All of lore.kernel.org
 help / color / mirror / Atom feed
From: John Hubbard <jhubbard@nvidia.com>
To: Danilo Krummrich <dakr@kernel.org>,
	Alexandre Courbot <acourbot@nvidia.com>
Cc: "Timur Tabi" <ttabi@nvidia.com>,
	"Alistair Popple" <apopple@nvidia.com>,
	"Eliot Courtney" <ecourtney@nvidia.com>,
	"Zhi Wang" <zhiw@nvidia.com>, "David Airlie" <airlied@gmail.com>,
	"Simona Vetter" <simona@ffwll.ch>,
	"Bjorn Helgaas" <bhelgaas@google.com>,
	"Miguel Ojeda" <ojeda@kernel.org>,
	"Alex Gaynor" <alex.gaynor@gmail.com>,
	"Boqun Feng" <boqun.feng@gmail.com>,
	"Gary Guo" <gary@garyguo.net>,
	"Björn Roy Baron" <bjorn3_gh@protonmail.com>,
	"Benno Lossin" <lossin@kernel.org>,
	"Andreas Hindborg" <a.hindborg@kernel.org>,
	"Alice Ryhl" <aliceryhl@google.com>,
	"Trevor Gross" <tmgross@umich.edu>,
	nova-gpu@lists.linux.dev, LKML <linux-kernel@vger.kernel.org>,
	"John Hubbard" <jhubbard@nvidia.com>
Subject: [PATCH v5 07/15] gpu: nova-core: wait for GFW boot in probe, not in the Gpu constructor
Date: Tue, 29 Sep 2026 20:41:40 -0700	[thread overview]
Message-ID: <20260930034148.590687-8-jhubbard@nvidia.com> (raw)
In-Reply-To: <20260930034148.590687-1-jhubbard@nvidia.com>

The GPU boots its own firmware, GFW, out of reset, and the driver must
not program the GPU until GFW reports completion.

nova-core waited for GFW inside the Gpu constructor, which also boots
the GSP. Code that has to run after GFW and before GSP boot, such as a
probe-time hardware self-test, had nowhere to go.

Move the wait into probe, ahead of the Gpu constructor, and read the
chipset there from a Spec that probe builds itself. Leave the DMA mask
in the constructor, since it programs the host rather than the GPU.

Assisted-by: LLM
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
---
 drivers/gpu/nova-core/driver.rs | 14 +++++++++++++-
 drivers/gpu/nova-core/gpu.rs    | 26 +++++++++++++++++++-------
 2 files changed, 32 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/nova-core/driver.rs b/drivers/gpu/nova-core/driver.rs
index 291a047e4d86..fc321c6a10b0 100644
--- a/drivers/gpu/nova-core/driver.rs
+++ b/drivers/gpu/nova-core/driver.rs
@@ -24,7 +24,11 @@
 
 use crate::{
     api::NovaCoreApi,
-    gpu::Gpu, //
+    gpu::{
+        self,
+        Gpu,
+        Spec, //
+    }, //
 };
 
 /// Counter for generating unique auxiliary device IDs.
@@ -113,6 +117,14 @@ fn probe<'bound>(
                 pdev.iomap_region(bar1_idx, c"nova-core/bar1")?
             },
 
+            _: {
+                let spec = Spec::new(pdev.as_ref(), bar)?;
+
+                // We must wait for GFW_BOOT completion before doing any significant setup on
+                // the GPU.
+                gpu::wait_gfw_boot_completion(pdev.as_ref(), bar, spec.chipset)?;
+            },
+
             // TODO: Use self-referential pin-init syntax once available.
             gpu <- Gpu::new(
                 pdev,
diff --git a/drivers/gpu/nova-core/gpu.rs b/drivers/gpu/nova-core/gpu.rs
index fb6f8a86a503..65715f906030 100644
--- a/drivers/gpu/nova-core/gpu.rs
+++ b/drivers/gpu/nova-core/gpu.rs
@@ -251,7 +251,7 @@ pub struct Spec {
 }
 
 impl Spec {
-    fn new(dev: &device::Device, bar: Bar0<'_>) -> Result<Spec> {
+    pub(crate) fn new(dev: &device::Device, bar: Bar0<'_>) -> Result<Spec> {
         // Some brief notes about boot0 and boot42, in chronological order:
         //
         // NV04 through NV50:
@@ -397,10 +397,8 @@ pub(crate) fn new<'a>(
                 dev_info!(dev,"NVIDIA ({})\n", spec);
             })?,
 
-            // We must wait for GFW_BOOT completion before doing any significant setup on the GPU.
             _: {
-                let hal = hal::gpu_hal(spec.chipset);
-                let dma_mask = hal.dma_mask();
+                let dma_mask = hal::gpu_hal(spec.chipset).dma_mask();
 
                 // SAFETY: `Gpu` owns all DMA allocations for this device, and we are
                 // still constructing it, so no concurrent DMA allocations can exist.
@@ -412,9 +410,6 @@ pub(crate) fn new<'a>(
                 // SAFETY: `Gpu` owns all DMA allocations for this device, and we are
                 // still constructing it, so no concurrent DMA allocations can exist.
                 unsafe { pdev.dma_set_max_seg_size(u32::MAX) };
-
-                hal.wait_gfw_boot_completion(bar)
-                    .inspect_err(|_| dev_err!(dev, "GFW boot did not complete\n"))?;
             },
 
             // Initialize this early because `gsp_resources` depends on it.
@@ -533,6 +528,23 @@ pub(crate) fn run_selftests(self: Pin<&mut Self>, pdev: &pci::Device<device::Bou
     }
 }
 
+/// Waits for GFW, the GPU's boot firmware, to report completion.
+///
+/// The driver must not program the GPU before then.
+///
+/// # Errors
+///
+/// `ETIMEDOUT` if GFW does not report completion in time.
+pub(crate) fn wait_gfw_boot_completion(
+    dev: &device::Device<device::Bound>,
+    bar: Bar0<'_>,
+    chipset: Chipset,
+) -> Result {
+    hal::gpu_hal(chipset)
+        .wait_gfw_boot_completion(bar)
+        .inspect_err(|_| dev_err!(dev, "GFW boot did not complete\n"))
+}
+
 /// Reads the boot0 register and returns its raw value.
 pub(crate) fn boot_0_raw(bar: Bar0<'_>) -> u32 {
     bar.read(regs::NV_PMC_BOOT_0).into_raw()
-- 
2.55.0


  parent reply	other threads:[~2026-09-30  3:43 UTC|newest]

Thread overview: 33+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-09-30  3:41 [PATCH v5 00/15] nova-core: GPU interrupt support and GSP event delivery John Hubbard
2026-09-30  3:41 ` [PATCH v5 01/15] rust: pci: declare IrqType and IrqTypes with impl_flags John Hubbard
2026-10-01 14:06   ` Alexandre Courbot
2026-09-30  3:41 ` [PATCH v5 02/15] rust: sync: completion: add wait_for_completion_timeout() John Hubbard
2026-09-30  3:59   ` sashiko-bot
2026-10-01 14:06   ` Alexandre Courbot
2026-10-02  8:21   ` Alice Ryhl
2026-10-02  9:11     ` John Hubbard
2026-10-02  9:50   ` Gary Guo
2026-10-02 10:55     ` Alexandre Courbot
2026-10-02 11:13       ` John Hubbard
2026-10-02 12:12         ` Alexandre Courbot
2026-10-02 13:01           ` Gary Guo
2026-10-02 12:20       ` Danilo Krummrich
2026-09-30  3:41 ` [PATCH v5 03/15] gpu: nova-core: add the GIN vector, leaf and subtree types John Hubbard
2026-09-30  3:41 ` [PATCH v5 04/15] gpu: nova-core: add the GIN CPU interrupt tree and MSI EOI registers John Hubbard
2026-09-30  3:41 ` [PATCH v5 05/15] gpu: nova-core: add the per-architecture GIN CPU interrupt HAL John Hubbard
2026-09-30  3:41 ` [PATCH v5 06/15] gpu: nova-core: add the GIN interrupt tree and allocate its vectors John Hubbard
2026-09-30  3:41 ` John Hubbard [this message]
2026-09-30 12:51   ` [PATCH v5 07/15] gpu: nova-core: wait for GFW boot in probe, not in the Gpu constructor Danilo Krummrich
2026-10-01 14:07     ` Alexandre Courbot
2026-09-30  3:41 ` [PATCH v5 08/15] gpu: nova-core: add an interrupt delivery self-test John Hubbard
2026-09-30  3:41 ` [PATCH v5 09/15] gpu: nova-core: log GSP events instead of discarding them John Hubbard
2026-09-30  3:41 ` [PATCH v5 10/15] gpu: nova-core: return ENOMSG for an unmatched GSP message John Hubbard
2026-09-30  3:41 ` [PATCH v5 11/15] gpu: nova-core: bound a GSP wait by a single deadline John Hubbard
2026-09-30  3:41 ` [PATCH v5 12/15] gpu: nova-core: add the falcon interrupt registers and HAL methods John Hubbard
2026-09-30  3:41 ` [PATCH v5 13/15] gpu: nova-core: service GSP events from the SWGEN0 interrupt John Hubbard
2026-09-30  3:41 ` [PATCH v5 14/15] gpu: nova-core: add KUnit tests for the interrupt tree John Hubbard
2026-09-30  3:41 ` [PATCH v5 15/15] gpu: nova-core: document the GIN interrupt controller and GSP events John Hubbard
2026-10-02 13:33   ` Alexandre Courbot
2026-10-01 14:09 ` [PATCH v5 00/15] nova-core: GPU interrupt support and GSP event delivery Danilo Krummrich
2026-10-01 14:10 ` Alexandre Courbot
2026-10-02 13:19 ` 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=20260930034148.590687-8-jhubbard@nvidia.com \
    --to=jhubbard@nvidia.com \
    --cc=a.hindborg@kernel.org \
    --cc=acourbot@nvidia.com \
    --cc=airlied@gmail.com \
    --cc=alex.gaynor@gmail.com \
    --cc=aliceryhl@google.com \
    --cc=apopple@nvidia.com \
    --cc=bhelgaas@google.com \
    --cc=bjorn3_gh@protonmail.com \
    --cc=boqun.feng@gmail.com \
    --cc=dakr@kernel.org \
    --cc=ecourtney@nvidia.com \
    --cc=gary@garyguo.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lossin@kernel.org \
    --cc=nova-gpu@lists.linux.dev \
    --cc=ojeda@kernel.org \
    --cc=simona@ffwll.ch \
    --cc=tmgross@umich.edu \
    --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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.