::BASE, |v| v.set_allow_phys_no_ctx(true)); - regs::NV_PFALCON_FALCON_DMACTL::default().write(bar, E::BASE); - regs::NV_PFALCON_FBIF_TRANSCFG::alter(bar, E::BASE, |v| { + regs::NV_PFALCON_FBIF_CTL::alter(bar, &E::ID, |v| v.set_allow_phys_no_ctx(true)); + regs::NV_PFALCON_FALCON_DMACTL::default().write(bar, &E::ID); + regs::NV_PFALCON_FBIF_TRANSCFG::alter(bar, &E::ID, 0, |v| { v.set_target(FalconFbifTarget::CoherentSysmem) .set_mem_type(FalconFbifMemType::Physical) }); @@ -517,7 +542,7 @@ impl<E: FalconEngine + 'static> Falcon<E> { // Set `BootVec` to start of non-secure code. regs::NV_PFALCON_FALCON_BOOTVEC::default() .set_value(fw.boot_addr()) - .write(bar, E::BASE); + .write(bar, &E::ID); Ok(()) } @@ -538,27 +563,27 @@ impl<E: FalconEngine + 'static> Falcon<E> { if let Some(mbox0) = mbox0 { regs::NV_PFALCON_FALCON_MAILBOX0::default() .set_value(mbox0) - .write(bar, E::BASE); + .write(bar, &E::ID); } if let Some(mbox1) = mbox1 { regs::NV_PFALCON_FALCON_MAILBOX1::default() .set_value(mbox1) - .write(bar, E::BASE); + .write(bar, &E::ID); } - match regs::NV_PFALCON_FALCON_CPUCTL::read(bar, E::BASE).alias_en() { + match regs::NV_PFALCON_FALCON_CPUCTL::read(bar, &E::ID).alias_en() { true => regs::NV_PFALCON_FALCON_CPUCTL_ALIAS::default() .set_startcpu(true) - .write(bar, E::BASE), + .write(bar, &E::ID), false => regs::NV_PFALCON_FALCON_CPUCTL::default() .set_startcpu(true) - .write(bar, E::BASE), + .write(bar, &E::ID), } // TIMEOUT: arbitrarily large value, firmwares should complete in less than 2 seconds. util::wait_on(Delta::from_secs(2), || { - let r = regs::NV_PFALCON_FALCON_CPUCTL::read(bar, E::BASE); + let r = regs::NV_PFALCON_FALCON_CPUCTL::read(bar, &E::ID); if r.halted() { Some(()) } else { @@ -567,8 +592,8 @@ impl<E: FalconEngine + 'static> Falcon<E> { })?; let (mbox0, mbox1) = ( - regs::NV_PFALCON_FALCON_MAILBOX0::read(bar, E::BASE).value(), - regs::NV_PFALCON_FALCON_MAILBOX1::read(bar, E::BASE).value(), + regs::NV_PFALCON_FALCON_MAILBOX0::read(bar, &E::ID).value(), + regs::NV_PFALCON_FALCON_MAILBOX1::read(bar, &E::ID).value(), ); Ok((mbox0, mbox1)) diff --git a/drivers/gpu/nova-core/falcon/gsp.rs b/drivers/gpu/nova-core/falcon/gsp.rs index d622e9a64470..f17599cb49fa 100644 --- a/drivers/gpu/nova-core/falcon/gsp.rs +++ b/drivers/gpu/nova-core/falcon/gsp.rs @@ -2,23 +2,31 @@ use crate::{ driver::Bar0, - falcon::{Falcon, FalconEngine}, - regs, + falcon::{Falcon, FalconEngine, PFalcon2Base, PFalconBase}, + regs::{self, macros::RegisterBase}, }; /// Type specifying the `Gsp` falcon engine. Cannot be instantiated. pub(crate) struct Gsp(()); -impl FalconEngine for Gsp { +impl RegisterBase<PFalconBase> for Gsp { const BASE: usize = 0x00110000; } +impl RegisterBase<PFalcon2Base> for Gsp { + const BASE: usize = 0x00111000; +} + +impl FalconEngine for Gsp { + const ID: Self = Gsp(()); +} + impl Falcon<Gsp> { /// Clears the SWGEN0 bit in the Falcon's IRQ status clear register to /// allow GSP to signal CPU for processing new messages in message queue. pub(crate) fn clear_swgen0_intr(&self, bar: &Bar0) { regs::NV_PFALCON_FALCON_IRQSCLR::default() .set_swgen0(true) - .write(bar, Gsp::BASE); + .write(bar, &Gsp::ID); } } diff --git a/drivers/gpu/nova-core/falcon/hal.rs b/drivers/gpu/nova-core/falcon/hal.rs index b233bc365882..bba288455617 100644 --- a/drivers/gpu/nova-core/falcon/hal.rs +++ b/drivers/gpu/nova-core/falcon/hal.rs @@ -13,7 +13,7 @@ mod ga102; /// Implements chipset-specific low-level operations. The trait is generic against [`FalconEngine`] /// so its `BASE` parameter can be used in order to avoid runtime bound checks when accessing /// registers. -pub(crate) trait FalconHal<E: FalconEngine>: Sync { +pub(crate) trait FalconHal<E: FalconEngine>: Send + Sync { /// Activates the Falcon core if the engine is a risvc/falcon dual engine. fn select_core(&self, _falcon: &Falcon<E>, _bar: &Bar0) -> Result { Ok(()) diff --git a/drivers/gpu/nova-core/falcon/hal/ga102.rs b/drivers/gpu/nova-core/falcon/hal/ga102.rs index 52c33d3f22a8..0b1cbe7853b3 100644 --- a/drivers/gpu/nova-core/falcon/hal/ga102.rs +++ b/drivers/gpu/nova-core/falcon/hal/ga102.rs @@ -16,15 +16,15 @@ use crate::util; use super::FalconHal; fn select_core_ga102<E: FalconEngine>(bar: &Bar0) -> Result { - let bcr_ctrl = regs::NV_PRISCV_RISCV_BCR_CTRL::read(bar, E::BASE); + let bcr_ctrl = regs::NV_PRISCV_RISCV_BCR_CTRL::read(bar, &E::ID); if bcr_ctrl.core_select() != PeregrineCoreSelect::Falcon { regs::NV_PRISCV_RISCV_BCR_CTRL::default() .set_core_select(PeregrineCoreSelect::Falcon) - .write(bar, E::BASE); + .write(bar, &E::ID); // TIMEOUT: falcon core should take less than 10ms to report being enabled. util::wait_on(Delta::from_millis(10), || { - let r = regs::NV_PRISCV_RISCV_BCR_CTRL::read(bar, E::BASE); + let r = regs::NV_PRISCV_RISCV_BCR_CTRL::read(bar, &E::ID); if r.valid() { Some(()) } else { @@ -42,50 +42,47 @@ fn signature_reg_fuse_version_ga102( engine_id_mask: u16, ucode_id: u8, ) -> Result<u32> { - // TODO[REGA]: The ucode fuse versions are contained in the - // FUSE_OPT_FPF_<ENGINE>_UCODE<X>_VERSION registers, which are an array. Our register - // definition macros do not allow us to manage them properly, so we need to hardcode their - // addresses for now. Clean this up once we support register arrays. + const NV_FUSE_OPT_FPF_SIZE: u8 = regs::NV_FUSE_OPT_FPF_SIZE as u8; // Each engine has 16 ucode version registers numbered from 1 to 16. - if ucode_id == 0 || ucode_id > 16 { - dev_err!(dev, "invalid ucode id {:#x}", ucode_id); - return Err(EINVAL); - } + let ucode_idx = match ucode_id { + 1..=NV_FUSE_OPT_FPF_SIZE => (ucode_id - 1) as usize, + _ => { + dev_err!(dev, "invalid ucode id {:#x}", ucode_id); + return Err(EINVAL); + } + }; - // Base address of the FUSE registers array corresponding to the engine. - let reg_fuse_base = if engine_id_mask & 0x0001 != 0 { - regs::NV_FUSE_OPT_FPF_SEC2_UCODE1_VERSION::OFFSET + // `ucode_idx` is guaranteed to be in the range [0..15], making the `read` calls provable valid + // at build-time. + let reg_fuse_version = if engine_id_mask & 0x0001 != 0 { + regs::NV_FUSE_OPT_FPF_SEC2_UCODE1_VERSION::read(bar, ucode_idx).data() } else if engine_id_mask & 0x0004 != 0 { - regs::NV_FUSE_OPT_FPF_NVDEC_UCODE1_VERSION::OFFSET + regs::NV_FUSE_OPT_FPF_NVDEC_UCODE1_VERSION::read(bar, ucode_idx).data() } else if engine_id_mask & 0x0400 != 0 { - regs::NV_FUSE_OPT_FPF_GSP_UCODE1_VERSION::OFFSET + regs::NV_FUSE_OPT_FPF_GSP_UCODE1_VERSION::read(bar, ucode_idx).data() } else { dev_err!(dev, "unexpected engine_id_mask {:#x}", engine_id_mask); return Err(EINVAL); }; - // Read `reg_fuse_base[ucode_id - 1]`. - let reg_fuse_version = - bar.read32(reg_fuse_base + ((ucode_id - 1) as usize * core::mem::size_of::<u32>())); - // TODO[NUMM]: replace with `last_set_bit` once it lands. - Ok(u32::BITS - reg_fuse_version.leading_zeros()) + Ok(u16::BITS - reg_fuse_version.leading_zeros()) } fn program_brom_ga102<E: FalconEngine>(bar: &Bar0, params: &FalconBromParams) -> Result { regs::NV_PFALCON2_FALCON_BROM_PARAADDR::default() .set_value(params.pkc_data_offset) - .write(bar, E::BASE); + .write(bar, &E::ID, 0); regs::NV_PFALCON2_FALCON_BROM_ENGIDMASK::default() .set_value(u32::from(params.engine_id_mask)) - .write(bar, E::BASE); + .write(bar, &E::ID); regs::NV_PFALCON2_FALCON_BROM_CURR_UCODE_ID::default() .set_ucode_id(params.ucode_id) - .write(bar, E::BASE); + .write(bar, &E::ID); regs::NV_PFALCON2_FALCON_MOD_SEL::default() .set_algo(FalconModSelAlgo::Rsa3k) - .write(bar, E::BASE); + .write(bar, &E::ID); Ok(()) } diff --git a/drivers/gpu/nova-core/falcon/sec2.rs b/drivers/gpu/nova-core/falcon/sec2.rs index 5147d9e2a7fe..815786c8480d 100644 --- a/drivers/gpu/nova-core/falcon/sec2.rs +++ b/drivers/gpu/nova-core/falcon/sec2.rs @@ -1,10 +1,19 @@ // SPDX-License-Identifier: GPL-2.0 -use crate::falcon::FalconEngine; +use crate::falcon::{FalconEngine, PFalcon2Base, PFalconBase}; +use crate::regs::macros::RegisterBase; /// Type specifying the `Sec2` falcon engine. Cannot be instantiated. pub(crate) struct Sec2(()); -impl FalconEngine for Sec2 { +impl RegisterBase<PFalconBase> for Sec2 { const BASE: usize = 0x00840000; } + +impl RegisterBase<PFalcon2Base> for Sec2 { + const BASE: usize = 0x00841000; +} + +impl FalconEngine for Sec2 { + const ID: Self = Sec2(()); +} diff --git a/drivers/gpu/nova-core/fb.rs b/drivers/gpu/nova-core/fb.rs index 4a702525fff4..68559902ae78 100644 --- a/drivers/gpu/nova-core/fb.rs +++ b/drivers/gpu/nova-core/fb.rs @@ -4,7 +4,7 @@ use core::ops::Range; use kernel::prelude::*; use kernel::sizes::*; -use kernel::types::ARef; +use kernel::sync::aref::ARef; use kernel::{dev_warn, device}; use crate::dma::DmaObject; diff --git a/drivers/gpu/nova-core/firmware.rs b/drivers/gpu/nova-core/firmware.rs index 2931912ddba0..4179a74a2342 100644 --- a/drivers/gpu/nova-core/firmware.rs +++ b/drivers/gpu/nova-core/firmware.rs @@ -4,48 +4,36 @@ //! to be loaded into a given execution unit. use core::marker::PhantomData; +use core::mem::size_of; use kernel::device; use kernel::firmware; use kernel::prelude::*; use kernel::str::CString; +use kernel::transmute::FromBytes; use crate::dma::DmaObject; use crate::falcon::FalconFirmware; use crate::gpu; -use crate::gpu::Chipset; +pub(crate) mod booter; pub(crate) mod fwsec; - -pub(crate) const FIRMWARE_VERSION: &str = "535.113.01"; - -/// Structure encapsulating the firmware blobs required for the GPU to operate. -#[expect(dead_code)] -pub(crate) struct Firmware { - booter_load: firmware::Firmware, - booter_unload: firmware::Firmware, - bootloader: firmware::Firmware, - gsp: firmware::Firmware, -} - -impl Firmware { - pub(crate) fn new(dev: &device::Device, chipset: Chipset, ver: &str) -> Result<Firmware> { - let mut chip_name = CString::try_from_fmt(fmt!("{chipset}"))?; - chip_name.make_ascii_lowercase(); - let chip_name = &*chip_name; - - let request = |name_| { - CString::try_from_fmt(fmt!("nvidia/{chip_name}/gsp/{name_}-{ver}.bin")) - .and_then(|path| firmware::Firmware::request(&path, dev)) - }; - - Ok(Firmware { - booter_load: request("booter_load")?, - booter_unload: request("booter_unload")?, - bootloader: request("bootloader")?, - gsp: request("gsp")?, - }) - } +pub(crate) mod gsp; +pub(crate) mod riscv; + +pub(crate) const FIRMWARE_VERSION: &str = "570.144"; + +/// Requests the GPU firmware `name` suitable for `chipset`, with version `ver`. +fn request_firmware( + dev: &device::Device, + chipset: gpu::Chipset, + name: &str, + ver: &str, +) -> Result<firmware::Firmware> { + let chip_name = chipset.name(); + + CString::try_from_fmt(fmt!("nvidia/{chip_name}/gsp/{name}-{ver}.bin")) + .and_then(|path| firmware::Firmware::request(&path, dev)) } /// Structure used to describe some firmwares, notably FWSEC-FRTS. @@ -150,6 +138,65 @@ impl<F: FalconFirmware> FirmwareDmaObject<F, Unsigned> { } } +/// Header common to most firmware files. +#[repr(C)] +#[derive(Debug, Clone)] +struct BinHdr { + /// Magic number, must be `0x10de`. + bin_magic: u32, + /// Version of the header. + bin_ver: u32, + /// Size in bytes of the binary (to be ignored). + bin_size: u32, + /// Offset of the start of the application-specific header. + header_offset: u32, + /// Offset of the start of the data payload. + data_offset: u32, + /// Size in bytes of the data payload. + data_size: u32, +} + +// SAFETY: all bit patterns are valid for this type, and it doesn't use interior mutability. +unsafe impl FromBytes for BinHdr {} + +// A firmware blob starting with a `BinHdr`. +struct BinFirmware<'a> { + hdr: BinHdr, + fw: &'a [u8], +} + +impl<'a> BinFirmware<'a> { + /// Interpret `fw` as a firmware image starting with a [`BinHdr`], and returns the + /// corresponding [`BinFirmware`] that can be used to extract its payload. + fn new(fw: &'a firmware::Firmware) -> Result<Self> { + const BIN_MAGIC: u32 = 0x10de; + let fw = fw.data(); + + fw.get(0..size_of::<BinHdr>()) + // Extract header. + .and_then(BinHdr::from_bytes_copy) + // Validate header. + .and_then(|hdr| { + if hdr.bin_magic == BIN_MAGIC { + Some(hdr) + } else { + None + } + }) + .map(|hdr| Self { hdr, fw }) + .ok_or(EINVAL) + } + + /// Returns the data payload of the firmware, or `None` if the data range is out of bounds of + /// the firmware image. + fn data(&self) -> Option<&[u8]> { + let fw_start = self.hdr.data_offset as usize; + let fw_size = self.hdr.data_size as usize; + + self.fw.get(fw_start..fw_start + fw_size) + } +} + pub(crate) struct ModInfoBuilder<const N: usize>(firmware::ModInfoBuilder<N>); impl<const N: usize> ModInfoBuilder<N> { @@ -180,8 +227,8 @@ impl<const N: usize> ModInfoBuilder<N> { let mut this = Self(firmware::ModInfoBuilder::new(module_name)); let mut i = 0; - while i < gpu::Chipset::NAMES.len() { - this = this.make_entry_chipset(gpu::Chipset::NAMES[i]); + while i < gpu::Chipset::ALL.len() { + this = this.make_entry_chipset(gpu::Chipset::ALL[i].name()); i += 1; } diff --git a/drivers/gpu/nova-core/firmware/booter.rs b/drivers/gpu/nova-core/firmware/booter.rs new file mode 100644 index 000000000000..b4ff1b17e4a0 --- /dev/null +++ b/drivers/gpu/nova-core/firmware/booter.rs @@ -0,0 +1,375 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Support for loading and patching the `Booter` firmware. `Booter` is a Heavy Secured firmware +//! running on [`Sec2`], that is used on Turing/Ampere to load the GSP firmware into the GSP falcon +//! (and optionally unload it through a separate firmware image). + +use core::marker::PhantomData; +use core::mem::size_of; +use core::ops::Deref; + +use kernel::device; +use kernel::prelude::*; +use kernel::transmute::FromBytes; + +use crate::dma::DmaObject; +use crate::driver::Bar0; +use crate::falcon::sec2::Sec2; +use crate::falcon::{Falcon, FalconBromParams, FalconFirmware, FalconLoadParams, FalconLoadTarget}; +use crate::firmware::{BinFirmware, FirmwareDmaObject, FirmwareSignature, Signed, Unsigned}; +use crate::gpu::Chipset; + +/// Local convenience function to return a copy of `S` by reinterpreting the bytes starting at +/// `offset` in `slice`. +fn frombytes_at<S: FromBytes + Sized>(slice: &[u8], offset: usize) -> Result<S> { + slice + .get(offset..offset + size_of::<S>()) + .and_then(S::from_bytes_copy) + .ok_or(EINVAL) +} + +/// Heavy-Secured firmware header. +/// +/// Such firmwares have an application-specific payload that needs to be patched with a given +/// signature. +#[repr(C)] +#[derive(Debug, Clone)] +struct HsHeaderV2 { + /// Offset to the start of the signatures. + sig_prod_offset: u32, + /// Size in bytes of the signatures. + sig_prod_size: u32, + /// Offset to a `u32` containing the location at which to patch the signature in the microcode + /// image. + patch_loc_offset: u32, + /// Offset to a `u32` containing the index of the signature to patch. + patch_sig_offset: u32, + /// Start offset to the signature metadata. + meta_data_offset: u32, + /// Size in bytes of the signature metadata. + meta_data_size: u32, + /// Offset to a `u32` containing the number of signatures in the signatures section. + num_sig_offset: u32, + /// Offset of the application-specific header. + header_offset: u32, + /// Size in bytes of the application-specific header. + header_size: u32, +} + +// SAFETY: all bit patterns are valid for this type, and it doesn't use interior mutability. +unsafe impl FromBytes for HsHeaderV2 {} + +/// Heavy-Secured Firmware image container. +/// +/// This provides convenient access to the fields of [`HsHeaderV2`] that are actually indices to +/// read from in the firmware data. +struct HsFirmwareV2<'a> { + hdr: HsHeaderV2, + fw: &'a [u8], +} + +impl<'a> HsFirmwareV2<'a> { + /// Interprets the header of `bin_fw` as a [`HsHeaderV2`] and returns an instance of + /// `HsFirmwareV2` for further parsing. + /// + /// Fails if the header pointed at by `bin_fw` is not within the bounds of the firmware image. + fn new(bin_fw: &BinFirmware<'a>) -> Result<Self> { + frombytes_at::<HsHeaderV2>(bin_fw.fw, bin_fw.hdr.header_offset as usize) + .map(|hdr| Self { hdr, fw: bin_fw.fw }) + } + + /// Returns the location at which the signatures should be patched in the microcode image. + /// + /// Fails if the offset of the patch location is outside the bounds of the firmware + /// image. + fn patch_location(&self) -> Result<u32> { + frombytes_at::<u32>(self.fw, self.hdr.patch_loc_offset as usize) + } + + /// Returns an iterator to the signatures of the firmware. The iterator can be empty if the + /// firmware is unsigned. + /// + /// Fails if the pointed signatures are outside the bounds of the firmware image. + fn signatures_iter(&'a self) -> Result<impl Iterator<Item = BooterSignature<'a>>> { + let num_sig = frombytes_at::<u32>(self.fw, self.hdr.num_sig_offset as usize)?; + let iter = match self.hdr.sig_prod_size.checked_div(num_sig) { + // If there are no signatures, return an iterator that will yield zero elements. + None => (&[] as &[u8]).chunks_exact(1), + Some(sig_size) => { + let patch_sig = frombytes_at::<u32>(self.fw, self.hdr.patch_sig_offset as usize)?; + let signatures_start = (self.hdr.sig_prod_offset + patch_sig) as usize; + + self.fw + // Get signatures range. + .get(signatures_start..signatures_start + self.hdr.sig_prod_size as usize) + .ok_or(EINVAL)? + .chunks_exact(sig_size as usize) + } + }; + + // Map the byte slices into signatures. + Ok(iter.map(BooterSignature)) + } +} + +/// Signature parameters, as defined in the firmware. +#[repr(C)] +struct HsSignatureParams { + /// Fuse version to use. + fuse_ver: u32, + /// Mask of engine IDs this firmware applies to. + engine_id_mask: u32, + /// ID of the microcode. + ucode_id: u32, +} + +// SAFETY: all bit patterns are valid for this type, and it doesn't use interior mutability. +unsafe impl FromBytes for HsSignatureParams {} + +impl HsSignatureParams { + /// Returns the signature parameters contained in `hs_fw`. + /// + /// Fails if the meta data parameter of `hs_fw` is outside the bounds of the firmware image, or + /// if its size doesn't match that of [`HsSignatureParams`]. + fn new(hs_fw: &HsFirmwareV2<'_>) -> Result<Self> { + let start = hs_fw.hdr.meta_data_offset as usize; + let end = start + .checked_add(hs_fw.hdr.meta_data_size as usize) + .ok_or(EINVAL)?; + + hs_fw + .fw + .get(start..end) + .and_then(Self::from_bytes_copy) + .ok_or(EINVAL) + } +} + +/// Header for code and data load offsets. +#[repr(C)] +#[derive(Debug, Clone)] +struct HsLoadHeaderV2 { + // Offset at which the code starts. + os_code_offset: u32, + // Total size of the code, for all apps. + os_code_size: u32, + // Offset at which the data starts. + os_data_offset: u32, + // Size of the data. + os_data_size: u32, + // Number of apps following this header. Each app is described by a [`HsLoadHeaderV2App`]. + num_apps: u32, +} + +// SAFETY: all bit patterns are valid for this type, and it doesn't use interior mutability. +unsafe impl FromBytes for HsLoadHeaderV2 {} + +impl HsLoadHeaderV2 { + /// Returns the load header contained in `hs_fw`. + /// + /// Fails if the header pointed at by `hs_fw` is not within the bounds of the firmware image. + fn new(hs_fw: &HsFirmwareV2<'_>) -> Result<Self> { + frombytes_at::<Self>(hs_fw.fw, hs_fw.hdr.header_offset as usize) + } +} + +/// Header for app code loader. +#[repr(C)] +#[derive(Debug, Clone)] +struct HsLoadHeaderV2App { + /// Offset at which to load the app code. + offset: u32, + /// Length in bytes of the app code. + len: u32, +} + +// SAFETY: all bit patterns are valid for this type, and it doesn't use interior mutability. +unsafe impl FromBytes for HsLoadHeaderV2App {} + +impl HsLoadHeaderV2App { + /// Returns the [`HsLoadHeaderV2App`] for app `idx` of `hs_fw`. + /// + /// Fails if `idx` is larger than the number of apps declared in `hs_fw`, or if the header is + /// not within the bounds of the firmware image. + fn new(hs_fw: &HsFirmwareV2<'_>, idx: u32) -> Result<Self> { + let load_hdr = HsLoadHeaderV2::new(hs_fw)?; + if idx >= load_hdr.num_apps { + Err(EINVAL) + } else { + frombytes_at::<Self>( + hs_fw.fw, + (hs_fw.hdr.header_offset as usize) + // Skip the load header... + .checked_add(size_of::<HsLoadHeaderV2>()) + // ... and jump to app header `idx`. + .and_then(|offset| { + offset.checked_add((idx as usize).checked_mul(size_of::<Self>())?) + }) + .ok_or(EINVAL)?, + ) + } + } +} + +/// Signature for Booter firmware. Their size is encoded into the header and not known a compile +/// time, so we just wrap a byte slices on which we can implement [`FirmwareSignature`]. +struct BooterSignature<'a>(&'a [u8]); + +impl<'a> AsRef<[u8]> for BooterSignature<'a> { + fn as_ref(&self) -> &[u8] { + self.0 + } +} + +impl<'a> FirmwareSignature<BooterFirmware> for BooterSignature<'a> {} + +/// The `Booter` loader firmware, responsible for loading the GSP. +pub(crate) struct BooterFirmware { + // Load parameters for `IMEM` falcon memory. + imem_load_target: FalconLoadTarget, + // Load parameters for `DMEM` falcon memory. + dmem_load_target: FalconLoadTarget, + // BROM falcon parameters. + brom_params: FalconBromParams, + // Device-mapped firmware image. + ucode: FirmwareDmaObject<Self, Signed>, +} + +impl FirmwareDmaObject<BooterFirmware, Unsigned> { + fn new_booter(dev: &device::Device<device::Bound>, data: &[u8]) -> Result<Self> { + DmaObject::from_data(dev, data).map(|ucode| Self(ucode, PhantomData)) + } +} + +#[derive(Copy, Clone, Debug, PartialEq)] +pub(crate) enum BooterKind { + Loader, + #[expect(unused)] + Unloader, +} + +impl BooterFirmware { + /// Parses the Booter firmware contained in `fw`, and patches the correct signature so it is + /// ready to be loaded and run on `falcon`. + pub(crate) fn new( + dev: &device::Device<device::Bound>, + kind: BooterKind, + chipset: Chipset, + ver: &str, + falcon: &Falcon<<Self as FalconFirmware>::Target>, + bar: &Bar0, + ) -> Result<Self> { + let fw_name = match kind { + BooterKind::Loader => "booter_load", + BooterKind::Unloader => "booter_unload", + }; + let fw = super::request_firmware(dev, chipset, fw_name, ver)?; + let bin_fw = BinFirmware::new(&fw)?; + + // The binary firmware embeds a Heavy-Secured firmware. + let hs_fw = HsFirmwareV2::new(&bin_fw)?; + + // The Heavy-Secured firmware embeds a firmware load descriptor. + let load_hdr = HsLoadHeaderV2::new(&hs_fw)?; + + // Offset in `ucode` where to patch the signature. + let patch_loc = hs_fw.patch_location()?; + + let sig_params = HsSignatureParams::new(&hs_fw)?; + let brom_params = FalconBromParams { + // `load_hdr.os_data_offset` is an absolute index, but `pkc_data_offset` is from the + // signature patch location. + pkc_data_offset: patch_loc + .checked_sub(load_hdr.os_data_offset) + .ok_or(EINVAL)?, + engine_id_mask: u16::try_from(sig_params.engine_id_mask).map_err(|_| EINVAL)?, + ucode_id: u8::try_from(sig_params.ucode_id).map_err(|_| EINVAL)?, + }; + let app0 = HsLoadHeaderV2App::new(&hs_fw, 0)?; + + // Object containing the firmware microcode to be signature-patched. + let ucode = bin_fw + .data() + .ok_or(EINVAL) + .and_then(|data| FirmwareDmaObject::<Self, _>::new_booter(dev, data))?; + + let ucode_signed = { + let mut signatures = hs_fw.signatures_iter()?.peekable(); + + if signatures.peek().is_none() { + // If there are no signatures, then the firmware is unsigned. + ucode.no_patch_signature() + } else { + // Obtain the version from the fuse register, and extract the corresponding + // signature. + let reg_fuse_version = falcon.signature_reg_fuse_version( + bar, + brom_params.engine_id_mask, + brom_params.ucode_id, + )?; + + // `0` means the last signature should be used. + const FUSE_VERSION_USE_LAST_SIG: u32 = 0; + let signature = match reg_fuse_version { + FUSE_VERSION_USE_LAST_SIG => signatures.last(), + // Otherwise hardware fuse version needs to be subtracted to obtain the index. + reg_fuse_version => { + let Some(idx) = sig_params.fuse_ver.checked_sub(reg_fuse_version) else { + dev_err!