I think this patch is for the correctness, because MONITOR/MWAIT will not releay enter C-state in VM. And MONITOR/MWAIT is also used to 'play_dead', then 100% of vcpu will be used by sys. So should

Check 'device' info of board.xml if an ioport type serial controler have a bdf and update 'TTYS_INFO'. Signed-off-by: Yuanyuan Zhao <yuanyuan.zhao@...> ---

From: "Yang,Yu-chu" <yu-chu.yang@...> Prevent allocator to allocate PCI bus mmio windows to other devices. Tracked-On: #8191 Signed-off-by: Yang,Yu-chu <yu-chu.yang@...> ---

Add a new flag in ioeventfd ioctl to support asyncio. After that, the IO request will be processed in asyncio path by kernel and hypervisor. Signed-off-by: Conghui <conghui.chen@...> ---

asyncio is a new mechanism in ACRN, which is special for these devices which need high IO performance. ACRN hypervisor would process the IO request from User VM in an async mode. Just like the

For an IO request, hv will check if it was registered in asyncio desc list. If yes, put the corresponding fd to the shared buffer. If the shared buffer is full, yield the vcpu and try again

Add hypercall to add/remove asyncio request info. Hv will record the info in a list, and when a new ioreq is come, hv will check if it is in the asyncio list, if yes, queue the fd to asyncio

Current IO emulation is synchronous. The user VM need to wait for the completion of the the I/O request before return. But Virtio Spec introduces introduces asynchronous IO with a new register in

Extend sbuf hypercall to support other kinds of share buffer. Signed-off-by: Conghui <conghui.chen@...> Acked-by: Eddie Dong <eddie.dong@...> --- hypervisor/arch/x86/guest/vmcall.c

sbuf is now only used for debug purpose, but later, it will be used as a common interfaces. So, move the sbuf related code out of the debug directory. Signed-off-by: Conghui

Ok. /* Mitigate the epoll_wait repeat cycles by read out the events as more * as possile.*/ Acked-by: Wang, Yu1 <yu1.wang@...>

Hi Yu, 100% cpu usage is the case without the data read, as the fd is always readable. I will add a comment: This read in loop cannot guarantee all data is read, it is only a mitigation. The race

I don't understand why it occupied 100% cpu. It get the event and find out nothing needs to be done, right?

What's the real impact of processing repeatly?

But you can not guarantee all data can be read out as there has race.

Special Notes: If you have Zoom connection issue by using web browser, pleaseinstall & launch Zoom application, manually input the meeting ID (320664063)to join the Zoom meeting. Agenda &

Hi Eddie,