diff options
author | Linus Torvalds <torvalds@linux-foundation.org> | 2023-03-17 13:31:16 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2023-03-17 13:31:16 -0700 |
commit | 478a351ce0d69cef2d2bf2a686a09b356b63a66c (patch) | |
tree | 42a6b550a0ae321799fc81f68e6548c532283ccc /net/mptcp/subflow.c | |
parent | 8d3c682a5e3d9dfc2448ecbb22f4cd48359b9e21 (diff) | |
parent | f5e305e63b035a1782a666a6535765f80bb2dca3 (diff) |
Merge tag 'net-6.3-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net
Pull networking fixes from Jakub Kicinski:
"Including fixes from netfilter, wifi and ipsec.
A little more changes than usual, but it's pretty normal for us that
the rc3/rc4 PRs are oversized as people start testing in earnest.
Possibly an extra boost from people deploying the 6.1 LTS but that's
more of an unscientific hunch.
Current release - regressions:
- phy: mscc: fix deadlock in phy_ethtool_{get,set}_wol()
- virtio: vsock: don't use skbuff state to account credit
- virtio: vsock: don't drop skbuff on copy failure
- virtio_net: fix page_to_skb() miscalculating the memory size
Current release - new code bugs:
- eth: correct xdp_features after device reconfig
- wifi: nl80211: fix the puncturing bitmap policy
- net/mlx5e: flower:
- fix raw counter initialization
- fix missing error code
- fix cloned flow attribute
- ipa:
- fix some register validity checks
- fix a surprising number of bad offsets
- kill FILT_ROUT_CACHE_CFG IPA register
Previous releases - regressions:
- tcp: fix bind() conflict check for dual-stack wildcard address
- veth: fix use after free in XDP_REDIRECT when skb headroom is small
- ipv4: fix incorrect table ID in IOCTL path
- ipvlan: make skb->skb_iif track skb->dev for l3s mode
- mptcp:
- fix possible deadlock in subflow_error_report
- fix UaFs when destroying unaccepted and listening sockets
- dsa: mv88e6xxx: fix max_mtu of 1492 on 6165, 6191, 6220, 6250, 6290
Previous releases - always broken:
- tcp: tcp_make_synack() can be called from process context, don't
assume preemption is disabled when updating stats
- netfilter: correct length for loading protocol registers
- virtio_net: add checking sq is full inside xdp xmit
- bonding: restore IFF_MASTER/SLAVE flags on bond enslave Ethertype
change
- phy: nxp-c45-tja11xx: fix MII_BASIC_CONFIG_REV bit number
- eth: i40e: fix crash during reboot when adapter is in recovery mode
- eth: ice: avoid deadlock on rtnl lock when auxiliary device
plug/unplug meets bonding
- dsa: mt7530:
- remove now incorrect comment regarding port 5
- set PLL frequency and trgmii only when trgmii is used
- eth: mtk_eth_soc: reset PCS state when changing interface types
Misc:
- ynl: another license adjustment
- move the TCA_EXT_WARN_MSG attribute for tc action"
* tag 'net-6.3-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (108 commits)
selftests: bonding: add tests for ether type changes
bonding: restore bond's IFF_SLAVE flag if a non-eth dev enslave fails
bonding: restore IFF_MASTER/SLAVE flags on bond enslave ether type change
net: renesas: rswitch: Fix GWTSDIE register handling
net: renesas: rswitch: Fix the output value of quote from rswitch_rx()
ethernet: sun: add check for the mdesc_grab()
net: ipa: fix some register validity checks
net: ipa: kill FILT_ROUT_CACHE_CFG IPA register
net: ipa: add two missing declarations
net: ipa: reg: include <linux/bug.h>
net: xdp: don't call notifiers during driver init
net/sched: act_api: add specific EXT_WARN_MSG for tc action
Revert "net/sched: act_api: move TCA_EXT_WARN_MSG to the correct hierarchy"
net: dsa: microchip: fix RGMII delay configuration on KSZ8765/KSZ8794/KSZ8795
ynl: make the tooling check the license
ynl: broaden the license even more
tools: ynl: make definitions optional again
hsr: ratelimit only when errors are printed
qed/qed_mng_tlv: correctly zero out ->min instead of ->hour
selftests: net: devlink_port_split.py: skip test if no suitable device available
...
