From a9e3760b0838299649c0d57cca44daaf40ba3c33 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 14 Sep 2026 22:12:34 -1000 Subject: sched_ext: Maintain an online cid mask in the scheduler arena 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 Reviewed-by: Andrea Righi --- drivers/block/rnull/Kconfig | 13 ++ drivers/block/rnull/Makefile | 3 + drivers/block/rnull/configfs.rs | 261 ++++++++++++++++++++++++++++++++++++++++ drivers/block/rnull/rnull.rs | 100 +++++++++++++++ 4 files changed, 377 insertions(+) create mode 100644 drivers/block/rnull/Kconfig create mode 100644 drivers/block/rnull/Makefile create mode 100644 drivers/block/rnull/configfs.rs create mode 100644 drivers/block/rnull/rnull.rs (limited to 'drivers/block/rnull') diff --git a/drivers/block/rnull/Kconfig b/drivers/block/rnull/Kconfig new file mode 100644 index 000000000..7bc5b376c --- /dev/null +++ b/drivers/block/rnull/Kconfig @@ -0,0 +1,13 @@ +# SPDX-License-Identifier: GPL-2.0 +# +# Rust null block device driver configuration + +config BLK_DEV_RUST_NULL + tristate "Rust null block driver (Experimental)" + depends on RUST && CONFIGFS_FS + help + This is the Rust implementation of the null block driver. Like + the C version, the driver allows the user to create virutal block + devices that can be configured via various configuration options. + + If unsure, say N. diff --git a/drivers/block/rnull/Makefile b/drivers/block/rnull/Makefile new file mode 100644 index 000000000..11cfa5e61 --- /dev/null +++ b/drivers/block/rnull/Makefile @@ -0,0 +1,3 @@ + +obj-$(CONFIG_BLK_DEV_RUST_NULL) += rnull_mod.o +rnull_mod-y := rnull.o diff --git a/drivers/block/rnull/configfs.rs b/drivers/block/rnull/configfs.rs new file mode 100644 index 000000000..7c2eb5c0b --- /dev/null +++ b/drivers/block/rnull/configfs.rs @@ -0,0 +1,261 @@ +// SPDX-License-Identifier: GPL-2.0 + +use super::{NullBlkDevice, THIS_MODULE}; +use kernel::{ + block::mq::gen_disk::{GenDisk, GenDiskBuilder}, + configfs::{self, AttributeOperations}, + configfs_attrs, + fmt::{self, Write as _}, + new_mutex, + page::PAGE_SIZE, + prelude::*, + str::{kstrtobool_bytes, CString}, + sync::Mutex, +}; + +pub(crate) fn subsystem() -> impl PinInit, Error> { + let item_type = configfs_attrs! { + container: configfs::Subsystem, + data: Config, + child: DeviceConfig, + attributes: [ + features: 0, + ], + }; + + kernel::configfs::Subsystem::new(c"rnull", item_type, try_pin_init!(Config {})) +} + +#[pin_data] +pub(crate) struct Config {} + +#[vtable] +impl AttributeOperations<0> for Config { + type Data = Config; + + fn show(_this: &Config, page: &mut [u8; PAGE_SIZE]) -> Result { + let mut writer = kernel::str::Formatter::new(page); + writer.write_str("blocksize,size,rotational,irqmode\n")?; + Ok(writer.bytes_written()) + } +} + +#[vtable] +impl configfs::GroupOperations for Config { + type Child = DeviceConfig; + + fn make_group( + &self, + name: &CStr, + ) -> Result, Error>> { + let item_type = configfs_attrs! { + container: configfs::Group, + data: DeviceConfig, + attributes: [ + // Named for compatibility with C null_blk + power: 0, + blocksize: 1, + rotational: 2, + size: 3, + irqmode: 4, + ], + }; + + Ok(configfs::Group::new( + name.try_into()?, + item_type, + // TODO: cannot coerce new_mutex!() to impl PinInit<_, Error>, so put mutex inside + try_pin_init!( DeviceConfig { + data <- new_mutex!