[PATCH 16/17] gpu: nova-core: add KUnit tests for the interrupt tree and HALs

[John Hubbard]

Neither the per-architecture interrupt policy nor the vector
arithmetic touches hardware, so KUnit can cover both without a GPU.

Add three suites:

    * nova_core_gin_tree covers the leaf index bounds, the
    subtree-to-leaf mapping and its out-of-range filtering, the vector
    encoding, the masking of subtrees an architecture does not
    implement, and that every supported chipset implements the subtree
    carrying the GSP notification.

    * nova_core_gin_hal covers the tree size on each family, and the
    rearm method for each combination of family and interrupt type.

    * nova_core_falcon_hal covers the falcon retrigger gate. It is keyed
    on the architecture rather than the HAL, because GA100 shares the
    Turing HAL but does have the register.

Assisted-by: Cursor:claude-opus-5
Reviewed-by: Will Pierce <wpierce@xxxxxxxxxx>
Signed-off-by: John Hubbard <jhubbard@xxxxxxxxxx>
---
 drivers/gpu/nova-core/falcon/hal.rs         |  24 ++++
 drivers/gpu/nova-core/irq/hal.rs            | 106 ++++++++++++++++-
 drivers/gpu/nova-core/irq/interrupt_tree.rs | 121 ++++++++++++++++++++
 3 files changed, 250 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/nova-core/falcon/hal.rs b/drivers/gpu/nova-core/falcon/hal.rs
index f0828b32aebb..6bff9fea1a79 100644
--- a/drivers/gpu/nova-core/falcon/hal.rs
+++ b/drivers/gpu/nova-core/falcon/hal.rs
@@ -107,3 +107,27 @@ pub(super) fn falcon_hal<E: FalconEngine + 'static>(
 
     Ok(hal)
 }
+
+#[kunit_tests(nova_core_falcon_hal)]
+mod tests {
+    use super::*;
+
+    /// Only Turing falcons lack the interrupt retrigger register. GA100 has it even though
+    /// [`falcon_hal`] gives GA100 the Turing HAL, which is why the gate is keyed on the
+    /// architecture instead.
+    #[test]
+    fn intr_retrigger_gate_per_arch() {
+        assert!(!has_intr_retrigger(Chipset::TU102));
+
+        for chipset in [
+            Chipset::GA100,
+            Chipset::GA102,
+            Chipset::AD102,
+            Chipset::GH100,
+            Chipset::GB100,
+            Chipset::GB202,
+        ] {
+            assert!(has_intr_retrigger(chipset));
+        }
+    }
+}
diff --git a/drivers/gpu/nova-core/irq/hal.rs b/drivers/gpu/nova-core/irq/hal.rs
index cf2d1aa080fa..1993e2ef5143 100644
--- a/drivers/gpu/nova-core/irq/hal.rs
+++ b/drivers/gpu/nova-core/irq/hal.rs
@@ -8,7 +8,8 @@
 
 use kernel::{
     io::Io,
-    pci::IrqType, //
+    pci::IrqType,
+    prelude::*, //
 };
 
