diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c index 082c46c0f50e..f717750906ff 100644 --- a/net/mptcp/fastopen.c +++ b/net/mptcp/fastopen.c @@ -24,12 +24,13 @@ void mptcp_fastopen_subflow_synack_set_params(struct mptcp_subflow_context *subf sk = subflow->conn; tp = tcp_sk(ssk); - subflow->is_mptfo = 1; - + /* A valid TFO cookie does not guarantee SYN data. */ skb = skb_peek(&ssk->sk_receive_queue); - if (WARN_ON_ONCE(!skb)) + if (!skb) return; + subflow->is_mptfo = 1; + /* dequeue the skb from sk receive queue */ __skb_unlink(skb, &ssk->sk_receive_queue); skb_ext_reset(skb); diff --git a/net/mptcp/options.c b/net/mptcp/options.c index c664023d37ba..1057d500577b 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -50,6 +50,14 @@ static void mptcp_parse_option(const struct sk_buff *skb, } } + /* Only the MPC + ACK can be used with a RM_ADDR */ + if (subopt == OPTION_MPTCP_MPC_ACK) { + if ((mp_opt->suboptions & ~OPTION_MPTCP_RM_ADDR) != 0) + break; + } else if (mp_opt->suboptions != 0) { + break; + } + /* Cfr RFC 8684 Section 3.3.0: * If a checksum is present but its use had * not been negotiated in the MP_CAPABLE handshake, the receiver MUST @@ -122,6 +130,11 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_MP_JOIN: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTION_MPTCP_RM_ADDR | + OPTION_MPTCP_PRIO)) != 0) + break; + if (opsize == TCPOLEN_MPTCP_MPJ_SYN) { mp_opt->suboptions |= OPTION_MPTCP_MPJ_SYN; mp_opt->backup = *ptr++ & MPTCPOPT_BACKUP; @@ -153,6 +166,14 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_DSS: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTION_MPTCP_ADD_ADDR | + OPTION_MPTCP_RM_ADDR | + OPTION_MPTCP_PRIO | + OPTION_MPTCP_FASTCLOSE | + OPTION_MPTCP_FAIL)) != 0) + break; + pr_debug("DSS\n"); ptr++; @@ -188,8 +209,14 @@ static void mptcp_parse_option(const struct sk_buff *skb, * RFC 8684 Section 3.3.0 checks later in subflow_data_ready */ if (opsize != expected_opsize && - opsize != expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) + opsize != expected_opsize + TCPOLEN_MPTCP_DSS_CHECKSUM) { + mp_opt->dsn64 = 0; + mp_opt->use_map = 0; + mp_opt->ack64 = 0; + mp_opt->use_ack = 0; + mp_opt->data_fin = 0; break; + } mp_opt->suboptions |= OPTION_MPTCP_DSS; if (mp_opt->use_ack) { @@ -234,6 +261,12 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_ADD_ADDR: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTIONS_MPTCP_DSS | + OPTION_MPTCP_RM_ADDR | + OPTION_MPTCP_PRIO)) != 0) + break; + mp_opt->echo = (*ptr++) & MPTCP_ADDR_ECHO; if (!mp_opt->echo) { if (opsize == TCPOLEN_MPTCP_ADD_ADDR || @@ -293,6 +326,14 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_RM_ADDR: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTION_MPTCP_MPC_ACK | + OPTIONS_MPTCP_MPJ | + OPTIONS_MPTCP_DSS | + OPTION_MPTCP_ADD_ADDR | + OPTION_MPTCP_PRIO)) != 0) + break; + if (opsize < TCPOLEN_MPTCP_RM_ADDR_BASE + 1 || opsize > TCPOLEN_MPTCP_RM_ADDR_BASE + MPTCP_RM_IDS_MAX) break; @@ -307,6 +348,13 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_MP_PRIO: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTIONS_MPTCP_MPJ | + OPTIONS_MPTCP_DSS | + OPTION_MPTCP_ADD_ADDR | + OPTION_MPTCP_RM_ADDR)) != 0) + break; + if (opsize != TCPOLEN_MPTCP_PRIO) break; @@ -316,6 +364,11 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_MP_FASTCLOSE: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTIONS_MPTCP_DSS | + OPTION_MPTCP_RST)) != 0) + break; + if (opsize != TCPOLEN_MPTCP_FASTCLOSE) break; @@ -327,6 +380,11 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_RST: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTION_MPTCP_FAIL | + OPTION_MPTCP_FASTCLOSE)) != 0) + break; + if (opsize != TCPOLEN_MPTCP_RST) break; @@ -342,6 +400,11 @@ static void mptcp_parse_option(const struct sk_buff *skb, break; case MPTCPOPT_MP_FAIL: + /* Can be used with a restricted number of other options */ + if ((mp_opt->suboptions & ~(OPTIONS_MPTCP_DSS | + OPTION_MPTCP_RST)) != 0) + break; + if (opsize != TCPOLEN_MPTCP_FAIL) break; @@ -1400,7 +1463,7 @@ void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp, * RM | C | C | C | P |------|------|------|------| * PRIO | X | C | C | C | C |------|------|------| * FAIL | X | X | C | X | X | X |------|------| - * FC | X | X | X | X | X | X | X |------| + * FC | X | X | P | X | X | X | X |------| * RST | X | X | X | X | X | X | O | O | * ------|------|------|------|------|------|------|------|------| * diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 6afd39aea110..64a1236aabee 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -380,6 +380,7 @@ static void mptcp_pm_add_addr_timer(struct timer_list *timer) struct mptcp_sock *msk = entry->sock; struct sock *sk = (struct