Commit 871a2c16 authored by Tomasz Grobelny's avatar Tomasz Grobelny Committed by Gerrit Renker
Browse files

dccp: Policy-based packet dequeueing infrastructure 



This patch adds a generic infrastructure for policy-based dequeueing of
TX packets and provides two policies:
 * a simple FIFO policy (which is the default) and
 * a priority based policy (set via socket options).
Both policies honour the tx_qlen sysctl for the maximum size of the write
queue (can be overridden via socket options).

The priority policy uses skb->priority internally to assign an u32 priority
identifier, using the same ranking as SO_PRIORITY. The skb->priority field
is set to 0 when the packet leaves DCCP. The priority is supplied as ancillary
data using cmsg(3), the patch also provides the requisite parsing routines.

Signed-off-by: default avatarTomasz Grobelny <tomasz@grobelny.oswiecenia.net>
Signed-off-by: default avatarGerrit Renker <gerrit@erg.abdn.ac.uk>
parent cfa969e3

Documentation/networking/dccp.txt

+20 −0
Original line number Diff line number Diff line
@@ -47,6 +47,26 @@ http://linux-net.osdl.org/index.php/DCCP_Testing#Experimental_DCCP_source_tree 


Socket options

==============

DCCP_SOCKOPT_QPOLICY_ID sets the dequeuing policy for outgoing packets. It takes

a policy ID as argument and can only be set before the connection (i.e. changes

during an established connection are not supported). Currently, two policies are

defined: the "simple" policy (DCCPQ_POLICY_SIMPLE), which does nothing special,

and a priority-based variant (DCCPQ_POLICY_PRIO). The latter allows to pass an

u32 priority value as ancillary data to sendmsg(), where higher numbers indicate

a higher packet priority (similar to SO_PRIORITY). This ancillary data needs to

be formatted using a cmsg(3) message header filled in as follows:

	cmsg->cmsg_level = SOL_DCCP;

	cmsg->cmsg_type	 = DCCP_SCM_PRIORITY;

	cmsg->cmsg_len	 = CMSG_LEN(sizeof(uint32_t));	/* or CMSG_LEN(4) */



DCCP_SOCKOPT_QPOLICY_TXQLEN sets the maximum length of the output queue. A zero

value is always interpreted as unbounded queue length. If different from zero,

the interpretation of this parameter depends on the current dequeuing policy

(see above): the "simple" policy will enforce a fixed queue size by returning

EAGAIN, whereas the "prio" policy enforces a fixed queue length by dropping the

lowest-priority packet first. The default value for this parameter is

initialised from /proc/sys/net/dccp/default/tx_qlen.



DCCP_SOCKOPT_SERVICE sets the service. The specification mandates use of

service codes (RFC 4340, sec. 8.1.2); if this socket option is not set,

the socket will fall back to 0 (which means that no meaningful service code

include/linux/dccp.h

+21 −0
Original line number Diff line number Diff line
@@ -197,6 +197,21 @@ enum dccp_feature_numbers { 
	DCCPF_MAX_CCID_SPECIFIC = 255,

};



/* DCCP socket control message types for cmsg */

enum dccp_cmsg_type {

	DCCP_SCM_PRIORITY = 1,

	DCCP_SCM_QPOLICY_MAX = 0xFFFF,

	/* ^-- Up to here reserved exclusively for qpolicy parameters */

	DCCP_SCM_MAX

};



/* DCCP priorities for outgoing/queued packets */

enum dccp_packet_dequeueing_policy {

	DCCPQ_POLICY_SIMPLE,

	DCCPQ_POLICY_PRIO,

	DCCPQ_POLICY_MAX

};



/* DCCP socket options */

#define DCCP_SOCKOPT_PACKET_SIZE	1 /* XXX deprecated, without effect */

#define DCCP_SOCKOPT_SERVICE		2
@@ -210,6 +225,8 @@ enum dccp_feature_numbers { 
#define DCCP_SOCKOPT_CCID		13

