* [PATCH v8 08/25] gpu: nova-core: mm: Add common memory management types
From: Joel Fernandes @ 2026-02-24 22:53 UTC (permalink / raw)
To: linux-kernel
Cc: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Dave Airlie, Daniel Almeida, Koen Koning,
dri-devel, nouveau, rust-for-linux, Nikola Djukic,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jonathan Corbet, Alex Deucher,
Christian König, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Huang Rui, Matthew Auld, Matthew Brost,
Lucas De Marchi, Thomas Hellström, Helge Deller, Alex Gaynor,
Boqun Feng, John Hubbard, Alistair Popple, Timur Tabi, Edwin Peer,
Alexandre Courbot, Andrea Righi, Andy Ritger, Zhi Wang,
Balbir Singh, Philipp Stanner, Elle Rhumsaa, alexeyi,
Eliot Courtney, joel, linux-doc, amd-gfx, intel-gfx, intel-xe,
linux-fbdev, Joel Fernandes
In-Reply-To: <20260224225323.3312204-1-joelagnelf@nvidia.com>
Add foundational types for GPU memory management. These types are used
throughout the nova memory management subsystem for page table
operations, address translation, and memory allocation.
Cc: Nikola Djukic <ndjukic@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
drivers/gpu/nova-core/mm.rs | 174 ++++++++++++++++++++++++++++++++++++
1 file changed, 174 insertions(+)
diff --git a/drivers/gpu/nova-core/mm.rs b/drivers/gpu/nova-core/mm.rs
index 7a5dd4220c67..a8b2e1870566 100644
--- a/drivers/gpu/nova-core/mm.rs
+++ b/drivers/gpu/nova-core/mm.rs
@@ -2,4 +2,178 @@
//! Memory management subsystems for nova-core.
+#![expect(dead_code)]
+
pub(crate) mod pramin;
+
+use kernel::sizes::SZ_4K;
+
+use crate::num::u64_as_usize;
+
+/// Page size in bytes (4 KiB).
+pub(crate) const PAGE_SIZE: usize = SZ_4K;
+
+bitfield! {
+ pub(crate) struct VramAddress(u64), "Physical VRAM address in GPU video memory" {
+ 11:0 offset as u64, "Offset within 4KB page";
+ 63:12 frame_number as u64 => Pfn, "Physical frame number";
+ }
+}
+
+impl VramAddress {
+ /// Create a new VRAM address from a raw value.
+ pub(crate) const fn new(addr: u64) -> Self {
+ Self(addr)
+ }
+
+ /// Get the raw address value as `usize` (useful for MMIO offsets).
+ pub(crate) const fn raw(&self) -> usize {
+ u64_as_usize(self.0)
+ }
+
+ /// Get the raw address value as `u64`.
+ pub(crate) const fn raw_u64(&self) -> u64 {
+ self.0
+ }
+}
+
+impl PartialEq for VramAddress {
+ fn eq(&self, other: &Self) -> bool {
+ self.0 == other.0
+ }
+}
+
+impl Eq for VramAddress {}
+
+impl PartialOrd for VramAddress {
+ fn partial_cmp(&self, other: &Self) -> Option<core::cmp::Ordering> {
+ Some(self.cmp(other))
+ }
+}
+
+impl Ord for VramAddress {
+ fn cmp(&self, other: &Self) -> core::cmp::Ordering {
+ self.0.cmp(&other.0)
+ }
+}
+
+impl From<Pfn> for VramAddress {
+ fn from(pfn: Pfn) -> Self {
+ Self::default().set_frame_number(pfn)
+ }
+}
+
+bitfield! {
+ pub(crate) struct VirtualAddress(u64), "Virtual address in GPU address space" {
+ 11:0 offset as u64, "Offset within 4KB page";
+ 20:12 l4_index as u64, "Level 4 index (PTE)";
+ 29:21 l3_index as u64, "Level 3 index (Dual PDE)";
+ 38:30 l2_index as u64, "Level 2 index";
+ 47:39 l1_index as u64, "Level 1 index";
+ 56:48 l0_index as u64, "Level 0 index (PDB)";
+ 63:12 frame_number as u64 => Vfn, "Virtual frame number";
+ }
+}
+
+impl VirtualAddress {
+ /// Create a new virtual address from a raw value.
+ #[expect(dead_code)]
+ pub(crate) const fn new(addr: u64) -> Self {
+ Self(addr)
+ }
+
+ /// Get the page table index for a given level (0-5).
+ pub(crate) fn level_index(&self, level: u64) -> u64 {
+ match level {
+ 0 => self.l0_index(),
+ 1 => self.l1_index(),
+ 2 => self.l2_index(),
+ 3 => self.l3_index(),
+ 4 => self.l4_index(),
+
+ // L5 is only used by MMU v3 (PTE level).
+ 5 => self.l4_index(),
+ _ => 0,
+ }
+ }
+}
+
+impl From<Vfn> for VirtualAddress {
+ fn from(vfn: Vfn) -> Self {
+ Self::default().set_frame_number(vfn)
+ }
+}
+
+/// Physical Frame Number.
+///
+/// Represents a physical page in VRAM.
+#[repr(transparent)]
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Default)]
+pub(crate) struct Pfn(u64);
+
+impl Pfn {
+ /// Create a new PFN from a frame number.
+ pub(crate) const fn new(frame_number: u64) -> Self {
+ Self(frame_number)
+ }
+
+ /// Get the raw frame number.
+ pub(crate) const fn raw(self) -> u64 {
+ self.0
+ }
+}
+
+impl From<VramAddress> for Pfn {
+ fn from(addr: VramAddress) -> Self {
+ addr.frame_number()
+ }
+}
+
+impl From<u64> for Pfn {
+ fn from(val: u64) -> Self {
+ Self(val)
+ }
+}
+
+impl From<Pfn> for u64 {
+ fn from(pfn: Pfn) -> Self {
+ pfn.0
+ }
+}
+
+/// Virtual Frame Number.
+///
+/// Represents a virtual page in GPU address space.
+#[repr(transparent)]
+#[derive(Debug, Clone, Copy, PartialEq, Eq, Default)]
+pub(crate) struct Vfn(u64);
+
+impl Vfn {
+ /// Create a new VFN from a frame number.
+ pub(crate) const fn new(frame_number: u64) -> Self {
+ Self(frame_number)
+ }
+
+ /// Get the raw frame number.
+ pub(crate) const fn raw(self) -> u64 {
+ self.0
+ }
+}
+
+impl From<VirtualAddress> for Vfn {
+ fn from(addr: VirtualAddress) -> Self {
+ addr.frame_number()
+ }
+}
+
+impl From<u64> for Vfn {
+ fn from(val: u64) -> Self {
+ Self(val)
+ }
+}
+
+impl From<Vfn> for u64 {
+ fn from(vfn: Vfn) -> Self {
+ vfn.0
+ }
+}
--
2.34.1
^ permalink raw reply related
* [PATCH v8 07/25] docs: gpu: nova-core: Document the PRAMIN aperture mechanism
From: Joel Fernandes @ 2026-02-24 22:53 UTC (permalink / raw)
To: linux-kernel
Cc: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Dave Airlie, Daniel Almeida, Koen Koning,
dri-devel, nouveau, rust-for-linux, Nikola Djukic,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jonathan Corbet, Alex Deucher,
Christian König, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Huang Rui, Matthew Auld, Matthew Brost,
Lucas De Marchi, Thomas Hellström, Helge Deller, Alex Gaynor,
Boqun Feng, John Hubbard, Alistair Popple, Timur Tabi, Edwin Peer,
Alexandre Courbot, Andrea Righi, Andy Ritger, Zhi Wang,
Balbir Singh, Philipp Stanner, Elle Rhumsaa, alexeyi,
Eliot Courtney, joel, linux-doc, amd-gfx, intel-gfx, intel-xe,
linux-fbdev, Joel Fernandes
In-Reply-To: <20260224225323.3312204-1-joelagnelf@nvidia.com>
Add documentation for the PRAMIN aperture mechanism used by nova-core
for direct VRAM access.
Nova only uses TARGET=VID_MEM for VRAM access. The SYS_MEM target values
are documented for completeness but not used by the driver.
Cc: Nikola Djukic <ndjukic@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
Documentation/gpu/nova/core/pramin.rst | 125 +++++++++++++++++++++++++
Documentation/gpu/nova/index.rst | 1 +
2 files changed, 126 insertions(+)
create mode 100644 Documentation/gpu/nova/core/pramin.rst
diff --git a/Documentation/gpu/nova/core/pramin.rst b/Documentation/gpu/nova/core/pramin.rst
new file mode 100644
index 000000000000..55ec9d920629
--- /dev/null
+++ b/Documentation/gpu/nova/core/pramin.rst
@@ -0,0 +1,125 @@
+.. SPDX-License-Identifier: GPL-2.0
+
+=========================
+PRAMIN aperture mechanism
+=========================
+
+.. note::
+ The following description is approximate and current as of the Ampere family.
+ It may change for future generations and is intended to assist in understanding
+ the driver code.
+
+Introduction
+============
+
+PRAMIN is a hardware aperture mechanism that provides CPU access to GPU Video RAM (VRAM) before
+the GPU's Memory Management Unit (MMU) and page tables are initialized. This 1MB sliding window,
+located at a fixed offset within BAR0, is essential for setting up page tables and other critical
+GPU data structures without relying on the GPU's MMU.
+
+Architecture Overview
+=====================
+
+The PRAMIN aperture mechanism is logically implemented by the GPU's PBUS (PCIe Bus Controller Unit)
+and provides a CPU-accessible window into VRAM through the PCIe interface::
+
+ +-----------------+ PCIe +------------------------------+
+ | CPU |<----------->| GPU |
+ +-----------------+ | |
+ | +----------------------+ |
+ | | PBUS | |
+ | | (Bus Controller) | |
+ | | | |
+ | | +--------------+<------------ (window starts at
+ | | | PRAMIN | | | BAR0 + 0x700000)
+ | | | Window | | |
+ | | | (1MB) | | |
+ | | +--------------+ | |
+ | | | | |
+ | +---------|------------+ |
+ | | |
+ | v |
+ | +----------------------+<------------ (Program PRAMIN to any
+ | | VRAM | | 64KB-aligned VRAM boundary)
+ | | (Several GBs) | |
+ | | | |
+ | | FB[0x000000000000] | |
+ | | ... | |
+ | | FB[0x7FFFFFFFFFF] | |
+ | +----------------------+ |
+ +------------------------------+
+
+PBUS (PCIe Bus Controller) is responsible for, among other things, handling MMIO
+accesses to the BAR registers.
+
+PRAMIN Window Operation
+=======================
+
+The PRAMIN window provides a 1MB sliding aperture that can be repositioned over
+the entire VRAM address space using the ``NV_PBUS_BAR0_WINDOW`` register.
+
+Window Control Mechanism
+-------------------------
+
+The window position is controlled via the PBUS ``BAR0_WINDOW`` register::
+
+ NV_PBUS_BAR0_WINDOW Register (0x1700):
+ +-------+--------+--------------------------------------+
+ | 31:26 | 25:24 | 23:0 |
+ | RSVD | TARGET | BASE_ADDR |
+ | | | (bits 39:16 of VRAM address) |
+ +-------+--------+--------------------------------------+
+
+ BASE_ADDR field (bits 23:0):
+ - Contains bits [39:16] of the target VRAM address
+ - Provides 40-bit (1TB) address space coverage
+ - Must be programmed with 64KB-aligned addresses
+
+ TARGET field (bits 25:24):
+ - 0x0: VRAM (Video Memory)
+ - 0x1: SYS_MEM_COH (Coherent System Memory)
+ - 0x2: SYS_MEM_NONCOH (Non-coherent System Memory)
+ - 0x3: Reserved
+
+ .. note::
+ Nova only uses TARGET=VRAM (0x0) for video memory access. The SYS_MEM
+ target values are documented here for hardware completeness but are
+ not used by the driver.
+
+64KB Alignment Requirement
+---------------------------
+
+The PRAMIN window must be aligned to 64KB boundaries in VRAM. This is enforced
+by the ``BASE_ADDR`` field representing bits [39:16] of the target address::
+
+ VRAM Address Calculation:
+ actual_vram_addr = (BASE_ADDR << 16) + pramin_offset
+ Where:
+ - BASE_ADDR: 24-bit value from NV_PBUS_BAR0_WINDOW[23:0]
+ - pramin_offset: 20-bit offset within the PRAMIN window [0x00000-0xFFFFF]
+
+ Example Window Positioning:
+ +---------------------------------------------------------+
+ | VRAM Space |
+ | |
+ | 0x000000000 +-----------------+ <-- 64KB aligned |
+ | | PRAMIN Window | |
+ | | (1MB) | |
+ | 0x0000FFFFF +-----------------+ |
+ | |
+ | | ^ |
+ | | | Window can slide |
+ | v | to any 64KB-aligned boundary |
+ | |
+ | 0x123400000 +-----------------+ <-- 64KB aligned |
+ | | PRAMIN Window | |
+ | | (1MB) | |
+ | 0x1234FFFFF +-----------------+ |
+ | |
+ | ... |
+ | |
+ | 0x7FFFF0000 +-----------------+ <-- 64KB aligned |
+ | | PRAMIN Window | |
+ | | (1MB) | |
+ | 0x7FFFFFFFF +-----------------+ |
+ +---------------------------------------------------------+
diff --git a/Documentation/gpu/nova/index.rst b/Documentation/gpu/nova/index.rst
index e39cb3163581..b8254b1ffe2a 100644
--- a/Documentation/gpu/nova/index.rst
+++ b/Documentation/gpu/nova/index.rst
@@ -32,3 +32,4 @@ vGPU manager VFIO driver and the nova-drm driver.
core/devinit
core/fwsec
core/falcon
+ core/pramin
--
2.34.1
^ permalink raw reply related
* [PATCH v8 06/25] gpu: nova-core: mm: Add support to use PRAMIN windows to write to VRAM
From: Joel Fernandes @ 2026-02-24 22:53 UTC (permalink / raw)
To: linux-kernel
Cc: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Dave Airlie, Daniel Almeida, Koen Koning,
dri-devel, nouveau, rust-for-linux, Nikola Djukic,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jonathan Corbet, Alex Deucher,
Christian König, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Huang Rui, Matthew Auld, Matthew Brost,
Lucas De Marchi, Thomas Hellström, Helge Deller, Alex Gaynor,
Boqun Feng, John Hubbard, Alistair Popple, Timur Tabi, Edwin Peer,
Alexandre Courbot, Andrea Righi, Andy Ritger, Zhi Wang,
Balbir Singh, Philipp Stanner, Elle Rhumsaa, alexeyi,
Eliot Courtney, joel, linux-doc, amd-gfx, intel-gfx, intel-xe,
linux-fbdev, Joel Fernandes
In-Reply-To: <20260224225323.3312204-1-joelagnelf@nvidia.com>
PRAMIN apertures are a crucial mechanism to direct read/write to VRAM.
Add support for the same.
Cc: Nikola Djukic <ndjukic@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
drivers/gpu/nova-core/mm.rs | 5 +
drivers/gpu/nova-core/mm/pramin.rs | 292 +++++++++++++++++++++++++++++
drivers/gpu/nova-core/nova_core.rs | 1 +
drivers/gpu/nova-core/regs.rs | 5 +
4 files changed, 303 insertions(+)
create mode 100644 drivers/gpu/nova-core/mm.rs
create mode 100644 drivers/gpu/nova-core/mm/pramin.rs
diff --git a/drivers/gpu/nova-core/mm.rs b/drivers/gpu/nova-core/mm.rs
new file mode 100644
index 000000000000..7a5dd4220c67
--- /dev/null
+++ b/drivers/gpu/nova-core/mm.rs
@@ -0,0 +1,5 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Memory management subsystems for nova-core.
+
+pub(crate) mod pramin;
diff --git a/drivers/gpu/nova-core/mm/pramin.rs b/drivers/gpu/nova-core/mm/pramin.rs
new file mode 100644
index 000000000000..04b652d3ee4f
--- /dev/null
+++ b/drivers/gpu/nova-core/mm/pramin.rs
@@ -0,0 +1,292 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! Direct VRAM access through the PRAMIN aperture.
+//!
+//! PRAMIN provides a 1MB sliding window into VRAM through BAR0, allowing the CPU to access
+//! video memory directly. Access is managed through a two-level API:
+//!
+//! - [`Pramin`]: The parent object that owns the BAR0 reference and synchronization lock.
+//! - [`PraminWindow`]: A guard object that holds exclusive PRAMIN access for its lifetime.
+//!
+//! The PRAMIN aperture is a 1MB region at BAR0 + 0x700000 for all GPUs. The window base is
+//! controlled by the `NV_PBUS_BAR0_WINDOW` register and must be 64KB aligned.
+//!
+//! # Examples
+//!
+//! ## Basic read/write
+//!
+//! ```no_run
+//! use crate::driver::Bar0;
+//! use crate::mm::pramin;
+//! use kernel::devres::Devres;
+//! use kernel::prelude::*;
+//! use kernel::sync::Arc;
+//!
+//! fn example(devres_bar: Arc<Devres<Bar0>>) -> Result<()> {
+//! let pramin = Arc::pin_init(pramin::Pramin::new(devres_bar)?, GFP_KERNEL)?;
+//! let mut window = pramin.window()?;
+//!
+//! // Write and read back.
+//! window.try_write32(0x100, 0xDEADBEEF)?;
+//! let val = window.try_read32(0x100)?;
+//! assert_eq!(val, 0xDEADBEEF);
+//!
+//! Ok(())
+//! // Original window position restored on drop.
+//! }
+//! ```
+//!
+//! ## Auto-repositioning across VRAM regions
+//!
+//! ```no_run
+//! use crate::driver::Bar0;
+//! use crate::mm::pramin;
+//! use kernel::devres::Devres;
+//! use kernel::prelude::*;
+//! use kernel::sync::Arc;
+//!
+//! fn example(devres_bar: Arc<Devres<Bar0>>) -> Result<()> {
+//! let pramin = Arc::pin_init(pramin::Pramin::new(devres_bar)?, GFP_KERNEL)?;
+//! let mut window = pramin.window()?;
+//!
+//! // Access first 1MB region.
+//! window.try_write32(0x100, 0x11111111)?;
+//!
+//! // Access at 2MB - window auto-repositions.
+//! window.try_write32(0x200000, 0x22222222)?;
+//!
+//! // Back to first region - window repositions again.
+//! let val = window.try_read32(0x100)?;
+//! assert_eq!(val, 0x11111111);
+//!
+//! Ok(())
+//! }
+//! ```
+
+#![expect(unused)]
+
+use crate::{
+ driver::Bar0,
+ num::u64_as_usize,
+ regs, //
+};
+
+use kernel::bits::genmask_u64;
+use kernel::devres::Devres;
+use kernel::io::Io;
+use kernel::new_mutex;
+use kernel::prelude::*;
+use kernel::ptr::{
+ Alignable,
+ Alignment, //
+};
+use kernel::sizes::{
+ SZ_1M,
+ SZ_64K, //
+};
+use kernel::sync::{
+ lock::mutex::MutexGuard,
+ Arc,
+ Mutex, //
+};
+
+/// PRAMIN aperture base offset in BAR0.
+const PRAMIN_BASE: usize = 0x700000;
+
+/// PRAMIN aperture size (1MB).
+const PRAMIN_SIZE: usize = SZ_1M;
+
+/// 64KB alignment for window base.
+const WINDOW_ALIGN: Alignment = Alignment::new::<SZ_64K>();
+
+/// Maximum addressable VRAM offset (40-bit address space).
+///
+/// The `NV_PBUS_BAR0_WINDOW` register has a 24-bit `window_base` field (bits 23:0) that stores
+/// bits [39:16] of the target VRAM address. This limits the addressable space to 2^40 bytes.
+const MAX_VRAM_OFFSET: usize = u64_as_usize(genmask_u64(0..=39));
+
+/// Generate a PRAMIN read accessor.
+macro_rules! define_pramin_read {
+ ($name:ident, $ty:ty) => {
+ #[doc = concat!("Read a `", stringify!($ty), "` from VRAM at the given offset.")]
+ pub(crate) fn $name(&mut self, vram_offset: usize) -> Result<$ty> {
+ // Compute window parameters without bar reference.
+ let (bar_offset, new_base) =
+ self.compute_window(vram_offset, ::core::mem::size_of::<$ty>())?;
+
+ // Update window base if needed and perform read.
+ let bar = self.bar.try_access().ok_or(ENODEV)?;
+ if let Some(base) = new_base {
+ Self::write_window_base(&bar, base);
+ self.state.current_base = base;
+ }
+ bar.$name(bar_offset)
+ }
+ };
+}
+
+/// Generate a PRAMIN write accessor.
+macro_rules! define_pramin_write {
+ ($name:ident, $ty:ty) => {
+ #[doc = concat!("Write a `", stringify!($ty), "` to VRAM at the given offset.")]
+ pub(crate) fn $name(&mut self, vram_offset: usize, value: $ty) -> Result {
+ // Compute window parameters without bar reference.
+ let (bar_offset, new_base) =
+ self.compute_window(vram_offset, ::core::mem::size_of::<$ty>())?;
+
+ // Update window base if needed and perform write.
+ let bar = self.bar.try_access().ok_or(ENODEV)?;
+ if let Some(base) = new_base {
+ Self::write_window_base(&bar, base);
+ self.state.current_base = base;
+ }
+ bar.$name(value, bar_offset)
+ }
+ };
+}
+
+/// PRAMIN state protected by mutex.
+struct PraminState {
+ current_base: usize,
+}
+
+/// PRAMIN aperture manager.
+///
+/// Call [`Pramin::window()`] to acquire exclusive PRAMIN access.
+#[pin_data]
+pub(crate) struct Pramin {
+ bar: Arc<Devres<Bar0>>,
+ /// PRAMIN aperture state, protected by a mutex.
+ ///
+ /// # Safety
+ ///
+ /// This lock is acquired during the DMA fence signalling critical path.
+ /// It must NEVER be held across any reclaimable CPU memory / allocations
+ /// (`GFP_KERNEL`), because the memory reclaim path can call
+ /// `dma_fence_wait()`, which would deadlock with this lock held.
+ #[pin]
+ state: Mutex<PraminState>,
+}
+
+impl Pramin {
+ /// Create a pin-initializer for PRAMIN.
+ pub(crate) fn new(bar: Arc<Devres<Bar0>>) -> Result<impl PinInit<Self>> {
+ let bar_access = bar.try_access().ok_or(ENODEV)?;
+ let current_base = Self::try_read_window_base(&bar_access)?;
+
+ Ok(pin_init!(Self {
+ bar,
+ state <- new_mutex!(PraminState { current_base }, "pramin_state"),
+ }))
+ }
+
+ /// Acquire exclusive PRAMIN access.
+ ///
+ /// Returns a [`PraminWindow`] guard that provides VRAM read/write accessors.
+ /// The [`PraminWindow`] is exclusive and only one can exist at a time.
+ pub(crate) fn window(&self) -> Result<PraminWindow<'_>> {
+ let state = self.state.lock();
+ let saved_base = state.current_base;
+ Ok(PraminWindow {
+ bar: self.bar.clone(),
+ state,
+ saved_base,
+ })
+ }
+
+ /// Read the current window base from the BAR0_WINDOW register.
+ fn try_read_window_base(bar: &Bar0) -> Result<usize> {
+ let reg = regs::NV_PBUS_BAR0_WINDOW::read(bar);
+ let base = u64::from(reg.window_base());
+ let shifted = base.checked_shl(16).ok_or(EOVERFLOW)?;
+ shifted.try_into().map_err(|_| EOVERFLOW)
+ }
+}
+
+/// PRAMIN window guard for direct VRAM access.
+///
+/// This guard holds exclusive access to the PRAMIN aperture. The window auto-repositions
+/// when accessing VRAM offsets outside the current 1MB range. Original window position
+/// is saved on creation and restored on drop.
+///
+/// Only one [`PraminWindow`] can exist at a time per [`Pramin`] instance (enforced by the
+/// internal `MutexGuard`).
+pub(crate) struct PraminWindow<'a> {
+ bar: Arc<Devres<Bar0>>,
+ state: MutexGuard<'a, PraminState>,
+ saved_base: usize,
+}
+
+impl PraminWindow<'_> {
+ /// Write a new window base to the BAR0_WINDOW register.
+ fn write_window_base(bar: &Bar0, base: usize) {
+ // CAST:
+ // - We have guaranteed that the base is within the addressable range (40-bits).
+ // - After >> 16, a 40-bit aligned base becomes 24 bits, which fits in u32.
+ regs::NV_PBUS_BAR0_WINDOW::default()
+ .set_window_base((base >> 16) as u32)
+ .write(bar);
+ }
+
+ /// Compute window parameters for a VRAM access.
+ ///
+ /// Returns (`bar_offset`, `new_base`) where:
+ /// - `bar_offset`: The BAR0 offset to use for the access.
+ /// - `new_base`: `Some(base)` if window needs repositioning, `None` otherwise.
+ fn compute_window(
+ &self,
+ vram_offset: usize,
+ access_size: usize,
+ ) -> Result<(usize, Option<usize>)> {
+ // Validate VRAM offset is within addressable range (40-bit address space).
+ let end_offset = vram_offset.checked_add(access_size).ok_or(EINVAL)?;
+ if end_offset > MAX_VRAM_OFFSET + 1 {
+ return Err(EINVAL);
+ }
+
+ // Calculate which 64KB-aligned base we need.
+ let needed_base = vram_offset.align_down(WINDOW_ALIGN);
+
+ // Calculate offset within the window.
+ let offset_in_window = vram_offset - needed_base;
+
+ // Check if access fits in 1MB window from this base.
+ if offset_in_window + access_size > PRAMIN_SIZE {
+ return Err(EINVAL);
+ }
+
+ // Return bar offset and whether window needs repositioning.
+ let new_base = if self.state.current_base != needed_base {
+ Some(needed_base)
+ } else {
+ None
+ };
+
+ Ok((PRAMIN_BASE + offset_in_window, new_base))
+ }
+
+ define_pramin_read!(try_read8, u8);
+ define_pramin_read!(try_read16, u16);
+ define_pramin_read!(try_read32, u32);
+ define_pramin_read!(try_read64, u64);
+
+ define_pramin_write!(try_write8, u8);
+ define_pramin_write!(try_write16, u16);
+ define_pramin_write!(try_write32, u32);
+ define_pramin_write!(try_write64, u64);
+}
+
+impl Drop for PraminWindow<'_> {
+ fn drop(&mut self) {
+ // Restore the original window base if it changed.
+ if self.state.current_base != self.saved_base {
+ if let Some(bar) = self.bar.try_access() {
+ Self::write_window_base(&bar, self.saved_base);
+
+ // Update state to reflect the restored base.
+ self.state.current_base = self.saved_base;
+ }
+ }
+ // MutexGuard drops automatically, releasing the lock.
+ }
+}
diff --git a/drivers/gpu/nova-core/nova_core.rs b/drivers/gpu/nova-core/nova_core.rs
index c1121e7c64c5..3de00db3279e 100644
--- a/drivers/gpu/nova-core/nova_core.rs
+++ b/drivers/gpu/nova-core/nova_core.rs
@@ -13,6 +13,7 @@
mod gfw;
mod gpu;
mod gsp;
+mod mm;
mod num;
mod regs;
mod sbuffer;
diff --git a/drivers/gpu/nova-core/regs.rs b/drivers/gpu/nova-core/regs.rs
index ea0d32f5396c..d0982e346f74 100644
--- a/drivers/gpu/nova-core/regs.rs
+++ b/drivers/gpu/nova-core/regs.rs
@@ -102,6 +102,11 @@ fn fmt(&self, f: &mut kernel::fmt::Formatter<'_>) -> kernel::fmt::Result {
31:16 frts_err_code as u16;
});
+register!(NV_PBUS_BAR0_WINDOW @ 0x00001700, "BAR0 window control for PRAMIN access" {
+ 25:24 target as u8, "Target memory (0=VRAM, 1=SYS_MEM_COH, 2=SYS_MEM_NONCOH)";
+ 23:0 window_base as u32, "Window base address (bits 39:16 of FB addr)";
+});
+
// PFB
// The following two registers together hold the physical system memory address that is used by the
--
2.34.1
^ permalink raw reply related
* [PATCH v8 05/25] gpu: nova-core: fb: Add usable_vram field to FbLayout
From: Joel Fernandes @ 2026-02-24 22:53 UTC (permalink / raw)
To: linux-kernel
Cc: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Dave Airlie, Daniel Almeida, Koen Koning,
dri-devel, nouveau, rust-for-linux, Nikola Djukic,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jonathan Corbet, Alex Deucher,
Christian König, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Huang Rui, Matthew Auld, Matthew Brost,
Lucas De Marchi, Thomas Hellström, Helge Deller, Alex Gaynor,
Boqun Feng, John Hubbard, Alistair Popple, Timur Tabi, Edwin Peer,
Alexandre Courbot, Andrea Righi, Andy Ritger, Zhi Wang,
Balbir Singh, Philipp Stanner, Elle Rhumsaa, alexeyi,
Eliot Courtney, joel, linux-doc, amd-gfx, intel-gfx, intel-xe,
linux-fbdev, Joel Fernandes
In-Reply-To: <20260224225323.3312204-1-joelagnelf@nvidia.com>
Add usable_vram field to FbLayout to store the usable VRAM region for
driver allocations. This is populated after GSP boot with the region
extracted from GSP's fbRegionInfoParams.
FbLayout is now a two-phase structure:
1. new() computes firmware layout from hardware
2. set_usable_vram() populates usable region from GSP
The new usable_vram field represents the actual usable VRAM region
(~23.7GB on a 24GB GPU GA102 Ampere GPU).
Cc: Nikola Djukic <ndjukic@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
drivers/gpu/nova-core/fb.rs | 26 +++++++++++++++++++++++++-
1 file changed, 25 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/nova-core/fb.rs b/drivers/gpu/nova-core/fb.rs
index c62abcaed547..d4d0f50d7afd 100644
--- a/drivers/gpu/nova-core/fb.rs
+++ b/drivers/gpu/nova-core/fb.rs
@@ -97,6 +97,10 @@ pub(crate) fn unregister(&self, bar: &Bar0) {
/// Layout of the GPU framebuffer memory.
///
/// Contains ranges of GPU memory reserved for a given purpose during the GSP boot process.
+///
+/// This structure is populated in 2 steps:
+/// 1. [`FbLayout::new()`] computes firmware layout from hardware.
+/// 2. [`FbLayout::set_usable_vram()`] populates usable region from GSP response.
#[derive(Debug)]
pub(crate) struct FbLayout {
/// Range of the framebuffer. Starts at `0`.
@@ -111,10 +115,16 @@ pub(crate) struct FbLayout {
pub(crate) elf: Range<u64>,
/// WPR2 heap.
pub(crate) wpr2_heap: Range<u64>,
- /// WPR2 region range, starting with an instance of `GspFwWprMeta`.
+ /// WPR2 region range, starting with an instance of [`GspFwWprMeta`].
pub(crate) wpr2: Range<u64>,
+ /// Non-WPR heap carved before WPR2, used by GSP firmware.
pub(crate) heap: Range<u64>,
pub(crate) vf_partition_count: u8,
+ /// Usable VRAM region for driver allocations (from GSP `fbRegionInfoParams`).
+ ///
+ /// Initially [`None`], populated after GSP boot with usable region info.
+ #[allow(dead_code)]
+ pub(crate) usable_vram: Option<Range<u64>>,
}
impl FbLayout {
@@ -212,6 +222,20 @@ pub(crate) fn new(chipset: Chipset, bar: &Bar0, gsp_fw: &GspFirmware) -> Result<
wpr2,
heap,
vf_partition_count: 0,
+ usable_vram: None,
})
}
+
+ /// Set the usable VRAM region from GSP response.
+ ///
+ /// Called after GSP boot with the first usable region extracted from
+ /// GSP's `fbRegionInfoParams`. Usable regions are those that:
+ /// - Are not reserved for firmware internal use.
+ /// - Are not protected (hardware-enforced access restrictions).
+ /// - Support compression (can use GPU memory compression for bandwidth).
+ /// - Support ISO (isochronous memory for display requiring guaranteed bandwidth).
+ #[allow(dead_code)]
+ pub(crate) fn set_usable_vram(&mut self, base: u64, size: u64) {
+ self.usable_vram = Some(base..base.saturating_add(size));
+ }
}
--
2.34.1
^ permalink raw reply related
* [PATCH v8 04/25] gpu: nova-core: gsp: Extract usable FB region from GSP
From: Joel Fernandes @ 2026-02-24 22:53 UTC (permalink / raw)
To: linux-kernel
Cc: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Dave Airlie, Daniel Almeida, Koen Koning,
dri-devel, nouveau, rust-for-linux, Nikola Djukic,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jonathan Corbet, Alex Deucher,
Christian König, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Huang Rui, Matthew Auld, Matthew Brost,
Lucas De Marchi, Thomas Hellström, Helge Deller, Alex Gaynor,
Boqun Feng, John Hubbard, Alistair Popple, Timur Tabi, Edwin Peer,
Alexandre Courbot, Andrea Righi, Andy Ritger, Zhi Wang,
Balbir Singh, Philipp Stanner, Elle Rhumsaa, alexeyi,
Eliot Courtney, joel, linux-doc, amd-gfx, intel-gfx, intel-xe,
linux-fbdev, Joel Fernandes
In-Reply-To: <20260224225323.3312204-1-joelagnelf@nvidia.com>
Add first_usable_fb_region() to GspStaticConfigInfo to extract the first
usable FB region from GSP's fbRegionInfoParams. Usable regions are those
that are not reserved or protected.
The extracted region is stored in GetGspStaticInfoReply and exposed via
usable_fb_region() API for use by the memory subsystem.
Cc: Nikola Djukic <ndjukic@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
drivers/gpu/nova-core/gsp/commands.rs | 12 ++++++++-
drivers/gpu/nova-core/gsp/fw/commands.rs | 32 ++++++++++++++++++++++++
2 files changed, 43 insertions(+), 1 deletion(-)
diff --git a/drivers/gpu/nova-core/gsp/commands.rs b/drivers/gpu/nova-core/gsp/commands.rs
index 8f270eca33be..c31046df3acf 100644
--- a/drivers/gpu/nova-core/gsp/commands.rs
+++ b/drivers/gpu/nova-core/gsp/commands.rs
@@ -186,9 +186,11 @@ fn init(&self) -> impl Init<Self::Command, Self::InitError> {
}
}
-/// The reply from the GSP to the [`GetGspInfo`] command.
+/// The reply from the GSP to the [`GetGspStaticInfo`] command.
pub(crate) struct GetGspStaticInfoReply {
gpu_name: [u8; 64],
+ /// First usable FB region `(base, size)` for memory allocation.
+ usable_fb_region: Option<(u64, u64)>,
}
impl MessageFromGsp for GetGspStaticInfoReply {
@@ -202,6 +204,7 @@ fn read(
) -> Result<Self, Self::InitError> {
Ok(GetGspStaticInfoReply {
gpu_name: msg.gpu_name_str(),
+ usable_fb_region: msg.first_usable_fb_region(),
})
}
}
@@ -228,6 +231,13 @@ pub(crate) fn gpu_name(&self) -> core::result::Result<&str, GpuNameError> {
.to_str()
.map_err(GpuNameError::InvalidUtf8)
}
+
+ /// Returns the usable FB region `(base, size)` for driver allocation which is
+ /// already retrieved from the GSP.
+ #[expect(dead_code)]
+ pub(crate) fn usable_fb_region(&self) -> Option<(u64, u64)> {
+ self.usable_fb_region
+ }
}
/// Send the [`GetGspInfo`] command and awaits for its reply.
diff --git a/drivers/gpu/nova-core/gsp/fw/commands.rs b/drivers/gpu/nova-core/gsp/fw/commands.rs
index 21be44199693..ff771a4aba4f 100644
--- a/drivers/gpu/nova-core/gsp/fw/commands.rs
+++ b/drivers/gpu/nova-core/gsp/fw/commands.rs
@@ -5,6 +5,7 @@
use kernel::{device, pci};
use crate::gsp::GSP_PAGE_SIZE;
+use crate::num::IntoSafeCast;
use super::bindings;
@@ -114,6 +115,37 @@ impl GspStaticConfigInfo {
pub(crate) fn gpu_name_str(&self) -> [u8; 64] {
self.0.gpuNameString
}
+
+ /// Extract the first usable FB region from GSP firmware data.
+ ///
+ /// Returns the first region suitable for driver memory allocation as a `(base, size)` tuple.
+ /// Usable regions are those that:
+ /// - Are not reserved for firmware internal use.
+ /// - Are not protected (hardware-enforced access restrictions).
+ /// - Support compression (can use GPU memory compression for bandwidth).
+ /// - Support ISO (isochronous memory for display requiring guaranteed bandwidth).
+ pub(crate) fn first_usable_fb_region(&self) -> Option<(u64, u64)> {
+ let fb_info = &self.0.fbRegionInfoParams;
+ for i in 0..fb_info.numFBRegions.into_safe_cast() {
+ if let Some(reg) = fb_info.fbRegion.get(i) {
+ // Skip malformed regions where limit < base.
+ if reg.limit < reg.base {
+ continue;
+ }
+
+ // Filter: not reserved, not protected, supports compression and ISO.
+ if reg.reserved == 0
+ && reg.bProtected == 0
+ && reg.supportCompressed != 0
+ && reg.supportISO != 0
+ {
+ let size = reg.limit - reg.base + 1;
+ return Some((reg.base, size));
+ }
+ }
+ }
+ None
+ }
}
// SAFETY: Padding is explicit and will not contain uninitialized data.
--
2.34.1
^ permalink raw reply related
* [PATCH v8 03/25] gpu: nova-core: gsp: Return GspStaticInfo and FbLayout from boot()
From: Joel Fernandes @ 2026-02-24 22:53 UTC (permalink / raw)
To: linux-kernel
Cc: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Dave Airlie, Daniel Almeida, Koen Koning,
dri-devel, nouveau, rust-for-linux, Nikola Djukic,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jonathan Corbet, Alex Deucher,
Christian König, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Huang Rui, Matthew Auld, Matthew Brost,
Lucas De Marchi, Thomas Hellström, Helge Deller, Alex Gaynor,
Boqun Feng, John Hubbard, Alistair Popple, Timur Tabi, Edwin Peer,
Alexandre Courbot, Andrea Righi, Andy Ritger, Zhi Wang,
Balbir Singh, Philipp Stanner, Elle Rhumsaa, alexeyi,
Eliot Courtney, joel, linux-doc, amd-gfx, intel-gfx, intel-xe,
linux-fbdev, Joel Fernandes
In-Reply-To: <20260224225323.3312204-1-joelagnelf@nvidia.com>
Refactor the GSP boot function to return the GspStaticInfo and FbLayout.
This enables access required for memory management initialization to:
- bar1_pde_base: BAR1 page directory base.
- bar2_pde_base: BAR2 page directory base.
- usable memory regions in vidmem.
Cc: Nikola Djukic <ndjukic@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
drivers/gpu/nova-core/gpu.rs | 9 +++++++--
drivers/gpu/nova-core/gsp/boot.rs | 15 ++++++++++++---
2 files changed, 19 insertions(+), 5 deletions(-)
diff --git a/drivers/gpu/nova-core/gpu.rs b/drivers/gpu/nova-core/gpu.rs
index 9b042ef1a308..5e084ec7c926 100644
--- a/drivers/gpu/nova-core/gpu.rs
+++ b/drivers/gpu/nova-core/gpu.rs
@@ -18,7 +18,10 @@
},
fb::SysmemFlush,
gfw,
- gsp::Gsp,
+ gsp::{
+ commands::GetGspStaticInfoReply,
+ Gsp, //
+ },
regs,
};
@@ -252,6 +255,8 @@ pub(crate) struct Gpu {
/// GSP runtime data. Temporarily an empty placeholder.
#[pin]
gsp: Gsp,
+ /// Static GPU information from GSP.
+ gsp_static_info: GetGspStaticInfoReply,
}
impl Gpu {
@@ -283,7 +288,7 @@ pub(crate) fn new<'a>(
gsp <- Gsp::new(pdev),
- _: { gsp.boot(pdev, bar, spec.chipset, gsp_falcon, sec2_falcon)? },
+ gsp_static_info: { gsp.boot(pdev, bar, spec.chipset, gsp_falcon, sec2_falcon)?.0 },
bar: devres_bar,
})
diff --git a/drivers/gpu/nova-core/gsp/boot.rs b/drivers/gpu/nova-core/gsp/boot.rs
index be427fe26a58..7a4a0c759267 100644
--- a/drivers/gpu/nova-core/gsp/boot.rs
+++ b/drivers/gpu/nova-core/gsp/boot.rs
@@ -32,7 +32,10 @@
},
gpu::Chipset,
gsp::{
- commands,
+ commands::{
+ self,
+ GetGspStaticInfoReply, //
+ },
sequencer::{
GspSequencer,
GspSequencerParams, //
@@ -127,6 +130,12 @@ fn run_fwsec_frts(
/// structures that the GSP will use at runtime.
