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 v8 14/25] gpu: nova-core: mm: Add MMU v3 page table types
Date: Tue, 24 Feb 2026 17:53:12 -0500 [thread overview]
Message-ID: <20260224225323.3312204-15-joelagnelf@nvidia.com> (raw)
In-Reply-To: <20260224225323.3312204-1-joelagnelf@nvidia.com>
Add page table entry and directory structures for MMU version 3
used by Hopper and later GPUs.
Cc: Nikola Djukic <ndjukic@nvidia.com>
Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
drivers/gpu/nova-core/mm/pagetable.rs | 1 +
drivers/gpu/nova-core/mm/pagetable/ver3.rs | 302 +++++++++++++++++++++
2 files changed, 303 insertions(+)
create mode 100644 drivers/gpu/nova-core/mm/pagetable/ver3.rs
diff --git a/drivers/gpu/nova-core/mm/pagetable.rs b/drivers/gpu/nova-core/mm/pagetable.rs
index 925063fde45d..5263a8f56529 100644
--- a/drivers/gpu/nova-core/mm/pagetable.rs
+++ b/drivers/gpu/nova-core/mm/pagetable.rs
@@ -8,6 +8,7 @@
#![expect(dead_code)]
pub(crate) mod ver2;
+pub(crate) mod ver3;
use crate::gpu::Architecture;
diff --git a/drivers/gpu/nova-core/mm/pagetable/ver3.rs b/drivers/gpu/nova-core/mm/pagetable/ver3.rs
new file mode 100644
index 000000000000..e6cab2fe7d33
--- /dev/null
+++ b/drivers/gpu/nova-core/mm/pagetable/ver3.rs
@@ -0,0 +1,302 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! MMU v3 page table types for Hopper and later GPUs.
+//!
+//! This module defines MMU version 3 specific types (Hopper and later GPUs).
+//!
+//! Key differences from MMU v2:
+//! - Unified 40-bit address field for all apertures (v2 had separate sys/vid fields).
+//! - PCF (Page Classification Field) replaces separate privilege/RO/atomic/cache bits.
+//! - KIND field is 4 bits (not 8).
+//! - IS_PTE bit in PDE to support large pages directly.
+//! - No COMPTAGLINE field (compression handled differently in v3).
+//! - No separate ENCRYPTED bit.
+//!
+//! Bit field layouts derived from the NVIDIA OpenRM documentation:
+//! `open-gpu-kernel-modules/src/common/inc/swref/published/hopper/gh100/dev_mmu.h`
+
+#![expect(dead_code)]
+
+use super::{
+ AperturePde,
+ AperturePte,
+ PageTableLevel, //
+};
+use crate::mm::{
+ Pfn,
+ VramAddress, //
+};
+use kernel::prelude::*;
+
+/// PDE levels for MMU v3 (6-level hierarchy).
+pub(crate) const PDE_LEVELS: &[PageTableLevel] = &[
+ PageTableLevel::Pdb,
+ PageTableLevel::L1,
+ PageTableLevel::L2,
+ PageTableLevel::L3,
+ PageTableLevel::L4,
+];
+
+/// PTE level for MMU v3.
+pub(crate) const PTE_LEVEL: PageTableLevel = PageTableLevel::L5;
+
+/// Dual PDE level for MMU v3 (128-bit entries).
+pub(crate) const DUAL_PDE_LEVEL: PageTableLevel = PageTableLevel::L4;
+
+// Page Classification Field (PCF) - 5 bits for PTEs in MMU v3.
+bitfield! {
+ pub(crate) struct PtePcf(u8), "Page Classification Field for PTEs" {
+ 0:0 uncached as bool, "Bypass L2 cache (0=cached, 1=bypass)";
+ 1:1 acd as bool, "Access counting disabled (0=enabled, 1=disabled)";
+ 2:2 read_only as bool, "Read-only access (0=read-write, 1=read-only)";
+ 3:3 no_atomic as bool, "Atomics disabled (0=enabled, 1=disabled)";
+ 4:4 privileged as bool, "Privileged access only (0=regular, 1=privileged)";
+ }
+}
+
+impl PtePcf {
+ /// Create PCF for read-write mapping (cached, no atomics, regular mode).