 use crate::{
@@ -109,3 +110,106 @@ pub(super) fn cpu_interrupt_hal(chipset: Chipset) -> &'static dyn CpuInterruptHa
         }
     }
 }
+
+#[kunit_tests(nova_core_gin_hal)]
+mod tests {
+    use super::*;
+
+    use crate::gpu::Chipset;
+
+    /// Pre-Hopper parts have an 8-leaf tree, so 4 subtrees and `0x0f`.
+    #[test]
+    fn pre_hopper_tree_size() {
+        for chipset in [Chipset::TU102, Chipset::GA102, Chipset::AD102] {
+            let hal = cpu_interrupt_hal(chipset);
+            assert_eq!(hal.num_leaves(), 8);
+            assert_eq!(hal.implemented_subtrees(), 0x0f);
+        }
+    }
+
+    /// Hopper and later implement a 16-leaf tree, so 8 subtrees and `0xff`.
+    #[test]
+    fn hopper_plus_tree_size() {
+        for chipset in [Chipset::GH100, Chipset::GB100, Chipset::GB202] {
+            let hal = cpu_interrupt_hal(chipset);
+            assert_eq!(hal.num_leaves(), 16);
+            assert_eq!(hal.implemented_subtrees(), 0xff);
+        }
+    }
+
+    /// The implemented subtrees always number exactly `num_leaves / 2`, one per subtree.
+    #[test]
+    fn implemented_subtrees_matches_leaf_count() {
+        for chipset in [
+            Chipset::TU102,
+            Chipset::GA102,
+            Chipset::AD102,
+            Chipset::GH100,
+            Chipset::GB100,
+            Chipset::GB202,
+        ] {
+            let hal = cpu_interrupt_hal(chipset);
+            assert_eq!(
+                hal.implemented_subtrees().count_ones() as usize,
+                hal.num_leaves() / 2
+            );
+        }
+    }
+
+    /// Only pre-Hopper MSI rearms through the configuration-space mirror. MSI on Hopper and later
+    /// cycles the `TOP` enables of every serviced subtree.
+    #[test]
+    fn msi_rearm_method_per_arch() {
+        for chipset in [Chipset::TU102, Chipset::GA102, Chipset::AD102] {
+            let hal = cpu_interrupt_hal(chipset);
+            assert_eq!(
+                hal.pci_irq_rearm_method(IrqType::Msi),
+                Some(PciIrqRearmMethod::ConfigMirrorEoi)
+            );
+        }
+
+        for chipset in [Chipset::GH100, Chipset::GB100, Chipset::GB202] {
+            let hal = cpu_interrupt_hal(chipset);
+            assert_eq!(
+                hal.pci_irq_rearm_method(IrqType::Msi),
+                Some(PciIrqRearmMethod::TopEnableCycleServiced)
+            );
+        }
+    }
+
+    /// MSI-X gives each subtree its own table entry, so on every architecture its rearm cycles
+    /// only the subtree the handler serves.
+    #[test]
+    fn msix_rearms_one_subtree_on_every_arch() {
+        for chipset in [
+            Chipset::TU102,
+            Chipset::GA102,
+            Chipset::AD102,
+            Chipset::GH100,
+            Chipset::GB100,
+            Chipset::GB202,
+        ] {
+            let hal = cpu_interrupt_hal(chipset);
+            assert_eq!(
+                hal.pci_irq_rearm_method(IrqType::MsiX),
+                Some(PciIrqRearmMethod::TopEnableCycleSubtree)
+            );
+        }
+    }
+
+    /// `INTx` is level-triggered and needs no rearm write on any architecture.
+    #[test]
+    fn intx_needs_no_rearm() {
+        for chipset in [
+            Chipset::TU102,
+            Chipset::GA102,
+            Chipset::AD102,
+            Chipset::GH100,
+            Chipset::GB100,
+            Chipset::GB202,
+        ] {
+            let hal = cpu_interrupt_hal(chipset);
+            assert_eq!(hal.pci_irq_rearm_method(IrqType::Intx), None);
+        }
+    }
+}
diff --git a/drivers/gpu/nova-core/irq/interrupt_tree.rs b/drivers/gpu/nova-core/irq/interrupt_tree.rs
index f4f1494cddba..42e72fa8089e 100644
--- a/drivers/gpu/nova-core/irq/interrupt_tree.rs
+++ b/drivers/gpu/nova-core/irq/interrupt_tree.rs
@@ -302,3 +302,124 @@ pub(super) fn clear_vectors(&self, bar: Bar0<'_>, vectors: u32) {
         }
     }
 }
+
+#[kunit_tests(nova_core_gin_tree)]
+mod tests {
+    use super::*;
+
+    /// A leaf index is a `Bounded<usize, 4>`, so it accepts 0..=15 and rejects 16.
+    #[test]
+    fn leaf_index_bounds() {
+        assert!(LeafIndex::try_new(0).is_some());
+        assert!(LeafIndex::try_new(15).is_some());
