Re: [PATCH 4/4] kvm/x86: Allow to respond to generic signals during slow page faults

From: Sean Christopherson
Date: Thu Jun 23 2022 - 10:46:22 EST


On Wed, Jun 22, 2022, Peter Xu wrote:
> diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c
> index e92f1ab63d6a..b39acb7cb16d 100644
> --- a/arch/x86/kvm/mmu/mmu.c
> +++ b/arch/x86/kvm/mmu/mmu.c
> @@ -3012,6 +3012,13 @@ static int kvm_handle_bad_page(struct kvm_vcpu *vcpu, gfn_t gfn, kvm_pfn_t pfn)
> static int handle_abnormal_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault,
> unsigned int access)
> {
> + /* NOTE: not all error pfn is fatal; handle intr before the other ones */
> + if (unlikely(is_intr_pfn(fault->pfn))) {
> + vcpu->run->exit_reason = KVM_EXIT_INTR;
> + ++vcpu->stat.signal_exits;
> + return -EINTR;
> + }
> +
> /* The pfn is invalid, report the error! */
> if (unlikely(is_error_pfn(fault->pfn)))
> return kvm_handle_bad_page(vcpu, fault->gfn, fault->pfn);
> @@ -4017,6 +4024,8 @@ static int kvm_faultin_pfn(struct kvm_vcpu *vcpu, struct kvm_page_fault *fault)
> }
> }
>
> + /* Allow to respond to generic signals in slow page faults */

"slow" is being overloaded here. The previous call __gfn_to_pfn_memslot() will
end up in hva_to_pfn_slow(), but because of passing a non-null async it won't wait.
This code really should have a more extensive comment irrespective of the interruptible
stuff, now would be a good time to add that.

Comments aside, isn't this series incomplete from the perspective that there are
still many flows where KVM will hang if gfn_to_pfn() gets stuck in gup? E.g. if
KVM is retrieving a page pointed at by vmcs12.

> + flags |= KVM_GTP_INTERRUPTIBLE;
> fault->pfn = __gfn_to_pfn_memslot(slot, fault->gfn, flags, NULL,
> &fault->map_writable, &fault->hva);
> return RET_PF_CONTINUE;
> diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> index 4f84a442f67f..c8d98e435537 100644
> --- a/include/linux/kvm_host.h
> +++ b/include/linux/kvm_host.h
> @@ -1163,6 +1163,7 @@ typedef unsigned int __bitwise kvm_gtp_flag_t;
>
> #define KVM_GTP_WRITE ((__force kvm_gtp_flag_t) BIT(0))
> #define KVM_GTP_ATOMIC ((__force kvm_gtp_flag_t) BIT(1))
> +#define KVM_GTP_INTERRUPTIBLE ((__force kvm_gtp_flag_t) BIT(2))
>
> kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn,
> kvm_gtp_flag_t gtp_flags, bool *async,
> diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
> index 952400b42ee9..b3873cac5672 100644
> --- a/virt/kvm/kvm_main.c
> +++ b/virt/kvm/kvm_main.c
> @@ -2462,6 +2462,8 @@ static int hva_to_pfn_slow(unsigned long addr, bool *async,
> flags |= FOLL_WRITE;
> if (async)
> flags |= FOLL_NOWAIT;
> + if (gtp_flags & KVM_GTP_INTERRUPTIBLE)
> + flags |= FOLL_INTERRUPTIBLE;
>
> npages = get_user_pages_unlocked(addr, 1, &page, flags);
> if (npages != 1)
> @@ -2599,6 +2601,8 @@ kvm_pfn_t hva_to_pfn(unsigned long addr, kvm_gtp_flag_t gtp_flags, bool *async,
> npages = hva_to_pfn_slow(addr, async, gtp_flags, writable, &pfn);
> if (npages == 1)
> return pfn;
> + if (npages == -EINTR)
> + return KVM_PFN_ERR_INTR;
>
> mmap_read_lock(current->mm);
> if (npages == -EHWPOISON ||
> --
> 2.32.0
>