From: Jakub Kicinski Date: Thu, 19 May 2022 18:23:59 +0000 (-0700) Subject: Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net X-Git-Url: http://git.maquefel.me/?a=commitdiff_plain;h=d7e6f5836038eeac561411ed7a74e2a225a6c138;p=linux.git Merge git://git./linux/kernel/git/netdev/net drivers/net/ethernet/mellanox/mlx5/core/main.c b33886971dbc ("net/mlx5: Initialize flow steering during driver probe") 40379a0084c2 ("net/mlx5_fpga: Drop INNOVA TLS support") f2b41b32cde8 ("net/mlx5: Remove ipsec_ops function table") https://lore.kernel.org/all/20220519040345.6yrjromcdistu7vh@sx1/ 16d42d313350 ("net/mlx5: Drain fw_reset when removing device") 8324a02c342a ("net/mlx5: Add exit route when waiting for FW") https://lore.kernel.org/all/20220519114119.060ce014@canb.auug.org.au/ tools/testing/selftests/net/mptcp/mptcp_join.sh e274f7154008 ("selftests: mptcp: add subflow limits test-cases") b6e074e171bc ("selftests: mptcp: add infinite map testcase") 5ac1d2d63451 ("selftests: mptcp: Add tests for userspace PM type") https://lore.kernel.org/all/20220516111918.366d747f@canb.auug.org.au/ net/mptcp/options.c ba2c89e0ea74 ("mptcp: fix checksum byte order") 1e39e5a32ad7 ("mptcp: infinite mapping sending") ea66758c1795 ("tcp: allow MPTCP to update the announced window") https://lore.kernel.org/all/20220519115146.751c3a37@canb.auug.org.au/ net/mptcp/pm.c 95d686517884 ("mptcp: fix subflow accounting on close") 4d25247d3ae4 ("mptcp: bypass in-kernel PM restrictions for non-kernel PMs") https://lore.kernel.org/all/20220516111435.72f35dca@canb.auug.org.au/ net/mptcp/subflow.c ae66fb2ba6c3 ("mptcp: Do TCP fallback on early DSS checksum failure") 0348c690ed37 ("mptcp: add the fallback check") f8d4bcacff3b ("mptcp: infinite mapping receiving") https://lore.kernel.org/all/20220519115837.380bb8d4@canb.auug.org.au/ Signed-off-by: Jakub Kicinski --- d7e6f5836038eeac561411ed7a74e2a225a6c138 diff --cc drivers/net/ethernet/mellanox/mlx5/core/main.c index 87f1552b5d737,ef196cb764e2a..fbd4dd76a19f3 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@@ -1181,7 -1192,15 +1190,7 @@@ static int mlx5_load(struct mlx5_core_d goto err_fpga_start; } - err = mlx5_init_fs(dev); - mlx5_accel_ipsec_init(dev); - - err = mlx5_accel_tls_init(dev); - if (err) { - mlx5_core_err(dev, "TLS device start failed %d\n", err); - goto err_tls_start; - } - + err = mlx5_fs_core_init(dev); if (err) { mlx5_core_err(dev, "Failed to init flow steering\n"); goto err_fs; @@@ -1226,8 -1245,11 +1235,8 @@@ err_ec err_vhca: mlx5_vhca_event_stop(dev); err_set_hca: - mlx5_cleanup_fs(dev); + mlx5_fs_core_cleanup(dev); err_fs: - mlx5_accel_tls_cleanup(dev); -err_tls_start: - mlx5_accel_ipsec_cleanup(dev); mlx5_fpga_device_stop(dev); err_fpga_start: mlx5_rsc_dump_cleanup(dev); @@@ -1252,7 -1274,9 +1261,7 @@@ static void mlx5_unload(struct mlx5_cor mlx5_ec_cleanup(dev); mlx5_sf_hw_table_destroy(dev); mlx5_vhca_event_stop(dev); - mlx5_cleanup_fs(dev); + mlx5_fs_core_cleanup(dev); - mlx5_accel_ipsec_cleanup(dev); - mlx5_accel_tls_cleanup(dev); mlx5_fpga_device_stop(dev); mlx5_rsc_dump_cleanup(dev); mlx5_hv_vhca_cleanup(dev->hv_vhca); @@@ -1608,7 -1627,10 +1617,11 @@@ static void