[PATCH net-next v2 0/3] net: Introducing socket mark receive socket option

[PATCH net-next v2 0/3] net: Introducing socket mark receive socket option

[Eyal Birger]

This patch set introduces a new socket option for fetching the mark
of skbs passed to sockets as ancillary data.

A userspace program may wish to receive the mark of packets it
receives, for example for distinguishing between different TPROXY
diversion rules to the same userspace proxy socket.

The patch set includes a minor function renaming, as well as a
change in struct sk_buff for allowing skb->mark to persist after
being queued to the socket queue.

---
Changes in v2:
- Function parameter indentation
- Commit message formatting
---

Eyal Birger (3):
  net: Rename sock_recv_ts_and_drops() to sock_cmsg_recv()
  net: use skb->priority for overloading skb->dropcount and
    skb->reserved_tailroom instead of skb->mark
  net: Introducing socket mark receive socket option

 arch/alpha/include/uapi/asm/socket.h   |  2 ++
 arch/avr32/include/uapi/asm/socket.h   |  2 ++
 arch/cris/include/uapi/asm/socket.h    |  2 ++
 arch/frv/include/uapi/asm/socket.h     |  2 ++
 arch/ia64/include/uapi/asm/socket.h    |  2 ++
 arch/m32r/include/uapi/asm/socket.h    |  2 ++
 arch/mips/include/uapi/asm/socket.h    |  2 ++
 arch/mn10300/include/uapi/asm/socket.h |  2 ++
 arch/parisc/include/uapi/asm/socket.h  |  2 ++
 arch/powerpc/include/uapi/asm/socket.h |  2 ++
 arch/s390/include/uapi/asm/socket.h    |  2 ++
 arch/sparc/include/uapi/asm/socket.h   |  2 ++
 arch/xtensa/include/uapi/asm/socket.h  |  2 ++
 include/linux/skbuff.h                 |  4 ++--
 include/net/sock.h                     | 18 ++++++++++--------
 include/uapi/asm-generic/socket.h      |  2 ++
 net/atm/common.c                       |  2 +-
 net/bluetooth/af_bluetooth.c           |  4 ++--
 net/can/bcm.c                          |  2 +-
 net/can/raw.c                          |  2 +-
 net/core/sock.c                        |  8 ++++++++
 net/ieee802154/socket.c                |  4 ++--
 net/ipv4/raw.c                         |  2 +-
 net/ipv4/udp.c                         |  2 +-
 net/ipv6/raw.c                         |  2 +-
 net/ipv6/udp.c                         |  2 +-
 net/key/af_key.c                       |  2 +-
 net/packet/af_packet.c                 |  2 +-
 net/rxrpc/ar-recvmsg.c                 |  2 +-
 net/sctp/socket.c                      |  2 +-
 net/socket.c                           | 15 ++++++++++++---
 31 files changed, 75 insertions(+), 28 deletions(-)

-- 
2.1.4

[PATCH net-next v2 1/3] net: Rename sock_recv_ts_and_drops() to sock_cmsg_recv()

[Eyal Birger]

sock_recv_ts_and_drops() - as its name suggests - allows receiving
timestamp information and drop statistics.
Generalize the function name in preparation for adding additional
ancillary information.

Signed-off-by: Eyal Birger <eyal.birger@gmail.com>
---
 include/net/sock.h           | 10 +++++-----
 net/atm/common.c             |  2 +-
 net/bluetooth/af_bluetooth.c |  4 ++--
 net/can/bcm.c                |  2 +-
 net/can/raw.c                |  2 +-
 net/ieee802154/socket.c      |  4 ++--
 net/ipv4/raw.c               |  2 +-
 net/ipv4/udp.c               |  2 +-
 net/ipv6/raw.c               |  2 +-
 net/ipv6/udp.c               |  2 +-
 net/key/af_key.c             |  2 +-
 net/packet/af_packet.c       |  2 +-
 net/rxrpc/ar-recvmsg.c       |  2 +-
 net/sctp/socket.c            |  2 +-
 net/socket.c                 |  6 +++---
 15 files changed, 23 insertions(+), 23 deletions(-)

diff --git a/include/net/sock.h b/include/net/sock.h
index e138245..ba7db59 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -2113,11 +2113,11 @@ sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb)
 		__sock_recv_wifi_status(msg, sk, skb);
 }
 
