[PATCH v4 08/33] gpu: nova-core: set DMA mask width based on GPU architecture

[John Hubbard <jhubbard@nvidia.com>]

This removes a "TODO" item in the code, which was hardcoded to work on
Ampere and Ada GPUs. Hopper/Blackwell+ have a larger width, so do an
early read of boot42, in order to pick the correct value.

Cc: Gary Guo <gary@garyguo.net>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
---
 drivers/gpu/nova-core/driver.rs | 33 ++++++++++++++--------------
 drivers/gpu/nova-core/gpu.rs    | 38 ++++++++++++++++++++++++---------
 2 files changed, 44 insertions(+), 27 deletions(-)

diff --git a/drivers/gpu/nova-core/driver.rs b/drivers/gpu/nova-core/driver.rs
index e39885c0d5ca..4ff07b643db6 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,
@@ -17,7 +16,10 @@
     sync::Arc, //
 };
 
-use crate::gpu::Gpu;
+use crate::gpu::{
+    Gpu,
+    Spec, //
+};
 
 #[pin_data]
 pub(crate) struct NovaCore {
@@ -29,14 +31,6 @@ 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!(
@@ -75,18 +69,23 @@ 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(
+            let devres_bar = Arc::pin_init(
                 pdev.iomap_region_sized::<BAR0_SIZE>(0, c"nova-core/bar0"),
                 GFP_KERNEL,
             )?;
 
+            // Read the GPU spec early to determine the correct DMA address width.
+            // Hopper/Blackwell+ support 52-bit DMA addresses, earlier architectures use 47-bit.
+            let spec = Spec::new(pdev.as_ref(), devres_bar.access(pdev.as_ref())?)?;
+            dev_info!(pdev.as_ref(), "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, devres_bar.clone(), devres_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 b6a898008a59..24feb0e8723e 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::*,
@@ -102,7 +103,7 @@ fn try_from(value: u32) -> Result<Self, Self::Error> {
 });
 
 impl Chipset {
-    pub(crate) fn arch(&self) -> Architecture {
+    pub(crate) const fn arch(&self) -> Architecture {
         match self {
             Self::TU102 | Self::TU104 | Self::TU106 | Self::TU117 | Self::TU116 => {
                 Architecture::Turing
@@ -155,6 +156,19 @@ pub(crate) enum Architecture {
     Blackwell = 0x1b,
 }
 
+impl Architecture {
+    /// Returns the DMA mask supported by this architecture.
+    ///
+    /// Hopper and Blackwell support 52-bit DMA addresses, while earlier architectures
+    /// (Turing, Ampere, Ada) support 47-bit DMA addresses.
+    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;
 
@@ -204,7 +218,7 @@ 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:
@@ -234,6 +248,10 @@ fn new(dev: &device::Device, bar: &Bar0) -> Result<Spec> {
             dev_err!(dev, "Unsupported chipset: {}\n", boot42);
         })
     }
+
+    pub(crate) fn chipset(&self) -> Chipset {
+        self.chipset
+    }
 }
 
 impl TryFrom<regs::NV_PMC_BOOT_42> for Spec {
@@ -281,33 +299,33 @@ 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 {
             // We must wait for GFW_BOOT completion before doing any significant setup on the GPU.
             _: {
                 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