From bc337e8c0e762b0c1eaca00aa6955cd0e7013ba1 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Fri, 21 Feb 2025 16:43:54 +0100 Subject: mptcp: pm: remove unused ret value to set flags The returned value is not used, it can then be dropped. Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-1-2b70ab1cee79@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 99705a9c2238..ff1e5695dc1d 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1922,13 +1922,11 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk, spin_unlock_bh(&msk->pm.lock); } -static int mptcp_nl_set_flags(struct net *net, - struct mptcp_addr_info *addr, - u8 bkup, u8 changed) +static void mptcp_nl_set_flags(struct net *net, struct mptcp_addr_info *addr, + u8 bkup, u8 changed) { long s_slot = 0, s_num = 0; struct mptcp_sock *msk; - int ret = -EINVAL; while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; @@ -1938,7 +1936,7 @@ static int mptcp_nl_set_flags(struct net *net, lock_sock(sk); if (changed & MPTCP_PM_ADDR_FLAG_BACKUP) - ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, NULL, bkup); + mptcp_pm_nl_mp_prio_send_ack(msk, addr, NULL, bkup); if (changed & MPTCP_PM_ADDR_FLAG_FULLMESH) mptcp_pm_nl_fullmesh(msk, addr); release_sock(sk); @@ -1948,7 +1946,7 @@ next: cond_resched(); } - return ret; + return; } int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local, -- cgit From 145dc6cc4abdb3b76eb01a0943a540db2a01ebe6 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Fri, 21 Feb 2025 16:43:55 +0100 Subject: mptcp: pm: change to fullmesh only for 'subflow' If an endpoint doesn't have the 'subflow' flag -- in fact, has no type, so not 'subflow', 'signal', nor 'implicit' -- there are then no subflows created from this local endpoint to at least the initial destination address. In this case, no need to call mptcp_pm_nl_fullmesh() which is there to recreate the subflows to reflect the new value of the fullmesh attribute. Similarly, there is then no need to iterate over all connections to do nothing, if only the 'fullmesh' flag has been changed, and the endpoint doesn't have the 'subflow' one. So stop early when dealing with this specific case. Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-2-2b70ab1cee79@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 16 +++++++++------- 1 file changed, 9 insertions(+), 7 deletions(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index ff1e5695dc1d..1a0695e087af 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1923,11 +1923,16 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk, } static void mptcp_nl_set_flags(struct net *net, struct mptcp_addr_info *addr, - u8 bkup, u8 changed) + u8 flags, u8 changed) { + u8 is_subflow = !!(flags & MPTCP_PM_ADDR_FLAG_SUBFLOW); + u8 bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP); long s_slot = 0, s_num = 0; struct mptcp_sock *msk; + if (changed == MPTCP_PM_ADDR_FLAG_FULLMESH && !is_subflow) + return; + while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; @@ -1937,7 +1942,8 @@ static void mptcp_nl_set_flags(struct net *net, struct mptcp_addr_info *addr, lock_sock(sk); if (changed & MPTCP_PM_ADDR_FLAG_BACKUP) mptcp_pm_nl_mp_prio_send_ack(msk, addr, NULL, bkup); - if (changed & MPTCP_PM_ADDR_FLAG_FULLMESH) + /* Subflows will only be recreated if the SUBFLOW flag is set */ + if (is_subflow && (changed & MPTCP_PM_ADDR_FLAG_FULLMESH)) mptcp_pm_nl_fullmesh(msk, addr); release_sock(sk); @@ -1959,7 +1965,6 @@ int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local, struct mptcp_pm_addr_entry *entry; struct pm_nl_pernet *pernet; u8 lookup_by_id = 0; - u8 bkup = 0; pernet = pm_nl_get_pernet(net); @@ -1972,9 +1977,6 @@ int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local, } } - if (local->flags & MPTCP_PM_ADDR_FLAG_BACKUP) - bkup = 1; - spin_lock_bh(&pernet->lock); entry = lookup_by_id ? __lookup_addr_by_id(pernet, local->addr.id) : __lookup_addr(pernet, &local->addr); @@ -1996,7 +1998,7 @@ int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local, *local = *entry; spin_unlock_bh(&pernet->lock); - mptcp_nl_set_flags(net, &local->addr, bkup, changed); + mptcp_nl_set_flags(net, &local->addr, entry->flags, changed); return 0; } -- cgit From 63132fb054744e58de61d45a6d4f2a707cdfcfb3 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 21 Feb 2025 16:43:56 +0100 Subject: mptcp: pm: add a build check for userspace_pm_dump_addr This patch adds a build check for mptcp_userspace_pm_dump_addr() to make sure there is enough space in 'cb->ctx' to store an address id bitmap. Just in case info stored in 'cb->ctx' are increased later. Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-3-2b70ab1cee79@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_userspace.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 277cf092a870..b69fb5b18130 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -643,6 +643,8 @@ int mptcp_userspace_pm_dump_addr(struct sk_buff *msg, struct sock *sk; void *hdr; + BUILD_BUG_ON(sizeof(struct id_bitmap) > sizeof(cb->ctx)); + bitmap = (struct id_bitmap *)cb->ctx; msk = mptcp_userspace_pm_get_sock(info); -- cgit From f8fe8174657329609a80f66da1d3dd80a80de76b Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 21 Feb 2025 16:43:57 +0100 Subject: mptcp: pm: add mptcp_pm_genl_fill_addr helper To save some redundant code in dump_addr() interfaces of both the netlink PM and userspace PM, the code that calls netlink message helpers (genlmsg_put/cancel/end) and mptcp_nl_fill_addr() is wrapped into a new helper mptcp_pm_genl_fill_addr(). Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-4-2b70ab1cee79@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm.c | 21 +++++++++++++++++++++ net/mptcp/pm_netlink.c | 12 +----------- net/mptcp/pm_userspace.c | 12 +----------- net/mptcp/protocol.h | 3 +++ 4 files changed, 26 insertions(+), 22 deletions(-) diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index b1f36dc1a091..16cacce6c10f 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -489,6 +489,27 @@ fail: return ret; } +int mptcp_pm_genl_fill_addr(struct sk_buff *msg, + struct netlink_callback *cb, + struct mptcp_pm_addr_entry *entry) +{ + void *hdr; + + hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, &mptcp_genl_family, + NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR); + if (!hdr) + return -EINVAL; + + if (mptcp_nl_fill_addr(msg, entry) < 0) { + genlmsg_cancel(msg, hdr); + return -EINVAL; + } + + genlmsg_end(msg, hdr); + return 0; +} + static int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb) { const struct genl_info *info = genl_info_dump(cb); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 1a0695e087af..98fcbf8b1465 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1798,7 +1798,6 @@ int mptcp_pm_nl_dump_addr(struct sk_buff *msg, struct mptcp_pm_addr_entry *entry; struct pm_nl_pernet *pernet; int id = cb->args[0]; - void *hdr; int i; pernet = pm_nl_get_pernet(net); @@ -1813,19 +1812,10 @@ int mptcp_pm_nl_dump_addr(struct sk_buff *msg, if (entry->addr.id <= id) continue; - hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, &mptcp_genl_family, - NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR); - if (!hdr) + if (mptcp_pm_genl_fill_addr(msg, cb, entry) < 0) break; - if (mptcp_nl_fill_addr(msg, entry) < 0) { - genlmsg_cancel(msg, hdr); - break; - } - id = entry->addr.id; - genlmsg_end(msg, hdr); } } rcu_read_unlock(); diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index b69fb5b18130..bedd6f9ebc8b 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -641,7 +641,6 @@ int mptcp_userspace_pm_dump_addr(struct sk_buff *msg, struct mptcp_sock *msk; int ret = -EINVAL; struct sock *sk; - void *hdr; BUILD_BUG_ON(sizeof(struct id_bitmap) > sizeof(cb->ctx)); @@ -659,19 +658,10 @@ int mptcp_userspace_pm_dump_addr(struct sk_buff *msg, if (test_bit(entry->addr.id, bitmap->map)) continue; - hdr = genlmsg_put(msg, NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, &mptcp_genl_family, - NLM_F_MULTI, MPTCP_PM_CMD_GET_ADDR); - if (!hdr) + if (mptcp_pm_genl_fill_addr(msg, cb, entry) < 0) break; - if (mptcp_nl_fill_addr(msg, entry) < 0) { - genlmsg_cancel(msg, hdr); - break; - } - __set_bit(entry->addr.id, bitmap->map); - genlmsg_end(msg, hdr); } spin_unlock_bh(&msk->pm.lock); release_sock(sk); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index ca65f8bff632..256677c43ca6 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -1057,6 +1057,9 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf struct request_sock *req); int mptcp_nl_fill_addr(struct sk_buff *skb, struct mptcp_pm_addr_entry *entry); +int mptcp_pm_genl_fill_addr(struct sk_buff *msg, + struct netlink_callback *cb, + struct mptcp_pm_addr_entry *entry); static inline bool mptcp_pm_should_add_signal(struct mptcp_sock *msk) { -- cgit From 640e3d69d0bc70d7d3de34800a1640793262bd08 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 21 Feb 2025 16:43:58 +0100 Subject: mptcp: pm: drop match in userspace_pm_append_new_local_addr The variable 'match' in mptcp_userspace_pm_append_new_local_addr() is a redundant one, and this patch drops it. No need to define 'match' as 'struct mptcp_pm_addr_entry *' type. In this function, it's only used to check whether it's NULL. It can be defined as a Boolean one. Also other variables 'addr_match' and 'id_match' make 'match' a redundant one, which can be replaced by directly checking 'addr_match && id_match'. Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-5-2b70ab1cee79@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_userspace.c | 11 +++-------- 1 file changed, 3 insertions(+), 8 deletions(-) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index bedd6f9ebc8b..a16e2fb45a6c 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -48,7 +48,6 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, bool needs_id) { DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); - struct mptcp_pm_addr_entry *match = NULL; struct sock *sk = (struct sock *)msk; struct mptcp_pm_addr_entry *e; bool addr_match = false; @@ -63,16 +62,12 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, if (addr_match && entry->addr.id == 0 && needs_id) entry->addr.id = e->addr.id; id_match = (e->addr.id == entry->addr.id); - if (addr_match && id_match) { - match = e; + if (addr_match || id_match) break; - } else if (addr_match || id_match) { - break; - } __set_bit(e->addr.id, id_bitmap); } - if (!match && !addr_match && !id_match) { + if (!addr_match && !id_match) { /* Memory for the entry is allocated from the * sock option buffer. */ @@ -90,7 +85,7 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, list_add_tail_rcu(&e->list, &msk->pm.userspace_pm_local_addr_list); msk->pm.local_addr_used++; ret = e->addr.id; - } else if (match) { + } else if (addr_match && id_match) { ret = entry->addr.id; } -- cgit From dc41695200a1f5db720f7988952a74833542831d Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 21 Feb 2025 16:43:59 +0100 Subject: mptcp: pm: drop inet6_sk after inet_sk In mptcp_event_add_subflow(), mptcp_event_pm_listener() and mptcp_nl_find_ssk(), 'issk' has already been got through inet_sk(). No need to use inet6_sk() to get 'ipv6_pinfo' again, just use issk->pinet6 instead. This patch also drops these 'ipv6_pinfo' variables. Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-6-2b70ab1cee79@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 8 ++------ net/mptcp/pm_userspace.c | 4 +--- 2 files changed, 3 insertions(+), 9 deletions(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 98fcbf8b1465..f67b637c1fcf 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -2022,9 +2022,7 @@ static int mptcp_event_add_subflow(struct sk_buff *skb, const struct sock *ssk) break; #if IS_ENABLED(CONFIG_MPTCP_IPV6) case AF_INET6: { - const struct ipv6_pinfo *np = inet6_sk(ssk); - - if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &np->saddr)) + if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &issk->pinet6->saddr)) return -EMSGSIZE; if (nla_put_in6_addr(skb, MPTCP_ATTR_DADDR6, &ssk->sk_v6_daddr)) return -EMSGSIZE; @@ -2251,9 +2249,7 @@ void mptcp_event_pm_listener(const struct sock *ssk, break; #if IS_ENABLED(CONFIG_MPTCP_IPV6) case AF_INET6: { - const struct ipv6_pinfo *np = inet6_sk(ssk); - - if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &np->saddr)) + if (nla_put_in6_addr(skb, MPTCP_ATTR_SADDR6, &issk->pinet6->saddr)) goto nla_put_failure; break; } diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index a16e2fb45a6c..6bf6a20ef7f3 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -460,9 +460,7 @@ static struct sock *mptcp_nl_find_ssk(struct mptcp_sock *msk, break; #if IS_ENABLED(CONFIG_MPTCP_IPV6) case AF_INET6: { - const struct ipv6_pinfo *pinfo = inet6_sk(ssk); - - if (!ipv6_addr_equal(&local->addr6, &pinfo->saddr) || + if (!ipv6_addr_equal(&local->addr6, &issk->pinet6->saddr) || !ipv6_addr_equal(&remote->addr6, &ssk->sk_v6_daddr)) continue; break; -- cgit From 7720790fd56b91259efe500a702ad4c0fd29b260 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 21 Feb 2025 16:44:00 +0100 Subject: mptcp: pm: use ipv6_addr_equal in addresses_equal Use ipv6_addr_equal() to check whether two IPv6 addresses are equal in mptcp_addresses_equal(). This is more appropriate than using !ipv6_addr_cmp(). Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts (NGI0) Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-7-2b70ab1cee79@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index f67b637c1fcf..ef85a60151ad 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -64,7 +64,7 @@ bool mptcp_addresses_equal(const struct mptcp_addr_info *a, addr_equals = a->addr.s_addr == b->addr.s_addr; #if IS_ENABLED(CONFIG_MPTCP_IPV6) else - addr_equals = !ipv6_addr_cmp(&a->addr6, &b->addr6); + addr_equals = ipv6_addr_equal(&a->addr6, &b->addr6); } else if (a->family == AF_INET) { if (ipv6_addr_v4mapped(&b->addr6)) addr_equals = a->addr.s_addr == b->addr6.s6_addr32[3]; -- cgit From 9771a96a7a35daa2220cc4f170b840b34af28b2c Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Fri, 21 Feb 2025 16:44:01 +0100 Subject: mptcp: sched: split get_subflow interface into two get_retrans() interface of the burst packet scheduler invokes a sleeping function mptcp_pm_subflow_chk_stale(), which calls __lock_sock_fast(). So get_retrans() interface should be set with BPF_F_SLEEPABLE flag in BPF. But get_send() interface of this scheduler can't be set with BPF_F_SLEEPABLE flag since it's invoked in ack_update_msk() under mptcp data lock. So this patch has to split get_subflow() interface of packet scheduer into two interfaces: get_send() and get_retrans(). Then we can set get_retrans() interface alone with BPF_F_SLEEPABLE flag. Signed-off-by: Geliang Tang Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-8-2b70ab1cee79@kernel.org Signed-off-by: Jakub Kicinski --- include/net/mptcp.h | 5 +++-- net/mptcp/sched.c | 35 ++++++++++++++++++++++++----------- 2 files changed, 27 insertions(+), 13 deletions(-) diff --git a/include/net/mptcp.h b/include/net/mptcp.h index 814b5f2e3ed5..2c85ca92bb1c 100644 --- a/include/net/mptcp.h +++ b/include/net/mptcp.h @@ -103,13 +103,14 @@ struct mptcp_out_options { #define MPTCP_SUBFLOWS_MAX 8 struct mptcp_sched_data { - bool reinject; u8 subflows; struct mptcp_subflow_context *contexts[MPTCP_SUBFLOWS_MAX]; }; struct mptcp_sched_ops { - int (*get_subflow)(struct mptcp_sock *msk, + int (*get_send)(struct mptcp_sock *msk, + struct mptcp_sched_data *data); + int (*get_retrans)(struct mptcp_sock *msk, struct mptcp_sched_data *data); char name[MPTCP_SCHED_NAME_MAX]; diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c index df7dbcfa3b71..94dc4b3ad82f 100644 --- a/net/mptcp/sched.c +++ b/net/mptcp/sched.c @@ -16,13 +16,25 @@ static DEFINE_SPINLOCK(mptcp_sched_list_lock); static LIST_HEAD(mptcp_sched_list); -static int mptcp_sched_default_get_subflow(struct mptcp_sock *msk, +static int mptcp_sched_default_get_send(struct mptcp_sock *msk, + struct mptcp_sched_data *data) +{ + struct sock *ssk; + + ssk = mptcp_subflow_get_send(msk); + if (!ssk) + return -EINVAL; + + mptcp_subflow_set_scheduled(mptcp_subflow_ctx(ssk), true); + return 0; +} + +static int mptcp_sched_default_get_retrans(struct mptcp_sock *msk, struct mptcp_sched_data *data) { struct sock *ssk; - ssk = data->reinject ? mptcp_subflow_get_retrans(msk) : - mptcp_subflow_get_send(msk); + ssk = mptcp_subflow_get_retrans(msk); if (!ssk) return -EINVAL; @@ -31,7 +43,8 @@ static int mptcp_sched_default_get_subflow(struct mptcp_sock *msk, } static struct mptcp_sched_ops mptcp_sched_default = { - .get_subflow = mptcp_sched_default_get_subflow, + .get_send = mptcp_sched_default_get_send, + .get_retrans = mptcp_sched_default_get_retrans, .name = "default", .owner = THIS_MODULE, }; @@ -73,7 +86,7 @@ void mptcp_get_available_schedulers(char *buf, size_t maxlen) int mptcp_register_scheduler(struct mptcp_sched_ops *sched) { - if (!sched->get_subflow) + if (!sched->get_send) return -EINVAL; spin_lock(&mptcp_sched_list_lock); @@ -164,10 +177,9 @@ int mptcp_sched_get_send(struct mptcp_sock *msk) return 0; } - data.reinject = false; if (msk->sched == &mptcp_sched_default || !msk->sched) - return mptcp_sched_default_get_subflow(msk, &data); - return msk->sched->get_subflow(msk, &data); + return mptcp_sched_default_get_send(msk, &data); + return msk->sched->get_send(msk, &data); } int mptcp_sched_get_retrans(struct mptcp_sock *msk) @@ -186,8 +198,9 @@ int mptcp_sched_get_retrans(struct mptcp_sock *msk) return 0; } - data.reinject = true; if (msk->sched == &mptcp_sched_default || !msk->sched) - return mptcp_sched_default_get_subflow(msk, &data); - return msk->sched->get_subflow(msk, &data); + return mptcp_sched_default_get_retrans(msk, &data); + if (msk->sched->get_retrans) + return msk->sched->get_retrans(msk, &data); + return msk->sched->get_send(msk, &data); } -- cgit From b68b106b0f15424db6c78d8c1a0616f698080b9d Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Fri, 21 Feb 2025 16:44:02 +0100 Subject: mptcp: sched: reduce size for unused data Thanks for the previous commit ("mptcp: sched: split get_subflow interface into two"), the mptcp_sched_data structure is now currently unused. This structure has been added to allow future extensions that are not ready yet. At the end, this structure will not even be used at all when mptcp_subflow bpf_iter will be supported [1]. Here is a first step to save 64 bytes on the stack for each scheduling operation. The structure is not removed yet not to break the WIP work on these extensions, but will be done when [1] will be ready and applied. Link: https://lore.kernel.org/6645ad6e-8874-44c5-8730-854c30673218@linux.dev [1] Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-9-2b70ab1cee79@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/sched.c | 14 +++++++------- 1 file changed, 7 