summaryrefslogtreecommitdiffstats
path: root/lib/mpi/mpi-sub-ui.c
diff options
context:
space:
mode:
authorLi RongQing <lirongqing@baidu.com>2021-07-27 19:12:47 +0800
committerPaolo Bonzini <pbonzini@redhat.com>2021-07-27 16:59:01 -0400
commit74775654332b2682a5580d6f954e5a9ac81e7477 (patch)
tree36e5a720e26b554856d3db47524f2369c8bd2d6a /lib/mpi/mpi-sub-ui.c
parent5868b8225ecef4ba3f5b17e65984d60bc5fd6254 (diff)
downloadlinux-stable-74775654332b2682a5580d6f954e5a9ac81e7477.tar.gz
linux-stable-74775654332b2682a5580d6f954e5a9ac81e7477.tar.bz2
linux-stable-74775654332b2682a5580d6f954e5a9ac81e7477.zip
KVM: use cpu_relax when halt polling
SMT siblings share caches and other hardware, and busy halt polling will degrade its sibling performance if its sibling is working Sean Christopherson suggested as below: "Rather than disallowing halt-polling entirely, on x86 it should be sufficient to simply have the hardware thread yield to its sibling(s) via PAUSE. It probably won't get back all performance, but I would expect it to be close. This compiles on all KVM architectures, and AFAICT the intended usage of cpu_relax() is identical for all architectures." Suggested-by: Sean Christopherson <seanjc@google.com> Signed-off-by: Li RongQing <lirongqing@baidu.com> Message-Id: <20210727111247.55510-1-lirongqing@baidu.com> Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Diffstat (limited to 'lib/mpi/mpi-sub-ui.c')
0 files changed, 0 insertions, 0 deletions