Skip to contentSkip to conversation

KVM: x86: Include host suspended time in steal time

PATCH Superseded Suleiman Souhlal 3 participants 8 messages Jul 14, 2025 – Jul 18, 2025

Subsystems (5)
Documentation x86 KVM KVM x86 +1 more subsystems

v7 of 8 Superseded Latest is v8 →

lore
Share & tools
lore
#0 lore raw

v7 cover KVM: x86: Include host suspended time in steal time

This series makes it so that the time that the host is suspended is included in guests' steal time.

When the host resumes from a suspend, the guest thinks any task that was running during the suspend ran for a long time, even though the effective run time was much shorter, which can end up having negative effects with scheduling.

To mitigate this issue, include the time that the host was suspended in steal time, if the guest requests it, which lets the guest subtract the duration from the tasks' runtime. Add new ABI to make this behavior opt-in per-guest.

In addition, make the guest TSC behavior consistent whether the host TSC went backwards or not.

v7:
- Fix build.
- Make advancing TSC dependent on X86_64.

v6: https://lore.kernel.org/kvm/[email protected]/
- Use true/false for bools.
- Indentation.
- Remove superfluous flag.
- Use atomic operations for accumulating suspend duration.
- Reuse generic vcpu block/kick infrastructure instead of rolling our own.
- Add ABI to make the behavior opt-in per-guest.
- Add command line parameter to make guest use this.
- Reword commit messages in imperative mood.

v5: https://lore.kernel.org/kvm/[email protected]/
- Fix grammar mistakes in commit message.

v4: https://lore.kernel.org/kvm/[email protected]/
- Advance guest TSC on suspends where host TSC goes backwards.
- Block vCPUs from running until resume notifier.
- Move suspend duration accounting out of machine-independent kvm to x86.
- Merge code and documentation patches.
- Reworded documentation.

v3: https://lore.kernel.org/kvm/[email protected]/
- Use PM notifier instead of syscore ops (kvm_suspend()/kvm_resume()), because the latter doesn't get called on shallow suspend.
- Don't call function under UACCESS.
- Whitespace.

v2: https://lore.kernel.org/kvm/[email protected]/
- Accumulate suspend time at machine-independent kvm layer and track per-VCPU instead of per-VM.
- Document changes.

v1: https://lore.kernel.org/kvm/[email protected]/

Suleiman Souhlal (3):
KVM: x86: Advance guest TSC after deep suspend.
KVM: x86: Include host suspended duration in steal time
KVM: x86: Add "suspendsteal" cmdline to request host to add suspend
duration in steal time

 .../admin-guide/kernel-parameters.txt         |   5 +
 Documentation/virt/kvm/x86/cpuid.rst          |   4 +
 Documentation/virt/kvm/x86/msr.rst            |  14 +++
 arch/x86/include/asm/kvm_host.h               |   6 +
 arch/x86/include/uapi/asm/kvm_para.h          |   2 +
 arch/x86/kernel/kvm.c                         |  15 +++
 arch/x86/kvm/cpuid.c                          |   4 +-
 arch/x86/kvm/x86.c                            | 112 +++++++++++++++++-
 8 files changed, 156 insertions(+), 6 deletions(-)
Signature · 1 line
2.50.0.727.gbf7dc18ff4-goog
#1 lore raw

PATCH v7 1/3 KVM: x86: Advance guest TSC after deep suspend.

Try to 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.

---
 arch/x86/include/asm/kvm_host.h |  3 +++
 arch/x86/kvm/x86.c              | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 35 insertions(+)
arch/x86/include/asm/kvm_host.h +3 -0
index 7b9ccdd99f32..3650a513ba19 100644
@@ -1414,6 +1414,9 @@ struct kvm_arch {
 	u64 cur_tsc_offset;
 	u64 cur_tsc_generation;
 	int nr_vcpus_matched_tsc;
+#ifdef CONFIG_X86_64
+	bool host_was_suspended;
+#endif
 
 	u32 default_tsc_khz;
 	bool user_set_tsc;
arch/x86/kvm/x86.c +32 -0
index e21f5f2fe059..6539af701016 100644
@@ -5035,7 +5035,36 @@ 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)) {
+#ifdef CONFIG_X86_64
+		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,
+						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, kvm->arch.cur_tsc_offset);
+		} else {
+			adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
+		}
+		kvm->arch.host_was_suspended = false;
+		raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
+#else
 		adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
+#endif /* CONFIG_X86_64 */
 		vcpu->arch.tsc_offset_adjustment = 0;
 		kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
 	}
@@ -12729,6 +12758,9 @@ int kvm_arch_enable_virtualization_cpu(void)
 				kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
 			}
 
+#ifdef CONFIG_X86_64
+			kvm->arch.host_was_suspended = true;
+#endif
 			/*
 			 * We have to disable TSC offset matching.. if you were
 			 * booting a VM while issuing an S4 host suspend....
Signature · 1 line
2.50.0.727.gbf7dc18ff4-goog
Tested-by on v7 1/3
#2 lore raw

Re: [PATCH v7 1/3] KVM: x86: Advance guest TSC after deep suspend.

