[PATCH v8 05/31] 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.

Move Spec creation into probe() so the architecture is known before
setting the DMA mask, and pass Spec into Gpu::new().

Signed-off-by: John Hubbard <jhubbard@nvidia.com>
---
 drivers/gpu/nova-core/driver.rs | 28 ++++++++++++----------------
 drivers/gpu/nova-core/gpu.rs    | 29 ++++++++++++++++++++---------
 2 files changed, 32 insertions(+), 25 deletions(-)

diff --git a/drivers/gpu/nova-core/driver.rs b/drivers/gpu/nova-core/driver.rs
index 84b0e1703150..41227d29934e 100644
--- a/drivers/gpu/nova-core/driver.rs
+++ b/drivers/gpu/nova-core/driver.rs
@@ -5,7 +5,6 @@
     device::Core,
     devres::Devres,
     dma::Device,
-    dma::DmaMask,
     pci,
     pci::{
         Class,
@@ -23,7 +22,10 @@
     },
 };
 
-use crate::gpu::Gpu;
+use crate::gpu::{
+    Gpu,
+    Spec, //
+};
 
 /// Counter for generating unique auxiliary device IDs.
 static AUXILIARY_ID_COUNTER: Atomic<u32> = Atomic::new(0);
@@ -38,14 +40,6 @@ 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!(
@@ -84,18 +78,20 @@ 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,
             )?;
+            let spec = Spec::new(pdev.as_ref(), bar.access(pdev.as_ref())?)?;
+            dev_info!(pdev, "NVIDIA ({})\n", spec);
+
+            // 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(spec.chipset().arch().dma_mask())? };
 
             Ok(try_pin_init!(Self {
-                gpu <- Gpu::new(pdev, bar.clone(), bar.access(pdev.as_ref())?),
+                gpu <- Gpu::new(pdev, bar.clone(), bar.access(pdev.as_ref())?, spec),
                 _reg <- auxiliary::Registration::new(
                     pdev.as_ref(),
                     c"nova-drm",
diff --git a/drivers/gpu/nova-core/gpu.rs b/drivers/gpu/nova-core/gpu.rs
index 3cd7709883be..e7c3860cfb28 100644
--- a/drivers/gpu/nova-core/gpu.rs
+++ b/drivers/gpu/nova-core/gpu.rs
@@ -3,6 +3,7 @@
 use kernel::{
     device,
     devres::Devres,
+    dma::DmaMask,
     fmt,
     pci,
     prelude::*,
@@ -162,6 +163,16 @@ pub(crate) enum Architecture {
     Blackwell = 0x1b,
 }
 
+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::Blackwell => DmaMask::new::<52>(),
+        }
+    }
+}
+
 impl TryFrom<u8> for Architecture {
     type Error = Error;
 
@@ -213,7 +224,7 @@ pub(crate) struct Spec {
 }
 
 impl Spec {
-    fn new(dev: &device::Device, bar: &Bar0) -> Result<Spec> {
+    pub(crate) fn new(dev: &device::Device, bar: &Bar0) -> Result<Spec> {
         // Some brief notes about boot0 and boot42, in chronological order:
         //
         // NV04 through NV50:
@@ -295,32 +306,32 @@ pub(crate) fn new<'a>(
         pdev: &'a pci::Device<device::Bound>,
         devres_bar: Arc<Devres<Bar0>>,
         bar: &'a Bar0,
+        spec: Spec,
     ) -> impl PinInit<Self, Error> + 'a {
-        try_pin_init!(Self {
-            spec: Spec::new(pdev.as_ref(), bar).inspect(|spec| {
-                dev_info!(pdev, "NVIDIA ({})\n", spec);
-            })?,
+        let chipset = spec.chipset();
 
+        try_pin_init!(Self {
             _: {
                 gfw::wait_gfw_boot_completion(bar)
                     .inspect_err(|_| dev_err!(pdev, "GFW boot did not complete\n"))?;
             },
 
-            sysmem_flush: SysmemFlush::register(pdev.as_ref(), bar, spec.chipset)?,
+            sysmem_flush: SysmemFlush::register(pdev.as_ref(), bar, chipset)?,
 
             gsp_falcon: Falcon::new(
                 pdev.as_ref(),
-                spec.chipset,
+                chipset,
             )
             .inspect(|falcon| falcon.clear_swgen0_intr(bar))?,
 
-            sec2_falcon: Falcon::new(pdev.as_ref(), spec.chipset)?,
+            sec2_falcon: Falcon::new(pdev.as_ref(), chipset)?,
 
             gsp <- Gsp::new(pdev),
 
-            _: { gsp.boot(pdev, bar, spec.chipset, gsp_falcon, sec2_falcon)? },
+            _: { gsp.boot(pdev, bar, chipset, gsp_falcon, sec2_falcon)? },
 
             bar: devres_bar,
+            spec,
         })
     }
 
-- 
2.53.0