Add safe Rust abstractions over the Linux kernel's GPU buddy allocator for physical memory management. The GPU buddy allocator implements a binary buddy system for useful for GPU physical memory allocation. nova-core will use it for physical memory allocation.
Signed-off-by: Joel Fernandes <[email protected]> --- rust/bindings/bindings_helper.h | 11 + rust/helpers/gpu.c | 23 ++ rust/helpers/helpers.c | 1 + rust/kernel/gpu/buddy.rs | 527 ++++++++++++++++++++++++++++++++ rust/kernel/gpu/mod.rs | 5 + rust/kernel/lib.rs | 2 + 6 files changed, 569 insertions(+) create mode 100644 rust/helpers/gpu.c create mode 100644 rust/kernel/gpu/buddy.rs create mode 100644 rust/kernel/gpu/mod.rs diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h index 6b973589a546..86a7e304b7ab 100644 --- a/rust/bindings/bindings_helper.h +++ b/rust/bindings/bindings_helper.h @@ -29,6 +29,7 @@ #include <linux/hrtimer_types.h> #include <linux/acpi.h> +#include <linux/gpu_buddy.h> #include <drm/drm_device.h> #include <drm/drm_drv.h> #include <drm/drm_file.h> @@ -112,6 +113,16 @@ const gfp_t RUST_CONST_HELPER_XA_FLAGS_ALLOC = XA_FLAGS_ALLOC; const gfp_t RUST_CONST_HELPER_XA_FLAGS_ALLOC1 = XA_FLAGS_ALLOC1; const vm_flags_t RUST_CONST_HELPER_VM_MERGEABLE = VM_MERGEABLE; +#if IS_ENABLED(CONFIG_GPU_BUDDY) +const unsigned long RUST_CONST_HELPER_GPU_BUDDY_RANGE_ALLOCATION = GPU_BUDDY_RANGE_ALLOCATION; +const unsigned long RUST_CONST_HELPER_GPU_BUDDY_TOPDOWN_ALLOCATION = GPU_BUDDY_TOPDOWN_ALLOCATION; +const unsigned long RUST_CONST_HELPER_GPU_BUDDY_CONTIGUOUS_ALLOCATION = + GPU_BUDDY_CONTIGUOUS_ALLOCATION; +const unsigned long RUST_CONST_HELPER_GPU_BUDDY_CLEAR_ALLOCATION = GPU_BUDDY_CLEAR_ALLOCATION; +const unsigned long RUST_CONST_HELPER_GPU_BUDDY_CLEARED = GPU_BUDDY_CLEARED; +const unsigned long RUST_CONST_HELPER_GPU_BUDDY_TRIM_DISABLE = GPU_BUDDY_TRIM_DISABLE; +#endif + #if IS_ENABLED(CONFIG_ANDROID_BINDER_IPC_RUST) #include "../../drivers/android/binder/rust_binder.h" #include "../../drivers/android/binder/rust_binder_events.h" diff --git a/rust/helpers/gpu.c b/rust/helpers/gpu.c new file mode 100644 index 000000000000..415836b86abf --- /dev/null +++ b/rust/helpers/gpu.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/gpu_buddy.h> + +#ifdef CONFIG_GPU_BUDDY + +u64 rust_helper_gpu_buddy_block_offset(const struct gpu_buddy_block *block) +{ + return gpu_buddy_block_offset(block); +} + +unsigned int rust_helper_gpu_buddy_block_order(struct gpu_buddy_block *block) +{ + return gpu_buddy_block_order(block); +} + +u64 rust_helper_gpu_buddy_block_size(struct gpu_buddy *mm, + struct gpu_buddy_block *block) +{ + return gpu_buddy_block_size(mm, block); +} + +#endif /* CONFIG_GPU_BUDDY */ diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c index 634fa2386bbb..6db7c4c25afa 100644 --- a/rust/helpers/helpers.c +++ b/rust/helpers/helpers.c @@ -29,6 +29,7 @@ #include "err.c" #include "irq.c" #include "fs.c" +#include "gpu.c" #include "io.c" #include "jump_label.c" #include "kunit.c" diff --git a/rust/kernel/gpu/buddy.rs b/rust/kernel/gpu/buddy.rs new file mode 100644 index 000000000000..3e1a9617e6aa --- /dev/null +++ b/rust/kernel/gpu/buddy.rs @@ -0,0 +1,527 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! GPU buddy allocator bindings. +//! +//! C header: [`include/linux/gpu_buddy.h`](srctree/include/linux/gpu_buddy.h) +//! +//! This module provides Rust abstractions over the Linux kernel's GPU buddy +//! allocator, which implements a binary buddy memory allocator. +//! +//! The buddy allocator manages a contiguous address space and allocates blocks +//! in power-of-two sizes, useful for GPU physical memory management. +//! +//! # Examples +//! +//! ``` +//! use kernel::{ +//! gpu::buddy::{BuddyFlags, GpuBuddy, GpuBuddyAllocParams, GpuBuddyParams}, +//! prelude::*, +//! sizes::*, // +//! }; +//! +//! // Create a 1GB buddy allocator with 4KB minimum chunk size. +//! let mut buddy = GpuBuddy::new(GpuBuddyParams { +//! physical_memory_size_bytes: SZ_1G as u64, +//! chunk_size_bytes: SZ_4K as u64, +//! })?; +//! +//! // Verify initial state. +//! assert_eq!(buddy.size(), SZ_1G as u64); +//! assert_eq!(buddy.chunk_size(), SZ_4K as u64); +//! let initial_free = buddy.free_memory_bytes(); +//! +//! // Base allocation params - reused across tests with field overrides. +//! let params = GpuBuddyAllocParams { +//! start_range_address: 0, +//! end_range_address: 0, // Entire range. +//! size_bytes: SZ_16M as u64, +//! min_block_size_bytes: SZ_16M as u64, +//! buddy_flags: BuddyFlags::try_new(BuddyFlags::RANGE_ALLOCATION)?, +//! }; +//! +//! // Test top-down allocation (allocates from highest addresses). +//! let topdown = buddy.alloc_blocks(GpuBuddyAllocParams { +//! buddy_flags: BuddyFlags::try_new(BuddyFlags::TOPDOWN_ALLOCATION)?, +//! ..params +//! })?; +//! assert_eq!(buddy.free_memory_bytes(), initial_free - SZ_16M as u64); +//! +//! for block in topdown.iter() { +//! assert_eq!(block.offset(), (SZ_1G - SZ_16M) as u64); +//! assert_eq!(block.order(), 12); // 2^12 pages +//! assert_eq!(block.size(), SZ_16M as u64); +//! } +//! drop(topdown); +//! assert_eq!(buddy.free_memory_bytes(), initial_free); +//! +//! // Allocate 16MB - should result in a single 16MB block at offset 0. +//! let allocated = buddy.alloc_blocks(params)?; +//! assert_eq!(buddy.free_memory_bytes(), initial_free - SZ_16M as u64); +//! +//! for block in allocated.iter() { +//! assert_eq!(block.offset(), 0); +//! assert_eq!(block.order(), 12); // 2^12 pages +//! assert_eq!(block.size(), SZ_16M as u64); +//! } +//! drop(allocated); +//! assert_eq!(buddy.free_memory_bytes(), initial_free); +//! +//! // Test non-contiguous allocation with fragmented memory. +//! // Create fragmentation by allocating 4MB blocks at [0,4M) and [8M,12M). +//! let params_4m = GpuBuddyAllocParams { +//! end_range_address: SZ_4M as u64, +//! size_bytes: SZ_4M as u64, +//! min_block_size_bytes: SZ_4M as u64, +//! ..params +//! }; +//! let frag1 = buddy.alloc_blocks(params_4m)?; +//! assert_eq!(buddy.free_memory_bytes(), initial_free - SZ_4M as u64); +//! +//! let frag2 = buddy.alloc_blocks(GpuBuddyAllocParams { +//! start_range_address: SZ_8M as u64, +//! end_range_address: (SZ_8M + SZ_4M) as u64, +//! ..params_4m +//! })?; +//! assert_eq!(buddy.free_memory_bytes(), initial_free - SZ_8M as u64); +//! +//! // Allocate 8MB without CONTIGUOUS - should return 2 blocks from the holes. +//! let fragmented = buddy.alloc_blocks(GpuBuddyAllocParams { +//! end_range_address: SZ_16M as u64, +//! size_bytes: SZ_8M as u64, +//! min_block_size_bytes: SZ_4M as u64, +//! ..params +//! })?; +//! assert_eq!(buddy.free_memory_bytes(), initial_free - (SZ_16M) as u64); +//! +//! let (mut count, mut total) = (0u32, 0u64); +//! for block in fragmented.iter() { +//! // The 8MB allocation should return 2 blocks, each 4MB. +//! assert_eq!(block.size(), SZ_4M as u64); +//! total += block.size(); +//! count += 1; +//! } +//! assert_eq!