summaryrefslogtreecommitdiffstats
path: root/Documentation/driver-api/index.rst
diff options
context:
space:
mode:
authorTim Chen <tim.c.chen@linux.intel.com>2026-09-21 17:37:22 -0700
committerIngo Molnar <mingo@kernel.org>2026-09-22 10:49:53 +0200
commit0d6526f82c3cdefcca47f73f5fc08dc6f335eac6 (patch)
tree176dc2d685debcfb082c151ee94f2425ac96b364 /Documentation/driver-api/index.rst
downloadlinux-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.rst152
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