Skip to contentSkip to conversation

net: correct udp zerocopy refcnt also when zerocopy only on append

PATCH Applied Willem de Bruijn 2 participants 2 messages Jun 7, 2019 – Jun 11, 2019

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

PATCH 1/1 net: correct udp zerocopy refcnt also when zerocopy only on append

From: Willem de Bruijn <[email protected]>

The below patch fixes an incorrect zerocopy refcnt increment when appending with MSG_MORE to an existing zerocopy udp skb.

send(.., MSG_ZEROCOPY | MSG_MORE); // refcnt 1
send(.., MSG_ZEROCOPY | MSG_MORE); // refcnt still 1 (bar frags)

But it missed that zerocopy need not be passed at the first send. The right test whether the uarg is newly allocated and thus has extra refcnt 1 is not !skb, but !skb_zcopy.

send(.., MSG_MORE); // <no uarg>
send(.., MSG_ZEROCOPY); // refcnt 1

Fixes 100f6d8e09905 ("net: correct zerocopy refcnt with udp MSG_MORE")
---
 net/ipv4/ip_output.c  | 2 +-
 net/ipv6/ip6_output.c | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)
net/ipv4/ip_output.c +1 -1
index 8c9189a41b136..16f9159234a20 100644
@@ -918,7 +918,7 @@ static int __ip_append_data(struct sock *sk,
 		uarg = sock_zerocopy_realloc(sk, length, skb_zcopy(skb));
 		if (!uarg)
 			return -ENOBUFS;
-		extra_uref = !skb;	/* only extra ref if !MSG_MORE */
+		extra_uref = !skb_zcopy(skb);	/* only ref on new uarg */
 		if (rt->dst.dev->features & NETIF_F_SG &&
 		    csummode == CHECKSUM_PARTIAL) {
 			paged = true;
net/ipv6/ip6_output.c +1 -1
index 934c88f128abb..834475717110e 100644
@@ -1340,7 +1340,7 @@ static int __ip6_append_data(struct sock *sk,
 		uarg = sock_zerocopy_realloc(sk, length, skb_zcopy(skb));
 		if (!uarg)
 			return -ENOBUFS;
-		extra_uref = !skb;	/* only extra ref if !MSG_MORE */
+		extra_uref = !skb_zcopy(skb);	/* only ref on new uarg */
 		if (rt->dst.dev->features & NETIF_F_SG &&
 		    csummode == CHECKSUM_PARTIAL) {
 			paged = true;
Signature · 1 line
2.22.0.rc2.383.gf4fbbf30c2-goog
maintainer Applied
#1 lore raw

From: Willem de Bruijn <[email protected]>
Date: Fri, 7 Jun 2019 17:57:48 -0400

Quoted 12 lines

From: Willem de Bruijn <[email protected]>

The below patch fixes an incorrect zerocopy refcnt increment when appending with MSG_MORE to an existing zerocopy udp skb.

send(.., MSG_ZEROCOPY | MSG_MORE); // refcnt 1
send(.., MSG_ZEROCOPY | MSG_MORE); // refcnt still 1 (bar frags)

But it missed that zerocopy need not be passed at the first send. The right test whether the uarg is newly allocated and thus has extra refcnt 1 is not !skb, but !skb_zcopy.

Quoted 6 lines

send(.., MSG_MORE); // <no uarg>
send(.., MSG_ZEROCOPY); // refcnt 1

Fixes 100f6d8e09905 ("net: correct zerocopy refcnt with udp MSG_MORE")

Applied, thanks Willem.