remove_one(struct pci_dev * struct mlx5_core_dev *dev = pci_get_drvdata(pdev); struct devlink *devlink = priv_to_devlink(dev); + /* mlx5_drain_fw_reset() is using devlink APIs. Hence, we must drain + * fw_reset before unregistering the devlink. + */ + mlx5_drain_fw_reset(dev); + set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state); devlink_unregister(devlink); mlx5_sriov_disable(pdev); mlx5_crdump_disable(dev); diff --cc net/mptcp/options.c index ac3b7b8a02f6e,b548cec86c9d8..be3b918a6d15e --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@@ -1236,53 -1234,13 +1236,53 @@@ static void mptcp_set_rwin(struct tcp_s subflow = mptcp_subflow_ctx(ssk); msk = mptcp_sk(subflow->conn); - ack_seq = READ_ONCE(msk->ack_seq) + tp->rcv_wnd; + ack_seq = READ_ONCE(msk->ack_seq); + rcv_wnd_new = ack_seq + tp->rcv_wnd; + + rcv_wnd_old = atomic64_read(&msk->rcv_wnd_sent); + if (after64(rcv_wnd_new, rcv_wnd_old)) { + u64 rcv_wnd; + + for (;;) { + rcv_wnd = atomic64_cmpxchg(&msk->rcv_wnd_sent, rcv_wnd_old, rcv_wnd_new); + + if (rcv_wnd == rcv_wnd_old) + break; + if (before64(rcv_wnd_new, rcv_wnd)) { + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICTUPDATE); + goto raise_win; + } + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDCONFLICT); + rcv_wnd_old = rcv_wnd; + } + return; + } + + if (rcv_wnd_new != rcv_wnd_old) { +raise_win: + win = rcv_wnd_old - ack_seq; + tp->rcv_wnd = min_t(u64, win, U32_MAX); + new_win = tp->rcv_wnd; - if (after64(ack_seq, READ_ONCE(msk->rcv_wnd_sent))) - WRITE_ONCE(msk->rcv_wnd_sent, ack_seq); + /* Make sure we do not exceed the maximum possible + * scaled window. + */ + if (unlikely(th->syn)) + new_win = min(new_win, 65535U) << tp->rx_opt.rcv_wscale; + if (!tp->rx_opt.rcv_wscale && + sock_net(ssk)->ipv4.sysctl_tcp_workaround_signed_windows) + new_win = min(new_win, MAX_TCP_WINDOW); + else + new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale)); + + /* RFC1323 scaling applied */ + new_win >>= tp->rx_opt.rcv_wscale; + th->window = htons(new_win); + MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_RCVWNDSHARED); + } } - u16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) + __sum16 __mptcp_make_csum(u64 data_seq, u32 subflow_seq, u16 data_len, __wsum sum) { struct csum_pseudo_header header; __wsum csum; @@@ -1307,7 -1265,17 +1307,17 @@@ static __sum16 mptcp_make_csum(const st ~csum_unfold(mpext->csum)); } + static void put_len_csum(u16 len, __sum16 csum, void *data) + { + __sum16 *sumptr = data + 2; + __be16 *ptr = data; + + put_unaligned_be16(len, ptr); + + put_unaligned(csum, sumptr); + } + -void mptcp_write_options(__be32 *ptr, const struct tcp_sock *tp, +void mptcp_write_options(struct tcphdr *th, __be32 *ptr, struct tcp_sock *tp, struct mptcp_out_options *opts) { const struct sock *ssk = (const struct sock *)tp; @@@ -1382,12 -1350,9 +1392,12 @@@ put_unaligned_be32(mpext->subflow_seq, ptr); ptr += 1; if (opts->csum_reqd) { + /* data_len == 0 is reserved for the infinite mapping, + * the checksum will also be set to 0. + */ - put_unaligned_be32(mpext->data_len << 16 | - (mpext->data_len ? mptcp_make_csum(mpext) : 0), - ptr); + put_len_csum(mpext->data_len, - mptcp_make_csum(mpext), ++ (mpext->data_len ? mptcp_make_csum(mpext) : 0), + ptr); } else { put_unaligned_be32(mpext->data_len << 16 | TCPOPT_NOP << 8 | TCPOPT_NOP, ptr); diff --cc net/mptcp/pm.c index cdc2d79071f8a,aa51b100e0335..59fdab2d0c271 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@@ -181,9 -178,7 +181,8 @@@ void mptcp_pm_subflow_check_next(struc struct mptcp_pm_data *pm = &msk->pm; bool update_subflows; - update_subflows = (ssk->sk_state == TCP_CLOSE) && - (subflow->request_join || subflow->mp_join) && - update_subflows = subflow->request_join || subflow->mp_join; ++ update_subflows = (subflow->request_join || subflow->mp_join) && + mptcp_pm_is_kernel(msk); if (!READ_ONCE(pm->work_pending) && !update_subflows) return; diff --cc net/mptcp/protocol.h index 4672901d0dfed,5655a63aa6a8b..08b8015cb69fb --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@@ -466,9 -443,9 +466,10 @@@ struct mptcp_subflow_context can_ack : 1, /* only after processing the remote a key */ disposable : 1, /* ctx can be free at ulp release time */ stale : 1, /* unable to snd/rcv data, do not use for xmit */ - local_id_valid : 1; /* local_id is correctly initialized */ + local_id_valid : 1, /* local_id is correctly initialized */ + valid_csum_seen : 1; /* at least one csum validated */ enum mptcp_data_avail data_avail; + bool mp_fail_response_expect; u32 remote_nonce; u64 thmac; u32 local_nonce; diff --cc net/mptcp/subflow.c index 6d59336a8e1e5,be76ada89d969..aecd98ac5dfe9 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@@ -1215,45 -1218,35 +1230,45 @@@ no_data return false; fallback: - /* RFC 8684 section 3.7. */ - if (subflow->send_mp_fail) { - if (mptcp_has_another_subflow(ssk)) { - while ((skb = skb_peek(&ssk->sk_receive_queue))) - sk_eat_skb(ssk, skb); + if (!__mptcp_check_fallback(msk)) { + /* RFC 8684 section 3.7. */ + if (subflow->send_mp_fail) { + if (mptcp_has_another_subflow(ssk) || + !READ_ONCE(msk->allow_infinite_fallback)) { + ssk->sk_err = EBADMSG; + tcp_set_state(ssk, TCP_CLOSE); + subflow->reset_transient = 0; + subflow->reset_reason = MPTCP_RST_EMIDDLEBOX; + tcp_send_active_reset(ssk, GFP_ATOMIC); + while ((skb = skb_peek(&ssk->sk_receive_queue))) + sk_eat_skb(ssk, skb); + } else { + WRITE_ONCE(subflow->mp_fail_response_expect, true); + /* The data lock is acquired in __mptcp_move_skbs() */ + sk_reset_timer((struct sock *)msk, + &((struct sock *)msk)->sk_timer, + jiffies + TCP_RTO_MAX); + } + WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA); + return true; } - ssk->sk_err = EBADMSG; - tcp_set_state(ssk, TCP_CLOSE); - subflow->reset_transient = 0; - subflow->reset_reason = MPTCP_RST_EMIDDLEBOX; - tcp_send_active_reset(ssk, GFP_ATOMIC); - WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA); - return true; - } - if ((subflow->mp_join || subflow->fully_established) && subflow->map_data_len) { - if (!subflow_can_fallback(subflow)) { - /* fatal protocol error, close the socket. - * subflow_error_report() will introduce the appropriate barriers - */ - ssk->sk_err = EBADMSG; - tcp_set_state(ssk, TCP_CLOSE); - subflow->reset_transient = 0; - subflow->reset_reason = MPTCP_RST_EMPTCP; - tcp_send_active_reset(ssk, GFP_ATOMIC); - WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA); - return false; ++ if (!subflow_can_fallback(subflow) && subflow->map_data_len) { + /* fatal protocol error, close the socket. + * subflow_error_report() will introduce the appropriate barriers + */ + ssk->sk_err = EBADMSG; + tcp_set_state(ssk, TCP_CLOSE); + subflow->reset_transient = 0; + subflow->reset_reason = MPTCP_RST_EMPTCP; + tcp_send_active_reset(ssk, GFP_ATOMIC); + WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA); + return false; + } + + __mptcp_do_fallback(msk); } - __mptcp_do_fallback(msk); skb = skb_peek(&ssk->sk_receive_queue); subflow->map_valid = 1; subflow->map_seq = READ_ONCE(msk->ack_seq); diff --cc tools/testing/selftests/net/mptcp/mptcp_join.sh index 7381d1f852099,48ef112f42c2e..1a5f211c59023 --- a/tools/testing/selftests/net/mptcp/mptcp_join.sh +++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh @@@ -2690,92 -2583,7 +2717,92 @@@ fastclose_tests( fi } +pedit_action_pkts() +{ + tc -n $ns2 -j -s action show action pedit index 100 | \ + grep "packets" | \ + sed 's/.*"packets":\([0-9]\+\),.*/\1/' +} + +fail_tests() +{ + # single subflow + if reset_with_fail "Infinite map" 1; then + run_tests $ns1 $ns2 10.0.1.1 128 + chk_join_nr 0 0 0 +1 +0 1 0 1 "$(pedit_action_pkts)" + chk_fail_nr 1 -1 invert + fi +} + +userspace_tests() +{ + # userspace pm type prevents add_addr + if reset "userspace pm type prevents add_addr"; then + set_userspace_pm $ns1 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + chk_add_nr 0 0 + fi + + # userspace pm type does not echo add_addr without daemon + if reset "userspace pm no echo w/o daemon"; then + set_userspace_pm $ns2 + pm_nl_set_limits $ns1 0 2 + pm_nl_set_limits $ns2 0 2 + pm_nl_add_endpoint $ns1 10.0.2.1 flags signal + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + chk_add_nr 1 0 + fi + + # userspace pm type rejects join + if reset "userspace pm type rejects join"; then + set_userspace_pm $ns1 + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 1 1 0 + fi + + # userspace pm type does not send join + if reset "userspace pm type does not send join"; then + set_userspace_pm $ns2 + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 + chk_join_nr 0 0 0 + fi + + # userspace pm type prevents mp_prio + if reset "userspace pm type prevents mp_prio"; then + set_userspace_pm $ns1 + pm_nl_set_limits $ns1 1 1 + pm_nl_set_limits $ns2 1 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 0 slow backup + chk_join_nr 1 1 0 + chk_prio_nr 0 0 + fi + + # userspace pm type prevents rm_addr + if reset "userspace pm type prevents rm_addr"; then + set_userspace_pm $ns1 + set_userspace_pm $ns2 + pm_nl_set_limits $ns1 0 1 + pm_nl_set_limits $ns2 0 1 + pm_nl_add_endpoint $ns2 10.0.3.2 flags subflow + run_tests $ns1 $ns2 10.0.1.1 0 0 -1 slow + chk_join_nr 0 0 0 + chk_rm_nr 0 0 + fi +} + - implicit_tests() + endpoint_tests() { # userspace pm type prevents add_addr if reset "implicit EP"; then @@@ -2843,9 -2668,7 +2887,9 @@@ all_tests_sorted= d@deny_join_id0_tests m@fullmesh_tests z@fastclose_tests + F@fail_tests + u@userspace_tests - I@implicit_tests + I@endpoint_tests ) all_tests_args=""