(dev, "invalid fuse version for Booter firmware\n"); + return Err(EINVAL); + }; + signatures.nth(idx as usize) + } + } + .ok_or(EINVAL)?; + + ucode.patch_signature(&signature, patch_loc as usize)? + } + }; + + Ok(Self { + imem_load_target: FalconLoadTarget { + src_start: app0.offset, + dst_start: 0, + len: app0.len, + }, + dmem_load_target: FalconLoadTarget { + src_start: load_hdr.os_data_offset, + dst_start: 0, + len: load_hdr.os_data_size, + }, + brom_params, + ucode: ucode_signed, + }) + } +} + +impl FalconLoadParams for BooterFirmware { + fn imem_load_params(&self) -> FalconLoadTarget { + self.imem_load_target.clone() + } + + fn dmem_load_params(&self) -> FalconLoadTarget { + self.dmem_load_target.clone() + } + + fn brom_params(&self) -> FalconBromParams { + self.brom_params.clone() + } + + fn boot_addr(&self) -> u32 { + self.imem_load_target.src_start + } +} + +impl Deref for BooterFirmware { + type Target = DmaObject; + + fn deref(&self) -> &Self::Target { + &self.ucode.0 + } +} + +impl FalconFirmware for BooterFirmware { + type Target = Sec2; +} diff --git a/drivers/gpu/nova-core/firmware/fwsec.rs b/drivers/gpu/nova-core/firmware/fwsec.rs index 0dff3cfa90af..8edbb5c0572c 100644 --- a/drivers/gpu/nova-core/firmware/fwsec.rs +++ b/drivers/gpu/nova-core/firmware/fwsec.rs @@ -202,9 +202,6 @@ pub(crate) struct FwsecFirmware { ucode: FirmwareDmaObject<Self, Signed>, } -// We need to load full DMEM pages. -const DMEM_LOAD_SIZE_ALIGN: u32 = 256; - impl FalconLoadParams for FwsecFirmware { fn imem_load_params(&self) -> FalconLoadTarget { FalconLoadTarget { @@ -218,11 +215,7 @@ impl FalconLoadParams for FwsecFirmware { FalconLoadTarget { src_start: self.desc.imem_load_size, dst_start: self.desc.dmem_phys_base, - // TODO[NUMM]: replace with `align_up` once it lands. - len: self - .desc - .dmem_load_size - .next_multiple_of(DMEM_LOAD_SIZE_ALIGN), + len: self.desc.dmem_load_size, } } @@ -253,8 +246,8 @@ impl FalconFirmware for FwsecFirmware { impl FirmwareDmaObject<FwsecFirmware, Unsigned> { fn new_fwsec(dev: &Device<device::Bound>, bios: &Vbios, cmd: FwsecCommand) -> Result<Self> { - let desc = bios.fwsec_image().header(dev)?; - let ucode = bios.fwsec_image().ucode(dev, desc)?; + let desc = bios.fwsec_image().header()?; + let ucode = bios.fwsec_image().ucode(desc)?; let mut dma_object = DmaObject::from_data(dev, ucode)?; let hdr_offset = (desc.imem_load_size + desc.interface_offset) as usize; @@ -343,7 +336,7 @@ impl FwsecFirmware { let ucode_dma = FirmwareDmaObject::<Self, _>::new_fwsec(dev, bios, cmd)?; // Patch signature if needed. - let desc = bios.fwsec_image().header(dev)?; + let desc = bios.fwsec_image().header()?; let ucode_signed = if desc.signature_count != 0 { let sig_base_img = (desc.imem_load_size + desc.pkc_data_offset) as usize; let desc_sig_versions = u32::from(desc.signature_versions); @@ -382,7 +375,7 @@ impl FwsecFirmware { dev_dbg!(dev, "patching signature with index {}\n", signature_idx); let signature = bios .fwsec_image() - .sigs(dev, desc) + .sigs(desc) .and_then(|sigs| sigs.get(signature_idx).ok_or(EINVAL))?; ucode_dma.patch_signature(signature, sig_base_img)? diff --git a/drivers/gpu/nova-core/firmware/gsp.rs b/drivers/gpu/nova-core/firmware/gsp.rs new file mode 100644 index 000000000000..9b70095434c6 --- /dev/null +++ b/drivers/gpu/nova-core/firmware/gsp.rs @@ -0,0 +1,243 @@ +// SPDX-License-Identifier: GPL-2.0 + +use core::mem::size_of_val; + +use kernel::device; +use kernel::dma::{DataDirection, DmaAddress}; +use kernel::kvec; +use kernel::prelude::*; +use kernel::scatterlist::{Owned, SGTable}; + +use crate::dma::DmaObject; +use crate::firmware::riscv::RiscvFirmware; +use crate::gpu::{Architecture, Chipset}; +use crate::gsp::GSP_PAGE_SIZE; + +/// Ad-hoc and temporary module to extract sections from ELF images. +/// +/// Some firmware images are currently packaged as ELF files, where sections names are used as keys +/// to specific and related bits of data. Future firmware versions are scheduled to move away from +/// that scheme before nova-core becomes stable, which means this module will eventually be +/// removed. +mod elf { + use core::mem::size_of; + + use kernel::bindings; + use kernel::str::CStr; + use kernel::transmute::FromBytes; + + /// Newtype to provide a [`FromBytes`] implementation. + #[repr(transparent)] + struct Elf64Hdr(bindings::elf64_hdr); + // SAFETY: all bit patterns are valid for this type, and it doesn't use interior mutability. + unsafe impl FromBytes for Elf64Hdr {} + + #[repr(transparent)] + struct Elf64SHdr(bindings::elf64_shdr); + // SAFETY: all bit patterns are valid for this type, and it doesn't use interior mutability. + unsafe impl FromBytes for Elf64SHdr {} + + /// Tries to extract section with name `name` from the ELF64 image `elf`, and returns it. + pub(super) fn elf64_section<'a, 'b>(elf: &'a [u8], name: &'b str) -> Option<&'a [u8]> { + let hdr = &elf + .get(0..size_of::<bindings::elf64_hdr>()) + .and_then(Elf64Hdr::from_bytes)? + .0; + + // Get all the section headers. + let mut shdr = { + let shdr_num = usize::from(hdr.e_shnum); + let shdr_start = usize::try_from(hdr.e_shoff).ok()?; + let shdr_end = shdr_num + .checked_mul(size_of::<Elf64SHdr>()) + .and_then(|v| v.checked_add(shdr_start))?; + + elf.get(shdr_start..shdr_end) + .map(|slice| slice.chunks_exact(size_of::<Elf64SHdr>()))? + }; + + // Get the strings table. + let strhdr = shdr + .clone() + .nth(usize::from(hdr.e_shstrndx)) + .and_then(Elf64SHdr::from_bytes)?; + + // Find the section which name matches `name` and return it. + shdr.find(|&sh| { + let Some(hdr) = Elf64SHdr::from_bytes(sh) else { + return false; + }; + + let Some(name_idx) = strhdr + .0 + .sh_offset + .checked_add(u64::from(hdr.0.sh_name)) + .and_then(|idx| usize::try_from(idx).ok()) + else { + return false; + }; + + // Get the start of the name. + elf.get(name_idx..) + // Stop at the first `0`. + .and_then(|nstr| nstr.get(0..=nstr.iter().position(|b| *b == 0)?)) + // Convert into CStr. This should never fail because of the line above. + .and_then(|nstr| CStr::from_bytes_with_nul(nstr).ok()) + // Convert into str. + .and_then(|c_str| c_str.to_str().ok()) + // Check that the name matches. + .map(|str| str == name) + .unwrap_or(false) + }) + // Return the slice containing the section. + .and_then(|sh| { + let hdr = Elf64SHdr::from_bytes(sh)?; + let start = usize::try_from(hdr.0.sh_offset).ok()?; + let end = usize::try_from(hdr.0.sh_size) + .ok() + .and_then(|sh_size| start.checked_add(sh_size))?; + + elf.get(start..end) + }) + } +} + +/// GSP firmware with 3-level radix page tables for the GSP bootloader. +/// +/// The bootloader expects firmware to be mapped starting at address 0 in GSP's virtual address +/// space: +/// +/// ```text +/// Level 0: 1 page, 1 entry -> points to first level 1 page +/// Level 1: Multiple pages/entries -> each entry points to a level 2 page +/// Level 2: Multiple pages/entries -> each entry points to a firmware page +/// ``` +/// +/// Each page is 4KB, each entry is 8 bytes (64-bit DMA address). +/// Also known as "Radix3" firmware. +#[pin_data] +pub(crate) struct GspFirmware { + /// The GSP firmware inside a [`VVec`], device-mapped via a SG table. + #[pin] + fw: SGTable<Owned<VVec<u8>>>, + /// Level 2 page table whose entries contain DMA addresses of firmware pages. + #[pin] + level2: SGTable<Owned<VVec<u8>>>, + /// Level 1 page table whose entries contain DMA addresses of level 2 pages. + #[pin] + level1: SGTable<Owned<VVec<u8>>>, + /// Level 0 page table (single 4KB page) with one entry: DMA address of first level 1 page. + level0: DmaObject, + /// Size in bytes of the firmware contained in [`Self::fw`]. + size: usize, + /// Device-mapped GSP signatures matching the GPU's [`Chipset`]. + signatures: DmaObject, + /// GSP bootloader, verifies the GSP firmware before loading and running it. + bootloader: RiscvFirmware, +} + +impl GspFirmware { + /// Loads the GSP firmware binaries, map them into `dev`'s address-space, and creates the page + /// tables expected by the GSP bootloader to load it. + pub(crate) fn new<'a, 'b>( + dev: &'a device::Device<device::Bound>, + chipset: Chipset, + ver: &'b str, + ) -> Result<impl PinInit<Self, Error> + 'a> { + let fw = super::request_firmware(dev, chipset, "gsp", ver)?; + + let fw_section = elf::elf64_section(fw.data(), ".fwimage").ok_or(EINVAL)?; + + let sigs_section = match chipset.arch() { + Architecture::Ampere => ".fwsignature_ga10x", + _ => return Err(ENOTSUPP), + }; + let signatures = elf::elf64_section(fw.data(), sigs_section) + .ok_or(EINVAL) + .and_then(|data| DmaObject::from_data(dev, data))?; + + let size = fw_section.len(); + + // Move the firmware into a vmalloc'd vector and map it into the device address + // space. + let fw_vvec = VVec::with_capacity(fw_section.len(), GFP_KERNEL) + .and_then(|mut v| { + v.extend_from_slice(fw_section, GFP_KERNEL)?; + Ok(v) + }) + .map_err(|_| ENOMEM)?; + + let bl = super::request_firmware(dev, chipset, "bootloader", ver)?; + let bootloader = RiscvFirmware::new(dev, &bl)?; + + Ok(try_pin_init!(Self { + fw <- SGTable::new(dev, fw_vvec, DataDirection::ToDevice, GFP_KERNEL), + level2 <- { + // Allocate the level 2 page table, map the firmware onto it, and map it into the + // device address space. + VVec::<u8>::with_capacity( + fw.iter().count() * core::mem::size_of::<u64>(), + GFP_KERNEL, + ) + .map_err(|_| ENOMEM) + .and_then(|level2| map_into_lvl(&fw, level2)) + .map(|level2| SGTable::new(dev, level2, DataDirection::ToDevice, GFP_KERNEL))? + }, + level1 <- { + // Allocate the level 1 page table, map the level 2 page table onto it, and map it + // into the device address space. + VVec::<u8>::with_capacity( + level2.iter().count() * core::mem::size_of::<u64>(), + GFP_KERNEL, + ) + .map_err(|_| ENOMEM) + .and_then(|level1| map_into_lvl(&level2, level1)) + .map(|level1| SGTable::new(dev, level1, DataDirection::ToDevice, GFP_KERNEL))? + }, + level0: { + // Allocate the level 0 page table as a device-visible DMA object, and map the + // level 1 page table onto it. + + // Level 0 page table data. + let mut level0_data = kvec![0u8; GSP_PAGE_SIZE]?; + + // Fill level 1 page entry. + #[allow(clippy::useless_conversion)] + let level1_entry = u64::from(level1.iter().next().unwrap().dma_address()); + let dst = &mut level0_data[..size_of_val(&level1_entry)]; + dst.copy_from_slice(&level1_entry.to_le_bytes()); + + // Turn the level0 page table into a [`DmaObject`]. + DmaObject::from_data(dev, &level0_data)? + }, + size, + signatures, + bootloader, + })) + } + + #[expect(unused)] + /// Returns the DMA handle of the radix3 level 0 page table. + pub(crate) fn radix3_dma_handle(&self) -> DmaAddress { + self.level0.dma_handle() + } +} + +/// Build a page table from a scatter-gather list. +/// +/// Takes each DMA-mapped region from `sg_table` and writes page table entries +/// for all 4KB pages within that region. For example, a 16KB SG entry becomes +/// 4 consecutive page table entries. +fn map_into_lvl(sg_table: &SGTable<Owned<VVec<u8>>>, mut dst: VVec<u8>) -> Result<VVec<u8>> { + for sg_entry in sg_table.iter() { + // Number of pages we need to map. + let num_pages = (sg_entry.dma_len() as usize).div_ceil(GSP_PAGE_SIZE); + + for i in 0..num_pages { + let entry = sg_entry.dma_address() + (i as u64 * GSP_PAGE_SIZE as u64); + dst.extend_from_slice(&entry.to_le_bytes(), GFP_KERNEL)?; + } + } + + Ok(dst) +} diff --git a/drivers/gpu/nova-core/firmware/riscv.rs b/drivers/gpu/nova-core/firmware/riscv.rs new file mode 100644 index 000000000000..afb08f5bc4ba --- /dev/null +++ b/drivers/gpu/nova-core/firmware/riscv.rs @@ -0,0 +1,91 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Support for firmware binaries designed to run on a RISC-V core. Such firmwares files have a +//! dedicated header. + +use core::mem::size_of; + +use kernel::device; +use kernel::firmware::Firmware; +use kernel::prelude::*; +use kernel::transmute::FromBytes; + +use crate::dma::DmaObject; +use crate::firmware::BinFirmware; + +/// Descriptor for microcode running on a RISC-V core. +#[repr(C)] +#[derive(Debug)] +struct RmRiscvUCodeDesc { + version: u32, + bootloader_offset: u32, + bootloader_size: u32, + bootloader_param_offset: u32, + bootloader_param_size: u32, + riscv_elf_offset: u32, + riscv_elf_size: u32, + app_version: u32, + manifest_offset: u32, + manifest_size: u32, + monitor_data_offset: u32, + monitor_data_size: u32, + monitor_code_offset: u32, + monitor_code_size: u32, +} + +// SAFETY: all bit patterns are valid for this type, and it doesn't use interior mutability. +unsafe impl FromBytes for RmRiscvUCodeDesc {} + +impl RmRiscvUCodeDesc { + /// Interprets the header of `bin_fw` as a [`RmRiscvUCodeDesc`] and returns it. + /// + /// Fails if the header pointed at by `bin_fw` is not within the bounds of the firmware image. + fn new(bin_fw: &BinFirmware<'_>) -> Result<Self> { + let offset = bin_fw.hdr.header_offset as usize; + + bin_fw + .fw + .get(offset..offset + size_of::<Self>()) + .and_then(Self::from_bytes_copy) + .ok_or(EINVAL) + } +} + +/// A parsed firmware for a RISC-V core, ready to be loaded and run. +#[expect(unused)] +pub(crate) struct RiscvFirmware { + /// Offset at which the code starts in the firmware image. + code_offset: u32, + /// Offset at which the data starts in the firmware image. + data_offset: u32, + /// Offset at which the manifest starts in the firmware image. + manifest_offset: u32, + /// Application version. + app_version: u32, + /// Device-mapped firmware image. + ucode: DmaObject, +} + +impl RiscvFirmware { + /// Parses the RISC-V firmware image contained in `fw`. + pub(crate) fn new(dev: &device::Device<device::Bound>, fw: &Firmware) -> Result<Self> { + let bin_fw = BinFirmware::new(fw)?; + + let riscv_desc = RmRiscvUCodeDesc::new(&bin_fw)?; + + let ucode = { + let start = bin_fw.hdr.data_offset as usize; + let len = bin_fw.hdr.data_size as usize; + + DmaObject::from_data(dev, fw.data().get(start..start + len).ok_or(EINVAL)?)? + }; + + Ok(Self { + ucode, + code_offset: riscv_desc.monitor_code_offset, + data_offset: riscv_desc.monitor_data_offset, + manifest_offset: riscv_desc.manifest_offset, + app_version: riscv_desc.app_version, + }) + } +} diff --git a/drivers/gpu/nova-core/gpu.rs b/drivers/gpu/nova-core/gpu.rs index b5c9786619a9..5da9ad726483 100644 --- a/drivers/gpu/nova-core/gpu.rs +++ b/drivers/gpu/nova-core/gpu.rs @@ -3,15 +3,11 @@ use kernel::{device, devres::Devres, error::code::*, pci, prelude::*, sync::Arc}; use crate::driver::Bar0; -use crate::falcon::{gsp::Gsp, sec2::Sec2, Falcon}; -use crate::fb::FbLayout; +use crate::falcon::{gsp::Gsp as GspFalcon, sec2::Sec2 as Sec2Falcon, Falcon}; use crate::fb::SysmemFlush; -use crate::firmware::fwsec::{FwsecCommand, FwsecFirmware}; -use crate::firmware::{Firmware, FIRMWARE_VERSION}; use crate::gfw; +use crate::gsp::Gsp; use crate::regs; -use crate::util; -use crate::vbios::Vbios; use core::fmt; macro_rules! define_chipset { @@ -28,13 +24,23 @@ macro_rules! define_chipset { $( Chipset::$variant, )* ]; - pub(crate) const NAMES: [&'static str; Self::ALL.len()] = [ - $( util::const_bytes_to_str( - util::to_lowercase_bytes::<{ stringify!($variant).len() }>( - stringify!($variant) - ).as_slice() - ), )* - ]; + ::kernel::macros::paste!( + /// Returns the name of this chipset, in lowercase. + /// + /// # Examples + /// + /// ``` + /// let chipset = Chipset::GA102; + /// assert_eq!(chipset.name(), "ga102"); + /// ``` + pub(crate) const fn name(&self) -> &'static str { + match *self { + $( + Chipset::$variant => stringify!([<$variant:lower>]), + )* + } + } + ); } // TODO[FPRI]: replace with something like derive(FromPrimitive) @@ -163,150 +169,74 @@ impl Spec { } /// Structure holding the resources required to operate the GPU. -#[pin_data(PinnedDrop)] +#[pin_data] pub(crate) struct Gpu { spec: Spec, /// MMIO mapping of PCI BAR 0 bar: Arc<Devres<Bar0>>, - fw: Firmware, /// System memory page required for flushing all pending GPU-side memory writes done through /// PCIE into system memory, via sysmembar (A GPU-initiated HW memory-barrier operation). sysmem_flush: SysmemFlush, -} - -#[pinned_drop] -impl PinnedDrop for Gpu { - fn drop(self: Pin<&mut Self>) { - // Unregister the sysmem flush page before we release it. - self.bar - .try_access_with(|b| self.sysmem_flush.unregister(b)); - } + /// GSP falcon instance, used for GSP boot up and cleanup. + gsp_falcon: Falcon<GspFalcon>, + /// SEC2 falcon instance, used for GSP boot up and cleanup. + sec2_falcon: Falcon<Sec2Falcon>, + /// GSP runtime data. Temporarily an empty placeholder. + #[pin] + gsp: Gsp, } impl Gpu { - /// Helper function to load and run the FWSEC-FRTS firmware and confirm that it has properly - /// created the WPR2 region. - /// - /// TODO: this needs to be moved into a larger type responsible for booting the whole GSP - /// (`GspBooter`?). - fn run_fwsec_frts( - dev: &device::Device<device::Bound>, - falcon: &Falcon<Gsp>, - bar: &Bar0, - bios: &Vbios, - fb_layout: &FbLayout, - ) -> Result<()> { - // Check that the WPR2 region does not already exists - if it does, we cannot run - // FWSEC-FRTS until the GPU is reset. - if regs::NV_PFB_PRI_MMU_WPR2_ADDR_HI::read(bar).higher_bound() != 0 { - dev_err!( - dev, - "WPR2 region already exists - GPU needs to be reset to proceed\n" - ); - return Err(EBUSY); - } + pub(crate) fn new<'a>( + pdev: &'a pci::Device<device::Bound>, + devres_bar: Arc<Devres<Bar0>>, + bar: &'a Bar0, + ) -> impl PinInit<Self, Error> + 'a { + try_pin_init!(Self { + spec: Spec::new(bar).inspect(|spec| { + dev_info!( + pdev.as_ref(), + "NVIDIA (Chipset: {}, Architecture: {:?}, Revision: {})\n", + spec.chipset, + spec.chipset.arch(), + spec.revision + ); + })?, - let fwsec_frts = FwsecFirmware::new( - dev, - falcon, - bar, - bios, - FwsecCommand::Frts { - frts_addr: fb_layout.frts.start, - frts_size: fb_layout.frts.end - fb_layout.frts.start, + // We must wait for GFW_BOOT completion before doing any significant setup on the GPU. + _: { + gfw::wait_gfw_boot_completion(bar) + .inspect_err(|_| dev_err!(pdev.as_ref(), "GFW boot did not complete"))?; }, - )?; - // Run FWSEC-FRTS to create the WPR2 region. - fwsec_frts.run(dev, falcon, bar)?; + sysmem_flush: SysmemFlush::register(pdev.as_ref(), bar, spec.chipset)?, - // SCRATCH_E contains the error code for FWSEC-FRTS. - let frts_status = regs::NV_PBUS_SW_SCRATCH_0E::read(bar).frts_err_code(); - if frts_status != 0 { - dev_err!( - dev, - "FWSEC-FRTS returned with error code {:#x}", - frts_status - ); + gsp_falcon: Falcon::new( + pdev.as_ref(), + spec.chipset, + bar, + spec.chipset > Chipset::GA100, + ) + .inspect(|falcon| falcon.clear_swgen0_intr(bar))?, - return Err(EIO); - } + sec2_falcon: Falcon::new(pdev.as_ref(), spec.chipset, bar, true)?, - // Check that the WPR2 region has been created as we requested. - let (wpr2_lo, wpr2_hi) = ( - regs::NV_PFB_PRI_MMU_WPR2_ADDR_LO::read(bar).lower_bound(), - regs::NV_PFB_PRI_MMU_WPR2_ADDR_HI::read(bar).higher_bound(), - ); + gsp <- Gsp::new(), - match (wpr2_lo, wpr2_hi) { - (_, 0) => { - dev_err!(dev, "WPR2 region not created after running FWSEC-FRTS\n"); + _: { gsp.boot(pdev, bar, spec.chipset, gsp_falcon, sec2_falcon)? }, - Err(EIO) - } - (wpr2_lo, _) if wpr2_lo != fb_layout.frts.start => { - dev_err!( - dev, - "WPR2 region created at unexpected address {:#x}; expected {:#x}\n", - wpr2_lo, - fb_layout.frts.start, - ); - - Err(EIO) - } - (wpr2_lo, wpr2_hi) => { - dev_dbg!(dev, "WPR2: {:#x}-{:#x}\n", wpr2_lo, wpr2_hi); - dev_dbg!(dev, "GPU instance built\n"); - - Ok(()) - } - } + bar: devres_bar, + }) } - pub(crate) fn new( - pdev: &pci::Device<device::Bound>, - devres_bar: Arc<Devres<Bar0>>, - ) -> Result<impl PinInit<Self>> { - let bar = devres_bar.access(pdev.as_ref())?; - let spec = Spec::new(bar)?; - let fw = Firmware::new(pdev.as_ref(), spec.chipset, FIRMWARE_VERSION)?; - - dev_info!( - pdev.as_ref(), - "NVIDIA (Chipset: {}, Architecture: {:?}, Revision: {})\n", - spec.chipset, - spec.chipset.arch(), - spec.revision - ); - - // We must wait for GFW_BOOT completion before doing any significant setup on the GPU. - gfw::wait_gfw_boot_completion(bar) - .inspect_err(|_| dev_err!