Merge branch 'mptcp-prereq'

Mat Martineau says:

====================
Multipath TCP: Prerequisites

v6 -> v7: Rename/move ULP clone helper to make inline-friendly (patch 5)

v5 -> v6: Fix BPF accessors for sk_type and sk_protocol (patch 2), fix
the width of an __unused bitfield (patch 6), and add some commit message
and comment text (patches 5 & 7).

v4 -> v5: Cover letter subject fix. No changes to commits.

v3 -> v4: Update coalesce/collapse of incoming MPTCP skbs (patch 7)

v2 -> v3: Ensure sk_type alignment in struct sock (patch 2)

v1 -> v2: sk_pacing_shift left as a regular struct member (patch 2), and
modified SACK space check based on recent -net fix (patch 9).

The MPTCP upstreaming community has been collaborating on an
upstreamable MPTCP implementation that complies with RFC 8684. A minimal
set of features to comply with the specification involves a sizeable set
of code changes, so David requested that we split this work in to
multiple, smaller patch sets to build up MPTCP infrastructure.

The minimal MPTCP feature set we are proposing for review in the v5.6
timeframe begins with these three parts:

Part 1 (this patch set): MPTCP prerequisites. Introduce some MPTCP
definitions, additional ULP and skb extension features, TCP option space
checking, and a few exported symbols.

Part 2: Single subflow implementation and self tests.

Part 3: Switch from MPTCP v0 (RFC 6824) to MPTCP v1 (new RFC 8684,
publication expected in the next few days).

Additional patches for multiple subflow support, path management, active
backup, and other features are in the pipeline for submission after
making progress with the above reviews.

Clone/fetch:
https://github.com/multipath-tcp/mptcp_net-next.git (tag: netdev-v7-part1)

Browse:
https://github.com/multipath-tcp/mptcp_net-next/tree/netdev-v7-part1

Thank you for your review. You can find us at mptcp@lists.01.org and
https://is.gd/mptcp_upstream
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

10 files changed, 101 insertions, 56 deletions

diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c
index 324306d6fde0..ff57ea89c27e 100644
--- a/net/ax25/af_ax25.c
+++ b/net/ax25/af_ax25.c
@@ -808,7 +808,7 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol,
 	struct sock *sk;
 	ax25_cb *ax25;
 
-	if (protocol < 0 || protocol > SK_PROTOCOL_MAX)
+	if (protocol < 0 || protocol > U8_MAX)
 		return -EINVAL;
 
 	if (!net_eq(net, &init_net))
diff --git a/net/core/filter.c b/net/core/filter.c
index 42fd17c48c5f..ef01c5599501 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -7607,21 +7607,21 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
 		break;
 
 	case offsetof(struct bpf_sock, type):
-		BUILD_BUG_ON(HWEIGHT32(SK_FL_TYPE_MASK) != BITS_PER_BYTE * 2);
-		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg,
-				      offsetof(struct sock, __sk_flags_offset));
-		*insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_TYPE_MASK);
-		*insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_TYPE_SHIFT);
-		*target_size = 2;
+		*insn++ = BPF_LDX_MEM(
+			BPF_FIELD_SIZEOF(struct sock, sk_type),
+			si->dst_reg, si->src_reg,
+			bpf_target_off(struct sock, sk_type,
+				       sizeof_field(struct sock, sk_type),
+				       target_size));
 		break;
 
 	case offsetof(struct bpf_sock, protocol):
-		BUILD_BUG_ON(HWEIGHT32(SK_FL_PROTO_MASK) != BITS_PER_BYTE);
-		*insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg,
-				      offsetof(struct sock, __sk_flags_offset));
-		*insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK);
-		*insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_PROTO_SHIFT);
-		*target_size = 1;
+		*insn++ = BPF_LDX_MEM(
+			BPF_FIELD_SIZEOF(struct sock, sk_protocol),
+			si->dst_reg, si->src_reg,
+			bpf_target_off(struct sock, sk_protocol,
+				       sizeof_field(struct sock, sk_protocol),
+				       target_size));
 		break;
 
 	case offsetof(struct bpf_sock, src_ip4):
@@ -7903,20 +7903,13 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type,
 		break;
 