Quoted 11 lines · Suleiman Souhlal

Try to 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.

Tested again with comparing date before and after suspend-to-RAM:
echo deep >/sys/power/mem_sleep
echo $(date '+%s' -d '+3 minutes') >/sys/class/rtc/rtc0/wakealarm echo mem >/sys/power/state

Without the patch, the guest's date is slower (~3 mins) than the host's after resuming.

Quoted 24 lines
arch/x86/kvm/x86.c +20 -0
@@ -5035,7 +5035,36 @@ 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)) {
+#ifdef CONFIG_X86_64
+		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,
+						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);

arch/x86/kvm/x86.c void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) · line 5067

Quoted 10 lines
arch/x86/kvm/x86.c +9 -0
+		} else if (advance) {
+			kvm_vcpu_write_tsc_offset(vcpu, kvm->arch.cur_tsc_offset);
+		} else {
+			adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
+		}
+		kvm->arch.host_was_suspended = false;
+		raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
+#else
 		adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
+#endif /* CONFIG_X86_64 */

Wondering if it needs to acquire the tsc_write_lock, given that:
- The original code adjust_tsc_offset_host() doesn't acquire. Note:
adjust_tsc_offset_host() eventually calls kvm_vcpu_write_tsc_offset() too.
- Documentation/virt/kvm/locking.rst [1].

[1] https://elixir.bootlin.com/linux/v6.15/source/Documentation/virt/kvm/locking.rst#L264

#3 lore raw

Re: [PATCH v7 1/3] KVM: x86: Advance guest TSC after deep suspend.

Quoted 19 lines · Tzung-Bi Shih
Quoted 11 lines · Suleiman Souhlal

Try to 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.

Tested again with comparing date before and after suspend-to-RAM:
echo deep >/sys/power/mem_sleep
echo $(date '+%s' -d '+3 minutes') >/sys/class/rtc/rtc0/wakealarm echo mem >/sys/power/state

Quoted 4 lines

Without the patch, the guest's date is slower (~3 mins) than the host's after resuming.

Thanks for testing!

Quoted 41 lines
Quoted 25 lines
arch/x86/kvm/x86.c +20 -0
@@ -5035,7 +5035,36 @@ 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)) {
+#ifdef CONFIG_X86_64
+             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,
+                                             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);

arch/x86/kvm/x86.c void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) · line 5067

Quoted 10 lines
arch/x86/kvm/x86.c +9 -0
+             } else if (advance) {
+                     kvm_vcpu_write_tsc_offset(vcpu, kvm->arch.cur_tsc_offset);
+             } else {
+                     adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
+             }
+             kvm->arch.host_was_suspended = false;
+             raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
+#else
              adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
+#endif /* CONFIG_X86_64 */

Wondering if it needs to acquire the tsc_write_lock, given that:
- The original code adjust_tsc_offset_host() doesn't acquire. Note:
adjust_tsc_offset_host() eventually calls kvm_vcpu_write_tsc_offset() too.
- Documentation/virt/kvm/locking.rst [1].

Quoted 1 line

[1] https://elixir.bootlin.com/linux/v6.15/source/Documentation/virt/kvm/locking.rst#L264

This is an excellent question.
I used a lock here to make sure that only one VCPU computes the offset and that all the others reuse it.
It might be doable with atomic operations, but using a lock seemed simpler to me.
I don't think it has to be tsc_write_lock specifically, but reusing it for this purpose seemed appropriate to me.

Thanks,
-- Suleiman

#4 lore raw

Re: [PATCH v7 1/3] KVM: x86: Advance guest TSC after deep suspend.

In reply to Suleiman Souhlal
Quoted 59 lines · Suleiman Souhlal

Try to 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.

---
 arch/x86/include/asm/kvm_host.h |  3 +++
 arch/x86/kvm/x86.c              | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 35 insertions(+)
arch/x86/include/asm/kvm_host.h +3 -0
index 7b9ccdd99f32..3650a513ba19 100644
@@ -1414,6 +1414,9 @@ struct kvm_arch {
        u64 cur_tsc_offset;
        u64 cur_tsc_generation;
        int nr_vcpus_matched_tsc;
+#ifdef CONFIG_X86_64
+       bool host_was_suspended;
+#endif
 
        u32 default_tsc_khz;
        bool user_set_tsc;
arch/x86/kvm/x86.c +20 -0
index e21f5f2fe059..6539af701016 100644
@@ -5035,7 +5035,36 @@ 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)) {
+#ifdef CONFIG_X86_64
+               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,
+                                               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);

arch/x86/kvm/x86.c void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) · line 5067

Quoted 10 lines
arch/x86/kvm/x86.c +9 -0
+               } else if (advance) {
+                       kvm_vcpu_write_tsc_offset(vcpu, kvm->arch.cur_tsc_offset);
+               } else {
+                       adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
+               }
+               kvm->arch.host_was_suspended = false;
+               raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
+#else
                adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
+#endif /* CONFIG_X86_64 */

Just style wise, it seems like renaming adjust_tsc_offset_host() to __adjust_tsc_offset_host(), and then moving the ifdefed logic into a new adjust_tsc_offset_host() implementation might be cleaner? Then you could have:

#ifdef COFNIG_X86_64
static inline void adjust_tsc_offset_host(...)
{
/* added logic above */
}
#else
static inline void adjust_tsc_offset_host(...)

{
    __adjust_tsc_offset_host(...);
}

#endif

arch/x86/kvm/x86.c int kvm_arch_enable_virtualization_cpu(void) · line 12763

Quoted 10 lines
arch/x86/kvm/x86.c +3 -0
                vcpu->arch.tsc_offset_adjustment = 0;
                kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
        }
@@ -12729,6 +12758,9 @@ int kvm_arch_enable_virtualization_cpu(void)
                                kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
                        }
 
+#ifdef CONFIG_X86_64
+                       kvm->arch.host_was_suspended = true;
+#endif

Similarly I'd wrap this in a:

#ifdef CONFIG_x86_64
static inline void kvm_set_host_was_suspended(*kvm)

{
    kvm->arch.host_was_suspended = true;
}

#else
static inline void kvm_set_host_was_suspended(*kvm) {
}
#endif

then call kvm_set_host_was_suspended(kvm) unconditionally in the logic above.

thanks
-john

#5 lore raw

Re: [PATCH v7 1/3] KVM: x86: Advance guest TSC after deep suspend.

Quoted 107 lines · John Stultz
Quoted 59 lines · Suleiman Souhlal

Try to 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.

---
 arch/x86/include/asm/kvm_host.h |  3 +++
 arch/x86/kvm/x86.c              | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 35 insertions(+)
arch/x86/include/asm/kvm_host.h +3 -0
index 7b9ccdd99f32..3650a513ba19 100644
@@ -1414,6 +1414,9 @@ struct kvm_arch {
        u64 cur_tsc_offset;
        u64 cur_tsc_generation;
        int nr_vcpus_matched_tsc;
+#ifdef CONFIG_X86_64
+       bool host_was_suspended;
+#endif
 
        u32 default_tsc_khz;
        bool user_set_tsc;
arch/x86/kvm/x86.c +20 -0
index e21f5f2fe059..6539af701016 100644
@@ -5035,7 +5035,36 @@ 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)) {
+#ifdef CONFIG_X86_64
+               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,
+                                               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);

arch/x86/kvm/x86.c void kvm_arch_vcpu_load(struct kvm_vcpu *vcpu, int cpu) · line 5067

Quoted 10 lines
arch/x86/kvm/x86.c +9 -0
+               } else if (advance) {
+                       kvm_vcpu_write_tsc_offset(vcpu, kvm->arch.cur_tsc_offset);
+               } else {
+                       adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
+               }
+               kvm->arch.host_was_suspended = false;
+               raw_spin_unlock_irqrestore(&kvm->arch.tsc_write_lock, flags);
+#else
                adjust_tsc_offset_host(vcpu, vcpu->arch.tsc_offset_adjustment);
+#endif /* CONFIG_X86_64 */

Just style wise, it seems like renaming adjust_tsc_offset_host() to __adjust_tsc_offset_host(), and then moving the ifdefed logic into a new adjust_tsc_offset_host() implementation might be cleaner? Then you could have:

#ifdef COFNIG_X86_64
static inline void adjust_tsc_offset_host(...)
{
/* added logic above */
}
#else
static inline void adjust_tsc_offset_host(...)

{
    __adjust_tsc_offset_host(...);
}

#endif

arch/x86/kvm/x86.c int kvm_arch_enable_virtualization_cpu(void) · line 12763

Quoted 10 lines
arch/x86/kvm/x86.c +3 -0
                vcpu->arch.tsc_offset_adjustment = 0;
                kvm_make_request(KVM_REQ_CLOCK_UPDATE, vcpu);
        }
@@ -12729,6 +12758,9 @@ int kvm_arch_enable_virtualization_cpu(void)
                                kvm_make_request(KVM_REQ_MASTERCLOCK_UPDATE, vcpu);
                        }
 
+#ifdef CONFIG_X86_64
+                       kvm->arch.host_was_suspended = true;
+#endif

Similarly I'd wrap this in a:

#ifdef CONFIG_x86_64
static inline void kvm_set_host_was_suspended(*kvm)

{
    kvm->arch.host_was_suspended = true;
}
Quoted 7 lines

#else
static inline void kvm_set_host_was_suspended(*kvm) {
}
#endif

then call kvm_set_host_was_suspended(kvm) unconditionally in the logic above.

Thanks for the good suggestions. I'll incorporate them into v8.

-- Suleiman

#6 lore raw

PATCH v7 2/3 KVM: x86: Include host suspended duration in steal time

In reply to Suleiman Souhlal

Introduce MSR_KVM_SUSPEND_STEAL which controls whether or not a guest wants the duration of host suspend to be included in steal time.

This lets guests subtract the duration during which the host was suspended from the runtime of tasks that were running over the suspend, in order to prevent cases where host suspend causes long runtimes in guest tasks, even though their effective runtime was much shorter.

---
 Documentation/virt/kvm/x86/cpuid.rst |  4 ++
 Documentation/virt/kvm/x86/msr.rst   | 14 +++++
 arch/x86/include/asm/kvm_host.h      |  3 ++
 arch/x86/include/uapi/asm/kvm_para.h |  2 +
 arch/x86/kvm/cpuid.c                 |  4 +-
 arch/x86/kvm/x86.c                   | 80 ++++++++++++++++++++++++++--
 6 files changed, 101 insertions(+), 6 deletions(-)
Documentation/virt/kvm/x86/cpuid.rst +4 -0
index bda3e3e737d7..71b42b649973 100644
@@ -103,6 +103,10 @@ KVM_FEATURE_HC_MAP_GPA_RANGE       16          guest checks this feature bit bef
 KVM_FEATURE_MIGRATION_CONTROL      17          guest checks this feature bit before
                                                using MSR_KVM_MIGRATION_CONTROL
 
+KVM_FEATURE_SUSPEND_STEAL          18          guest checks this feature bit
+                                               before using
+                                               MSR_KVM_SUSPEND_STEAL.
+
 KVM_FEATURE_CLOCKSOURCE_STABLE_BIT 24          host will warn if no guest-side
                                                per-cpu warps are expected in
                                                kvmclock
Documentation/virt/kvm/x86/msr.rst +14 -0
index 3aecf2a70e7b..7c33f9ee11f5 100644
@@ -296,6 +296,12 @@ data:
 		the amount of time in which this vCPU did not run, in
 		nanoseconds. Time during which the vcpu is idle, will not be
 		reported as steal time.
+		If the guest set the enable bit in MSR_KVM_SUSPEND_STEAL,
+		steal time includes the duration during which the host is
+		suspended. The case where the host suspends during a VM
+		migration might not be accounted if VCPUs aren't entered
+		post-resume. A workaround would be for the VMM to ensure that
+		the guest is entered with KVM_RUN after resuming from suspend.
 
 	preempted:
 		indicate the vCPU who owns this struct is running or
@@ -388,3 +394,11 @@ data:
         guest is communicating page encryption status to the host using the
         ``KVM_HC_MAP_GPA_RANGE`` hypercall, it can set bit 0 in this MSR to
         allow live migration of the guest.
+
+MSR_KVM_SUSPEND_STEAL:
+	0x4b564d09
+
+data:
+	This MSR is available if KVM_FEATURE_SUSPEND_STEAL is present in
+	CPUID. Bit 0 controls whether the host should include the duration it
+	has been suspended in steal time (1), or not (0).
arch/x86/include/asm/kvm_host.h +3 -0
index 3650a513ba19..015cf86b4e63 100644
@@ -932,6 +932,8 @@ struct kvm_vcpu_arch {
 		u8 preempted;
 		u64 msr_val;
 		u64 last_steal;
+		u64 suspend_ts;
+		atomic64_t suspend_ns;
 		struct gfn_to_hva_cache cache;
 	} st;
 
