Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Thu, Mar 26, 2015 at 04:28:37PM -0700, Andy Lutomirski wrote: > On Thu, Mar 26, 2015 at 4:22 PM, Marcelo Tosatti wrote: > > On Thu, Mar 26, 2015 at 04:09:53PM -0700, Andy Lutomirski wrote: > >> On Thu, Mar 26, 2015 at 3:56 PM, Marcelo Tosatti > >> wrote: > >> > On Thu, Mar 26, 2015 at 01:58:25PM -0700, Andy Lutomirski wrote: > >> >> On Thu, Mar 26, 2015 at 1:31 PM, Radim Krcmar > >> >> wrote: > >> >> > 2015-03-26 11:51-0700, Andy Lutomirski: > >> >> >> On Thu, Mar 26, 2015 at 4:29 AM, Marcelo Tosatti > >> >> >> wrote: > >> >> >> > On Wed, Mar 25, 2015 at 04:22:03PM -0700, Andy Lutomirski wrote: > >> >> >> >> Suppose we start out with all vcpus agreeing on their pvti and > >> >> >> >> perfect > >> >> >> >> invariant TSCs. Now the host updates its frequency (due to NTP or > >> >> >> >> whatever). KVM updates vcpu 0's pvti. Before KVM updates vcpu > >> >> >> >> 1's > >> >> >> >> pvti, guest code on vcpus 0 and 1 see synced TSCs but different > >> >> >> >> pvti. > >> >> >> >> They'll disagree on the time, and one of them will be ahead until > >> >> >> >> vcpu > >> >> >> >> 1's pvti gets updated. > >> >> >> > > >> >> >> > The masterclock scheme enforces the same > >> >> >> > system_timestamp/tsc_timestamp pairs > >> >> >> > to be visible at one time, for all vcpus. > >> >> >> > > >> >> >> > > >> >> >> > * That is, when timespec0 != timespec1, M < N. Unfortunately that > >> >> >> > is > >> >> >> > * not > >> >> >> > * always the case (the difference between two distinct xtime > >> >> >> > instances > >> >> >> > * might be smaller then the difference between corresponding TSC > >> >> >> > reads, > >> >> >> > * when updating guest vcpus pvclock areas). > >> >> >> > * > >> >> >> > * To avoid that problem, do not allow visibility of distinct > >> >> >> > * system_timestamp/tsc_timestamp values simultaneously: use a > >> >> >> > master > >> >> >> > * copy of host monotonic time values. Update that master copy > >> >> >> > * in lockstep. > >> >> >> > >> >> >> Yuck. So we have per cpu timing data, but the protocol is only > >> >> >> usable > >> >> >> for monotonic timing because we forcibly freeze all vcpus when we > >> >> >> update the nominally per cpu data. > >> >> >> > >> >> >> The obvious guest implementations are still unnecessarily slow, > >> >> >> though. It would be nice if the guest could get away without using > >> >> >> any getcpu operation at all. > >> >> >> > >> >> >> Even if we fixed the host to increment version as advertised, I think > >> >> >> we can't avoid two getcpu ops. We need one before rdtsc to figure > >> >> >> out > >> >> >> which pvti to look at, > >> >> > > >> >> > Yes. > >> >> > > >> >> >>and we need another to make sure that we were > >> >> >> actually on that cpu at the time we did rdtsc. (Rdtscp doesn't help > >> >> >> -- we need to check version before rdtsc, and we don't know what > >> >> >> version to check until we do a getcpu.). > >> >> > > >> >> > Exactly, reading cpuid after rdtsc doesn't do that though, we could > >> >> > have > >> >> > migrated back between those reads. > >> >> > rtdscp would allow us to check that we read tsc of pvti's cpu. > >> >> > (It doesn't get rid of that first read.) > >> >> > > >> >> >> The migration hook has the > >> >> >> same issue -- we need to check the migration count, then confirm > >> >> >> we're > >> >> >> on that cpu, then check the migration count again, and we can't do > >> >> >> that until we know what cpu we're on. > >> >> > > >> >> > True; the revert has a bug -- we need to check cpuid for the second > >> >> > time before rdtsc. (Migration hook is there just because we don't > >> >> > know > >> >> > which cpu executed rdtsc.) > >> >> > >> >> One way or another, I'm planning on completely rewriting the vdso > >> >> code. An early draft is here: > >> >> > >> >> https://git.kernel.org/cgit/linux/kernel/git/luto/linux.git/commit/?h=x86/vdso&id=57ace6e6e032afc4faf7b9ec52f78a8e6642c980 > >> >> > >> >> but I can't finish it until the KVM side shakes out. > >> >> > >> >> I think there are at least two ways that would work: > >> >> > >> >> a) If KVM incremented version as advertised: > >> > > >> > All for it. > >> > > >> >> cpu = getcpu(); > >> >> pvti = pvti for cpu; > >> >> > >> >> ver1 = pvti->version; > >> >> check stable bit; > >> >> rdtsc_barrier, rdtsc, read scale, shift, etc. > >> >> if (getcpu() != cpu) retry; > >> >> if (pvti->version != ver1) retry; > >> >> > >> >> I think this is safe because, we're guaranteed that there was an > >> >> interval (between the two version reads) in which the vcpu we think > >> >> we're on was running and the kvmclock data was valid and marked > >> >> stable, and we know that the tsc we read came from that interval. > >> >> > >> >> Note: rdtscp isn't needed. If we're stable, is makes no difference > >> >> which cpu's tsc we actually read. > >> > > >> > Yes, can't see a problem with that. > >> > > >
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Thu, Mar 26, 2015 at 4:22 PM, Marcelo Tosatti wrote: > On Thu, Mar 26, 2015 at 04:09:53PM -0700, Andy Lutomirski wrote: >> On Thu, Mar 26, 2015 at 3:56 PM, Marcelo Tosatti wrote: >> > On Thu, Mar 26, 2015 at 01:58:25PM -0700, Andy Lutomirski wrote: >> >> On Thu, Mar 26, 2015 at 1:31 PM, Radim Krcmar wrote: >> >> > 2015-03-26 11:51-0700, Andy Lutomirski: >> >> >> On Thu, Mar 26, 2015 at 4:29 AM, Marcelo Tosatti >> >> >> wrote: >> >> >> > On Wed, Mar 25, 2015 at 04:22:03PM -0700, Andy Lutomirski wrote: >> >> >> >> Suppose we start out with all vcpus agreeing on their pvti and >> >> >> >> perfect >> >> >> >> invariant TSCs. Now the host updates its frequency (due to NTP or >> >> >> >> whatever). KVM updates vcpu 0's pvti. Before KVM updates vcpu 1's >> >> >> >> pvti, guest code on vcpus 0 and 1 see synced TSCs but different >> >> >> >> pvti. >> >> >> >> They'll disagree on the time, and one of them will be ahead until >> >> >> >> vcpu >> >> >> >> 1's pvti gets updated. >> >> >> > >> >> >> > The masterclock scheme enforces the same >> >> >> > system_timestamp/tsc_timestamp pairs >> >> >> > to be visible at one time, for all vcpus. >> >> >> > >> >> >> > >> >> >> > * That is, when timespec0 != timespec1, M < N. Unfortunately that is >> >> >> > * not >> >> >> > * always the case (the difference between two distinct xtime >> >> >> > instances >> >> >> > * might be smaller then the difference between corresponding TSC >> >> >> > reads, >> >> >> > * when updating guest vcpus pvclock areas). >> >> >> > * >> >> >> > * To avoid that problem, do not allow visibility of distinct >> >> >> > * system_timestamp/tsc_timestamp values simultaneously: use a master >> >> >> > * copy of host monotonic time values. Update that master copy >> >> >> > * in lockstep. >> >> >> >> >> >> Yuck. So we have per cpu timing data, but the protocol is only usable >> >> >> for monotonic timing because we forcibly freeze all vcpus when we >> >> >> update the nominally per cpu data. >> >> >> >> >> >> The obvious guest implementations are still unnecessarily slow, >> >> >> though. It would be nice if the guest could get away without using >> >> >> any getcpu operation at all. >> >> >> >> >> >> Even if we fixed the host to increment version as advertised, I think >> >> >> we can't avoid two getcpu ops. We need one before rdtsc to figure out >> >> >> which pvti to look at, >> >> > >> >> > Yes. >> >> > >> >> >>and we need another to make sure that we were >> >> >> actually on that cpu at the time we did rdtsc. (Rdtscp doesn't help >> >> >> -- we need to check version before rdtsc, and we don't know what >> >> >> version to check until we do a getcpu.). >> >> > >> >> > Exactly, reading cpuid after rdtsc doesn't do that though, we could have >> >> > migrated back between those reads. >> >> > rtdscp would allow us to check that we read tsc of pvti's cpu. >> >> > (It doesn't get rid of that first read.) >> >> > >> >> >> The migration hook has the >> >> >> same issue -- we need to check the migration count, then confirm we're >> >> >> on that cpu, then check the migration count again, and we can't do >> >> >> that until we know what cpu we're on. >> >> > >> >> > True; the revert has a bug -- we need to check cpuid for the second >> >> > time before rdtsc. (Migration hook is there just because we don't know >> >> > which cpu executed rdtsc.) >> >> >> >> One way or another, I'm planning on completely rewriting the vdso >> >> code. An early draft is here: >> >> >> >> https://git.kernel.org/cgit/linux/kernel/git/luto/linux.git/commit/?h=x86/vdso&id=57ace6e6e032afc4faf7b9ec52f78a8e6642c980 >> >> >> >> but I can't finish it until the KVM side shakes out. >> >> >> >> I think there are at least two ways that would work: >> >> >> >> a) If KVM incremented version as advertised: >> > >> > All for it. >> > >> >> cpu = getcpu(); >> >> pvti = pvti for cpu; >> >> >> >> ver1 = pvti->version; >> >> check stable bit; >> >> rdtsc_barrier, rdtsc, read scale, shift, etc. >> >> if (getcpu() != cpu) retry; >> >> if (pvti->version != ver1) retry; >> >> >> >> I think this is safe because, we're guaranteed that there was an >> >> interval (between the two version reads) in which the vcpu we think >> >> we're on was running and the kvmclock data was valid and marked >> >> stable, and we know that the tsc we read came from that interval. >> >> >> >> Note: rdtscp isn't needed. If we're stable, is makes no difference >> >> which cpu's tsc we actually read. >> > >> > Yes, can't see a problem with that. >> > >> >> b) If version remains buggy but we use this migrations_from hack: >> > >> > There is no reason for version to remain buggy. >> > >> >> cpu = getcpu(); >> >> pvti = pvti for cpu; >> >> m1 = pvti->migrations_from; >> >> barrier(); >> >> >> >> ver1 = pvti->version; >> >> check stable bit; >> >> rdtsc_barrier, rdtsc, read scale, shift, etc. >> >> if (getcpu() != cpu) retry; >> >> if
