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 /samples/kobject/kobject-example.c | |
| 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 'samples/kobject/kobject-example.c')
| -rw-r--r-- | samples/kobject/kobject-example.c | 145 |
1 files changed, 145 insertions, 0 deletions
diff --git a/samples/kobject/kobject-example.c b/samples/kobject/kobject-example.c new file mode 100644 index 000000000..36f3fbc47 --- /dev/null +++ b/samples/kobject/kobject-example.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Sample kobject implementation + * + * Copyright (C) 2004-2007 Greg Kroah-Hartman <greg@kroah.com> + * Copyright (C) 2007 Novell Inc. + */ +#include <linux/kobject.h> +#include <linux/string.h> +#include <linux/sysfs.h> +#include <linux/module.h> +#include <linux/init.h> + +/* + * This module shows how to create a simple subdirectory in sysfs called + * /sys/kernel/kobject_example In that directory, 3 files are created: + * "foo", "baz", and "bar". If an integer is written to these files, it can be + * later read out of it. + */ + +static int foo; +static int baz; +static int bar; + +/* + * The "foo" file where a static variable is read from and written to. + */ +static ssize_t foo_show(struct kobject *kobj, const struct kobj_attribute *attr, + char *buf) +{ + return sysfs_emit(buf, "%d\n", foo); +} + +static ssize_t foo_store(struct kobject *kobj, const struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int ret; + + ret = kstrtoint(buf, 10, &foo); + if (ret < 0) + return ret; + + return count; +} + +/* Sysfs attributes cannot be world-writable. */ +static const struct kobj_attribute foo_attribute = + __KOBJ_ATTR(foo, 0664, foo_show, foo_store); + +/* + * More complex function where we determine which variable is being accessed by + * looking at the attribute for the "baz" and "bar" files. + */ +static ssize_t b_show(struct kobject *kobj, const struct kobj_attribute *attr, + char *buf) +{ + int var; + + if (strcmp(attr->attr.name, "baz") == 0) + var = baz; + else + var = bar; + return sysfs_emit(buf, "%d\n", var); +} + +static ssize_t b_store(struct kobject *kobj, const struct kobj_attribute *attr, + const char *buf, size_t count) +{ + int var, ret; + + ret = kstrtoint(buf, 10, &var); + if (ret < 0) + return ret; + + if (strcmp(attr->attr.name, "baz") == 0) + baz = var; + else + bar = var; + return count; +} + +static const struct kobj_attribute baz_attribute = + __KOBJ_ATTR(baz, 0664, b_show, b_store); +static const struct kobj_attribute bar_attribute = + __KOBJ_ATTR(bar, 0664, b_show, b_store); + + +/* + * Create a group of attributes so that we can create and destroy them all + * at once. + */ +static const struct attribute *const attrs[] = { + &foo_attribute.attr, + &baz_attribute.attr, + &bar_attribute.attr, + NULL, /* need to NULL terminate the list of attributes */ +}; + +/* + * An unnamed attribute group will put all of the attributes directly in + * the kobject directory. If we specify a name, a subdirectory will be + * created for the attributes with the directory being the name of the + * attribute group. + */ +static const struct attribute_group attr_group = { + .attrs_const = attrs, +}; + +static struct kobject *example_kobj; + +static int __init example_init(void) +{ + int retval; + + /* + * Create a simple kobject with the name of "kobject_example", + * located under /sys/kernel/ + * + * As this is a simple directory, no uevent will be sent to + * userspace. That is why this function should not be used for + * any type of dynamic kobjects, where the name and number are + * not known ahead of time. + */ + example_kobj = kobject_create_and_add("kobject_example", kernel_kobj); + if (!example_kobj) + return -ENOMEM; + + /* Create the files associated with this kobject */ + retval = sysfs_create_group(example_kobj, &attr_group); + if (retval) + kobject_put(example_kobj); + + return retval; +} + +static void __exit example_exit(void) +{ + kobject_put(example_kobj); +} + +module_init(example_init); +module_exit(example_exit); +MODULE_DESCRIPTION("Sample kobject implementation"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Greg Kroah-Hartman <greg@kroah.com>"); |