-void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
-			      struct sk_buff *skb);
+void __sock_cmsg_recv(struct msghdr *msg, struct sock *sk,
+		      struct sk_buff *skb);
 
-static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
-					  struct sk_buff *skb)
+static inline void sock_cmsg_recv(struct msghdr *msg, struct sock *sk,
+				  struct sk_buff *skb)
 {
 #define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL)			| \
 			   (1UL << SOCK_RCVTSTAMP))
@@ -2125,7 +2125,7 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 			   SOF_TIMESTAMPING_RAW_HARDWARE)
 
 	if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY)
-		__sock_recv_ts_and_drops(msg, sk, skb);
+		__sock_cmsg_recv(msg, sk, skb);
 	else
 		sk->sk_stamp = skb->tstamp;
 }
diff --git a/net/atm/common.c b/net/atm/common.c
index b84057e..611b1c2 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -557,7 +557,7 @@ int vcc_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *msg,
 	error = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (error)
 		return error;
-	sock_recv_ts_and_drops(msg, sk, skb);
+	sock_cmsg_recv(msg, sk, skb);
 
 	if (!(flags & MSG_PEEK)) {
 		pr_debug("%d -= %d\n", atomic_read(&sk->sk_rmem_alloc),
diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c
index ce22e0c..4bdcbc9 100644
--- a/net/bluetooth/af_bluetooth.c
+++ b/net/bluetooth/af_bluetooth.c
@@ -241,7 +241,7 @@ int bt_sock_recvmsg(struct kiocb *iocb, struct socket *sock,
 	skb_reset_transport_header(skb);
 	err = skb_copy_datagram_msg(skb, 0, msg, copied);
 	if (err == 0) {
-		sock_recv_ts_and_drops(msg, sk, skb);
+		sock_cmsg_recv(msg, sk, skb);
 
 		if (bt_sk(sk)->skb_msg_name)
 			bt_sk(sk)->skb_msg_name(skb, msg->msg_name,
@@ -339,7 +339,7 @@ int bt_sock_stream_recvmsg(struct kiocb *iocb, struct socket *sock,
 		copied += chunk;
 		size   -= chunk;
 
-		sock_recv_ts_and_drops(msg, sk, skb);
+		sock_cmsg_recv(msg, sk, skb);
 
 		if (!(flags & MSG_PEEK)) {
 			int skb_len = skb_headlen(skb);
diff --git a/net/can/bcm.c b/net/can/bcm.c
index ee9ffd9..f741f29 100644
--- a/net/can/bcm.c
+++ b/net/can/bcm.c
@@ -1559,7 +1559,7 @@ static int bcm_recvmsg(struct kiocb *iocb, struct socket *sock,
 		return err;
 	}
 
-	sock_recv_ts_and_drops(msg, sk, skb);
+	sock_cmsg_recv(msg, sk, skb);
 
 	if (msg->msg_name) {
 		__sockaddr_check_size(sizeof(struct sockaddr_can));
diff --git a/net/can/raw.c b/net/can/raw.c
index 00c13ef..549b871 100644
--- a/net/can/raw.c
+++ b/net/can/raw.c
@@ -754,7 +754,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct socket *sock,
 		return err;
 	}
 
