From e76c8ef5cc5b77debe711717f61a3fbf24904873 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 17 May 2023 12:16:15 -0700 Subject: mptcp: refactor mptcp_stream_accept() Rewrite the mptcp socket accept op, leveraging the new __inet_accept() helper. This way we can avoid acquiring the new socket lock twice and we can avoid a couple of indirect calls. Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 21 ++++++++++++--------- 1 file changed, 12 insertions(+), 9 deletions(-) (limited to 'net/mptcp') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 08dc53f56bc2..2d331b2d62b7 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3747,6 +3747,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, { struct mptcp_sock *msk = mptcp_sk(sock->sk); struct socket *ssock; + struct sock *newsk; int err; pr_debug("msk=%p", msk); @@ -3758,17 +3759,20 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, if (!ssock) return -EINVAL; - err = ssock->ops->accept(sock, newsock, flags, kern); - if (err == 0 && !mptcp_is_tcpsk(newsock->sk)) { - struct mptcp_sock *msk = mptcp_sk(newsock->sk); + newsk = mptcp_accept(sock->sk, flags, &err, kern); + if (!newsk) + return err; + + lock_sock(newsk); + + __inet_accept(sock, newsock, newsk); + if (!mptcp_is_tcpsk(newsock->sk)) { + struct mptcp_sock *msk = mptcp_sk(newsk); struct mptcp_subflow_context *subflow; - struct sock *newsk = newsock->sk; set_bit(SOCK_CUSTOM_SOCKOPT, &newsock->flags); msk->in_accept_queue = 0; - lock_sock(newsk); - /* set ssk->sk_socket of accept()ed flows to mptcp socket. * This is needed so NOSPACE flag can be set from tcp stack. */ @@ -3789,11 +3793,10 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock, if (unlikely(list_empty(&msk->conn_list))) inet_sk_state_store(newsk, TCP_CLOSE); } - - release_sock(newsk); } + release_sock(newsk); - return err; + return 0; } static __poll_t mptcp_check_writeable(struct mptcp_sock *msk) -- cgit v1.2.3 From 45b1a1227a7aaa99254551c513406c7aa904e968 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Wed, 17 May 2023 12:16:16 -0700 Subject: mptcp: introduces more address related mibs Currently we don't track explicitly a few events related to address management suboption handling; this patch adds new mibs for ADD_ADDR and RM_ADDR options tx and for missed tx events due to internal storage exhaustion. The self-tests must be updated to properly handle different mibs with the same/shared prefix. Additionally removes a couple of warning tracking the loss event. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/378 Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Mat Martineau Signed-off-by: Jakub Kicinski --- net/mptcp/mib.c | 6 ++++++ net/mptcp/mib.h | 18 ++++++++++++++++++ net/mptcp/options.c | 5 ++++- net/mptcp/pm.c | 6 ++++-- tools/testing/selftests/net/mptcp/mptcp_join.sh | 4 ++-- 5 files changed, 34 insertions(+), 5 deletions(-) (limited to 'net/mptcp') diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c index 0dac2863c6e1..a0990c365a2e 100644 --- a/net/mptcp/mib.c +++ b/net/mptcp/mib.c @@ -34,7 +34,11 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("NoDSSInWindow", MPTCP_MIB_NODSSWINDOW), SNMP_MIB_ITEM("DuplicateData", MPTCP_MIB_DUPDATA), SNMP_MIB_ITEM("AddAddr", MPTCP_MIB_ADDADDR), + SNMP_MIB_ITEM("AddAddrTx", MPTCP_MIB_ADDADDRTX), + SNMP_MIB_ITEM("AddAddrTxDrop", MPTCP_MIB_ADDADDRTXDROP), SNMP_MIB_ITEM("EchoAdd", MPTCP_MIB_ECHOADD), + SNMP_MIB_ITEM("EchoAddTx", MPTCP_MIB_ECHOADDTX), + SNMP_MIB_ITEM("EchoAddTxDrop", MPTCP_MIB_ECHOADDTXDROP), SNMP_MIB_ITEM("PortAdd", MPTCP_MIB_PORTADD), SNMP_MIB_ITEM("AddAddrDrop", MPTCP_MIB_ADDADDRDROP), SNMP_MIB_ITEM("MPJoinPortSynRx", MPTCP_MIB_JOINPORTSYNRX), @@ -44,6 +48,8 @@ static const struct snmp_mib mptcp_snmp_list[] = { SNMP_MIB_ITEM("MismatchPortAckRx", MPTCP_MIB_MISMATCHPORTACKRX), SNMP_MIB_ITEM("RmAddr", MPTCP_MIB_RMADDR), SNMP_MIB_ITEM("RmAddrDrop", MPTCP_MIB_RMADDRDROP), + SNMP_MIB_ITEM("RmAddrTx", MPTCP_MIB_RMADDRTX), + SNMP_MIB_ITEM("RmAddrTxDrop", MPTCP_MIB_RMADDRTXDROP), SNMP_MIB_ITEM("RmSubflow", MPTCP_MIB_RMSUBFLOW), SNMP_MIB_ITEM("MPPrioTx", MPTCP_MIB_MPPRIOTX), SNMP_MIB_ITEM("MPPrioRx", MPTCP_MIB_MPPRIORX), diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h index 2be3596374f4..cae71d947252 100644 --- a/net/mptcp/mib.h +++ b/net/mptcp/mib.h @@ -27,7 +27,15 @@ enum linux_mptcp_mib_field { MPTCP_MIB_NODSSWINDOW, /* Segments not in MPTCP windows */ MPTCP_MIB_DUPDATA, /* Segments discarded due to duplicate DSS */ MPTCP_MIB_ADDADDR, /* Received ADD_ADDR with echo-flag=0 */ + MPTCP_MIB_ADDADDRTX, /* Sent ADD_ADDR with echo-flag=0 */ + MPTCP_MIB_ADDADDRTXDROP, /* ADD_ADDR with echo-flag=0 not send due to + * resource exhaustion + */ MPTCP_MIB_ECHOADD, /* Received ADD_ADDR with echo-flag=1 */ + MPTCP_MIB_ECHOADDTX, /* Send ADD_ADDR with echo-flag=1 */ + MPTCP_MIB_ECHOADDTXDROP, /* ADD_ADDR with echo-flag=1 not send due + * to resource exhaustion + */ MPTCP_MIB_PORTADD, /* Received ADD_ADDR with a port-number */ MPTCP_MIB_ADDADDRDROP, /* Dropped incoming ADD_ADDR */ MPTCP_MIB_JOINPORTSYNRX, /* Received a SYN MP_JOIN with a different port-number */ @@ -37,6 +45,8 @@ enum linux_mptcp_mib_field { MPTCP_MIB_MISMATCHPORTACKRX, /* Received an ACK MP_JOIN with a mismatched port-number */ MPTCP_MIB_RMADDR, /* Received RM_ADDR */ MPTCP_MIB_RMADDRDROP, /* Dropped incoming RM_ADDR */ + MPTCP_MIB_RMADDRTX, /* Sent RM_ADDR */ + MPTCP_MIB_RMADDRTXDROP, /* RM_ADDR not sent due to resource exhaustion */ MPTCP_MIB_RMSUBFLOW, /* Remove a subflow */ MPTCP_MIB_MPPRIOTX, /* Transmit a MP_PRIO */ MPTCP_MIB_MPPRIORX, /* Received a MP_PRIO */ @@ -63,6 +73,14 @@ struct mptcp_mib { unsigned long mibs[LINUX_MIB_MPTCP_MAX]; }; +static inline void MPTCP_ADD_STATS(struct net *net, + enum linux_mptcp_mib_field field, + int val) +{ + if (likely(net->mib.mptcp_statistics)) + SNMP_ADD_STATS(net->mib.mptcp_statistics, field, val); +} + static inline void MPTCP_INC_STATS(struct net *net, enum linux_mptcp_mib_field field) { diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 19a01b6566f1..8a8083207be4 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -687,9 +687,12 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff * } opts->suboptions |= OPTION_MPTCP_ADD_ADDR; if (!echo) { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ADDADDRTX); opts->ahmac = add_addr_generate_hmac(msk->local_key, msk->remote_key, &opts->addr); + } else { + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADDTX); } pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d", opts->addr.id, opts->ahmac, echo, ntohs(opts->addr.port)); @@ -723,7 +726,7 @@ static bool mptcp_established_options_rm_addr(struct sock *sk, for (i = 0; i < opts->rm_list.nr; i++) pr_debug("rm_list_ids[%d]=%d", i, opts->rm_list.ids[i]); - + MPTCP_ADD_STATS(sock_net(sk), MPTCP_MIB_RMADDRTX, opts->rm_list.nr); return true; } diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 78c924506e83..7d03b5fd8200 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -26,7 +26,8 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk, if (add_addr & (echo ? BIT(MPTCP_ADD_ADDR_ECHO) : BIT(MPTCP_ADD_ADDR_SIGNAL))) { - pr_warn("addr_signal error, add_addr=%d, echo=%d", add_addr, echo); + MPTCP_INC_STATS(sock_net((struct sock *)msk), + echo ? MPTCP_MIB_ECHOADDTXDROP : MPTCP_MIB_ADDADDRTXDROP); return -EINVAL; } @@ -48,7 +49,8 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_ pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr); if (rm_addr) { - pr_warn("addr_signal error, rm_addr=%d", rm_addr); + MPTCP_ADD_STATS(sock_net((struct sock *)msk), + MPTCP_MIB_RMADDRTXDROP, rm_list->nr); return -EINVAL; } diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index 26310c17b4c6..0886ed2c59ea 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -1492,7 +1492,7 @@ chk_add_nr() fi echo -n " - echo " - count=$(ip netns exec $ns1 nstat -as | grep MPTcpExtEchoAdd | awk '{print $2}') + count=$(ip netns exec $ns1 nstat -as MPTcpExtEchoAdd | grep MPTcpExtEchoAdd | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$echo_nr" ]; then echo "[fail] got $count ADD_ADDR echo[s] expected $echo_nr" @@ -1614,7 +1614,7 @@ chk_rm_nr() fi printf "%-${nr_blank}s %s" " " "rm " - count=$(ip netns exec $addr_ns nstat -as | grep MPTcpExtRmAddr | awk '{print $2}') + count=$(ip netns exec $addr_ns nstat -as MPTcpExtRmAddr | grep MPTcpExtRmAddr | awk '{print $2}') [ -z "$count" ] && count=0 if [ "$count" != "$rm_addr_nr" ]; then echo "[fail] got $count RM_ADDR[s] expected $rm_addr_nr" -- cgit v1.2.3 From dc886bce753cc2cf3c88ec5c7a6880a4e17d65ba Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Thu, 8 Jun 2023 15:20:49 +0200 Subject: mptcp: export local_address Rename local_address() with "mptcp_" prefix and export it in protocol.h. This function will be re-used in the common PM code (pm.c) in the following commit. Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Reviewed-by: Larysa Zaremba Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 17 ++++++++--------- net/mptcp/protocol.h | 1 + 2 files changed, 9 insertions(+), 9 deletions(-) (limited to 'net/mptcp') diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 59f8f3124855..0bf09c45febd 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -86,8 +86,7 @@ bool mptcp_addresses_equal(const struct mptcp_addr_info *a, return a->port == b->port; } -static void local_address(const struct sock_common *skc, - struct mptcp_addr_info *addr) +void mptcp_local_address(const struct sock_common *skc, struct mptcp_addr_info *addr) { addr->family = skc->skc_family; addr->port = htons(skc->skc_num); @@ -122,7 +121,7 @@ static bool lookup_subflow_by_saddr(const struct list_head *list, list_for_each_entry(subflow, list, node) { skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow); - local_address(skc, &cur); + mptcp_local_address(skc, &cur); if (mptcp_addresses_equal(&cur, saddr, saddr->port)) return true; } @@ -263,7 +262,7 @@ bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk) struct mptcp_addr_info saddr; bool ret = false; - local_address((struct sock_common *)sk, &saddr); + mptcp_local_address((struct sock_common *)sk, &saddr); spin_lock_bh(&msk->pm.lock); list_for_each_entry(entry, &msk->pm.anno_list, list) { @@ -541,7 +540,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) struct mptcp_addr_info mpc_addr; bool backup = false; - local_address((struct sock_common *)msk->first, &mpc_addr); + mptcp_local_address((struct sock_common *)msk->first, &mpc_addr); rcu_read_lock(); entry = __lookup_addr(pernet, &mpc_addr, false); if (entry) { @@ -752,7 +751,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, struct sock *ssk = mptcp_subflow_tcp_sock(subflow); struct mptcp_addr_info local, remote; - local_address((struct sock_common *)ssk, &local); + mptcp_local_address((struct sock_common *)ssk, &local); if (!mptcp_addresses_equal(&local, addr, addr->port)) continue; @@ -1070,8 +1069,8 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) /* The 0 ID mapping is defined by the first subflow, copied into the msk * addr */ - local_address((struct sock_common *)msk, &msk_local); - local_address((struct sock_common *)skc, &skc_local); + mptcp_local_address((struct sock_common *)msk, &msk_local); + mptcp_local_address((struct sock_common *)skc, &skc_local); if (mptcp_addresses_equal(&msk_local, &skc_local, false)) return 0; @@ -1491,7 +1490,7 @@ static int mptcp_nl_remove_id_zero_address(struct net *net, if (list_empty(&msk->conn_list) || mptcp_pm_is_userspace(msk)) goto next; - local_address((struct sock_common *)msk, &msk_local); + mptcp_local_address((struct sock_common *)msk, &msk_local); if (!mptcp_addresses_equal(&msk_local, addr, addr->port)) goto next; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 70c957bc56a8..3580c7fc39c3 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -638,6 +638,7 @@ void mptcp_set_owner_r(struct sk_buff *skb, struct sock *sk); bool mptcp_addresses_equal(const struct mptcp_addr_info *a, const struct mptcp_addr_info *b, bool use_port); +void mptcp_local_address(const struct sock_common *skc, struct mptcp_addr_info *addr); /* called with sk socket lock held */ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, -- cgit v1.2.3 From 9bbec87ecfe8a5c06710100a93e6b7e66f2cbbaf Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Thu, 8 Jun 2023 15:20:50 +0200 Subject: mptcp: unify pm get_local_id interfaces This patch unifies the three PM get_local_id() interfaces: mptcp_pm_nl_get_local_id() in mptcp/pm_netlink.c for the in-kernel PM and mptcp_userspace_pm_get_local_id() in mptcp/pm_userspace.c for the userspace PM. They'll be switched in the common PM infterface mptcp_pm_get_local_id() in mptcp/pm.c based on whether mptcp_pm_is_userspace() or not. Also put together the declarations of these three functions in protocol.h. Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Reviewed-by: Larysa Zaremba Signed-off-by: Jakub Kicinski --- net/mptcp/pm.c | 18 +++++++++++++++++- net/mptcp/pm_netlink.c | 22 +++------------------- net/mptcp/protocol.h | 2 +- 3 files changed, 21 insertions(+), 21 deletions(-) (limited to 'net/mptcp') diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 92d540e527a2..300fa9bea047 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -415,7 +415,23 @@ out_unlock: int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) { - return mptcp_pm_nl_get_local_id(msk, skc); + struct mptcp_addr_info skc_local; + struct mptcp_addr_info msk_local; + + if (WARN_ON_ONCE(!msk)) + return -1; + + /* The 0 ID mapping is defined by the first subflow, copied into the msk + * addr + */ + mptcp_local_address((struct sock_common *)msk, &msk_local); + mptcp_local_address((struct sock_common *)skc, &skc_local); + if (mptcp_addresses_equal(&msk_local, &skc_local, false)) + return 0; + + if (mptcp_pm_is_userspace(msk)) + return mptcp_userspace_pm_get_local_id(msk, &skc_local); + return mptcp_pm_nl_get_local_id(msk, &skc_local); } void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk) diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 0bf09c45febd..e51d98877485 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1055,33 +1055,17 @@ static int mptcp_pm_nl_create_listen_socket(struct sock *sk, return 0; } -int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) +int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc) { struct mptcp_pm_addr_entry *entry; - struct mptcp_addr_info skc_local; - struct mptcp_addr_info msk_local; struct pm_nl_pernet *pernet; int ret = -1; - if (WARN_ON_ONCE(!msk)) - return -1; - - /* The 0 ID mapping is defined by the first subflow, copied into the msk - * addr - */ - mptcp_local_address((struct sock_common *)msk, &msk_local); - mptcp_local_address((struct sock_common *)skc, &skc_local); - if (mptcp_addresses_equal(&msk_local, &skc_local, false)) - return 0; - - if (mptcp_pm_is_userspace(msk)) - return mptcp_userspace_pm_get_local_id(msk, &skc_local); - pernet = pm_nl_get_pernet_from_msk(msk); rcu_read_lock(); list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) { - if (mptcp_addresses_equal(&entry->addr, &skc_local, entry->addr.port)) { + if (mptcp_addresses_equal(&entry->addr, skc, entry->addr.port)) { ret = entry->addr.id; break; } @@ -1095,7 +1079,7 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) if (!entry) return -ENOMEM; - entry->addr = skc_local; + entry->addr = *skc; entry->addr.id = 0; entry->addr.port = 0; entry->ifindex = 0; diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 3580c7fc39c3..1ac799a6b959 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -917,13 +917,13 @@ bool mptcp_pm_add_addr_signal(struct mptcp_sock *msk, const struct sk_buff *skb, bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining, struct mptcp_rm_list *rm_list); int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); +int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc); void __init mptcp_pm_nl_init(void); void mptcp_pm_nl_work(struct mptcp_sock *msk); void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); -int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct sock_common *skc); unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk); unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk); -- cgit v1.2.3 From f40be0db0b7680c2e9f0b1289788542813ba0f00 Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Thu, 8 Jun 2023 15:20:51 +0200 Subject: mptcp: unify pm get_flags_and_ifindex_by_id This patch unifies the three PM get_flags_and_ifindex_by_id() interfaces: mptcp_pm_nl_get_flags_and_ifindex_by_id() in mptcp/pm_netlink.c for the in-kernel PM and mptcp_userspace_pm_get_flags_and_ifindex_by_id() in mptcp/pm_userspace.c for the userspace PM. They'll be switched in the common PM infterface mptcp_pm_get_flags_and_ifindex_by_id() in mptcp/pm.c based on whether mptcp_pm_is_userspace() or not. Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Reviewed-by: Larysa Zaremba Signed-off-by: Jakub Kicinski --- net/mptcp/pm.c | 14 ++++++++++++++ net/mptcp/pm_netlink.c | 27 ++++++++------------------- net/mptcp/pm_userspace.c | 3 --- net/mptcp/protocol.h | 2 ++ 4 files changed, 24 insertions(+), 22 deletions(-) (limited to 'net/mptcp') diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 300fa9bea047..b4a1277b4bb5 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -434,6 +434,20 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc) return mptcp_pm_nl_get_local_id(msk, &skc_local); } +int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, + u8 *flags, int *ifindex) +{ + *flags = 0; + *ifindex = 0; + + if (!id) + return 0; + + if (mptcp_pm_is_userspace(msk)) + return mptcp_userspace_pm_get_flags_and_ifindex_by_id(msk, id, flags, ifindex); + return mptcp_pm_nl_get_flags_and_ifindex_by_id(msk, id, flags, ifindex); +} + void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index e51d98877485..0fd938933373 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1356,31 +1356,20 @@ out_free: return ret; } -int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, - u8 *flags, int *ifindex) +int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, + u8 *flags, int *ifindex) { struct mptcp_pm_addr_entry *entry; struct sock *sk = (struct sock *)msk; struct net *net = sock_net(sk); - *flags = 0; - *ifindex = 0; - - if (id) { - if (mptcp_pm_is_userspace(msk)) - return mptcp_userspace_pm_get_flags_and_ifindex_by_id(msk, - id, - flags, - ifindex); - - rcu_read_lock(); - entry = __lookup_addr_by_id(pm_nl_get_pernet(net), id); - if (entry) { - *flags = entry->flags; - *ifindex = entry->ifindex; - } - rcu_read_unlock(); + rcu_read_lock(); + entry = __lookup_addr_by_id(pm_nl_get_pernet(net), id); + if (entry) { + *flags = entry->flags; + *ifindex = entry->ifindex; } + rcu_read_unlock(); return 0; } diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index b06aa58dfcf2..47a883a16c11 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -111,9 +111,6 @@ int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, { struct mptcp_pm_addr_entry *entry, *match = NULL; - *flags = 0; - *ifindex = 0; - spin_lock_bh(&msk->pm.lock); list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) { if (id == entry->addr.id) { diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 1ac799a6b959..0a0a36fd0310 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -822,6 +822,8 @@ mptcp_lookup_anno_list_by_saddr(const struct mptcp_sock *msk, int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, u8 *flags, int *ifindex); +int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, + u8 *flags, int *ifindex); int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, u8 *flags, int *ifindex); -- cgit v1.2.3 From 6ba7ce89905c5d5cdb4ff9ff7c763a6a1d31f48d Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Thu, 8 Jun 2023 15:20:52 +0200 Subject: mptcp: unify pm set_flags interfaces This patch unifies the three PM set_flags() interfaces: mptcp_pm_nl_set_flags() in mptcp/pm_netlink.c for the in-kernel PM and mptcp_userspace_pm_set_flags() in mptcp/pm_userspace.c for the userspace PM. They'll be switched in the common PM infterface mptcp_pm_set_flags() in mptcp/pm.c based on whether token is NULL or not. Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Reviewed-by: Larysa Zaremba Signed-off-by: Jakub Kicinski --- net/mptcp/pm.c | 9 +++++++ net/mptcp/pm_netlink.c | 70 +++++++++++++++++++++++++++----------------------- net/mptcp/protocol.h | 4 +++ 3 files changed, 51 insertions(+), 32 deletions(-) (limited to 'net/mptcp') diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index b4a1277b4bb5..7dbbad1e4f55 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -448,6 +448,15 @@ int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id return mptcp_pm_nl_get_flags_and_ifindex_by_id(msk, id, flags, ifindex); } +int mptcp_pm_set_flags(struct net *net, struct nlattr *token, + struct mptcp_pm_addr_entry *loc, + struct mptcp_pm_addr_entry *rem, u8 bkup) +{ + if (token) + return mptcp_userspace_pm_set_flags(net, token, loc, rem, bkup); + return mptcp_pm_nl_set_flags(net, loc, bkup); +} + void mptcp_pm_subflow_chk_stale(const struct mptcp_sock *msk, struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index 0fd938933373..a12a87b780f6 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -1882,18 +1882,50 @@ next: return ret; } +int mptcp_pm_nl_set_flags(struct net *net, struct mptcp_pm_addr_entry *addr, u8 bkup) +{ + struct pm_nl_pernet *pernet = pm_nl_get_pernet(net); + u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP | + MPTCP_PM_ADDR_FLAG_FULLMESH; + struct mptcp_pm_addr_entry *entry; + u8 lookup_by_id = 0; + + if (addr->addr.family == AF_UNSPEC) { + lookup_by_id = 1; + if (!addr->addr.id) + return -EOPNOTSUPP; + } + + spin_lock_bh(&pernet->lock); + entry = __lookup_addr(pernet, &addr->addr, lookup_by_id); + if (!entry) { + spin_unlock_bh(&pernet->lock); + return -EINVAL; + } + if ((addr->flags & MPTCP_PM_ADDR_FLAG_FULLMESH) && + (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { + spin_unlock_bh(&pernet->lock); + return -EINVAL; + } + + changed = (addr->flags ^ entry->flags) & mask; + entry->flags = (entry->flags & ~mask) | (addr->flags & mask); + *addr = *entry; + spin_unlock_bh(&pernet->lock); + + mptcp_nl_set_flags(net, &addr->addr, bkup, changed); + return 0; +} + static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) { - struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }, *entry; struct mptcp_pm_addr_entry remote = { .addr = { .family = AF_UNSPEC }, }; + struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }; struct nlattr *attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; - struct pm_nl_pernet *pernet = genl_info_pm_nl(info); - u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP | - MPTCP_PM_ADDR_FLAG_FULLMESH; struct net *net = sock_net(skb->sk); - u8 bkup = 0, lookup_by_id = 0; + u8 bkup = 0; int ret; ret = mptcp_pm_parse_entry(attr, info, false, &addr); @@ -1908,34 +1940,8 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) if (addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP) bkup = 1; - if (addr.addr.family == AF_UNSPEC) { - lookup_by_id = 1; - if (!addr.addr.id) - return -EOPNOTSUPP; - } - - if (token) - return mptcp_userspace_pm_set_flags(net, token, &addr, &remote, bkup); - - spin_lock_bh(&pernet->lock); - entry = __lookup_addr(pernet, &addr.addr, lookup_by_id); - if (!entry) { - spin_unlock_bh(&pernet->lock); - return -EINVAL; - } - if ((addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) && - (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) { - spin_unlock_bh(&pernet->lock); - return -EINVAL; - } - changed = (addr.flags ^ entry->flags) & mask; - entry->flags = (entry->flags & ~mask) | (addr.flags & mask); - addr = *entry; - spin_unlock_bh(&pernet->lock); - - mptcp_nl_set_flags(net, &addr.addr, bkup, changed); - return 0; + return mptcp_pm_set_flags(net, token, &addr, &remote, bkup); } static void mptcp_nl_mcast_send(struct net *net, struct sk_buff *nlskb, gfp_t gfp) diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 0a0a36fd0310..47b46602870e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -827,6 +827,10 @@ int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, u8 *flags, int *ifindex); +int mptcp_pm_set_flags(struct net *net, struct nlattr *token, + struct mptcp_pm_addr_entry *loc, + struct mptcp_pm_addr_entry *rem, u8 bkup); +int mptcp_pm_nl_set_flags(struct net *net, struct mptcp_pm_addr_entry *addr, u8 bkup); int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token, struct mptcp_pm_addr_entry *loc, struct mptcp_pm_addr_entry *rem, u8 bkup); -- cgit v1.2.3 From 5e2ff6704a275be009be8979af17c52361b79b89 Mon Sep 17 00:00:00 2001 From: Alexander Mikhalitsyn Date: Thu, 8 Jun 2023 22:26:25 +0200 Subject: scm: add SO_PASSPIDFD and SCM_PIDFD Implement SCM_PIDFD, a new type of CMSG type analogical to SCM_CREDENTIALS, but it contains pidfd instead of plain pid, which allows programmers not to care about PID reuse problem. We mask SO_PASSPIDFD feature if CONFIG_UNIX is not builtin because it depends on a pidfd_prepare() API which is not exported to the kernel modules. Idea comes from UAPI kernel group: https://uapi-group.org/kernel-features/ Big thanks to Christian Brauner and Lennart Poettering for productive discussions about this. Cc: "David S. Miller" Cc: Eric Dumazet Cc: Jakub Kicinski Cc: Paolo Abeni Cc: Leon Romanovsky Cc: David Ahern Cc: Arnd Bergmann Cc: Kees Cook Cc: Christian Brauner Cc: Kuniyuki Iwashima Cc: Lennart Poettering Cc: Luca Boccassi Cc: linux-kernel@vger.kernel.org Cc: netdev@vger.kernel.org Cc: linux-arch@vger.kernel.org Tested-by: Luca Boccassi Reviewed-by: Kuniyuki Iwashima Reviewed-by: Christian Brauner Signed-off-by: Alexander Mikhalitsyn Reviewed-by: Eric Dumazet Signed-off-by: David S. Miller --- arch/alpha/include/uapi/asm/socket.h | 2 ++ arch/mips/include/uapi/asm/socket.h | 2 ++ arch/parisc/include/uapi/asm/socket.h | 2 ++ arch/sparc/include/uapi/asm/socket.h | 2 ++ include/linux/net.h | 1 + include/linux/socket.h | 1 + include/net/scm.h | 39 +++++++++++++++++++++++++++++++-- include/uapi/asm-generic/socket.h | 2 ++ net/core/sock.c | 11 ++++++++++ net/mptcp/sockopt.c | 1 + net/unix/af_unix.c | 18 ++++++++++----- tools/include/uapi/asm-generic/socket.h | 2 ++ 12 files changed, 76 insertions(+), 7 deletions(-) (limited to 'net/mptcp') diff --git a/arch/alpha/include/uapi/asm/socket.h b/arch/alpha/include/uapi/asm/socket.h index 739891b94136..ff310613ae64 100644 --- a/arch/alpha/include/uapi/asm/socket.h +++ b/arch/alpha/include/uapi/asm/socket.h @@ -137,6 +137,8 @@ #define SO_RCVMARK 75 +#define SO_PASSPIDFD 76 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/mips/include/uapi/asm/socket.h b/arch/mips/include/uapi/asm/socket.h index 18f3d95ecfec..762dcb80e4ec 100644 --- a/arch/mips/include/uapi/asm/socket.h +++ b/arch/mips/include/uapi/asm/socket.h @@ -148,6 +148,8 @@ #define SO_RCVMARK 75 +#define SO_PASSPIDFD 76 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/parisc/include/uapi/asm/socket.h b/arch/parisc/include/uapi/asm/socket.h index f486d3dfb6bb..df16a3e16d64 100644 --- a/arch/parisc/include/uapi/asm/socket.h +++ b/arch/parisc/include/uapi/asm/socket.h @@ -129,6 +129,8 @@ #define SO_RCVMARK 0x4049 +#define SO_PASSPIDFD 0x404A + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 diff --git a/arch/sparc/include/uapi/asm/socket.h b/arch/sparc/include/uapi/asm/socket.h index 2fda57a3ea86..6e2847804fea 100644 --- a/arch/sparc/include/uapi/asm/socket.h +++ b/arch/sparc/include/uapi/asm/socket.h @@ -130,6 +130,8 @@ #define SO_RCVMARK 0x0054 +#define SO_PASSPIDFD 0x0055 + #if !defined(__KERNEL__) diff --git a/include/linux/net.h b/include/linux/net.h index 8defc8f1d82e..23324e9a2b3d 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -43,6 +43,7 @@ struct net; #define SOCK_PASSSEC 4 #define SOCK_SUPPORT_ZC 5 #define SOCK_CUSTOM_SOCKOPT 6 +#define SOCK_PASSPIDFD 7 #ifndef ARCH_HAS_SOCKET_TYPES /** diff --git a/include/linux/socket.h b/include/linux/socket.h index 3fd3436bc09f..58204700018a 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -177,6 +177,7 @@ static inline size_t msg_data_left(struct msghdr *msg) #define SCM_RIGHTS 0x01 /* rw: access rights (array of int) */ #define SCM_CREDENTIALS 0x02 /* rw: struct ucred */ #define SCM_SECURITY 0x03 /* rw: security label */ +#define SCM_PIDFD 0x04 /* ro: pidfd (int) */ struct ucred { __u32 pid; diff --git a/include/net/scm.h b/include/net/scm.h index 585adc1346bd..c67f765a165b 100644 --- a/include/net/scm.h +++ b/include/net/scm.h @@ -120,12 +120,44 @@ static inline bool scm_has_secdata(struct socket *sock) } #endif /* CONFIG_SECURITY_NETWORK */ +static __inline__ void scm_pidfd_recv(struct msghdr *msg, struct scm_cookie *scm) +{ + struct file *pidfd_file = NULL; + int pidfd; + + /* + * put_cmsg() doesn't return an error if CMSG is truncated, + * that's why we need to opencode these checks here. + */ + if ((msg->msg_controllen <= sizeof(struct cmsghdr)) || + (msg->msg_controllen - sizeof(struct cmsghdr)) < sizeof(int)) { + msg->msg_flags |= MSG_CTRUNC; + return; + } + + WARN_ON_ONCE(!scm->pid); + pidfd = pidfd_prepare(scm->pid, 0, &pidfd_file); + + if (put_cmsg(msg, SOL_SOCKET, SCM_PIDFD, sizeof(int), &pidfd)) { + if (pidfd_file) { + put_unused_fd(pidfd); + fput(pidfd_file); + } + + return; + } + + if (pidfd_file) + fd_install(pidfd, pidfd_file); +} + static __inline__ void scm_recv(struct socket *sock, struct msghdr *msg, struct scm_cookie *scm, int flags) { if (!msg->msg_control) { - if (test_bit(SOCK_PASSCRED, &sock->flags) || scm->fp || - scm_has_secdata(sock)) + if (test_bit(SOCK_PASSCRED, &sock->flags) || + test_bit(SOCK_PASSPIDFD, &sock->flags) || + scm->fp || scm_has_secdata(sock)) msg->msg_flags |= MSG_CTRUNC; scm_destroy(scm); return; @@ -141,6 +173,9 @@ static __inline__ void scm_recv(struct socket *sock, struct msghdr *msg, put_cmsg(msg, SOL_SOCKET, SCM_CREDENTIALS, sizeof(ucreds), &ucreds); } + if (test_bit(SOCK_PASSPIDFD, &sock->flags)) + scm_pidfd_recv(msg, scm); + scm_destroy_cred(scm); scm_passec(sock, msg, scm); diff --git a/include/uapi/asm-generic/socket.h b/include/uapi/asm-generic/socket.h index 638230899e98..b76169fdb80b 100644 --- a/include/uapi/asm-generic/socket.h +++ b/include/uapi/asm-generic/socket.h @@ -132,6 +132,8 @@ #define SO_RCVMARK 75 +#define SO_PASSPIDFD 76 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) diff --git a/net/core/sock.c b/net/core/sock.c index 24f2761bdb1d..ed4eb4ba738b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1246,6 +1246,13 @@ set_sndbuf: clear_bit(SOCK_PASSCRED, &sock->flags); break; + case SO_PASSPIDFD: + if (valbool) + set_bit(SOCK_PASSPIDFD, &sock->flags); + else + clear_bit(SOCK_PASSPIDFD, &sock->flags); + break; + case SO_TIMESTAMP_OLD: case SO_TIMESTAMP_NEW: case SO_TIMESTAMPNS_OLD: @@ -1732,6 +1739,10 @@ int sk_getsockopt(struct sock *sk, int level, int optname, v.val = !!test_bit(SOCK_PASSCRED, &sock->flags); break; + case SO_PASSPIDFD: + v.val = !!test_bit(SOCK_PASSPIDFD, &sock->flags); + break; + case SO_PEERCRED: { struct ucred peercred; diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index d4258869ac48..e172a5848b0d 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -355,6 +355,7 @@ static int mptcp_setsockopt_sol_socket(struct mptcp_sock *msk, int optname, case SO_BROADCAST: case SO_BSDCOMPAT: case SO_PASSCRED: + case SO_PASSPIDFD: case SO_PASSSEC: case SO_RXQ_OVFL: case SO_WIFI_STATUS: diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 653136d68b32..c46c2f5d860c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1361,7 +1361,8 @@ static int unix_dgram_connect(struct socket *sock, struct sockaddr *addr, if (err) goto out; - if (test_bit(SOCK_PASSCRED, &sock->flags) && + if ((test_bit(SOCK_PASSCRED, &sock->flags) || + test_bit(SOCK_PASSPIDFD, &sock->flags)) && !unix_sk(sk)->addr) { err = unix_autobind(sk); if (err) @@ -1469,7 +1470,8 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr, if (err) goto out; - if (test_bit(SOCK_PASSCRED, &sock->flags) && !u->addr) { + if ((test_bit(SOCK_PASSCRED, &sock->flags) || + test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) { err = unix_autobind(sk); if (err) goto out; @@ -1670,6 +1672,8 @@ static void unix_sock_inherit_flags(const struct socket *old, { if (test_bit(SOCK_PASSCRED, &old->flags)) set_bit(SOCK_PASSCRED, &new->flags); + if (test_bit(SOCK_PASSPIDFD, &old->flags)) + set_bit(SOCK_PASSPIDFD, &new->flags); if (test_bit(SOCK_PASSSEC, &old->flags)) set_bit(SOCK_PASSSEC, &new->flags); } @@ -1819,8 +1823,10 @@ static bool unix_passcred_enabled(const struct socket *sock, const struct sock *other) { return test_bit(SOCK_PASSCRED, &sock->flags) || + test_bit(SOCK_PASSPIDFD, &sock->flags) || !other->sk_socket || - test_bit(SOCK_PASSCRED, &other->sk_socket->flags); + test_bit(SOCK_PASSCRED, &other->sk_socket->flags) || + test_bit(SOCK_PASSPIDFD, &other->sk_socket->flags); } /* @@ -1904,7 +1910,8 @@ static int unix_dgram_sendmsg(struct socket *sock, struct msghdr *msg, goto out; } - if (test_bit(SOCK_PASSCRED, &sock->flags) && !u->addr) { + if ((test_bit(SOCK_PASSCRED, &sock->flags) || + test_bit(SOCK_PASSPIDFD, &sock->flags)) && !u->addr) { err = unix_autobind(sk); if (err) goto out; @@ -2718,7 +2725,8 @@ unlock: /* Never glue messages from different writers */ if (!unix_skb_scm_eq(skb, &scm)) break; - } else if (test_bit(SOCK_PASSCRED, &sock->flags)) { + } else if (test_bit(SOCK_PASSCRED, &sock->flags) || + test_bit(SOCK_PASSPIDFD, &sock->flags)) { /* Copy credentials */ scm_set_cred(&scm, UNIXCB(skb).pid, UNIXCB(skb).uid, UNIXCB(skb).gid); unix_set_secdata(&scm, skb); diff --git a/tools/include/uapi/asm-generic/socket.h b/tools/include/uapi/asm-generic/socket.h index 8756df13be50..fbbc4bf53ee3 100644 --- a/tools/include/uapi/asm-generic/socket.h +++ b/tools/include/uapi/asm-generic/socket.h @@ -121,6 +121,8 @@ #define SO_RCVMARK 75 +#define SO_PASSPIDFD 76 + #if !defined(__KERNEL__) #if __BITS_PER_LONG == 64 || (defined(__x86_64__) && defined(__ILP32__)) -- cgit v1.2.3 From e1d001fa5b477c4da46a29be1fcece91db7c7c6f Mon Sep 17 00:00:00 2001 From: Breno Leitao Date: Fri, 9 Jun 2023 08:27:42 -0700 Subject: net: ioctl: Use kernel memory on protocol ioctl callbacks Most of the ioctls to net protocols operates directly on userspace argument (arg). Usually doing get_user()/put_user() directly in the ioctl callback. This is not flexible, because it is hard to reuse these functions without passing userspace buffers. Change the "struct proto" ioctls to avoid touching userspace memory and operate on kernel buffers, i.e., all protocol's ioctl callbacks is adapted to operate on a kernel memory other than on userspace (so, no more {put,get}_user() and friends being called in the ioctl callback). This changes the "struct proto" ioctl format in the following way: int (*ioctl)(struct sock *sk, int cmd, - unsigned long arg); + int *karg); (Important to say that this patch does not touch the "struct proto_ops" protocols) So, the "karg" argument, which is passed to the ioctl callback, is a pointer allocated to kernel space memory (inside a function wrapper). This buffer (karg) may contain input