net: add support for skbs with unreadable frags

For device memory TCP, we expect the skb headers to be available in host
memory for access, and we expect the skb frags to be in device memory
and unaccessible to the host. We expect there to be no mixing and
matching of device memory frags (unaccessible) with host memory frags
(accessible) in the same skb.

Add a skb->devmem flag which indicates whether the frags in this skb
are device memory frags or not.

__skb_fill_netmem_desc() now checks frags added to skbs for net_iov,
and marks the skb as skb->devmem accordingly.

Add checks through the network stack to avoid accessing the frags of
devmem skbs and avoid coalescing devmem skbs with non devmem skbs.

Signed-off-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Kaiyuan Zhang <kaiyuanz@google.com>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Link: https://patch.msgid.link/20240910171458.219195-9-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

3 files changed, 17 insertions, 4 deletions

diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 06dcf89e2cca..a2fac029a84a 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2160,6 +2160,9 @@ static int tcp_zerocopy_receive(struct sock *sk,
 				skb = tcp_recv_skb(sk, seq, &offset);
 			}
 
+			if (!skb_frags_readable(skb))
+				break;
+
 			if (TCP_SKB_CB(skb)->has_rxtstamp) {
 				tcp_update_recv_tstamps(skb, tss);
 				zc->msg_flags |= TCP_CMSG_TS;
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index e37488d3453f..9f314dfa1490 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -5391,6 +5391,9 @@ restart:
 	for (end_of_skbs = true; skb != NULL && skb != tail; skb = n) {
 		n = tcp_skb_next(skb, list);
 
+		if (!skb_frags_readable(skb))
+			goto skip_this;
+
 		/* No new bits? It is possible on ofo queue. */
 		if (!before(start, TCP_SKB_CB(skb)->end_seq)) {
 			skb = tcp_collapse_one(sk, skb, list, root);
@@ -5411,17 +5414,20 @@ restart:
 			break;
 		}
 
-		if (n && n != tail && tcp_skb_can_collapse_rx(skb, n) &&
+		if (n && n != tail && skb_frags_readable(n) &&
+		    tcp_skb_can_collapse_rx(skb, n) &&
 		    TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) {
 			end_of_skbs = false;
 			break;
 		}
 
+skip_this:
 		/* Decided to skip this, advance start seq. */
 		start = TCP_SKB_CB(skb)->end_seq;
 	}
 	if (end_of_skbs ||
-	    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
+	    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) ||
+	    !skb_frags_readable(skb))
 		return;
 
 	__skb_queue_head_init(&tmp);
@@ -5463,7 +5469,8 @@ restart:
 				if (!skb ||
 				    skb == tail ||
 				    !tcp_skb_can_collapse_rx(nskb, skb) ||
-				    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
+				    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) ||
+				    !skb_frags_readable(skb))
 					goto end;
 			}
 		}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index cdd0def14427..4fd746bd4d54 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2344,7 +2344,8 @@ static bool tcp_can_coalesce_send_queue_head(struct sock *sk, int len)
 
 		if (unlikely(TCP_SKB_CB(skb)->eor) ||
 		    tcp_has_tx_tstamp(skb) ||
-		    !skb_pure_zcopy_same(skb, next))
+		    !skb_pure_zcopy_same(skb, next) ||
+		    skb_frags_readable(skb) != skb_frags_readable(next))
 			return false;
 
 		len -= skb->len;
@@ -3264,6 +3265,8 @@ static bool tcp_can_collapse(const struct sock *sk, const struct sk_buff *skb)
 		return false;
 	if (skb_cloned(skb))
 		return false;
+	if (!skb_frags_readable(skb))
+		return false;
 	/* Some heuristics for collapsing over SACK'd could be invented */
 	if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
 		return false;