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Thu, Mar 26, 2015 at 04:09:53PM -0700, Andy Lutomirski wrote: > On Thu, Mar 26, 2015 at 3:56 PM, Marcelo Tosatti wrote: > > On Thu, Mar 26, 2015 at 01:58:25PM -0700, Andy Lutomirski wrote: > >> On Thu, Mar 26, 2015 at 1:31 PM, Radim Krcmar wrote: > >> > 2015-03-26 11:51-0700, Andy Lutomirski: > >> >> On Thu, Mar 26, 2015 at 4:29 AM, Marcelo Tosatti > >> >> wrote: > >> >> > On Wed, Mar 25, 2015 at 04:22:03PM -0700, Andy Lutomirski wrote: > >> >> >> Suppose we start out with all vcpus agreeing on their pvti and > >> >> >> perfect > >> >> >> invariant TSCs. Now the host updates its frequency (due to NTP or > >> >> >> whatever). KVM updates vcpu 0's pvti. Before KVM updates vcpu 1's > >> >> >> pvti, guest code on vcpus 0 and 1 see synced TSCs but different pvti. > >> >> >> They'll disagree on the time, and one of them will be ahead until > >> >> >> vcpu > >> >> >> 1's pvti gets updated. > >> >> > > >> >> > The masterclock scheme enforces the same > >> >> > system_timestamp/tsc_timestamp pairs > >> >> > to be visible at one time, for all vcpus. > >> >> > > >> >> > > >> >> > * That is, when timespec0 != timespec1, M < N. Unfortunately that is > >> >> > * not > >> >> > * always the case (the difference between two distinct xtime > >> >> > instances > >> >> > * might be smaller then the difference between corresponding TSC > >> >> > reads, > >> >> > * when updating guest vcpus pvclock areas). > >> >> > * > >> >> > * To avoid that problem, do not allow visibility of distinct > >> >> > * system_timestamp/tsc_timestamp values simultaneously: use a master > >> >> > * copy of host monotonic time values. Update that master copy > >> >> > * in lockstep. > >> >> > >> >> Yuck. So we have per cpu timing data, but the protocol is only usable > >> >> for monotonic timing because we forcibly freeze all vcpus when we > >> >> update the nominally per cpu data. > >> >> > >> >> The obvious guest implementations are still unnecessarily slow, > >> >> though. It would be nice if the guest could get away without using > >> >> any getcpu operation at all. > >> >> > >> >> Even if we fixed the host to increment version as advertised, I think > >> >> we can't avoid two getcpu ops. We need one before rdtsc to figure out > >> >> which pvti to look at, > >> > > >> > Yes. > >> > > >> >>and we need another to make sure that we were > >> >> actually on that cpu at the time we did rdtsc. (Rdtscp doesn't help > >> >> -- we need to check version before rdtsc, and we don't know what > >> >> version to check until we do a getcpu.). > >> > > >> > Exactly, reading cpuid after rdtsc doesn't do that though, we could have > >> > migrated back between those reads. > >> > rtdscp would allow us to check that we read tsc of pvti's cpu. > >> > (It doesn't get rid of that first read.) > >> > > >> >> The migration hook has the > >> >> same issue -- we need to check the migration count, then confirm we're > >> >> on that cpu, then check the migration count again, and we can't do > >> >> that until we know what cpu we're on. > >> > > >> > True; the revert has a bug -- we need to check cpuid for the second > >> > time before rdtsc. (Migration hook is there just because we don't know > >> > which cpu executed rdtsc.) > >> > >> One way or another, I'm planning on completely rewriting the vdso > >> code. An early draft is here: > >> > >> https://git.kernel.org/cgit/linux/kernel/git/luto/linux.git/commit/?h=x86/vdso&id=57ace6e6e032afc4faf7b9ec52f78a8e6642c980 > >> > >> but I can't finish it until the KVM side shakes out. > >> > >> I think there are at least two ways that would work: > >> > >> a) If KVM incremented version as advertised: > > > > All for it. > > > >> cpu = getcpu(); > >> pvti = pvti for cpu; > >> > >> ver1 = pvti->version; > >> check stable bit; > >> rdtsc_barrier, rdtsc, read scale, shift, etc. > >> if (getcpu() != cpu) retry; > >> if (pvti->version != ver1) retry; > >> > >> I think this is safe because, we're guaranteed that there was an > >> interval (between the two version reads) in which the vcpu we think > >> we're on was running and the kvmclock data was valid and marked > >> stable, and we know that the tsc we read came from that interval. > >> > >> Note: rdtscp isn't needed. If we're stable, is makes no difference > >> which cpu's tsc we actually read. > > > > Yes, can't see a problem with that. > > > >> b) If version remains buggy but we use this migrations_from hack: > > > > There is no reason for version to remain buggy. > > > >> cpu = getcpu(); > >> pvti = pvti for cpu; > >> m1 = pvti->migrations_from; > >> barrier(); > >> > >> ver1 = pvti->version; > >> check stable bit; > >> rdtsc_barrier, rdtsc, read scale, shift, etc. > >> if (getcpu() != cpu) retry; > >> if (pvti->version != ver1) retry; /* probably not really needed */ > >> > >> barrier(); > >> if (pvti->migrations_from != m1) retry; > >> > >> This is just like (a), except that we're usi
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Thu, Mar 26, 2015 at 3:56 PM, Marcelo Tosatti wrote: > On Thu, Mar 26, 2015 at 01:58:25PM -0700, Andy Lutomirski wrote: >> On Thu, Mar 26, 2015 at 1:31 PM, Radim Krcmar wrote: >> > 2015-03-26 11:51-0700, Andy Lutomirski: >> >> On Thu, Mar 26, 2015 at 4:29 AM, Marcelo Tosatti >> >> wrote: >> >> > On Wed, Mar 25, 2015 at 04:22:03PM -0700, Andy Lutomirski wrote: >> >> >> Suppose we start out with all vcpus agreeing on their pvti and perfect >> >> >> invariant TSCs. Now the host updates its frequency (due to NTP or >> >> >> whatever). KVM updates vcpu 0's pvti. Before KVM updates vcpu 1's >> >> >> pvti, guest code on vcpus 0 and 1 see synced TSCs but different pvti. >> >> >> They'll disagree on the time, and one of them will be ahead until vcpu >> >> >> 1's pvti gets updated. >> >> > >> >> > The masterclock scheme enforces the same system_timestamp/tsc_timestamp >> >> > pairs >> >> > to be visible at one time, for all vcpus. >> >> > >> >> > >> >> > * That is, when timespec0 != timespec1, M < N. Unfortunately that is >> >> > * not >> >> > * always the case (the difference between two distinct xtime instances >> >> > * might be smaller then the difference between corresponding TSC reads, >> >> > * when updating guest vcpus pvclock areas). >> >> > * >> >> > * To avoid that problem, do not allow visibility of distinct >> >> > * system_timestamp/tsc_timestamp values simultaneously: use a master >> >> > * copy of host monotonic time values. Update that master copy >> >> > * in lockstep. >> >> >> >> Yuck. So we have per cpu timing data, but the protocol is only usable >> >> for monotonic timing because we forcibly freeze all vcpus when we >> >> update the nominally per cpu data. >> >> >> >> The obvious guest implementations are still unnecessarily slow, >> >> though. It would be nice if the guest could get away without using >> >> any getcpu operation at all. >> >> >> >> Even if we fixed the host to increment version as advertised, I think >> >> we can't avoid two getcpu ops. We need one before rdtsc to figure out >> >> which pvti to look at, >> > >> > Yes. >> > >> >>and we need another to make sure that we were >> >> actually on that cpu at the time we did rdtsc. (Rdtscp doesn't help >> >> -- we need to check version before rdtsc, and we don't know what >> >> version to check until we do a getcpu.). >> > >> > Exactly, reading cpuid after rdtsc doesn't do that though, we could have >> > migrated back between those reads. >> > rtdscp would allow us to check that we read tsc of pvti's cpu. >> > (It doesn't get rid of that first read.) >> > >> >> The migration hook has the >> >> same issue -- we need to check the migration count, then confirm we're >> >> on that cpu, then check the migration count again, and we can't do >> >> that until we know what cpu we're on. >> > >> > True; the revert has a bug -- we need to check cpuid for the second >> > time before rdtsc. (Migration hook is there just because we don't know >> > which cpu executed rdtsc.) >> >> One way or another, I'm planning on completely rewriting the vdso >> code. An early draft is here: >> >> https://git.kernel.org/cgit/linux/kernel/git/luto/linux.git/commit/?h=x86/vdso&id=57ace6e6e032afc4faf7b9ec52f78a8e6642c980 >> >> but I can't finish it until the KVM side shakes out. >> >> I think there are at least two ways that would work: >> >> a) If KVM incremented version as advertised: > > All for it. > >> cpu = getcpu(); >> pvti = pvti for cpu; >> >> ver1 = pvti->version; >> check stable bit; >> rdtsc_barrier, rdtsc, read scale, shift, etc. >> if (getcpu() != cpu) retry; >> if (pvti->version != ver1) retry; >> >> I think this is safe because, we're guaranteed that there was an >> interval (between the two version reads) in which the vcpu we think >> we're on was running and the kvmclock data was valid and marked >> stable, and we know that the tsc we read came from that interval. >> >> Note: rdtscp isn't needed. If we're stable, is makes no difference >> which cpu's tsc we actually read. > > Yes, can't see a problem with that. > >> b) If version remains buggy but we use this migrations_from hack: > > There is no reason for version to remain buggy. > >> cpu = getcpu(); >> pvti = pvti for cpu; >> m1 = pvti->migrations_from; >> barrier(); >> >> ver1 = pvti->version; >> check stable bit; >> rdtsc_barrier, rdtsc, read scale, shift, etc. >> if (getcpu() != cpu) retry; >> if (pvti->version != ver1) retry; /* probably not really needed */ >> >> barrier(); >> if (pvti->migrations_from != m1) retry; >> >> This is just like (a), except that we're using a guest kernel hack to >> ensure that no one migrated off the vcpu during the version-protected >> critical section and that we were, in fact, on that vcpu at some point >> during that critical section. Once we've ensured that we were on >> pvti's associated vcpu for the entire time we were reading it, then we >> are protected by the
