gpu: nova-core: Add basic Turing HAL

Add the basic HAL for recognizing Turing GPUs.  This isn't enough
to support booting GSP-RM on Turing, but it's a start.

Note that GA100, which boots using the same method as Turing, is not
supported yet.

Signed-off-by: Timur Tabi <ttabi@nvidia.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Reviewed-by: Gary Guo <gary@garyguo.net>
Acked-by: Danilo Krummrich <dakr@kernel.org>
Link: https://patch.msgid.link/20260122222848.2555890-8-ttabi@nvidia.com
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>

diff --git a/drivers/gpu/nova-core/falcon/hal.rs b/drivers/gpu/nova-core/falcon/hal.rs
index c77a1568ea96e86fd198e5bc30510a5dbc898722..c886ba03d1f65d84cc49bc00462da1b431118830 100644 (file)
--- a/drivers/gpu/nova-core/falcon/hal.rs
+++ b/drivers/gpu/nova-core/falcon/hal.rs
@@ -13,6 +13,7 @@ use crate::{
 };
 
 mod ga102;
+mod tu102;
 
 /// Hardware Abstraction Layer for Falcon cores.
 ///
@@ -60,6 +61,9 @@ pub(super) fn falcon_hal<E: FalconEngine + 'static>(
     use Chipset::*;
 
     let hal = match chipset {
+        TU102 | TU104 | TU106 | TU116 | TU117 => {
+            KBox::new(tu102::Tu102::<E>::new(), GFP_KERNEL)? as KBox<dyn FalconHal<E>>
+        }
         GA102 | GA103 | GA104 | GA106 | GA107 | AD102 | AD103 | AD104 | AD106 | AD107 => {
             KBox::new(ga102::Ga102::<E>::new(), GFP_KERNEL)? as KBox<dyn FalconHal<E>>
         }

diff --git a/drivers/gpu/nova-core/falcon/hal/tu102.rs b/drivers/gpu/nova-core/falcon/hal/tu102.rs
new file mode 100644 (file)
index 0000000..586d5dc
--- /dev/null
+++ b/drivers/gpu/nova-core/falcon/hal/tu102.rs
@@ -0,0 +1,79 @@
+// SPDX-License-Identifier: GPL-2.0
+
+use core::marker::PhantomData;
+
+use kernel::{
+    io::poll::read_poll_timeout,
+    prelude::*,
+    time::delay::fsleep,
+    time::Delta, //
+};
+
+use crate::{
+    driver::Bar0,
+    falcon::{
+        Falcon,
+        FalconBromParams,
+        FalconEngine, //
+    },
+    regs, //
+};
+
+use super::FalconHal;
+
+pub(super) struct Tu102<E: FalconEngine>(PhantomData<E>);
+
+impl<E: FalconEngine> Tu102<E> {
+    pub(super) fn new() -> Self {
+        Self(PhantomData)
+    }
+}
+
+impl<E: FalconEngine> FalconHal<E> for Tu102<E> {
+    fn select_core(&self, _falcon: &Falcon<E>, _bar: &Bar0) -> Result {
+        Ok(())
+    }
+
+    fn signature_reg_fuse_version(
+        &self,
+        _falcon: &Falcon<E>,
+        _bar: &Bar0,
+        _engine_id_mask: u16,
+        _ucode_id: u8,
+    ) -> Result<u32> {
+        Ok(0)
+    }
+
+    fn program_brom(&self, _falcon: &Falcon<E>, _bar: &Bar0, _params: &FalconBromParams) -> Result {
+        Ok(())
+    }
+
+    fn is_riscv_active(&self, bar: &Bar0) -> bool {
+        let cpuctl = regs::NV_PRISCV_RISCV_CORE_SWITCH_RISCV_STATUS::read(bar, &E::ID);
+        cpuctl.active_stat()
+    }
+
+    fn reset_wait_mem_scrubbing(&self, bar: &Bar0) -> Result {
+        // TIMEOUT: memory scrubbing should complete in less than 10ms.
+        read_poll_timeout(
+            || Ok(regs::NV_PFALCON_FALCON_DMACTL::read(bar, &E::ID)),
+            |r| r.mem_scrubbing_done(),
+            Delta::ZERO,
+            Delta::from_millis(10),
+        )
+        .map(|_| ())
+    }
+
+    fn reset_eng(&self, bar: &Bar0) -> Result {
+        regs::NV_PFALCON_FALCON_ENGINE::update(bar, &E::ID, |v| v.set_reset(true));
+
+        // TIMEOUT: falcon engine should not take more than 10us to reset.
+        fsleep(Delta::from_micros(10));
+
+        regs::NV_PFALCON_FALCON_ENGINE::update(bar, &E::ID, |v| v.set_reset(false));
+
+        self.reset_wait_mem_scrubbing(bar)?;
+
+        Ok(())
+    }
+}

diff --git a/drivers/gpu/nova-core/regs.rs b/drivers/gpu/nova-core/regs.rs
index b8ddfe2e5ae7ffeb2ca580f92c6523a05b43604d..cd7b7aa6fc2adf2b8fecf34dee808bc995964e68 100644 (file)
--- a/drivers/gpu/nova-core/regs.rs
+++ b/drivers/gpu/nova-core/regs.rs
@@ -307,6 +307,13 @@ register!(NV_PFALCON_FALCON_DMACTL @ PFalconBase[0x0000010c] {
     7:7     secure_stat as bool;
 });
 
+impl NV_PFALCON_FALCON_DMACTL {
+    /// Returns `true` if memory scrubbing is completed.
+    pub(crate) fn mem_scrubbing_done(self) -> bool {
+        !self.dmem_scrubbing() && !self.imem_scrubbing()
+    }
+}
+
 register!(NV_PFALCON_FALCON_DMATRFBASE @ PFalconBase[0x00000110] {
     31:0    base as u32;
 });
@@ -389,6 +396,13 @@ register!(NV_PFALCON2_FALCON_BROM_PARAADDR @ PFalcon2Base[0x00000210[1]] {
 
 // PRISCV
 
+// RISC-V status register for debug (Turing and GA100 only).
+// Reflects current RISC-V core status.
+register!(NV_PRISCV_RISCV_CORE_SWITCH_RISCV_STATUS @ PFalcon2Base[0x00000240] {
+    0:0     active_stat as bool, "RISC-V core active/inactive status";
+});
+
+// GA102 and later
 register!(NV_PRISCV_RISCV_CPUCTL @ PFalcon2Base[0x00000388] {
     0:0     halted as bool;
     7:7     active_stat as bool;