From: Joel Fernandes <joelagnelf@nvidia.com>
To: linux-kernel@vger.kernel.org
Cc: "Maarten Lankhorst" <maarten.lankhorst@linux.intel.com>,
"Maxime Ripard" <mripard@kernel.org>,
"Thomas Zimmermann" <tzimmermann@suse.de>,
"David Airlie" <airlied@gmail.com>,
"Simona Vetter" <simona@ffwll.ch>,
"Jonathan Corbet" <corbet@lwn.net>,
"Alex Deucher" <alexander.deucher@amd.com>,
"Christian König" <christian.koenig@amd.com>,
"Jani Nikula" <jani.nikula@linux.intel.com>,
"Joonas Lahtinen" <joonas.lahtinen@linux.intel.com>,
"Rodrigo Vivi" <rodrigo.vivi@intel.com>,
"Tvrtko Ursulin" <tursulin@ursulin.net>,
"Huang Rui" <ray.huang@amd.com>,
"Matthew Auld" <matthew.auld@intel.com>,
"Matthew Brost" <matthew.brost@intel.com>,
"Lucas De Marchi" <lucas.demarchi@intel.com>,
"Thomas Hellström" <thomas.hellstrom@linux.intel.com>,
"Helge Deller" <deller@gmx.de>,
"Danilo Krummrich" <dakr@kernel.org>,
"Alice Ryhl" <aliceryhl@google.com>,
"Miguel Ojeda" <ojeda@kernel.org>,
"Alex Gaynor" <alex.gaynor@gmail.com>,
"Boqun Feng" <boqun.feng@gmail.com>,
"Gary Guo" <gary@garyguo.net>,
"Björn Roy Baron" <bjorn3_gh@protonmail.com>,
"Benno Lossin" <lossin@kernel.org>,
"Andreas Hindborg" <a.hindborg@kernel.org>,
"Trevor Gross" <tmgross@umich.edu>,
"John Hubbard" <jhubbard@nvidia.com>,
"Alistair Popple" <apopple@nvidia.com>,
"Timur Tabi" <ttabi@nvidia.com>, "Edwin Peer" <epeer@nvidia.com>,
"Alexandre Courbot" <acourbot@nvidia.com>,
"Andrea Righi" <arighi@nvidia.com>,
"Andy Ritger" <aritger@nvidia.com>, "Zhi Wang" <zhiw@nvidia.com>,
"Balbir Singh" <balbirs@nvidia.com>,
"Philipp Stanner" <phasta@kernel.org>,
"Elle Rhumsaa" <elle@weathered-steel.dev>,
"Daniel Almeida" <daniel.almeida@collabora.com>,
"Eliot Courtney" <ecourtney@nvidia.com>,
joel@joelfernandes.org, nouveau@lists.freedesktop.org,
dri-devel@lists.freedesktop.org, rust-for-linux@vger.kernel.org,
linux-doc@vger.kernel.org, amd-gfx@lists.freedesktop.org,
intel-gfx@lists.freedesktop.org, intel-xe@lists.freedesktop.org,
linux-fbdev@vger.kernel.org,
"Joel Fernandes" <joelagnelf@nvidia.com>,
"Nikola Djukic" <ndjukic@nvidia.com>
Subject: [PATCH v7 09/23] nova-core: mm: Add unified page table entry wrapper enums
Date: Wed, 18 Feb 2026 16:20:06 -0500 [thread overview]
Message-ID: <20260218212020.800836-10-joelagnelf@nvidia.com> (raw)
In-Reply-To: <20260218212020.800836-1-joelagnelf@nvidia.com>
Add unified Pte, Pde, and DualPde wrapper enums that abstract over
MMU v2 and v3 page table entry formats. These enums allow the page
table walker and VMM to work with both MMU versions.
Each unified type:
- Takes MmuVersion parameter in constructors
- Wraps both ver2 and ver3 variants
- Delegates method calls to the appropriate variant
This enables version-agnostic page table operations while keeping
version-specific implementation details encapsulated in the ver2
and ver3 modules.