+ pub(crate) fn rw() -> Self {
+ Self::default().set_no_atomic(true)
+ }
+
+ /// Create PCF for read-only mapping (cached, no atomics, regular mode).
+ pub(crate) fn ro() -> Self {
+ Self::default().set_read_only(true).set_no_atomic(true)
+ }
+
+ /// Get the raw `u8` value.
+ pub(crate) fn raw_u8(&self) -> u8 {
+ self.0
+ }
+}
+
+impl From<u8> for PtePcf {
+ fn from(val: u8) -> Self {
+ Self(val)
+ }
+}
+
+// Page Classification Field (PCF) - 3 bits for PDEs in MMU v3.
+// Controls Address Translation Services (ATS) and caching.
+bitfield! {
+ pub(crate) struct PdePcf(u8), "Page Classification Field for PDEs" {
+ 0:0 uncached as bool, "Bypass L2 cache (0=cached, 1=bypass)";
+ 1:1 no_ats as bool, "Address Translation Services disabled (0=enabled, 1=disabled)";
+ }
+}
+
+impl PdePcf {
+ /// Create PCF for cached mapping with ATS enabled (default).
+ pub(crate) fn cached() -> Self {
+ Self::default()
+ }
+
+ /// Get the raw `u8` value.
+ pub(crate) fn raw_u8(&self) -> u8 {
+ self.0
+ }
+}
+
+impl From<u8> for PdePcf {
+ fn from(val: u8) -> Self {
+ Self(val)
+ }
+}
+
+// Page Table Entry (PTE) for MMU v3.
+bitfield! {
+ pub(crate) struct Pte(u64), "Page Table Entry for MMU v3" {
+ 0:0 valid as bool, "Entry is valid";
+ 2:1 aperture as u8 => AperturePte, "Memory aperture type";
+ 7:3 pcf as u8 => PtePcf, "Page Classification Field";
+ 11:8 kind as u8, "Surface kind (4 bits, 0x0=pitch, 0xF=invalid)";
+ 51:12 frame_number as u64 => Pfn, "Physical frame number (for all apertures)";
+ 63:61 peer_id as u8, "Peer GPU ID for peer memory (0-7)";
+ }
+}
+
+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(frame: Pfn, writable: bool) -> Self {
+ let pcf = if writable { PtePcf::rw() } else { PtePcf::ro() };
+ Self::default()
+ .set_valid(true)
+ .set_aperture(AperturePte::VideoMemory)
+ .set_pcf(pcf)
+ .set_frame_number(frame)
+ }
+
+ /// Create an invalid PTE.
+ pub(crate) fn invalid() -> Self {
+ Self::default()
+ }
+
+ /// Get the raw `u64` value.
+ pub(crate) fn raw_u64(&self) -> u64 {
+ self.0
+ }
+}
+
+// Page Directory Entry (PDE) for MMU v3.
+//
+// Note: v3 uses a unified 40-bit address field (v2 had separate sys/vid address fields).
+bitfield! {
+ pub(crate) struct Pde(u64), "Page Directory Entry for MMU v3 (Hopper+)" {
+ 0:0 is_pte as bool, "Entry is a PTE (0=PDE, 1=large page PTE)";
+ 2:1 aperture as u8 => AperturePde, "Memory aperture (0=invalid, 1=vidmem, 2=coherent, 3=non-coherent)";
+ 5:3 pcf as u8 => PdePcf, "Page Classification Field (3 bits for PDE)";
+ 51:12 table_frame as u64 => Pfn, "Table frame number (40-bit unified address)";
+ }
+}
+
+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_is_pte(false)
+ .set_aperture(AperturePde::VideoMemory)
+ .set_table_frame(table_pfn)
+ }
+
+ /// Create an invalid PDE.
+ pub(crate) fn invalid() -> Self {
+ Self::default().set_aperture(AperturePde::Invalid)
+ }
+
+ /// Check if this PDE is valid.