#define DCCP_SOCKOPT_TX_CCID		14

#define DCCP_SOCKOPT_RX_CCID		15

#define DCCP_SOCKOPT_QPOLICY_ID		16

#define DCCP_SOCKOPT_QPOLICY_TXQLEN	17

#define DCCP_SOCKOPT_CCID_RX_INFO	128

#define DCCP_SOCKOPT_CCID_TX_INFO	192
@@ -458,6 +475,8 @@ struct dccp_ackvec; 
 * @dccps_hc_rx_ccid - CCID used for the receiver (or receiving half-connection)

 * @dccps_hc_tx_ccid - CCID used for the sender (or sending half-connection)

 * @dccps_options_received - parsed set of retrieved options

 * @dccps_qpolicy - TX dequeueing policy, one of %dccp_packet_dequeueing_policy

 * @dccps_tx_qlen - maximum length of the TX queue

 * @dccps_role - role of this sock, one of %dccp_role

 * @dccps_hc_rx_insert_options - receiver wants to add options when acking

 * @dccps_hc_tx_insert_options - sender wants to add options when sending
@@ -500,6 +519,8 @@ struct dccp_sock { 
	struct ccid			*dccps_hc_rx_ccid;

	struct ccid			*dccps_hc_tx_ccid;

	struct dccp_options_received	dccps_options_received;

	__u8				dccps_qpolicy;

	__u32				dccps_tx_qlen;

	enum dccp_role			dccps_role:2;

	__u8				dccps_hc_rx_insert_options:1;

	__u8				dccps_hc_tx_insert_options:1;

net/dccp/Makefile

+2 −2
Original line number Diff line number Diff line 
obj-$(CONFIG_IP_DCCP) += dccp.o dccp_ipv4.o



dccp-y := ccid.o feat.o input.o minisocks.o options.o output.o proto.o timer.o



dccp-y := ccid.o feat.o input.o minisocks.o options.o output.o proto.o timer.o \

	  qpolicy.o

#

# CCID algorithms to be used by dccp.ko

#

net/dccp/dccp.h

+12 −0
Original line number Diff line number Diff line
@@ -243,6 +243,18 @@ extern void dccp_reqsk_send_ack(struct sock *sk, struct sk_buff *skb, 
extern void dccp_send_sync(struct sock *sk, const u64 seq,

			   const enum dccp_pkt_type pkt_type);



/*

 * TX Packet Dequeueing Interface

 */

extern void		dccp_qpolicy_push(struct sock *sk, struct sk_buff *skb);

extern bool		dccp_qpolicy_full(struct sock *sk);

extern void		dccp_qpolicy_drop(struct sock *sk, struct sk_buff *skb);

extern struct sk_buff	*dccp_qpolicy_top(struct sock *sk);

extern struct sk_buff	*dccp_qpolicy_pop(struct sock *sk);



/*

 * TX Packet Output and TX Timers

 */

extern void   dccp_write_xmit(struct sock *sk);

extern void   dccp_write_space(struct sock *sk);

extern void   dccp_flush_write_queue(struct sock *sk, long *time_budget);

net/dccp/output.c

+3 −4
Original line number Diff line number Diff line
@@ -242,7 +242,7 @@ static void dccp_xmit_packet(struct sock *sk) 
{

	int err, len;

	struct dccp_sock *dp = dccp_sk(sk);

	struct sk_buff *skb = skb_dequeue(&sk->sk_write_queue);

	struct sk_buff *skb = dccp_qpolicy_pop(sk);



	if (unlikely(skb == NULL))

		return;
@@ -345,7 +345,7 @@ void dccp_write_xmit(struct sock *sk) 
	struct dccp_sock *dp = dccp_sk(sk);

	struct sk_buff *skb;



	while ((skb = skb_peek(&sk->sk_write_queue))) {

	while ((skb = dccp_qpolicy_top(sk))) {

		int rc = ccid_hc_tx_send_packet(dp->dccps_hc_tx_ccid, sk, skb);



		switch (ccid_packet_dequeue_eval(rc)) {
@@ -359,8 +359,7 @@ void dccp_write_xmit(struct sock *sk) 
			dccp_xmit_packet(sk);

			break;

		case CCID_PACKET_ERR:

			skb_dequeue(&sk->sk_write_queue);

			kfree_skb(skb);

			dccp_qpolicy_drop(sk, skb);

			dccp_pr_debug("packet discarded due to err=%d\n", rc);

		}

	}

CRA Git | Maintained and supported by SUSTech CRA and CCSE