(total, SZ_8M as u64); +//! assert_eq!(count, 2); +//! drop(fragmented); +//! drop(frag2); +//! drop(frag1); +//! assert_eq!(buddy.free_memory_bytes(), initial_free); +//! +//! // Test CONTIGUOUS failure when only fragmented space available. +//! // Create a small buddy allocator with only 16MB of memory. +//! let mut small = GpuBuddy::new(GpuBuddyParams { +//! physical_memory_size_bytes: SZ_16M as u64, +//! chunk_size_bytes: SZ_4K as u64, +//! })?; +//! +//! // Allocate 4MB blocks at [0,4M) and [8M,12M) to create fragmented memory. +//! let hole1 = small.alloc_blocks(params_4m)?; +//! let hole2 = small.alloc_blocks(GpuBuddyAllocParams { +//! start_range_address: SZ_8M as u64, +//! end_range_address: (SZ_8M + SZ_4M) as u64, +//! ..params_4m +//! })?; +//! +//! // 8MB contiguous should fail - only two non-contiguous 4MB holes exist. +//! let result = small.alloc_blocks(GpuBuddyAllocParams { +//! size_bytes: SZ_8M as u64, +//! min_block_size_bytes: SZ_4M as u64, +//! buddy_flags: BuddyFlags::try_new(BuddyFlags::CONTIGUOUS_ALLOCATION)?, +//! ..params +//! }); +//! assert!(result.is_err()); +//! drop(hole2); +//! drop(hole1); +//! +//! # Ok::<(), Error>(()) +//! ``` + +use crate::{ + bindings, + clist::CListHead, + clist_create, + error::to_result, + new_mutex, + prelude::*, + sync::{ + lock::mutex::MutexGuard, + Arc, + Mutex, // + }, + types::Opaque, +}; + +/// Flags for GPU buddy allocator operations. +/// +/// These flags control the allocation behavior of the buddy allocator. +#[derive(Clone, Copy, Default, PartialEq, Eq)] +pub struct BuddyFlags(usize); + +impl BuddyFlags { + /// Range-based allocation from start to end addresses. + pub const RANGE_ALLOCATION: usize = bindings::GPU_BUDDY_RANGE_ALLOCATION; + + /// Allocate from top of address space downward. + pub const TOPDOWN_ALLOCATION: usize = bindings::GPU_BUDDY_TOPDOWN_ALLOCATION; + + /// Allocate physically contiguous blocks. + pub const CONTIGUOUS_ALLOCATION: usize = bindings::GPU_BUDDY_CONTIGUOUS_ALLOCATION; + + /// Request allocation from the cleared (zeroed) memory. The zero'ing is not + /// done by the allocator, but by the caller before freeing old blocks. + pub const CLEAR_ALLOCATION: usize = bindings::GPU_BUDDY_CLEAR_ALLOCATION; + + /// Disable trimming of partially used blocks. + pub const TRIM_DISABLE: usize = bindings::GPU_BUDDY_TRIM_DISABLE; + + /// Mark blocks as cleared (zeroed) when freeing. When set during free, + /// indicates that the caller has already zeroed the memory. + pub const CLEARED: usize = bindings::GPU_BUDDY_CLEARED; + + /// Create [`BuddyFlags`] from a raw value with validation. + /// + /// Use `|` operator to combine flags if needed, before calling this method. + pub fn try_new(flags: usize) -> Result<Self> { + // Flags must not exceed u32::MAX to satisfy the GPU buddy allocator C API. + if flags > u32::MAX as usize { + return Err(EINVAL); + } + + // `TOPDOWN_ALLOCATION` only works without `RANGE_ALLOCATION`. When both are + // set, `TOPDOWN_ALLOCATION` is silently ignored by the allocator. Reject this. + if (flags & Self::RANGE_ALLOCATION) != 0 && (flags & Self::TOPDOWN_ALLOCATION) != 0 { + return Err(EINVAL); + } + + Ok(Self(flags)) + } + + /// Get raw value of the flags. + pub(crate) fn as_raw(self) -> usize { + self.0 + } +} + +/// Parameters for creating a GPU buddy allocator. +#[derive(Clone, Copy)] +pub struct GpuBuddyParams { + /// Total physical memory size managed by the