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 v3 09/14] gpu: nova-core: recover the GSP receive path from corrupt framing
Date: Wed, 2 Sep 2026 20:15:08 -0700 [thread overview]
Message-ID: <20260903031514.1515905-10-jhubbard@nvidia.com> (raw)
In-Reply-To: <20260903031514.1515905-1-jhubbard@nvidia.com>
A GSP message carries its length inside the checksummed region, so once
the framing or the checksum fails, the length cannot be trusted to skip
the message.
Two paths left a bad message at the queue head. A framing or checksum
failure returned without advancing the read pointer, so every later
receive re-parsed the same message. A validly framed message whose typed
payload failed to decode returned early and did the same.
Poison the queue on a framing or checksum failure, log what was
inconsistent, and fail every later receive, so the bad head is parsed
once and recovery requires a reset. Advance the read pointer past a
validly framed message whether or not its payload decodes.
Assisted-by: Cursor:claude-opus-5
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
---
drivers/gpu/nova-core/gsp/cmdq.rs | 96 +++++++++++++++++++++----------
1 file changed, 66 insertions(+), 30 deletions(-)
diff --git a/drivers/gpu/nova-core/gsp/cmdq.rs b/drivers/gpu/nova-core/gsp/cmdq.rs
index 5572224db233..ce4d6a111e68 100644
--- a/drivers/gpu/nova-core/gsp/cmdq.rs
+++ b/drivers/gpu/nova-core/gsp/cmdq.rs
@@ -2,7 +2,10 @@
mod continuation;
-use core::mem;
+use core::{
+ cell::Cell,
+ mem, //
+};
use kernel::{
device,
@@ -11,6 +14,7 @@
CoherentBox,
DmaAddress, //
},
+ fmt,
io::{
io_project,
poll::read_poll_timeout,
@@ -531,6 +535,7 @@ pub(crate) fn new(dev: &device::Device<device::Bound>) -> impl PinInit<Self, Err
dev: dev.into(),
gsp_mem,
seq: 0,
+ poisoned: Cell::new(false),
}),
}))
})
@@ -624,6 +629,12 @@ struct CmdqInner {
dev: ARef<device::Device>,
/// Current command sequence number.
seq: u32,
+ /// Set once a message with corrupt framing or a bad checksum is seen. Such a message has an
+ /// untrusted length, so the queue cannot be advanced past it, and every later receive fails
+ /// until the queue is torn down and reset.
+ ///
+ /// A [`Cell`], so the shared-borrow read path [`Self::wait_for_msg`] can set it.
+ poisoned: Cell<bool>,
/// Memory area shared with the GSP for communicating commands and messages.
gsp_mem: DmaGspMem,
}
@@ -732,6 +743,19 @@ fn send_command<M>(&mut self, bar: Bar0<'_>, command: M) -> Result
}
}
+ /// Marks the queue unusable and returns the error every later receive fails with.
+ ///
+ /// `reason` names the inconsistency. Without it the failure is invisible, because the queue
+ /// just stops producing messages.
+ ///
+ /// Takes `&self` so the shared-borrow read path [`Self::wait_for_msg`] can call it.
+ fn poison(&self, reason: fmt::Arguments<'_>) -> Error {
+ dev_err!(&self.dev, "GSP RPC: receive: queue poisoned: {}\n", reason);
+ self.poisoned.set(true);
+
+ EIO
+ }
+
/// 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
@@ -746,11 +770,13 @@ fn send_command<M>(&mut self, bar: Bar0<'_>, command: M) -> Result
/// # Errors
///
/// - `ETIMEDOUT` if `timeout` has elapsed before any message becomes available.
- /// - `EIO` if there was some inconsistency (e.g. message shorter than advertised) on the
- /// message queue.
- ///
- /// Error codes returned by the message constructor are propagated as-is.
+ /// - `EIO` if the framing or the checksum is invalid, or the queue was already poisoned by an
+ /// earlier such failure. Either failure poisons the queue, so recovery requires a reset.
fn wait_for_msg(&self, timeout: Delta) -> Result<GspMessage<'_>> {
+ if self.poisoned.get() {
+ return Err(EIO);
+ }
+
// Wait for a message to arrive from the GSP.
let (slice_1, slice_2) = read_poll_timeout(
|| Ok(self.gsp_mem.driver_read_area()),
@@ -761,7 +787,12 @@ fn wait_for_msg(&self, timeout: Delta) -> Result<GspMessage<'_>> {
.map(|(slice_1, slice_2)| (slice_1.as_flattened(), slice_2.as_flattened()))?;
// Extract the `GspMsgElement`.
- let (header, slice_1) = GspMsgElement::from_bytes_prefix(slice_1).ok_or(EIO)?;
+ let Some((header, slice_1)) = GspMsgElement::from_bytes_prefix(slice_1) else {
+ return Err(self.poison(fmt!(
+ "read area of {} bytes is shorter than a message header",
+ slice_1.len()
+ )));
+ };
dev_dbg!(
&self.dev,
@@ -775,7 +806,11 @@ fn wait_for_msg(&self, timeout: Delta) -> Result<GspMessage<'_>> {
// Check that the driver read area is large enough for the message.
if slice_1.len() + slice_2.len() < payload_length {
- return Err(EIO);
+ return Err(self.poison(fmt!(
+ "message advertises {} payload bytes but only {} are readable",
+ payload_length,
+ slice_1.len() + slice_2.len()
+ )));
}
// Cut the message slices down to the actual length of the message.
