kvm/eventfd: Use priority waitqueue to catch events before userspace

As far as I can tell, when we use posted interrupts we silently cut off
the events from userspace, if it's listening on the same eventfd that
feeds the irqfd.

I like that behaviour. Let's do it all the time, even without posted
interrupts. It makes it much easier to handle IRQ remapping invalidation
without having to constantly add/remove the fd from the userspace poll
set. We can just leave userspace polling on it, and the bypass will...
well... bypass it.

Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
Message-Id: <20201026175325.585623-2-dwmw2@infradead.org>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
This commit is contained in:
David Woodhouse 2020-10-26 17:53:25 +00:00 committed by Paolo Bonzini
parent c4d51a52c6
commit e8dbf19508
1 changed files with 4 additions and 2 deletions

View File

@ -191,6 +191,7 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
struct kvm *kvm = irqfd->kvm;
unsigned seq;
int idx;
int ret = 0;
if (flags & EPOLLIN) {
idx = srcu_read_lock(&kvm->irq_srcu);
@ -204,6 +205,7 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
false) == -EWOULDBLOCK)
schedule_work(&irqfd->inject);
srcu_read_unlock(&kvm->irq_srcu, idx);
ret = 1;
}
if (flags & EPOLLHUP) {
@ -227,7 +229,7 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
spin_unlock_irqrestore(&kvm->irqfds.lock, iflags);
}
return 0;
return ret;
}
static void
@ -236,7 +238,7 @@ irqfd_ptable_queue_proc(struct file *file, wait_queue_head_t *wqh,
{
struct kvm_kernel_irqfd *irqfd =
container_of(pt, struct kvm_kernel_irqfd, pt);
add_wait_queue(wqh, &irqfd->wait);
add_wait_queue_priority(wqh, &irqfd->wait);
}
/* Must be called under irqfds.lock */