Cc: Nikola Djukic <ndjukic@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
drivers/gpu/nova-core/mm/pagetable/mod.rs | 327 ++++++++++++++++++++++
1 file changed, 327 insertions(+)
diff --git a/drivers/gpu/nova-core/mm/pagetable/mod.rs b/drivers/gpu/nova-core/mm/pagetable/mod.rs
index 5263a8f56529..1f783261a30f 100644
--- a/drivers/gpu/nova-core/mm/pagetable/mod.rs
+++ b/drivers/gpu/nova-core/mm/pagetable/mod.rs
@@ -10,6 +10,14 @@
pub(crate) mod ver2;
pub(crate) mod ver3;
+use kernel::prelude::*;
+
+use super::{
+ pramin,
+ Pfn,
+ VramAddress,
+ PAGE_SIZE, //
+};
use crate::gpu::Architecture;
/// MMU version enumeration.
@@ -77,6 +85,76 @@ pub(crate) const fn as_index(&self) -> u64 {
}
}
+impl MmuVersion {
+ /// Get the `PDE` levels (excluding PTE level) for page table walking.
+ pub(crate) fn pde_levels(&self) -> &'static [PageTableLevel] {
+ match self {
+ Self::V2 => ver2::PDE_LEVELS,
+ Self::V3 => ver3::PDE_LEVELS,
+ }
+ }
+
+ /// Get the PTE level for this MMU version.
+ pub(crate) fn pte_level(&self) -> PageTableLevel {
+ match self {
+ Self::V2 => ver2::PTE_LEVEL,
+ Self::V3 => ver3::PTE_LEVEL,
+ }
+ }
+
+ /// Get the dual PDE level (128-bit entries) for this MMU version.
+ pub(crate) fn dual_pde_level(&self) -> PageTableLevel {
+ match self {
+ Self::V2 => ver2::DUAL_PDE_LEVEL,
+ Self::V3 => ver3::DUAL_PDE_LEVEL,
+ }
+ }
+
+ /// Get the number of PDE levels for this MMU version.
+ pub(crate) fn pde_level_count(&self) -> usize {
+ self.pde_levels().len()
+ }
+
+ /// Get the entry size in bytes for a given level.
+ pub(crate) fn entry_size(&self, level: PageTableLevel) -> usize {
+ if level == self.dual_pde_level() {
+ 16 // 128-bit dual PDE
+ } else {
+ 8 // 64-bit PDE/PTE
+ }
+ }
+
+ /// Get the number of entries per page table page for a given level.
+ pub(crate) fn entries_per_page(&self, level: PageTableLevel) -> usize {
+ PAGE_SIZE / self.entry_size(level)
+ }
+
+ /// Compute upper bound on page table pages needed for `num_virt_pages`.
+ ///
+ /// Walks from PTE level up through PDE levels, accumulating the tree.
+ pub(crate) fn pt_pages_upper_bound(&self, num_virt_pages: usize) -> usize {
+ let mut total = 0;
+
+ // PTE pages at the leaf level.
+ let pte_epp = self.entries_per_page(self.pte_level());
+ // Ceiling of (num_virt_pages / entries_per_page).
+ let mut pages_at_level = (num_virt_pages + pte_epp - 1) / pte_epp;
+ total += pages_at_level;
+
+ // Walk PDE levels bottom-up (reverse of pde_levels()).
+ for &level in self.pde_levels().iter().rev() {
+ let epp = self.entries_per_page(level);
+ // How many pages at this level do we need to point to
+ // the previous pages_at_level?
+ // Calculated as ceiling of (pages_at_level / entries_per_page).
+ pages_at_level = (pages_at_level + epp - 1) / epp;
+ total += pages_at_level;
+ }
+
+ total
+ }
+}
+
/// Memory aperture for Page Table Entries (`PTE`s).
