gpu: nova-core: add falcon register definitions and base code

Booting the GSP on Ampere requires an intricate dance between the GSP
and SEC2 falcons, where the GSP starts by running the FWSEC firmware to
create the WPR2 region , and then SEC2 loads the actual RISC-V firmware
into the GSP.

Add the common Falcon code and HAL for Ampere GPUs, and instantiate the
GSP and SEC2 Falcons that will be required to perform that dance and
boot the GSP.

Thanks to Ben Skeggs for pointing out an important bug in the memory
scrubbing code that could lead to a race condition and ultimately a
failure to boot the GSP!

Reviewed-by: Lyude Paul <lyude@redhat.com>
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Link: https://lore.kernel.org/r/20250619-nova-frts-v6-15-ecf41ef99252@nvidia.com
Signed-off-by: Danilo Krummrich <dakr@kernel.org>

Author: Gnurou

drivers/gpu/nova-core/falcon.rs

@@ -0,0 +1,24 @@
+// SPDX-License-Identifier: GPL-2.0
+
+use crate::{
+    driver::Bar0,
+    falcon::{Falcon, FalconEngine},
+    regs,
+};
+
+/// Type specifying the `Gsp` falcon engine. Cannot be instantiated.
+pub(crate) struct Gsp(());
+
+impl FalconEngine for Gsp {
+    const BASE: usize = 0x00110000;
+}
+
+impl Falcon<Gsp> {
+    /// Clears the SWGEN0 bit in the Falcon's IRQ status clear register to
+    /// allow GSP to signal CPU for processing new messages in message queue.
+    pub(crate) fn clear_swgen0_intr(&self, bar: &Bar0) {
+        regs::NV_PFALCON_FALCON_IRQSCLR::default()
+            .set_swgen0(true)
+            .write(bar, Gsp::BASE);
+    }
+}

drivers/gpu/nova-core/falcon/gsp.rs

@@ -0,0 +1,54 @@
+// SPDX-License-Identifier: GPL-2.0
+
+use kernel::prelude::*;
+
+use crate::driver::Bar0;
+use crate::falcon::{Falcon, FalconBromParams, FalconEngine};
+use crate::gpu::Chipset;
+
+mod ga102;
+
+/// Hardware Abstraction Layer for Falcon cores.
+///
+/// Implements chipset-specific low-level operations. The trait is generic against [`FalconEngine`]
+/// so its `BASE` parameter can be used in order to avoid runtime bound checks when accessing
+/// registers.
+pub(crate) trait FalconHal<E: FalconEngine>: Sync {
+    /// Activates the Falcon core if the engine is a risvc/falcon dual engine.
+    fn select_core(&self, _falcon: &Falcon<E>, _bar: &Bar0) -> Result {
+        Ok(())
+    }
+
+    /// Returns the fused version of the signature to use in order to run a HS firmware on this
+    /// falcon instance. `engine_id_mask` and `ucode_id` are obtained from the firmware header.
+    fn signature_reg_fuse_version(
+        &self,
+        falcon: &Falcon<E>,
+        bar: &Bar0,
+        engine_id_mask: u16,
+        ucode_id: u8,
+    ) -> Result<u32>;
+
+    /// Program the boot ROM registers prior to starting a secure firmware.
+    fn program_brom(&self, falcon: &Falcon<E>, bar: &Bar0, params: &FalconBromParams) -> Result;
+}
+
+/// Returns a boxed falcon HAL adequate for `chipset`.
+///
+/// We use a heap-allocated trait object instead of a statically defined one because the
+/// generic `FalconEngine` argument makes it difficult to define all the combinations
+/// statically.
+pub(super) fn falcon_hal<E: FalconEngine + 'static>(
+    chipset: Chipset,
+) -> Result<KBox<dyn FalconHal<E>>> {
+    use Chipset::*;
+
+    let hal = match chipset {
+        GA102 | GA103 | GA104 | GA106 | GA107 => {
+            KBox::new(ga102::Ga102::<E>::new(), GFP_KERNEL)? as KBox<dyn FalconHal<E>>
+        }
+        _ => return Err(ENOTSUPP),
+    };
+
+    Ok(hal)
+}

