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 <[e-mail]>
Signed-off-by: Kaiyuan Zhang <[e-mail]>
Signed-off-by: Mina Almasry <[e-mail]>
Reviewed-by: Eric Dumazet <[e-mail]>
Reviewed-by: Jakub Kicinski <[e-mail]>
Link: https://patch.msgid.link/[e-mail]
Signed-off-by: Jakub Kicinski <[e-mail]>

include/linux/skbuff.h

···
  *	@csum_level: indicates the number of consecutive checksums found in
  *		the packet minus one that have been verified as
  *		CHECKSUM_UNNECESSARY (max 3)
+ *	@unreadable: indicates that at least 1 of the fragments in this skb is
+ *		unreadable.
  *	@dst_pending_confirm: need to confirm neighbour
  *	@decrypted: Decrypted SKB
  *	@slow_gro: state present at GRO time, slower prepare step required
···
 #if IS_ENABLED(CONFIG_IP_SCTP)
 	__u8			csum_not_inet:1;
 #endif
-
+	__u8			unreadable:1;
 #if defined(CONFIG_NET_SCHED) || defined(CONFIG_NET_XGRESS)
 	__u16			tc_index;	/* traffic control index */
 #endif
···
 		__skb_zcopy_downgrade_managed(skb);
 }
 
+/* Return true if frags in this skb are readable by the host. */
+static inline bool skb_frags_readable(const struct sk_buff *skb)
+{
+	return !skb->unreadable;
+}
+
 static inline void skb_mark_not_on_list(struct sk_buff *skb)
 {
 	skb->next = NULL;
···
 static inline void __skb_fill_netmem_desc(struct sk_buff *skb, int i,
 					  netmem_ref netmem, int off, int size)
 {
-	struct page *page = netmem_to_page(netmem);
+	struct page *page;
 
 	__skb_fill_netmem_desc_noacc(skb_shinfo(skb), i, netmem, off, size);
+
+	if (netmem_is_net_iov(netmem)) {
+		skb->unreadable = true;
+		return;
+	}
+
+	page = netmem_to_page(netmem);
 
 	/* Propagate page pfmemalloc to the skb if we can. The problem is
 	 * that not all callers have unique ownership of the page but rely

include/net/tcp.h

···
 	/* skb_cmp_decrypted() not needed, use tcp_write_collapse_fence() */
 	return likely(tcp_skb_can_collapse_to(to) &&
 		      mptcp_skb_can_collapse(to, from) &&
-		      skb_pure_zcopy_same(to, from));
+		      skb_pure_zcopy_same(to, from) &&
+		      skb_frags_readable(to) == skb_frags_readable(from));
 }
 
 static inline bool tcp_skb_can_collapse_rx(const struct sk_buff *to,

net/core/datagram.c

···
 			return 0;
 	}
 
+	if (!skb_frags_readable(skb))
+		goto short_copy;
+
 	/* Copy paged appendix. Hmm... why does this look so complicated? */
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		int end;
···
 				struct iov_iter *from, size_t length)
 {
 	int frag = skb_shinfo(skb)->nr_frags;
+
+	if (!skb_frags_readable(skb))
+		return -EFAULT;
 
 	while (length && iov_iter_count(from)) {
 		struct page *head, *last_head = NULL;

net/core/dev.c

···
 		return -EINVAL;
 	}
 
+	if (!skb_frags_readable(skb)) {
+		return -EFAULT;
+	}
+
 	/* Before computing a checksum, we should make sure no frag could
 	 * be modified by an external entity : checksum could be wrong.
 	 */

net/core/skbuff.c

···
 	if (skb_shared(skb) || skb_unclone(skb, gfp_mask))
 		return -EINVAL;
 
+	if (!skb_frags_readable(skb))
+		return -EFAULT;
+
 	if (!num_frags)
 		goto release;
 
···
 	struct sk_buff *n;
 	unsigned int size;
 	int headerlen;
+
+	if (!skb_frags_readable(skb))
+		return NULL;
 
 	if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST))
 		return NULL;
···
 	int head_copy_len, head_copy_off;
 	struct sk_buff *n;
 	int oldheadroom;
+
+	if (!skb_frags_readable(skb))
+		return NULL;
 
 	if (WARN_ON_ONCE(skb_shinfo(skb)->gso_type & SKB_GSO_FRAGLIST))
 		return NULL;
···
 	 */
 	int i, k, eat = (skb->tail + delta) - skb->end;
 
+	if (!skb_frags_readable(skb))
+		return NULL;
+
 	if (eat > 0 || skb_cloned(skb)) {
 		if (pskb_expand_head(skb, 0, eat > 0 ? eat + 128 : 0,
 				     GFP_ATOMIC))
···
 		offset += copy;
 		to     += copy;
 	}
+
+	if (!skb_frags_readable(skb))
+		goto fault;
 
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		int end;
···
 	/*
 	 * then map the fragments
 	 */
+	if (!skb_frags_readable(skb))
+		return false;
+
 	for (seg = 0; seg < skb_shinfo(skb)->nr_frags; seg++) {
 		const skb_frag_t *f = &skb_shinfo(skb)->frags[seg];
 
···
 		from += copy;
 	}
 
+	if (!skb_frags_readable(skb))
+		goto fault;
+
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
 		int end;
···
 		offset += copy;
 		pos	= copy;
 	}
+
+	if (WARN_ON_ONCE(!skb_frags_readable(skb)))
+		return 0;
 
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		int end;
···
 		to     += copy;
 		pos	= copy;
 	}
+
+	if (!skb_frags_readable(skb))
+		return 0;
 
 	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
 		int end;
···
 		skb_shinfo(skb1)->frags[i] = skb_shinfo(skb)->frags[i];
 
 	skb_shinfo(skb1)->nr_frags = skb_shinfo(skb)->nr_frags;
+	skb1->unreadable	   = skb->unreadable;
 	skb_shinfo(skb)->nr_frags  = 0;
 	skb1->data_len		   = skb->data_len;
 	skb1->len		   += skb1->data_len;
···
 		pos += size;
 	}
 	skb_shinfo(skb1)->nr_frags = k;
+
+	skb1->unreadable = skb->unreadable;
 }
 
 /**
···
 		*data = st->cur_skb->data + (abs_offset - st->stepped_offset);
 		return block_limit - abs_offset;
 	}
+
+	if (!skb_frags_readable(st->cur_skb))
+		return 0;
 
 	if (st->frag_idx == 0 && !st->frag_data)
 		st->stepped_offset += skb_headlen(st->cur_skb);
···
 	if (to->pp_recycle != from->pp_recycle)
 		return false;
 
-	if (len <= skb_tailroom(to)) {
+	if (skb_frags_readable(from) != skb_frags_readable(to))
+		return false;
+
+	if (len <= skb_tailroom(to) && skb_frags_readable(from)) {
 		if (len)
 			BUG_ON(skb_copy_bits(from, 0, skb_put(to, len), len));
 		*delta_truesize = 0;
···
 {
 	if (!pskb_may_pull(skb, write_len))
 		return -ENOMEM;
+
+	if (!skb_frags_readable(skb))
+		return -EFAULT;
 
 	if (!skb_cloned(skb) || skb_clone_writable(skb, write_len))
 		return 0;
···
 {
 	if (skb->data_len) {
 		if (skb->data_len > skb->end - skb->tail ||
-		    skb_cloned(skb))
+		    skb_cloned(skb) || !skb_frags_readable(skb))
 			return;
 
 		/* Nice, we can free page frag(s) right now */

net/ipv4/tcp.c

···
 				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;

net/ipv4/tcp_input.c

···
 	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);
···
 			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);
···
 				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;
 			}
 		}

net/ipv4/tcp_output.c

···
 
 		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;
···
 	if (tcp_skb_pcount(skb) > 1)
 		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)

net/packet/af_packet.c

···
 		}
 	}
 
-	snaplen = skb->len;
+	snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb);
 
 	res = run_filter(skb, sk, snaplen);
 	if (!res)
···
 		}
 	}
 
-	snaplen = skb->len;
+	snaplen = skb_frags_readable(skb) ? skb->len : skb_headlen(skb);
 
 	res = run_filter(skb, sk, snaplen);
 	if (!res)