NVIDIA GPU driver infrastructure
 help / color / mirror / Atom feed
From: Alexandre Courbot <acourbot@nvidia.com>
To: Danilo Krummrich <dakr@kernel.org>,
	Alice Ryhl <aliceryhl@google.com>,
	 David Airlie <airlied@gmail.com>,
	Simona Vetter <simona@ffwll.ch>,  Gary Guo <gary@garyguo.net>
Cc: John Hubbard <jhubbard@nvidia.com>,
	 Alistair Popple <apopple@nvidia.com>,
	Timur Tabi <ttabi@nvidia.com>,
	 Eliot Courtney <ecourtney@nvidia.com>,
	Zhi Wang <zhiw@nvidia.com>,
	 nova-gpu@lists.linux.dev, dri-devel@lists.freedesktop.org,
	 linux-kernel@vger.kernel.org, rust-for-linux@vger.kernel.org,
	 Alexandre Courbot <acourbot@nvidia.com>
Subject: [PATCH 3/6] gpu: nova-core: gsp: move boot code into local closure
Date: Fri, 19 Jun 2026 22:42:18 +0900	[thread overview]
Message-ID: <20260619-nova-bootcontext-v1-3-45193cd0a2e5@nvidia.com> (raw)
In-Reply-To: <20260619-nova-bootcontext-v1-0-45193cd0a2e5@nvidia.com>

The next patch aims at replacing the cumbersome `BootUnloadGuard` with a
more local and less intrusive mechanism to run the GSP unload sequence
upon GSP boot failure. Doing so requires running the boot code in a
local closure, which changes its indentation and would make other
changes difficult to track in the diff. Thus, this preparatory patch
moves said boot code into a local closure that is run upon construction,
so the next patch does not need to re-indent code that changes.

This is a mechanical preparatory patch to make the next patch easier to
read. No functional change intended.

Signed-off-by: Alexandre Courbot <acourbot@nvidia.com>
---
 drivers/gpu/nova-core/gsp/boot.rs      | 42 ++++++++-------
 drivers/gpu/nova-core/gsp/hal/gh100.rs | 40 +++++++-------
 drivers/gpu/nova-core/gsp/hal/tu102.rs | 96 ++++++++++++++++++----------------
 3 files changed, 96 insertions(+), 82 deletions(-)

diff --git a/drivers/gpu/nova-core/gsp/boot.rs b/drivers/gpu/nova-core/gsp/boot.rs
index bb2000b7a78b..9eccfd634b61 100644
--- a/drivers/gpu/nova-core/gsp/boot.rs
+++ b/drivers/gpu/nova-core/gsp/boot.rs
@@ -119,30 +119,36 @@ pub(crate) fn boot(
 
         // Perform the chipset-specific boot sequence, and retrieve the unload bundle.
         let unload_guard = hal.boot(&self, &ctx, &fb_layout, &wpr_meta)?;
+        // Run from a closure so we can retrieve the result, and run the unload sequence of the GSP
+        // in case of error.
+        let res = (|| {
+            gsp_falcon.write_os_version(bar, gsp_fw.bootloader.app_version);
 
-        gsp_falcon.write_os_version(bar, gsp_fw.bootloader.app_version);
+            // Poll for RISC-V to become active before continuing.
+            read_poll_timeout(
+                || Ok(gsp_falcon.is_riscv_active(bar)),
+                |val: &bool| *val,
+                Delta::from_millis(10),
+                Delta::from_secs(5),
+            )?;
 
-        // Poll for RISC-V to become active before continuing.
-        read_poll_timeout(
-            || Ok(gsp_falcon.is_riscv_active(bar)),
-            |val: &bool| *val,
-            Delta::from_millis(10),
-            Delta::from_secs(5),
-        )?;
+            dev_dbg!(pdev, "RISC-V active? {}\n", gsp_falcon.is_riscv_active(bar),);
 
-        dev_dbg!(pdev, "RISC-V active? {}\n", gsp_falcon.is_riscv_active(bar),);
+            self.cmdq
+                .send_command_no_wait(bar, commands::SetSystemInfo::new(pdev, chipset))?;
+            self.cmdq
+                .send_command_no_wait(bar, commands::SetRegistry::new())?;
 
-        self.cmdq
-            .send_command_no_wait(bar, commands::SetSystemInfo::new(pdev, chipset))?;
-        self.cmdq
-            .send_command_no_wait(bar, commands::SetRegistry::new())?;
+            hal.post_boot(&self, &ctx, &gsp_fw)?;
 
-        hal.post_boot(&self, &ctx, &gsp_fw)?;
+            // Wait until GSP is fully initialized.
+            commands::wait_gsp_init_done(&self.cmdq)
+        })();
 
-        // Wait until GSP is fully initialized.
-        commands::wait_gsp_init_done(&self.cmdq)?;
-
-        Ok(unload_guard.dismiss())
+        match res {
+            Err(e) => Err(e),
+            Ok(()) => Ok(unload_guard.dismiss()),
+        }
     }
 
     /// Shut down the GSP and wait until it is offline.
diff --git a/drivers/gpu/nova-core/gsp/hal/gh100.rs b/drivers/gpu/nova-core/gsp/hal/gh100.rs
index c9fdc8cacedc..46e03f34bc74 100644
--- a/drivers/gpu/nova-core/gsp/hal/gh100.rs
+++ b/drivers/gpu/nova-core/gsp/hal/gh100.rs
@@ -162,31 +162,35 @@ fn boot<'a>(
         let gsp_falcon = ctx.gsp_falcon;
         let sec2_falcon = ctx.sec2_falcon;
 
-        let fsp_fw = FspFirmware::new(dev, chipset, FIRMWARE_VERSION)?;
+        let res = (|| {
+            let fsp_fw = FspFirmware::new(dev, chipset, FIRMWARE_VERSION)?;
 
-        let unload_bundle = crate::gsp::UnloadBundle(
-            KBox::new(FspUnloadBundle, GFP_KERNEL)? as KBox<dyn UnloadBundle>
-        );
+            let unload_bundle = crate::gsp::UnloadBundle(
+                KBox::new(FspUnloadBundle, GFP_KERNEL)? as KBox<dyn UnloadBundle>
+            );
 
-        // Wrap the unload bundle into a drop guard so it is automatically run upon failure.
-        let unload_guard =
-            BootUnloadGuard::new(gsp, dev, bar, gsp_falcon, sec2_falcon, Some(unload_bundle));
+            // Wrap the unload bundle into a drop guard so it is automatically run upon failure.
+            let unload_guard =
+                BootUnloadGuard::new(gsp, dev, bar, gsp_falcon, sec2_falcon, Some(unload_bundle));
 
-        let mut fsp = Fsp::wait_secure_boot(dev, bar, chipset, fsp_fw)?;
+            let mut fsp = Fsp::wait_secure_boot(dev, bar, chipset, fsp_fw)?;
 
-        let args = FmcBootArgs::new(
-            dev,
-            chipset,
-            wpr_meta.dma_handle(),
-            gsp.libos.dma_handle(),
-            false,
-        )?;
+            let args = FmcBootArgs::new(
+                dev,
+                chipset,
+                wpr_meta.dma_handle(),
+                gsp.libos.dma_handle(),
+                false,
+            )?;
 
-        fsp.boot_fmc(dev, bar, fb_layout, &args)?;
+            fsp.boot_fmc(dev, bar, fb_layout, &args)?;
 
-        wait_for_gsp_lockdown_release(dev, bar, gsp_falcon, args.boot_params_dma_handle())?;
+            wait_for_gsp_lockdown_release(dev, bar, gsp_falcon, args.boot_params_dma_handle())?;
 
-        Ok(unload_guard)
+            Ok(unload_guard)
+        })();
+
+        res
     }
 }
 
diff --git a/drivers/gpu/nova-core/gsp/hal/tu102.rs b/drivers/gpu/nova-core/gsp/hal/tu102.rs
index 6ed4ee268086..9b24361f924b 100644
--- a/drivers/gpu/nova-core/gsp/hal/tu102.rs
+++ b/drivers/gpu/nova-core/gsp/hal/tu102.rs
@@ -277,59 +277,63 @@ fn boot<'a>(
         let gsp_falcon = ctx.gsp_falcon;
         let sec2_falcon = ctx.sec2_falcon;
 
-        let bios = Vbios::new(dev, bar)?;
+        let res = (|| {
+            let bios = Vbios::new(dev, bar)?;
 
-        // Try and prepare the unload bundle.
-        //
-        // If the unload bundle creation fails, the GPU will need to be reset before the driver can
-        // be probed again.
-        let unload_bundle =
-            Sec2UnloadBundle::build(dev, bar, chipset, &bios, gsp_falcon, sec2_falcon)
-                .inspect_err(|e| {
-                    dev_warn!(dev, "Failed to prepare unload firmware: {:?}\n", e);
-                    dev_warn!(dev, "The GSP won't be able to unload properly on unbind.\n");
-                    dev_warn!(
-                        dev,
-                        "The GPU will need to be reset before the driver can bind again.\n"
-                    );
-                })
-                .ok()
-                .map(crate::gsp::UnloadBundle);
+            // Try and prepare the unload bundle.
+            //
+            // If the unload bundle creation fails, the GPU will need to be reset before the driver
+            // can be probed again.
+            let unload_bundle =
+                Sec2UnloadBundle::build(dev, bar, chipset, &bios, gsp_falcon, sec2_falcon)
+                    .inspect_err(|e| {
+                        dev_warn!(dev, "Failed to prepare unload firmware: {:?}\n", e);
+                        dev_warn!(dev, "The GSP won't be able to unload properly on unbind.\n");
+                        dev_warn!(
+                            dev,
+                            "The GPU will need to be reset before the driver can bind again.\n"
+                        );
+                    })
+                    .ok()
+                    .map(crate::gsp::UnloadBundle);
 
-        // Wrap the unload bundle into a drop guard so it is automatically run upon failure.
-        let unload_guard =
-            BootUnloadGuard::new(gsp, dev, bar, gsp_falcon, sec2_falcon, unload_bundle);
+            // Wrap the unload bundle into a drop guard so it is automatically run upon failure.
+            let unload_guard =
+                BootUnloadGuard::new(gsp, dev, bar, gsp_falcon, sec2_falcon, unload_bundle);
 
-        // FWSEC-FRTS is not executed on chips where the FRTS region size is 0 (e.g. GA100).
-        if !fb_layout.frts.is_empty() {
-            run_fwsec_frts(dev, chipset, gsp_falcon, bar, &bios, fb_layout)?;
-        }
+            // FWSEC-FRTS is not executed on chips where the FRTS region size is 0 (e.g. GA100).
+            if !fb_layout.frts.is_empty() {
+                run_fwsec_frts(dev, chipset, gsp_falcon, bar, &bios, fb_layout)?;
+            }
 
-        gsp_falcon.reset(bar)?;
-        let libos_handle = gsp.libos.dma_handle();
-        let (mbox0, mbox1) = gsp_falcon.boot(
-            bar,
-            Some(libos_handle as u32),
-            Some((libos_handle >> 32) as u32),
-        )?;
-        dev_dbg!(dev, "GSP MBOX0: {:#x}, MBOX1: {:#x}\n", mbox0, mbox1);
+            gsp_falcon.reset(bar)?;
+            let libos_handle = gsp.libos.dma_handle();
+            let (mbox0, mbox1) = gsp_falcon.boot(
+                bar,
+                Some(libos_handle as u32),
+                Some((libos_handle >> 32) as u32),
+            )?;
+            dev_dbg!(dev, "GSP MBOX0: {:#x}, MBOX1: {:#x}\n", mbox0, mbox1);
 
-        dev_dbg!(
-            dev,
-            "Using SEC2 to load and run the booter_load firmware...\n"
-        );
+            dev_dbg!(
+                dev,
+                "Using SEC2 to load and run the booter_load firmware...\n"
+            );
 
-        BooterFirmware::new(
-            dev,
-            BooterKind::Loader,
-            chipset,
-            FIRMWARE_VERSION,
-            sec2_falcon,
-            bar,
-        )?
-        .run(dev, bar, sec2_falcon, wpr_meta)?;
+            BooterFirmware::new(
+                dev,
+                BooterKind::Loader,
+                chipset,
+                FIRMWARE_VERSION,
+                sec2_falcon,
+                bar,
+            )?
+            .run(dev, bar, sec2_falcon, wpr_meta)?;
 
-        Ok(unload_guard)
+            Ok(unload_guard)
+        })();
+
+        res
     }
 
     fn post_boot(&self, gsp: &Gsp, ctx: &GspBootContext<'_>, gsp_fw: &GspFirmware) -> Result {

-- 
2.54.0


  parent reply	other threads:[~2026-06-19 13:42 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-06-19 13:42 [PATCH 0/6] gpu: nova-core: consolidate and streamline GSP boot process Alexandre Courbot
2026-06-19 13:42 ` [PATCH 1/6] gpu: nova-core: gsp: sequencer: use GspBootContext Alexandre Courbot
2026-06-19 13:42 ` [PATCH 2/6] gpu: nova-core: gsp: sequencer: do not store sequence into GspSequencer Alexandre Courbot
2026-06-19 13:42 ` Alexandre Courbot [this message]
2026-06-19 13:42 ` [PATCH 4/6] gpu: nova-core: gsp: replace BootUnloadGuard with local handler Alexandre Courbot
2026-06-19 13:42 ` [PATCH 5/6] gpu: nova-core: gsp: move unload bundle error handling to Gsp::boot Alexandre Courbot
2026-06-19 13:42 ` [PATCH 6/6] gpu: nova-core: gsp: make unload take GspBootContext Alexandre Courbot

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20260619-nova-bootcontext-v1-3-45193cd0a2e5@nvidia.com \
    --to=acourbot@nvidia.com \
    --cc=airlied@gmail.com \
    --cc=aliceryhl@google.com \
    --cc=apopple@nvidia.com \
    --cc=dakr@kernel.org \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=ecourtney@nvidia.com \
    --cc=gary@garyguo.net \
    --cc=jhubbard@nvidia.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=nova-gpu@lists.linux.dev \
    --cc=rust-for-linux@vger.kernel.org \
    --cc=simona@ffwll.ch \
    --cc=ttabi@nvidia.com \
    --cc=zhiw@nvidia.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox