xfrm: hold device only for the asynchronous decryption

The dev_hold() on skb->dev during packet reception was originally
added to prevent the device from being released prematurely during
asynchronous decryption operations.

As current hardware can offload decryption, this asynchronous path is
not always utilized. This often results in a pattern of dev_hold()
immediately followed by dev_put() for each packet, creating
unnecessary reference counting overhead detrimental to performance.

This patch optimizes this by skipping the dev_hold() and subsequent
dev_put() when asynchronous decryption is not being performed.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Cosmin Ratiu <cratiu@nvidia.com>
Signed-off-by: Steffen Klassert <steffen.klassert@secunet.com>

Author: Jianbo Liu

net/xfrm/xfrm_input.c

@@ -503,6 +503,7 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 		/* An encap_type of -1 indicates async resumption. */
 		if (encap_type == -1) {
 			async = 1;
+			dev_put(skb->dev);
 			seq = XFRM_SKB_CB(skb)->seq.input.low;
 			goto resume;
 		}
@@ -649,18 +650,18 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
 		XFRM_SKB_CB(skb)->seq.input.low = seq;
 		XFRM_SKB_CB(skb)->seq.input.hi = seq_hi;
 
-		dev_hold(skb->dev);
-
-		if (crypto_done)
+		if (crypto_done) {
 			nexthdr = x->type_offload->input_tail(x, skb);
-		else
+		} else {
+			dev_hold(skb->dev);
+
 			nexthdr = x->type->input(x, skb);
+			if (nexthdr == -EINPROGRESS)
+				return 0;
 
-		if (nexthdr == -EINPROGRESS)
-			return 0;
+			dev_put(skb->dev);
+		}
 resume:
-		dev_put(skb->dev);
-
 		spin_lock(&x->lock);
 		if (nexthdr < 0) {
 			if (nexthdr == -EBADMSG) {