///
/// Determines which memory region the `PTE` points to.
@@ -149,3 +227,252 @@ fn from(val: AperturePde) -> Self {
val as u8
}
}
+
+/// Unified Page Table Entry wrapper for both MMU v2 and v3 `PTE`
+/// types, allowing the walker to work with either format.
+#[derive(Debug, Clone, Copy)]
+pub(crate) enum Pte {
+ /// MMU v2 `PTE` (Turing/Ampere/Ada).
+ V2(ver2::Pte),
+ /// MMU v3 `PTE` (Hopper+).
+ V3(ver3::Pte),
+}
+
+impl Pte {
+ /// Create a `PTE` from a raw `u64` value for the given MMU version.
+ pub(crate) fn new(version: MmuVersion, val: u64) -> Self {
+ match version {
+ MmuVersion::V2 => Self::V2(ver2::Pte::new(val)),
+ MmuVersion::V3 => Self::V3(ver3::Pte::new(val)),
+ }
+ }
+
+ /// Create an invalid `PTE` for the given MMU version.
+ pub(crate) fn invalid(version: MmuVersion) -> Self {
+ match version {
+ MmuVersion::V2 => Self::V2(ver2::Pte::invalid()),
+ MmuVersion::V3 => Self::V3(ver3::Pte::invalid()),
+ }
+ }
+
+ /// Create a valid `PTE` for video memory.
+ pub(crate) fn new_vram(version: MmuVersion, pfn: Pfn, writable: bool) -> Self {
+ match version {
+ MmuVersion::V2 => Self::V2(ver2::Pte::new_vram(pfn, writable)),
+ MmuVersion::V3 => Self::V3(ver3::Pte::new_vram(pfn, writable)),
+ }
+ }
+
+ /// Check if this `PTE` is valid.
+ pub(crate) fn is_valid(&self) -> bool {
+ match self {
+ Self::V2(p) => p.valid(),
+ Self::V3(p) => p.valid(),
+ }
+ }
+
+ /// Get the physical frame number.
+ pub(crate) fn frame_number(&self) -> Pfn {
+ match self {
+ Self::V2(p) => p.frame_number(),
+ Self::V3(p) => p.frame_number(),
+ }
+ }
+
+ /// Get the raw `u64` value.
+ pub(crate) fn raw_u64(&self) -> u64 {
+ match self {
+ Self::V2(p) => p.raw_u64(),
+ Self::V3(p) => p.raw_u64(),
+ }
+ }
+
+ /// Read a `PTE` from VRAM.
+ pub(crate) fn read(
+ window: &mut pramin::PraminWindow<'_>,
+ addr: VramAddress,
+ mmu_version: MmuVersion,
+ ) -> Result<Self> {
+ let val = window.try_read64(addr.raw())?;
+ Ok(Self::new(mmu_version, val))
+ }
+
+ /// Write this `PTE` to VRAM.
+ pub(crate) fn write(
+ &self,
+ window: &mut pramin::PraminWindow<'_>,
+ addr: VramAddress,
+ ) -> Result {
+ window.try_write64(addr.raw(), self.raw_u64())
+ }
+}
+
+impl Default for Pte {
+ fn default() -> Self {
+ Self::V2(ver2::Pte::default())
+ }
+}
+
+/// Unified Page Directory Entry wrapper for both MMU v2 and v3 `PDE`.
+#[derive(Debug, Clone, Copy)]
+pub(crate) enum Pde {
+ /// MMU v2 `PDE` (Turing/Ampere/Ada).
+ V2(ver2::Pde),
+ /// MMU v3 `PDE` (Hopper+).
+ V3(ver3::Pde),
+}
+
+impl Pde {
+ /// Create a `PDE` from a raw `u64` value for the given MMU version.