+        assert!(LeafIndex::try_new(16).is_none());
+    }
+
+    /// Subtree `N` covers the two adjacent leaves `2N` and `2N + 1`.
+    #[test]
+    fn subtree_covers_two_adjacent_leaves() {
+        let tree = Tree {
+            num_leaves: 16,
+            serviced_subtrees: 0xff,
+            rearm_method: None,
+        };
+
+        for index in 0..8usize {
+            let mut leaves = Subtree { index }.iter_leaves(&tree);
+            assert_eq!(leaves.next().map(|leaf| leaf.index.get()), Some(index * 2));
+            assert_eq!(
+                leaves.next().map(|leaf| leaf.index.get()),
+                Some(index * 2 + 1)
+            );
+            assert!(leaves.next().is_none());
+        }
+    }
+
+    /// Leaves that fall outside the addressable range are filtered out, never panicking. The
+    /// filter is the [`LeafIndex`] bound, not the tree's leaf count, so this holds even on the
+    /// widest tree.
+    #[test]
+    fn subtree_leaves_out_of_range_are_filtered() {
+        let tree = Tree {
+            num_leaves: 16,
+            serviced_subtrees: 0xff,
+            rearm_method: None,
+        };
+
+        // Subtree 8 would cover leaves 16 and 17, both beyond the leaf index range.
+        assert!(Subtree { index: 8 }.iter_leaves(&tree).next().is_none());
+    }
+
+    /// The production [`vector_leaf_bit`] maps every vector to a `(leaf, bit)` pair, valid leaves
+    /// stay within [`LeafIndex`], and the fixed doorbell (129) and GSP (155) vectors land where
+    /// the handlers expect.
+    #[test]
+    fn vector_maps_to_leaf_and_bit() {
+        // Every vector of a 16-leaf tree maps to an addressable leaf and a bit in 0..32.
+        for vector in 0u32..(16 * 32) {
+            let (leaf, bit) = vector_leaf_bit(vector);
+
+            assert!(LeafIndex::try_new(leaf).is_some());
+            assert!(bit < 32);
+            assert_eq!(leaf as u32 * 32 + bit, vector);
+        }
+
+        // The fixed vectors the handlers rely on: CPU doorbell 129 and GSP notification 155, both
+        // in leaf 4, which is present on both the 8-leaf (pre-Hopper) and 16-leaf trees.
+        assert_eq!(vector_leaf_bit(129), (4, 1));
+        assert_eq!(vector_leaf_bit(155), (4, 27));
+        assert!(LeafIndex::try_new(vector_leaf_bit(155).0).is_some());
+
+        // The first vector beyond the 16-leaf tree lands in leaf 16, which is out of range.
+        assert!(LeafIndex::try_new(vector_leaf_bit(16 * 32).0).is_none());
+    }
+
+    /// [`vector_subtree_mask`] agrees with [`vector_leaf_bit`] on which subtree holds a vector,
+    /// and the doorbell (129) and GSP (155) vectors share one, so a single allocation and a single
+    /// enabled subtree serve both.
+    #[test]
+    fn vector_maps_to_subtree() {
+        for vector in 0u32..(16 * 32) {
+            let (leaf, _) = vector_leaf_bit(vector);
+
+            assert_eq!(vector_subtree_mask(vector), 1u32 << (leaf / 2));
+        }
+
+        assert_eq!(vector_subtree_mask(155), 1 << 2);
+        assert_eq!(vector_subtree_mask(129), vector_subtree_mask(155));
+    }
+
+    /// [`Tree::new`] drops subtrees the architecture does not implement, so a caller cannot enable
+    /// a `TOP` bit with no leaves behind it.
+    #[test]
+    fn tree_new_masks_unimplemented_subtrees() {
+        assert_eq!(
+            Tree::new(Chipset::TU102, IrqType::Msi, 0xff).serviced_subtrees,
+            0x0f
+        );
+        assert_eq!(
+            Tree::new(Chipset::GH100, IrqType::Msi, 0xff).serviced_subtrees,
+            0xff
+        );
+    }
+
+    /// Every supported chipset implements the subtree that carries the GSP notification.
+    #[test]
+    fn serviced_subtree_is_implemented_everywhere() {
+        let serviced = crate::irq::gsp::GSP_SUBTREE;
+
+        for chipset in [
+            Chipset::TU102,
+            Chipset::GA102,
+            Chipset::AD102,
+            Chipset::GH100,
+            Chipset::GB100,
+            Chipset::GB202,
+        ] {
+            assert_eq!(
+                serviced & !cpu_interrupt_hal(chipset).implemented_subtrees(),
+                0
+            );
+        }
+    }
+}
-- 
2.55.0