-	sock_recv_ts_and_drops(msg, sk, skb);
+	sock_cmsg_recv(msg, sk, skb);
 
 	if (msg->msg_name) {
 		__sockaddr_check_size(sizeof(struct sockaddr_can));
diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c
index 2878d8c..41ac5fa 100644
--- a/net/ieee802154/socket.c
+++ b/net/ieee802154/socket.c
@@ -348,7 +348,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	if (err)
 		goto done;
 
-	sock_recv_ts_and_drops(msg, sk, skb);
+	sock_cmsg_recv(msg, sk, skb);
 
 	if (flags & MSG_TRUNC)
 		copied = skb->len;
@@ -739,7 +739,7 @@ static int dgram_recvmsg(struct kiocb *iocb, struct sock *sk,
 	if (err)
 		goto done;
 
-	sock_recv_ts_and_drops(msg, sk, skb);
+	sock_cmsg_recv(msg, sk, skb);
 
 	if (saddr) {
 		saddr->family = AF_IEEE802154;
diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c
index f027a70..a28a83b 100644
--- a/net/ipv4/raw.c
+++ b/net/ipv4/raw.c
@@ -740,7 +740,7 @@ static int raw_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
 	if (err)
 		goto done;
 
-	sock_recv_ts_and_drops(msg, sk, skb);
+	sock_cmsg_recv(msg, sk, skb);
 
 	/* Copy the address. */
 	if (sin) {
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 97ef1f8b..07b1394 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -1318,7 +1318,7 @@ try_again:
 		UDP_INC_STATS_USER(sock_net(sk),
 				UDP_MIB_INDATAGRAMS, is_udplite);
 
-	sock_recv_ts_and_drops(msg, sk, skb);
+	sock_cmsg_recv(msg, sk, skb);
 
 	/* Copy the address. */
 	if (sin) {
diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c
index dae7f1a..882c997 100644
--- a/net/ipv6/raw.c
+++ b/net/ipv6/raw.c
@@ -510,7 +510,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk,
 		*addr_len = sizeof(*sin6);
 	}
 
-	sock_recv_ts_and_drops(msg, sk, skb);
+	sock_cmsg_recv(msg, sk, skb);
 
 	if (np->rxopt.all)
 		ip6_datagram_recv_ctl(sk, msg, skb);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index d048d46..be0cfae 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -469,7 +469,7 @@ try_again:
 					UDP_MIB_INDATAGRAMS, is_udplite);
 	}
 
-	sock_recv_ts_and_drops(msg, sk, skb);
+	sock_cmsg_recv(msg, sk, skb);
 
 	/* Copy the address. */
 	if (msg->msg_name) {
diff --git a/net/key/af_key.c b/net/key/af_key.c
index f8ac939..e03ba49 100644
--- a/net/key/af_key.c
+++ b/net/key/af_key.c
@@ -3658,7 +3658,7 @@ static int pfkey_recvmsg(struct kiocb *kiocb,
 	if (err)
 		goto out_free;
 
-	sock_recv_ts_and_drops(msg, sk, skb);
+	sock_cmsg_recv(msg, sk, skb);
 
 	err = (flags & MSG_TRUNC) ? skb->len : copied;
 
diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
index 9c28cec..6033520 100644
--- a/net/packet/af_packet.c
+++ b/net/packet/af_packet.c
@@ -2982,7 +2982,7 @@ static int packet_recvmsg(struct kiocb *iocb, struct socket *sock,
 	if (err)
 		goto out_free;
 
-	sock_recv_ts_and_drops(msg, sk, skb);
+	sock_cmsg_recv(msg, sk, skb);
 
 	if (msg->msg_name) {
 		/* If the address length field is there to be filled
diff --git a/net/rxrpc/ar-recvmsg.c b/net/rxrpc/ar-recvmsg.c
index 4575485..323b1c7 100644
--- a/net/rxrpc/ar-recvmsg.c
+++ b/net/rxrpc/ar-recvmsg.c
@@ -150,7 +150,7 @@ int rxrpc_recvmsg(struct kiocb *iocb, struct socket *sock,
 				       &call->conn->trans->peer->srx, len);
 				msg->msg_namelen = len;
 			}
-			sock_recv_ts_and_drops(msg, &rx->sk, skb);
+			sock_cmsg_recv(msg, &rx->sk, skb);
 		}
 