insertions(+), 7 deletions(-) diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c index 94dc4b3ad82f..c16c6fbd4ba2 100644 --- a/net/mptcp/sched.c +++ b/net/mptcp/sched.c @@ -157,7 +157,7 @@ void mptcp_subflow_set_scheduled(struct mptcp_subflow_context *subflow, int mptcp_sched_get_send(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; - struct mptcp_sched_data data; + struct mptcp_sched_data *data = NULL; msk_owned_by_me(msk); @@ -178,14 +178,14 @@ int mptcp_sched_get_send(struct mptcp_sock *msk) } if (msk->sched == &mptcp_sched_default || !msk->sched) - return mptcp_sched_default_get_send(msk, &data); - return msk->sched->get_send(msk, &data); + return mptcp_sched_default_get_send(msk, data); + return msk->sched->get_send(msk, data); } int mptcp_sched_get_retrans(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; - struct mptcp_sched_data data; + struct mptcp_sched_data *data = NULL; msk_owned_by_me(msk); @@ -199,8 +199,8 @@ int mptcp_sched_get_retrans(struct mptcp_sock *msk) } if (msk->sched == &mptcp_sched_default || !msk->sched) - return mptcp_sched_default_get_retrans(msk, &data); + return mptcp_sched_default_get_retrans(msk, data); if (msk->sched->get_retrans) - return msk->sched->get_retrans(msk, &data); - return msk->sched->get_send(msk, &data); + return msk->sched->get_retrans(msk, data); + return msk->sched->get_send(msk, data); } -- cgit From 8275ac799ee15e972841eb77b694d63f5e888519 Mon Sep 17 00:00:00 2001 From: "Matthieu Baerts (NGI0)" Date: Fri, 21 Feb 2025 16:44:03 +0100 Subject: mptcp: blackhole: avoid checking the state twice A small cleanup, reordering the conditions to avoid checking things twice. The code here is called in case of timeout on a TCP connection, before triggering a retransmission. But it only acts on SYN + MPC packets. So the conditions can be re-order to exit early in case of non-MPTCP SYN + MPC. This also reduce the indentation levels. Reviewed-by: Mat Martineau Signed-off-by: Matthieu Baerts (NGI0) Link: https://patch.msgid.link/20250221-net-next-mptcp-pm-misc-cleanup-3-v1-10-2b70ab1cee79@kernel.org Signed-off-by: Jakub Kicinski --- net/mptcp/ctrl.c | 30 +++++++++++++++++------------- 1 file changed, 17 insertions(+), 13 deletions(-) diff --git a/net/mptcp/ctrl.c b/net/mptcp/ctrl.c index 2dd81e6c26bd..be6c0237e10b 100644 --- a/net/mptcp/ctrl.c +++ b/net/mptcp/ctrl.c @@ -401,26 +401,30 @@ void mptcp_active_enable(struct sock *sk) void mptcp_active_detect_blackhole(struct sock *ssk, bool expired) { struct mptcp_subflow_context *subflow; + u8 timeouts, to_max; + struct net *net; - if (!sk_is_mptcp(ssk)) + /* Only check MPTCP SYN ... */ + if (likely(!sk_is_mptcp(ssk) || ssk->sk_state != TCP_SYN_SENT)) return; subflow = mptcp_subflow_ctx(ssk); - if (subflow->request_mptcp && ssk->sk_state == TCP_SYN_SENT) { - struct net *net = sock_net(ssk); - u8 timeouts, to_max; + /* ... + MP_CAPABLE */ + if (!subflow->request_mptcp) { + /* Mark as blackhole iif the 1st non-MPTCP SYN is accepted */ + subflow->mpc_drop = 0; + return; + } - timeouts = inet_csk(ssk)->icsk_retransmits; - to_max = mptcp_get_pernet(net)->syn_retrans_before_tcp_fallback; + net = sock_net(ssk); + timeouts = inet_csk(ssk)->icsk_retransmits; + to_max = mptcp_get_pernet(net)->syn_retrans_before_tcp_fallback; - if (timeouts == to_max || (timeouts < to_max && expired)) { - MPTCP_INC_STATS(net, MPTCP_MIB_MPCAPABLEACTIVEDROP); - subflow->mpc_drop = 1; - mptcp_subflow_early_fallback(mptcp_sk(subflow->conn), subflow); - } - } else if (ssk->sk_state == TCP_SYN_SENT) { - subflow->mpc_drop = 0; + if (timeouts == to_max || (timeouts < to_max && expired)) { + MPTCP_INC_STATS(net, MPTCP_MIB_MPCAPABLEACTIVEDROP); + subflow->mpc_drop = 1; + mptcp_subflow_early_fallback(mptcp_sk(subflow->conn), subflow); } } -- cgit