Acked-by: Eddie Dong <eddie.dong@...> Thx Eddie

There are no callers of send_dest_ipi_mask. This patch removes it. Signed-off-by: Kaige Fu <kaige.fu@...> --- hypervisor/arch/x86/lapic.c | 22 ----------------------

There are some functions which rely on smp call, such as vcpu_dumpreg. This function is very useful when debug guest hang issue as it can provides the vCPU contexts where the guest hang at. So, this

This patch introduces a new exec_smp_call to execute the smp call funtion on target CPUs. Currently, it is only called by kick_notification. And we will call it in NMI notification function in coming

This patch introduces a new local function notify_cpus to replace send_dest_ipi_mask. And in following patch, we will check if the target cpu is for lapic_pt enabled vCPU in notify_cpus. If yes,

There are some functions which rely on smp call, such as vcpu_dumpreg. This function is very useful when debug guest hang issue as it can provides the vCPU contexts where the guest hang at. So, this

DM ACPI provides the guest with 'active low' for INTx polarity. So, the initial pin state should be 'HIGH' to indicate that there is no interrupts asserted. Signed-off-by: Kaige Fu

DM ACPI provides the guest with 'active low' for INTx polarity. So, we should set 'LOW' to assert one interrupt and 'HIGH' to deassert one interrupt. Signed-off-by: Shuo Liu

vIOAPIC pinstate should be reset to initial state when configure lintr route according pin polarity. Currently, ACRN devicemodel provides guest with 'active low' polarity. This patchset resets the

This patch overwrites the idle driver of service OS for industry, sdc, sdc2 scenarios. HLT will be used as the default idle action. Signed-off-by: Shuo A Liu <shuo.a.liu@...> ---

HLT emulation is import to CPU resource maximum utilization. vcpu doing HLT means it is idle and can give up CPU proactively. Thus, we pause the vcpu thread in HLT emulation and resume it while event

Sometimes HV wants to know if there are pending interrupts of one vcpu. Add .has_pending_intr interface in acrn_apicv_ops and return the pending interrupts status by check IRRs of

Introduce two kinds of events for each vcpu, VCPU_EVENT_IOREQ: for vcpu waiting for IO request completion VCPU_EVENT_VIRTUAL_INTERRUPT: for vcpu waiting for virtual interrupts events vcpu can wait

This simple event implemention can only support exclusive waiting at same time. It mainly used by thread who want to wait for special event happens. Thread A who want to wait for some events

As we enabled cpu sharing, PAUSE-loop exiting can help vcpu to release its pcpu proactively. It's good for performance. VMX_PLE_GAP: upper bound on the amount of time between two

When multiple vcpus running on same pcpu, it's good for performance if vcpu can yield pcpu proactively. When vcpus are idle, they should release pcpu and let scheduler pickup other vcpus to run. To

Hi Shuo: It seems to be simple :) From abstraction p.o.v., the APIs are still coupled with the event we are using now. If we can have a neutral event wait/signal APIs, + 2 specific event, that will

This patch overwrites the idle driver of service OS for industry, sdc, sdc2 scenarios. HLT will be used as the default idle action. Signed-off-by: Shuo A Liu <shuo.a.liu@...> ---

HLT emulation is import to CPU resource maximum utilization. vcpu doing HLT means it is idle and can give up CPU proactively. Thus, we pause the vcpu in HLT emulation and resume it while event

Sometimes HV wants to know if there are pending interrupts of one vcpu. Add .has_pending_intr interface in acrn_apicv_ops and return the pending interrupts status by check IRRs of