 	case offsetof(struct bpf_sock_addr, type):
-		SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(
-			struct bpf_sock_addr_kern, struct sock, sk,
-			__sk_flags_offset, BPF_W, 0);
-		*insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_TYPE_MASK);
-		*insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_TYPE_SHIFT);
+		SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern,
+					    struct sock, sk, sk_type);
 		break;
 
 	case offsetof(struct bpf_sock_addr, protocol):
-		SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(
-			struct bpf_sock_addr_kern, struct sock, sk,
-			__sk_flags_offset, BPF_W, 0);
-		*insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK);
-		*insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg,
-					SK_FL_PROTO_SHIFT);
+		SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern,
+					    struct sock, sk, sk_protocol);
 		break;
 
 	case offsetof(struct bpf_sock_addr, msg_src_ip4):
@@ -8835,11 +8828,11 @@ sk_reuseport_is_valid_access(int off, int size,
 				    skb,				\
 				    SKB_FIELD)
 
-#define SK_REUSEPORT_LOAD_SK_FIELD_SIZE_OFF(SK_FIELD, BPF_SIZE, EXTRA_OFF) \
-	SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(struct sk_reuseport_kern,	\
-					     struct sock,		\
-					     sk,			\
-					     SK_FIELD, BPF_SIZE, EXTRA_OFF)
+#define SK_REUSEPORT_LOAD_SK_FIELD(SK_FIELD)				\
+	SOCK_ADDR_LOAD_NESTED_FIELD(struct sk_reuseport_kern,		\
+				    struct sock,			\
+				    sk,					\
+				    SK_FIELD)
 
 static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type,
 					   const struct bpf_insn *si,
@@ -8863,16 +8856,7 @@ static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type,
 		break;
 
 	case offsetof(struct sk_reuseport_md, ip_protocol):
-		BUILD_BUG_ON(HWEIGHT32(SK_FL_PROTO_MASK) != BITS_PER_BYTE);
-		SK_REUSEPORT_LOAD_SK_FIELD_SIZE_OFF(__sk_flags_offset,
-						    BPF_W, 0);
-		*insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK);
-		*insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg,
-					SK_FL_PROTO_SHIFT);
-		/* SK_FL_PROTO_MASK and SK_FL_PROTO_SHIFT are endian
-		 * aware.  No further narrowing or masking is needed.
-		 */
-		*target_size = 1;
+		SK_REUSEPORT_LOAD_SK_FIELD(sk_protocol);
 		break;
 
 	case offsetof(struct sk_reuseport_md, data_end):
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 44b0894d8ae1..48a7029529c9 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -68,6 +68,7 @@
 #include <net/ip6_checksum.h>
 #include <net/xfrm.h>
 #include <net/mpls.h>
+#include <net/mptcp.h>
 
 #include <linux/uaccess.h>
 #include <trace/events/skb.h>
@@ -4109,6 +4110,9 @@ static const u8 skb_ext_type_len[] = {
 #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
 	[TC_SKB_EXT] = SKB_EXT_CHUNKSIZEOF(struct tc_skb_ext),
 #endif
+#if IS_ENABLED(CONFIG_MPTCP)
+	[SKB_EXT_MPTCP] = SKB_EXT_CHUNKSIZEOF(struct mptcp_ext),
+#endif
 };
 
 static __always_inline unsigned int skb_ext_total_length(void)
@@ -4123,6 +4127,9 @@ static __always_inline unsigned int skb_ext_total_length(void)
 #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT)
 		skb_ext_type_len[TC_SKB_EXT] +
 #endif
+#if IS_ENABLED(CONFIG_MPTCP)
+		skb_ext_type_len[SKB_EXT_MPTCP] +
+#endif
 		0;
 }
 
@@ -5980,7 +5987,14 @@ static void *skb_ext_get_ptr(struct skb_ext *ext, enum skb_ext_id id)
 	return (void *)ext + (ext->offset[id] * SKB_EXT_ALIGN_VALUE);
 }
 
-static struct skb_ext *skb_ext_alloc(void)
+/**
+ * __skb_ext_alloc - allocate a new skb extensions storage
+ *
+ * Returns the newly allocated pointer. The pointer can later attached to a
+ * skb via __skb_ext_set().
+ * Note: caller must handle the skb_ext as an opaque data.
+ */
+struct skb_ext *__skb_ext_alloc(void)
 {
 	struct skb_ext *new = kmem_cache_alloc(skbuff_ext_cache, GFP_ATOMIC);
 