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Thu, Mar 26, 2015 at 01:58:25PM -0700, Andy Lutomirski wrote: > On Thu, Mar 26, 2015 at 1:31 PM, Radim Krcmar wrote: > > 2015-03-26 11:51-0700, Andy Lutomirski: > >> On Thu, Mar 26, 2015 at 4:29 AM, Marcelo Tosatti > >> wrote: > >> > On Wed, Mar 25, 2015 at 04:22:03PM -0700, Andy Lutomirski wrote: > >> >> Suppose we start out with all vcpus agreeing on their pvti and perfect > >> >> invariant TSCs. Now the host updates its frequency (due to NTP or > >> >> whatever). KVM updates vcpu 0's pvti. Before KVM updates vcpu 1's > >> >> pvti, guest code on vcpus 0 and 1 see synced TSCs but different pvti. > >> >> They'll disagree on the time, and one of them will be ahead until vcpu > >> >> 1's pvti gets updated. > >> > > >> > The masterclock scheme enforces the same system_timestamp/tsc_timestamp > >> > pairs > >> > to be visible at one time, for all vcpus. > >> > > >> > > >> > * That is, when timespec0 != timespec1, M < N. Unfortunately that is > >> > * not > >> > * always the case (the difference between two distinct xtime instances > >> > * might be smaller then the difference between corresponding TSC reads, > >> > * when updating guest vcpus pvclock areas). > >> > * > >> > * To avoid that problem, do not allow visibility of distinct > >> > * system_timestamp/tsc_timestamp values simultaneously: use a master > >> > * copy of host monotonic time values. Update that master copy > >> > * in lockstep. > >> > >> Yuck. So we have per cpu timing data, but the protocol is only usable > >> for monotonic timing because we forcibly freeze all vcpus when we > >> update the nominally per cpu data. > >> > >> The obvious guest implementations are still unnecessarily slow, > >> though. It would be nice if the guest could get away without using > >> any getcpu operation at all. > >> > >> Even if we fixed the host to increment version as advertised, I think > >> we can't avoid two getcpu ops. We need one before rdtsc to figure out > >> which pvti to look at, > > > > Yes. > > > >>and we need another to make sure that we were > >> actually on that cpu at the time we did rdtsc. (Rdtscp doesn't help > >> -- we need to check version before rdtsc, and we don't know what > >> version to check until we do a getcpu.). > > > > Exactly, reading cpuid after rdtsc doesn't do that though, we could have > > migrated back between those reads. > > rtdscp would allow us to check that we read tsc of pvti's cpu. > > (It doesn't get rid of that first read.) > > > >> The migration hook has the > >> same issue -- we need to check the migration count, then confirm we're > >> on that cpu, then check the migration count again, and we can't do > >> that until we know what cpu we're on. > > > > True; the revert has a bug -- we need to check cpuid for the second > > time before rdtsc. (Migration hook is there just because we don't know > > which cpu executed rdtsc.) > > One way or another, I'm planning on completely rewriting the vdso > code. An early draft is here: > > https://git.kernel.org/cgit/linux/kernel/git/luto/linux.git/commit/?h=x86/vdso&id=57ace6e6e032afc4faf7b9ec52f78a8e6642c980 > > but I can't finish it until the KVM side shakes out. > > I think there are at least two ways that would work: > > a) If KVM incremented version as advertised: All for it. > cpu = getcpu(); > pvti = pvti for cpu; > > ver1 = pvti->version; > check stable bit; > rdtsc_barrier, rdtsc, read scale, shift, etc. > if (getcpu() != cpu) retry; > if (pvti->version != ver1) retry; > > I think this is safe because, we're guaranteed that there was an > interval (between the two version reads) in which the vcpu we think > we're on was running and the kvmclock data was valid and marked > stable, and we know that the tsc we read came from that interval. > > Note: rdtscp isn't needed. If we're stable, is makes no difference > which cpu's tsc we actually read. Yes, can't see a problem with that. > b) If version remains buggy but we use this migrations_from hack: There is no reason for version to remain buggy. > cpu = getcpu(); > pvti = pvti for cpu; > m1 = pvti->migrations_from; > barrier(); > > ver1 = pvti->version; > check stable bit; > rdtsc_barrier, rdtsc, read scale, shift, etc. > if (getcpu() != cpu) retry; > if (pvti->version != ver1) retry; /* probably not really needed */ > > barrier(); > if (pvti->migrations_from != m1) retry; > > This is just like (a), except that we're using a guest kernel hack to > ensure that no one migrated off the vcpu during the version-protected > critical section and that we were, in fact, on that vcpu at some point > during that critical section. Once we've ensured that we were on > pvti's associated vcpu for the entire time we were reading it, then we > are protected by the existing versioning in the host. > > > > >> If, on the other hand, we could rely on having all of these things in > >> sync, then this complication goes away, and we
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Thu, Mar 26, 2015 at 03:24:10PM -0700, Andy Lutomirski wrote:
> On Thu, Mar 26, 2015 at 3:22 PM, Marcelo Tosatti wrote:
> > On Thu, Mar 26, 2015 at 09:59:24PM +0100, Radim Krčmář wrote:
> >> 2015-03-23 20:21-0300, Marcelo Tosatti:
> >> >
> >> > The following point:
> >> >
> >> > 2. per-CPU pvclock time info is updated if the
> >> >underlying CPU changes.
> >> >
> >> > Is not true anymore since "KVM: x86: update pvclock area conditionally,
> >> > on cpu migration".
> >> >
> >> > Add task migration notification back.
> >> >
> >> > Problem noticed by Andy Lutomirski.
> >> >
> >> > Signed-off-by: Marcelo Tosatti
> >> > CC: sta...@kernel.org # 3.11+
> >>
> >> Revert contains a bug that got pointed out in the discussion:
> >>
> >> > diff --git a/arch/x86/vdso/vclock_gettime.c
> >> > b/arch/x86/vdso/vclock_gettime.c
> >> > do {
> >> > cpu = __getcpu() & VGETCPU_CPU_MASK;
> >> >
> >> > pvti = get_pvti(cpu);
> >>
> >> We can migrate to 'other cpu' here.
> >>
> >> > + migrate_count = pvti->migrate_count;
> >> > +
> >> > version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags);
> >>
> >> And migrate back to 'cpu' here.
> >
> > Migrating back will increase pvti->migrate_count, right ?
>
> I thought it only increased the count when we migrated away.
Right.
> --Andy
>
> >
> >> rdtsc was executed on different cpu, so pvti and tsc might not be in
> >> sync, but migrate_count hasn't changed.
> >>
> >> > cpu1 = __getcpu() & VGETCPU_CPU_MASK;
> >>
> >> (Reading cpuid here is useless.)
> >>
> >> > } while (unlikely(cpu != cpu1 ||
> >> > (pvti->pvti.version & 1) ||
> >> > - pvti->pvti.version != version));
> >> > + pvti->pvti.version != version ||
> >> > + pvti->migrate_count != migrate_count));
> >>
> >> We can workaround the bug with,
> >>
> >> cpu = __getcpu() & VGETCPU_CPU_MASK;
> >> pvti = get_pvti(cpu);
> >> migrate_count = pvti->migrate_count;
> >> if (cpu != (__getcpu() & VGETCPU_CPU_MASK))
> >> continue;
Looks good, please submit a fix.
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Thu, Mar 26, 2015 at 3:22 PM, Marcelo Tosatti wrote:
> On Thu, Mar 26, 2015 at 09:59:24PM +0100, Radim Krčmář wrote:
>> 2015-03-23 20:21-0300, Marcelo Tosatti:
>> >
>> > The following point:
>> >
>> > 2. per-CPU pvclock time info is updated if the
>> >underlying CPU changes.
>> >
>> > Is not true anymore since "KVM: x86: update pvclock area conditionally,
>> > on cpu migration".
>> >
>> > Add task migration notification back.
>> >
>> > Problem noticed by Andy Lutomirski.
>> >
>> > Signed-off-by: Marcelo Tosatti
>> > CC: sta...@kernel.org # 3.11+
>>
>> Revert contains a bug that got pointed out in the discussion:
>>
>> > diff --git a/arch/x86/vdso/vclock_gettime.c
>> > b/arch/x86/vdso/vclock_gettime.c
>> > do {
>> > cpu = __getcpu() & VGETCPU_CPU_MASK;
>> >
>> > pvti = get_pvti(cpu);
>>
>> We can migrate to 'other cpu' here.
>>
>> > + migrate_count = pvti->migrate_count;
>> > +
>> > version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags);
>>
>> And migrate back to 'cpu' here.
>
> Migrating back will increase pvti->migrate_count, right ?
I thought it only increased the count when we migrated away.
--Andy
>
>> rdtsc was executed on different cpu, so pvti and tsc might not be in
>> sync, but migrate_count hasn't changed.
>>
>> > cpu1 = __getcpu() & VGETCPU_CPU_MASK;
>>
>> (Reading cpuid here is useless.)
