[PATCH 3/5] x86: KVM: remove the dummy allocation case from async page fault handling

[Paolo Bonzini]

The page ready notification for asynchronous page faults is delivered as
an interrupt to the same vCPU that received the not-present exception.
As long as interrupts are not enabled before the page fault is registered
in the sleepers' hash table, the page ready notification must happen
after a prior registration.

This is now the case indeed, so the dummy allocation case is dead and
can be dropped.

Note however that a write of the apf-enable MSR that goes from enabled
to enabled might trigger *both* a broadcast notification interrupt
and, later, individual interrupts for pending asynchronous page faults.
While Linux will never do such a write, the host might do a KVM_SET_MSRS
call that would result in the broadcast notification, so do not complain
too loudly if the wait does not find a token and only do a pr_once().

Signed-off-by: Paolo Bonzini <pbonzini@xxxxxxxxxx>
---
 arch/x86/include/asm/kvm_para.h |  1 -
 arch/x86/kernel/kvm.c           | 66 ++++++++-------------------------
 2 files changed, 15 insertions(+), 52 deletions(-)

diff --git a/arch/x86/include/asm/kvm_para.h b/arch/x86/include/asm/kvm_para.h
index 1e28c89b1405..b986edb1a225 100644
--- a/arch/x86/include/asm/kvm_para.h
+++ b/arch/x86/include/asm/kvm_para.h
@@ -123,7 +123,6 @@ struct kvm_task_sleep_node {
 	struct swait_queue_head wq;
 	u32 token;
 	int cpu;
-	bool dummy;
 };
 
 #ifdef CONFIG_KVM_GUEST
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index d3a0e0d7bb84..ad0b6a4ad097 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -111,26 +111,11 @@ bool kvm_async_pf_queue_task(u32 token, struct kvm_task_sleep_node *n)
 	raw_spin_lock(&b->lock);
 	e = _find_apf_task(b, token);
 	if (e) {
-		struct kvm_task_sleep_node *dummy = NULL;
-
-		/*
-		 * The entry can either be a 'dummy' entry (which is put on the
-		 * list when wake-up happens ahead of APF handling completion)
-		 * or a token from another task which should not be touched.
-		 */
-		if (e->dummy) {
-			hlist_del(&e->link);
-			dummy = e;
-		}
-
 		raw_spin_unlock(&b->lock);
-		kfree(dummy);
 		return false;
 	}
-
 	n->token = token;
 	n->cpu = smp_processor_id();
-	n->dummy = false;
 	init_swait_queue_head(&n->wq);
 	hlist_add_head(&n->link, &b->list);
 	raw_spin_unlock(&b->lock);
@@ -200,53 +185,32 @@ static void kvm_async_pf_task_wake(u32 token)
 {
 	u32 key = hash_32(token, KVM_TASK_SLEEP_HASHBITS);
 	struct kvm_task_sleep_head *b = &async_pf_sleepers[key];
-	struct kvm_task_sleep_node *n, *dummy = NULL;
+	struct kvm_task_sleep_node *n;
 
 	if (token == ~0) {
 		apf_task_wake_all();
 		return;
 	}
 
-again:
 	raw_spin_lock(&b->lock);
 	n = _find_apf_task(b, token);
-	if (!n) {
-		/*
-		 * Async #PF not yet handled, add a dummy entry for the token.
-		 * Allocating the token must be down outside of the raw lock
-		 * as the allocator is preemptible on PREEMPT_RT kernels.
-		 */
-		if (!dummy) {
-			raw_spin_unlock(&b->lock);
-			dummy = kzalloc_obj(*dummy, GFP_ATOMIC);
 
-			/*
-			 * Continue looping on allocation failure, eventually
-			 * the async #PF will be handled and allocating a new
-			 * node will be unnecessary.
-			 */
-			if (!dummy)
-				cpu_relax();
-
-			/*
-			 * Recheck for async #PF completion before enqueueing
-			 * the dummy token to avoid duplicate list entries.
-			 */
-			goto again;
-		}
-		dummy->token = token;
-		dummy->cpu = smp_processor_id();
-		dummy->dummy = true;
-		init_swait_queue_head(&dummy->wq);
-		hlist_add_head(&dummy->link, &b->list);
-		dummy = NULL;
-	} else {
+	/*
+	 * A broadcast wakeup, which can happen for example if the VMM calls
+	 * KVM_SET_MSRS, might still leave the individual wakeups queued.
+	 * In that case _find_apf_task() will not find the token when the
+	 * individual wakeup comes, so just ignore the case where n is NULL.
+	 * Nevertheless it *should* not happen, so print a message for the
+	 * user in case something bad actually happens later.
+	 */
+	if (n)
 		apf_task_wake_one(n);
-	}
-	raw_spin_unlock(&b->lock);
+	else
+		pr_info_once("Async page fault waiter not found. This is probably triggered "
+			     "by the host and harmless. However, if a userspace task hangs, "
+			     "please include this message in your bug report.\n");
 
-	/* A dummy token might be allocated and ultimately not used.  */
-	kfree(dummy);
+	raw_spin_unlock(&b->lock);
 }
 
 noinstr u32 kvm_read_and_reset_apf_flags(void)
-- 
2.56.0