 		/* receive the message */
diff --git a/net/sctp/socket.c b/net/sctp/socket.c
index aafe94b..27835aa 100644
--- a/net/sctp/socket.c
+++ b/net/sctp/socket.c
@@ -2108,7 +2108,7 @@ static int sctp_recvmsg(struct kiocb *iocb, struct sock *sk,
 	if (err)
 		goto out_free;
 
-	sock_recv_ts_and_drops(msg, sk, skb);
+	sock_cmsg_recv(msg, sk, skb);
 	if (sctp_ulpevent_is_notification(event)) {
 		msg->msg_flags |= MSG_NOTIFICATION;
 		sp->pf->event_msgname(event, msg->msg_name, addr_len);
diff --git a/net/socket.c b/net/socket.c
index bbedbfc..17be338 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -736,13 +736,13 @@ static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk,
 			sizeof(__u32), &skb->dropcount);
 }
 
-void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
-	struct sk_buff *skb)
+void __sock_cmsg_recv(struct msghdr *msg, struct sock *sk,
+		      struct sk_buff *skb)
 {
 	sock_recv_timestamp(msg, sk, skb);
 	sock_recv_drops(msg, sk, skb);
 }
-EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops);
+EXPORT_SYMBOL_GPL(__sock_cmsg_recv);
 
 static inline int __sock_recvmsg_nosec(struct kiocb *iocb, struct socket *sock,
 				       struct msghdr *msg, size_t size, int flags)
-- 
2.1.4

[PATCH net-next v2 2/3] net: use skb->priority for overloading skb->dropcount and skb->reserved_tailroom instead of skb->mark

[Eyal Birger]

Commit 977750076d98 ("af_packet: add interframe drop cmsg (v6)")
unionized skb->mark and skb->dropcount in order to allow recording
of the socket drop count while maintaining struct sk_buff size.

In order to allow for the skb->mark to be fetched by user-space code
it needs to be detached from this union; skb->priority is used
instead.

Signed-off-by: Eyal Birger <eyal.birger@gmail.com>
----
The purpose of overloading skb->priority is solely for retaining
struct sk_buff size; skb->priority is not used after the skb queued
to the socket and has the same guarentee of not being shared as
skb->mark.
---
 include/linux/skbuff.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 1bb36ed..23f1a94 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -621,7 +621,7 @@ struct sk_buff {
 			__u16	csum_offset;
 		};
 	};
-	__u32			priority;
+	__u32			mark;
 	int			skb_iif;
 	__u32			hash;
 	__be16			vlan_proto;
@@ -636,7 +636,7 @@ struct sk_buff {
 	__u32			secmark;
 #endif
 	union {
-		__u32		mark;
+		__u32		priority;
 		__u32		dropcount;
 		__u32		reserved_tailroom;
 	};
-- 
2.1.4

Re: [PATCH net-next v2 2/3] net: use skb->priority for overloading skb->dropcount and skb->reserved_tailroom instead of skb->mark

[David Miller]

From: Eyal Birger <eyal.birger@gmail.com>
Date: Thu, 12 Feb 2015 06:32:14 +0200

> The purpose of overloading skb->priority is solely for retaining
> struct sk_buff size; skb->priority is not used after the skb queued
> to the socket and has the same guarentee of not being shared as
> skb->mark.

I don't think this analysis is accurate.

