x86/kvm: Pass stable clocksource to guests when running nested on Hyper-V

Currently, KVM is able to work in 'masterclock' mode passing
PVCLOCK_TSC_STABLE_BIT to guests when the clocksource which is used on the
host is TSC.

When running nested on Hyper-V the guest normally uses a different one: TSC
page which is resistant to TSC frequency changes on events like L1
migration. Add support for it in KVM.

The only non-trivial change is in vgettsc(): when updating the gtod copy
both the clock readout and tsc value have to be updated now.

Signed-off-by: Vitaly Kuznetsov <vkuznets@redhat.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Paolo Bonzini <pbonzini@redhat.com>
Cc: Stephen Hemminger <sthemmin@microsoft.com>
Cc: kvm@vger.kernel.org
Cc: Radim Krčmář <rkrcmar@redhat.com>
Cc: Haiyang Zhang <haiyangz@microsoft.com>
Cc: "Michael Kelley (EOSG)" <Michael.H.Kelley@microsoft.com>
Cc: Roman Kagan <rkagan@virtuozzo.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: devel@linuxdriverproject.org
Cc: "K. Y. Srinivasan" <kys@microsoft.com>
Cc: Cathy Avery <cavery@redhat.com>
Cc: Mohammed Gamal <mmorsy@redhat.com>
Link: https://lkml.kernel.org/r/20180124132337.30138-7-vkuznets@redhat.com

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c53298dfbf50a78c8f1e209e7f52614ec6c4ea36..b1ce368a07af310955d220a6434929c1eecbe093 100644 (file)
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -67,6 +67,7 @@
 #include <asm/pvclock.h>
 #include <asm/div64.h>
 #include <asm/irq_remapping.h>
+#include <asm/mshyperv.h>
 
 #define CREATE_TRACE_POINTS
 #include "trace.h"
@@ -1377,6 +1378,11 @@ static u64 compute_guest_tsc(struct kvm_vcpu *vcpu, s64 kernel_ns)
        return tsc;
 }
 
+static inline int gtod_is_based_on_tsc(int mode)
+{
+       return mode == VCLOCK_TSC || mode == VCLOCK_HVCLOCK;
+}
+
 static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
 {
 #ifdef CONFIG_X86_64
@@ -1396,7 +1402,7 @@ static void kvm_track_tsc_matching(struct kvm_vcpu *vcpu)
         * perform request to enable masterclock.
         */
        if (ka->use_master_clock ||
-           (gtod->clock.vclock_mode == VCLOCK_TSC && vcpus_matched))
+           (gtod_is_based_on_tsc(gtod->clock.vclock_mode) && vcpus_matched))
                kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
 
        trace_kvm_track_tsc(vcpu->vcpu_id, ka->nr_vcpus_matched_tsc,
@@ -1459,6 +1465,19 @@ static void kvm_vcpu_write_tsc_offset(struct kvm_vcpu *vcpu, u64 offset)
        vcpu->arch.tsc_offset = offset;
 }
 
+static inline bool kvm_check_tsc_unstable(void)
+{
+#ifdef CONFIG_X86_64
+       /*
+        * TSC is marked unstable when we're running on Hyper-V,
+        * 'TSC page' clocksource is good.
+        */
+       if (pvclock_gtod_data.clock.vclock_mode == VCLOCK_HVCLOCK)
+               return false;
+#endif
+       return check_tsc_unstable();
+}
+
 void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
 {
        struct kvm *kvm = vcpu->kvm;
@@ -1504,7 +1523,7 @@ void kvm_write_tsc(struct kvm_vcpu *vcpu, struct msr_data *msr)
          */
        if (synchronizing &&
            vcpu->arch.virtual_tsc_khz == kvm->arch.last_tsc_khz) {
-               if (!check_tsc_unstable()) {
+               if (!kvm_check_tsc_unstable()) {
                        offset = kvm->arch.cur_tsc_offset;
                        pr_debug("kvm: matched tsc offset for %llu\n", data);
                } else {
@@ -1604,18 +1623,43 @@ static u64 read_tsc(void)
        return last;
 }
 
-static inline u64 vgettsc(u64 *cycle_now)
+static inline u64 vgettsc(u64 *tsc_timestamp, int *mode)
 {
        long v;
        struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
+       u64 tsc_pg_val;
+
+       switch (gtod->clock.vclock_mode) {
+       case VCLOCK_HVCLOCK:
+               tsc_pg_val = hv_read_tsc_page_tsc(hv_get_tsc_page(),
+                                                 tsc_timestamp);
+               if (tsc_pg_val != U64_MAX) {
+                       /* TSC page valid */
+                       *mode = VCLOCK_HVCLOCK;
+                       v = (tsc_pg_val - gtod->clock.cycle_last) &
+                               gtod->clock.mask;
+               } else {
+                       /* TSC page invalid */
+                       *mode = VCLOCK_NONE;
+               }
+               break;
+       case VCLOCK_TSC:
+               *mode = VCLOCK_TSC;
+               *tsc_timestamp = read_tsc();
+               v = (*tsc_timestamp - gtod->clock.cycle_last) &
+                       gtod->clock.mask;
+               break;
+       default:
+               *mode = VCLOCK_NONE;
+       }
 
-       *cycle_now = read_tsc();
+       if (*mode == VCLOCK_NONE)
+               *tsc_timestamp = v = 0;
 
-       v = (*cycle_now - gtod->clock.cycle_last) & gtod->clock.mask;
        return v * gtod->clock.mult;
 }
 