(DeviceConfigInner { + powered: false, + block_size: 4096, + rotational: false, + disk: None, + capacity_mib: 4096, + irq_mode: IRQMode::None, + name: name.try_into()?, + }), + }), + )) + } +} + +#[derive(Debug, Clone, Copy)] +pub(crate) enum IRQMode { + None, + Soft, +} + +impl TryFrom for IRQMode { + type Error = kernel::error::Error; + + fn try_from(value: u8) -> Result { + match value { + 0 => Ok(Self::None), + 1 => Ok(Self::Soft), + _ => Err(EINVAL), + } + } +} + +impl fmt::Display for IRQMode { + fn fmt(&self, f: &mut fmt::Formatter<'_>) -> fmt::Result { + match self { + Self::None => f.write_str("0")?, + Self::Soft => f.write_str("1")?, + } + Ok(()) + } +} + +#[pin_data] +pub(crate) struct DeviceConfig { + #[pin] + data: Mutex, +} + +#[pin_data] +struct DeviceConfigInner { + powered: bool, + name: CString, + block_size: u32, + rotational: bool, + capacity_mib: u64, + irq_mode: IRQMode, + disk: Option>, +} + +#[vtable] +impl configfs::AttributeOperations<0> for DeviceConfig { + type Data = DeviceConfig; + + fn show(this: &DeviceConfig, page: &mut [u8; PAGE_SIZE]) -> Result { + let mut writer = kernel::str::Formatter::new(page); + + if this.data.lock().powered { + writer.write_str("1\n")?; + } else { + writer.write_str("0\n")?; + } + + Ok(writer.bytes_written()) + } + + fn store(this: &DeviceConfig, page: &[u8]) -> Result { + let power_op = kstrtobool_bytes(page)?; + let mut guard = this.data.lock(); + + if !guard.powered && power_op { + guard.disk = Some(NullBlkDevice::new( + &guard.name, + guard.block_size, + guard.rotational, + guard.capacity_mib, + guard.irq_mode, + )?); + guard.powered = true; + } else if guard.powered && !power_op { + drop(guard.disk.take()); + guard.powered = false; + } + + Ok(()) + } +} + +#[vtable] +impl configfs::AttributeOperations<1> for DeviceConfig { + type Data = DeviceConfig; + + fn show(this: &DeviceConfig, page: &mut [u8; PAGE_SIZE]) -> Result { + let mut writer = kernel::str::Formatter::new(page); + writer.write_fmt(fmt!("{}\n", this.data.lock().block_size))?; + Ok(writer.bytes_written()) + } + + fn store(this: &DeviceConfig, page: &[u8]) -> Result { + if this.data.lock().powered { + return Err(EBUSY); + } + + let text = core::str::from_utf8(page)?.trim(); + let value = text.parse::().map_err(|_| EINVAL)?; + + GenDiskBuilder::validate_block_size(value)?; + this.data.lock().block_size = value; + Ok(()) + } +} + +#[vtable] +impl configfs::AttributeOperations<2> for DeviceConfig { + type Data = DeviceConfig; + + fn show(this: &DeviceConfig, page: &mut [u8; PAGE_SIZE]) -> Result { + let mut writer = kernel::str::Formatter::new(page); + + if this.data.lock().rotational { + writer.write_str("1\n")?; + } else { + writer.write_str("0\n")?; + } + + Ok(writer.bytes_written()) + } + + fn store(this: &DeviceConfig, page: &[u8]) -> Result { + if this.data.lock().powered { + return Err(EBUSY); + } + + this.data.lock().rotational = kstrtobool_bytes(page)?; + + Ok(()) + } +} + +#[vtable] +impl configfs::AttributeOperations<3> for DeviceConfig { + type Data = DeviceConfig; + + fn show(this: &DeviceConfig, page: &mut [u8; PAGE_SIZE]) -> Result { + let mut writer = kernel::str::Formatter::new(page); + writer.write_fmt(fmt!