allocator in bytes. + pub physical_memory_size_bytes: u64, + /// Minimum allocation unit / chunk size in bytes, must be >= 4KB. + pub chunk_size_bytes: u64, +} + +/// Parameters for allocating blocks from a GPU buddy allocator. +#[derive(Clone, Copy)] +pub struct GpuBuddyAllocParams { + /// Start of allocation range in bytes. Use 0 for beginning. + pub start_range_address: u64, + /// End of allocation range in bytes. Use 0 for entire range. + pub end_range_address: u64, + /// Total size to allocate in bytes. + pub size_bytes: u64, + /// Minimum block size for fragmented allocations in bytes. + pub min_block_size_bytes: u64, + /// Buddy allocator behavior flags. + pub buddy_flags: BuddyFlags, +} + +/// Inner structure holding the actual buddy allocator. +/// +/// # Synchronization +/// +/// The C `gpu_buddy` API requires synchronization (see `include/linux/gpu_buddy.h`). +/// The internal [`GpuBuddyGuard`] ensures that the lock is held for all +/// allocator and free operations, preventing races between concurrent allocations +/// and the freeing that occurs when [`AllocatedBlocks`] is dropped. +/// +/// # Invariants +/// +/// The inner [`Opaque`] contains a valid, initialized buddy allocator. +#[pin_data(PinnedDrop)] +struct GpuBuddyInner { + #[pin] + inner: Opaque<bindings::gpu_buddy>, + #[pin] + lock: Mutex<()>, +} + +impl GpuBuddyInner { + /// Create a pin-initializer for the buddy allocator. + fn new(params: &GpuBuddyParams) -> impl PinInit<Self, Error> { + let size = params.physical_memory_size_bytes; + let chunk_size = params.chunk_size_bytes; + + try_pin_init!(Self { + inner <- Opaque::try_ffi_init(|ptr| { + // SAFETY: ptr points to valid uninitialized memory from the pin-init + // infrastructure. gpu_buddy_init will initialize the structure. + to_result(unsafe { bindings::gpu_buddy_init(ptr, size, chunk_size) }) + }), + lock <- new_mutex!(()), + }) + } + + /// Lock the mutex and return a guard for accessing the allocator. + fn lock(&self) -> GpuBuddyGuard<'_> { + GpuBuddyGuard { + inner: self, + _guard: self.lock.lock(), + } + } +} + +#[pinned_drop] +impl PinnedDrop for GpuBuddyInner { + fn drop(self: Pin<&mut Self>) { + let guard = self.lock(); + + // SAFETY: guard provides exclusive access to the allocator. + unsafe { + bindings::gpu_buddy_fini(guard.as_raw()); + } + } +} + +// SAFETY: [`GpuBuddyInner`] can be sent between threads. +unsafe impl Send for GpuBuddyInner {} + +// SAFETY: [`GpuBuddyInner`] is `Sync` because the internal [`GpuBuddyGuard`] +// serializes all access to the C allocator, preventing data races. +unsafe impl Sync for GpuBuddyInner {} + +/// Guard that proves the lock is held, enabling access to the allocator. +/// +/// # Invariants +/// +/// The inner `_guard` holds the lock for the duration of this guard's lifetime. +pub(crate) struct GpuBuddyGuard<'a> { + inner: &'a GpuBuddyInner, + _guard: MutexGuard<'a, ()>, +} + +impl GpuBuddyGuard<'_> { + /// Get a raw pointer to the underlying C `gpu_buddy` structure. + fn as_raw(&self) -> *mut bindings::gpu_buddy { + self.inner.inner.get() + } +} + +/// GPU buddy allocator instance. +/// +/// This structure wraps the C `gpu_buddy` allocator using reference counting. +/// The allocator is automatically cleaned up when all references are dropped. +/// +/// # Invariants +/// +/// The inner [`Arc`] points to a valid, initialized GPU buddy allocator. +pub struct GpuBuddy(Arc<GpuBuddyInner>); + +impl GpuBuddy { + /// Create a new