aboutsummaryrefslogtreecommitdiff
path: root/lib/libvgl/(public-mirror)
diff options
context:
space:
mode:
authorAlan Cox <alc@FreeBSD.org>2026-08-07 21:51:04 +0000
committerAlan Cox <alc@FreeBSD.org>2026-08-14 20:57:35 +0000
commit6fa9c2b1d2824034268646e0744e5e010155ffaf (patch)
treeb39943ae752499de8d20013550fc5127456e2253 /lib/libvgl/(public-mirror)
parent7753a59fdf196fcbd8bb5706ad44bfc590bce0a9 (diff)
arm64: close a race in SVE register managementHEADmain
While testing an unrelated pmap change, D58708, that dramatically reduces the number of TLBI instructions performed, and likely the timing of unrelated events, I started seeing "Storing an invalid VFP state" panics in vfp_save_state_common(). However, the origin of this panic is elsewhere, in the else branch of sve_restore_state(). Specifically, my pmap change seems to have increased the likelihood that the thread executing the else branch would be preempted by another thread between the critical_exit() inside the else branch's call to vfp_restore_state_common() and its own call to critical_enter(). Prior to expanding the scope of the else branch's critical section, the MPASS added by this change would fire, catching the problem at its source, rather than later in vfp_save_state_common(). Assisted-by: Claude Code (Opus 5) Reviewed by: kib, markj MFC after: 1 week Differential Revision: https://reviews.freebsd.org/D58723
Diffstat (limited to 'lib/libvgl/(public-mirror)')
0 files changed, 0 insertions, 0 deletions