("{}\n", this.data.lock().capacity_mib))?; + Ok(writer.bytes_written()) + } + + fn store(this: &DeviceConfig, page: &[u8]) -> Result { + if this.data.lock().powered { + return Err(EBUSY); + } + + let text = core::str::from_utf8(page)?.trim(); + let value = text.parse::().map_err(|_| EINVAL)?; + + this.data.lock().capacity_mib = value; + Ok(()) + } +} + +#[vtable] +impl configfs::AttributeOperations<4> for DeviceConfig { + type Data = DeviceConfig; + + fn show(this: &DeviceConfig, page: &mut [u8; PAGE_SIZE]) -> Result { + let mut writer = kernel::str::Formatter::new(page); + writer.write_fmt(fmt!("{}\n", this.data.lock().irq_mode))?; + Ok(writer.bytes_written()) + } + + fn store(this: &DeviceConfig, page: &[u8]) -> Result { + if this.data.lock().powered { + return Err(EBUSY); + } + + let text = core::str::from_utf8(page)?.trim(); + let value = text.parse::().map_err(|_| EINVAL)?; + + this.data.lock().irq_mode = IRQMode::try_from(value)?; + Ok(()) + } +} diff --git a/drivers/block/rnull/rnull.rs b/drivers/block/rnull/rnull.rs new file mode 100644 index 000000000..0ca8715fe --- /dev/null +++ b/drivers/block/rnull/rnull.rs @@ -0,0 +1,100 @@ +// SPDX-License-Identifier: GPL-2.0 + +//! This is a Rust implementation of the C null block driver. + +mod configfs; + +use configfs::IRQMode; +use kernel::{ + block::{ + self, + mq::{ + self, + gen_disk::{self, GenDisk}, + Operations, TagSet, + }, + }, + prelude::*, + sync::{aref::ARef, Arc}, +}; + +module! { + type: NullBlkModule, + name: "rnull_mod", + authors: ["Andreas Hindborg"], + description: "Rust implementation of the C null block driver", + license: "GPL v2", +} + +#[pin_data] +struct NullBlkModule { + #[pin] + configfs_subsystem: kernel::configfs::Subsystem, +} + +impl kernel::InPlaceModule for NullBlkModule { + fn init(_module: &'static ThisModule) -> impl PinInit { + pr_info!("Rust null_blk loaded\n"); + + try_pin_init!(Self { + configfs_subsystem <- configfs::subsystem(), + }) + } +} + +struct NullBlkDevice; + +impl NullBlkDevice { + fn new( + name: &CStr, + block_size: u32, + rotational: bool, + capacity_mib: u64, + irq_mode: IRQMode, + ) -> Result> { + let tagset = Arc::pin_init(TagSet::new(1, 256, 1), GFP_KERNEL)?; + + let queue_data = Box::new(QueueData { irq_mode }, GFP_KERNEL)?; + + gen_disk::GenDiskBuilder::new() + .capacity_sectors(capacity_mib << (20 - block::SECTOR_SHIFT)) + .logical_block_size(block_size)? + .physical_block_size(block_size)? + .rotational(rotational) + .build(fmt!("{}", name.to_str()?), tagset, queue_data) + } +} + +struct QueueData { + irq_mode: IRQMode, +} + +#[vtable] +impl Operations for NullBlkDevice { + type QueueData = KBox; + + #[inline(always)] + fn queue_rq(queue_data: &QueueData, rq: ARef>, _is_last: bool) -> Result { + match queue_data.irq_mode { + IRQMode::None => mq::Request::end_ok(rq) + .map_err(|_e| kernel::error::code::EIO) + // We take no refcounts on the request, so we expect to be able to + // end the request. The request reference must be unique at this + // point, and so `end_ok` cannot fail. + .expect("Fatal error - expected to be able to end request"), + IRQMode::Soft => mq::Request::complete(rq), + } + Ok(()) + } + + fn commit_rqs(_queue_data: &QueueData) {} + + fn complete(rq: ARef>) { + mq::Request::end_ok(rq) + .map_err(|_e| kernel::error::code::EIO) + // We take no refcounts on the request, so we expect to be able to + // end the request. The request reference must be unique at this + // point, and so `end_ok` cannot fail. + .expect("Fatal error - expected to be able to end request"); + } +} -- cgit v1.3.1