diff mbox series

[v10,18/19] KVM: pfncache: check the need for invalidation under read lock first

Message ID 20231204144334.910-19-paul@xen.org
State Superseded
Headers show
Series KVM: xen: update shared_info and vcpu_info handling | expand

Commit Message

Paul Durrant Dec. 4, 2023, 2:43 p.m. UTC
From: Paul Durrant <pdurrant@amazon.com>

Taking a write lock on a pfncache will be disruptive if the cache is
heavily used (which only requires a read lock). Hence, in the MMU notifier
callback, take read locks on caches to check for a match; only taking a
write lock to actually perform an invalidation (after a another check).

Signed-off-by: Paul Durrant <pdurrant@amazon.com>
---
Cc: Sean Christopherson <seanjc@google.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: David Woodhouse <dwmw2@infradead.org>

v10:
 - New in this version.
---
 virt/kvm/pfncache.c | 22 +++++++++++++++++++---
 1 file changed, 19 insertions(+), 3 deletions(-)

Comments

David Woodhouse Dec. 14, 2023, 2:08 p.m. UTC | #1
On Mon, 2023-12-04 at 14:43 +0000, Paul Durrant wrote:
> From: Paul Durrant <pdurrant@amazon.com>
> 
> Taking a write lock on a pfncache will be disruptive if the cache is
> heavily used (which only requires a read lock). Hence, in the MMU notifier
> callback, take read locks on caches to check for a match; only taking a
> write lock to actually perform an invalidation (after a another check).
> 
> Signed-off-by: Paul Durrant <pdurrant@amazon.com>

Reviewed-by: David Woodhouse <dwmw@amazon.co.uk>

In particular, the previous 'don't block on pfncache locks in
kvm_xen_set_evtchn_fast()' patch in this series is easy to justify on
the basis that it only falls back to the slow path if it can't take a
read lock immediately. And surely it should *always* be able to take a
read lock immediately unless there's an actual *writer* — which should
be a rare event, and means the cache was probably going to be
invalidates anyway.

But then we realised the MMU notifier was going to disrupt that.



> ---
> Cc: Sean Christopherson <seanjc@google.com>
> Cc: Paolo Bonzini <pbonzini@redhat.com>
> Cc: David Woodhouse <dwmw2@infradead.org>
> 
> v10:
>  - New in this version.
> ---
>  virt/kvm/pfncache.c | 22 +++++++++++++++++++---
>  1 file changed, 19 insertions(+), 3 deletions(-)
> 
> diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c
> index c2a2d1e145b6..4da16d494f4b 100644
> --- a/virt/kvm/pfncache.c
> +++ b/virt/kvm/pfncache.c
> @@ -29,14 +29,30 @@ void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start,
>  
>         spin_lock(&kvm->gpc_lock);
>         list_for_each_entry(gpc, &kvm->gpc_list, list) {
> -               write_lock_irq(&gpc->lock);
> +               read_lock_irq(&gpc->lock);
>  
>                 /* Only a single page so no need to care about length */
>                 if (gpc->valid && !is_error_noslot_pfn(gpc->pfn) &&
>                     gpc->uhva >= start && gpc->uhva < end) {
> -                       gpc->valid = false;
> +                       read_unlock_irq(&gpc->lock);
> +
> +                       /*
> +                        * There is a small window here where the cache could
> +                        * be modified, and invalidation would no longer be
> +                        * necessary. Hence check again whether invalidation
> +                        * is still necessary once the write lock has been
> +                        * acquired.
> +                        */
> +
> +                       write_lock_irq(&gpc->lock);
> +                       if (gpc->valid && !is_error_noslot_pfn(gpc->pfn) &&
> +                           gpc->uhva >= start && gpc->uhva < end)
> +                               gpc->valid = false;
> +                       write_unlock_irq(&gpc->lock);
> +                       continue;
>                 }
> -               write_unlock_irq(&gpc->lock);
> +
> +               read_unlock_irq(&gpc->lock);
>         }
>         spin_unlock(&kvm->gpc_lock);
>  }
diff mbox series

Patch

diff --git a/virt/kvm/pfncache.c b/virt/kvm/pfncache.c
index c2a2d1e145b6..4da16d494f4b 100644
--- a/virt/kvm/pfncache.c
+++ b/virt/kvm/pfncache.c
@@ -29,14 +29,30 @@  void gfn_to_pfn_cache_invalidate_start(struct kvm *kvm, unsigned long start,
 
 	spin_lock(&kvm->gpc_lock);
 	list_for_each_entry(gpc, &kvm->gpc_list, list) {
-		write_lock_irq(&gpc->lock);
+		read_lock_irq(&gpc->lock);
 
 		/* Only a single page so no need to care about length */
 		if (gpc->valid && !is_error_noslot_pfn(gpc->pfn) &&
 		    gpc->uhva >= start && gpc->uhva < end) {
-			gpc->valid = false;
+			read_unlock_irq(&gpc->lock);
+
+			/*
+			 * There is a small window here where the cache could
+			 * be modified, and invalidation would no longer be
+			 * necessary. Hence check again whether invalidation
+			 * is still necessary once the write lock has been
+			 * acquired.
+			 */
+
+			write_lock_irq(&gpc->lock);
+			if (gpc->valid && !is_error_noslot_pfn(gpc->pfn) &&
+			    gpc->uhva >= start && gpc->uhva < end)
+				gpc->valid = false;
+			write_unlock_irq(&gpc->lock);
+			continue;
 		}
-		write_unlock_irq(&gpc->lock);
+
+		read_unlock_irq(&gpc->lock);
 	}
 	spin_unlock(&kvm->gpc_lock);
 }