///
/// Upon return, the GSP is up and running, and its runtime object given as return value.
+ ///
+ /// Returns a tuple containing:
+ /// - [`GetGspStaticInfoReply`]: Static GPU information from GSP, including the BAR1 page
+ /// directory base address needed for memory management.
+ /// - [`FbLayout`]: Frame buffer layout computed during boot, containing memory regions
+ /// required for [`GpuMm`] initialization.
pub(crate) fn boot(
mut self: Pin<&mut Self>,
pdev: &pci::Device<device::Bound>,
@@ -134,7 +143,7 @@ pub(crate) fn boot(
chipset: Chipset,
gsp_falcon: &Falcon<Gsp>,
sec2_falcon: &Falcon<Sec2>,
- ) -> Result {
+ ) -> Result<(GetGspStaticInfoReply, FbLayout)> {
let dev = pdev.as_ref();
let bios = Vbios::new(dev, bar)?;
@@ -243,6 +252,6 @@ pub(crate) fn boot(
Err(e) => dev_warn!(pdev.as_ref(), "GPU name unavailable: {:?}\n", e),
}
- Ok(())
+ Ok((info, fb_layout))
}
}
--
2.34.1
^ permalink raw reply related
* [PATCH v8 02/25] gpu: nova-core: Kconfig: Sort select statements alphabetically
From: Joel Fernandes @ 2026-02-24 22:53 UTC (permalink / raw)
To: linux-kernel
Cc: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Dave Airlie, Daniel Almeida, Koen Koning,
dri-devel, nouveau, rust-for-linux, Nikola Djukic,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jonathan Corbet, Alex Deucher,
Christian König, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Huang Rui, Matthew Auld, Matthew Brost,
Lucas De Marchi, Thomas Hellström, Helge Deller, Alex Gaynor,
Boqun Feng, John Hubbard, Alistair Popple, Timur Tabi, Edwin Peer,
Alexandre Courbot, Andrea Righi, Andy Ritger, Zhi Wang,
Balbir Singh, Philipp Stanner, Elle Rhumsaa, alexeyi,
Eliot Courtney, joel, linux-doc, amd-gfx, intel-gfx, intel-xe,
linux-fbdev, Joel Fernandes
In-Reply-To: <20260224225323.3312204-1-joelagnelf@nvidia.com>
Reorder the select statements in NOVA_CORE Kconfig to be in
alphabetical order.
Suggested-by: Danilo Krummrich <dakr@kernel.org>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
drivers/gpu/nova-core/Kconfig | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/nova-core/Kconfig b/drivers/gpu/nova-core/Kconfig
index 809485167aff..6513007bf66f 100644
--- a/drivers/gpu/nova-core/Kconfig
+++ b/drivers/gpu/nova-core/Kconfig
@@ -3,9 +3,9 @@ config NOVA_CORE
depends on 64BIT
depends on PCI
depends on RUST
- select RUST_FW_LOADER_ABSTRACTIONS
select AUXILIARY_BUS
select GPU_BUDDY
+ select RUST_FW_LOADER_ABSTRACTIONS
default n
help
Choose this if you want to build the Nova Core driver for Nvidia
--
2.34.1
^ permalink raw reply related
* [PATCH v8 01/25] gpu: nova-core: Select GPU_BUDDY for VRAM allocation
From: Joel Fernandes @ 2026-02-24 22:52 UTC (permalink / raw)
To: linux-kernel
Cc: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Dave Airlie, Daniel Almeida, Koen Koning,
dri-devel, nouveau, rust-for-linux, Nikola Djukic,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jonathan Corbet, Alex Deucher,
Christian König, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Huang Rui, Matthew Auld, Matthew Brost,
Lucas De Marchi, Thomas Hellström, Helge Deller, Alex Gaynor,
Boqun Feng, John Hubbard, Alistair Popple, Timur Tabi, Edwin Peer,
Alexandre Courbot, Andrea Righi, Andy Ritger, Zhi Wang,
Balbir Singh, Philipp Stanner, Elle Rhumsaa, alexeyi,
Eliot Courtney, joel, linux-doc, amd-gfx, intel-gfx, intel-xe,
linux-fbdev, Joel Fernandes
In-Reply-To: <20260224225323.3312204-1-joelagnelf@nvidia.com>
nova-core will use the GPU buddy allocator for physical VRAM management.
Enable it in Kconfig.
Cc: Nikola Djukic <ndjukic@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
drivers/gpu/nova-core/Kconfig | 1 +
1 file changed, 1 insertion(+)
diff --git a/drivers/gpu/nova-core/Kconfig b/drivers/gpu/nova-core/Kconfig
index 527920f9c4d3..809485167aff 100644
--- a/drivers/gpu/nova-core/Kconfig
+++ b/drivers/gpu/nova-core/Kconfig
@@ -5,6 +5,7 @@ config NOVA_CORE
depends on RUST
select RUST_FW_LOADER_ABSTRACTIONS
select AUXILIARY_BUS
+ select GPU_BUDDY
default n
help
Choose this if you want to build the Nova Core driver for Nvidia
--
2.34.1
^ permalink raw reply related
* [PATCH v8 00/25] gpu: nova-core: Add memory management support
From: Joel Fernandes @ 2026-02-24 22:52 UTC (permalink / raw)
To: linux-kernel
Cc: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Dave Airlie, Daniel Almeida, Koen Koning,
dri-devel, nouveau, rust-for-linux, Nikola Djukic,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jonathan Corbet, Alex Deucher,
Christian König, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Huang Rui, Matthew Auld, Matthew Brost,
Lucas De Marchi, Thomas Hellström, Helge Deller, Alex Gaynor,
Boqun Feng, John Hubbard, Alistair Popple, Timur Tabi, Edwin Peer,
Alexandre Courbot, Andrea Righi, Andy Ritger, Zhi Wang,
Balbir Singh, Philipp Stanner, Elle Rhumsaa, alexeyi,
Eliot Courtney, joel, linux-doc, amd-gfx, intel-gfx, intel-xe,
linux-fbdev, Joel Fernandes
This series adds support for nova-core memory management, including VRAM
allocation, PRAMIN, VMM, page table walking, and BAR 1 read/writes.
These are critical for channel management, vGPU, and all other memory
management uses of nova-core.
Changes from v7 to v8:
- Incorporated "Select GPU_BUDDY for VRAM allocation" patch from the
dependency series (Alex).
- Significant patch reordering for better logical flow (GSP/FB patches
moved earlier, page table patches, Vmm, Bar1, tests) (Alex).
- Replaced several 'as' usages with into_safe_cast() (Danilo, Alex).
- Updated BAR 1 test cases to include exercising the block size API (Eliot, Danilo).
Changes from v6 to v7:
- Addressed DMA fence signalling usecase per Danilo's feedback.
Pre v6:
- Simplified PRAMIN code (John Hubbard, Alex Courbot).
- Handled different MMU versions: ver2 versus ver3 (John Hubbard).
- Added BAR1 usecase so we have user of DRM Buddy / VMM (John Hubbard).
- Iterating over clist/buddy bindings.
All patches, along with all the dependencies (including CList), can be
found at:
https://git.kernel.org/pub/scm/linux/kernel/git/jfern/linux.git (branch nova/mm)
Link to v7: https://lore.kernel.org/all/20260218212020.800836-1-joelagnelf@nvidia.com/
Joel Fernandes (25):
gpu: nova-core: Select GPU_BUDDY for VRAM allocation
gpu: nova-core: Kconfig: Sort select statements alphabetically
gpu: nova-core: gsp: Return GspStaticInfo and FbLayout from boot()
gpu: nova-core: gsp: Extract usable FB region from GSP
gpu: nova-core: fb: Add usable_vram field to FbLayout
gpu: nova-core: mm: Add support to use PRAMIN windows to write to VRAM
docs: gpu: nova-core: Document the PRAMIN aperture mechanism
gpu: nova-core: mm: Add common memory management types
gpu: nova-core: mm: Add TLB flush support
gpu: nova-core: mm: Add GpuMm centralized memory manager
gpu: nova-core: mm: Use usable VRAM region for buddy allocator
gpu: nova-core: mm: Add common types for all page table formats
gpu: nova-core: mm: Add MMU v2 page table types
gpu: nova-core: mm: Add MMU v3 page table types
gpu: nova-core: mm: Add unified page table entry wrapper enums
gpu: nova-core: mm: Add page table walker for MMU v2/v3
gpu: nova-core: mm: Add Virtual Memory Manager
gpu: nova-core: mm: Add virtual address range tracking to VMM
gpu: nova-core: mm: Add multi-page mapping API to VMM
gpu: nova-core: Add BAR1 aperture type and size constant
gpu: nova-core: gsp: Add BAR1 PDE base accessors
gpu: nova-core: mm: Add BAR1 user interface
gpu: nova-core: mm: Add BarUser to struct Gpu and create at boot
gpu: nova-core: mm: Add BAR1 memory management self-tests
gpu: nova-core: mm: Add PRAMIN aperture self-tests
Documentation/gpu/nova/core/pramin.rst | 125 ++++++
Documentation/gpu/nova/index.rst | 1 +
drivers/gpu/nova-core/Kconfig | 13 +-
drivers/gpu/nova-core/driver.rs | 9 +-
drivers/gpu/nova-core/fb.rs | 26 +-
drivers/gpu/nova-core/gpu.rs | 130 +++++-
drivers/gpu/nova-core/gsp/boot.rs | 22 +-
drivers/gpu/nova-core/gsp/commands.rs | 18 +-
drivers/gpu/nova-core/gsp/fw/commands.rs | 40 ++
drivers/gpu/nova-core/mm.rs | 245 ++++++++++
drivers/gpu/nova-core/mm/bar_user.rs | 406 +++++++++++++++++
drivers/gpu/nova-core/mm/pagetable.rs | 453 +++++++++++++++++++
drivers/gpu/nova-core/mm/pagetable/ver2.rs | 199 +++++++++
drivers/gpu/nova-core/mm/pagetable/ver3.rs | 302 +++++++++++++
drivers/gpu/nova-core/mm/pagetable/walk.rs | 218 +++++++++
drivers/gpu/nova-core/mm/pramin.rs | 453 +++++++++++++++++++
drivers/gpu/nova-core/mm/tlb.rs | 90 ++++
drivers/gpu/nova-core/mm/vmm.rs | 494 +++++++++++++++++++++
drivers/gpu/nova-core/nova_core.rs | 1 +
drivers/gpu/nova-core/regs.rs | 38 ++
20 files changed, 3273 insertions(+), 10 deletions(-)
create mode 100644 Documentation/gpu/nova/core/pramin.rst
create mode 100644 drivers/gpu/nova-core/mm.rs
create mode 100644 drivers/gpu/nova-core/mm/bar_user.rs
create mode 100644 drivers/gpu/nova-core/mm/pagetable.rs
create mode 100644 drivers/gpu/nova-core/mm/pagetable/ver2.rs
create mode 100644 drivers/gpu/nova-core/mm/pagetable/ver3.rs
create mode 100644 drivers/gpu/nova-core/mm/pagetable/walk.rs
create mode 100644 drivers/gpu/nova-core/mm/pramin.rs
create mode 100644 drivers/gpu/nova-core/mm/tlb.rs
create mode 100644 drivers/gpu/nova-core/mm/vmm.rs
base-commit: 2961f841b025fb234860bac26dfb7fa7cb0fb122
prerequisite-patch-id: f8778e0b72697243cfe40a8bfcc3ca1d66160b12
prerequisite-patch-id: 763b30c69f9806de97eb58bc8e3406feb6bf61b4
prerequisite-patch-id: 2cded1a588520cf7d08f51bf5b3646d5b3dc26bd
prerequisite-patch-id: 4933d6b86caab3e4630c92292cfe8e9d3b8f3524
prerequisite-patch-id: 9f58738611f42a330b00bd976fbcafe2b7e6d75e
prerequisite-patch-id: 07f81850399af27b61dcba81ad1bb24bcf977ac1
--
2.34.1
^ permalink raw reply
* [reference PATCH v11 2/4] gpu: Move DRM buddy allocator one level up (part two)
From: Joel Fernandes @ 2026-02-24 22:40 UTC (permalink / raw)
To: linux-kernel
Cc: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Dave Airlie, Daniel Almeida, Koen Koning,
dri-devel, nouveau, rust-for-linux, Nikola Djukic,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jonathan Corbet, Alex Deucher,
Christian König, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Huang Rui, Matthew Auld, Matthew Brost,
Lucas De Marchi, Thomas Hellström, Helge Deller, Alex Gaynor,
Boqun Feng, John Hubbard, Alistair Popple, Timur Tabi, Edwin Peer,
Alexandre Courbot, Andrea Righi, Andy Ritger, Zhi Wang,
Balbir Singh, Philipp Stanner, Elle Rhumsaa, alexeyi,
Eliot Courtney, joel, linux-doc, amd-gfx, intel-gfx, intel-xe,
linux-fbdev, Joel Fernandes
In-Reply-To: <20260224224005.3232841-1-joelagnelf@nvidia.com>
Move the DRM buddy allocator one level up so that it can be used by GPU
drivers (example, nova-core) that have usecases other than DRM (such as
VFIO vGPU support). Modify the API, structures and Kconfigs to use
"gpu_buddy" terminology. Adapt the drivers and tests to use the new API.
The commit cannot be split due to bisectability, however no functional
change is intended. Verified by running K-UNIT tests and build tested
various configurations.
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
[airlied: I've split this into two so git can find copies easier.
I've also just nuked drm_random library, that stuff needs to be done
elsewhere and only the buddy tests seem to be using it].
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
Documentation/gpu/drm-mm.rst | 6 +
MAINTAINERS | 8 +-
drivers/gpu/Kconfig | 13 +
drivers/gpu/Makefile | 1 +
drivers/gpu/buddy.c | 556 +++++++++---------
drivers/gpu/drm/Kconfig | 1 +
drivers/gpu/drm/Makefile | 2 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 2 +-
.../gpu/drm/amd/amdgpu/amdgpu_res_cursor.h | 12 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 79 +--
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h | 18 +-
drivers/gpu/drm/drm_buddy.c | 77 +++
drivers/gpu/drm/i915/i915_scatterlist.c | 8 +-
drivers/gpu/drm/i915/i915_ttm_buddy_manager.c | 55 +-
drivers/gpu/drm/i915/i915_ttm_buddy_manager.h | 4 +-
.../drm/i915/selftests/intel_memory_region.c | 20 +-
.../gpu/drm/ttm/tests/ttm_bo_validate_test.c | 4 +-
drivers/gpu/drm/ttm/tests/ttm_mock_manager.c | 18 +-
drivers/gpu/drm/ttm/tests/ttm_mock_manager.h | 2 +-
drivers/gpu/drm/xe/xe_res_cursor.h | 34 +-
drivers/gpu/drm/xe/xe_svm.c | 12 +-
drivers/gpu/drm/xe/xe_ttm_vram_mgr.c | 71 +--
drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h | 2 +-
drivers/gpu/tests/Makefile | 2 +-
drivers/gpu/tests/gpu_buddy_test.c | 412 ++++++-------
drivers/gpu/tests/gpu_random.c | 16 +-
drivers/gpu/tests/gpu_random.h | 18 +-
drivers/video/Kconfig | 1 +
include/drm/drm_buddy.h | 18 +
include/linux/gpu_buddy.h | 120 ++--
30 files changed, 853 insertions(+), 739 deletions(-)
create mode 100644 drivers/gpu/Kconfig
create mode 100644 drivers/gpu/drm/drm_buddy.c
create mode 100644 include/drm/drm_buddy.h
diff --git a/Documentation/gpu/drm-mm.rst b/Documentation/gpu/drm-mm.rst
index ceee0e663237..32fb506db05b 100644
--- a/Documentation/gpu/drm-mm.rst
+++ b/Documentation/gpu/drm-mm.rst
@@ -532,6 +532,12 @@ Buddy Allocator Function References (GPU buddy)
.. kernel-doc:: drivers/gpu/buddy.c
:export:
+DRM Buddy Specific Logging Function References
+----------------------------------------------
+
+.. kernel-doc:: drivers/gpu/drm/drm_buddy.c
+ :export:
+
DRM Cache Handling and Fast WC memcpy()
=======================================
diff --git a/MAINTAINERS b/MAINTAINERS
index 0dc318c94c99..f1e5a8011d2f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8905,15 +8905,17 @@ T: git https://gitlab.freedesktop.org/drm/misc/kernel.git
F: drivers/gpu/drm/ttm/
F: include/drm/ttm/
-DRM BUDDY ALLOCATOR
+GPU BUDDY ALLOCATOR
M: Matthew Auld <matthew.auld@intel.com>
M: Arun Pravin <arunpravin.paneerselvam@amd.com>
R: Christian Koenig <christian.koenig@amd.com>
L: dri-devel@lists.freedesktop.org
S: Maintained
T: git https://gitlab.freedesktop.org/drm/misc/kernel.git
-F: drivers/gpu/drm/drm_buddy.c
-F: drivers/gpu/drm/tests/drm_buddy_test.c
+F: drivers/gpu/drm_buddy.c
+F: drivers/gpu/buddy.c
+F: drivers/gpu/tests/gpu_buddy_test.c
+F: include/linux/gpu_buddy.h
F: include/drm/drm_buddy.h
DRM AUTOMATED TESTING
diff --git a/drivers/gpu/Kconfig b/drivers/gpu/Kconfig
new file mode 100644
index 000000000000..ebb2ad4b7ea0
--- /dev/null
+++ b/drivers/gpu/Kconfig
@@ -0,0 +1,13 @@
+# SPDX-License-Identifier: GPL-2.0
+
+config GPU_BUDDY
+ bool
+ help
+ A page based buddy allocator for GPU memory.
+
+config GPU_BUDDY_KUNIT_TEST
+ tristate "KUnit tests for GPU buddy allocator" if !KUNIT_ALL_TESTS
+ depends on GPU_BUDDY && KUNIT
+ default KUNIT_ALL_TESTS
+ help
+ KUnit tests for the GPU buddy allocator.
diff --git a/drivers/gpu/Makefile b/drivers/gpu/Makefile
index c5292ee2c852..5cd54d06e262 100644
--- a/drivers/gpu/Makefile
+++ b/drivers/gpu/Makefile
@@ -6,3 +6,4 @@ obj-y += host1x/ drm/ vga/ tests/
obj-$(CONFIG_IMX_IPUV3_CORE) += ipu-v3/
obj-$(CONFIG_TRACE_GPU_MEM) += trace/
obj-$(CONFIG_NOVA_CORE) += nova-core/
+obj-$(CONFIG_GPU_BUDDY) += buddy.o
diff --git a/drivers/gpu/buddy.c b/drivers/gpu/buddy.c
index 4cc63d961d26..603c59a2013a 100644
--- a/drivers/gpu/buddy.c
+++ b/drivers/gpu/buddy.c
@@ -11,27 +11,17 @@
#include <linux/sizes.h>
#include <linux/gpu_buddy.h>
-#include <drm/drm_print.h>
-
-enum drm_buddy_free_tree {
- DRM_BUDDY_CLEAR_TREE = 0,
- DRM_BUDDY_DIRTY_TREE,
- DRM_BUDDY_MAX_FREE_TREES,
-};
static struct kmem_cache *slab_blocks;
-#define for_each_free_tree(tree) \
- for ((tree) = 0; (tree) < DRM_BUDDY_MAX_FREE_TREES; (tree)++)
-
-static struct drm_buddy_block *drm_block_alloc(struct drm_buddy *mm,
- struct drm_buddy_block *parent,
+static struct gpu_buddy_block *gpu_block_alloc(struct gpu_buddy *mm,
+ struct gpu_buddy_block *parent,
unsigned int order,
u64 offset)
{
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
- BUG_ON(order > DRM_BUDDY_MAX_ORDER);
+ BUG_ON(order > GPU_BUDDY_MAX_ORDER);
block = kmem_cache_zalloc(slab_blocks, GFP_KERNEL);
if (!block)
@@ -43,30 +33,30 @@ static struct drm_buddy_block *drm_block_alloc(struct drm_buddy *mm,
RB_CLEAR_NODE(&block->rb);
- BUG_ON(block->header & DRM_BUDDY_HEADER_UNUSED);
+ BUG_ON(block->header & GPU_BUDDY_HEADER_UNUSED);
return block;
}
-static void drm_block_free(struct drm_buddy *mm,
- struct drm_buddy_block *block)
+static void gpu_block_free(struct gpu_buddy *mm,
+ struct gpu_buddy_block *block)
{
kmem_cache_free(slab_blocks, block);
}
-static enum drm_buddy_free_tree
-get_block_tree(struct drm_buddy_block *block)
+static enum gpu_buddy_free_tree
+get_block_tree(struct gpu_buddy_block *block)
{
- return drm_buddy_block_is_clear(block) ?
- DRM_BUDDY_CLEAR_TREE : DRM_BUDDY_DIRTY_TREE;
+ return gpu_buddy_block_is_clear(block) ?
+ GPU_BUDDY_CLEAR_TREE : GPU_BUDDY_DIRTY_TREE;
}
-static struct drm_buddy_block *
+static struct gpu_buddy_block *
rbtree_get_free_block(const struct rb_node *node)
{
- return node ? rb_entry(node, struct drm_buddy_block, rb) : NULL;
+ return node ? rb_entry(node, struct gpu_buddy_block, rb) : NULL;
}
-static struct drm_buddy_block *
+static struct gpu_buddy_block *
rbtree_last_free_block(struct rb_root *root)
{
return rbtree_get_free_block(rb_last(root));
@@ -77,33 +67,33 @@ static bool rbtree_is_empty(struct rb_root *root)
return RB_EMPTY_ROOT(root);
}
-static bool drm_buddy_block_offset_less(const struct drm_buddy_block *block,
- const struct drm_buddy_block *node)
+static bool gpu_buddy_block_offset_less(const struct gpu_buddy_block *block,
+ const struct gpu_buddy_block *node)
{
- return drm_buddy_block_offset(block) < drm_buddy_block_offset(node);
+ return gpu_buddy_block_offset(block) < gpu_buddy_block_offset(node);
}
static bool rbtree_block_offset_less(struct rb_node *block,
const struct rb_node *node)
{
- return drm_buddy_block_offset_less(rbtree_get_free_block(block),
+ return gpu_buddy_block_offset_less(rbtree_get_free_block(block),
rbtree_get_free_block(node));
}
-static void rbtree_insert(struct drm_buddy *mm,
- struct drm_buddy_block *block,
- enum drm_buddy_free_tree tree)
+static void rbtree_insert(struct gpu_buddy *mm,
+ struct gpu_buddy_block *block,
+ enum gpu_buddy_free_tree tree)
{
rb_add(&block->rb,
- &mm->free_trees[tree][drm_buddy_block_order(block)],
+ &mm->free_trees[tree][gpu_buddy_block_order(block)],
rbtree_block_offset_less);
}
-static void rbtree_remove(struct drm_buddy *mm,
- struct drm_buddy_block *block)
+static void rbtree_remove(struct gpu_buddy *mm,
+ struct gpu_buddy_block *block)
{
- unsigned int order = drm_buddy_block_order(block);
- enum drm_buddy_free_tree tree;
+ unsigned int order = gpu_buddy_block_order(block);
+ enum gpu_buddy_free_tree tree;
struct rb_root *root;
tree = get_block_tree(block);
@@ -113,42 +103,42 @@ static void rbtree_remove(struct drm_buddy *mm,
RB_CLEAR_NODE(&block->rb);
}
-static void clear_reset(struct drm_buddy_block *block)
+static void clear_reset(struct gpu_buddy_block *block)
{
- block->header &= ~DRM_BUDDY_HEADER_CLEAR;
+ block->header &= ~GPU_BUDDY_HEADER_CLEAR;
}
-static void mark_cleared(struct drm_buddy_block *block)
+static void mark_cleared(struct gpu_buddy_block *block)
{
- block->header |= DRM_BUDDY_HEADER_CLEAR;
+ block->header |= GPU_BUDDY_HEADER_CLEAR;
}
-static void mark_allocated(struct drm_buddy *mm,
- struct drm_buddy_block *block)
+static void mark_allocated(struct gpu_buddy *mm,
+ struct gpu_buddy_block *block)
{
- block->header &= ~DRM_BUDDY_HEADER_STATE;
- block->header |= DRM_BUDDY_ALLOCATED;
+ block->header &= ~GPU_BUDDY_HEADER_STATE;
+ block->header |= GPU_BUDDY_ALLOCATED;
rbtree_remove(mm, block);
}
-static void mark_free(struct drm_buddy *mm,
- struct drm_buddy_block *block)
+static void mark_free(struct gpu_buddy *mm,
+ struct gpu_buddy_block *block)
{
- enum drm_buddy_free_tree tree;
+ enum gpu_buddy_free_tree tree;
- block->header &= ~DRM_BUDDY_HEADER_STATE;
- block->header |= DRM_BUDDY_FREE;
+ block->header &= ~GPU_BUDDY_HEADER_STATE;
+ block->header |= GPU_BUDDY_FREE;
tree = get_block_tree(block);
rbtree_insert(mm, block, tree);
}
-static void mark_split(struct drm_buddy *mm,
- struct drm_buddy_block *block)
+static void mark_split(struct gpu_buddy *mm,
+ struct gpu_buddy_block *block)
{
- block->header &= ~DRM_BUDDY_HEADER_STATE;
- block->header |= DRM_BUDDY_SPLIT;
+ block->header &= ~GPU_BUDDY_HEADER_STATE;
+ block->header |= GPU_BUDDY_SPLIT;
rbtree_remove(mm, block);
}
@@ -163,10 +153,10 @@ static inline bool contains(u64 s1, u64 e1, u64 s2, u64 e2)
return s1 <= s2 && e1 >= e2;
}
-static struct drm_buddy_block *
-__get_buddy(struct drm_buddy_block *block)
+static struct gpu_buddy_block *
+__get_buddy(struct gpu_buddy_block *block)
{
- struct drm_buddy_block *parent;
+ struct gpu_buddy_block *parent;
parent = block->parent;
if (!parent)
@@ -178,19 +168,19 @@ __get_buddy(struct drm_buddy_block *block)
return parent->left;
}
-static unsigned int __drm_buddy_free(struct drm_buddy *mm,
- struct drm_buddy_block *block,
+static unsigned int __gpu_buddy_free(struct gpu_buddy *mm,
+ struct gpu_buddy_block *block,
bool force_merge)
{
- struct drm_buddy_block *parent;
+ struct gpu_buddy_block *parent;
unsigned int order;
while ((parent = block->parent)) {
- struct drm_buddy_block *buddy;
+ struct gpu_buddy_block *buddy;
buddy = __get_buddy(block);
- if (!drm_buddy_block_is_free(buddy))
+ if (!gpu_buddy_block_is_free(buddy))
break;
if (!force_merge) {
@@ -198,31 +188,31 @@ static unsigned int __drm_buddy_free(struct drm_buddy *mm,
* Check the block and its buddy clear state and exit
* the loop if they both have the dissimilar state.
*/
- if (drm_buddy_block_is_clear(block) !=
- drm_buddy_block_is_clear(buddy))
+ if (gpu_buddy_block_is_clear(block) !=
+ gpu_buddy_block_is_clear(buddy))
break;
- if (drm_buddy_block_is_clear(block))
+ if (gpu_buddy_block_is_clear(block))
mark_cleared(parent);
}
rbtree_remove(mm, buddy);
- if (force_merge && drm_buddy_block_is_clear(buddy))
- mm->clear_avail -= drm_buddy_block_size(mm, buddy);
+ if (force_merge && gpu_buddy_block_is_clear(buddy))
+ mm->clear_avail -= gpu_buddy_block_size(mm, buddy);
- drm_block_free(mm, block);
- drm_block_free(mm, buddy);
+ gpu_block_free(mm, block);
+ gpu_block_free(mm, buddy);
block = parent;
}
- order = drm_buddy_block_order(block);
+ order = gpu_buddy_block_order(block);
mark_free(mm, block);
return order;
}
-static int __force_merge(struct drm_buddy *mm,
+static int __force_merge(struct gpu_buddy *mm,
u64 start,
u64 end,
unsigned int min_order)
@@ -241,7 +231,7 @@ static int __force_merge(struct drm_buddy *mm,
struct rb_node *iter = rb_last(&mm->free_trees[tree][i]);
while (iter) {
- struct drm_buddy_block *block, *buddy;
+ struct gpu_buddy_block *block, *buddy;
u64 block_start, block_end;
block = rbtree_get_free_block(iter);
@@ -250,18 +240,18 @@ static int __force_merge(struct drm_buddy *mm,
if (!block || !block->parent)
continue;
- block_start = drm_buddy_block_offset(block);
- block_end = block_start + drm_buddy_block_size(mm, block) - 1;
+ block_start = gpu_buddy_block_offset(block);
+ block_end = block_start + gpu_buddy_block_size(mm, block) - 1;
if (!contains(start, end, block_start, block_end))
continue;
buddy = __get_buddy(block);
- if (!drm_buddy_block_is_free(buddy))
+ if (!gpu_buddy_block_is_free(buddy))
continue;
- WARN_ON(drm_buddy_block_is_clear(block) ==
- drm_buddy_block_is_clear(buddy));
+ WARN_ON(gpu_buddy_block_is_clear(block) ==
+ gpu_buddy_block_is_clear(buddy));
/*
* Advance to the next node when the current node is the buddy,
@@ -271,10 +261,10 @@ static int __force_merge(struct drm_buddy *mm,
iter = rb_prev(iter);
rbtree_remove(mm, block);
- if (drm_buddy_block_is_clear(block))
- mm->clear_avail -= drm_buddy_block_size(mm, block);
+ if (gpu_buddy_block_is_clear(block))
+ mm->clear_avail -= gpu_buddy_block_size(mm, block);
- order = __drm_buddy_free(mm, block, true);
+ order = __gpu_buddy_free(mm, block, true);
if (order >= min_order)
return 0;
}
@@ -285,9 +275,9 @@ static int __force_merge(struct drm_buddy *mm,
}
/**
- * drm_buddy_init - init memory manager
+ * gpu_buddy_init - init memory manager
*
- * @mm: DRM buddy manager to initialize
+ * @mm: GPU buddy manager to initialize
* @size: size in bytes to manage
* @chunk_size: minimum page size in bytes for our allocations
*
@@ -296,7 +286,7 @@ static int __force_merge(struct drm_buddy *mm,
* Returns:
* 0 on success, error code on failure.
*/
-int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size)
+int gpu_buddy_init(struct gpu_buddy *mm, u64 size, u64 chunk_size)
{
unsigned int i, j, root_count = 0;
u64 offset = 0;
@@ -318,9 +308,9 @@ int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size)
mm->chunk_size = chunk_size;
mm->max_order = ilog2(size) - ilog2(chunk_size);
- BUG_ON(mm->max_order > DRM_BUDDY_MAX_ORDER);
+ BUG_ON(mm->max_order > GPU_BUDDY_MAX_ORDER);
- mm->free_trees = kmalloc_array(DRM_BUDDY_MAX_FREE_TREES,
+ mm->free_trees = kmalloc_array(GPU_BUDDY_MAX_FREE_TREES,
sizeof(*mm->free_trees),
GFP_KERNEL);
if (!mm->free_trees)
@@ -340,7 +330,7 @@ int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size)
mm->n_roots = hweight64(size);
mm->roots = kmalloc_array(mm->n_roots,
- sizeof(struct drm_buddy_block *),
+ sizeof(struct gpu_buddy_block *),
GFP_KERNEL);
if (!mm->roots)
goto out_free_tree;
@@ -350,21 +340,21 @@ int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size)
* not itself a power-of-two.
*/
do {
- struct drm_buddy_block *root;
+ struct gpu_buddy_block *root;
unsigned int order;
u64 root_size;
order = ilog2(size) - ilog2(chunk_size);
root_size = chunk_size << order;
- root = drm_block_alloc(mm, NULL, order, offset);
+ root = gpu_block_alloc(mm, NULL, order, offset);
if (!root)
goto out_free_roots;
mark_free(mm, root);
BUG_ON(root_count > mm->max_order);
- BUG_ON(drm_buddy_block_size(mm, root) < chunk_size);
+ BUG_ON(gpu_buddy_block_size(mm, root) < chunk_size);
mm->roots[root_count] = root;
@@ -377,7 +367,7 @@ int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size)
out_free_roots:
while (root_count--)
- drm_block_free(mm, mm->roots[root_count]);
+ gpu_block_free(mm, mm->roots[root_count]);
kfree(mm->roots);
out_free_tree:
while (i--)
@@ -385,16 +375,16 @@ int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size)
kfree(mm->free_trees);
return -ENOMEM;
}
-EXPORT_SYMBOL(drm_buddy_init);
+EXPORT_SYMBOL(gpu_buddy_init);
/**
- * drm_buddy_fini - tear down the memory manager
+ * gpu_buddy_fini - tear down the memory manager
*
- * @mm: DRM buddy manager to free
+ * @mm: GPU buddy manager to free
*
* Cleanup memory manager resources and the freetree
*/
-void drm_buddy_fini(struct drm_buddy *mm)
+void gpu_buddy_fini(struct gpu_buddy *mm)
{
u64 root_size, size, start;
unsigned int order;
@@ -404,13 +394,13 @@ void drm_buddy_fini(struct drm_buddy *mm)
for (i = 0; i < mm->n_roots; ++i) {
order = ilog2(size) - ilog2(mm->chunk_size);
- start = drm_buddy_block_offset(mm->roots[i]);
+ start = gpu_buddy_block_offset(mm->roots[i]);
__force_merge(mm, start, start + size, order);
- if (WARN_ON(!drm_buddy_block_is_free(mm->roots[i])))
+ if (WARN_ON(!gpu_buddy_block_is_free(mm->roots[i])))
kunit_fail_current_test("buddy_fini() root");
- drm_block_free(mm, mm->roots[i]);
+ gpu_block_free(mm, mm->roots[i]);
root_size = mm->chunk_size << order;
size -= root_size;
@@ -423,31 +413,31 @@ void drm_buddy_fini(struct drm_buddy *mm)
kfree(mm->free_trees);
kfree(mm->roots);
}
-EXPORT_SYMBOL(drm_buddy_fini);
+EXPORT_SYMBOL(gpu_buddy_fini);
-static int split_block(struct drm_buddy *mm,
- struct drm_buddy_block *block)
+static int split_block(struct gpu_buddy *mm,
+ struct gpu_buddy_block *block)
{
- unsigned int block_order = drm_buddy_block_order(block) - 1;
- u64 offset = drm_buddy_block_offset(block);
+ unsigned int block_order = gpu_buddy_block_order(block) - 1;
+ u64 offset = gpu_buddy_block_offset(block);
- BUG_ON(!drm_buddy_block_is_free(block));
- BUG_ON(!drm_buddy_block_order(block));
+ BUG_ON(!gpu_buddy_block_is_free(block));
+ BUG_ON(!gpu_buddy_block_order(block));
- block->left = drm_block_alloc(mm, block, block_order, offset);
+ block->left = gpu_block_alloc(mm, block, block_order, offset);
if (!block->left)
return -ENOMEM;
- block->right = drm_block_alloc(mm, block, block_order,
+ block->right = gpu_block_alloc(mm, block, block_order,
offset + (mm->chunk_size << block_order));
if (!block->right) {
- drm_block_free(mm, block->left);
+ gpu_block_free(mm, block->left);
return -ENOMEM;
}
mark_split(mm, block);
- if (drm_buddy_block_is_clear(block)) {
+ if (gpu_buddy_block_is_clear(block)) {
mark_cleared(block->left);
mark_cleared(block->right);
clear_reset(block);
@@ -460,34 +450,34 @@ static int split_block(struct drm_buddy *mm,
}
/**
- * drm_get_buddy - get buddy address
+ * gpu_get_buddy - get buddy address
*
- * @block: DRM buddy block
+ * @block: GPU buddy block
*
* Returns the corresponding buddy block for @block, or NULL
* if this is a root block and can't be merged further.
* Requires some kind of locking to protect against
* any concurrent allocate and free operations.
*/
-struct drm_buddy_block *
-drm_get_buddy(struct drm_buddy_block *block)
+struct gpu_buddy_block *
+gpu_get_buddy(struct gpu_buddy_block *block)
{
return __get_buddy(block);
}
-EXPORT_SYMBOL(drm_get_buddy);
+EXPORT_SYMBOL(gpu_get_buddy);
/**
- * drm_buddy_reset_clear - reset blocks clear state
+ * gpu_buddy_reset_clear - reset blocks clear state
*
- * @mm: DRM buddy manager
+ * @mm: GPU buddy manager
* @is_clear: blocks clear state
*
* Reset the clear state based on @is_clear value for each block
* in the freetree.
*/
-void drm_buddy_reset_clear(struct drm_buddy *mm, bool is_clear)
+void gpu_buddy_reset_clear(struct gpu_buddy *mm, bool is_clear)
{
- enum drm_buddy_free_tree src_tree, dst_tree;
+ enum gpu_buddy_free_tree src_tree, dst_tree;
u64 root_size, size, start;
unsigned int order;
int i;
@@ -495,60 +485,60 @@ void drm_buddy_reset_clear(struct drm_buddy *mm, bool is_clear)
size = mm->size;
for (i = 0; i < mm->n_roots; ++i) {
order = ilog2(size) - ilog2(mm->chunk_size);
- start = drm_buddy_block_offset(mm->roots[i]);
+ start = gpu_buddy_block_offset(mm->roots[i]);
__force_merge(mm, start, start + size, order);
root_size = mm->chunk_size << order;
size -= root_size;
}
- src_tree = is_clear ? DRM_BUDDY_DIRTY_TREE : DRM_BUDDY_CLEAR_TREE;
- dst_tree = is_clear ? DRM_BUDDY_CLEAR_TREE : DRM_BUDDY_DIRTY_TREE;
+ src_tree = is_clear ? GPU_BUDDY_DIRTY_TREE : GPU_BUDDY_CLEAR_TREE;
+ dst_tree = is_clear ? GPU_BUDDY_CLEAR_TREE : GPU_BUDDY_DIRTY_TREE;
for (i = 0; i <= mm->max_order; ++i) {
struct rb_root *root = &mm->free_trees[src_tree][i];
- struct drm_buddy_block *block, *tmp;
+ struct gpu_buddy_block *block, *tmp;
rbtree_postorder_for_each_entry_safe(block, tmp, root, rb) {
rbtree_remove(mm, block);
if (is_clear) {
mark_cleared(block);
- mm->clear_avail += drm_buddy_block_size(mm, block);
+ mm->clear_avail += gpu_buddy_block_size(mm, block);
} else {
clear_reset(block);
- mm->clear_avail -= drm_buddy_block_size(mm, block);
+ mm->clear_avail -= gpu_buddy_block_size(mm, block);
}
rbtree_insert(mm, block, dst_tree);
}
}
}
-EXPORT_SYMBOL(drm_buddy_reset_clear);
+EXPORT_SYMBOL(gpu_buddy_reset_clear);
/**
- * drm_buddy_free_block - free a block
+ * gpu_buddy_free_block - free a block
*
- * @mm: DRM buddy manager
+ * @mm: GPU buddy manager
* @block: block to be freed
*/
-void drm_buddy_free_block(struct drm_buddy *mm,
- struct drm_buddy_block *block)
+void gpu_buddy_free_block(struct gpu_buddy *mm,
+ struct gpu_buddy_block *block)
{
- BUG_ON(!drm_buddy_block_is_allocated(block));
- mm->avail += drm_buddy_block_size(mm, block);
- if (drm_buddy_block_is_clear(block))
- mm->clear_avail += drm_buddy_block_size(mm, block);
+ BUG_ON(!gpu_buddy_block_is_allocated(block));
+ mm->avail += gpu_buddy_block_size(mm, block);
+ if (gpu_buddy_block_is_clear(block))
+ mm->clear_avail += gpu_buddy_block_size(mm, block);
- __drm_buddy_free(mm, block, false);
+ __gpu_buddy_free(mm, block, false);
}
-EXPORT_SYMBOL(drm_buddy_free_block);
+EXPORT_SYMBOL(gpu_buddy_free_block);
-static void __drm_buddy_free_list(struct drm_buddy *mm,
+static void __gpu_buddy_free_list(struct gpu_buddy *mm,
struct list_head *objects,
bool mark_clear,
bool mark_dirty)
{
- struct drm_buddy_block *block, *on;
+ struct gpu_buddy_block *block, *on;
WARN_ON(mark_dirty && mark_clear);
@@ -557,13 +547,13 @@ static void __drm_buddy_free_list(struct drm_buddy *mm,
mark_cleared(block);
else if (mark_dirty)
clear_reset(block);
- drm_buddy_free_block(mm, block);
+ gpu_buddy_free_block(mm, block);
cond_resched();
}
INIT_LIST_HEAD(objects);
}
-static void drm_buddy_free_list_internal(struct drm_buddy *mm,
+static void gpu_buddy_free_list_internal(struct gpu_buddy *mm,
struct list_head *objects)
{
/*
@@ -571,43 +561,43 @@ static void drm_buddy_free_list_internal(struct drm_buddy *mm,
* at this point. For example we might have just failed part of the
* allocation.
