Re: [PATCH v3] mshv: Add support for integrated scheduler

[Stanislav Kinsburskii]

On Fri, Jan 30, 2026 at 05:47:48PM +0000, Anirudh Rayabharam wrote:
> On Fri, Jan 30, 2026 at 04:04:14PM +0000, Stanislav Kinsburskii wrote:
> > Query the hypervisor for integrated scheduler support and use it if
> > configured.
> > 
> > Microsoft Hypervisor originally provided two schedulers: root and core. The
> > root scheduler allows the root partition to schedule guest vCPUs across
> > physical cores, supporting both time slicing and CPU affinity (e.g., via
> > cgroups). In contrast, the core scheduler delegates vCPU-to-physical-core
> > scheduling entirely to the hypervisor.
> > 
> > Direct virtualization introduces a new privileged guest partition type - L1
> > Virtual Host (L1VH) — which can create child partitions from its own
> > resources. These child partitions are effectively siblings, scheduled by
> > the hypervisor's core scheduler. This prevents the L1VH parent from setting
> > affinity or time slicing for its own processes or guest VPs. While cgroups,
> > CFS, and cpuset controllers can still be used, their effectiveness is
> > unpredictable, as the core scheduler swaps vCPUs according to its own logic
> > (typically round-robin across all allocated physical CPUs). As a result,
> > the system may appear to "steal" time from the L1VH and its children.
> > 
> > To address this, Microsoft Hypervisor introduces the integrated scheduler.
> > This allows an L1VH partition to schedule its own vCPUs and those of its
> 
> How could an L1VH partition schedule its own vCPUs?
> 

By the mean of the integrated scheduler. Or,  from another perspective,
the same way like any other root partition does: by placing load on a
particular code and halting when there is nothing to do.

> > guests across its "physical" cores, effectively emulating root scheduler
> > behavior within the L1VH, while retaining core scheduler behavior for the
> > rest of the system.
> > 
> > The integrated scheduler is controlled by the root partition and gated by
> > the vmm_enable_integrated_scheduler capability bit. If set, the hypervisor
> > supports the integrated scheduler. The L1VH partition must then check if it
> > is enabled by querying the corresponding extended partition property. If
> > this property is true, the L1VH partition must use the root scheduler
> > logic; otherwise, it must use the core scheduler. This requirement makes
> > reading VMM capabilities in L1VH partition a requirement too.
> > 
> > Signed-off-by: Andreea Pintilie <anpintil@xxxxxxxxxxxxx>
> > Signed-off-by: Stanislav Kinsburskii <skinsburskii@xxxxxxxxxxxxxxxxxxx>
> > ---
> >  drivers/hv/mshv_root_main.c |   85 +++++++++++++++++++++++++++----------------
> >  include/hyperv/hvhdk_mini.h |    7 +++-
> >  2 files changed, 59 insertions(+), 33 deletions(-)
> > 
> > diff --git a/drivers/hv/mshv_root_main.c b/drivers/hv/mshv_root_main.c
> > index 1134a82c7881..6a6bf641b352 100644
> > --- a/drivers/hv/mshv_root_main.c
> > +++ b/drivers/hv/mshv_root_main.c
> > @@ -2053,6 +2053,32 @@ static const char *scheduler_type_to_string(enum hv_scheduler_type type)
> >  	};
> >  }
> >  
> > +static int __init l1vh_retrive_scheduler_type(enum hv_scheduler_type *out)
> 
> typo: retrieve*
> 

Thanks, will fix.

> > +{
> > +	u64 integrated_sched_enabled;
> > +	int ret;
> > +
> > +	*out = HV_SCHEDULER_TYPE_CORE_SMT;
> > +
> > +	if (!mshv_root.vmm_caps.vmm_enable_integrated_scheduler)
> > +		return 0;
> > +
> > +	ret = hv_call_get_partition_property_ex(HV_PARTITION_ID_SELF,
> > +						HV_PARTITION_PROPERTY_INTEGRATED_SCHEDULER_ENABLED,
> > +						0, &integrated_sched_enabled,
> > +						sizeof(integrated_sched_enabled));
> > +	if (ret)
> > +		return ret;
> > +
> > +	if (integrated_sched_enabled)
> > +		*out = HV_SCHEDULER_TYPE_ROOT;
> > +
> > +	pr_debug("%s: integrated scheduler property read: ret=%d value=%llu\n",
> > +		 __func__, ret, integrated_sched_enabled);
> 
> ret is always 0 here, right? We don't need to bother printing then.
> 

Oh yes, good point. Will fix.

> > +
> > +	return 0;
> > +}
> > +
> >  /* TODO move this to hv_common.c when needed outside */
> >  static int __init hv_retrieve_scheduler_type(enum hv_scheduler_type *out)
> >  {
> > @@ -2085,13 +2111,12 @@ static int __init hv_retrieve_scheduler_type(enum hv_scheduler_type *out)
> >  /* Retrieve and stash the supported scheduler type */
> >  static int __init mshv_retrieve_scheduler_type(struct device *dev)
> >  {
> > -	int ret = 0;
> > +	int ret;
> >  
> >  	if (hv_l1vh_partition())
> > -		hv_scheduler_type = HV_SCHEDULER_TYPE_CORE_SMT;
> > +		ret = l1vh_retrive_scheduler_type(&hv_scheduler_type);
> >  	else
> >  		ret = hv_retrieve_scheduler_type(&hv_scheduler_type);
> > -
> >  	if (ret)
> >  		return ret;
> >  
> > @@ -2211,42 +2236,29 @@ struct notifier_block mshv_reboot_nb = {
> >  static void mshv_root_partition_exit(void)
> >  {
> >  	unregister_reboot_notifier(&mshv_reboot_nb);
> > -	root_scheduler_deinit();
> >  }
> >  
> >  static int __init mshv_root_partition_init(struct device *dev)
> >  {
> > -	int err;
> > -
> > -	err = root_scheduler_init(dev);
> > -	if (err)
> > -		return err;
> > -
> > -	err = register_reboot_notifier(&mshv_reboot_nb);
> > -	if (err)
> > -		goto root_sched_deinit;
> > -
> > -	return 0;
> > -
> > -root_sched_deinit:
> > -	root_scheduler_deinit();
> > -	return err;
> > +	return register_reboot_notifier(&mshv_reboot_nb);
> >  }
> >  
> > -static void mshv_init_vmm_caps(struct device *dev)
> > +static int __init mshv_init_vmm_caps(struct device *dev)
> >  {
> > -	/*
> > -	 * This can only fail here if HVCALL_GET_PARTITION_PROPERTY_EX or
> > -	 * HV_PARTITION_PROPERTY_VMM_CAPABILITIES are not supported. In that
> > -	 * case it's valid to proceed as if all vmm_caps are disabled (zero).
> > -	 */
> > -	if (hv_call_get_partition_property_ex(HV_PARTITION_ID_SELF,
> > -					      HV_PARTITION_PROPERTY_VMM_CAPABILITIES,
> > -					      0, &mshv_root.vmm_caps,
> > -					      sizeof(mshv_root.vmm_caps)))
> > -		dev_warn(dev, "Unable to get VMM capabilities\n");
> > +	int ret;
> > +
> > +	ret = hv_call_get_partition_property_ex(HV_PARTITION_ID_SELF,
> > +						HV_PARTITION_PROPERTY_VMM_CAPABILITIES,
> > +						0, &mshv_root.vmm_caps,
> > +						sizeof(mshv_root.vmm_caps));
> > +	if (ret && hv_l1vh_partition()) {
> > +		dev_err(dev, "Failed to get VMM capabilities: %d\n", ret);
> > +		return ret;
> 
> I don't think we need to fail here. If there are not VMM caps available,
> that means integrated scheduler is not supported by the hypervisor, so
> fall back to core scheduler.
> 

I believe we discussed this in a personal conversation earlier.
Let me know, is we need to discuss it further.

Thanks,
Stanislav

> Thanks,
> Anirudh
> 
> > +	}
> >  
> >  	dev_dbg(dev, "vmm_caps = %#llx\n", mshv_root.vmm_caps.as_uint64[0]);
> > +
> > +	return 0;
> >  }
> >  
> >  static int __init mshv_parent_partition_init(void)
> > @@ -2292,6 +2304,10 @@ static int __init mshv_parent_partition_init(void)
> >  
> >  	mshv_cpuhp_online = ret;
> >  
> > +	ret = mshv_init_vmm_caps(dev);
> > +	if (ret)
> > +		goto remove_cpu_state;
> > +
> >  	ret = mshv_retrieve_scheduler_type(dev);
> >  	if (ret)
> >  		goto remove_cpu_state;
> > @@ -2301,11 +2317,13 @@ static int __init mshv_parent_partition_init(void)
> >  	if (ret)
> >  		goto remove_cpu_state;
> >  
> > -	mshv_init_vmm_caps(dev);
> > +	ret = root_scheduler_init(dev);
> > +	if (ret)
> > +		goto exit_partition;
> >  
> >  	ret = mshv_irqfd_wq_init();
> >  	if (ret)
> > -		goto exit_partition;
> > +		goto deinit_root_scheduler;
> >  
> >  	spin_lock_init(&mshv_root.pt_ht_lock);
> >  	hash_init(mshv_root.pt_htable);
> > @@ -2314,6 +2332,8 @@ static int __init mshv_parent_partition_init(void)
> >  
> >  	return 0;
> >  
> > +deinit_root_scheduler:
> > +	root_scheduler_deinit();
> >  exit_partition:
> >  	if (hv_root_partition())
> >  		mshv_root_partition_exit();
> > @@ -2332,6 +2352,7 @@ static void __exit mshv_parent_partition_exit(void)
> >  	mshv_port_table_fini();
> >  	misc_deregister(&mshv_dev);
> >  	mshv_irqfd_wq_cleanup();
> > +	root_scheduler_deinit();
> >  	if (hv_root_partition())
> >  		mshv_root_partition_exit();
> >  	cpuhp_remove_state(mshv_cpuhp_online);
> > diff --git a/include/hyperv/hvhdk_mini.h b/include/hyperv/hvhdk_mini.h
> > index 41a29bf8ec14..c0300910808b 100644
> > --- a/include/hyperv/hvhdk_mini.h
> > +++ b/include/hyperv/hvhdk_mini.h
> > @@ -87,6 +87,9 @@ enum hv_partition_property_code {
> >  	HV_PARTITION_PROPERTY_PRIVILEGE_FLAGS			= 0x00010000,
> >  	HV_PARTITION_PROPERTY_SYNTHETIC_PROC_FEATURES		= 0x00010001,
> >  
> > +	/* Integrated scheduling properties */
> > +	HV_PARTITION_PROPERTY_INTEGRATED_SCHEDULER_ENABLED	= 0x00020005,
> > +
> >  	/* Resource properties */
> >  	HV_PARTITION_PROPERTY_GPA_PAGE_ACCESS_TRACKING		= 0x00050005,
> >  	HV_PARTITION_PROPERTY_UNIMPLEMENTED_MSR_ACTION		= 0x00050017,
> > @@ -102,7 +105,7 @@ enum hv_partition_property_code {
> >  };
> >  
> >  #define HV_PARTITION_VMM_CAPABILITIES_BANK_COUNT		1
> > -#define HV_PARTITION_VMM_CAPABILITIES_RESERVED_BITFIELD_COUNT	59
> > +#define HV_PARTITION_VMM_CAPABILITIES_RESERVED_BITFIELD_COUNT	57
> >  
> >  struct hv_partition_property_vmm_capabilities {
> >  	u16 bank_count;
> > @@ -119,6 +122,8 @@ struct hv_partition_property_vmm_capabilities {
> >  			u64 reservedbit3: 1;
> >  #endif
> >  			u64 assignable_synthetic_proc_features: 1;
> > +			u64 reservedbit5: 1;
> > +			u64 vmm_enable_integrated_scheduler : 1;
> >  			u64 reserved0: HV_PARTITION_VMM_CAPABILITIES_RESERVED_BITFIELD_COUNT;
> >  		} __packed;
> >  	};
> > 
> >