> @@ -621,7 +621,7 @@ struct sk_buff {
>  			__u16	csum_offset;
>  		};
>  	};
> -	__u32			priority;
> +	__u32			mark;
>  	int			skb_iif;
>  	__u32			hash;
>  	__be16			vlan_proto;
> @@ -636,7 +636,7 @@ struct sk_buff {
>  	__u32			secmark;
>  #endif
>  	union {
> -		__u32		mark;
> +		__u32		priority;
>  		__u32		dropcount;
>  		__u32		reserved_tailroom;
>  	};
> -- 

You are going to now write to dropcount in packet_rcv() and that will
corrupt skb->priority.  If we got to packet_rcv() via
dev_queue_xmit_nit() then that skb->priority value is actually going
to be used by the packet schedulers for classification, flow
scheduling, etc.

So I don't think this transformation is going to work properly.

I'm also wondering if aliasing with skb->mark, which is what happens
now, is legal too.

Re: [PATCH net-next v2 2/3] net: use skb->priority for overloading skb->dropcount and skb->reserved_tailroom instead of skb->mark

[Eyal Birger]

Hi,

Thanks for the review.

On Thu, Feb 19, 2015 at 10:05 PM, David Miller <davem@davemloft.net> wrote:
> From: Eyal Birger <eyal.birger@gmail.com>
> Date: Thu, 12 Feb 2015 06:32:14 +0200
>
>> The purpose of overloading skb->priority is solely for retaining
>> struct sk_buff size; skb->priority is not used after the skb queued
>> to the socket and has the same guarentee of not being shared as
>> skb->mark.
>
> I don't think this analysis is accurate.
>
>> @@ -621,7 +621,7 @@ struct sk_buff {
>>                       __u16   csum_offset;
>>               };
>>       };
>> -     __u32                   priority;
>> +     __u32                   mark;
>>       int                     skb_iif;
>>       __u32                   hash;
>>       __be16                  vlan_proto;
>> @@ -636,7 +636,7 @@ struct sk_buff {
>>       __u32                   secmark;
>>  #endif
>>       union {
>> -             __u32           mark;
>> +             __u32           priority;
>>               __u32           dropcount;
>>               __u32           reserved_tailroom;
>>       };
>> --
>
> You are going to now write to dropcount in packet_rcv() and that will
> corrupt skb->priority.  If we got to packet_rcv() via
> dev_queue_xmit_nit() then that skb->priority value is actually going
> to be used by the packet schedulers for classification, flow
> scheduling, etc.

As you've mentioned below, this is not a new behavior introduced by
this patch, it was
true for skb->mark as well.

However, It seems the skb is cloned prior to setting dropcount and
other skb header
fields before it is enqueued in packet_rcv(). Would that not prevent
interference with
the transmit path?

> So I don't think this transformation is going to work properly.
>
> I'm also wondering if aliasing with skb->mark, which is what happens
> now, is legal too.

As mentioned, the case is similar for skb->mark.

Best regards,
Eyal.

Re: [PATCH net-next v2 2/3] net: use skb->priority for overloading skb->dropcount and skb->reserved_tailroom instead of skb->mark

[David Miller]

From: Eyal Birger <eyal.birger@gmail.com>
Date: Fri, 20 Feb 2015 13:32:48 +0200

> However, It seems the skb is cloned prior to setting dropcount and
> other skb header fields before it is enqueued in packet_rcv(). Would
> that not prevent interference with the transmit path?

You're right, that should take care of all cases.

Please resubmit this series, perhaps adding some commit
log text explaining this for the next person who reads
these changes.

[PATCH net-next v2 3/3] net: Introducing socket mark receive socket option

[Eyal Birger]

A userspace program may wish to receive the mark of packets it
receives.

Packets may be marked by Netfilter, by other userspace applications
using the SO_MARK socket option, or by other kernel means.

Receiving the mark in userspace is useful for example for
distinguishing between different TPROXY diversion rules to the same
userspace proxy socket.