+ pub(crate) fn is_valid(&self) -> bool {
+ self.aperture() != AperturePde::Invalid
+ }
+
+ /// 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())
+ }
+
+ /// Get the raw `u64` value.
+ pub(crate) fn raw_u64(&self) -> u64 {
+ self.0
+ }
+}
+
+// Big Page Table pointer for Dual PDE - 64-bit lower word of the 128-bit Dual PDE.
+bitfield! {
+ pub(crate) struct DualPdeBig(u64), "Big Page Table pointer in Dual PDE (MMU v3)" {
+ 0:0 is_pte as bool, "Entry is a PTE (for large pages)";
+ 2:1 aperture as u8 => AperturePde, "Memory aperture type";
+ 5:3 pcf as u8 => PdePcf, "Page Classification Field";
+ 51:8 table_frame as u64, "Table frame (table address 256-byte aligned)";
+ }
+}
+
+impl DualPdeBig {
+ /// Create a big page table pointer from a `u64` value.
+ pub(crate) fn new(val: u64) -> Self {
+ Self(val)
+ }
+
+ /// Create an invalid big page table pointer.
+ pub(crate) fn invalid() -> Self {
+ Self::default().set_aperture(AperturePde::Invalid)
+ }
+
+ /// Create a valid big PDE pointing to a page table in video memory.
+ pub(crate) fn new_vram(table_addr: VramAddress) -> Result<Self> {
+ // Big page table addresses must be 256-byte aligned (shift 8).
+ if table_addr.raw_u64() & 0xFF != 0 {
+ return Err(EINVAL);
+ }
+
+ let table_frame = table_addr.raw_u64() >> 8;
+ Ok(Self::default()
+ .set_is_pte(false)
+ .set_aperture(AperturePde::VideoMemory)
+ .set_table_frame(table_frame))
+ }
+
+ /// Check if this big PDE is valid.
+ pub(crate) fn is_valid(&self) -> bool {
+ self.aperture() != AperturePde::Invalid
+ }
+
+ /// Get the VRAM address of the big page table.
+ pub(crate) fn table_vram_address(&self) -> VramAddress {
+ debug_assert!(
+ self.aperture() == AperturePde::VideoMemory,
+ "table_vram_address called on non-VRAM DualPdeBig (aperture: {:?})",
+ self.aperture()
+ );
+ VramAddress::new(self.table_frame() << 8)
+ }
+
+ /// Get the raw `u64` value.
+ pub(crate) fn raw_u64(&self) -> u64 {
+ self.0
+ }
+}
+
+/// Dual PDE at Level 4 for MMU v3 - 128-bit entry.
+///
+/// Contains both big (64KB) and small (4KB) page table pointers:
+/// - Lower 64 bits: Big Page Table pointer.
+/// - Upper 64 bits: Small Page Table pointer.
+///
+/// ## Note
+///
+/// The big and small page table pointers have different address layouts:
+/// - Big address = field value << 8 (256-byte alignment).
+/// - Small address = field value << 12 (4KB alignment).
+///
+/// This is why `DualPdeBig` is a separate type from `Pde`.
+#[repr(C)]
+#[derive(Debug, Clone, Copy, Default)]
+pub(crate) struct DualPde {
+ /// Big Page Table pointer.
+ pub big: DualPdeBig,
+ /// Small Page Table pointer.
+ pub 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: DualPdeBig::new(big),
+ small: Pde::new(small),
+ }
+ }
+
+ /// Create a dual PDE with only the small page table pointer set.