argument (copied from userspace in a prep function) and it might return a value/buffer, which is copied back to userspace if necessary. There is not one-size-fits-all format (that is I am using 'may' above), but basically, there are three type of ioctls: 1) Do not read from userspace, returns a result to userspace 2) Read an input parameter from userspace, and does not return anything to userspace 3) Read an input from userspace, and return a buffer to userspace. The default case (1) (where no input parameter is given, and an "int" is returned to userspace) encompasses more than 90% of the cases, but there are two other exceptions. Here is a list of exceptions: * Protocol RAW: * cmd = SIOCGETVIFCNT: * input and output = struct sioc_vif_req * cmd = SIOCGETSGCNT * input and output = struct sioc_sg_req * Explanation: for the SIOCGETVIFCNT case, userspace passes the input argument, which is struct sioc_vif_req. Then the callback populates the struct, which is copied back to userspace. * Protocol RAW6: * cmd = SIOCGETMIFCNT_IN6 * input and output = struct sioc_mif_req6 * cmd = SIOCGETSGCNT_IN6 * input and output = struct sioc_sg_req6 * Protocol PHONET: * cmd == SIOCPNADDRESOURCE | SIOCPNDELRESOURCE * input int (4 bytes) * Nothing is copied back to userspace. For the exception cases, functions sock_sk_ioctl_inout() will copy the userspace input, and copy it back to kernel space. The wrapper that prepare the buffer and put the buffer back to user is sk_ioctl(), so, instead of calling sk->sk_prot->ioctl(), the callee now calls sk_ioctl(), which will handle all cases. Signed-off-by: Breno Leitao Reviewed-by: Willem de Bruijn Reviewed-by: David Ahern Reviewed-by: Kuniyuki Iwashima Link: https://lore.kernel.org/r/20230609152800.830401-1-leitao@debian.org Signed-off-by: Jakub Kicinski --- include/linux/icmpv6.h | 6 +++++ include/linux/mroute.h | 22 ++++++++++++++-- include/linux/mroute6.h | 31 ++++++++++++++++++++-- include/net/phonet/phonet.h | 21 +++++++++++++++ include/net/sock.h | 5 +++- include/net/tcp.h | 2 +- include/net/udp.h | 2 +- net/core/sock.c | 64 +++++++++++++++++++++++++++++++++++++++++++++ net/dccp/dccp.h | 2 +- net/dccp/proto.c | 12 ++++----- net/ieee802154/socket.c | 15 +++++------ net/ipv4/af_inet.c | 2 +- net/ipv4/ipmr.c | 63 +++++++++++++++++++++++++++----------------- net/ipv4/raw.c | 16 ++++++------ net/ipv4/tcp.c | 5 ++-- net/ipv4/udp.c | 12 ++++----- net/ipv6/af_inet6.c | 2 +- net/ipv6/ip6mr.c | 44 +++++++++++++------------------ net/ipv6/raw.c | 16 ++++++------ net/l2tp/l2tp_core.h | 2 +- net/l2tp/l2tp_ip.c | 9 +++---- net/mptcp/protocol.c | 11 ++++---- net/phonet/datagram.c | 11 +++----- net/phonet/pep.c | 11 ++++---- net/phonet/socket.c | 2 +- net/sctp/socket.c | 8 +++--- 26 files changed, 267 insertions(+), 129 deletions(-) (limited to 'net/mptcp') diff --git a/include/linux/icmpv6.h b/include/linux/icmpv6.h index db0f4fcfdaf4..1fe33e6741cc 100644 --- a/include/linux/icmpv6.h +++ b/include/linux/icmpv6.h @@ -111,4 +111,10 @@ static inline bool icmpv6_is_err(int type) return false; } +static inline int sk_is_icmpv6(struct sock *sk) +{ + return sk->sk_family == AF_INET6 && + inet_sk(sk)->inet_num == IPPROTO_ICMPV6; +} + #endif diff --git a/include/linux/mroute.h b/include/linux/mroute.h index 80b8400ab8b2..94c6e6f549f0 100644 --- a/include/linux/mroute.h +++ b/include/linux/mroute.h @@ -16,12 +16,19 @@ static inline int ip_mroute_opt(int opt) return opt >= MRT_BASE && opt <= MRT_MAX; } +static inline int sk_is_ipmr(struct sock *sk) +{ + return sk->sk_family == AF_INET && + inet_sk(sk)->inet_num == IPPROTO_IGMP; +} + int ip_mroute_setsockopt(struct sock *, int, sockptr_t, unsigned int); int ip_mroute_getsockopt(struct sock *, int, sockptr_t, sockptr_t); -int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg); +int ipmr_ioctl(struct sock *sk, int cmd, void *arg); int ipmr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); int ip_mr_init(void); bool ipmr_rule_default(const struct fib_rule *rule); +int ipmr_sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); #else static inline int ip_mroute_setsockopt(struct sock *sock, int optname, sockptr_t optval, unsigned int optlen) @@ -35,7 +42,7 @@ static inline int ip_mroute_getsockopt(struct sock *sk, int optname, return -ENOPROTOOPT; } -static inline int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) +static inline int ipmr_ioctl(struct sock *sk, int cmd, void *arg) { return -ENOIOCTLCMD; } @@ -50,10 +57,21 @@ static inline int ip_mroute_opt(int opt) return 0; } +static inline int sk_is_ipmr(struct sock *sk) +{ + return 0; +} + static inline bool ipmr_rule_default(const struct fib_rule *rule) { return true; } + +static inline int ipmr_sk_ioctl(struct sock *sk, unsigned int cmd, + void __user *arg) +{ + return 1; +} #endif #define VIFF_STATIC 0x8000 diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h index 8f2b307fb124..2f95d5b4e47a 100644 --- a/include/linux/mroute6.h +++ b/include/linux/mroute6.h @@ -29,10 +29,10 @@ struct sock; extern int ip6_mroute_setsockopt(struct sock *, int, sockptr_t, unsigned int); extern int ip6_mroute_getsockopt(struct sock *, int, sockptr_t, sockptr_t); extern int ip6_mr_input(struct sk_buff *skb); -extern int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg); extern int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); extern int ip6_mr_init(void); extern void ip6_mr_cleanup(void); +int ip6mr_ioctl(struct sock *sk, int cmd, void *arg); #else static inline int ip6_mroute_setsockopt(struct sock *sock, int optname, sockptr_t optval, unsigned int optlen) @@ -48,7 +48,7 @@ int ip6_mroute_getsockopt(struct sock *sock, } static inline -int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) +int ip6mr_ioctl(struct sock *sk, int cmd, void *arg) { return -ENOIOCTLCMD; } @@ -100,6 +100,27 @@ extern int ip6mr_get_route(struct net *net, struct sk_buff *skb, #ifdef CONFIG_IPV6_MROUTE bool mroute6_is_socket(struct net *net, struct sk_buff *skb); extern int ip6mr_sk_done(struct sock *sk); +static inline int ip6mr_sk_ioctl(struct sock *sk, unsigned int cmd, + void __user *arg) +{ + switch (cmd) { + /* These userspace buffers will be consumed by ip6mr_ioctl() */ + case SIOCGETMIFCNT_IN6: { + struct sioc_mif_req6 buffer; + + return sock_ioctl_inout(sk, cmd, arg, &buffer, + sizeof(buffer)); + } + case SIOCGETSGCNT_IN6: { + struct sioc_mif_req6 buffer; + + return sock_ioctl_inout(sk, cmd, arg, &buffer, + sizeof(buffer)); + } + } + + return 1; +} #else static inline bool mroute6_is_socket(struct net *net, struct sk_buff *skb) { @@ -109,5 +130,11 @@ static inline int ip6mr_sk_done(struct sock *sk) { return 0; } + +static inline int ip6mr_sk_ioctl(struct sock *sk, unsigned int cmd, + void __user *arg) +{ + return 1; +} #endif #endif diff --git a/include/net/phonet/phonet.h b/include/net/phonet/phonet.h index 862f1719b523..cf5ecae4a2fc 100644 --- a/include/net/phonet/phonet.h +++ b/include/net/phonet/phonet.h @@ -109,4 +109,25 @@ void phonet_sysctl_exit(void); int isi_register(void); void isi_unregister(void); +static inline bool sk_is_phonet(struct sock *sk) +{ + return sk->sk_family == PF_PHONET; +} + +static inline int phonet_sk_ioctl(struct sock *sk, unsigned int cmd, + void __user *arg) +{ + int karg; + + switch (cmd) { + case SIOCPNADDRESOURCE: + case SIOCPNDELRESOURCE: + if (get_user(karg, (int __user *)arg)) + return -EFAULT; + + return sk->sk_prot->ioctl(sk, cmd, &karg); + } + /* A positive return value means that the ioctl was not processed */ + return 1; +} #endif diff --git a/include/net/sock.h b/include/net/sock.h index 2790133b4b76..62a1b99da349 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1258,7 +1258,7 @@ struct proto { bool kern); int (*ioctl)(struct sock *sk, int cmd, - unsigned long arg); + int *karg); int (*init)(struct sock *sk); void (*destroy)(struct sock *sk); void (*shutdown)(struct sock *sk, int how); @@ -2974,6 +2974,9 @@ int sock_get_timeout(long timeo, void *optval, bool old_timeval); int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, sockptr_t optval, int optlen, bool old_timeval); +int sock_ioctl_inout(struct sock *sk, unsigned int cmd, + void __user *arg, void *karg, size_t size); +int sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg); static inline bool sk_is_readable(struct sock *sk) { if (sk->sk_prot->sock_is_readable) diff --git a/include/net/tcp.h b/include/net/tcp.h index bf9f56225821..9c08eab647a2 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -340,7 +340,7 @@ void tcp_release_cb(struct sock *sk); void tcp_wfree(struct sk_buff *skb); void tcp_write_timer_handler(struct sock *sk); void tcp_delack_timer_handler(struct sock *sk); -int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg); +int tcp_ioctl(struct sock *sk, int cmd, int *karg); int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb); void tcp_rcv_established(struct sock *sk, struct sk_buff *skb); void tcp_rcv_space_adjust(struct sock *sk); diff --git a/include/net/udp.h b/include/net/udp.h index e01340a27155..4d13424f8f72 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -285,7 +285,7 @@ void udp_flush_pending_frames(struct sock *sk); int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size); void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst); int udp_rcv(struct sk_buff *skb); -int udp_ioctl(struct sock *sk, int cmd, unsigned long arg); +int udp_ioctl(struct sock *sk, int cmd, int *karg); int udp_init_sock(struct sock *sk); int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len); int __udp_disconnect(struct sock *sk, int flags); diff --git a/net/core/sock.c b/net/core/sock.c index ea66b1afadd0..cff3e82514d1 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -114,6 +114,9 @@ #include #include #include +#include +#include +#include #include @@ -138,6 +141,7 @@ #include #include +#include #include @@ -4150,3 +4154,63 @@ int sock_bind_add(struct sock *sk, struct sockaddr *addr, int addr_len) return sk->sk_prot->bind_add(sk, addr, addr_len); } EXPORT_SYMBOL(sock_bind_add); + +/* Copy 'size' bytes from userspace and return `size` back to userspace */ +int sock_ioctl_inout(struct sock *sk, unsigned int cmd, + void __user *arg, void *karg, size_t size) +{ + int ret; + + if (copy_from_user(karg, arg, size)) + return -EFAULT; + + ret = READ_ONCE(sk->sk_prot)->ioctl(sk, cmd, karg); + if (ret) + return ret; + + if (copy_to_user(arg, karg, size)) + return -EFAULT; + + return 0; +} +EXPORT_SYMBOL(sock_ioctl_inout); + +/* This is the most common ioctl prep function, where the result (4 bytes) is + * copied back to userspace if the ioctl() returns successfully. No input is + * copied from userspace as input argument. + */ +static int sock_ioctl_out(struct sock *sk, unsigned int cmd, void __user *arg) +{ + int ret, karg = 0; + + ret = READ_ONCE(sk->sk_prot)->ioctl(sk, cmd, &karg); + if (ret) + return ret; + + return put_user(karg, (int __user *)arg); +} + +/* A wrapper around sock ioctls, which copies the data from userspace + * (depending on the protocol/ioctl), and copies back the result to userspace. + * The main motivation for this function is to pass kernel memory to the + * protocol ioctl callbacks, instead of userspace memory. + */ +int sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) +{ + int rc = 1; + + if (sk_is_ipmr(sk)) + rc = ipmr_sk_ioctl(sk, cmd, arg); + else if (sk_is_icmpv6(sk)) + rc = ip6mr_sk_ioctl(sk, cmd, arg); + else if (sk_is_phonet(sk)) + rc = phonet_sk_ioctl(sk, cmd, arg); + + /* If ioctl was processed, returns its value */ + if (rc <= 0) + return rc; + + /* Otherwise call the default handler */ + return sock_ioctl_out(sk, cmd, arg); +} +EXPORT_SYMBOL(sk_ioctl); diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 9ddc3a9e89e4..1f748ed1279d 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -292,7 +292,7 @@ int dccp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); int dccp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, unsigned int optlen); -int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg); +int dccp_ioctl(struct sock *sk, int cmd, int *karg); int dccp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int dccp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len); diff --git a/net/dccp/proto.c b/net/dccp/proto.c index b0ebf853cb07..f331e5977a84 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -362,7 +362,7 @@ __poll_t dccp_poll(struct file *file, struct socket *sock, EXPORT_SYMBOL_GPL(dccp_poll); -int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg) +int dccp_ioctl(struct sock *sk, int cmd, int *karg) { int rc = -ENOTCONN; @@ -373,17 +373,17 @@ int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg) switch (cmd) { case SIOCOUTQ: { - int amount = sk_wmem_alloc_get(sk); + *karg = sk_wmem_alloc_get(sk); /* Using sk_wmem_alloc here because sk_wmem_queued is not used by DCCP and * always 0, comparably to UDP. */ - rc = put_user(amount, (int __user *)arg); + rc = 0; } break; case SIOCINQ: { struct sk_buff *skb; - unsigned long amount = 0; + *karg = 0; skb = skb_peek(&sk->sk_receive_queue); if (skb != NULL) { @@ -391,9 +391,9 @@ int dccp_ioctl(struct sock *sk, int cmd, unsigned long arg) * We will only return the amount of this packet since * that is all that will be read. */ - amount = skb->len; + *karg = skb->len; } - rc = put_user(amount, (int __user *)arg); + rc = 0; } break; default: diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index 1fa2fe041ec0..9c124705120d 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -162,7 +162,7 @@ static int ieee802154_sock_ioctl(struct socket *sock, unsigned int cmd, default: if (!sk->sk_prot->ioctl) return -ENOIOCTLCMD; - return sk->sk_prot->ioctl(sk, cmd, arg); + return sk_ioctl(sk, cmd, (void __user *)arg); } } @@ -531,22 +531,21 @@ out: return err; } -static int dgram_ioctl(struct sock *sk, int cmd, unsigned long arg) +static int dgram_ioctl(struct sock *sk, int cmd, int *karg) { switch (cmd) { case SIOCOUTQ: { - int amount = sk_wmem_alloc_get(sk); + *karg = sk_wmem_alloc_get(sk); - return put_user(amount, (int __user *)arg); + return 0; } case SIOCINQ: { struct sk_buff *skb; - unsigned long amount; - amount = 0; + *karg = 0; spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb) { @@ -554,10 +553,10 @@ static int dgram_ioctl(struct sock *sk, int cmd, unsigned long arg) * of this packet since that is all * that will be read. */ - amount = skb->len - ieee802154_hdr_length(skb); + *karg = skb->len - ieee802154_hdr_length(skb); } spin_unlock_bh(&sk->sk_receive_queue.lock); - return put_user(amount, (int __user *)arg); + return 0; } } diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 0e16ac8282c5..38e649fb4474 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -998,7 +998,7 @@ int inet_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) break; default: if (sk->sk_prot->ioctl) - err = sk->sk_prot->ioctl(sk, cmd, arg); + err = sk_ioctl(sk, cmd, (void __user *)arg); else err = -ENOIOCTLCMD; break; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index eec1f6df80d8..3f0c6d602fb7 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1547,6 +1547,28 @@ out: return ret; } +/* Execute if this ioctl is a special mroute ioctl */ +int ipmr_sk_ioctl(struct sock *sk, unsigned int cmd, void __user *arg) +{ + switch (cmd) { + /* These userspace buffers will be consumed by ipmr_ioctl() */ + case SIOCGETVIFCNT: { + struct sioc_vif_req buffer; + + return sock_ioctl_inout(sk, cmd, arg, &buffer, + sizeof(buffer)); + } + case SIOCGETSGCNT: { + struct sioc_sg_req buffer; + + return sock_ioctl_inout(sk, cmd, arg, &buffer, + sizeof(buffer)); + } + } + /* return code > 0 means that the ioctl was not executed */ + return 1; +} + /* Getsock opt support for the multicast routing system. */ int ip_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval, sockptr_t optlen) @@ -1593,13 +1615,13 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval, } /* The IP multicast ioctl support routines. */ -int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) +int ipmr_ioctl(struct sock *sk, int cmd, void *arg) { - struct sioc_sg_req sr; - struct sioc_vif_req vr; struct vif_device *vif; struct mfc_cache *c; struct net *net = sock_net(sk); + struct sioc_vif_req *vr; + struct sioc_sg_req *sr; struct mr_table *mrt; mrt = ipmr_get_table(net, raw_sk(sk)->ipmr_table ? : RT_TABLE_DEFAULT); @@ -1608,40 +1630,33 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) switch (cmd) { case SIOCGETVIFCNT: - if (copy_from_user(&vr, arg, sizeof(vr))) - return -EFAULT; - if (vr.vifi >= mrt->maxvif) + vr = (struct sioc_vif_req *)arg; + if (vr->vifi >= mrt->maxvif) return -EINVAL; - vr.vifi = array_index_nospec(vr.vifi, mrt->maxvif); + vr->vifi = array_index_nospec(vr->vifi, mrt->maxvif); rcu_read_lock(); - vif = &mrt->vif_table[vr.vifi]; - if (VIF_EXISTS(mrt, vr.vifi)) { - vr.icount = READ_ONCE(vif->pkt_in); - vr.ocount = READ_ONCE(vif->pkt_out); - vr.ibytes = READ_ONCE(vif->bytes_in); - vr.obytes = READ_ONCE(vif->bytes_out); + vif = &mrt->vif_table[vr->vifi]; + if (VIF_EXISTS(mrt, vr->vifi)) { + vr->icount = READ_ONCE(vif->pkt_in); + vr->ocount = READ_ONCE(vif->pkt_out); + vr->ibytes = READ_ONCE(vif->bytes_in); + vr->obytes = READ_ONCE(vif->bytes_out); rcu_read_unlock(); - if (copy_to_user(arg, &vr, sizeof(vr))) - return -EFAULT; return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; case SIOCGETSGCNT: - if (copy_from_user(&sr, arg, sizeof(sr))) - return -EFAULT; + sr = (struct sioc_sg_req *)arg; rcu_read_lock(); - c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr); + c = ipmr_cache_find(mrt, sr->src.s_addr, sr->grp.s_addr); if (c) { - sr.pktcnt = c->_c.mfc_un.res.pkt; - sr.bytecnt = c->_c.mfc_un.res.bytes; - sr.wrong_if = c->_c.mfc_un.res.wrong_if; + sr->pktcnt = c->_c.mfc_un.res.pkt; + sr->bytecnt = c->_c.mfc_un.res.bytes; + sr->wrong_if = c->_c.mfc_un.res.wrong_if; rcu_read_unlock(); - - if (copy_to_user(arg, &sr, sizeof(sr))) - return -EFAULT; return 0; } rcu_read_unlock(); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 9aacce9db7b9..7782ff5e6539 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -856,29 +856,29 @@ static int raw_getsockopt(struct sock *sk, int level, int optname, return do_raw_getsockopt(sk, level, optname, optval, optlen); } -static int raw_ioctl(struct sock *sk, int cmd, unsigned long arg) +static int raw_ioctl(struct sock *sk, int cmd, int *karg) { switch (cmd) { case SIOCOUTQ: { - int amount = sk_wmem_alloc_get(sk); - - return put_user(amount, (int __user *)arg); + *karg = sk_wmem_alloc_get(sk); + return 0; } case SIOCINQ: { struct sk_buff *skb; - int amount = 0; spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb) - amount = skb->len; + *karg = skb->len; + else + *karg = 0; spin_unlock_bh(&sk->sk_receive_queue.lock); - return put_user(amount, (int __user *)arg); + return 0; } default: #ifdef CONFIG_IP_MROUTE - return ipmr_ioctl(sk, cmd, (void __user *)arg); + return ipmr_ioctl(sk, cmd, karg); #else return -ENOIOCTLCMD; #endif diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index fba6578bc98f..0e21ea92dc1d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -599,7 +599,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) } EXPORT_SYMBOL(tcp_poll); -int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) +int tcp_ioctl(struct sock *sk, int cmd, int *karg) { struct tcp_sock *tp = tcp_sk(sk); int answ; @@ -641,7 +641,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) return -ENOIOCTLCMD; } - return put_user(answ, (int __user *)arg); + *karg = answ; + return 0; } EXPORT_SYMBOL(tcp_ioctl); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 7e0542c10471..48fdcd3cad9c 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1692,21 +1692,19 @@ static int first_packet_length(struct sock *sk) * IOCTL requests applicable to the UDP protocol */ -int udp_ioctl(struct sock *sk, int cmd, unsigned long arg) +int udp_ioctl(struct sock *sk, int cmd, int *karg) { switch (cmd) { case SIOCOUTQ: { - int amount = sk_wmem_alloc_get(sk); - - return put_user(amount, (int __user *)arg); + *karg = sk_wmem_alloc_get(sk); + return 0; } case SIOCINQ: { - int amount = max_t(int, 0, first_packet_length(sk)); - - return put_user(amount, (int __user *)arg); + *karg = max_t(int, 0, first_packet_length(sk)); + return 0; } default: diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 564942bee067..b3451cf47d29 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -579,7 +579,7 @@ int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) prot = READ_ONCE(sk->sk_prot); if (!prot->ioctl) return -ENOIOCTLCMD; - return prot->ioctl(sk, cmd, arg); + return sk_ioctl(sk, cmd, (void __user *)arg); } /*NOTREACHED*/ return 0; diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 51cf37abd142..cc3d5ad17257 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -1879,11 +1879,10 @@ int ip6_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval, /* * The IP multicast ioctl support routines. */ - -int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) +int ip6mr_ioctl(struct sock *sk, int cmd, void *arg) { - struct sioc_sg_req6 sr; - struct sioc_mif_req6 vr; + struct sioc_sg_req6 *sr; + struct sioc_mif_req6 *vr; struct vif_device *vif; struct mfc6_cache *c; struct net *net = sock_net(sk); @@ -1895,40 +1894,33 @@ int ip6mr_ioctl(struct sock *sk, int cmd, void __user *arg) switch (cmd) { case SIOCGETMIFCNT_IN6: - if (copy_from_user(&vr, arg, sizeof(vr))) - return -EFAULT; - if (vr.mifi >= mrt->maxvif) + vr = (struct sioc_mif_req6 *)arg; + if (vr->mifi >= mrt->maxvif) return -EINVAL; - vr.mifi = array_index_nospec(vr.mifi, mrt->maxvif); + vr->mifi = array_index_nospec(vr->mifi, mrt->maxvif); rcu_read_lock(); - vif = &mrt->vif_table[vr.mifi]; - if (VIF_EXISTS(mrt, vr.mifi)) { - vr.icount = READ_ONCE(vif->pkt_in); - vr.ocount = READ_ONCE(vif->pkt_out); - vr.ibytes = READ_ONCE(vif->bytes_in); - vr.obytes = READ_ONCE(vif->bytes_out); + vif = &mrt->vif_table[vr->mifi]; + if (VIF_EXISTS(mrt, vr->mifi)) { + vr->icount = READ_ONCE(vif->pkt_in); + vr->ocount = READ_ONCE(vif->pkt_out); + vr->ibytes = READ_ONCE(vif->bytes_in); + vr->obytes = READ_ONCE(vif->bytes_out); rcu_read_unlock(); - - if (copy_to_user(arg, &vr, sizeof(vr))) - return -EFAULT; return 0; } rcu_read_unlock(); return -EADDRNOTAVAIL; case SIOCGETSGCNT_IN6: - if (copy_from_user(&sr, arg, sizeof(sr))) - return -EFAULT; + sr = (struct sioc_sg_req6 *)arg; rcu_read_lock(); - c = ip6mr_cache_find(mrt, &sr.src.sin6_addr, &sr.grp.sin6_addr); + c = ip6mr_cache_find(mrt, &sr->src.sin6_addr, + &sr->grp.sin6_addr); if (c) { - sr.pktcnt = c->_c.mfc_un.res.pkt; - sr.bytecnt = c->_c.mfc_un.res.bytes; - sr.wrong_if = c->_c.mfc_un.res.wrong_if; + sr->pktcnt = c->_c.mfc_un.res.pkt; + sr->bytecnt = c->_c.mfc_un.res.bytes; + sr->wrong_if = c->_c.mfc_un.res.wrong_if; rcu_read_unlock(); - - if (copy_to_user(arg, &sr, sizeof(sr))) - return -EFAULT; return 0; } rcu_read_unlock(); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 44ee7a2e72ac..c9caeb5a43ed 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1118,29 +1118,29 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname, return do_rawv6_getsockopt(sk, level, optname, optval, optlen); } -static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) +static int rawv6_ioctl(struct sock *sk, int cmd, int *karg) { switch (cmd) { case SIOCOUTQ: { - int amount = sk_wmem_alloc_get(sk); - - return put_user(amount, (int __user *)arg); + *karg = sk_wmem_alloc_get(sk); + return 0; } case SIOCINQ: { struct sk_buff *skb; - int amount = 0; spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb) - amount = skb->len; + *karg = skb->len; + else + *karg = 0; spin_unlock_bh(&sk->sk_receive_queue.lock); - return put_user(amount, (int __user *)arg); + return 0; } default: #ifdef CONFIG_IPV6_MROUTE - return ip6mr_ioctl(sk, cmd, (void __user *)arg); + return ip6mr_ioctl(sk, cmd, karg); #else return -ENOIOCTLCMD; #endif diff --git a/net/l2tp/l2tp_core.h b/net/l2tp/l2tp_core.h index a88e070b431d..91ebf0a3f499 100644 --- a/net/l2tp/l2tp_core.h +++ b/net/l2tp/l2tp_core.h @@ -272,7 +272,7 @@ int l2tp_nl_register_ops(enum l2tp_pwtype pw_type, const struct l2tp_nl_cmd_ops void l2tp_nl_unregister_ops(enum l2tp_pwtype pw_type); /* IOCTL helper for IP encap modules. */ -int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg); +int l2tp_ioctl(struct sock *sk, int cmd, int *karg); /* Extract the tunnel structure from a socket's sk_user_data pointer, * validating the tunnel magic feather. diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 41a74fc84ca1..2b795c1064f5 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -562,19 +562,18 @@ out: return err ? err : copied; } -int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg) +int l2tp_ioctl(struct sock *sk, int cmd, int *karg) { struct sk_buff *skb; - int amount; switch (cmd) { case SIOCOUTQ: - amount = sk_wmem_alloc_get(sk); + *karg = sk_wmem_alloc_get(sk); break; case SIOCINQ: spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); - amount = skb ? skb->len : 0; + *karg = skb ? skb->len : 0; spin_unlock_bh(&sk->sk_receive_queue.lock); break; @@ -582,7 +581,7 @@ int l2tp_ioctl(struct sock *sk, int cmd, unsigned long arg) return -ENOIOCTLCMD; } - return put_user(amount, (int __user *)arg); + return 0; } EXPORT_SYMBOL_GPL(l2tp_ioctl); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 5df5cc0ffedc..992b89c75631 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3570,11 +3570,10 @@ static int mptcp_ioctl_outq(const struct mptcp_sock *msk, u64 v) return (int)delta; } -static int mptcp_ioctl(struct sock *sk, int cmd, unsigned long arg) +static int mptcp_ioctl(struct sock *sk, int cmd, int *karg) { struct mptcp_sock *msk = mptcp_sk(sk); bool slow; - int answ; switch (cmd) { case SIOCINQ: @@ -3583,24 +3582,24 @@ static int mptcp_ioctl(struct sock *sk, int cmd, unsigned long arg) lock_sock(sk); __mptcp_move_skbs(msk); - answ = mptcp_inq_hint(sk); + *karg = mptcp_inq_hint(sk); release_sock(sk); break; case SIOCOUTQ: slow = lock_sock_fast(sk); - answ = mptcp_ioctl_outq(msk, READ_ONCE(msk->snd_una)); + *karg = mptcp_ioctl_outq(msk, READ_ONCE(msk->snd_una)); unlock_sock_fast(sk, slow); break; case SIOCOUTQNSD: slow = lock_sock_fast(sk); - answ = mptcp_ioctl_outq(msk, msk->snd_nxt); + *karg = mptcp_ioctl_outq(msk, msk->snd_nxt); unlock_sock_fast(sk, slow); break; default: return -ENOIOCTLCMD; } - return put_user(answ, (int __user *)arg); + return 0; } static void mptcp_subflow_early_fallback(struct mptcp_sock *msk, diff --git a/net/phonet/datagram.c b/net/phonet/datagram.c index ff5f49ab236e..3aa50dc7535b 100644 --- a/net/phonet/datagram.c +++ b/net/phonet/datagram.c @@ -28,24 +28,21 @@ static void pn_sock_close(struct sock *sk, long timeout) sk_common_release(sk); } -static int pn_ioctl(struct sock *sk, int cmd, unsigned long arg) +static int pn_ioctl(struct sock *sk, int cmd, int *karg) { struct sk_buff *skb; - int answ; switch (cmd) { case SIOCINQ: lock_sock(sk); skb = skb_peek(&sk->sk_receive_queue); - answ = skb ? skb->len : 0; + *karg = skb ? skb->len : 0; release_sock(sk); - return put_user(answ, (int __user *)arg); + return 0; case SIOCPNADDRESOURCE: case SIOCPNDELRESOURCE: { - u32 res; - if (get_user(res, (u32 __user *)arg)) - return -EFAULT; + u32 res = *karg; if (res >= 256) return -EINVAL; if (cmd == SIOCPNADDRESOURCE) diff --git a/net/phonet/pep.c b/net/phonet/pep.c index 83ea13a50690..faba31f2eff2 100644 --- a/net/phonet/pep.c +++ b/net/phonet/pep.c @@ -917,10 +917,9 @@ static int pep_sock_enable(struct sock *sk, struct sockaddr *addr, int len) return 0; } -static int pep_ioctl(struct sock *sk, int cmd, unsigned long arg) +static int pep_ioctl(struct sock *sk, int cmd, int *karg) { struct pep_sock *pn = pep_sk(sk); - int answ; int ret = -ENOIOCTLCMD; switch (cmd) { @@ -933,13 +932,13 @@ static int pep_ioctl(struct sock *sk, int cmd, unsigned long arg) lock_sock(sk); if (sock_flag(sk, SOCK_URGINLINE) && !skb_queue_empty(&pn->ctrlreq_queue)) - answ = skb_peek(&pn->ctrlreq_queue)->len; + *karg = skb_peek(&pn->ctrlreq_queue)->len; else if (!skb_queue_empty(&sk->sk_receive_queue)) - answ = skb_peek(&sk->sk_receive_queue)->len; + *karg = skb_peek(&sk->sk_receive_queue)->len; else - answ = 0; + *karg = 0; release_sock(sk); - ret = put_user(answ, (int __user *)arg); + ret = 0; break; case SIOCPNENABLEPIPE: diff --git a/net/phonet/socket.c b/net/phonet/socket.c index 71e2caf6ab85..967f9b4dc026 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -387,7 +387,7 @@ static int pn_socket_ioctl(struct socket *sock, unsigned int cmd, return put_user(handle, (__u16 __user *)arg); } - return sk->sk_prot->ioctl(sk, cmd, arg); + return sk_ioctl(sk, cmd, (void __user *)arg); } static int pn_socket_listen(struct socket *sock, int backlog) diff --git a/net/sctp/socket.c b/net/sctp/socket.c index a68e1d541b12..6554a357fe33 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -4895,7 +4895,7 @@ out: } /* The SCTP ioctl handler. */ -static int sctp_ioctl(struct sock *sk, int cmd, unsigned long arg) +static int sctp_ioctl(struct sock *sk, int cmd, int *karg) { int rc = -ENOTCONN; @@ -4911,7 +4911,7 @@ static int sctp_ioctl(struct sock *sk, int cmd, unsigned long arg) switch (cmd) { case SIOCINQ: { struct sk_buff *skb; - unsigned int amount = 0; + *karg = 0; skb = skb_peek(&sk->sk_receive_queue); if (skb != NULL) { @@ -4919,9 +4919,9 @@ static int sctp_ioctl(struct sock *sk, int cmd, unsigned long arg) * We will only return the amount of this packet since * that is all that will be read. */ - amount = skb->len; + *karg = skb->len; } - rc = put_user(amount, (int __user *)arg); + rc = 0; break; } default: -- cgit v1.2.3 From 92b08290859b09a2ead2dc553aaaadb015748536 Mon Sep 17 00:00:00 2001 From: Christophe JAILLET Date: Sun, 18 Jun 2023 11:46:46 +0200 Subject: mptcp: Reorder fields in 'struct mptcp_pm_add_entry' Group some variables based on their sizes to reduce hole and avoid padding. On x86_64, this shrinks the size of 'struct mptcp_pm_add_entry' from 136 to 128 bytes. It saves a few bytes of memory and is more cache-line friendly. Signed-off-by: Christophe JAILLET Reviewed-by: Matthieu Baerts Reviewed-by: Jiri Pirko Link: https://lore.kernel.org/r/e47b71de54fd3e580544be56fc1bb2985c77b0f4.1687081558.git.christophe.jaillet@wanadoo.fr Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/mptcp') diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index a12a87b780f6..a56718ffdd02 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -25,9 +25,9 @@ static int pm_nl_pernet_id; struct mptcp_pm_add_entry { struct list_head list; struct mptcp_addr_info addr; + u8 retrans_times; struct timer_list add_timer; struct mptcp_sock *sock; - u8 retrans_times; }; struct pm_nl_pernet { -- cgit v1.2.3 From c026d33b8f5081969503e322ea30d7c1a6b17dda Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 20 Jun 2023 18:30:14 +0200 Subject: mptcp: move snd_una update earlier for fallback socket That will avoid an unneeded conditional in both the fast-path and in the fallback case and will simplify a bit the next patch. Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- net/mptcp/options.c | 6 ++++++ net/mptcp/protocol.c | 6 ------ 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'net/mptcp') diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 8a8083207be4..4bdcd2b326bd 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1119,6 +1119,12 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) mptcp_data_lock(subflow->conn); if (sk_stream_memory_free(sk)) __mptcp_check_push(subflow->conn, sk); + + /* on fallback we just need to ignore the msk-level snd_una, as + * this is really plain TCP + */ + msk->snd_una = READ_ONCE(msk->snd_nxt); + __mptcp_data_acked(subflow->conn); mptcp_data_unlock(subflow->conn); return true; diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 992b89c75631..9c756d675d4d 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -1004,12 +1004,6 @@ static void __mptcp_clean_una(struct sock *sk) struct mptcp_data_frag *dtmp, *dfrag; u64 snd_una; - /* on fallback we just need to ignore snd_una, as this is really - * plain TCP - */ - if (__mptcp_check_fallback(msk)) - msk->snd_una = READ_ONCE(msk->snd_nxt); - snd_una = msk->snd_una; list_for_each_entry_safe(dfrag, dtmp, &msk->rtx_queue, list) { if (after64(dfrag->data_seq + dfrag->data_len, snd_una)) -- cgit v1.2.3 From 38967f424b5be79c4c676712e5640d846efd07e3 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 20 Jun 2023 18:30:15 +0200 Subject: mptcp: track some aggregate data counters Currently there are no data transfer counters accounting for all the subflows used by a given MPTCP socket. The user-space can compute such figures aggregating the subflow info, but that is inaccurate if any subflow is closed before the MPTCP socket itself. Add the new counters in the MPTCP socket itself and expose them via the existing diag and sockopt. While touching mptcp_diag_fill_info(), acquire the relevant locks before fetching the msk data, to ensure better data consistency Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/385 Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 5 +++++ net/mptcp/options.c | 10 ++++++++-- net/mptcp/protocol.c | 11 ++++++++++- net/mptcp/protocol.h | 4 ++++ net/mptcp/sockopt.c | 25 ++++++++++++++++++++----- 5 files changed, 47 insertions(+), 8 deletions(-) (limited to 'net/mptcp') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index 32af2d278cb4..a124be6ebbba 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -123,6 +123,11 @@ struct mptcp_info { __u8 mptcpi_local_addr_used; __u8 mptcpi_local_addr_max; __u8 mptcpi_csum_enabled; + __u32 mptcpi_retransmits; + __u64 mptcpi_bytes_retrans; + __u64 mptcpi_bytes_sent; + __u64 mptcpi_bytes_received; + __u64 mptcpi_bytes_acked; }; /* diff --git a/net/mptcp/options.c b/net/mptcp/options.c index 4bdcd2b326bd..c254accb14de 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -1026,6 +1026,12 @@ u64 __mptcp_expand_seq(u64 old_seq, u64 cur_seq) return cur_seq; } +static void __mptcp_snd_una_update(struct mptcp_sock *msk, u64 new_snd_una) +{ + msk->bytes_acked += new_snd_una - msk->snd_una; + msk->snd_una = new_snd_una; +} + static void ack_update_msk(struct mptcp_sock *msk, struct sock *ssk, struct mptcp_options_received *mp_opt) @@ -1057,7 +1063,7 @@ static void ack_update_msk(struct mptcp_sock *msk, __mptcp_check_push(sk, ssk); if (after64(new_snd_una, old_snd_una)) { - msk->snd_una = new_snd_una; + __mptcp_snd_una_update(msk, new_snd_una); __mptcp_data_acked(sk); } mptcp_data_unlock(sk); @@ -1123,7 +1129,7 @@ bool mptcp_incoming_options(struct sock *sk, struct sk_buff *skb) /* on fallback we just need to ignore the msk-level snd_una, as * this is really plain TCP */ - msk->snd_una = READ_ONCE(msk->snd_nxt); + __mptcp_snd_una_update(msk, READ_ONCE(msk->snd_nxt)); __mptcp_data_acked(subflow->conn); mptcp_data_unlock(subflow->conn); diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 9c756d675d4d..d5b8e488bce1 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -377,6 +377,7 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk, if (MPTCP_SKB_CB(skb)->map_seq == msk->ack_seq) { /* in sequence */ + msk->bytes_received += copy_len; WRITE_ONCE(msk->ack_seq, msk->ack_seq + copy_len); tail = skb_peek_tail(&sk->sk_receive_queue); if (tail && mptcp_try_coalesce(sk, tail, skb)) @@ -760,6 +761,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk) MPTCP_SKB_CB(skb)->map_seq += delta; __skb_queue_tail(&sk->sk_receive_queue, skb); } + msk->bytes_received += end_seq - msk->ack_seq; msk->ack_seq = end_seq; moved = true; } @@ -1531,8 +1533,10 @@ static void mptcp_update_post_push(struct mptcp_sock *msk, * that has been handed to the subflow for transmission * and skip update in case it was old dfrag. */ - if (likely(after64(snd_nxt_new, msk->snd_nxt))) + if (likely(after64(snd_nxt_new, msk->snd_nxt))) { + msk->bytes_sent += snd_nxt_new - msk->snd_nxt; msk->snd_nxt = snd_nxt_new; + } } void mptcp_check_and_set_pending(struct sock *sk) @@ -2590,6 +2594,7 @@ static void __mptcp_retrans(struct sock *sk) } if (copied) { dfrag->already_sent = max(dfrag->already_sent, info.sent); + msk->bytes_retrans += copied; tcp_push(ssk, 0, info.mss_now, tcp_sk(ssk)->nonagle, info.size_goal); WRITE_ONCE(msk->allow_infinite_fallback, false); @@ -3102,6 +3107,10 @@ static int mptcp_disconnect(struct sock *sk, int flags) WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); mptcp_pm_data_reset(msk); mptcp_ca_reset(sk); + msk->bytes_acked = 0; + msk->bytes_received = 0; + msk->bytes_sent = 0; + msk->bytes_retrans = 0; WRITE_ONCE(sk->sk_shutdown, 0); sk_error_report(sk); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 47b46602870e..27adfcc5aaa2 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -262,10 +262,13 @@ struct mptcp_sock { u64 local_key; u64 remote_key; u64 write_seq; + u64 bytes_sent; u64 snd_nxt; + u64 bytes_received; u64 ack_seq; atomic64_t rcv_wnd_sent; u64 rcv_data_fin_seq; + u64 bytes_retrans; int rmem_fwd_alloc; struct sock *last_snd; int snd_burst; @@ -274,6 +277,7 @@ struct mptcp_sock { * recovery related fields are under data_lock * protection */ + u64 bytes_acked; u64 snd_una; u64 wnd_end; unsigned long timer_ival; diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index e172a5848b0d..fa5055d5b029 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -889,7 +889,9 @@ out: void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) { + struct sock *sk = (struct sock *)msk; u32 flags = 0; + bool slow; memset(info, 0, sizeof(*info)); @@ -898,6 +900,9 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) info->mptcpi_add_addr_accepted = READ_ONCE(msk->pm.add_addr_accepted); info->mptcpi_local_addr_used = READ_ONCE(msk->pm.local_addr_used); + if (inet_sk_state_load(sk) == TCP_LISTEN) + return; + /* The following limits only make sense for the in-kernel PM */ if (mptcp_pm_is_kernel(msk)) { info->mptcpi_subflows_max = @@ -915,11 +920,21 @@ void mptcp_diag_fill_info(struct mptcp_sock *msk, struct mptcp_info *info) if (READ_ONCE(msk->can_ack)) flags |= MPTCP_INFO_FLAG_REMOTE_KEY_RECEIVED; info->mptcpi_flags = flags; - info->mptcpi_token = READ_ONCE(msk->token); - info->mptcpi_write_seq = READ_ONCE(msk->write_seq); - info->mptcpi_snd_una = READ_ONCE(msk->snd_una); - info->mptcpi_rcv_nxt = READ_ONCE(msk->ack_seq); - info->mptcpi_csum_enabled = READ_ONCE(msk->csum_enabled); + mptcp_data_lock(sk); + info->mptcpi_snd_una = msk->snd_una; + info->mptcpi_rcv_nxt = msk->ack_seq; + info->mptcpi_bytes_acked = msk->bytes_acked; + mptcp_data_unlock(sk); + + slow = lock_sock_fast(sk); + info->mptcpi_csum_enabled = msk->csum_enabled; + info->mptcpi_token = msk->token; + info->mptcpi_write_seq = msk->write_seq; + info->mptcpi_retransmits = inet_csk(sk)->icsk_retransmits; + info->mptcpi_bytes_sent = msk->bytes_sent; + info->mptcpi_bytes_received = msk->bytes_received; + info->mptcpi_bytes_retrans = msk->bytes_retrans; + unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(mptcp_diag_fill_info); -- cgit v1.2.3 From 6f06b4d4d1cc676a3f9d947f931ec3866b6c4f6c Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 20 Jun 2023 18:30:17 +0200 Subject: mptcp: add subflow unique id The user-space need to properly account the data received/sent by individual subflows. When additional subflows are created and/or closed during the MPTCP socket lifetime, the information currently exposed via MPTCP_TCPINFO are not enough: subflows are identified only by the sequential position inside the info dumps, and that will change with the above mentioned events. To solve the above problem, this patch introduces a new subflow identifier that is unique inside the given MPTCP socket scope. The initial subflow get the id 1 and the other subflows get incremental values at join time. Link: https://github.com/multipath-tcp/mptcp_net-next/issues/388 Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 6 ++++++ net/mptcp/protocol.h | 5 ++++- net/mptcp/subflow.c | 2 ++ 3 files changed, 12 insertions(+), 1 deletion(-) (limited to 'net/mptcp') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index d5b8e488bce1..4ebd6e9aa949 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -96,6 +96,7 @@ static int __mptcp_socket_create(struct mptcp_sock *msk) list_add(&subflow->node, &msk->conn_list); sock_hold(ssock->sk); subflow->request_mptcp = 1; + subflow->subflow_id = msk->subflow_id++; /* This is the first subflow, always with id 0 */ subflow->local_id_valid = 1; @@ -847,6 +848,7 @@ static bool __mptcp_finish_join(struct mptcp_sock *msk, struct sock *ssk) if (sk->sk_socket && !ssk->sk_socket) mptcp_sock_graft(ssk, sk->sk_socket); + mptcp_subflow_ctx(ssk)->subflow_id = msk->subflow_id++; mptcp_sockopt_sync_locked(msk, ssk); mptcp_subflow_joined(msk, ssk); return true; @@ -2732,6 +2734,7 @@ static int __mptcp_init_sock(struct sock *sk) WRITE_ONCE(msk->csum_enabled, mptcp_is_checksum_enabled(sock_net(sk))); WRITE_ONCE(msk->allow_infinite_fallback, true); msk->recovery = false; + msk->subflow_id = 1; mptcp_pm_data_init(msk); @@ -3160,6 +3163,9 @@ struct sock *mptcp_sk_clone_init(const struct sock *sk, msk->wnd_end = msk->snd_nxt + req->rsk_rcv_wnd; msk->setsockopt_seq = mptcp_sk(sk)->setsockopt_seq; + /* passive msk is created after the first/MPC subflow */ + msk->subflow_id = 2; + sock_reset_flag(nsk, SOCK_RCU_FREE); security_inet_csk_clone(nsk, req); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 27adfcc5aaa2..bb4cacd92778 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -323,7 +323,8 @@ struct mptcp_sock { u64 rtt_us; /* last maximum rtt of subflows */ } rcvq_space; - u32 setsockopt_seq; + u32 subflow_id; + u32 setsockopt_seq; char ca_name[TCP_CA_NAME_MAX]; struct mptcp_sock *dl_next; }; @@ -504,6 +505,8 @@ struct mptcp_subflow_context { u8 reset_reason:4; u8 stale_count; + u32 subflow_id; + long delegated_status; unsigned long fail_tout; diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 4688daa6b38b..222dfcdadf2e 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -819,6 +819,7 @@ create_child: if (!ctx->conn) goto fallback; + ctx->subflow_id = 1; owner = mptcp_sk(ctx->conn); mptcp_pm_new_connection(owner, child, 1); @@ -1574,6 +1575,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, subflow->remote_id = remote_id; subflow->request_join = 1; subflow->request_bkup = !!(flags & MPTCP_PM_ADDR_FLAG_BACKUP); + subflow->subflow_id = msk->subflow_id++; mptcp_info2sockaddr(remote, &addr, ssk->sk_family); sock_hold(ssk); -- cgit v1.2.3 From 492432074e4fce4f8880213bf009b47adbf94a3a Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 20 Jun 2023 18:30:18 +0200 Subject: mptcp: introduce MPTCP_FULL_INFO getsockopt Some user-space applications want to monitor the subflows utilization. Dumping the per subflow tcp_info is not enough, as the PM could close and re-create the subflows under-the-hood, fooling the accounting. Even checking the src/dst addresses used by each subflow could not be enough, because new subflows could re-use the same address/port of the just closed one. This patch introduces a new socket option, allow dumping all the relevant information all-at-once (everything, everywhere...), in a consistent manner. Closes: https://github.com/multipath-tcp/mptcp_net-next/issues/388 Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- include/uapi/linux/mptcp.h | 24 +++++++++ net/mptcp/sockopt.c | 127 ++++++++++++++++++++++++++++++++++++++++++++- 2 files changed, 149 insertions(+), 2 deletions(-) (limited to 'net/mptcp') diff --git a/include/uapi/linux/mptcp.h b/include/uapi/linux/mptcp.h index a124be6ebbba..ee9c49f949a2 100644 --- a/include/uapi/linux/mptcp.h +++ b/include/uapi/linux/mptcp.h @@ -249,9 +249,33 @@ struct mptcp_subflow_addrs { }; }; +struct mptcp_subflow_info { + __u32 id; + struct mptcp_subflow_addrs addrs; +}; + +struct mptcp_full_info { + __u32 size_tcpinfo_kernel; /* must be 0, set by kernel */ + __u32 size_tcpinfo_user; + __u32 size_sfinfo_kernel; /* must be 0, set by kernel */ + __u32 size_sfinfo_user; + __u32 num_subflows; /* must be 0, set by kernel (real subflow count) */ + __u32 size_arrays_user; /* max subflows that userspace is interested in; + * the buffers at subflow_info/tcp_info + * are respectively at least: + * size_arrays * size_sfinfo_user + * size_arrays * size_tcpinfo_user + * bytes wide + */ + __aligned_u64 subflow_info; + __aligned_u64 tcp_info; + struct mptcp_info mptcp_info; +}; + /* MPTCP socket options */ #define MPTCP_INFO 1 #define MPTCP_TCPINFO 2 #define MPTCP_SUBFLOW_ADDRS 3 +#define MPTCP_FULL_INFO 4 #endif /* _UAPI_MPTCP_H */ diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c index fa5055d5b029..63f7a09335c5 100644 --- a/net/mptcp/sockopt.c +++ b/net/mptcp/sockopt.c @@ -14,7 +14,8 @@ #include #include "protocol.h" -#define MIN_INFO_OPTLEN_SIZE 16 +#define MIN_INFO_OPTLEN_SIZE 16 +#define MIN_FULL_INFO_OPTLEN_SIZE 40 static struct sock *__mptcp_tcp_fallback(struct mptcp_sock *msk) { @@ -981,7 +982,8 @@ static int mptcp_put_subflow_data(struct mptcp_subflow_data *sfd, } static int mptcp_get_subflow_data(struct mptcp_subflow_data *sfd, - char __user *optval, int __user *optlen) + char __user *optval, + int __user *optlen) { int len, copylen; @@ -1162,6 +1164,125 @@ static int mptcp_getsockopt_subflow_addrs(struct mptcp_sock *msk, char __user *o return 0; } +static int mptcp_get_full_info(struct mptcp_full_info *mfi, + char __user *optval, + int __user *optlen) +{ + int len; + + BUILD_BUG_ON(offsetof(struct mptcp_full_info, mptcp_info) != + MIN_FULL_INFO_OPTLEN_SIZE); + + if (get_user(len, optlen)) + return -EFAULT; + + if (len < MIN_FULL_INFO_OPTLEN_SIZE) + return -EINVAL; + + memset(mfi, 0, sizeof(*mfi)); + if (copy_from_user(mfi, optval, MIN_FULL_INFO_OPTLEN_SIZE)) + return -EFAULT; + + if (mfi->size_tcpinfo_kernel || + mfi->size_sfinfo_kernel || + mfi->num_subflows) + return -EINVAL; + + if (mfi->size_sfinfo_user > INT_MAX || + mfi->size_tcpinfo_user > INT_MAX) + return -EINVAL; + + return len - MIN_FULL_INFO_OPTLEN_SIZE; +} + +static int mptcp_put_full_info(struct mptcp_full_info *mfi, + char __user *optval, + u32 copylen, + int __user *optlen) +{ + copylen += MIN_FULL_INFO_OPTLEN_SIZE; + if (put_user(copylen, optlen)) + return -EFAULT; + + if (copy_to_user(optval, mfi, copylen)) + return -EFAULT; + return 0; +} + +static int mptcp_getsockopt_full_info(struct mptcp_sock *msk, char __user *optval, + int __user *optlen) +{ + unsigned int sfcount = 0, copylen = 0; + struct mptcp_subflow_context *subflow; + struct sock *sk = (struct sock *)msk; + void __user *tcpinfoptr, *sfinfoptr; + struct mptcp_full_info mfi; + int len; + + len = mptcp_get_full_info(&mfi, optval, optlen); + if (len < 0) + return len; + + /* don't bother filling the mptcp info if there is not enough + * user-space-provided storage + */ + if (len > 0) { + mptcp_diag_fill_info(msk, &mfi.mptcp_info); + copylen += min_t(unsigned int, len, sizeof(struct mptcp_info)); + } + + mfi.size_tcpinfo_kernel = sizeof(struct tcp_info); + mfi.size_tcpinfo_user = min_t(unsigned int, mfi.size_tcpinfo_user, + sizeof(struct tcp_info)); + sfinfoptr = u64_to_user_ptr(mfi.subflow_info); + mfi.size_sfinfo_kernel = sizeof(struct mptcp_subflow_info); + mfi.size_sfinfo_user = min_t(unsigned int, mfi.size_sfinfo_user, + sizeof(struct mptcp_subflow_info)); + tcpinfoptr = u64_to_user_ptr(mfi.tcp_info); + + lock_sock(sk); + mptcp_for_each_subflow(msk, subflow) { + struct sock *ssk = mptcp_subflow_tcp_sock(subflow); + struct mptcp_subflow_info sfinfo; + struct tcp_info tcp_info; + + if (sfcount++ >= mfi.size_arrays_user) + continue; + + /* fetch addr/tcp_info only if the user space buffers + * are wide enough + */ + memset(&sfinfo, 0, sizeof(sfinfo)); + sfinfo.id = subflow->subflow_id; + if (mfi.size_sfinfo_user > + offsetof(struct mptcp_subflow_info, addrs)) + mptcp_get_sub_addrs(ssk, &sfinfo.addrs); + if (copy_to_user(sfinfoptr, &sfinfo, mfi.size_sfinfo_user)) + goto fail_release; + + if (mfi.size_tcpinfo_user) { + tcp_get_info(ssk, &tcp_info); + if (copy_to_user(tcpinfoptr, &tcp_info, + mfi.size_tcpinfo_user)) + goto fail_release; + } + + tcpinfoptr += mfi.size_tcpinfo_user; + sfinfoptr += mfi.size_sfinfo_user; + } + release_sock(sk); + + mfi.num_subflows = sfcount; + if (mptcp_put_full_info(&mfi, optval, copylen, optlen)) + return -EFAULT; + + return 0; + +fail_release: + release_sock(sk); + return -EFAULT; +} + static int mptcp_put_int_option(struct mptcp_sock *msk, char __user *optval, int __user *optlen, int val) { @@ -1235,6 +1356,8 @@ static int mptcp_getsockopt_sol_mptcp(struct mptcp_sock *msk, int optname, switch (optname) { case MPTCP_INFO: return mptcp_getsockopt_info(msk, optval, optlen); + case MPTCP_FULL_INFO: + return mptcp_getsockopt_full_info(msk, optval, optlen); case MPTCP_TCPINFO: return mptcp_getsockopt_tcpinfo(msk, optval, optlen); case MPTCP_SUBFLOW_ADDRS: -- cgit v1.2.3 From bbd49d114d5790a2dc3f67926cec3fc48b2d5d81 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Tue, 20 Jun 2023 18:30:21 +0200 Subject: mptcp: consolidate transition to TCP_CLOSE in mptcp_do_fastclose() The MPTCP code always set the msk state to TCP_CLOSE before calling performing the fast-close. Move such state transition in mptcp_do_fastclose() to avoid some code duplication. Signed-off-by: Paolo Abeni Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- net/mptcp/protocol.c | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'net/mptcp') diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 4ebd6e9aa949..f65eec3e0d22 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2655,6 +2655,7 @@ static void mptcp_do_fastclose(struct sock *sk) struct mptcp_subflow_context *subflow, *tmp; struct mptcp_sock *msk = mptcp_sk(sk); + inet_sk_state_store(sk, TCP_CLOSE); mptcp_for_each_subflow_safe(msk, subflow, tmp) __mptcp_close_ssk(sk, mptcp_subflow_tcp_sock(subflow), subflow, MPTCP_CF_FASTCLOSE); @@ -2692,10 +2693,9 @@ static void mptcp_worker(struct work_struct *work) * even if it is orphaned and in FIN_WAIT2 state */ if (sock_flag(sk, SOCK_DEAD)) { - if (mptcp_should_close(sk)) { - inet_sk_state_store(sk, TCP_CLOSE); + if (mptcp_should_close(sk)) mptcp_do_fastclose(sk); - } + if (sk->sk_state == TCP_CLOSE) { __mptcp_destroy_sock(sk); goto unlock; @@ -2938,7 +2938,6 @@ static void __mptcp_destroy_sock(struct sock *sk) void __mptcp_unaccepted_force_close(struct sock *sk) { sock_set_flag(sk, SOCK_DEAD); - inet_sk_state_store(sk, TCP_CLOSE); mptcp_do_fastclose(sk); __mptcp_destroy_sock(sk); } @@ -2980,7 +2979,6 @@ bool __mptcp_close(struct sock *sk, long timeout) /* If the msk has read data, or the caller explicitly ask it, * do the MPTCP equivalent of TCP reset, aka MPTCP fastclose */ - inet_sk_state_store(sk, TCP_CLOSE); mptcp_do_fastclose(sk); timeout = 0; } else if (mptcp_close_state(sk)) { -- cgit v1.2.3 From 528cb5f2a1e859522f36f091f29f5c81ec6d4a4c Mon Sep 17 00:00:00 2001 From: Geliang Tang Date: Tue, 20 Jun 2023 18:30:22 +0200 Subject: mptcp: pass addr to mptcp_pm_alloc_anno_list Pass addr parameter to mptcp_pm_alloc_anno_list() instead of entry. We can reduce the scope, e.g. in mptcp_pm_alloc_anno_list(), we only access "entry->addr", we can then restrict to the pointer to "addr" then. Signed-off-by: Geliang Tang Reviewed-by: Matthieu Baerts Signed-off-by: Matthieu Baerts Signed-off-by: Jakub Kicinski --- net/mptcp/pm_netlink.c | 8 ++++---- net/mptcp/pm_userspace.c | 2 +- net/mptcp/protocol.h | 2 +- 3 files changed, 6 insertions(+), 6 deletions(-) (limited to 'net/mptcp') diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index a56718ffdd02..547e51c65480 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -341,7 +341,7 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk, } bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, - const struct mptcp_pm_addr_entry *entry) + const struct mptcp_addr_info *addr) { struct mptcp_pm_add_entry *add_entry = NULL; struct sock *sk = (struct sock *)msk; @@ -349,7 +349,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, lockdep_assert_held(&msk->pm.lock); - add_entry = mptcp_lookup_anno_list_by_saddr(msk, &entry->addr); + add_entry = mptcp_lookup_anno_list_by_saddr(msk, addr); if (add_entry) { if (mptcp_pm_is_kernel(msk)) @@ -366,7 +366,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, list_add(&add_entry->list, &msk->pm.anno_list); - add_entry->addr = entry->addr; + add_entry->addr = *addr; add_entry->sock = msk; add_entry->retrans_times = 0; @@ -576,7 +576,7 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) return; if (local) { - if (mptcp_pm_alloc_anno_list(msk, local)) { + if (mptcp_pm_alloc_anno_list(msk, &local->addr)) { __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); msk->pm.add_addr_signaled++; mptcp_pm_announce_addr(msk, &local->addr, false); diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 