Signed-off-by: Eyal Birger <eyal.birger@gmail.com>
---
 arch/alpha/include/uapi/asm/socket.h   | 2 ++
 arch/avr32/include/uapi/asm/socket.h   | 2 ++
 arch/cris/include/uapi/asm/socket.h    | 2 ++
 arch/frv/include/uapi/asm/socket.h     | 2 ++
 arch/ia64/include/uapi/asm/socket.h    | 2 ++
 arch/m32r/include/uapi/asm/socket.h    | 2 ++
 arch/mips/include/uapi/asm/socket.h    | 2 ++
 arch/mn10300/include/uapi/asm/socket.h | 2 ++
 arch/parisc/include/uapi/asm/socket.h  | 2 ++
 arch/powerpc/include/uapi/asm/socket.h | 2 ++
 arch/s390/include/uapi/asm/socket.h    | 2 ++
 arch/sparc/include/uapi/asm/socket.h   | 2 ++
 arch/xtensa/include/uapi/asm/socket.h  | 2 ++
 include/net/sock.h                     | 8 +++++---
 include/uapi/asm-generic/socket.h      | 2 ++
 net/core/sock.c                        | 8 ++++++++
 net/socket.c                           | 9 +++++++++
 17 files changed, 50 insertions(+), 3 deletions(-)

diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h
index 9a20821..7c49f4b 100644
--- a/arch/alpha/include/uapi/asm/socket.h
+++ b/arch/alpha/include/uapi/asm/socket.h
@@ -92,4 +92,6 @@
 #define SO_ATTACH_BPF		50
 #define SO_DETACH_BPF		SO_DETACH_FILTER
 
+#define SO_RCVMARK		51
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/avr32/include/uapi/asm/socket.h b/arch/avr32/include/uapi/asm/socket.h
index 2b65ed6..6c81e0e 100644
--- a/arch/avr32/include/uapi/asm/socket.h
+++ b/arch/avr32/include/uapi/asm/socket.h
@@ -85,4 +85,6 @@
 #define SO_ATTACH_BPF		50
 #define SO_DETACH_BPF		SO_DETACH_FILTER
 
+#define SO_RCVMARK		51
+
 #endif /* _UAPI__ASM_AVR32_SOCKET_H */
diff --git a/arch/cris/include/uapi/asm/socket.h b/arch/cris/include/uapi/asm/socket.h
index e2503d9f..55ca3be 100644
--- a/arch/cris/include/uapi/asm/socket.h
+++ b/arch/cris/include/uapi/asm/socket.h
@@ -87,6 +87,8 @@
 #define SO_ATTACH_BPF		50
 #define SO_DETACH_BPF		SO_DETACH_FILTER
 
+#define SO_RCVMARK		51
+
 #endif /* _ASM_SOCKET_H */
 
 
diff --git a/arch/frv/include/uapi/asm/socket.h b/arch/frv/include/uapi/asm/socket.h
index 4823ad1..b69f0d5 100644
--- a/arch/frv/include/uapi/asm/socket.h
+++ b/arch/frv/include/uapi/asm/socket.h
@@ -85,5 +85,7 @@
 #define SO_ATTACH_BPF		50
 #define SO_DETACH_BPF		SO_DETACH_FILTER
 
+#define SO_RCVMARK		51
+
 #endif /* _ASM_SOCKET_H */
 
diff --git a/arch/ia64/include/uapi/asm/socket.h b/arch/ia64/include/uapi/asm/socket.h
index 59be3d8..ee6abaf 100644
--- a/arch/ia64/include/uapi/asm/socket.h
+++ b/arch/ia64/include/uapi/asm/socket.h
@@ -94,4 +94,6 @@
 #define SO_ATTACH_BPF		50
 #define SO_DETACH_BPF		SO_DETACH_FILTER
 
+#define SO_RCVMARK		51
+
 #endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/m32r/include/uapi/asm/socket.h b/arch/m32r/include/uapi/asm/socket.h
index 7bc4cb2..bf0f932 100644
--- a/arch/m32r/include/uapi/asm/socket.h
+++ b/arch/m32r/include/uapi/asm/socket.h
@@ -85,4 +85,6 @@
 #define SO_ATTACH_BPF		50
 #define SO_DETACH_BPF		SO_DETACH_FILTER
 
