Instead, to track the bytes already consumed inside each skb, use a
msk-level new field, tracking the amount of bytes already copied to
user-space, alike what TCP is already doing.

This simplify a bit the code and will make possible the next patch.

Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
Note: this has the potential to break almost everything. On the flip
side the CB->offset vs copied_seq difference from TCP is quite confusing
and removing it will be for the good.

Also this explicitly relays on "mptcp: do not drop partial packets" to
avoid dropping partially consumed packets
---
 net/mptcp/fastopen.c |  1 -
 net/mptcp/protocol.c | 30 +++++++++++-------------------
 net/mptcp/protocol.h |  2 +-
 net/mptcp/subflow.c  |  1 +
 4 files changed, 13 insertions(+), 21 deletions(-)

diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c
index 82ec15bcfd7f..fe579e45ecdf 100644
--- a/net/mptcp/fastopen.c
+++ b/net/mptcp/fastopen.c
@@ -44,7 +44,6 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf
 	/* Only the sequence delta is relevant */
 	MPTCP_SKB_CB(skb)->map_seq = -skb->len;
 	MPTCP_SKB_CB(skb)->end_seq = 0;
-	MPTCP_SKB_CB(skb)->offset = 0;
 	MPTCP_SKB_CB(skb)->has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
 	MPTCP_SKB_CB(skb)->cant_coalesce = 1;
 
diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
index ad0a289b544b..c0b77d77c268 100644
--- a/net/mptcp/protocol.c
+++ b/net/mptcp/protocol.c
@@ -161,7 +161,6 @@ static bool __mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
 
 	if (MPTCP_SKB_CB(from)->map_seq != MPTCP_SKB_CB(to)->end_seq ||
 	    unlikely(MPTCP_SKB_CB(to)->cant_coalesce) ||
-	    MPTCP_SKB_CB(from)->offset ||
 	    ((to->len + from->len) > (limit >> 3)) ||
 	    !skb_try_coalesce(to, from, fragstolen, delta))
 		return false;
@@ -343,8 +342,7 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)
 	skb_set_owner_r(skb, sk);
 }
 
-static void mptcp_init_skb(struct sock *ssk, struct sk_buff *skb, int offset,
-			   int copy_len)
+static void mptcp_init_skb(struct sock *ssk, struct sk_buff *skb, int offset)
 {
 	struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
 	bool has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
@@ -353,9 +351,8 @@ static void mptcp_init_skb(struct sock *ssk, struct sk_buff *skb, int offset,
 	 * mptcp_subflow_get_mapped_dsn() is based on the current tp->copied_seq
 	 * value
 	 */
-	MPTCP_SKB_CB(skb)->map_seq = mptcp_subflow_get_mapped_dsn(subflow);
-	MPTCP_SKB_CB(skb)->end_seq = MPTCP_SKB_CB(skb)->map_seq + copy_len;
-	MPTCP_SKB_CB(skb)->offset = offset;
+	MPTCP_SKB_CB(skb)->map_seq = mptcp_subflow_get_mapped_dsn(subflow) - offset;
+	MPTCP_SKB_CB(skb)->end_seq = MPTCP_SKB_CB(skb)->map_seq + skb->len;
 	MPTCP_SKB_CB(skb)->has_rxtstamp = has_rxtstamp;
 	MPTCP_SKB_CB(skb)->cant_coalesce = 0;
 
@@ -728,7 +725,7 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
 		if (offset < skb->len) {
 			size_t len = skb->len - offset;
 
