diff mbox series

[v5,1/2] KVM: x86: Advance guest TSC after deep suspend.

Message ID 20250325041350.1728373-2-suleiman@google.com (mailing list archive)
State New
Headers show
Series KVM: x86: Include host suspended time in steal time | expand

Commit Message

Suleiman Souhlal March 25, 2025, 4:13 a.m. UTC
Advance guest TSC to current time after suspend when the host
TSCs went backwards.

This makes the behavior consistent between suspends where host TSC
resets and suspends where it doesn't, such as suspend-to-idle, where
in the former case if the host TSC resets, the guests' would
previously be "frozen" due to KVM's backwards TSC prevention, while
in the latter case they would advance.

Suggested-by: Sean Christopherson <seanjc@google.com>
Signed-off-by: Suleiman Souhlal <suleiman@google.com>
---
 arch/x86/include/asm/kvm_host.h |  1 +
 arch/x86/kvm/x86.c              | 33 ++++++++++++++++++++++++++++++++-
 2 files changed, 33 insertions(+), 1 deletion(-)
diff mbox series

Patch

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 32ae3aa50c7e38..f5ce2c2782142b 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1399,6 +1399,7 @@  struct kvm_arch {
 	u64 cur_tsc_offset;
 	u64 cur_tsc_generation;
 	int nr_vcpus_matched_tsc;
+	bool host_was_suspended;
 
 	u32 default_tsc_khz;
 	bool user_set_tsc;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 4b64ab350bcd4d..6b4ea3be66e814 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4971,7 +4971,37 @@  void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	/* Apply any externally detected TSC adjustments (due to suspend) */
 	if (unlikely(vcpu->arch.tsc_offset_adjustment)) {
-		adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
+		unsigned long flags;
+		struct kvm *kvm;
+		bool advance;
+		u64 kernel_ns, l1_tsc, offset, tsc_now;
+
+		kvm = vcpu->kvm;
+		advance = kvm_get_time_and_clockread(&kernel_ns,
+		    &tsc_now);
+		raw_spin_lock_irqsave(&kvm->arch.tsc_write_lock, flags);
+		/*
+		 * Advance the guest's TSC to current time instead of only
+		 * preventing it from going backwards, while making sure
+		 * all the vCPUs use the same offset.
+		 */
+		if (kvm->arch.host_was_suspended && advance) {
+			l1_tsc = nsec_to_cycles(vcpu,
+			    vcpu->kvm->arch.kvmclock_offset +
+			    kernel_ns);
+			offset = kvm_compute_l1_tsc_offset(vcpu,
+			    l1_tsc);
+			kvm->arch.cur_tsc_offset = offset;
+			kvm_vcpu_write_tsc_offset(vcpu, offset);
+		} else if (advance)
+			kvm_vcpu_write_tsc_offset(vcpu,
+			    vcpu->kvm->arch.cur_tsc_offset);
+		else
+			adjust_tsc_offset_host(vcpu,
+			    vcpu->arch.tsc_offset_adjustment);
+		kvm->arch.host_was_suspended = 0;
+		raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock,
+		    flags);
 		vcpu->arch.tsc_offset_adjustment = 0;
 		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 	}
@@ -12640,6 +12670,7 @@  int kvm_arch_enable_virtualization_cpu(void)
 				kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
 			}
 
+			kvm->arch.host_was_suspended = 1;
 			/*
 			 * We have to disable TSC offset matching.. if you were
 			 * booting a VM while issuing an S4 host suspend....