sock *)msk; unsigned int timeout = 0; + bool retransmit; pr_debug("msk=%p\n", msk); @@ -412,14 +413,15 @@ static void mptcp_pm_add_addr_timer(struct timer_list *timer) entry->retrans_times++; } - if (entry->retrans_times < ADD_ADDR_RETRANS_MAX) + retransmit = entry->retrans_times < ADD_ADDR_RETRANS_MAX; + if (retransmit) timeout <<= entry->retrans_times; else timeout = 0; spin_unlock_bh(&msk->pm.lock); - if (entry->retrans_times == ADD_ADDR_RETRANS_MAX) + if (!retransmit) mptcp_pm_subflow_established(msk); out: @@ -441,6 +443,9 @@ bool mptcp_pm_announced_alloc(struct mptcp_sock *msk, lockdep_assert_held(&msk->pm.lock); + if (msk->pm.status & BIT(MPTCP_PM_DESTROYING)) + return false; + add_entry = mptcp_pm_announced_lookup(msk, addr); if (add_entry) { if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk))) @@ -1143,10 +1148,16 @@ void mptcp_pm_worker(struct mptcp_sock *msk) void mptcp_pm_destroy(struct mptcp_sock *msk) { + spin_lock_bh(&msk->pm.lock); + msk->pm.status |= BIT(MPTCP_PM_DESTROYING); + spin_unlock_bh(&msk->pm.lock); + mptcp_pm_free_announced_list(msk); - if (mptcp_pm_is_userspace(msk)) - mptcp_userspace_pm_free_local_addr_list(msk); + /* Free the userspace local address list unconditionally: the socket + * can be reused (mptcp_disconnect()) and re-selected to a different PM + */ + mptcp_userspace_pm_free_local_addr_list(msk); } void mptcp_pm_data_reset(struct mptcp_sock *msk) diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index 945aa5afc2dd..2203cc2d2748 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -54,6 +54,10 @@ static int mptcp_userspace_pm_append_new_local_addr(struct mptcp_sock *msk, bitmap_zero(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); spin_lock_bh(&msk->pm.lock); + if (msk->pm.status & BIT(MPTCP_PM_DESTROYING)) { + ret = -EINVAL; + goto append_err; + } mptcp_for_each_userspace_pm_addr(msk, e) { addr_match = mptcp_addresses_equal(&e->addr, &entry->addr, true); if (addr_match && entry->addr.id == 0 && needs_id) diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index ca644ec53eed..7c8180d8d5ef 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -149,6 +149,12 @@ struct sock *__mptcp_nmpc_sk(struct mptcp_sock *msk) static void mptcp_drop(struct sock *sk, struct sk_buff *skb) { + /* The skb forward memory was already transferred to sk by + * mptcp_borrow_fwdmem(), even before setting the destructor. + */ + if (!skb->destructor) + sk_mem_reclaim(sk); + sk_drops_skbadd(sk, skb); __kfree_skb(skb); } diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 4a2d40cd7b13..1b80f2d6ec5a 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -37,6 +37,7 @@ OPTION_MPTCP_MPC_ACK) #define OPTIONS_MPTCP_MPJ (OPTION_MPTCP_MPJ_SYN | OPTION_MPTCP_MPJ_SYNACK | \ OPTION_MPTCP_MPJ_ACK) +#define OPTIONS_MPTCP_DSS (OPTION_MPTCP_DSS | OPTION_MPTCP_CSUMREQD) /* MPTCP option subtypes */ #define MPTCPOPT_MP_CAPABLE 0 @@ -189,9 +190,10 @@ enum mptcp_pm_status { MPTCP_PM_ESTABLISHED, MPTCP_PM_SUBFLOW_ESTABLISHED, MPTCP_PM_ALREADY_ESTABLISHED, /* persistent status, set after ESTABLISHED event */ - MPTCP_PM_MPC_ENDPOINT_ACCOUNTED /* persistent status, set after MPC local address is - * accounted int id_avail_bitmap - */ + MPTCP_PM_MPC_ENDPOINT_ACCOUNTED, /* persistent status, set after MPC local address is + * accounted int id_avail_bitmap + */ + MPTCP_PM_DESTROYING, /* To fence out PM list allocs */ }; enum mptcp_pm_type { diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 8e386899ceb9..e1f20ff8fdb4 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -174,8 +174,6 @@ static int subflow_check_req(struct request_sock *req, if (unlikely(listener->pm_listener)) return subflow_reset_req_endp(req, skb); - if (opt_mp_join) - return 0; } else if (opt_mp_join) { SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX); @@ -277,9 +275,6 @@ int mptcp_subflow_init_cookie_req(struct request_sock *req, opt_mp_capable = !!(mp_opt.suboptions & OPTION_MPTCP_MPC_ACK); opt_mp_join = !!(mp_opt.suboptions & OPTION_MPTCP_MPJ_ACK); - if (opt_mp_capable && opt_mp_join) - return -EINVAL; - if (opt_mp_capable && listener->request_mptcp) { if (mp_opt.sndr_key == 0) return -EINVAL; diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh index c0aeffd5cb71..7dc91fac4917 100755 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@ -584,7 +584,7 @@ check_transfer() mv "$tmpfile" "$out" tmpfile="" fi - cmp -l "$in" "$out" | while read -r i a b; do + while read -r i a b; do local sum=$((0${a} + 0${b})) if [ $check_invert -eq 0 ] || [ $sum -ne $((0xff)) ]; then fail_test "$what does not match (in, out):" @@ -595,7 +595,7 @@ check_transfer() else print_info "$what has inverted byte at ${i}" fi - done + done < <(cmp -l "$in" "$out") return 0 }