(pdev.as_ref(), "GFW boot did not complete"))?; - - let sysmem_flush = SysmemFlush::register(pdev.as_ref(), bar, spec.chipset)?; - - let gsp_falcon = Falcon::<Gsp>::new( - pdev.as_ref(), - spec.chipset, - bar, - spec.chipset > Chipset::GA100, - )?; - gsp_falcon.clear_swgen0_intr(bar); - - let _sec2_falcon = Falcon::<Sec2>::new(pdev.as_ref(), spec.chipset, bar, true)?; - - let fb_layout = FbLayout::new(spec.chipset, bar)?; - dev_dbg!(pdev.as_ref(), "{:#x?}\n", fb_layout); - - let bios = Vbios::new(pdev, bar)?; - - Self::run_fwsec_frts(pdev.as_ref(), &gsp_falcon, bar, &bios, &fb_layout)?; - - Ok(pin_init!(Self { - spec, - bar: devres_bar, - fw, - sysmem_flush, - })) + /// Called when the corresponding [`Device`](device::Device) is unbound. + /// + /// Note: This method must only be called from `Driver::unbind`. + pub(crate) fn unbind(&self, dev: &device::Device<device::Core>) { + kernel::warn_on!(self + .bar + .access(dev) + .inspect(|bar| self.sysmem_flush.unregister(bar)) + .is_err()); } } diff --git a/drivers/gpu/nova-core/gsp.rs b/drivers/gpu/nova-core/gsp.rs new file mode 100644 index 000000000000..64e472e7a9d3 --- /dev/null +++ b/drivers/gpu/nova-core/gsp.rs @@ -0,0 +1,22 @@ +// SPDX-License-Identifier: GPL-2.0 + +mod boot; + +use kernel::prelude::*; + +mod fw; + +pub(crate) const GSP_PAGE_SHIFT: usize = 12; +pub(crate) const GSP_PAGE_SIZE: usize = 1 << GSP_PAGE_SHIFT; + +/// GSP runtime data. +/// +/// This is an empty pinned placeholder for now. +#[pin_data] +pub(crate) struct Gsp {} + +impl Gsp { + pub(crate) fn new() -> impl PinInit<Self> { + pin_init!(Self {}) + } +} diff --git a/drivers/gpu/nova-core/gsp/boot.rs b/drivers/gpu/nova-core/gsp/boot.rs new file mode 100644 index 000000000000..2800f3aee37d --- /dev/null +++ b/drivers/gpu/nova-core/gsp/boot.rs @@ -0,0 +1,137 @@ +// SPDX-License-Identifier: GPL-2.0 + +use kernel::device; +use kernel::pci; +use kernel::prelude::*; + +use crate::driver::Bar0; +use crate::falcon::{gsp::Gsp, sec2::Sec2, Falcon}; +use crate::fb::FbLayout; +use crate::firmware::{ + booter::{BooterFirmware, BooterKind}, + fwsec::{FwsecCommand, FwsecFirmware}, + gsp::GspFirmware, + FIRMWARE_VERSION, +}; +use crate::gpu::Chipset; +use crate::regs; +use crate::vbios::Vbios; + +impl super::Gsp { + /// Helper function to load and run the FWSEC-FRTS firmware and confirm that it has properly + /// created the WPR2 region. + fn run_fwsec_frts( + dev: &device::Device<device::Bound>, + falcon: &Falcon<Gsp>, + bar: &Bar0, + bios: &Vbios, + fb_layout: &FbLayout, + ) -> Result<()> { + // Check that the WPR2 region does not already exists - if it does, we cannot run + // FWSEC-FRTS until the GPU is reset. + if regs::NV_PFB_PRI_MMU_WPR2_ADDR_HI::read(bar).higher_bound() != 0 { + dev_err!( + dev, + "WPR2 region already exists - GPU needs to be reset to proceed\n" + ); + return Err(EBUSY); + } + + let fwsec_frts = FwsecFirmware::new( + dev, + falcon, + bar, + bios, + FwsecCommand::Frts { + frts_addr: fb_layout.frts.start, + frts_size: fb_layout.frts.end - fb_layout.frts.start, + }, + )?; + + // Run FWSEC-FRTS to create the WPR2 region. + fwsec_frts.run(dev, falcon, bar)?; + + // SCRATCH_E contains the error code for FWSEC-FRTS. + let frts_status = regs::NV_PBUS_SW_SCRATCH_0E_FRTS_ERR::read(bar).frts_err_code(); + if frts_status != 0 { + dev_err!( + dev, + "FWSEC-FRTS returned with error code {:#x}", + frts_status + ); + + return Err(EIO); + } + + // Check that the WPR2 region has been created as we requested. + let (wpr2_lo, wpr2_hi) = ( + regs::NV_PFB_PRI_MMU_WPR2_ADDR_LO::read(bar).lower_bound(), + regs::NV_PFB_PRI_MMU_WPR2_ADDR_HI::read(bar).higher_bound(), + ); + + match (wpr2_lo, wpr2_hi) { + (_, 0) => { + dev_err!(dev, "WPR2 region not created after running FWSEC-FRTS\n"); + + Err(EIO) + } + (wpr2_lo, _) if wpr2_lo != fb_layout.frts.start => { + dev_err!( + dev, + "WPR2 region created at unexpected address {:#x}; expected {:#x}\n", + wpr2_lo, + fb_layout.frts.start, + ); + + Err(EIO) + } + (wpr2_lo, wpr2_hi) => { + dev_dbg!(dev, "WPR2: {:#x}-{:#x}\n", wpr2_lo, wpr2_hi); + dev_dbg!(dev, "GPU instance built\n"); + + Ok(()) + } + } + } + + /// Attempt to boot the GSP. + /// + /// This is a GPU-dependent and complex procedure that involves loading firmware files from + /// user-space, patching them with signatures, and building firmware-specific intricate data + /// structures that the GSP will use at runtime. + /// + /// Upon return, the GSP is up and running, and its runtime object given as return value. + pub(crate) fn boot( + self: Pin<&mut Self>, + pdev: &pci::Device<device::Bound>, + bar: &Bar0, + chipset: Chipset, + gsp_falcon: &Falcon<Gsp>, + sec2_falcon: &Falcon<Sec2>, + ) -> Result { + let dev = pdev.as_ref(); + + let bios = Vbios::new(dev, bar)?; + + let _gsp_fw = KBox::pin_init( + GspFirmware::new(dev, chipset, FIRMWARE_VERSION)?, + GFP_KERNEL, + )?; + + let fb_layout = FbLayout::new(chipset, bar)?; + dev_dbg!(dev, "{:#x?}\n", fb_layout); + + Self::run_fwsec_frts(dev, gsp_falcon, bar, &bios, &fb_layout)?; + + let _booter_loader = BooterFirmware::new( + dev, + BooterKind::Loader, + chipset, + FIRMWARE_VERSION, + sec2_falcon, + bar, + )?; + + Ok(()) + } +} diff --git a/drivers/gpu/nova-core/gsp/fw.rs b/drivers/gpu/nova-core/gsp/fw.rs new file mode 100644 index 000000000000..34226dd00982 --- /dev/null +++ b/drivers/gpu/nova-core/gsp/fw.rs @@ -0,0 +1,7 @@ +// SPDX-License-Identifier: GPL-2.0 + +mod r570_144; + +// Alias to avoid repeating the version number with every use. +#[expect(unused)] +use r570_144 as bindings; diff --git a/drivers/gpu/nova-core/gsp/fw/r570_144.rs b/drivers/gpu/nova-core/gsp/fw/r570_144.rs new file mode 100644 index 000000000000..35cb0370a7c9 --- /dev/null +++ b/drivers/gpu/nova-core/gsp/fw/r570_144.rs @@ -0,0 +1,29 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Firmware bindings. +//! +//! Imports the generated bindings by `bindgen`. +//! +//! This module may not be directly used. Please abstract or re-export the needed symbols in the +//! parent module instead. + +#![cfg_attr(test, allow(deref_nullptr))] +#![cfg_attr(test, allow(unaligned_references))] +#![cfg_attr(test, allow(unsafe_op_in_unsafe_fn))] +#![allow( + dead_code, + unused_imports, + clippy::all, + clippy::undocumented_unsafe_blocks, + clippy::ptr_as_ptr, + clippy::ref_as_ptr, + missing_docs, + non_camel_case_types, + non_upper_case_globals, + non_snake_case, + improper_ctypes, + unreachable_pub, + unsafe_op_in_unsafe_fn +)] +use kernel::ffi; +include!("r570_144/bindings.rs"); diff --git a/drivers/gpu/nova-core/gsp/fw/r570_144/bindings.rs b/drivers/gpu/nova-core/gsp/fw/r570_144/bindings.rs new file mode 100644 index 000000000000..cec594032515 --- /dev/null +++ b/drivers/gpu/nova-core/gsp/fw/r570_144/bindings.rs @@ -0,0 +1 @@ +// SPDX-License-Identifier: GPL-2.0 diff --git a/drivers/gpu/nova-core/nova_core.rs b/drivers/gpu/nova-core/nova_core.rs index cb2bbb30cba1..fffcaee2249f 100644 --- a/drivers/gpu/nova-core/nova_core.rs +++ b/drivers/gpu/nova-core/nova_core.rs @@ -9,6 +9,7 @@ mod fb; mod firmware; mod gfw; mod gpu; +mod gsp; mod regs; mod util; mod vbios; diff --git a/drivers/gpu/nova-core/regs.rs b/drivers/gpu/nova-core/regs.rs index d49fddf6a3c6..206dab2e1335 100644 --- a/drivers/gpu/nova-core/regs.rs +++ b/drivers/gpu/nova-core/regs.rs @@ -5,11 +5,11 @@ #![allow(non_camel_case_types)] #[macro_use] -mod macros; +pub(crate) mod macros; use crate::falcon::{ DmaTrfCmdSize, FalconCoreRev, FalconCoreRevSubversion, FalconFbifMemType, FalconFbifTarget, - FalconModSelAlgo, FalconSecurityModel, PeregrineCoreSelect, + FalconModSelAlgo, FalconSecurityModel, PFalcon2Base, PFalconBase, PeregrineCoreSelect, }; use crate::gpu::{Architecture, Chipset}; use kernel::prelude::*; @@ -28,7 +28,7 @@ impl NV_PMC_BOOT_0 { /// Combines `architecture_0` and `architecture_1` to obtain the architecture of the chip. pub(crate) fn architecture(self) -> Result<Architecture> { Architecture::try_from( - self.architecture_0() | (self.architecture_1() << Self::ARCHITECTURE_0.len()), + self.architecture_0() | (self.architecture_1() << Self::ARCHITECTURE_0_RANGE.len()), ) } @@ -36,7 +36,8 @@ impl NV_PMC_BOOT_0 { pub(crate) fn chipset(self) -> Result<Chipset> { self.architecture() .map(|arch| { - ((arch as u32) << Self::IMPLEMENTATION.len()) | u32::from(self.implementation()) + ((arch as u32) << Self::IMPLEMENTATION_RANGE.len()) + | u32::from(self.implementation()) }) .and_then(Chipset::try_from) } @@ -44,8 +45,10 @@ impl NV_PMC_BOOT_0 { // PBUS -// TODO[REGA]: this is an array of registers. -register!(NV_PBUS_SW_SCRATCH_0E@0x00001438 { +register!(NV_PBUS_SW_SCRATCH @ 0x00001400[64] {}); + +register!(NV_PBUS_SW_SCRATCH_0E_FRTS_ERR => NV_PBUS_SW_SCRATCH[0xe], + "scratch register 0xe used as FRTS firmware error code" { 31:16 frts_err_code as u16; }); @@ -123,13 +126,12 @@ register!(NV_PGC6_AON_SECURE_SCRATCH_GROUP_05_PRIV_LEVEL_MASK @ 0x00118128, 0:0 read_protection_level0 as bool, "Set after FWSEC lowers its protection level"; }); -// TODO[REGA]: This is an array of registers. -register!(NV_PGC6_AON_SECURE_SCRATCH_GROUP_05 @ 0x00118234 { - 31:0 value as u32; -}); +// OpenRM defines this as a register array, but doesn't specify its size and only uses its first +// element. Be conservative until we know the actual size or need to use more registers. +register!(NV_PGC6_AON_SECURE_SCRATCH_GROUP_05 @ 0x00118234[1] {}); register!( - NV_PGC6_AON_SECURE_SCRATCH_GROUP_05_0_GFW_BOOT => NV_PGC6_AON_SECURE_SCRATCH_GROUP_05, + NV_PGC6_AON_SECURE_SCRATCH_GROUP_05_0_GFW_BOOT => NV_PGC6_AON_SECURE_SCRATCH_GROUP_05[0], "Scratch group 05 register 0 used as GFW boot progress indicator" { 7:0 progress as u8, "Progress of GFW boot (0xff means completed)"; } @@ -180,38 +182,40 @@ impl NV_PDISP_VGA_WORKSPACE_BASE { // FUSE -register!(NV_FUSE_OPT_FPF_NVDEC_UCODE1_VERSION @ 0x00824100 { +pub(crate) const NV_FUSE_OPT_FPF_SIZE: usize = 16; + +register!(NV_FUSE_OPT_FPF_NVDEC_UCODE1_VERSION @ 0x00824100[NV_FUSE_OPT_FPF_SIZE] { 15:0 data as u16; }); -register!(NV_FUSE_OPT_FPF_SEC2_UCODE1_VERSION @ 0x00824140 { +register!(NV_FUSE_OPT_FPF_SEC2_UCODE1_VERSION @ 0x00824140[NV_FUSE_OPT_FPF_SIZE] { 15:0 data as u16; }); -register!(NV_FUSE_OPT_FPF_GSP_UCODE1_VERSION @ 0x008241c0 { +register!(NV_FUSE_OPT_FPF_GSP_UCODE1_VERSION @ 0x008241c0[NV_FUSE_OPT_FPF_SIZE] { 15:0 data as u16; }); // PFALCON -register!(NV_PFALCON_FALCON_IRQSCLR @ +0x00000004 { +register!(NV_PFALCON_FALCON_IRQSCLR @ PFalconBase[0x00000004] { 4:4 halt as bool; 6:6 swgen0 as bool; }); -register!(NV_PFALCON_FALCON_MAILBOX0 @ +0x00000040 { +register!(NV_PFALCON_FALCON_MAILBOX0 @ PFalconBase[0x00000040] { 31:0 value as u32; }); -register!(NV_PFALCON_FALCON_MAILBOX1 @ +0x00000044 { +register!(NV_PFALCON_FALCON_MAILBOX1 @ PFalconBase[0x00000044] { 31:0 value as u32; }); -register!(NV_PFALCON_FALCON_RM @ +0x00000084 { +register!(NV_PFALCON_FALCON_RM @ PFalconBase[0x00000084] { 31:0 value as u32; }); -register!(NV_PFALCON_FALCON_HWCFG2 @ +0x000000f4 { +register!(NV_PFALCON_FALCON_HWCFG2 @ PFalconBase[0x000000f4] { 10:10 riscv as bool; 12:12 mem_scrubbing as bool, "Set to 0 after memory scrubbing is completed"; 31:31 reset_ready as bool, "Signal indicating that reset is completed (GA102+)"; @@ -224,17 +228,17 @@ impl NV_PFALCON_FALCON_HWCFG2 { } } -register!(NV_PFALCON_FALCON_CPUCTL @ +0x00000100 { +register!(NV_PFALCON_FALCON_CPUCTL @ PFalconBase[0x00000100] { 1:1 startcpu as bool; 4:4 halted as bool; 6:6 alias_en as bool; }); -register!(NV_PFALCON_FALCON_BOOTVEC @ +0x00000104 { +register!(NV_PFALCON_FALCON_BOOTVEC @ PFalconBase[0x00000104] { 31:0 value as u32; }); -register!(NV_PFALCON_FALCON_DMACTL @ +0x0000010c { +register!(NV_PFALCON_FALCON_DMACTL @ PFalconBase[0x0000010c] { 0:0 require_ctx as bool; 1:1 dmem_scrubbing as bool; 2:2 imem_scrubbing as bool; @@ -242,15 +246,15 @@ register!(NV_PFALCON_FALCON_DMACTL @ +0x0000010c { 7:7 secure_stat as bool; }); -register!(NV_PFALCON_FALCON_DMATRFBASE @ +0x00000110 { +register!(NV_PFALCON_FALCON_DMATRFBASE @ PFalconBase[0x00000110] { 31:0 base as u32; }); -register!(NV_PFALCON_FALCON_DMATRFMOFFS @ +0x00000114 { +register!(NV_PFALCON_FALCON_DMATRFMOFFS @ PFalconBase[0x00000114] { 23:0 offs as u32; }); -register!(NV_PFALCON_FALCON_DMATRFCMD @ +0x00000118 { +register!(NV_PFALCON_FALCON_DMATRFCMD @ PFalconBase[0x00000118] { 0:0 full as bool; 1:1 idle as bool; 3:2 sec as u8; @@ -261,60 +265,62 @@ register!(NV_PFALCON_FALCON_DMATRFCMD @ +0x00000118 { 16:16 set_dmtag as u8; }); -register!(NV_PFALCON_FALCON_DMATRFFBOFFS @ +0x0000011c { +register!(NV_PFALCON_FALCON_DMATRFFBOFFS @ PFalconBase[0x0000011c] { 31:0 offs as u32; }); -register!(NV_PFALCON_FALCON_DMATRFBASE1 @ +0x00000128 { +register!(NV_PFALCON_FALCON_DMATRFBASE1 @ PFalconBase[0x00000128] { 8:0 base as u16; }); -register!(NV_PFALCON_FALCON_HWCFG1 @ +0x0000012c { +register!(NV_PFALCON_FALCON_HWCFG1 @ PFalconBase[0x0000012c] { 3:0 core_rev as u8 ?=> FalconCoreRev, "Core revision"; 5:4 security_model as u8 ?=> FalconSecurityModel, "Security model"; 7:6 core_rev_subversion as u8 ?=> FalconCoreRevSubversion, "Core revision subversion"; }); -register!(NV_PFALCON_FALCON_CPUCTL_ALIAS @ +0x00000130 { +register!(NV_PFALCON_FALCON_CPUCTL_ALIAS @ PFalconBase[0x00000130] { 1:1 startcpu as bool; }); // Actually known as `NV_PSEC_FALCON_ENGINE` and `NV_PGSP_FALCON_ENGINE` depending on the falcon // instance. -register!(NV_PFALCON_FALCON_ENGINE @ +0x000003c0 { +register!(NV_PFALCON_FALCON_ENGINE @ PFalconBase[0x000003c0] { 0:0 reset as bool; }); -// TODO[REGA]: this is an array of registers. -register!(NV_PFALCON_FBIF_TRANSCFG @ +0x00000600 { +register!(NV_PFALCON_FBIF_TRANSCFG @ PFalconBase[0x00000600[8]] { 1:0 target as u8 ?=> FalconFbifTarget; 2:2 mem_type as bool => FalconFbifMemType; }); -register!(NV_PFALCON_FBIF_CTL @ +0x00000624 { +register!(NV_PFALCON_FBIF_CTL @ PFalconBase[0x00000624] { 7:7 allow_phys_no_ctx as bool; }); -register!(NV_PFALCON2_FALCON_MOD_SEL @ +0x00001180 { +/* PFALCON2 */ + +register!(NV_PFALCON2_FALCON_MOD_SEL @ PFalcon2Base[0x00000180] { 7:0 algo as u8 ?=> FalconModSelAlgo; }); -register!(NV_PFALCON2_FALCON_BROM_CURR_UCODE_ID @ +0x00001198 { +register!(NV_PFALCON2_FALCON_BROM_CURR_UCODE_ID @ PFalcon2Base[0x00000198] { 7:0 ucode_id as u8; }); -register!(NV_PFALCON2_FALCON_BROM_ENGIDMASK @ +0x0000119c { +register!(NV_PFALCON2_FALCON_BROM_ENGIDMASK @ PFalcon2Base[0x0000019c] { 31:0 value as u32; }); -// TODO[REGA]: this is an array of registers. -register!(NV_PFALCON2_FALCON_BROM_PARAADDR @ +0x00001210 { +// OpenRM defines this as a register array, but doesn't specify its size and only uses its first +// element. Be conservative until we know the actual size or need to use more registers. +register!(NV_PFALCON2_FALCON_BROM_PARAADDR @ PFalcon2Base[0x00000210[1]] { 31:0 value as u32; }); // PRISCV -register!(NV_PRISCV_RISCV_BCR_CTRL @ +0x00001668 { +register!(NV_PRISCV_RISCV_BCR_CTRL @ PFalconBase[0x00001668] { 0:0 valid as bool; 4:4 core_select as bool => PeregrineCoreSelect; 8:8 br_fetch as bool; diff --git a/drivers/gpu/nova-core/regs/macros.rs b/drivers/gpu/nova-core/regs/macros.rs index a3e6de1779d4..754c14ee7f40 100644 --- a/drivers/gpu/nova-core/regs/macros.rs +++ b/drivers/gpu/nova-core/regs/macros.rs @@ -1,17 +1,27 @@ // SPDX-License-Identifier: GPL-2.0 -//! Macro to define register layout and accessors. +//! `register!` macro to define register layout and accessors. //! //! A single register typically includes several fields, which are accessed through a combination //! of bit-shift and mask operations that introduce a class of potential mistakes, notably because //! not all possible field values are necessarily valid. //! -//! The macro in this module allow to define, using an intruitive and readable syntax, a dedicated -//! type for each register with its own field accessors that can return an error is a field's value -//! is invalid. +//! The `register!` macro in this module provides an intuitive and readable syntax for defining a +//! dedicated type for each register. Each such type comes with its own field accessors that can +//! return an error if a field's value is invalid. -/// Defines a dedicated type for a register with an absolute offset, alongside with getter and -/// setter methods for its fields and methods to read and write it from an `Io` region. +/// Trait providing a base address to be added to the offset of a relative register to obtain +/// its actual offset. +/// +/// The `T` generic argument is used to distinguish which base to use, in case a type provides +/// several bases. It is given to the `register!` macro to restrict the use of the register to +/// implementors of this particular variant. +pub(crate) trait RegisterBase<T> { + const BASE: usize; +} + +/// Defines a dedicated type for a register with an absolute offset, including getter and setter +/// methods for its fields and methods to read and write it from an `Io` region. /// /// Example: /// @@ -24,7 +34,7 @@ /// ``` /// /// This defines a `BOOT_0` type which can be read or written from offset `0x100` of an `Io` -/// region. It is composed of 3 fields, for instance `minor_revision` is made of the 4 less +/// region. It is composed of 3 fields, for instance `minor_revision` is made of the 4 least /// significant bits of the register. Each field can be accessed and modified using accessor /// methods: /// @@ -33,130 +43,344 @@ /// let boot0 = BOOT_0::read(&bar); /// pr_info!("chip revision: {}.{}", boot0.major_revision(), boot0.minor_revision()); /// -/// // `Chipset::try_from` will be called with the value of the field and returns an error if the -/// // value is invalid. +/// // `Chipset::try_from` is called with the value of the `chipset` field and returns an +/// // error if it is invalid. /// let chipset = boot0.chipset()?; /// /// // Update some fields and write the value back. /// boot0.set_major_revision(3).set_minor_revision(10).write(&bar); /// -/// // Or just read and update the register in a single step: +/// // Or, just read and update the register in a single step: /// BOOT_0::alter(&bar, |r| r.set_major_revision(3).set_minor_revision(10)); /// ``` /// -/// Fields can be defined as follows: +/// Fields are defined as follows: /// -/// - `as <type>` simply returns the field value casted as the requested integer type, typically -/// `u32`, `u16`, `u8` or `bool`. Note that `bool` fields must have a range of 1 bit. +/// - `as <type>` simply returns the field value casted to <type>, typically `u32`, `u16`, `u8` or +/// `bool`. Note that `bool` fields must have a range of 1 bit. /// - `as <type> => <into_type>` calls `<into_type>`'s `From::<<type>>` implementation and returns /// the result. /// - `as <type> ?=> <try_into_type>` calls `<try_into_type>`'s `TryFrom::<<type>>` implementation -/// and returns the result. This is useful on fields for which not all values are value. +/// and returns the result. This is useful with fields for which not all values are valid. /// /// The documentation strings are optional. If present, they will be added to the type's /// definition, or the field getter and setter methods they are attached to. /// -/// Putting a `+` before the address of the register makes it relative to a base: the `read` and -/// `write` methods take a `base` argument that is added to the specified address before access, -/// and `try_read` and `try_write` methods are also created, allowing access with offsets unknown -/// at compile-time: +/// It is also possible to create a alias register by using the `=> ALIAS` syntax. This is useful +/// for cases where a register's interpretation depends on the context: /// /// ```no_run -/// register!(CPU_CTL @ +0x0000010, "CPU core control" { -/// 0:0 start as bool, "Start the CPU core"; +/// register!(SCRATCH @ 0x00000200, "Scratch register" { +/// 31:0 value as u32, "Raw value"; /// }); /// -/// // Flip the `start` switch for the CPU core which base address is at `CPU_BASE`. -/// let cpuctl = CPU_CTL::read(&bar, CPU_BASE); -/// pr_info!("CPU CTL: {:#x}", cpuctl); -/// cpuctl.set_start(true).write(&bar, CPU_BASE); +/// register!(SCRATCH_BOOT_STATUS => SCRATCH, "Boot status of the firmware" { +/// 0:0 completed as bool, "Whether the firmware has completed booting"; +/// }); /// ``` /// -/// It is also possible to create a alias register by using the `=> ALIAS` syntax. This is useful -/// for cases where a register's interpretation depends on the context: +/// In this example, `SCRATCH_0_BOOT_STATUS` uses the same I/O address as `SCRATCH`, while also +/// providing its own `completed` field. +/// +/// ## Relative registers +/// +/// A register can be defined as being accessible from a fixed offset of a provided base. For +/// instance, imagine the following I/O space: +/// +/// ```text +/// +-----------------------------+ +/// | ... | +/// | | +/// 0x100--->+------------CPU0-------------+ +/// | | +/// 0x110--->+-----------------------------+ +/// | CPU_CTL | +/// +-----------------------------+ +/// | ... | +/// | | +/// | | +/// 0x200--->+------------CPU1-------------+ +/// | | +/// 0x210--->+-----------------------------+ +/// | CPU_CTL | +/// +-----------------------------+ +/// | ... | +/// +-----------------------------+ +/// ``` +/// +/// `CPU0` and `CPU1` both have a `CPU_CTL` register that starts at offset `0x10` of their I/O +/// space segment. Since both instances of `CPU_CTL` share the same layout, we don't want to define +/// them twice and would prefer a way to select which one to use from a single definition +/// +/// This can be done using the `Base[Offset]` syntax when specifying the register's address. +/// +/// `Base` is an arbitrary type (typically a ZST) to be used as a generic parameter of the +/// [`RegisterBase`] trait to provide the base as a constant, i.e. each type providing a base for +/// this register needs to implement `RegisterBase<Base>`. Here is the above example translated +/// into code: /// /// ```no_run -/// register!(SCRATCH_0 @ 0x0000100, "Scratch register 0" { -/// 31:0 value as u32, "Raw value"; +/// // Type used to identify the base. +/// pub(crate) struct CpuCtlBase; /// -/// register!