47a883a16c11..b5a8aa4c1ebd 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -193,7 +193,7 @@ int mptcp_nl_cmd_announce(struct sk_buff *skb, struct genl_info *info) lock_sock((struct sock *)msk); spin_lock_bh(&msk->pm.lock); - if (mptcp_pm_alloc_anno_list(msk, &addr_val)) { + if (mptcp_pm_alloc_anno_list(msk, &addr_val.addr)) { msk->pm.add_addr_signaled++; mptcp_pm_announce_addr(msk, &addr_val.addr, false); mptcp_pm_nl_addr_send_ack(msk); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index bb4cacd92778..3a1a64cdeba6 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -817,7 +817,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, struct mptcp_addr_info *rem, u8 bkup); bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, - const struct mptcp_pm_addr_entry *entry); + const struct mptcp_addr_info *addr); void mptcp_pm_free_anno_list(struct mptcp_sock *msk); bool mptcp_pm_sport_in_anno_list(struct mptcp_sock *msk, const struct sock *sk); struct mptcp_pm_add_entry * -- cgit v1.2.3 From dc97391e661009eab46783030d2404c9b6e6f2e7 Mon Sep 17 00:00:00 2001 From: David Howells Date: Fri, 23 Jun 2023 23:55:12 +0100 Subject: sock: Remove ->sendpage*() in favour of sendmsg(MSG_SPLICE_PAGES) Remove ->sendpage() and ->sendpage_locked(). sendmsg() with MSG_SPLICE_PAGES should be used instead. This allows multiple pages and multipage folios to be passed through. Signed-off-by: David Howells Acked-by: Marc Kleine-Budde # for net/can cc: Jens Axboe cc: Matthew Wilcox cc: linux-afs@lists.infradead.org cc: mptcp@lists.linux.dev cc: rds-devel@oss.oracle.com cc: tipc-discussion@lists.sourceforge.net cc: virtualization@lists.linux-foundation.org Link: https://lore.kernel.org/r/20230623225513.2732256-16-dhowells@redhat.com Signed-off-by: Jakub Kicinski --- Documentation/bpf/map_sockmap.rst | 10 ++--- Documentation/filesystems/locking.rst | 2 - Documentation/filesystems/vfs.rst | 1 - Documentation/networking/scaling.rst | 4 +- crypto/af_alg.c | 28 ------------- crypto/algif_aead.c | 22 ++-------- crypto/algif_rng.c | 2 - crypto/algif_skcipher.c | 14 ------- .../ethernet/chelsio/inline_crypto/chtls/chtls.h | 2 - .../chelsio/inline_crypto/chtls/chtls_io.c | 14 ------- .../chelsio/inline_crypto/chtls/chtls_main.c | 1 - fs/nfsd/vfs.c | 2 +- include/crypto/if_alg.h | 2 - include/linux/net.h | 8 ---- include/net/inet_common.h | 2 - include/net/sock.h | 6 --- include/net/tcp.h | 4 -- net/appletalk/ddp.c | 1 - net/atm/pvc.c | 1 - net/atm/svc.c | 1 - net/ax25/af_ax25.c | 1 - net/caif/caif_socket.c | 2 - net/can/bcm.c | 1 - net/can/isotp.c | 1 - net/can/j1939/socket.c | 1 - net/can/raw.c | 1 - net/core/sock.c | 35 +--------------- net/dccp/ipv4.c | 1 - net/dccp/ipv6.c | 1 - net/ieee802154/socket.c | 2 - net/ipv4/af_inet.c | 21 ---------- net/ipv4/tcp.c | 43 ++----------------- net/ipv4/tcp_bpf.c | 23 +---------- net/ipv4/tcp_ipv4.c | 1 - net/ipv4/udp.c | 15 ------- net/ipv4/udp_impl.h | 2 - net/ipv4/udplite.c | 1 - net/ipv6/af_inet6.c | 3 -- net/ipv6/raw.c | 1 - net/ipv6/tcp_ipv6.c | 1 - net/kcm/kcmsock.c | 20 --------- net/key/af_key.c | 1 - net/l2tp/l2tp_ip.c | 1 - net/l2tp/l2tp_ip6.c | 1 - net/llc/af_llc.c | 1 - net/mctp/af_mctp.c | 1 - net/mptcp/protocol.c | 2 - net/netlink/af_netlink.c | 1 - net/netrom/af_netrom.c | 1 - net/packet/af_packet.c | 2 - net/phonet/socket.c | 2 - net/qrtr/af_qrtr.c | 1 - net/rds/af_rds.c | 1 - net/rose/af_rose.c | 1 - net/rxrpc/af_rxrpc.c | 1 - net/sctp/protocol.c | 1 - net/socket.c | 48 ---------------------- net/tipc/socket.c | 3 -- net/tls/tls.h | 6 --- net/tls/tls_device.c | 17 -------- net/tls/tls_main.c | 7 ---- net/tls/tls_sw.c | 35 ---------------- net/unix/af_unix.c | 19 --------- net/vmw_vsock/af_vsock.c | 3 -- net/x25/af_x25.c | 1 - net/xdp/xsk.c | 1 - 66 files changed, 20 insertions(+), 442 deletions(-) (limited to 'net/mptcp') diff --git a/Documentation/bpf/map_sockmap.rst b/Documentation/bpf/map_sockmap.rst index cc92047c6630..2d630686a00b 100644 --- a/Documentation/bpf/map_sockmap.rst +++ b/Documentation/bpf/map_sockmap.rst @@ -240,11 +240,11 @@ offsets into ``msg``, respectively. If a program of type ``BPF_PROG_TYPE_SK_MSG`` is run on a ``msg`` it can only parse data that the (``data``, ``data_end``) pointers have already consumed. For ``sendmsg()`` hooks this is likely the first scatterlist element. But for -calls relying on the ``sendpage`` handler (e.g., ``sendfile()``) this will be -the range (**0**, **0**) because the data is shared with user space and by -default the objective is to avoid allowing user space to modify data while (or -after) BPF verdict is being decided. This helper can be used to pull in data -and to set the start and end pointers to given values. Data will be copied if +calls relying on MSG_SPLICE_PAGES (e.g., ``sendfile()``) this will be the +range (**0**, **0**) because the data is shared with user space and by default +the objective is to avoid allowing user space to modify data while (or after) +BPF verdict is being decided. This helper can be used to pull in data and to +set the start and end pointers to given values. Data will be copied if necessary (i.e., if data was not linear and if start and end pointers do not point to the same chunk). diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst index aa1a233b0fa8..ed148919e11a 100644 --- a/Documentation/filesystems/locking.rst +++ b/Documentation/filesystems/locking.rst @@ -521,8 +521,6 @@ prototypes:: int (*fsync) (struct file *, loff_t start, loff_t end, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); - ssize_t (*sendpage) (struct file *, struct page *, int, size_t, - loff_t *, int); unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); int (*check_flags)(int); diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst index 769be5230210..cb2a97e49872 100644 --- a/Documentation/filesystems/vfs.rst +++ b/Documentation/filesystems/vfs.rst @@ -1086,7 +1086,6 @@ This describes how the VFS can manipulate an open file. As of kernel int (*fsync) (struct file *, loff_t, loff_t, int datasync); int (*fasync) (int, struct file *, int); int (*lock) (struct file *, int, struct file_lock *); - ssize_t (*sendpage) (struct file *, struct page *, int, size_t, loff_t *, int); unsigned long (*get_unmapped_area)(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); int (*check_flags)(int); int (*flock) (struct file *, int, struct file_lock *); diff --git a/Documentation/networking/scaling.rst b/Documentation/networking/scaling.rst index 3d435caa3ef2..92c9fb46d6a2 100644 --- a/Documentation/networking/scaling.rst +++ b/Documentation/networking/scaling.rst @@ -269,8 +269,8 @@ a single application thread handles flows with many different flow hashes. rps_sock_flow_table is a global flow table that contains the *desired* CPU for flows: the CPU that is currently processing the flow in userspace. Each table value is a CPU index that is updated during calls to recvmsg -and sendmsg (specifically, inet_recvmsg(), inet_sendmsg(), inet_sendpage() -and tcp_splice_read()). +and sendmsg (specifically, inet_recvmsg(), inet_sendmsg() and +tcp_splice_read()). When the scheduler moves a thread to a new CPU while it has outstanding receive packets on the old CPU, packets may arrive out of order. To diff --git a/crypto/af_alg.c b/crypto/af_alg.c index cdb1dcc5dd1a..6218c773d71c 100644 --- a/crypto/af_alg.c +++ b/crypto/af_alg.c @@ -482,7 +482,6 @@ static const struct proto_ops alg_proto_ops = { .listen = sock_no_listen, .shutdown = sock_no_shutdown, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, .sendmsg = sock_no_sendmsg, .recvmsg = sock_no_recvmsg, @@ -1106,33 +1105,6 @@ unlock: } EXPORT_SYMBOL_GPL(af_alg_sendmsg); -/** - * af_alg_sendpage - sendpage system call handler - * @sock: socket of connection to user space to write to - * @page: data to send - * @offset: offset into page to begin sending - * @size: length of data - * @flags: message send/receive flags - * - * This is a generic implementation of sendpage to fill ctx->tsgl_list. - */ -ssize_t af_alg_sendpage(struct socket *sock, struct page *page, - int offset, size_t size, int flags) -{ - struct bio_vec bvec; - struct msghdr msg = { - .msg_flags = flags | MSG_SPLICE_PAGES, - }; - - if (flags & MSG_SENDPAGE_NOTLAST) - msg.msg_flags |= MSG_MORE; - - bvec_set_page(&bvec, page, size, offset); - iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); - return sock_sendmsg(sock, &msg); -} -EXPORT_SYMBOL_GPL(af_alg_sendpage); - /** * af_alg_free_resources - release resources required for crypto request * @areq: Request holding the TX and RX SGL diff --git a/crypto/algif_aead.c b/crypto/algif_aead.c index 35bfa283748d..7d58cbbce4af 100644 --- a/crypto/algif_aead.c +++ b/crypto/algif_aead.c @@ -9,10 +9,10 @@ * The following concept of the memory management is used: * * The kernel maintains two SGLs, the TX SGL and the RX SGL. The TX SGL is - * filled by user space with the data submitted via sendpage. Filling up - * the TX SGL does not cause a crypto operation -- the data will only be - * tracked by the kernel. Upon receipt of one recvmsg call, the caller must - * provide a buffer which is tracked with the RX SGL. + * filled by user space with the data submitted via sendmsg (maybe with + * MSG_SPLICE_PAGES). Filling up the TX SGL does not cause a crypto operation + * -- the data will only be tracked by the kernel. Upon receipt of one recvmsg + * call, the caller must provide a buffer which is tracked with the RX SGL. * * During the processing of the recvmsg operation, the cipher request is * allocated and prepared. As part of the recvmsg operation, the processed @@ -370,7 +370,6 @@ static struct proto_ops algif_aead_ops = { .release = af_alg_release, .sendmsg = aead_sendmsg, - .sendpage = af_alg_sendpage, .recvmsg = aead_recvmsg, .poll = af_alg_poll, }; @@ -422,18 +421,6 @@ static int aead_sendmsg_nokey(struct socket *sock, struct msghdr *msg, return aead_sendmsg(sock, msg, size); } -static ssize_t aead_sendpage_nokey(struct socket *sock, struct page *page, - int offset, size_t size, int flags) -{ - int err; - - err = aead_check_key(sock); - if (err) - return err; - - return af_alg_sendpage(sock, page, offset, size, flags); -} - static int aead_recvmsg_nokey(struct socket *sock, struct msghdr *msg, size_t ignored, int flags) { @@ -461,7 +448,6 @@ static struct proto_ops algif_aead_ops_nokey = { .release = af_alg_release, .sendmsg = aead_sendmsg_nokey, - .sendpage = aead_sendpage_nokey, .recvmsg = aead_recvmsg_nokey, .poll = af_alg_poll, }; diff --git a/crypto/algif_rng.c b/crypto/algif_rng.c index 407408c43730..10c41adac3b1 100644 --- a/crypto/algif_rng.c +++ b/crypto/algif_rng.c @@ -174,7 +174,6 @@ static struct proto_ops algif_rng_ops = { .bind = sock_no_bind, .accept = sock_no_accept, .sendmsg = sock_no_sendmsg, - .sendpage = sock_no_sendpage, .release = af_alg_release, .recvmsg = rng_recvmsg, @@ -192,7 +191,6 @@ static struct proto_ops __maybe_unused algif_rng_test_ops = { .mmap = sock_no_mmap, .bind = sock_no_bind, .accept = sock_no_accept, - .sendpage = sock_no_sendpage, .release = af_alg_release, .recvmsg = rng_test_recvmsg, diff --git a/crypto/algif_skcipher.c b/crypto/algif_skcipher.c index b1f321b9f846..9ada9b741af8 100644 --- a/crypto/algif_skcipher.c +++ b/crypto/algif_skcipher.c @@ -194,7 +194,6 @@ static struct proto_ops algif_skcipher_ops = { .release = af_alg_release, .sendmsg = skcipher_sendmsg, - .sendpage = af_alg_sendpage, .recvmsg = skcipher_recvmsg, .poll = af_alg_poll, }; @@ -246,18 +245,6 @@ static int skcipher_sendmsg_nokey(struct socket *sock, struct msghdr *msg, return skcipher_sendmsg(sock, msg, size); } -static ssize_t skcipher_sendpage_nokey(struct socket *sock, struct page *page, - int offset, size_t size, int flags) -{ - int err; - - err = skcipher_check_key(sock); - if (err) - return err; - - return af_alg_sendpage(sock, page, offset, size, flags); -} - static int skcipher_recvmsg_nokey(struct socket *sock, struct msghdr *msg, size_t ignored, int flags) { @@ -285,7 +272,6 @@ static struct proto_ops algif_skcipher_ops_nokey = { .release = af_alg_release, .sendmsg = skcipher_sendmsg_nokey, - .sendpage = skcipher_sendpage_nokey, .recvmsg = skcipher_recvmsg_nokey, .poll = af_alg_poll, }; diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h index da4818d2c856..68562a82d036 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls.h @@ -569,8 +569,6 @@ int chtls_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int chtls_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len); void chtls_splice_eof(struct socket *sock); -int chtls_sendpage(struct sock *sk, struct page *page, - int offset, size_t size, int flags); int send_tx_flowc_wr(struct sock *sk, int compl, u32 snd_nxt, u32 rcv_nxt); void chtls_tcp_push(struct sock *sk, int flags); diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c index e08ac960c967..5fc64e47568a 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c @@ -1246,20 +1246,6 @@ void chtls_splice_eof(struct socket *sock) release_sock(sk); } -int chtls_sendpage(struct sock *sk, struct page *page, - int offset, size_t size, int flags) -{ - struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES, }; - struct bio_vec bvec; - - if (flags & MSG_SENDPAGE_NOTLAST) - msg.msg_flags |= MSG_MORE; - - bvec_set_page(&bvec, page, size, offset); - iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); - return chtls_sendmsg(sk, &msg, size); -} - static void chtls_select_window(struct sock *sk) { struct chtls_sock *csk = rcu_dereference_sk_user_data(sk); diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c index 6b6787eafd2f..455a54708be4 100644 --- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c +++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_main.c @@ -607,7 +607,6 @@ static void __init chtls_init_ulp_ops(void) chtls_cpl_prot.shutdown = chtls_shutdown; chtls_cpl_prot.sendmsg = chtls_sendmsg; chtls_cpl_prot.splice_eof = chtls_splice_eof; - chtls_cpl_prot.sendpage = chtls_sendpage; chtls_cpl_prot.recvmsg = chtls_recvmsg; chtls_cpl_prot.setsockopt = chtls_setsockopt; chtls_cpl_prot.getsockopt = chtls_getsockopt; diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index db67f8e19344..8879e207ff5a 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -936,7 +936,7 @@ nfsd_open_verified(struct svc_rqst *rqstp, struct svc_fh *fhp, int may_flags, /* * Grab and keep cached pages associated with a file in the svc_rqst - * so that they can be passed to the network sendmsg/sendpage routines + * so that they can be passed to the network sendmsg routines * directly. They will be released after the sending has completed. * * Return values: Number of bytes consumed, or -EIO if there are no diff --git a/include/crypto/if_alg.h b/include/crypto/if_alg.h index 34224e77f5a2..ef8ce86b1f78 100644 --- a/include/crypto/if_alg.h +++ b/include/crypto/if_alg.h @@ -229,8 +229,6 @@ void af_alg_wmem_wakeup(struct sock *sk); int af_alg_wait_for_data(struct sock *sk, unsigned flags, unsigned min); int af_alg_sendmsg(struct socket *sock, struct msghdr *msg, size_t size, unsigned int ivsize); -ssize_t af_alg_sendpage(struct socket *sock, struct page *page, - int offset, size_t size, int flags); void af_alg_free_resources(struct af_alg_async_req *areq); void af_alg_async_cb(void *data, int err); __poll_t af_alg_poll(struct file *file, struct socket *sock, diff --git a/include/linux/net.h b/include/linux/net.h index 23324e9a2b3d..41c608c1b02c 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -207,8 +207,6 @@ struct proto_ops { size_t total_len, int flags); int (*mmap) (struct file *file, struct socket *sock, struct vm_area_struct * vma); - ssize_t (*sendpage) (struct socket *sock, struct page *page, - int offset, size_t size, int flags); ssize_t (*splice_read)(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); void (*splice_eof)(struct socket *sock); @@ -222,8 +220,6 @@ struct proto_ops { sk_read_actor_t recv_actor); /* This is different from read_sock(), it reads an entire skb at a time. */ int (*read_skb)(struct sock *sk, skb_read_actor_t recv_actor); - int (*sendpage_locked)(struct sock *sk, struct page *page, - int offset, size_t size, int flags); int (*sendmsg_locked)(struct sock *sk, struct msghdr *msg, size_t size); int (*set_rcvlowat)(struct sock *sk, int val); @@ -341,10 +337,6 @@ int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, int flags); int kernel_getsockname(struct socket *sock, struct sockaddr *addr); int kernel_getpeername(struct socket *sock, struct sockaddr *addr); -int kernel_sendpage(struct socket *sock, struct page *page, int offset, - size_t size, int flags); -int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, - size_t size, int flags); int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how); /* Routine returns the IP overhead imposed by a (caller-protected) socket. */ diff --git a/include/net/inet_common.h b/include/net/inet_common.h index a75333342c4e..b86b8e21de7f 100644 --- a/include/net/inet_common.h +++ b/include/net/inet_common.h @@ -36,8 +36,6 @@ void __inet_accept(struct socket *sock, struct socket *newsock, int inet_send_prepare(struct sock *sk); int inet_sendmsg(struct socket *sock, struct msghdr *msg, size_t size); void inet_splice_eof(struct socket *sock); -ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, - size_t size, int flags); int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags); int inet_shutdown(struct socket *sock, int how); diff --git a/include/net/sock.h b/include/net/sock.h index 