gpu: nova-core: wait for GFW_BOOT completion

Upon reset, the GPU executes the GFW (GPU Firmware) in order to
initialize its base parameters such as clocks. The driver must ensure
that this step is completed before using the hardware.

Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
Link: https://lore.kernel.org/r/20250619-nova-frts-v6-12-ecf41ef99252@nvidia.com
[ Slightly adjust comments in wait_gfw_boot_completion(). - Danilo ]
Signed-off-by: Danilo Krummrich <dakr@kernel.org>

Author: Gnurou

drivers/gpu/nova-core/gfw.rs

@@ -0,0 +1,41 @@
+// SPDX-License-Identifier: GPL-2.0
+
+//! GPU Firmware (GFW) support.
+//!
+//! Upon reset, the GPU runs some firmware code from the BIOS to setup its core parameters. Most of
+//! the GPU is considered unusable until this step is completed, so we must wait on it before
+//! performing driver initialization.
+
+use core::time::Duration;
+
+use kernel::bindings;
+use kernel::prelude::*;
+
+use crate::driver::Bar0;
+use crate::regs;
+use crate::util;
+
+/// Wait until `GFW` (GPU Firmware) completes, or a 4 seconds timeout elapses.
+pub(crate) fn wait_gfw_boot_completion(bar: &Bar0) -> Result {
+    // TIMEOUT: arbitrarily large value. GFW starts running immediately after the GPU is put out of
+    // reset, and should complete in less time than that.
+    util::wait_on(Duration::from_secs(4), || {
+        // Check that FWSEC has lowered its protection level before reading the GFW_BOOT
+        // status.
+        let gfw_booted = regs::NV_PGC6_AON_SECURE_SCRATCH_GROUP_05_PRIV_LEVEL_MASK::read(bar)
+            .read_protection_level0()
+            && regs::NV_PGC6_AON_SECURE_SCRATCH_GROUP_05_0_GFW_BOOT::read(bar).completed();
+
+        if gfw_booted {
+            Some(())
+        } else {
+            // TODO: replace with [1] once merged.
+            // [1] https://lore.kernel.org/rust-for-linux/20250423192857.199712-6-fujita.tomonori@gmail.com/
+            //
+            // SAFETY: `msleep()` is safe to call with any parameter.
+            unsafe { bindings::msleep(1) };
+
+            None
+        }
+    })
+}

drivers/gpu/nova-core/gpu.rs

@@ -4,6 +4,7 @@ use kernel::{device, devres::Devres, error::code::*, pci, prelude::*};
 
 use crate::driver::Bar0;
 use crate::firmware::{Firmware, FIRMWARE_VERSION};
+use crate::gfw;
 use crate::regs;
 use crate::util;
 use core::fmt;
@@ -182,6 +183,10 @@ impl Gpu {
             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"))?;
+
         Ok(pin_init!(Self {
             spec,
             bar: devres_bar,

drivers/gpu/nova-core/nova_core.rs

@@ -4,6 +4,7 @@
 
 mod driver;
 mod firmware;
+mod gfw;
 mod gpu;
 mod regs;
 mod util;

drivers/gpu/nova-core/regs.rs

@@ -37,3 +37,28 @@ impl NV_PMC_BOOT_0 {
             .and_then(Chipset::try_from)
     }
 }
+
+/* PGC6 */
+
+register!(NV_PGC6_AON_SECURE_SCRATCH_GROUP_05_PRIV_LEVEL_MASK @ 0x00118128 {
+    0:0     read_protection_level0 as bool, "Set after FWSEC lowers its protection level";
+});
+
+// TODO: This is an array of registers.
+register!(NV_PGC6_AON_SECURE_SCRATCH_GROUP_05 @ 0x00118234 {
+    31:0    value as u32;
+});
+
+register!(
+    NV_PGC6_AON_SECURE_SCRATCH_GROUP_05_0_GFW_BOOT => NV_PGC6_AON_SECURE_SCRATCH_GROUP_05,
+    "Scratch group 05 register 0 used as GFW boot progress indicator" {
+        7:0    progress as u8, "Progress of GFW boot (0xff means completed)";
+    }
+);
+
+impl NV_PGC6_AON_SECURE_SCRATCH_GROUP_05_0_GFW_BOOT {
+    /// Returns `true` if GFW boot is completed.
+    pub(crate) fn completed(self) -> bool {
+        self.progress() == 0xff
+    }
+}

drivers/gpu/nova-core/util.rs

@@ -34,7 +34,6 @@ pub(crate) const fn const_bytes_to_str(bytes: &[u8]) -> &str {
 ///
 /// TODO: replace with `read_poll_timeout` once it is available.
 /// (https://lore.kernel.org/lkml/20250220070611.214262-8-fujita.tomonori@gmail.com/)
-#[expect(dead_code)]
 pub(crate) fn wait_on<R, F: Fn() -> Option<R>>(timeout: Duration, cond: F) -> Result<R> {
     let start_time = Instant::now();