(SCRATCH_0_BOOT_STATUS => SCRATCH_0, "Boot status of the firmware" { -/// 0:0 completed as bool, "Whether the firmware has completed booting"; +/// // ZST describing `CPU0`. +/// struct Cpu0; +/// impl RegisterBase<CpuCtlBase> for Cpu0 { +/// const BASE: usize = 0x100; +/// } +/// // Singleton of `CPU0` used to identify it. +/// const CPU0: Cpu0 = Cpu0; +/// +/// // ZST describing `CPU1`. +/// struct Cpu1; +/// impl RegisterBase<CpuCtlBase> for Cpu1 { +/// const BASE: usize = 0x200; +/// } +/// // Singleton of `CPU1` used to identify it. +/// const CPU1: Cpu1 = Cpu1; +/// +/// // This makes `CPU_CTL` accessible from all implementors of `RegisterBase<CpuCtlBase>`. +/// register!(CPU_CTL @ CpuCtlBase[0x10], "CPU core control" { +/// 0:0 start as bool, "Start the CPU core"; +/// }); +/// +/// // The `read`, `write` and `alter` methods of relative registers take an extra `base` argument +/// // that is used to resolve its final address by adding its `BASE` to the offset of the +/// // register. +/// +/// // Start `CPU0`. +/// CPU_CTL::alter(bar, &CPU0, |r| r.set_start(true)); +/// +/// // Start `CPU1`. +/// CPU_CTL::alter(bar, &CPU1, |r| r.set_start(true)); +/// +/// // Aliases can also be defined for relative register. +/// register!(CPU_CTL_ALIAS => CpuCtlBase[CPU_CTL], "Alias to CPU core control" { +/// 1:1 alias_start as bool, "Start the aliased CPU core"; +/// }); +/// +/// // Start the aliased `CPU0`. +/// CPU_CTL_ALIAS::alter(bar, &CPU0, |r| r.set_alias_start(true)); +/// ``` +/// +/// ## Arrays of registers +/// +/// Some I/O areas contain consecutive values that can be interpreted in the same way. These areas +/// can be defined as an array of identical registers, allowing them to be accessed by index with +/// compile-time or runtime bound checking. Simply define their address as `Address[Size]`, and add +/// an `idx` parameter to their `read`, `write` and `alter` methods: +/// +/// ```no_run +/// # fn no_run() -> Result<(), Error> { +/// # fn get_scratch_idx() -> usize { +/// # 0x15 +/// # } +/// // Array of 64 consecutive registers with the same layout starting at offset `0x80`. +/// register!(SCRATCH @ 0x00000080[64], "Scratch registers" { +/// 31:0 value as u32; +/// }); +/// +/// // Read scratch register 0, i.e. I/O address `0x80`. +/// let scratch_0 = SCRATCH::read(bar, 0).value(); +/// // Read scratch register 15, i.e. I/O address `0x80 + (15 * 4)`. +/// let scratch_15 = SCRATCH::read(bar, 15).value(); +/// +/// // This is out of bounds and won't build. +/// // let scratch_128 = SCRATCH::read(bar, 128).value(); +/// +/// // Runtime-obtained array index. +/// let scratch_idx = get_scratch_idx(); +/// // Access on a runtime index returns an error if it is out-of-bounds. +/// let some_scratch = SCRATCH::try_read(bar, scratch_idx)?.value(); +/// +/// // Alias to a particular register in an array. +/// // Here `SCRATCH[8]` is used to convey the firmware exit code. +/// register!(FIRMWARE_STATUS => SCRATCH[8], "Firmware exit status code" { +/// 7:0 status as u8; +/// }); +/// +/// let status = FIRMWARE_STATUS::read(bar).status(); +/// +/// // Non-contiguous register arrays can be defined by adding a stride parameter. +/// // Here, each of the 16 registers of the array are separated by 8 bytes, meaning that the +/// // registers of the two declarations below are interleaved. +/// register!(SCRATCH_INTERLEAVED_0 @ 0x000000c0[16 ; 8], "Scratch registers bank 0" { +/// 31:0 value as u32; +/// }); +/// register!(SCRATCH_INTERLEAVED_1 @ 0x000000c4[16 ; 8], "Scratch registers bank 1" { +/// 31:0 value as u32; +/// }); +/// # Ok(()) +/// # } /// ``` /// -/// In this example, `SCRATCH_0_BOOT_STATUS` uses the same I/O address as `SCRATCH_0`, while also -/// providing its own `completed` method. +/// ## Relative arrays of registers +/// +/// Combining the two features described in the sections above, arrays of registers accessible from +/// a base can also be defined: +/// +/// ```no_run +/// # fn no_run() -> Result<(), Error> { +/// # fn get_scratch_idx() -> usize { +/// # 0x15 +/// # } +/// // Type used as parameter of `RegisterBase` to specify the base. +/// pub(crate) struct CpuCtlBase; +/// +/// // ZST describing `CPU0`. +/// struct Cpu0; +/// impl RegisterBase<CpuCtlBase> for Cpu0 { +/// const BASE: usize = 0x100; +/// } +/// // Singleton of `CPU0` used to identify it. +/// const CPU0: Cpu0 = Cpu0; +/// +/// // ZST describing `CPU1`. +/// struct Cpu1; +/// impl RegisterBase<CpuCtlBase> for Cpu1 { +/// const BASE: usize = 0x200; +/// } +/// // Singleton of `CPU1` used to identify it. +/// const CPU1: Cpu1 = Cpu1; +/// +/// // 64 per-cpu scratch registers, arranged as an contiguous array. +/// register!(CPU_SCRATCH @ CpuCtlBase[0x00000080[64]], "Per-CPU scratch registers" { +/// 31:0 value as u32; +/// }); +/// +/// let cpu0_scratch_0 = CPU_SCRATCH::read(bar, &Cpu0, 0).value(); +/// let cpu1_scratch_15 = CPU_SCRATCH::read(bar, &Cpu1, 15).value(); +/// +/// // This won't build. +/// // let cpu0_scratch_128 = CPU_SCRATCH::read(bar, &Cpu0, 128).value(); +/// +/// // Runtime-obtained array index. +/// let scratch_idx = get_scratch_idx(); +/// // Access on a runtime value returns an error if it is out-of-bounds. +/// let cpu0_some_scratch = CPU_SCRATCH::try_read(bar, &Cpu0, scratch_idx)?.value(); +/// +/// // `SCRATCH[8]` is used to convey the firmware exit code. +/// register!(CPU_FIRMWARE_STATUS => CpuCtlBase[CPU_SCRATCH[8]], +/// "Per-CPU firmware exit status code" { +/// 7:0 status as u8; +/// }); +/// +/// let cpu0_status = CPU_FIRMWARE_STATUS::read(bar, &Cpu0).status(); +/// +/// // Non-contiguous register arrays can be defined by adding a stride parameter. +/// // Here, each of the 16 registers of the array are separated by 8 bytes, meaning that the +/// // registers of the two declarations below are interleaved. +/// register!(CPU_SCRATCH_INTERLEAVED_0 @ CpuCtlBase[0x00000d00[16 ; 8]], +/// "Scratch registers bank 0" { +/// 31:0 value as u32; +/// }); +/// register!(CPU_SCRATCH_INTERLEAVED_1 @ CpuCtlBase[0x00000d04[16 ; 8]], +/// "Scratch registers bank 1" { +/// 31:0 value as u32; +/// }); +/// # Ok(()) +/// # } +/// ``` macro_rules! register { // Creates a register at a fixed offset of the MMIO space. + ($name:ident @ $offset:literal $(, $comment:literal)? { $($fields:tt)* } ) => { + register!(@core $name $(, $comment)? { $($fields)* } ); + register!(@io_fixed $name @ $offset); + }; + + // Creates an alias register of fixed offset register `alias` with its own fields. + ($name:ident => $alias:ident $(, $comment:literal)? { $($fields:tt)* } ) => { + register!(@core $name $(, $comment)? { $($fields)* } ); + register!(@io_fixed $name @ $alias::OFFSET); + }; + + // Creates a register at a relative offset from a base address provider. + ($name:ident @ $base:ty [ $offset:literal ] $(, $comment:literal)? { $($fields:tt)* } ) => { + register!(@core $name $(, $comment)? { $($fields)* } ); + register!(@io_relative $name @ $base [ $offset ]); + }; + + // Creates an alias register of relative offset register `alias` with its own fields. + ($name:ident => $base:ty [ $alias:ident ] $(, $comment:literal)? { $($fields:tt)* }) => { + register!(@core $name $(, $comment)? { $($fields)* } ); + register!(@io_relative $name @ $base [ $alias::OFFSET ]); + }; + + // Creates an array of registers at a fixed offset of the MMIO space. ( - $name:ident @ $offset:literal $(, $comment:literal)? { + $name:ident @ $offset:literal [ $size:expr ; $stride:expr ] $(, $comment:literal)? { $($fields:tt)* } ) => { - register!(@common $name @ $offset $(, $comment)?); - register!(@field_accessors $name { $($fields)* }); - register!(@io $name @ $offset); + static_assert!(::core::mem::size_of::<u32>() <= $stride); + register!(@core $name $(, $comment)? { $($fields)* } ); + register!(@io_array $name @ $offset [ $size ; $stride ]); }; - // Creates a alias register of fixed offset register `alias` with its own fields. + // Shortcut for contiguous array of registers (stride == size of element). ( - $name:ident => $alias:ident $(, $comment:literal)? { + $name:ident @ $offset:literal [ $size:expr ] $(, $comment:literal)? { $($fields:tt)* } ) => { - register!(@common $name @ $alias::OFFSET $(, $comment)?); - register!(@field_accessors $name { $($fields)* }); - register!(@io $name @ $alias::OFFSET); + register!($name @ $offset [ $size ; ::core::mem::size_of::<u32>() ] $(, $comment)? { + $($fields)* + } ); + }; + + // Creates an array of registers at a relative offset from a base address provider. + ( + $name:ident @ $base:ty [ $offset:literal [ $size:expr ; $stride:expr ] ] + $(, $comment:literal)? { $($fields:tt)* } + ) => { + static_assert!(::core::mem::size_of::<u32>() <= $stride); + register!(@core $name $(, $comment)? { $($fields)* } ); + register!(@io_relative_array $name @ $base [ $offset [ $size ; $stride ] ]); }; - // Creates a register at a relative offset from a base address. + // Shortcut for contiguous array of relative registers (stride == size of element). ( - $name:ident @ + $offset:literal $(, $comment:literal)? { + $name:ident @ $base:ty [ $offset:literal [ $size:expr ] ] $(, $comment:literal)? { $($fields:tt)* } ) => { - register!(@common $name @ $offset $(, $comment)?); - register!(@field_accessors $name { $($fields)* }); - register!(@io$name @ + $offset); + register!($name @ $base [ $offset [ $size ; ::core::mem::size_of::<u32>() ] ] + $(, $comment)? { $($fields)* } ); }; - // Creates a alias register of relative offset register `alias` with its own fields. + // Creates an alias of register `idx` of relative array of registers `alias` with its own + // fields. ( - $name:ident => + $alias:ident $(, $comment:literal)? { + $name:ident => $base:ty [ $alias:ident [ $idx:expr ] ] $(, $comment:literal)? { $($fields:tt)* } ) => { - register!(@common $name @ $alias::OFFSET $(, $comment)?); - register!(@field_accessors $name { $($fields)* }); - register!(@io $name @ + $alias::OFFSET); + static_assert!($idx < $alias::SIZE); + register!(@core $name $(, $comment)? { $($fields)* } ); + register!(@io_relative $name @ $base [ $alias::OFFSET + $idx * $alias::STRIDE ] ); + }; + + // Creates an alias of register `idx` of array of registers `alias` with its own fields. + // This rule belongs to the (non-relative) register arrays set, but needs to be put last + // to avoid it being interpreted in place of the relative register array alias rule. + ($name:ident => $alias:ident [ $idx:expr ] $(, $comment:literal)? { $($fields:tt)* }) => { + static_assert!($idx < $alias::SIZE); + register!(@core $name $(, $comment)? { $($fields)* } ); + register!(@io_fixed $name @ $alias::OFFSET + $idx * $alias::STRIDE ); }; // All rules below are helpers. - // Defines the wrapper `$name` type, as well as its relevant implementations (`Debug`, `BitOr`, - // and conversion to regular `u32`). - (@common $name:ident @ $offset:expr $(, $comment:literal)?) => { + // Defines the wrapper `$name` type, as well as its relevant implementations (`Debug`, + // `Default`, `BitOr`, and conversion to the value type) and field accessor methods. + (@core $name:ident $(, $comment:literal)? { $($fields:tt)* }) => { $( #[doc=$comment] )? #[repr(transparent)] - #[derive(Clone, Copy, Default)] + #[derive(Clone, Copy)] pub(crate) struct $name(u32); - #[allow(dead_code)] - impl $name { - pub(crate) const OFFSET: usize = $offset; - } - - // TODO[REGA]: display the raw hex value, then the value of all the fields. This requires - // matching the fields, which will complexify the syntax considerably... - impl ::core::fmt::Debug for $name { - fn fmt(&self, f: &mut ::core::fmt::Formatter<'_>) -> ::core::fmt::Result { - f.debug_tuple(stringify!($name)) - .field(&format_args!("0x{0:x}", &self.0)) - .finish() - } - } - impl ::core::ops::BitOr for $name { type Output = Self; @@ -170,6 +394,34 @@ macro_rules! register { reg.0 } } + + register!(@fields_dispatcher $name { $($fields)* }); + }; + + // Captures the fields and passes them to all the implementers that require field information. + // + // Used to simplify the matching rules for implementers, so they don't need to match the entire + // complex fields rule even though they only make use of part of it. + (@fields_dispatcher $name:ident { + $($hi:tt:$lo:tt $field:ident as $type:tt + $(?=> $try_into_type:ty)? + $(=> $into_type:ty)? + $(, $comment:literal)? + ; + )* + } + ) => { + register!(@field_accessors $name { + $( + $hi:$lo $field as $type + $(?=> $try_into_type)? + $(=> $into_type)? + $(, $comment)? + ; + )* + }); + register!(@debug $name { $($field;)* }); + register!(@default $name { $($field;)* }); }; // Defines all the field getter/methods methods for `$name`. @@ -228,7 +480,7 @@ macro_rules! register { $(, $comment:literal)?; ) => { register!( - @leaf_accessor $name $hi:$lo $field as bool + @leaf_accessor $name $hi:$lo $field { |f| <$into_type>::from(if f != 0 { true } else { false }) } $into_type => $into_type $(, $comment)?; ); @@ -246,7 +498,7 @@ macro_rules! register { @field_accessor $name:ident $hi:tt:$lo:tt $field:ident as $type:tt ?=> $try_into_type:ty $(, $comment:literal)?; ) => { - register!(@leaf_accessor $name $hi:$lo $field as $type + register!(@leaf_accessor $name $hi:$lo $field { |f| <$try_into_type>::try_from(f as $type) } $try_into_type => ::core::result::Result< $try_into_type, @@ -260,11 +512,11 @@ macro_rules! register { @field_accessor $name:ident $hi:tt:$lo:tt $field:ident as $type:tt => $into_type:ty $(, $comment:literal)?; ) => { - register!(@leaf_accessor $name $hi:$lo $field as $type + register!(@leaf_accessor $name $hi:$lo $field { |f| <$into_type>::from(f as $type) } $into_type => $into_type $(, $comment)?;); }; - // Shortcut for fields defined as non-`bool` without the `=>` or `?=>` syntax. + // Shortcut for non-boolean fields defined without the `=>` or `?=>` syntax. ( @field_accessor $name:ident $hi:tt:$lo:tt $field:ident as $type:tt $(, $comment:literal)?; @@ -274,11 +526,11 @@ macro_rules! register { // Generates the accessor methods for a single field. ( - @leaf_accessor $name:ident $hi:tt:$lo:tt $field:ident as $type:ty + @leaf_accessor $name:ident $hi:tt:$lo:tt $field:ident { $process:expr } $to_type:ty => $res_type:ty $(, $comment:literal)?; ) => { ::kernel::macros::paste!( - const [<$field:upper>]: ::core::ops::RangeInclusive<u8> = $lo..=$hi; + const [<$field:upper _RANGE>]: ::core::ops::RangeInclusive<u8> = $lo..=$hi; const [<$field:upper _MASK>]: u32 = ((((1 << $hi) - 1) << 1) + 1) - ((1 << $lo) - 1); const [<$field:upper _SHIFT>]: u32 = Self::[<$field:upper _MASK>].trailing_zeros(); ); @@ -287,7 +539,7 @@ macro_rules! register { #[doc="Returns the value of this field:"] #[doc=$comment] )? - #[inline] + #[inline(always)] pub(crate) fn $field(self) -> $res_type { ::kernel::macros::paste!( const MASK: u32 = $name::[<$field:upper _MASK>]; @@ -303,7 +555,7 @@ macro_rules! register { #[doc="Sets the value of this field:"] #[doc=$comment] )? - #[inline] + #[inline(always)] pub(crate) fn [<set_ $field>](mut self, value: $to_type) -> Self { const MASK: u32 = $name::[<$field:upper _MASK>]; const SHIFT: u32 = $name::[<$field:upper _SHIFT>]; @@ -315,25 +567,64 @@ macro_rules! register { ); }; - // Creates the IO accessors for a fixed offset register. - (@io $name:ident @ $offset:expr) => { + // Generates the `Debug` implementation for `$name`. + (@debug $name:ident { $($field:ident;)* }) => { + impl ::core::fmt::Debug for $name { + fn fmt(&self, f: &mut ::core::fmt::Formatter<'_>) -> ::core::fmt::Result { + f.debug_struct(stringify!($name)) + .field("<raw>", &format_args!("{:#x}", &self.0)) + $( + .field(stringify!($field), &self.$field()) + )* + .finish() + } + } + }; + + // Generates the `Default` implementation for `$name`. + (@default $name:ident { $($field:ident;)* }) => { + /// Returns a value for the register where all fields are set to their default value. + impl ::core::default::Default for $name { + fn default() -> Self { + #[allow(unused_mut)] + let mut value = Self(Default::default()); + + ::kernel::macros::paste!( + $( + value.[<set_ $field>](Default::default()); + )* + ); + + value + } + } + }; + + // Generates the IO accessors for a fixed offset register. + (@io_fixed $name:ident @ $offset:expr) => { #[allow(dead_code)] impl $name { - #[inline] + pub(crate) const OFFSET: usize = $offset; + + /// Read the register from its address in `io`. + #[inline(always)] pub(crate) fn read<const SIZE: usize, T>(io: &T) -> Self where T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, { Self(io.read32($offset)) } - #[inline] + /// Write the value contained in `self` to the register address in `io`. + #[inline(always)] pub(crate) fn write<const SIZE: usize, T>(self, io: &T) where T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, { io.write32(self.0, $offset) } - #[inline] + /// Read the register from its address in `io` and run `f` on its value to obtain a new + /// value to write back. + #[inline(always)] pub(crate) fn alter<const SIZE: usize, T, F>( io: &T, f: F, @@ -347,76 +638,322 @@ macro_rules! register { } }; - // Create the IO accessors for a relative offset register. - (@io $name:ident @ + $offset:literal) => { + // Generates the IO accessors for a relative offset register. + (@io_relative $name:ident @ $base:ty [ $offset:expr ]) => { #[allow(dead_code)] impl $name { - #[inline] + pub(crate) const OFFSET: usize = $offset; + + /// Read the register from `io`, using the base address provided by `base` and adding + /// the register's offset to it. + #[inline(always)] + pub(crate) fn read<const SIZE: usize, T, B>( + io: &T, + #[allow(unused_variables)] + base: &B, + ) -> Self where + T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, + B: crate::regs::macros::RegisterBase<$base>, + { + const OFFSET: usize = $name::OFFSET; + + let value = io.read32( + <B as crate::regs::macros::RegisterBase<$base>>::BASE + OFFSET + ); + + Self(value) + } + + /// Write the value contained in `self` to `io`, using the base address provided by + /// `base` and adding the register's offset to it. + #[inline(always)] + pub(crate) fn write<const SIZE: usize, T, B>( + self, + io: &T, + #[allow(unused_variables)] + base: &B, + ) where + T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, + B: crate::regs::macros::RegisterBase<$base>, + { + const OFFSET: usize = $name::OFFSET; + + io.write32( + self.0, + <B as crate::regs::macros::RegisterBase<$base>>::BASE + OFFSET + ); + } + + /// Read the register from `io`, using the base address provided by `base` and adding + /// the register's offset to it, then run `f` on its value to obtain a new value to + /// write back. + #[inline(always)] + pub(crate) fn alter<const SIZE: usize, T, B, F>( + io: &T, + base: &B, + f: F, + ) where + T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, + B: crate::regs::macros::RegisterBase<$base>, + F: ::core::ops::FnOnce(Self) -> Self, + { + let reg = f(Self::read(io, base)); + reg.write(io, base); + } + } + }; + + // Generates the IO accessors for an array of registers. + (@io_array $name:ident @ $offset:literal [ $size:expr ; $stride:expr ]) => { + #[allow(dead_code)] + impl $name { + pub(crate) const OFFSET: usize = $offset; + pub(crate) const SIZE: usize = $size; + pub(crate) const STRIDE: usize = $stride; + + /// Read the array register at index `idx` from its address in `io`. + #[inline(always)] pub(crate) fn read<const SIZE: usize, T>( io: &T, - base: usize, + idx: usize, ) -> Self where T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, { - Self(io.read32(base + $offset)) + build_assert!(idx < Self::SIZE); + + let offset = Self::OFFSET + (idx * Self::STRIDE); + let value = io.read32(offset); + + Self(value) } - #[inline] + /// Write the value contained in `self` to the array register with index `idx` in `io`. + #[inline(always)] pub(crate) fn write<const SIZE: usize, T>( self, io: &T, - base: usize, + idx: usize ) where T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, { - io.write32(self.0, base + $offset) + build_assert!(idx < Self::SIZE); + + let offset = Self::OFFSET + (idx * Self::STRIDE); + + io.write32(self.0, offset); } - #[inline] + /// Read the array register at index `idx` in `io` and run `f` on its value to obtain a + /// new value to write back. + #[inline(always)] pub(crate) fn alter<const SIZE: usize, T, F>( io: &T, - base: usize, + idx: usize, f: F, ) where T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, F: ::core::ops::FnOnce(Self) -> Self, { - let reg = f(Self::read(io, base)); - reg.write(io, base); + let reg = f(Self::read(io, idx)); + reg.write(io, idx); } - #[inline] + /// Read the array register at index `idx` from its address in `io`. + /// + /// The validity of `idx` is checked at run-time, and `EINVAL` is returned is the + /// access was out-of-bounds. + #[inline(always)] pub(crate) fn try_read<const SIZE: usize, T>( io: &T, - base: usize, + idx: usize, ) -> ::kernel::error::Result<Self> where T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, { - io.try_read32(base + $offset).map(Self) + if idx < Self::SIZE { + Ok(Self::read(io, idx)) + } else { + Err(EINVAL) + } } - #[inline] + /// Write the value contained in `self` to the array register with index `idx` in `io`. + /// + /// The validity of `idx` is checked at run-time, and `EINVAL` is returned is the + /// access was out-of-bounds. + #[inline(always)] pub(crate) fn try_write<const SIZE: usize, T>( self, io: &T, - base: usize, - ) -> ::kernel::error::Result<()> where + idx: usize, + ) -> ::kernel::error::Result where T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, { - io.try_write32(self.0, base + $offset) + if idx < Self::SIZE { + Ok(self.write(io, idx)) + } else { + Err(EINVAL) + } } - #[inline] + /// Read the array register at index `idx` in `io` and run `f` on its value to obtain a + /// new value to write back. + /// + /// The validity of `idx` is checked at run-time, and `EINVAL` is returned is the + /// access was out-of-bounds. + #[inline(always)] pub(crate) fn try_alter<const SIZE: usize, T, F>( io: &T, - base: usize, + idx: usize, + f: F, + ) -> ::kernel::error::Result where + T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, + F: ::core::ops::FnOnce(Self) -> Self, + { + if idx < Self::SIZE { + Ok(Self::alter(io, idx, f)) + } else { + Err(EINVAL) + } + } + } + }; + + // Generates the IO accessors for an array of relative registers. + ( + @io_relative_array $name:ident @ $base:ty + [ $offset:literal [ $size:expr ; $stride:expr ] ] + ) => { + #[allow(dead_code)] + impl $name { + pub(crate) const OFFSET: usize = $offset; + pub(crate) const SIZE: usize = $size; + pub(crate) const STRIDE: usize = $stride; + + /// Read the array register at index `idx` from `io`, using the base address provided + /// by `base` and adding the register's offset to it. + #[inline(always)] + pub(crate) fn read<const SIZE: usize, T, B>( + io: &T, + #[allow(unused_variables)] + base: &B, + idx: usize, + ) -> Self where + T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, + B: crate::regs::macros::RegisterBase<$base>, + { + build_assert!