62a1b99da349..121284f455a8 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -1277,8 +1277,6 @@ struct proto { size_t len); int (*recvmsg)(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len); - int (*sendpage)(struct sock *sk, struct page *page, - int offset, size_t size, int flags); void (*splice_eof)(struct socket *sock); int (*bind)(struct sock *sk, struct sockaddr *addr, int addr_len); @@ -1919,10 +1917,6 @@ int sock_no_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t len); int sock_no_recvmsg(struct socket *, struct msghdr *, size_t, int); int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma); -ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, - size_t size, int flags); -ssize_t sock_no_sendpage_locked(struct sock *sk, struct page *page, - int offset, size_t size, int flags); /* * Functions to fill in entries in struct proto_ops when a protocol diff --git a/include/net/tcp.h b/include/net/tcp.h index 31b534370787..226bce6d1e8c 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -329,10 +329,6 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size); int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, int *copied, size_t size, struct ubuf_info *uarg); void tcp_splice_eof(struct socket *sock); -int tcp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, - int flags); -int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, - size_t size, int flags); int tcp_send_mss(struct sock *sk, int *size_goal, int flags); int tcp_wmem_schedule(struct sock *sk, int copy); void tcp_push(struct sock *sk, int flags, int mss_now, int nonagle, diff --git a/net/appletalk/ddp.c b/net/appletalk/ddp.c index a06f4d4a6f47..8978fb6212ff 100644 --- a/net/appletalk/ddp.c +++ b/net/appletalk/ddp.c @@ -1929,7 +1929,6 @@ static const struct proto_ops atalk_dgram_ops = { .sendmsg = atalk_sendmsg, .recvmsg = atalk_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; static struct notifier_block ddp_notifier = { diff --git a/net/atm/pvc.c b/net/atm/pvc.c index 53e7d3f39e26..66d9a9bd5896 100644 --- a/net/atm/pvc.c +++ b/net/atm/pvc.c @@ -126,7 +126,6 @@ static const struct proto_ops pvc_proto_ops = { .sendmsg = vcc_sendmsg, .recvmsg = vcc_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; diff --git a/net/atm/svc.c b/net/atm/svc.c index d83556d8beb9..36a814f1fbd1 100644 --- a/net/atm/svc.c +++ b/net/atm/svc.c @@ -654,7 +654,6 @@ static const struct proto_ops svc_proto_ops = { .sendmsg = vcc_sendmsg, .recvmsg = vcc_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index d8da400cb4de..5db805d5f74d 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -2022,7 +2022,6 @@ static const struct proto_ops ax25_proto_ops = { .sendmsg = ax25_sendmsg, .recvmsg = ax25_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; /* diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 4eebcc66c19a..9c82698da4f5 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -976,7 +976,6 @@ static const struct proto_ops caif_seqpacket_ops = { .sendmsg = caif_seqpkt_sendmsg, .recvmsg = caif_seqpkt_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; static const struct proto_ops caif_stream_ops = { @@ -996,7 +995,6 @@ static const struct proto_ops caif_stream_ops = { .sendmsg = caif_stream_sendmsg, .recvmsg = caif_stream_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; /* This function is called when a socket is finally destroyed. */ diff --git a/net/can/bcm.c b/net/can/bcm.c index a962ec2b8ba5..9ba35685b043 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -1703,7 +1703,6 @@ static const struct proto_ops bcm_ops = { .sendmsg = bcm_sendmsg, .recvmsg = bcm_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; static struct proto bcm_proto __read_mostly = { diff --git a/net/can/isotp.c b/net/can/isotp.c index 84f9aba02901..1f25b45868cf 100644 --- a/net/can/isotp.c +++ b/net/can/isotp.c @@ -1699,7 +1699,6 @@ static const struct proto_ops isotp_ops = { .sendmsg = isotp_sendmsg, .recvmsg = isotp_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; static struct proto isotp_proto __read_mostly = { diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 35970c25496a..feaec4ad6d16 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -1306,7 +1306,6 @@ static const struct proto_ops j1939_ops = { .sendmsg = j1939_sk_sendmsg, .recvmsg = j1939_sk_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; static struct proto j1939_proto __read_mostly = { diff --git a/net/can/raw.c b/net/can/raw.c index f64469b98260..15c79b079184 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -962,7 +962,6 @@ static const struct proto_ops raw_ops = { .sendmsg = raw_sendmsg, .recvmsg = raw_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; static struct proto raw_proto __read_mostly = { diff --git a/net/core/sock.c b/net/core/sock.c index 5f1747c12004..de719094b804 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -3261,36 +3261,6 @@ void __receive_sock(struct file *file) } } -ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) -{ - ssize_t res; - struct msghdr msg = {.msg_flags = flags}; - struct kvec iov; - char *kaddr = kmap(page); - iov.iov_base = kaddr + offset; - iov.iov_len = size; - res = kernel_sendmsg(sock, &msg, &iov, 1, size); - kunmap(page); - return res; -} -EXPORT_SYMBOL(sock_no_sendpage); - -ssize_t sock_no_sendpage_locked(struct sock *sk, struct page *page, - int offset, size_t size, int flags) -{ - ssize_t res; - struct msghdr msg = {.msg_flags = flags}; - struct kvec iov; - char *kaddr = kmap(page); - - iov.iov_base = kaddr + offset; - iov.iov_len = size; - res = kernel_sendmsg_locked(sk, &msg, &iov, 1, size); - kunmap(page); - return res; -} -EXPORT_SYMBOL(sock_no_sendpage_locked); - /* * Default Socket Callbacks */ @@ -4046,7 +4016,7 @@ static void proto_seq_printf(struct seq_file *seq, struct proto *proto) { seq_printf(seq, "%-9s %4u %6d %6ld %-3s %6u %-3s %-10s " - "%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n", + "%2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c %2c\n", proto->name, proto->obj_size, sock_prot_inuse_get(seq_file_net(seq), proto), @@ -4067,7 +4037,6 @@ static void proto_seq_printf(struct seq_file *seq, struct proto *proto) proto_method_implemented(proto->getsockopt), proto_method_implemented(proto->sendmsg), proto_method_implemented(proto->recvmsg), - proto_method_implemented(proto->sendpage), proto_method_implemented(proto->bind), proto_method_implemented(proto->backlog_rcv), proto_method_implemented(proto->hash), @@ -4088,7 +4057,7 @@ static int proto_seq_show(struct seq_file *seq, void *v) "maxhdr", "slab", "module", - "cl co di ac io in de sh ss gs se re sp bi br ha uh gp em\n"); + "cl co di ac io in de sh ss gs se re bi br ha uh gp em\n"); else proto_seq_printf(seq, list_entry(v, struct proto, node)); return 0; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 3ab68415d121..fa8079303cb0 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -1010,7 +1010,6 @@ static const struct proto_ops inet_dccp_ops = { .sendmsg = inet_sendmsg, .recvmsg = sock_common_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; static struct inet_protosw dccp_v4_protosw = { diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 93c98990d726..7249ef218178 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -1087,7 +1087,6 @@ static const struct proto_ops inet6_dccp_ops = { .sendmsg = inet_sendmsg, .recvmsg = sock_common_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif diff --git a/net/ieee802154/socket.c b/net/ieee802154/socket.c index 9c124705120d..00302e8b9615 100644 --- a/net/ieee802154/socket.c +++ b/net/ieee802154/socket.c @@ -426,7 +426,6 @@ static const struct proto_ops ieee802154_raw_ops = { .sendmsg = ieee802154_sock_sendmsg, .recvmsg = sock_common_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; /* DGRAM Sockets (802.15.4 dataframes) */ @@ -989,7 +988,6 @@ static const struct proto_ops ieee802154_dgram_ops = { .sendmsg = ieee802154_sock_sendmsg, .recvmsg = sock_common_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; static void ieee802154_sock_destruct(struct sock *sk) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 38e649fb4474..9b2ca2fcc5a1 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -847,23 +847,6 @@ void inet_splice_eof(struct socket *sock) } EXPORT_SYMBOL_GPL(inet_splice_eof); -ssize_t inet_sendpage(struct socket *sock, struct page *page, int offset, - size_t size, int flags) -{ - struct sock *sk = sock->sk; - const struct proto *prot; - - if (unlikely(inet_send_prepare(sk))) - return -EAGAIN; - - /* IPV6_ADDRFORM can change sk->sk_prot under us. */ - prot = READ_ONCE(sk->sk_prot); - if (prot->sendpage) - return prot->sendpage(sk, page, offset, size, flags); - return sock_no_sendpage(sock, page, offset, size, flags); -} -EXPORT_SYMBOL(inet_sendpage); - INDIRECT_CALLABLE_DECLARE(int udp_recvmsg(struct sock *, struct msghdr *, size_t, int, int *)); int inet_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, @@ -1067,12 +1050,10 @@ const struct proto_ops inet_stream_ops = { .mmap = tcp_mmap, #endif .splice_eof = inet_splice_eof, - .sendpage = inet_sendpage, .splice_read = tcp_splice_read, .read_sock = tcp_read_sock, .read_skb = tcp_read_skb, .sendmsg_locked = tcp_sendmsg_locked, - .sendpage_locked = tcp_sendpage_locked, .peek_len = tcp_peek_len, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, @@ -1102,7 +1083,6 @@ const struct proto_ops inet_dgram_ops = { .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .splice_eof = inet_splice_eof, - .sendpage = inet_sendpage, .set_peek_off = sk_set_peek_off, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, @@ -1134,7 +1114,6 @@ static const struct proto_ops inet_sockraw_ops = { .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, .splice_eof = inet_splice_eof, - .sendpage = inet_sendpage, #ifdef CONFIG_COMPAT .compat_ioctl = inet_compat_ioctl, #endif diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index d56edc2c885f..e03e08745308 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -923,11 +923,10 @@ int tcp_send_mss(struct sock *sk, int *size_goal, int flags) return mss_now; } -/* In some cases, both sendpage() and sendmsg() could have added - * an skb to the write queue, but failed adding payload on it. - * We need to remove it to consume less memory, but more - * importantly be able to generate EPOLLOUT for Edge Trigger epoll() - * users. +/* In some cases, both sendmsg() could have added an skb to the write queue, + * but failed adding payload on it. We need to remove it to consume less + * memory, but more importantly be able to generate EPOLLOUT for Edge Trigger + * epoll() users. */ void tcp_remove_empty_skb(struct sock *sk) { @@ -975,40 +974,6 @@ int tcp_wmem_schedule(struct sock *sk, int copy) return min(copy, sk->sk_forward_alloc); } -int tcp_sendpage_locked(struct sock *sk, struct page *page, int offset, - size_t size, int flags) -{ - struct bio_vec bvec; - struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES, }; - - if (!(sk->sk_route_caps & NETIF_F_SG)) - return sock_no_sendpage_locked(sk, page, offset, size, flags); - - tcp_rate_check_app_limited(sk); /* is sending application-limited? */ - - bvec_set_page(&bvec, page, size, offset); - iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); - - if (flags & MSG_SENDPAGE_NOTLAST) - msg.msg_flags |= MSG_MORE; - - return tcp_sendmsg_locked(sk, &msg, size); -} -EXPORT_SYMBOL_GPL(tcp_sendpage_locked); - -int tcp_sendpage(struct sock *sk, struct page *page, int offset, - size_t size, int flags) -{ - int ret; - - lock_sock(sk); - ret = tcp_sendpage_locked(sk, page, offset, size, flags); - release_sock(sk); - - return ret; -} -EXPORT_SYMBOL(tcp_sendpage); - void tcp_free_fastopen_req(struct tcp_sock *tp) { if (tp->fastopen_req) { diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 31d6005cea9b..81f0dff69e0b 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -486,7 +486,7 @@ static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) long timeo; int flags; - /* Don't let internal sendpage flags through */ + /* Don't let internal flags through */ flags = (msg->msg_flags & ~MSG_SENDPAGE_DECRYPTED); flags |= MSG_NO_SHARED_FRAGS; @@ -566,23 +566,6 @@ out_err: return copied ? copied : err; } -static int tcp_bpf_sendpage(struct sock *sk, struct page *page, int offset, - size_t size, int flags) -{ - struct bio_vec bvec; - struct msghdr msg = { - .msg_flags = flags | MSG_SPLICE_PAGES, - }; - - bvec_set_page(&bvec, page, size, offset); - iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); - - if (flags & MSG_SENDPAGE_NOTLAST) - msg.msg_flags |= MSG_MORE; - - return tcp_bpf_sendmsg(sk, &msg, size); -} - enum { TCP_BPF_IPV4, TCP_BPF_IPV6, @@ -612,7 +595,6 @@ static void tcp_bpf_rebuild_protos(struct proto prot[TCP_BPF_NUM_CFGS], prot[TCP_BPF_TX] = prot[TCP_BPF_BASE]; prot[TCP_BPF_TX].sendmsg = tcp_bpf_sendmsg; - prot[TCP_BPF_TX].sendpage = tcp_bpf_sendpage; prot[TCP_BPF_RX] = prot[TCP_BPF_BASE]; prot[TCP_BPF_RX].recvmsg = tcp_bpf_recvmsg_parser; @@ -647,8 +629,7 @@ static int tcp_bpf_assert_proto_ops(struct proto *ops) * indeed valid assumptions. */ return ops->recvmsg == tcp_recvmsg && - ops->sendmsg == tcp_sendmsg && - ops->sendpage == tcp_sendpage ? 0 : -ENOTSUPP; + ops->sendmsg == tcp_sendmsg ? 0 : -ENOTSUPP; } int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 9213804b034f..fd365de4d5ff 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -3117,7 +3117,6 @@ struct proto tcp_prot = { .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, .splice_eof = tcp_splice_eof, - .sendpage = tcp_sendpage, .backlog_rcv = tcp_v4_do_rcv, .release_cb = tcp_release_cb, .hash = inet_hash, diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 48fdcd3cad9c..42a96b3547c9 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1340,20 +1340,6 @@ void udp_splice_eof(struct socket *sock) } EXPORT_SYMBOL_GPL(udp_splice_eof); -int udp_sendpage(struct sock *sk, struct page *page, int offset, - size_t size, int flags) -{ - struct bio_vec bvec; - struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES }; - - if (flags & MSG_SENDPAGE_NOTLAST) - msg.msg_flags |= MSG_MORE; - - bvec_set_page(&bvec, page, size, offset); - iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); - return udp_sendmsg(sk, &msg, size); -} - #define UDP_SKB_IS_STATELESS 0x80000000 /* all head states (dst, sk, nf conntrack) except skb extensions are @@ -2933,7 +2919,6 @@ struct proto udp_prot = { .sendmsg = udp_sendmsg, .recvmsg = udp_recvmsg, .splice_eof = udp_splice_eof, - .sendpage = udp_sendpage, .release_cb = ip4_datagram_release_cb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h index 4ba7a88a1b1d..e1ff3a375996 100644 --- a/net/ipv4/udp_impl.h +++ b/net/ipv4/udp_impl.h @@ -19,8 +19,6 @@ int udp_getsockopt(struct sock *sk, int level, int optname, int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int flags, int *addr_len); -int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, - int flags); void udp_destroy_sock(struct sock *sk); #ifdef CONFIG_PROC_FS diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index 143f93a12f25..39ecdad1b50c 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -56,7 +56,6 @@ struct proto udplite_prot = { .getsockopt = udp_getsockopt, .sendmsg = udp_sendmsg, .recvmsg = udp_recvmsg, - .sendpage = udp_sendpage, .hash = udp_lib_hash, .unhash = udp_lib_unhash, .rehash = udp_v4_rehash, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index b3451cf47d29..5d593ddc0347 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -696,9 +696,7 @@ const struct proto_ops inet6_stream_ops = { .mmap = tcp_mmap, #endif .splice_eof = inet_splice_eof, - .sendpage = inet_sendpage, .sendmsg_locked = tcp_sendmsg_locked, - .sendpage_locked = tcp_sendpage_locked, .splice_read = tcp_splice_read, .read_sock = tcp_read_sock, .read_skb = tcp_read_skb, @@ -729,7 +727,6 @@ const struct proto_ops inet6_dgram_ops = { .recvmsg = inet6_recvmsg, /* retpoline's sake */ .read_skb = udp_read_skb, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, .set_peek_off = sk_set_peek_off, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index c9caeb5a43ed..ac1cef094c5f 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -1296,7 +1296,6 @@ const struct proto_ops inet6_sockraw_ops = { .sendmsg = inet_sendmsg, /* ok */ .recvmsg = sock_common_recvmsg, /* ok */ .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index c17c8ff94b79..40dd92a2f480 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -2151,7 +2151,6 @@ struct proto tcpv6_prot = { .