From 1033990ac5b2ab6cee93734cb6d301aa3a35bcaa Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 15 Apr 2019 17:15:06 +0800 Subject: [PATCH 1/2] sctp: implement memory accounting on tx path Now when sending packets, sk_mem_charge() and sk_mem_uncharge() have been used to set sk_forward_alloc. We just need to call sk_wmem_schedule() to check if the allocated should be raised, and call sk_mem_reclaim() to check if the allocated should be reduced when it's under memory pressure. If sk_wmem_schedule() returns false, which means no memory is allowed to allocate, it will block and wait for memory to become available. Note different from tcp, sctp wait_for_buf happens before allocating any skb, so memory accounting check is done with the whole msg_len before it too. Reported-by: Matteo Croce Tested-by: Matteo Croce Acked-by: Neil Horman Acked-by: Marcelo Ricardo Leitner Signed-off-by: Xin Long Signed-off-by: David S. Miller --- net/sctp/socket.c | 10 ++++++++-- 1 file changed, 8 insertions(+), 2 deletions(-) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 9874e60c9b0d..f66dca3b1055 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -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 From 9dde27de3e5efa0d032f3c891a0ca833a0d31911 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 15 Apr 2019 17:15:07 +0800 Subject: [PATCH 2/2] sctp: implement memory accounting on rx path sk_forward_alloc's updating is also done on rx path, but to be consistent we change to use sk_mem_charge() in sctp_skb_set_owner_r(). In sctp_eat_data(), it's not enough to check sctp_memory_pressure only, which doesn't work for mem_cgroup_sockets_enabled, so we change to use sk_under_memory_pressure(). When it's under memory pressure, sk_mem_reclaim() and sk_rmem_schedule() should be called on both RENEGE or CHUNK DELIVERY path exit the memory pressure status as soon as possible. Note that sk_rmem_schedule() is using datalen to make things easy there. Reported-by: Matteo Croce Tested-by: Matteo Croce Acked-by: Neil Horman Acked-by: Marcelo Ricardo Leitner Signed-off-by: Xin Long Signed-off-by: David S. Miller --- include/net/sctp/sctp.h | 2 +- net/sctp/sm_statefuns.c | 6 ++++-- net/sctp/ulpevent.c | 19 ++++++++----------- net/sctp/ulpqueue.c | 3 ++- 4 files changed, 15 insertions(+), 15 deletions(-) diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 1d13ec3f2707..eefdfa5abf6e 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -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. */ diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index c9ae3404b1bb..7dfc34b28f4f 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -6412,13 +6412,15 @@ 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); + } } /* diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 8cb7d9858270..c2a7478587ab 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -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))) - goto fail; - } + 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); diff --git a/net/sctp/ulpqueue.c b/net/sctp/ulpqueue.c index 7cdc3623fa35..a212fe079c07 100644 --- a/net/sctp/ulpqueue.c +++ b/net/sctp/ulpqueue.c @@ -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