+ pub(crate) fn new(version: MmuVersion, val: u64) -> Self {
+ match version {
+ MmuVersion::V2 => Self::V2(ver2::Pde::new(val)),
+ MmuVersion::V3 => Self::V3(ver3::Pde::new(val)),
+ }
+ }
+
+ /// Create a valid `PDE` pointing to a page table in video memory.
+ pub(crate) fn new_vram(version: MmuVersion, table_pfn: Pfn) -> Self {
+ match version {
+ MmuVersion::V2 => Self::V2(ver2::Pde::new_vram(table_pfn)),
+ MmuVersion::V3 => Self::V3(ver3::Pde::new_vram(table_pfn)),
+ }
+ }
+
+ /// Create an invalid `PDE` for the given MMU version.
+ pub(crate) fn invalid(version: MmuVersion) -> Self {
+ match version {
+ MmuVersion::V2 => Self::V2(ver2::Pde::invalid()),
+ MmuVersion::V3 => Self::V3(ver3::Pde::invalid()),
+ }
+ }
+
+ /// Check if this `PDE` is valid.
+ pub(crate) fn is_valid(&self) -> bool {
+ match self {
+ Self::V2(p) => p.is_valid(),
+ Self::V3(p) => p.is_valid(),
+ }
+ }
+
+ /// Get the VRAM address of the page table.
+ pub(crate) fn table_vram_address(&self) -> VramAddress {
+ match self {
+ Self::V2(p) => p.table_vram_address(),
+ Self::V3(p) => p.table_vram_address(),
+ }
+ }
+
+ /// Get the raw `u64` value.
+ pub(crate) fn raw_u64(&self) -> u64 {
+ match self {
+ Self::V2(p) => p.raw_u64(),
+ Self::V3(p) => p.raw_u64(),
+ }
+ }
+
+ /// Read a `PDE` from VRAM.
+ pub(crate) fn read(
+ window: &mut pramin::PraminWindow<'_>,
+ addr: VramAddress,
+ mmu_version: MmuVersion,
+ ) -> Result<Self> {
+ let val = window.try_read64(addr.raw())?;
+ Ok(Self::new(mmu_version, val))
+ }
+
+ /// Write this `PDE` to VRAM.
+ pub(crate) fn write(
+ &self,
+ window: &mut pramin::PraminWindow<'_>,
+ addr: VramAddress,
+ ) -> Result {
+ window.try_write64(addr.raw(), self.raw_u64())
+ }
+}
+
+impl Default for Pde {
+ fn default() -> Self {
+ Self::V2(ver2::Pde::default())
+ }
+}
+
+/// Unified Dual Page Directory Entry wrapper for both MMU v2 and v3 [`DualPde`].
+#[derive(Debug, Clone, Copy)]
+pub(crate) enum DualPde {
+ /// MMU v2 [`DualPde`] (Turing/Ampere/Ada).
+ V2(ver2::DualPde),
+ /// MMU v3 [`DualPde`] (Hopper+).
+ V3(ver3::DualPde),
+}
+
+impl DualPde {
+ /// Create a [`DualPde`] from raw 128-bit value (two `u64`s) for the given MMU version.
+ pub(crate) fn new(version: MmuVersion, big: u64, small: u64) -> Self {
+ match version {
+ MmuVersion::V2 => Self::V2(ver2::DualPde::new(big, small)),
+ MmuVersion::V3 => Self::V3(ver3::DualPde::new(big, small)),
+ }
+ }
+
+ /// Create a [`DualPde`] with only the small page table pointer set.
+ pub(crate) fn new_small(version: MmuVersion, table_pfn: Pfn) -> Self {
+ match version {
+ MmuVersion::V2 => Self::V2(ver2::DualPde::new_small(table_pfn)),
+ MmuVersion::V3 => Self::V3(ver3::DualPde::new_small(table_pfn)),
+ }
+ }
+
+ /// Check if the small page table pointer is valid.
+ pub(crate) fn has_small(&self) -> bool {
+ match self {
+ Self::V2(d) => d.has_small(),
+ Self::V3(d) => d.has_small(),
+ }
+ }
+
+ /// Get the small page table VRAM address.