>>
>> > } while (unlikely(cpu != cpu1 ||
>> > (pvti->pvti.version & 1) ||
>> > - pvti->pvti.version != version));
>> > + pvti->pvti.version != version ||
>> > + pvti->migrate_count != migrate_count));
>>
>> We can workaround the bug with,
>>
>> cpu = __getcpu() & VGETCPU_CPU_MASK;
>> pvti = get_pvti(cpu);
>> migrate_count = pvti->migrate_count;
>> if (cpu != (__getcpu() & VGETCPU_CPU_MASK))
>> continue;
--
Andy Lutomirski
AMA Capital Management, LLC
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Thu, Mar 26, 2015 at 09:59:24PM +0100, Radim Krčmář wrote:
> 2015-03-23 20:21-0300, Marcelo Tosatti:
> >
> > The following point:
> >
> > 2. per-CPU pvclock time info is updated if the
> >underlying CPU changes.
> >
> > Is not true anymore since "KVM: x86: update pvclock area conditionally,
> > on cpu migration".
> >
> > Add task migration notification back.
> >
> > Problem noticed by Andy Lutomirski.
> >
> > Signed-off-by: Marcelo Tosatti
> > CC: sta...@kernel.org # 3.11+
>
> Revert contains a bug that got pointed out in the discussion:
>
> > diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
> > do {
> > cpu = __getcpu() & VGETCPU_CPU_MASK;
> >
> > pvti = get_pvti(cpu);
>
> We can migrate to 'other cpu' here.
>
> > + migrate_count = pvti->migrate_count;
> > +
> > version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags);
>
> And migrate back to 'cpu' here.
Migrating back will increase pvti->migrate_count, right ?
> rdtsc was executed on different cpu, so pvti and tsc might not be in
> sync, but migrate_count hasn't changed.
>
> > cpu1 = __getcpu() & VGETCPU_CPU_MASK;
>
> (Reading cpuid here is useless.)
>
> > } while (unlikely(cpu != cpu1 ||
> > (pvti->pvti.version & 1) ||
> > - pvti->pvti.version != version));
> > + pvti->pvti.version != version ||
> > + pvti->migrate_count != migrate_count));
>
> We can workaround the bug with,
>
> cpu = __getcpu() & VGETCPU_CPU_MASK;
> pvti = get_pvti(cpu);
> migrate_count = pvti->migrate_count;
> if (cpu != (__getcpu() & VGETCPU_CPU_MASK))
> continue;
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
[much snippage] On Thu, Mar 26, 2015 at 1:58 PM, Andy Lutomirski wrote: > > If the versioning were fixed, I think we could almost get away with: > > pvti = pvti for vcpu 0; > > ver1 = pvti->version; > check stable bit; > rdtsc_barrier, rdtsc, read scale, shift, etc. > if (pvti->version != ver1) retry; > > This guarantees that the tsc came from an interval in which vcpu0's > kvmclock was *marked* stable. If vcpu0's kvmclock were genuinely > stable in that interval, then we'd be fine, but there's a race window > in which the kvmclock is *not* stable and vcpu 0 wasn't running. Rik pointed out that this could actually be okay. Apparently vcpu 0 is somewhat special, and it may actually be impossible to switch from stable to unstable which a vcpu other than 0 is running and vcpu0 hasn't updated its kvmclock data. --Andy > > Why doesn't KVM just update all of the kvmclock data at once? (For > that matter, why is the pvti in guest memory at all? Wouldn't this > all be simpler if the kvmclock data were host-allocated so the host > could write it directly and maybe even share it between guests?) > > --Andy -- Andy Lutomirski AMA Capital Management, LLC -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
2015-03-23 20:21-0300, Marcelo Tosatti:
>
> The following point:
>
> 2. per-CPU pvclock time info is updated if the
>underlying CPU changes.
>
> Is not true anymore since "KVM: x86: update pvclock area conditionally,
> on cpu migration".
>
> Add task migration notification back.
>
> Problem noticed by Andy Lutomirski.
>
> Signed-off-by: Marcelo Tosatti
> CC: sta...@kernel.org # 3.11+
Revert contains a bug that got pointed out in the discussion:
> diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
> do {
> cpu = __getcpu() & VGETCPU_CPU_MASK;
>
> pvti = get_pvti(cpu);
We can migrate to 'other cpu' here.
> + migrate_count = pvti->migrate_count;
> +
> version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags);
And migrate back to 'cpu' here.
rdtsc was executed on different cpu, so pvti and tsc might not be in
sync, but migrate_count hasn't changed.
> cpu1 = __getcpu() & VGETCPU_CPU_MASK;
(Reading cpuid here is useless.)
> } while (unlikely(cpu != cpu1 ||
> (pvti->pvti.version & 1) ||
> - pvti->pvti.version != version));
> + pvti->pvti.version != version ||
> + pvti->migrate_count != migrate_count));
We can workaround the bug with,
cpu = __getcpu() & VGETCPU_CPU_MASK;
pvti = get_pvti(cpu);
migrate_count = pvti->migrate_count;
if (cpu != (__getcpu() & VGETCPU_CPU_MASK))
continue;
--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Thu, Mar 26, 2015 at 1:31 PM, Radim Krcmar wrote: > 2015-03-26 11:51-0700, Andy Lutomirski: >> On Thu, Mar 26, 2015 at 4:29 AM, Marcelo Tosatti wrote: >> > On Wed, Mar 25, 2015 at 04:22:03PM -0700, Andy Lutomirski wrote: >> >> Suppose we start out with all vcpus agreeing on their pvti and perfect >> >> invariant TSCs. Now the host updates its frequency (due to NTP or >> >> whatever). KVM updates vcpu 0's pvti. Before KVM updates vcpu 1's >> >> pvti, guest code on vcpus 0 and 1 see synced TSCs but different pvti. >> >> They'll disagree on the time, and one of them will be ahead until vcpu >> >> 1's pvti gets updated. >> > >> > The masterclock scheme enforces the same system_timestamp/tsc_timestamp >> > pairs >> > to be visible at one time, for all vcpus. >> > >> > >> > * That is, when timespec0 != timespec1, M < N. Unfortunately that is >> > * not >> > * always the case (the difference between two distinct xtime instances >> > * might be smaller then the difference between corresponding TSC reads, >> > * when updating guest vcpus pvclock areas). >> > * >> > * To avoid that problem, do not allow visibility of distinct >> > * system_timestamp/tsc_timestamp values simultaneously: use a master >> > * copy of host monotonic time values. Update that master copy >> > * in lockstep. >> >> Yuck. So we have per cpu timing data, but the protocol is only usable >> for monotonic timing because we forcibly freeze all vcpus when we >> update the nominally per cpu data. >> >> The obvious guest implementations are still unnecessarily slow, >> though. It would be nice if the guest could get away without using >> any getcpu operation at all. >> >> Even if we fixed the host to increment version as advertised, I think >> we can't avoid two getcpu ops. We need one before rdtsc to figure out >> which pvti to look at, > > Yes. > >>and we need another to make sure that we were >> actually on that cpu at the time we did rdtsc. (Rdtscp doesn't help >> -- we need to check version before rdtsc, and we don't know what >> version to check until we do a getcpu.). > > Exactly, reading cpuid after rdtsc doesn't do that though, we could have > migrated back between those reads. > rtdscp would allow us to check that we read tsc of pvti's cpu. > (It doesn't get rid of that first read.) > >> The migration hook has the >> same issue -- we need to check the migration count, then confirm we're >> on that cpu, then check the migration count again, and we can't do >> that until we know what cpu we're on. > > True; the revert has a bug -- we need to check cpuid for the second > time before rdtsc. (Migration hook is there just because we don't know > which cpu executed rdtsc.) One way or another, I'm planning on completely rewriting the vdso code. An early draft is here: https://git.kernel.org/cgit/linux/kernel/git/luto/linux.git/commit/?h=x86/vdso&id=57ace6e6e032afc4faf7b9ec52f78a8e6642c980 but I can't finish it until the KVM side shakes out. I think there are at least two ways that would work: a) If KVM incremented version as advertised: cpu = getcpu(); pvti = pvti for cpu; ver1 = pvti->version; check stable bit; rdtsc_barrier, rdtsc, read scale, shift, etc. if (getcpu() != cpu) retry; if (pvti->version != ver1) retry; I think this is safe because, we're guaranteed that there was an interval (between the two version reads) in which the vcpu we think we're on was running and the kvmclock data was valid and marked stable, and we know that the tsc we read came from that interval. Note: rdtscp isn't needed. If we're stable, is makes no difference which cpu's tsc we actually read. b) If version remains buggy but we use this migrations_from hack: cpu = getcpu(); pvti = pvti for cpu; m1 = pvti->migrations_from; barrier(); ver1 = pvti->version; check stable bit; rdtsc_barrier, rdtsc, read scale, shift, etc. if (getcpu() != cpu) retry; if (pvti->version != ver1) retry; /* probably not really needed */ barrier(); if (pvti->migrations_from != m1) retry; This is just like (a), except that we're using a guest kernel hack to ensure that no one migrated off the vcpu during the version-protected critical section and that we were, in fact, on that vcpu at some point during that critical section. Once we've ensured that we were on pvti's associated vcpu for the entire time we were reading it, then we are protected by the existing versioning in the host. > >> If, on the other hand, we could rely on having all of these things in >> sync, then this complication goes away, and we go down from two getcpu >> ops to zero. > > (Yeah, we should look what are the drawbacks of doing it differently.) If the versioning were fixed, I think we could almost get away with: pvti = pvti for vcpu 0; ver1 = pvti->version; check stable bit; rdtsc_barrier, rdtsc, read scale, shift, etc. if (pvti->version != ver1) retry; This guarantees that the tsc came from an interval in which
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On 26/03/2015 21:10, Radim Krčmář wrote: > 2015-03-26 11:47-0700, Andy Lutomirski: >> On Wed, Mar 25, 2015 at 4:08 AM, Radim Krčmář wrote: >>> diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c >>> + /* A guest can read other VCPU's kvmclock; specification says that >>> +* version is odd if data is being modified and even after it is >>> +* consistent. >>> +* We write three times to be sure. >>> +* 1) update version to odd number >>> +* 2) write modified data (version is still odd) >>> +* 3) update version to even number >>> +* >>> +* TODO: optimize >>> +* - only two writes should be enough -- version is first >>> +* - the second write could update just version >>> */ >> >> The trouble with this is that kvm_write_guest_cached seems to >> correspond roughly to a "rep movs" variant, and those are weakly >> ordered. As a result, I don't really know whether they have >> well-defined semantics wrt concurrent reads. What we really want is >> just "mov". > > Ah, so the first optimization TODO is not possible, but stores are > weakly ordered only within one rep movs. We're safe if compiler > outputs three mov-like instructions. > > (Btw. does current hardware reorder string stores?) It probably does so if they hit multiple cache lines. Within a cache line, probably not. We can add kvm_map/unmap_guest_cached and then use __put_user. Paolo -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