buddy allocator. + /// + /// Creates a buddy allocator that manages a contiguous address space of the given + /// size, with the specified minimum allocation unit (chunk_size must be at least 4KB). + pub fn new(params: GpuBuddyParams) -> Result<Self> { + Ok(Self(Arc::pin_init( + GpuBuddyInner::new(¶ms), + GFP_KERNEL, + )?)) + } + + /// Get the chunk size (minimum allocation unit). + pub fn chunk_size(&self) -> u64 { + let guard = self.0.lock(); + // SAFETY: guard provides exclusive access to the allocator. + unsafe { (*guard.as_raw()).chunk_size } + } + + /// Get the total managed size. + pub fn size(&self) -> u64 { + let guard = self.0.lock(); + // SAFETY: guard provides exclusive access to the allocator. + unsafe { (*guard.as_raw()).size } + } + + /// Get the available (free) memory in bytes. + pub fn free_memory_bytes(&self) -> u64 { + let guard = self.0.lock(); + // SAFETY: guard provides exclusive access to the allocator. + unsafe { (*guard.as_raw()).avail } + } + + /// Allocate blocks from the buddy allocator. + /// + /// Returns an [`Arc<AllocatedBlocks>`] structure that owns the allocated blocks + /// and automatically frees them when all references are dropped. + pub fn alloc_blocks(&mut self, params: GpuBuddyAllocParams) -> Result<Arc<AllocatedBlocks>> { + let buddy_arc = Arc::clone(&self.0); + + // Create pin-initializer that initializes list and allocates blocks. + let init = try_pin_init!(AllocatedBlocks { + list <- CListHead::try_init(|list| { + // Lock while allocating to serialize with concurrent frees. + let guard = buddy_arc.lock(); + + // SAFETY: guard provides exclusive access, list is initialized. + to_result(unsafe { + bindings::gpu_buddy_alloc_blocks( + guard.as_raw(), + params.start_range_address, + params.end_range_address, + params.size_bytes, + params.min_block_size_bytes, + list.as_raw(), + params.buddy_flags.as_raw(), + ) + }) + }), + buddy: Arc::clone(&buddy_arc), + flags: params.buddy_flags, + }); + + Arc::pin_init(init, GFP_KERNEL) + } +} + +/// Allocated blocks from the buddy allocator with automatic cleanup. +/// +/// This structure owns a list of allocated blocks and ensures they are +/// automatically freed when dropped. Use `iter()` to iterate over all +/// allocated [`Block`] structures. +/// +/// # Invariants +/// +/// - `list` is an initialized, valid list head containing allocated blocks. +/// - `buddy` references a valid [`GpuBuddyInner`]. +#[pin_data(PinnedDrop)] +pub struct AllocatedBlocks { + #[pin] + list: CListHead, + buddy: Arc<GpuBuddyInner>, + flags: BuddyFlags, +} + +impl AllocatedBlocks { + /// Check if the block list is empty. + pub fn is_empty(&self) -> bool { + // An empty list head points to itself. + !self.list.is_linked() + } + + /// Iterate over allocated blocks. + /// + /// Returns an iterator yielding [`AllocatedBlock`] references. The blocks + /// are only valid for the duration of the borrow of `self`. + pub fn iter(&self) -> impl Iterator<Item = AllocatedBlock<'_>> + '_ { + // SAFETY: list contains gpu_buddy_block items linked via __bindgen_anon_1.link. + let clist = unsafe { + clist_create!( + self.list.as_raw(), + Block, + bindings::gpu_buddy_block, + __bindgen_anon_1.link + ) + }; + + clist + .iter() + .map(|block| AllocatedBlock { block, alloc: self }) + } +} + +#[pinned_drop] +impl PinnedDrop for AllocatedBlocks { + fn drop(self: Pin<&mut Self>) { + let guard = self.buddy.lock(); + + // SAFETY: + // - list is valid per the type's invariants. + // - guard provides exclusive access to the allocator. + // CAST: BuddyFlags were validated to fit in u32 at construction. + unsafe { + bindings::gpu_buddy_free_list( + guard.as_raw(), + self.list.as_raw(), + self.flags.as_raw() as u32, + ); + } + } +} + +/// A GPU buddy block. +/// +/// Transparent wrapper over C `gpu_buddy_block` structure. This type is returned +/// as references from [`CListIter`] during iteration over [`AllocatedBlocks`]. +/// +/// # Invariants +/// +/// The inner [`Opaque`] contains a valid, allocated `gpu_buddy_block`. +#[repr(transparent)] +pub struct Block(Opaque<bindings::gpu_buddy_block>); + +impl Block { + /// Get a raw pointer to the underlying C block. + fn as_raw(&self) -> *mut bindings::gpu_buddy_block { + self.0.get() + } + + /// Get the block's offset in the address space. + pub(crate) fn offset(&self) -> u64 { + // SAFETY: self.as_raw() is valid per the type's invariants. + unsafe { bindings::gpu_buddy_block_offset(self.as_raw()) } + } + + /// Get the block order. + pub(crate) fn order(&self) -> u32 { + // SAFETY: self.as_raw() is valid per the type's invariants. + unsafe { bindings::gpu_buddy_block_order(self.as_raw()) } + } +} + +// SAFETY: `Block` is a transparent wrapper over `gpu_buddy_block` which is not +// modified after allocation. It can be safely sent between threads. +unsafe impl Send for Block {} + +// SAFETY: `Block` is a transparent wrapper over `gpu_buddy_block` which is not +// modified after allocation. It can be safely shared among threads. +unsafe impl Sync for Block {} + +/// An allocated block with access to the buddy allocator. +/// +/// This wrapper holds references to the block and the allocation list, +/// enabling the `size()` method which requires the allocator. +/// +/// # Invariants +/// +/// - `block` is a valid reference to an allocated [`Block`]. +/// - `alloc` is a valid reference to the [`AllocatedBlocks`] that owns this block. +pub struct AllocatedBlock<'a> { + block: &'a Block, + alloc: &'a AllocatedBlocks, +} + +impl AllocatedBlock<'_> { + /// Get the block's offset in the address space. + pub fn offset(&self) -> u64 { + self.block.offset() + } + + /// Get the block order (size = chunk_size << order). + pub fn order(&self) -> u32 { + self.block.order() + } + + /// Get the block's size in bytes. + pub fn size(&self) -> u64 { + // Acquire guard to calculate block size since it is calculated from + // the chunk size, which requires access to the allocator. While the chunk size + // cannot change after initialization, we still need the guard to gain access + // to the allocator's pointer. + let guard = self.alloc.buddy.lock(); + // SAFETY: + // - Guard provides exclusive access to the allocator. + // - `block.as_raw()` is a valid pointer per the type's invariants. + unsafe { bindings::gpu_buddy_block_size(guard.as_raw(), self.block.as_raw()) } + } +} diff --git a/rust/kernel/gpu/mod.rs b/rust/kernel/gpu/mod.rs new file mode 100644 index 000000000000..8f25e6367edc --- /dev/null +++ b/rust/kernel/gpu/mod.rs @@ -0,0 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! GPU subsystem abstractions. + +pub mod buddy; diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs index b69cc5ed3b59..850cbbf4c3e7 100644 --- a/rust/kernel/lib.rs +++ b/rust/kernel/lib.rs @@ -95,6 +95,8 @@ pub mod firmware; pub mod fmt; pub mod fs; +#[cfg(CONFIG_GPU_BUDDY)] +pub mod gpu; pub mod id_pool; pub mod init; pub mod io; -- 2.34.1
