| Message ID | 1579702953-24184-2-git-send-email-pbonzini@redhat.com (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
| Series | KVM: x86: do not mix raw and monotonic clocks in kvmclock | expand |
Paolo Bonzini <pbonzini@redhat.com> writes: > We will need a copy of tk->offs_boot in the next patch. Store it and > cleanup the struct: instead of storing tk->tkr_xxx.base with the tk->offs_boot > included, store the raw value in struct pvclock_clock and sum tk->offs_boot > in do_monotonic_raw and do_realtime. tk->tkr_xxx.xtime_nsec also moves > to struct pvclock_clock. > > While at it, fix a (usually harmless) typo in do_monotonic_raw, which > was using gtod->clock.shift instead of gtod->raw_clock.shift. > > Fixes: 53fafdbb8b21f ("KVM: x86: switch KVMCLOCK base to monotonic raw clock") > Cc: stable@vger.kernel.org > Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> > --- > arch/x86/kvm/x86.c | 29 ++++++++++++----------------- > 1 file changed, 12 insertions(+), 17 deletions(-) > > diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c > index 89621025577a..1b4273cce63c 100644 > --- a/arch/x86/kvm/x86.c > +++ b/arch/x86/kvm/x86.c > @@ -1532,6 +1532,8 @@ struct pvclock_clock { > u64 mask; > u32 mult; > u32 shift; > + u64 base_cycles; > + u64 offset; > }; > > struct pvclock_gtod_data { > @@ -1540,11 +1542,8 @@ struct pvclock_gtod_data { > struct pvclock_clock clock; /* extract of a clocksource struct */ > struct pvclock_clock raw_clock; /* extract of a clocksource struct */ > > - u64 boot_ns_raw; > - u64 boot_ns; > - u64 nsec_base; > + ktime_t offs_boot; > u64 wall_time_sec; > - u64 monotonic_raw_nsec; > }; > > static struct pvclock_gtod_data pvclock_gtod_data; > @@ -1552,10 +1551,6 @@ struct pvclock_gtod_data { > static void update_pvclock_gtod(struct timekeeper *tk) > { > struct pvclock_gtod_data *vdata = &pvclock_gtod_data; > - u64 boot_ns, boot_ns_raw; > - > - boot_ns = ktime_to_ns(ktime_add(tk->tkr_mono.base, tk->offs_boot)); > - boot_ns_raw = ktime_to_ns(ktime_add(tk->tkr_raw.base, tk->offs_boot)); > > write_seqcount_begin(&vdata->seq); > > @@ -1565,20 +1560,20 @@ static void update_pvclock_gtod(struct timekeeper *tk) > vdata->clock.mask = tk->tkr_mono.mask; > vdata->clock.mult = tk->tkr_mono.mult; > vdata->clock.shift = tk->tkr_mono.shift; > + vdata->clock.base_cycles = tk->tkr_mono.xtime_nsec; > + vdata->clock.offset = tk->tkr_mono.base; > > vdata->raw_clock.vclock_mode = tk->tkr_raw.clock->archdata.vclock_mode; > vdata->raw_clock.cycle_last = tk->tkr_raw.cycle_last; > vdata->raw_clock.mask = tk->tkr_raw.mask; > vdata->raw_clock.mult = tk->tkr_raw.mult; > vdata->raw_clock.shift = tk->tkr_raw.shift; > - > - vdata->boot_ns = boot_ns; > - vdata->nsec_base = tk->tkr_mono.xtime_nsec; > + vdata->raw_clock.base_cycles = tk->tkr_raw.xtime_nsec; > + vdata->raw_clock.offset = tk->tkr_raw.base; Likely a personal preference but the suggested naming is a bit confusing: we use 'base_cycles' to keep 'xtime_nsec' and 'offset' to keep ... 'base'. Not that I think that 'struct timekeeper' is perfect but at least it is documented. Should we maybe just stick to it (and name 'struct pvclock_clock' fields accordingly?) > > vdata->wall_time_sec = tk->xtime_sec; > > - vdata->boot_ns_raw = boot_ns_raw; > - vdata->monotonic_raw_nsec = tk->tkr_raw.xtime_nsec; > + vdata->offs_boot = tk->offs_boot; > > write_seqcount_end(&vdata->seq); > } > @@ -2048,10 +2043,10 @@ static int do_monotonic_raw(s64 *t, u64 *tsc_timestamp) > > do { > seq = read_seqcount_begin(>od->seq); > - ns = gtod->monotonic_raw_nsec; > + ns = gtod->raw_clock.base_cycles; > ns += vgettsc(>od->raw_clock, tsc_timestamp, &mode); > - ns >>= gtod->clock.shift; > - ns += gtod->boot_ns_raw; > + ns >>= gtod->raw_clock.shift; > + ns += ktime_to_ns(ktime_add(gtod->raw_clock.offset, gtod->offs_boot)); > } while (unlikely(read_seqcount_retry(>od->seq, seq))); > *t = ns; > > @@ -2068,7 +2063,7 @@ static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp) > do { > seq = read_seqcount_begin(>od->seq); > ts->tv_sec = gtod->wall_time_sec; > - ns = gtod->nsec_base; > + ns = gtod->clock.base_cycles; > ns += vgettsc(>od->clock, tsc_timestamp, &mode); > ns >>= gtod->clock.shift; > } while (unlikely(read_seqcount_retry(>od->seq, seq))); FWIW, Reviewed-by: Vitaly Kuznetsov <vkuznets@redhat.com>
On 23/01/20 12:32, Vitaly Kuznetsov wrote: > Likely a personal preference but the suggested naming is a bit > confusing: we use 'base_cycles' to keep 'xtime_nsec' and 'offset' to > keep ... 'base'. Not that I think that 'struct timekeeper' is perfect > but at least it is documented. Should we maybe just stick to it (and > name 'struct pvclock_clock' fields accordingly?) > The problem is that xtime_nsec is not nanoseconds, and I'd really not want to have a worse name just for consistency. :( I chose "base_cycles" as an incremental improvement over nsec_base, even though that meant also changing struct timekeeper's "base" to "offset". Paolo
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 89621025577a..1b4273cce63c 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1532,6 +1532,8 @@ struct pvclock_clock { u64 mask; u32 mult; u32 shift; + u64 base_cycles; + u64 offset; }; struct pvclock_gtod_data { @@ -1540,11 +1542,8 @@ struct pvclock_gtod_data { struct pvclock_clock clock; /* extract of a clocksource struct */ struct pvclock_clock raw_clock; /* extract of a clocksource struct */ - u64 boot_ns_raw; - u64 boot_ns; - u64 nsec_base; + ktime_t offs_boot; u64 wall_time_sec; - u64 monotonic_raw_nsec; }; static struct pvclock_gtod_data pvclock_gtod_data; @@ -1552,10 +1551,6 @@ struct pvclock_gtod_data { static void update_pvclock_gtod(struct timekeeper *tk) { struct pvclock_gtod_data *vdata = &pvclock_gtod_data; - u64 boot_ns, boot_ns_raw; - - boot_ns = ktime_to_ns(ktime_add(tk->tkr_mono.base, tk->offs_boot)); - boot_ns_raw = ktime_to_ns(ktime_add(tk->tkr_raw.base, tk->offs_boot)); write_seqcount_begin(&vdata->seq); @@ -1565,20 +1560,20 @@ static void update_pvclock_gtod(struct timekeeper *tk) vdata->clock.mask = tk->tkr_mono.mask; vdata->clock.mult = tk->tkr_mono.mult; vdata->clock.shift = tk->tkr_mono.shift; + vdata->clock.base_cycles = tk->tkr_mono.xtime_nsec; + vdata->clock.offset = tk->tkr_mono.base; vdata->raw_clock.vclock_mode = tk->tkr_raw.clock->archdata.vclock_mode; vdata->raw_clock.cycle_last = tk->tkr_raw.cycle_last; vdata->raw_clock.mask = tk->tkr_raw.mask; vdata->raw_clock.mult = tk->tkr_raw.mult; vdata->raw_clock.shift = tk->tkr_raw.shift; - - vdata->boot_ns = boot_ns; - vdata->nsec_base = tk->tkr_mono.xtime_nsec; + vdata->raw_clock.base_cycles = tk->tkr_raw.xtime_nsec; + vdata->raw_clock.offset = tk->tkr_raw.base; vdata->wall_time_sec = tk->xtime_sec; - vdata->boot_ns_raw = boot_ns_raw; - vdata->monotonic_raw_nsec = tk->tkr_raw.xtime_nsec; + vdata->offs_boot = tk->offs_boot; write_seqcount_end(&vdata->seq); } @@ -2048,10 +2043,10 @@ static int do_monotonic_raw(s64 *t, u64 *tsc_timestamp) do { seq = read_seqcount_begin(>od->seq); - ns = gtod->monotonic_raw_nsec; + ns = gtod->raw_clock.base_cycles; ns += vgettsc(>od->raw_clock, tsc_timestamp, &mode); - ns >>= gtod->clock.shift; - ns += gtod->boot_ns_raw; + ns >>= gtod->raw_clock.shift; + ns += ktime_to_ns(ktime_add(gtod->raw_clock.offset, gtod->offs_boot)); } while (unlikely(read_seqcount_retry(>od->seq, seq))); *t = ns; @@ -2068,7 +2063,7 @@ static int do_realtime(struct timespec64 *ts, u64 *tsc_timestamp) do { seq = read_seqcount_begin(>od->seq); ts->tv_sec = gtod->wall_time_sec; - ns = gtod->nsec_base; + ns = gtod->clock.base_cycles; ns += vgettsc(>od->clock, tsc_timestamp, &mode); ns >>= gtod->clock.shift; } while (unlikely(read_seqcount_retry(>od->seq, seq)));
We will need a copy of tk->offs_boot in the next patch. Store it and cleanup the struct: instead of storing tk->tkr_xxx.base with the tk->offs_boot included, store the raw value in struct pvclock_clock and sum tk->offs_boot in do_monotonic_raw and do_realtime. tk->tkr_xxx.xtime_nsec also moves to struct pvclock_clock. While at it, fix a (usually harmless) typo in do_monotonic_raw, which was using gtod->clock.shift instead of gtod->raw_clock.shift. Fixes: 53fafdbb8b21f ("KVM: x86: switch KVMCLOCK base to monotonic raw clock") Cc: stable@vger.kernel.org Signed-off-by: Paolo Bonzini <pbonzini@redhat.com> --- arch/x86/kvm/x86.c | 29 ++++++++++++----------------- 1 file changed, 12 insertions(+), 17 deletions(-)