From 099ecf59f05b5f30f42ebac0ab8cb94f9b18c90c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 5 Nov 2019 14:11:54 -0800 Subject: net: annotate lockless accesses to sk->sk_max_ack_backlog sk->sk_max_ack_backlog can be read without any lock being held at least in TCP/DCCP cases. We need to use READ_ONCE()/WRITE_ONCE() to avoid load/store tearing and/or potential KCSAN warnings. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/sctp/socket.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/sctp/socket.c') diff --git a/net/sctp/socket.c b/net/sctp/socket.c index ffd3262b7a41..53abb97e0061 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -8376,7 +8376,7 @@ static int sctp_listen_start(struct sock *sk, int backlog) } } - sk->sk_max_ack_backlog = backlog; + WRITE_ONCE(sk->sk_max_ack_backlog, backlog); return sctp_hash_endpoint(ep); } @@ -8430,7 +8430,7 @@ int sctp_inet_listen(struct socket *sock, int backlog) /* If we are already listening, just update the backlog */ if (sctp_sstate(sk, LISTENING)) - sk->sk_max_ack_backlog = backlog; + WRITE_ONCE(sk->sk_max_ack_backlog, backlog); else { err = sctp_listen_start(sk, backlog); if (err) -- cgit v1.2.3 From aef587be42925f92418083f08852d0011b2766ca Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 8 Nov 2019 13:20:32 +0800 Subject: sctp: add pf_expose per netns and sock and asoc As said in rfc7829, section 3, point 12: The SCTP stack SHOULD expose the PF state of its destination addresses to the ULP as well as provide the means to notify the ULP of state transitions of its destination addresses from active to PF, and vice versa. However, it is recommended that an SCTP stack implementing SCTP-PF also allows for the ULP to be kept ignorant of the PF state of its destinations and the associated state transitions, thus allowing for retention of the simpler state transition model of [RFC4960] in the ULP. Not only does it allow to expose the PF state to ULP, but also allow to ignore sctp-pf to ULP. So this patch is to add pf_expose per netns, sock and asoc. And in sctp_assoc_control_transport(), ulp_notify will be set to false if asoc->expose is not 'enabled' in next patch. It also allows a user to change pf_expose per netns by sysctl, and pf_expose per sock and asoc will be initialized with it. Note that pf_expose also works for SCTP_GET_PEER_ADDR_INFO sockopt, to not allow a user to query the state of a sctp-pf peer address when pf_expose is 'disabled', as said in section 7.3. v1->v2: - Fix a build warning noticed by Nathan Chancellor. v2->v3: - set pf_expose to UNUSED by default to keep compatible with old applications. v3->v4: - add a new entry for pf_expose on ip-sysctl.txt, as Marcelo suggested. - change this patch to 1/5, and move sctp_assoc_control_transport change into 2/5, as Marcelo suggested. - use SCTP_PF_EXPOSE_UNSET instead of SCTP_PF_EXPOSE_UNUSED, and set SCTP_PF_EXPOSE_UNSET to 0 in enum, as Marcelo suggested. Signed-off-by: Xin Long Acked-by: Neil Horman Signed-off-by: David S. Miller --- net/sctp/socket.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) (limited to 'net/sctp/socket.c') diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 53abb97e0061..318222e9c0a8 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5041,6 +5041,7 @@ static int sctp_init_sock(struct sock *sk) sp->hbinterval = net->sctp.hb_interval; sp->pathmaxrxt = net->sctp.max_retrans_path; sp->pf_retrans = net->sctp.pf_retrans; + sp->pf_expose = net->sctp.pf_expose; sp->pathmtu = 0; /* allow default discovery */ sp->sackdelay = net->sctp.sack_timeout; sp->sackfreq = 2; @@ -5521,8 +5522,16 @@ static int sctp_getsockopt_peer_addr_info(struct sock *sk, int len, transport = sctp_addr_id2transport(sk, &pinfo.spinfo_address, pinfo.spinfo_assoc_id); - if (!transport) - return -EINVAL; + if (!transport) { + retval = -EINVAL; + goto out; + } + + if (transport->state == SCTP_PF && + transport->asoc->pf_expose == SCTP_PF_EXPOSE_DISABLE) { + retval = -EACCES; + goto out; + } pinfo.spinfo_assoc_id = sctp_assoc2id(transport->asoc); pinfo.spinfo_state = transport->state; -- cgit v1.2.3 From 8d2a6935d842f12c25611b165eace778adb09a53 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 8 Nov 2019 13:20:34 +0800 Subject: sctp: add SCTP_EXPOSE_POTENTIALLY_FAILED_STATE sockopt This is a sockopt defined in section 7.3 of rfc7829: "Exposing the Potentially Failed Path State", by which users can change pf_expose per sock and asoc. The new sockopt SCTP_EXPOSE_POTENTIALLY_FAILED_STATE is also known as SCTP_EXPOSE_PF_STATE for short. v2->v3: - return -EINVAL if params.assoc_value > SCTP_PF_EXPOSE_MAX. - define SCTP_EXPOSE_PF_STATE SCTP_EXPOSE_POTENTIALLY_FAILED_STATE. v3->v4: - improve changelog. Signed-off-by: Xin Long Acked-by: Neil Horman Signed-off-by: David S. Miller --- net/sctp/socket.c | 79 +++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 79 insertions(+) (limited to 'net/sctp/socket.c') diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 318222e9c0a8..74c4e62ac741 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4589,6 +4589,40 @@ out: return retval; } +static int sctp_setsockopt_pf_expose(struct sock *sk, + char __user *optval, + unsigned int optlen) +{ + struct sctp_assoc_value params; + struct sctp_association *asoc; + int retval = -EINVAL; + + if (optlen != sizeof(params)) + goto out; + + if (copy_from_user(¶ms, optval, optlen)) { + retval = -EFAULT; + goto out; + } + + if (params.assoc_value > SCTP_PF_EXPOSE_MAX) + goto out; + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + goto out; + + if (asoc) + asoc->pf_expose = params.assoc_value; + else + sctp_sk(sk)->pf_expose = params.assoc_value; + retval = 0; + +out: + return retval; +} + /* API 6.2 setsockopt(), getsockopt() * * Applications use setsockopt() and getsockopt() to set or retrieve @@ -4798,6 +4832,9 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, case SCTP_ECN_SUPPORTED: retval = sctp_setsockopt_ecn_supported(sk, optval, optlen); break; + case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE: + retval = sctp_setsockopt_pf_expose(sk, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; @@ -7909,6 +7946,45 @@ out: return retval; } +static int sctp_getsockopt_pf_expose(struct sock *sk, int len, + char __user *optval, + int __user *optlen) +{ + struct sctp_assoc_value params; + struct sctp_association *asoc; + int retval = -EFAULT; + + if (len < sizeof(params)) { + retval = -EINVAL; + goto out; + } + + len = sizeof(params); + if (copy_from_user(¶ms, optval, len)) + goto out; + + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { + retval = -EINVAL; + goto out; + } + + params.assoc_value = asoc ? asoc->pf_expose + : sctp_sk(sk)->pf_expose; + + if (put_user(len, optlen)) + goto out; + + if (copy_to_user(optval, ¶ms, len)) + goto out; + + retval = 0; + +out: + return retval; +} + static int sctp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -8121,6 +8197,9 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, case SCTP_ECN_SUPPORTED: retval = sctp_getsockopt_ecn_supported(sk, len, optval, optlen); break; + case SCTP_EXPOSE_POTENTIALLY_FAILED_STATE: + retval = sctp_getsockopt_pf_expose(sk, len, optval, optlen); + break; default: retval = -ENOPROTOOPT; break; -- cgit v1.2.3 From 34515e94c92c3f593cd696abca8609246cbd75e6 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 