tjh.dev / kernel
Linux kernel mirror (for testing) git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
kernel os linux
1
fork

Configure Feed

Select the types of activity you want to include in your feed.

sched: Fix some typos in include/linux/preempt.h

There are some typos in the comments of migrate in
include/linux/preempt.h:

elegible -> eligible
it's -> its
migirate_disable -> migrate_disable
abritrary -> arbitrary

Just fix them.

Signed-off-by: Menglong Dong <dongml2@chinatelecom.cn>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>

authored by

Menglong Dong and committed by
Peter Zijlstra 45b7f780 378b7708

+4 -4
+4 -4
include/linux/preempt.h
··· 372 372 /* 373 373 * Migrate-Disable and why it is undesired. 374 374 * 375 - * When a preempted task becomes elegible to run under the ideal model (IOW it 375 + * When a preempted task becomes eligible to run under the ideal model (IOW it 376 376 * becomes one of the M highest priority tasks), it might still have to wait 377 377 * for the preemptee's migrate_disable() section to complete. Thereby suffering 378 378 * a reduction in bandwidth in the exact duration of the migrate_disable() ··· 387 387 * - a lower priority tasks; which under preempt_disable() could've instantly 388 388 * migrated away when another CPU becomes available, is now constrained 389 389 * by the ability to push the higher priority task away, which might itself be 390 - * in a migrate_disable() section, reducing it's available bandwidth. 390 + * in a migrate_disable() section, reducing its available bandwidth. 391 391 * 392 392 * IOW it trades latency / moves the interference term, but it stays in the 393 393 * system, and as long as it remains unbounded, the system is not fully ··· 399 399 * PREEMPT_RT breaks a number of assumptions traditionally held. By forcing a 400 400 * number of primitives into becoming preemptible, they would also allow 401 401 * migration. This turns out to break a bunch of per-cpu usage. To this end, 402 - * all these primitives employ migirate_disable() to restore this implicit 402 + * all these primitives employ migrate_disable() to restore this implicit 403 403 * assumption. 404 404 * 405 405 * This is a 'temporary' work-around at best. The correct solution is getting ··· 407 407 * per-cpu locking or short preempt-disable regions. 408 408 * 409 409 * The end goal must be to get rid of migrate_disable(), alternatively we need 410 - * a schedulability theory that does not depend on abritrary migration. 410 + * a schedulability theory that does not depend on arbitrary migration. 411 411 * 412 412 * 413 413 * Notes on the implementation.