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, .splice_eof = tcp_splice_eof, - .sendpage = tcp_sendpage, .backlog_rcv = tcp_v6_do_rcv, .release_cb = tcp_release_cb, .hash = inet6_hash, diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index d0537c1c8cd7..393f01b2a7e6 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -963,24 +963,6 @@ static void kcm_splice_eof(struct socket *sock) release_sock(sk); } -static ssize_t kcm_sendpage(struct socket *sock, struct page *page, - int offset, size_t size, int flags) - -{ - struct bio_vec bvec; - struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES, }; - - if (flags & MSG_SENDPAGE_NOTLAST) - msg.msg_flags |= MSG_MORE; - - if (flags & MSG_OOB) - return -EOPNOTSUPP; - - bvec_set_page(&bvec, page, size, offset); - iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); - return kcm_sendmsg(sock, &msg, size); -} - static int kcm_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { @@ -1769,7 +1751,6 @@ static const struct proto_ops kcm_dgram_ops = { .recvmsg = kcm_recvmsg, .mmap = sock_no_mmap, .splice_eof = kcm_splice_eof, - .sendpage = kcm_sendpage, }; static const struct proto_ops kcm_seqpacket_ops = { @@ -1791,7 +1772,6 @@ static const struct proto_ops kcm_seqpacket_ops = { .recvmsg = kcm_recvmsg, .mmap = sock_no_mmap, .splice_eof = kcm_splice_eof, - .sendpage = kcm_sendpage, .splice_read = kcm_splice_read, }; diff --git a/net/key/af_key.c b/net/key/af_key.c index 31ab12fd720a..ede3c6a60353 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -3761,7 +3761,6 @@ static const struct proto_ops pfkey_ops = { .listen = sock_no_listen, .shutdown = sock_no_shutdown, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, /* Now the operations that really occur. */ .release = pfkey_release, diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 2b795c1064f5..f9073bc7281f 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -624,7 +624,6 @@ static const struct proto_ops l2tp_ip_ops = { .sendmsg = inet_sendmsg, .recvmsg = sock_common_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; static struct inet_protosw l2tp_ip_protosw = { diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 5137ea1861ce..b1623f9c4f92 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -751,7 +751,6 @@ static const struct proto_ops l2tp_ip6_ops = { .sendmsg = inet_sendmsg, .recvmsg = sock_common_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 9ffbc667be6c..57c35c960b2c 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -1232,7 +1232,6 @@ static const struct proto_ops llc_ui_ops = { .sendmsg = llc_ui_sendmsg, .recvmsg = llc_ui_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; static const char llc_proc_err_msg[] __initconst = diff --git a/net/mctp/af_mctp.c b/net/mctp/af_mctp.c index bb4bd0b6a4f7..f6be58b68c6f 100644 --- a/net/mctp/af_mctp.c +++ b/net/mctp/af_mctp.c @@ -485,7 +485,6 @@ static const struct proto_ops mctp_dgram_ops = { .sendmsg = mctp_sendmsg, .recvmsg = mctp_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, #ifdef CONFIG_COMPAT .compat_ioctl = mctp_compat_ioctl, #endif diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index bd023debedc8..e892673deb73 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -3866,7 +3866,6 @@ static const struct proto_ops mptcp_stream_ops = { .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, - .sendpage = inet_sendpage, }; static struct inet_protosw mptcp_protosw = { @@ -3961,7 +3960,6 @@ static const struct proto_ops mptcp_v6_stream_ops = { .sendmsg = inet6_sendmsg, .recvmsg = inet6_recvmsg, .mmap = sock_no_mmap, - .sendpage = inet_sendpage, #ifdef CONFIG_COMPAT .compat_ioctl = inet6_compat_ioctl, #endif diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index cbd9aa7ee24a..39cfb778ebc5 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -2815,7 +2815,6 @@ static const struct proto_ops netlink_ops = { .sendmsg = netlink_sendmsg, .recvmsg = netlink_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; static const struct net_proto_family netlink_family_ops = { diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 5a4cb796150f..eb8ccbd58df7 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -1364,7 +1364,6 @@ static const struct proto_ops nr_proto_ops = { .sendmsg = nr_sendmsg, .recvmsg = nr_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; static struct notifier_block nr_dev_notifier = { diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a2dbeb264f26..85ff90a03b0c 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -4621,7 +4621,6 @@ static const struct proto_ops packet_ops_spkt = { .sendmsg = packet_sendmsg_spkt, .recvmsg = packet_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; static const struct proto_ops packet_ops = { @@ -4643,7 +4642,6 @@ static const struct proto_ops packet_ops = { .sendmsg = packet_sendmsg, .recvmsg = packet_recvmsg, .mmap = packet_mmap, - .sendpage = sock_no_sendpage, }; static const struct net_proto_family packet_family_ops = { diff --git a/net/phonet/socket.c b/net/phonet/socket.c index 967f9b4dc026..1018340d89a7 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -441,7 +441,6 @@ const struct proto_ops phonet_dgram_ops = { .sendmsg = pn_socket_sendmsg, .recvmsg = sock_common_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; const struct proto_ops phonet_stream_ops = { @@ -462,7 +461,6 @@ const struct proto_ops phonet_stream_ops = { .sendmsg = pn_socket_sendmsg, .recvmsg = sock_common_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; EXPORT_SYMBOL(phonet_stream_ops); diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c index 76f0434d3d06..78beb74146e7 100644 --- a/net/qrtr/af_qrtr.c +++ b/net/qrtr/af_qrtr.c @@ -1244,7 +1244,6 @@ static const struct proto_ops qrtr_proto_ops = { .shutdown = sock_no_shutdown, .release = qrtr_release, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; static struct proto qrtr_proto = { diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 3ff6995244e5..01c4cdfef45d 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -653,7 +653,6 @@ static const struct proto_ops rds_proto_ops = { .sendmsg = rds_sendmsg, .recvmsg = rds_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; static void rds_sock_destruct(struct sock *sk) diff --git a/net/rose/af_rose.c b/net/rose/af_rose.c index ca2b17f32670..49dafe9ac72f 100644 --- a/net/rose/af_rose.c +++ b/net/rose/af_rose.c @@ -1496,7 +1496,6 @@ static const struct proto_ops rose_proto_ops = { .sendmsg = rose_sendmsg, .recvmsg = rose_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; static struct notifier_block rose_dev_notifier = { diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index da0b3b5157d5..f2cf4aa99db2 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -954,7 +954,6 @@ static const struct proto_ops rxrpc_rpc_ops = { .sendmsg = rxrpc_sendmsg, .recvmsg = rxrpc_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; static struct proto rxrpc_proto = { diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 664d1f2e9121..274d07bd774f 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -1133,7 +1133,6 @@ static const struct proto_ops inet_seqpacket_ops = { .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; /* Registration with AF_INET family. */ diff --git a/net/socket.c b/net/socket.c index b778fc03c6e0..8c3c8b29995a 100644 --- a/net/socket.c +++ b/net/socket.c @@ -3552,54 +3552,6 @@ int kernel_getpeername(struct socket *sock, struct sockaddr *addr) } EXPORT_SYMBOL(kernel_getpeername); -/** - * kernel_sendpage - send a &page through a socket (kernel space) - * @sock: socket - * @page: page - * @offset: page offset - * @size: total size in bytes - * @flags: flags (MSG_DONTWAIT, ...) - * - * Returns the total amount sent in bytes or an error. - */ - -int kernel_sendpage(struct socket *sock, struct page *page, int offset, - size_t size, int flags) -{ - if (sock->ops->sendpage) { - /* Warn in case the improper page to zero-copy send */ - WARN_ONCE(!sendpage_ok(page), "improper page for zero-copy send"); - return sock->ops->sendpage(sock, page, offset, size, flags); - } - return sock_no_sendpage(sock, page, offset, size, flags); -} -EXPORT_SYMBOL(kernel_sendpage); - -/** - * kernel_sendpage_locked - send a &page through the locked sock (kernel space) - * @sk: sock - * @page: page - * @offset: page offset - * @size: total size in bytes - * @flags: flags (MSG_DONTWAIT, ...) - * - * Returns the total amount sent in bytes or an error. - * Caller must hold @sk. - */ - -int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, - size_t size, int flags) -{ - struct socket *sock = sk->sk_socket; - - if (sock->ops->sendpage_locked) - return sock->ops->sendpage_locked(sk, page, offset, size, - flags); - - return sock_no_sendpage_locked(sk, page, offset, size, flags); -} -EXPORT_SYMBOL(kernel_sendpage_locked); - /** * kernel_sock_shutdown - shut down part of a full-duplex connection (kernel space) * @sock: socket diff --git a/net/tipc/socket.c b/net/tipc/socket.c index dd73d71c02a9..ef8e5139a873 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -3375,7 +3375,6 @@ static const struct proto_ops msg_ops = { .sendmsg = tipc_sendmsg, .recvmsg = tipc_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage }; static const struct proto_ops packet_ops = { @@ -3396,7 +3395,6 @@ static const struct proto_ops packet_ops = { .sendmsg = tipc_send_packet, .recvmsg = tipc_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage }; static const struct proto_ops stream_ops = { @@ -3417,7 +3415,6 @@ static const struct proto_ops stream_ops = { .sendmsg = tipc_sendstream, .recvmsg = tipc_recvstream, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage }; static const struct net_proto_family tipc_family_ops = { diff --git a/net/tls/tls.h b/net/tls/tls.h index d002c3af1966..86cef1c68e03 100644 --- a/net/tls/tls.h +++ b/net/tls/tls.h @@ -98,10 +98,6 @@ void tls_sw_strparser_arm(struct sock *sk, struct tls_context *ctx); void tls_sw_strparser_done(struct tls_context *tls_ctx); int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); void tls_sw_splice_eof(struct socket *sock); -int tls_sw_sendpage_locked(struct sock *sk, struct page *page, - int offset, size_t size, int flags); -int tls_sw_sendpage(struct sock *sk, struct page *page, - int offset, size_t size, int flags); void tls_sw_cancel_work_tx(struct tls_context *tls_ctx); void tls_sw_release_resources_tx(struct sock *sk); void tls_sw_free_ctx_tx(struct tls_context *tls_ctx); @@ -117,8 +113,6 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); void tls_device_splice_eof(struct socket *sock); -int tls_device_sendpage(struct sock *sk, struct page *page, - int offset, size_t size, int flags); int tls_tx_records(struct sock *sk, int flags); void tls_sw_write_space(struct sock *sk, struct tls_context *ctx); diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 975299d7213b..840ee06f1708 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -621,23 +621,6 @@ void tls_device_splice_eof(struct socket *sock) mutex_unlock(&tls_ctx->tx_lock); } -int tls_device_sendpage(struct sock *sk, struct page *page, - int offset, size_t size, int flags) -{ - struct bio_vec bvec; - struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES, }; - - if (flags & MSG_SENDPAGE_NOTLAST) - msg.msg_flags |= MSG_MORE; - - if (flags & MSG_OOB) - return -EOPNOTSUPP; - - bvec_set_page(&bvec, page, size, offset); - iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); - return tls_device_sendmsg(sk, &msg, size); -} - struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, u32 seq, u64 *p_record_sn) { diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 7b9c83dd7de2..d5ed4d47b16e 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -958,7 +958,6 @@ static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG] ops[TLS_SW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE]; ops[TLS_SW ][TLS_BASE].splice_eof = tls_sw_splice_eof; - ops[TLS_SW ][TLS_BASE].sendpage_locked = tls_sw_sendpage_locked; ops[TLS_BASE][TLS_SW ] = ops[TLS_BASE][TLS_BASE]; ops[TLS_BASE][TLS_SW ].splice_read = tls_sw_splice_read; @@ -970,17 +969,14 @@ static void build_proto_ops(struct proto_ops ops[TLS_NUM_CONFIG][TLS_NUM_CONFIG] #ifdef CONFIG_TLS_DEVICE ops[TLS_HW ][TLS_BASE] = ops[TLS_BASE][TLS_BASE]; - ops[TLS_HW ][TLS_BASE].sendpage_locked = NULL; ops[TLS_HW ][TLS_SW ] = ops[TLS_BASE][TLS_SW ]; - ops[TLS_HW ][TLS_SW ].sendpage_locked = NULL; ops[TLS_BASE][TLS_HW ] = ops[TLS_BASE][TLS_SW ]; ops[TLS_SW ][TLS_HW ] = ops[TLS_SW ][TLS_SW ]; ops[TLS_HW ][TLS_HW ] = ops[TLS_HW ][TLS_SW ]; - ops[TLS_HW ][TLS_HW ].sendpage_locked = NULL; #endif #ifdef CONFIG_TLS_TOE ops[TLS_HW_RECORD][TLS_HW_RECORD] = *base; @@ -1029,7 +1025,6 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], prot[TLS_SW][TLS_BASE] = prot[TLS_BASE][TLS_BASE]; prot[TLS_SW][TLS_BASE].sendmsg = tls_sw_sendmsg; prot[TLS_SW][TLS_BASE].splice_eof = tls_sw_splice_eof; - prot[TLS_SW][TLS_BASE].sendpage = tls_sw_sendpage; prot[TLS_BASE][TLS_SW] = prot[TLS_BASE][TLS_BASE]; prot[TLS_BASE][TLS_SW].recvmsg = tls_sw_recvmsg; @@ -1045,12 +1040,10 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], prot[TLS_HW][TLS_BASE] = prot[TLS_BASE][TLS_BASE]; prot[TLS_HW][TLS_BASE].sendmsg = tls_device_sendmsg; prot[TLS_HW][TLS_BASE].splice_eof = tls_device_splice_eof; - prot[TLS_HW][TLS_BASE].sendpage = tls_device_sendpage; prot[TLS_HW][TLS_SW] = prot[TLS_BASE][TLS_SW]; prot[TLS_HW][TLS_SW].sendmsg = tls_device_sendmsg; prot[TLS_HW][TLS_SW].splice_eof = tls_device_splice_eof; - prot[TLS_HW][TLS_SW].sendpage = tls_device_sendpage; prot[TLS_BASE][TLS_HW] = prot[TLS_BASE][TLS_SW]; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 319f61590d2c..9b3aa89a4292 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1281,41 +1281,6 @@ unlock: mutex_unlock(&tls_ctx->tx_lock); } -int tls_sw_sendpage_locked(struct sock *sk, struct page *page, - int offset, size_t size, int flags) -{ - struct bio_vec bvec; - struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES, }; - - if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | - MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY | - MSG_NO_SHARED_FRAGS)) - return -EOPNOTSUPP; - if (flags & MSG_SENDPAGE_NOTLAST) - msg.msg_flags |= MSG_MORE; - - bvec_set_page(&bvec, page, size, offset); - iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); - return tls_sw_sendmsg_locked(sk, &msg, size); -} - -int tls_sw_sendpage(struct sock *sk, struct page *page, - int offset, size_t size, int flags) -{ - struct bio_vec bvec; - struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES, }; - - if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | - MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY)) - return -EOPNOTSUPP; - if (flags & MSG_SENDPAGE_NOTLAST) - msg.msg_flags |= MSG_MORE; - - bvec_set_page(&bvec, page, size, offset); - iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); - return tls_sw_sendmsg(sk, &msg, size); -} - static int tls_rx_rec_wait(struct sock *sk, struct sk_psock *psock, bool nonblock, bool released) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index f9d196439b49..f2f234f0b92c 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -758,8 +758,6 @@ static int unix_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned lon static int unix_shutdown(struct socket *, int); static int unix_stream_sendmsg(struct socket *, struct msghdr *, size_t); static int unix_stream_recvmsg(struct socket *, struct msghdr *, size_t, int); -static ssize_t unix_stream_sendpage(struct socket *, struct page *, int offset, - size_t size, int flags); static ssize_t unix_stream_splice_read(struct socket *, loff_t *ppos, struct pipe_inode_info *, size_t size, unsigned int flags); @@ -852,7 +850,6 @@ static const struct proto_ops unix_stream_ops = { .recvmsg = unix_stream_recvmsg, .read_skb = unix_stream_read_skb, .mmap = sock_no_mmap, - .sendpage = unix_stream_sendpage, .splice_read = unix_stream_splice_read, .set_peek_off = unix_set_peek_off, .show_fdinfo = unix_show_fdinfo, @@ -878,7 +875,6 @@ static const struct proto_ops unix_dgram_ops = { .read_skb = unix_read_skb, .recvmsg = unix_dgram_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, .set_peek_off = unix_set_peek_off, .show_fdinfo = unix_show_fdinfo, }; @@ -902,7 +898,6 @@ static const struct proto_ops unix_seqpacket_ops = { .sendmsg = unix_seqpacket_sendmsg, .recvmsg = unix_seqpacket_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, .set_peek_off = unix_set_peek_off, .show_fdinfo = unix_show_fdinfo, }; @@ -2294,20 +2289,6 @@ out_err: return sent ? : err; } -static ssize_t unix_stream_sendpage(struct socket *socket, struct page *page, - int offset, size_t size, int flags) -{ - struct bio_vec bvec; - struct msghdr msg = { .msg_flags = flags | MSG_SPLICE_PAGES }; - - if (flags & MSG_SENDPAGE_NOTLAST) - msg.msg_flags |= MSG_MORE; - - bvec_set_page(&bvec, page, size, offset); - iov_iter_bvec(&msg.msg_iter, ITER_SOURCE, &bvec, 1, size); - return unix_stream_sendmsg(socket, &msg, size); -} - static int unix_seqpacket_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index efb8a0937a13..020cf17ab7e4 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -1306,7 +1306,6 @@ static const struct proto_ops vsock_dgram_ops = { .sendmsg = vsock_dgram_sendmsg, .recvmsg = vsock_dgram_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, .read_skb = vsock_read_skb, }; @@ -2234,7 +2233,6 @@ static const struct proto_ops vsock_stream_ops = { .sendmsg = vsock_connectible_sendmsg, .recvmsg = vsock_connectible_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, .set_rcvlowat = vsock_set_rcvlowat, .read_skb = vsock_read_skb, }; @@ -2257,7 +2255,6 @@ static const struct proto_ops vsock_seqpacket_ops = { .sendmsg = vsock_connectible_sendmsg, .recvmsg = vsock_connectible_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, .read_skb = vsock_read_skb, }; diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 5c7ad301d742..0fb5143bec7a 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -1757,7 +1757,6 @@ static const struct proto_ops x25_proto_ops = { .sendmsg = x25_sendmsg, .recvmsg = x25_recvmsg, .mmap = sock_no_mmap, - .sendpage = sock_no_sendpage, }; static struct packet_type x25_packet_type __read_mostly = { diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index cc1e7f15fa73..5a8c0dd250af 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -1389,7 +1389,6 @@ static const struct proto_ops xsk_proto_ops = { .sendmsg = xsk_sendmsg, .recvmsg = xsk_recvmsg, .mmap = xsk_mmap, - .sendpage = sock_no_sendpage, }; static void xsk_destruct(struct sock *sk) -- cgit v1.2.3