mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Simon Song <xinmengs@nvidia.com>
To: <dakr@kernel.org>, <acourbot@nvidia.com>, <kvm@vger.kernel.org>,
	<rust-for-linux@vger.kernel.org>, <nova-gpu@lists.linux.dev>,
	<linux-pci@vger.kernel.org>
Cc: Simon Song <xinmengs@nvidia.com>, <alex@shazbot.org>,
	<jgg@nvidia.com>, <yishaih@nvidia.com>, <skolothumtho@nvidia.com>,
	<kevin.tian@intel.com>, <airlied@gmail.com>, <simona@ffwll.ch>,
	<ojeda@kernel.org>, <alex.gaynor@gmail.com>,
	<boqun.feng@gmail.com>, <gary@garyguo.net>,
	<bjorn3_gh@protonmail.com>, <lossin@kernel.org>,
	<a.hindborg@kernel.org>, <aliceryhl@google.com>,
	<tmgross@umich.edu>, <jhubbard@nvidia.com>,
	<ecourtney@nvidia.com>, <cjia@nvidia.com>, <smitra@nvidia.com>,
	<kjaju@nvidia.com>, <alkumar@nvidia.com>, <ankita@nvidia.com>,
	<aniketa@nvidia.com>, <kwankhede@nvidia.com>,
	<targupta@nvidia.com>, <linux-kernel@vger.kernel.org>,
	<zhiwang@kernel.org>, <zhiw@nvidia.com>, <boqun@kernel.org>,
	<daniel.almeida@collabora.com>, <tamird@kernel.org>,
	<work@onurozkan.dev>, <jgg@ziepe.ca>, <bhelgaas@google.com>,
	<kwilczynski@kernel.org>, <dri-devel@lists.freedesktop.org>,
	<peter@colberg.org>
Subject: [PATCH v3 5/9] rust: pci: add an error_detected callback
Date: Thu, 19 Nov 2026 13:50:40 -0800	[thread overview]
Message-ID: <20261119215046.2892839-6-xinmengs@nvidia.com> (raw)
In-Reply-To: <20261119215046.2892839-1-xinmengs@nvidia.com>

VFIO PCI variant drivers will use error_detected() to notify userspace
of PCI errors through vfio-pci-core.

Adding error_detected() to pci::Driver lets VFIO variants reuse the PCI
adapter's error callback dispatch.

Suggested-by: Zhi Wang <zhiw@nvidia.com>
Signed-off-by: Simon Song <xinmengs@nvidia.com>
---
 rust/kernel/pci.rs | 89 ++++++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 87 insertions(+), 2 deletions(-)

diff --git a/rust/kernel/pci.rs b/rust/kernel/pci.rs
index 8fcec16e6ccf..27ac8d8435f7 100644
--- a/rust/kernel/pci.rs
+++ b/rust/kernel/pci.rs
@@ -106,7 +106,7 @@ unsafe fn register(
             (*pdrv.get()).remove = Some(Self::remove_callback);
             (*pdrv.get()).id_table = T::ID_TABLE.as_ptr();
             (*pdrv.get()).driver_managed_dma = T::DRIVER_MANAGED_DMA.is_some();
-            if T::HAS_RESET_PREPARE || T::HAS_RESET_DONE {
+            if T::HAS_ERROR_DETECTED || T::HAS_RESET_PREPARE || T::HAS_RESET_DONE {
                 (*pdrv.get()).err_handler = &Self::ERROR_HANDLERS;
             }
             if T::HAS_SRIOV_ENABLE {
@@ -212,8 +212,36 @@ extern "C" fn reset_done_callback(pdev: *mut bindings::pci_dev) {
         T::reset_done(pdev, data);
     }
 
