gpu: nova-core: fix stack overflow in GSP memory allocation

The `Cmdq::new` function was allocating a `PteArray` struct on the stack
and was causing a stack overflow with 8216 bytes.

Modify the `PteArray` to calculate and write the Page Table Entries
directly into the coherent DMA buffer one-by-one. This reduces the stack
usage quite a lot.

Reported-by: Gary Guo <gary@garyguo.net>
Closes: https://rust-for-linux.zulipchat.com/#narrow/channel/509436-Nova/topic/.60Cmdq.3A.3Anew.60.20uses.20excessive.20stack.20size/near/570375549
Link: https://lore.kernel.org/rust-for-linux/CANiq72mAQxbRJZDnik3Qmd4phvFwPA01O2jwaaXRh_T+2=L-qA@mail.gmail.com/
Fixes: f38b4f105cfc ("gpu: nova-core: Create initial Gsp")
Acked-by: Alexandre Courbot <acourbot@nvidia.com>
Signed-off-by: Tim Kovalenko <tim.kovalenko@proton.me>
Link: https://patch.msgid.link/20260309-drm-rust-next-v4-4-4ef485b19a4c@proton.me
[ * Use PteArray::entry() in LogBuffer::new(),
  * Add TODO comment to use IoView projections once available,
  * Add PTE_ARRAY_SIZE constant to avoid duplication.

    - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>

2 files changed, 29 insertions, 17 deletions

diff --git a/drivers/gpu/nova-core/gsp.rs b/drivers/gpu/nova-core/gsp.rs
index 25cd48514c77..c69adaa92bbe 100644
--- a/drivers/gpu/nova-core/gsp.rs
+++ b/drivers/gpu/nova-core/gsp.rs
@@ -47,16 +47,12 @@ struct PteArray<const NUM_ENTRIES: usize>([u64; NUM_ENTRIES]);
 unsafe impl<const NUM_ENTRIES: usize> AsBytes for PteArray<NUM_ENTRIES> {}
 
 impl<const NUM_PAGES: usize> PteArray<NUM_PAGES> {
-    /// Creates a new page table array mapping `NUM_PAGES` GSP pages starting at address `start`.
-    fn new(start: DmaAddress) -> Result<Self> {
-        let mut ptes = [0u64; NUM_PAGES];
-        for (i, pte) in ptes.iter_mut().enumerate() {
-            *pte = start
-                .checked_add(num::usize_as_u64(i) << GSP_PAGE_SHIFT)
-                .ok_or(EOVERFLOW)?;
-        }
-
-        Ok(Self(ptes))
+    /// Returns the page table entry for `index`, for a mapping starting at `start`.
+    // TODO: Replace with `IoView` projection once available.
+    fn entry(start: DmaAddress, index: usize) -> Result<u64> {
+        start
+            .checked_add(num::usize_as_u64(index) << GSP_PAGE_SHIFT)
+            .ok_or(EOVERFLOW)
     }
 }
 
@@ -86,16 +82,22 @@ impl LogBuffer {
             NUM_PAGES * GSP_PAGE_SIZE,
             GFP_KERNEL | __GFP_ZERO,
         )?);
-        let ptes = PteArray::<NUM_PAGES>::new(obj.0.dma_handle())?;
+
+        let start_addr = obj.0.dma_handle();
 
         // SAFETY: `obj` has just been created and we are its sole user.
-        unsafe {
-            // Copy the self-mapping PTE at the expected location.
+        let pte_region = unsafe {
             obj.0
-                .as_slice_mut(size_of::<u64>(), size_of_val(&ptes))?
-                .copy_from_slice(ptes.as_bytes())
+                .as_slice_mut(size_of::<u64>(), NUM_PAGES * size_of::<u64>())?
         };
 
+        // Write values one by one to avoid an on-stack instance of `PteArray`.
+        for (i, chunk) in pte_region.chunks_exact_mut(size_of::<u64>()).enumerate() {
+            let pte_value = PteArray::<0>::entry(start_addr, i)?;
+
+            chunk.copy_from_slice(&pte_value.to_ne_bytes());
+        }
+
         Ok(obj)
     }
 }
diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs
index ae54708c38eb..9c5efd2daf45 100644
--- a/drivers/gpu/nova-core/gsp/cmdq.rs
+++ b/drivers/gpu/nova-core/gsp/cmdq.rs
@@ -159,7 +159,7 @@ struct Msgq {
 #[repr(C)]
 struct GspMem {
     /// Self-mapping page table entries.
-    ptes: PteArray<{ GSP_PAGE_SIZE / size_of::<u64>() }>,
+    ptes: PteArray<{ Self::PTE_ARRAY_SIZE }>,
     /// CPU queue: the driver writes commands here, and the GSP reads them. It also contains the
     /// write and read pointers that the CPU updates.
     ///
@@ -172,6 +172,10 @@ struct GspMem {
     gspq: Msgq,
 }
 
+impl GspMem {
+    const PTE_ARRAY_SIZE: usize = GSP_PAGE_SIZE / size_of::<u64>();
+}
+
 // SAFETY: These structs don't meet the no-padding requirements of AsBytes but
 // that is not a problem because they are not used outside the kernel.
 unsafe impl AsBytes for GspMem {}
@@ -201,7 +205,13 @@ impl DmaGspMem {
 
         let gsp_mem =
             CoherentAllocation::<GspMem>::alloc_coherent(dev, 1, GFP_KERNEL | __GFP_ZERO)?;
-        dma_write!(gsp_mem, [0]?.ptes, PteArray::new(gsp_mem.dma_handle())?);
+
+        let start = gsp_mem.dma_handle();
+        // Write values one by one to avoid an on-stack instance of `PteArray`.
+        for i in 0..GspMem::PTE_ARRAY_SIZE {
+            dma_write!(gsp_mem, [0]?.ptes.0[i], PteArray::<0>::entry(start, i)?);
+        }
+
         dma_write!(
             gsp_mem,
             [0]?.cpuq.tx,