2015-03-26 11:51-0700, Andy Lutomirski: > On Thu, Mar 26, 2015 at 4:29 AM, Marcelo Tosatti wrote: > > On Wed, Mar 25, 2015 at 04:22:03PM -0700, Andy Lutomirski wrote: > >> Suppose we start out with all vcpus agreeing on their pvti and perfect > >> invariant TSCs. Now the host updates its frequency (due to NTP or > >> whatever). KVM updates vcpu 0's pvti. Before KVM updates vcpu 1's > >> pvti, guest code on vcpus 0 and 1 see synced TSCs but different pvti. > >> They'll disagree on the time, and one of them will be ahead until vcpu > >> 1's pvti gets updated. > > > > The masterclock scheme enforces the same system_timestamp/tsc_timestamp > > pairs > > to be visible at one time, for all vcpus. > > > > > > * That is, when timespec0 != timespec1, M < N. Unfortunately that is > > * not > > * always the case (the difference between two distinct xtime instances > > * might be smaller then the difference between corresponding TSC reads, > > * when updating guest vcpus pvclock areas). > > * > > * To avoid that problem, do not allow visibility of distinct > > * system_timestamp/tsc_timestamp values simultaneously: use a master > > * copy of host monotonic time values. Update that master copy > > * in lockstep. > > Yuck. So we have per cpu timing data, but the protocol is only usable > for monotonic timing because we forcibly freeze all vcpus when we > update the nominally per cpu data. > > The obvious guest implementations are still unnecessarily slow, > though. It would be nice if the guest could get away without using > any getcpu operation at all. > > Even if we fixed the host to increment version as advertised, I think > we can't avoid two getcpu ops. We need one before rdtsc to figure out > which pvti to look at, Yes. >and we need another to make sure that we were > actually on that cpu at the time we did rdtsc. (Rdtscp doesn't help > -- we need to check version before rdtsc, and we don't know what > version to check until we do a getcpu.). Exactly, reading cpuid after rdtsc doesn't do that though, we could have migrated back between those reads. rtdscp would allow us to check that we read tsc of pvti's cpu. (It doesn't get rid of that first read.) > The migration hook has the > same issue -- we need to check the migration count, then confirm we're > on that cpu, then check the migration count again, and we can't do > that until we know what cpu we're on. True; the revert has a bug -- we need to check cpuid for the second time before rdtsc. (Migration hook is there just because we don't know which cpu executed rdtsc.) > If, on the other hand, we could rely on having all of these things in > sync, then this complication goes away, and we go down from two getcpu > ops to zero. (Yeah, we should look what are the drawbacks of doing it differently.) -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
2015-03-26 11:47-0700, Andy Lutomirski: > On Wed, Mar 25, 2015 at 4:08 AM, Radim Krčmář wrote: > > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c > > + /* A guest can read other VCPU's kvmclock; specification says that > > +* version is odd if data is being modified and even after it is > > +* consistent. > > +* We write three times to be sure. > > +* 1) update version to odd number > > +* 2) write modified data (version is still odd) > > +* 3) update version to even number > > +* > > +* TODO: optimize > > +* - only two writes should be enough -- version is first > > +* - the second write could update just version > > */ > > The trouble with this is that kvm_write_guest_cached seems to > correspond roughly to a "rep movs" variant, and those are weakly > ordered. As a result, I don't really know whether they have > well-defined semantics wrt concurrent reads. What we really want is > just "mov". Ah, so the first optimization TODO is not possible, but stores are weakly ordered only within one rep movs. We're safe if compiler outputs three mov-like instructions. (Btw. does current hardware reorder string stores?) -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Thu, Mar 26, 2015 at 4:29 AM, Marcelo Tosatti wrote: > On Wed, Mar 25, 2015 at 04:22:03PM -0700, Andy Lutomirski wrote: >> On Wed, Mar 25, 2015 at 4:13 PM, Marcelo Tosatti wrote: >> > On Wed, Mar 25, 2015 at 03:48:02PM -0700, Andy Lutomirski wrote: >> >> On Wed, Mar 25, 2015 at 3:41 PM, Marcelo Tosatti >> >> wrote: >> >> > On Wed, Mar 25, 2015 at 03:33:10PM -0700, Andy Lutomirski wrote: >> >> >> On Mar 25, 2015 2:29 PM, "Marcelo Tosatti" wrote: >> >> >> > >> >> >> > On Wed, Mar 25, 2015 at 01:52:15PM +0100, Radim Krčmář wrote: >> >> >> > > 2015-03-25 12:08+0100, Radim Krčmář: >> >> >> > > > Reverting the patch protects us from any migration, but I don't >> >> >> > > > think we >> >> >> > > > need to care about changing VCPUs as long as we read a >> >> >> > > > consistent data >> >> >> > > > from kvmclock. (VCPU can change outside of this loop too, so it >> >> >> > > > doesn't >> >> >> > > > matter if we return a value not fit for this VCPU.) >> >> >> > > > >> >> >> > > > I think we could drop the second __getcpu if our kvmclock was >> >> >> > > > being >> >> >> > > > handled better; maybe with a patch like the one below: >> >> >> > > >> >> >> > > The second __getcpu is not neccessary, but I forgot about rdtsc. >> >> >> > > We need to either use rtdscp, know the host has synchronized tsc, >> >> >> > > or >> >> >> > > monitor VCPU migrations. Only the last one works everywhere. >> >> >> > >> >> >> > The vdso code is only used if host has synchronized tsc. >> >> >> > >> >> >> > But you have to handle the case where host goes from synchronized >> >> >> > tsc to >> >> >> > unsynchronized tsc (see the clocksource notifier in the host side). >> >> >> > >> >> >> >> >> >> Can't we change the host to freeze all vcpus and clear the stable bit >> >> >> on all of them if this happens? This would simplify and speed up >> >> >> vclock_gettime. >> >> >> >> >> >> --Andy >> >> > >> >> > Seems interesting to do on 512-vcpus, but sure, could be done. >> >> > >> >> >> >> If you have a 512-vcpu system that switches between stable and >> >> unstable more than once per migration, then I expect that you have >> >> serious problems and this is the least of your worries. >> >> >> >> Personally, I'd *much* rather we just made vcpu 0's pvti authoritative >> >> if we're stable. If nothing else, I'm not even remotely convinced >> >> that the current scheme gives monotonic timing due to skew between >> >> when the updates happen on different vcpus. >> > >> > Can you write down the problem ? >> > >> >> I can try. >> >> Suppose we start out with all vcpus agreeing on their pvti and perfect >> invariant TSCs. Now the host updates its frequency (due to NTP or >> whatever). KVM updates vcpu 0's pvti. Before KVM updates vcpu 1's >> pvti, guest code on vcpus 0 and 1 see synced TSCs but different pvti. >> They'll disagree on the time, and one of them will be ahead until vcpu >> 1's pvti gets updated. > > The masterclock scheme enforces the same system_timestamp/tsc_timestamp pairs > to be visible at one time, for all vcpus. > > > * That is, when timespec0 != timespec1, M < N. Unfortunately that is > * not > * always the case (the difference between two distinct xtime instances > * might be smaller then the difference between corresponding TSC reads, > * when updating guest vcpus pvclock areas). > * > * To avoid that problem, do not allow visibility of distinct > * system_timestamp/tsc_timestamp values simultaneously: use a master > * copy of host monotonic time values. Update that master copy > * in lockstep. > > [resend without HTML] Yuck. So we have per cpu timing data, but the protocol is only usable for monotonic timing because we forcibly freeze all vcpus when we update the nominally per cpu data. The obvious guest implementations are still unnecessarily slow, though. It would be nice if the guest could get away without using any getcpu operation at all. Even if we fixed the host to increment version as advertised, I think we can't avoid two getcpu ops. We need one before rdtsc to figure out which pvti to look at, and we need another to make sure that we were actually on that cpu at the time we did rdtsc. (Rdtscp doesn't help -- we need to check version before rdtsc, and we don't know what version to check until we do a getcpu.). The migration hook has the same issue -- we need to check the migration count, then confirm we're on that cpu, then check the migration count again, and we can't do that until we know what cpu we're on. If, on the other hand, we could rely on having all of these things in sync, then this complication goes away, and we go down from two getcpu ops to zero. --Andy -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Wed, Mar 25, 2015 at 4:08 AM, Radim Krčmář wrote: > 2015-03-24 15:33-0700, Andy Lutomirski: >> On Tue, Mar 24, 2015 at 8:34 AM, Radim Krčmář wrote: >> > What is the problem? >> >> The kvmclock spec says that the host will increment a version field to >> an odd number, then update stuff, then increment it to an even number. >> The host is buggy and doesn't do this, and the result is observable >> when one vcpu reads another vcpu's kvmclock data. >> >> Since there's no good way for a guest kernel to keep its vdso from >> reading a different vcpu's kvmclock data, this is a real corner-case >> bug. This patch allows the vdso to retry when this happens. I don't >> think it's a great solution, but it should mostly work. > > Great explanation, thank you. > > Reverting the patch protects us from any migration, but I don't think we > need to care about changing VCPUs as long as we read a consistent data > from kvmclock. (VCPU can change outside of