(idx < Self::SIZE); + + let offset = <B as crate::regs::macros::RegisterBase<$base>>::BASE + + Self::OFFSET + (idx * Self::STRIDE); + let value = io.read32(offset); + + Self(value) + } + + /// Write the value contained in `self` to `io`, using the base address provided by + /// `base` and adding the offset of array register `idx` to it. + #[inline(always)] + pub(crate) fn write<const SIZE: usize, T, B>( + self, + io: &T, + #[allow(unused_variables)] + base: &B, + idx: usize + ) where + T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, + B: crate::regs::macros::RegisterBase<$base>, + { + build_assert!(idx < Self::SIZE); + + let offset = <B as crate::regs::macros::RegisterBase<$base>>::BASE + + Self::OFFSET + (idx * Self::STRIDE); + + io.write32(self.0, offset); + } + + /// Read the array register at index `idx` from `io`, using the base address provided + /// by `base` and adding the register's offset to it, then run `f` on its value to + /// obtain a new value to write back. + #[inline(always)] + pub(crate) fn alter<const SIZE: usize, T, B, F>( + io: &T, + base: &B, + idx: usize, + f: F, + ) where + T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, + B: crate::regs::macros::RegisterBase<$base>, + F: ::core::ops::FnOnce(Self) -> Self, + { + let reg = f(Self::read(io, base, idx)); + reg.write(io, base, idx); + } + + /// Read the array register at index `idx` from `io`, using the base address provided + /// by `base` and adding the register's offset to it. + /// + /// The validity of `idx` is checked at run-time, and `EINVAL` is returned is the + /// access was out-of-bounds. + #[inline(always)] + pub(crate) fn try_read<const SIZE: usize, T, B>( + io: &T, + base: &B, + idx: usize, + ) -> ::kernel::error::Result<Self> where + T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, + B: crate::regs::macros::RegisterBase<$base>, + { + if idx < Self::SIZE { + Ok(Self::read(io, base, idx)) + } else { + Err(EINVAL) + } + } + + /// Write the value contained in `self` to `io`, using the base address provided by + /// `base` and adding the offset of array register `idx` to it. + /// + /// The validity of `idx` is checked at run-time, and `EINVAL` is returned is the + /// access was out-of-bounds. + #[inline(always)] + pub(crate) fn try_write<const SIZE: usize, T, B>( + self, + io: &T, + base: &B, + idx: usize, + ) -> ::kernel::error::Result where + T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, + B: crate::regs::macros::RegisterBase<$base>, + { + if idx < Self::SIZE { + Ok(self.write(io, base, idx)) + } else { + Err(EINVAL) + } + } + + /// Read the array register at index `idx` from `io`, using the base address provided + /// by `base` and adding the register's offset to it, then run `f` on its value to + /// obtain a new value to write back. + /// + /// The validity of `idx` is checked at run-time, and `EINVAL` is returned is the + /// access was out-of-bounds. + #[inline(always)] + pub(crate) fn try_alter<const SIZE: usize, T, B, F>( + io: &T, + base: &B, + idx: usize, f: F, - ) -> ::kernel::error::Result<()> where + ) -> ::kernel::error::Result where T: ::core::ops::Deref<Target = ::kernel::io::Io<SIZE>>, + B: crate::regs::macros::RegisterBase<$base>, F: ::core::ops::FnOnce(Self) -> Self, { - let reg = f(Self::try_read(io, base)?); - reg.try_write(io, base) + if idx < Self::SIZE { + Ok(Self::alter(io, base, idx, f)) + } else { + Err(EINVAL) + } } } }; diff --git a/drivers/gpu/nova-core/util.rs b/drivers/gpu/nova-core/util.rs index 76cedf3710d7..bf35f00cb732 100644 --- a/drivers/gpu/nova-core/util.rs +++ b/drivers/gpu/nova-core/util.rs @@ -3,26 +3,6 @@ use kernel::prelude::*; use kernel::time::{Delta, Instant, Monotonic}; -pub(crate) const fn to_lowercase_bytes<const N: usize>(s: &str) -> [u8; N] { - let src = s.as_bytes(); - let mut dst = [0; N]; - let mut i = 0; - - while i < src.len() && i < N { - dst[i] = (src[i] as char).to_ascii_lowercase() as u8; - i += 1; - } - - dst -} - -pub(crate) const fn const_bytes_to_str(bytes: &[u8]) -> &str { - match core::str::from_utf8(bytes) { - Ok(string) => string, - Err(_) => kernel::build_error!("Bytes are not valid UTF-8."), - } -} - /// Wait until `cond` is true or `timeout` elapsed. /// /// When `cond` evaluates to `Some`, its return value is returned. diff --git a/drivers/gpu/nova-core/vbios.rs b/drivers/gpu/nova-core/vbios.rs index 5b5d9f38cbb3..e6a060714205 100644 --- a/drivers/gpu/nova-core/vbios.rs +++ b/drivers/gpu/nova-core/vbios.rs @@ -8,8 +8,8 @@ use crate::firmware::FalconUCodeDescV3; use core::convert::TryFrom; use kernel::device; use kernel::error::Result; -use kernel::pci; use kernel::prelude::*; +use kernel::types::ARef; /// The offset of the VBIOS ROM in the BAR0 space. const ROM_OFFSET: usize = 0x300000; @@ -31,7 +31,7 @@ const FALCON_UCODE_ENTRY_APPID_FWSEC_PROD: u8 = 0x85; /// Vbios Reader for constructing the VBIOS data. struct VbiosIterator<'a> { - pdev: &'a pci::Device, + dev: &'a device::Device, bar0: &'a Bar0, /// VBIOS data vector: As BIOS images are scanned, they are added to this vector for reference /// or copying into other data structures. It is the entire scanned contents of the VBIOS which @@ -46,9 +46,9 @@ struct VbiosIterator<'a> { } impl<'a> VbiosIterator<'a> { - fn new(pdev: &'a pci::Device, bar0: &'a Bar0) -> Result<Self> { + fn new(dev: &'a device::Device, bar0: &'a Bar0) -> Result<Self> { Ok(Self { - pdev, + dev, bar0, data: KVec::new(), current_offset: 0, @@ -64,7 +64,7 @@ impl<'a> VbiosIterator<'a> { // Ensure length is a multiple of 4 for 32-bit reads if len % core::mem::size_of::<u32>() != 0 { dev_err!( - self.pdev.as_ref(), + self.dev, "VBIOS read length {} is not a multiple of 4\n", len ); @@ -89,7 +89,7 @@ impl<'a> VbiosIterator<'a> { /// Read bytes at a specific offset, filling any gap. fn read_more_at_offset(&mut self, offset: usize, len: usize) -> Result { if offset > BIOS_MAX_SCAN_LEN { - dev_err!(self.pdev.as_ref(), "Error: exceeded BIOS scan limit.\n"); + dev_err!(self.dev, "Error: exceeded BIOS scan limit.\n"); return Err(EINVAL); } @@ -115,7 +115,7 @@ impl<'a> VbiosIterator<'a> { if offset + len > data_len { self.read_more_at_offset(offset, len).inspect_err(|e| { dev_err!( - self.pdev.as_ref(), + self.dev, "Failed to read more at offset {:#x}: {:?}\n", offset, e @@ -123,9 +123,9 @@ impl<'a> VbiosIterator<'a> { })?; } - BiosImage::new(self.pdev, &self.data[offset..offset + len]).inspect_err(|err| { + BiosImage::new(self.dev, &self.data[offset..offset + len]).inspect_err(|err| { dev_err!( - self.pdev.as_ref(), + self.dev, "Failed to {} at offset {:#x}: {:?}\n", context, offset, @@ -146,10 +146,7 @@ impl<'a> Iterator for VbiosIterator<'a> { } if self.current_offset > BIOS_MAX_SCAN_LEN { - dev_err!( - self.pdev.as_ref(), - "Error: exceeded BIOS scan limit, stopping scan\n" - ); + dev_err!(self.dev, "Error: exceeded BIOS scan limit, stopping scan\n"); return None; } @@ -192,18 +189,18 @@ impl Vbios { /// Probe for VBIOS extraction. /// /// Once the VBIOS object is built, `bar0` is not read for [`Vbios`] purposes anymore. - pub(crate) fn new(pdev: &pci::Device, bar0: &Bar0) -> Result<Vbios> { + pub(crate) fn new(dev: &device::Device, bar0: &Bar0) -> Result<Vbios> { // Images to extract from iteration let mut pci_at_image: Option<PciAtBiosImage> = None; let mut first_fwsec_image: Option<FwSecBiosBuilder> = None; let mut second_fwsec_image: Option<FwSecBiosBuilder> = None; // Parse all VBIOS images in the ROM - for image_result in VbiosIterator::new(pdev, bar0)? { + for image_result in VbiosIterator::new(dev, bar0)? { let full_image = image_result?; dev_dbg!( - pdev.as_ref(), + dev, "Found BIOS image: size: {:#x}, type: {}, last: {}\n", full_image.image_size_bytes(), full_image.image_type_str(), @@ -234,14 +231,14 @@ impl Vbios { (second_fwsec_image, first_fwsec_image, pci_at_image) { second - .setup_falcon_data(pdev, &pci_at, &first) - .inspect_err(|e| dev_err!(pdev.as_ref(), "Falcon data setup failed: {:?}\n", e))?; + .setup_falcon_data(&pci_at, &first) + .inspect_err(|e| dev_err!(dev, "Falcon data setup failed: {:?}\n", e))?; Ok(Vbios { - fwsec_image: second.build(pdev)?, + fwsec_image: second.build()?, }) } else { dev_err!( - pdev.as_ref(), + dev, "Missing required images for falcon data setup, skipping\n" ); Err(EINVAL) @@ -284,9 +281,9 @@ struct PcirStruct { } impl PcirStruct { - fn new(pdev: &pci::Device, data: &[u8]) -> Result<Self> { + fn new(dev: &device::Device, data: &[u8]) -> Result<Self> { if data.len() < core::mem::size_of::<PcirStruct>() { - dev_err!(pdev.as_ref(), "Not enough data for PcirStruct\n"); + dev_err!(dev, "Not enough data for PcirStruct\n"); return Err(EINVAL); } @@ -295,11 +292,7 @@ impl PcirStruct { // Signature should be "PCIR" (0x52494350) or "NPDS" (0x5344504e). if &signature != b"PCIR" && &signature != b"NPDS" { - dev_err!( - pdev.as_ref(), - "Invalid signature for PcirStruct: {:?}\n", - signature - ); + dev_err!(dev, "Invalid signature for PcirStruct: {:?}\n", signature); return Err(EINVAL); } @@ -308,7 +301,7 @@ impl PcirStruct { let image_len = u16::from_le_bytes([data[16], data[17]]); if image_len == 0 { - dev_err!(pdev.as_ref(), "Invalid image length: 0\n"); + dev_err!(dev, "Invalid image length: 0\n"); return Err(EINVAL); } @@ -345,7 +338,7 @@ impl PcirStruct { /// its header) is in the [`PciAtBiosImage`] and the falcon data it is pointing to is in the /// [`FwSecBiosImage`]. #[derive(Debug, Clone, Copy)] -#[expect(dead_code)] +#[repr(C)] struct BitHeader { /// 0h: BIT Header Identifier (BMP=0x7FFF/BIT=0xB8FF) id: u16, @@ -365,7 +358,7 @@ struct BitHeader { impl BitHeader { fn new(data: &[u8]) -> Result<Self> { - if data.len() < 12 { + if data.len() < core::mem::size_of::<Self>() { return Err(EINVAL); } @@ -467,7 +460,7 @@ struct PciRomHeader { } impl PciRomHeader { - fn new(pdev: &pci::Device, data: &[u8]) -> Result<Self> { + fn new(dev: &device::Device, data: &[u8]) -> Result<Self> { if data.len() < 26 { // Need at least 26 bytes to read pciDataStrucPtr and sizeOfBlock. return Err(EINVAL); @@ -479,7 +472,7 @@ impl PciRomHeader { match signature { 0xAA55 | 0xBB77 | 0x4E56 => {} _ => { - dev_err!(pdev.as_ref(), "ROM signature unknown {:#x}\n", signature); + dev_err!(dev, "ROM signature unknown {:#x}\n", signature); return Err(EINVAL); } } @@ -538,9 +531,9 @@ struct NpdeStruct { } impl NpdeStruct { - fn new(pdev: &pci::Device, data: &[u8]) -> Option<Self> { + fn new(dev: &device::Device, data: &[u8]) -> Option<Self> { if data.len() < core::mem::size_of::<Self>() { - dev_dbg!(pdev.as_ref(), "Not enough data for NpdeStruct\n"); + dev_dbg!(dev, "Not enough data for NpdeStruct\n"); return None; } @@ -549,17 +542,13 @@ impl NpdeStruct { // Signature should be "NPDE" (0x4544504E). if &signature != b"NPDE" { - dev_dbg!( - pdev.as_ref(), - "Invalid signature for NpdeStruct: {:?}\n", - signature - ); + dev_dbg!(dev, "Invalid signature for NpdeStruct: {:?}\n", signature); return None; } let subimage_len = u16::from_le_bytes([data[8], data[9]]); if subimage_len == 0 { - dev_dbg!(pdev.as_ref(), "Invalid subimage length: 0\n"); + dev_dbg!(dev, "Invalid subimage length: 0\n"); return None; } @@ -584,7 +573,7 @@ impl NpdeStruct { /// Try to find NPDE in the data, the NPDE is right after the PCIR. fn find_in_data( - pdev: &pci::Device, + dev: &device::Device, data: &[u8], rom_header: &PciRomHeader, pcir: &PcirStruct, @@ -596,12 +585,12 @@ impl NpdeStruct { // Check if we have enough data if npde_start + core::mem::size_of::<Self>() > data.len() { - dev_dbg!(pdev.as_ref(), "Not enough data for NPDE\n"); + dev_dbg!(dev, "Not enough data for NPDE\n"); return None; } // Try to create NPDE from the data - NpdeStruct::new(pdev, &data[npde_start..]) + NpdeStruct::new(dev, &data[npde_start..]) } } @@ -669,10 +658,10 @@ impl BiosImage { /// Create a [`BiosImageBase`] from a byte slice and convert it to a [`BiosImage`] which /// triggers the constructor of the specific BiosImage enum variant. - fn new(pdev: &pci::Device, data: &[u8]) -> Result<Self> { - let base = BiosImageBase::new(pdev, data)?; + fn new(dev: &device::Device, data: &[u8]) -> Result<Self> { + let base = BiosImageBase::new(dev, data)?; let image = base.into_image().inspect_err(|e| { - dev_err!(pdev.as_ref(), "Failed to create BiosImage: {:?}\n", e); + dev_err!(dev, "Failed to create BiosImage: {:?}\n", e); })?; Ok(image) @@ -754,9 +743,10 @@ impl TryFrom<BiosImageBase> for BiosImage { /// /// Each BiosImage type has a BiosImageBase type along with other image-specific fields. Note that /// Rust favors composition of types over inheritance. -#[derive(Debug)] #[expect(dead_code)] struct BiosImageBase { + /// Used for logging. + dev: ARef<device::Device>, /// PCI ROM Expansion Header rom_header: PciRomHeader, /// PCI Data Structure @@ -773,16 +763,16 @@ impl BiosImageBase { } /// Creates a new BiosImageBase from raw byte data. - fn new(pdev: &pci::Device, data: &[u8]) -> Result<Self> { + fn new(dev: &device::Device, data: &[u8]) -> Result<Self> { // Ensure we have enough data for the ROM header. if data.len() < 26 { - dev_err!(pdev.as_ref(), "Not enough data for ROM header\n"); + dev_err!(dev, "Not enough data for ROM header\n"); return Err(EINVAL); } // Parse the ROM header. - let rom_header = PciRomHeader::new(pdev, &data[0..26]) - .inspect_err(|e| dev_err!(pdev.as_ref(), "Failed to create PciRomHeader: {:?}\n", e))?; + let rom_header = PciRomHeader::new(dev, &data[0..26]) + .inspect_err(|e| dev_err!(dev, "Failed to create PciRomHeader: {:?}\n", e))?; // Get the PCI Data Structure using the pointer from the ROM header. let pcir_offset = rom_header.pci_data_struct_offset as usize; @@ -791,28 +781,29 @@ impl BiosImageBase { .ok_or(EINVAL) .inspect_err(|_| { dev_err!( - pdev.as_ref(), + dev, "PCIR offset {:#x} out of bounds (data length: {})\n", pcir_offset, data.len() ); dev_err!( - pdev.as_ref(), + dev, "Consider reading more data for construction of BiosImage\n" ); })?; - let pcir = PcirStruct::new(pdev, pcir_data) - .inspect_err(|e| dev_err!(pdev.as_ref(), "Failed to create PcirStruct: {:?}\n", e))?; + let pcir = PcirStruct::new(dev, pcir_data) + .inspect_err(|e| dev_err!(dev, "Failed to create PcirStruct: {:?}\n", e))?; // Look for NPDE structure if this is not an NBSI image (type != 0x70). - let npde = NpdeStruct::find_in_data(pdev, data, &rom_header, &pcir); + let npde = NpdeStruct::find_in_data(dev, data, &rom_header, &pcir); // Create a copy of the data. let mut data_copy = KVec::new(); data_copy.extend_from_slice(data, GFP_KERNEL)?; Ok(BiosImageBase { + dev: dev.into(), rom_header, pcir, npde, @@ -848,7 +839,7 @@ impl PciAtBiosImage { /// /// This is just a 4 byte structure that contains a pointer to the Falcon data in the FWSEC /// image. - fn falcon_data_ptr(&self, pdev: &pci::Device) -> Result<u32> { + fn falcon_data_ptr(&self) -> Result<u32> { let token = self.get_bit_token(BIT_TOKEN_ID_FALCON_DATA)?; // Make sure we don't go out of bounds @@ -859,14 +850,14 @@ impl PciAtBiosImage { // read the 4 bytes at the offset specified in the token let offset = token.data_offset as usize; let bytes: [u8; 4] = self.base.data[offset..offset + 4].try_into().map_err(|_| { - dev_err!(pdev.as_ref(), "Failed to convert data slice to array"); + dev_err!(self.base.dev, "Failed to convert data slice to array"); EINVAL })?; let data_ptr = u32::from_le_bytes(bytes); if (data_ptr as usize) < self.base.data.len() { - dev_err!(pdev.as_ref(), "Falcon data pointer out of bounds\n"); + dev_err!(self.base.dev, "Falcon data pointer out of bounds\n"); return Err(EINVAL); } @@ -892,7 +883,7 @@ impl TryFrom<BiosImageBase> for PciAtBiosImage { /// The [`PmuLookupTableEntry`] structure is a single entry in the [`PmuLookupTable`]. /// /// See the [`PmuLookupTable`] description for more information. -#[expect(dead_code)] +#[repr(C, packed)] struct PmuLookupTableEntry { application_id: u8, target_id: u8, @@ -901,7 +892,7 @@ struct PmuLookupTableEntry { impl PmuLookupTableEntry { fn new(data: &[u8]) -> Result<Self> { - if data.len() < 6 { + if data.len() < core::mem::size_of::<Self>() { return Err(EINVAL); } @@ -928,7 +919,7 @@ struct PmuLookupTable { } impl PmuLookupTable { - fn new(pdev: &pci::Device, data: &[u8]) -> Result<Self> { + fn new(dev: &device::Device, data: &[u8]) -> Result<Self> { if data.len() < 4 { return Err(EINVAL); } @@ -940,10 +931,7 @@ impl PmuLookupTable { let required_bytes = header_len + (entry_count * entry_len); if data.len() < required_bytes { - dev_err!( - pdev.as_ref(), - "PmuLookupTable data length less than required\n" - ); + dev_err!(dev, "PmuLookupTable data length less than required\n"); return Err(EINVAL); } @@ -956,11 +944,7 @@ impl PmuLookupTable { // Debug logging of entries (dumps the table data to dmesg) for i in (header_len..required_bytes).step_by(entry_len) { - dev_dbg!( - pdev.as_ref(), - "PMU entry: {:02x?}\n", - &data[i..][..entry_len] - ); + dev_dbg!(dev, "PMU entry: {:02x?}\n", &data[i..][..entry_len]); } Ok(PmuLookupTable { @@ -997,11 +981,10 @@ impl PmuLookupTable { impl FwSecBiosBuilder { fn setup_falcon_data( &mut self, - pdev: &pci::Device, pci_at_image: &PciAtBiosImage, first_fwsec: &FwSecBiosBuilder, ) -> Result { - let mut offset = pci_at_image.falcon_data_ptr(pdev)? as usize; + let mut offset = pci_at_image.falcon_data_ptr()? as usize; let mut pmu_in_first_fwsec = false; // The falcon data pointer assumes that the PciAt and FWSEC images @@ -1024,10 +1007,15 @@ impl FwSecBiosBuilder { self.falcon_data_offset = Some(offset); if pmu_in_first_fwsec { - self.pmu_lookup_table = - Some(PmuLookupTable::new(pdev, &first_fwsec.base.data[offset..])?); + self.pmu_lookup_table = Some(PmuLookupTable::new( + &self.base.dev, + &first_fwsec.base.data[offset..], + )?); } else { - self.pmu_lookup_table = Some(PmuLookupTable::new(pdev, &self.base.data[offset..])?); + self.pmu_lookup_table = Some(PmuLookupTable::new( + &self.base.dev, + &self.base.data[offset..], + )?); } match self @@ -1040,7 +1028,7 @@ impl FwSecBiosBuilder { let mut ucode_offset = entry.data as usize; ucode_offset -= pci_at_image.base.data.len(); if ucode_offset < first_fwsec.base.data.len() { - dev_err!(pdev.as_ref(), "Falcon Ucode offset not in second Fwsec.\n"); + dev_err!(self.base.dev, "Falcon Ucode offset not in second Fwsec.\n"); return Err(EINVAL); } ucode_offset -= first_fwsec.base.data.len(); @@ -1048,7 +1036,7 @@ impl FwSecBiosBuilder { } Err(e) => { dev_err!( - pdev.as_ref(), + self.base.dev, "PmuLookupTableEntry not found, error: {:?}\n", e ); @@ -1059,7 +1047,7 @@ impl FwSecBiosBuilder { } /// Build the final FwSecBiosImage from this builder - fn build(self, pdev: &pci::Device) -> Result<FwSecBiosImage> { + fn build(self) -> Result<FwSecBiosImage> { let ret = FwSecBiosImage { base: self.base, falcon_ucode_offset: self.falcon_ucode_offset.ok_or(EINVAL)?, @@ -1067,8 +1055,8 @@ impl FwSecBiosBuilder { if cfg!(debug_assertions) { // Print the desc header for debugging - let desc = ret.header(pdev.as_ref())?; - dev_dbg!(pdev.as_ref(), "PmuLookupTableEntry desc: {:#?}\n", desc); + let desc = ret.header()?; + dev_dbg!(ret.base.dev, "PmuLookupTableEntry desc: {:#?}\n", desc); } Ok(ret) @@ -1077,13 +1065,16 @@ impl FwSecBiosBuilder { impl FwSecBiosImage { /// Get the FwSec header ([`FalconUCodeDescV3`]). - pub(crate) fn header(&self, dev: &device::Device) -> Result<&FalconUCodeDescV3> { + pub(crate) fn header(&self) -> Result<&FalconUCodeDescV3> { // Get the falcon ucode offset that was found in setup_falcon_data. let falcon_ucode_offset = self.falcon_ucode_offset; // Make sure the offset is within the data bounds. if falcon_ucode_offset + core::mem::size_of::<FalconUCodeDescV3>() > self.base.data.len() { - dev_err!(dev, "fwsec-frts header not contained within BIOS bounds\n"); + dev_err!( + self.base.dev, + "fwsec-frts header not contained within BIOS bounds\n" + ); return Err(ERANGE); } @@ -1095,7 +1086,7 @@ impl FwSecBiosImage { let ver = (hdr & 0xff00) >> 8; if ver != 3 { - dev_err!(dev, "invalid fwsec firmware version: {:?}\n", ver); + dev_err!(self.base.dev, "invalid fwsec firmware version: {:?}\n", ver); return Err(EINVAL); } @@ -1115,7 +1106,7 @@ impl FwSecBiosImage { } /// Get the ucode data as a byte slice - pub(crate) fn ucode(&self, dev: &device::Device, desc: &FalconUCodeDescV3) -> Result<&[u8]> { + pub(crate) fn ucode(&self, desc: &FalconUCodeDescV3) -> Result<&[u8]> { let falcon_ucode_offset = self.falcon_ucode_offset; // The ucode data follows the descriptor. @@ -1127,15 +1118,16 @@ impl FwSecBiosImage { .data .get(ucode_data_offset..ucode_data_offset + size) .ok_or(ERANGE) - .inspect_err(|_| dev_err!(dev, "fwsec ucode data not contained within BIOS bounds\n")) + .inspect_err(|_| { + dev_err!( + self.base.dev, + "fwsec ucode data not contained within BIOS bounds\n" + ) + }) } /// Get the signatures as a byte slice - pub(crate) fn sigs( - &self, - dev: &device::Device, - desc: &FalconUCodeDescV3, - ) -> Result<&[Bcrt30Rsa3kSignature]> { + pub(crate) fn sigs(&self, desc: &FalconUCodeDescV3) -> Result<&[Bcrt30Rsa3kSignature]> { // The signatures data follows the descriptor. let sigs_data_offset = self.falcon_ucode_offset + core::mem::size_of::<FalconUCodeDescV3>(); let sigs_size = @@ -1144,7 +1136,7 @@ impl FwSecBiosImage { // Make sure the data is within bounds. if sigs_data_offset + sigs_size > self.base.data.len() { dev_err!