*/
- __drm_buddy_free_list(mm, objects, false, false);
+ __gpu_buddy_free_list(mm, objects, false, false);
}
/**
- * drm_buddy_free_list - free blocks
+ * gpu_buddy_free_list - free blocks
*
- * @mm: DRM buddy manager
+ * @mm: GPU buddy manager
* @objects: input list head to free blocks
- * @flags: optional flags like DRM_BUDDY_CLEARED
+ * @flags: optional flags like GPU_BUDDY_CLEARED
*/
-void drm_buddy_free_list(struct drm_buddy *mm,
+void gpu_buddy_free_list(struct gpu_buddy *mm,
struct list_head *objects,
unsigned int flags)
{
- bool mark_clear = flags & DRM_BUDDY_CLEARED;
+ bool mark_clear = flags & GPU_BUDDY_CLEARED;
- __drm_buddy_free_list(mm, objects, mark_clear, !mark_clear);
+ __gpu_buddy_free_list(mm, objects, mark_clear, !mark_clear);
}
-EXPORT_SYMBOL(drm_buddy_free_list);
+EXPORT_SYMBOL(gpu_buddy_free_list);
-static bool block_incompatible(struct drm_buddy_block *block, unsigned int flags)
+static bool block_incompatible(struct gpu_buddy_block *block, unsigned int flags)
{
- bool needs_clear = flags & DRM_BUDDY_CLEAR_ALLOCATION;
+ bool needs_clear = flags & GPU_BUDDY_CLEAR_ALLOCATION;
- return needs_clear != drm_buddy_block_is_clear(block);
+ return needs_clear != gpu_buddy_block_is_clear(block);
}
-static struct drm_buddy_block *
-__alloc_range_bias(struct drm_buddy *mm,
+static struct gpu_buddy_block *
+__alloc_range_bias(struct gpu_buddy *mm,
u64 start, u64 end,
unsigned int order,
unsigned long flags,
bool fallback)
{
u64 req_size = mm->chunk_size << order;
- struct drm_buddy_block *block;
- struct drm_buddy_block *buddy;
+ struct gpu_buddy_block *block;
+ struct gpu_buddy_block *buddy;
LIST_HEAD(dfs);
int err;
int i;
@@ -622,23 +612,23 @@ __alloc_range_bias(struct drm_buddy *mm,
u64 block_end;
block = list_first_entry_or_null(&dfs,
- struct drm_buddy_block,
+ struct gpu_buddy_block,
tmp_link);
if (!block)
break;
list_del(&block->tmp_link);
- if (drm_buddy_block_order(block) < order)
+ if (gpu_buddy_block_order(block) < order)
continue;
- block_start = drm_buddy_block_offset(block);
- block_end = block_start + drm_buddy_block_size(mm, block) - 1;
+ block_start = gpu_buddy_block_offset(block);
+ block_end = block_start + gpu_buddy_block_size(mm, block) - 1;
if (!overlaps(start, end, block_start, block_end))
continue;
- if (drm_buddy_block_is_allocated(block))
+ if (gpu_buddy_block_is_allocated(block))
continue;
if (block_start < start || block_end > end) {
@@ -654,17 +644,17 @@ __alloc_range_bias(struct drm_buddy *mm,
continue;
if (contains(start, end, block_start, block_end) &&
- order == drm_buddy_block_order(block)) {
+ order == gpu_buddy_block_order(block)) {
/*
* Find the free block within the range.
*/
- if (drm_buddy_block_is_free(block))
+ if (gpu_buddy_block_is_free(block))
return block;
continue;
}
- if (!drm_buddy_block_is_split(block)) {
+ if (!gpu_buddy_block_is_split(block)) {
err = split_block(mm, block);
if (unlikely(err))
goto err_undo;
@@ -684,19 +674,19 @@ __alloc_range_bias(struct drm_buddy *mm,
*/
buddy = __get_buddy(block);
if (buddy &&
- (drm_buddy_block_is_free(block) &&
- drm_buddy_block_is_free(buddy)))
- __drm_buddy_free(mm, block, false);
+ (gpu_buddy_block_is_free(block) &&
+ gpu_buddy_block_is_free(buddy)))
+ __gpu_buddy_free(mm, block, false);
return ERR_PTR(err);
}
-static struct drm_buddy_block *
-__drm_buddy_alloc_range_bias(struct drm_buddy *mm,
+static struct gpu_buddy_block *
+__gpu_buddy_alloc_range_bias(struct gpu_buddy *mm,
u64 start, u64 end,
unsigned int order,
unsigned long flags)
{
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
bool fallback = false;
block = __alloc_range_bias(mm, start, end, order,
@@ -708,12 +698,12 @@ __drm_buddy_alloc_range_bias(struct drm_buddy *mm,
return block;
}
-static struct drm_buddy_block *
-get_maxblock(struct drm_buddy *mm,
+static struct gpu_buddy_block *
+get_maxblock(struct gpu_buddy *mm,
unsigned int order,
- enum drm_buddy_free_tree tree)
+ enum gpu_buddy_free_tree tree)
{
- struct drm_buddy_block *max_block = NULL, *block = NULL;
+ struct gpu_buddy_block *max_block = NULL, *block = NULL;
struct rb_root *root;
unsigned int i;
@@ -728,8 +718,8 @@ get_maxblock(struct drm_buddy *mm,
continue;
}
- if (drm_buddy_block_offset(block) >
- drm_buddy_block_offset(max_block)) {
+ if (gpu_buddy_block_offset(block) >
+ gpu_buddy_block_offset(max_block)) {
max_block = block;
}
}
@@ -737,25 +727,25 @@ get_maxblock(struct drm_buddy *mm,
return max_block;
}
-static struct drm_buddy_block *
-alloc_from_freetree(struct drm_buddy *mm,
+static struct gpu_buddy_block *
+alloc_from_freetree(struct gpu_buddy *mm,
unsigned int order,
unsigned long flags)
{
- struct drm_buddy_block *block = NULL;
+ struct gpu_buddy_block *block = NULL;
struct rb_root *root;
- enum drm_buddy_free_tree tree;
+ enum gpu_buddy_free_tree tree;
unsigned int tmp;
int err;
- tree = (flags & DRM_BUDDY_CLEAR_ALLOCATION) ?
- DRM_BUDDY_CLEAR_TREE : DRM_BUDDY_DIRTY_TREE;
+ tree = (flags & GPU_BUDDY_CLEAR_ALLOCATION) ?
+ GPU_BUDDY_CLEAR_TREE : GPU_BUDDY_DIRTY_TREE;
- if (flags & DRM_BUDDY_TOPDOWN_ALLOCATION) {
+ if (flags & GPU_BUDDY_TOPDOWN_ALLOCATION) {
block = get_maxblock(mm, order, tree);
if (block)
/* Store the obtained block order */
- tmp = drm_buddy_block_order(block);
+ tmp = gpu_buddy_block_order(block);
} else {
for (tmp = order; tmp <= mm->max_order; ++tmp) {
/* Get RB tree root for this order and tree */
@@ -768,8 +758,8 @@ alloc_from_freetree(struct drm_buddy *mm,
if (!block) {
/* Try allocating from the other tree */
- tree = (tree == DRM_BUDDY_CLEAR_TREE) ?
- DRM_BUDDY_DIRTY_TREE : DRM_BUDDY_CLEAR_TREE;
+ tree = (tree == GPU_BUDDY_CLEAR_TREE) ?
+ GPU_BUDDY_DIRTY_TREE : GPU_BUDDY_CLEAR_TREE;
for (tmp = order; tmp <= mm->max_order; ++tmp) {
root = &mm->free_trees[tree][tmp];
@@ -782,7 +772,7 @@ alloc_from_freetree(struct drm_buddy *mm,
return ERR_PTR(-ENOSPC);
}
- BUG_ON(!drm_buddy_block_is_free(block));
+ BUG_ON(!gpu_buddy_block_is_free(block));
while (tmp != order) {
err = split_block(mm, block);
@@ -796,18 +786,18 @@ alloc_from_freetree(struct drm_buddy *mm,
err_undo:
if (tmp != order)
- __drm_buddy_free(mm, block, false);
+ __gpu_buddy_free(mm, block, false);
return ERR_PTR(err);
}
-static int __alloc_range(struct drm_buddy *mm,
+static int __alloc_range(struct gpu_buddy *mm,
struct list_head *dfs,
u64 start, u64 size,
struct list_head *blocks,
u64 *total_allocated_on_err)
{
- struct drm_buddy_block *block;
- struct drm_buddy_block *buddy;
+ struct gpu_buddy_block *block;
+ struct gpu_buddy_block *buddy;
u64 total_allocated = 0;
LIST_HEAD(allocated);
u64 end;
@@ -820,31 +810,31 @@ static int __alloc_range(struct drm_buddy *mm,
u64 block_end;
block = list_first_entry_or_null(dfs,
- struct drm_buddy_block,
+ struct gpu_buddy_block,
tmp_link);
if (!block)
break;
list_del(&block->tmp_link);
- block_start = drm_buddy_block_offset(block);
- block_end = block_start + drm_buddy_block_size(mm, block) - 1;
+ block_start = gpu_buddy_block_offset(block);
+ block_end = block_start + gpu_buddy_block_size(mm, block) - 1;
if (!overlaps(start, end, block_start, block_end))
continue;
- if (drm_buddy_block_is_allocated(block)) {
+ if (gpu_buddy_block_is_allocated(block)) {
err = -ENOSPC;
goto err_free;
}
if (contains(start, end, block_start, block_end)) {
- if (drm_buddy_block_is_free(block)) {
+ if (gpu_buddy_block_is_free(block)) {
mark_allocated(mm, block);
- total_allocated += drm_buddy_block_size(mm, block);
- mm->avail -= drm_buddy_block_size(mm, block);
- if (drm_buddy_block_is_clear(block))
- mm->clear_avail -= drm_buddy_block_size(mm, block);
+ total_allocated += gpu_buddy_block_size(mm, block);
+ mm->avail -= gpu_buddy_block_size(mm, block);
+ if (gpu_buddy_block_is_clear(block))
+ mm->clear_avail -= gpu_buddy_block_size(mm, block);
list_add_tail(&block->link, &allocated);
continue;
} else if (!mm->clear_avail) {
@@ -853,7 +843,7 @@ static int __alloc_range(struct drm_buddy *mm,
}
}
- if (!drm_buddy_block_is_split(block)) {
+ if (!gpu_buddy_block_is_split(block)) {
err = split_block(mm, block);
if (unlikely(err))
goto err_undo;
@@ -880,22 +870,22 @@ static int __alloc_range(struct drm_buddy *mm,
*/
buddy = __get_buddy(block);
if (buddy &&
- (drm_buddy_block_is_free(block) &&
- drm_buddy_block_is_free(buddy)))
- __drm_buddy_free(mm, block, false);
+ (gpu_buddy_block_is_free(block) &&
+ gpu_buddy_block_is_free(buddy)))
+ __gpu_buddy_free(mm, block, false);
err_free:
if (err == -ENOSPC && total_allocated_on_err) {
list_splice_tail(&allocated, blocks);
*total_allocated_on_err = total_allocated;
} else {
- drm_buddy_free_list_internal(mm, &allocated);
+ gpu_buddy_free_list_internal(mm, &allocated);
}
return err;
}
-static int __drm_buddy_alloc_range(struct drm_buddy *mm,
+static int __gpu_buddy_alloc_range(struct gpu_buddy *mm,
u64 start,
u64 size,
u64 *total_allocated_on_err,
@@ -911,13 +901,13 @@ static int __drm_buddy_alloc_range(struct drm_buddy *mm,
blocks, total_allocated_on_err);
}
-static int __alloc_contig_try_harder(struct drm_buddy *mm,
+static int __alloc_contig_try_harder(struct gpu_buddy *mm,
u64 size,
u64 min_block_size,
struct list_head *blocks)
{
u64 rhs_offset, lhs_offset, lhs_size, filled;
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
unsigned int tree, order;
LIST_HEAD(blocks_lhs);
unsigned long pages;
@@ -943,8 +933,8 @@ static int __alloc_contig_try_harder(struct drm_buddy *mm,
block = rbtree_get_free_block(iter);
/* Allocate blocks traversing RHS */
- rhs_offset = drm_buddy_block_offset(block);
- err = __drm_buddy_alloc_range(mm, rhs_offset, size,
+ rhs_offset = gpu_buddy_block_offset(block);
+ err = __gpu_buddy_alloc_range(mm, rhs_offset, size,
&filled, blocks);
if (!err || err != -ENOSPC)
return err;
@@ -954,18 +944,18 @@ static int __alloc_contig_try_harder(struct drm_buddy *mm,
lhs_size = round_up(lhs_size, min_block_size);
/* Allocate blocks traversing LHS */
- lhs_offset = drm_buddy_block_offset(block) - lhs_size;
- err = __drm_buddy_alloc_range(mm, lhs_offset, lhs_size,
+ lhs_offset = gpu_buddy_block_offset(block) - lhs_size;
+ err = __gpu_buddy_alloc_range(mm, lhs_offset, lhs_size,
NULL, &blocks_lhs);
if (!err) {
list_splice(&blocks_lhs, blocks);
return 0;
} else if (err != -ENOSPC) {
- drm_buddy_free_list_internal(mm, blocks);
+ gpu_buddy_free_list_internal(mm, blocks);
return err;
}
/* Free blocks for the next iteration */
- drm_buddy_free_list_internal(mm, blocks);
+ gpu_buddy_free_list_internal(mm, blocks);
iter = rb_prev(iter);
}
@@ -975,9 +965,9 @@ static int __alloc_contig_try_harder(struct drm_buddy *mm,
}
/**
- * drm_buddy_block_trim - free unused pages
+ * gpu_buddy_block_trim - free unused pages
*
- * @mm: DRM buddy manager
+ * @mm: GPU buddy manager
* @start: start address to begin the trimming.
* @new_size: original size requested
* @blocks: Input and output list of allocated blocks.
@@ -993,13 +983,13 @@ static int __alloc_contig_try_harder(struct drm_buddy *mm,
* Returns:
* 0 on success, error code on failure.
*/
-int drm_buddy_block_trim(struct drm_buddy *mm,
+int gpu_buddy_block_trim(struct gpu_buddy *mm,
u64 *start,
u64 new_size,
struct list_head *blocks)
{
- struct drm_buddy_block *parent;
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *parent;
+ struct gpu_buddy_block *block;
u64 block_start, block_end;
LIST_HEAD(dfs);
u64 new_start;
@@ -1009,22 +999,22 @@ int drm_buddy_block_trim(struct drm_buddy *mm,
return -EINVAL;
block = list_first_entry(blocks,
- struct drm_buddy_block,
+ struct gpu_buddy_block,
link);
- block_start = drm_buddy_block_offset(block);
- block_end = block_start + drm_buddy_block_size(mm, block);
+ block_start = gpu_buddy_block_offset(block);
+ block_end = block_start + gpu_buddy_block_size(mm, block);
- if (WARN_ON(!drm_buddy_block_is_allocated(block)))
+ if (WARN_ON(!gpu_buddy_block_is_allocated(block)))
return -EINVAL;
- if (new_size > drm_buddy_block_size(mm, block))
+ if (new_size > gpu_buddy_block_size(mm, block))
return -EINVAL;
if (!new_size || !IS_ALIGNED(new_size, mm->chunk_size))
return -EINVAL;
- if (new_size == drm_buddy_block_size(mm, block))
+ if (new_size == gpu_buddy_block_size(mm, block))
return 0;
new_start = block_start;
@@ -1043,9 +1033,9 @@ int drm_buddy_block_trim(struct drm_buddy *mm,
list_del(&block->link);
mark_free(mm, block);
- mm->avail += drm_buddy_block_size(mm, block);
- if (drm_buddy_block_is_clear(block))
- mm->clear_avail += drm_buddy_block_size(mm, block);
+ mm->avail += gpu_buddy_block_size(mm, block);
+ if (gpu_buddy_block_is_clear(block))
+ mm->clear_avail += gpu_buddy_block_size(mm, block);
/* Prevent recursively freeing this node */
parent = block->parent;
@@ -1055,26 +1045,26 @@ int drm_buddy_block_trim(struct drm_buddy *mm,
err = __alloc_range(mm, &dfs, new_start, new_size, blocks, NULL);
if (err) {
mark_allocated(mm, block);
- mm->avail -= drm_buddy_block_size(mm, block);
- if (drm_buddy_block_is_clear(block))
- mm->clear_avail -= drm_buddy_block_size(mm, block);
+ mm->avail -= gpu_buddy_block_size(mm, block);
+ if (gpu_buddy_block_is_clear(block))
+ mm->clear_avail -= gpu_buddy_block_size(mm, block);
list_add(&block->link, blocks);
}
block->parent = parent;
return err;
}
-EXPORT_SYMBOL(drm_buddy_block_trim);
+EXPORT_SYMBOL(gpu_buddy_block_trim);
-static struct drm_buddy_block *
-__drm_buddy_alloc_blocks(struct drm_buddy *mm,
+static struct gpu_buddy_block *
+__gpu_buddy_alloc_blocks(struct gpu_buddy *mm,
u64 start, u64 end,
unsigned int order,
unsigned long flags)
{
- if (flags & DRM_BUDDY_RANGE_ALLOCATION)
+ if (flags & GPU_BUDDY_RANGE_ALLOCATION)
/* Allocate traversing within the range */
- return __drm_buddy_alloc_range_bias(mm, start, end,
+ return __gpu_buddy_alloc_range_bias(mm, start, end,
order, flags);
else
/* Allocate from freetree */
@@ -1082,15 +1072,15 @@ __drm_buddy_alloc_blocks(struct drm_buddy *mm,
}
/**
- * drm_buddy_alloc_blocks - allocate power-of-two blocks
+ * gpu_buddy_alloc_blocks - allocate power-of-two blocks
*
- * @mm: DRM buddy manager to allocate from
+ * @mm: GPU buddy manager to allocate from
* @start: start of the allowed range for this block
* @end: end of the allowed range for this block
* @size: size of the allocation in bytes
* @min_block_size: alignment of the allocation
* @blocks: output list head to add allocated blocks
- * @flags: DRM_BUDDY_*_ALLOCATION flags
+ * @flags: GPU_BUDDY_*_ALLOCATION flags
*
* alloc_range_bias() called on range limitations, which traverses
* the tree and returns the desired block.
@@ -1101,13 +1091,13 @@ __drm_buddy_alloc_blocks(struct drm_buddy *mm,
* Returns:
* 0 on success, error code on failure.
*/
-int drm_buddy_alloc_blocks(struct drm_buddy *mm,
+int gpu_buddy_alloc_blocks(struct gpu_buddy *mm,
u64 start, u64 end, u64 size,
u64 min_block_size,
struct list_head *blocks,
unsigned long flags)
{
- struct drm_buddy_block *block = NULL;
+ struct gpu_buddy_block *block = NULL;
u64 original_size, original_min_size;
unsigned int min_order, order;
LIST_HEAD(allocated);
@@ -1137,14 +1127,14 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm,
if (!IS_ALIGNED(start | end, min_block_size))
return -EINVAL;
- return __drm_buddy_alloc_range(mm, start, size, NULL, blocks);
+ return __gpu_buddy_alloc_range(mm, start, size, NULL, blocks);
}
original_size = size;
original_min_size = min_block_size;
/* Roundup the size to power of 2 */
- if (flags & DRM_BUDDY_CONTIGUOUS_ALLOCATION) {
+ if (flags & GPU_BUDDY_CONTIGUOUS_ALLOCATION) {
size = roundup_pow_of_two(size);
min_block_size = size;
/* Align size value to min_block_size */
@@ -1157,8 +1147,8 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm,
min_order = ilog2(min_block_size) - ilog2(mm->chunk_size);
if (order > mm->max_order || size > mm->size) {
- if ((flags & DRM_BUDDY_CONTIGUOUS_ALLOCATION) &&
- !(flags & DRM_BUDDY_RANGE_ALLOCATION))
+ if ((flags & GPU_BUDDY_CONTIGUOUS_ALLOCATION) &&
+ !(flags & GPU_BUDDY_RANGE_ALLOCATION))
return __alloc_contig_try_harder(mm, original_size,
original_min_size, blocks);
@@ -1171,7 +1161,7 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm,
BUG_ON(order < min_order);
do {
- block = __drm_buddy_alloc_blocks(mm, start,
+ block = __gpu_buddy_alloc_blocks(mm, start,
end,
order,
flags);
@@ -1182,7 +1172,7 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm,
/* Try allocation through force merge method */
if (mm->clear_avail &&
!__force_merge(mm, start, end, min_order)) {
- block = __drm_buddy_alloc_blocks(mm, start,
+ block = __gpu_buddy_alloc_blocks(mm, start,
end,
min_order,
flags);
@@ -1196,8 +1186,8 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm,
* Try contiguous block allocation through
* try harder method.
*/
- if (flags & DRM_BUDDY_CONTIGUOUS_ALLOCATION &&
- !(flags & DRM_BUDDY_RANGE_ALLOCATION))
+ if (flags & GPU_BUDDY_CONTIGUOUS_ALLOCATION &&
+ !(flags & GPU_BUDDY_RANGE_ALLOCATION))
return __alloc_contig_try_harder(mm,
original_size,
original_min_size,
@@ -1208,9 +1198,9 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm,
} while (1);
mark_allocated(mm, block);
- mm->avail -= drm_buddy_block_size(mm, block);
- if (drm_buddy_block_is_clear(block))
- mm->clear_avail -= drm_buddy_block_size(mm, block);
+ mm->avail -= gpu_buddy_block_size(mm, block);
+ if (gpu_buddy_block_is_clear(block))
+ mm->clear_avail -= gpu_buddy_block_size(mm, block);
kmemleak_update_trace(block);
list_add_tail(&block->link, &allocated);
@@ -1221,7 +1211,7 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm,
} while (1);
/* Trim the allocated block to the required size */
- if (!(flags & DRM_BUDDY_TRIM_DISABLE) &&
+ if (!(flags & GPU_BUDDY_TRIM_DISABLE) &&
original_size != size) {
struct list_head *trim_list;
LIST_HEAD(temp);
@@ -1234,11 +1224,11 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm,
block = list_last_entry(&allocated, typeof(*block), link);
list_move(&block->link, &temp);
trim_list = &temp;
- trim_size = drm_buddy_block_size(mm, block) -
+ trim_size = gpu_buddy_block_size(mm, block) -
(size - original_size);
}
- drm_buddy_block_trim(mm,
+ gpu_buddy_block_trim(mm,
NULL,
trim_size,
trim_list);
@@ -1251,44 +1241,42 @@ int drm_buddy_alloc_blocks(struct drm_buddy *mm,
return 0;
err_free:
- drm_buddy_free_list_internal(mm, &allocated);
+ gpu_buddy_free_list_internal(mm, &allocated);
return err;
}
-EXPORT_SYMBOL(drm_buddy_alloc_blocks);
+EXPORT_SYMBOL(gpu_buddy_alloc_blocks);
/**
- * drm_buddy_block_print - print block information
+ * gpu_buddy_block_print - print block information
*
- * @mm: DRM buddy manager
- * @block: DRM buddy block
- * @p: DRM printer to use
+ * @mm: GPU buddy manager
+ * @block: GPU buddy block
*/
-void drm_buddy_block_print(struct drm_buddy *mm,
- struct drm_buddy_block *block,
- struct drm_printer *p)
+void gpu_buddy_block_print(struct gpu_buddy *mm,
+ struct gpu_buddy_block *block)
{
- u64 start = drm_buddy_block_offset(block);
- u64 size = drm_buddy_block_size(mm, block);
+ u64 start = gpu_buddy_block_offset(block);
+ u64 size = gpu_buddy_block_size(mm, block);
- drm_printf(p, "%#018llx-%#018llx: %llu\n", start, start + size, size);
+ pr_info("%#018llx-%#018llx: %llu\n", start, start + size, size);
}
-EXPORT_SYMBOL(drm_buddy_block_print);
+EXPORT_SYMBOL(gpu_buddy_block_print);
/**
- * drm_buddy_print - print allocator state
+ * gpu_buddy_print - print allocator state
*
- * @mm: DRM buddy manager
- * @p: DRM printer to use
+ * @mm: GPU buddy manager
+ * @p: GPU printer to use
*/
-void drm_buddy_print(struct drm_buddy *mm, struct drm_printer *p)
+void gpu_buddy_print(struct gpu_buddy *mm)
{
int order;
- drm_printf(p, "chunk_size: %lluKiB, total: %lluMiB, free: %lluMiB, clear_free: %lluMiB\n",
- mm->chunk_size >> 10, mm->size >> 20, mm->avail >> 20, mm->clear_avail >> 20);
+ pr_info("chunk_size: %lluKiB, total: %lluMiB, free: %lluMiB, clear_free: %lluMiB\n",
+ mm->chunk_size >> 10, mm->size >> 20, mm->avail >> 20, mm->clear_avail >> 20);
for (order = mm->max_order; order >= 0; order--) {
- struct drm_buddy_block *block, *tmp;
+ struct gpu_buddy_block *block, *tmp;
struct rb_root *root;
u64 count = 0, free;
unsigned int tree;
@@ -1297,40 +1285,38 @@ void drm_buddy_print(struct drm_buddy *mm, struct drm_printer *p)
root = &mm->free_trees[tree][order];
rbtree_postorder_for_each_entry_safe(block, tmp, root, rb) {
- BUG_ON(!drm_buddy_block_is_free(block));
+ BUG_ON(!gpu_buddy_block_is_free(block));
count++;
}
}
- drm_printf(p, "order-%2d ", order);
-
free = count * (mm->chunk_size << order);
if (free < SZ_1M)
- drm_printf(p, "free: %8llu KiB", free >> 10);
+ pr_info("order-%2d free: %8llu KiB, blocks: %llu\n",
+ order, free >> 10, count);
else
- drm_printf(p, "free: %8llu MiB", free >> 20);
-
- drm_printf(p, ", blocks: %llu\n", count);
+ pr_info("order-%2d free: %8llu MiB, blocks: %llu\n",
+ order, free >> 20, count);
}
}
-EXPORT_SYMBOL(drm_buddy_print);
+EXPORT_SYMBOL(gpu_buddy_print);
-static void drm_buddy_module_exit(void)
+static void gpu_buddy_module_exit(void)
{
kmem_cache_destroy(slab_blocks);
}
-static int __init drm_buddy_module_init(void)
+static int __init gpu_buddy_module_init(void)
{
- slab_blocks = KMEM_CACHE(drm_buddy_block, 0);
+ slab_blocks = KMEM_CACHE(gpu_buddy_block, 0);
if (!slab_blocks)
return -ENOMEM;
return 0;
}
-module_init(drm_buddy_module_init);
-module_exit(drm_buddy_module_exit);
+module_init(gpu_buddy_module_init);
+module_exit(gpu_buddy_module_exit);
-MODULE_DESCRIPTION("DRM Buddy Allocator");
+MODULE_DESCRIPTION("GPU Buddy Allocator");
MODULE_LICENSE("Dual MIT/GPL");
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index ca2a2801e77f..f48d00fe28cc 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -220,6 +220,7 @@ config DRM_GPUSVM
config DRM_BUDDY
tristate
depends on DRM
+ select GPU_BUDDY
help
A page based buddy allocator
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index 5c86bc908955..6ff0f6f10b58 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -113,7 +113,7 @@ drm_gpusvm_helper-$(CONFIG_ZONE_DEVICE) += \
obj-$(CONFIG_DRM_GPUSVM) += drm_gpusvm_helper.o
-obj-$(CONFIG_DRM_BUDDY) += ../buddy.o
+obj-$(CONFIG_DRM_BUDDY) += drm_buddy.o
drm_dma_helper-y := drm_gem_dma_helper.o
drm_dma_helper-$(CONFIG_DRM_FBDEV_EMULATION) += drm_fbdev_dma.o
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
index f582113d78b7..149f8f942eae 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
@@ -5663,7 +5663,7 @@ int amdgpu_ras_add_critical_region(struct amdgpu_device *adev,
struct amdgpu_ras *con = amdgpu_ras_get_context(adev);
struct amdgpu_vram_mgr_resource *vres;
struct ras_critical_region *region;
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
int ret = 0;
if (!bo || !bo->tbo.resource)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
index be2e56ce1355..8908d9e08a30 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_res_cursor.h
@@ -55,7 +55,7 @@ static inline void amdgpu_res_first(struct ttm_resource *res,
uint64_t start, uint64_t size,
struct amdgpu_res_cursor *cur)
{
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
struct list_head *head, *next;
struct drm_mm_node *node;
@@ -71,7 +71,7 @@ static inline void amdgpu_res_first(struct ttm_resource *res,
head = &to_amdgpu_vram_mgr_resource(res)->blocks;
block = list_first_entry_or_null(head,
- struct drm_buddy_block,
+ struct gpu_buddy_block,
link);
if (!block)
goto fallback;
@@ -81,7 +81,7 @@ static inline void amdgpu_res_first(struct ttm_resource *res,
next = block->link.next;
if (next != head)
- block = list_entry(next, struct drm_buddy_block, link);
+ block = list_entry(next, struct gpu_buddy_block, link);
}
cur->start = amdgpu_vram_mgr_block_start(block) + start;
@@ -125,7 +125,7 @@ static inline void amdgpu_res_first(struct ttm_resource *res,
*/
static inline void amdgpu_res_next(struct amdgpu_res_cursor *cur, uint64_t size)
{
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
struct drm_mm_node *node;
struct list_head *next;
@@ -146,7 +146,7 @@ static inline void amdgpu_res_next(struct amdgpu_res_cursor *cur, uint64_t size)
block = cur->node;
next = block->link.next;
- block = list_entry(next, struct drm_buddy_block, link);
+ block = list_entry(next, struct gpu_buddy_block, link);
cur->node = block;
cur->start = amdgpu_vram_mgr_block_start(block);
@@ -175,7 +175,7 @@ static inline void amdgpu_res_next(struct amdgpu_res_cursor *cur, uint64_t size)
*/
static inline bool amdgpu_res_cleared(struct amdgpu_res_cursor *cur)
{
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
switch (cur->mem_type) {
case TTM_PL_VRAM:
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
index 9d934c07fa6b..cd94f6efb7cb 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
@@ -25,6 +25,7 @@
#include <linux/dma-mapping.h>
#include <drm/ttm/ttm_range_manager.h>
#include <drm/drm_drv.h>
+#include <drm/drm_buddy.h>
#include "amdgpu.h"
#include "amdgpu_vm.h"
@@ -52,15 +53,15 @@ to_amdgpu_device(struct amdgpu_vram_mgr *mgr)
return container_of(mgr, struct amdgpu_device, mman.vram_mgr);
}
-static inline struct drm_buddy_block *
+static inline struct gpu_buddy_block *
amdgpu_vram_mgr_first_block(struct list_head *list)
{
- return list_first_entry_or_null(list, struct drm_buddy_block, link);
+ return list_first_entry_or_null(list, struct gpu_buddy_block, link);
}
static inline bool amdgpu_is_vram_mgr_blocks_contiguous(struct list_head *head)
{
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
u64 start, size;
block = amdgpu_vram_mgr_first_block(head);
@@ -71,7 +72,7 @@ static inline bool amdgpu_is_vram_mgr_blocks_contiguous(struct list_head *head)
start = amdgpu_vram_mgr_block_start(block);
size = amdgpu_vram_mgr_block_size(block);
- block = list_entry(block->link.next, struct drm_buddy_block, link);
+ block = list_entry(block->link.next, struct gpu_buddy_block, link);
if (start + size != amdgpu_vram_mgr_block_start(block))
return false;
}
@@ -81,7 +82,7 @@ static inline bool amdgpu_is_vram_mgr_blocks_contiguous(struct list_head *head)
static inline u64 amdgpu_vram_mgr_blocks_size(struct list_head *head)
{
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
u64 size = 0;
list_for_each_entry(block, head, link)
@@ -254,7 +255,7 @@ const struct attribute_group amdgpu_vram_mgr_attr_group = {
* Calculate how many bytes of the DRM BUDDY block are inside visible VRAM
*/
static u64 amdgpu_vram_mgr_vis_size(struct amdgpu_device *adev,
- struct drm_buddy_block *block)
+ struct gpu_buddy_block *block)
{
u64 start = amdgpu_vram_mgr_block_start(block);
u64 end = start + amdgpu_vram_mgr_block_size(block);
@@ -279,7 +280,7 @@ u64 amdgpu_vram_mgr_bo_visible_size(struct amdgpu_bo *bo)
struct amdgpu_device *adev = amdgpu_ttm_adev(bo->tbo.bdev);
struct ttm_resource *res = bo->tbo.resource;
struct amdgpu_vram_mgr_resource *vres = to_amdgpu_vram_mgr_resource(res);
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
u64 usage = 0;
if (amdgpu_gmc_vram_full_visible(&adev->gmc))
@@ -299,15 +300,15 @@ static void amdgpu_vram_mgr_do_reserve(struct ttm_resource_manager *man)
{
struct amdgpu_vram_mgr *mgr = to_vram_mgr(man);
struct amdgpu_device *adev = to_amdgpu_device(mgr);
- struct drm_buddy *mm = &mgr->mm;
+ struct gpu_buddy *mm = &mgr->mm;
struct amdgpu_vram_reservation *rsv, *temp;
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
uint64_t vis_usage;
list_for_each_entry_safe(rsv, temp, &mgr->reservations_pending, blocks) {
- if (drm_buddy_alloc_blocks(mm, rsv->start, rsv->start + rsv->size,
+ if (gpu_buddy_alloc_blocks(mm, rsv->start, rsv->start + rsv->size,
rsv->size, mm->chunk_size, &rsv->allocated,
- DRM_BUDDY_RANGE_ALLOCATION))
+ GPU_BUDDY_RANGE_ALLOCATION))
continue;
block = amdgpu_vram_mgr_first_block(&rsv->allocated);
@@ -403,7 +404,7 @@ int amdgpu_vram_mgr_query_address_block_info(struct amdgpu_vram_mgr *mgr,
uint64_t address, struct amdgpu_vram_block_info *info)
{
struct amdgpu_vram_mgr_resource *vres;
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
u64 start, size;
int ret = -ENOENT;
@@ -450,8 +451,8 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
struct amdgpu_vram_mgr_resource *vres;
u64 size, remaining_size, lpfn, fpfn;
unsigned int adjust_dcc_size = 0;
- struct drm_buddy *mm = &mgr->mm;
- struct drm_buddy_block *block;
+ struct gpu_buddy *mm = &mgr->mm;
+ struct gpu_buddy_block *block;
unsigned long pages_per_block;
int r;
@@ -493,17 +494,17 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
INIT_LIST_HEAD(&vres->blocks);
if (place->flags & TTM_PL_FLAG_TOPDOWN)
- vres->flags |= DRM_BUDDY_TOPDOWN_ALLOCATION;
+ vres->flags |= GPU_BUDDY_TOPDOWN_ALLOCATION;
if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)
- vres->flags |= DRM_BUDDY_CONTIGUOUS_ALLOCATION;
+ vres->flags |= GPU_BUDDY_CONTIGUOUS_ALLOCATION;
if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CLEARED)
- vres->flags |= DRM_BUDDY_CLEAR_ALLOCATION;
+ vres->flags |= GPU_BUDDY_CLEAR_ALLOCATION;
if (fpfn || lpfn != mgr->mm.size)
/* Allocate blocks in desired range */
- vres->flags |= DRM_BUDDY_RANGE_ALLOCATION;
+ vres->flags |= GPU_BUDDY_RANGE_ALLOCATION;
if (bo->flags & AMDGPU_GEM_CREATE_GFX12_DCC &&
adev->gmc.gmc_funcs->get_dcc_alignment)
@@ -516,7 +517,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
dcc_size = roundup_pow_of_two(vres->base.size + adjust_dcc_size);
remaining_size = (u64)dcc_size;
- vres->flags |= DRM_BUDDY_TRIM_DISABLE;
+ vres->flags |= GPU_BUDDY_TRIM_DISABLE;
}
mutex_lock(&mgr->lock);
@@ -536,7 +537,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
BUG_ON(min_block_size < mm->chunk_size);
- r = drm_buddy_alloc_blocks(mm, fpfn,
+ r = gpu_buddy_alloc_blocks(mm, fpfn,
lpfn,
size,
min_block_size,
@@ -545,7 +546,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
if (unlikely(r == -ENOSPC) && pages_per_block == ~0ul &&
!(place->flags & TTM_PL_FLAG_CONTIGUOUS)) {
- vres->flags &= ~DRM_BUDDY_CONTIGUOUS_ALLOCATION;
+ vres->flags &= ~GPU_BUDDY_CONTIGUOUS_ALLOCATION;
pages_per_block = max_t(u32, 2UL << (20UL - PAGE_SHIFT),
tbo->page_alignment);
@@ -566,7 +567,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
list_add_tail(&vres->vres_node, &mgr->allocated_vres_list);
if (bo->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS && adjust_dcc_size) {
- struct drm_buddy_block *dcc_block;
+ struct gpu_buddy_block *dcc_block;
unsigned long dcc_start;
u64 trim_start;
@@ -576,7 +577,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
roundup((unsigned long)amdgpu_vram_mgr_block_start(dcc_block),
adjust_dcc_size);
trim_start = (u64)dcc_start;
- drm_buddy_block_trim(mm, &trim_start,
+ gpu_buddy_block_trim(mm, &trim_start,
(u64)vres->base.size,
&vres->blocks);
}
@@ -614,7 +615,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
return 0;
error_free_blocks:
- drm_buddy_free_list(mm, &vres->blocks, 0);
+ gpu_buddy_free_list(mm, &vres->blocks, 0);
mutex_unlock(&mgr->lock);
error_fini:
ttm_resource_fini(man, &vres->base);
@@ -637,8 +638,8 @@ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man,
struct amdgpu_vram_mgr_resource *vres = to_amdgpu_vram_mgr_resource(res);
struct amdgpu_vram_mgr *mgr = to_vram_mgr(man);
struct amdgpu_device *adev = to_amdgpu_device(mgr);
- struct drm_buddy *mm = &mgr->mm;
- struct drm_buddy_block *block;
+ struct gpu_buddy *mm = &mgr->mm;
+ struct gpu_buddy_block *block;
uint64_t vis_usage = 0;
mutex_lock(&mgr->lock);
@@ -649,7 +650,7 @@ static void amdgpu_vram_mgr_del(struct ttm_resource_manager *man,
list_for_each_entry(block, &vres->blocks, link)
vis_usage += amdgpu_vram_mgr_vis_size(adev, block);
- drm_buddy_free_list(mm, &vres->blocks, vres->flags);
+ gpu_buddy_free_list(mm, &vres->blocks, vres->flags);
amdgpu_vram_mgr_do_reserve(man);
mutex_unlock(&mgr->lock);
@@ -688,7 +689,7 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
if (!*sgt)
return -ENOMEM;
- /* Determine the number of DRM_BUDDY blocks to export */
+ /* Determine the number of GPU_BUDDY blocks to export */
amdgpu_res_first(res, offset, length, &cursor);
while (cursor.remaining) {
num_entries++;
@@ -704,10 +705,10 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
sg->length = 0;
/*
- * Walk down DRM_BUDDY blocks to populate scatterlist nodes
- * @note: Use iterator api to get first the DRM_BUDDY block
+ * Walk down GPU_BUDDY blocks to populate scatterlist nodes
+ * @note: Use iterator api to get first the GPU_BUDDY block
* and the number of bytes from it. Access the following
- * DRM_BUDDY block(s) if more buffer needs to exported
+ * GPU_BUDDY block(s) if more buffer needs to exported
*/
amdgpu_res_first(res, offset, length, &cursor);
for_each_sgtable_sg((*sgt), sg, i) {
@@ -792,10 +793,10 @@ uint64_t amdgpu_vram_mgr_vis_usage(struct amdgpu_vram_mgr *mgr)
void amdgpu_vram_mgr_clear_reset_blocks(struct amdgpu_device *adev)
{
struct amdgpu_vram_mgr *mgr = &adev->mman.vram_mgr;
- struct drm_buddy *mm = &mgr->mm;
+ struct gpu_buddy *mm = &mgr->mm;
mutex_lock(&mgr->lock);
- drm_buddy_reset_clear(mm, false);
+ gpu_buddy_reset_clear(mm, false);
mutex_unlock(&mgr->lock);
}
@@ -815,7 +816,7 @@ static bool amdgpu_vram_mgr_intersects(struct ttm_resource_manager *man,
size_t size)
{
struct amdgpu_vram_mgr_resource *mgr = to_amdgpu_vram_mgr_resource(res);
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
/* Check each drm buddy block individually */
list_for_each_entry(block, &mgr->blocks, link) {
@@ -848,7 +849,7 @@ static bool amdgpu_vram_mgr_compatible(struct ttm_resource_manager *man,
size_t size)
{
struct amdgpu_vram_mgr_resource *mgr = to_amdgpu_vram_mgr_resource(res);
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
/* Check each drm buddy block individually */
list_for_each_entry(block, &mgr->blocks, link) {
@@ -877,7 +878,7 @@ static void amdgpu_vram_mgr_debug(struct ttm_resource_manager *man,
struct drm_printer *printer)
{
struct amdgpu_vram_mgr *mgr = to_vram_mgr(man);
- struct drm_buddy *mm = &mgr->mm;
+ struct gpu_buddy *mm = &mgr->mm;
struct amdgpu_vram_reservation *rsv;
drm_printf(printer, " vis usage:%llu\n",
@@ -930,7 +931,7 @@ int amdgpu_vram_mgr_init(struct amdgpu_device *adev)
mgr->default_page_size = PAGE_SIZE;
man->func = &amdgpu_vram_mgr_func;
