Commit c7cf89b5 authored by David S. Miller's avatar David S. Miller
Browse files

Merge branch 'sctp-fully-support-memory-accounting' 



Xin Long says:

====================
sctp: fully support memory accounting

sctp memory accounting is added in this patchset by using
these kernel APIs on send side:

  - sk_mem_charge()
  - sk_mem_uncharge()
  - sk_wmem_schedule()
  - sk_under_memory_pressure()
  - sk_mem_reclaim()

and these on receive side:

  - sk_mem_charge()
  - sk_mem_uncharge()
  - sk_rmem_schedule()
  - sk_under_memory_pressure()
  - sk_mem_reclaim()

With sctp memory accounting, we can limit the memory allocation by
either sysctl:

  # sysctl -w net.sctp.sctp_mem="10 20 50"

or cgroup:

  # echo $((8<<14)) > \
    /sys/fs/cgroup/memory/sctp_mem/memory.kmem.tcp.limit_in_bytes

When the socket is under memory pressure, the send side will block
and wait, while the receive side will renege or drop.

v1->v2:
  - add the missing Reported/Tested/Acked/-bys.
====================

Signed-off-by: default avatarDavid S. Miller <davem@davemloft.net>
parents 93144b0e 9dde27de

include/net/sctp/sctp.h

+1 −1
Original line number Diff line number Diff line
@@ -421,7 +421,7 @@ static inline void sctp_skb_set_owner_r(struct sk_buff *skb, struct sock *sk) 
	/*

	 * This mimics the behavior of skb_set_owner_r

	 */

	sk->sk_forward_alloc -= event->rmem_len;

	sk_mem_charge(sk, event->rmem_len);

}



/* Tests if the list has one and only one entry. */

net/sctp/sm_statefuns.c

+4 −2
Original line number Diff line number Diff line
@@ -6412,12 +6412,14 @@ static int sctp_eat_data(const struct sctp_association *asoc, 
	 * in sctp_ulpevent_make_rcvmsg will drop the frame if we grow our

	 * memory usage too much

	 */

	if (*sk->sk_prot_creator->memory_pressure) {

	if (sk_under_memory_pressure(sk)) {

		if (sctp_tsnmap_has_gap(map) &&

		    (sctp_tsnmap_get_ctsn(map) + 1) == tsn) {

			pr_debug("%s: under pressure, reneging for tsn:%u\n",

				 __func__, tsn);

			deliver = SCTP_CMD_RENEGE;

		} else {

			sk_mem_reclaim(sk);

		}

	}

net/sctp/socket.c

+8 −2
Original line number Diff line number Diff line
@@ -1913,7 +1913,10 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, 
	if (sctp_wspace(asoc) < (int)msg_len)

		sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc));



	if (sctp_wspace(asoc) <= 0) {

	if (sk_under_memory_pressure(sk))

		sk_mem_reclaim(sk);



	if (sctp_wspace(asoc) <= 0 || !sk_wmem_schedule(sk, msg_len)) {

		timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT);

		err = sctp_wait_for_sndbuf(asoc, &timeo, msg_len);

		if (err)
@@ -8930,7 +8933,10 @@ static int sctp_wait_for_sndbuf(struct sctp_association *asoc, long *timeo_p, 
			goto do_error;

		if (signal_pending(current))

			goto do_interrupted;

		if ((int)msg_len <= sctp_wspace(asoc))

		if (sk_under_memory_pressure(sk))

			sk_mem_reclaim(sk);

		if ((int)msg_len <= sctp_wspace(asoc) &&

		    sk_wmem_schedule(sk, msg_len))

			break;



		/* Let another process have a go.  Since we are going

net/sctp/ulpevent.c

+8 −11
Original line number Diff line number Diff line
@@ -634,8 +634,9 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc, 
						gfp_t gfp)

{

	struct sctp_ulpevent *event = NULL;

	struct sk_buff *skb;

	size_t padding, len;

	struct sk_buff *skb = chunk->skb;

	struct sock *sk = asoc->base.sk;

	size_t padding, datalen;

	int rx_count;



	/*
@@ -646,15 +647,12 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc, 
	if (asoc->ep->rcvbuf_policy)

		rx_count = atomic_read(&asoc->rmem_alloc);

	else

		rx_count = atomic_read(&asoc->base.sk->sk_rmem_alloc);

		rx_count = atomic_read(&sk->sk_rmem_alloc);



	if (rx_count >= asoc->base.sk->sk_rcvbuf) {

	datalen = ntohs(chunk->chunk_hdr->length);



		if ((asoc->base.sk->sk_userlocks & SOCK_RCVBUF_LOCK) ||

		    (!sk_rmem_schedule(asoc->base.sk, chunk->skb,

				       chunk->skb->truesize)))

	if (rx_count >= sk->sk_rcvbuf || !sk_rmem_schedule(sk, skb, datalen))

		goto fail;

	}



	/* Clone the original skb, sharing the data.  */

	skb = skb_clone(chunk->skb, gfp);
@@ -681,8 +679,7 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc, 
	 * The sender should never pad with more than 3 bytes.  The receiver

	 * MUST ignore the padding bytes.

	 */

	len = ntohs(chunk->chunk_hdr->length);

	padding = SCTP_PAD4(len) - len;

	padding = SCTP_PAD4(datalen) - datalen;



	/* Fixup cloned skb with just this chunks data.  */

	skb_trim(skb, chunk->chunk_end - padding - skb->data);

net/sctp/ulpqueue.c

+2 −1
Original line number Diff line number Diff line
@@ -1104,7 +1104,8 @@ void sctp_ulpq_renege(struct sctp_ulpq *ulpq, struct sctp_chunk *chunk, 
			freed += sctp_ulpq_renege_frags(ulpq, needed - freed);

	}

	/* If able to free enough room, accept this chunk. */

	if (freed >= needed) {

	if (sk_rmem_schedule(asoc->base.sk, chunk->skb, needed) &&

	    freed >= needed) {

		int retval = sctp_ulpq_tail_data(ulpq, chunk, gfp);

		/*

		 * Enter partial delivery if chunk has not been

CRA Git | Maintained and supported by SUSTech CRA and CCSE