Refactor kvm_synchronize_tsc to make a new function that allows callers
to specify TSC parameters (offset, value, nanoseconds, etc.) explicitly
for the sake of participating in TSC synchronization.
This changes the locking semantics around TSC writes. Writes to the TSC
will now take the pvclock gtod lock while holding the tsc write lock,
whereas before these locks were disjoint.
Reviewed-by: David Matlack <dmatlack@xxxxxxxxxx>
Signed-off-by: Oliver Upton <oupton@xxxxxxxxxx>
---
Documentation/virt/kvm/locking.rst | 11 +++
arch/x86/kvm/x86.c | 106 +++++++++++++++++------------
2 files changed, 74 insertions(+), 43 deletions(-)
diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst
index 1fc860c007a3..d21e0e480d63 100644
--- a/Documentation/virt/kvm/locking.rst
+++ b/Documentation/virt/kvm/locking.rst
@@ -25,6 +25,9 @@ On x86:
holding kvm->arch.mmu_lock (typically with ``read_lock``, otherwise
there's no need to take kvm->arch.tdp_mmu_pages_lock at all).
+- kvm->arch.tsc_write_lock is taken outside
+ kvm->arch.pvclock_gtod_sync_lock
+
Everything else is a leaf: no other lock is taken inside the critical
sections.
@@ -211,6 +214,14 @@ time it will be set using the Dirty tracking mechanism described above.
:Comment: 'raw' because hardware enabling/disabling must be atomic /wrt
migration.
+:Name: kvm_arch::pvclock_gtod_sync_lock
+:Type: raw_spinlock_t
+:Arch: x86
+:Protects: kvm_arch::{cur_tsc_generation,cur_tsc_nsec,cur_tsc_write,
+ cur_tsc_offset,nr_vcpus_matched_tsc}
+:Comment: 'raw' because updating the kvm master clock must not be
+ preempted.
+
:Name: kvm_arch::tsc_write_lock
:Type: raw_spinlock
:Arch: x86
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 9b6bca616929..61069995a592 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -2351,13 +2351,73 @@ static inline bool kvm_check_tsc_unstable(void)
return check_tsc_unstable();
}
+/*
+ * Infers attempts to synchronize the guest's tsc from host writes. Sets the
+ * offset for the vcpu and tracks the TSC matching generation that the vcpu
+ * participates in.
+ *
+ * Must hold kvm->arch.tsc_write_lock to call this function.
+ */
+static void __kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 offset, u64 tsc,
+ u64 ns, bool matched)
+{
+ struct kvm *kvm = vcpu->kvm;
+ bool already_matched;
+ unsigned long flags;
+
+ lockdep_assert_held(&kvm->arch.tsc_write_lock);
+
+ already_matched =
+ (vcpu->arch.this_tsc_generation == kvm->arch.cur_tsc_generation);
+
+ /*
+ * We track the most recent recorded KHZ, write and time to
+ * allow the matching interval to be extended at each write.
+ */
+ kvm->arch.last_tsc_nsec = ns;
+ kvm->arch.last_tsc_write = tsc;
+ kvm->arch.last_tsc_khz = vcpu->arch.virtual_tsc_khz;
+
+ vcpu->arch.last_guest_tsc = tsc;
+
+ /* Keep track of which generation this VCPU has synchronized to */
+ vcpu->arch.this_tsc_generation = kvm->arch.cur_tsc_generation;
+ vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec;
+ vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write;
+
+ kvm_vcpu_write_tsc_offset(vcpu, offset);
+
+ spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags);
+ if (!matched) {
+ /*
+ * We split periods of matched TSC writes into generations.
+ * For each generation, we track the original measured
+ * nanosecond time, offset, and write, so if TSCs are in
+ * sync, we can match exact offset, and if not, we can match
+ * exact software computation in compute_guest_tsc()
+ *
+ * These values are tracked in kvm->arch.cur_xxx variables.
+ */
+ kvm->arch.nr_vcpus_matched_tsc = 0;
+ kvm->arch.cur_tsc_generation++;
+ kvm->arch.cur_tsc_nsec = ns;
+ kvm->arch.cur_tsc_write = tsc;
+ kvm->arch.cur_tsc_offset = offset;
+ matched = false;
+ } else if (!already_matched) {
+ kvm->arch.nr_vcpus_matched_tsc++;
+ }
+
+ kvm_track_tsc_matching(vcpu);
+ spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags);
+}
+
static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
{
struct kvm *kvm = vcpu->kvm;
u64 offset, ns, elapsed;
unsigned long flags;
- bool matched;
- bool already_matched;
+ bool matched = false;
bool synchronizing = false;
raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
@@ -2403,51 +2463,11 @@ static void kvm_synchronize_tsc(struct kvm_vcpu *vcpu, u64 data)
offset = kvm_compute_tsc_offset(vcpu, data);
}
matched = true;
- already_matched = (vcpu->arch.this_tsc_generation == kvm->arch.cur_tsc_generation);
- } else {
- /*
- * We split periods of matched TSC writes into generations.
- * For each generation, we track the original measured
- * nanosecond time, offset, and write, so if TSCs are in
- * sync, we can match exact offset, and if not, we can match
- * exact software computation in compute_guest_tsc()
- *
- * These values are tracked in kvm->arch.cur_xxx variables.
- */
- kvm->arch.cur_tsc_generation++;
- kvm->arch.cur_tsc_nsec = ns;
- kvm->arch.cur_tsc_write = data;
- kvm->arch.cur_tsc_offset = offset;
- matched = false;
}
- /*
- * We also track th most recent recorded KHZ, write and time to
- * allow the matching interval to be extended at each write.
- */
- kvm->arch.last_tsc_nsec = ns;
- kvm->arch.last_tsc_write = data;
- kvm->arch.last_tsc_khz = vcpu->arch.virtual_tsc_khz;
-
- vcpu->arch.last_guest_tsc = data;
+ __kvm_synchronize_tsc(vcpu, offset, data, ns, matched);
- /* Keep track of which generation this VCPU has synchronized to */
- vcpu->arch.this_tsc_generation = kvm->arch.cur_tsc_generation;
- vcpu->arch.this_tsc_nsec = kvm->arch.cur_tsc_nsec;
- vcpu->arch.this_tsc_write = kvm->arch.cur_tsc_write;
-
- kvm_vcpu_write_tsc_offset(vcpu, offset);
raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
-
- spin_lock_irqsave(&kvm->arch.pvclock_gtod_sync_lock, flags);
- if (!matched) {
- kvm->arch.nr_vcpus_matched_tsc = 0;
- } else if (!already_matched) {
- kvm->arch.nr_vcpus_matched_tsc++;
- }
-
- kvm_track_tsc_matching(vcpu);
- spin_unlock_irqrestore(&kvm->arch.pvclock_gtod_sync_lock, flags);
}
static inline void adjust_tsc_offset_guest(struct kvm_vcpu *vcpu,
--
2.32.0.rc1.229.g3e70b5a671-goog