- err = drm_buddy_init(&mgr->mm, man->size, PAGE_SIZE);
+ err = gpu_buddy_init(&mgr->mm, man->size, PAGE_SIZE);
if (err)
return err;
@@ -965,11 +966,11 @@ void amdgpu_vram_mgr_fini(struct amdgpu_device *adev)
kfree(rsv);
list_for_each_entry_safe(rsv, temp, &mgr->reserved_pages, blocks) {
- drm_buddy_free_list(&mgr->mm, &rsv->allocated, 0);
+ gpu_buddy_free_list(&mgr->mm, &rsv->allocated, 0);
kfree(rsv);
}
if (!adev->gmc.is_app_apu)
- drm_buddy_fini(&mgr->mm);
+ gpu_buddy_fini(&mgr->mm);
mutex_unlock(&mgr->lock);
ttm_resource_manager_cleanup(man);
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h
index 874779618056..429a21a2e9b2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h
@@ -28,7 +28,7 @@
struct amdgpu_vram_mgr {
struct ttm_resource_manager manager;
- struct drm_buddy mm;
+ struct gpu_buddy mm;
/* protects access to buffer objects */
struct mutex lock;
struct list_head reservations_pending;
@@ -57,19 +57,19 @@ struct amdgpu_vram_mgr_resource {
struct amdgpu_vres_task task;
};
-static inline u64 amdgpu_vram_mgr_block_start(struct drm_buddy_block *block)
+static inline u64 amdgpu_vram_mgr_block_start(struct gpu_buddy_block *block)
{
- return drm_buddy_block_offset(block);
+ return gpu_buddy_block_offset(block);
}
-static inline u64 amdgpu_vram_mgr_block_size(struct drm_buddy_block *block)
+static inline u64 amdgpu_vram_mgr_block_size(struct gpu_buddy_block *block)
{
- return (u64)PAGE_SIZE << drm_buddy_block_order(block);
+ return (u64)PAGE_SIZE << gpu_buddy_block_order(block);
}
-static inline bool amdgpu_vram_mgr_is_cleared(struct drm_buddy_block *block)
+static inline bool amdgpu_vram_mgr_is_cleared(struct gpu_buddy_block *block)
{
- return drm_buddy_block_is_clear(block);
+ return gpu_buddy_block_is_clear(block);
}
static inline struct amdgpu_vram_mgr_resource *
@@ -82,8 +82,8 @@ static inline void amdgpu_vram_mgr_set_cleared(struct ttm_resource *res)
{
struct amdgpu_vram_mgr_resource *ares = to_amdgpu_vram_mgr_resource(res);
- WARN_ON(ares->flags & DRM_BUDDY_CLEARED);
- ares->flags |= DRM_BUDDY_CLEARED;
+ WARN_ON(ares->flags & GPU_BUDDY_CLEARED);
+ ares->flags |= GPU_BUDDY_CLEARED;
}
int amdgpu_vram_mgr_query_address_block_info(struct amdgpu_vram_mgr *mgr,
diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/drm/drm_buddy.c
new file mode 100644
index 000000000000..841f3de5f307
--- /dev/null
+++ b/drivers/gpu/drm/drm_buddy.c
@@ -0,0 +1,77 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#include <kunit/test-bug.h>
+
+#include <linux/export.h>
+#include <linux/kmemleak.h>
+#include <linux/module.h>
+#include <linux/sizes.h>
+
+#include <linux/gpu_buddy.h>
+#include <drm/drm_buddy.h>
+#include <drm/drm_print.h>
+
+/**
+ * drm_buddy_block_print - print block information
+ *
+ * @mm: DRM buddy manager
+ * @block: DRM buddy block
+ * @p: DRM printer to use
+ */
+void drm_buddy_block_print(struct gpu_buddy *mm,
+ struct gpu_buddy_block *block,
+ struct drm_printer *p)
+{
+ u64 start = gpu_buddy_block_offset(block);
+ u64 size = gpu_buddy_block_size(mm, block);
+
+ drm_printf(p, "%#018llx-%#018llx: %llu\n", start, start + size, size);
+}
+EXPORT_SYMBOL(drm_buddy_block_print);
+
+/**
+ * drm_buddy_print - print allocator state
+ *
+ * @mm: DRM buddy manager
+ * @p: DRM printer to use
+ */
+void drm_buddy_print(struct gpu_buddy *mm, struct drm_printer *p)
+{
+ int order;
+
+ drm_printf(p, "chunk_size: %lluKiB, total: %lluMiB, free: %lluMiB, clear_free: %lluMiB\n",
+ mm->chunk_size >> 10, mm->size >> 20, mm->avail >> 20, mm->clear_avail >> 20);
+
+ for (order = mm->max_order; order >= 0; order--) {
+ struct gpu_buddy_block *block, *tmp;
+ struct rb_root *root;
+ u64 count = 0, free;
+ unsigned int tree;
+
+ for_each_free_tree(tree) {
+ root = &mm->free_trees[tree][order];
+
+ rbtree_postorder_for_each_entry_safe(block, tmp, root, rb) {
+ BUG_ON(!gpu_buddy_block_is_free(block));
+ count++;
+ }
+ }
+
+ drm_printf(p, "order-%2d ", order);
+
+ free = count * (mm->chunk_size << order);
+ if (free < SZ_1M)
+ drm_printf(p, "free: %8llu KiB", free >> 10);
+ else
+ drm_printf(p, "free: %8llu MiB", free >> 20);
+
+ drm_printf(p, ", blocks: %llu\n", count);
+ }
+}
+EXPORT_SYMBOL(drm_buddy_print);
+
+MODULE_DESCRIPTION("DRM-specific GPU Buddy Allocator Print Helpers");
+MODULE_LICENSE("Dual MIT/GPL");
diff --git a/drivers/gpu/drm/i915/i915_scatterlist.c b/drivers/gpu/drm/i915/i915_scatterlist.c
index 30246f02bcfe..6a34dae13769 100644
--- a/drivers/gpu/drm/i915/i915_scatterlist.c
+++ b/drivers/gpu/drm/i915/i915_scatterlist.c
@@ -167,9 +167,9 @@ struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res,
struct i915_ttm_buddy_resource *bman_res = to_ttm_buddy_resource(res);
const u64 size = res->size;
const u32 max_segment = round_down(UINT_MAX, page_alignment);
- struct drm_buddy *mm = bman_res->mm;
+ struct gpu_buddy *mm = bman_res->mm;
struct list_head *blocks = &bman_res->blocks;
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
struct i915_refct_sgt *rsgt;
struct scatterlist *sg;
struct sg_table *st;
@@ -202,8 +202,8 @@ struct i915_refct_sgt *i915_rsgt_from_buddy_resource(struct ttm_resource *res,
list_for_each_entry(block, blocks, link) {
u64 block_size, offset;
- block_size = min_t(u64, size, drm_buddy_block_size(mm, block));
- offset = drm_buddy_block_offset(block);
+ block_size = min_t(u64, size, gpu_buddy_block_size(mm, block));
+ offset = gpu_buddy_block_offset(block);
while (block_size) {
u64 len;
diff --git a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
index 6b256d95badd..c5ca90088705 100644
--- a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
+++ b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
@@ -6,6 +6,7 @@
#include <linux/slab.h>
#include <linux/gpu_buddy.h>
+#include <drm/drm_buddy.h>
#include <drm/drm_print.h>
#include <drm/ttm/ttm_placement.h>
#include <drm/ttm/ttm_bo.h>
@@ -16,7 +17,7 @@
struct i915_ttm_buddy_manager {
struct ttm_resource_manager manager;
- struct drm_buddy mm;
+ struct gpu_buddy mm;
struct list_head reserved;
struct mutex lock;
unsigned long visible_size;
@@ -38,7 +39,7 @@ static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man,
{
struct i915_ttm_buddy_manager *bman = to_buddy_manager(man);
struct i915_ttm_buddy_resource *bman_res;
- struct drm_buddy *mm = &bman->mm;
+ struct gpu_buddy *mm = &bman->mm;
unsigned long n_pages, lpfn;
u64 min_page_size;
u64 size;
@@ -57,13 +58,13 @@ static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man,
bman_res->mm = mm;
if (place->flags & TTM_PL_FLAG_TOPDOWN)
- bman_res->flags |= DRM_BUDDY_TOPDOWN_ALLOCATION;
+ bman_res->flags |= GPU_BUDDY_TOPDOWN_ALLOCATION;
if (place->flags & TTM_PL_FLAG_CONTIGUOUS)
- bman_res->flags |= DRM_BUDDY_CONTIGUOUS_ALLOCATION;
+ bman_res->flags |= GPU_BUDDY_CONTIGUOUS_ALLOCATION;
if (place->fpfn || lpfn != man->size)
- bman_res->flags |= DRM_BUDDY_RANGE_ALLOCATION;
+ bman_res->flags |= GPU_BUDDY_RANGE_ALLOCATION;
GEM_BUG_ON(!bman_res->base.size);
size = bman_res->base.size;
@@ -89,7 +90,7 @@ static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man,
goto err_free_res;
}
- err = drm_buddy_alloc_blocks(mm, (u64)place->fpfn << PAGE_SHIFT,
+ err = gpu_buddy_alloc_blocks(mm, (u64)place->fpfn << PAGE_SHIFT,
(u64)lpfn << PAGE_SHIFT,
(u64)n_pages << PAGE_SHIFT,
min_page_size,
@@ -101,15 +102,15 @@ static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man,
if (lpfn <= bman->visible_size) {
bman_res->used_visible_size = PFN_UP(bman_res->base.size);
} else {
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
list_for_each_entry(block, &bman_res->blocks, link) {
unsigned long start =
- drm_buddy_block_offset(block) >> PAGE_SHIFT;
+ gpu_buddy_block_offset(block) >> PAGE_SHIFT;
if (start < bman->visible_size) {
unsigned long end = start +
- (drm_buddy_block_size(mm, block) >> PAGE_SHIFT);
+ (gpu_buddy_block_size(mm, block) >> PAGE_SHIFT);
bman_res->used_visible_size +=
min(end, bman->visible_size) - start;
@@ -126,7 +127,7 @@ static int i915_ttm_buddy_man_alloc(struct ttm_resource_manager *man,
return 0;
err_free_blocks:
- drm_buddy_free_list(mm, &bman_res->blocks, 0);
+ gpu_buddy_free_list(mm, &bman_res->blocks, 0);
mutex_unlock(&bman->lock);
err_free_res:
ttm_resource_fini(man, &bman_res->base);
@@ -141,7 +142,7 @@ static void i915_ttm_buddy_man_free(struct ttm_resource_manager *man,
struct i915_ttm_buddy_manager *bman = to_buddy_manager(man);
mutex_lock(&bman->lock);
- drm_buddy_free_list(&bman->mm, &bman_res->blocks, 0);
+ gpu_buddy_free_list(&bman->mm, &bman_res->blocks, 0);
bman->visible_avail += bman_res->used_visible_size;
mutex_unlock(&bman->lock);
@@ -156,8 +157,8 @@ static bool i915_ttm_buddy_man_intersects(struct ttm_resource_manager *man,
{
struct i915_ttm_buddy_resource *bman_res = to_ttm_buddy_resource(res);
struct i915_ttm_buddy_manager *bman = to_buddy_manager(man);
- struct drm_buddy *mm = &bman->mm;
- struct drm_buddy_block *block;
+ struct gpu_buddy *mm = &bman->mm;
+ struct gpu_buddy_block *block;
if (!place->fpfn && !place->lpfn)
return true;
@@ -176,9 +177,9 @@ static bool i915_ttm_buddy_man_intersects(struct ttm_resource_manager *man,
/* Check each drm buddy block individually */
list_for_each_entry(block, &bman_res->blocks, link) {
unsigned long fpfn =
- drm_buddy_block_offset(block) >> PAGE_SHIFT;
+ gpu_buddy_block_offset(block) >> PAGE_SHIFT;
unsigned long lpfn = fpfn +
- (drm_buddy_block_size(mm, block) >> PAGE_SHIFT);
+ (gpu_buddy_block_size(mm, block) >> PAGE_SHIFT);
if (place->fpfn < lpfn && place->lpfn > fpfn)
return true;
@@ -194,8 +195,8 @@ static bool i915_ttm_buddy_man_compatible(struct ttm_resource_manager *man,
{
struct i915_ttm_buddy_resource *bman_res = to_ttm_buddy_resource(res);
struct i915_ttm_buddy_manager *bman = to_buddy_manager(man);
- struct drm_buddy *mm = &bman->mm;
- struct drm_buddy_block *block;
+ struct gpu_buddy *mm = &bman->mm;
+ struct gpu_buddy_block *block;
if (!place->fpfn && !place->lpfn)
return true;
@@ -209,9 +210,9 @@ static bool i915_ttm_buddy_man_compatible(struct ttm_resource_manager *man,
/* Check each drm buddy block individually */
list_for_each_entry(block, &bman_res->blocks, link) {
unsigned long fpfn =
- drm_buddy_block_offset(block) >> PAGE_SHIFT;
+ gpu_buddy_block_offset(block) >> PAGE_SHIFT;
unsigned long lpfn = fpfn +
- (drm_buddy_block_size(mm, block) >> PAGE_SHIFT);
+ (gpu_buddy_block_size(mm, block) >> PAGE_SHIFT);
if (fpfn < place->fpfn || lpfn > place->lpfn)
return false;
@@ -224,7 +225,7 @@ static void i915_ttm_buddy_man_debug(struct ttm_resource_manager *man,
struct drm_printer *printer)
{
struct i915_ttm_buddy_manager *bman = to_buddy_manager(man);
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
mutex_lock(&bman->lock);
drm_printf(printer, "default_page_size: %lluKiB\n",
@@ -293,7 +294,7 @@ int i915_ttm_buddy_man_init(struct ttm_device *bdev,
if (!bman)
return -ENOMEM;
- err = drm_buddy_init(&bman->mm, size, chunk_size);
+ err = gpu_buddy_init(&bman->mm, size, chunk_size);
if (err)
goto err_free_bman;
@@ -333,7 +334,7 @@ int i915_ttm_buddy_man_fini(struct ttm_device *bdev, unsigned int type)
{
struct ttm_resource_manager *man = ttm_manager_type(bdev, type);
struct i915_ttm_buddy_manager *bman = to_buddy_manager(man);
- struct drm_buddy *mm = &bman->mm;
+ struct gpu_buddy *mm = &bman->mm;
int ret;
ttm_resource_manager_set_used(man, false);
@@ -345,8 +346,8 @@ int i915_ttm_buddy_man_fini(struct ttm_device *bdev, unsigned int type)
ttm_set_driver_manager(bdev, type, NULL);
mutex_lock(&bman->lock);
- drm_buddy_free_list(mm, &bman->reserved, 0);
- drm_buddy_fini(mm);
+ gpu_buddy_free_list(mm, &bman->reserved, 0);
+ gpu_buddy_fini(mm);
bman->visible_avail += bman->visible_reserved;
WARN_ON_ONCE(bman->visible_avail != bman->visible_size);
mutex_unlock(&bman->lock);
@@ -371,15 +372,15 @@ int i915_ttm_buddy_man_reserve(struct ttm_resource_manager *man,
u64 start, u64 size)
{
struct i915_ttm_buddy_manager *bman = to_buddy_manager(man);
- struct drm_buddy *mm = &bman->mm;
+ struct gpu_buddy *mm = &bman->mm;
unsigned long fpfn = start >> PAGE_SHIFT;
unsigned long flags = 0;
int ret;
- flags |= DRM_BUDDY_RANGE_ALLOCATION;
+ flags |= GPU_BUDDY_RANGE_ALLOCATION;
mutex_lock(&bman->lock);
- ret = drm_buddy_alloc_blocks(mm, start,
+ ret = gpu_buddy_alloc_blocks(mm, start,
start + size,
size, mm->chunk_size,
&bman->reserved,
diff --git a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.h b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.h
index d64620712830..1cff018c1689 100644
--- a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.h
+++ b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.h
@@ -13,7 +13,7 @@
struct ttm_device;
struct ttm_resource_manager;
-struct drm_buddy;
+struct gpu_buddy;
/**
* struct i915_ttm_buddy_resource
@@ -33,7 +33,7 @@ struct i915_ttm_buddy_resource {
struct list_head blocks;
unsigned long flags;
unsigned long used_visible_size;
- struct drm_buddy *mm;
+ struct gpu_buddy *mm;
};
/**
diff --git a/drivers/gpu/drm/i915/selftests/intel_memory_region.c b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
index 7b856b5090f9..8307390943a2 100644
--- a/drivers/gpu/drm/i915/selftests/intel_memory_region.c
+++ b/drivers/gpu/drm/i915/selftests/intel_memory_region.c
@@ -6,7 +6,7 @@
#include <linux/prime_numbers.h>
#include <linux/sort.h>
-#include <drm/drm_buddy.h>
+#include <linux/gpu_buddy.h>
#include "../i915_selftest.h"
@@ -371,7 +371,7 @@ static int igt_mock_splintered_region(void *arg)
struct drm_i915_private *i915 = mem->i915;
struct i915_ttm_buddy_resource *res;
struct drm_i915_gem_object *obj;
- struct drm_buddy *mm;
+ struct gpu_buddy *mm;
unsigned int expected_order;
LIST_HEAD(objects);
u64 size;
@@ -447,8 +447,8 @@ static int igt_mock_max_segment(void *arg)
struct drm_i915_private *i915 = mem->i915;
struct i915_ttm_buddy_resource *res;
struct drm_i915_gem_object *obj;
- struct drm_buddy_block *block;
- struct drm_buddy *mm;
+ struct gpu_buddy_block *block;
+ struct gpu_buddy *mm;
struct list_head *blocks;
struct scatterlist *sg;
I915_RND_STATE(prng);
@@ -487,8 +487,8 @@ static int igt_mock_max_segment(void *arg)
mm = res->mm;
size = 0;
list_for_each_entry(block, blocks, link) {
- if (drm_buddy_block_size(mm, block) > size)
- size = drm_buddy_block_size(mm, block);
+ if (gpu_buddy_block_size(mm, block) > size)
+ size = gpu_buddy_block_size(mm, block);
}
if (size < max_segment) {
pr_err("%s: Failed to create a huge contiguous block [> %u], largest block %lld\n",
@@ -527,14 +527,14 @@ static u64 igt_object_mappable_total(struct drm_i915_gem_object *obj)
struct intel_memory_region *mr = obj->mm.region;
struct i915_ttm_buddy_resource *bman_res =
to_ttm_buddy_resource(obj->mm.res);
- struct drm_buddy *mm = bman_res->mm;
- struct drm_buddy_block *block;
+ struct gpu_buddy *mm = bman_res->mm;
+ struct gpu_buddy_block *block;
u64 total;
total = 0;
list_for_each_entry(block, &bman_res->blocks, link) {
- u64 start = drm_buddy_block_offset(block);
- u64 end = start + drm_buddy_block_size(mm, block);
+ u64 start = gpu_buddy_block_offset(block);
+ u64 end = start + gpu_buddy_block_size(mm, block);
if (start < resource_size(&mr->io))
total += min_t(u64, end, resource_size(&mr->io)) - start;
diff --git a/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c b/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c
index 6d95447a989d..e32f3c8d7b84 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_bo_validate_test.c
@@ -251,7 +251,7 @@ static void ttm_bo_validate_basic(struct kunit *test)
NULL, &dummy_ttm_bo_destroy);
KUNIT_EXPECT_EQ(test, err, 0);
- snd_place = ttm_place_kunit_init(test, snd_mem, DRM_BUDDY_TOPDOWN_ALLOCATION);
+ snd_place = ttm_place_kunit_init(test, snd_mem, GPU_BUDDY_TOPDOWN_ALLOCATION);
snd_placement = ttm_placement_kunit_init(test, snd_place, 1);
err = ttm_bo_validate(bo, snd_placement, &ctx_val);
@@ -263,7 +263,7 @@ static void ttm_bo_validate_basic(struct kunit *test)
KUNIT_EXPECT_TRUE(test, ttm_tt_is_populated(bo->ttm));
KUNIT_EXPECT_EQ(test, bo->resource->mem_type, snd_mem);
KUNIT_EXPECT_EQ(test, bo->resource->placement,
- DRM_BUDDY_TOPDOWN_ALLOCATION);
+ GPU_BUDDY_TOPDOWN_ALLOCATION);
ttm_bo_fini(bo);
ttm_mock_manager_fini(priv->ttm_dev, snd_mem);
diff --git a/drivers/gpu/drm/ttm/tests/ttm_mock_manager.c b/drivers/gpu/drm/ttm/tests/ttm_mock_manager.c
index dd395229e388..294d56d9067e 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_mock_manager.c
+++ b/drivers/gpu/drm/ttm/tests/ttm_mock_manager.c
@@ -31,7 +31,7 @@ static int ttm_mock_manager_alloc(struct ttm_resource_manager *man,
{
struct ttm_mock_manager *manager = to_mock_mgr(man);
struct ttm_mock_resource *mock_res;
- struct drm_buddy *mm = &manager->mm;
+ struct gpu_buddy *mm = &manager->mm;
u64 lpfn, fpfn, alloc_size;
int err;
@@ -47,14 +47,14 @@ static int ttm_mock_manager_alloc(struct ttm_resource_manager *man,
INIT_LIST_HEAD(&mock_res->blocks);
if (place->flags & TTM_PL_FLAG_TOPDOWN)
- mock_res->flags |= DRM_BUDDY_TOPDOWN_ALLOCATION;
+ mock_res->flags |= GPU_BUDDY_TOPDOWN_ALLOCATION;
if (place->flags & TTM_PL_FLAG_CONTIGUOUS)
- mock_res->flags |= DRM_BUDDY_CONTIGUOUS_ALLOCATION;
+ mock_res->flags |= GPU_BUDDY_CONTIGUOUS_ALLOCATION;
alloc_size = (uint64_t)mock_res->base.size;
mutex_lock(&manager->lock);
- err = drm_buddy_alloc_blocks(mm, fpfn, lpfn, alloc_size,
+ err = gpu_buddy_alloc_blocks(mm, fpfn, lpfn, alloc_size,
manager->default_page_size,
&mock_res->blocks,
mock_res->flags);
@@ -67,7 +67,7 @@ static int ttm_mock_manager_alloc(struct ttm_resource_manager *man,
return 0;
error_free_blocks:
- drm_buddy_free_list(mm, &mock_res->blocks, 0);
+ gpu_buddy_free_list(mm, &mock_res->blocks, 0);
ttm_resource_fini(man, &mock_res->base);
mutex_unlock(&manager->lock);
@@ -79,10 +79,10 @@ static void ttm_mock_manager_free(struct ttm_resource_manager *man,
{
struct ttm_mock_manager *manager = to_mock_mgr(man);
struct ttm_mock_resource *mock_res = to_mock_mgr_resource(res);
- struct drm_buddy *mm = &manager->mm;
+ struct gpu_buddy *mm = &manager->mm;
mutex_lock(&manager->lock);
- drm_buddy_free_list(mm, &mock_res->blocks, 0);
+ gpu_buddy_free_list(mm, &mock_res->blocks, 0);
mutex_unlock(&manager->lock);
ttm_resource_fini(man, res);
@@ -106,7 +106,7 @@ int ttm_mock_manager_init(struct ttm_device *bdev, u32 mem_type, u32 size)
mutex_init(&manager->lock);
- err = drm_buddy_init(&manager->mm, size, PAGE_SIZE);
+ err = gpu_buddy_init(&manager->mm, size, PAGE_SIZE);
if (err) {
kfree(manager);
@@ -142,7 +142,7 @@ void ttm_mock_manager_fini(struct ttm_device *bdev, u32 mem_type)
ttm_resource_manager_set_used(man, false);
mutex_lock(&mock_man->lock);
- drm_buddy_fini(&mock_man->mm);
+ gpu_buddy_fini(&mock_man->mm);
mutex_unlock(&mock_man->lock);
ttm_set_driver_manager(bdev, mem_type, NULL);
diff --git a/drivers/gpu/drm/ttm/tests/ttm_mock_manager.h b/drivers/gpu/drm/ttm/tests/ttm_mock_manager.h
index 96ea8c9aae34..08710756fd8e 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_mock_manager.h
+++ b/drivers/gpu/drm/ttm/tests/ttm_mock_manager.h
@@ -9,7 +9,7 @@
struct ttm_mock_manager {
struct ttm_resource_manager man;
- struct drm_buddy mm;
+ struct gpu_buddy mm;
u64 default_page_size;
/* protects allocations of mock buffer objects */
struct mutex lock;
diff --git a/drivers/gpu/drm/xe/xe_res_cursor.h b/drivers/gpu/drm/xe/xe_res_cursor.h
index 4e00008b7081..5f4ab08c0686 100644
--- a/drivers/gpu/drm/xe/xe_res_cursor.h
+++ b/drivers/gpu/drm/xe/xe_res_cursor.h
@@ -58,7 +58,7 @@ struct xe_res_cursor {
/** @dma_addr: Current element in a struct drm_pagemap_addr array */
const struct drm_pagemap_addr *dma_addr;
/** @mm: Buddy allocator for VRAM cursor */
- struct drm_buddy *mm;
+ struct gpu_buddy *mm;
/**
* @dma_start: DMA start address for the current segment.
* This may be different to @dma_addr.addr since elements in
@@ -69,7 +69,7 @@ struct xe_res_cursor {
u64 dma_seg_size;
};
-static struct drm_buddy *xe_res_get_buddy(struct ttm_resource *res)
+static struct gpu_buddy *xe_res_get_buddy(struct ttm_resource *res)
{
struct ttm_resource_manager *mgr;
@@ -104,30 +104,30 @@ static inline void xe_res_first(struct ttm_resource *res,
case XE_PL_STOLEN:
case XE_PL_VRAM0:
case XE_PL_VRAM1: {
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
struct list_head *head, *next;
- struct drm_buddy *mm = xe_res_get_buddy(res);
+ struct gpu_buddy *mm = xe_res_get_buddy(res);
head = &to_xe_ttm_vram_mgr_resource(res)->blocks;
block = list_first_entry_or_null(head,
- struct drm_buddy_block,
+ struct gpu_buddy_block,
link);
if (!block)
goto fallback;
- while (start >= drm_buddy_block_size(mm, block)) {
- start -= drm_buddy_block_size(mm, block);
+ while (start >= gpu_buddy_block_size(mm, block)) {
+ start -= gpu_buddy_block_size(mm, block);
next = block->link.next;
if (next != head)
- block = list_entry(next, struct drm_buddy_block,
+ block = list_entry(next, struct gpu_buddy_block,
link);
}
cur->mm = mm;
- cur->start = drm_buddy_block_offset(block) + start;
- cur->size = min(drm_buddy_block_size(mm, block) - start,
+ cur->start = gpu_buddy_block_offset(block) + start;
+ cur->size = min(gpu_buddy_block_size(mm, block) - start,
size);
cur->remaining = size;
cur->node = block;
@@ -259,7 +259,7 @@ static inline void xe_res_first_dma(const struct drm_pagemap_addr *dma_addr,
*/
static inline void xe_res_next(struct xe_res_cursor *cur, u64 size)
{
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
struct list_head *next;
u64 start;
@@ -295,18 +295,18 @@ static inline void xe_res_next(struct xe_res_cursor *cur, u64 size)
block = cur->node;
next = block->link.next;
- block = list_entry(next, struct drm_buddy_block, link);
+ block = list_entry(next, struct gpu_buddy_block, link);
- while (start >= drm_buddy_block_size(cur->mm, block)) {
- start -= drm_buddy_block_size(cur->mm, block);
+ while (start >= gpu_buddy_block_size(cur->mm, block)) {
+ start -= gpu_buddy_block_size(cur->mm, block);
next = block->link.next;
- block = list_entry(next, struct drm_buddy_block, link);
+ block = list_entry(next, struct gpu_buddy_block, link);
}
- cur->start = drm_buddy_block_offset(block) + start;
- cur->size = min(drm_buddy_block_size(cur->mm, block) - start,
+ cur->start = gpu_buddy_block_offset(block) + start;
+ cur->size = min(gpu_buddy_block_size(cur->mm, block) - start,
cur->remaining);
cur->node = block;
break;
diff --git a/drivers/gpu/drm/xe/xe_svm.c b/drivers/gpu/drm/xe/xe_svm.c
index 213f0334518a..cda3bf7e2418 100644
--- a/drivers/gpu/drm/xe/xe_svm.c
+++ b/drivers/gpu/drm/xe/xe_svm.c
@@ -747,7 +747,7 @@ static u64 block_offset_to_pfn(struct drm_pagemap *dpagemap, u64 offset)
return PHYS_PFN(offset + xpagemap->hpa_base);
}
-static struct drm_buddy *vram_to_buddy(struct xe_vram_region *vram)
+static struct gpu_buddy *vram_to_buddy(struct xe_vram_region *vram)
{
return &vram->ttm.mm;
}
@@ -758,17 +758,17 @@ static int xe_svm_populate_devmem_pfn(struct drm_pagemap_devmem *devmem_allocati
struct xe_bo *bo = to_xe_bo(devmem_allocation);
struct ttm_resource *res = bo->ttm.resource;
struct list_head *blocks = &to_xe_ttm_vram_mgr_resource(res)->blocks;
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
int j = 0;
list_for_each_entry(block, blocks, link) {
struct xe_vram_region *vr = block->private;
- struct drm_buddy *buddy = vram_to_buddy(vr);
+ struct gpu_buddy *buddy = vram_to_buddy(vr);
u64 block_pfn = block_offset_to_pfn(devmem_allocation->dpagemap,
- drm_buddy_block_offset(block));
+ gpu_buddy_block_offset(block));
int i;
- for (i = 0; i < drm_buddy_block_size(buddy, block) >> PAGE_SHIFT; ++i)
+ for (i = 0; i < gpu_buddy_block_size(buddy, block) >> PAGE_SHIFT; ++i)
pfn[j++] = block_pfn + i;
}
@@ -1033,7 +1033,7 @@ static int xe_drm_pagemap_populate_mm(struct drm_pagemap *dpagemap,
struct dma_fence *pre_migrate_fence = NULL;
struct xe_device *xe = vr->xe;
struct device *dev = xe->drm.dev;
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
struct xe_validation_ctx vctx;
struct list_head *blocks;
struct drm_exec exec;
diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
index 6553a19f7cf2..d119217d566a 100644
--- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
+++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr.c
@@ -6,6 +6,7 @@
#include <drm/drm_managed.h>
#include <drm/drm_drv.h>
+#include <drm/drm_buddy.h>
#include <drm/ttm/ttm_placement.h>
#include <drm/ttm/ttm_range_manager.h>
@@ -16,16 +17,16 @@
#include "xe_ttm_vram_mgr.h"
#include "xe_vram_types.h"
-static inline struct drm_buddy_block *
+static inline struct gpu_buddy_block *
xe_ttm_vram_mgr_first_block(struct list_head *list)
{
- return list_first_entry_or_null(list, struct drm_buddy_block, link);
+ return list_first_entry_or_null(list, struct gpu_buddy_block, link);
}
-static inline bool xe_is_vram_mgr_blocks_contiguous(struct drm_buddy *mm,
+static inline bool xe_is_vram_mgr_blocks_contiguous(struct gpu_buddy *mm,
struct list_head *head)
{
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
u64 start, size;
block = xe_ttm_vram_mgr_first_block(head);
@@ -33,12 +34,12 @@ static inline bool xe_is_vram_mgr_blocks_contiguous(struct drm_buddy *mm,
return false;
while (head != block->link.next) {
- start = drm_buddy_block_offset(block);
- size = drm_buddy_block_size(mm, block);
+ start = gpu_buddy_block_offset(block);
+ size = gpu_buddy_block_size(mm, block);
- block = list_entry(block->link.next, struct drm_buddy_block,
+ block = list_entry(block->link.next, struct gpu_buddy_block,
link);
- if (start + size != drm_buddy_block_offset(block))
+ if (start + size != gpu_buddy_block_offset(block))
return false;
}
@@ -52,7 +53,7 @@ static int xe_ttm_vram_mgr_new(struct ttm_resource_manager *man,
{
struct xe_ttm_vram_mgr *mgr = to_xe_ttm_vram_mgr(man);
struct xe_ttm_vram_mgr_resource *vres;
- struct drm_buddy *mm = &mgr->mm;
+ struct gpu_buddy *mm = &mgr->mm;
u64 size, min_page_size;
unsigned long lpfn;
int err;
@@ -79,10 +80,10 @@ static int xe_ttm_vram_mgr_new(struct ttm_resource_manager *man,
INIT_LIST_HEAD(&vres->blocks);
if (place->flags & TTM_PL_FLAG_TOPDOWN)
- vres->flags |= DRM_BUDDY_TOPDOWN_ALLOCATION;
+ vres->flags |= GPU_BUDDY_TOPDOWN_ALLOCATION;
if (place->fpfn || lpfn != man->size >> PAGE_SHIFT)
- vres->flags |= DRM_BUDDY_RANGE_ALLOCATION;
+ vres->flags |= GPU_BUDDY_RANGE_ALLOCATION;
if (WARN_ON(!vres->base.size)) {
err = -EINVAL;
@@ -118,27 +119,27 @@ static int xe_ttm_vram_mgr_new(struct ttm_resource_manager *man,
lpfn = max_t(unsigned long, place->fpfn + (size >> PAGE_SHIFT), lpfn);
}
- err = drm_buddy_alloc_blocks(mm, (u64)place->fpfn << PAGE_SHIFT,
+ err = gpu_buddy_alloc_blocks(mm, (u64)place->fpfn << PAGE_SHIFT,
(u64)lpfn << PAGE_SHIFT, size,
min_page_size, &vres->blocks, vres->flags);
if (err)
goto error_unlock;
if (place->flags & TTM_PL_FLAG_CONTIGUOUS) {
- if (!drm_buddy_block_trim(mm, NULL, vres->base.size, &vres->blocks))
+ if (!gpu_buddy_block_trim(mm, NULL, vres->base.size, &vres->blocks))
size = vres->base.size;
}
if (lpfn <= mgr->visible_size >> PAGE_SHIFT) {
vres->used_visible_size = size;
} else {
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
list_for_each_entry(block, &vres->blocks, link) {
- u64 start = drm_buddy_block_offset(block);
+ u64 start = gpu_buddy_block_offset(block);
if (start < mgr->visible_size) {
- u64 end = start + drm_buddy_block_size(mm, block);
+ u64 end = start + gpu_buddy_block_size(mm, block);
vres->used_visible_size +=
min(end, mgr->visible_size) - start;
@@ -158,11 +159,11 @@ static int xe_ttm_vram_mgr_new(struct ttm_resource_manager *man,
* the object.
*/
if (vres->base.placement & TTM_PL_FLAG_CONTIGUOUS) {
- struct drm_buddy_block *block = list_first_entry(&vres->blocks,
+ struct gpu_buddy_block *block = list_first_entry(&vres->blocks,
typeof(*block),
link);
- vres->base.start = drm_buddy_block_offset(block) >> PAGE_SHIFT;
+ vres->base.start = gpu_buddy_block_offset(block) >> PAGE_SHIFT;
} else {
vres->base.start = XE_BO_INVALID_OFFSET;
}
@@ -184,10 +185,10 @@ static void xe_ttm_vram_mgr_del(struct ttm_resource_manager *man,
struct xe_ttm_vram_mgr_resource *vres =
to_xe_ttm_vram_mgr_resource(res);
struct xe_ttm_vram_mgr *mgr = to_xe_ttm_vram_mgr(man);
- struct drm_buddy *mm = &mgr->mm;
+ struct gpu_buddy *mm = &mgr->mm;
mutex_lock(&mgr->lock);
- drm_buddy_free_list(mm, &vres->blocks, 0);
+ gpu_buddy_free_list(mm, &vres->blocks, 0);
mgr->visible_avail += vres->used_visible_size;
mutex_unlock(&mgr->lock);
@@ -200,7 +201,7 @@ static void xe_ttm_vram_mgr_debug(struct ttm_resource_manager *man,
struct drm_printer *printer)
{
struct xe_ttm_vram_mgr *mgr = to_xe_ttm_vram_mgr(man);
- struct drm_buddy *mm = &mgr->mm;
+ struct gpu_buddy *mm = &mgr->mm;
mutex_lock(&mgr->lock);
drm_printf(printer, "default_page_size: %lluKiB\n",
@@ -223,8 +224,8 @@ static bool xe_ttm_vram_mgr_intersects(struct ttm_resource_manager *man,
struct xe_ttm_vram_mgr *mgr = to_xe_ttm_vram_mgr(man);
struct xe_ttm_vram_mgr_resource *vres =
to_xe_ttm_vram_mgr_resource(res);
- struct drm_buddy *mm = &mgr->mm;
- struct drm_buddy_block *block;
+ struct gpu_buddy *mm = &mgr->mm;
+ struct gpu_buddy_block *block;
if (!place->fpfn && !place->lpfn)
return true;
@@ -234,9 +235,9 @@ static bool xe_ttm_vram_mgr_intersects(struct ttm_resource_manager *man,
list_for_each_entry(block, &vres->blocks, link) {
unsigned long fpfn =
- drm_buddy_block_offset(block) >> PAGE_SHIFT;
+ gpu_buddy_block_offset(block) >> PAGE_SHIFT;
unsigned long lpfn = fpfn +
- (drm_buddy_block_size(mm, block) >> PAGE_SHIFT);
+ (gpu_buddy_block_size(mm, block) >> PAGE_SHIFT);
if (place->fpfn < lpfn && place->lpfn > fpfn)
return true;
@@ -253,8 +254,8 @@ static bool xe_ttm_vram_mgr_compatible(struct ttm_resource_manager *man,
struct xe_ttm_vram_mgr *mgr = to_xe_ttm_vram_mgr(man);
struct xe_ttm_vram_mgr_resource *vres =
to_xe_ttm_vram_mgr_resource(res);
- struct drm_buddy *mm = &mgr->mm;
- struct drm_buddy_block *block;
+ struct gpu_buddy *mm = &mgr->mm;
+ struct gpu_buddy_block *block;
if (!place->fpfn && !place->lpfn)
return true;
@@ -264,9 +265,9 @@ static bool xe_ttm_vram_mgr_compatible(struct ttm_resource_manager *man,
list_for_each_entry(block, &vres->blocks, link) {
unsigned long fpfn =
- drm_buddy_block_offset(block) >> PAGE_SHIFT;
+ gpu_buddy_block_offset(block) >> PAGE_SHIFT;
unsigned long lpfn = fpfn +
- (drm_buddy_block_size(mm, block) >> PAGE_SHIFT);
+ (gpu_buddy_block_size(mm, block) >> PAGE_SHIFT);
if (fpfn < place->fpfn || lpfn > place->lpfn)
return false;
@@ -296,7 +297,7 @@ static void xe_ttm_vram_mgr_fini(struct drm_device *dev, void *arg)
WARN_ON_ONCE(mgr->visible_avail != mgr->visible_size);
- drm_buddy_fini(&mgr->mm);
+ gpu_buddy_fini(&mgr->mm);
ttm_resource_manager_cleanup(&mgr->manager);
@@ -327,7 +328,7 @@ int __xe_ttm_vram_mgr_init(struct xe_device *xe, struct xe_ttm_vram_mgr *mgr,
mgr->visible_avail = io_size;
ttm_resource_manager_init(man, &xe->ttm, size);
- err = drm_buddy_init(&mgr->mm, man->size, default_page_size);
+ err = gpu_buddy_init(&mgr->mm, man->size, default_page_size);
if (err)
return err;
@@ -375,7 +376,7 @@ int xe_ttm_vram_mgr_alloc_sgt(struct xe_device *xe,
if (!*sgt)
return -ENOMEM;
- /* Determine the number of DRM_BUDDY blocks to export */
+ /* Determine the number of GPU_BUDDY blocks to export */
xe_res_first(res, offset, length, &cursor);
while (cursor.remaining) {
num_entries++;
@@ -392,10 +393,10 @@ int xe_ttm_vram_mgr_alloc_sgt(struct xe_device *xe,
sg->length = 0;
/*
- * Walk down DRM_BUDDY blocks to populate scatterlist nodes
- * @note: Use iterator api to get first the DRM_BUDDY block
+ * Walk down GPU_BUDDY blocks to populate scatterlist nodes
+ * @note: Use iterator api to get first the GPU_BUDDY block
* and the number of bytes from it. Access the following
- * DRM_BUDDY block(s) if more buffer needs to exported
+ * GPU_BUDDY block(s) if more buffer needs to exported
*/
xe_res_first(res, offset, length, &cursor);
for_each_sgtable_sg((*sgt), sg, i) {
diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h b/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
index babeec5511d9..9106da056b49 100644
--- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
+++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
@@ -18,7 +18,7 @@ struct xe_ttm_vram_mgr {
/** @manager: Base TTM resource manager */
struct ttm_resource_manager manager;
/** @mm: DRM buddy allocator which manages the VRAM */
- struct drm_buddy mm;
+ struct gpu_buddy mm;
/** @visible_size: Proped size of the CPU visible portion */
u64 visible_size;
/** @visible_avail: CPU visible portion still unallocated */
diff --git a/drivers/gpu/tests/Makefile b/drivers/gpu/tests/Makefile
index 8e7654e87d82..4183e6e2de45 100644
--- a/drivers/gpu/tests/Makefile
+++ b/drivers/gpu/tests/Makefile
@@ -1,4 +1,4 @@
# SPDX-License-Identifier: GPL-2.0
gpu_buddy_tests-y = gpu_buddy_test.o gpu_random.o
-obj-$(CONFIG_DRM_KUNIT_TEST) += gpu_buddy_tests.o
+obj-$(CONFIG_GPU_BUDDY_KUNIT_TEST) += gpu_buddy_tests.o
diff --git a/drivers/gpu/tests/gpu_buddy_test.c b/drivers/gpu/tests/gpu_buddy_test.c
index b905932da990..450e71deed90 100644
--- a/drivers/gpu/tests/gpu_buddy_test.c
+++ b/drivers/gpu/tests/gpu_buddy_test.c
@@ -21,9 +21,9 @@ static inline u64 get_size(int order, u64 chunk_size)
return (1 << order) * chunk_size;
}
-static void drm_test_buddy_fragmentation_performance(struct kunit *test)
+static void gpu_test_buddy_fragmentation_performance(struct kunit *test)
{
- struct drm_buddy_block *block, *tmp;
+ struct gpu_buddy_block *block, *tmp;
int num_blocks, i, ret, count = 0;
LIST_HEAD(allocated_blocks);
unsigned long elapsed_ms;
@@ -32,7 +32,7 @@ static void drm_test_buddy_fragmentation_performance(struct kunit *test)
LIST_HEAD(clear_list);
LIST_HEAD(dirty_list);
LIST_HEAD(free_list);
- struct drm_buddy mm;
+ struct gpu_buddy mm;
u64 mm_size = SZ_4G;
ktime_t start, end;
@@ -47,7 +47,7 @@ static void drm_test_buddy_fragmentation_performance(struct kunit *test)
* quickly the allocator can satisfy larger, aligned requests from a pool of
* highly fragmented space.
