Skip to contentSkip to conversation

udp: Avoid post-GRO UDP checksum recalculation

PATCH In review Sean Tranchetti 3 participants 3 messages May 28, 2019 – May 30, 2019

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

PATCH v2 1/1 udp: Avoid post-GRO UDP checksum recalculation

Currently, when resegmenting an unexpected UDP GRO packet, the full UDP checksum will be calculated for every new SKB created by skb_segment() because the netdev features passed in by udp_rcv_segment() lack any information about checksum offload capabilities.

Usually, we have no need to perform this calculation again, as
1) The GRO implementation guarantees that any packets making it to the udp_rcv_segment() function had correct checksums, and, more importantly,
2) Upon the successful return of udp_rcv_segment(), we immediately pull the UDP header off and either queue the segment to the socket or hand it off to a new protocol handler.

Unless userspace has set the IP_CHECKSUM sockopt to indicate that they want the final checksum values, we can pass the needed netdev feature flags to __skb_gso_segment() to avoid checksumming each segment in skb_segment().

Fixes cf329aa42b66 ("udp: cope with UDP GRO packet misdirection")
Cc Paolo Abeni <[email protected]>
Cc Subash Abhinov Kasiviswanathan <[email protected]>
---
 include/net/udp.h | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)
include/net/udp.h +8 -1
index d8ce937..dbe030d 100644
@@ -471,12 +471,19 @@ struct udp_iter_state {
 static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
 					      struct sk_buff *skb, bool ipv4)
 {
+	netdev_features_t features = NETIF_F_SG;
 	struct sk_buff *segs;
 
+	/* Avoid csum recalculation by skb_segment unless userspace explicitly
+	 * asks for the final checksum values
+	 */
+	if (!inet_get_convert_csum(sk))
+		features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+
 	/* the GSO CB lays after the UDP one, no need to save and restore any
 	 * CB fragment
 	 */
-	segs = __skb_gso_segment(skb, NETIF_F_SG, false);
+	segs = __skb_gso_segment(skb, features, false);
 	if (unlikely(IS_ERR_OR_NULL(segs))) {
 		int segs_nr = skb_shinfo(skb)->gso_segs;
 
Signature · 1 line
1.9.1
maintainer Acked-by on v2 1/1
#1 lore raw
Quoted 40 lines · Sean Tranchetti

Currently, when resegmenting an unexpected UDP GRO packet, the full UDP checksum will be calculated for every new SKB created by skb_segment() because the netdev features passed in by udp_rcv_segment() lack any information about checksum offload capabilities.

Usually, we have no need to perform this calculation again, as
1) The GRO implementation guarantees that any packets making it to the udp_rcv_segment() function had correct checksums, and, more importantly,
2) Upon the successful return of udp_rcv_segment(), we immediately pull the UDP header off and either queue the segment to the socket or hand it off to a new protocol handler.

Unless userspace has set the IP_CHECKSUM sockopt to indicate that they want the final checksum values, we can pass the needed netdev feature flags to __skb_gso_segment() to avoid checksumming each segment in skb_segment().

Fixes cf329aa42b66 ("udp: cope with UDP GRO packet misdirection")
Cc Paolo Abeni <[email protected]>
Cc Subash Abhinov Kasiviswanathan <[email protected]>
---
 include/net/udp.h | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)
include/net/udp.h +4 -0
index d8ce937..dbe030d 100644
@@ -471,12 +471,19 @@ struct udp_iter_state {
 static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
 					      struct sk_buff *skb, bool ipv4)
 {
+	netdev_features_t features = NETIF_F_SG;
 	struct sk_buff *segs;
 
+	/* Avoid csum recalculation by skb_segment unless userspace explicitly
+	 * asks for the final checksum values
+	 */

include/net/udp.h struct udp_iter_state { · line 488

Quoted 10 lines
include/net/udp.h +4 -1
+	if (!inet_get_convert_csum(sk))
+		features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM;
+
 	/* the GSO CB lays after the UDP one, no need to save and restore any
 	 * CB fragment
 	 */
-	segs = __skb_gso_segment(skb, NETIF_F_SG, false);
+	segs = __skb_gso_segment(skb, features, false);
 	if (unlikely(IS_ERR_OR_NULL(segs))) {
 		int segs_nr = skb_shinfo(skb)->gso_segs;

The patch itself LGTM, thanks.

Possibly this can target the 'net' tree as the relevant commit is already there and the patch itself is not very invasive.

Paolo

maintainer
#2 lore raw
In reply to Sean Tranchetti

From: Sean Tranchetti <[email protected]>
Date: Tue, 28 May 2019 12:22:54 -0600

Quoted 18 lines

Currently, when resegmenting an unexpected UDP GRO packet, the full UDP checksum will be calculated for every new SKB created by skb_segment() because the netdev features passed in by udp_rcv_segment() lack any information about checksum offload capabilities.

Usually, we have no need to perform this calculation again, as
1) The GRO implementation guarantees that any packets making it to the udp_rcv_segment() function had correct checksums, and, more importantly,
2) Upon the successful return of udp_rcv_segment(), we immediately pull the UDP header off and either queue the segment to the socket or hand it off to a new protocol handler.

Unless userspace has set the IP_CHECKSUM sockopt to indicate that they want the final checksum values, we can pass the needed netdev feature flags to __skb_gso_segment() to avoid checksumming each segment in skb_segment().

Quoted 4 lines
Fixes cf329aa42b66 ("udp: cope with UDP GRO packet misdirection")
Cc Paolo Abeni <[email protected]>
Cc Subash Abhinov Kasiviswanathan <[email protected]>

I've decided to apply this to 'net', thank you.