On Sat, Jan 20, 2024, Xu Yilun wrote:
> On Tue, Jan 09, 2024 at 05:15:32PM -0800, Sean Christopherson wrote:
> > Get a reference to the target VM's address space in async_pf_execute()
> > instead of gifting a reference from kvm_setup_async_pf(). Keeping the
> > address space alive just to service an async #PF is counter-productive,
> > i.e. if the process is exiting and all vCPUs are dead, then NOT doing
> > get_user_pages_remote() and freeing the address space asap is desirable.
> >
> > Handling the mm reference entirely within async_pf_execute() also
> > simplifies the async #PF flows as a whole, e.g. it's not immediately
> > obvious when the worker task vs. the vCPU task is responsible for putting
> > the gifted mm reference.
> >
> > Signed-off-by: Sean Christopherson <seanjc@xxxxxxxxxx>
> > ---
> > include/linux/kvm_host.h | 1 -
> > virt/kvm/async_pf.c | 32 ++++++++++++++++++--------------
> > 2 files changed, 18 insertions(+), 15 deletions(-)
> >
> > diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
> > index 7e7fd25b09b3..bbfefd7e612f 100644
> > --- a/include/linux/kvm_host.h
> > +++ b/include/linux/kvm_host.h
> > @@ -238,7 +238,6 @@ struct kvm_async_pf {
> > struct list_head link;
> > struct list_head queue;
> > struct kvm_vcpu *vcpu;
> > - struct mm_struct *mm;
> > gpa_t cr2_or_gpa;
> > unsigned long addr;
> > struct kvm_arch_async_pf arch;
> > diff --git a/virt/kvm/async_pf.c b/virt/kvm/async_pf.c
> > index d5dc50318aa6..c3f4f351a2ae 100644
> > --- a/virt/kvm/async_pf.c
> > +++ b/virt/kvm/async_pf.c
> > @@ -46,8 +46,8 @@ static void async_pf_execute(struct work_struct *work)
> > {
> > struct kvm_async_pf *apf =
> > container_of(work, struct kvm_async_pf, work);
> > - struct mm_struct *mm = apf->mm;
> > struct kvm_vcpu *vcpu = apf->vcpu;
> > + struct mm_struct *mm = vcpu->kvm->mm;
> > unsigned long addr = apf->addr;
> > gpa_t cr2_or_gpa = apf->cr2_or_gpa;
> > int locked = 1;
> > @@ -56,16 +56,24 @@ static void async_pf_execute(struct work_struct *work)
> > might_sleep();
> >
> > /*
> > - * This work is run asynchronously to the task which owns
> > - * mm and might be done in another context, so we must
> > - * access remotely.
> > + * Attempt to pin the VM's host address space, and simply skip gup() if
> > + * acquiring a pin fail, i.e. if the process is exiting. Note, KVM
> > + * holds a reference to its associated mm_struct until the very end of
> > + * kvm_destroy_vm(), i.e. the struct itself won't be freed before this
> > + * work item is fully processed.
> > */
> > - mmap_read_lock(mm);
> > - get_user_pages_remote(mm, addr, 1, FOLL_WRITE, NULL, &locked);
> > - if (locked)
> > - mmap_read_unlock(mm);
> > - mmput(mm);
> > + if (mmget_not_zero(mm)) {
> > + mmap_read_lock(mm);
> > + get_user_pages_remote(mm, addr, 1, FOLL_WRITE, NULL, &locked);
> > + if (locked)
> > + mmap_read_unlock(mm);
> > + mmput(mm);
> > + }
> >
> > + /*
> > + * Notify and kick the vCPU even if faulting in the page failed, e.g.
>
> How about when the process is exiting? Could we just skip the following?
Maybe? I'm not opposed to trimming this down even more, but I doubt it will make
much of a difference. The vCPU can't be running so async_pf.lock shouldn't be
contended, no IPIs will be issued for kicks, etc. So for this patch at least,
I want to take the most conservative approach while still cleaning up the mm_struct
usage.
> > + * so that the vCPU can retry the fault synchronously.
> > + */
> > if (IS_ENABLED(CONFIG_KVM_ASYNC_PF_SYNC))
> > kvm_arch_async_page_present(vcpu, apf);
> >
> > @@ -129,10 +137,8 @@ void kvm_clear_async_pf_completion_queue(struct kvm_vcpu *vcpu)
> > #ifdef CONFIG_KVM_ASYNC_PF_SYNC
> > flush_work(&work->work);
> > #else
> > - if (cancel_work_sync(&work->work)) {
> > - mmput(work->mm);
> > + if (cancel_work_sync(&work->work))
> > kmem_cache_free(async_pf_cache, work);
> > - }
> > #endif
> > spin_lock(&vcpu->async_pf.lock);
> > }
> > @@ -211,8 +217,6 @@ bool kvm_setup_async_pf(struct kvm_vcpu *vcpu, gpa_t cr2_or_gpa,
> > work->cr2_or_gpa = cr2_or_gpa;
> > work->addr = hva;
> > work->arch = *arch;
> > - work->mm = current->mm;
> > - mmget(work->mm);
> >
> > INIT_WORK(&work->work, async_pf_execute);
> >
> > --
> > 2.43.0.472.g3155946c3a-goog
> >