+ pub(crate) fn new_small(table_pfn: Pfn) -> Self {
+ Self {
+ big: DualPdeBig::invalid(),
+ 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()
+ }
+}
--
2.34.1
next prev parent reply other threads:[~2026-02-24 22:54 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-02-24 22:52 [PATCH v8 00/25] gpu: nova-core: Add memory management support Joel Fernandes
2026-02-24 22:52 ` [PATCH v8 01/25] gpu: nova-core: Select GPU_BUDDY for VRAM allocation Joel Fernandes
2026-03-01 12:41 ` Alexandre Courbot
2026-02-24 22:53 ` [PATCH v8 02/25] gpu: nova-core: Kconfig: Sort select statements alphabetically Joel Fernandes
2026-03-01 12:40 ` Alexandre Courbot
2026-02-24 22:53 ` [PATCH v8 03/25] gpu: nova-core: gsp: Return GspStaticInfo and FbLayout from boot() Joel Fernandes
2026-02-24 22:53 ` [PATCH v8 04/25] gpu: nova-core: gsp: Extract usable FB region from GSP Joel Fernandes
2026-03-01 12:43 ` Alexandre Courbot
2026-02-24 22:53 ` [PATCH v8 05/25] gpu: nova-core: fb: Add usable_vram field to FbLayout Joel Fernandes
2026-02-24 22:53 ` [PATCH v8 06/25] gpu: nova-core: mm: Add support to use PRAMIN windows to write to VRAM Joel Fernandes
2026-03-02 11:58 ` Alexandre Courbot
2026-03-02 12:23 ` Alexandre Courbot
2026-02-24 22:53 ` [PATCH v8 07/25] docs: gpu: nova-core: Document the PRAMIN aperture mechanism Joel Fernandes
2026-03-02 12:02 ` Alexandre Courbot
2026-02-24 22:53 ` [PATCH v8 08/25] gpu: nova-core: mm: Add common memory management types Joel Fernandes
2026-02-24 22:53 ` [PATCH v8 09/25] gpu: nova-core: mm: Add TLB flush support Joel Fernandes
2026-02-24 22:53 ` [PATCH v8 10/25] gpu: nova-core: mm: Add GpuMm centralized memory manager Joel Fernandes
2026-02-24 22:53 ` [PATCH v8 11/25] gpu: nova-core: mm: Use usable VRAM region for buddy allocator Joel Fernandes
2026-03-01 12:56 ` Alexandre Courbot
2026-03-02 3:08 ` Alexandre Courbot
2026-02-24 22:53 ` [PATCH v8 12/25] gpu: nova-core: mm: Add common types for all page table formats Joel Fernandes
2026-02-24 22:53 ` [PATCH v8 13/25] gpu: nova-core: mm: Add MMU v2 page table types Joel Fernandes
2026-02-24 22:53 ` Joel Fernandes [this message]
2026-02-24 22:53 ` [PATCH v8 15/25] gpu: nova-core: mm: Add unified page table entry wrapper enums Joel Fernandes
2026-02-24 22:53 ` [PATCH v8 16/25] gpu: nova-core: mm: Add page table walker for MMU v2/v3 Joel Fernandes
2026-02-25 5:39 ` Gary Guo
2026-02-25 14:26 ` Joel Fernandes
2026-03-01 13:15 ` Gary Guo
2026-02-24 22:53 ` [PATCH v8 17/25] gpu: nova-core: mm: Add Virtual Memory Manager Joel Fernandes
2026-02-24 22:53 ` [PATCH v8 18/25] gpu: nova-core: mm: Add virtual address range tracking to VMM Joel Fernandes
2026-02-24 22:53 ` [PATCH v8 19/25] gpu: nova-core: mm: Add multi-page mapping API " Joel Fernandes
2026-02-24 22:53 ` [PATCH v8 20/25] gpu: nova-core: Add BAR1 aperture type and size constant Joel Fernandes
2026-02-24 22:53 ` [PATCH v8 21/25] gpu: nova-core: gsp: Add BAR1 PDE base accessors Joel Fernandes
2026-02-24 22:53 ` [PATCH v8 22/25] gpu: nova-core: mm: Add BAR1 user interface Joel Fernandes
2026-02-24 22:53 ` [PATCH v8 23/25] gpu: nova-core: mm: Add BarUser to struct Gpu and create at boot Joel Fernandes
2026-02-24 22:53 ` [PATCH v8 24/25] gpu: nova-core: mm: Add BAR1 memory management self-tests Joel Fernandes
2026-02-24 22:53 ` [PATCH v8 25/25] gpu: nova-core: mm: Add PRAMIN aperture self-tests Joel Fernandes
2026-03-02 12:04 ` 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=20260224225323.3312204-15-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