this loop too, so it doesn't > matter if we return a value not fit for this VCPU.) > > I think we could drop the second __getcpu if our kvmclock was being > handled better; maybe with a patch like the one below: > > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c > index cc2c759f69a3..8658599e0024 100644 > --- a/arch/x86/kvm/x86.c > +++ b/arch/x86/kvm/x86.c > @@ -1658,12 +1658,24 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) > &guest_hv_clock, sizeof(guest_hv_clock > return 0; > > - /* > -* The interface expects us to write an even number signaling that the > -* update is finished. Since the guest won't see the intermediate > -* state, we just increase by 2 at the end. > + /* A guest can read other VCPU's kvmclock; specification says that > +* version is odd if data is being modified and even after it is > +* consistent. > +* We write three times to be sure. > +* 1) update version to odd number > +* 2) write modified data (version is still odd) > +* 3) update version to even number > +* > +* TODO: optimize > +* - only two writes should be enough -- version is first > +* - the second write could update just version > */ > - vcpu->hv_clock.version = guest_hv_clock.version + 2; > + guest_hv_clock.version += 1; > + kvm_write_guest_cached(v->kvm, &vcpu->pv_time, > + &guest_hv_clock, > + sizeof(guest_hv_clock)); > + > + vcpu->hv_clock.version = guest_hv_clock.version; > > /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */ > pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED); > @@ -1684,6 +1696,11 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) > kvm_write_guest_cached(v->kvm, &vcpu->pv_time, > &vcpu->hv_clock, > sizeof(vcpu->hv_clock)); > + > + vcpu->hv_clock.version += 1; > + kvm_write_guest_cached(v->kvm, &vcpu->pv_time, > + &vcpu->hv_clock, > + sizeof(vcpu->hv_clock)); > return 0; > } > The trouble with this is that kvm_write_guest_cached seems to correspond roughly to a "rep movs" variant, and those are weakly ordered. As a result, I don't really know whether they have well-defined semantics wrt concurrent reads. What we really want is just "mov". --Andy -- Andy Lutomirski AMA Capital Management, LLC -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Wed, Mar 25, 2015 at 04:22:03PM -0700, Andy Lutomirski wrote: > On Wed, Mar 25, 2015 at 4:13 PM, Marcelo Tosatti wrote: > > On Wed, Mar 25, 2015 at 03:48:02PM -0700, Andy Lutomirski wrote: > >> On Wed, Mar 25, 2015 at 3:41 PM, Marcelo Tosatti > >> wrote: > >> > On Wed, Mar 25, 2015 at 03:33:10PM -0700, Andy Lutomirski wrote: > >> >> On Mar 25, 2015 2:29 PM, "Marcelo Tosatti" wrote: > >> >> > > >> >> > On Wed, Mar 25, 2015 at 01:52:15PM +0100, Radim Krčmář wrote: > >> >> > > 2015-03-25 12:08+0100, Radim Krčmář: > >> >> > > > Reverting the patch protects us from any migration, but I don't > >> >> > > > think we > >> >> > > > need to care about changing VCPUs as long as we read a consistent > >> >> > > > data > >> >> > > > from kvmclock. (VCPU can change outside of this loop too, so it > >> >> > > > doesn't > >> >> > > > matter if we return a value not fit for this VCPU.) > >> >> > > > > >> >> > > > I think we could drop the second __getcpu if our kvmclock was > >> >> > > > being > >> >> > > > handled better; maybe with a patch like the one below: > >> >> > > > >> >> > > The second __getcpu is not neccessary, but I forgot about rdtsc. > >> >> > > We need to either use rtdscp, know the host has synchronized tsc, or > >> >> > > monitor VCPU migrations. Only the last one works everywhere. > >> >> > > >> >> > The vdso code is only used if host has synchronized tsc. > >> >> > > >> >> > But you have to handle the case where host goes from synchronized tsc > >> >> > to > >> >> > unsynchronized tsc (see the clocksource notifier in the host side). > >> >> > > >> >> > >> >> Can't we change the host to freeze all vcpus and clear the stable bit > >> >> on all of them if this happens? This would simplify and speed up > >> >> vclock_gettime. > >> >> > >> >> --Andy > >> > > >> > Seems interesting to do on 512-vcpus, but sure, could be done. > >> > > >> > >> If you have a 512-vcpu system that switches between stable and > >> unstable more than once per migration, then I expect that you have > >> serious problems and this is the least of your worries. > >> > >> Personally, I'd *much* rather we just made vcpu 0's pvti authoritative > >> if we're stable. If nothing else, I'm not even remotely convinced > >> that the current scheme gives monotonic timing due to skew between > >> when the updates happen on different vcpus. > > > > Can you write down the problem ? > > > > I can try. > > Suppose we start out with all vcpus agreeing on their pvti and perfect > invariant TSCs. Now the host updates its frequency (due to NTP or > whatever). KVM updates vcpu 0's pvti. Before KVM updates vcpu 1's > pvti, guest code on vcpus 0 and 1 see synced TSCs but different pvti. > They'll disagree on the time, and one of them will be ahead until vcpu > 1's pvti gets updated. The masterclock scheme enforces the same system_timestamp/tsc_timestamp pairs to be visible at one time, for all vcpus. * That is, when timespec0 != timespec1, M < N. Unfortunately that is * not * always the case (the difference between two distinct xtime instances * might be smaller then the difference between corresponding TSC reads, * when updating guest vcpus pvclock areas). * * To avoid that problem, do not allow visibility of distinct * system_timestamp/tsc_timestamp values simultaneously: use a master * copy of host monotonic time values. Update that master copy * in lockstep. -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Wed, Mar 25, 2015 at 4:13 PM, Marcelo Tosatti wrote: > On Wed, Mar 25, 2015 at 03:48:02PM -0700, Andy Lutomirski wrote: >> On Wed, Mar 25, 2015 at 3:41 PM, Marcelo Tosatti wrote: >> > On Wed, Mar 25, 2015 at 03:33:10PM -0700, Andy Lutomirski wrote: >> >> On Mar 25, 2015 2:29 PM, "Marcelo Tosatti" wrote: >> >> > >> >> > On Wed, Mar 25, 2015 at 01:52:15PM +0100, Radim Krčmář wrote: >> >> > > 2015-03-25 12:08+0100, Radim Krčmář: >> >> > > > Reverting the patch protects us from any migration, but I don't >> >> > > > think we >> >> > > > need to care about changing VCPUs as long as we read a consistent >> >> > > > data >> >> > > > from kvmclock. (VCPU can change outside of this loop too, so it >> >> > > > doesn't >> >> > > > matter if we return a value not fit for this VCPU.) >> >> > > > >> >> > > > I think we could drop the second __getcpu if our kvmclock was being >> >> > > > handled better; maybe with a patch like the one below: >> >> > > >> >> > > The second __getcpu is not neccessary, but I forgot about rdtsc. >> >> > > We need to either use rtdscp, know the host has synchronized tsc, or >> >> > > monitor VCPU migrations. Only the last one works everywhere. >> >> > >> >> > The vdso code is only used if host has synchronized tsc. >> >> > >> >> > But you have to handle the case where host goes from synchronized tsc to >> >> > unsynchronized tsc (see the clocksource notifier in the host side). >> >> > >> >> >> >> Can't we change the host to freeze all vcpus and clear the stable bit >> >> on all of them if this happens? This would simplify and speed up >> >> vclock_gettime. >> >> >> >> --Andy >> > >> > Seems interesting to do on 512-vcpus, but sure, could be done. >> > >> >> If you have a 512-vcpu system that switches between stable and >> unstable more than once per migration, then I expect that you have >> serious problems and this is the least of your worries. >> >> Personally, I'd *much* rather we just made vcpu 0's pvti authoritative >> if we're stable. If nothing else, I'm not even remotely convinced >> that the current scheme gives monotonic timing due to skew between >> when the updates happen on different vcpus. > > Can you write down the problem ? > I can try. Suppose we start out with all vcpus agreeing on their pvti and perfect invariant TSCs. Now the host updates its frequency (due to NTP or whatever). KVM updates vcpu 0's pvti. Before KVM updates vcpu 1's pvti, guest code on vcpus 0 and 1 see synced TSCs but different pvti. They'll disagree on the time, and one of them will be ahead until vcpu 1's pvti gets updated. --Andy -- Andy Lutomirski AMA Capital Management, LLC -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Wed, Mar 25, 2015 at 03:48:02PM -0700, Andy Lutomirski wrote: > On Wed, Mar 25, 2015 at 3:41 PM, Marcelo Tosatti wrote: > > On Wed, Mar 25, 2015 at 03:33:10PM -0700, Andy Lutomirski wrote: > >> On Mar 25, 2015 2:29 PM, "Marcelo Tosatti" wrote: > >> > > >> > On Wed, Mar 25, 2015 at 01:52:15PM +0100, Radim Krčmář wrote: > >> > > 2015-03-25 12:08+0100, Radim Krčmář: > >> > > > Reverting the patch protects us from any migration, but I don't > >> > > > think we > >> > > > need to care about changing VCPUs as long as we read a consistent > >> > > > data > >> > > > from kvmclock. (VCPU can change outside of this loop too, so it > >> > > > doesn't > >> > > > matter if we return a value not fit for this VCPU.) > >> > > > > >> > > > I think we could drop the second __getcpu if our kvmclock was being > >> > > > handled better; maybe with a patch like the one below: > >> > > > >> > > The second __getcpu is not neccessary, but I forgot about rdtsc. > >> > > We need to either use rtdscp, know the host has synchronized tsc, or > >> > > monitor VCPU migrations. Only the last one works everywhere. > >> > > >> > The vdso code is only used if host has synchronized tsc. > >> > > >> > But you have to handle the case where host goes from synchronized tsc to > >> > unsynchronized tsc (see the clocksource notifier in the host side). > >> > > >> > >> Can't we change the host to freeze all vcpus and clear the stable bit > >> on all of them if this happens? This would simplify and speed up > >> vclock_gettime. > >> > >> --Andy > > > > Seems interesting to do on 512-vcpus, but sure, could be done. > > > > If you have a 512-vcpu system that switches between stable and > unstable more than once per migration, then I expect that you have > serious problems and this is the least of your worries. > > Personally, I'd *much* rather we just made vcpu 0's pvti authoritative > if we're stable. If nothing else, I'm not even remotely convinced > that the current scheme gives monotonic timing due to skew between > when the updates happen on different vcpus. Can you write down the problem ? -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Wed, Mar 25, 2015 at 3:41 PM, Marcelo Tosatti wrote: > On Wed, Mar 25, 2015 at 03:33:10PM -0700, Andy Lutomirski wrote: >> On Mar 25, 2015 2:29 PM, "Marcelo Tosatti" wrote: >> > >> > On Wed, Mar 25, 2015 at 01:52:15PM +0100, Radim Krčmář wrote: >> > > 2015-03-25 12:08+0100, Radim Krčmář: >> > > > Reverting the patch protects us from any migration, but I don't think >> > > > we >> > > > need to care about changing VCPUs as long as we read a consistent data >> > > > from kvmclock. (VCPU can change outside of this loop too, so it >> > > > doesn't >> > > > matter if we return a value not fit for this VCPU.) >> > > > >> > > > I think we could drop the second __getcpu if our kvmclock was being >> > > > handled better; maybe with a patch like the one below: >> > > >> > > The second __getcpu is not neccessary, but I forgot about rdtsc. >> > > We need to either use rtdscp, know the host has synchronized tsc, or >> > > monitor VCPU migrations. Only the last one works everywhere. >> > >> > The vdso code is only used if host has synchronized tsc. >> > >> > But you have to handle the case where host goes from synchronized tsc to >> > unsynchronized tsc (see the clocksource notifier in the host side). >> > >> >> Can't we change the host to freeze all vcpus and clear the stable bit >> on all of them if this happens? This would simplify and speed up >> vclock_gettime. >> >> --Andy > > Seems interesting to do on 512-vcpus, but sure, could be done. > If you have a 512-vcpu system that switches between stable and unstable more than once per migration, then I expect that you have serious problems and this is the least of your worries. Personally, I'd *much* rather we just made vcpu 0's pvti authoritative if we're stable. If nothing else, I'm not even remotely convinced that the current scheme gives monotonic timing due to skew between when the updates happen on different vcpus. --Andy -- Andy Lutomirski AMA Capital Management, LLC -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Wed, Mar 25, 2015 at 03:33:10PM -0700, Andy Lutomirski wrote: > On Mar 25, 2015 2:29 PM, "Marcelo Tosatti" wrote: > > > > On Wed, Mar 25, 2015 at 01:52:15PM +0100, Radim Krčmář wrote: > > > 2015-03-25 12:08+0100, Radim Krčmář: > > > > Reverting the patch protects us from any migration, but I don't think we > > > > need to care about changing VCPUs as long as we read a consistent data > > > > from kvmclock. (VCPU can change outside of this loop too, so it doesn't > > > > matter if we return a value not fit for this VCPU.) > > > > > > > > I think we could drop the second __getcpu if our kvmclock was being > > > > handled better; maybe with a patch like the one below: > > > > > > The second __getcpu is not neccessary, but I forgot about rdtsc. > > > We need to either use rtdscp, know the host has synchronized tsc, or > > > monitor VCPU migrations. Only the last one works everywhere. > > > > The vdso code is only used if host has synchronized tsc. > > > > But you have to handle the case where host goes from synchronized tsc to > > unsynchronized tsc (see the clocksource notifier in the host side). > > > > Can't we change the host to freeze all vcpus and clear the stable bit > on all of them if this happens? This would simplify and speed up > vclock_gettime. > > --Andy Seems interesting to do on 512-vcpus, but sure, could be done. -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Mar 25, 2015 2:29 PM, "Marcelo Tosatti" wrote: > > On Wed, Mar 25, 2015 at 01:52:15PM +0100, Radim Krčmář wrote: > > 2015-03-25 12:08+0100, Radim Krčmář: > > > Reverting the patch protects us from any migration, but I don't think we > > > need to care about changing VCPUs as long as we read a consistent data > > > from kvmclock. (VCPU can change outside of this loop too, so it doesn't > > > matter if we return a value not fit for this VCPU.) > > > > > > I think we could drop the second __getcpu if our kvmclock was being > > > handled better; maybe with a patch like the one below: > > > > The second __getcpu is not neccessary, but I forgot about rdtsc. > > We need to either use rtdscp, know the host has synchronized tsc, or > > monitor VCPU migrations. Only the last one works everywhere. > > The vdso code is only used if host has synchronized tsc. > > But you have to handle the case where host goes from synchronized tsc to > unsynchronized tsc (see the clocksource notifier in the host side). > Can't we change the host to freeze all vcpus and clear the stable bit on all of them if this happens? This would simplify and speed up vclock_gettime. --Andy -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Wed, Mar 25, 2015 at 01:52:15PM +0100, Radim Krčmář wrote: > 2015-03-25 12:08+0100, Radim Krčmář: > > Reverting the patch protects us from any migration, but I don't think we > > need to care about changing VCPUs as long as we read a consistent data > > from kvmclock. (VCPU can change outside of this loop too, so it doesn't > > matter if we return a value not fit for this VCPU.) > > > > I think we could drop the second __getcpu if our kvmclock was being > > handled better; maybe with a patch like the one below: > > The second __getcpu is not neccessary, but I forgot about rdtsc. > We need to either use rtdscp, know the host has synchronized tsc, or > monitor VCPU migrations. Only the last one works everywhere. The vdso code is only used if host has synchronized tsc. But you have to handle the case where host goes from synchronized tsc to unsynchronized tsc (see the clocksource notifier in the host side). -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
2015-03-23 20:21-0300, Marcelo Tosatti: > The following point: > > 2. per-CPU pvclock time info is updated if the >underlying CPU changes. > > Is not true anymore since "KVM: x86: update pvclock area conditionally, > on cpu migration". > > Add task migration notification back. > > Problem noticed by Andy Lutomirski. > > Signed-off-by: Marcelo Tosatti > CC: sta...@kernel.org # 3.11+ Please improve the commit message. "KVM: x86: update pvclock area conditionally [...]" was merged half a year before the patch we are reverting and is completely unrelated to the bug we are fixing now, (reverted patch just was just wrong) Reviewed-by: Radim Krčmář > diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c > @@ -82,18 +82,15 @@ static notrace cycle_t vread_pvclock(int *mode) > /* > - * Note: hypervisor must guarantee that: > - * 1. cpu ID number maps 1:1 to per-CPU pvclock time info. > - * 2. that per-CPU pvclock time info is updated if the > - *underlying CPU changes. > - * 3. that version is increased whenever underlying CPU > - *changes. > - * > + * When looping to get a consistent (time-info, tsc) pair, we > + * also need to deal with the possibility we can switch vcpus, > + * so make sure we always re-fetch time-info for the current vcpu. (All points from the original comment need to hold -- it would be nicer to keep both.) -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
2015-03-25 12:08+0100, Radim Krčmář: > Reverting the patch protects us from any migration, but I don't think we > need to care about changing VCPUs as long as we read a consistent data > from kvmclock. (VCPU can change outside of this loop too, so it doesn't > matter if we return a value not fit for this VCPU.) > > I think we could drop the second __getcpu if our kvmclock was being > handled better; maybe with a patch like the one below: The second __getcpu is not neccessary, but I forgot about rdtsc. We need to either use rtdscp, know the host has synchronized tsc, or monitor VCPU migrations. Only the last one works everywhere. -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
2015-03-24 19:59-0300, Marcelo Tosatti: > On Tue, Mar 24, 2015 at 04:34:12PM +0100, Radim Krčmář wrote: > > 2015-03-23 20:21-0300, Marcelo Tosatti: > > > The following point: > > > > > > 2. per-CPU pvclock time info is updated if the > > >underlying CPU changes. > > > > > > Is not true anymore since "KVM: x86: update pvclock area conditionally, > > > on cpu migration". > > > > I think that the revert doesn't fix point 2.: "KVM: x86: update pvclock > > [...]" changed the host to skip clock update on physical CPU change, but > > guest's task migration notifier isn't tied to it at all. > > "per-CPU pvclock time info is updated if the underlying CPU changes" > is the same as > "always perform clock update on physical CPU change". > > That was a requirement for the original patch, to drop migration > notifiers. > > > (Guest can have all tasks pinned, so the revert changed nothing.) > > > > > Add task migration notification back. > > > > > > Problem noticed by Andy Lutomirski. > > > > What is the problem? > > > > Thanks. > > The problem is this: > > T1) guest thread1 on vcpu1. > T2) guest thread1 on vcpu2. > T3) guest thread1 on vcpu1. > > Inside a pvclock read loop. > > Since the writes by hypervisor of pvclock area are not ordered, > you cannot rely on version being updated _before_ > the rest of pvclock data. > > (in the case above, "has the physical cpu changed" check, inside the > guests thread1, obviously fails). Ah, thanks! so the "KVM: x86: update pvclock area conditionally [...]" has nothing to do with it -- that really confused me. -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
2015-03-24 15:33-0700, Andy Lutomirski: > On Tue, Mar 24, 2015 at 8:34 AM, Radim Krčmář wrote: > > What is the problem? > > The kvmclock spec says that the host will increment a version field to > an odd number, then update stuff, then increment it to an even number. > The host is buggy and doesn't do this, and the result is observable > when one vcpu reads another vcpu's kvmclock data. > > Since there's no good way for a guest kernel to keep its vdso from > reading a different vcpu's kvmclock data, this is a real corner-case > bug. This patch allows the vdso to retry when this happens. I don't > think it's a great solution, but it should mostly work. Great explanation, thank you. Reverting the patch protects us from any migration, but I don't think we need to care about changing VCPUs as long as we read a consistent data from kvmclock. (VCPU can change outside of this loop too, so it doesn't matter if we return a value not fit for this VCPU.) I think we could drop the second __getcpu if our kvmclock was being handled better; maybe with a patch like the one below: diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index cc2c759f69a3..8658599e0024 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1658,12 +1658,24 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) &guest_hv_clock, sizeof(guest_hv_clock return 0; - /* -* The interface expects us to write an even number signaling that the -* update is finished. Since the guest won't see the intermediate -* state, we just increase by 2 at the end. + /* A guest can read other VCPU's kvmclock; specification says that +* version is odd if data is being modified and even after it is +* consistent. +* We write three times to be sure. +* 1) update version to odd number +* 2) write modified data (version is still odd) +* 3) update version to even number +* +* TODO: optimize +* - only two writes should be enough -- version is first +* - the second write could update just version */ - vcpu->hv_clock.version = guest_hv_clock.version + 2; + guest_hv_clock.version += 1; + kvm_write_guest_cached(v->kvm, &vcpu->pv_time, + &guest_hv_clock, + sizeof(guest_hv_clock)); + + vcpu->hv_clock.version = guest_hv_clock.version; /* retain PVCLOCK_GUEST_STOPPED if set in guest copy */ pvclock_flags = (guest_hv_clock.flags & PVCLOCK_GUEST_STOPPED); @@ -1684,6 +1696,11 @@ static int kvm_guest_time_update(struct kvm_vcpu *v) kvm_write_guest_cached(v->kvm, &vcpu->pv_time, &vcpu->hv_clock, sizeof(vcpu->hv_clock)); + + vcpu->hv_clock.version += 1; + kvm_write_guest_cached(v->kvm, &vcpu->pv_time, + &vcpu->hv_clock, + sizeof(vcpu->hv_clock)); return 0; } -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Tue, Mar 24, 2015 at 04:34:12PM +0100, Radim Krčmář wrote: > 2015-03-23 20:21-0300, Marcelo Tosatti: > > The following point: > > > > 2. per-CPU pvclock time info is updated if the > >underlying CPU changes. > > > > Is not true anymore since "KVM: x86: update pvclock area conditionally, > > on cpu migration". > > I think that the revert doesn't fix point 2.: "KVM: x86: update pvclock > [...]" changed the host to skip clock update on physical CPU change, but > guest's task migration notifier isn't tied to it at all. "per-CPU pvclock time info is updated if the underlying CPU changes" is the same as "always perform clock update on physical CPU change". That was a requirement for the original patch, to drop migration notifiers. > (Guest can have all tasks pinned, so the revert changed nothing.) > > > Add task migration notification back. > > > > Problem noticed by Andy Lutomirski. > > What is the problem? > > Thanks. The problem is this: T1) guest thread1 on vcpu1. T2) guest thread1 on vcpu2. T3) guest thread1 on vcpu1. Inside a pvclock read loop. Since the writes by hypervisor of pvclock area are not ordered, you cannot rely on version being updated _before_ the rest of pvclock data. (in the case above, "has the physical cpu changed" check, inside the guests thread1, obviously fails). -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Tue, Mar 24, 2015 at 8:34 AM, Radim Krčmář wrote: > 2015-03-23 20:21-0300, Marcelo Tosatti: >> The following point: >> >> 2. per-CPU pvclock time info is updated if the >>underlying CPU changes. >> >> Is not true anymore since "KVM: x86: update pvclock area conditionally, >> on cpu migration". > > I think that the revert doesn't fix point 2.: "KVM: x86: update pvclock > [...]" changed the host to skip clock update on physical CPU change, but > guest's task migration notifier isn't tied to it at all. > (Guest can have all tasks pinned, so the revert changed nothing.) > >> Add task migration notification back. >> >> Problem noticed by Andy Lutomirski. > > What is the problem? The kvmclock spec says that the host will increment a version field to an odd number, then update stuff, then increment it to an even number. The host is buggy and doesn't do this, and the result is observable when one vcpu reads another vcpu's kvmclock data. Since there's no good way for a guest kernel to keep its vdso from reading a different vcpu's kvmclock data, this is a real corner-case bug. This patch allows the vdso to retry when this happens. I don't think it's a great solution, but it should mostly work. --Andy -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
2015-03-23 20:21-0300, Marcelo Tosatti: > The following point: > > 2. per-CPU pvclock time info is updated if the >underlying CPU changes. > > Is not true anymore since "KVM: x86: update pvclock area conditionally, > on cpu migration". I think that the revert doesn't fix point 2.: "KVM: x86: update pvclock [...]" changed the host to skip clock update on physical CPU change, but guest's task migration notifier isn't tied to it at all. (Guest can have all tasks pinned, so the revert changed nothing.) > Add task migration notification back. > > Problem noticed by Andy Lutomirski. What is the problem? Thanks. -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Re: x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
On Mon, Mar 23, 2015 at 4:21 PM, Marcelo Tosatti wrote: > > The following point: > > 2. per-CPU pvclock time info is updated if the >underlying CPU changes. > > Is not true anymore since "KVM: x86: update pvclock area conditionally, > on cpu migration". > > Add task migration notification back. IMO this is a pretty big hammer to use to work around what appears to be a bug in the host, but I guess that's okay. It's also unfortunate in another regard: it seems non-obvious to me how to use this without reading the cpu number twice in the vdso. On the other hand, unless we have a global pvti, or at least a global indication of TSC stability, I don't see how to do that even with the host bug fixed. Grumble. On a more useful note, could you rename migrate_count to migrate_from_count, since that's what it is? --Andy -- To unsubscribe from this list: send the line "unsubscribe kvm" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
x86: kvm: Revert "remove sched notifier for cross-cpu migrations"
The following point:
2. per-CPU pvclock time info is updated if the
underlying CPU changes.
Is not true anymore since "KVM: x86: update pvclock area conditionally,
on cpu migration".
Add task migration notification back.
Problem noticed by Andy Lutomirski.
Signed-off-by: Marcelo Tosatti
CC: sta...@kernel.org # 3.11+
diff --git a/arch/x86/include/asm/pvclock.h b/arch/x86/include/asm/pvclock.h
index d6b078e..25b1cc0 100644
--- a/arch/x86/include/asm/pvclock.h
+++ b/arch/x86/include/asm/pvclock.h
@@ -95,6 +95,7 @@ unsigned __pvclock_read_cycles(const struct
pvclock_vcpu_time_info *src,
struct pvclock_vsyscall_time_info {
struct pvclock_vcpu_time_info pvti;
+ u32 migrate_count;
} __attribute__((__aligned__(SMP_CACHE_BYTES)));
#define PVTI_SIZE sizeof(struct pvclock_vsyscall_time_info)
diff --git a/arch/x86/kernel/pvclock.c b/arch/x86/kernel/pvclock.c
index 2f355d2..e5ecd20 100644
--- a/arch/x86/kernel/pvclock.c
+++ b/arch/x86/kernel/pvclock.c
@@ -141,7 +141,46 @@ void pvclock_read_wallclock(struct pvclock_wall_clock
*wall_clock,
set_normalized_timespec(ts, now.tv_sec, now.tv_nsec);
}
+static struct pvclock_vsyscall_time_info *pvclock_vdso_info;
+
+static struct pvclock_vsyscall_time_info *
+pvclock_get_vsyscall_user_time_info(int cpu)
+{
+ if (!pvclock_vdso_info) {
+ BUG();
+ return NULL;
+ }
+
+ return &pvclock_vdso_info[cpu];
+}
+
+struct pvclock_vcpu_time_info *pvclock_get_vsyscall_time_info(int cpu)
+{
+ return &pvclock_get_vsyscall_user_time_info(cpu)->pvti;
+}
+
#ifdef CONFIG_X86_64
+static int pvclock_task_migrate(struct notifier_block *nb, unsigned long l,
+ void *v)
+{
+ struct task_migration_notifier *mn = v;
+ struct pvclock_vsyscall_time_info *pvti;
+
+ pvti = pvclock_get_vsyscall_user_time_info(mn->from_cpu);
+
+ /* this is NULL when pvclock vsyscall is not initialized */
+ if (unlikely(pvti == NULL))
+ return NOTIFY_DONE;
+
+ pvti->migrate_count++;
+
+ return NOTIFY_DONE;
+}
+
+static struct notifier_block pvclock_migrate = {
+ .notifier_call = pvclock_task_migrate,
+};
+
/*
* Initialize the generic pvclock vsyscall state. This will allocate
* a/some page(s) for the per-vcpu pvclock information, set up a
@@ -155,12 +194,17 @@ int __init pvclock_init_vsyscall(struct
pvclock_vsyscall_time_info *i,
WARN_ON (size != PVCLOCK_VSYSCALL_NR_PAGES*PAGE_SIZE);
+ pvclock_vdso_info = i;
+
for (idx = 0; idx <= (PVCLOCK_FIXMAP_END-PVCLOCK_FIXMAP_BEGIN); idx++) {
__set_fixmap(PVCLOCK_FIXMAP_BEGIN + idx,
__pa(i) + (idx*PAGE_SIZE),
PAGE_KERNEL_VVAR);
}
+
+ register_task_migration_notifier(&pvclock_migrate);
+
return 0;
}
#endif
diff --git a/arch/x86/vdso/vclock_gettime.c b/arch/x86/vdso/vclock_gettime.c
index 9793322..3093376 100644
--- a/arch/x86/vdso/vclock_gettime.c
+++ b/arch/x86/vdso/vclock_gettime.c
@@ -82,18 +82,15 @@ static notrace cycle_t vread_pvclock(int *mode)
cycle_t ret;
u64 last;
u32 version;
+ u32 migrate_count;
u8 flags;
unsigned cpu, cpu1;
/*
-* Note: hypervisor must guarantee that:
-* 1. cpu ID number maps 1:1 to per-CPU pvclock time info.
-* 2. that per-CPU pvclock time info is updated if the
-*underlying CPU changes.
-* 3. that version is increased whenever underlying CPU
-*changes.
-*
+* When looping to get a consistent (time-info, tsc) pair, we
+* also need to deal with the possibility we can switch vcpus,
+* so make sure we always re-fetch time-info for the current vcpu.
*/
do {
cpu = __getcpu() & VGETCPU_CPU_MASK;
@@ -104,6 +101,8 @@ static notrace cycle_t vread_pvclock(int *mode)
pvti = get_pvti(cpu);
+ migrate_count = pvti->migrate_count;
+
version = __pvclock_read_cycles(&pvti->pvti, &ret, &flags);
/*
@@ -115,7 +114,8 @@ static notrace cycle_t vread_pvclock(int *mode)
cpu1 = __getcpu() & VGETCPU_CPU_MASK;
} while (unlikely(cpu != cpu1 ||
(pvti->pvti.version & 1) ||
- pvti->pvti.version != version));
+ pvti->pvti.version != version ||
+ pvti->migrate_count != migrate_count));
if (unlikely(!(flags & PVCLOCK_TSC_STABLE_BIT)))
*mode = VCLOCK_NONE;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 6d77432..be98910 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -176,6 +176,14 @@ extern void get_iowait_load(unsigned long *nr_waiters,
unsigned long *load);
extern void calc_global_load(unsigned long ticks);
extern void update_cpu_load_nohz(void);
