kvm: x86: protect masterclock with a seqcount

Browse source

Protect the reference point for kvmclock with a seqcount, so that
kvmclock updates for all vCPUs can proceed in parallel.  Xen runstate
updates will also run in parallel and not bounce the kvmclock cacheline.

Of the variables that were protected by pvclock_gtod_sync_lock,
nr_vcpus_matched_tsc is different because it is updated outside
pvclock_update_vm_gtod_copy and read inside it.  Therefore, we
need to keep it protected by a spinlock.  In fact it must now
be a raw spinlock, because pvclock_update_vm_gtod_copy, being the
write-side of a seqcount, is non-preemptible.  Since we already
have tsc_write_lock which is a raw spinlock, we can just use
tsc_write_lock as the lock that protects the write-side of the
seqcount.

Co-developed-by: Oliver Upton <oupton@google.com>
Message-Id: <20210916181538.968978-6-oupton@google.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>

...

This commit is contained in:

Paolo Bonzini 2021-09-16 18:15:36 +00:00

parent c68dc1b577

commit 869b44211a

2 changed files with 51 additions and 38 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download patch file Download diff file Expand all files Collapse all files

7

arch/x86/include/asm/kvm_host.h

View file

82

arch/x86/kvm/x86.c

View file