@@ -6021,6 +6035,30 @@ static struct skb_ext *skb_ext_maybe_cow(struct skb_ext *old,
 }
 
 /**
+ * __skb_ext_set - attach the specified extension storage to this skb
+ * @skb: buffer
+ * @id: extension id
+ * @ext: extension storage previously allocated via __skb_ext_alloc()
+ *
+ * Existing extensions, if any, are cleared.
+ *
+ * Returns the pointer to the extension.
+ */
+void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id,
+		    struct skb_ext *ext)
+{
+	unsigned int newlen, newoff = SKB_EXT_CHUNKSIZEOF(*ext);
+
+	skb_ext_put(skb);
+	newlen = newoff + skb_ext_type_len[id];
+	ext->chunks = newlen;
+	ext->offset[id] = newoff;
+	skb->extensions = ext;
+	skb->active_extensions = 1 << id;
+	return skb_ext_get_ptr(ext, id);
+}
+
+/**
  * skb_ext_add - allocate space for given extension, COW if needed
  * @skb: buffer
  * @id: extension to allocate space for
@@ -6053,7 +6091,7 @@ void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id)
 	} else {
 		newoff = SKB_EXT_CHUNKSIZEOF(*new);
 
-		new = skb_ext_alloc();
+		new = __skb_ext_alloc();
 		if (!new)
 			return NULL;
 	}
diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c
index e19a92a62e14..0a46ea3bddd5 100644
--- a/net/decnet/af_decnet.c
+++ b/net/decnet/af_decnet.c
@@ -670,7 +670,7 @@ static int dn_create(struct net *net, struct socket *sock, int protocol,
 {
 	struct sock *sk;
 
-	if (protocol < 0 || protocol > SK_PROTOCOL_MAX)
+	if (protocol < 0 || protocol > U8_MAX)
 		return -EINVAL;
 
 	if (!net_eq(net, &init_net))
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 18c0d5bffe12..6a691fd04398 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -770,6 +770,18 @@ void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req,
 }
 EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add);
 
+static void inet_clone_ulp(const struct request_sock *req, struct sock *newsk,
+			   const gfp_t priority)
+{
+	struct inet_connection_sock *icsk = inet_csk(newsk);
+
+	if (!icsk->icsk_ulp_ops)
+		return;
+
+	if (icsk->icsk_ulp_ops->clone)
+		icsk->icsk_ulp_ops->clone(req, newsk, priority);
+}
+
 /**
  *	inet_csk_clone_lock - clone an inet socket, and lock its clone
  *	@sk: the socket to clone
@@ -810,6 +822,8 @@ struct sock *inet_csk_clone_lock(const struct sock *sk,
 		/* Deinitialize accept_queue to trap illegal accesses. */
 		memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue));
 
+		inet_clone_ulp(req, newsk, priority);
+
 		security_inet_csk_clone(newsk, req);
 	}
 	return newsk;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f09fbc85b108..6711a97de3ce 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -690,8 +690,8 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb,
 	       refcount_read(&sk->sk_wmem_alloc) > skb->truesize;
 }
 
-static void tcp_push(struct sock *sk, int flags, int mss_now,
-		     int nonagle, int size_goal)
+void tcp_push(struct sock *sk, int flags, int mss_now,
+	      int nonagle, int size_goal)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 	struct sk_buff *skb;
@@ -925,7 +925,7 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now,
 	return max(size_goal, mss_now);
 }
 
-static int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
+int tcp_send_mss(struct sock *sk, int *size_goal, int flags)
 {
 	int mss_now;
 
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 062b696a5fa1..2914fdf1d543 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1422,7 +1422,7 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb,
 	if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED)
 		goto fallback;
 
-	if (!tcp_skb_can_collapse_to(prev))
+	if (!tcp_skb_can_collapse(prev, skb))
 		goto fallback;
 
 	in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) &&
@@ -4423,6 +4423,9 @@ static bool tcp_try_coalesce(struct sock *sk,
 	if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq)
 		return false;
 
