From 2692ba61a82203404abd7dd2a027bda962861f74 Mon Sep 17 00:00:00 2001 From: Xi Wang Date: Fri, 16 Dec 2011 12:44:15 +0000 Subject: sctp: fix incorrect overflow check on autoclose Commit 8ffd3208 voids the previous patches f6778aab and 810c0719 for limiting the autoclose value. If userspace passes in -1 on 32-bit platform, the overflow check didn't work and autoclose would be set to 0xffffffff. This patch defines a max_autoclose (in seconds) for limiting the value and exposes it through sysctl, with the following intentions. 1) Avoid overflowing autoclose * HZ. 2) Keep the default autoclose bound consistent across 32- and 64-bit platforms (INT_MAX / HZ in this patch). 3) Keep the autoclose value consistent between setsockopt() and getsockopt() calls. Suggested-by: Vlad Yasevich Signed-off-by: Xi Wang Signed-off-by: David S. Miller --- net/sctp/associola.c | 2 +- net/sctp/protocol.c | 3 +++ net/sctp/socket.c | 2 -- net/sctp/sysctl.c | 13 +++++++++++++ 4 files changed, 17 insertions(+), 3 deletions(-) (limited to 'net/sctp') diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 152b5b3c3fff..acd2edbc073e 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -173,7 +173,7 @@ static struct sctp_association *sctp_association_init(struct sctp_association *a asoc->timeouts[SCTP_EVENT_TIMEOUT_HEARTBEAT] = 0; asoc->timeouts[SCTP_EVENT_TIMEOUT_SACK] = asoc->sackdelay; asoc->timeouts[SCTP_EVENT_TIMEOUT_AUTOCLOSE] = - (unsigned long)sp->autoclose * HZ; + min_t(unsigned long, sp->autoclose, sctp_max_autoclose) * HZ; /* Initializes the timers */ for (i = SCTP_EVENT_TIMEOUT_NONE; i < SCTP_NUM_TIMEOUT_TYPES; ++i) diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 61b9fca5a173..6f6ad8686833 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1285,6 +1285,9 @@ SCTP_STATIC __init int sctp_init(void) sctp_max_instreams = SCTP_DEFAULT_INSTREAMS; sctp_max_outstreams = SCTP_DEFAULT_OUTSTREAMS; + /* Initialize maximum autoclose timeout. */ + sctp_max_autoclose = INT_MAX / HZ; + /* Initialize handle used for association ids. */ idr_init(&sctp_assocs_id); diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 13bf5fcdbff1..54a7cd2fdd7a 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -2200,8 +2200,6 @@ static int sctp_setsockopt_autoclose(struct sock *sk, char __user *optval, return -EINVAL; if (copy_from_user(&sp->autoclose, optval, optlen)) return -EFAULT; - /* make sure it won't exceed MAX_SCHEDULE_TIMEOUT */ - sp->autoclose = min_t(long, sp->autoclose, MAX_SCHEDULE_TIMEOUT / HZ); return 0; } diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 6b3952961b85..60ffbd067ff7 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -53,6 +53,10 @@ static int sack_timer_min = 1; static int sack_timer_max = 500; static int addr_scope_max = 3; /* check sctp_scope_policy_t in include/net/sctp/constants.h for max entries */ static int rwnd_scale_max = 16; +static unsigned long max_autoclose_min = 0; +static unsigned long max_autoclose_max = + (MAX_SCHEDULE_TIMEOUT / HZ > UINT_MAX) + ? UINT_MAX : MAX_SCHEDULE_TIMEOUT / HZ; extern long sysctl_sctp_mem[3]; extern int sysctl_sctp_rmem[3]; @@ -258,6 +262,15 @@ static ctl_table sctp_table[] = { .extra1 = &one, .extra2 = &rwnd_scale_max, }, + { + .procname = "max_autoclose", + .data = &sctp_max_autoclose, + .maxlen = sizeof(unsigned long), + .mode = 0644, + .proc_handler = &proc_doulongvec_minmax, + .extra1 = &max_autoclose_min, + .extra2 = &max_autoclose_max, + }, { /* sentinel */ } }; -- cgit v1.2.3-55-g7522 From a76c0adf60f6ca5ff3481992e4ea0383776b24d2 Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Mon, 19 Dec 2011 04:11:40 +0000 Subject: sctp: Do not account for sizeof(struct sk_buff) in estimated rwnd When checking whether a DATA chunk fits into the estimated rwnd a full sizeof(struct sk_buff) is added to the needed chunk size. This quickly exhausts the available rwnd space and leads to packets being sent which are much below the PMTU limit. This can lead to much worse performance. The reason for this behaviour was to avoid putting too much memory pressure on the receiver. The concept is not completely irational because a Linux receiver does in fact clone an skb for each DATA chunk delivered. However, Linux also reserves half the available socket buffer space for data structures therefore usage of it is already accounted for. When proposing to change this the last time it was noted that this behaviour was introduced to solve a performance issue caused by rwnd overusage in combination with small DATA chunks. Trying to reproduce this I found that with the sk_buff overhead removed, the performance would improve significantly unless socket buffer limits are increased. The following numbers have been gathered using a patched iperf supporting SCTP over a live 1 Gbit ethernet network. The -l option was used to limit DATA chunk sizes. The numbers listed are based on the average of 3 test runs each. Default values have been used for sk_(r|w)mem. Chunk Size Unpatched No Overhead ------------------------------------- 4 15.2 Kbit [!] 12.2 Mbit [!] 8 35.8 Kbit [!] 26.0 Mbit [!] 16 95.5 Kbit [!] 54.4 Mbit [!] 32 106.7 Mbit 102.3 Mbit 64 189.2 Mbit 188.3 Mbit 128 331.2 Mbit 334.8 Mbit 256 537.7 Mbit 536.0 Mbit 512 766.9 Mbit 766.6 Mbit 1024 810.1 Mbit 808.6 Mbit Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- net/sctp/output.c | 8 +------- net/sctp/outqueue.c | 6 ++---- 2 files changed, 3 insertions(+), 11 deletions(-) (limited to 'net/sctp') diff --git a/net/sctp/output.c b/net/sctp/output.c index 08b3cead6503..817174eb5f41 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -697,13 +697,7 @@ static void sctp_packet_append_data(struct sctp_packet *packet, /* Keep track of how many bytes are in flight to the receiver. */ asoc->outqueue.outstanding_bytes += datasize; - /* Update our view of the receiver's rwnd. Include sk_buff overhead - * while updating peer.rwnd so that it reduces the chances of a - * receiver running out of receive buffer space even when receive - * window is still open. This can happen when a sender is sending - * sending small messages. - */ - datasize += sizeof(struct sk_buff); + /* Update our view of the receiver's rwnd. */ if (datasize < rwnd) rwnd -= datasize; else diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index 14c2b06028ff..cfeb1d4a1ee6 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -411,8 +411,7 @@ void sctp_retransmit_mark(struct sctp_outq *q, chunk->transport->flight_size -= sctp_data_size(chunk); q->outstanding_bytes -= sctp_data_size(chunk); - q->asoc->peer.rwnd += (sctp_data_size(chunk) + - sizeof(struct sk_buff)); + q->asoc->peer.rwnd += sctp_data_size(chunk); } continue; } @@ -432,8 +431,7 @@ void sctp_retransmit_mark(struct sctp_outq *q, * (Section 7.2.4)), add the data size of those * chunks to the rwnd. */ - q->asoc->peer.rwnd += (sctp_data_size(chunk) + - sizeof(struct sk_buff)); + q->asoc->peer.rwnd += sctp_data_size(chunk); q->outstanding_bytes -= sctp_data_size(chunk); if (chunk->transport) transport->flight_size -= sctp_data_size(chunk); -- cgit v1.2.3-55-g7522