*/
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, SZ_4K),
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_init(&mm, mm_size, SZ_4K),
"buddy_init failed\n");
num_blocks = mm_size / SZ_64K;
@@ -55,7 +55,7 @@ static void drm_test_buddy_fragmentation_performance(struct kunit *test)
start = ktime_get();
/* Allocate with maximum fragmentation - 8K blocks with 64K alignment */
for (i = 0; i < num_blocks; i++)
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, SZ_8K, SZ_64K,
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, 0, mm_size, SZ_8K, SZ_64K,
&allocated_blocks, 0),
"buddy_alloc hit an error size=%u\n", SZ_8K);
@@ -68,21 +68,21 @@ static void drm_test_buddy_fragmentation_performance(struct kunit *test)
}
/* Free with different flags to ensure no coalescing */
- drm_buddy_free_list(&mm, &clear_list, DRM_BUDDY_CLEARED);
- drm_buddy_free_list(&mm, &dirty_list, 0);
+ gpu_buddy_free_list(&mm, &clear_list, GPU_BUDDY_CLEARED);
+ gpu_buddy_free_list(&mm, &dirty_list, 0);
for (i = 0; i < num_blocks; i++)
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, SZ_64K, SZ_64K,
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, 0, mm_size, SZ_64K, SZ_64K,
&test_blocks, 0),
"buddy_alloc hit an error size=%u\n", SZ_64K);
- drm_buddy_free_list(&mm, &test_blocks, 0);
+ gpu_buddy_free_list(&mm, &test_blocks, 0);
end = ktime_get();
elapsed_ms = ktime_to_ms(ktime_sub(end, start));
kunit_info(test, "Fragmented allocation took %lu ms\n", elapsed_ms);
- drm_buddy_fini(&mm);
+ gpu_buddy_fini(&mm);
/*
* Reverse free order under fragmentation
@@ -96,13 +96,13 @@ static void drm_test_buddy_fragmentation_performance(struct kunit *test)
* deallocation occurs in the opposite order of allocation, exposing the
* cost difference between a linear freelist scan and an ordered tree lookup.
*/
- ret = drm_buddy_init(&mm, mm_size, SZ_4K);
+ ret = gpu_buddy_init(&mm, mm_size, SZ_4K);
KUNIT_ASSERT_EQ(test, ret, 0);
start = ktime_get();
/* Allocate maximum fragmentation */
for (i = 0; i < num_blocks; i++)
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, SZ_8K, SZ_64K,
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, 0, mm_size, SZ_8K, SZ_64K,
&allocated_blocks, 0),
"buddy_alloc hit an error size=%u\n", SZ_8K);
@@ -111,28 +111,28 @@ static void drm_test_buddy_fragmentation_performance(struct kunit *test)
list_move_tail(&block->link, &free_list);
count++;
}
- drm_buddy_free_list(&mm, &free_list, DRM_BUDDY_CLEARED);
+ gpu_buddy_free_list(&mm, &free_list, GPU_BUDDY_CLEARED);
list_for_each_entry_safe_reverse(block, tmp, &allocated_blocks, link)
list_move(&block->link, &reverse_list);
- drm_buddy_free_list(&mm, &reverse_list, DRM_BUDDY_CLEARED);
+ gpu_buddy_free_list(&mm, &reverse_list, GPU_BUDDY_CLEARED);
end = ktime_get();
elapsed_ms = ktime_to_ms(ktime_sub(end, start));
kunit_info(test, "Reverse-ordered free took %lu ms\n", elapsed_ms);
- drm_buddy_fini(&mm);
+ gpu_buddy_fini(&mm);
}
-static void drm_test_buddy_alloc_range_bias(struct kunit *test)
+static void gpu_test_buddy_alloc_range_bias(struct kunit *test)
{
u32 mm_size, size, ps, bias_size, bias_start, bias_end, bias_rem;
- DRM_RND_STATE(prng, random_seed);
+ GPU_RND_STATE(prng, random_seed);
unsigned int i, count, *order;
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
unsigned long flags;
- struct drm_buddy mm;
+ struct gpu_buddy mm;
LIST_HEAD(allocated);
bias_size = SZ_1M;
@@ -142,11 +142,11 @@ static void drm_test_buddy_alloc_range_bias(struct kunit *test)
kunit_info(test, "mm_size=%u, ps=%u\n", mm_size, ps);
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, ps),
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_init(&mm, mm_size, ps),
"buddy_init failed\n");
count = mm_size / bias_size;
- order = drm_random_order(count, &prng);
+ order = gpu_random_order(count, &prng);
KUNIT_EXPECT_TRUE(test, order);
/*
@@ -166,79 +166,79 @@ static void drm_test_buddy_alloc_range_bias(struct kunit *test)
/* internal round_up too big */
KUNIT_ASSERT_TRUE_MSG(test,
- drm_buddy_alloc_blocks(&mm, bias_start,
+ gpu_buddy_alloc_blocks(&mm, bias_start,
bias_end, bias_size + ps, bias_size,
&allocated,
- DRM_BUDDY_RANGE_ALLOCATION),
+ GPU_BUDDY_RANGE_ALLOCATION),
"buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
bias_start, bias_end, bias_size, bias_size);
/* size too big */
KUNIT_ASSERT_TRUE_MSG(test,
- drm_buddy_alloc_blocks(&mm, bias_start,
+ gpu_buddy_alloc_blocks(&mm, bias_start,
bias_end, bias_size + ps, ps,
&allocated,
- DRM_BUDDY_RANGE_ALLOCATION),
+ GPU_BUDDY_RANGE_ALLOCATION),
"buddy_alloc didn't fail with bias(%x-%x), size=%u, ps=%u\n",
bias_start, bias_end, bias_size + ps, ps);
/* bias range too small for size */
KUNIT_ASSERT_TRUE_MSG(test,
- drm_buddy_alloc_blocks(&mm, bias_start + ps,
+ gpu_buddy_alloc_blocks(&mm, bias_start + ps,
bias_end, bias_size, ps,
&allocated,
- DRM_BUDDY_RANGE_ALLOCATION),
+ GPU_BUDDY_RANGE_ALLOCATION),
"buddy_alloc didn't fail with bias(%x-%x), size=%u, ps=%u\n",
bias_start + ps, bias_end, bias_size, ps);
/* bias misaligned */
KUNIT_ASSERT_TRUE_MSG(test,
- drm_buddy_alloc_blocks(&mm, bias_start + ps,
+ gpu_buddy_alloc_blocks(&mm, bias_start + ps,
bias_end - ps,
bias_size >> 1, bias_size >> 1,
&allocated,
- DRM_BUDDY_RANGE_ALLOCATION),
+ GPU_BUDDY_RANGE_ALLOCATION),
"buddy_alloc h didn't fail with bias(%x-%x), size=%u, ps=%u\n",
bias_start + ps, bias_end - ps, bias_size >> 1, bias_size >> 1);
/* single big page */
KUNIT_ASSERT_FALSE_MSG(test,
- drm_buddy_alloc_blocks(&mm, bias_start,
+ gpu_buddy_alloc_blocks(&mm, bias_start,
bias_end, bias_size, bias_size,
&tmp,
- DRM_BUDDY_RANGE_ALLOCATION),
+ GPU_BUDDY_RANGE_ALLOCATION),
"buddy_alloc i failed with bias(%x-%x), size=%u, ps=%u\n",
bias_start, bias_end, bias_size, bias_size);
- drm_buddy_free_list(&mm, &tmp, 0);
+ gpu_buddy_free_list(&mm, &tmp, 0);
/* single page with internal round_up */
KUNIT_ASSERT_FALSE_MSG(test,
- drm_buddy_alloc_blocks(&mm, bias_start,
+ gpu_buddy_alloc_blocks(&mm, bias_start,
bias_end, ps, bias_size,
&tmp,
- DRM_BUDDY_RANGE_ALLOCATION),
+ GPU_BUDDY_RANGE_ALLOCATION),
"buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
bias_start, bias_end, ps, bias_size);
- drm_buddy_free_list(&mm, &tmp, 0);
+ gpu_buddy_free_list(&mm, &tmp, 0);
/* random size within */
size = max(round_up(prandom_u32_state(&prng) % bias_rem, ps), ps);
if (size)
KUNIT_ASSERT_FALSE_MSG(test,
- drm_buddy_alloc_blocks(&mm, bias_start,
+ gpu_buddy_alloc_blocks(&mm, bias_start,
bias_end, size, ps,
&tmp,
- DRM_BUDDY_RANGE_ALLOCATION),
+ GPU_BUDDY_RANGE_ALLOCATION),
"buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
bias_start, bias_end, size, ps);
bias_rem -= size;
/* too big for current avail */
KUNIT_ASSERT_TRUE_MSG(test,
- drm_buddy_alloc_blocks(&mm, bias_start,
+ gpu_buddy_alloc_blocks(&mm, bias_start,
bias_end, bias_rem + ps, ps,
&allocated,
- DRM_BUDDY_RANGE_ALLOCATION),
+ GPU_BUDDY_RANGE_ALLOCATION),
"buddy_alloc didn't fail with bias(%x-%x), size=%u, ps=%u\n",
bias_start, bias_end, bias_rem + ps, ps);
@@ -248,10 +248,10 @@ static void drm_test_buddy_alloc_range_bias(struct kunit *test)
size = max(size, ps);
KUNIT_ASSERT_FALSE_MSG(test,
- drm_buddy_alloc_blocks(&mm, bias_start,
+ gpu_buddy_alloc_blocks(&mm, bias_start,
bias_end, size, ps,
&allocated,
- DRM_BUDDY_RANGE_ALLOCATION),
+ GPU_BUDDY_RANGE_ALLOCATION),
"buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
bias_start, bias_end, size, ps);
/*
@@ -259,15 +259,15 @@ static void drm_test_buddy_alloc_range_bias(struct kunit *test)
* unallocated, and ideally not always on the bias
* boundaries.
*/
- drm_buddy_free_list(&mm, &tmp, 0);
+ gpu_buddy_free_list(&mm, &tmp, 0);
} else {
list_splice_tail(&tmp, &allocated);
}
}
kfree(order);
- drm_buddy_free_list(&mm, &allocated, 0);
- drm_buddy_fini(&mm);
+ gpu_buddy_free_list(&mm, &allocated, 0);
+ gpu_buddy_fini(&mm);
/*
* Something more free-form. Idea is to pick a random starting bias
@@ -278,7 +278,7 @@ static void drm_test_buddy_alloc_range_bias(struct kunit *test)
* allocated nodes in the middle of the address space.
*/
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, ps),
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_init(&mm, mm_size, ps),
"buddy_init failed\n");
bias_start = round_up(prandom_u32_state(&prng) % (mm_size - ps), ps);
@@ -290,10 +290,10 @@ static void drm_test_buddy_alloc_range_bias(struct kunit *test)
u32 size = max(round_up(prandom_u32_state(&prng) % bias_rem, ps), ps);
KUNIT_ASSERT_FALSE_MSG(test,
- drm_buddy_alloc_blocks(&mm, bias_start,
+ gpu_buddy_alloc_blocks(&mm, bias_start,
bias_end, size, ps,
&allocated,
- DRM_BUDDY_RANGE_ALLOCATION),
+ GPU_BUDDY_RANGE_ALLOCATION),
"buddy_alloc failed with bias(%x-%x), size=%u, ps=%u\n",
bias_start, bias_end, size, ps);
bias_rem -= size;
@@ -319,24 +319,24 @@ static void drm_test_buddy_alloc_range_bias(struct kunit *test)
KUNIT_ASSERT_EQ(test, bias_start, 0);
KUNIT_ASSERT_EQ(test, bias_end, mm_size);
KUNIT_ASSERT_TRUE_MSG(test,
- drm_buddy_alloc_blocks(&mm, bias_start, bias_end,
+ gpu_buddy_alloc_blocks(&mm, bias_start, bias_end,
ps, ps,
&allocated,
- DRM_BUDDY_RANGE_ALLOCATION),
+ GPU_BUDDY_RANGE_ALLOCATION),
"buddy_alloc passed with bias(%x-%x), size=%u\n",
bias_start, bias_end, ps);
- drm_buddy_free_list(&mm, &allocated, 0);
- drm_buddy_fini(&mm);
+ gpu_buddy_free_list(&mm, &allocated, 0);
+ gpu_buddy_fini(&mm);
/*
- * Allocate cleared blocks in the bias range when the DRM buddy's clear avail is
+ * Allocate cleared blocks in the bias range when the GPU buddy's clear avail is
* zero. This will validate the bias range allocation in scenarios like system boot
* when no cleared blocks are available and exercise the fallback path too. The resulting
* blocks should always be dirty.
*/
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, ps),
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_init(&mm, mm_size, ps),
"buddy_init failed\n");
bias_start = round_up(prandom_u32_state(&prng) % (mm_size - ps), ps);
@@ -344,11 +344,11 @@ static void drm_test_buddy_alloc_range_bias(struct kunit *test)
bias_end = max(bias_end, bias_start + ps);
bias_rem = bias_end - bias_start;
- flags = DRM_BUDDY_CLEAR_ALLOCATION | DRM_BUDDY_RANGE_ALLOCATION;
+ flags = GPU_BUDDY_CLEAR_ALLOCATION | GPU_BUDDY_RANGE_ALLOCATION;
size = max(round_up(prandom_u32_state(&prng) % bias_rem, ps), ps);
KUNIT_ASSERT_FALSE_MSG(test,
- drm_buddy_alloc_blocks(&mm, bias_start,
+ gpu_buddy_alloc_blocks(&mm, bias_start,
bias_end, size, ps,
&allocated,
flags),
@@ -356,27 +356,27 @@ static void drm_test_buddy_alloc_range_bias(struct kunit *test)
bias_start, bias_end, size, ps);
list_for_each_entry(block, &allocated, link)
- KUNIT_EXPECT_EQ(test, drm_buddy_block_is_clear(block), false);
+ KUNIT_EXPECT_EQ(test, gpu_buddy_block_is_clear(block), false);
- drm_buddy_free_list(&mm, &allocated, 0);
- drm_buddy_fini(&mm);
+ gpu_buddy_free_list(&mm, &allocated, 0);
+ gpu_buddy_fini(&mm);
}
-static void drm_test_buddy_alloc_clear(struct kunit *test)
+static void gpu_test_buddy_alloc_clear(struct kunit *test)
{
unsigned long n_pages, total, i = 0;
const unsigned long ps = SZ_4K;
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
const int max_order = 12;
LIST_HEAD(allocated);
- struct drm_buddy mm;
+ struct gpu_buddy mm;
unsigned int order;
u32 mm_size, size;
LIST_HEAD(dirty);
LIST_HEAD(clean);
mm_size = SZ_4K << max_order;
- KUNIT_EXPECT_FALSE(test, drm_buddy_init(&mm, mm_size, ps));
+ KUNIT_EXPECT_FALSE(test, gpu_buddy_init(&mm, mm_size, ps));
KUNIT_EXPECT_EQ(test, mm.max_order, max_order);
@@ -389,11 +389,11 @@ static void drm_test_buddy_alloc_clear(struct kunit *test)
* is indeed all dirty pages and vice versa. Free it all again,
* keeping the dirty/clear status.
*/
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, 0, mm_size,
5 * ps, ps, &allocated,
- DRM_BUDDY_TOPDOWN_ALLOCATION),
+ GPU_BUDDY_TOPDOWN_ALLOCATION),
"buddy_alloc hit an error size=%lu\n", 5 * ps);
- drm_buddy_free_list(&mm, &allocated, DRM_BUDDY_CLEARED);
+ gpu_buddy_free_list(&mm, &allocated, GPU_BUDDY_CLEARED);
n_pages = 10;
do {
@@ -406,37 +406,37 @@ static void drm_test_buddy_alloc_clear(struct kunit *test)
flags = 0;
} else {
list = &clean;
- flags = DRM_BUDDY_CLEAR_ALLOCATION;
+ flags = GPU_BUDDY_CLEAR_ALLOCATION;
}
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, 0, mm_size,
ps, ps, list,
flags),
"buddy_alloc hit an error size=%lu\n", ps);
} while (++i < n_pages);
list_for_each_entry(block, &clean, link)
- KUNIT_EXPECT_EQ(test, drm_buddy_block_is_clear(block), true);
+ KUNIT_EXPECT_EQ(test, gpu_buddy_block_is_clear(block), true);
list_for_each_entry(block, &dirty, link)
- KUNIT_EXPECT_EQ(test, drm_buddy_block_is_clear(block), false);
+ KUNIT_EXPECT_EQ(test, gpu_buddy_block_is_clear(block), false);
- drm_buddy_free_list(&mm, &clean, DRM_BUDDY_CLEARED);
+ gpu_buddy_free_list(&mm, &clean, GPU_BUDDY_CLEARED);
/*
* Trying to go over the clear limit for some allocation.
* The allocation should never fail with reasonable page-size.
*/
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, 0, mm_size,
10 * ps, ps, &clean,
- DRM_BUDDY_CLEAR_ALLOCATION),
+ GPU_BUDDY_CLEAR_ALLOCATION),
"buddy_alloc hit an error size=%lu\n", 10 * ps);
- drm_buddy_free_list(&mm, &clean, DRM_BUDDY_CLEARED);
- drm_buddy_free_list(&mm, &dirty, 0);
- drm_buddy_fini(&mm);
+ gpu_buddy_free_list(&mm, &clean, GPU_BUDDY_CLEARED);
+ gpu_buddy_free_list(&mm, &dirty, 0);
+ gpu_buddy_fini(&mm);
- KUNIT_EXPECT_FALSE(test, drm_buddy_init(&mm, mm_size, ps));
+ KUNIT_EXPECT_FALSE(test, gpu_buddy_init(&mm, mm_size, ps));
/*
* Create a new mm. Intentionally fragment the address space by creating
@@ -458,34 +458,34 @@ static void drm_test_buddy_alloc_clear(struct kunit *test)
else
list = &clean;
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, 0, mm_size,
ps, ps, list, 0),
"buddy_alloc hit an error size=%lu\n", ps);
} while (++i < n_pages);
- drm_buddy_free_list(&mm, &clean, DRM_BUDDY_CLEARED);
- drm_buddy_free_list(&mm, &dirty, 0);
+ gpu_buddy_free_list(&mm, &clean, GPU_BUDDY_CLEARED);
+ gpu_buddy_free_list(&mm, &dirty, 0);
order = 1;
do {
size = SZ_4K << order;
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, 0, mm_size,
size, size, &allocated,
- DRM_BUDDY_CLEAR_ALLOCATION),
+ GPU_BUDDY_CLEAR_ALLOCATION),
"buddy_alloc hit an error size=%u\n", size);
total = 0;
list_for_each_entry(block, &allocated, link) {
if (size != mm_size)
- KUNIT_EXPECT_EQ(test, drm_buddy_block_is_clear(block), false);
- total += drm_buddy_block_size(&mm, block);
+ KUNIT_EXPECT_EQ(test, gpu_buddy_block_is_clear(block), false);
+ total += gpu_buddy_block_size(&mm, block);
}
KUNIT_EXPECT_EQ(test, total, size);
- drm_buddy_free_list(&mm, &allocated, 0);
+ gpu_buddy_free_list(&mm, &allocated, 0);
} while (++order <= max_order);
- drm_buddy_fini(&mm);
+ gpu_buddy_fini(&mm);
/*
* Create a new mm with a non power-of-two size. Allocate a random size from each
@@ -494,44 +494,44 @@ static void drm_test_buddy_alloc_clear(struct kunit *test)
*/
mm_size = (SZ_4K << max_order) + (SZ_4K << (max_order - 2));
- KUNIT_EXPECT_FALSE(test, drm_buddy_init(&mm, mm_size, ps));
+ KUNIT_EXPECT_FALSE(test, gpu_buddy_init(&mm, mm_size, ps));
KUNIT_EXPECT_EQ(test, mm.max_order, max_order);
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, SZ_4K << max_order,
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, 0, SZ_4K << max_order,
4 * ps, ps, &allocated,
- DRM_BUDDY_RANGE_ALLOCATION),
+ GPU_BUDDY_RANGE_ALLOCATION),
"buddy_alloc hit an error size=%lu\n", 4 * ps);
- drm_buddy_free_list(&mm, &allocated, DRM_BUDDY_CLEARED);
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, SZ_4K << max_order,
+ gpu_buddy_free_list(&mm, &allocated, GPU_BUDDY_CLEARED);
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, 0, SZ_4K << max_order,
2 * ps, ps, &allocated,
- DRM_BUDDY_CLEAR_ALLOCATION),
+ GPU_BUDDY_CLEAR_ALLOCATION),
"buddy_alloc hit an error size=%lu\n", 2 * ps);
- drm_buddy_free_list(&mm, &allocated, DRM_BUDDY_CLEARED);
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, SZ_4K << max_order, mm_size,
+ gpu_buddy_free_list(&mm, &allocated, GPU_BUDDY_CLEARED);
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, SZ_4K << max_order, mm_size,
ps, ps, &allocated,
- DRM_BUDDY_RANGE_ALLOCATION),
+ GPU_BUDDY_RANGE_ALLOCATION),
"buddy_alloc hit an error size=%lu\n", ps);
- drm_buddy_free_list(&mm, &allocated, DRM_BUDDY_CLEARED);
- drm_buddy_fini(&mm);
+ gpu_buddy_free_list(&mm, &allocated, GPU_BUDDY_CLEARED);
+ gpu_buddy_fini(&mm);
}
-static void drm_test_buddy_alloc_contiguous(struct kunit *test)
+static void gpu_test_buddy_alloc_contiguous(struct kunit *test)
{
const unsigned long ps = SZ_4K, mm_size = 16 * 3 * SZ_4K;
unsigned long i, n_pages, total;
- struct drm_buddy_block *block;
- struct drm_buddy mm;
+ struct gpu_buddy_block *block;
+ struct gpu_buddy mm;
LIST_HEAD(left);
LIST_HEAD(middle);
LIST_HEAD(right);
LIST_HEAD(allocated);
- KUNIT_EXPECT_FALSE(test, drm_buddy_init(&mm, mm_size, ps));
+ KUNIT_EXPECT_FALSE(test, gpu_buddy_init(&mm, mm_size, ps));
/*
* Idea is to fragment the address space by alternating block
* allocations between three different lists; one for left, middle and
* right. We can then free a list to simulate fragmentation. In
- * particular we want to exercise the DRM_BUDDY_CONTIGUOUS_ALLOCATION,
+ * particular we want to exercise the GPU_BUDDY_CONTIGUOUS_ALLOCATION,
* including the try_harder path.
*/
@@ -548,66 +548,66 @@ static void drm_test_buddy_alloc_contiguous(struct kunit *test)
else
list = &right;
KUNIT_ASSERT_FALSE_MSG(test,
- drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ gpu_buddy_alloc_blocks(&mm, 0, mm_size,
ps, ps, list, 0),
"buddy_alloc hit an error size=%lu\n",
ps);
} while (++i < n_pages);
- KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ KUNIT_ASSERT_TRUE_MSG(test, gpu_buddy_alloc_blocks(&mm, 0, mm_size,
3 * ps, ps, &allocated,
- DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ GPU_BUDDY_CONTIGUOUS_ALLOCATION),
"buddy_alloc didn't error size=%lu\n", 3 * ps);
- drm_buddy_free_list(&mm, &middle, 0);
- KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ gpu_buddy_free_list(&mm, &middle, 0);
+ KUNIT_ASSERT_TRUE_MSG(test, gpu_buddy_alloc_blocks(&mm, 0, mm_size,
3 * ps, ps, &allocated,
- DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ GPU_BUDDY_CONTIGUOUS_ALLOCATION),
"buddy_alloc didn't error size=%lu\n", 3 * ps);
- KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ KUNIT_ASSERT_TRUE_MSG(test, gpu_buddy_alloc_blocks(&mm, 0, mm_size,
2 * ps, ps, &allocated,
- DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ GPU_BUDDY_CONTIGUOUS_ALLOCATION),
"buddy_alloc didn't error size=%lu\n", 2 * ps);
- drm_buddy_free_list(&mm, &right, 0);
- KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ gpu_buddy_free_list(&mm, &right, 0);
+ KUNIT_ASSERT_TRUE_MSG(test, gpu_buddy_alloc_blocks(&mm, 0, mm_size,
3 * ps, ps, &allocated,
- DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ GPU_BUDDY_CONTIGUOUS_ALLOCATION),
"buddy_alloc didn't error size=%lu\n", 3 * ps);
/*
* At this point we should have enough contiguous space for 2 blocks,
* however they are never buddies (since we freed middle and right) so
* will require the try_harder logic to find them.
*/
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, 0, mm_size,
2 * ps, ps, &allocated,
- DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ GPU_BUDDY_CONTIGUOUS_ALLOCATION),
"buddy_alloc hit an error size=%lu\n", 2 * ps);
- drm_buddy_free_list(&mm, &left, 0);
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size,
+ gpu_buddy_free_list(&mm, &left, 0);
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, 0, mm_size,
3 * ps, ps, &allocated,
- DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ GPU_BUDDY_CONTIGUOUS_ALLOCATION),
"buddy_alloc hit an error size=%lu\n", 3 * ps);
total = 0;
list_for_each_entry(block, &allocated, link)
- total += drm_buddy_block_size(&mm, block);
+ total += gpu_buddy_block_size(&mm, block);
KUNIT_ASSERT_EQ(test, total, ps * 2 + ps * 3);
- drm_buddy_free_list(&mm, &allocated, 0);
- drm_buddy_fini(&mm);
+ gpu_buddy_free_list(&mm, &allocated, 0);
+ gpu_buddy_fini(&mm);
}
-static void drm_test_buddy_alloc_pathological(struct kunit *test)
+static void gpu_test_buddy_alloc_pathological(struct kunit *test)
{
u64 mm_size, size, start = 0;
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
const int max_order = 3;
unsigned long flags = 0;
int order, top;
- struct drm_buddy mm;
+ struct gpu_buddy mm;
LIST_HEAD(blocks);
LIST_HEAD(holes);
LIST_HEAD(tmp);
@@ -620,7 +620,7 @@ static void drm_test_buddy_alloc_pathological(struct kunit *test)
*/
mm_size = SZ_4K << max_order;
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, SZ_4K),
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_init(&mm, mm_size, SZ_4K),
"buddy_init failed\n");
KUNIT_EXPECT_EQ(test, mm.max_order, max_order);
@@ -630,18 +630,18 @@ static void drm_test_buddy_alloc_pathological(struct kunit *test)
block = list_first_entry_or_null(&blocks, typeof(*block), link);
if (block) {
list_del(&block->link);
- drm_buddy_free_block(&mm, block);
+ gpu_buddy_free_block(&mm, block);
}
for (order = top; order--;) {
size = get_size(order, mm.chunk_size);
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start,
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, start,
mm_size, size, size,
&tmp, flags),
"buddy_alloc hit -ENOMEM with order=%d, top=%d\n",
order, top);
- block = list_first_entry_or_null(&tmp, struct drm_buddy_block, link);
+ block = list_first_entry_or_null(&tmp, struct gpu_buddy_block, link);
KUNIT_ASSERT_TRUE_MSG(test, block, "alloc_blocks has no blocks\n");
list_move_tail(&block->link, &blocks);
@@ -649,45 +649,45 @@ static void drm_test_buddy_alloc_pathological(struct kunit *test)
/* There should be one final page for this sub-allocation */
size = get_size(0, mm.chunk_size);
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, start, mm_size,
size, size, &tmp, flags),
"buddy_alloc hit -ENOMEM for hole\n");
- block = list_first_entry_or_null(&tmp, struct drm_buddy_block, link);
+ block = list_first_entry_or_null(&tmp, struct gpu_buddy_block, link);
KUNIT_ASSERT_TRUE_MSG(test, block, "alloc_blocks has no blocks\n");
list_move_tail(&block->link, &holes);
size = get_size(top, mm.chunk_size);
- KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
+ KUNIT_ASSERT_TRUE_MSG(test, gpu_buddy_alloc_blocks(&mm, start, mm_size,
size, size, &tmp, flags),
"buddy_alloc unexpectedly succeeded at top-order %d/%d, it should be full!",
top, max_order);
}
- drm_buddy_free_list(&mm, &holes, 0);
+ gpu_buddy_free_list(&mm, &holes, 0);
/* Nothing larger than blocks of chunk_size now available */
for (order = 1; order <= max_order; order++) {
size = get_size(order, mm.chunk_size);
- KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
+ KUNIT_ASSERT_TRUE_MSG(test, gpu_buddy_alloc_blocks(&mm, start, mm_size,
size, size, &tmp, flags),
"buddy_alloc unexpectedly succeeded at order %d, it should be full!",
order);
}
list_splice_tail(&holes, &blocks);
- drm_buddy_free_list(&mm, &blocks, 0);
- drm_buddy_fini(&mm);
+ gpu_buddy_free_list(&mm, &blocks, 0);
+ gpu_buddy_fini(&mm);
}
-static void drm_test_buddy_alloc_pessimistic(struct kunit *test)
+static void gpu_test_buddy_alloc_pessimistic(struct kunit *test)
{
u64 mm_size, size, start = 0;
- struct drm_buddy_block *block, *bn;
+ struct gpu_buddy_block *block, *bn;
const unsigned int max_order = 16;
unsigned long flags = 0;
- struct drm_buddy mm;
+ struct gpu_buddy mm;
unsigned int order;
LIST_HEAD(blocks);
LIST_HEAD(tmp);
@@ -699,19 +699,19 @@ static void drm_test_buddy_alloc_pessimistic(struct kunit *test)
*/
mm_size = SZ_4K << max_order;
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, SZ_4K),
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_init(&mm, mm_size, SZ_4K),
"buddy_init failed\n");
KUNIT_EXPECT_EQ(test, mm.max_order, max_order);
for (order = 0; order < max_order; order++) {
size = get_size(order, mm.chunk_size);
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, start, mm_size,
size, size, &tmp, flags),
"buddy_alloc hit -ENOMEM with order=%d\n",
order);
- block = list_first_entry_or_null(&tmp, struct drm_buddy_block, link);
+ block = list_first_entry_or_null(&tmp, struct gpu_buddy_block, link);
KUNIT_ASSERT_TRUE_MSG(test, block, "alloc_blocks has no blocks\n");
list_move_tail(&block->link, &blocks);
@@ -719,11 +719,11 @@ static void drm_test_buddy_alloc_pessimistic(struct kunit *test)
/* And now the last remaining block available */
size = get_size(0, mm.chunk_size);
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, start, mm_size,
size, size, &tmp, flags),
"buddy_alloc hit -ENOMEM on final alloc\n");
- block = list_first_entry_or_null(&tmp, struct drm_buddy_block, link);
+ block = list_first_entry_or_null(&tmp, struct gpu_buddy_block, link);
KUNIT_ASSERT_TRUE_MSG(test, block, "alloc_blocks has no blocks\n");
list_move_tail(&block->link, &blocks);
@@ -731,58 +731,58 @@ static void drm_test_buddy_alloc_pessimistic(struct kunit *test)
/* Should be completely full! */
for (order = max_order; order--;) {
size = get_size(order, mm.chunk_size);
- KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
+ KUNIT_ASSERT_TRUE_MSG(test, gpu_buddy_alloc_blocks(&mm, start, mm_size,
size, size, &tmp, flags),
"buddy_alloc unexpectedly succeeded, it should be full!");
}
block = list_last_entry(&blocks, typeof(*block), link);
list_del(&block->link);
- drm_buddy_free_block(&mm, block);
+ gpu_buddy_free_block(&mm, block);
/* As we free in increasing size, we make available larger blocks */
order = 1;
list_for_each_entry_safe(block, bn, &blocks, link) {
list_del(&block->link);
- drm_buddy_free_block(&mm, block);
+ gpu_buddy_free_block(&mm, block);
size = get_size(order, mm.chunk_size);
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, start, mm_size,
size, size, &tmp, flags),
"buddy_alloc hit -ENOMEM with order=%d\n",
order);
- block = list_first_entry_or_null(&tmp, struct drm_buddy_block, link);
+ block = list_first_entry_or_null(&tmp, struct gpu_buddy_block, link);
KUNIT_ASSERT_TRUE_MSG(test, block, "alloc_blocks has no blocks\n");
list_del(&block->link);
- drm_buddy_free_block(&mm, block);
+ gpu_buddy_free_block(&mm, block);
order++;
}
/* To confirm, now the whole mm should be available */
size = get_size(max_order, mm.chunk_size);
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, start, mm_size,
size, size, &tmp, flags),
"buddy_alloc (realloc) hit -ENOMEM with order=%d\n",
max_order);
- block = list_first_entry_or_null(&tmp, struct drm_buddy_block, link);
+ block = list_first_entry_or_null(&tmp, struct gpu_buddy_block, link);
KUNIT_ASSERT_TRUE_MSG(test, block, "alloc_blocks has no blocks\n");
list_del(&block->link);
- drm_buddy_free_block(&mm, block);
- drm_buddy_free_list(&mm, &blocks, 0);
- drm_buddy_fini(&mm);
+ gpu_buddy_free_block(&mm, block);
+ gpu_buddy_free_list(&mm, &blocks, 0);
+ gpu_buddy_fini(&mm);
}
-static void drm_test_buddy_alloc_optimistic(struct kunit *test)
+static void gpu_test_buddy_alloc_optimistic(struct kunit *test)
{
u64 mm_size, size, start = 0;
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
unsigned long flags = 0;
const int max_order = 16;
- struct drm_buddy mm;
+ struct gpu_buddy mm;
LIST_HEAD(blocks);
LIST_HEAD(tmp);
int order;
@@ -794,19 +794,19 @@ static void drm_test_buddy_alloc_optimistic(struct kunit *test)
mm_size = SZ_4K * ((1 << (max_order + 1)) - 1);
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, SZ_4K),
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_init(&mm, mm_size, SZ_4K),
"buddy_init failed\n");
KUNIT_EXPECT_EQ(test, mm.max_order, max_order);
for (order = 0; order <= max_order; order++) {
size = get_size(order, mm.chunk_size);
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, start, mm_size,
size, size, &tmp, flags),
"buddy_alloc hit -ENOMEM with order=%d\n",
order);
- block = list_first_entry_or_null(&tmp, struct drm_buddy_block, link);
+ block = list_first_entry_or_null(&tmp, struct gpu_buddy_block, link);
KUNIT_ASSERT_TRUE_MSG(test, block, "alloc_blocks has no blocks\n");
list_move_tail(&block->link, &blocks);
@@ -814,115 +814,115 @@ static void drm_test_buddy_alloc_optimistic(struct kunit *test)
/* Should be completely full! */
size = get_size(0, mm.chunk_size);
- KUNIT_ASSERT_TRUE_MSG(test, drm_buddy_alloc_blocks(&mm, start, mm_size,
+ KUNIT_ASSERT_TRUE_MSG(test, gpu_buddy_alloc_blocks(&mm, start, mm_size,
size, size, &tmp, flags),
"buddy_alloc unexpectedly succeeded, it should be full!");
- drm_buddy_free_list(&mm, &blocks, 0);
- drm_buddy_fini(&mm);
+ gpu_buddy_free_list(&mm, &blocks, 0);
+ gpu_buddy_fini(&mm);
}
-static void drm_test_buddy_alloc_limit(struct kunit *test)
+static void gpu_test_buddy_alloc_limit(struct kunit *test)
{
u64 size = U64_MAX, start = 0;
- struct drm_buddy_block *block;
+ struct gpu_buddy_block *block;
unsigned long flags = 0;
LIST_HEAD(allocated);
- struct drm_buddy mm;
+ struct gpu_buddy mm;
- KUNIT_EXPECT_FALSE(test, drm_buddy_init(&mm, size, SZ_4K));
+ KUNIT_EXPECT_FALSE(test, gpu_buddy_init(&mm, size, SZ_4K));
- KUNIT_EXPECT_EQ_MSG(test, mm.max_order, DRM_BUDDY_MAX_ORDER,
+ KUNIT_EXPECT_EQ_MSG(test, mm.max_order, GPU_BUDDY_MAX_ORDER,
"mm.max_order(%d) != %d\n", mm.max_order,
- DRM_BUDDY_MAX_ORDER);
+ GPU_BUDDY_MAX_ORDER);
size = mm.chunk_size << mm.max_order;
- KUNIT_EXPECT_FALSE(test, drm_buddy_alloc_blocks(&mm, start, size, size,
+ KUNIT_EXPECT_FALSE(test, gpu_buddy_alloc_blocks(&mm, start, size, size,
mm.chunk_size, &allocated, flags));
- block = list_first_entry_or_null(&allocated, struct drm_buddy_block, link);
+ block = list_first_entry_or_null(&allocated, struct gpu_buddy_block, link);
KUNIT_EXPECT_TRUE(test, block);
- KUNIT_EXPECT_EQ_MSG(test, drm_buddy_block_order(block), mm.max_order,
+ KUNIT_EXPECT_EQ_MSG(test, gpu_buddy_block_order(block), mm.max_order,
"block order(%d) != %d\n",
- drm_buddy_block_order(block), mm.max_order);
+ gpu_buddy_block_order(block), mm.max_order);
- KUNIT_EXPECT_EQ_MSG(test, drm_buddy_block_size(&mm, block),
+ KUNIT_EXPECT_EQ_MSG(test, gpu_buddy_block_size(&mm, block),
BIT_ULL(mm.max_order) * mm.chunk_size,
"block size(%llu) != %llu\n",
- drm_buddy_block_size(&mm, block),
+ gpu_buddy_block_size(&mm, block),
BIT_ULL(mm.max_order) * mm.chunk_size);
- drm_buddy_free_list(&mm, &allocated, 0);
- drm_buddy_fini(&mm);
+ gpu_buddy_free_list(&mm, &allocated, 0);
+ gpu_buddy_fini(&mm);
}
-static void drm_test_buddy_alloc_exceeds_max_order(struct kunit *test)
+static void gpu_test_buddy_alloc_exceeds_max_order(struct kunit *test)
{
u64 mm_size = SZ_8G + SZ_2G, size = SZ_8G + SZ_1G, min_block_size = SZ_8G;
- struct drm_buddy mm;
+ struct gpu_buddy mm;
LIST_HEAD(blocks);
int err;
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_init(&mm, mm_size, SZ_4K),
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_init(&mm, mm_size, SZ_4K),
"buddy_init failed\n");
/* CONTIGUOUS allocation should succeed via try_harder fallback */
- KUNIT_ASSERT_FALSE_MSG(test, drm_buddy_alloc_blocks(&mm, 0, mm_size, size,
+ KUNIT_ASSERT_FALSE_MSG(test, gpu_buddy_alloc_blocks(&mm, 0, mm_size, size,
SZ_4K, &blocks,
- DRM_BUDDY_CONTIGUOUS_ALLOCATION),
+ GPU_BUDDY_CONTIGUOUS_ALLOCATION),
"buddy_alloc hit an error size=%llu\n", size);
- drm_buddy_free_list(&mm, &blocks, 0);
+ gpu_buddy_free_list(&mm, &blocks, 0);
/* Non-CONTIGUOUS with large min_block_size should return -EINVAL */
- err = drm_buddy_alloc_blocks(&mm, 0, mm_size, size, min_block_size, &blocks, 0);
+ err = gpu_buddy_alloc_blocks(&mm, 0, mm_size, size, min_block_size, &blocks, 0);
KUNIT_EXPECT_EQ(test, err, -EINVAL);
/* Non-CONTIGUOUS + RANGE with large min_block_size should return -EINVAL */
- err = drm_buddy_alloc_blocks(&mm, 0, mm_size, size, min_block_size, &blocks,
- DRM_BUDDY_RANGE_ALLOCATION);
+ err = gpu_buddy_alloc_blocks(&mm, 0, mm_size, size, min_block_size, &blocks,
+ GPU_BUDDY_RANGE_ALLOCATION);
KUNIT_EXPECT_EQ(test, err, -EINVAL);
/* CONTIGUOUS + RANGE should return -EINVAL (no try_harder for RANGE) */
- err = drm_buddy_alloc_blocks(&mm, 0, mm_size, size, SZ_4K, &blocks,
- DRM_BUDDY_CONTIGUOUS_ALLOCATION | DRM_BUDDY_RANGE_ALLOCATION);
+ err = gpu_buddy_alloc_blocks(&mm, 0, mm_size, size, SZ_4K, &blocks,
+ GPU_BUDDY_CONTIGUOUS_ALLOCATION | GPU_BUDDY_RANGE_ALLOCATION);
KUNIT_EXPECT_EQ(test, err, -EINVAL);
- drm_buddy_fini(&mm);
+ gpu_buddy_fini(&mm);
}
-static int drm_buddy_suite_init(struct kunit_suite *suite)
+static int gpu_buddy_suite_init(struct kunit_suite *suite)
{
while (!random_seed)
random_seed = get_random_u32();
- kunit_info(suite, "Testing DRM buddy manager, with random_seed=0x%x\n",
+ kunit_info(suite, "Testing GPU buddy manager, with random_seed=0x%x\n",
random_seed);
return 0;
}
-static struct kunit_case drm_buddy_tests[] = {
- KUNIT_CASE(drm_test_buddy_alloc_limit),
- KUNIT_CASE(drm_test_buddy_alloc_optimistic),
- KUNIT_CASE(drm_test_buddy_alloc_pessimistic),
- KUNIT_CASE(drm_test_buddy_alloc_pathological),
- KUNIT_CASE(drm_test_buddy_alloc_contiguous),
- KUNIT_CASE(drm_test_buddy_alloc_clear),
- KUNIT_CASE(drm_test_buddy_alloc_range_bias),
- KUNIT_CASE(drm_test_buddy_fragmentation_performance),
- KUNIT_CASE(drm_test_buddy_alloc_exceeds_max_order),
+static struct kunit_case gpu_buddy_tests[] = {
+ KUNIT_CASE(gpu_test_buddy_alloc_limit),
+ KUNIT_CASE(gpu_test_buddy_alloc_optimistic),
+ KUNIT_CASE(gpu_test_buddy_alloc_pessimistic),
+ KUNIT_CASE(gpu_test_buddy_alloc_pathological),
+ KUNIT_CASE(gpu_test_buddy_alloc_contiguous),
+ KUNIT_CASE(gpu_test_buddy_alloc_clear),
+ KUNIT_CASE(gpu_test_buddy_alloc_range_bias),
+ KUNIT_CASE(gpu_test_buddy_fragmentation_performance),
+ KUNIT_CASE(gpu_test_buddy_alloc_exceeds_max_order),
{}
};
-static struct kunit_suite drm_buddy_test_suite = {
- .name = "drm_buddy",
- .suite_init = drm_buddy_suite_init,
- .test_cases = drm_buddy_tests,
+static struct kunit_suite gpu_buddy_test_suite = {
+ .name = "gpu_buddy",
+ .suite_init = gpu_buddy_suite_init,
+ .test_cases = gpu_buddy_tests,
};
-kunit_test_suite(drm_buddy_test_suite);
+kunit_test_suite(gpu_buddy_test_suite);
MODULE_AUTHOR("Intel Corporation");
-MODULE_DESCRIPTION("Kunit test for drm_buddy functions");
+MODULE_DESCRIPTION("Kunit test for gpu_buddy functions");
MODULE_LICENSE("GPL");
diff --git a/drivers/gpu/tests/gpu_random.c b/drivers/gpu/tests/gpu_random.c
index ddd1f594b5d5..6356372f7e52 100644
--- a/drivers/gpu/tests/gpu_random.c
+++ b/drivers/gpu/tests/gpu_random.c
@@ -8,26 +8,26 @@
#include "gpu_random.h"
-u32 drm_prandom_u32_max_state(u32 ep_ro, struct rnd_state *state)
+u32 gpu_prandom_u32_max_state(u32 ep_ro, struct rnd_state *state)
{
return upper_32_bits((u64)prandom_u32_state(state) * ep_ro);
}
-EXPORT_SYMBOL(drm_prandom_u32_max_state);
+EXPORT_SYMBOL(gpu_prandom_u32_max_state);
-void drm_random_reorder(unsigned int *order, unsigned int count,
+void gpu_random_reorder(unsigned int *order, unsigned int count,
struct rnd_state *state)
{
unsigned int i, j;
for (i = 0; i < count; ++i) {
BUILD_BUG_ON(sizeof(unsigned int) > sizeof(u32));
- j = drm_prandom_u32_max_state(count, state);
+ j = gpu_prandom_u32_max_state(count, state);
swap(order[i], order[j]);
}
}
-EXPORT_SYMBOL(drm_random_reorder);
+EXPORT_SYMBOL(gpu_random_reorder);
-unsigned int *drm_random_order(unsigned int count, struct rnd_state *state)
+unsigned int *gpu_random_order(unsigned int count, struct rnd_state *state)
{
unsigned int *order, i;
@@ -38,7 +38,7 @@ unsigned int *drm_random_order(unsigned int count, struct rnd_state *state)
for (i = 0; i < count; i++)
order[i] = i;
- drm_random_reorder(order, count, state);
+ gpu_random_reorder(order, count, state);
return order;
}
-EXPORT_SYMBOL(drm_random_order);
+EXPORT_SYMBOL(gpu_random_order);
diff --git a/drivers/gpu/tests/gpu_random.h b/drivers/gpu/tests/gpu_random.h
index 9f827260a89d..b68cf3448264 100644
--- a/drivers/gpu/tests/gpu_random.h
+++ b/drivers/gpu/tests/gpu_random.h
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef __DRM_RANDOM_H__
-#define __DRM_RANDOM_H__
+#ifndef __GPU_RANDOM_H__
+#define __GPU_RANDOM_H__
/* This is a temporary home for a couple of utility functions that should
* be transposed to lib/ at the earliest convenience.