Diffstat (limited to 'net/mptcp/subflow.c')
-rw-r--r-- | net/mptcp/subflow.c | 128 |
1 files changed, 42 insertions, 86 deletions
diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 4ae1a7304cf0..a0041360ee9d 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -397,10 +397,15 @@ void mptcp_subflow_reset(struct sock *ssk) struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); struct sock *sk = subflow->conn; + /* mptcp_mp_fail_no_response() can reach here on an already closed + * socket + */ + if (ssk->sk_state == TCP_CLOSE) + return; + /* must hold: tcp_done() could drop last reference on parent */ sock_hold(sk); - tcp_set_state(ssk, TCP_CLOSE); tcp_send_active_reset(ssk, GFP_ATOMIC); tcp_done(ssk); if (!test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &mptcp_sk(sk)->flags) && @@ -622,7 +627,7 @@ static struct request_sock_ops mptcp_subflow_v6_request_sock_ops __ro_after_init static struct tcp_request_sock_ops subflow_request_sock_ipv6_ops __ro_after_init; static struct inet_connection_sock_af_ops subflow_v6_specific __ro_after_init; static struct inet_connection_sock_af_ops subflow_v6m_specific __ro_after_init; -static struct proto tcpv6_prot_override; +static struct proto tcpv6_prot_override __ro_after_init; static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb) { @@ -693,9 +698,10 @@ static bool subflow_hmac_valid(const struct request_sock *req, static void mptcp_force_close(struct sock *sk) { - /* the msk is not yet exposed to user-space */ + /* the msk is not yet exposed to user-space, and refcount is 2 */ inet_sk_state_store(sk, TCP_CLOSE); sk_common_release(sk); + sock_put(sk); } static void subflow_ulp_fallback(struct sock *sk, @@ -711,7 +717,7 @@ static void subflow_ulp_fallback(struct sock *sk, mptcp_subflow_ops_undo_override(sk); } -static void subflow_drop_ctx(struct sock *ssk) +void mptcp_subflow_drop_ctx(struct sock *ssk) { struct mptcp_subflow_context *ctx = mptcp_subflow_ctx(ssk); @@ -750,6 +756,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk, struct mptcp_options_received mp_opt; bool fallback, fallback_is_fatal; struct sock *new_msk = NULL; + struct mptcp_sock *owner; struct sock *child; pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn); @@ -816,7 +823,7 @@ create_child: if (new_msk) mptcp_copy_inaddrs(new_msk, child); - subflow_drop_ctx(child); + mptcp_subflow_drop_ctx(child); goto out; } @@ -824,6 +831,8 @@ create_child: ctx->setsockopt_seq = listener->setsockopt_seq; if (ctx->mp_capable) { + owner = mptcp_sk(new_msk); + /* this can't race with mptcp_close(), as the msk is * not yet exposted to user-space */ @@ -832,14 +841,14 @@ create_child: /* record the newly created socket as the first msk * subflow, but don't link it yet into conn_list */ - WRITE_ONCE(mptcp_sk(new_msk)->first, child); + WRITE_ONCE(owner->first, child); /* new mpc subflow takes ownership of the newly * created mptcp socket */ mptcp_sk(new_msk)->setsockopt_seq = ctx->setsockopt_seq; - mptcp_pm_new_connection(mptcp_sk(new_msk), child, 1); - mptcp_token_accept(subflow_req, mptcp_sk(new_msk)); + mptcp_pm_new_connection(owner, child, 1); + mptcp_token_accept(subflow_req, owner); ctx->conn = new_msk; new_msk = NULL; @@ -847,15 +856,21 @@ create_child: * uses the correct data */ mptcp_copy_inaddrs(ctx->conn, child); + mptcp_propagate_sndbuf(ctx->conn, child); + + mptcp_rcv_space_init(owner, child); + list_add(&ctx->node, &owner->conn_list); + sock_hold(child); /* with OoO packets we can reach here without ingress * mpc option */ - if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) + if (mp_opt.suboptions & OPTION_MPTCP_MPC_ACK) { mptcp_subflow_fully_established(ctx, &mp_opt); + mptcp_pm_fully_established(owner, child, GFP_ATOMIC); + ctx->pm_notified = 1; + } } else if (ctx->mp_join) { - struct mptcp_sock *owner; - owner = subflow_req->msk; if (!owner) { subflow_add_reset_reason(skb, MPTCP_RST_EPROHIBIT); @@ -899,7 +914,7 @@ out: return child; dispose_child: - subflow_drop_ctx(child); + mptcp_subflow_drop_ctx(child); tcp_rsk(req)->drop_req = true; inet_csk_prepare_for_destroy_sock(child); tcp_done(child); @@ -910,7 +925,7 @@ dispose_child: } static struct inet_connection_sock_af_ops subflow_specific __ro_after_init; -static struct proto tcp_prot_override; +static struct proto tcp_prot_override __ro_after_init; enum mapping_status { MAPPING_OK, @@ -1432,6 +1447,13 @@ static void subflow_error_report(struct sock *ssk) { struct sock *sk = mptcp_subflow_ctx(ssk)->conn; + /* bail early if this is a no-op, so that we avoid introducing a + * problematic lockdep dependency between TCP accept queue lock + * and msk socket spinlock + */ + if (!sk->sk_socket) + return; + mptcp_data_lock(sk); if (!sock_owned_by_user(sk)) __mptcp_error_report(sk); @@ -1803,79 +1825,6 @@ static void subflow_state_change(struct sock *sk) } } -void mptcp_subflow_queue_clean(struct sock *listener_sk, struct sock *listener_ssk) -{ - struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue; - struct mptcp_sock *msk, *next, *head = NULL; - struct request_sock *req; - - /* build a list of all unaccepted mptcp sockets */ - spin_lock_bh(&queue->rskq_lock); - for (req = queue->rskq_accept_head; req; req = req->dl_next) { - struct mptcp_subflow_context *subflow; - struct sock *ssk = req->sk; - struct mptcp_sock *msk; - - if (!sk_is_mptcp(ssk)) - continue; - - subflow = mptcp_subflow_ctx(ssk); - if (!subflow || !subflow->conn) - continue; - - /* skip if already in list */ - msk = mptcp_sk(subflow->conn); - if (msk->dl_next || msk == head) - continue; - - msk->dl_next = head; - head = msk; - } - spin_unlock_bh(&queue->rskq_lock); - if (!head) - return; - - /* can't acquire the msk socket lock under the subflow one, - * or will cause ABBA deadlock - */ - release_sock(listener_ssk); - - for (msk = head; msk; msk = next) { - struct sock *sk = (struct sock *)msk; - bool do_cancel_work; - - sock_hold(sk); - lock_sock_nested(sk, SINGLE_DEPTH_NESTING); - next = msk->dl_next; - msk->first = NULL; - msk->dl_next = NULL; - - do_cancel_work = __mptcp_close(sk, 0); - release_sock(sk); - if (do_cancel_work) { - /* lockdep will report a false positive ABBA deadlock - * between cancel_work_sync and the listener socket. - * The involved locks belong to different sockets WRT - * the existing AB chain. - * Using a per socket key is problematic as key - * deregistration requires process context and must be - * performed at socket disposal time, in atomic - * context. - * Just tell lockdep to consider the listener socket - * released here. - */ - mutex_release(&listener_sk->sk_lock.dep_map, _RET_IP_); - mptcp_cancel_work(sk); - mutex_acquire(&listener_sk->sk_lock.dep_map, - SINGLE_DEPTH_NESTING, 0, _RET_IP_); - } - sock_put(sk); - } - - /* we are still under the listener msk socket lock */ - lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING); -} - static int subflow_ulp_init(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -1932,6 +1881,13 @@ static void subflow_ulp_release(struct sock *ssk) * when the subflow is still unaccepted */ release = ctx->disposable || list_empty(&ctx->node); + + /* inet_child_forget() does not call sk_state_change(), + * explicitly trigger the socket close machinery + */ + if (!release && !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, + &mptcp_sk(sk)->flags)) + mptcp_schedule_work(sk); sock_put(sk); } |