-static int do_monotonic_boot(s64 *t, u64 *cycle_now)
+static int do_monotonic_boot(s64 *t, u64 *tsc_timestamp)
 {
        struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
        unsigned long seq;
@@ -1624,9 +1668,8 @@ static int do_monotonic_boot(s64 *t, u64 *cycle_now)
 
        do {
                seq = read_seqcount_begin(&gtod->seq);
-               mode = gtod->clock.vclock_mode;
                ns = gtod->nsec_base;
-               ns += vgettsc(cycle_now);
+               ns += vgettsc(tsc_timestamp, &mode);
                ns >>= gtod->clock.shift;
                ns += gtod->boot_ns;
        } while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
@@ -1635,7 +1678,7 @@ static int do_monotonic_boot(s64 *t, u64 *cycle_now)
        return mode;
 }
 
-static int do_realtime(struct timespec *ts, u64 *cycle_now)
+static int do_realtime(struct timespec *ts, u64 *tsc_timestamp)
 {
        struct pvclock_gtod_data *gtod = &pvclock_gtod_data;
        unsigned long seq;
@@ -1644,10 +1687,9 @@ static int do_realtime(struct timespec *ts, u64 *cycle_now)
 
        do {
                seq = read_seqcount_begin(&gtod->seq);
-               mode = gtod->clock.vclock_mode;
                ts->tv_sec = gtod->wall_time_sec;
                ns = gtod->nsec_base;
-               ns += vgettsc(cycle_now);
+               ns += vgettsc(tsc_timestamp, &mode);
                ns >>= gtod->clock.shift;
        } while (unlikely(read_seqcount_retry(&gtod->seq, seq)));
 
@@ -1657,25 +1699,26 @@ static int do_realtime(struct timespec *ts, u64 *cycle_now)
        return mode;
 }
 
-/* returns true if host is using tsc clocksource */
-static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *cycle_now)
+/* returns true if host is using TSC based clocksource */
+static bool kvm_get_time_and_clockread(s64 *kernel_ns, u64 *tsc_timestamp)
 {
        /* checked again under seqlock below */
-       if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC)
+       if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode))
                return false;
 
-       return do_monotonic_boot(kernel_ns, cycle_now) == VCLOCK_TSC;
+       return gtod_is_based_on_tsc(do_monotonic_boot(kernel_ns,
+                                                     tsc_timestamp));
 }
 
-/* returns true if host is using tsc clocksource */
+/* returns true if host is using TSC based clocksource */
 static bool kvm_get_walltime_and_clockread(struct timespec *ts,
-                                          u64 *cycle_now)
+                                          u64 *tsc_timestamp)
 {
        /* checked again under seqlock below */
-       if (pvclock_gtod_data.clock.vclock_mode != VCLOCK_TSC)
+       if (!gtod_is_based_on_tsc(pvclock_gtod_data.clock.vclock_mode))
                return false;
 
-       return do_realtime(ts, cycle_now) == VCLOCK_TSC;
+       return gtod_is_based_on_tsc(do_realtime(ts, tsc_timestamp));
 }
 #endif
 
@@ -2869,13 +2912,13 @@ void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
                kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
        }
 
-       if (unlikely(vcpu->cpu != cpu) || check_tsc_unstable()) {
+       if (unlikely(vcpu->cpu != cpu) || kvm_check_tsc_unstable()) {
                s64 tsc_delta = !vcpu->arch.last_host_tsc ? 0 :
                                rdtsc() - vcpu->arch.last_host_tsc;
                if (tsc_delta < 0)
                        mark_tsc_unstable("KVM discovered backwards TSC");
 
-               if (check_tsc_unstable()) {
+               if (kvm_check_tsc_unstable()) {
                        u64 offset = kvm_compute_tsc_offset(vcpu,
                                                vcpu->arch.last_guest_tsc);
                        kvm_vcpu_write_tsc_offset(vcpu, offset);
@@ -6110,9 +6153,9 @@ static int pvclock_gtod_notify(struct notifier_block *nb, unsigned long unused,
        update_pvclock_gtod(tk);
 
        /* disable master clock if host does not trust, or does not
-        * use, TSC clocksource
+        * use, TSC based clocksource.
         */
-       if (gtod->clock.vclock_mode != VCLOCK_TSC &&
+       if (!gtod_is_based_on_tsc(gtod->clock.vclock_mode) &&
            atomic_read(&kvm_guest_has_master_clock) != 0)
                queue_work(system_long_wq, &pvclock_gtod_work);
 
@@ -7767,7 +7810,7 @@ struct kvm_vcpu *kvm_arch_vcpu_create(struct kvm *kvm,
 {
        struct kvm_vcpu *vcpu;
 
-       if (check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
+       if (kvm_check_tsc_unstable() && atomic_read(&kvm->online_vcpus) != 0)
                printk_once(KERN_WARNING
                "kvm: SMP vm created on host with unstable TSC; "
                "guest TSC will not be reliable\n");
@@ -7924,7 +7967,7 @@ int kvm_arch_hardware_enable(void)
                return ret;
 
        local_tsc = rdtsc();
-       stable = !check_tsc_unstable();
+       stable = !kvm_check_tsc_unstable();
        list_for_each_entry(kvm, &vm_list, vm_list) {
                kvm_for_each_vcpu(i, vcpu, kvm) {
                        if (!stable && vcpu->cpu == smp_processor_id())