@@ -1028,6 +1030,7 @@ struct kvm_vcpu_arch {
 	} pv_eoi;
 
 	u64 msr_kvm_poll_control;
+	u64 msr_kvm_suspend_steal;
 
 	/* pv related host specific info */
 	struct {
arch/x86/include/uapi/asm/kvm_para.h +2 -0
index a1efa7907a0b..678ebc3d7eeb 100644
@@ -36,6 +36,7 @@
 #define KVM_FEATURE_MSI_EXT_DEST_ID	15
 #define KVM_FEATURE_HC_MAP_GPA_RANGE	16
 #define KVM_FEATURE_MIGRATION_CONTROL	17
+#define KVM_FEATURE_SUSPEND_STEAL	18
 
 #define KVM_HINTS_REALTIME      0
 
@@ -58,6 +59,7 @@
 #define MSR_KVM_ASYNC_PF_INT	0x4b564d06
 #define MSR_KVM_ASYNC_PF_ACK	0x4b564d07
 #define MSR_KVM_MIGRATION_CONTROL	0x4b564d08
+#define MSR_KVM_SUSPEND_STEAL	0x4b564d09
 
 struct kvm_steal_time {
 	__u64 steal;
arch/x86/kvm/cpuid.c +3 -1
index b2d006756e02..983867f243ca 100644
@@ -1614,8 +1614,10 @@ static inline int __do_cpuid_func(struct kvm_cpuid_array *array, u32 function)
 			     (1 << KVM_FEATURE_PV_SCHED_YIELD) |
 			     (1 << KVM_FEATURE_ASYNC_PF_INT);
 
-		if (sched_info_on())
+		if (sched_info_on()) {
 			entry->eax |= (1 << KVM_FEATURE_STEAL_TIME);
+			entry->eax |= (1 << KVM_FEATURE_SUSPEND_STEAL);
+		}
 
 		entry->ebx = 0;
 		entry->ecx = 0;
arch/x86/kvm/x86.c +75 -5

118 lines not on this page · raw message

Signature · 1 line
2.50.0.727.gbf7dc18ff4-goog
#7 lore raw

PATCH v7 3/3 KVM: x86: Add "suspendsteal" cmdline to request host to add suspend duration in steal time

In reply to Suleiman Souhlal

Introduce a new command line parameter, "suspendsteal", enabling the guest to use MSR_KVM_SUSPEND_STEAL, which tells the host that it would like host suspend duration to be included in steal time.

---
 Documentation/admin-guide/kernel-parameters.txt |  5 +++++
 arch/x86/kernel/kvm.c                           | 15 +++++++++++++++
 2 files changed, 20 insertions(+)
Documentation/admin-guide/kernel-parameters.txt +5 -0
index f1f2c0874da9..9f5758ca8fad 100644
@@ -7074,6 +7074,11 @@
 			improve throughput, but will also increase the
 			amount of memory reserved for use by the client.
 
+	suspendsteal
+			[X86,PV_OPS]
+			Enable requesting the host to include the duration the
+			host was suspended in steal time. Disabled by default.
+
 	suspend.pm_test_delay=
 			[SUSPEND]
 			Sets the number of seconds to remain in a suspend test
arch/x86/kernel/kvm.c +15 -0
index 921c1c783bc1..35d1bb2283c2 100644
@@ -320,6 +320,18 @@ static void __init paravirt_ops_setup(void)
 #endif
 }
 
+static bool suspend_steal;
+
+static int __init suspendsteal_setup(char *s)
+{
+	if (kvm_para_has_feature(KVM_FEATURE_SUSPEND_STEAL))
+		suspend_steal = true;
+
+	return 0;
+}
+
+early_param("suspendsteal", suspendsteal_setup);
+
 static void kvm_register_steal_time(void)
 {
 	int cpu = smp_processor_id();
@@ -331,6 +343,9 @@ static void kvm_register_steal_time(void)
 	wrmsrq(MSR_KVM_STEAL_TIME, (slow_virt_to_phys(st) | KVM_MSR_ENABLED));
 	pr_debug("stealtime: cpu %d, msr %llx\n", cpu,
 		(unsigned long long) slow_virt_to_phys(st));
+
+	if (suspend_steal)
+		wrmsrl(MSR_KVM_SUSPEND_STEAL, KVM_MSR_ENABLED);
 }
 
 static DEFINE_PER_CPU_DECRYPTED(unsigned long, kvm_apic_eoi) = KVM_PV_EOI_DISABLED;
Signature · 1 line
2.50.0.727.gbf7dc18ff4-goog