[PATCH RFC v6 05/26] nova-core: mm: Add support to use PRAMIN windows to write to VRAM

[Joel Fernandes <joelagnelf@nvidia.com>]

PRAMIN apertures are a crucial mechanism to direct read/write to VRAM.
Add support for the same.

Signed-off-by: Joel Fernandes <joelagnelf@nvidia.com>
---
 drivers/gpu/nova-core/mm/mod.rs    |   5 +
 drivers/gpu/nova-core/mm/pramin.rs | 244 +++++++++++++++++++++++++++++
 drivers/gpu/nova-core/nova_core.rs |   1 +
 drivers/gpu/nova-core/regs.rs      |   5 +
 4 files changed, 255 insertions(+)
 create mode 100644 drivers/gpu/nova-core/mm/mod.rs
 create mode 100644 drivers/gpu/nova-core/mm/pramin.rs

diff --git a/drivers/gpu/nova-core/mm/mod.rs b/drivers/gpu/nova-core/mm/mod.rs
new file mode 100644
index 000000000000..7a5dd4220c67
--- /dev/null
+++ b/drivers/gpu/nova-core/mm/mod.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..6a7ea2dc7d77
--- /dev/null
+++ b/drivers/gpu/nova-core/mm/pramin.rs
@@ -0,0 +1,244 @@
+// 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. The [`Window`] type automatically repositions the window when
+//! accessing different VRAM regions and restores the original position on drop. This allows
+//! to reuse the same window for multiple accesses in the same window.
+//!
+//! 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::sync::Arc;
+//!
+//! fn example(devres_bar: Arc<Devres<Bar0>>) -> Result<()> {
+//!     let mut pram_win = pramin::Window::new(devres_bar)?;
+//!
+//!     // Write and read back.
+//!     pram_win.try_write32(0x100, 0xDEADBEEF)?;
+//!     let val = pram_win.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::sync::Arc;
+//!
+//! fn example(devres_bar: Arc<Devres<Bar0>>) -> Result<()> {
+//!     let mut pram_win = pramin::Window::new(devres_bar)?;
+//!
+//!     // Access first 1MB region.
+//!     pram_win.try_write32(0x100, 0x11111111)?;
+//!
+//!     // Access at 2MB - window auto-repositions.
+//!     pram_win.try_write32(0x200000, 0x22222222)?;
+//!
+//!     // Back to first region - window repositions again.
+//!     let val = pram_win.try_read32(0x100)?;
+//!     assert_eq!(val, 0x11111111);
+//!
+//!     Ok(())
+//! }
+//! ```
+
+#![allow(unused)]
+
+use crate::{
+    driver::Bar0,
+    regs, //
+};
+
+use kernel::bits::genmask_u64;
+use kernel::devres::Devres;
+use kernel::prelude::*;
+use kernel::ptr::{
+    Alignable,
+    Alignment, //
+};
+use kernel::sizes::{
+    SZ_1M,
+    SZ_64K, //
+};
+use kernel::sync::Arc;
+
+/// 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.
+///
+/// CAST: On 64-bit systems, this fits in usize.
+const MAX_VRAM_OFFSET: usize = genmask_u64(0..=39) as usize;
+
+/// 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::<$ty>())?;
+
+            // Update window base if needed and perform read.
+            let bar = self.bar.try_access().ok_or(ENODEV)?;
+            if let Some(base) = new_base {
+                Self::write_window_base(&bar, base);
+                self.current_base = base;
+            }
+            bar.$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.current_base = base;
+            }
+            bar.$name(value, bar_offset)
+        }
+    };
+}
+
+/// PRAMIN window for direct VRAM access.
+///
+/// The window auto-repositions when accessing VRAM offsets outside the current 1MB range.
+/// Original window position is saved on creation and restored on drop.
+pub(crate) struct Window {
+    bar: Arc<Devres<Bar0>>,
+    saved_base: usize,
+    current_base: usize,
+}
+
+impl Window {
+    /// Create a new PRAMIN window accessor.
+    ///
+    /// Saves the current window position for restoration on drop.
+    pub(crate) fn new(bar: Arc<Devres<Bar0>>) -> Result<Self> {
+        let bar_access = bar.try_access().ok_or(ENODEV)?;
+        let saved_base = Self::try_read_window_base(&bar_access)?;
+
+        Ok(Self {
+            bar,
+            saved_base,
+            current_base: 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)
+    }
+
+    /// 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.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 Window {
+    fn drop(&mut self) {
+        // Restore the original window base if it changed.
+        if self.current_base != self.saved_base {
+            if let Some(bar) = self.bar.try_access() {
+                Self::write_window_base(&bar, self.saved_base);
+            }
+        }
+    }
+}
+
+// SAFETY: `Window` requires `&mut self` for all accessors.
+unsafe impl Send for Window {}
+
+// SAFETY: `Window` requires `&mut self` for all accessors.
+unsafe impl Sync for Window {}
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 82cc6c0790e5..c8b8fbdcf608 100644
--- a/drivers/gpu/nova-core/regs.rs
+++ b/drivers/gpu/nova-core/regs.rs
@@ -96,6 +96,11 @@ 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