drivers/gpu/nova-core/falcon/hal.rs

@@ -0,0 +1,119 @@
+// SPDX-License-Identifier: GPL-2.0
+
+use core::marker::PhantomData;
+use core::time::Duration;
+
+use kernel::device;
+use kernel::prelude::*;
+
+use crate::driver::Bar0;
+use crate::falcon::{
+    Falcon, FalconBromParams, FalconEngine, FalconModSelAlgo, PeregrineCoreSelect,
+};
+use crate::regs;
+use crate::util;
+
+use super::FalconHal;
+
+fn select_core_ga102<E: FalconEngine>(bar: &Bar0) -> Result {
+    let bcr_ctrl = regs::NV_PRISCV_RISCV_BCR_CTRL::read(bar, E::BASE);
+    if bcr_ctrl.core_select() != PeregrineCoreSelect::Falcon {
+        regs::NV_PRISCV_RISCV_BCR_CTRL::default()
+            .set_core_select(PeregrineCoreSelect::Falcon)
+            .write(bar, E::BASE);
+
+        // TIMEOUT: falcon core should take less than 10ms to report being enabled.
+        util::wait_on(Duration::from_millis(10), || {
+            let r = regs::NV_PRISCV_RISCV_BCR_CTRL::read(bar, E::BASE);
+            if r.valid() {
+                Some(())
+            } else {
+                None
+            }
+        })?;
+    }
+
+    Ok(())
+}
+
+fn signature_reg_fuse_version_ga102(
+    dev: &device::Device,
+    bar: &Bar0,
+    engine_id_mask: u16,
+    ucode_id: u8,
+) -> Result<u32> {
+    // TODO: The ucode fuse versions are contained in the FUSE_OPT_FPF_<ENGINE>_UCODE<X>_VERSION
+    // registers, which are an array. Our register definition macros do not allow us to manage them
+    // properly, so we need to hardcode their addresses for now. Clean this up once we support
+    // register arrays.
+
+    // Each engine has 16 ucode version registers numbered from 1 to 16.
+    if ucode_id == 0 || ucode_id > 16 {
+        dev_err!(dev, "invalid ucode id {:#x}", ucode_id);
+        return Err(EINVAL);
+    }
+
+    // Base address of the FUSE registers array corresponding to the engine.
+    let reg_fuse_base = if engine_id_mask & 0x0001 != 0 {
+        regs::NV_FUSE_OPT_FPF_SEC2_UCODE1_VERSION::OFFSET
+    } else if engine_id_mask & 0x0004 != 0 {
+        regs::NV_FUSE_OPT_FPF_NVDEC_UCODE1_VERSION::OFFSET
+    } else if engine_id_mask & 0x0400 != 0 {
+        regs::NV_FUSE_OPT_FPF_GSP_UCODE1_VERSION::OFFSET
+    } else {
+        dev_err!(dev, "unexpected engine_id_mask {:#x}", engine_id_mask);
+        return Err(EINVAL);
+    };
+
+    // Read `reg_fuse_base[ucode_id - 1]`.
+    let reg_fuse_version =
+        bar.read32(reg_fuse_base + ((ucode_id - 1) as usize * core::mem::size_of::<u32>()));
+
+    // TODO: replace with `last_set_bit` once it lands.
+    Ok(u32::BITS - reg_fuse_version.leading_zeros())
+}
+
+fn program_brom_ga102<E: FalconEngine>(bar: &Bar0, params: &FalconBromParams) -> Result {
+    regs::NV_PFALCON2_FALCON_BROM_PARAADDR::default()
+        .set_value(params.pkc_data_offset)
+        .write(bar, E::BASE);
+    regs::NV_PFALCON2_FALCON_BROM_ENGIDMASK::default()
+        .set_value(params.engine_id_mask as u32)
+        .write(bar, E::BASE);
+    regs::NV_PFALCON2_FALCON_BROM_CURR_UCODE_ID::default()
+        .set_ucode_id(params.ucode_id)
+        .write(bar, E::BASE);
+    regs::NV_PFALCON2_FALCON_MOD_SEL::default()
+        .set_algo(FalconModSelAlgo::Rsa3k)
+        .write(bar, E::BASE);
+
+    Ok(())
+}
+
+pub(super) struct Ga102<E: FalconEngine>(PhantomData<E>);
+
+impl<E: FalconEngine> Ga102<E> {
+    pub(super) fn new() -> Self {
+        Self(PhantomData)
+    }
+}
+
+impl<E: FalconEngine> FalconHal<E> for Ga102<E> {
+    fn select_core(&self, _falcon: &Falcon<E>, bar: &Bar0) -> Result {
+        select_core_ga102::<E>(bar)
+    }
+
+    fn signature_reg_fuse_version(
+        &self,
+        falcon: &Falcon<E>,
+        bar: &Bar0,
+        engine_id_mask: u16,
+        ucode_id: u8,
+    ) -> Result<u32> {
+        signature_reg_fuse_version_ga102(&falcon.dev, bar, engine_id_mask, ucode_id)
+    }
+
+    fn program_brom(&self, _falcon: &Falcon<E>, bar: &Bar0, params: &FalconBromParams) -> Result {
+        program_brom_ga102::<E>(bar, params)
+    }
+}

drivers/gpu/nova-core/falcon/hal/ga102.rs

@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+
+use crate::falcon::FalconEngine;
+
+/// Type specifying the `Sec2` falcon engine. Cannot be instantiated.
+pub(crate) struct Sec2(());
+
+impl FalconEngine for Sec2 {
+    const BASE: usize = 0x00840000;
+}

drivers/gpu/nova-core/falcon/sec2.rs

@@ -3,6 +3,7 @@
 use kernel::{device, devres::Devres, error::code::*, pci, prelude::*};
 
 use crate::driver::Bar0;
+use crate::falcon::{gsp::Gsp, sec2::Sec2, Falcon};
 use crate::fb::SysmemFlush;
 use crate::firmware::{Firmware, FIRMWARE_VERSION};
 use crate::gfw;
@@ -203,6 +204,16 @@ impl Gpu {
         // System memory page required for sysmembar to properly flush into system memory.
         let sysmem_flush = SysmemFlush::register(pdev.as_ref(), bar, spec.chipset)?;
 
+        let gsp_falcon = Falcon::<Gsp>::new(
+            pdev.as_ref(),
+            spec.chipset,
+            bar,
+            spec.chipset > Chipset::GA100,
+        )?;
+        gsp_falcon.clear_swgen0_intr(bar);
+
+        let _sec2_falcon = Falcon::<Sec2>::new(pdev.as_ref(), spec.chipset, bar, true)?;
+
         Ok(pin_init!(Self {
             spec,
             bar: devres_bar,

drivers/gpu/nova-core/gpu.rs

@@ -4,6 +4,7 @@
 
 mod dma;
 mod driver;
+mod falcon;
 mod fb;
 mod firmware;
 mod gfw;