From: Joel Fernandes <joelagnelf@nvidia.com>
To: linux-kernel@vger.kernel.org
Cc: "Miguel Ojeda" <ojeda@kernel.org>,
"Boqun Feng" <boqun@kernel.org>, "Gary Guo" <gary@garyguo.net>,
"Björn Roy Baron" <bjorn3_gh@protonmail.com>,
"Benno Lossin" <lossin@kernel.org>,
"Andreas Hindborg" <a.hindborg@kernel.org>,
"Alice Ryhl" <aliceryhl@google.com>,
"Trevor Gross" <tmgross@umich.edu>,
"Danilo Krummrich" <dakr@kernel.org>,
"Dave Airlie" <airlied@redhat.com>,
"Daniel Almeida" <daniel.almeida@collabora.com>,
"Koen Koning" <koen.koning@linux.intel.com>,
dri-devel@lists.freedesktop.org, nouveau@lists.freedesktop.org,
rust-for-linux@vger.kernel.org,
"Nikola Djukic" <ndjukic@nvidia.com>,
"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>,
"Alex Gaynor" <alex.gaynor@gmail.com>,
"Boqun Feng" <boqun.feng@gmail.com>,
"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>,
alexeyi@nvidia.com, "Eliot Courtney" <ecourtney@nvidia.com>,
joel@joelfernandes.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>
Subject: [PATCH v9 12/23] gpu: nova-core: mm: Add MMU v2 page table types
Date: Tue, 10 Mar 2026 20:39:57 -0400 [thread overview]
Message-ID: <20260311004008.2208806-13-joelagnelf@nvidia.com> (raw)
In-Reply-To: <20260311004008.2208806-1-joelagnelf@nvidia.com>
Add page table entry and directory structures for MMU version 2
used by Turing/Ampere/Ada GPUs.
Cc: Nikola Djukic <ndjukic@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
drivers/gpu/nova-core/mm/pagetable.rs | 2 +
drivers/gpu/nova-core/mm/pagetable/ver2.rs | 232 +++++++++++++++++++++
2 files changed, 234 insertions(+)
create mode 100644 drivers/gpu/nova-core/mm/pagetable/ver2.rs
diff --git a/drivers/gpu/nova-core/mm/pagetable.rs b/drivers/gpu/nova-core/mm/pagetable.rs
index 3946ce2f50a5..2dcd559cc692 100644
--- a/drivers/gpu/nova-core/mm/pagetable.rs
+++ b/drivers/gpu/nova-core/mm/pagetable.rs
@@ -8,6 +8,8 @@
#![expect(dead_code)]
+pub(crate) mod ver2;
+
use crate::gpu::Architecture;
/// Extracts the page table index at a given level from a virtual address.
diff --git a/drivers/gpu/nova-core/mm/pagetable/ver2.rs b/drivers/gpu/nova-core/mm/pagetable/ver2.rs
new file mode 100644
index 000000000000..6e617846c57b
--- /dev/null
+++ b/drivers/gpu/nova-core/mm/pagetable/ver2.rs
@@ -0,0 +1,232 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! MMU v2 page table types for Turing and Ampere GPUs.
+//!
+//! This module defines MMU version 2 specific types (Turing, Ampere and Ada GPUs).
+//!
+//! Bit field layouts derived from the NVIDIA OpenRM documentation:
+//! `open-gpu-kernel-modules/src/common/inc/swref/published/turing/tu102/dev_mmu.h`
+
+#![expect(dead_code)]
+
+use super::{
+ AperturePde,
+ AperturePte,
+ PageTableLevel,
+ VaLevelIndex, //
+};
+use crate::mm::{
+ Pfn,
+ VirtualAddress,
+ VramAddress, //
+};
+
+bitfield! {
+ pub(crate) struct VirtualAddressV2(u64), "MMU v2 49-bit virtual address layout" {
+ 11:0 offset as u64, "Page offset [11:0]";
+ 20:12 pt_idx as u64, "PT index [20:12]";
+ 28:21 pde0_idx as u64, "PDE0 index [28:21]";
+ 37:29 pde1_idx as u64, "PDE1 index [37:29]";
+ 46:38 pde2_idx as u64, "PDE2 index [46:38]";
+ 48:47 pde3_idx as u64, "PDE3 index [48:47]";
+ }
+}
+
+impl VirtualAddressV2 {
+ /// Create a [`VirtualAddressV2`] from a [`VirtualAddress`].