@@ -8,21 +8,21 @@
#include <linux/prandom.h>
-#define DRM_RND_STATE_INITIALIZER(seed__) ({ \
+#define GPU_RND_STATE_INITIALIZER(seed__) ({ \
struct rnd_state state__; \
prandom_seed_state(&state__, (seed__)); \
state__; \
})
-#define DRM_RND_STATE(name__, seed__) \
- struct rnd_state name__ = DRM_RND_STATE_INITIALIZER(seed__)
+#define GPU_RND_STATE(name__, seed__) \
+ struct rnd_state name__ = GPU_RND_STATE_INITIALIZER(seed__)
-unsigned int *drm_random_order(unsigned int count,
+unsigned int *gpu_random_order(unsigned int count,
struct rnd_state *state);
-void drm_random_reorder(unsigned int *order,
+void gpu_random_reorder(unsigned int *order,
unsigned int count,
struct rnd_state *state);
-u32 drm_prandom_u32_max_state(u32 ep_ro,
+u32 gpu_prandom_u32_max_state(u32 ep_ro,
struct rnd_state *state);
-#endif /* !__DRM_RANDOM_H__ */
+#endif /* !__GPU_RANDOM_H__ */
diff --git a/drivers/video/Kconfig b/drivers/video/Kconfig
index 9884f003247d..a7144d275f54 100644
--- a/drivers/video/Kconfig
+++ b/drivers/video/Kconfig
@@ -37,6 +37,7 @@ source "drivers/char/agp/Kconfig"
source "drivers/gpu/vga/Kconfig"
+source "drivers/gpu/Kconfig"
source "drivers/gpu/host1x/Kconfig"
source "drivers/gpu/ipu-v3/Kconfig"
source "drivers/gpu/nova-core/Kconfig"
diff --git a/include/drm/drm_buddy.h b/include/drm/drm_buddy.h
new file mode 100644
index 000000000000..3054369bebff
--- /dev/null
+++ b/include/drm/drm_buddy.h
@@ -0,0 +1,18 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2021 Intel Corporation
+ */
+
+#ifndef __DRM_BUDDY_H__
+#define __DRM_BUDDY_H__
+
+#include <linux/gpu_buddy.h>
+
+struct drm_printer;
+
+/* DRM-specific GPU Buddy Allocator print helpers */
+void drm_buddy_print(struct gpu_buddy *mm, struct drm_printer *p);
+void drm_buddy_block_print(struct gpu_buddy *mm,
+ struct gpu_buddy_block *block,
+ struct drm_printer *p);
+#endif
diff --git a/include/linux/gpu_buddy.h b/include/linux/gpu_buddy.h
index b909fa8f810a..07ac65db6d2e 100644
--- a/include/linux/gpu_buddy.h
+++ b/include/linux/gpu_buddy.h
@@ -3,8 +3,8 @@
* Copyright © 2021 Intel Corporation
*/
-#ifndef __DRM_BUDDY_H__
-#define __DRM_BUDDY_H__
+#ifndef __GPU_BUDDY_H__
+#define __GPU_BUDDY_H__
#include <linux/bitops.h>
#include <linux/list.h>
@@ -12,38 +12,45 @@
#include <linux/sched.h>
#include <linux/rbtree.h>
-struct drm_printer;
+#define GPU_BUDDY_RANGE_ALLOCATION BIT(0)
+#define GPU_BUDDY_TOPDOWN_ALLOCATION BIT(1)
+#define GPU_BUDDY_CONTIGUOUS_ALLOCATION BIT(2)
+#define GPU_BUDDY_CLEAR_ALLOCATION BIT(3)
+#define GPU_BUDDY_CLEARED BIT(4)
+#define GPU_BUDDY_TRIM_DISABLE BIT(5)
-#define DRM_BUDDY_RANGE_ALLOCATION BIT(0)
-#define DRM_BUDDY_TOPDOWN_ALLOCATION BIT(1)
-#define DRM_BUDDY_CONTIGUOUS_ALLOCATION BIT(2)
-#define DRM_BUDDY_CLEAR_ALLOCATION BIT(3)
-#define DRM_BUDDY_CLEARED BIT(4)
-#define DRM_BUDDY_TRIM_DISABLE BIT(5)
+enum gpu_buddy_free_tree {
+ GPU_BUDDY_CLEAR_TREE = 0,
+ GPU_BUDDY_DIRTY_TREE,
+ GPU_BUDDY_MAX_FREE_TREES,
+};
-struct drm_buddy_block {
-#define DRM_BUDDY_HEADER_OFFSET GENMASK_ULL(63, 12)
-#define DRM_BUDDY_HEADER_STATE GENMASK_ULL(11, 10)
-#define DRM_BUDDY_ALLOCATED (1 << 10)
-#define DRM_BUDDY_FREE (2 << 10)
-#define DRM_BUDDY_SPLIT (3 << 10)
-#define DRM_BUDDY_HEADER_CLEAR GENMASK_ULL(9, 9)
+#define for_each_free_tree(tree) \
+ for ((tree) = 0; (tree) < GPU_BUDDY_MAX_FREE_TREES; (tree)++)
+
+struct gpu_buddy_block {
+#define GPU_BUDDY_HEADER_OFFSET GENMASK_ULL(63, 12)
+#define GPU_BUDDY_HEADER_STATE GENMASK_ULL(11, 10)
+#define GPU_BUDDY_ALLOCATED (1 << 10)
+#define GPU_BUDDY_FREE (2 << 10)
+#define GPU_BUDDY_SPLIT (3 << 10)
+#define GPU_BUDDY_HEADER_CLEAR GENMASK_ULL(9, 9)
/* Free to be used, if needed in the future */
-#define DRM_BUDDY_HEADER_UNUSED GENMASK_ULL(8, 6)
-#define DRM_BUDDY_HEADER_ORDER GENMASK_ULL(5, 0)
+#define GPU_BUDDY_HEADER_UNUSED GENMASK_ULL(8, 6)
+#define GPU_BUDDY_HEADER_ORDER GENMASK_ULL(5, 0)
u64 header;
- struct drm_buddy_block *left;
- struct drm_buddy_block *right;
- struct drm_buddy_block *parent;
+ struct gpu_buddy_block *left;
+ struct gpu_buddy_block *right;
+ struct gpu_buddy_block *parent;
void *private; /* owned by creator */
/*
- * While the block is allocated by the user through drm_buddy_alloc*,
+ * While the block is allocated by the user through gpu_buddy_alloc*,
* the user has ownership of the link, for example to maintain within
* a list, if so desired. As soon as the block is freed with
- * drm_buddy_free* ownership is given back to the mm.
+ * gpu_buddy_free* ownership is given back to the mm.
*/
union {
struct rb_node rb;
@@ -54,15 +61,15 @@ struct drm_buddy_block {
};
/* Order-zero must be at least SZ_4K */
-#define DRM_BUDDY_MAX_ORDER (63 - 12)
+#define GPU_BUDDY_MAX_ORDER (63 - 12)
/*
* Binary Buddy System.
*
* Locking should be handled by the user, a simple mutex around
- * drm_buddy_alloc* and drm_buddy_free* should suffice.
+ * gpu_buddy_alloc* and gpu_buddy_free* should suffice.
*/
-struct drm_buddy {
+struct gpu_buddy {
/* Maintain a free list for each order. */
struct rb_root **free_trees;
@@ -73,7 +80,7 @@ struct drm_buddy {
* block. Nodes are either allocated or free, in which case they will
* also exist on the respective free list.
*/
- struct drm_buddy_block **roots;
+ struct gpu_buddy_block **roots;
/*
* Anything from here is public, and remains static for the lifetime of
@@ -90,82 +97,81 @@ struct drm_buddy {
};
static inline u64
-drm_buddy_block_offset(const struct drm_buddy_block *block)
+gpu_buddy_block_offset(const struct gpu_buddy_block *block)
{
- return block->header & DRM_BUDDY_HEADER_OFFSET;
+ return block->header & GPU_BUDDY_HEADER_OFFSET;
}
static inline unsigned int
-drm_buddy_block_order(struct drm_buddy_block *block)
+gpu_buddy_block_order(struct gpu_buddy_block *block)
{
- return block->header & DRM_BUDDY_HEADER_ORDER;
+ return block->header & GPU_BUDDY_HEADER_ORDER;
}
static inline unsigned int
-drm_buddy_block_state(struct drm_buddy_block *block)
+gpu_buddy_block_state(struct gpu_buddy_block *block)
{
- return block->header & DRM_BUDDY_HEADER_STATE;
+ return block->header & GPU_BUDDY_HEADER_STATE;
}
static inline bool
-drm_buddy_block_is_allocated(struct drm_buddy_block *block)
+gpu_buddy_block_is_allocated(struct gpu_buddy_block *block)
{
- return drm_buddy_block_state(block) == DRM_BUDDY_ALLOCATED;
+ return gpu_buddy_block_state(block) == GPU_BUDDY_ALLOCATED;
}
static inline bool
-drm_buddy_block_is_clear(struct drm_buddy_block *block)
+gpu_buddy_block_is_clear(struct gpu_buddy_block *block)
{
- return block->header & DRM_BUDDY_HEADER_CLEAR;
+ return block->header & GPU_BUDDY_HEADER_CLEAR;
}
static inline bool
-drm_buddy_block_is_free(struct drm_buddy_block *block)
+gpu_buddy_block_is_free(struct gpu_buddy_block *block)
{
- return drm_buddy_block_state(block) == DRM_BUDDY_FREE;
+ return gpu_buddy_block_state(block) == GPU_BUDDY_FREE;
}
static inline bool
-drm_buddy_block_is_split(struct drm_buddy_block *block)
+gpu_buddy_block_is_split(struct gpu_buddy_block *block)
{
- return drm_buddy_block_state(block) == DRM_BUDDY_SPLIT;
+ return gpu_buddy_block_state(block) == GPU_BUDDY_SPLIT;
}
static inline u64
-drm_buddy_block_size(struct drm_buddy *mm,
- struct drm_buddy_block *block)
+gpu_buddy_block_size(struct gpu_buddy *mm,
+ struct gpu_buddy_block *block)
{
- return mm->chunk_size << drm_buddy_block_order(block);
+ return mm->chunk_size << gpu_buddy_block_order(block);
}
-int drm_buddy_init(struct drm_buddy *mm, u64 size, u64 chunk_size);
+int gpu_buddy_init(struct gpu_buddy *mm, u64 size, u64 chunk_size);
-void drm_buddy_fini(struct drm_buddy *mm);
+void gpu_buddy_fini(struct gpu_buddy *mm);
-struct drm_buddy_block *
-drm_get_buddy(struct drm_buddy_block *block);
+struct gpu_buddy_block *
+gpu_get_buddy(struct gpu_buddy_block *block);
-int drm_buddy_alloc_blocks(struct drm_buddy *mm,
+int gpu_buddy_alloc_blocks(struct gpu_buddy *mm,
u64 start, u64 end, u64 size,
u64 min_page_size,
struct list_head *blocks,
unsigned long flags);
-int drm_buddy_block_trim(struct drm_buddy *mm,
+int gpu_buddy_block_trim(struct gpu_buddy *mm,
u64 *start,
u64 new_size,
struct list_head *blocks);
-void drm_buddy_reset_clear(struct drm_buddy *mm, bool is_clear);
+void gpu_buddy_reset_clear(struct gpu_buddy *mm, bool is_clear);
-void drm_buddy_free_block(struct drm_buddy *mm, struct drm_buddy_block *block);
+void gpu_buddy_free_block(struct gpu_buddy *mm, struct gpu_buddy_block *block);
-void drm_buddy_free_list(struct drm_buddy *mm,
+void gpu_buddy_free_list(struct gpu_buddy *mm,
struct list_head *objects,
unsigned int flags);
-void drm_buddy_print(struct drm_buddy *mm, struct drm_printer *p);
-void drm_buddy_block_print(struct drm_buddy *mm,
- struct drm_buddy_block *block,
- struct drm_printer *p);
+void gpu_buddy_print(struct gpu_buddy *mm);
+void gpu_buddy_block_print(struct gpu_buddy *mm,
+ struct gpu_buddy_block *block);
#endif
--
2.34.1
^ permalink raw reply related
* [PATCH v11 4/4] rust: gpu: Add GPU buddy allocator bindings
From: Joel Fernandes @ 2026-02-24 22:40 UTC (permalink / raw)
To: linux-kernel
Cc: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Dave Airlie, Daniel Almeida, Koen Koning,
dri-devel, nouveau, rust-for-linux, Nikola Djukic,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jonathan Corbet, Alex Deucher,
Christian König, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Huang Rui, Matthew Auld, Matthew Brost,
Lucas De Marchi, Thomas Hellström, Helge Deller, Alex Gaynor,
Boqun Feng, John Hubbard, Alistair Popple, Timur Tabi, Edwin Peer,
Alexandre Courbot, Andrea Righi, Andy Ritger, Zhi Wang,
Balbir Singh, Philipp Stanner, Elle Rhumsaa, alexeyi,
Eliot Courtney, joel, linux-doc, amd-gfx, intel-gfx, intel-xe,
linux-fbdev, Joel Fernandes
In-Reply-To: <20260224224005.3232841-1-joelagnelf@nvidia.com>
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 useful for GPU physical memory
allocation. nova-core will use it for physical memory allocation.
Cc: Nikola Djukic <ndjukic@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
MAINTAINERS | 8 +
rust/bindings/bindings_helper.h | 11 +
rust/helpers/gpu.c | 23 ++
rust/helpers/helpers.c | 1 +
rust/kernel/gpu/buddy.rs | 536 ++++++++++++++++++++++++++++++++
rust/kernel/gpu/mod.rs | 5 +
rust/kernel/lib.rs | 2 +
7 files changed, 586 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/MAINTAINERS b/MAINTAINERS
index f1e5a8011d2f..6befe3890f78 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -23191,6 +23191,14 @@ S: Maintained
T: git https://github.com/Rust-for-Linux/linux.git ffi-next
F: rust/kernel/ffi/
+RUST [GPU BUDDY]
+M: Joel Fernandes <joelagnelf@nvidia.com>
+L: dri-devel@lists.freedesktop.org
+L: rust-for-linux@vger.kernel.org
+S: Maintained
+F: rust/helpers/gpu.c
+F: rust/kernel/gpu/
+
RUST [NUM]
M: Alexandre Courbot <acourbot@nvidia.com>
R: Yury Norov <yury.norov@gmail.com>
diff --git a/rust/bindings/bindings_helper.h b/rust/bindings/bindings_helper.h
index 083cc44aa952..dbb765a9fdbd 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>
@@ -146,6 +147,16 @@ const vm_flags_t RUST_CONST_HELPER_VM_MIXEDMAP = VM_MIXEDMAP;
const vm_flags_t RUST_CONST_HELPER_VM_HUGEPAGE = VM_HUGEPAGE;
const vm_flags_t RUST_CONST_HELPER_VM_NOHUGEPAGE = VM_NOHUGEPAGE;
+#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..38b1a4e6bef8
--- /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
+
+__rust_helper u64 rust_helper_gpu_buddy_block_offset(const struct gpu_buddy_block *block)
+{
+ return gpu_buddy_block_offset(block);
+}
+
+__rust_helper unsigned int rust_helper_gpu_buddy_block_order(struct gpu_buddy_block *block)
+{
+ return gpu_buddy_block_order(block);
+}
+
+__rust_helper 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 724fcb8240ac..a53929ce52a3 100644
--- a/rust/helpers/helpers.c
+++ b/rust/helpers/helpers.c
@@ -32,6 +32,7 @@
#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..4383f82c0fc1
--- /dev/null
+++ b/rust/kernel/gpu/buddy.rs
@@ -0,0 +1,536 @@
+// 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 buddy = GpuBuddy::new(GpuBuddyParams {
+//! base_offset_bytes: 0,
+//! 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 - mutated between calls for field overrides.
+//! let mut 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).
+//! params.buddy_flags = BuddyFlags::try_new(BuddyFlags::TOPDOWN_ALLOCATION)?;
+//! let topdown = KBox::pin_init(buddy.alloc_blocks(¶ms), GFP_KERNEL)?;
+//! 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.
+//! params.buddy_flags = BuddyFlags::try_new(BuddyFlags::RANGE_ALLOCATION)?;
+//! let allocated = KBox::pin_init(buddy.alloc_blocks(¶ms), GFP_KERNEL)?;
+//! 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).
+//! params.end_range_address = SZ_4M as u64;
+//! params.size_bytes = SZ_4M as u64;
+//! params.min_block_size_bytes = SZ_4M as u64;
+//! let frag1 = KBox::pin_init(buddy.alloc_blocks(¶ms), GFP_KERNEL)?;
+//! assert_eq!(buddy.free_memory_bytes(), initial_free - SZ_4M as u64);
+//!
+//! params.start_range_address = SZ_8M as u64;
+//! params.end_range_address = (SZ_8M + SZ_4M) as u64;
+//! let frag2 = KBox::pin_init(buddy.alloc_blocks(¶ms), GFP_KERNEL)?;
+//! assert_eq!(buddy.free_memory_bytes(), initial_free - SZ_8M as u64);
+//!
+//! // Allocate 8MB without CONTIGUOUS - should return 2 blocks from the holes.
+//! params.start_range_address = 0;
+//! params.end_range_address = SZ_16M as u64;
+//! params.size_bytes = SZ_8M as u64;
+//! let fragmented = KBox::pin_init(buddy.alloc_blocks(¶ms), GFP_KERNEL)?;
+//! 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 small = GpuBuddy::new(GpuBuddyParams {
+//! base_offset_bytes: 0,
+//! 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.
+//! params.start_range_address = 0;
+//! params.end_range_address = SZ_4M as u64;
+//! params.size_bytes = SZ_4M as u64;
+//! let hole1 = KBox::pin_init(small.alloc_blocks(¶ms), GFP_KERNEL)?;
+//!
+//! params.start_range_address = SZ_8M as u64;
+//! params.end_range_address = (SZ_8M + SZ_4M) as u64;
+//! let hole2 = KBox::pin_init(small.alloc_blocks(¶ms), GFP_KERNEL)?;
+//!
+//! // 8MB contiguous should fail - only two non-contiguous 4MB holes exist.
+//! params.start_range_address = 0;
+//! params.end_range_address = 0;
+//! params.size_bytes = SZ_8M as u64;
+//! params.buddy_flags = BuddyFlags::try_new(BuddyFlags::CONTIGUOUS_ALLOCATION)?;
+//! let result = KBox::pin_init(small.alloc_blocks(¶ms), GFP_KERNEL);
+//! assert!(result.is_err());
+//! drop(hole2);
+//! drop(hole1);
+//!
+//! # Ok::<(), Error>(())
+//! ```
+
+use crate::{
+ bindings,
+ clist_create,
+ error::to_result,
+ ffi::clist::CListHead,
+ 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.
+pub struct GpuBuddyParams {
+ /// Base offset in bytes where the managed memory region starts.
+ /// Allocations will be offset by this value.
+ pub base_offset_bytes: u64,
+ /// 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.
+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>,
+
+ // TODO: Replace `Mutex<()>` with `Mutex<Opaque<..>>` once `Mutex::new()`
+ // accepts `impl PinInit<T>`.
+ #[pin]
+ lock: Mutex<()>,
+ /// Base offset for all allocations (does not change after init).
+ base_offset: u64,
+ /// Cached chunk size (does not change after init).
+ chunk_size: u64,
+ /// Cached total size (does not change after init).
+ size: u64,
+}
+
+impl GpuBuddyInner {
+ /// Create a pin-initializer for the buddy allocator.
+ fn new(params: GpuBuddyParams) -> impl PinInit<Self, Error> {
+ let base_offset = params.base_offset_bytes;
+ 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!(()),
+ base_offset: base_offset,
+ chunk_size: chunk_size,
+ size: size,
+ })
+ }
+
+ /// 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(params), GFP_KERNEL)?))
+ }
+
+ /// Get the base offset for allocations.
+ pub fn base_offset(&self) -> u64 {
+ self.0.base_offset
+ }
+
+ /// Get the chunk size (minimum allocation unit).
+ pub fn chunk_size(&self) -> u64 {
+ self.0.chunk_size
+ }
+
+ /// Get the total managed size.
+ pub fn size(&self) -> u64 {
+ self.0.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 a pin-initializer for [`AllocatedBlocks`].
+ ///
+ /// Takes `&self` instead of `&mut self` because the internal [`Mutex`] provides
+ /// synchronization - no external `&mut` exclusivity needed.
+ pub fn alloc_blocks(
+ &self,
+ params: &GpuBuddyAllocParams,
+ ) -> impl PinInit<AllocatedBlocks, Error> {
+ let buddy_arc = Arc::clone(&self.0);
+ let start = params.start_range_address;
+ let end = params.end_range_address;
+ let size = params.size_bytes;
+ let min_block_size = params.min_block_size_bytes;
+ let flags = params.buddy_flags;
+
+ // Create pin-initializer that initializes list and allocates blocks.
+ try_pin_init!(AllocatedBlocks {
+ buddy: buddy_arc,
+ list <- CListHead::new(),
+ flags: flags,
+ _: {
+ // Lock while allocating to serialize with concurrent frees.
+ let guard = buddy.lock();
+
+ // SAFETY: `guard` provides exclusive access to the buddy allocator.
+ to_result(unsafe {
+ bindings::gpu_buddy_alloc_blocks(
+ guard.as_raw(),
+ start,
+ end,
+ size,
+ min_block_size,
+ list.as_raw(),
+ flags.as_raw(),
+ )
+ })?
+ }
+ })
+ }
+}
+
+/// 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.
+#[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`] values. Each [`AllocatedBlock`]
+ /// borrows `self` and is only valid for the duration of that borrow.
+ pub fn iter(&self) -> impl Iterator<Item = AllocatedBlock<'_>> + '_ {
+ // SAFETY: list contains gpu_buddy_block items linked via __bindgen_anon_1.link.
+ let clist = clist_create!(unsafe {
+ 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 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 not modified after allocation for the lifetime
+// of `AllocatedBlock`.
+unsafe impl Send for Block {}
+
+// SAFETY: `Block` is not modified after allocation for the lifetime
+// of `AllocatedBlock`.
+unsafe impl Sync for Block {}
+
+/// An allocated block with access to the GPU buddy allocator.
+///
+/// It is returned by [`AllocatedBlocks::iter()`] and provides access to the
+/// GPU buddy allocator required for some accessors.
+///
+/// # 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.
+ ///
+ /// Returns the absolute offset including the allocator's base offset.
+ /// This is the actual address to use for accessing the allocated memory.
+ pub fn offset(&self) -> u64 {
+ self.alloc.buddy.base_offset + 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 {
+ self.alloc.buddy.chunk_size << self.block.order()
+ }
+}
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 58dbb02c5197..b8287601f464 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -97,6 +97,8 @@
pub mod firmware;
pub mod fmt;
pub mod fs;
+#[cfg(CONFIG_GPU_BUDDY)]
+pub mod gpu;
#[cfg(CONFIG_I2C = "y")]
pub mod i2c;
pub mod id_pool;
--
2.34.1
^ permalink raw reply related
* [reference PATCH v11 3/4] gpu: Fix uninitialized buddy for built-in drivers
From: Joel Fernandes @ 2026-02-24 22:40 UTC (permalink / raw)
To: linux-kernel
Cc: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Dave Airlie, Daniel Almeida, Koen Koning,
dri-devel, nouveau, rust-for-linux, Nikola Djukic,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jonathan Corbet, Alex Deucher,
Christian König, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Huang Rui, Matthew Auld, Matthew Brost,
Lucas De Marchi, Thomas Hellström, Helge Deller, Alex Gaynor,
Boqun Feng, John Hubbard, Alistair Popple, Timur Tabi, Edwin Peer,
Alexandre Courbot, Andrea Righi, Andy Ritger, Zhi Wang,
Balbir Singh, Philipp Stanner, Elle Rhumsaa, alexeyi,
Eliot Courtney, joel, linux-doc, amd-gfx, intel-gfx, intel-xe,
linux-fbdev, Joel Fernandes, Peter Senna Tschudin
In-Reply-To: <20260224224005.3232841-1-joelagnelf@nvidia.com>
From: Koen Koning <koen.koning@linux.intel.com>
Use subsys_initcall instead of module_init for the GPU buddy allocator,
so its initialization code runs before any gpu drivers.
Otherwise, a built-in driver that tries to use the buddy allocator will
run into a kernel NULL pointer dereference because slab_blocks is
uninitialized.
Specifically, this fixes drm/xe (as built-in) running into a kernel
panic during boot, because it uses buddy during device probe.
Fixes: ba110db8e1bc ("gpu: Move DRM buddy allocator one level up (part two)")
Cc: Joel Fernandes <joelagnelf@nvidia.com>
Cc: Dave Airlie <airlied@redhat.com>
Cc: intel-xe@lists.freedesktop.org
Cc: Peter Senna Tschudin <peter.senna@linux.intel.com>
Cc: Matthew Auld <matthew.auld@intel.com>
Signed-off-by: Koen Koning <koen.koning@linux.intel.com>
Reviewed-by: Joel Fernandes <joelagnelf@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
Please note: Greg and Danilo suggest fixing this in the Makefile like Koen
initially did, so please do so. I am just including this patch here for
reference.
drivers/gpu/buddy.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/gpu/buddy.c b/drivers/gpu/buddy.c
index 603c59a2013a..81f57fdf913b 100644
--- a/drivers/gpu/buddy.c
+++ b/drivers/gpu/buddy.c
@@ -1315,7 +1315,7 @@ static int __init gpu_buddy_module_init(void)
return 0;
}
-module_init(gpu_buddy_module_init);
+subsys_initcall(gpu_buddy_module_init);
module_exit(gpu_buddy_module_exit);
MODULE_DESCRIPTION("GPU Buddy Allocator");
--
2.34.1
^ permalink raw reply related
* [reference PATCH v11 1/4] gpu: Move DRM buddy allocator one level up (part one)
From: Joel Fernandes @ 2026-02-24 22:40 UTC (permalink / raw)
To: linux-kernel
Cc: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Dave Airlie, Daniel Almeida, Koen Koning,
dri-devel, nouveau, rust-for-linux, Nikola Djukic,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jonathan Corbet, Alex Deucher,
Christian König, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Huang Rui, Matthew Auld, Matthew Brost,
Lucas De Marchi, Thomas Hellström, Helge Deller, Alex Gaynor,
Boqun Feng, John Hubbard, Alistair Popple, Timur Tabi, Edwin Peer,
Alexandre Courbot, Andrea Righi, Andy Ritger, Zhi Wang,
Balbir Singh, Philipp Stanner, Elle Rhumsaa, alexeyi,
Eliot Courtney, joel, linux-doc, amd-gfx, intel-gfx, intel-xe,
linux-fbdev, Joel Fernandes
In-Reply-To: <20260224224005.3232841-1-joelagnelf@nvidia.com>
Move the DRM buddy allocator one level up so that it can be used by GPU
drivers (example, nova-core) that have usecases other than DRM (such as
VFIO vGPU support). Modify the API, structures and Kconfigs to use
"gpu_buddy" terminology. Adapt the drivers and tests to use the new API.
The commit cannot be split due to bisectability, however no functional
change is intended. Verified by running K-UNIT tests and build tested
various configurations.
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
Reviewed-by: Dave Airlie <airlied@redhat.com>
[airlied: I've split this into two so git can find copies easier.
I've also just nuked drm_random library, that stuff needs to be done
elsewhere and only the buddy tests seem to be using it].
Signed-off-by: Dave Airlie <airlied@redhat.com>
---
Documentation/gpu/drm-mm.rst | 6 +++---
drivers/gpu/Makefile | 2 +-
drivers/gpu/{drm/drm_buddy.c => buddy.c} | 2 +-
drivers/gpu/drm/Kconfig | 4 ----
drivers/gpu/drm/Kconfig.debug | 1 -
drivers/gpu/drm/Makefile | 3 +--
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h | 2 +-
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 2 +-
drivers/gpu/drm/i915/i915_scatterlist.c | 2 +-
drivers/gpu/drm/i915/i915_ttm_buddy_manager.c | 2 +-
drivers/gpu/drm/tests/Makefile | 1 -
drivers/gpu/drm/tests/drm_exec_test.c | 2 --
drivers/gpu/drm/tests/drm_mm_test.c | 2 --
drivers/gpu/drm/ttm/tests/ttm_mock_manager.h | 2 +-
drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h | 2 +-
drivers/gpu/tests/Makefile | 4 ++++
.../{drm/tests/drm_buddy_test.c => tests/gpu_buddy_test.c} | 4 ++--
drivers/gpu/{drm/lib/drm_random.c => tests/gpu_random.c} | 2 +-
drivers/gpu/{drm/lib/drm_random.h => tests/gpu_random.h} | 0
include/{drm/drm_buddy.h => linux/gpu_buddy.h} | 0
20 files changed, 19 insertions(+), 26 deletions(-)
rename drivers/gpu/{drm/drm_buddy.c => buddy.c} (99%)
create mode 100644 drivers/gpu/tests/Makefile
rename drivers/gpu/{drm/tests/drm_buddy_test.c => tests/gpu_buddy_test.c} (99%)
rename drivers/gpu/{drm/lib/drm_random.c => tests/gpu_random.c} (97%)
rename drivers/gpu/{drm/lib/drm_random.h => tests/gpu_random.h} (100%)
rename include/{drm/drm_buddy.h => linux/gpu_buddy.h} (100%)
diff --git a/Documentation/gpu/drm-mm.rst b/Documentation/gpu/drm-mm.rst
index f22433470c76..ceee0e663237 100644
--- a/Documentation/gpu/drm-mm.rst
+++ b/Documentation/gpu/drm-mm.rst
@@ -526,10 +526,10 @@ DRM GPUVM Function References
DRM Buddy Allocator
===================
-DRM Buddy Function References
------------------------------
+Buddy Allocator Function References (GPU buddy)
+-----------------------------------------------
-.. kernel-doc:: drivers/gpu/drm/drm_buddy.c
+.. kernel-doc:: drivers/gpu/buddy.c
:export:
DRM Cache Handling and Fast WC memcpy()
diff --git a/drivers/gpu/Makefile b/drivers/gpu/Makefile
index 36a54d456630..c5292ee2c852 100644
--- a/drivers/gpu/Makefile
+++ b/drivers/gpu/Makefile
@@ -2,7 +2,7 @@
# drm/tegra depends on host1x, so if both drivers are built-in care must be
# taken to initialize them in the correct order. Link order is the only way
# to ensure this currently.
-obj-y += host1x/ drm/ vga/
+obj-y += host1x/ drm/ vga/ tests/
obj-$(CONFIG_IMX_IPUV3_CORE) += ipu-v3/
obj-$(CONFIG_TRACE_GPU_MEM) += trace/
obj-$(CONFIG_NOVA_CORE) += nova-core/
diff --git a/drivers/gpu/drm/drm_buddy.c b/drivers/gpu/buddy.c
similarity index 99%
rename from drivers/gpu/drm/drm_buddy.c
rename to drivers/gpu/buddy.c
index fd34d3755f7c..4cc63d961d26 100644
--- a/drivers/gpu/drm/drm_buddy.c
+++ b/drivers/gpu/buddy.c
@@ -10,7 +10,7 @@
#include <linux/module.h>
#include <linux/sizes.h>
-#include <drm/drm_buddy.h>
+#include <linux/gpu_buddy.h>
#include <drm/drm_print.h>
enum drm_buddy_free_tree {
diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
index d3d52310c9cc..ca2a2801e77f 100644
--- a/drivers/gpu/drm/Kconfig
+++ b/drivers/gpu/drm/Kconfig
@@ -269,10 +269,6 @@ config DRM_SCHED
config DRM_PANEL_BACKLIGHT_QUIRKS
tristate
-config DRM_LIB_RANDOM
- bool
- default n
-
config DRM_PRIVACY_SCREEN
bool
default n
diff --git a/drivers/gpu/drm/Kconfig.debug b/drivers/gpu/drm/Kconfig.debug
index 05dc43c0b8c5..3b7886865335 100644
--- a/drivers/gpu/drm/Kconfig.debug
+++ b/drivers/gpu/drm/Kconfig.debug
@@ -69,7 +69,6 @@ config DRM_KUNIT_TEST
select DRM_EXPORT_FOR_TESTS if m
select DRM_GEM_SHMEM_HELPER
select DRM_KUNIT_TEST_HELPERS
- select DRM_LIB_RANDOM
select DRM_SYSFB_HELPER
select PRIME_NUMBERS
default KUNIT_ALL_TESTS
diff --git a/drivers/gpu/drm/Makefile b/drivers/gpu/drm/Makefile
index ec2c5ff82382..5c86bc908955 100644
--- a/drivers/gpu/drm/Makefile
+++ b/drivers/gpu/drm/Makefile
@@ -78,7 +78,6 @@ drm-$(CONFIG_DRM_CLIENT) += \
drm_client_event.o \
drm_client_modeset.o \
drm_client_sysrq.o
-drm-$(CONFIG_DRM_LIB_RANDOM) += lib/drm_random.o
drm-$(CONFIG_COMPAT) += drm_ioc32.o
drm-$(CONFIG_DRM_PANEL) += drm_panel.o
drm-$(CONFIG_OF) += drm_of.o
@@ -114,7 +113,7 @@ drm_gpusvm_helper-$(CONFIG_ZONE_DEVICE) += \
obj-$(CONFIG_DRM_GPUSVM) += drm_gpusvm_helper.o
-obj-$(CONFIG_DRM_BUDDY) += drm_buddy.o
+obj-$(CONFIG_DRM_BUDDY) += ../buddy.o
drm_dma_helper-y := drm_gem_dma_helper.o
drm_dma_helper-$(CONFIG_DRM_FBDEV_EMULATION) += drm_fbdev_dma.o
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h
index 5f5fd9a911c2..874779618056 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h
@@ -24,7 +24,7 @@
#ifndef __AMDGPU_VRAM_MGR_H__
#define __AMDGPU_VRAM_MGR_H__
-#include <drm/drm_buddy.h>
+#include <linux/gpu_buddy.h>
struct amdgpu_vram_mgr {
struct ttm_resource_manager manager;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
index f65fe86c02b5..eeda5daa544f 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
@@ -5,7 +5,7 @@
#include <linux/shmem_fs.h>
-#include <drm/drm_buddy.h>
+#include <linux/gpu_buddy.h>
#include <drm/drm_print.h>
#include <drm/ttm/ttm_placement.h>
#include <drm/ttm/ttm_tt.h>
diff --git a/drivers/gpu/drm/i915/i915_scatterlist.c b/drivers/gpu/drm/i915/i915_scatterlist.c
index 4d830740946d..30246f02bcfe 100644
--- a/drivers/gpu/drm/i915/i915_scatterlist.c
+++ b/drivers/gpu/drm/i915/i915_scatterlist.c
@@ -7,7 +7,7 @@
#include "i915_scatterlist.h"
#include "i915_ttm_buddy_manager.h"
-#include <drm/drm_buddy.h>
+#include <linux/gpu_buddy.h>
#include <drm/drm_mm.h>
#include <linux/slab.h>
diff --git a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
index d5c6e6605086..6b256d95badd 100644
--- a/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
+++ b/drivers/gpu/drm/i915/i915_ttm_buddy_manager.c
@@ -5,7 +5,7 @@
#include <linux/slab.h>
-#include <drm/drm_buddy.h>
+#include <linux/gpu_buddy.h>
#include <drm/drm_print.h>
#include <drm/ttm/ttm_placement.h>
#include <drm/ttm/ttm_bo.h>
diff --git a/drivers/gpu/drm/tests/Makefile b/drivers/gpu/drm/tests/Makefile
index 87d5d5f9332a..d2e2e3d8349a 100644
--- a/drivers/gpu/drm/tests/Makefile
+++ b/drivers/gpu/drm/tests/Makefile
@@ -7,7 +7,6 @@ obj-$(CONFIG_DRM_KUNIT_TEST) += \
drm_atomic_test.o \
drm_atomic_state_test.o \
drm_bridge_test.o \
- drm_buddy_test.o \
drm_cmdline_parser_test.o \
drm_connector_test.o \
drm_damage_helper_test.o \
diff --git a/drivers/gpu/drm/tests/drm_exec_test.c b/drivers/gpu/drm/tests/drm_exec_test.c
index 3a20c788c51f..2fc47f3b463b 100644
--- a/drivers/gpu/drm/tests/drm_exec_test.c
+++ b/drivers/gpu/drm/tests/drm_exec_test.c
@@ -16,8 +16,6 @@
#include <drm/drm_gem.h>
#include <drm/drm_kunit_helpers.h>
-#include "../lib/drm_random.h"
-
struct drm_exec_priv {
struct device *dev;
struct drm_device *drm;
diff --git a/drivers/gpu/drm/tests/drm_mm_test.c b/drivers/gpu/drm/tests/drm_mm_test.c
index aec9eccdeae9..e24a619059d8 100644
--- a/drivers/gpu/drm/tests/drm_mm_test.c
+++ b/drivers/gpu/drm/tests/drm_mm_test.c
@@ -16,8 +16,6 @@
#include <drm/drm_mm.h>
#include <drm/drm_print.h>
-#include "../lib/drm_random.h"
-
enum {
BEST,
BOTTOMUP,
diff --git a/drivers/gpu/drm/ttm/tests/ttm_mock_manager.h b/drivers/gpu/drm/ttm/tests/ttm_mock_manager.h
index e4c95f86a467..96ea8c9aae34 100644
--- a/drivers/gpu/drm/ttm/tests/ttm_mock_manager.h
+++ b/drivers/gpu/drm/ttm/tests/ttm_mock_manager.h
@@ -5,7 +5,7 @@
#ifndef TTM_MOCK_MANAGER_H
#define TTM_MOCK_MANAGER_H
-#include <drm/drm_buddy.h>
+#include <linux/gpu_buddy.h>
struct ttm_mock_manager {
struct ttm_resource_manager man;
diff --git a/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h b/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
index a71e14818ec2..babeec5511d9 100644
--- a/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
+++ b/drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h
@@ -6,7 +6,7 @@
#ifndef _XE_TTM_VRAM_MGR_TYPES_H_
#define _XE_TTM_VRAM_MGR_TYPES_H_
-#include <drm/drm_buddy.h>
+#include <linux/gpu_buddy.h>
#include <drm/ttm/ttm_device.h>
/**
diff --git a/drivers/gpu/tests/Makefile b/drivers/gpu/tests/Makefile
new file mode 100644
index 000000000000..8e7654e87d82
--- /dev/null
+++ b/drivers/gpu/tests/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+
+gpu_buddy_tests-y = gpu_buddy_test.o gpu_random.o
+obj-$(CONFIG_DRM_KUNIT_TEST) += gpu_buddy_tests.o
diff --git a/drivers/gpu/drm/tests/drm_buddy_test.c b/drivers/gpu/tests/gpu_buddy_test.c
similarity index 99%
rename from drivers/gpu/drm/tests/drm_buddy_test.c
rename to drivers/gpu/tests/gpu_buddy_test.c
index e6f8459c6c54..b905932da990 100644
--- a/drivers/gpu/drm/tests/drm_buddy_test.c
+++ b/drivers/gpu/tests/gpu_buddy_test.c
@@ -10,9 +10,9 @@
#include <linux/sched/signal.h>
#include <linux/sizes.h>
-#include <drm/drm_buddy.h>
+#include <linux/gpu_buddy.h>
-#include "../lib/drm_random.h"
+#include "gpu_random.h"
static unsigned int random_seed;
diff --git a/drivers/gpu/drm/lib/drm_random.c b/drivers/gpu/tests/gpu_random.c
similarity index 97%
rename from drivers/gpu/drm/lib/drm_random.c
rename to drivers/gpu/tests/gpu_random.c
index 0e9dba1ef4af..ddd1f594b5d5 100644
--- a/drivers/gpu/drm/lib/drm_random.c
+++ b/drivers/gpu/tests/gpu_random.c
@@ -6,7 +6,7 @@
#include <linux/slab.h>
#include <linux/types.h>
-#include "drm_random.h"
+#include "gpu_random.h"
u32 drm_prandom_u32_max_state(u32 ep_ro, struct rnd_state *state)
{
diff --git a/drivers/gpu/drm/lib/drm_random.h b/drivers/gpu/tests/gpu_random.h
similarity index 100%
rename from drivers/gpu/drm/lib/drm_random.h
rename to drivers/gpu/tests/gpu_random.h
diff --git a/include/drm/drm_buddy.h b/include/linux/gpu_buddy.h
similarity index 100%
rename from include/drm/drm_buddy.h
rename to include/linux/gpu_buddy.h
--
2.34.1
^ permalink raw reply related
* [PATCH v11 0/4] Rust GPU buddy allocator bindings
From: Joel Fernandes @ 2026-02-24 22:40 UTC (permalink / raw)
To: linux-kernel
Cc: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Danilo Krummrich, Dave Airlie, Daniel Almeida, Koen Koning,
dri-devel, nouveau, rust-for-linux, Nikola Djukic,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann, David Airlie,
Simona Vetter, Jonathan Corbet, Alex Deucher,
Christian König, Jani Nikula, Joonas Lahtinen, Rodrigo Vivi,
Tvrtko Ursulin, Huang Rui, Matthew Auld, Matthew Brost,
Lucas De Marchi, Thomas Hellström, Helge Deller, Alex Gaynor,
Boqun Feng, John Hubbard, Alistair Popple, Timur Tabi, Edwin Peer,
Alexandre Courbot, Andrea Righi, Andy Ritger, Zhi Wang,
Balbir Singh, Philipp Stanner, Elle Rhumsaa, alexeyi,
Eliot Courtney, joel, linux-doc, amd-gfx, intel-gfx, intel-xe,
linux-fbdev, Joel Fernandes
The series adds Rust GPU buddy allocator bindings for use by nova-core.
Note: Patches 1-3 are included for reference only and should not be merged
through this series. They are the DRM buddy allocator code movement patches
(already being pulled into upstream via drm-misc-next by Dave Airlie) and the
uninitialized buddy fix by Koen Koning (which is going in independently). They
are included here as they are prerequisites for the Rust GPU buddy bindings
(and could be further revised).
The series along with all dependencies, including clist and nova-core mm
patches, are available in:
https://git.kernel.org/pub/scm/linux/kernel/git/jfern/linux.git/log/?h=nova/mm
Changes from v10 to v11:
- Dropped "rust: ffi: Convert pub use to pub mod and create ffi module" patch;
the ffi module restructuring will go through a different path.
- Dropped "rust: clist: Add support to interface with C linked lists" patch;
the clist module will be submitted separately.
- Dropped "nova-core: Kconfig: Sort select statements alphabetically" cosmetic
patch.
- Patches 1-3 (DRM buddy movement and fix) are included as reference only;
they are already being pulled into upstream via drm-misc-next.
- Removed clist patches as those can go in independently (Alice).
- Moved the Kconfig GPU_BUDDY selection patch to nova-core mm series to enable
it when it is actually used.
- Various nits to comments, etc.
Changes from v9 to v10:
- Absorbed the DRM buddy code movement patches into this series as patches 1-2.
Dave Airlie reworked these into two parts for better git history.
- Added "gpu: Fix uninitialized buddy for built-in drivers" fix by Koen Koning,
using subsys_initcall instead of module_init to fix NULL pointer dereference
when built-in drivers use the buddy allocator before initialization.
- Added "rust: ffi: Convert pub use to pub mod and create ffi module" to prepare
the ffi module for hosting clist as a sub-module.
- Moved clist from rust/kernel/clist.rs to rust/kernel/ffi/.
- Added "nova-core: Kconfig: Sort select statements alphabetically" (Danilo).
Changes from v8 to v9:
- Updated nova-core Kconfig patch: addressed sorting of Kconfig options.
- Added Daniel Almeida's Reviewed-by tag to clist patch.
- Minor refinements to GPU buddy bindings.
Changes from v7 to v8:
- Added nova-core Kconfig patch to select GPU_BUDDY for VRAM allocation.
- Various changes suggested by Danilo Krummrich, Gary Guo, and Daniel Almeida.
- Added Acked-by: Gary Guo for clist patch.
Changes from v6 to v7:
- Major restructuring: split the large 26-patch v6 RFC series. v7 only contains
the Rust infrastructure patches (clist + GPU buddy bindings), extracted from
the full nova-core MM series. The nova-core MM patches follow separately.
- Rebased on linux-next.
Changes from v5 to v6:
- Rebased on drm-rust-kernel/drm-rust-next.
- Expanded from 6 to 26 patches with full nova-core MM infrastructure including
page table walker, VMM, BAR1 user interface, TLB flush, and GpuMm manager.
Changes from v4 to v5:
- Added PRAMIN aperture support with documentation and self-tests.
- Improved buddy allocator bindings (fewer lines of code).
- Based on drm-rust-next instead of linux-next.
Changes from v3 to v4:
- Combined the clist and DRM buddy series into a single coherent series.
- Added DRM buddy allocator movement from drivers/gpu/drm/ up to drivers/gpu/,
renaming API from drm_buddy to gpu_buddy.
- Added Rust bindings for the GPU buddy allocator.
Changes from v2 to v3:
- Squashed 3 clist patches into one due to inter-dependencies.
- Changed Clist to Clist<'a, T> using const generic offset (Alex Courbot).
- Simplified C helpers to only list_add_tail (Alex Courbot, John Hubbard).
- Added init_list_head() Rust function (Alex Courbot).
- Added FusedIterator, PartialEq/Eq impls.
- Added MAINTAINERS entry (Miguel Ojeda).
Changes from v1 (RFC) to v2:
- Dropped DRM buddy allocator patches; series focuses solely on clist module.
- Dropped sample modules, replaced with doctests.
- Added proper lifetime management similar to scatterlist.
- Split clist into 3 separate patches.
Link to v10: https://lore.kernel.org/all/20260218205507.689429-1-joelagnelf@nvidia.com/
Joel Fernandes (3):
gpu: Move DRM buddy allocator one level up (part one)
gpu: Move DRM buddy allocator one level up (part two)
rust: gpu: Add GPU buddy allocator bindings
Koen Koning (1):
gpu: Fix uninitialized buddy for built-in drivers
Documentation/gpu/drm-mm.rst | 10 +-
MAINTAINERS | 16 +-
drivers/gpu/Kconfig | 13 +
drivers/gpu/Makefile | 3 +-
drivers/gpu/buddy.c | 1322 +++++++++++++++++
drivers/gpu/drm/Kconfig | 5 +-
drivers/gpu/drm/Kconfig.debug | 1 -
drivers/gpu/drm/Makefile | 1 -
drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c | 2 +-
.../gpu/drm/amd/amdgpu/amdgpu_res_cursor.h | 12 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c | 79 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.h | 20 +-
drivers/gpu/drm/drm_buddy.c | 1277 +---------------
drivers/gpu/drm/i915/gem/i915_gem_ttm.c | 2 +-
drivers/gpu/drm/i915/i915_scatterlist.c | 10 +-
drivers/gpu/drm/i915/i915_ttm_buddy_manager.c | 55 +-
drivers/gpu/drm/i915/i915_ttm_buddy_manager.h | 4 +-
.../drm/i915/selftests/intel_memory_region.c | 20 +-
drivers/gpu/drm/tests/Makefile | 1 -
drivers/gpu/drm/tests/drm_exec_test.c | 2 -
drivers/gpu/drm/tests/drm_mm_test.c | 2 -
.../gpu/drm/ttm/tests/ttm_bo_validate_test.c | 4 +-
drivers/gpu/drm/ttm/tests/ttm_mock_manager.c | 18 +-
drivers/gpu/drm/ttm/tests/ttm_mock_manager.h | 4 +-
drivers/gpu/drm/xe/xe_res_cursor.h | 34 +-
drivers/gpu/drm/xe/xe_svm.c | 12 +-
drivers/gpu/drm/xe/xe_ttm_vram_mgr.c | 71 +-
drivers/gpu/drm/xe/xe_ttm_vram_mgr_types.h | 4 +-
drivers/gpu/tests/Makefile | 4 +
.../gpu_buddy_test.c} | 416 +++---
.../lib/drm_random.c => tests/gpu_random.c} | 18 +-
.../lib/drm_random.h => tests/gpu_random.h} | 18 +-
drivers/video/Kconfig | 1 +
include/drm/drm_buddy.h | 163 +-
include/linux/gpu_buddy.h | 177 +++
rust/bindings/bindings_helper.h | 11 +
rust/helpers/gpu.c | 23 +
rust/helpers/helpers.c | 1 +
rust/kernel/gpu/buddy.rs | 536 +++++++
rust/kernel/gpu/mod.rs | 5 +
rust/kernel/lib.rs | 2 +
41 files changed, 2536 insertions(+), 1843 deletions(-)
create mode 100644 drivers/gpu/Kconfig
create mode 100644 drivers/gpu/buddy.c
create mode 100644 drivers/gpu/tests/Makefile
rename drivers/gpu/{drm/tests/drm_buddy_test.c => tests/gpu_buddy_test.c} (67%)
rename drivers/gpu/{drm/lib/drm_random.c => tests/gpu_random.c} (59%)
rename drivers/gpu/{drm/lib/drm_random.h => tests/gpu_random.h} (53%)
create mode 100644 include/linux/gpu_buddy.h
create mode 100644 rust/helpers/gpu.c
create mode 100644 rust/kernel/gpu/buddy.rs
create mode 100644 rust/kernel/gpu/mod.rs
base-commit: 2961f841b025fb234860bac26dfb7fa7cb0fb122
prerequisite-patch-id: f8778e0b72697243cfe40a8bfcc3ca1d66160b12
prerequisite-patch-id: 763b30c69f9806de97eb58bc8e3406feb6bf61b4
--
2.34.1
^ permalink raw reply
* [PATCH v11 2/2] rust: clist: Add support to interface with C linked lists
From: Joel Fernandes @ 2026-02-24 22:27 UTC (permalink / raw)
To: linux-kernel
Cc: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Alex Gaynor, Danilo Krummrich, Dave Airlie, David Airlie,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann,
Simona Vetter, Daniel Almeida, Koen Koning, Nikola Djukic,
Alexandre Courbot, Philipp Stanner, Elle Rhumsaa, Jonathan Corbet,
Alex Deucher, Christian König, Jani Nikula, Joonas Lahtinen,
Rodrigo Vivi, Tvrtko Ursulin, Huang Rui, Matthew Auld,
Matthew Brost, Lucas De Marchi, Thomas Hellström,
Helge Deller, John Hubbard, Alistair Popple, Timur Tabi,
Edwin Peer, Andrea Righi, Andy Ritger, Zhi Wang, Balbir Singh,
alexeyi, Eliot Courtney, dri-devel, nouveau, rust-for-linux,
linux-doc, amd-gfx, intel-gfx, intel-xe, linux-fbdev,
Joel Fernandes
In-Reply-To: <20260224222734.3153931-1-joelagnelf@nvidia.com>
Add a new module `clist` for working with C's doubly circular linked
lists. Provide low-level iteration over list nodes.
Typed iteration over actual items is provided with a `clist_create`
macro to assist in creation of the `CList` type.
Cc: Nikola Djukic <ndjukic@nvidia.com>
Reviewed-by: Daniel Almeida <daniel.almeida@collabora.com>
Acked-by: Gary Guo <gary@garyguo.net>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
MAINTAINERS | 8 +
rust/helpers/helpers.c | 1 +
rust/helpers/list.c | 17 ++
rust/kernel/ffi/clist.rs | 338 +++++++++++++++++++++++++++++++++++++++
rust/kernel/ffi/mod.rs | 2 +
rust/kernel/lib.rs | 1 +
6 files changed, 367 insertions(+)
create mode 100644 rust/helpers/list.c
create mode 100644 rust/kernel/ffi/clist.rs
diff --git a/MAINTAINERS b/MAINTAINERS
index dc82a6bd1a61..0dc318c94c99 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -23181,6 +23181,14 @@ T: git https://github.com/Rust-for-Linux/linux.git alloc-next
F: rust/kernel/alloc.rs
F: rust/kernel/alloc/
+RUST [FFI HELPER]
+M: Joel Fernandes <joelagnelf@nvidia.com> (CLIST)
+M: Alexandre Courbot <acourbot@nvidia.com> (CLIST)
+L: rust-for-linux@vger.kernel.org
+S: Maintained
+T: git https://github.com/Rust-for-Linux/linux.git ffi-next
+F: rust/kernel/ffi/
+
RUST [NUM]
M: Alexandre Courbot <acourbot@nvidia.com>
R: Yury Norov <yury.norov@gmail.com>
diff --git a/rust/helpers/helpers.c b/rust/helpers/helpers.c
index a3c42e51f00a..724fcb8240ac 100644
--- a/rust/helpers/helpers.c
+++ b/rust/helpers/helpers.c
@@ -35,6 +35,7 @@
#include "io.c"
#include "jump_label.c"
#include "kunit.c"
+#include "list.c"
#include "maple_tree.c"
#include "mm.c"
#include "mutex.c"
diff --git a/rust/helpers/list.c b/rust/helpers/list.c
new file mode 100644
index 000000000000..18095a5593c5
--- /dev/null
+++ b/rust/helpers/list.c
@@ -0,0 +1,17 @@
+// SPDX-License-Identifier: GPL-2.0
+
+/*
+ * Helpers for C circular doubly linked list implementation.
+ */
+
+#include <linux/list.h>
+
+__rust_helper void rust_helper_INIT_LIST_HEAD(struct list_head *list)
+{
+ INIT_LIST_HEAD(list);
+}
+
+__rust_helper void rust_helper_list_add_tail(struct list_head *new, struct list_head *head)
+{
+ list_add_tail(new, head);
+}
diff --git a/rust/kernel/ffi/clist.rs b/rust/kernel/ffi/clist.rs
new file mode 100644
index 000000000000..a645358eee58
--- /dev/null
+++ b/rust/kernel/ffi/clist.rs
@@ -0,0 +1,338 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! FFI interface for C doubly circular intrusive linked lists.
+//!
+//! This module provides Rust abstractions for iterating over C `list_head`-based
+//! linked lists. It should only be used for cases where C and Rust code share
+//! direct access to the same linked list through an FFI interface.
+//!
+//! Note: This *must not* be used by Rust components that just need a linked list
+//! primitive. Use [`kernel::list::List`] instead.
+//!
+//! # Examples
+//!
+//! ```
+//! use kernel::{
+//! bindings,
+//! clist_create,
+//! types::Opaque,
+//! };
+//! # // Create test list with values (0, 10, 20) - normally done by C code but it is
+//! # // emulated here for doctests using the C bindings.
+//! # use core::mem::MaybeUninit;
+//! #
+//! # /// C struct with embedded `list_head` (typically will be allocated by C code).
+//! # #[repr(C)]
+//! # pub struct SampleItemC {
+//! # pub value: i32,
+//! # pub link: bindings::list_head,
+//! # }
+//! #
+//! # let mut head = MaybeUninit::<bindings::list_head>::uninit();
+//! #
+//! # let head = head.as_mut_ptr();
+//! # // SAFETY: head and all the items are test objects allocated in this scope.
+//! # unsafe { bindings::INIT_LIST_HEAD(head) };
+//! #
+//! # let mut items = [
+//! # MaybeUninit::<SampleItemC>::uninit(),
+//! # MaybeUninit::<SampleItemC>::uninit(),
+//! # MaybeUninit::<SampleItemC>::uninit(),
+//! # ];
+//! #
+//! # for (i, item) in items.iter_mut().enumerate() {
+//! # let ptr = item.as_mut_ptr();
+//! # // SAFETY: `ptr` points to a valid `MaybeUninit<SampleItemC>`.
+//! # unsafe { (*ptr).value = i as i32 * 10 };
+//! # // SAFETY: `&raw mut` creates a pointer valid for `INIT_LIST_HEAD`.
+//! # unsafe { bindings::INIT_LIST_HEAD(&raw mut (*ptr).link) };
+//! # // SAFETY: `link` was just initialized and `head` is a valid list head.
+//! # unsafe { bindings::list_add_tail(&mut (*ptr).link, head) };
+//! # }
+//!
+//! // Rust wrapper for the C struct.
+//! // The list item struct in this example is defined in C code as:
+//! // struct SampleItemC {
+//! // int value;
+//! // struct list_head link;
+//! // };
+//! //
+//! #[repr(transparent)]
+//! pub struct Item(Opaque<SampleItemC>);
+//!
+//! impl Item {
+//! pub fn value(&self) -> i32 {
+//! // SAFETY: [`Item`] has same layout as [`SampleItemC`].
+//! unsafe { (*self.0.get()).value }
+//! }
+//! }
+//!
+//! // Create typed [`CList`] from sentinel head.
+//! // SAFETY: head is valid and initialized, items are `SampleItemC` with
+//! // embedded `link` field, and `Item` is `#[repr(transparent)]` over `SampleItemC`.
+//! let list = clist_create!(unsafe { head, Item, SampleItemC, link });
+//!
+//! // Iterate directly over typed items.
+//! let mut found_0 = false;
+//! let mut found_10 = false;
+//! let mut found_20 = false;
+//!
+//! for item in list.iter() {
+//! let val = item.value();
+//! if val == 0 { found_0 = true; }
+//! if val == 10 { found_10 = true; }
+//! if val == 20 { found_20 = true; }
+//! }
+//!
+//! assert!(found_0 && found_10 && found_20);
+//! ```
+
+use core::{
+ iter::FusedIterator,
+ marker::PhantomData, //
+};
+
+use crate::{
+ bindings,
+ types::Opaque, //
+};
+
+use pin_init::{
+ pin_data,
+ pin_init,
+ PinInit, //
+};
+
+/// FFI wrapper for a C `list_head` object used in intrusive linked lists.
+///
+/// # Invariants
+///
+/// - The underlying `list_head` has been initialized (e.g. via `INIT_LIST_HEAD()`) and its
+/// `next`/`prev` pointers are valid and non-NULL.
+#[pin_data]
+#[repr(transparent)]
+pub struct CListHead {
+ #[pin]
+ inner: Opaque<bindings::list_head>,
+}
+
+impl CListHead {
+ /// Create a `&CListHead` reference from a raw `list_head` pointer.
+ ///
+ /// # Safety
+ ///
+ /// - `ptr` must be a valid pointer to an initialized `list_head` (e.g. via
+ /// `INIT_LIST_HEAD()`), with valid non-NULL `next`/`prev` pointers.
+ /// - `ptr` must remain valid for the lifetime `'a`.
+ /// - The list and all linked `list_head` nodes must not be modified from
+ /// anywhere for the lifetime `'a`, unless done so via any [`CListHead`] APIs.
+ #[inline]
+ pub unsafe fn from_raw<'a>(ptr: *mut bindings::list_head) -> &'a Self {
+ // SAFETY:
+ // - [`CListHead`] has same layout as `list_head`.
+ // - `ptr` is valid and unmodified for 'a per caller guarantees.
+ unsafe { &*ptr.cast() }
+ }
+
+ /// Get the raw `list_head` pointer.
+ #[inline]
+ pub fn as_raw(&self) -> *mut bindings::list_head {
+ self.inner.get()
+ }
+
+ /// Get the next [`CListHead`] in the list.
+ #[inline]
+ pub fn next(&self) -> &Self {
+ let raw = self.as_raw();
+ // SAFETY:
+ // - `self.as_raw()` is valid and initialized per type invariants.
+ // - The `next` pointer is valid and non-NULL per type invariants
+ // (initialized via `INIT_LIST_HEAD()` or equivalent).
+ unsafe { Self::from_raw((*raw).next) }
+ }
+
+ /// Check if this node is linked in a list (not isolated).
+ #[inline]
+ pub fn is_linked(&self) -> bool {
+ let raw = self.as_raw();
+ // SAFETY: self.as_raw() is valid per type invariants.
+ unsafe { (*raw).next != raw && (*raw).prev != raw }
+ }
+
+ /// Pin-initializer that initializes the list head.
+ pub fn new() -> impl PinInit<Self> {
+ pin_init!(Self {
+ // SAFETY: `INIT_LIST_HEAD` initializes `slot` to a valid empty list.
+ inner <- Opaque::ffi_init(|slot| unsafe { bindings::INIT_LIST_HEAD(slot) }),
+ })
+ }
+}
+
+// SAFETY: `list_head` contains no thread-bound state; it only holds
+// `next`/`prev` pointers.
+unsafe impl Send for CListHead {}
+
+// SAFETY: `CListHead` can be shared among threads as modifications are
+// not allowed at the moment.
+unsafe impl Sync for CListHead {}
+
+impl PartialEq for CListHead {
+ #[inline]
+ fn eq(&self, other: &Self) -> bool {
+ core::ptr::eq(self, other)
+ }
+}
+
+impl Eq for CListHead {}
+
+/// Low-level iterator over `list_head` nodes.
+///
+/// An iterator used to iterate over a C intrusive linked list (`list_head`). Caller has to
+/// perform conversion of returned [`CListHead`] to an item (using `container_of` macro or similar).
+///
+/// # Invariants
+///
+/// [`CListHeadIter`] is iterating over an initialized and valid list.
+struct CListHeadIter<'a> {
+ /// Current position in the list.
+ current: &'a CListHead,
+ /// The sentinel head (used to detect end of iteration).
+ sentinel: &'a CListHead,
+}
+
+impl<'a> Iterator for CListHeadIter<'a> {
+ type Item = &'a CListHead;
+
+ #[inline]
+ fn next(&mut self) -> Option<Self::Item> {
+ // Check if we've reached the sentinel (end of list).
+ if self.current == self.sentinel {
+ return None;
+ }
+
+ let item = self.current;
+ self.current = item.next();
+ Some(item)
+ }
+}
+
+impl<'a> FusedIterator for CListHeadIter<'a> {}
+
+/// A typed C linked list with a sentinel head intended for FFI use-cases where
+/// C subsystem manages a linked list that Rust code needs to read. Generally
+/// required only for special cases.
+///
+/// A sentinel head [`CListHead`] represents the entire linked list and can be used
+/// for iteration over items of type `T`, it is not associated with a specific item.
+///
+/// The const generic `OFFSET` specifies the byte offset of the `list_head` field within
+/// the struct that `T` wraps.
+///
+/// # Invariants
+///
+/// - The sentinel [`CListHead`] has been initialized (e.g. via `INIT_LIST_HEAD()`) with valid
+/// non-NULL `next`/`prev` pointers.
+/// - `OFFSET` is the byte offset of the `list_head` field within the struct that `T` wraps.
+/// - All the list's `list_head` nodes have been initialized with valid non-NULL `next`/`prev`
+/// pointers.
+#[repr(transparent)]
+pub struct CList<T, const OFFSET: usize>(CListHead, PhantomData<T>);
+
+impl<T, const OFFSET: usize> CList<T, OFFSET> {
+ /// Create a typed [`CList`] reference from a raw sentinel `list_head` pointer.
+ ///
+ /// # Safety
+ ///
+ /// - `ptr` must be a valid pointer to an initialized sentinel `list_head` (e.g. via
+ /// `INIT_LIST_HEAD()`), with valid non-NULL `next`/`prev` pointers.
+ /// - `ptr` must remain valid for the lifetime `'a`.
+ /// - The list and all linked nodes must not be concurrently modified for the lifetime `'a`.
+ /// - The list must contain items where the `list_head` field is at byte offset `OFFSET`.
+ /// - `T` must be `#[repr(transparent)]` over the C struct.
+ #[inline]
+ pub unsafe fn from_raw<'a>(ptr: *mut bindings::list_head) -> &'a Self {
+ // SAFETY:
+ // - [`CList`] has same layout as [`CListHead`] due to repr(transparent).
+ // - Caller guarantees `ptr` is a valid, sentinel `list_head` object.
+ unsafe { &*ptr.cast() }
+ }
+
+ /// Check if the list is empty.
+ #[inline]
+ pub fn is_empty(&self) -> bool {
+ !self.0.is_linked()
+ }
+
+ /// Create an iterator over typed items.
+ #[inline]
+ pub fn iter(&self) -> CListIter<'_, T, OFFSET> {
+ let head = &self.0;
+ CListIter {
+ head_iter: CListHeadIter {
+ current: head.next(),
+ sentinel: head,
+ },
+ _phantom: PhantomData,
+ }
+ }
+}
+
+/// High-level iterator over typed list items.
+pub struct CListIter<'a, T, const OFFSET: usize> {
+ head_iter: CListHeadIter<'a>,
+ _phantom: PhantomData<&'a T>,
+}
+
+impl<'a, T, const OFFSET: usize> Iterator for CListIter<'a, T, OFFSET> {
+ type Item = &'a T;
+
+ #[inline]
+ fn next(&mut self) -> Option<Self::Item> {
+ let head = self.head_iter.next()?;
+
+ // Convert to item using OFFSET.
+ // SAFETY: `item_ptr` calculation from `OFFSET` (calculated using offset_of!)
+ // is valid per invariants.
+ Some(unsafe { &*head.as_raw().byte_sub(OFFSET).cast::<T>() })
+ }
+}
+
+impl<'a, T, const OFFSET: usize> FusedIterator for CListIter<'a, T, OFFSET> {}
+
+/// Create a C doubly-circular linked list interface `CList` from a raw `list_head` pointer.
+///
+/// This macro creates a `CList<T, OFFSET>` that can iterate over items of type `$rust_type`
+/// linked via the `$field` field in the underlying C struct `$c_type`.
+///
+/// # Arguments
+///
+/// - `$head`: Raw pointer to the sentinel `list_head` object (`*mut bindings::list_head`).
+/// - `$rust_type`: Each item's rust wrapper type.
+/// - `$c_type`: Each item's C struct type that contains the embedded `list_head`.
+/// - `$field`: The name of the `list_head` field within the C struct.
+///
+/// # Safety
+///
+/// The caller must ensure:
+///
+/// - `$head` is a valid, initialized sentinel `list_head` (e.g. via `INIT_LIST_HEAD()`)
+/// pointing to a list that is not concurrently modified for the lifetime of the `CList`.
+/// - The list contains items of type `$c_type` linked via an embedded `$field`.
+/// - `$rust_type` is `#[repr(transparent)]` over `$c_type` or has compatible layout.
+///
+/// # Examples
+///
+/// Refer to the examples in this module's documentation.
+#[macro_export]
+macro_rules! clist_create {
+ (unsafe { $head:expr, $rust_type:ty, $c_type:ty, $($field:tt).+ }) => {{
+ // Compile-time check that field path is a list_head.
+ let _: fn(*const $c_type) -> *const $crate::bindings::list_head =
+ |p| unsafe { &raw const (*p).$($field).+ };
+
+ // Calculate offset and create `CList`.
+ const OFFSET: usize = ::core::mem::offset_of!($c_type, $($field).+);
+ // SAFETY: The caller of this macro is responsible for ensuring safety.
+ unsafe { $crate::ffi::clist::CList::<$rust_type, OFFSET>::from_raw($head) }
+ }};
+}
diff --git a/rust/kernel/ffi/mod.rs b/rust/kernel/ffi/mod.rs
index 7d844e9cb339..8c235ca0d1e3 100644
--- a/rust/kernel/ffi/mod.rs
+++ b/rust/kernel/ffi/mod.rs
@@ -5,3 +5,5 @@
// Re-export C type definitions from the `ffi` crate so that existing
// `kernel::ffi::c_int` etc. paths continue to work.
pub use ::ffi::*;
+
+pub mod clist;
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 0a77b4c0ffeb..58dbb02c5197 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -28,6 +28,7 @@
#![feature(lint_reasons)]
//
// Stable since Rust 1.82.0.
+#![feature(offset_of_nested)]
#![feature(raw_ref_op)]
//
// Stable since Rust 1.83.0.
--
2.34.1
^ permalink raw reply related
* [PATCH v11 1/2] rust: ffi: Convert pub use to pub mod and create ffi module
From: Joel Fernandes @ 2026-02-24 22:27 UTC (permalink / raw)
To: linux-kernel
Cc: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Alex Gaynor, Danilo Krummrich, Dave Airlie, David Airlie,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann,
Simona Vetter, Daniel Almeida, Koen Koning, Nikola Djukic,
Alexandre Courbot, Philipp Stanner, Elle Rhumsaa, Jonathan Corbet,
Alex Deucher, Christian König, Jani Nikula, Joonas Lahtinen,
Rodrigo Vivi, Tvrtko Ursulin, Huang Rui, Matthew Auld,
Matthew Brost, Lucas De Marchi, Thomas Hellström,
Helge Deller, John Hubbard, Alistair Popple, Timur Tabi,
Edwin Peer, Andrea Righi, Andy Ritger, Zhi Wang, Balbir Singh,
alexeyi, Eliot Courtney, dri-devel, nouveau, rust-for-linux,
linux-doc, amd-gfx, intel-gfx, intel-xe, linux-fbdev,
Joel Fernandes
In-Reply-To: <20260224222734.3153931-1-joelagnelf@nvidia.com>
Convert `pub use ffi` to `pub mod ffi` in lib.rs and create the
corresponding `rust/kernel/ffi/mod.rs` module file. Also re-export all C
type definitions from `ffi` crate so that existing `kernel::ffi::c_int`
etc. paths continue to work.
This prepares the ffi module to host additional sub-modules in later
patches (clist).
Reviewed-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
rust/kernel/ffi/mod.rs | 7 +++++++
rust/kernel/lib.rs | 3 +--
2 files changed, 8 insertions(+), 2 deletions(-)
create mode 100644 rust/kernel/ffi/mod.rs
diff --git a/rust/kernel/ffi/mod.rs b/rust/kernel/ffi/mod.rs
new file mode 100644
index 000000000000..7d844e9cb339
--- /dev/null
+++ b/rust/kernel/ffi/mod.rs
@@ -0,0 +1,7 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! FFI infrastructure for interfacing with C code.
+
+// Re-export C type definitions from the `ffi` crate so that existing
+// `kernel::ffi::c_int` etc. paths continue to work.
+pub use ::ffi::*;
diff --git a/rust/kernel/lib.rs b/rust/kernel/lib.rs
index 3da92f18f4ee..0a77b4c0ffeb 100644
--- a/rust/kernel/lib.rs
+++ b/rust/kernel/lib.rs
@@ -62,8 +62,6 @@
// Allow proc-macros to refer to `::kernel` inside the `kernel` crate (this crate).
extern crate self as kernel;
-pub use ffi;
-
pub mod acpi;
pub mod alloc;
#[cfg(CONFIG_AUXILIARY_BUS)]
@@ -93,6 +91,7 @@
pub mod drm;
pub mod error;
pub mod faux;
+pub mod ffi;
#[cfg(CONFIG_RUST_FW_LOADER_ABSTRACTIONS)]
pub mod firmware;
pub mod fmt;
--
2.34.1
^ permalink raw reply related
* [PATCH v11 0/2] rust: clist patches for nova-core memory management
From: Joel Fernandes @ 2026-02-24 22:27 UTC (permalink / raw)
To: linux-kernel
Cc: Miguel Ojeda, Boqun Feng, Gary Guo, Björn Roy Baron,
Benno Lossin, Andreas Hindborg, Alice Ryhl, Trevor Gross,
Alex Gaynor, Danilo Krummrich, Dave Airlie, David Airlie,
Maarten Lankhorst, Maxime Ripard, Thomas Zimmermann,
Simona Vetter, Daniel Almeida, Koen Koning, Nikola Djukic,
Alexandre Courbot, Philipp Stanner, Elle Rhumsaa, Jonathan Corbet,
Alex Deucher, Christian König, Jani Nikula, Joonas Lahtinen,
Rodrigo Vivi, Tvrtko Ursulin, Huang Rui, Matthew Auld,
Matthew Brost, Lucas De Marchi, Thomas Hellström,
Helge Deller, John Hubbard, Alistair Popple, Timur Tabi,
Edwin Peer, Andrea Righi, Andy Ritger, Zhi Wang, Balbir Singh,
alexeyi, Eliot Courtney, dri-devel, nouveau, rust-for-linux,
linux-doc, amd-gfx, intel-gfx, intel-xe, linux-fbdev,
Joel Fernandes
This series provides the clist module needed for nova-core memory management.
These patches are being sent separately from the rest of the preparatory
patches (DRM buddy movement, GPU buddy bindings, etc.) as they can go in
independently.
The clist module provides Rust abstractions for iterating over C
list_head-based linked lists. The primary use-case is iterating over GPU buddy
allocator blocks.
The git tree with all patches can be found at:
git://git.kernel.org/pub/scm/linux/kernel/git/jfern/linux.git (tag: clist-v11-20260224)
Detailed changelog
------------------
Changes from v10 to v11:
- Sending only the ffi/clist patches separately from the rest of the
preparatory series, as these can go in independently.
- MAINTAINERS entry: Renamed from "RUST TO C LIST INTERFACES" to
"RUST [FFI HELPER]" with (CLIST) scope annotations for maintainers,
following Danilo's suggestion. Note: There is still an ongoing
discussion about the MAINTAINER file entry naming between Miguel and
Danilo: https://lore.kernel.org/all/DGJXYEXCYIII.Z6FOAA8YYMAZ@kernel.org/
- Updated clist.rs module documentation per Danilo's review: generalized
the FFI usage description and added explicit note directing Rust-only
users to kernel::list::List instead.
- Implemented suggestions from Alice related to safety of CList wrt
concurrent modifications.
- Removed unnecessary trailing comment markers from example imports.
- Added feature guard for offset_of_nested (Eliot).
Changes from v9 to v10:
- Combined clist/ffi patches into the larger "Preparatory patches for
nova-core memory management" series (8 patches total).
- Added new ffi module patch: Convert pub use to pub mod and create
rust/kernel/ffi/mod.rs to host clist as a sub-module.
- Moved clist from rust/kernel/clist.rs to rust/kernel/ffi/clist.rs.
- Added Reviewed-by and Acked-by tags from Gary and Daniel.
Changes from v8 to v9:
- Added nova-core Kconfig change to select GPU_BUDDY.
- Minor fixups.
Changes from v7 to v8:
- Various changes suggested by Danilo, Gary, Daniel. Added tags.
Changes from v6 to v7:
- Extracted clist and GPU buddy patches from the larger RFC v6 nova-core
memory management series into a standalone series.
- Changes based on suggestions by Gary and Dave.
Changes from v5 to v6:
- Part of the larger RFC v6 nova-core memory management series
(26 patches).
Changes from v4 to v5:
- Part of the larger RFC v5 nova-core memory management series
(6 patches).
Changes from v3 to v4:
- Combined the clist and DRM buddy series back together.
- Added Rust bindings for the GPU buddy allocator.
- Moved DRM buddy allocator one level up to drivers/gpu/ so it can be
used by GPU drivers (e.g. nova-core) that have non-DRM usecases.
Changes from v2 to v3:
- Consolidated 3 patches into a single patch.
Changes from v1 to v2:
- Dropped the DRM buddy allocator patches. Series now focuses solely on
the clist module.
- Dropped samples and added doctests.
- Added proper lifetime management similar to scatterlist.
Link to v10: https://lore.kernel.org/all/20260218205507.689429-1-joelagnelf@nvidia.com/
Link to v9: https://lore.kernel.org/all/20260210233204.790524-1-joelagnelf@nvidia.com/
Link to v8: https://lore.kernel.org/all/20260209214246.2783990-1-joelagnelf@nvidia.com/
Link to v7: https://lore.kernel.org/all/20260206004110.1914814-1-joelagnelf@nvidia.com/
Joel Fernandes (2):
rust: ffi: Convert pub use to pub mod and create ffi module
rust: clist: Add support to interface with C linked lists
MAINTAINERS | 8 +
rust/helpers/helpers.c | 1 +
rust/helpers/list.c | 17 ++
rust/kernel/ffi/clist.rs | 338 +++++++++++++++++++++++++++++++++++++++
rust/kernel/ffi/mod.rs | 9 ++
rust/kernel/lib.rs | 4 +-
6 files changed, 375 insertions(+), 2 deletions(-)
create mode 100644 rust/helpers/list.c
create mode 100644 rust/kernel/ffi/clist.rs
create mode 100644 rust/kernel/ffi/mod.rs
base-commit: 2961f841b025fb234860bac26dfb7fa7cb0fb122
--
2.34.1
^ permalink raw reply
* Re: [PATCH v2 0/4] fbdev: defio: Protect against device/module removal
From: Helge Deller @ 2026-02-24 22:02 UTC (permalink / raw)
To: Thomas Zimmermann, simona; +Cc: linux-fbdev, dri-devel
In-Reply-To: <20260224082657.207284-1-tzimmermann@suse.de>
On 2/24/26 09:25, Thomas Zimmermann wrote:
> There's a long-standing bug in defio where the framebuffer device or
> module gets removed while mmap'ed areas of the framebuffer memory
> persists in userspace. Page faults in the area then operate on defined
> state.
>
> Patches 1 and 2 fix these problems. Patches 3 and 4 build upon the fix
> and put defio state into the correct places.
>
> v2:
> - use alloc_obj() functions
>
> Thomas Zimmermann (4):
> fbdev: defio: Disconnect deferred I/O from the lifetime of struct
> fb_info
> fbdev: defio: Keep module reference from VMAs
> fbdev: defio: Move variable state into struct fb_deferred_io_state
> fbdev: defio: Move pageref array to struct fb_deferred_io_state
>
> drivers/video/fbdev/core/fb_defio.c | 266 ++++++++++++++++++++--------
> include/linux/fb.h | 9 +-
> 2 files changed, 195 insertions(+), 80 deletions(-)
Series added to fbdev git tree for further testing.
Thanks!
Helge
^ permalink raw reply
* [PATCH] staging: sm750fb: Fix "varios" typo in ddk750_swi2c.c
From: Ahmet Ramazan Capoglu @ 2026-02-24 11:37 UTC (permalink / raw)
To: sudipm.mukherjee, teddy.wang, gregkh
Cc: Ahmet Ramazan Capoglu, linux-fbdev, linux-staging, linux-kernel
Fix spelling of "varios" to "various".
Signed-off-by: Ahmet Ramazan Capoglu <ahmetramazancapoglu@gmail.com>
---
drivers/staging/sm750fb/ddk750_swi2c.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/drivers/staging/sm750fb/ddk750_swi2c.c b/drivers/staging/sm750fb/ddk750_swi2c.c
index 0ef8d4ff2ef9..e63f3b00ec4c 100644
--- a/drivers/staging/sm750fb/ddk750_swi2c.c
+++ b/drivers/staging/sm750fb/ddk750_swi2c.c
@@ -27,7 +27,7 @@
*
* I.e. the SCL may only be changed in section 1. and section 3. while
* the SDA may only be changed in section 2. and section 4. The table
- * below gives the changes for these 2 lines in the varios sections.
+ * below gives the changes for these 2 lines in the various sections.
*
* Section changes Table:
* ======================
--
2.52.0
^ permalink raw reply related
* [PATCH v2 1/4] fbdev: defio: Disconnect deferred I/O from the lifetime of struct fb_info
From: Thomas Zimmermann @ 2026-02-24 8:25 UTC (permalink / raw)
To: deller, simona, jayalk; +Cc: linux-fbdev, dri-devel, Thomas Zimmermann, stable
In-Reply-To: <20260224082657.207284-1-tzimmermann@suse.de>
Hold state of deferred I/O in struct fb_deferred_io_state. Allocate an
instance as part of initializing deferred I/O and remove it only after
the final mapping has been closed. If the fb_info and the contained
deferred I/O meanwhile goes away, clear struct fb_deferred_io_state.info
to invalidate the mapping. Any access will then result in a SIGBUS
signal.
Fixes a long-standing problem, where a device hot-unplug happens while
user space still has an active mapping of the graphics memory. The hot-
unplug frees the instance of struct fb_info. Accessing the memory will
operate on undefined state.
v2:
- use kzalloc_obj()
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
Fixes: 60b59beafba8 ("fbdev: mm: Deferred IO support")
Cc: Helge Deller <deller@gmx.de>
Cc: linux-fbdev@vger.kernel.org
Cc: dri-devel@lists.freedesktop.org
Cc: <stable@vger.kernel.org> # v2.6.22+
---
drivers/video/fbdev/core/fb_defio.c | 178 ++++++++++++++++++++++------
include/linux/fb.h | 4 +-
2 files changed, 145 insertions(+), 37 deletions(-)
diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c
index ca48b89a323d..93bd2f696fa4 100644
--- a/drivers/video/fbdev/core/fb_defio.c
+++ b/drivers/video/fbdev/core/fb_defio.c
@@ -24,6 +24,75 @@
#include <linux/rmap.h>
#include <linux/pagemap.h>
+/*
+ * struct fb_deferred_io_state
+ */
+
+struct fb_deferred_io_state {
+ struct kref ref;
+
+ struct mutex lock; /* mutex that protects the pageref list */
+ /* fields protected by lock */
+ struct fb_info *info;
+};
+
+static struct fb_deferred_io_state *fb_deferred_io_state_alloc(void)
+{
+ struct fb_deferred_io_state *fbdefio_state;
+
+ fbdefio_state = kzalloc_obj(*fbdefio_state);
+ if (!fbdefio_state)
+ return NULL;
+
+ kref_init(&fbdefio_state->ref);
+ mutex_init(&fbdefio_state->lock);
+
+ return fbdefio_state;
+}
+
+static void fb_deferred_io_state_release(struct fb_deferred_io_state *fbdefio_state)
+{
+ mutex_destroy(&fbdefio_state->lock);
+
+ kfree(fbdefio_state);
+}
+
+static void fb_deferred_io_state_get(struct fb_deferred_io_state *fbdefio_state)
+{
+ kref_get(&fbdefio_state->ref);
+}
+
+static void __fb_deferred_io_state_release(struct kref *ref)
+{
+ struct fb_deferred_io_state *fbdefio_state =
+ container_of(ref, struct fb_deferred_io_state, ref);
+
+ fb_deferred_io_state_release(fbdefio_state);
+}
+
+static void fb_deferred_io_state_put(struct fb_deferred_io_state *fbdefio_state)
+{
+ kref_put(&fbdefio_state->ref, __fb_deferred_io_state_release);
+}
+
+/*
+ * struct vm_operations_struct
+ */
+
+static void fb_deferred_io_vm_open(struct vm_area_struct *vma)
+{
+ struct fb_deferred_io_state *fbdefio_state = vma->vm_private_data;
+
+ fb_deferred_io_state_get(fbdefio_state);
+}
+
+static void fb_deferred_io_vm_close(struct vm_area_struct *vma)
+{
+ struct fb_deferred_io_state *fbdefio_state = vma->vm_private_data;
+
+ fb_deferred_io_state_put(fbdefio_state);
+}
+
static struct page *fb_deferred_io_get_page(struct fb_info *info, unsigned long offs)
{
struct fb_deferred_io *fbdefio = info->fbdefio;
@@ -121,25 +190,46 @@ static void fb_deferred_io_pageref_put(struct fb_deferred_io_pageref *pageref,
/* this is to find and return the vmalloc-ed fb pages */
static vm_fault_t fb_deferred_io_fault(struct vm_fault *vmf)
{
+ struct fb_info *info;
unsigned long offset;
struct page *page;
- struct fb_info *info = vmf->vma->vm_private_data;
+ vm_fault_t ret;
+ struct fb_deferred_io_state *fbdefio_state = vmf->vma->vm_private_data;
+
+ mutex_lock(&fbdefio_state->lock);
+
+ info = fbdefio_state->info;
+ if (!info) {
+ ret = VM_FAULT_SIGBUS; /* our device is gone */
+ goto err_mutex_unlock;
+ }
offset = vmf->pgoff << PAGE_SHIFT;
- if (offset >= info->fix.smem_len)
- return VM_FAULT_SIGBUS;
+ if (offset >= info->fix.smem_len) {
+ ret = VM_FAULT_SIGBUS;
+ goto err_mutex_unlock;
+ }
page = fb_deferred_io_get_page(info, offset);
- if (!page)
- return VM_FAULT_SIGBUS;
+ if (!page) {
+ ret = VM_FAULT_SIGBUS;
+ goto err_mutex_unlock;
+ }
if (!vmf->vma->vm_file)
fb_err(info, "no mapping available\n");
BUG_ON(!info->fbdefio->mapping);
+ mutex_unlock(&fbdefio_state->lock);
+
vmf->page = page;
+
return 0;
+
+err_mutex_unlock:
+ mutex_unlock(&fbdefio_state->lock);
+ return ret;
}
int fb_deferred_io_fsync(struct file *file, loff_t start, loff_t end, int datasync)
@@ -166,15 +256,24 @@ EXPORT_SYMBOL_GPL(fb_deferred_io_fsync);
* Adds a page to the dirty list. Call this from struct
* vm_operations_struct.page_mkwrite.
*/
-static vm_fault_t fb_deferred_io_track_page(struct fb_info *info, unsigned long offset,
- struct page *page)
+static vm_fault_t fb_deferred_io_track_page(struct fb_deferred_io_state *fbdefio_state,
+ unsigned long offset, struct page *page)
{
- struct fb_deferred_io *fbdefio = info->fbdefio;
+ struct fb_info *info;
+ struct fb_deferred_io *fbdefio;
struct fb_deferred_io_pageref *pageref;
vm_fault_t ret;
/* protect against the workqueue changing the page list */
- mutex_lock(&fbdefio->lock);
+ mutex_lock(&fbdefio_state->lock);
+
+ info = fbdefio_state->info;
+ if (!info) {
+ ret = VM_FAULT_SIGBUS; /* our device is gone */
+ goto err_mutex_unlock;
+ }
+
+ fbdefio = info->fbdefio;
pageref = fb_deferred_io_pageref_get(info, offset, page);
if (WARN_ON_ONCE(!pageref)) {
@@ -192,50 +291,38 @@ static vm_fault_t fb_deferred_io_track_page(struct fb_info *info, unsigned long
*/
lock_page(pageref->page);
- mutex_unlock(&fbdefio->lock);
+ mutex_unlock(&fbdefio_state->lock);
/* come back after delay to process the deferred IO */
schedule_delayed_work(&info->deferred_work, fbdefio->delay);
return VM_FAULT_LOCKED;
err_mutex_unlock:
- mutex_unlock(&fbdefio->lock);
+ mutex_unlock(&fbdefio_state->lock);
return ret;
}
-/*
- * fb_deferred_io_page_mkwrite - Mark a page as written for deferred I/O
- * @fb_info: The fbdev info structure
- * @vmf: The VM fault
- *
- * This is a callback we get when userspace first tries to
- * write to the page. We schedule a workqueue. That workqueue
- * will eventually mkclean the touched pages and execute the
- * deferred framebuffer IO. Then if userspace touches a page
- * again, we repeat the same scheme.
- *
- * Returns:
- * VM_FAULT_LOCKED on success, or a VM_FAULT error otherwise.
- */
-static vm_fault_t fb_deferred_io_page_mkwrite(struct fb_info *info, struct vm_fault *vmf)
+static vm_fault_t fb_deferred_io_page_mkwrite(struct fb_deferred_io_state *fbdefio_state,
+ struct vm_fault *vmf)
{
unsigned long offset = vmf->pgoff << PAGE_SHIFT;
struct page *page = vmf->page;
file_update_time(vmf->vma->vm_file);
- return fb_deferred_io_track_page(info, offset, page);
+ return fb_deferred_io_track_page(fbdefio_state, offset, page);
}
-/* vm_ops->page_mkwrite handler */
static vm_fault_t fb_deferred_io_mkwrite(struct vm_fault *vmf)
{
- struct fb_info *info = vmf->vma->vm_private_data;
+ struct fb_deferred_io_state *fbdefio_state = vmf->vma->vm_private_data;
- return fb_deferred_io_page_mkwrite(info, vmf);
+ return fb_deferred_io_page_mkwrite(fbdefio_state, vmf);
}
static const struct vm_operations_struct fb_deferred_io_vm_ops = {
+ .open = fb_deferred_io_vm_open,
+ .close = fb_deferred_io_vm_close,
.fault = fb_deferred_io_fault,
.page_mkwrite = fb_deferred_io_mkwrite,
};
@@ -252,7 +339,10 @@ int fb_deferred_io_mmap(struct fb_info *info, struct vm_area_struct *vma)
vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP);
if (!(info->flags & FBINFO_VIRTFB))
vm_flags_set(vma, VM_IO);
- vma->vm_private_data = info;
+ vma->vm_private_data = info->fbdefio_state;
+
+ fb_deferred_io_state_get(info->fbdefio_state); /* released in vma->vm_ops->close() */
+
return 0;
}
EXPORT_SYMBOL_GPL(fb_deferred_io_mmap);
@@ -263,9 +353,10 @@ static void fb_deferred_io_work(struct work_struct *work)
struct fb_info *info = container_of(work, struct fb_info, deferred_work.work);
struct fb_deferred_io_pageref *pageref, *next;
struct fb_deferred_io *fbdefio = info->fbdefio;
+ struct fb_deferred_io_state *fbdefio_state = info->fbdefio_state;
/* here we wrprotect the page's mappings, then do all deferred IO. */
- mutex_lock(&fbdefio->lock);
+ mutex_lock(&fbdefio_state->lock);
#ifdef CONFIG_MMU
list_for_each_entry(pageref, &fbdefio->pagereflist, list) {
struct page *page = pageref->page;
@@ -283,12 +374,13 @@ static void fb_deferred_io_work(struct work_struct *work)
list_for_each_entry_safe(pageref, next, &fbdefio->pagereflist, list)
fb_deferred_io_pageref_put(pageref, info);
- mutex_unlock(&fbdefio->lock);
+ mutex_unlock(&fbdefio_state->lock);
}
int fb_deferred_io_init(struct fb_info *info)
{
struct fb_deferred_io *fbdefio = info->fbdefio;
+ struct fb_deferred_io_state *fbdefio_state;
struct fb_deferred_io_pageref *pagerefs;
unsigned long npagerefs;
int ret;
@@ -298,7 +390,11 @@ int fb_deferred_io_init(struct fb_info *info)
if (WARN_ON(!info->fix.smem_len))
return -EINVAL;
- mutex_init(&fbdefio->lock);
+ fbdefio_state = fb_deferred_io_state_alloc();
+ if (!fbdefio_state)
+ return -ENOMEM;
+ fbdefio_state->info = info;
+
INIT_DELAYED_WORK(&info->deferred_work, fb_deferred_io_work);
INIT_LIST_HEAD(&fbdefio->pagereflist);
if (fbdefio->delay == 0) /* set a default of 1 s */
@@ -315,10 +411,12 @@ int fb_deferred_io_init(struct fb_info *info)
info->npagerefs = npagerefs;
info->pagerefs = pagerefs;
+ info->fbdefio_state = fbdefio_state;
+
return 0;
err:
- mutex_destroy(&fbdefio->lock);
+ fb_deferred_io_state_release(fbdefio_state);
return ret;
}
EXPORT_SYMBOL_GPL(fb_deferred_io_init);
@@ -352,11 +450,19 @@ EXPORT_SYMBOL_GPL(fb_deferred_io_release);
void fb_deferred_io_cleanup(struct fb_info *info)
{
struct fb_deferred_io *fbdefio = info->fbdefio;
+ struct fb_deferred_io_state *fbdefio_state = info->fbdefio_state;
fb_deferred_io_lastclose(info);
+ info->fbdefio_state = NULL;
+
+ mutex_lock(&fbdefio_state->lock);
+ fbdefio_state->info = NULL;
+ mutex_unlock(&fbdefio_state->lock);
+
+ fb_deferred_io_state_put(fbdefio_state);
+
kvfree(info->pagerefs);
- mutex_destroy(&fbdefio->lock);
fbdefio->mapping = NULL;
}
EXPORT_SYMBOL_GPL(fb_deferred_io_cleanup);
diff --git a/include/linux/fb.h b/include/linux/fb.h
index 6d4a58084fd5..aed17567fe50 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -218,13 +218,14 @@ struct fb_deferred_io {
unsigned long delay;
bool sort_pagereflist; /* sort pagelist by offset */
int open_count; /* number of opened files; protected by fb_info lock */
- struct mutex lock; /* mutex that protects the pageref list */
struct list_head pagereflist; /* list of pagerefs for touched pages */
struct address_space *mapping; /* page cache object for fb device */
/* callback */
struct page *(*get_page)(struct fb_info *info, unsigned long offset);
void (*deferred_io)(struct fb_info *info, struct list_head *pagelist);
};
+
+struct fb_deferred_io_state;
#endif
/*
@@ -487,6 +488,7 @@ struct fb_info {
unsigned long npagerefs;
struct fb_deferred_io_pageref *pagerefs;
struct fb_deferred_io *fbdefio;
+ struct fb_deferred_io_state *fbdefio_state;
#endif
const struct fb_ops *fbops;
--
2.52.0
^ permalink raw reply related
* [PATCH v2 0/4] fbdev: defio: Protect against device/module removal
From: Thomas Zimmermann @ 2026-02-24 8:25 UTC (permalink / raw)
To: deller, simona, jayalk; +Cc: linux-fbdev, dri-devel, Thomas Zimmermann
There's a long-standing bug in defio where the framebuffer device or
module gets removed while mmap'ed areas of the framebuffer memory
persists in userspace. Page faults in the area then operate on defined
state.
Patches 1 and 2 fix these problems. Patches 3 and 4 build upon the fix
and put defio state into the correct places.
v2:
- use alloc_obj() functions
Thomas Zimmermann (4):
fbdev: defio: Disconnect deferred I/O from the lifetime of struct
fb_info
fbdev: defio: Keep module reference from VMAs
fbdev: defio: Move variable state into struct fb_deferred_io_state
fbdev: defio: Move pageref array to struct fb_deferred_io_state
drivers/video/fbdev/core/fb_defio.c | 266 ++++++++++++++++++++--------
include/linux/fb.h | 9 +-
2 files changed, 195 insertions(+), 80 deletions(-)
base-commit: 1c44015babd759b8e5234084dffcc08a0b784333
--
2.52.0
^ permalink raw reply
* [PATCH v2 4/4] fbdev: defio: Move pageref array to struct fb_deferred_io_state
From: Thomas Zimmermann @ 2026-02-24 8:25 UTC (permalink / raw)
To: deller, simona, jayalk; +Cc: linux-fbdev, dri-devel, Thomas Zimmermann
In-Reply-To: <20260224082657.207284-1-tzimmermann@suse.de>
The pageref array stores all pageref structures for a device's defio
helpers. Move it into struct fb_deferred_io_state to not expose it to
drivers.
v2:
- use kvzalloc_objs()
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
---
drivers/video/fbdev/core/fb_defio.c | 55 ++++++++++++++---------------
include/linux/fb.h | 2 --
2 files changed, 27 insertions(+), 30 deletions(-)
diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c
index 35ac13727da1..a12dd25ab697 100644
--- a/drivers/video/fbdev/core/fb_defio.c
+++ b/drivers/video/fbdev/core/fb_defio.c
@@ -41,28 +41,46 @@ struct fb_deferred_io_state {
/* fields protected by lock */
struct fb_info *info;
struct list_head pagereflist; /* list of pagerefs for touched pages */
+ unsigned long npagerefs;
+ struct fb_deferred_io_pageref *pagerefs;
};
-static struct fb_deferred_io_state *fb_deferred_io_state_alloc(void)
+static struct fb_deferred_io_state *fb_deferred_io_state_alloc(unsigned long len)
{
struct fb_deferred_io_state *fbdefio_state;
+ struct fb_deferred_io_pageref *pagerefs;
+ unsigned long npagerefs;
fbdefio_state = kzalloc_obj(*fbdefio_state);
if (!fbdefio_state)
return NULL;
+ npagerefs = DIV_ROUND_UP(len, PAGE_SIZE);
+
+ /* alloc a page ref for each page of the display memory */
+ pagerefs = kvzalloc_objs(*pagerefs, npagerefs);
+ if (!pagerefs)
+ goto err_kfree;
+ fbdefio_state->npagerefs = npagerefs;
+ fbdefio_state->pagerefs = pagerefs;
+
kref_init(&fbdefio_state->ref);
mutex_init(&fbdefio_state->lock);
INIT_LIST_HEAD(&fbdefio_state->pagereflist);
return fbdefio_state;
+
+err_kfree:
+ kfree(fbdefio_state);
+ return NULL;
}
static void fb_deferred_io_state_release(struct fb_deferred_io_state *fbdefio_state)
{
WARN_ON(!list_empty(&fbdefio_state->pagereflist));
mutex_destroy(&fbdefio_state->lock);
+ kvfree(fbdefio_state->pagerefs);
kfree(fbdefio_state);
}
@@ -125,18 +143,19 @@ static struct page *fb_deferred_io_get_page(struct fb_info *info, unsigned long
return page;
}
-static struct fb_deferred_io_pageref *fb_deferred_io_pageref_lookup(struct fb_info *info,
- unsigned long offset,
- struct page *page)
+static struct fb_deferred_io_pageref *
+fb_deferred_io_pageref_lookup(struct fb_deferred_io_state *fbdefio_state, unsigned long offset,
+ struct page *page)
{
+ struct fb_info *info = fbdefio_state->info;
unsigned long pgoff = offset >> PAGE_SHIFT;
struct fb_deferred_io_pageref *pageref;
- if (fb_WARN_ON_ONCE(info, pgoff >= info->npagerefs))
+ if (fb_WARN_ON_ONCE(info, pgoff >= fbdefio_state->npagerefs))
return NULL; /* incorrect allocation size */
/* 1:1 mapping between pageref and page offset */
- pageref = &info->pagerefs[pgoff];
+ pageref = &fbdefio_state->pagerefs[pgoff];
if (pageref->page)
goto out;
@@ -160,7 +179,7 @@ static struct fb_deferred_io_pageref *fb_deferred_io_pageref_get(struct fb_info
struct list_head *pos = &fbdefio_state->pagereflist;
struct fb_deferred_io_pageref *pageref, *cur;
- pageref = fb_deferred_io_pageref_lookup(info, offset, page);
+ pageref = fb_deferred_io_pageref_lookup(fbdefio_state, offset, page);
if (!pageref)
return NULL;
@@ -397,16 +416,13 @@ int fb_deferred_io_init(struct fb_info *info)
{
struct fb_deferred_io *fbdefio = info->fbdefio;
struct fb_deferred_io_state *fbdefio_state;
- struct fb_deferred_io_pageref *pagerefs;
- unsigned long npagerefs;
- int ret;
BUG_ON(!fbdefio);
if (WARN_ON(!info->fix.smem_len))
return -EINVAL;
- fbdefio_state = fb_deferred_io_state_alloc();
+ fbdefio_state = fb_deferred_io_state_alloc(info->fix.smem_len);
if (!fbdefio_state)
return -ENOMEM;
fbdefio_state->info = info;
@@ -415,24 +431,9 @@ int fb_deferred_io_init(struct fb_info *info)
if (fbdefio->delay == 0) /* set a default of 1 s */
fbdefio->delay = HZ;
- npagerefs = DIV_ROUND_UP(info->fix.smem_len, PAGE_SIZE);
-
- /* alloc a page ref for each page of the display memory */
- pagerefs = kvzalloc_objs(*pagerefs, npagerefs);
- if (!pagerefs) {
- ret = -ENOMEM;
- goto err;
- }
- info->npagerefs = npagerefs;
- info->pagerefs = pagerefs;
-
info->fbdefio_state = fbdefio_state;
return 0;
-
-err:
- fb_deferred_io_state_release(fbdefio_state);
- return ret;
}
EXPORT_SYMBOL_GPL(fb_deferred_io_init);
@@ -475,7 +476,5 @@ void fb_deferred_io_cleanup(struct fb_info *info)
mutex_unlock(&fbdefio_state->lock);
fb_deferred_io_state_put(fbdefio_state);
-
- kvfree(info->pagerefs);
}
EXPORT_SYMBOL_GPL(fb_deferred_io_cleanup);
diff --git a/include/linux/fb.h b/include/linux/fb.h
index 2791777f3a50..b27943719fab 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -482,8 +482,6 @@ struct fb_info {
#ifdef CONFIG_FB_DEFERRED_IO
struct delayed_work deferred_work;
- unsigned long npagerefs;
- struct fb_deferred_io_pageref *pagerefs;
struct fb_deferred_io *fbdefio;
struct fb_deferred_io_state *fbdefio_state;
#endif
--
2.52.0
^ permalink raw reply related
* [PATCH v2 3/4] fbdev: defio: Move variable state into struct fb_deferred_io_state
From: Thomas Zimmermann @ 2026-02-24 8:25 UTC (permalink / raw)
To: deller, simona, jayalk; +Cc: linux-fbdev, dri-devel, Thomas Zimmermann
In-Reply-To: <20260224082657.207284-1-tzimmermann@suse.de>
Move variable fields from struct fb_deferred_io into struct
fb_deferred_io_state. These fields are internal to the defio code
and should not be exposed to drivers. At some later point, struct
fb_defered_io might become const in all defio code.
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
---
drivers/video/fbdev/core/fb_defio.c | 37 +++++++++++++++++------------
include/linux/fb.h | 3 ---
2 files changed, 22 insertions(+), 18 deletions(-)
diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c
index 56030eb42f71..35ac13727da1 100644
--- a/drivers/video/fbdev/core/fb_defio.c
+++ b/drivers/video/fbdev/core/fb_defio.c
@@ -25,6 +25,8 @@
#include <linux/rmap.h>
#include <linux/pagemap.h>
+struct address_space;
+
/*
* struct fb_deferred_io_state
*/
@@ -32,9 +34,13 @@
struct fb_deferred_io_state {
struct kref ref;
+ int open_count; /* number of opened files; protected by fb_info lock */
+ struct address_space *mapping; /* page cache object for fb device */
+
struct mutex lock; /* mutex that protects the pageref list */
/* fields protected by lock */
struct fb_info *info;
+ struct list_head pagereflist; /* list of pagerefs for touched pages */
};
static struct fb_deferred_io_state *fb_deferred_io_state_alloc(void)
@@ -48,11 +54,14 @@ static struct fb_deferred_io_state *fb_deferred_io_state_alloc(void)
kref_init(&fbdefio_state->ref);
mutex_init(&fbdefio_state->lock);
+ INIT_LIST_HEAD(&fbdefio_state->pagereflist);
+
return fbdefio_state;
}
static void fb_deferred_io_state_release(struct fb_deferred_io_state *fbdefio_state)
{
+ WARN_ON(!list_empty(&fbdefio_state->pagereflist));
mutex_destroy(&fbdefio_state->lock);
kfree(fbdefio_state);
@@ -147,7 +156,8 @@ static struct fb_deferred_io_pageref *fb_deferred_io_pageref_get(struct fb_info
struct page *page)
{
struct fb_deferred_io *fbdefio = info->fbdefio;
- struct list_head *pos = &fbdefio->pagereflist;
+ struct fb_deferred_io_state *fbdefio_state = info->fbdefio_state;
+ struct list_head *pos = &fbdefio_state->pagereflist;
struct fb_deferred_io_pageref *pageref, *cur;
pageref = fb_deferred_io_pageref_lookup(info, offset, page);
@@ -171,7 +181,7 @@ static struct fb_deferred_io_pageref *fb_deferred_io_pageref_get(struct fb_info
* pages. If possible, drivers should try to work with
* unsorted page lists instead.
*/
- list_for_each_entry(cur, &fbdefio->pagereflist, list) {
+ list_for_each_entry(cur, &fbdefio_state->pagereflist, list) {
if (cur->offset > pageref->offset)
break;
}
@@ -222,7 +232,7 @@ static vm_fault_t fb_deferred_io_fault(struct vm_fault *vmf)
if (!vmf->vma->vm_file)
fb_err(info, "no mapping available\n");
- BUG_ON(!info->fbdefio->mapping);
+ fb_WARN_ON_ONCE(info, !fbdefio_state->mapping);
mutex_unlock(&fbdefio_state->lock);
@@ -364,20 +374,20 @@ static void fb_deferred_io_work(struct work_struct *work)
/* here we wrprotect the page's mappings, then do all deferred IO. */
mutex_lock(&fbdefio_state->lock);
#ifdef CONFIG_MMU
- list_for_each_entry(pageref, &fbdefio->pagereflist, list) {
+ list_for_each_entry(pageref, &fbdefio_state->pagereflist, list) {
struct page *page = pageref->page;
pgoff_t pgoff = pageref->offset >> PAGE_SHIFT;
- mapping_wrprotect_range(fbdefio->mapping, pgoff,
+ mapping_wrprotect_range(fbdefio_state->mapping, pgoff,
page_to_pfn(page), 1);
}
#endif
/* driver's callback with pagereflist */
- fbdefio->deferred_io(info, &fbdefio->pagereflist);
+ fbdefio->deferred_io(info, &fbdefio_state->pagereflist);
/* clear the list */
- list_for_each_entry_safe(pageref, next, &fbdefio->pagereflist, list)
+ list_for_each_entry_safe(pageref, next, &fbdefio_state->pagereflist, list)
fb_deferred_io_pageref_put(pageref, info);
mutex_unlock(&fbdefio_state->lock);
@@ -402,7 +412,6 @@ int fb_deferred_io_init(struct fb_info *info)
fbdefio_state->info = info;
INIT_DELAYED_WORK(&info->deferred_work, fb_deferred_io_work);
- INIT_LIST_HEAD(&fbdefio->pagereflist);
if (fbdefio->delay == 0) /* set a default of 1 s */
fbdefio->delay = HZ;
@@ -431,11 +440,11 @@ void fb_deferred_io_open(struct fb_info *info,
struct inode *inode,
struct file *file)
{
- struct fb_deferred_io *fbdefio = info->fbdefio;
+ struct fb_deferred_io_state *fbdefio_state = info->fbdefio_state;
- fbdefio->mapping = file->f_mapping;
+ fbdefio_state->mapping = file->f_mapping;
file->f_mapping->a_ops = &fb_deferred_io_aops;
- fbdefio->open_count++;
+ fbdefio_state->open_count++;
}
EXPORT_SYMBOL_GPL(fb_deferred_io_open);
@@ -446,16 +455,15 @@ static void fb_deferred_io_lastclose(struct fb_info *info)
void fb_deferred_io_release(struct fb_info *info)
{
- struct fb_deferred_io *fbdefio = info->fbdefio;
+ struct fb_deferred_io_state *fbdefio_state = info->fbdefio_state;
- if (!--fbdefio->open_count)
+ if (!--fbdefio_state->open_count)
fb_deferred_io_lastclose(info);
}
EXPORT_SYMBOL_GPL(fb_deferred_io_release);
void fb_deferred_io_cleanup(struct fb_info *info)
{
- struct fb_deferred_io *fbdefio = info->fbdefio;
struct fb_deferred_io_state *fbdefio_state = info->fbdefio_state;
fb_deferred_io_lastclose(info);
@@ -469,6 +477,5 @@ void fb_deferred_io_cleanup(struct fb_info *info)
fb_deferred_io_state_put(fbdefio_state);
kvfree(info->pagerefs);
- fbdefio->mapping = NULL;
}
EXPORT_SYMBOL_GPL(fb_deferred_io_cleanup);
diff --git a/include/linux/fb.h b/include/linux/fb.h
index aed17567fe50..2791777f3a50 100644
--- a/include/linux/fb.h
+++ b/include/linux/fb.h
@@ -217,9 +217,6 @@ struct fb_deferred_io {
/* delay between mkwrite and deferred handler */
unsigned long delay;
bool sort_pagereflist; /* sort pagelist by offset */
- int open_count; /* number of opened files; protected by fb_info lock */
- struct list_head pagereflist; /* list of pagerefs for touched pages */
- struct address_space *mapping; /* page cache object for fb device */
/* callback */
struct page *(*get_page)(struct fb_info *info, unsigned long offset);
void (*deferred_io)(struct fb_info *info, struct list_head *pagelist);
--
2.52.0
^ permalink raw reply related
* [PATCH v2 2/4] fbdev: defio: Keep module reference from VMAs
From: Thomas Zimmermann @ 2026-02-24 8:25 UTC (permalink / raw)
To: deller, simona, jayalk; +Cc: linux-fbdev, dri-devel, Thomas Zimmermann
In-Reply-To: <20260224082657.207284-1-tzimmermann@suse.de>
Acquire a module reference on each mmap and VMA open; hold it until
the kernel closes the VMA. Protects against unloading the module
while user space still has a mapping of the graphics memory. The
VMA page-fault handling would then call into undefined code.
This situation can happen if the underlying device has been unplugged
and the driver has been unloaded. It would then be possible to trigger
the bug by unloading the fbdev core module.
Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>
---
drivers/video/fbdev/core/fb_defio.c | 6 ++++++
1 file changed, 6 insertions(+)
diff --git a/drivers/video/fbdev/core/fb_defio.c b/drivers/video/fbdev/core/fb_defio.c
index 93bd2f696fa4..56030eb42f71 100644
--- a/drivers/video/fbdev/core/fb_defio.c
+++ b/drivers/video/fbdev/core/fb_defio.c
@@ -14,6 +14,7 @@
#include <linux/export.h>
#include <linux/string.h>
#include <linux/mm.h>
+#include <linux/module.h>
#include <linux/vmalloc.h>
#include <linux/delay.h>
#include <linux/interrupt.h>
@@ -83,6 +84,7 @@ static void fb_deferred_io_vm_open(struct vm_area_struct *vma)
{
struct fb_deferred_io_state *fbdefio_state = vma->vm_private_data;
+ WARN_ON_ONCE(!try_module_get(THIS_MODULE));
fb_deferred_io_state_get(fbdefio_state);
}
@@ -91,6 +93,7 @@ static void fb_deferred_io_vm_close(struct vm_area_struct *vma)
struct fb_deferred_io_state *fbdefio_state = vma->vm_private_data;
fb_deferred_io_state_put(fbdefio_state);
+ module_put(THIS_MODULE);
}
static struct page *fb_deferred_io_get_page(struct fb_info *info, unsigned long offs)
@@ -335,6 +338,9 @@ int fb_deferred_io_mmap(struct fb_info *info, struct vm_area_struct *vma)
{
vma->vm_page_prot = pgprot_decrypted(vma->vm_page_prot);
+ if (!try_module_get(THIS_MODULE))
+ return -EINVAL;
+
vma->vm_ops = &fb_deferred_io_vm_ops;
vm_flags_set(vma, VM_DONTEXPAND | VM_DONTDUMP);
if (!(info->flags & FBINFO_VIRTFB))
--
2.52.0
^ permalink raw reply related
* Re: [PATCH 13/13] lib/fonts: Remove internal symbols and macros from public header file
From: Helge Deller @ 2026-02-23 15:05 UTC (permalink / raw)
To: Thomas Zimmermann, gregkh, sam; +Cc: linux-fbdev, dri-devel, linux-kernel
In-Reply-To: <20260218083855.10743-14-tzimmermann@suse.de>
On 2/18/26 09:16, Thomas Zimmermann wrote:
> diff --git a/include/linux/font.h b/include/linux/font.h
> index 4ff956a1cd0a..6e9a4c93b47b 100644
> --- a/include/linux/font.h
> +++ b/include/linux/font.h
> @@ -92,20 +92,12 @@ struct font_desc {
> #define FONT6x8_IDX 12
> #define TER10x18_IDX 13
>
> -extern const struct font_desc font_vga_8x8,
> - font_vga_8x16,
> - font_pearl_8x8,
> - font_vga_6x11,
> - font_7x14,
> - font_10x18,
> - font_sun_8x16,
> - font_sun_12x22,
> - font_acorn_8x8,
> - font_mini_4x6,
> - font_6x10,
> - font_ter_16x32,
> - font_6x8,
> - font_ter_10x18;
> +#if defined(CONFIG_FONT_8x8)
> +extern const struct font_desc font_vga_8x8;
> +#endif
> +#if defined(CONFIG_FONT_8x16)
> +extern const struct font_desc font_vga_8x16;
> +#endif
I suggest not to use all those #ifdef(CONFIG_XXX) in the header files.
They are not necessary, and trigger a rebuild of a whole lot C-files
in case one single CONFIG option is changed.
Instead use it in the C-files only.
That way (re-)compilation is faster and you still get a link/build error
when a symbol is used although the config option is not set.
> diff --git a/lib/fonts/font.h b/lib/fonts/font.h
> new file mode 100644
> index 000000000000..00f65a3da5c2
> --- /dev/null
> +++ b/lib/fonts/font.h
> @@ -0,0 +1,52 @@
> +/* SPDX-License-Identifier: GPL-2.0 */
> +
> +#ifndef _LIB_FONTS_FONT_H
> +#define _LIB_FONTS_FONT_H
> +
> +#include <linux/font.h>
> +
> +#if defined(CONFIG_FONT_PEARL_8x8)
> +extern const struct font_desc font_pearl_8x8;
> +#endif
> +#if defined(CONFIG_FONT_6x11)
> +extern const struct font_desc font_vga_6x11;
> +#endif
...
same here...
Helge
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox