public inbox for drm-ai-reviews@public-inbox.freedesktop.org
 help / color / mirror / Atom feed
From: Eliot Courtney <ecourtney@nvidia.com>
To: Danilo Krummrich <dakr@kernel.org>,
	Alice Ryhl <aliceryhl@google.com>,
	Alexandre Courbot <acourbot@nvidia.com>,
	David Airlie <airlied@gmail.com>, Simona Vetter <simona@ffwll.ch>,
	Miguel Ojeda <ojeda@kernel.org>, Boqun Feng <boqun@kernel.org>,
	Gary Guo <gary@garyguo.net>,
	Björn Roy Baron <bjorn3_gh@protonmail.com>,
	Benno Lossin <lossin@kernel.org>,
	Andreas Hindborg <a.hindborg@kernel.org>,
	Trevor Gross <tmgross@umich.edu>
Cc: nouveau@lists.freedesktop.org, dri-devel@lists.freedesktop.org,
	linux-kernel@vger.kernel.org, rust-for-linux@vger.kernel.org,
	Eliot Courtney <ecourtney@nvidia.com>, Zhi Wang <zhiw@nvidia.com>
Subject: [PATCH v3 8/9] gpu: nova-core: gsp: support large RPCs via continuation record
Date: Thu, 26 Feb 2026 20:45:40 +0900	[thread overview]
Message-ID: <20260226-cmdq-continuation-v3-8-572ab9916766@nvidia.com> (raw)
In-Reply-To: <20260226-cmdq-continuation-v3-0-572ab9916766@nvidia.com>

Splits large RPCs if necessary and sends the remaining parts using
continuation records. RPCs that do not need continuation records
continue to write directly into the command buffer. Ones that do write
into a staging buffer first, so there is one copy.

Continuation record for receive is not necessary to support at the
moment because those replies do not need to be read and are currently
drained by retrying `receive_msg` on ERANGE.

Tested-by: Zhi Wang <zhiw@nvidia.com>
Signed-off-by: Eliot Courtney <ecourtney@nvidia.com>
---
 drivers/gpu/nova-core/gsp/cmdq.rs     |  43 +++++++++-
 drivers/gpu/nova-core/gsp/commands.rs | 144 +++++++++++++++++++++++++++++++++-
 drivers/gpu/nova-core/gsp/fw.rs       |   4 +
 3 files changed, 187 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs
index 4a663a5b3437..d68b93ddf7cc 100644
--- a/drivers/gpu/nova-core/gsp/cmdq.rs
+++ b/drivers/gpu/nova-core/gsp/cmdq.rs
@@ -28,6 +28,10 @@
 use crate::{
     driver::Bar0,
     gsp::{
+        commands::{
+            ContinuationRecord,
+            SplitState, //
+        },
         fw::{
             GspMsgElement,
             MsgFunction,
@@ -452,7 +456,7 @@ struct GspMessage<'a> {
 
 /// Computes the total size of the command (including its variable-length payload) without the
 /// [`GspMsgElement`] header.
-fn command_size<M>(command: &M) -> usize
+pub(crate) fn command_size<M>(command: &M) -> usize
 where
     M: CommandToGsp,
 {
@@ -520,7 +524,7 @@ fn notify_gsp(bar: &Bar0) {
             .write(bar);
     }
 
-    /// Sends `command` to the GSP.
+    /// Sends `command` to the GSP, without splitting it.
     ///
     /// # Errors
     ///
@@ -529,7 +533,7 @@ fn notify_gsp(bar: &Bar0) {
     ///   written to by its [`CommandToGsp::init_variable_payload`] method.
     ///
     /// Error codes returned by the command initializers are propagated as-is.
-    pub(crate) fn send_command<M>(&mut self, bar: &Bar0, command: M) -> Result
+    fn send_single_command<M>(&mut self, bar: &Bar0, command: M) -> Result
     where
         M: CommandToGsp,
         // This allows all error types, including `Infallible`, to be used for `M::InitError`.
@@ -588,6 +592,39 @@ pub(crate) fn send_command<M>(&mut self, bar: &Bar0, command: M) -> Result
         Ok(())
     }
 
+    /// Sends `command` to the GSP.
+    ///
+    /// The command may be split into multiple messages if it is large.
+    ///
+    /// # Errors
+    ///
+    /// - `ETIMEDOUT` if space does not become available within the timeout.
+    /// - `EIO` if the variable payload requested by the command has not been entirely
+    ///   written to by its [`CommandToGsp::init_variable_payload`] method.
+    ///
+    /// Error codes returned by the command initializers are propagated as-is.
+    pub(crate) fn send_command<M>(&mut self, bar: &Bar0, command: M) -> Result
+    where
+        M: CommandToGsp,
+        Error: From<M::InitError>,
+    {
+        let mut state = SplitState::new(&command)?;
+
+        self.send_single_command(bar, state.command(command))?;
+
+        while let Some(continuation) = state.next_continuation_record() {
+            dev_dbg!(
+                &self.dev,
+                "GSP RPC: send continuation: size=0x{:x}\n",
+                command_size(&continuation),
+            );
+            // Turbofish needed because the compiler cannot infer M here.
+            self.send_single_command::<ContinuationRecord<'_>>(bar, continuation)?;
+        }
+
+        Ok(())
+    }
+
     /// Wait for a message to become available on the message queue.
     ///
     /// This works purely at the transport layer and does not interpret or validate the message
diff --git a/drivers/gpu/nova-core/gsp/commands.rs b/drivers/gpu/nova-core/gsp/commands.rs
index 8f270eca33be..6ffd0b9cbf05 100644
--- a/drivers/gpu/nova-core/gsp/commands.rs
+++ b/drivers/gpu/nova-core/gsp/commands.rs
@@ -4,6 +4,7 @@
     array,
     convert::Infallible,
     ffi::FromBytesUntilNulError,
+    marker::PhantomData,
     str::Utf8Error, //
 };
 
@@ -22,13 +23,16 @@
     driver::Bar0,
     gsp::{
         cmdq::{
+            command_size,
             Cmdq,
             CommandToGsp,
             MessageFromGsp, //
         },
         fw::{
             commands::*,
-            MsgFunction, //
+            GspMsgElement,
+            MsgFunction,
+            GSP_MSG_QUEUE_ELEMENT_SIZE_MAX, //
         },
     },
     sbuffer::SBufferIter,
@@ -242,3 +246,141 @@ pub(crate) fn get_gsp_info(cmdq: &mut Cmdq, bar: &Bar0) -> Result<GetGspStaticIn
         }
     }
 }
+
+/// The `ContinuationRecord` command.
+pub(crate) struct ContinuationRecord<'a> {
+    data: &'a [u8],
+}
+
+impl<'a> ContinuationRecord<'a> {
+    /// Creates a new `ContinuationRecord` command with the given data.
+    pub(crate) fn new(data: &'a [u8]) -> Self {
+        Self { data }
+    }
+}
+
+impl<'a> CommandToGsp for ContinuationRecord<'a> {
+    const FUNCTION: MsgFunction = MsgFunction::ContinuationRecord;
+    type Command = ();
+    type InitError = Infallible;
+
+    fn init(&self) -> impl Init<Self::Command, Self::InitError> {
+        <()>::init_zeroed()
+    }
+
+    fn variable_payload_len(&self) -> usize {
+        self.data.len()
+    }
+
+    fn init_variable_payload(
+        &self,
+        dst: &mut SBufferIter<core::array::IntoIter<&mut [u8], 2>>,
+    ) -> Result {
+        dst.write_all(self.data)
+    }
+}
+
+/// Wrapper that splits a command across continuation records if needed.
+pub(crate) struct SplitState<C: CommandToGsp> {
+    state: Option<(KVVec<u8>, usize)>,
+    _phantom: PhantomData<C>,
+}
+
+impl<C: CommandToGsp> SplitState<C> {
+    /// Maximum command size that fits in a single queue element.
+    const MAX_CMD_SIZE: usize = GSP_MSG_QUEUE_ELEMENT_SIZE_MAX - size_of::<GspMsgElement>();
+
+    /// Maximum size of the variable payload that can be sent in the main command.
+    const MAX_FIRST_PAYLOAD_SIZE: usize = Self::MAX_CMD_SIZE - size_of::<C::Command>();
+
+    /// Creates a new `SplitState` for the given command.
+    ///
+    /// If the command is too large, it will be split into a main command and some number of
+    /// continuation records.
+    pub(crate) fn new(inner: &C) -> Result<Self> {
+        if command_size(inner) > Self::MAX_CMD_SIZE {
+            let mut staging =
+                KVVec::<u8>::from_elem(0u8, inner.variable_payload_len(), GFP_KERNEL)?;
+            let mut sbuffer = SBufferIter::new_writer([staging.as_mut_slice(), &mut []]);
+            inner.init_variable_payload(&mut sbuffer)?;
+            if !sbuffer.is_empty() {
+                return Err(EIO);
+            }
+            drop(sbuffer);
+
+            Ok(Self {
+                state: Some((staging, Self::MAX_FIRST_PAYLOAD_SIZE)),
+                _phantom: PhantomData,
+            })
+        } else {
+            Ok(Self {
+                state: None,
+                _phantom: PhantomData,
+            })
+        }
+    }
+
+    /// Returns the main command.
+    pub(crate) fn command(&self, inner: C) -> SplitCommand<'_, C> {
+        if let Some((staging, _)) = &self.state {
+            SplitCommand::Split(inner, staging)
+        } else {
+            SplitCommand::Single(inner)
+        }
+    }
+
+    /// Returns the next continuation record, or `None` if there are no more.
+    pub(crate) fn next_continuation_record(&mut self) -> Option<ContinuationRecord<'_>> {
+        let (staging, offset) = self.state.as_mut()?;
+
+        let remaining = staging.len() - *offset;
+        if remaining > 0 {
+            let chunk_size = remaining.min(Self::MAX_CMD_SIZE);
+            let record = ContinuationRecord::new(&staging[*offset..(*offset + chunk_size)]);
+            *offset += chunk_size;
+            Some(record)
+        } else {
+            None
+        }
+    }
+}
+
+/// Wrapper enum that represents either a single command or a split command with its staging buffer.
+pub(crate) enum SplitCommand<'a, C: CommandToGsp> {
+    /// A command that fits in a single queue element.
+    Single(C),
+    /// A command split across continuation records, with its full payload in a staging buffer.
+    Split(C, &'a [u8]),
+}
+
+impl<'a, C: CommandToGsp> CommandToGsp for SplitCommand<'a, C> {
+    const FUNCTION: MsgFunction = C::FUNCTION;
+    type Command = C::Command;
+    type InitError = C::InitError;
+
+    fn init(&self) -> impl Init<Self::Command, Self::InitError> {
+        match self {
+            SplitCommand::Single(cmd) => cmd.init(),
+            SplitCommand::Split(cmd, _) => cmd.init(),
+        }
+    }
+
+    fn variable_payload_len(&self) -> usize {
+        match self {
+            SplitCommand::Single(cmd) => cmd.variable_payload_len(),
+            SplitCommand::Split(_, _) => SplitState::<C>::MAX_FIRST_PAYLOAD_SIZE,
+        }
+    }
+
+    fn init_variable_payload(
+        &self,
+        dst: &mut SBufferIter<core::array::IntoIter<&mut [u8], 2>>,
+    ) -> Result {
+        match self {
+            SplitCommand::Single(cmd) => cmd.init_variable_payload(dst),
+            SplitCommand::Split(_, staging) => {
+                dst.write_all(&staging[..self.variable_payload_len()])
+            }
+        }
+    }
+}
diff --git a/drivers/gpu/nova-core/gsp/fw.rs b/drivers/gpu/nova-core/gsp/fw.rs
index 6005362450cb..25fca1f6db2c 100644
--- a/drivers/gpu/nova-core/gsp/fw.rs
+++ b/drivers/gpu/nova-core/gsp/fw.rs
@@ -202,6 +202,7 @@ pub(crate) enum MsgFunction {
     AllocObject = bindings::NV_VGPU_MSG_FUNCTION_ALLOC_OBJECT,
     AllocRoot = bindings::NV_VGPU_MSG_FUNCTION_ALLOC_ROOT,
     BindCtxDma = bindings::NV_VGPU_MSG_FUNCTION_BIND_CTX_DMA,
+    ContinuationRecord = bindings::NV_VGPU_MSG_FUNCTION_CONTINUATION_RECORD,
     Free = bindings::NV_VGPU_MSG_FUNCTION_FREE,
     GetGspStaticInfo = bindings::NV_VGPU_MSG_FUNCTION_GET_GSP_STATIC_INFO,
     GetStaticInfo = bindings::NV_VGPU_MSG_FUNCTION_GET_STATIC_INFO,
@@ -239,6 +240,9 @@ fn try_from(value: u32) -> Result<MsgFunction> {
             bindings::NV_VGPU_MSG_FUNCTION_ALLOC_OBJECT => Ok(MsgFunction::AllocObject),
             bindings::NV_VGPU_MSG_FUNCTION_ALLOC_ROOT => Ok(MsgFunction::AllocRoot),
             bindings::NV_VGPU_MSG_FUNCTION_BIND_CTX_DMA => Ok(MsgFunction::BindCtxDma),
+            bindings::NV_VGPU_MSG_FUNCTION_CONTINUATION_RECORD => {
+                Ok(MsgFunction::ContinuationRecord)
+            }
             bindings::NV_VGPU_MSG_FUNCTION_FREE => Ok(MsgFunction::Free),
             bindings::NV_VGPU_MSG_FUNCTION_GET_GSP_STATIC_INFO => Ok(MsgFunction::GetGspStaticInfo),
             bindings::NV_VGPU_MSG_FUNCTION_GET_STATIC_INFO => Ok(MsgFunction::GetStaticInfo),

-- 
2.53.0


  parent reply	other threads:[~2026-02-26 11:47 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-02-26 11:45 [PATCH v3 0/9] gpu: nova-core: gsp: add continuation record support Eliot Courtney
2026-02-26 11:45 ` [PATCH v3 1/9] gpu: nova-core: gsp: sort MsgFunction variants alphabetically Eliot Courtney
2026-02-27  2:21   ` Claude review: " Claude Code Review Bot
2026-02-26 11:45 ` [PATCH v3 2/9] gpu: nova-core: gsp: add mechanism to wait for space on command queue Eliot Courtney
2026-02-27  2:21   ` Claude review: " Claude Code Review Bot
2026-02-26 11:45 ` [PATCH v3 3/9] rust: add EMSGSIZE error code Eliot Courtney
2026-02-26 14:04   ` Miguel Ojeda
2026-02-27  2:21   ` Claude review: " Claude Code Review Bot
2026-02-26 11:45 ` [PATCH v3 4/9] gpu: nova-core: gsp: add checking oversized commands Eliot Courtney
2026-02-27  2:21   ` Claude review: " Claude Code Review Bot
2026-02-26 11:45 ` [PATCH v3 5/9] gpu: nova-core: gsp: clarify invariant on command queue Eliot Courtney
2026-02-27  2:21   ` Claude review: " Claude Code Review Bot
2026-02-26 11:45 ` [PATCH v3 6/9] gpu: nova-core: gsp: unconditionally call variable payload handling Eliot Courtney
2026-02-27  2:21   ` Claude review: " Claude Code Review Bot
2026-02-26 11:45 ` [PATCH v3 7/9] gpu: nova-core: gsp: add command_size helper Eliot Courtney
2026-02-27  2:21   ` Claude review: " Claude Code Review Bot
2026-02-26 11:45 ` Eliot Courtney [this message]
2026-02-27  2:21   ` Claude review: gpu: nova-core: gsp: support large RPCs via continuation record Claude Code Review Bot
2026-02-26 11:45 ` [PATCH v3 9/9] gpu: nova-core: gsp: add tests for SplitState Eliot Courtney
2026-02-27  2:22   ` Claude review: " Claude Code Review Bot
2026-02-27  2:21 ` Claude review: gpu: nova-core: gsp: add continuation record support Claude Code Review Bot

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=20260226-cmdq-continuation-v3-8-572ab9916766@nvidia.com \
    --to=ecourtney@nvidia.com \
    --cc=a.hindborg@kernel.org \
    --cc=acourbot@nvidia.com \
    --cc=airlied@gmail.com \
    --cc=aliceryhl@google.com \
    --cc=bjorn3_gh@protonmail.com \
    --cc=boqun@kernel.org \
    --cc=dakr@kernel.org \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=gary@garyguo.net \
    --cc=linux-kernel@vger.kernel.org \
    --cc=lossin@kernel.org \
    --cc=nouveau@lists.freedesktop.org \
    --cc=ojeda@kernel.org \
    --cc=rust-for-linux@vger.kernel.org \
    --cc=simona@ffwll.ch \
    --cc=tmgross@umich.edu \
    --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