[PATCH v5 15/34] KVM: x86: Restructure kvm_guest_time_update() for TSC upscaling

[David Woodhouse <dwmw2@infradead.org>]

From: David Woodhouse <dwmw@amazon.co.uk>

Restructure kvm_guest_time_update() so that kernel_ns/host_tsc are
always "now" when doing TSC catchup, then swap in the master clock
reference values afterward for the hv_clock.

This makes the TSC upscaling code considerably simpler: the catchup
adjustment is computed as the delta between what the guest TSC *should*
be at "now" and what it actually is, rather than mixing "now" and
"master clock reference" timestamps.

The seqcount loop now also contains the kvm_get_time_and_clockread()
call (matching get_kvmclock's pattern), with the same WARN for
unexpected failure.

Based on a suggestion by Sean Christopherson.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
---
 arch/x86/kvm/x86.c | 74 +++++++++++++++++++++++++++++++++-------------
 1 file changed, 53 insertions(+), 21 deletions(-)

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 8aae22401046..92e32d720523 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -3363,46 +3363,63 @@ static void kvm_setup_guest_pvclock(struct pvclock_vcpu_time_info *ref_hv_clock,
 int kvm_guest_time_update(struct kvm_vcpu *v)
 {
 	struct pvclock_vcpu_time_info hv_clock = {};
-	unsigned long flags;
 	u64 tgt_tsc_hz;
 	unsigned seq;
 	struct kvm_vcpu_arch *vcpu = &v->arch;
 	struct kvm_arch *ka = &v->kvm->arch;
 	s64 kernel_ns;
 	u64 tsc_timestamp, host_tsc;
+	u64 master_host_tsc = 0;
+	s64 master_kernel_ns = 0;
 	bool use_master_clock;
 
-	kernel_ns = 0;
-	host_tsc = 0;
-
 	/*
 	 * If the host uses TSC clock, then passthrough TSC as stable
 	 * to the guest.
 	 */
 	do {
 		seq = read_seqcount_begin(&ka->pvclock_sc);
+
 		use_master_clock = ka->use_master_clock;
-		if (use_master_clock) {
-			host_tsc = ka->master_cycle_now;
-			kernel_ns = ka->master_kernel_ns;
-		}
+
+		/*
+		 * The TSC read and the call to get_cpu_tsc_khz() must happen
+		 * on the same CPU.
+		 */
+		get_cpu();
+
+		tgt_tsc_hz = (u64)get_cpu_tsc_khz() * 1000;
+
+#ifdef CONFIG_X86_64
+		if (use_master_clock &&
+		    !kvm_get_time_and_clockread(&kernel_ns, &host_tsc) &&
+		    !read_seqcount_retry(&ka->pvclock_sc, seq))
+			use_master_clock = false;
+#endif
+
+		put_cpu();
+
+		if (!use_master_clock)
+			break;
+
+		master_host_tsc = ka->master_cycle_now;
+		master_kernel_ns = ka->master_kernel_ns;
 	} while (read_seqcount_retry(&ka->pvclock_sc, seq));
 
-	/* Keep irq disabled to prevent changes to the clock */
-	local_irq_save(flags);
-	tgt_tsc_hz = (u64)get_cpu_tsc_khz() * 1000;
 	if (unlikely(tgt_tsc_hz == 0)) {
-		local_irq_restore(flags);
 		kvm_make_request(KVM_REQ_CLOCK_UPDATE, v);
 		return 1;
 	}
+
 	if (!use_master_clock) {
+		unsigned long flags;
+
+		local_irq_save(flags);
 		host_tsc = rdtsc();
 		kernel_ns = get_kvmclock_base_ns();
+		local_irq_restore(flags);
 	}
 
-	tsc_timestamp = kvm_read_l1_tsc(v, host_tsc);
-
 	/*
 	 * We may have to catch up the TSC to match elapsed wall clock
 	 * time for two reasons, even if kvmclock is used.
@@ -3411,17 +3428,32 @@ int kvm_guest_time_update(struct kvm_vcpu *v)
 	 *      entry to avoid unknown leaps of TSC even when running
 	 *      again on the same CPU.  This may cause apparent elapsed
 	 *      time to disappear, and the guest to stand still or run
-	 *	very slowly.
+	 *      very slowly.
 	 */
 	if (vcpu->tsc_catchup) {
-		u64 tsc = compute_guest_tsc(v, kernel_ns);
-		if (tsc > tsc_timestamp) {
-			adjust_tsc_offset_guest(v, tsc - tsc_timestamp);
-			tsc_timestamp = tsc;
-		}
+		s64 adjustment;
+
+		/*
+		 * Calculate the delta between what the guest TSC *should* be
+		 * and what it actually is according to kvm_read_l1_tsc().
+		 */
+		adjustment = compute_guest_tsc(v, kernel_ns) -
+			     kvm_read_l1_tsc(v, host_tsc);
+		if (adjustment > 0)
+			adjust_tsc_offset_guest(v, adjustment);
 	}
 
-	local_irq_restore(flags);
+	/*
+	 * Now that TSC upscaling is out of the way, the remaining calculations
+	 * are all relative to the reference time that's placed in hv_clock.
+	 * If the master clock is NOT in use, the reference time is "now".  If
+	 * master clock is in use, the reference time comes from there.
+	 */
+	if (use_master_clock) {
+		host_tsc = master_host_tsc;
+		kernel_ns = master_kernel_ns;
+	}
+	tsc_timestamp = kvm_read_l1_tsc(v, host_tsc);
 
 	/* With all the info we got, fill in the values */
 
-- 
2.54.0