Re: [PATCH v2 03/11] kvm-all: Do not allow reap vcpu dirty ring buffer if not ready

2022-11-29 Thread Hyman Huang
在 2022/11/30 6:42, Peter Xu 写道: Hi, Yong, On Mon, Nov 21, 2022 at 11:26:35AM -0500, huang...@chinatelecom.cn wrote: From: Hyman Huang(黄勇) When tested large vcpu size vm with dirtylimit feature, Qemu crashed due to the assertion in kvm_dirty_ring_reap_one, which assert that vcpu's kvm_dirty

Re: [PATCH v2 03/11] kvm-all: Do not allow reap vcpu dirty ring buffer if not ready

2022-11-29 Thread Peter Xu
Hi, Yong, On Mon, Nov 21, 2022 at 11:26:35AM -0500, huang...@chinatelecom.cn wrote: > From: Hyman Huang(黄勇) > > When tested large vcpu size vm with dirtylimit feature, Qemu crashed > due to the assertion in kvm_dirty_ring_reap_one, which assert that > vcpu's kvm_dirty_gfns has been allocated and

[PATCH v2 03/11] kvm-all: Do not allow reap vcpu dirty ring buffer if not ready

2022-11-21 Thread huangy81
From: Hyman Huang(黄勇) When tested large vcpu size vm with dirtylimit feature, Qemu crashed due to the assertion in kvm_dirty_ring_reap_one, which assert that vcpu's kvm_dirty_gfns has been allocated and not NULL. Because dirty ring reaper thread races with Qemu main thread, reaper may reap vcpu'