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/protocol.c | 3 +++ 1 file changed, 3 insertions(+) (limited to 'net/sctp/protocol.c') diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 08d14d86ecfb..f86be7bf0972 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1220,6 +1220,9 @@ static int __net_init sctp_defaults_init(struct net *net) /* Enable pf state by default */ net->sctp.pf_enable = 1; + /* Ignore pf exposure feature by default */ + net->sctp.pf_expose = SCTP_PF_EXPOSE_UNSET; + /* Association.Max.Retrans - 10 attempts * Path.Max.Retrans - 5 attempts (per destination address) * Max.Init.Retransmits - 8 attempts -- 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 --- Documentation/networking/ip-sysctl.txt | 12 ++++++++++++ include/net/netns/sctp.h | 6 ++++++ include/net/sctp/constants.h | 2 ++ include/net/sctp/structs.h | 11 ++++++++--- net/sctp/associola.c | 3 +++ net/sctp/protocol.c | 3 +++ net/sctp/sm_sideeffect.c | 5 +++++ net/sctp/socket.c | 1 + net/sctp/sysctl.c | 12 +++++++++++- 9 files changed, 51 insertions(+), 4 deletions(-) (limited to 'net/sctp/protocol.c') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 0b0feb5b6b00..099a55bd1432 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -2195,6 +2195,18 @@ pf_retrans - INTEGER Default: 0 +ps_retrans - INTEGER + Primary.Switchover.Max.Retrans (PSMR), it's a tunable parameter coming + from section-5 "Primary Path Switchover" in rfc7829. 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". 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. + + Default: 0xffff + rto_initial - INTEGER The initial round trip timeout value in milliseconds that will be used in calculating round trip times. This is the initial time interval diff --git a/include/net/netns/sctp.h b/include/net/netns/sctp.h index 18c3ddae77a3..d8d02e4188d1 100644 --- a/include/net/netns/sctp.h +++ b/include/net/netns/sctp.h @@ -89,6 +89,12 @@ struct netns_sctp { */ int pf_retrans; + /* Primary.Switchover.Max.Retrans sysctl value + * taken from: + * https://tools.ietf.org/html/rfc7829 + */ + int ps_retrans; + /* * Disable Potentially-Failed feature, the feature is enabled by default * pf_enable - 0 : disable pf diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index e88b77a34cb1..15b4d9aec7ff 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -296,6 +296,8 @@ enum { }; #define SCTP_PF_EXPOSE_MAX SCTP_PF_EXPOSE_ENABLE +#define SCTP_PS_RETRANS_MAX 0xffff + /* These return values describe the success or failure of a number of * routines which form the lower interface to SCTP_outqueue. */ diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index 9a43738774d7..3cc913f328cd 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -184,7 +184,8 @@ struct sctp_sock { __u32 flowlabel; __u8 dscp; - int pf_retrans; + __u16 pf_retrans; + __u16 ps_retrans; /* The initial Path MTU to use for new associations. */ __u32 pathmtu; @@ -897,7 +898,9 @@ struct sctp_transport { * and will be initialized from the assocs value. This can be changed * using the SCTP_PEER_ADDR_THLDS socket option */ - int pf_retrans; + __u16 pf_retrans; + /* Used for primary path switchover. */ + __u16 ps_retrans; /* PMTU : The current known path MTU. */ __u32 pathmtu; @@ -1773,7 +1776,9 @@ struct sctp_association { * and will be initialized from the assocs value. This can be * changed using the SCTP_PEER_ADDR_THLDS socket option */ - int pf_retrans; + __u16 pf_retrans; + /* Used for primary path switchover. */ + __u16 ps_retrans; /* Maximum number of times the endpoint will retransmit INIT */ __u16 max_init_attempts; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index ad7a74e942d3..8f8d18abd013 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -86,6 +86,7 @@ static struct sctp_association *sctp_association_init( */ asoc->max_retrans = sp->assocparams.sasoc_asocmaxrxt; asoc->pf_retrans = sp->pf_retrans; + asoc->ps_retrans = sp->ps_retrans; asoc->pf_expose = sp->pf_expose; asoc->rto_initial = msecs_to_jiffies(sp->rtoinfo.srto_initial); @@ -628,6 +629,8 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, /* And the partial failure retrans threshold */ peer->pf_retrans = asoc->pf_retrans; + /* And the primary path switchover retrans threshold */ + peer->ps_retrans = asoc->ps_retrans; /* Initialize the peer's SACK delay timeout based on the * association configured value. diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index f86be7bf0972..fbbf19128c2d 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1217,6 +1217,9 @@ static int __net_init sctp_defaults_init(struct net *net) /* Max.Burst - 4 */ net->sctp.max_burst = SCTP_DEFAULT_MAX_BURST; + /* Disable of Primary Path Switchover by default */ + net->sctp.ps_retrans = SCTP_PS_RETRANS_MAX; + /* Enable pf state by default */ net->sctp.pf_enable = 1; diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index e52b2128e43b..acd737d4c0e0 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -567,6 +567,11 @@ static void sctp_do_8_2_transport_strike(struct sctp_cmd_seq *commands, SCTP_FAILED_THRESHOLD); } + if (transport->error_count > transport->ps_retrans && + asoc->peer.primary_path == transport && + asoc->peer.active_path != transport) + sctp_assoc_set_primary(asoc, asoc->peer.active_path); + /* E2) For the destination address for which the timer * expires, set RTO <- RTO * 2 ("back off the timer"). The * maximum value discussed in rule C7 above (RTO.max) may be 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; diff --git a/net/sctp/sysctl.c b/net/sctp/sysctl.c index 5d1ad44a29d1..4740aa70e652 100644 --- a/net/sctp/sysctl.c +++ b/net/sctp/sysctl.c @@ -35,6 +35,7 @@ static int rto_beta_min = 0; static int rto_alpha_max = 1000; static int rto_beta_max = 1000; static int pf_expose_max = SCTP_PF_EXPOSE_MAX; +static int ps_retrans_max = SCTP_PS_RETRANS_MAX; static unsigned long max_autoclose_min = 0; static unsigned long max_autoclose_max = @@ -213,7 +214,16 @@ static struct ctl_table sctp_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_INT_MAX, + .extra2 = &init_net.sctp.ps_retrans, + }, + { + .procname = "ps_retrans", + .data = &init_net.sctp.ps_retrans, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &init_net.sctp.pf_retrans, + .extra2 = &ps_retrans_max, }, { .procname = "sndbuf_policy", -- cgit v1.2.3 From b6f3320b1d5267e7b583a6d0c88dda518101740c Mon Sep 17 00:00:00 2001 From: Xin Long Date: Mon, 9 Dec 2019 13:45:54 +0800 Subject: sctp: fully initialize v4 addr in some functions Syzbot found a crash: BUG: KMSAN: uninit-value in crc32_body lib/crc32.c:112 [inline] BUG: KMSAN: uninit-value in crc32_le_generic lib/crc32.c:179 [inline] BUG: KMSAN: uninit-value in __crc32c_le_base+0x4fa/0xd30 lib/crc32.c:202 Call Trace: crc32_body lib/crc32.c:112 [inline] crc32_le_generic lib/crc32.c:179 [inline] __crc32c_le_base+0x4fa/0xd30 lib/crc32.c:202 chksum_update+0xb2/0x110 crypto/crc32c_generic.c:90 crypto_shash_update+0x4c5/0x530 crypto/shash.c:107 crc32c+0x150/0x220 