8 Nov 2019 13:20:35 +0800 Subject: sctp: add support for Primary Path Switchover This is a new feature defined in section 5 of rfc7829: "Primary Path Switchover". By introducing a new tunable parameter: Primary.Switchover.Max.Retrans (PSMR) The primary path will be changed to another active path when the path error counter on the old primary path exceeds PSMR, so that "the SCTP sender is allowed to continue data transmission on a new working path even when the old primary destination address becomes active again". This patch is to add this tunable parameter, 'ps_retrans' per netns, sock, asoc and transport. It also allows a user to change ps_retrans per netns by sysctl, and ps_retrans per sock/asoc/transport will be initialized with it. The check will be done in sctp_do_8_2_transport_strike() when this feature is enabled. Note this feature is disabled by initializing 'ps_retrans' per netns as 0xffff by default, and its value can't be less than 'pf_retrans' when changing by sysctl. v3->v4: - add define SCTP_PS_RETRANS_MAX 0xffff, and use it on extra2 of sysctl 'ps_retrans'. - add a new entry for ps_retrans on ip-sysctl.txt. Signed-off-by: Xin Long Acked-by: Neil Horman Signed-off-by: David S. Miller --- net/sctp/socket.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/sctp/socket.c') diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 74c4e62ac741..64452ee410da 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -5078,6 +5078,7 @@ static int sctp_init_sock(struct sock *sk) sp->hbinterval = net->sctp.hb_interval; sp->pathmaxrxt = net->sctp.max_retrans_path; sp->pf_retrans = net->sctp.pf_retrans; + sp->ps_retrans = net->sctp.ps_retrans; sp->pf_expose = net->sctp.pf_expose; sp->pathmtu = 0; /* allow default discovery */ sp->sackdelay = net->sctp.sack_timeout; -- cgit v1.2.3 From d467ac0a38551a5904878b1f5a2fe20a040c0e11 Mon Sep 17 00:00:00 2001 From: Xin Long Date: Fri, 8 Nov 2019 13:20:36 +0800 Subject: sctp: add SCTP_PEER_ADDR_THLDS_V2 sockopt Section 7.2 of rfc7829: "Peer Address Thresholds (SCTP_PEER_ADDR_THLDS) Socket Option" extends 'struct sctp_paddrthlds' with 'spt_pathcpthld' added to allow a user to change ps_retrans per sock/asoc/transport, as other 2 paddrthlds: pf_retrans, pathmaxrxt. Note: to not break the user's program, here to support pf_retrans dump and setting by adding a new sockopt SCTP_PEER_ADDR_THLDS_V2, and a new structure sctp_paddrthlds_v2 instead of extending sctp_paddrthlds. Also, when setting ps_retrans, the value is not allowed to be greater than pf_retrans. v1->v2: - use SCTP_PEER_ADDR_THLDS_V2 to set/get pf_retrans instead, as Marcelo and David Laight suggested. Signed-off-by: Xin Long Acked-by: Neil Horman Signed-off-by: David S. Miller --- net/sctp/socket.c | 54 ++++++++++++++++++++++++++++++++++++++++-------------- 1 file changed, 40 insertions(+), 14 deletions(-) (limited to 'net/sctp/socket.c') diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 64452ee410da..83e4ca1fabda 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -3943,18 +3943,22 @@ static int sctp_setsockopt_auto_asconf(struct sock *sk, char __user *optval, */ static int sctp_setsockopt_paddr_thresholds(struct sock *sk, char __user *optval, - unsigned int optlen) + unsigned int optlen, bool v2) { - struct sctp_paddrthlds val; + struct sctp_paddrthlds_v2 val; struct sctp_transport *trans; struct sctp_association *asoc; + int len; - if (optlen < sizeof(struct sctp_paddrthlds)) + len = v2 ? sizeof(val) : sizeof(struct sctp_paddrthlds); + if (optlen < len) return -EINVAL; - if (copy_from_user(&val, (struct sctp_paddrthlds __user *)optval, - sizeof(struct sctp_paddrthlds))) + if (copy_from_user(&val, optval, len)) return -EFAULT; + if (v2 && val.spt_pathpfthld > val.spt_pathcpthld) + return -EINVAL; + if (!sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) { trans = sctp_addr_id2transport(sk, &val.spt_address, val.spt_assoc_id); @@ -3963,6 +3967,8 @@ static int sctp_setsockopt_paddr_thresholds(struct sock *sk, if (val.spt_pathmaxrxt) trans->pathmaxrxt = val.spt_pathmaxrxt; + if (v2) + trans->ps_retrans = val.spt_pathcpthld; trans->pf_retrans = val.spt_pathpfthld; return 0; @@ -3978,17 +3984,23 @@ static int sctp_setsockopt_paddr_thresholds(struct sock *sk, transports) { if (val.spt_pathmaxrxt) trans->pathmaxrxt = val.spt_pathmaxrxt; + if (v2) + trans->ps_retrans = val.spt_pathcpthld; trans->pf_retrans = val.spt_pathpfthld; } if (val.spt_pathmaxrxt) asoc->pathmaxrxt = val.spt_pathmaxrxt; + if (v2) + asoc->ps_retrans = val.spt_pathcpthld; asoc->pf_retrans = val.spt_pathpfthld; } else { struct sctp_sock *sp = sctp_sk(sk); if (val.spt_pathmaxrxt) sp->pathmaxrxt = val.spt_pathmaxrxt; + if (v2) + sp->ps_retrans = val.spt_pathcpthld; sp->pf_retrans = val.spt_pathpfthld; } @@ -4778,7 +4790,12 @@ static int sctp_setsockopt(struct sock *sk, int level, int optname, retval = sctp_setsockopt_auto_asconf(sk, optval, optlen); break; case SCTP_PEER_ADDR_THLDS: - retval = sctp_setsockopt_paddr_thresholds(sk, optval, optlen); + retval = sctp_setsockopt_paddr_thresholds(sk, optval, optlen, + false); + break; + case SCTP_PEER_ADDR_THLDS_V2: + retval = sctp_setsockopt_paddr_thresholds(sk, optval, optlen, + true); break; case SCTP_RECVRCVINFO: retval = sctp_setsockopt_recvrcvinfo(sk, optval, optlen); @@ -7217,18 +7234,19 @@ static int sctp_getsockopt_assoc_ids(struct sock *sk, int len, * http://www.ietf.org/id/draft-nishida-tsvwg-sctp-failover-05.txt */ static int sctp_getsockopt_paddr_thresholds(struct sock *sk, - char __user *optval, - int len, - int __user *optlen) + char __user *optval, int len, + int __user *optlen, bool v2) { - struct sctp_paddrthlds val; + struct sctp_paddrthlds_v2 val; struct sctp_transport *trans; struct sctp_association *asoc; + int min; - if (len < sizeof(struct sctp_paddrthlds)) + min = v2 ? sizeof(val) : sizeof(struct sctp_paddrthlds); + if (len < min) return -EINVAL; - len = sizeof(struct sctp_paddrthlds); - if (copy_from_user(&val, (struct sctp_paddrthlds __user *)optval, len)) + len = min; + if (copy_from_user(&val, optval, len)) return -EFAULT; if (!sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) { @@ -7239,6 +7257,7 @@ static int sctp_getsockopt_paddr_thresholds(struct sock *sk, val.spt_pathmaxrxt = trans->pathmaxrxt; val.spt_pathpfthld = trans->pf_retrans; + val.spt_pathcpthld = trans->ps_retrans; goto out; } @@ -7251,11 +7270,13 @@ static int sctp_getsockopt_paddr_thresholds(struct sock *sk, if (asoc) { val.spt_pathpfthld = asoc->pf_retrans; val.spt_pathmaxrxt = asoc->pathmaxrxt; + val.spt_pathcpthld = asoc->ps_retrans; } else { struct sctp_sock *sp = sctp_sk(sk); val.spt_pathpfthld = sp->pf_retrans; val.spt_pathmaxrxt = sp->pathmaxrxt; + val.spt_pathcpthld = sp->ps_retrans; } out: @@ -8135,7 +8156,12 @@ static int sctp_getsockopt(struct sock *sk, int level, int optname, retval = sctp_getsockopt_auto_asconf(sk, len, optval, optlen); break; case SCTP_PEER_ADDR_THLDS: - retval = sctp_getsockopt_paddr_thresholds(sk, optval, len, optlen); + retval = sctp_getsockopt_paddr_thresholds(sk, optval, len, + optlen, false); + break; + case SCTP_PEER_ADDR_THLDS_V2: + retval = sctp_getsockopt_paddr_thresholds(sk, optval, len, + optlen, true); break; case SCTP_GET_ASSOC_STATS: retval = sctp_getsockopt_assoc_stats(sk, len, optval, optlen); -- cgit v1.2.3