+#define SO_RCVMARK		51
+
 #endif /* _ASM_M32R_SOCKET_H */
diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h
index dec3c85..47a61c4 100644
--- a/arch/mips/include/uapi/asm/socket.h
+++ b/arch/mips/include/uapi/asm/socket.h
@@ -103,4 +103,6 @@
 #define SO_ATTACH_BPF		50
 #define SO_DETACH_BPF		SO_DETACH_FILTER
 
+#define SO_RCVMARK		51
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/mn10300/include/uapi/asm/socket.h b/arch/mn10300/include/uapi/asm/socket.h
index cab7d6d..216305b 100644
--- a/arch/mn10300/include/uapi/asm/socket.h
+++ b/arch/mn10300/include/uapi/asm/socket.h
@@ -85,4 +85,6 @@
 #define SO_ATTACH_BPF		50
 #define SO_DETACH_BPF		SO_DETACH_FILTER
 
+#define SO_RCVMARK		51
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h
index a5cd40c..047980a3 100644
--- a/arch/parisc/include/uapi/asm/socket.h
+++ b/arch/parisc/include/uapi/asm/socket.h
@@ -84,4 +84,6 @@
 #define SO_ATTACH_BPF		0x402B
 #define SO_DETACH_BPF		SO_DETACH_FILTER
 
+#define SO_RCVMARK		0x402C
+
 #endif /* _UAPI_ASM_SOCKET_H */
diff --git a/arch/powerpc/include/uapi/asm/socket.h b/arch/powerpc/include/uapi/asm/socket.h
index c046666..188abb6 100644
--- a/arch/powerpc/include/uapi/asm/socket.h
+++ b/arch/powerpc/include/uapi/asm/socket.h
@@ -92,4 +92,6 @@
 #define SO_ATTACH_BPF		50
 #define SO_DETACH_BPF		SO_DETACH_FILTER
 
+#define SO_RCVMARK		51
+
 #endif	/* _ASM_POWERPC_SOCKET_H */
diff --git a/arch/s390/include/uapi/asm/socket.h b/arch/s390/include/uapi/asm/socket.h
index 296942d..70a5791 100644
--- a/arch/s390/include/uapi/asm/socket.h
+++ b/arch/s390/include/uapi/asm/socket.h
@@ -91,4 +91,6 @@
 #define SO_ATTACH_BPF		50
 #define SO_DETACH_BPF		SO_DETACH_FILTER
 
+#define SO_RCVMARK		51
+
 #endif /* _ASM_SOCKET_H */
diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h
index e6a16c4..f7ee249 100644
--- a/arch/sparc/include/uapi/asm/socket.h
+++ b/arch/sparc/include/uapi/asm/socket.h
@@ -81,6 +81,8 @@
 #define SO_ATTACH_BPF		0x0034
 #define SO_DETACH_BPF		SO_DETACH_FILTER
 
+#define SO_RCVMARK		0x0035
+
 /* Security levels - as per NRL IPv6 - don't actually do anything */
 #define SO_SECURITY_AUTHENTICATION		0x5001
 #define SO_SECURITY_ENCRYPTION_TRANSPORT	0x5002
diff --git a/arch/xtensa/include/uapi/asm/socket.h b/arch/xtensa/include/uapi/asm/socket.h
index 4120af0..5b588fa 100644
--- a/arch/xtensa/include/uapi/asm/socket.h
+++ b/arch/xtensa/include/uapi/asm/socket.h
@@ -96,4 +96,6 @@
 #define SO_ATTACH_BPF		50
 #define SO_DETACH_BPF		SO_DETACH_FILTER
 