lib/libcrc32c.c:47 sctp_csum_update+0x89/0xa0 include/net/sctp/checksum.h:36 __skb_checksum+0x1297/0x12a0 net/core/skbuff.c:2640 sctp_compute_cksum include/net/sctp/checksum.h:59 [inline] sctp_packet_pack net/sctp/output.c:528 [inline] sctp_packet_transmit+0x40fb/0x4250 net/sctp/output.c:597 sctp_outq_flush_transports net/sctp/outqueue.c:1146 [inline] sctp_outq_flush+0x1823/0x5d80 net/sctp/outqueue.c:1194 sctp_outq_uncork+0xd0/0xf0 net/sctp/outqueue.c:757 sctp_cmd_interpreter net/sctp/sm_sideeffect.c:1781 [inline] sctp_side_effects net/sctp/sm_sideeffect.c:1184 [inline] sctp_do_sm+0x8fe1/0x9720 net/sctp/sm_sideeffect.c:1155 sctp_primitive_REQUESTHEARTBEAT+0x175/0x1a0 net/sctp/primitive.c:185 sctp_apply_peer_addr_params+0x212/0x1d40 net/sctp/socket.c:2433 sctp_setsockopt_peer_addr_params net/sctp/socket.c:2686 [inline] sctp_setsockopt+0x189bb/0x19090 net/sctp/socket.c:4672 The issue was caused by transport->ipaddr set with uninit addr param, which was passed by: sctp_transport_init net/sctp/transport.c:47 [inline] sctp_transport_new+0x248/0xa00 net/sctp/transport.c:100 sctp_assoc_add_peer+0x5ba/0x2030 net/sctp/associola.c:611 sctp_process_param net/sctp/sm_make_chunk.c:2524 [inline] where 'addr' is set by sctp_v4_from_addr_param(), and it doesn't initialize the padding of addr->v4. Later when calling sctp_make_heartbeat(), hbinfo.daddr(=transport->ipaddr) will become the part of skb, and the issue occurs. This patch is to fix it by initializing the padding of addr->v4 in sctp_v4_from_addr_param(), as well as other functions that do the similar thing, and these functions shouldn't trust that the caller initializes the memory, as Marcelo suggested. Reported-by: syzbot+6dcbfea81cd3d4dd0b02@syzkaller.appspotmail.com Signed-off-by: Xin Long Acked-by: Neil Horman Signed-off-by: David S. Miller --- net/sctp/protocol.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'net/sctp/protocol.c') diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index fbbf19128c2d..78af2fcf90cc 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -227,6 +227,7 @@ static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb, sa->sin_port = sh->dest; sa->sin_addr.s_addr = ip_hdr(skb)->daddr; } + memset(sa->sin_zero, 0, sizeof(sa->sin_zero)); } /* Initialize an sctp_addr from a socket. */ @@ -235,6 +236,7 @@ static void sctp_v4_from_sk(union sctp_addr *addr, struct sock *sk) addr->v4.sin_family = AF_INET; addr->v4.sin_port = 0; addr->v4.sin_addr.s_addr = inet_sk(sk)->inet_rcv_saddr; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Initialize sk->sk_rcv_saddr from sctp_addr. */ @@ -257,6 +259,7 @@ static void sctp_v4_from_addr_param(union sctp_addr *addr, addr->v4.sin_family = AF_INET; addr->v4.sin_port = port; addr->v4.sin_addr.s_addr = param->v4.addr.s_addr; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Initialize an address parameter from a sctp_addr and return the length @@ -281,6 +284,7 @@ static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct flowi4 *fl4, saddr->v4.sin_family = AF_INET; saddr->v4.sin_port = port; saddr->v4.sin_addr.s_addr = fl4->saddr; + memset(saddr->v4.sin_zero, 0, sizeof(saddr->v4.sin_zero)); } /* Compare two addresses exactly. */ @@ -303,6 +307,7 @@ static void sctp_v4_inaddr_any(union sctp_addr *addr, __be16 port) addr->v4.sin_family = AF_INET; addr->v4.sin_addr.s_addr = htonl(INADDR_ANY); addr->v4.sin_port = port; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Is this a wildcard address? */ -- cgit v1.2.3