[PATCH v10 05/28] gpu: nova-core: set DMA mask width based on GPU architecture

[John Hubbard <jhubbard@nvidia.com>]

Replace the hardcoded 47-bit DMA mask with per-architecture values.
Add Architecture::dma_mask() with an exhaustive match, so new
architectures get a compile-time reminder to specify their width.

Set the DMA mask in Gpu::new(). Gpu owns all DMA allocations for
the device, so no concurrent allocations can exist while the
constructor is still running.

Signed-off-by: John Hubbard <jhubbard@nvidia.com>
---
 drivers/gpu/nova-core/driver.rs | 16 ----------------
 drivers/gpu/nova-core/gpu.rs    | 22 ++++++++++++++++++++--
 2 files changed, 20 insertions(+), 18 deletions(-)

diff --git a/drivers/gpu/nova-core/driver.rs b/drivers/gpu/nova-core/driver.rs
index 84b0e1703150..3f655337ef6f 100644
--- a/drivers/gpu/nova-core/driver.rs
+++ b/drivers/gpu/nova-core/driver.rs
@@ -4,8 +4,6 @@
     auxiliary,
     device::Core,
     devres::Devres,
-    dma::Device,
-    dma::DmaMask,
     pci,
     pci::{
         Class,
@@ -38,14 +36,6 @@ pub(crate) struct NovaCore {
 
 const BAR0_SIZE: usize = SZ_16M;
 
-// For now we only support Ampere which can use up to 47-bit DMA addresses.
-//
-// TODO: Add an abstraction for this to support newer GPUs which may support
-// larger DMA addresses. Limiting these GPUs to smaller address widths won't
-// have any adverse affects, unless installed on systems which require larger
-// DMA addresses. These systems should be quite rare.
-const GPU_DMA_BITS: u32 = 47;
-
 pub(crate) type Bar0 = pci::Bar<BAR0_SIZE>;
 
 kernel::pci_device_table!(
@@ -84,16 +74,10 @@ fn probe(pdev: &pci::Device<Core>, _info: &Self::IdInfo) -> impl PinInit<Self, E
             pdev.enable_device_mem()?;
             pdev.set_master();
 
-            // SAFETY: No concurrent DMA allocations or mappings can be made because
-            // the device is still being probed and therefore isn't being used by
-            // other threads of execution.
-            unsafe { pdev.dma_set_mask_and_coherent(DmaMask::new::<GPU_DMA_BITS>())? };
-
             let bar = Arc::pin_init(
                 pdev.iomap_region_sized::<BAR0_SIZE>(0, c"nova-core/bar0"),
                 GFP_KERNEL,
             )?;
-
             Ok(try_pin_init!(Self {
                 gpu <- Gpu::new(pdev, bar.clone(), bar.access(pdev.as_ref())?),
                 _reg <- auxiliary::Registration::new(
diff --git a/drivers/gpu/nova-core/gpu.rs b/drivers/gpu/nova-core/gpu.rs
index 4cf5e1ff830b..6db646a49519 100644
--- a/drivers/gpu/nova-core/gpu.rs
+++ b/drivers/gpu/nova-core/gpu.rs
@@ -3,6 +3,10 @@
 use kernel::{
     device,
     devres::Devres,
+    dma::{
+        Device,
+        DmaMask, //
+    },
     fmt,
     io::Io,
     num::Bounded,
@@ -159,6 +163,16 @@ pub(crate) enum Architecture with TryFrom<Bounded<u32, 6>> {
     }
 }
 
+impl Architecture {
+    /// Returns the DMA mask supported by this architecture.
+    pub(crate) const fn dma_mask(&self) -> DmaMask {
+        match self {
+            Self::Turing | Self::Ampere | Self::Ada => DmaMask::new::<47>(),
+            Self::Hopper | Self::BlackwellGB10x | Self::BlackwellGB20x => DmaMask::new::<52>(),
+        }
+    }
+}
+
 #[derive(Clone, Copy)]
 pub(crate) struct Revision {
     major: Bounded<u8, 4>,
@@ -262,17 +276,21 @@ pub(crate) struct Gpu {
 
 impl Gpu {
     pub(crate) fn new<'a>(
-        pdev: &'a pci::Device<device::Bound>,
+        pdev: &'a pci::Device<device::Core>,
         devres_bar: Arc<Devres<Bar0>>,
         bar: &'a Bar0,
     ) -> impl PinInit<Self, Error> + 'a {
         try_pin_init!(Self {
             spec: Spec::new(pdev.as_ref(), bar).inspect(|spec| {
-                dev_info!(pdev,"NVIDIA ({})\n", spec);
+                dev_info!(pdev, "NVIDIA ({})\n", spec);
             })?,
 
             // We must wait for GFW_BOOT completion before doing any significant setup on the GPU.
             _: {
+                // SAFETY: `Gpu` owns all DMA allocations for this device, and we are
+                // still constructing it, so no concurrent DMA allocations can exist.
+                unsafe { pdev.dma_set_mask_and_coherent(spec.chipset.arch().dma_mask())? };
+
                 gfw::wait_gfw_boot_completion(bar)
                     .inspect_err(|_| dev_err!(pdev, "GFW boot did not complete\n"))?;
             },
-- 
2.53.0