There is a window where we may miss the current request in the notification period when the work flow is as the following: CPUx + + CPUr | | | +--+ | | | Handle pending req | <--+ +--+ | | | Set req f

NMI will be used as notification signal for lapic-pt vCPUs and ACRN doesn't support vNMI for lapic-pt vCPUs. Because it is not possible to distinguish between notification NMIs and external NMIs for l

ACRN hypervisor needs to kick vCPU off VMX non-root mode to do some operations in hypervisor, such as interrupt/exception injection, EPT flush etc. For non lapic-pt vCPUs, we can use IPI to do so. But

This patch adds a helper function send_single_nmi. The fisrt caller will soon come with the following patch. Acked-by: Eddie Dong <eddie.dong@...> Signed-off-by: Kaige Fu <kaige.fu@...> --

This patch pushs the NMI vector (2) on to the exception stack. So, we can get the right vector in dispatch_exception. Acked-by: Eddie Dong <eddie.dong@...> Signed-off-by: Kaige Fu <kaige.fu@inte

ACRN hypervisor needs to kick vCPU off VMX non-root mode to do some operations in hypervisor, such as interrupt/exception injection, EPT flush etc. For non lapic-pt vCPUs, we can use IPI to do so. But

Thanks for your review. I am trying to figure out why the 3/7 and 6/7 are lost in outlook but can be seen in list.projectacrn.org. And will come back once I find the reason. -- Thanks Kaige Fu

Hi Hongbo and Nanlin, I send this patch series to maillist but Like and Eddie can't see some of the patch mail in outlook. I checked the list.projectacrn.org and find all of them shown in the website.

I can see the series except for 3/7 and 6/7. But I can see all the patches in the series in lists.projectacrn.org PATCH 0/7: https://lists.projectacrn.org/g/acrn-dev/message/25993?p=,,,20,0,0,0::Creat

Actually, if we use the NMI as the notification signal, acrn hypervisor will have no way to support vNMI (inject NMI to the guest) as we can't distinguish between NMI for notification and NMI for gues

We don't use INIT signal notification method now. This patch removes them. Signed-off-by: Kaige Fu <kaige.fu@...> --- hypervisor/arch/x86/guest/vmexit.c | 21 +-------------------- hypervisor/arc

We have implemented a new notification method using NMI. So replace the INIT notification method with the NMI one. Then we can remove INIT notification related code later. Signed-off-by: Kaige Fu <kai

There is a window where we may miss the current request in the notification period when the work flow is as the following: CPUx + + CPUr | | | +--+ | | | Handle pending req | <--+ +--+ | | | Set req f

NMI will be used as notification signal for lapic-pt vCPUs and ACRN doesn't support vNMI for lapic-pt vCPUs. Because it is not possible to distinguish between notification NMIs and external NMIs for l

ACRN hypervisor needs to kick vCPU off VMX non-root mode to do some operations in hypervisor, such as interrupt/exception injection, EPT flush etc. For non lapic-pt vCPUs, we can use IPI to do so. But

This patch adds a helper function send_single_nmi. The fisrt caller will soon come with the following patch. Signed-off-by: Kaige Fu <kaige.fu@...> --- hypervisor/arch/x86/lapic.c | 15 +++++++++

ACRN hypervisor needs to kick vCPU off VMX non-root mode to do some operations in hypervisor, such as interrupt/exception injection, EPT flush etc. For non lapic-pt vCPUs, we can use IPI to do so. But

This patch pushs the NMI vector (2) on to the exception stack. So, we can get the right vector in dispatch_exception. Signed-off-by: Kaige Fu <kaige.fu@...> --- hypervisor/arch/x86/idt.S | 6 +++

I can see 3/7 and 6/7 in my outlook. Let me resend it.