-			mptcp_init_skb(ssk, skb, offset, len);
+			mptcp_init_skb(ssk, skb, offset);
 
 			if (own_msk) {
 				mptcp_subflow_lend_fwdmem(subflow, skb);
@@ -795,8 +792,6 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
 			pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d\n",
 				 MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq,
 				 delta);
-			MPTCP_SKB_CB(skb)->offset += delta;
-			MPTCP_SKB_CB(skb)->map_seq += delta;
 			__skb_queue_tail(&sk->sk_receive_queue, skb);
 		}
 		msk->bytes_received += end_seq - msk->ack_seq;
@@ -2050,7 +2045,7 @@ static int __mptcp_recvmsg_mskq(struct sock *sk, struct msghdr *msg,
 	int copied = 0;
 
 	skb_queue_walk_safe(&sk->sk_receive_queue, skb, tmp) {
-		u32 delta, offset = MPTCP_SKB_CB(skb)->offset;
+		u32 delta, offset = msk->copied_seq - MPTCP_SKB_CB(skb)->map_seq;
 		u32 data_len = skb->len - offset;
 		u32 count;
 		int err;
@@ -2088,11 +2083,9 @@ static int __mptcp_recvmsg_mskq(struct sock *sk, struct msghdr *msg,
 
 		if (!(flags & MSG_PEEK)) {
 			msk->bytes_consumed += count;
-			if (count < data_len) {
-				MPTCP_SKB_CB(skb)->offset += count;
-				MPTCP_SKB_CB(skb)->map_seq += count;
+			msk->copied_seq += count;
+			if (count < data_len)
 				break;
-			}
 
 			mptcp_eat_recv_skb(sk, skb);
 		} else {
@@ -3457,6 +3450,7 @@ static int mptcp_disconnect(struct sock *sk, int flags)
 
 	/* for fallback's sake */
 	WRITE_ONCE(msk->ack_seq, 0);
+	WRITE_ONCE(msk->copied_seq, 0);
 
 	WRITE_ONCE(sk->sk_shutdown, 0);
 	sk_error_report(sk);
@@ -4340,7 +4334,7 @@ static struct sk_buff *mptcp_recv_skb(struct sock *sk, u32 *off)
 		mptcp_move_skbs(sk);
 
 	while ((skb = skb_peek(&sk->sk_receive_queue)) != NULL) {
-		offset = MPTCP_SKB_CB(skb)->offset;
+		offset = msk->copied_seq - MPTCP_SKB_CB(skb)->map_seq;
 		if (offset < skb->len) {
 			*off = offset;
 			return skb;
@@ -4382,11 +4376,9 @@ static int __mptcp_read_sock(struct sock *sk, read_descriptor_t *desc,
 		copied += count;
 
 		msk->bytes_consumed += count;
-		if (count < data_len) {
-			MPTCP_SKB_CB(skb)->offset += count;
-			MPTCP_SKB_CB(skb)->map_seq += count;
+		msk->copied_seq += count;
+		if (count < data_len)
 			break;
-		}
 
 		mptcp_eat_recv_skb(sk, skb);
 	}
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 661600f8b573..dd437643e604 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -128,7 +128,6 @@
 struct mptcp_skb_cb {
 	u64 map_seq;
 	u64 end_seq;
-	u32 offset;
 	u8  has_rxtstamp;
 	u8  cant_coalesce;
 };
@@ -289,6 +288,7 @@ struct mptcp_sock {
 	u64		bytes_sent;
 	u64		snd_nxt;
 	u64		bytes_received;
+	u64		copied_seq;
 	u64		ack_seq;
 	atomic64_t	rcv_wnd_sent;
 	u64		rcv_data_fin_seq;
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
index c57ed27a5fb0..2a8d5da4aaea 100644
--- a/net/mptcp/subflow.c
+++ b/net/mptcp/subflow.c
@@ -494,6 +494,7 @@ static void subflow_set_remote_key(struct mptcp_sock *msk,
 
 	WRITE_ONCE(msk->remote_key, subflow->remote_key);
 	WRITE_ONCE(msk->ack_seq, subflow->iasn);
+	WRITE_ONCE(msk->copied_seq, subflow->iasn);
 	WRITE_ONCE(msk->can_ack, true);
 	atomic64_set(&msk->rcv_wnd_sent, subflow->iasn);
 }
-- 
2.53.0