( - dev, + self.base.dev, "fwsec signatures data not contained within BIOS bounds\n" ); return Err(ERANGE); diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h index 84d60635e8a9..c2cc52ee9945 100644 --- a/rust/bindings/bindings_helper.h +++ b/rust/bindings/bindings_helper.h @@ -47,6 +47,7 @@ #include <linux/cpumask.h> #include <linux/cred.h> #include <linux/device/faux.h> +#include <linux/dma-direction.h> #include <linux/dma-mapping.h> #include <linux/errname.h> #include <linux/ethtool.h> @@ -57,6 +58,7 @@ #include <linux/jiffies.h> #include <linux/jump_label.h> #include <linux/mdio.h> +#include <linux/mm.h> #include <linux/miscdevice.h> #include <linux/of_device.h> #include <linux/pci.h> diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c index 7cf7fe95e41d..e94542bf6ea7 100644 --- a/rust/helpers/helpers.c +++ b/rust/helpers/helpers.c @@ -39,6 +39,7 @@ #include "rcu.c" #include "refcount.c" #include "regulator.c" +#include "scatterlist.c" #include "security.c" #include "signal.c" #include "slab.c" diff --git a/rust/helpers/scatterlist.c b/rust/helpers/scatterlist.c new file mode 100644 index 000000000000..80c956ee09ab --- /dev/null +++ b/rust/helpers/scatterlist.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/dma-direction.h> + +dma_addr_t rust_helper_sg_dma_address(struct scatterlist *sg) +{ + return sg_dma_address(sg); +} + +unsigned int rust_helper_sg_dma_len(struct scatterlist *sg) +{ + return sg_dma_len(sg); +} + +struct scatterlist *rust_helper_sg_next(struct scatterlist *sg) +{ + return sg_next(sg); +} + +void rust_helper_dma_unmap_sgtable(struct device *dev, struct sg_table *sgt, + enum dma_data_direction dir, unsigned long attrs) +{ + return dma_unmap_sgtable(dev, sgt, dir, attrs); +} diff --git a/rust/kernel/alloc/allocator.rs b/rust/kernel/alloc/allocator.rs index 2692cf90c948..84ee7e9d7b0e 100644 --- a/rust/kernel/alloc/allocator.rs +++ b/rust/kernel/alloc/allocator.rs @@ -15,8 +15,12 @@ use core::ptr::NonNull; use crate::alloc::{AllocError, Allocator}; use crate::bindings; +use crate::page; use crate::pr_warn; +mod iter; +pub use self::iter::VmallocPageIter; + /// The contiguous kernel allocator. /// /// `Kmalloc` is typically used for physically contiguous allocations up to page size, but also @@ -142,6 +146,54 @@ unsafe impl Allocator for Kmalloc { } } +impl Vmalloc { + /// Convert a pointer to a [`Vmalloc`] allocation to a [`page::BorrowedPage`]. + /// + /// # Examples + /// + /// ``` + /// # use core::ptr::{NonNull, from_mut}; + /// # use kernel::{page, prelude::*}; + /// use kernel::alloc::allocator::Vmalloc; + /// + /// let mut vbox = VBox::<[u8; page::PAGE_SIZE]>::new_uninit(GFP_KERNEL)?; + /// + /// { + /// // SAFETY: By the type invariant of `Box` the inner pointer of `vbox` is non-null. + /// let ptr = unsafe { NonNull::new_unchecked(from_mut(&mut *vbox)) }; + /// + /// // SAFETY: + /// // `ptr` is a valid pointer to a `Vmalloc` allocation. + /// // `ptr` is valid for the entire lifetime of `page`. + /// let page = unsafe { Vmalloc::to_page(ptr.cast()) }; + /// + /// // SAFETY: There is no concurrent read or write to the same page. + /// unsafe { page.fill_zero_raw(0, page::PAGE_SIZE)? }; + /// } + /// # Ok::<(), Error>(()) + /// ``` + /// + /// # Safety + /// + /// - `ptr` must be a valid pointer to a [`Vmalloc`] allocation. + /// - `ptr` must remain valid for the entire duration of `'a`. + pub unsafe fn to_page<'a>(ptr: NonNull<u8>) -> page::BorrowedPage<'a> { + // SAFETY: `ptr` is a valid pointer to `Vmalloc` memory. + let page = unsafe { bindings::vmalloc_to_page(ptr.as_ptr().cast()) }; + + // SAFETY: `vmalloc_to_page` returns a valid pointer to a `struct page` for a valid pointer + // to `Vmalloc` memory. + let page = unsafe { NonNull::new_unchecked(page) }; + + // SAFETY: + // - `page` is a valid pointer to a `struct page`, given that by the safety requirements of + // this function `ptr` is a valid pointer to a `Vmalloc` allocation. + // - By the safety requirements of this function `ptr` is valid for the entire lifetime of + // `'a`. + unsafe { page::BorrowedPage::from_raw(page) } + } +} + // SAFETY: `realloc` delegates to `ReallocFunc::call`, which guarantees that // - memory remains valid until it is explicitly freed, // - passing a pointer to a valid memory allocation is OK, diff --git a/rust/kernel/alloc/allocator/iter.rs b/rust/kernel/alloc/allocator/iter.rs new file mode 100644 index 000000000000..5759f86029b7 --- /dev/null +++ b/rust/kernel/alloc/allocator/iter.rs @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0 + +use super::Vmalloc; +use crate::page; +use core::marker::PhantomData; +use core::ptr::NonNull; + +/// An [`Iterator`] of [`page::BorrowedPage`] items owned by a [`Vmalloc`] allocation. +/// +/// # Guarantees +/// +/// The pages iterated by the [`Iterator`] appear in the order as they are mapped in the CPU's +/// virtual address space ascendingly. +/// +/// # Invariants +/// +/// - `buf` is a valid and [`page::PAGE_SIZE`] aligned pointer into a [`Vmalloc`] allocation. +/// - `size` is the number of bytes from `buf` until the end of the [`Vmalloc`] allocation `buf` +/// points to. +pub struct VmallocPageIter<'a> { + /// The base address of the [`Vmalloc`] buffer. + buf: NonNull<u8>, + /// The size of the buffer pointed to by `buf` in bytes. + size: usize, + /// The current page index of the [`Iterator`]. + index: usize, + _p: PhantomData<page::BorrowedPage<'a>>, +} + +impl<'a> Iterator for VmallocPageIter<'a> { + type Item = page::BorrowedPage<'a>; + + fn next(&mut self) -> Option<Self::Item> { + let offset = self.index.checked_mul(page::PAGE_SIZE)?; + + // Even though `self.size()` may be smaller than `Self::page_count() * page::PAGE_SIZE`, it + // is always a number between `(Self::page_count() - 1) * page::PAGE_SIZE` and + // `Self::page_count() * page::PAGE_SIZE`, hence the check below is sufficient. + if offset < self.size() { + self.index += 1; + } else { + return None; + } + + // TODO: Use `NonNull::add()` instead, once the minimum supported compiler version is + // bumped to 1.80 or later. + // + // SAFETY: `offset` is in the interval `[0, (self.page_count() - 1) * page::PAGE_SIZE]`, + // hence the resulting pointer is guaranteed to be within the same allocation. + let ptr = unsafe { self.buf.as_ptr().add(offset) }; + + // SAFETY: `ptr` is guaranteed to be non-null given that it is derived from `self.buf`. + let ptr = unsafe { NonNull::new_unchecked(ptr) }; + + // SAFETY: + // - `ptr` is a valid pointer to a `Vmalloc` allocation. + // - `ptr` is valid for the duration of `'a`. + Some(unsafe { Vmalloc::to_page(ptr) }) + } + + fn size_hint(&self) -> (usize, Option<usize>) { + let remaining = self.page_count().saturating_sub(self.index); + + (remaining, Some(remaining)) + } +} + +impl<'a> VmallocPageIter<'a> { + /// Creates a new [`VmallocPageIter`] instance. + /// + /// # Safety + /// + /// - `buf` must be a [`page::PAGE_SIZE`] aligned pointer into a [`Vmalloc`] allocation. + /// - `buf` must be valid for at least the lifetime of `'a`. + /// - `size` must be the number of bytes from `buf` until the end of the [`Vmalloc`] allocation + /// `buf` points to. + pub unsafe fn new(buf: NonNull<u8>, size: usize) -> Self { + // INVARIANT: By the safety requirements, `buf` is a valid and `page::PAGE_SIZE` aligned + // pointer into a [`Vmalloc`] allocation. + Self { + buf, + size, + index: 0, + _p: PhantomData, + } + } + + /// Returns the size of the backing [`Vmalloc`] allocation in bytes. + /// + /// Note that this is the size the [`Vmalloc`] allocation has been allocated with. Hence, this + /// number may be smaller than `[`Self::page_count`] * [`page::PAGE_SIZE`]`. + #[inline] + pub fn size(&self) -> usize { + self.size + } + + /// Returns the number of pages owned by the backing [`Vmalloc`] allocation. + #[inline] + pub fn page_count(&self) -> usize { + self.size().div_ceil(page::PAGE_SIZE) + } +} diff --git a/rust/kernel/alloc/allocator_test.rs b/rust/kernel/alloc/allocator_test.rs index 90dd987d40e4..7b10e276f621 100644 --- a/rust/kernel/alloc/allocator_test.rs +++ b/rust/kernel/alloc/allocator_test.rs @@ -12,8 +12,10 @@ use super::{flags::*, AllocError, Allocator, Flags}; use core::alloc::Layout; use core::cmp; +use core::marker::PhantomData; use core::ptr; use core::ptr::NonNull; +use kernel::page; /// The userspace allocator based on libc. pub struct Cmalloc; @@ -33,6 +35,33 @@ impl Cmalloc { } } +pub struct VmallocPageIter<'a> { + _p: PhantomData<page::BorrowedPage<'a>>, +} + +impl<'a> Iterator for VmallocPageIter<'a> { + type Item = page::BorrowedPage<'a>; + + fn next(&mut self) -> Option<Self::Item> { + None + } +} + +impl<'a> VmallocPageIter<'a> { + #[allow(clippy::missing_safety_doc)] + pub unsafe fn new(_buf: NonNull<u8>, _size: usize) -> Self { + Self { _p: PhantomData } + } + + pub fn size(&self) -> usize { + 0 + } + + pub fn page_count(&self) -> usize { + 0 + } +} + extern "C" { #[link_name = "aligned_alloc"] fn libc_aligned_alloc(align: usize, size: usize) -> *mut crate::ffi::c_void; diff --git a/rust/kernel/alloc/kbox.rs b/rust/kernel/alloc/kbox.rs index 856d05aa60f1..b69ff4a1d748 100644 --- a/rust/kernel/alloc/kbox.rs +++ b/rust/kernel/alloc/kbox.rs @@ -3,7 +3,7 @@ //! Implementation of [`Box`]. #[allow(unused_imports)] // Used in doc comments. -use super::allocator::{KVmalloc, Kmalloc, Vmalloc}; +use super::allocator::{KVmalloc, Kmalloc, Vmalloc, VmallocPageIter}; use super::{AllocError, Allocator, Flags}; use core::alloc::Layout; use core::borrow::{Borrow, BorrowMut}; @@ -18,6 +18,7 @@ use core::result::Result; use crate::ffi::c_void; use crate::init::InPlaceInit; +use crate::page::AsPageIter; use crate::types::ForeignOwnable; use pin_init::{InPlaceWrite, Init, PinInit, ZeroableOption}; @@ -598,3 +599,40 @@ where unsafe { A::free(self.0.cast(), layout) }; } } + +/// # Examples +/// +/// ``` +/// # use kernel::prelude::*; +/// use kernel::alloc::allocator::VmallocPageIter; +/// use kernel::page::{AsPageIter, PAGE_SIZE}; +/// +/// let mut vbox = VBox::new((), GFP_KERNEL)?; +/// +/// assert!(vbox.page_iter().next().is_none()); +/// +/// let mut vbox = VBox::<[u8; PAGE_SIZE]>::new_uninit(GFP_KERNEL)?; +/// +/// let page = vbox.page_iter().next().expect("At least one page should be available.\n"); +/// +/// // SAFETY: There is no concurrent read or write to the same page. +/// unsafe { page.fill_zero_raw(0, PAGE_SIZE)? }; +/// # Ok::<(), Error>(()) +/// ``` +impl<T> AsPageIter for VBox<T> { + type Iter<'a> + = VmallocPageIter<'a> + where + T: 'a; + + fn page_iter(&mut self) -> Self::Iter<'_> { + let ptr = self.0.cast(); + let size = core::mem::size_of::<T>(); + + // SAFETY: + // - `ptr` is a valid pointer to the beginning of a `Vmalloc` allocation. + // - `ptr` is guaranteed to be valid for the lifetime of `'a`. + // - `size` is the size of the `Vmalloc` allocation `ptr` points to. + unsafe { VmallocPageIter::new(ptr, size) } + } +} diff --git a/rust/kernel/alloc/kvec.rs b/rust/kernel/alloc/kvec.rs index 3c72e0bdddb8..ac438e70a1ed 100644 --- a/rust/kernel/alloc/kvec.rs +++ b/rust/kernel/alloc/kvec.rs @@ -3,10 +3,11 @@ //! Implementation of [`Vec`]. use super::{ - allocator::{KVmalloc, Kmalloc, Vmalloc}, + allocator::{KVmalloc, Kmalloc, Vmalloc, VmallocPageIter}, layout::ArrayLayout, AllocError, Allocator, Box, Flags, }; +use crate::page::AsPageIter; use core::{ borrow::{Borrow, BorrowMut}, fmt, @@ -1017,6 +1018,43 @@ where } } +/// # Examples +/// +/// ``` +/// # use kernel::prelude::*; +/// use kernel::alloc::allocator::VmallocPageIter; +/// use kernel::page::{AsPageIter, PAGE_SIZE}; +/// +/// let mut vec = VVec::<u8>::new(); +/// +/// assert!(vec.page_iter().next().is_none()); +/// +/// vec.reserve(PAGE_SIZE, GFP_KERNEL)?; +/// +/// let page = vec.page_iter().next().expect("At least one page should be available.\n"); +/// +/// // SAFETY: There is no concurrent read or write to the same page. +/// unsafe { page.fill_zero_raw(0, PAGE_SIZE)? }; +/// # Ok::<(), Error>(()) +/// ``` +impl<T> AsPageIter for VVec<T> { + type Iter<'a> + = VmallocPageIter<'a> + where + T: 'a; + + fn page_iter(&mut self) -> Self::Iter<'_> { + let ptr = self.ptr.cast(); + let size = self.layout.size(); + + // SAFETY: + // - `ptr` is a valid pointer to the beginning of a `Vmalloc` allocation. + // - `ptr` is guaranteed to be valid for the lifetime of `'a`. + // - `size` is the size of the `Vmalloc` allocation `ptr` points to. + unsafe { VmallocPageIter::new(ptr, size) } + } +} + /// An [`Iterator`] implementation for [`Vec`] that moves elements out of a vector. /// /// This structure is created by the [`Vec::into_iter`] method on [`Vec`] (provided by the diff --git a/rust/kernel/alloc/layout.rs b/rust/kernel/alloc/layout.rs index 93ed514f7cc7..666accb7859c 100644 --- a/rust/kernel/alloc/layout.rs +++ b/rust/kernel/alloc/layout.rs @@ -98,6 +98,11 @@ impl<T> ArrayLayout<T> { pub const fn is_empty(&self) -> bool { self.len == 0 } + + /// Returns the size of the [`ArrayLayout`] in bytes. + pub const fn size(&self) -> usize { + self.len() * core::mem::size_of::<T>() + } } impl<T> From<ArrayLayout<T>> for Layout { diff --git a/rust/kernel/devres.rs b/rust/kernel/devres.rs index d04e3fcebafb..aea6b7e31170 100644 --- a/rust/kernel/devres.rs +++ b/rust/kernel/devres.rs @@ -135,11 +135,9 @@ impl<T: Send> Devres<T> { T: 'a, Error: From<E>, { - let callback = Self::devres_callback; - try_pin_init!(&this in Self { dev: dev.into(), - callback, + callback: Self::devres_callback, // INVARIANT: `inner` is properly initialized. inner <- Opaque::pin_init(try_pin_init!(Inner { devm <- Completion::new(), @@ -160,7 +158,7 @@ impl<T: Send> Devres<T> { // properly initialized, because we require `dev` (i.e. the *bound* device) to // live at least as long as the returned `impl PinInit<Self, Error>`. to_result(unsafe { - bindings::devm_add_action(dev.as_raw(), Some(callback), inner.cast()) + bindings::devm_add_action(dev.as_raw(), Some(*callback), inner.cast()) }).inspect_err(|_| { let inner = Opaque::cast_into(inner); diff --git a/rust/kernel/dma.rs b/rust/kernel/dma.rs index 2bc8ab51ec28..b2a6282876da 100644 --- a/rust/kernel/dma.rs +++ b/rust/kernel/dma.rs @@ -13,6 +13,16 @@ use crate::{ types::ARef, }; +/// DMA address type. +/// +/// Represents a bus address used for Direct Memory Access (DMA) operations. +/// +/// This is an alias of the kernel's `dma_addr_t`, which may be `u32` or `u64` depending on +/// `CONFIG_ARCH_DMA_ADDR_T_64BIT`. +/// +/// Note that this may be `u64` even on 32-bit architectures. +pub type DmaAddress = bindings::dma_addr_t; + /// Trait to be implemented by DMA capable bus devices. /// /// The [`dma::Device`](Device) trait should be implemented by bus specific device representations, @@ -244,6 +254,74 @@ pub mod attrs { pub const DMA_ATTR_PRIVILEGED: Attrs = Attrs(bindings::DMA_ATTR_PRIVILEGED); } +/// DMA data direction. +/// +/// Corresponds to the C [`enum dma_data_direction`]. +/// +/// [`enum dma_data_direction`]: srctree/include/linux/dma-direction.h +#[derive(Copy, Clone, PartialEq, Eq, Debug)] +#[repr(u32)] +pub enum DataDirection { + /// The DMA mapping is for bidirectional data transfer. + /// + /// This is used when the buffer can be both read from and written to by the device. + /// The cache for the corresponding memory region is both flushed and invalidated. + Bidirectional = Self::const_cast(bindings::dma_data_direction_DMA_BIDIRECTIONAL), + + /// The DMA mapping is for data transfer from memory to the device (write). + /// + /// The CPU has prepared data in the buffer, and the device will read it. + /// The cache for the corresponding memory region is flushed before device access. + ToDevice = Self::const_cast(bindings::dma_data_direction_DMA_TO_DEVICE), + + /// The DMA mapping is for data transfer from the device to memory (read). + /// + /// The device will write data into the buffer for the CPU to read. + /// The cache for the corresponding memory region is invalidated before CPU access. + FromDevice = Self::const_cast(bindings::dma_data_direction_DMA_FROM_DEVICE), + + /// The DMA mapping is not for data transfer. + /// + /// This is primarily for debugging purposes. With this direction, the DMA mapping API + /// will not perform any cache coherency operations. + None = Self::const_cast(bindings::dma_data_direction_DMA_NONE), +} + +impl DataDirection { + /// Casts the bindgen-generated enum type to a `u32` at compile time. + /// + /// This function will cause a compile-time error if the underlying value of the + /// C enum is out of bounds for `u32`. + const fn const_cast(val: bindings::dma_data_direction) -> u32 { + // CAST: The C standard allows compilers to choose different integer types for enums. + // To safely check the value, we cast it to a wide signed integer type (`i128`) + // which can hold any standard C integer enum type without truncation. + let wide_val = val as i128; + + // Check if the value is outside the valid range for the target type `u32`. + // CAST: `u32::MAX` is cast to `i128` to match the type of `wide_val` for the comparison. + if wide_val < 0 || wide_val > u32::MAX as i128 { + // Trigger a compile-time error in a const context. + build_error!("C enum value is out of bounds for the target type `u32`."); + } + + // CAST: This cast is valid because the check above guarantees that `wide_val` + // is within the representable range of `u32`. + wide_val as u32 + } +} + +impl From<DataDirection> for bindings::dma_data_direction { + /// Returns the raw representation of [`enum dma_data_direction`]. + fn from(direction: DataDirection) -> Self { + // CAST: `direction as u32` gets the underlying representation of our `#[repr(u32)]` enum. + // The subsequent cast to `Self` (the bindgen type) assumes the C enum is compatible + // with the enum variants of `DataDirection`, which is a valid assumption given our + // compile-time checks. + direction as u32 as Self + } +} + /// An abstraction of the `dma_alloc_coherent` API. /// /// This is an abstraction around the `dma_alloc_coherent` API which is used to allocate and map @@ -275,7 +353,7 @@ pub mod attrs { // entire `CoherentAllocation` including the allocated memory itself. pub struct CoherentAllocation<T: AsBytes + FromBytes> { dev: ARef<device::Device>, - dma_handle: bindings::dma_addr_t, + dma_handle: DmaAddress, count: usize, cpu_addr: *mut T, dma_attrs: Attrs, @@ -376,7 +454,7 @@ impl<T: AsBytes + FromBytes> CoherentAllocation<T> { /// Returns a DMA handle which may be given to the device as the DMA address base of /// the region. - pub fn dma_handle(&self) -> bindings::dma_addr_t { + pub fn dma_handle(&self) -> DmaAddress { self.dma_handle } @@ -384,13 +462,13 @@ impl<T: AsBytes + FromBytes> CoherentAllocation<T> { /// device as the DMA address base of the region. /// /// Returns `EINVAL` if `offset` is not within the bounds of the allocation. - pub fn dma_handle_with_offset(&self, offset: usize) -> Result<bindings::dma_addr_t> { + pub fn dma_handle_with_offset(&self, offset: usize) -> Result<DmaAddress> { if offset >= self.count { Err(EINVAL) } else { // INVARIANT: The type invariant of `Self` guarantees that `size_of::<T> * count` fits // into a `usize`, and `offset` is inferior to `count`. - Ok(self.dma_handle + (offset * core::mem::size_of::<T>()) as bindings::dma_addr_t) + Ok(self.dma_handle + (offset * core::mem::size_of::<T>()) as DmaAddress) } } diff --git a/rust/kernel/drm/driver.rs b/rust/kernel/drm/driver.rs index 8fefae41bcc6..91e13b6ca26a 100644 --- a/rust/kernel/drm/driver.rs +++ b/rust/kernel/drm/driver.rs @@ -86,6 +86,9 @@ pub struct AllocOps { /// Trait for memory manager implementations. Implemented internally. pub trait AllocImpl: super::private::Sealed + drm::gem::IntoGEMObject { + /// The [`Driver`] implementation for this [`AllocImpl`]. + type Driver: drm::Driver; + /// The C callback operations for this memory manager. const ALLOC_OPS: AllocOps; } diff --git a/rust/kernel/drm/gem/mod.rs b/rust/kernel/drm/gem/mod.rs index a822aedee949..6ccbb25628a1 100644 --- a/rust/kernel/drm/gem/mod.rs +++ b/rust/kernel/drm/gem/mod.rs @@ -13,34 +13,34 @@ use crate::{ sync::aref::{ARef, AlwaysRefCounted}, types::Opaque, }; -use core::{mem, ops::Deref, ptr::NonNull}; +use core::{ops::Deref, ptr::NonNull}; + +/// A type alias for retrieving a [`Driver`]s [`DriverFile`] implementation from its +/// [`DriverObject`] implementation. +/// +/// [`Driver`]: drm::Driver +/// [`DriverFile`]: drm::file::DriverFile +pub type DriverFile<T> = drm::File<<<T as DriverObject>::Driver as drm::Driver>::File>; /// GEM object functions, which must be implemented by drivers. -pub trait BaseDriverObject<T: BaseObject>: Sync + Send + Sized { +pub trait DriverObject: Sync + Send + Sized { + /// Parent `Driver` for this object. + type Driver: drm::Driver; + /// Create a new driver data object for a GEM object of a given size. - fn new(dev: &drm::Device<T::Driver>, size: usize) -> impl PinInit<Self, Error>; + fn new(dev: &drm::Device<Self::Driver>, size: usize) -> impl PinInit<Self, Error>; /// Open a new handle to an existing object, associated with a File. - fn open( - _obj: &<<T as IntoGEMObject>::Driver as drm::Driver>::Object, - _file: &drm::File<<<T as IntoGEMObject>::Driver as drm::Driver>::File>, - ) -> Result { + fn open(_obj: &<Self::Driver as drm::Driver>::Object, _file: &DriverFile<Self>) -> Result { Ok(()) } /// Close a handle to an existing object, associated with a File. - fn close( - _obj: &<<T as IntoGEMObject>::Driver as drm::Driver>::Object, - _file: &drm::File<<<T as IntoGEMObject>::Driver as drm::Driver>::File>, - ) { - } + fn close(_obj: &<Self::Driver as drm::Driver>::Object, _file: &DriverFile<Self>) {} } /// Trait that represents a GEM object subtype pub trait