sched_ext: Maintain an online cid mask in the scheduler arenagrafted

Schedulers on the default cid mapping treat [0, nr_online_cids) as the
online set and restart on hotplug. Schedulers that install their own mapping
with scx_bpf_cid_override() have no way to learn which cids are online: the
count no longer identifies members and the CPU-form cpumask is unusable from
cid programs. This is an obvious hole in the cid API.

Add scx_bpf_online_cmask(), a kernel-maintained cmask in the scheduler's
arena, allocated alongside the per-CPU scratch masks and populated after the
cid mapping is finalized and before ops.init(), for child schedulers too.
The pointer stays valid through ops.exit() with no reference to take. It is
the arena offset as a void pointer, the same form struct_ops arena arguments
arrive in. The verifier types the void return as a scalar for the program's
arena cast.

The mask follows the SCX hotplug notifications: seeded from cpu_active_mask
and updated before ops.cid_online/offline() runs, so it lags cpu_online_mask
only inside a hotplug transition. Updates walk the scheduler list under the
lock that also serializes unlinking. Reads are live, not atomic snapshots.
Root initialization excludes hotplug.

v2: Reworded the getter kerneldoc (Andrea Righi).

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>

1 files changed, 178 insertions, 0 deletions

diff --git a/samples/rust/rust_debugfs.rs b/samples/rust/rust_debugfs.rs
new file mode 100644
index 000000000..1f59e08aa
--- /dev/null
+++ b/samples/rust/rust_debugfs.rs
@@ -0,0 +1,178 @@
+// SPDX-License-Identifier: GPL-2.0
+
+// Copyright (C) 2025 Google LLC.
+
+//! Sample DebugFS exporting platform driver
+//!
+//! To successfully probe this driver with ACPI, use an ssdt that looks like
+//!
+//! ```dsl
+//! DefinitionBlock ("", "SSDT", 2, "TEST", "VIRTACPI", 0x00000001)
+//! {
+//!    Scope (\_SB)
+//!    {
+//!        Device (T432)
+//!        {
+//!            Name (_HID, "LNUXBEEF")  // ACPI hardware ID to match
+//!            Name (_UID, 1)
+//!            Name (_STA, 0x0F)        // Device present, enabled
+//!            Name (_DSD, Package () { // Sample attribute
+//!                ToUUID("daffd814-6eba-4d8c-8a91-bc9bbf4aa301"),
+//!                Package() {
+//!                    Package(2) {"compatible", "sample-debugfs"}
+//!                }
+//!            })
+//!            Name (_CRS, ResourceTemplate ()
+//!            {
+//!                Memory32Fixed (ReadWrite, 0xFED00000, 0x1000)
+//!            })
+//!        }
+//!    }
+//! }
+//! ```
+
+use core::str::FromStr;
+use kernel::{
+    acpi,
+    debugfs::{
+        Dir,
+        File, //
+    },
+    device::Core,
+    new_mutex,
+    of,
+    platform,
+    prelude::*,
+    sizes::*,
+    str::CString,
+    sync::{
+        aref::ARef,
+        atomic::{
+            Atomic,
+            Relaxed, //
+        },
+        Mutex,
+    }, //
+};
+
+kernel::module_platform_driver! {
+    type: RustDebugFs,
+    name: "rust_debugfs",
+    authors: ["Matthew Maurer"],
+    description: "Rust DebugFS usage sample",
+    license: "GPL",
+}
+
+#[pin_data]
+struct RustDebugFs {
+    pdev: ARef<platform::Device>,
+    // As we only hold these for drop effect (to remove the directory/files) we have a leading
+    // underscore to indicate to the compiler that we don't expect to use this field directly.
+    _debugfs: Dir,
+    #[pin]
+    _compatible: File<CString>,
+    #[pin]
+    counter: File<Atomic<usize>>,
+    #[pin]
+    inner: File<Mutex<Inner>>,
+    #[pin]
+    array_blob: File<Mutex<[u8; 4]>>,
+    #[pin]
+    vector_blob: File<Mutex<KVec<u8>>>,
+}
+
+#[derive(Debug)]
+struct Inner {
+    x: u32,
+    y: u32,
+}
+
+impl FromStr for Inner {
+    type Err = Error;
+    fn from_str(s: &str) -> Result<Self> {
+        let mut parts = s.split_whitespace();
+        let x = parts
+            .next()
+            .ok_or(EINVAL)?
+            .parse::<u32>()
+            .map_err(|_| EINVAL)?;
+        let y = parts
+            .next()
+            .ok_or(EINVAL)?
+            .parse::<u32>()
+            .map_err(|_| EINVAL)?;
+        if parts.next().is_some() {
+            return Err(EINVAL);
+        }
+        Ok(Inner { x, y })
+    }
+}
+
+kernel::acpi_device_table!(
+    ACPI_TABLE,
+    MODULE_ACPI_TABLE,
+    <RustDebugFs as platform::Driver>::IdInfo,
+    [(acpi::DeviceId::new(c"LNUXBEEF"), ())]
+);
+
+impl platform::Driver for RustDebugFs {
+    type IdInfo = ();
+    type Data<'bound> = Self;
+    const OF_ID_TABLE: Option<of::IdTable<Self::IdInfo>> = None;
+    const ACPI_ID_TABLE: Option<acpi::IdTable<Self::IdInfo>> = Some(&ACPI_TABLE);
+
+    fn probe<'bound>(
+        pdev: &'bound platform::Device<Core<'_>>,
+        _info: Option<&'bound Self::IdInfo>,
+    ) -> impl PinInit<Self, Error> + 'bound {
+        RustDebugFs::new(pdev).pin_chain(|this| {
+            this.counter.store(91, Relaxed);
+            {
+                let mut guard = this.inner.lock();
+                guard.x = guard.y;
+                guard.y = 42;
+            }
+
+            Ok(())
+        })
+    }
+}
+
+impl RustDebugFs {
+    fn build_counter(dir: &Dir) -> impl PinInit<File<Atomic<usize>>> + '_ {
+        dir.read_write_file(c"counter", Atomic::<usize>::new(0))
+    }
+
+    fn build_inner(dir: &Dir) -> impl PinInit<File<Mutex<Inner>>> + '_ {
+        dir.read_write_file(c"pair", new_mutex!(Inner { x: 3, y: 10 }))
+    }
+
+    fn new<'a>(pdev: &'a platform::Device<Core<'_>>) -> impl PinInit<Self, Error> + 'a {
+        let debugfs = Dir::new(c"sample_debugfs");
+        let dev = pdev.as_ref();
+
+        try_pin_init! {
+            Self {
+                _compatible <- debugfs.read_only_file(
+                    c"compatible",
+                    dev.fwnode()
+                        .ok_or(ENOENT)?
+                        .property_read::<CString>(c"compatible")
+                        .required_by(dev)?,
+                ),
+                counter <- Self::build_counter(&debugfs),
+                inner <- Self::build_inner(&debugfs),
+                array_blob <- debugfs.read_write_binary_file(
+                    c"array_blob",
+                    new_mutex!([0x62, 0x6c, 0x6f, 0x62]),
+                ),
+                vector_blob <- debugfs.read_write_binary_file(
+                    c"vector_blob",
+                    new_mutex!(kernel::kvec!(0x42; SZ_4K)?),
+                ),
+                _debugfs: debugfs,
+                pdev: pdev.into(),
+            }
+        }
+    }
+}