+ pub(crate) fn new(va: VirtualAddress) -> Self {
+ Self(va.raw_u64())
+ }
+}
+
+impl VaLevelIndex for VirtualAddressV2 {
+ fn level_index(&self, level: u64) -> u64 {
+ match level {
+ 0 => self.pde3_idx(),
+ 1 => self.pde2_idx(),
+ 2 => self.pde1_idx(),
+ 3 => self.pde0_idx(),
+ 4 => self.pt_idx(),
+ _ => 0,
+ }
+ }
+}
+
+/// PDE levels for MMU v2 (5-level hierarchy: PDB -> L1 -> L2 -> L3 -> L4).
+pub(crate) const PDE_LEVELS: &[PageTableLevel] = &[
+ PageTableLevel::Pdb,
+ PageTableLevel::L1,
+ PageTableLevel::L2,
+ PageTableLevel::L3,
+];
+
+/// PTE level for MMU v2.
+pub(crate) const PTE_LEVEL: PageTableLevel = PageTableLevel::L4;
+
+/// Dual PDE level for MMU v2 (128-bit entries).
+pub(crate) const DUAL_PDE_LEVEL: PageTableLevel = PageTableLevel::L3;
+
+// Page Table Entry (PTE) for MMU v2 - 64-bit entry at level 4.
+bitfield! {
+ pub(crate) struct Pte(u64), "Page Table Entry for MMU v2" {
+ 0:0 valid as bool, "Entry is valid";
+ 2:1 aperture as u8 => AperturePte, "Memory aperture type";
+ 3:3 volatile as bool, "Volatile (bypass L2 cache)";
+ 4:4 encrypted as bool, "Encryption enabled (Confidential Computing)";
+ 5:5 privilege as bool, "Privileged access only";
+ 6:6 read_only as bool, "Write protection";
+ 7:7 atomic_disable as bool, "Atomic operations disabled";
+ 53:8 frame_number_sys as u64 => Pfn, "Frame number for system memory";
+ 32:8 frame_number_vid as u64 => Pfn, "Frame number for video memory";
+ 35:33 peer_id as u8, "Peer GPU ID for peer memory (0-7)";
+ 53:36 comptagline as u32, "Compression tag line bits";
+ 63:56 kind as u8, "Surface kind/format";
+ }
+}
+
+impl Pte {
+ /// Create a PTE from a `u64` value.
+ pub(crate) fn new(val: u64) -> Self {
+ Self(val)
+ }
+
+ /// Create a valid PTE for video memory.
+ pub(crate) fn new_vram(pfn: Pfn, writable: bool) -> Self {
+ Self::default()
+ .set_valid(true)
+ .set_aperture(AperturePte::VideoMemory)
+ .set_frame_number_vid(pfn)
+ .set_read_only(!writable)
+ }
+
+ /// Create an invalid PTE.
+ pub(crate) fn invalid() -> Self {
+ Self::default()
+ }
+
+ /// Get the frame number based on aperture type.
+ pub(crate) fn frame_number(&self) -> Pfn {
+ match self.aperture() {
+ AperturePte::VideoMemory => self.frame_number_vid(),
+ _ => self.frame_number_sys(),
+ }
+ }
+
+ /// Get the raw `u64` value.
+ pub(crate) fn raw_u64(&self) -> u64 {
+ self.0
+ }
+}
+
+// Page Directory Entry (PDE) for MMU v2 - 64-bit entry at levels 0-2.
+bitfield! {
+ pub(crate) struct Pde(u64), "Page Directory Entry for MMU v2" {
+ 0:0 valid_inverted as bool, "Valid bit (inverted logic)";
+ 2:1 aperture as u8 => AperturePde, "Memory aperture type";
+ 3:3 volatile as bool, "Volatile (bypass L2 cache)";
+ 5:5 no_ats as bool, "Disable Address Translation Services";
+ 53:8 table_frame_sys as u64 => Pfn, "Table frame number for system memory";
+ 32:8 table_frame_vid as u64 => Pfn, "Table frame number for video memory";
+ 35:33 peer_id as u8, "Peer GPU ID (0-7)";
+ }
+}
+
+impl Pde {
+ /// Create a PDE from a `u64` value.