+ pub(crate) fn small_vram_address(&self) -> VramAddress {
+ match self {
+ Self::V2(d) => d.small.table_vram_address(),
+ Self::V3(d) => d.small.table_vram_address(),
+ }
+ }
+
+ /// Get the raw `u64` value of the big PDE.
+ pub(crate) fn big_raw_u64(&self) -> u64 {
+ match self {
+ Self::V2(d) => d.big.raw_u64(),
+ Self::V3(d) => d.big.raw_u64(),
+ }
+ }
+
+ /// Get the raw `u64` value of the small PDE.
+ pub(crate) fn small_raw_u64(&self) -> u64 {
+ match self {
+ Self::V2(d) => d.small.raw_u64(),
+ Self::V3(d) => d.small.raw_u64(),
+ }
+ }
+
+ /// Read a dual PDE (128-bit) from VRAM.
+ pub(crate) fn read(
+ window: &mut pramin::PraminWindow<'_>,
+ addr: VramAddress,
+ mmu_version: MmuVersion,
+ ) -> Result<Self> {
+ let lo = window.try_read64(addr.raw())?;
+ let hi = window.try_read64(addr.raw() + 8)?;
+ Ok(Self::new(mmu_version, lo, hi))
+ }
+
+ /// Write this dual PDE (128-bit) to VRAM.
+ pub(crate) fn write(
+ &self,
+ window: &mut pramin::PraminWindow<'_>,
+ addr: VramAddress,
+ ) -> Result {
+ window.try_write64(addr.raw(), self.big_raw_u64())?;
+ window.try_write64(addr.raw() + 8, self.small_raw_u64())
+ }
+}
--
2.34.1
next prev parent reply other threads:[~2026-02-18 21:21 UTC|newest]
Thread overview: 28+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-02-18 21:19 [PATCH v7 00/23] nova-core: Add memory management support Joel Fernandes
2026-02-18 21:19 ` [PATCH v7 01/23] nova-core: mm: Add support to use PRAMIN windows to write to VRAM Joel Fernandes
2026-02-18 21:19 ` [PATCH v7 02/23] docs: gpu: nova-core: Document the PRAMIN aperture mechanism Joel Fernandes
2026-02-18 21:20 ` [PATCH v7 03/23] nova-core: Add BAR1 aperture type and size constant Joel Fernandes
2026-02-18 21:20 ` [PATCH v7 04/23] nova-core: gsp: Add BAR1 PDE base accessors Joel Fernandes
2026-02-18 21:20 ` [PATCH v7 05/23] nova-core: mm: Add common memory management types Joel Fernandes
2026-02-18 21:20 ` [PATCH v7 06/23] nova-core: mm: Add common types for all page table formats Joel Fernandes
2026-02-18 21:20 ` [PATCH v7 07/23] nova-core: mm: Add MMU v2 page table types Joel Fernandes
2026-02-18 21:20 ` [PATCH v7 08/23] nova-core: mm: Add MMU v3 " Joel Fernandes
2026-02-18 21:20 ` Joel Fernandes [this message]
2026-02-18 21:20 ` [PATCH v7 10/23] nova-core: mm: Add TLB flush support Joel Fernandes
2026-02-18 21:20 ` [PATCH v7 11/23] nova-core: mm: Add GpuMm centralized memory manager Joel Fernandes
2026-02-18 21:20 ` [PATCH v7 12/23] nova-core: mm: Add page table walker for MMU v2/v3 Joel Fernandes
2026-02-18 21:20 ` [PATCH v7 13/23] nova-core: mm: Add Virtual Memory Manager Joel Fernandes
2026-02-18 21:20 ` [PATCH v7 14/23] nova-core: mm: Add virtual address range tracking to VMM Joel Fernandes
2026-02-18 21:20 ` [PATCH v7 15/23] nova-core: mm: Add multi-page mapping API " Joel Fernandes
