diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2021-06-18 18:55:29 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2021-06-18 18:55:29 -0700 |
commit | 9ed13a17e38e0537e24d9b507645002bf8d0201f (patch) | |
tree | 648bcd0bce8cd2bdcc1b16ec880428a3e1fe031f /net/mptcp/subflow.c | |
parent | 6fab154a33ba9b3574ba74a86ed085e0ed8454cb (diff) | |
parent | 9cca0c2d70149160407bda9a9446ce0c29b6e6c6 (diff) | |
download | linux-9ed13a17e38e0537e24d9b507645002bf8d0201f.tar.bz2 |
Merge tag 'net-5.13-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Networking fixes for 5.13-rc7, including fixes from wireless, bpf,
bluetooth, netfilter and can.
Current release - regressions:
- mlxsw: spectrum_qdisc: Pass handle, not band number to find_class()
to fix modifying offloaded qdiscs
- lantiq: net: fix duplicated skb in rx descriptor ring
- rtnetlink: fix regression in bridge VLAN configuration, empty info
is not an error, bot-generated "fix" was not needed
- libbpf: s/rx/tx/ typo on umem->rx_ring_setup_done to fix umem
creation
Current release - new code bugs:
- ethtool: fix NULL pointer dereference during module EEPROM dump via
the new netlink API
- mlx5e: don't update netdev RQs with PTP-RQ, the special purpose
queue should not be visible to the stack
- mlx5e: select special PTP queue only for SKBTX_HW_TSTAMP skbs
- mlx5e: verify dev is present in get devlink port ndo, avoid a panic
Previous releases - regressions:
- neighbour: allow NUD_NOARP entries to be force GCed
- further fixes for fallout from reorg of WiFi locking (staging:
rtl8723bs, mac80211, cfg80211)
- skbuff: fix incorrect msg_zerocopy copy notifications
- mac80211: fix NULL ptr deref for injected rate info
- Revert "net/mlx5: Arm only EQs with EQEs" it may cause missed IRQs
Previous releases - always broken:
- bpf: more speculative execution fixes
- netfilter: nft_fib_ipv6: skip ipv6 packets from any to link-local
- udp: fix race between close() and udp_abort() resulting in a panic
- fix out of bounds when parsing TCP options before packets are
validated (in netfilter: synproxy, tc: sch_cake and mptcp)
- mptcp: improve operation under memory pressure, add missing
wake-ups
- mptcp: fix double-lock/soft lookup in subflow_error_report()
- bridge: fix races (null pointer deref and UAF) in vlan tunnel
egress
- ena: fix DMA mapping function issues in XDP
- rds: fix memory leak in rds_recvmsg
Misc:
- vrf: allow larger MTUs
- icmp: don't send out ICMP messages with a source address of 0.0.0.0
- cdc_ncm: switch to eth%d interface naming"
* tag 'net-5.13-rc7' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (139 commits)
net: ethernet: fix potential use-after-free in ec_bhf_remove
selftests/net: Add icmp.sh for testing ICMP dummy address responses
icmp: don't send out ICMP messages with a source address of 0.0.0.0
net: ll_temac: Avoid ndo_start_xmit returning NETDEV_TX_BUSY
net: ll_temac: Fix TX BD buffer overwrite
net: ll_temac: Add memory-barriers for TX BD access
net: ll_temac: Make sure to free skb when it is completely used
MAINTAINERS: add Guvenc as SMC maintainer
bnxt_en: Call bnxt_ethtool_free() in bnxt_init_one() error path
bnxt_en: Fix TQM fastpath ring backing store computation
bnxt_en: Rediscover PHY capabilities after firmware reset
cxgb4: fix wrong shift.
mac80211: handle various extensible elements correctly
mac80211: reset profile_periodicity/ema_ap
cfg80211: avoid double free of PMSR request
cfg80211: make certificate generation more robust
mac80211: minstrel_ht: fix sample time check
net: qed: Fix memcpy() overflow of qed_dcbx_params()
net: cdc_eem: fix tx fixup skb leak
net: hamradio: fix memory leak in mkiss_close
...
Diffstat (limited to 'net/mptcp/subflow.c')
-rw-r--r-- | net/mptcp/subflow.c | 108 |
1 files changed, 53 insertions, 55 deletions
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index ef3d037f984a..be1de4084196 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -784,10 +784,10 @@ static u64 expand_seq(u64 old_seq, u16 old_data_len, u64 seq) return seq | ((old_seq + old_data_len + 1) & GENMASK_ULL(63, 32)); } -static void warn_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) +static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) { - WARN_ONCE(1, "Bad mapping: ssn=%d map_seq=%d map_data_len=%d", - ssn, subflow->map_subflow_seq, subflow->map_data_len); + pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d", + ssn, subflow->map_subflow_seq, subflow->map_data_len); } static bool skb_is_fully_mapped(struct sock *ssk, struct sk_buff *skb) @@ -812,13 +812,13 @@ static bool validate_mapping(struct sock *ssk, struct sk_buff *skb) /* Mapping covers data later in the subflow stream, * currently unsupported. */ - warn_bad_map(subflow, ssn); + dbg_bad_map(subflow, ssn); return false; } if (unlikely(!before(ssn, subflow->map_subflow_seq + subflow->map_data_len))) { /* Mapping does covers past subflow data, invalid */ - warn_bad_map(subflow, ssn + skb->len); + dbg_bad_map(subflow, ssn); return false; } return true; @@ -1000,7 +1000,7 @@ static bool subflow_check_data_avail(struct sock *ssk) struct sk_buff *skb; if (!skb_peek(&ssk->sk_receive_queue)) - subflow->data_avail = 0; + WRITE_ONCE(subflow->data_avail, 0); if (subflow->data_avail) return true; @@ -1039,18 +1039,13 @@ static bool subflow_check_data_avail(struct sock *ssk) ack_seq = mptcp_subflow_get_mapped_dsn(subflow); pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack, ack_seq); - if (ack_seq == old_ack) { - subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL; - break; - } else if (after64(ack_seq, old_ack)) { - subflow->data_avail = MPTCP_SUBFLOW_OOO_DATA; - break; + if (unlikely(before64(ack_seq, old_ack))) { + mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq); + continue; } - /* only accept in-sequence mapping. Old values are spurious - * retransmission - */ - mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq); + WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); + break; } return true; @@ -1065,12 +1060,11 @@ fallback: * subflow_error_report() will introduce the appropriate barriers */ ssk->sk_err = EBADMSG; - ssk->sk_error_report(ssk); tcp_set_state(ssk, TCP_CLOSE); subflow->reset_transient = 0; subflow->reset_reason = MPTCP_RST_EMPTCP; tcp_send_active_reset(ssk, GFP_ATOMIC); - subflow->data_avail = 0; + WRITE_ONCE(subflow->data_avail, 0); return false; } @@ -1080,7 +1074,7 @@ fallback: subflow->map_seq = READ_ONCE(msk->ack_seq); subflow->map_data_len = skb->len; subflow->map_subflow_seq = tcp_sk(ssk)->copied_seq - subflow->ssn_offset; - subflow->data_avail = MPTCP_SUBFLOW_DATA_AVAIL; + WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); return true; } @@ -1092,7 +1086,7 @@ bool mptcp_subflow_data_available(struct sock *sk) if (subflow->map_valid && mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len) { subflow->map_valid = 0; - subflow->data_avail = 0; + WRITE_ONCE(subflow->data_avail, 0); pr_debug("Done with mapping: seq=%u data_len=%u", subflow->map_subflow_seq, @@ -1120,41 +1114,6 @@ void mptcp_space(const struct sock *ssk, int *space, int *full_space) *full_space = tcp_full_space(sk); } -static void subflow_data_ready(struct sock *sk) -{ - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - u16 state = 1 << inet_sk_state_load(sk); - struct sock *parent = subflow->conn; - struct mptcp_sock *msk; - - msk = mptcp_sk(parent); - if (state & TCPF_LISTEN) { - /* MPJ subflow are removed from accept queue before reaching here, - * avoid stray wakeups - */ - if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue)) - return; - - set_bit(MPTCP_DATA_READY, &msk->flags); - parent->sk_data_ready(parent); - return; - } - - WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable && - !subflow->mp_join && !(state & TCPF_CLOSE)); - - if (mptcp_subflow_data_available(sk)) - mptcp_data_ready(parent, sk); -} - -static void subflow_write_space(struct sock *ssk) -{ - struct sock *sk = mptcp_subflow_ctx(ssk)->conn; - - mptcp_propagate_sndbuf(sk, ssk); - mptcp_write_space(sk); -} - void __mptcp_error_report(struct sock *sk) { struct mptcp_subflow_context *subflow; @@ -1195,6 +1154,43 @@ static void subflow_error_report(struct sock *ssk) mptcp_data_unlock(sk); } +static void subflow_data_ready(struct sock *sk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); + u16 state = 1 << inet_sk_state_load(sk); + struct sock *parent = subflow->conn; + struct mptcp_sock *msk; + + msk = mptcp_sk(parent); + if (state & TCPF_LISTEN) { + /* MPJ subflow are removed from accept queue before reaching here, + * avoid stray wakeups + */ + if (reqsk_queue_empty(&inet_csk(sk)->icsk_accept_queue)) + return; + + set_bit(MPTCP_DATA_READY, &msk->flags); + parent->sk_data_ready(parent); + return; + } + + WARN_ON_ONCE(!__mptcp_check_fallback(msk) && !subflow->mp_capable && + !subflow->mp_join && !(state & TCPF_CLOSE)); + + if (mptcp_subflow_data_available(sk)) + mptcp_data_ready(parent, sk); + else if (unlikely(sk->sk_err)) + subflow_error_report(sk); +} + +static void subflow_write_space(struct sock *ssk) +{ + struct sock *sk = mptcp_subflow_ctx(ssk)->conn; + + mptcp_propagate_sndbuf(sk, ssk); + mptcp_write_space(sk); +} + static struct inet_connection_sock_af_ops * subflow_default_af_ops(struct sock *sk) { @@ -1505,6 +1501,8 @@ static void subflow_state_change(struct sock *sk) */ if (mptcp_subflow_data_available(sk)) mptcp_data_ready(parent, sk); + else if (unlikely(sk->sk_err)) + subflow_error_report(sk); subflow_sched_work_if_closed(mptcp_sk(parent), sk); |