From 0d6526f82c3cdefcca47f73f5fc08dc6f335eac6 Mon Sep 17 00:00:00 2001 From: Tim Chen Date: Mon, 21 Sep 2026 17:37:22 -0700 Subject: sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling bug alb_break_llc() decides whether to break LLC preference during active load balance. It does so by testing that every runnable fair task on the source rq prefers its LLC: env->src_rq->nr_pref_llc_running == env->src_rq->cfs.h_nr_runnable But the two counters cover different sets. nr_pref_llc_running is updated in account_llc_enqueue()/account_llc_dequeue(), next to cfs_rq->nr_queued, so it follows queued tasks. h_nr_runnable is updated in set_delayed()/ clear_delayed() and drops delay-dequeued tasks. So under DELAY_DEQUEUE, a preferring task that goes to sleep stays counted in nr_pref_llc_running while h_nr_runnable falls. The equality then breaks, alb_break_llc() returns false, and active balance is free to pull a task off its preferred LLC. Active balance only moves runnable tasks, and this is the only LLC check it consults: once the stopper runs, LBF_ACTIVE_LB skips the per-task test in can_migrate_task(). The runnable set is the one we want. Fix it on the counter side. A task should be counted in nr_pref_llc_running exactly while it is both queued on its preferred LLC (pref_llc_queued) and runnable (!sched_delayed). Define that membership once in task_pref_llc_runnable(), and adjust the counter only through pref_llc_running_inc()/pref_llc_running_dec() from the four sites that change either input: account_llc_enqueue(), account_llc_dequeue(), set_delayed() and clear_delayed(). Gating every update on the same predicate keeps the delay, wake and dequeue paths from double-counting or underflowing; see the comments at those sites for the ordering. nr_llc_running and sd->llc_counts are not touched and stay on queued semantics. Fixes: 714059f79ff0 ("sched/cache: Handle moving single tasks to/from their preferred LLC") Closes: https://lore.kernel.org/lkml/20260827135000.735138-1-zhanxusheng@xiaomi.com/ Reported-by: Zhan Xusheng Suggested-by: Chen Yu Signed-off-by: Tim Chen Signed-off-by: Peter Zijlstra (Intel) Signed-off-by: Ingo Molnar Reviewed-by: Kayra Cizmeci Cc: # v7.2.x Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com --- drivers/block/rnull/configfs.rs | 261 ++++++++++++++++++++++++++++++++++++++++ 1 file changed, 261 insertions(+) create mode 100644 drivers/block/rnull/configfs.rs (limited to 'drivers/block/rnull/configfs.rs') diff --git a/drivers/block/rnull/configfs.rs b/drivers/block/rnull/configfs.rs new file mode 100644 index 000000000..32c10c3f4 --- /dev/null +++ b/drivers/block/rnull/configfs.rs @@ -0,0 +1,261 @@ +// SPDX-License-Identifier: GPL-2.0 + +use super::NullBlkDevice; +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(()) + } +} -- cgit v1.3.1