+    extern "C" fn error_detected_callback(
+        pdev: *mut bindings::pci_dev,
+        state: bindings::pci_channel_state_t,
+    ) -> bindings::pci_ers_result_t {
+        // SAFETY: PCI error recovery only ever calls the error_detected callback with a valid
+        // pointer to a `struct pci_dev`. AER (`report_error_detected()`) and EEH hold the device
+        // lock while calling it.
+        //
+        // INVARIANT: `pdev` is valid for the duration of `error_detected_callback()`.
+        let pdev = unsafe { &*pdev.cast::<Device<device::CoreInternal<'_>>>() };
+
+        // SAFETY: PCI error recovery only calls this callback for a device bound to this driver.
+        // The device lock excludes `probe_callback()` and `remove_callback()`, so the stored
+        // pointer has type `T::Data<'_>` and remains valid throughout this callback.
+        let data = unsafe { pdev.as_ref().drvdata_borrow::<T::Data<'_>>() };
+
+        let Some(state) = ChannelState::from_raw(state) else {
+            // PCI error recovery only reports the states `ChannelState` represents.
+            return ErsResult::None.as_raw();
+        };
+
+        T::error_detected(pdev, data, state).as_raw()
+    }
+
     const ERROR_HANDLERS: bindings::pci_error_handlers = bindings::pci_error_handlers {
-        error_detected: None,
+        error_detected: if T::HAS_ERROR_DETECTED {
+            Some(Self::error_detected_callback)
+        } else {
+            None
+        },
         mmio_enabled: None,
         slot_reset: None,
         reset_prepare: if T::HAS_RESET_PREPARE {
@@ -363,6 +391,55 @@ impl<D: ?Sized> DriverManagedDma<D> {
     }
 }
 
+/// The state of the I/O channel to a device, as reported by PCI error recovery.
+#[derive(Clone, Copy, Debug, PartialEq, Eq)]
+pub enum ChannelState {
+    /// The I/O channel remains operational.
+    Normal,
+    /// I/O to the device is blocked.
+    Frozen,
+    /// The device has permanently failed.
+    PermanentFailure,
+}
+
+impl ChannelState {
+    fn from_raw(state: bindings::pci_channel_state_t) -> Option<Self> {
+        match state {
+            bindings::pci_channel_io_normal => Some(Self::Normal),
+            bindings::pci_channel_io_frozen => Some(Self::Frozen),
+            bindings::pci_channel_io_perm_failure => Some(Self::PermanentFailure),
+            _ => None,
+        }
+    }
+}
+
+/// The result a driver reports to PCI error recovery.
+#[derive(Clone, Copy, Debug, PartialEq, Eq)]
+pub enum ErsResult {
+    /// The driver has no result to report.
+    None,
+    /// The driver can recover without a slot reset.
+    CanRecover,
+    /// The driver needs the slot to be reset.
+    NeedReset,
+    /// The device has failed completely and cannot be recovered.
+    Disconnect,
+    /// The driver has fully recovered and the device is operational.
+    Recovered,
+}
+
+impl ErsResult {
+    fn as_raw(self) -> bindings::pci_ers_result_t {
+        match self {
+            Self::None => bindings::pci_ers_result_PCI_ERS_RESULT_NONE,
+            Self::CanRecover => bindings::pci_ers_result_PCI_ERS_RESULT_CAN_RECOVER,
+            Self::NeedReset => bindings::pci_ers_result_PCI_ERS_RESULT_NEED_RESET,
+            Self::Disconnect => bindings::pci_ers_result_PCI_ERS_RESULT_DISCONNECT,
+            Self::Recovered => bindings::pci_ers_result_PCI_ERS_RESULT_RECOVERED,
+        }
+    }
+}
+
 /// `IdTable` type for PCI.
 pub type IdTable<T> = &'static dyn kernel::device_id::IdTable<DeviceId, T>;
 
@@ -461,6 +538,14 @@ fn unbind<'bound>(dev: &'bound Device<device::Core<'_>>, this: Pin<&Self::Data<'
     #[optional]
     fn reset_done<'bound>(_dev: &Device<device::Core<'_>>, _this: Pin<&Self::Data<'bound>>);
 
+    /// Handle a PCI error and return the PCI recovery result, with the device lock held.
+    #[optional]
+    fn error_detected<'bound>(
+        _dev: &Device<device::Core<'_>>,
+        _this: Pin<&Self::Data<'bound>>,
+        _state: ChannelState,
+    ) -> ErsResult;
+
     /// Enables Single Root I/O Virtualization (SR-IOV) for a PF.
     ///
     /// This callback is only invoked when `CONFIG_PCI_IOV` is enabled.
-- 
2.43.7


  parent reply	other threads:[~2026-11-19 21:51 UTC|newest]

Thread overview: 10+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2026-11-19 21:50 [PATCH v3 0/9] Rust VFIO PCI support and NVIDIA vGPU driver Simon Song
2026-11-19 21:50 ` [PATCH v3 1/9] rust: pci: add VFIO override device IDs Simon Song
2026-11-19 21:50 ` [PATCH v3 2/9] rust: pci: expose the VF index within its PF Simon Song
2026-11-19 21:50 ` [PATCH v3 3/9] rust: pci: allow drivers to manage DMA ownership Simon Song
2026-11-19 21:50 ` [PATCH v3 4/9] rust: pci: add reset callbacks Simon Song
2026-11-19 21:50 ` Simon Song [this message]
2026-11-19 21:50 ` [PATCH v3 6/9] rust: vfio: add common VFIO device handling Simon Song
2026-11-19 21:50 ` [PATCH v3 7/9] rust: vfio: add PCI variant driver abstractions Simon Song
2026-11-19 21:50 ` [PATCH v3 8/9] gpu: nova-core: publish typed SR-IOV PF APIs Simon Song
2026-11-19 21:50 ` [PATCH v3 9/9] vfio/nova-vgpu: add the Rust VFIO variant driver Simon Song

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=20261119215046.2892839-6-xinmengs@nvidia.com \
    --to=xinmengs@nvidia.com \
    --cc=a.hindborg@kernel.org \
    --cc=acourbot@nvidia.com \
    --cc=airlied@gmail.com \
    --cc=alex.gaynor@gmail.com \
    --cc=alex@shazbot.org \
    --cc=aliceryhl@google.com \
    --cc=alkumar@nvidia.com \
    --cc=aniketa@nvidia.com \
    --cc=ankita@nvidia.com \
    --cc=bhelgaas@google.com \
    --cc=bjorn3_gh@protonmail.com \
    --cc=boqun.feng@gmail.com \
    --cc=boqun@kernel.org \
    --cc=cjia@nvidia.com \
    --cc=dakr@kernel.org \
    --cc=daniel.almeida@collabora.com \
    --cc=dri-devel@lists.freedesktop.org \
    --cc=ecourtney@nvidia.com \
    --cc=gary@garyguo.net \
    --cc=jgg@nvidia.com \
    --cc=jgg@ziepe.ca \
    --cc=jhubbard@nvidia.com \
    --cc=kevin.tian@intel.com \
    --cc=kjaju@nvidia.com \
    --cc=kvm@vger.kernel.org \
    --cc=kwankhede@nvidia.com \
    --cc=kwilczynski@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=lossin@kernel.org \
    --cc=nova-gpu@lists.linux.dev \
    --cc=ojeda@kernel.org \
    --cc=peter@colberg.org \
    --cc=rust-for-linux@vger.kernel.org \
    --cc=simona@ffwll.ch \
    --cc=skolothumtho@nvidia.com \
    --cc=smitra@nvidia.com \
    --cc=tamird@kernel.org \
    --cc=targupta@nvidia.com \
    --cc=tmgross@umich.edu \
    --cc=work@onurozkan.dev \
    --cc=yishaih@nvidia.com \
    --cc=zhiw@nvidia.com \
    --cc=zhiwang@kernel.org \
    /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

all inboxes | Powered by JetHome®