+	if (!mptcp_skb_can_collapse(to, from))
+		return false;
+
 #ifdef CONFIG_TLS_DEVICE
 	if (from->decrypted != to->decrypted)
 		return false;
@@ -4932,7 +4935,7 @@ restart:
 		/* The first skb to collapse is:
 		 * - not SYN/FIN and
 		 * - bloated or contains data before "start" or
-		 *   overlaps to the next one.
+		 *   overlaps to the next one and mptcp allow collapsing.
 		 */
 		if (!(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) &&
 		    (tcp_win_from_space(sk, skb->truesize) > skb->len ||
@@ -4941,7 +4944,7 @@ restart:
 			break;
 		}
 
-		if (n && n != tail &&
+		if (n && n != tail && mptcp_skb_can_collapse(skb, n) &&
 		    TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) {
 			end_of_skbs = false;
 			break;
@@ -4974,6 +4977,7 @@ restart:
 		else
 			__skb_queue_tail(&tmp, nskb); /* defer rbtree insertion */
 		skb_set_owner_r(nskb, sk);
+		mptcp_skb_ext_move(nskb, skb);
 
 		/* Copy data, releasing collapsed skbs. */
 		while (copy > 0) {
@@ -4993,6 +4997,7 @@ restart:
 				skb = tcp_collapse_one(sk, skb, list, root);
 				if (!skb ||
 				    skb == tail ||
+				    !mptcp_skb_can_collapse(nskb, skb) ||
 				    (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)))
 					goto end;
 #ifdef CONFIG_TLS_DEVICE
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 4adac9c75343..fedb537839ec 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1426,7 +1426,7 @@ struct request_sock_ops tcp_request_sock_ops __read_mostly = {
 	.syn_ack_timeout =	tcp_syn_ack_timeout,
 };
 
-static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
+const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = {
 	.mss_clamp	=	TCP_MSS_DEFAULT,
 #ifdef CONFIG_TCP_MD5SIG
 	.req_md5_lookup	=	tcp_v4_md5_lookup,
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 58c92a7d671c..05109d0c675b 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -754,13 +754,17 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb
 	eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack;
 	if (unlikely(eff_sacks)) {
 		const unsigned int remaining = MAX_TCP_OPTION_SPACE - size;
+		if (unlikely(remaining < TCPOLEN_SACK_BASE_ALIGNED +
+					 TCPOLEN_SACK_PERBLOCK))
+			return size;
+
 		opts->num_sack_blocks =
 			min_t(unsigned int, eff_sacks,
 			      (remaining - TCPOLEN_SACK_BASE_ALIGNED) /
 			      TCPOLEN_SACK_PERBLOCK);
-		if (likely(opts->num_sack_blocks))
-			size += TCPOLEN_SACK_BASE_ALIGNED +
-				opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
+
+		size += TCPOLEN_SACK_BASE_ALIGNED +
+			opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK;
 	}
 
 	return size;
@@ -2865,7 +2869,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to,
 		if (!tcp_can_collapse(sk, skb))
 			break;
 
-		if (!tcp_skb_can_collapse_to(to))
+		if (!tcp_skb_can_collapse(to, skb))
 			break;
 
 		space -= skb->len;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 95e4e1e95db2..5b5260103b65 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -75,7 +75,7 @@ static void	tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb,
 static int	tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb);
 
 static const struct inet_connection_sock_af_ops ipv6_mapped;
-static const struct inet_connection_sock_af_ops ipv6_specific;
+const struct inet_connection_sock_af_ops ipv6_specific;
 #ifdef CONFIG_TCP_MD5SIG
 static const struct tcp_sock_af_ops tcp_sock_ipv6_specific;
 static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific;
@@ -819,7 +819,7 @@ struct request_sock_ops tcp6_request_sock_ops __read_mostly = {
 	.syn_ack_timeout =	tcp_syn_ack_timeout,
 };
 
-static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
+const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = {
 	.mss_clamp	=	IPV6_MIN_MTU - sizeof(struct tcphdr) -
 				sizeof(struct ipv6hdr),
 #ifdef CONFIG_TCP_MD5SIG
@@ -1794,7 +1794,7 @@ static struct timewait_sock_ops tcp6_timewait_sock_ops = {
 	.twsk_destructor = tcp_twsk_destructor,
 };
 
-static const struct inet_connection_sock_af_ops ipv6_specific = {
+const struct inet_connection_sock_af_ops ipv6_specific = {
 	.queue_xmit	   = inet6_csk_xmit,
 	.send_check	   = tcp_v6_send_check,
 	.rebuild_header	   = inet6_sk_rebuild_header,