+#define SO_RCVMARK		51
+
 #endif	/* _XTENSA_SOCKET_H */
diff --git a/include/net/sock.h b/include/net/sock.h
index ba7db59..16e52fa 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -719,6 +719,7 @@ enum sock_flags {
 		     */
 	SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */
 	SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */
+	SOCK_RCVMARK,
 };
 
 static inline void sock_copy_flags(struct sock *nsk, struct sock *osk)
@@ -2119,12 +2120,13 @@ void __sock_cmsg_recv(struct msghdr *msg, struct sock *sk,
 static inline void sock_cmsg_recv(struct msghdr *msg, struct sock *sk,
 				  struct sk_buff *skb)
 {
-#define FLAGS_TS_OR_DROPS ((1UL << SOCK_RXQ_OVFL)			| \
-			   (1UL << SOCK_RCVTSTAMP))
+#define FLAGS_CMSG_ANY	  ((1UL << SOCK_RXQ_OVFL)			| \
+			   (1UL << SOCK_RCVTSTAMP)			| \
+			   (1UL << SOCK_RCVMARK))
 #define TSFLAGS_ANY	  (SOF_TIMESTAMPING_SOFTWARE			| \
 			   SOF_TIMESTAMPING_RAW_HARDWARE)
 
-	if (sk->sk_flags & FLAGS_TS_OR_DROPS || sk->sk_tsflags & TSFLAGS_ANY)
+	if (sk->sk_flags & FLAGS_CMSG_ANY || sk->sk_tsflags & TSFLAGS_ANY)
 		__sock_cmsg_recv(msg, sk, skb);
 	else
 		sk->sk_stamp = skb->tstamp;
diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h
index 5c15c2a..17a1e2e 100644
--- a/include/uapi/asm-generic/socket.h
+++ b/include/uapi/asm-generic/socket.h
@@ -87,4 +87,6 @@
 #define SO_ATTACH_BPF		50
 #define SO_DETACH_BPF		SO_DETACH_FILTER
 
+#define SO_RCVMARK		51
+
 #endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/net/core/sock.c b/net/core/sock.c
index 93c8b20..36fe687 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -928,6 +928,10 @@ set_rcvbuf:
 			sk->sk_mark = val;
 		break;
 
+	case SO_RCVMARK:
+		sock_valbool_flag(sk, SOCK_RCVMARK, valbool);
+		break;
+
 		/* We implement the SO_SNDLOWAT etc to
 		   not be settable (1003.1g 5.3) */
 	case SO_RXQ_OVFL:
@@ -1179,6 +1183,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 		v.val = sk->sk_mark;
 		break;
 
+	case SO_RCVMARK:
+		v.val = sock_flag(sk, SOCK_RCVMARK);
+		break;
+
 	case SO_RXQ_OVFL:
 		v.val = sock_flag(sk, SOCK_RXQ_OVFL);
 		break;
diff --git a/net/socket.c b/net/socket.c
index 17be338..d4a860b 100644
--- a/net/socket.c
+++ b/net/socket.c
@@ -736,11 +736,20 @@ static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk,
 			sizeof(__u32), &skb->dropcount);
 }
 
+static inline void sock_recv_mark(struct msghdr *msg, struct sock *sk,
+				  struct sk_buff *skb)
+{
+	if (sock_flag(sk, SOCK_RCVMARK) && skb)
+		put_cmsg(msg, SOL_SOCKET, SO_RCVMARK,
+			 sizeof(__u32), &skb->mark);
+}
+
 void __sock_cmsg_recv(struct msghdr *msg, struct sock *sk,
 		      struct sk_buff *skb)
 {
 	sock_recv_timestamp(msg, sk, skb);
 	sock_recv_drops(msg, sk, skb);
+	sock_recv_mark(msg, sk, skb);
 }
 EXPORT_SYMBOL_GPL(__sock_cmsg_recv);
 
-- 
2.1.4