gpu: nova-core: move GSP boot code to its own module

Right now the GSP boot code is very incomplete and limited to running
FRTS, so having it in `Gpu::new` is not a big constraint.

However, this will change as we add more steps of the GSP boot process,
and not all GPU families follow the same procedure, so having these
steps in a dedicated method is the logical construct.

There is also the fact the GSP will require its own runtime data, and
while it won't immediately need to be pinned, we want to be ready for
the time where it will - most likely when it starts using mutexes.

Thus, add an empty `Gsp` type that is pinned inside `Gpu` and
initialized using a pin initializer. This sets the constraint we need to
observe from the start, and could spare us some costly refactoring down
the road.

Then, move the code related to GSP boot to the `gsp::boot` module, as
part of the `Gsp` implementation.

Doing so allows us to make `Gpu::new` return a fallible `impl PinInit`
instead of a `Result.` This is more idiomatic when working with pinned
objects, and sets up the pinned initialization pattern we want to
preserve as the code grows more complex.

Acked-by: Danilo Krummrich <dakr@kernel.org>
Link: https://lore.kernel.org/r/20250913-nova_firmware-v6-2-9007079548b0@nvidia.com
Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>

1 files changed, 41 insertions, 118 deletions

diff --git a/drivers/gpu/nova-core/gpu.rs b/drivers/gpu/nova-core/gpu.rs
index a0878ecdc18b..3c019df01d30 100644
--- a/drivers/gpu/nova-core/gpu.rs
+++ b/drivers/gpu/nova-core/gpu.rs
@@ -3,15 +3,13 @@
 use kernel::{device, devres::Devres, error::code::*, pci, prelude::*, sync::Arc};
 
 use crate::driver::Bar0;
-use crate::falcon::{gsp::Gsp, sec2::Sec2, Falcon};
-use crate::fb::FbLayout;
+use crate::falcon::{gsp::Gsp as GspFalcon, sec2::Sec2 as Sec2Falcon, Falcon};
 use crate::fb::SysmemFlush;
-use crate::firmware::fwsec::{FwsecCommand, FwsecFirmware};
 use crate::firmware::{Firmware, FIRMWARE_VERSION};
 use crate::gfw;
+use crate::gsp::Gsp;
 use crate::regs;
 use crate::util;
-use crate::vbios::Vbios;
 use core::fmt;
 
 macro_rules! define_chipset {
@@ -172,133 +170,58 @@ pub(crate) struct Gpu {
     /// System memory page required for flushing all pending GPU-side memory writes done through
     /// PCIE into system memory, via sysmembar (A GPU-initiated HW memory-barrier operation).
     sysmem_flush: SysmemFlush,
+    /// GSP falcon instance, used for GSP boot up and cleanup.
+    gsp_falcon: Falcon<GspFalcon>,
+    /// SEC2 falcon instance, used for GSP boot up and cleanup.
+    sec2_falcon: Falcon<Sec2Falcon>,
+    /// GSP runtime data. Temporarily an empty placeholder.
+    #[pin]
+    gsp: Gsp,
 }
 
 impl Gpu {
-    /// Helper function to load and run the FWSEC-FRTS firmware and confirm that it has properly
-    /// created the WPR2 region.
-    ///
-    /// TODO: this needs to be moved into a larger type responsible for booting the whole GSP
-    /// (`GspBooter`?).
-    fn run_fwsec_frts(
-        dev: &device::Device<device::Bound>,
-        falcon: &Falcon<Gsp>,
-        bar: &Bar0,
-        bios: &Vbios,
-        fb_layout: &FbLayout,
-    ) -> Result<()> {
-        // Check that the WPR2 region does not already exists - if it does, we cannot run
-        // FWSEC-FRTS until the GPU is reset.
-        if regs::NV_PFB_PRI_MMU_WPR2_ADDR_HI::read(bar).higher_bound() != 0 {
-            dev_err!(
-                dev,
-                "WPR2 region already exists - GPU needs to be reset to proceed\n"
-            );
-            return Err(EBUSY);
-        }
-
-        let fwsec_frts = FwsecFirmware::new(
-            dev,
-            falcon,
-            bar,
-            bios,
-            FwsecCommand::Frts {
-                frts_addr: fb_layout.frts.start,
-                frts_size: fb_layout.frts.end - fb_layout.frts.start,
-            },
-        )?;
-
-        // Run FWSEC-FRTS to create the WPR2 region.
-        fwsec_frts.run(dev, falcon, bar)?;
-
-        // SCRATCH_E contains the error code for FWSEC-FRTS.
-        let frts_status = regs::NV_PBUS_SW_SCRATCH_0E_FRTS_ERR::read(bar).frts_err_code();
-        if frts_status != 0 {
-            dev_err!(
-                dev,
-                "FWSEC-FRTS returned with error code {:#x}",
-                frts_status
-            );
-
-            return Err(EIO);
-        }
-
-        // Check that the WPR2 region has been created as we requested.
-        let (wpr2_lo, wpr2_hi) = (
-            regs::NV_PFB_PRI_MMU_WPR2_ADDR_LO::read(bar).lower_bound(),
-            regs::NV_PFB_PRI_MMU_WPR2_ADDR_HI::read(bar).higher_bound(),
-        );
-
-        match (wpr2_lo, wpr2_hi) {
-            (_, 0) => {
-                dev_err!(dev, "WPR2 region not created after running FWSEC-FRTS\n");
-
-                Err(EIO)
-            }
-            (wpr2_lo, _) if wpr2_lo != fb_layout.frts.start => {
-                dev_err!(
-                    dev,
-                    "WPR2 region created at unexpected address {:#x}; expected {:#x}\n",
-                    wpr2_lo,
-                    fb_layout.frts.start,
-                );
-
-                Err(EIO)
-            }
-            (wpr2_lo, wpr2_hi) => {
-                dev_dbg!(dev, "WPR2: {:#x}-{:#x}\n", wpr2_lo, wpr2_hi);
-                dev_dbg!(dev, "GPU instance built\n");
-
-                Ok(())
-            }
-        }
-    }
-
-    pub(crate) fn new(
-        pdev: &pci::Device<device::Bound>,
+    pub(crate) fn new<'a>(
+        pdev: &'a pci::Device<device::Bound>,
         devres_bar: Arc<Devres<Bar0>>,
-    ) -> Result<impl PinInit<Self>> {
-        let bar = devres_bar.access(pdev.as_ref())?;
-        let spec = Spec::new(bar)?;
-        let fw = Firmware::new(pdev.as_ref(), spec.chipset, FIRMWARE_VERSION)?;
-
-        dev_info!(
-            pdev.as_ref(),
-            "NVIDIA (Chipset: {}, Architecture: {:?}, Revision: {})\n",
-            spec.chipset,
-            spec.chipset.arch(),
-            spec.revision
-        );
+        bar: &'a Bar0,
+    ) -> impl PinInit<Self, Error> + 'a {
+        try_pin_init!(Self {
+            spec: Spec::new(bar).inspect(|spec| {
+                dev_info!(
+                    pdev.as_ref(),
+                    "NVIDIA (Chipset: {}, Architecture: {:?}, Revision: {})\n",
+                    spec.chipset,
+                    spec.chipset.arch(),
+                    spec.revision
+                );
+            })?,
 
-        // 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.as_ref(), "GFW boot did not complete"))?;
+            // 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.as_ref(), "GFW boot did not complete"))?;
+            },
 
-        let sysmem_flush = SysmemFlush::register(pdev.as_ref(), bar, spec.chipset)?;
+            fw <- Firmware::new(pdev.as_ref(), spec.chipset, FIRMWARE_VERSION)?,
 
-        let gsp_falcon = Falcon::<Gsp>::new(
-            pdev.as_ref(),
-            spec.chipset,
-            bar,
-            spec.chipset > Chipset::GA100,
-        )?;
-        gsp_falcon.clear_swgen0_intr(bar);
+            sysmem_flush: SysmemFlush::register(pdev.as_ref(), bar, spec.chipset)?,
 
-        let _sec2_falcon = Falcon::<Sec2>::new(pdev.as_ref(), spec.chipset, bar, true)?;
+            gsp_falcon: Falcon::new(
+                pdev.as_ref(),
+                spec.chipset,
+                bar,
+                spec.chipset > Chipset::GA100,
+            )
+            .inspect(|falcon| falcon.clear_swgen0_intr(bar))?,
 
-        let fb_layout = FbLayout::new(spec.chipset, bar)?;
-        dev_dbg!(pdev.as_ref(), "{:#x?}\n", fb_layout);
+            sec2_falcon: Falcon::new(pdev.as_ref(), spec.chipset, bar, true)?,
 
-        let bios = Vbios::new(pdev.as_ref(), bar)?;
+            gsp <- Gsp::new(),
 
-        Self::run_fwsec_frts(pdev.as_ref(), &gsp_falcon, bar, &bios, &fb_layout)?;
+            _: { gsp.boot(pdev, bar, spec.chipset, gsp_falcon, sec2_falcon)? },
 
-        Ok(pin_init!(Self {
-            spec,
             bar: devres_bar,
-            fw,
-            sysmem_flush,
-        }))
+        })
     }
 
     /// Called when the corresponding [`Device`](device::Device) is unbound.