2026-02-18 21:20 ` [PATCH v7 16/23] nova-core: mm: Add BAR1 user interface Joel Fernandes
2026-02-18 21:20 ` [PATCH v7 17/23] nova-core: gsp: Return GspStaticInfo and FbLayout from boot() Joel Fernandes
2026-02-18 21:20 ` [PATCH v7 18/23] nova-core: mm: Add BAR1 memory management self-tests Joel Fernandes
2026-02-18 21:20 ` [PATCH v7 19/23] nova-core: mm: Add PRAMIN aperture self-tests Joel Fernandes
2026-02-18 21:20 ` [PATCH v7 20/23] nova-core: gsp: Extract usable FB region from GSP Joel Fernandes
2026-02-18 21:20 ` [PATCH v7 21/23] nova-core: fb: Add usable_vram field to FbLayout Joel Fernandes
2026-02-18 21:20 ` [PATCH v7 22/23] nova-core: mm: Use usable VRAM region for buddy allocator Joel Fernandes
2026-02-18 21:20 ` [PATCH v7 23/23] nova-core: mm: Add BarUser to struct Gpu and create at boot Joel Fernandes
2026-02-19 15:20 ` [PATCH v7 00/23] nova-core: Add memory management support Alexandre Courbot
2026-02-19 19:48 ` Joel Fernandes
2026-02-20 1:54 ` Alexandre Courbot
2026-02-20 3:25 ` Alexandre Courbot
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20260218212020.800836-10-joelagnelf@nvidia.com \
--to=joelagnelf@nvidia.com \
--cc=a.hindborg@kernel.org \
--cc=acourbot@nvidia.com \
--cc=airlied@gmail.com \
--cc=alex.gaynor@gmail.com \
--cc=alexander.deucher@amd.com \
--cc=aliceryhl@google.com \
--cc=amd-gfx@lists.freedesktop.org \
--cc=apopple@nvidia.com \
--cc=arighi@nvidia.com \
--cc=aritger@nvidia.com \
--cc=balbirs@nvidia.com \
--cc=bjorn3_gh@protonmail.com \
--cc=boqun.feng@gmail.com \
--cc=christian.koenig@amd.com \
--cc=corbet@lwn.net \
--cc=dakr@kernel.org \
--cc=daniel.almeida@collabora.com \
--cc=deller@gmx.de \
--cc=dri-devel@lists.freedesktop.org \
--cc=ecourtney@nvidia.com \
--cc=elle@weathered-steel.dev \
--cc=epeer@nvidia.com \
--cc=gary@garyguo.net \
--cc=intel-gfx@lists.freedesktop.org \
--cc=intel-xe@lists.freedesktop.org \
--cc=jani.nikula@linux.intel.com \
--cc=jhubbard@nvidia.com \
--cc=joel@joelfernandes.org \
--cc=joonas.lahtinen@linux.intel.com \
--cc=linux-doc@vger.kernel.org \
--cc=linux-fbdev@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=lossin@kernel.org \
--cc=lucas.demarchi@intel.com \
--cc=maarten.lankhorst@linux.intel.com \
--cc=matthew.auld@intel.com \
--cc=matthew.brost@intel.com \
--cc=mripard@kernel.org \
--cc=ndjukic@nvidia.com \
--cc=nouveau@lists.freedesktop.org \
--cc=ojeda@kernel.org \
--cc=phasta@kernel.org \
--cc=ray.huang@amd.com \
--cc=rodrigo.vivi@intel.com \
--cc=rust-for-linux@vger.kernel.org \
--cc=simona@ffwll.ch \
--cc=thomas.hellstrom@linux.intel.com \
--cc=tmgross@umich.edu \
--cc=ttabi@nvidia.com \
--cc=tursulin@ursulin.net \
--cc=tzimmermann@suse.de \
--cc=zhiw@nvidia.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox