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 06/23] gpu: nova-core: mm: Add support to use PRAMIN windows to write to VRAM
Date: Tue, 10 Mar 2026 20:39:51 -0400 [thread overview]
Message-ID: <20260311004008.2208806-7-joelagnelf@nvidia.com> (raw)
In-Reply-To: <20260311004008.2208806-1-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 | 293 +++++++++++++++++++++++++++++
drivers/gpu/nova-core/nova_core.rs | 1 +
drivers/gpu/nova-core/regs.rs | 6 +
4 files changed, 305 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..707794f49add
--- /dev/null
+++ b/drivers/gpu/nova-core/mm/pramin.rs
@@ -0,0 +1,293 @@
+// 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 is 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>>, vram_region: core::ops::Range<u64>) -> Result<()> {
+//! let pramin = Arc::pin_init(pramin::Pramin::new(devres_bar, vram_region)?, 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(())
+//! }
+//! ```
+//!
+//! ## 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>>, vram_region: core::ops::Range<u64>) -> Result<()> {
+//! let pramin = Arc::pin_init(pramin::Pramin::new(devres_bar, vram_region)?, 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 core::ops::Range;
+
+use crate::{
+ driver::Bar0,
+ num::IntoSafeCast,
+ regs, //
+};
+
+use kernel::{
+ devres::Devres,
+ io::Io,
+ new_mutex,
+ prelude::*,
+ revocable::RevocableGuard,
+ sizes::{
+ SZ_1M,
+ SZ_64K, //
+ },
+ sync::{
+ lock::mutex::MutexGuard,
+ Arc,
+ Mutex, //
+ },
+};
+
+/// Target memory type for the BAR0 window register.
+///
+/// Only VRAM is supported; Hopper+ GPUs do not support other targets.
+#[repr(u8)]
+#[derive(Debug, Default)]
+pub(crate) enum Bar0WindowTarget {
+ /// Video RAM (GPU framebuffer memory).
+ #[default]
+ Vram = 0,
+}
+
+impl From<Bar0WindowTarget> for u8 {
+ fn from(value: Bar0WindowTarget) -> Self {
+ value as u8
+ }
+}
+
+impl TryFrom<u8> for Bar0WindowTarget {
+ type Error = Error;
+
+ fn try_from(value: u8) -> Result<Self> {
+ match value {
+ 0 => Ok(Self::Vram),
+ _ => Err(EINVAL),
+ }
+ }
+}
+
+/// PRAMIN aperture base offset in BAR0.
+const PRAMIN_BASE: usize = 0x700000;
+
+/// PRAMIN aperture size (1MB).
+const PRAMIN_SIZE: usize = SZ_1M;
+
+/// 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> {
+ let (bar_offset, new_base) =
+ self.compute_window(vram_offset, ::core::mem::size_of::<$ty>())?;
+
+ if let Some(base) = new_base {
+ Self::write_window_base(&self.bar, base);
+ *self.state = base;
+ }
+ self.bar.$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: $ty) -> Result {
+ let (bar_offset, new_base) =
+ self.compute_window(vram_offset, ::core::mem::size_of::<$ty>())?;
+
+ if let Some(base) = new_base {
+ Self::write_window_base(&self.bar, base);
+ *self.state = base;
+ }
+ self.bar.$name(value, bar_offset)
+ }
+ };
+}
+
+/// PRAMIN aperture manager.
+///
+/// Call [`Pramin::window()`] to acquire exclusive PRAMIN access.
+#[pin_data]
+pub(crate) struct Pramin {
+ bar: Arc<Devres<Bar0>>,
+ /// Valid VRAM region. Accesses outside this range are rejected.
+ vram_region: Range<u64>,
+ /// PRAMIN aperture state, protected by a mutex.
+ ///
+ /// # Safety
+ ///
+ /// This lock is acquired during the DMA fence signaling 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<u64>,
+}
+
+impl Pramin {
+ /// Create a pin-initializer for PRAMIN.
+ ///
+ /// `vram_region` specifies the valid VRAM address range.
+ pub(crate) fn new(
+ bar: Arc<Devres<Bar0>>,
+ vram_region: Range<u64>,
+ ) -> Result<impl PinInit<Self>> {
+ let bar_access = bar.try_access().ok_or(ENODEV)?;
+ let current_base = Self::read_window_base(&bar_access);
+
+ Ok(pin_init!(Self {
+ bar,
+ vram_region,
+ state <- new_mutex!(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 bar = self.bar.try_access().ok_or(ENODEV)?;
+ let state = self.state.lock();
+ Ok(PraminWindow {
+ bar,
+ vram_region: self.vram_region.clone(),
+ state,
+ })
+ }
+
+ /// Read the current window base from the BAR0_WINDOW register.
+ fn read_window_base(bar: &Bar0) -> u64 {
+ let reg = regs::NV_PBUS_BAR0_WINDOW::read(bar);
+ // TODO: Convert to Bounded<u64, 40> when available.
+ u64::from(reg.window_base()) << 16
+ }
+}
+
+/// 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.
+///
+/// Only one [`PraminWindow`] can exist at a time per [`Pramin`] instance (enforced by the
+/// internal `MutexGuard`).
+pub(crate) struct PraminWindow<'a> {
+ bar: RevocableGuard<'a, Bar0>,
+ vram_region: Range<u64>,
+ state: MutexGuard<'a, u64>,
+}
+
+impl PraminWindow<'_> {
+ /// Write a new window base to the BAR0_WINDOW register.
+ fn write_window_base(bar: &Bar0, base: u64) {
+ // CAST: The caller (compute_window) validates that base is within the
+ // VRAM region which is always <= 40 bits. After >> 16, a 40-bit base
+ // becomes 24 bits, which fits in u32.
+ regs::NV_PBUS_BAR0_WINDOW::default()
+ .set_target(Bar0WindowTarget::Vram)
+ .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<u64>)> {
+ // Validate VRAM offset is within the valid VRAM region.
+ let vram_addr = vram_offset as u64;
+ let end_addr = vram_addr.checked_add(access_size as u64).ok_or(EINVAL)?;
+ if vram_addr < self.vram_region.start || end_addr > self.vram_region.end {
+ return Err(EINVAL);
+ }
+
+ // Check if access fits within the current 1MB window.
+ let current_base = *self.state;
+ if vram_addr >= current_base {
+ let offset_in_window: usize = (vram_addr - current_base).into_safe_cast();
+ if offset_in_window + access_size <= PRAMIN_SIZE {
+ return Ok((PRAMIN_BASE + offset_in_window, None));
+ }
+ }
+
+ // Access doesn't fit in current window - reposition.
+ // Hardware requires 64KB alignment for the window base register.
+ let needed_base = vram_addr & !(SZ_64K as u64 - 1);
+ let offset_in_window: usize = (vram_addr - needed_base).into_safe_cast();
+
+ // Verify access fits in the 1MB window from the new base.
+ if offset_in_window + access_size > PRAMIN_SIZE {
+ return Err(EINVAL);
+ }
+
+ Ok((PRAMIN_BASE + offset_in_window, Some(needed_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);
+}
diff --git a/drivers/gpu/nova-core/nova_core.rs b/drivers/gpu/nova-core/nova_core.rs
index b5caf1044697..c5a78d6388e5 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..8ec35b8c4b28 100644
--- a/drivers/gpu/nova-core/regs.rs
+++ b/drivers/gpu/nova-core/regs.rs
@@ -32,6 +32,7 @@
Architecture,
Chipset, //
},
+ mm::pramin::Bar0WindowTarget,
num::FromSafeCast,
};
@@ -102,6 +103,11 @@ 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 ?=> Bar0WindowTarget;
+ 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
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 ` Joel Fernandes [this message]
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 ` [PATCH v9 12/23] gpu: nova-core: mm: Add MMU v2 page table types Joel Fernandes
2026-03-11 0:39 ` [PATCH v9 13/23] gpu: nova-core: mm: Add MMU v3 " 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=20260311004008.2208806-7-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