+ pub(crate) fn new(val: u64) -> Self {
+ Self(val)
+ }
+
+ /// Create a valid PDE pointing to a page table in video memory.
+ pub(crate) fn new_vram(table_pfn: Pfn) -> Self {
+ Self::default()
+ .set_valid_inverted(false) // 0 = valid
+ .set_aperture(AperturePde::VideoMemory)
+ .set_table_frame_vid(table_pfn)
+ }
+
+ /// Create an invalid PDE.
+ pub(crate) fn invalid() -> Self {
+ Self::default()
+ .set_valid_inverted(true)
+ .set_aperture(AperturePde::Invalid)
+ }
+
+ /// Check if this PDE is valid.
+ pub(crate) fn is_valid(&self) -> bool {
+ !self.valid_inverted() && self.aperture() != AperturePde::Invalid
+ }
+
+ /// Get the table frame number based on aperture type.
+ pub(crate) fn table_frame(&self) -> Pfn {
+ match self.aperture() {
+ AperturePde::VideoMemory => self.table_frame_vid(),
+ _ => self.table_frame_sys(),
+ }
+ }
+
+ /// Get the VRAM address of the page table.
+ pub(crate) fn table_vram_address(&self) -> VramAddress {
+ debug_assert!(
+ self.aperture() == AperturePde::VideoMemory,
+ "table_vram_address called on non-VRAM PDE (aperture: {:?})",
+ self.aperture()
+ );
+ VramAddress::from(self.table_frame_vid())
+ }
+
+ /// Get the raw `u64` value of the PDE.
+ pub(crate) fn raw_u64(&self) -> u64 {
+ self.0
+ }
+}
+
+/// Dual PDE at Level 3 - 128-bit entry of Large/Small Page Table pointers.
+///
+/// The dual PDE supports both large (64KB) and small (4KB) page tables.
+#[repr(C)]
+#[derive(Debug, Clone, Copy, Default)]
+pub(crate) struct DualPde {
+ /// Large/Big Page Table pointer (lower 64 bits).
+ pub(crate) big: Pde,
+ /// Small Page Table pointer (upper 64 bits).
+ pub(crate) small: Pde,
+}
+
+impl DualPde {
+ /// Create a dual PDE from raw 128-bit value (two `u64`s).
+ pub(crate) fn new(big: u64, small: u64) -> Self {
+ Self {
+ big: Pde::new(big),
+ small: Pde::new(small),
+ }
+ }
+
+ /// Create a dual PDE with only the small page table pointer set.
+ ///
+ /// Note: The big (LPT) portion is set to 0, not `Pde::invalid()`.
+ /// According to hardware documentation, clearing bit 0 of the 128-bit
+ /// entry makes the PDE behave as a "normal" PDE. Using `Pde::invalid()`
+ /// would set bit 0 (valid_inverted), which breaks page table walking.
+ pub(crate) fn new_small(table_pfn: Pfn) -> Self {
+ Self {
+ big: Pde::new(0),
+ small: Pde::new_vram(table_pfn),
+ }
+ }
+
+ /// Check if the small page table pointer is valid.
+ pub(crate) fn has_small(&self) -> bool {
+ self.small.is_valid()
+ }
+
+ /// Check if the big page table pointer is valid.
+ pub(crate) fn has_big(&self) -> bool {
+ self.big.is_valid()
+ }
+
+ /// Get the small page table PFN.
+ pub(crate) fn small_pfn(&self) -> Pfn {
+ self.small.table_frame()
+ }
+}
--
2.34.1
next prev parent reply other threads:[~2026-03-11 0:40 UTC|newest]
Thread overview: 32+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-11 0:39 [PATCH v9 00/23] gpu: nova-core: Add memory management support Joel Fernandes
2026-03-11 0:39 ` [PATCH v9 01/23] gpu: nova-core: Select GPU_BUDDY for VRAM allocation Joel Fernandes
2026-03-12 6:34 ` Eliot Courtney
2026-03-16 13:17 ` Alexandre Courbot
2026-03-11 0:39 ` [PATCH v9 02/23] gpu: nova-core: Kconfig: Sort select statements alphabetically Joel Fernandes
2026-03-12 6:35 ` Eliot Courtney
2026-03-16 13:17 ` Alexandre Courbot
2026-03-11 0:39 ` [PATCH v9 03/23] gpu: nova-core: gsp: Return GspStaticInfo from boot() Joel Fernandes
2026-03-12 6:37 ` Eliot Courtney
2026-03-11 0:39 ` [PATCH v9 04/23] gpu: nova-core: gsp: Extract usable FB region from GSP Joel Fernandes
2026-03-13 6:58 ` Eliot Courtney
2026-03-16 13:18 ` Alexandre Courbot
2026-03-11 0:39 ` [PATCH v9 05/23] gpu: nova-core: gsp: Expose total physical VRAM end from FB region info Joel Fernandes
2026-03-16 13:19 ` Alexandre Courbot
2026-03-11 0:39 ` [PATCH v9 06/23] gpu: nova-core: mm: Add support to use PRAMIN windows to write to VRAM Joel Fernandes
2026-03-11 0:39 ` [PATCH v9 07/23] docs: gpu: nova-core: Document the PRAMIN aperture mechanism Joel Fernandes
2026-03-11 0:39 ` [PATCH v9 08/23] gpu: nova-core: mm: Add common memory management types Joel Fernandes
2026-03-11 0:39 ` [PATCH v9 09/23] gpu: nova-core: mm: Add TLB flush support Joel Fernandes
2026-03-11 0:39 ` [PATCH v9 10/23] gpu: nova-core: mm: Add GpuMm centralized memory manager Joel Fernandes
2026-03-11 0:39 ` [PATCH v9 11/23] gpu: nova-core: mm: Add common types for all page table formats Joel Fernandes
2026-03-11 0:39 ` Joel Fernandes [this message]
2026-03-11 0:39 ` [PATCH v9 13/23] gpu: nova-core: mm: Add MMU v3 page table types Joel Fernandes
2026-03-11 0:39 ` [PATCH v9 14/23] gpu: nova-core: mm: Add unified page table entry wrapper enums Joel Fernandes
2026-03-11 0:40 ` [PATCH v9 15/23] gpu: nova-core: mm: Add page table walker for MMU v2/v3 Joel Fernandes
2026-03-11 0:40 ` [PATCH v9 16/23] gpu: nova-core: mm: Add Virtual Memory Manager Joel Fernandes
2026-03-11 0:40 ` [PATCH v9 17/23] gpu: nova-core: mm: Add virtual address range tracking to VMM Joel Fernandes
2026-03-11 0:40 ` [PATCH v9 18/23] gpu: nova-core: mm: Add multi-page mapping API " Joel Fernandes
2026-03-11 0:40 ` [PATCH v9 19/23] gpu: nova-core: Add BAR1 aperture type and size constant Joel Fernandes
2026-03-11 0:40 ` [PATCH v9 20/23] gpu: nova-core: mm: Add BAR1 user interface Joel Fernandes
2026-03-11 0:40 ` [PATCH v9 21/23] gpu: nova-core: mm: Add BAR1 memory management self-tests Joel Fernandes
2026-03-11 0:40 ` [PATCH v9 22/23] gpu: nova-core: mm: Add PRAMIN aperture self-tests Joel Fernandes
2026-03-11 0:40 ` [PATCH v9 23/23] gpu: nova-core: Use runtime BAR1 size instead of hardcoded 256MB Joel Fernandes
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=20260311004008.2208806-13-joelagnelf@nvidia.com \
--to=joelagnelf@nvidia.com \
--cc=a.hindborg@kernel.org \
--cc=acourbot@nvidia.com \
--cc=airlied@gmail.com \
--cc=airlied@redhat.com \
--cc=alex.gaynor@gmail.com \
--cc=alexander.deucher@amd.com \
--cc=alexeyi@nvidia.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=boqun@kernel.org \
--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=koen.koning@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