@@ -798,12 +833,10 @@ fn wait_for_msg(&self, timeout: Delta) -> Result<GspMessage<'_>> {
slice_2,
])) != 0
{
- dev_err!(
- &self.dev,
- "GSP RPC: receive: Call {} - bad checksum\n",
+ return Err(self.poison(fmt!(
+ "message with sequence {} has a bad checksum",
header.sequence()
- );
- return Err(EIO);
+ )));
}
Ok(GspMessage {
@@ -824,8 +857,8 @@ fn wait_for_msg(&self, timeout: Delta) -> Result<GspMessage<'_>> {
/// # Errors
///
/// - `ETIMEDOUT` if `timeout` has elapsed before any message becomes available.
- /// - `EIO` if there was some inconsistency (e.g. message shorter than advertised) on the
- /// message queue.
+ /// - `EIO` if the queue is poisoned or the message fails framing or checksum validation (see
+ /// [`Self::wait_for_msg`]), or if the matched message is too short for `M::Message`.
/// - `ERANGE` if the message was not the awaited reply.
///
/// Error codes returned by [`MessageFromGsp::read`] are propagated as-is.
@@ -838,23 +871,26 @@ fn receive_msg<M: MessageFromGsp>(&mut self, timeout: Delta) -> Result<M>
let function = message.header.function();
let seq = message.header.sequence();
- // Bind the result rather than returning early. The read pointer must advance past this
- // message on every path.
+ // Every path must advance the read pointer past this message, including a failed decode.
let result = if matches!(function, Ok(f) if f == M::FUNCTION) {
- let (cmd, contents_1) = M::Message::from_bytes_prefix(message.contents.0).ok_or(EIO)?;
- let mut sbuffer = SBufferIter::new_reader([contents_1, message.contents.1]);
-
- M::read(cmd, &mut sbuffer)
- .map_err(|e| e.into())
- .inspect(|_| {
- if !sbuffer.is_empty() {
- dev_warn!(
- &self.dev,
- "GSP message {:?} has unprocessed data\n",
- M::FUNCTION
- );
- }
- })
+ match M::Message::from_bytes_prefix(message.contents.0) {
+ Some((cmd, contents_1)) => {
+ let mut sbuffer = SBufferIter::new_reader([contents_1, message.contents.1]);
+
+ M::read(cmd, &mut sbuffer)
+ .map_err(|e| e.into())
+ .inspect(|_| {
+ if !sbuffer.is_empty() {
+ dev_warn!(
+ &self.dev,
+ "GSP message {:?} has unprocessed data\n",
+ M::FUNCTION
+ );
+ }
+ })
+ }
+ None => Err(EIO),
+ }
} else {
self.classify_event(function, seq);
--
2.55.0
next prev parent reply other threads:[~2026-09-03 3:15 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-09-03 3:14 [PATCH v3 00/14] nova-core: GPU interrupt support and GSP event delivery John Hubbard
2026-09-03 3:15 ` [PATCH v3 01/14] rust: pci: declare IrqType and IrqTypes with impl_flags John Hubbard
2026-09-03 3:15 ` [PATCH v3 02/14] rust: sync: completion: add wait_for_completion_timeout() John Hubbard
2026-09-03 3:15 ` [PATCH v3 03/14] gpu: nova-core: add the GIN vector and subtree newtypes John Hubbard
2026-09-03 3:15 ` [PATCH v3 04/14] gpu: nova-core: add the GIN CPU interrupt tree and MSI EOI registers John Hubbard
2026-09-03 3:15 ` [PATCH v3 05/14] gpu: nova-core: add the per-architecture GIN CPU interrupt HAL John Hubbard
2026-09-03 3:15 ` [PATCH v3 06/14] gpu: nova-core: add the GIN interrupt tree and allocate its vectors John Hubbard
2026-09-03 3:15 ` [PATCH v3 07/14] gpu: nova-core: add an interrupt delivery self-test John Hubbard
2026-09-03 3:29 ` sashiko-bot
2026-09-03 3:57 ` John Hubbard
2026-09-03 3:15 ` [PATCH v3 08/14] gpu: nova-core: log GSP events instead of discarding them John Hubbard
2026-09-03 3:15 ` John Hubbard [this message]
2026-09-04 10:53 ` [PATCH v3 09/14] gpu: nova-core: recover the GSP receive path from corrupt framing Alexandre Courbot
2026-09-04 11:17 ` Gary Guo
2026-09-04 13:45 ` Alexandre Courbot
2026-09-03 3:15 ` [PATCH v3 10/14] gpu: nova-core: bound a GSP wait by a single deadline John Hubbard
2026-09-04 11:13 ` Alexandre Courbot
2026-09-04 11:26 ` Gary Guo
2026-09-04 13:32 ` Alexandre Courbot
2026-09-04 13:41 ` Gary Guo
2026-09-03 3:15 ` [PATCH v3 11/14] gpu: nova-core: add the falcon interrupt status and routing registers John Hubbard
2026-09-03 3:15 ` [PATCH v3 12/14] gpu: nova-core: drive GSP events with the SWGEN0 interrupt John Hubbard
2026-09-03 3:28 ` sashiko-bot
2026-09-03 3:55 ` John Hubbard
2026-09-04 1:53 ` John Hubbard
2026-09-03 3:15 ` [PATCH v3 13/14] gpu: nova-core: add KUnit tests for the interrupt tree and HALs John Hubbard
2026-09-03 3:15 ` [PATCH v3 14/14] gpu: nova-core: document the GIN interrupt controller and GSP events John Hubbard
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=20260903031514.1515905-10-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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox