diff options
| author | Tim Chen <tim.c.chen@linux.intel.com> | 2026-09-21 17:37:22 -0700 |
|---|---|---|
| committer | Ingo Molnar <mingo@kernel.org> | 2026-09-22 10:49:53 +0200 |
| commit | 0d6526f82c3cdefcca47f73f5fc08dc6f335eac6 (patch) | |
| tree | 176dc2d685debcfb082c151ee94f2425ac96b364 /Documentation/driver-api/index.rst | |
| download | linux-stable-0d6526f82c3cdefcca47f73f5fc08dc6f335eac6.tar.gz linux-stable-0d6526f82c3cdefcca47f73f5fc08dc6f335eac6.zip | |
sched/cache: Keep nr_pref_llc_running in the runnable domain, to fix LLC mis-scheduling buggrafted
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 <zhanxusheng@xiaomi.com>
Suggested-by: Chen Yu <yu.c.chen@intel.com>
Signed-off-by: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Kayra Cizmeci <kayracizmeci@gmail.com>
Cc: <stable@kernel.org> # v7.2.x
Link: https://patch.msgid.link/06af61afedac32e6477f57feb4d658f6c411c3af.1790035273.git.tim.c.chen@linux.intel.com
Diffstat (limited to 'Documentation/driver-api/index.rst')
| -rw-r--r-- | Documentation/driver-api/index.rst | 152 |
1 files changed, 152 insertions, 0 deletions
diff --git a/Documentation/driver-api/index.rst b/Documentation/driver-api/index.rst new file mode 100644 index 000000000..6601a2586 --- /dev/null +++ b/Documentation/driver-api/index.rst @@ -0,0 +1,152 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============================== +Driver implementer's API guide +============================== + +The kernel offers a wide variety of interfaces to support the development +of device drivers. This document is an only somewhat organized collection +of some of those interfaces — it will hopefully get better over time! The +available subsections can be seen below. + + +General information for driver authors +====================================== + +This section contains documentation that should, at some point or other, be +of interest to most developers working on device drivers. + +.. toctree:: + :maxdepth: 1 + + basics + driver-model/index + device_link + infrastructure + ioctl + pm/index + +Useful support libraries +======================== + +This section contains documentation that should, at some point or other, be +of interest to most developers working on device drivers. + +.. toctree:: + :maxdepth: 1 + + early-userspace/index + connector + device-io + devfreq + dma-buf + component + io-mapping + io_ordering + uio-howto + vfio-mediated-device + vfio + vfio-pci-device-specific-driver-acceptance + +Bus-level documentation +======================= + +.. toctree:: + :maxdepth: 1 + + auxiliary_bus + cxl/index + eisa + firewire + i3c/index + isa + men-chameleon-bus + pci/index + rapidio/index + slimbus + usb/index + virtio/index + vme + w1 + xillybus + + +Subsystem-specific APIs +======================= + +.. toctree:: + :maxdepth: 1 + + 80211/index + acpi/index + backlight/lp855x-driver.rst + clk + coco/index + console + crypto/index + dmaengine/index + dpll + edac + extcon + firmware/index + fpga/index + frame-buffer + aperture + generic-counter + generic_pt + gpio/index + hsi + hte/index + hw-recoverable-errors + i2c + iio/index + infiniband + input + interconnect + ipmb + ipmi + issei/index + libata + mailbox + md/index + media/index + mei/index + memory-devices/index + message-based + misc_devices + miscellaneous + mmc/index + mtd/index + mtdnand + nfc/index + ntb + nvdimm/index + nvmem + parport-lowlevel + phy/index + pin-control + pldmfw/index + pps + ptp + pwm + pwrseq + regulator + reset + rfkill + s390-drivers + scsi + serial/index + sm501 + soundwire/index + spi + surface_aggregator/index + switchtec + sync_file + target + tee + thermal/index + tty/index + wbrf + wmi + xilinx/index + zorro |