IntoGEMObject: Sized + super::private::Sealed + AlwaysRefCounted { - /// Owning driver for this type - type Driver: drm::Driver; - /// Returns a reference to the raw `drm_gem_object` structure, which must be valid as long as /// this owning object is valid. fn as_raw(&self) -> *mut bindings::drm_gem_object; @@ -75,25 +75,16 @@ unsafe impl<T: IntoGEMObject> AlwaysRefCounted for T { } } -/// Trait which must be implemented by drivers using base GEM objects. -pub trait DriverObject: BaseDriverObject<Object<Self>> { - /// Parent `Driver` for this object. - type Driver: drm::Driver; -} - -extern "C" fn open_callback<T: BaseDriverObject<U>, U: BaseObject>( +extern "C" fn open_callback<T: DriverObject>( raw_obj: *mut bindings::drm_gem_object, raw_file: *mut bindings::drm_file, ) -> core::ffi::c_int { // SAFETY: `open_callback` is only ever called with a valid pointer to a `struct drm_file`. - let file = unsafe { - drm::File::<<<U as IntoGEMObject>::Driver as drm::Driver>::File>::from_raw(raw_file) - }; - // SAFETY: `open_callback` is specified in the AllocOps structure for `Object<T>`, ensuring that - // `raw_obj` is indeed contained within a `Object<T>`. - let obj = unsafe { - <<<U as IntoGEMObject>::Driver as drm::Driver>::Object as IntoGEMObject>::from_raw(raw_obj) - }; + 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) }; match T::open(obj, file) { Err(e) => e.to_errno(), @@ -101,26 +92,21 @@ extern "C" fn open_callback<T: BaseDriverObject<U>, U: BaseObject>( } } -extern "C" fn close_callback<T: BaseDriverObject<U>, U: BaseObject>( +extern "C" fn close_callback<T: DriverObject>( raw_obj: *mut bindings::drm_gem_object, raw_file: *mut bindings::drm_file, ) { // SAFETY: `open_callback` is only ever called with a valid pointer to a `struct drm_file`. - let file = unsafe { - drm::File::<<<U as IntoGEMObject>::Driver as drm::Driver>::File>::from_raw(raw_file) - }; + let file = unsafe { DriverFile::<T>::from_raw(raw_file) }; + // 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 { - <<<U as IntoGEMObject>::Driver as drm::Driver>::Object as IntoGEMObject>::from_raw(raw_obj) - }; + let obj = unsafe { <<T::Driver as drm::Driver>::Object as IntoGEMObject>::from_raw(raw_obj) }; T::close(obj, file); } impl<T: DriverObject> IntoGEMObject for Object<T> { - type Driver = T::Driver; - fn as_raw(&self) -> *mut bindings::drm_gem_object { self.obj.get() } @@ -142,10 +128,12 @@ pub trait BaseObject: IntoGEMObject { /// Creates a new handle for the object associated with a given `File` /// (or returns an existing one). - fn create_handle( - &self, - file: &drm::File<<<Self as IntoGEMObject>::Driver as drm::Driver>::File>, - ) -> Result<u32> { + fn create_handle<D, F>(&self, file: &drm::File<F>) -> Result<u32> + where + Self: AllocImpl<Driver = D>, + D: drm::Driver<Object = Self, File = F>, + F: drm::file::DriverFile<Driver = D>, + { let mut handle: u32 = 0; // SAFETY: The arguments are all valid per the type invariants. to_result(unsafe { @@ -155,10 +143,12 @@ pub trait BaseObject: IntoGEMObject { } /// Looks up an object by its handle for a given `File`. - fn lookup_handle( - file: &drm::File<<<Self as IntoGEMObject>::Driver as drm::Driver>::File>, - handle: u32, - ) -> Result<ARef<Self>> { + 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>, + F: drm::file::DriverFile<Driver = D>, + { // SAFETY: The arguments are all valid per the type invariants. let ptr = unsafe { bindings::drm_gem_object_lookup(file.as_raw().cast(), handle) }; if ptr.is_null() { @@ -208,13 +198,10 @@ pub struct Object<T: DriverObject + Send + Sync> { } impl<T: DriverObject> Object<T> { - /// The size of this object's structure. - pub const SIZE: usize = mem::size_of::<Self>(); - const OBJECT_FUNCS: bindings::drm_gem_object_funcs = bindings::drm_gem_object_funcs { free: Some(Self::free_callback), - open: Some(open_callback::<T, Object<T>>), - close: Some(close_callback::<T, Object<T>>), + open: Some(open_callback::<T>), + close: Some(close_callback::<T>), print_info: None, export: None, pin: None, @@ -297,6 +284,8 @@ impl<T: DriverObject> Deref for Object<T> { } impl<T: DriverObject> AllocImpl for Object<T> { + type Driver = T::Driver; + const ALLOC_OPS: AllocOps = AllocOps { gem_create_object: None, prime_handle_to_fd: None, diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index fef97f2a5098..44e4b8853ff3 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -18,6 +18,7 @@ // // Stable since Rust 1.79.0. #![feature(inline_const)] +#![feature(pointer_is_aligned)] // // Stable since Rust 1.81.0. #![feature(lint_reasons)] @@ -113,6 +114,7 @@ pub mod print; pub mod rbtree; pub mod regulator; pub mod revocable; +pub mod scatterlist; pub mod security; pub mod seq_file; pub mod sizes; diff --git a/rust/kernel/page.rs b/rust/kernel/page.rs index 7c1b17246ed5..75ef096075cb 100644 --- a/rust/kernel/page.rs +++ b/rust/kernel/page.rs @@ -9,7 +9,12 @@ use crate::{ error::Result, uaccess::UserSliceReader, }; -use core::ptr::{self, NonNull}; +use core::{ + marker::PhantomData, + mem::ManuallyDrop, + ops::Deref, + ptr::{self, NonNull}, +}; /// A bitwise shift for the page size. pub const PAGE_SHIFT: usize = bindings::PAGE_SHIFT as usize; @@ -30,6 +35,86 @@ pub const fn page_align(addr: usize) -> usize { (addr + (PAGE_SIZE - 1)) & PAGE_MASK } +/// Representation of a non-owning reference to a [`Page`]. +/// +/// This type provides a borrowed version of a [`Page`] that is owned by some other entity, e.g. a +/// [`Vmalloc`] allocation such as [`VBox`]. +/// +/// # Example +/// +/// ``` +/// # use kernel::{bindings, prelude::*}; +/// use kernel::page::{BorrowedPage, Page, PAGE_SIZE}; +/// # use core::{mem::MaybeUninit, ptr, ptr::NonNull }; +/// +/// fn borrow_page<'a>(vbox: &'a mut VBox<MaybeUninit<[u8; PAGE_SIZE]>>) -> BorrowedPage<'a> { +/// let ptr = ptr::from_ref(&**vbox); +/// +/// // SAFETY: `ptr` is a valid pointer to `Vmalloc` memory. +/// let page = unsafe { bindings::vmalloc_to_page(ptr.cast()) }; +/// +/// // SAFETY: `vmalloc_to_page` returns a valid pointer to a `struct page` for a valid +/// // pointer to `Vmalloc` memory. +/// let page = unsafe { NonNull::new_unchecked(page) }; +/// +/// // SAFETY: +/// // - `self.0` is a valid pointer to a `struct page`. +/// // - `self.0` is valid for the entire lifetime of `self`. +/// unsafe { BorrowedPage::from_raw(page) } +/// } +/// +/// let mut vbox = VBox::<[u8; PAGE_SIZE]>::new_uninit(GFP_KERNEL)?; +/// let page = borrow_page(&mut vbox); +/// +/// // SAFETY: There is no concurrent read or write to this page. +/// unsafe { page.fill_zero_raw(0, PAGE_SIZE)? }; +/// # Ok::<(), Error>(()) +/// ``` +/// +/// # Invariants +/// +/// The borrowed underlying pointer to a `struct page` is valid for the entire lifetime `'a`. +/// +/// [`VBox`]: kernel::alloc::VBox +/// [`Vmalloc`]: kernel::alloc::allocator::Vmalloc +pub struct BorrowedPage<'a>(ManuallyDrop<Page>, PhantomData<&'a Page>); + +impl<'a> BorrowedPage<'a> { + /// Constructs a [`BorrowedPage`] from a raw pointer to a `struct page`. + /// + /// # Safety + /// + /// - `ptr` must point to a valid `bindings::page`. + /// - `ptr` must remain valid for the entire lifetime `'a`. + pub unsafe fn from_raw(ptr: NonNull<bindings::page>) -> Self { + let page = Page { page: ptr }; + + // INVARIANT: The safety requirements guarantee that `ptr` is valid for the entire lifetime + // `'a`. + Self(ManuallyDrop::new(page), PhantomData) + } +} + +impl<'a> Deref for BorrowedPage<'a> { + type Target = Page; + + fn deref(&self) -> &Self::Target { + &self.0 + } +} + +/// Trait to be implemented by types which provide an [`Iterator`] implementation of +/// [`BorrowedPage`] items, such as [`VmallocPageIter`](kernel::alloc::allocator::VmallocPageIter). +pub trait AsPageIter { + /// The [`Iterator`] type, e.g. [`VmallocPageIter`](kernel::alloc::allocator::VmallocPageIter). + type Iter<'a>: Iterator<Item = BorrowedPage<'a>> + where + Self: 'a; + + /// Returns an [`Iterator`] of [`BorrowedPage`] items over all pages owned by `self`. + fn page_iter(&mut self) -> Self::Iter<'_>; +} + /// A pointer to a page that owns the page allocation. /// /// # Invariants diff --git a/rust/kernel/scatterlist.rs b/rust/kernel/scatterlist.rs new file mode 100644 index 000000000000..9709dff60b5a --- /dev/null +++ b/rust/kernel/scatterlist.rs @@ -0,0 +1,491 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! Abstractions for scatter-gather lists. +//! +//! C header: [`include/linux/scatterlist.h`](srctree/include/linux/scatterlist.h) +//! +//! Scatter-gather (SG) I/O is a memory access technique that allows devices to perform DMA +//! operations on data buffers that are not physically contiguous in memory. It works by creating a +//! "scatter-gather list", an array where each entry specifies the address and length of a +//! physically contiguous memory segment. +//! +//! The device's DMA controller can then read this list and process the segments sequentially as +//! part of one logical I/O request. This avoids the need for a single, large, physically contiguous +//! memory buffer, which can be difficult or impossible to allocate. +//! +//! This module provides safe Rust abstractions over the kernel's `struct scatterlist` and +//! `struct sg_table` types. +//! +//! The main entry point is the [`SGTable`] type, which represents a complete scatter-gather table. +//! It can be either: +//! +//! - An owned table ([`SGTable<Owned<P>>`]), created from a Rust memory buffer (e.g., [`VVec`]). +//! This type manages the allocation of the `struct sg_table`, the DMA mapping of the buffer, and +//! the automatic cleanup of all resources. +//! - A borrowed reference (&[`SGTable`]), which provides safe, read-only access to a table that was +//! allocated by other (e.g., C) code. +//! +//! Individual entries in the table are represented by [`SGEntry`], which can be accessed by +//! iterating over an [`SGTable`]. + +use crate::{ + alloc, + alloc::allocator::VmallocPageIter, + bindings, + device::{Bound, Device}, + devres::Devres, + dma, error, + io::resource::ResourceSize, + page, + prelude::*, + types::{ARef, Opaque}, +}; +use core::{ops::Deref, ptr::NonNull}; + +/// A single entry in a scatter-gather list. +/// +/// An `SGEntry` represents a single, physically contiguous segment of memory that has been mapped +/// for DMA. +/// +/// Instances of this struct are obtained by iterating over an [`SGTable`]. Drivers do not create +/// or own [`SGEntry`] objects directly. +#[repr(transparent)] +pub struct SGEntry(Opaque<bindings::scatterlist>); + +// SAFETY: `SGEntry` can be sent to any task. +unsafe impl Send for SGEntry {} + +// SAFETY: `SGEntry` has no interior mutability and can be accessed concurrently. +unsafe impl Sync for SGEntry {} + +impl SGEntry { + /// Convert a raw `struct scatterlist *` to a `&'a SGEntry`. + /// + /// # Safety + /// + /// Callers must ensure that the `struct scatterlist` pointed to by `ptr` is valid for the + /// lifetime `'a`. + #[inline] + unsafe fn from_raw<'a>(ptr: *mut bindings::scatterlist) -> &'a Self { + // SAFETY: The safety requirements of this function guarantee that `ptr` is a valid pointer + // to a `struct scatterlist` for the duration of `'a`. + unsafe { &*ptr.cast() } + } + + /// Obtain the raw `struct scatterlist *`. + #[inline] + fn as_raw(&self) -> *mut bindings::scatterlist { + self.0.get() + } + + /// Returns the DMA address of this SG entry. + /// + /// This is the address that the device should use to access the memory segment. + #[inline] + pub fn dma_address(&self) -> dma::DmaAddress { + // SAFETY: `self.as_raw()` is a valid pointer to a `struct scatterlist`. + unsafe { bindings::sg_dma_address(self.as_raw()) } + } + + /// Returns the length of this SG entry in bytes. + #[inline] + pub fn dma_len(&self) -> ResourceSize { + #[allow(clippy::useless_conversion)] + // SAFETY: `self.as_raw()` is a valid pointer to a `struct scatterlist`. + unsafe { bindings::sg_dma_len(self.as_raw()) }.into() + } +} + +/// The borrowed generic type of an [`SGTable`], representing a borrowed or externally managed +/// table. +#[repr(transparent)] +pub struct Borrowed(Opaque<bindings::sg_table>); + +// SAFETY: `Borrowed` can be sent to any task. +unsafe impl Send for Borrowed {} + +// SAFETY: `Borrowed` has no interior mutability and can be accessed concurrently. +unsafe impl Sync for Borrowed {} + +/// A scatter-gather table. +/// +/// This struct is a wrapper around the kernel's `struct sg_table`. It manages a list of DMA-mapped +/// memory segments that can be passed to a device for I/O operations. +/// +/// The generic parameter `T` is used as a generic type to distinguish between owned and borrowed +/// tables. +/// +/// - [`SGTable<Owned>`]: An owned table created and managed entirely by Rust code. It handles +/// allocation, DMA mapping, and cleanup of all associated resources. See [`SGTable::new`]. +/// - [`SGTable<Borrowed>`} (or simply [`SGTable`]): Represents a table whose lifetime is managed +/// externally. It can be used safely via a borrowed reference `&'a SGTable`, where `'a` is the +/// external lifetime. +/// +/// All [`SGTable`] variants can be iterated over the individual [`SGEntry`]s. +#[repr(transparent)] +#[pin_data] +pub struct SGTable<T: private::Sealed = Borrowed> { + #[pin] + inner: T, +} + +impl SGTable { + /// Creates a borrowed `&'a SGTable` from a raw `struct sg_table` pointer. + /// + /// This allows safe access to an `sg_table` that is managed elsewhere (for example, in C code). + /// + /// # Safety + /// + /// Callers must ensure that: + /// + /// - the `struct sg_table` pointed to by `ptr` is valid for the entire lifetime of `'a`, + /// - the data behind `ptr` is not modified concurrently for the duration of `'a`. + #[inline] + pub unsafe fn from_raw<'a>(ptr: *mut bindings::sg_table) -> &'a Self { + // SAFETY: The safety requirements of this function guarantee that `ptr` is a valid pointer + // to a `struct sg_table` for the duration of `'a`. + unsafe { &*ptr.cast() } + } + + #[inline] + fn as_raw(&self) -> *mut bindings::sg_table { + self.inner.0.get() + } + + /// Returns an [`SGTableIter`] bound to the lifetime of `self`. + pub fn iter(&self) -> SGTableIter<'_> { + // SAFETY: `self.as_raw()` is a valid pointer to a `struct sg_table`. + let nents = unsafe { (*self.as_raw()).nents }; + + let pos = if nents > 0 { + // SAFETY: `self.as_raw()` is a valid pointer to a `struct sg_table`. + let ptr = unsafe { (*self.as_raw()).sgl }; + + // SAFETY: `ptr` is guaranteed to be a valid pointer to a `struct scatterlist`. + Some(unsafe { SGEntry::from_raw(ptr) }) + } else { + None + }; + + SGTableIter { pos, nents } + } +} + +/// Represents the DMA mapping state of a `struct sg_table`. +/// +/// This is used as an inner type of [`Owned`] to manage the DMA mapping lifecycle. +/// +/// # Invariants +/// +/// - `sgt` is a valid pointer to a `struct sg_table` for the entire lifetime of the +/// [`DmaMappedSgt`]. +/// - `sgt` is always DMA mapped. +struct DmaMappedSgt { + sgt: NonNull<bindings::sg_table>, + dev: ARef<Device>, + dir: dma::DataDirection, +} + +// SAFETY: `DmaMappedSgt` can be sent to any task. +unsafe impl Send for DmaMappedSgt {} + +// SAFETY: `DmaMappedSgt` has no interior mutability and can be accessed concurrently. +unsafe impl Sync for DmaMappedSgt {} + +impl DmaMappedSgt { + /// # Safety + /// + /// - `sgt` must be a valid pointer to a `struct sg_table` for the entire lifetime of the + /// returned [`DmaMappedSgt`]. + /// - The caller must guarantee that `sgt` remains DMA mapped for the entire lifetime of + /// [`DmaMappedSgt`]. + unsafe fn new( + sgt: NonNull<bindings::sg_table>, + dev: &Device<Bound>, + dir: dma::DataDirection, + ) -> Result<Self> { + // SAFETY: + // - `dev.as_raw()` is a valid pointer to a `struct device`, which is guaranteed to be + // bound to a driver for the duration of this call. + // - `sgt` is a valid pointer to a `struct sg_table`. + error::to_result(unsafe { + bindings::dma_map_sgtable(dev.as_raw(), sgt.as_ptr(), dir.into(), 0) + })?; + + // INVARIANT: By the safety requirements of this function it is guaranteed that `sgt` is + // valid for the entire lifetime of this object instance. + Ok(Self { + sgt, + dev: dev.into(), + dir, + }) + } +} + +impl Drop for DmaMappedSgt { + #[inline] + fn drop(&mut self) { + // SAFETY: + // - `self.dev.as_raw()` is a pointer to a valid `struct device`. + // - `self.dev` is the same device the mapping has been created for in `Self::new()`. + // - `self.sgt.as_ptr()` is a valid pointer to a `struct sg_table` by the type invariants + // of `Self`. + // - `self.dir` is the same `dma::DataDirection` the mapping has been created with in + // `Self::new()`. + unsafe { + bindings::dma_unmap_sgtable(self.dev.as_raw(), self.sgt.as_ptr(), self.dir.into(), 0) + }; + } +} + +/// A transparent wrapper around a `struct sg_table`. +/// +/// While we could also create the `struct sg_table` in the constructor of [`Owned`], we can't tear +/// down the `struct sg_table` in [`Owned::drop`]; the drop order in [`Owned`] matters. +#[repr(transparent)] +struct RawSGTable(Opaque<bindings::sg_table>); + +// SAFETY: `RawSGTable` can be sent to any task. +unsafe impl Send for RawSGTable {} + +// SAFETY: `RawSGTable` has no interior mutability and can be accessed concurrently. +unsafe impl Sync for RawSGTable {} + +impl RawSGTable { + /// # Safety + /// + /// - `pages` must be a slice of valid `struct page *`. + /// - The pages pointed to by `pages` must remain valid for the entire lifetime of the returned + /// [`RawSGTable`]. + unsafe fn new( + pages: &mut [*mut bindings::page], + size: usize, + max_segment: u32, + flags: alloc::Flags, + ) -> Result<Self> { + // `sg_alloc_table_from_pages_segment()` expects at least one page, otherwise it + // produces a NPE. + if pages.is_empty() { + return Err(EINVAL); + } + + let sgt = Opaque::zeroed(); + // SAFETY: + // - `sgt.get()` is a valid pointer to uninitialized memory. + // - As by the check above, `pages` is not empty. + error::to_result(unsafe { + bindings::sg_alloc_table_from_pages_segment( + sgt.get(), + pages.as_mut_ptr(), + pages.len().try_into()?, + 0, + size, + max_segment, + flags.as_raw(), + ) + })?; + + Ok(Self(sgt)) + } + + #[inline] + fn as_raw(&self) -> *mut bindings::sg_table { + self.0.get() + } +} + +impl Drop for RawSGTable { + #[inline] + fn drop(&mut self) { + // SAFETY: `sgt` is a valid and initialized `struct sg_table`. + unsafe { bindings::sg_free_table(self.0.get()) }; + } +} + +/// The [`Owned`] generic type of an [`SGTable`]. +/// +/// A [`SGTable<Owned>`] signifies that the [`SGTable`] owns all associated resources: +/// +/// - The backing memory pages. +/// - The `struct sg_table` allocation (`sgt`). +/// - The DMA mapping, managed through a [`Devres`]-managed `DmaMappedSgt`. +/// +/// Users interact with this type through the [`SGTable`] handle and do not need to manage +/// [`Owned`] directly. +#[pin_data] +pub struct Owned<P> { + // Note: The drop order is relevant; we first have to unmap the `struct sg_table`, then free the + // `struct sg_table` and finally free the backing pages. + #[pin] + dma: Devres<DmaMappedSgt>, + sgt: RawSGTable, + _pages: P, +} + +// SAFETY: `Owned` can be sent to any task if `P` can be send to any task. +unsafe impl<P: Send> Send for Owned<P> {} + +// SAFETY: `Owned` has no interior mutability and can be accessed concurrently if `P` can be +// accessed concurrently. +unsafe impl<P: Sync> Sync for Owned<P> {} + +impl<P> Owned<P> +where + for<'a> P: page::AsPageIter<Iter<'a> = VmallocPageIter<'a>> + 'static, +{ + fn new( + dev: &Device<Bound>, + mut pages: P, + dir: dma::DataDirection, + flags: alloc::Flags, + ) -> Result<impl PinInit<Self, Error> + '_> { + let page_iter = pages.page_iter(); + let size = page_iter.size(); + + let mut page_vec: KVec<*mut bindings::page> = + KVec::with_capacity(page_iter.page_count(), flags)?; + + for page in page_iter { + page_vec.push(page.as_ptr(), flags)?; + } + + // `dma_max_mapping_size` returns `size_t`, but `sg_alloc_table_from_pages_segment()` takes + // an `unsigned int`. + // + // SAFETY: `dev.as_raw()` is a valid pointer to a `struct device`. + let max_segment = match unsafe { bindings::dma_max_mapping_size(dev.as_raw()) } { + 0 => u32::MAX, + max_segment => u32::try_from(max_segment).unwrap_or(u32::MAX), + }; + + Ok(try_pin_init!(&this in Self { + // SAFETY: + // - `page_vec` is a `KVec` of valid `struct page *` obtained from `pages`. + // - The pages contained in `pages` remain valid for the entire lifetime of the + // `RawSGTable`. + sgt: unsafe { RawSGTable::new(&mut page_vec, size, max_segment, flags) }?, + dma <- { + // SAFETY: `this` is a valid pointer to uninitialized memory. + let sgt = unsafe { &raw mut (*this.as_ptr()).sgt }.cast(); + + // SAFETY: `sgt` is guaranteed to be non-null. + let sgt = unsafe { NonNull::new_unchecked(sgt) }; + + // SAFETY: + // - It is guaranteed that the object returned by `DmaMappedSgt::new` won't out-live + // `sgt`. + // - `sgt` is never DMA unmapped manually. + Devres::new(dev, unsafe { DmaMappedSgt::new(sgt, dev, dir) }) + }, + _pages: pages, + })) + } +} + +impl<P> SGTable<Owned<P>> +where + for<'a> P: page::AsPageIter<Iter<'a> = VmallocPageIter<'a>> + 'static, +{ + /// Allocates a new scatter-gather table from the given pages and maps it for DMA. + /// + /// This constructor creates a new [`SGTable<Owned>`] that takes ownership of `P`. + /// It allocates a `struct sg_table`, populates it with entries corresponding to the physical + /// pages of `P`, and maps the table for DMA with the specified [`Device`] and + /// [`dma::DataDirection`]. + /// + /// The DMA mapping is managed through [`Devres`], ensuring that the DMA mapping is unmapped + /// once the associated [`Device`] is unbound, or when the [`SGTable<Owned>`] is dropped. + /// + /// # Parameters + /// + /// * `dev`: The [`Device`] that will be performing the DMA. + /// * `pages`: The entity providing the backing pages. It must implement [`page::AsPageIter`]. + /// The ownership of this entity is moved into the new [`SGTable<Owned>`]. + /// * `dir`: The [`dma::DataDirection`] of the DMA transfer. + /// * `flags`: Allocation flags for internal allocations (e.g., [`GFP_KERNEL`]). + /// + /// # Examples + /// + /// ``` + /// use kernel::{ + /// device::{Bound, Device}, + /// dma, page, + /// prelude::*, + /// scatterlist::{SGTable, Owned}, + /// }; + /// + /// fn test(dev: &Device<Bound>) -> Result { + /// let size = 4 * page::PAGE_SIZE; + /// let pages = VVec::<u8>::with_capacity(size, GFP_KERNEL)?; + /// + /// let sgt = KBox::pin_init(SGTable::new( + /// dev, + /// pages, + /// dma::DataDirection::ToDevice, + /// GFP_KERNEL, + /// ), GFP_KERNEL)?; + /// + /// Ok(()) + /// } + /// ``` + pub fn new( + dev: &Device<Bound>, + pages: P, + dir: dma::DataDirection, + flags: alloc::Flags, + ) -> impl PinInit<Self, Error> + '_ { + try_pin_init!(Self { + inner <- Owned::new(dev, pages, dir, flags)? + }) + } +} + +impl<P> Deref for SGTable<Owned<P>> { + type Target = SGTable; + + #[inline] + fn deref(&self) -> &Self::Target { + // SAFETY: + // - `self.inner.sgt.as_raw()` is a valid pointer to a `struct sg_table` for the entire + // lifetime of `self`. + // - The backing `struct sg_table` is not modified for the entire lifetime of `self`. + unsafe { SGTable::from_raw(self.inner.sgt.as_raw()) } + } +} + +mod private { + pub trait Sealed {} + + impl Sealed for super::Borrowed {} + impl<P> Sealed for super::Owned<P> {} +} + +/// An [`Iterator`] over the DMA mapped [`SGEntry`] items of an [`SGTable`]. +/// +/// Note that the existence of an [`SGTableIter`] does not guarantee that the [`SGEntry`] items +/// actually remain DMA mapped; they are prone to be unmapped on device unbind. +pub struct SGTableIter<'a> { + pos: Option<&'a SGEntry>, + /// The number of DMA mapped entries in a `struct sg_table`. + nents: c_uint, +} + +impl<'a> Iterator for SGTableIter<'a> { + type Item = &'a SGEntry; + + fn next(&mut self) -> Option<Self::Item> { + let entry = self.pos?; + self.nents = self.nents.saturating_sub(1); + + // SAFETY: `entry.as_raw()` is a valid pointer to a `struct scatterlist`. + let next = unsafe { bindings::sg_next(entry.as_raw()) }; + + self.pos = (!next.is_null() && self.nents > 0).then(|| { + // SAFETY: If `next` is not NULL, `sg_next()` guarantees to return a valid pointer to + // the next `struct scatterlist`. + unsafe { SGEntry::from_raw(next) } + }); + + Some(entry) + } +} diff --git a/rust/kernel/transmute.rs b/rust/kernel/transmute.rs index 1c7d43771a37..cfc37d81adf2 100644 --- a/rust/kernel/transmute.rs +++ b/rust/kernel/transmute.rs @@ -2,6 +2,8 @@ //! Traits for transmuting types. +use core::mem::size_of; + /// Types for which any bit pattern is valid. /// /// Not all types are valid for all values. For example, a `bool` must be either zero or one, so @@ -9,10 +11,93 @@ /// /// It's okay for the type to have padding, as initializing those bytes has no effect. /// +/// # Examples +/// +/// ``` +/// use kernel::transmute::FromBytes; +/// +/// # fn test() -> Option<()> { +/// let raw = [1, 2, 3, 4]; +/// +/// let result = u32::from_bytes(&raw)?; +/// +/// #[cfg(target_endian = "little")] +/// assert_eq!(*result, 0x4030201); +/// +/// #[cfg(target_endian = "big")] +/// assert_eq!(*result, 0x1020304); +/// +/// # Some(()) } +/// # test().ok_or(EINVAL)?; +/// # Ok::<(), Error>(()) +/// ``` +/// /// # Safety /// /// All bit-patterns must be valid for this type. This type must not have interior mutability. -pub unsafe trait FromBytes {} +pub unsafe trait FromBytes { + /// Converts a slice of bytes to a reference to `Self`. + /// + /// Succeeds if the reference is properly aligned, and the size of `bytes` is equal to that of + /// `T` and different from zero. + /// + /// Otherwise, returns [`None`]. + fn from_bytes(bytes: &[u8]) -> Option<&Self> + where + Self: Sized, + { + let slice_ptr = bytes.as_ptr().cast::<Self>(); + let size = size_of::<Self>(); + + #[allow(clippy::incompatible_msrv)] + if bytes.len() == size && slice_ptr.is_aligned() { + // SAFETY: Size and alignment were just checked. + unsafe { Some(&*slice_ptr) } + } else { + None + } + } + + /// Converts a mutable slice of bytes to a reference to `Self`. + /// + /// Succeeds if the reference is properly aligned, and the size of `bytes` is equal to that of + /// `T` and different from zero. + /// + /// Otherwise, returns [`None`]. + fn from_bytes_mut(bytes: &mut [u8]) -> Option<&mut Self> + where + Self: AsBytes + Sized, + { + let slice_ptr = bytes.as_mut_ptr().cast::<Self>(); + let size = size_of::<Self>(); + + #[allow(clippy::incompatible_msrv)] + if bytes.len() == size && slice_ptr.is_aligned() { + // SAFETY: Size and alignment were just checked. + unsafe { Some(&mut *slice_ptr) } + } else { + None + } + } + + /// Creates an owned instance of `Self` by copying `bytes`. + /// + /// Unlike [`FromBytes::from_bytes`], which requires aligned input, this method can be used on + /// non-aligned data at the cost of a copy. + fn from_bytes_copy(bytes: &[u8]) -> Option<Self> + where + Self: Sized, + { + if bytes.len() == size_of::<Self>() { + // SAFETY: we just verified that `bytes` has the same size as `Self`, and per the + // invariants of `FromBytes`, any byte sequence of the correct length is a valid value + // for `Self`. + Some(unsafe { core::ptr::read_unaligned(bytes.as_ptr().cast::<Self>()) }) + } else { + None + } + } +} macro_rules! impl_frombytes { ($($({$($generics:tt)*})? $t:ty, )*) => { @@ -47,7 +132,32 @@ impl_frombytes! { /// /// Values of this type may not contain any uninitialized bytes. This type must not have interior /// mutability. -pub unsafe trait AsBytes {} +pub unsafe trait AsBytes { + /// Returns `self` as a slice of bytes. + fn as_bytes(&self) -> &[u8] { + // CAST: `Self` implements `AsBytes` thus all bytes of `self` are initialized. + let data = core::ptr::from_ref(self).cast::<u8>(); + let len = core::mem::size_of_val(self); + + // SAFETY: `data` is non-null and valid for reads of `len * sizeof::<u8>()` bytes. + unsafe { core::slice::from_raw_parts(data, len) } + } + + /// Returns `self` as a mutable slice of bytes. + fn as_bytes_mut(&mut self) -> &mut [u8] + where + Self: FromBytes, + { + // CAST: `Self` implements both `AsBytes` and `FromBytes` thus making `Self` + // bi-directionally transmutable to `[u8; size_of_val(self)]`. + let data = core::ptr::from_mut(self).cast::<u8>(); + let len = core::mem::size_of_val(self); + + // SAFETY: `data` is non-null and valid for read and writes of `len * sizeof::<u8>()` + // bytes. + unsafe { core::slice::from_raw_parts_mut(data, len) } + } +} macro_rules! impl_asbytes { ($($({$($generics:tt)*})? $t:ty, )*) => { diff --git a/rust/kernel/workqueue.rs b/rust/kernel/workqueue.rs index b9343d5bc00f..706e833e9702 100644 --- a/rust/kernel/workqueue.rs +++ b/rust/kernel/workqueue.rs @@ -356,18 +356,11 @@ struct ClosureWork<T> { func: Option<T>, } -impl<T> ClosureWork<T> { - fn project(self: Pin<&mut Self>) -> &mut Option<T> { - // SAFETY: The `func` field is not structurally pinned. - unsafe { &mut self.get_unchecked_mut().func } - } -} - impl<T: FnOnce()> WorkItem for ClosureWork<T> { type Pointer = Pin<KBox<Self>>; fn run(mut this: Pin<KBox<Self>>) { - if let Some(func) = this.as_mut().project().take() { + if let Some(func) = this.as_mut().project().func.take() { (func)() } } diff --git a/rust/pin-init/README.md b/rust/pin-init/README.md index a4c01a8d78b2..723e275445d4 100644 --- a/rust/pin-init/README.md +++ b/rust/pin-init/README.md @@ -6,6 +6,18 @@  # `pin-init` +> [!NOTE] +> +> This crate was originally named [`pinned-init`], but the migration to +> `pin-init` is not yet complete. The `legcay` branch contains the current +> version of the `pinned-init` crate & the `main` branch already incorporates +> the rename to `pin-init`. +> +> There are still some changes needed on the kernel side before the migration +> can be completed. + +[`pinned-init`]: https://crates.io/crates/pinned-init + <!-- cargo-rdme start --> Library to safely and fallibly initialize pinned `struct`s using in-place constructors. diff --git a/rust/pin-init/examples/error.rs b/rust/pin-init/examples/error.rs index e0cc258746ce..8f4e135eb8ba 100644 --- a/rust/pin-init/examples/error.rs +++ b/rust/pin-init/examples/error.rs @@ -24,4 +24,6 @@ impl From<AllocError> for Error { } #[allow(dead_code)] -fn main() {} +fn main() { + let _ = Error; +} diff --git a/rust/pin-init/src/lib.rs b/rust/pin-init/src/lib.rs index 62e013a5cc20..dd553212836e 100644 --- a/rust/pin-init/src/lib.rs +++ b/rust/pin-init/src/lib.rs @@ -740,6 +740,8 @@ macro_rules! stack_try_pin_init { /// As already mentioned in the examples above, inside of `pin_init!` a `struct` initializer with /// the following modifications is expected: /// - Fields that you want to initialize in-place have to use `<-` instead of `:`. +/// - You can use `_: { /* run any user-code here */ },` anywhere where you can place fields in +/// order to run arbitrary code. /// - In front of the initializer you can write `&this in` to have access to a [`NonNull<Self>`] /// pointer named `this` inside of the initializer. /// - Using struct update syntax one can place `..Zeroable::init_zeroed()` at the very end of the @@ -994,7 +996,7 @@ macro_rules! try_init { /// } /// /// impl<T> Foo<T> { -/// fn project(self: Pin<&mut Self>) -> Pin<&mut T> { +/// fn project_this(self: Pin<&mut Self>) -> Pin<&mut T> { /// assert_pinned!(Foo<T>, elem, T, inline); /// /// // SAFETY: The field is structurally pinned. diff --git a/rust/pin-init/src/macros.rs b/rust/pin-init/src/macros.rs index 9ced630737b8..d6acf2cd291e 100644 --- a/rust/pin-init/src/macros.rs +++ b/rust/pin-init/src/macros.rs @@ -831,6 +831,17 @@ macro_rules! __pin_data { $($fields)* } + $crate::__pin_data!(make_pin_projections: + @vis($vis), + @name($name), + @impl_generics($($impl_generics)*), + @ty_generics($($ty_generics)*), + @decl_generics($($decl_generics)*), + @where($($whr)*), + @pinned($($pinned)*), + @not_pinned($($not_pinned)*), + ); + // We put the rest into this const item, because it then will not be accessible to anything // outside. const _: () = { @@ -980,6 +991,56 @@ macro_rules! __pin_data { stringify!($($rest)*), ); }; + (make_pin_projections: + @vis($vis:vis), + @name($name:ident), + @impl_generics($($impl_generics:tt)*), + @ty_generics($($ty_generics:tt)*), + @decl_generics($($decl_generics:tt)*), + @where($($whr:tt)*), + @pinned($($(#[$($p_attr:tt)*])* $pvis:vis $p_field:ident : $p_type:ty),* $(,)?), + @not_pinned($($(#[$($attr:tt)*])* $fvis:vis $field:ident : $type:ty),* $(,)?), + ) => { + $crate::macros::paste! { + #[doc(hidden)] + $vis struct [< $name Projection >] <'__pin, $($decl_generics)*> { + $($(#[$($p_attr)*])* $pvis $p_field : ::core::pin::Pin<&'__pin mut $p_type>,)* + $($(#[$($attr)*])* $fvis $field : &'__pin mut $type,)* + ___pin_phantom_data: ::core::marker::PhantomData<&'__pin mut ()>, + } + + impl<$($impl_generics)*> $name<$($ty_generics)*> + where $($whr)* + { + /// Pin-projects all fields of `Self`. + /// + /// These fields are structurally pinned: + $(#[doc = ::core::concat!(" - `", ::core::stringify!($p_field), "`")])* + /// + /// These fields are **not** structurally pinned: + $(#[doc = ::core::concat!(" - `", ::core::stringify!($field), "`")])* + #[inline] + $vis fn project<'__pin>( + self: ::core::pin::Pin<&'__pin mut Self>, + ) -> [< $name Projection >] <'__pin, $($ty_generics)*> { + // SAFETY: we only give access to `&mut` for fields not structurally pinned. + let this = unsafe { ::core::pin::Pin::get_unchecked_mut(self) }; + [< $name Projection >] { + $( + // SAFETY: `$p_field` is structurally pinned. + $(#[$($p_attr)*])* + $p_field : unsafe { ::core::pin::Pin::new_unchecked(&mut this.$p_field) }, + )* + $( + $(#[$($attr)*])* + $field : &mut this.$field, + )* + ___pin_phantom_data: ::core::marker::PhantomData, + } + } + } + } + }; (make_pin_data: @pin_data($pin_data:ident), @impl_generics($($impl_generics:tt)*), @@ -988,38 +1049,56 @@ macro_rules! __pin_data { @pinned($($(#[$($p_attr:tt)*])* $pvis:vis $p_field:ident : $p_type:ty),* $(,)?), @not_pinned($($(#[$($attr:tt)*])* $fvis:vis $field:ident : $type:ty),* $(,)?), ) => { - // For every field, we create a projection function according to its projection type. If a - // field is structurally pinned, then it must be initialized via `PinInit`, if it is not - // structurally pinned, then it can be initialized via `Init`. - // - // The functions are `unsafe` to prevent accidentally calling them. - #[allow(dead_code)] - #[expect(clippy::missing_safety_doc)] - impl<$($impl_generics)*> $pin_data<$($ty_generics)*> - where $($whr)* - { - $( - $(#[$($p_attr)*])* - $pvis unsafe fn $p_field<E>( - self, - slot: *mut $p_type, - init: impl $crate::PinInit<$p_type, E>, - ) -> ::core::result::Result<(), E> { - // SAFETY: TODO. - unsafe { $crate::PinInit::__pinned_init(init, slot) } - } - )* - $( - $(#[$($attr)*])* - $fvis unsafe fn $field<E>( - self, - slot: *mut $type, - init: impl $crate::Init<$type, E>, - ) -> ::core::result::Result<(), E> { - // SAFETY: TODO. - unsafe { $crate::Init::__init(init, slot) } - } - )* + $crate::macros::paste! { + // For every field, we create a projection function according to its projection type. If a + // field is structurally pinned, then it must be initialized via `PinInit`, if it is not + // structurally pinned, then it can be initialized via `Init`. + // + // The functions are `unsafe` to prevent accidentally calling them. + #[allow(dead_code)] + #[expect(clippy::missing_safety_doc)] + impl<$($impl_generics)*> $pin_data<$($ty_generics)*> + where $($whr)* + { + $( + $(#[$($p_attr)*])* + $pvis unsafe fn $p_field<E>( + self, + slot: *mut $p_type, + init: impl $crate::PinInit<$p_type, E>, + ) -> ::core::result::Result<(), E> { + // SAFETY: TODO. + unsafe { $crate::PinInit::__pinned_init(init, slot) } + } + + $(#[$($p_attr)*])* + $pvis unsafe fn [<__project_ $p_field>]<'__slot>( + self, + slot: &'__slot mut $p_type, + ) -> ::core::pin::Pin<&'__slot mut $p_type> { + ::core::pin::Pin::new_unchecked(slot) + } + )* + $( + $(#[$($attr)*])* + $fvis unsafe fn $field<E>( + self, + slot: *mut $type, + init: impl $crate::Init<$type, E>, + ) -> ::core::result::Result<(), E> { + // SAFETY: TODO. + unsafe { $crate::Init::__init(init, slot) } + } + + $(#[$($attr)*])* + $fvis unsafe fn [<__project_ $field>]<'__slot>( + self, + slot: &'__slot mut $type, + ) -> &'__slot mut $type { + slot + } + )* + } } }; } @@ -1202,6 +1281,21 @@ macro_rules! __init_internal { // have been initialized. Therefore we can now dismiss the guards by forgetting them. $(::core::mem::forget($guards);)* }; + (init_slot($($use_data:ident)?): + @data($data:ident), + @slot($slot:ident), + @guards($($guards:ident,)*), + // arbitrary code block + @munch_fields(_: { $($code:tt)* }, $($rest:tt)*), + ) => { + { $($code)* } + $crate::__init_internal!(init_slot($($use_data)?): + @data($data), + @slot($slot), + @guards($($guards,)*), + @munch_fields($($rest)*), + ); + }; (init_slot($use_data:ident): // `use_data` is present, so we use the `data` to init fields. @data($data:ident), @slot($slot:ident), @@ -1216,6 +1310,13 @@ macro_rules! __init_internal { // return when an error/panic occurs. // We also use the `data` to require the correct trait (`Init` or `PinInit`) for `$field`. unsafe { $data.$field(::core::ptr::addr_of_mut!((*$slot).$field), init)? }; + // SAFETY: + // - the project function does the correct field projection, + // - the field has been initialized, + // - the reference is only valid until the end of the initializer. + #[allow(unused_variables)] + let $field = $crate::macros::paste!(unsafe { $data.[< __project_ $field >](&mut (*$slot).$field) }); + // Create the drop guard: // // We rely on macro hygiene to make it impossible for users to access this local variable. @@ -1247,6 +1348,14 @@ macro_rules! __init_internal { // SAFETY: `slot` is valid, because we are inside of an initializer closure, we // return when an error/panic occurs. unsafe { $crate::Init::__init(init, ::core::ptr::addr_of_mut!((*$slot).$field))? }; + + // SAFETY: + // - the field is not structurally pinned, since the line above must compile, + // - the field has been initialized, + // - the reference is only valid until the end of the initializer. + #[allow(unused_variables)] + let $field = unsafe { &mut (*$slot).$field }; + // Create the drop guard: // // We rely on macro hygiene to make it impossible for users to access this local variable. @@ -1265,7 +1374,48 @@ macro_rules! __init_internal { ); } }; - (init_slot($($use_data:ident)?): + (init_slot(): // No `use_data`, so all fields are not structurally pinned + @data($data:ident), + @slot($slot:ident), + @guards($($guards:ident,)*), + // Init by-value. + @munch_fields($field:ident $(: $val:expr)?, $($rest:tt)*), + ) => { + { + $(let $field = $val;)? + // Initialize the field. + // + // SAFETY: The memory at `slot` is uninitialized. + unsafe { ::core::ptr::write(::core::ptr::addr_of_mut!((*$slot).$field), $field) }; + } + + #[allow(unused_variables)] + // SAFETY: + // - the field is not structurally pinned, since no `use_data` was required to create this + // initializer, + // - the field has been initialized, + // - the reference is only valid until the end of the initializer. + let $field = unsafe { &mut (*$slot).$field }; + + // Create the drop guard: + // + // We rely on macro hygiene to make it impossible for users to access this local variable. + // We use `paste!` to create new hygiene for `$field`. + $crate::macros::paste! { + // SAFETY: We forget the guard later when initialization has succeeded. + let [< __ $field _guard >] = unsafe { + $crate::__internal::DropGuard::new(::core::ptr::addr_of_mut!((*$slot).$field)) + }; + + $crate::__init_internal!(init_slot(): + @data($data), + @slot($slot), + @guards([< __ $field _guard >], $($guards,)*), + @munch_fields($($rest)*), + ); + } + }; + (init_slot($use_data:ident): @data($data:ident), @slot($slot:ident), @guards($($guards:ident,)*), @@ -1279,6 +1429,13 @@ macro_rules! __init_internal { // SAFETY: The memory at `slot` is uninitialized. unsafe { ::core::ptr::write(::core::ptr::addr_of_mut!((*$slot).$field), $field) }; } + // SAFETY: + // - the project function does the correct field projection, + // - the field has been initialized, + // - the reference is only valid until the end of the initializer. + #[allow(unused_variables)] + let $field = $crate::macros::paste!(unsafe { $data.[< __project_ $field >](&mut (*$slot).$field) }); + // Create the drop guard: // // We rely on macro hygiene to make it impossible for users to access this local variable. @@ -1289,7 +1446,7 @@ macro_rules! __init_internal { $crate::__internal::DropGuard::new(::core::ptr::addr_of_mut!((*$slot).$field)) }; - $crate::__init_internal!(init_slot($($use_data)?): + $crate::__init_internal!(init_slot($use_data): @data($data), @slot($slot), @guards([< __ $field _guard >], $($guards,)*), @@ -1300,6 +1457,20 @@ macro_rules! __init_internal { (make_initializer: @slot($slot:ident), @type_name($t:path), + @munch_fields(_: { $($code:tt)* }, $($rest:tt)*), + @acc($($acc:tt)*), + ) => { + // code blocks are ignored for the initializer check + $crate::__init_internal!(make_initializer: + @slot($slot), + @type_name($t), + @munch_fields($($rest)*), + @acc($($acc)*), + ); + }; + (make_initializer: + @slot($slot:ident), + @type_name($t:path), @munch_fields(..Zeroable::init_zeroed() $(,)?), @acc($($acc:tt)*), ) => { diff --git a/rust/uapi/uapi_helper.h b/rust/uapi/uapi_helper.h index 1409441359f5..d4a239cf2a64 100644 --- a/rust/uapi/uapi_helper.h +++ b/rust/uapi/uapi_helper.h @@ -9,6 +9,7 @@ #include <uapi/asm-generic/ioctl.h> #include <uapi/drm/drm.h> #include <uapi/drm/nova_drm.h> +#include <uapi/drm/panthor_drm.h> #include <uapi/linux/mdio.h> #include <uapi/linux/mii.h> #include <uapi/linux/ethtool.h> diff --git a/samples/rust/rust_dma.rs b/samples/rust/rust_dma.rs index c5e7cce68654..04007e29fd85 100644 --- a/samples/rust/rust_dma.rs +++ b/samples/rust/rust_dma.rs @@ -7,15 +7,19 @@ use kernel::{ bindings, device::Core, - dma::{CoherentAllocation, Device, DmaMask}, - pci, + dma::{CoherentAllocation, DataDirection, Device, DmaMask}, + page, pci, prelude::*, + scatterlist::{Owned, SGTable}, types::ARef, }; +#[pin_data(PinnedDrop)] struct DmaSampleDriver { pdev: ARef<pci::Device>, ca: CoherentAllocation<MyStruct>, + #[pin] + sgt: SGTable<Owned<VVec<u8>>>, } const TEST_VALUES: [(u32, u32); 5] = [ @@ -70,21 +74,30 @@ impl pci::Driver for DmaSampleDriver { kernel::dma_write!(ca[i] = MyStruct::new(value.0, value.1))?; } - let drvdata = KBox::new( - Self { + let size = 4 * page::PAGE_SIZE; + let pages = VVec::with_capacity(size, GFP_KERNEL)?; + + let sgt = SGTable::new(pdev.as_ref(), pages, DataDirection::ToDevice, GFP_KERNEL); + + let drvdata = KBox::pin_init( + try_pin_init!(Self { pdev: pdev.into(), ca, - }, + sgt <- sgt, + }), GFP_KERNEL, )?; - Ok(drvdata.into()) + Ok(drvdata) } } -impl Drop for DmaSampleDriver { - fn drop(&mut self) { - dev_info!(self.pdev.as_ref(), "Unload DMA test driver.\n"); +#[pinned_drop] +impl PinnedDrop for DmaSampleDriver { + fn drop(self: Pin<&mut Self>) { + let dev = self.pdev.as_ref(); + + dev_info!(dev, "Unload DMA test driver.\n"); for (i, value) in TEST_VALUES.into_iter().enumerate() { let val0 = kernel::dma_read!(self.ca[i].h); @@ -99,6 +112,10 @@ impl Drop for DmaSampleDriver { assert_eq!(val1, value.1); } } + + for (i, entry) in self.sgt.iter().enumerate() { + dev_info!(dev, "Entry[{}]: DMA address: {:#x}", i, entry.dma_address()); + } } } diff --git a/samples/rust/rust_driver_pci.rs b/samples/rust/rust_driver_pci.rs index 606946ff4d7f..1ac0b06fa3b3 100644 --- a/samples/rust/rust_driver_pci.rs +++ b/samples/rust/rust_driver_pci.rs @@ -78,8 +78,8 @@ impl pci::Driver for SampleDriver { let drvdata = KBox::pin_init( try_pin_init!(Self { - pdev: pdev.into(), bar <- pdev.iomap_region_sized::<{ Regs::END }>(0, c_str!("rust_driver_pci")), + pdev: pdev.into(), index: *info, }), GFP_KERNEL, |